Close Round 05.1 selector calibration

AGENTS.md

@@ -79,6 +79,7 @@ tests/
 selector/
 scripts/
 reports/
+local_ccra_reviews/
 ```
 
 Each folder should contain a README explaining its purpose.
@@ -219,8 +220,10 @@ At minimum, keep these files consistent:
 - `docs/PROJECT_BRIEF.md`
 - `docs/DATA_CONTRACT.md`
 - `docs/WORKFLOW.md`
+- `docs/ROUND_AUTOMATION_PROTOCOL.md` when Round Conductor behavior changes
 - `docs/DECISIONS.md`
 - `PROJECTS.md`
+- `local_ccra_reviews/README.md` when Local CCRA review process changes
 
 ## 13. Cross-Repository Collaboration Rules
 
@@ -241,6 +244,14 @@ Use installed runnable Skills from:
 C:\Users\wangq\.agents\skills
 ```
 
+Local CCRA review runs belong in `local_ccra_reviews/`, but the `ccra-local-reviewer` Agent Spec, review rubric, Runtime Spec, invocation protocol, session-continuation contract, and companion capability classification belong in `ccpe-system`.
+
+Round Conductor automation belongs in this repository only as a product-local file protocol and execution workflow. It may orchestrate Local CCRA passes, write Chinese `findings-confirmation.md`, and implement Owner-accepted repairs, but it must not replace Owner decision, Web CCRA review, or lifecycle authority.
+
+Do not repair Local CCRA findings before `owner-decision.md` records `accept_for_codex_fix`.
+
+Do not create a `skills-vault` request for Local CCRA companion automation until CCPE or the project owner classifies the operation as reusable deterministic automation.
+
 If a missing capability blocks model extraction:
 
 1. Classify whether it is a CCPE need or a skills-vault need.

PROJECTS.md

@@ -22,6 +22,8 @@ This repository owns:
 - Selector rules and examples for this product
 - Application implementation when the project later adopts frameworks such as CrewAI, LangGraph, or a server runtime
 - Project-specific requirements, handoffs, validation reports, and decision records
+- Local CCRA review run records under `local_ccra_reviews/`
+- Project-local Round Conductor process records, Owner decisions, and applied repair loops for this product
 
 This repository does not own canonical expert-agent specifications, reusable automation Skill source, or upstream source archives.
 
@@ -60,6 +62,9 @@ requirements/ccpe/
 Use this channel when the project needs:
 
 - Expert-agent definition
+- Local CCRA reviewer Agent Spec
+- CCPE Agent Runtime invocation protocol
+- Runtime session-continuation contract
 - CCPE-Lite prompt card
 - Agent Spec
 - Committee Spec
@@ -71,6 +76,10 @@ Use this channel when the project needs:
 
 Do not store canonical CCPE artifacts in this repository. Store the request here, then let `ccpe-system` own the supplied artifact.
 
+For Local CCRA, this repository stores only review run inputs, runtime session metadata, local review reports, Owner decisions, and action registers. The `ccra-local-reviewer` Agent Spec and Runtime protocol belong in `ccpe-system`.
+
+For Round Conductor automation, this repository owns the product-specific file protocol in `docs/ROUND_AUTOMATION_PROTOCOL.md`, round charters under `reports/`, `findings-confirmation.md`, Owner decisions, accepted repairs, validation outputs, and Web bundle assembly. CCPE still owns reviewer/runtime governance and lifecycle authority rules.
+
 ### skills-vault Requests
 
 Use:
@@ -92,6 +101,10 @@ Use this channel when the project needs:
 
 Do not store reusable automation Skill source in this repository. Store the request here, then let `skills-vault` own the implementation source if the need becomes stable and reusable.
 
+For Local CCRA companion automation, route the capability through `requirements/ccpe/` first when it is unclear whether the need is Agent-specific, Runtime-specific, product-local, or reusable. Create a `skills-vault` request only after the operation has been abstracted as deterministic, reusable automation.
+
+Do not create a `skills-vault` request merely because Round Conductor automation exists. Extract a reusable Skill only after repeated use shows a deterministic, cross-project operation.
+
 ## Model Extraction Work Mode
 
 Model extraction is a duplex workflow:

README.md

@@ -79,7 +79,8 @@ selector/  Rule-based selector configuration and examples.
 scripts/   Local validation and selector demo scripts.
 reports/   Validation reports, extraction notes, and concrete session handoffs.
 knowledge_assets/  Stable long-term reusable knowledge distilled from local project artifacts.
-ccra_review_bundle/  Per-round CCRA review packages; each round must live in its own dated subdirectory.
+ccra_review_bundle/  Per-round Web CCRA / GPT review packages; each round must live in its own dated subdirectory.
+local_ccra_reviews/  File-first Local CCRA review runs, including runtime invocation packets, child-session metadata, local review reports, Owner decisions, and action registers.
 ```
 
 ## 7. Data Format
@@ -174,11 +175,16 @@ Files intended for GPT / CCRA upload inside a review bundle should include the r
 
 Use the installed `bundle-zip` Skill for review bundle raw zips. Do not hand-roll source-relative zip creation with PowerShell `Compress-Archive` when directory paths matter.
 
+Local CCRA first-pass reviews are recorded under `local_ccra_reviews/<public-round>/<local-pass>/`. They run through a real CCPE Agent Runtime child session and normally use the same-child `review_turn` plus `planning_turn` pattern. Local CCRA v0.1.2 requires explicit helper/runtime policies for bundle audit profile, gate execution mode, routing diff policy, and lifecycle scan scope. Local CCRA output is formal local first review, but it does not replace Owner or Web CCRA judgment. Formal Web CCRA bundles do not include the local review report by default.
+
+Round Conductor rules for Round 05 and later trial use are documented in `docs/ROUND_AUTOMATION_PROTOCOL.md`. The protocol allows Codex to automate Local CCRA orchestration and Chinese findings confirmation, then repair only findings recorded by Owner as `accept_for_codex_fix`.
+
 ## 13. Next Steps
 
 1. Round 03 is closed after the Round 03.2a CCRA / GPT pass decision.
 2. Keep QPI and Intellectual Archaeology at `draft / B / pending` until Owner / CCRA review accepts stronger status.
 3. Round 04.1 is closed after GPT review acceptance and closeout documentation. The closeout records `R04-BI-022` as an accepted collateral depth-limited QPI override and adds it to regression.
-4. Round 05 discussion should start from the handoff report in a new session; do not treat Round 04.1 closure as a model lifecycle upgrade.
-5. Defer any third-model expansion until the current QPI selector and case layer are accepted.
-6. Route missing reusable extraction, inspection, or stability-scoring tools to `requirements/skills-vault/` or `requirements/ccpe/` instead of improvising local platform features.
+4. Round 05 should start from Owner / Web CCRA planning, then use `docs/ROUND_AUTOMATION_PROTOCOL.md` for the project-local Round Conductor flow.
+5. Do not treat Round 04.1 closure as a model lifecycle upgrade or as a predefined Round 05 scope.
+6. Defer any third-model expansion until the current QPI selector and case layer are accepted.
+7. Route missing reusable extraction, inspection, or stability-scoring tools to `requirements/skills-vault/` or `requirements/ccpe/` instead of improvising local platform features.

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_05.1.md

@@ -0,0 +1,103 @@
+# Round 05.1 Web CCRA Review Brief
+
+Date: 2026-06-19
+
+Repository: `C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong`
+
+Round: `05.1`
+
+Topic: Selector calibration scoped patch after Round 05 policy review
+
+## 1. Review Goal
+
+Review whether Round 05.1 stayed within the Owner-approved scoped selector calibration patch, with complete before/after behavior evidence and without lifecycle, regression, product-surface, or model-scope overreach.
+
+This is not a new blind routing run and not an open selector redesign.
+
+## 2. Owner Decision
+
+Owner approved moving from Local CCRA pass 01 to formal Web CCRA bundle preparation on 2026-06-19.
+
+Owner decision mapping for this bundle:
+
+- Proceed to Web CCRA bundle: yes.
+- Do not open Round 05.1a selector repair by default.
+- Do not include raw Local CCRA review files in the Web bundle by default.
+- Treat Round 05 setup/context files outside the Round 05.1 patch evidence as packaging-scope context, not selector patch evidence.
+- Defer new regression additions to a future round.
+- Defer structured `prior_qpi_result` / `qpi_context_provided` product contract to a future round.
+
+## 3. What Changed In Round 05.1
+
+- `selector/selector_rules.json` moved from `0.2.1-draft` to `0.2.2-draft`.
+- Added narrow governance / responsibility / consensus QPI weak-positive signals.
+- Added narrow path / responsibility-boundary / stable-output QPI trigger phrases.
+- Added one ambiguous low-context no-call signal.
+- Added 19 Round 05.1 calibration rows to `selector/selector_calibration_inputs.json`.
+- Added deterministic Round 05.1 selector patch audit tooling and tests.
+- Generated before/after behavior diff, validation evidence, lifecycle guard evidence, and post-patch closeout.
+
+## 4. What Did Not Change
+
+- No third model was added.
+- QPI lifecycle status was not upgraded.
+- Intellectual Archaeology lifecycle status was not upgraded.
+- No LLM selector was introduced.
+- No RAG, vector database, frontend, backend, accounts, or service layer was introduced.
+- No regression cases were added at the start of Round 05.1.
+- The full Round 04 blind pool was not converted into regression.
+- Structured `prior_qpi_result` support was not implemented.
+
+## 5. Behavior Diff Summary
+
+- Total cases compared: 215.
+- Changed cases: 7.
+- Targeted behavior changes: 7.
+- Non-target behavior changes: 0.
+- Missing-before cases: 19, all newly added calibration rows.
+- Missing-after cases: 0.
+
+Changed target cases:
+
+- `R04-BI-010`
+- `R04-BI-011`
+- `R04-BI-012`
+- `R04-BI-013`
+- `R04-BI-015`
+- `R04-BI-017`
+- `R04-BI-030`
+
+## 6. Validation Summary
+
+The Round 05.1 gate runner reported PASS for:
+
+- `python -m unittest tests.test_round05_1_selector_patch_audit -v`
+- `python -m unittest discover -s tests -p test*.py -v`
+- `python scripts\run_selector_calibration_smoke.py`
+- `python scripts\rebuild_indexes.py --check`
+- `python scripts\validate_model_library.py`
+- `python scripts\run_selector_regression.py`
+- `python scripts\check_card_contract.py`
+- `python scripts\check_model_card_sync.py`
+
+Lifecycle status guard scan reported PASS with no lifecycle/status blockers.
+
+## 7. Local CCRA Result
+
+Local CCRA pass 01 concluded:
+
+- Round 05.1 stayed inside the scoped selector calibration patch.
+- No Round 05.1a selector repair is required before Web CCRA review.
+- The only finding was minor bundle-packaging hygiene: clarify the boundary between Round 05 setup/context files and Round 05.1 patch evidence.
+
+Raw Local CCRA files are not included in this Web bundle by default. This brief summarizes the local result for review context.
+
+## 8. Suggested Read Order
+
+1. `01_POLICY_SCOPE_AND_OWNER_DECISION_05.1.md`
+2. `02_SELECTOR_BEHAVIOR_DIFF_05.1.md`
+3. `03_VALIDATION_LIFECYCLE_REGRESSION_05.1.md`
+4. `05_EVIDENCE_INDEX_05.1.md`
+5. `04_REVIEW_QUESTIONS_FOR_WEB_CCRA_05.1.md`
+
+Use `optional_raw_changed_files_05.1.zip` only when exact source-file inspection is needed.

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/01_POLICY_SCOPE_AND_OWNER_DECISION_05.1.md

@@ -0,0 +1,62 @@
+# Round 05.1 Policy Scope And Owner Decision
+
+## 1. Policy Basis
+
+Round 05 was a selector calibration policy review. Round 05.1 was a scoped implementation based on:
+
+- `ccra_review_bundle/round-05_init_selector-calibration-policy/06_ROUND05_POLICY_DECISION_MATRIX.md`
+- `ccra_review_bundle/round-05_init_selector-calibration-policy/07_ROUND05_1_PATCH_PLANNING.md`
+
+The approved implementation target was limited to selector calibration inputs, narrow selector rules, deterministic before/after diff evidence, and validation reports.
+
+## 2. Approved Scope
+
+Round 05.1 could:
+
+- Add calibration entries for approved policy categories.
+- Patch selector rules only within the approved Section 6 scope.
+- Preserve QPI-before-IA default behavior.
+- Preserve natural-language prior-QPI claims under lightweight QPI review.
+- Add before/after diff checker output with selected models, rejected models, scores, no-call status, reasons, penalties, target/non-target classification, and changed fields.
+- Run required validation gates.
+
+## 3. Non-Goals
+
+Round 05.1 could not:
+
+- Add a third model.
+- Upgrade QPI lifecycle status.
+- Upgrade Intellectual Archaeology lifecycle status.
+- Introduce an LLM selector.
+- Introduce RAG, vector database, frontend, backend, accounts, or service layer.
+- Convert the full Round 04 blind pool into regression.
+- Treat all organization / governance / capacity / resource / path wording as QPI recall.
+- Implement structured `prior_qpi_result` support.
+
+## 4. Owner Decision For This Web Bundle
+
+The Owner approved preparing the formal Web CCRA bundle after Local CCRA pass 01.
+
+Decision mapping:
+
+| decision_id | decision |
+| --- | --- |
+| OD-001 | `proceed_to_web_bundle` |
+| OD-002 | `exclude_local_report_default` |
+| OD-003 | exclude Round 05 setup/context files from Round 05.1 patch evidence by default; mention as packaging-scope context only if needed |
+| OD-004 | `defer_to_future_round` |
+| OD-005 | `defer_to_future_round` |
+
+No Round 05.1a selector repair is authorized by this decision.
+
+No lifecycle promotion is authorized by this decision.
+
+## 5. Local CCRA Finding Disposition
+
+Local CCRA finding `LC-05.1-001`:
+
+- Severity: minor.
+- Finding: Web bundle packaging should clarify Round 05 setup/context files versus Round 05.1 patch evidence.
+- Disposition for this bundle: addressed by excluding local review files and Round 05 setup/context files from raw patch evidence by default, while summarizing the distinction in this bundle.
+
+This finding does not block Web CCRA review.

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/02_SELECTOR_BEHAVIOR_DIFF_05.1.md

@@ -0,0 +1,63 @@
+# Round 05.1 Selector Behavior Diff Summary
+
+## 1. Main Diff Evidence
+
+Primary deterministic diff:
+
+- `selector_behavior_diff/round05_1_behavior_diff.md`
+- `selector_behavior_diff/round05_1_behavior_diff.json`
+
+Independent helper diff:
+
+- `independent_routing_diff/routing-behavior-diff.md`
+- `independent_routing_diff/routing-behavior-diff.json`
+
+## 2. Summary
+
+| Metric | Value |
+| --- | --- |
+| total_cases_compared | 215 |
+| changed_cases | 7 |
+| targeted_changes | 7 |
+| non_target_changes | 0 |
+| missing_before_cases | 19 |
+| missing_after_cases | 0 |
+
+The 19 missing-before cases are newly added Round 05.1 calibration rows. They are not behavior regressions.
+
+## 3. Targeted Behavior Changes
+
+| case_id | expected change |
+| --- | --- |
+| R04-BI-010 | governance / responsibility input moves from no-call to QPI |
+| R04-BI-011 | governance / conflict input moves from no-call to QPI |
+| R04-BI-012 | consensus / waiting behavior input moves from no-call to QPI |
+| R04-BI-013 | decision authority gap input moves from no-call to QPI |
+| R04-BI-015 | minimum path input moves from no-call to QPI |
+| R04-BI-017 | fragmented time / stable output input moves from no-call to QPI |
+| R04-BI-030 | ambiguous low-context stuckness input moves from QPI to no-call |
+
+## 4. Non-Target Behavior Changes
+
+None.
+
+Both the project diff and independent routing diff report 0 non-target behavior changes.
+
+## 5. Diff Contract Coverage
+
+The machine-readable project diff includes:
+
+- selected models
+- rejected models
+- scores
+- no-call status
+- reasons
+- penalties
+- target / non-target classification
+- changed fields
+- before / after objects
+- policy expectation marker
+
+## 6. Attention Status Clarification
+
+The independent routing diff reports `ATTENTION` because newly added calibration rows are missing from the before baseline. This is expected for rows introduced during Round 05.1 and does not indicate new failures.

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/03_VALIDATION_LIFECYCLE_REGRESSION_05.1.md

@@ -0,0 +1,54 @@
+# Round 05.1 Validation, Lifecycle, And Regression Summary
+
+## 1. Validation Evidence
+
+Primary validation evidence:
+
+- `validation_gates/gate-run-report.md`
+- `validation_gates/gate-run-report.json`
+- `validation_gates/logs/`
+
+Gate-runner status: PASS.
+
+Commands run:
+
+- `python -m unittest tests.test_round05_1_selector_patch_audit -v`
+- `python -m unittest discover -s tests -p test*.py -v`
+- `python scripts\run_selector_calibration_smoke.py`
+- `python scripts\rebuild_indexes.py --check`
+- `python scripts\validate_model_library.py`
+- `python scripts\run_selector_regression.py`
+- `python scripts\check_card_contract.py`
+- `python scripts\check_model_card_sync.py`
+
+Commands skipped: none.
+
+## 2. Regression Impact
+
+Regression JSON files were not expanded at the start of Round 05.1.
+
+Round 05.1 evidence reports:
+
+- No new regression cases were added.
+- Existing selector regression passed.
+- Round 05.1 calibration additions remain calibration material unless a later Owner / CCRA decision promotes selected high-risk guardrails to regression.
+
+## 3. Lifecycle Status
+
+Lifecycle scan evidence:
+
+- `lifecycle_scan/lifecycle-status-guard-scan.md`
+- `lifecycle_scan/lifecycle-status-guard-scan.json`
+
+Lifecycle status remains unchanged:
+
+| model | status | stability_level | regression_status |
+| --- | --- | --- | --- |
+| QPI | draft | B | pending |
+| Intellectual Archaeology | draft | B | pending |
+
+Round 05.1 is not a model lifecycle promotion round.
+
+## 4. Transient Validation Cache Note
+
+The gate-runner report lists `__pycache__` paths as changed during validation. Those were transient Python cache files generated by validation execution and were removed from the working tree after Local CCRA pass 01. They are not included in this Web bundle or in `optional_raw_changed_files_05.1.zip`.

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/04_REVIEW_QUESTIONS_FOR_WEB_CCRA_05.1.md

@@ -0,0 +1,36 @@
+# Review Questions For Web CCRA
+
+## 1. Scope
+
+1. Does Web CCRA accept that Round 05.1 stayed within the approved selector calibration patch scope?
+2. Does Web CCRA agree that this was not an open selector redesign and not a second blind test?
+3. Does Web CCRA agree that no third model, lifecycle upgrade, LLM selector, RAG, vector database, frontend, backend, accounts, or service layer was introduced?
+
+## 2. Behavior Diff
+
+4. Does Web CCRA accept the seven targeted selector behavior changes?
+5. Does Web CCRA accept the zero non-target behavior change disposition?
+6. Does Web CCRA agree that the independent routing diff `ATTENTION` status is adequately explained by newly added calibration rows missing from the before baseline?
+
+## 3. Calibration And Regression
+
+7. Should Round 05.1 calibration rows remain calibration material for now?
+8. Should any specific Round 05.1 case be promoted to regression in a later round?
+9. Does Web CCRA agree that no regression addition was required during Round 05.1 implementation?
+
+## 4. QPI / IA Boundary
+
+10. Does Web CCRA agree that QPI-before-IA remains the default?
+11. Does Web CCRA agree that direct IA exception policy should remain future calibration/product-contract material?
+12. Does Web CCRA agree that natural-language prior-QPI claims should not bypass lightweight QPI review until structured `prior_qpi_result` / `qpi_context_provided` is defined?
+
+## 5. Lifecycle
+
+13. Does Web CCRA agree that QPI remains `draft / B / pending`?
+14. Does Web CCRA agree that Intellectual Archaeology remains `draft / B / pending`?
+15. Does Web CCRA agree that Round 05.1 does not provide lifecycle upgrade evidence?
+
+## 6. Next Step
+
+16. Should Round 05.1 be closed as `document_only` with no Round 05.1a selector repair?
+17. Should the next work item be future calibration / product-contract discussion rather than another no-call patch?

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/05_EVIDENCE_INDEX_05.1.md

@@ -0,0 +1,89 @@
+# Round 05.1 Evidence Index
+
+## 1. Bundle-Level Files
+
+- `00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_05.1.md`
+- `01_POLICY_SCOPE_AND_OWNER_DECISION_05.1.md`
+- `02_SELECTOR_BEHAVIOR_DIFF_05.1.md`
+- `03_VALIDATION_LIFECYCLE_REGRESSION_05.1.md`
+- `04_REVIEW_QUESTIONS_FOR_WEB_CCRA_05.1.md`
+- `05_EVIDENCE_INDEX_05.1.md`
+- `BUNDLE_FILE_MANIFEST_05.1.md`
+- `WEB_BUNDLE_MANIFEST_05.1.json`
+- `validation_sidecar_05.1.json`
+
+## 2. Policy And Scope Evidence
+
+Included in optional raw zip:
+
+- `ccra_review_bundle/round-05_init_selector-calibration-policy/06_ROUND05_POLICY_DECISION_MATRIX.md`
+- `ccra_review_bundle/round-05_init_selector-calibration-policy/07_ROUND05_1_PATCH_PLANNING.md`
+
+Summarized in:
+
+- `01_POLICY_SCOPE_AND_OWNER_DECISION_05.1.md`
+
+## 3. Post-Patch Evidence Pack
+
+Copied into `post_patch_evidence/`:
+
+- `01_ROUND05_1_POST_PATCH_CLOSEOUT.md`
+- `02_ROUND05_1_CHANGED_FILES.md`
+- `03_ROUND05_1_TARGET_BEHAVIOR_DIFF.md`
+- `04_ROUND05_1_NON_TARGET_BEHAVIOR_DIFF.md`
+- `05_ROUND05_1_NON_TARGET_DISPOSITION_TABLE.md`
+- `06_ROUND05_1_VALIDATION_REPORT.md`
+- `07_ROUND05_1_REGRESSION_IMPACT.md`
+- `08_ROUND05_1_LIFECYCLE_GUARD.md`
+- `09_ROUND05_1_OWNER_DECISION_NEEDED.md`
+
+## 4. Behavior Diff Evidence
+
+Copied into `selector_behavior_diff/`:
+
+- `before_selector_behavior.md`
+- `before_selector_behavior.json`
+- `after_selector_behavior.md`
+- `after_selector_behavior.json`
+- `round05_1_behavior_diff.md`
+- `round05_1_behavior_diff.json`
+- `gate-manifest.yaml`
+
+Copied into `independent_routing_diff/`:
+
+- `routing-behavior-diff.md`
+- `routing-behavior-diff.json`
+
+## 5. Validation Evidence
+
+Copied into `validation_gates/`:
+
+- `gate-run-report.md`
+- `gate-run-report.json`
+- `logs/`
+
+## 6. Lifecycle Evidence
+
+Copied into `lifecycle_scan/`:
+
+- `lifecycle-status-guard-scan.md`
+- `lifecycle-status-guard-scan.json`
+- `lifecycle-guard-config.yaml`
+
+## 7. Optional Raw Changed Files
+
+Use `optional_raw_changed_files_05.1.zip` only when exact source-file inspection is needed.
+
+It is generated from `raw_file_list_05.1.txt` and validated by `optional_raw_changed_files_05.1.zip.validation.json`.
+
+## 8. Local-Only Files Not Uploaded By Default
+
+The following were intentionally kept outside the Web bundle by default:
+
+- `local_ccra_reviews/round-05.1_selector-calibration-scoped-patch/01/04_LOCAL_CCRA_REVIEW_REPORT.md`
+- `local_ccra_reviews/round-05.1_selector-calibration-scoped-patch/01/next-review-requirements.md`
+- `local_ccra_reviews/round-05.1_selector-calibration-scoped-patch/01/returned-output.md`
+- `local_ccra_reviews/round-05.1_selector-calibration-scoped-patch/01/findings-confirmation.md`
+- `local_ccra_reviews/round-05.1_selector-calibration-scoped-patch/01/owner-decision.md`
+
+The Web bundle brief summarizes the Local CCRA result and Owner approval instead.

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/BUNDLE_FILE_MANIFEST_05.1.md

@@ -0,0 +1,58 @@
+# Round 05.1 Web CCRA Bundle File Manifest
+
+## 1. Review Files
+
+- `00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_05.1.md`
+- `01_POLICY_SCOPE_AND_OWNER_DECISION_05.1.md`
+- `02_SELECTOR_BEHAVIOR_DIFF_05.1.md`
+- `03_VALIDATION_LIFECYCLE_REGRESSION_05.1.md`
+- `04_REVIEW_QUESTIONS_FOR_WEB_CCRA_05.1.md`
+- `05_EVIDENCE_INDEX_05.1.md`
+- `BUNDLE_FILE_MANIFEST_05.1.md`
+- `WEB_BUNDLE_MANIFEST_05.1.json`
+- `validation_sidecar_05.1.json`
+- `raw_file_list_05.1.txt`
+
+## 2. Copied Evidence Directories
+
+- `post_patch_evidence/`
+- `selector_behavior_diff/`
+- `independent_routing_diff/`
+- `validation_gates/`
+- `lifecycle_scan/`
+
+## 3. Optional Raw Changed Files
+
+- `optional_raw_changed_files_05.1.zip`
+- `optional_raw_changed_files_05.1.zip.validation.json`
+
+The zip is optional and should be used only when exact source-file inspection is needed.
+
+It was generated with the installed `bundle-zip` Skill and preserves source-relative paths from `the-mindscape-of-bro-tsong`.
+
+Zip validation:
+
+- status: PASS
+- source_file_count: 63
+- zip_entry_count: 63
+- warnings: none
+- errors: none
+
+## 4. Context And Audit Outputs
+
+- `context/review-context.md`
+- `context/review-file-manifest.json`
+- `audit/bundle-audit.md`
+- `audit/bundle-audit.json`
+
+Audit outputs are generated after bundle assembly and should be treated as package-completeness evidence, not as Web CCRA acceptance.
+
+## 5. Source-Relative Files Included In Raw Zip
+
+See `raw_file_list_05.1.txt`.
+
+## 6. Local-Only Files Excluded By Default
+
+The Local CCRA review report, planning output, returned output, findings confirmation, helper outputs, and raw Owner decision file remain in `local_ccra_reviews/` and are not included by default.
+
+This bundle includes a brief Owner-decision summary instead.

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/WEB_BUNDLE_MANIFEST_05.1.json

@@ -0,0 +1,78 @@
+{
+  "bundle_id": "round-05.1_2026-06-19_selector-calibration-scoped-patch",
+  "bundle_type": "web_ccra_review_bundle",
+  "project": "the-mindscape-of-bro-tsong",
+  "created_at": "2026-06-19",
+  "round": "05.1",
+  "topic": "selector calibration scoped patch",
+  "owner_decision": {
+    "proceed_to_web_bundle": true,
+    "round05_1a_repair_authorized": false,
+    "include_local_ccra_raw_files": false,
+    "lifecycle_promotion_authorized": false
+  },
+  "non_goals": [
+    "no third model",
+    "no QPI lifecycle upgrade",
+    "no Intellectual Archaeology lifecycle upgrade",
+    "no LLM selector",
+    "no RAG",
+    "no vector database",
+    "no frontend",
+    "no backend",
+    "no accounts",
+    "no service layer",
+    "no full Round 04 blind pool to regression conversion",
+    "no structured prior_qpi_result selector support"
+  ],
+  "review_files": [
+    "00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_05.1.md",
+    "01_POLICY_SCOPE_AND_OWNER_DECISION_05.1.md",
+    "02_SELECTOR_BEHAVIOR_DIFF_05.1.md",
+    "03_VALIDATION_LIFECYCLE_REGRESSION_05.1.md",
+    "04_REVIEW_QUESTIONS_FOR_WEB_CCRA_05.1.md",
+    "05_EVIDENCE_INDEX_05.1.md",
+    "BUNDLE_FILE_MANIFEST_05.1.md"
+  ],
+  "evidence_directories": {
+    "post_patch_evidence": "post_patch_evidence/",
+    "selector_behavior_diff": "selector_behavior_diff/",
+    "independent_routing_diff": "independent_routing_diff/",
+    "validation_gates": "validation_gates/",
+    "lifecycle_scan": "lifecycle_scan/"
+  },
+  "optional_raw_zip": {
+    "file": "optional_raw_changed_files_05.1.zip",
+    "source_list": "raw_file_list_05.1.txt",
+    "validation": "optional_raw_changed_files_05.1.zip.validation.json",
+    "source_file_count": 63,
+    "zip_entry_count": 63
+  },
+  "behavior_diff_summary": {
+    "total_cases_compared": 215,
+    "changed_cases": 7,
+    "targeted_changes": 7,
+    "non_target_changes": 0,
+    "missing_before_cases": 19,
+    "missing_after_cases": 0
+  },
+  "validation_summary": {
+    "gate_runner_status": "PASS",
+    "commands_declared": 8,
+    "commands_run": 8,
+    "commands_skipped": 0,
+    "lifecycle_guard_status": "PASS"
+  },
+  "lifecycle_status": {
+    "qpi": {
+      "status": "draft",
+      "stability_level": "B",
+      "regression_status": "pending"
+    },
+    "intellectual_archaeology": {
+      "status": "draft",
+      "stability_level": "B",
+      "regression_status": "pending"
+    }
+  }
+}

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/audit/bundle-audit.json

@@ -0,0 +1,169 @@
+{
+  "bundle_root": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\ccra_review_bundle\\round-05.1_2026-06-19_selector-calibration-scoped-patch",
+  "profile": "round05_1_web_ccra_bundle",
+  "files_discovered": [
+    "00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_05.1.md",
+    "01_POLICY_SCOPE_AND_OWNER_DECISION_05.1.md",
+    "02_SELECTOR_BEHAVIOR_DIFF_05.1.md",
+    "03_VALIDATION_LIFECYCLE_REGRESSION_05.1.md",
+    "04_REVIEW_QUESTIONS_FOR_WEB_CCRA_05.1.md",
+    "05_EVIDENCE_INDEX_05.1.md",
+    "audit/bundle-audit.json",
+    "audit/bundle-audit.md",
+    "bundle-audit-profile.yaml",
+    "BUNDLE_FILE_MANIFEST_05.1.md",
+    "context/review-context.md",
+    "context/review-file-manifest.json",
+    "independent_routing_diff/routing-behavior-diff.json",
+    "independent_routing_diff/routing-behavior-diff.md",
+    "lifecycle_scan/lifecycle-guard-config.yaml",
+    "lifecycle_scan/lifecycle-status-guard-scan.json",
+    "lifecycle_scan/lifecycle-status-guard-scan.md",
+    "optional_raw_changed_files_05.1.zip",
+    "optional_raw_changed_files_05.1.zip.validation.json",
+    "post_patch_evidence/01_ROUND05_1_POST_PATCH_CLOSEOUT.md",
+    "post_patch_evidence/02_ROUND05_1_CHANGED_FILES.md",
+    "post_patch_evidence/03_ROUND05_1_TARGET_BEHAVIOR_DIFF.md",
+    "post_patch_evidence/04_ROUND05_1_NON_TARGET_BEHAVIOR_DIFF.md",
+    "post_patch_evidence/05_ROUND05_1_NON_TARGET_DISPOSITION_TABLE.md",
+    "post_patch_evidence/06_ROUND05_1_VALIDATION_REPORT.md",
+    "post_patch_evidence/07_ROUND05_1_REGRESSION_IMPACT.md",
+    "post_patch_evidence/08_ROUND05_1_LIFECYCLE_GUARD.md",
+    "post_patch_evidence/09_ROUND05_1_OWNER_DECISION_NEEDED.md",
+    "raw_file_list_05.1.txt",
+    "selector_behavior_diff/after_selector_behavior.json",
+    "selector_behavior_diff/after_selector_behavior.md",
+    "selector_behavior_diff/before_selector_behavior.json",
+    "selector_behavior_diff/before_selector_behavior.md",
+    "selector_behavior_diff/gate-manifest.yaml",
+    "selector_behavior_diff/round05_1_behavior_diff.json",
+    "selector_behavior_diff/round05_1_behavior_diff.md",
+    "validation_gates/gate-run-report.json",
+    "validation_gates/gate-run-report.md",
+    "validation_gates/logs/card-contract.log",
+    "validation_gates/logs/full-unittest-discover.log",
+    "validation_gates/logs/model-card-sync.log",
+    "validation_gates/logs/rebuild-indexes-check.log",
+    "validation_gates/logs/round05-1-audit-script-tests.log",
+    "validation_gates/logs/selector-calibration-smoke.log",
+    "validation_gates/logs/selector-regression.log",
+    "validation_gates/logs/validate-model-library.log",
+    "validation_sidecar_05.1.json",
+    "WEB_BUNDLE_MANIFEST_05.1.json"
+  ],
+  "required_files_present": {
+    "brief": [
+      "00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_05.1.md"
+    ],
+    "manifest": [
+      "WEB_BUNDLE_MANIFEST_05.1.json"
+    ],
+    "validation_sidecar": [
+      "validation_sidecar_05.1.json"
+    ],
+    "file_manifest": [
+      "BUNDLE_FILE_MANIFEST_05.1.md"
+    ],
+    "review_questions": [
+      "04_REVIEW_QUESTIONS_FOR_WEB_CCRA_05.1.md"
+    ]
+  },
+  "required_files_missing": [],
+  "optional_files_present": {
+    "report": [
+      "00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_05.1.md",
+      "01_POLICY_SCOPE_AND_OWNER_DECISION_05.1.md",
+      "02_SELECTOR_BEHAVIOR_DIFF_05.1.md",
+      "03_VALIDATION_LIFECYCLE_REGRESSION_05.1.md",
+      "04_REVIEW_QUESTIONS_FOR_WEB_CCRA_05.1.md",
+      "05_EVIDENCE_INDEX_05.1.md",
+      "BUNDLE_FILE_MANIFEST_05.1.md",
+      "audit/bundle-audit.md",
+      "context/review-context.md",
+      "independent_routing_diff/routing-behavior-diff.md",
+      "lifecycle_scan/lifecycle-status-guard-scan.md",
+      "post_patch_evidence/01_ROUND05_1_POST_PATCH_CLOSEOUT.md",
+      "post_patch_evidence/02_ROUND05_1_CHANGED_FILES.md",
+      "post_patch_evidence/03_ROUND05_1_TARGET_BEHAVIOR_DIFF.md",
+      "post_patch_evidence/04_ROUND05_1_NON_TARGET_BEHAVIOR_DIFF.md",
+      "post_patch_evidence/05_ROUND05_1_NON_TARGET_DISPOSITION_TABLE.md",
+      "post_patch_evidence/06_ROUND05_1_VALIDATION_REPORT.md",
+      "post_patch_evidence/07_ROUND05_1_REGRESSION_IMPACT.md",
+      "post_patch_evidence/08_ROUND05_1_LIFECYCLE_GUARD.md",
+      "post_patch_evidence/09_ROUND05_1_OWNER_DECISION_NEEDED.md",
+      "selector_behavior_diff/after_selector_behavior.md",
+      "selector_behavior_diff/before_selector_behavior.md",
+      "selector_behavior_diff/round05_1_behavior_diff.md",
+      "validation_gates/gate-run-report.md"
+    ],
+    "zip": [
+      "optional_raw_changed_files_05.1.zip"
+    ],
+    "zip_validation": [
+      "optional_raw_changed_files_05.1.zip.validation.json"
+    ]
+  },
+  "manifest_status": {
+    "status": "present",
+    "files": [
+      "WEB_BUNDLE_MANIFEST_05.1.json"
+    ]
+  },
+  "zip_status": {
+    "status": "readable",
+    "files": [
+      "optional_raw_changed_files_05.1.zip"
+    ],
+    "entry_counts": {
+      "optional_raw_changed_files_05.1.zip": 63
+    }
+  },
+  "validation_sidecar_status": {
+    "status": "present",
+    "files": [
+      "validation_sidecar_05.1.json"
+    ]
+  },
+  "report_status": {
+    "status": "present",
+    "files": [
+      "00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_05.1.md",
+      "01_POLICY_SCOPE_AND_OWNER_DECISION_05.1.md",
+      "02_SELECTOR_BEHAVIOR_DIFF_05.1.md",
+      "03_VALIDATION_LIFECYCLE_REGRESSION_05.1.md",
+      "04_REVIEW_QUESTIONS_FOR_WEB_CCRA_05.1.md",
+      "05_EVIDENCE_INDEX_05.1.md",
+      "BUNDLE_FILE_MANIFEST_05.1.md",
+      "audit/bundle-audit.md",
+      "context/review-context.md",
+      "independent_routing_diff/routing-behavior-diff.md",
+      "lifecycle_scan/lifecycle-status-guard-scan.md",
+      "post_patch_evidence/01_ROUND05_1_POST_PATCH_CLOSEOUT.md",
+      "post_patch_evidence/02_ROUND05_1_CHANGED_FILES.md",
+      "post_patch_evidence/03_ROUND05_1_TARGET_BEHAVIOR_DIFF.md",
+      "post_patch_evidence/04_ROUND05_1_NON_TARGET_BEHAVIOR_DIFF.md",
+      "post_patch_evidence/05_ROUND05_1_NON_TARGET_DISPOSITION_TABLE.md",
+      "post_patch_evidence/06_ROUND05_1_VALIDATION_REPORT.md",
+      "post_patch_evidence/07_ROUND05_1_REGRESSION_IMPACT.md",
+      "post_patch_evidence/08_ROUND05_1_LIFECYCLE_GUARD.md",
+      "post_patch_evidence/09_ROUND05_1_OWNER_DECISION_NEEDED.md",
+      "selector_behavior_diff/after_selector_behavior.md",
+      "selector_behavior_diff/before_selector_behavior.md",
+      "selector_behavior_diff/round05_1_behavior_diff.md",
+      "validation_gates/gate-run-report.md"
+    ]
+  },
+  "warnings": [],
+  "blocking_errors": [],
+  "machine_readable_summary": {
+    "status": "PASS",
+    "files_discovered_count": 48,
+    "required_missing_count": 0,
+    "warning_count": 0,
+    "blocking_error_count": 0,
+    "manifest_status": "present",
+    "zip_status": "readable",
+    "validation_sidecar_status": "present",
+    "report_status": "present"
+  }
+}

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/audit/bundle-audit.md

@@ -0,0 +1,85 @@
+# Review Bundle Audit
+
+## Summary
+
+- Status: `PASS`
+- Bundle root: `C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\ccra_review_bundle\round-05.1_2026-06-19_selector-calibration-scoped-patch`
+- Profile: `round05_1_web_ccra_bundle`
+- Files discovered: 48
+- Required files missing: 0
+- Warnings: 0
+- Blocking errors: 0
+
+## Required Files
+
+- `brief`: `00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_05.1.md`
+- `manifest`: `WEB_BUNDLE_MANIFEST_05.1.json`
+- `validation_sidecar`: `validation_sidecar_05.1.json`
+- `file_manifest`: `BUNDLE_FILE_MANIFEST_05.1.md`
+- `review_questions`: `04_REVIEW_QUESTIONS_FOR_WEB_CCRA_05.1.md`
+
+## Package Status
+
+- `manifest_status`: `present` (`WEB_BUNDLE_MANIFEST_05.1.json`)
+- `validation_sidecar_status`: `present` (`validation_sidecar_05.1.json`)
+- `zip_status`: `readable` (`optional_raw_changed_files_05.1.zip`)
+- `report_status`: `present` (`00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_05.1.md`, `01_POLICY_SCOPE_AND_OWNER_DECISION_05.1.md`, `02_SELECTOR_BEHAVIOR_DIFF_05.1.md`, `03_VALIDATION_LIFECYCLE_REGRESSION_05.1.md`, `04_REVIEW_QUESTIONS_FOR_WEB_CCRA_05.1.md`, `05_EVIDENCE_INDEX_05.1.md`, `BUNDLE_FILE_MANIFEST_05.1.md`, `audit/bundle-audit.md`, `context/review-context.md`, `independent_routing_diff/routing-behavior-diff.md`, `lifecycle_scan/lifecycle-status-guard-scan.md`, `post_patch_evidence/01_ROUND05_1_POST_PATCH_CLOSEOUT.md`, `post_patch_evidence/02_ROUND05_1_CHANGED_FILES.md`, `post_patch_evidence/03_ROUND05_1_TARGET_BEHAVIOR_DIFF.md`, `post_patch_evidence/04_ROUND05_1_NON_TARGET_BEHAVIOR_DIFF.md`, `post_patch_evidence/05_ROUND05_1_NON_TARGET_DISPOSITION_TABLE.md`, `post_patch_evidence/06_ROUND05_1_VALIDATION_REPORT.md`, `post_patch_evidence/07_ROUND05_1_REGRESSION_IMPACT.md`, `post_patch_evidence/08_ROUND05_1_LIFECYCLE_GUARD.md`, `post_patch_evidence/09_ROUND05_1_OWNER_DECISION_NEEDED.md`, `selector_behavior_diff/after_selector_behavior.md`, `selector_behavior_diff/before_selector_behavior.md`, `selector_behavior_diff/round05_1_behavior_diff.md`, `validation_gates/gate-run-report.md`)
+
+## Blocking Errors
+
+- None
+
+## Warnings
+
+- None
+
+## Files Discovered
+
+- `00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_05.1.md`
+- `01_POLICY_SCOPE_AND_OWNER_DECISION_05.1.md`
+- `02_SELECTOR_BEHAVIOR_DIFF_05.1.md`
+- `03_VALIDATION_LIFECYCLE_REGRESSION_05.1.md`
+- `04_REVIEW_QUESTIONS_FOR_WEB_CCRA_05.1.md`
+- `05_EVIDENCE_INDEX_05.1.md`
+- `audit/bundle-audit.json`
+- `audit/bundle-audit.md`
+- `bundle-audit-profile.yaml`
+- `BUNDLE_FILE_MANIFEST_05.1.md`
+- `context/review-context.md`
+- `context/review-file-manifest.json`
+- `independent_routing_diff/routing-behavior-diff.json`
+- `independent_routing_diff/routing-behavior-diff.md`
+- `lifecycle_scan/lifecycle-guard-config.yaml`
+- `lifecycle_scan/lifecycle-status-guard-scan.json`
+- `lifecycle_scan/lifecycle-status-guard-scan.md`
+- `optional_raw_changed_files_05.1.zip`
+- `optional_raw_changed_files_05.1.zip.validation.json`
+- `post_patch_evidence/01_ROUND05_1_POST_PATCH_CLOSEOUT.md`
+- `post_patch_evidence/02_ROUND05_1_CHANGED_FILES.md`
+- `post_patch_evidence/03_ROUND05_1_TARGET_BEHAVIOR_DIFF.md`
+- `post_patch_evidence/04_ROUND05_1_NON_TARGET_BEHAVIOR_DIFF.md`
+- `post_patch_evidence/05_ROUND05_1_NON_TARGET_DISPOSITION_TABLE.md`
+- `post_patch_evidence/06_ROUND05_1_VALIDATION_REPORT.md`
+- `post_patch_evidence/07_ROUND05_1_REGRESSION_IMPACT.md`
+- `post_patch_evidence/08_ROUND05_1_LIFECYCLE_GUARD.md`
+- `post_patch_evidence/09_ROUND05_1_OWNER_DECISION_NEEDED.md`
+- `raw_file_list_05.1.txt`
+- `selector_behavior_diff/after_selector_behavior.json`
+- `selector_behavior_diff/after_selector_behavior.md`
+- `selector_behavior_diff/before_selector_behavior.json`
+- `selector_behavior_diff/before_selector_behavior.md`
+- `selector_behavior_diff/gate-manifest.yaml`
+- `selector_behavior_diff/round05_1_behavior_diff.json`
+- `selector_behavior_diff/round05_1_behavior_diff.md`
+- `validation_gates/gate-run-report.json`
+- `validation_gates/gate-run-report.md`
+- `validation_gates/logs/card-contract.log`
+- `validation_gates/logs/full-unittest-discover.log`
+- `validation_gates/logs/model-card-sync.log`
+- `validation_gates/logs/rebuild-indexes-check.log`
+- `validation_gates/logs/round05-1-audit-script-tests.log`
+- `validation_gates/logs/selector-calibration-smoke.log`
+- `validation_gates/logs/selector-regression.log`
+- `validation_gates/logs/validate-model-library.log`
+- `validation_sidecar_05.1.json`
+- `WEB_BUNDLE_MANIFEST_05.1.json`

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/bundle-audit-profile.yaml

@@ -0,0 +1,33 @@
+profiles:
+  round05_1_web_ccra_bundle:
+    required_files:
+      brief:
+        - 00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_05.1.md
+      manifest:
+        - WEB_BUNDLE_MANIFEST_05.1.json
+      validation_sidecar:
+        - validation_sidecar_05.1.json
+      file_manifest:
+        - BUNDLE_FILE_MANIFEST_05.1.md
+      review_questions:
+        - 04_REVIEW_QUESTIONS_FOR_WEB_CCRA_05.1.md
+    optional_files:
+      report:
+        - "*.md"
+      zip:
+        - optional_raw_changed_files_05.1.zip
+      zip_validation:
+        - optional_raw_changed_files_05.1.zip.validation.json
+    allowed_extra_patterns:
+      - "*.md"
+      - "*.json"
+      - "*.txt"
+      - "*.yaml"
+      - "post_patch_evidence/*"
+      - "selector_behavior_diff/*"
+      - "independent_routing_diff/*"
+      - "validation_gates/*"
+      - "validation_gates/logs/*"
+      - "lifecycle_scan/*"
+      - "context/*"
+      - "audit/*"

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/context/review-context.md

@@ -0,0 +1,173 @@
+# Review Context
+
+This context is an index. It does not replace reading source files.
+
+## Metadata
+
+- Review ID: `round-05.1-web-ccra-selector-calibration-scoped-patch`
+- Context profile: `web-ccra`
+- Status: `PASS`
+
+## Source Roots
+
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch`
+
+## Files Included
+
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_05.1.md` (3927 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/01_POLICY_SCOPE_AND_OWNER_DECISION_05.1.md` (2525 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/02_SELECTOR_BEHAVIOR_DIFF_05.1.md` (1921 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/03_VALIDATION_LIFECYCLE_REGRESSION_05.1.md` (1803 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/04_REVIEW_QUESTIONS_FOR_WEB_CCRA_05.1.md` (1884 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/05_EVIDENCE_INDEX_05.1.md` (2773 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/BUNDLE_FILE_MANIFEST_05.1.md` (1741 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/WEB_BUNDLE_MANIFEST_05.1.json` (2373 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/audit/bundle-audit.json` (4248 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/audit/bundle-audit.md` (2672 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/bundle-audit-profile.yaml` (900 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/context/review-context.md` (8724 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/context/review-file-manifest.json` (12355 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/independent_routing_diff/routing-behavior-diff.json` (203586 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/independent_routing_diff/routing-behavior-diff.md` (25705 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/lifecycle_scan/lifecycle-guard-config.yaml` (901 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/lifecycle_scan/lifecycle-status-guard-scan.json` (1809 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/lifecycle_scan/lifecycle-status-guard-scan.md` (667 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/optional_raw_changed_files_05.1.zip.validation.json` (4200 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/01_ROUND05_1_POST_PATCH_CLOSEOUT.md` (972 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/02_ROUND05_1_CHANGED_FILES.md` (1407 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/03_ROUND05_1_TARGET_BEHAVIOR_DIFF.md` (895 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/04_ROUND05_1_NON_TARGET_BEHAVIOR_DIFF.md` (577 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/05_ROUND05_1_NON_TARGET_DISPOSITION_TABLE.md` (478 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/06_ROUND05_1_VALIDATION_REPORT.md` (880 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/07_ROUND05_1_REGRESSION_IMPACT.md` (442 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/08_ROUND05_1_LIFECYCLE_GUARD.md` (508 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/09_ROUND05_1_OWNER_DECISION_NEEDED.md` (644 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/raw_file_list_05.1.txt` (3420 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/after_selector_behavior.json` (278115 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/after_selector_behavior.md` (412 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/before_selector_behavior.json` (255136 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/before_selector_behavior.md` (412 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/gate-manifest.yaml` (2203 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/round05_1_behavior_diff.json` (25759 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/round05_1_behavior_diff.md` (2641 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/gate-run-report.json` (8743 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/gate-run-report.md` (2062 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/card-contract.log` (283 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/full-unittest-discover.log` (4539 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/model-card-sync.log` (428 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/rebuild-indexes-check.log` (423 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/round05-1-audit-script-tests.log` (807 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/selector-calibration-smoke.log` (476 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/selector-regression.log` (446 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/validate-model-library.log` (416 bytes)
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_sidecar_05.1.json` (1750 bytes)
+
+## Files Excluded
+
+- None
+
+## Important Reports
+
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_05.1.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/01_POLICY_SCOPE_AND_OWNER_DECISION_05.1.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/02_SELECTOR_BEHAVIOR_DIFF_05.1.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/03_VALIDATION_LIFECYCLE_REGRESSION_05.1.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/04_REVIEW_QUESTIONS_FOR_WEB_CCRA_05.1.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/05_EVIDENCE_INDEX_05.1.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/BUNDLE_FILE_MANIFEST_05.1.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/WEB_BUNDLE_MANIFEST_05.1.json`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/audit/bundle-audit.json`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/audit/bundle-audit.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/bundle-audit-profile.yaml`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/context/review-context.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/context/review-file-manifest.json`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/independent_routing_diff/routing-behavior-diff.json`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/independent_routing_diff/routing-behavior-diff.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/lifecycle_scan/lifecycle-guard-config.yaml`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/lifecycle_scan/lifecycle-status-guard-scan.json`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/lifecycle_scan/lifecycle-status-guard-scan.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/optional_raw_changed_files_05.1.zip.validation.json`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/01_ROUND05_1_POST_PATCH_CLOSEOUT.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/02_ROUND05_1_CHANGED_FILES.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/03_ROUND05_1_TARGET_BEHAVIOR_DIFF.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/04_ROUND05_1_NON_TARGET_BEHAVIOR_DIFF.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/05_ROUND05_1_NON_TARGET_DISPOSITION_TABLE.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/06_ROUND05_1_VALIDATION_REPORT.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/07_ROUND05_1_REGRESSION_IMPACT.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/08_ROUND05_1_LIFECYCLE_GUARD.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/09_ROUND05_1_OWNER_DECISION_NEEDED.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/raw_file_list_05.1.txt`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/after_selector_behavior.json`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/after_selector_behavior.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/before_selector_behavior.json`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/before_selector_behavior.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/gate-manifest.yaml`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/round05_1_behavior_diff.json`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/round05_1_behavior_diff.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/gate-run-report.json`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/gate-run-report.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/card-contract.log`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/full-unittest-discover.log`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/model-card-sync.log`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/rebuild-indexes-check.log`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/round05-1-audit-script-tests.log`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/selector-calibration-smoke.log`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/selector-regression.log`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/validate-model-library.log`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_sidecar_05.1.json`
+
+## Test Or Validation Outputs
+
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/03_VALIDATION_LIFECYCLE_REGRESSION_05.1.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/optional_raw_changed_files_05.1.zip.validation.json`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/06_ROUND05_1_VALIDATION_REPORT.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/gate-manifest.yaml`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/gate-run-report.json`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/gate-run-report.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/card-contract.log`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/full-unittest-discover.log`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/model-card-sync.log`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/rebuild-indexes-check.log`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/round05-1-audit-script-tests.log`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/selector-calibration-smoke.log`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/selector-regression.log`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/validate-model-library.log`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_sidecar_05.1.json`
+
+## Diff Or Changed File References
+
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/02_SELECTOR_BEHAVIOR_DIFF_05.1.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/independent_routing_diff/routing-behavior-diff.json`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/independent_routing_diff/routing-behavior-diff.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/optional_raw_changed_files_05.1.zip.validation.json`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/02_ROUND05_1_CHANGED_FILES.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/03_ROUND05_1_TARGET_BEHAVIOR_DIFF.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/04_ROUND05_1_NON_TARGET_BEHAVIOR_DIFF.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/after_selector_behavior.json`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/after_selector_behavior.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/before_selector_behavior.json`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/before_selector_behavior.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/gate-manifest.yaml`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/round05_1_behavior_diff.json`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/round05_1_behavior_diff.md`
+
+## Prior Decision References
+
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/01_POLICY_SCOPE_AND_OWNER_DECISION_05.1.md`
+- `ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/09_ROUND05_1_OWNER_DECISION_NEEDED.md`
+
+## Known Non Goals
+
+- None
+
+## Open Questions For Reviewer Or Agent
+
+- None
+
+## Blocking Errors
+
+- None
+
+## Machine Readable Manifest
+
+- `review-file-manifest.json`

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/context/review-file-manifest.json

@@ -0,0 +1,349 @@
+{
+  "review_id": "round-05.1-web-ccra-selector-calibration-scoped-patch",
+  "context_profile": "web-ccra",
+  "project_root": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
+  "source_roots": [
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+  ],
+  "missing_source_roots": [],
+  "files_included": [
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_05.1.md",
+      "size_bytes": 3927,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/01_POLICY_SCOPE_AND_OWNER_DECISION_05.1.md",
+      "size_bytes": 2525,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/02_SELECTOR_BEHAVIOR_DIFF_05.1.md",
+      "size_bytes": 1921,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/03_VALIDATION_LIFECYCLE_REGRESSION_05.1.md",
+      "size_bytes": 1803,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/04_REVIEW_QUESTIONS_FOR_WEB_CCRA_05.1.md",
+      "size_bytes": 1884,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/05_EVIDENCE_INDEX_05.1.md",
+      "size_bytes": 2773,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/BUNDLE_FILE_MANIFEST_05.1.md",
+      "size_bytes": 1741,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/WEB_BUNDLE_MANIFEST_05.1.json",
+      "size_bytes": 2373,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/audit/bundle-audit.json",
+      "size_bytes": 4248,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/audit/bundle-audit.md",
+      "size_bytes": 2672,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/bundle-audit-profile.yaml",
+      "size_bytes": 900,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/context/review-context.md",
+      "size_bytes": 8724,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/context/review-file-manifest.json",
+      "size_bytes": 12355,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/independent_routing_diff/routing-behavior-diff.json",
+      "size_bytes": 203586,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/independent_routing_diff/routing-behavior-diff.md",
+      "size_bytes": 25705,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/lifecycle_scan/lifecycle-guard-config.yaml",
+      "size_bytes": 901,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/lifecycle_scan/lifecycle-status-guard-scan.json",
+      "size_bytes": 1809,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/lifecycle_scan/lifecycle-status-guard-scan.md",
+      "size_bytes": 667,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/optional_raw_changed_files_05.1.zip.validation.json",
+      "size_bytes": 4200,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/01_ROUND05_1_POST_PATCH_CLOSEOUT.md",
+      "size_bytes": 972,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/02_ROUND05_1_CHANGED_FILES.md",
+      "size_bytes": 1407,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/03_ROUND05_1_TARGET_BEHAVIOR_DIFF.md",
+      "size_bytes": 895,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/04_ROUND05_1_NON_TARGET_BEHAVIOR_DIFF.md",
+      "size_bytes": 577,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/05_ROUND05_1_NON_TARGET_DISPOSITION_TABLE.md",
+      "size_bytes": 478,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/06_ROUND05_1_VALIDATION_REPORT.md",
+      "size_bytes": 880,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/07_ROUND05_1_REGRESSION_IMPACT.md",
+      "size_bytes": 442,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/08_ROUND05_1_LIFECYCLE_GUARD.md",
+      "size_bytes": 508,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/09_ROUND05_1_OWNER_DECISION_NEEDED.md",
+      "size_bytes": 644,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/raw_file_list_05.1.txt",
+      "size_bytes": 3420,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/after_selector_behavior.json",
+      "size_bytes": 278115,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/after_selector_behavior.md",
+      "size_bytes": 412,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/before_selector_behavior.json",
+      "size_bytes": 255136,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/before_selector_behavior.md",
+      "size_bytes": 412,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/gate-manifest.yaml",
+      "size_bytes": 2203,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/round05_1_behavior_diff.json",
+      "size_bytes": 25759,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/round05_1_behavior_diff.md",
+      "size_bytes": 2641,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/gate-run-report.json",
+      "size_bytes": 8743,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/gate-run-report.md",
+      "size_bytes": 2062,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/card-contract.log",
+      "size_bytes": 283,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/full-unittest-discover.log",
+      "size_bytes": 4539,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/model-card-sync.log",
+      "size_bytes": 428,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/rebuild-indexes-check.log",
+      "size_bytes": 423,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/round05-1-audit-script-tests.log",
+      "size_bytes": 807,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/selector-calibration-smoke.log",
+      "size_bytes": 476,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/selector-regression.log",
+      "size_bytes": 446,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/validate-model-library.log",
+      "size_bytes": 416,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_sidecar_05.1.json",
+      "size_bytes": 1750,
+      "source_root": "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch"
+    }
+  ],
+  "files_excluded": [],
+  "important_reports": [
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_05.1.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/01_POLICY_SCOPE_AND_OWNER_DECISION_05.1.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/02_SELECTOR_BEHAVIOR_DIFF_05.1.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/03_VALIDATION_LIFECYCLE_REGRESSION_05.1.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/04_REVIEW_QUESTIONS_FOR_WEB_CCRA_05.1.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/05_EVIDENCE_INDEX_05.1.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/BUNDLE_FILE_MANIFEST_05.1.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/WEB_BUNDLE_MANIFEST_05.1.json",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/audit/bundle-audit.json",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/audit/bundle-audit.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/bundle-audit-profile.yaml",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/context/review-context.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/context/review-file-manifest.json",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/independent_routing_diff/routing-behavior-diff.json",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/independent_routing_diff/routing-behavior-diff.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/lifecycle_scan/lifecycle-guard-config.yaml",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/lifecycle_scan/lifecycle-status-guard-scan.json",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/lifecycle_scan/lifecycle-status-guard-scan.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/optional_raw_changed_files_05.1.zip.validation.json",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/01_ROUND05_1_POST_PATCH_CLOSEOUT.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/02_ROUND05_1_CHANGED_FILES.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/03_ROUND05_1_TARGET_BEHAVIOR_DIFF.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/04_ROUND05_1_NON_TARGET_BEHAVIOR_DIFF.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/05_ROUND05_1_NON_TARGET_DISPOSITION_TABLE.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/06_ROUND05_1_VALIDATION_REPORT.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/07_ROUND05_1_REGRESSION_IMPACT.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/08_ROUND05_1_LIFECYCLE_GUARD.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/09_ROUND05_1_OWNER_DECISION_NEEDED.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/raw_file_list_05.1.txt",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/after_selector_behavior.json",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/after_selector_behavior.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/before_selector_behavior.json",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/before_selector_behavior.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/gate-manifest.yaml",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/round05_1_behavior_diff.json",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/round05_1_behavior_diff.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/gate-run-report.json",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/gate-run-report.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/card-contract.log",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/full-unittest-discover.log",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/model-card-sync.log",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/rebuild-indexes-check.log",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/round05-1-audit-script-tests.log",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/selector-calibration-smoke.log",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/selector-regression.log",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/validate-model-library.log",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_sidecar_05.1.json"
+  ],
+  "test_or_validation_outputs": [
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/03_VALIDATION_LIFECYCLE_REGRESSION_05.1.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/optional_raw_changed_files_05.1.zip.validation.json",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/06_ROUND05_1_VALIDATION_REPORT.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/gate-manifest.yaml",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/gate-run-report.json",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/gate-run-report.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/card-contract.log",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/full-unittest-discover.log",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/model-card-sync.log",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/rebuild-indexes-check.log",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/round05-1-audit-script-tests.log",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/selector-calibration-smoke.log",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/selector-regression.log",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/validate-model-library.log",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_sidecar_05.1.json"
+  ],
+  "diff_or_changed_file_references": [
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/02_SELECTOR_BEHAVIOR_DIFF_05.1.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/independent_routing_diff/routing-behavior-diff.json",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/independent_routing_diff/routing-behavior-diff.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/optional_raw_changed_files_05.1.zip.validation.json",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/02_ROUND05_1_CHANGED_FILES.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/03_ROUND05_1_TARGET_BEHAVIOR_DIFF.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/04_ROUND05_1_NON_TARGET_BEHAVIOR_DIFF.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/after_selector_behavior.json",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/after_selector_behavior.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/before_selector_behavior.json",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/before_selector_behavior.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/gate-manifest.yaml",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/round05_1_behavior_diff.json",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/round05_1_behavior_diff.md"
+  ],
+  "prior_decision_references": [
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/01_POLICY_SCOPE_AND_OWNER_DECISION_05.1.md",
+    "ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/09_ROUND05_1_OWNER_DECISION_NEEDED.md"
+  ],
+  "known_non_goals": [],
+  "open_questions_for_reviewer_or_agent": [],
+  "metadata": {},
+  "blocking_errors": [],
+  "machine_readable_summary": {
+    "status": "PASS",
+    "source_roots_count": 1,
+    "missing_source_roots_count": 0,
+    "files_included_count": 47,
+    "files_excluded_count": 0,
+    "important_reports_count": 47,
+    "validation_outputs_count": 15,
+    "diff_references_count": 14,
+    "prior_decisions_count": 2,
+    "blocking_error_count": 0
+  }
+}

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/independent_routing_diff/routing-behavior-diff.md

@@ -0,0 +1,270 @@
+# Routing Behavior Diff
+
+Status: `ATTENTION`
+
+## Summary
+
+- Total cases compared: 215
+- Unchanged cases: 208
+- Changed cases: 7
+- Targeted changes: 7
+- Non-target changes: 0
+- New failures: 0
+- Resolved failures: 0
+- Missing before cases: 19
+- Missing after cases: 0
+
+## Diff Table
+
+| Case ID | Change Type | Targeted | Before Route | After Route | Before Failure | After Failure | No-Call Changed |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| R04-BI-001 | unchanged | False | no_call | no_call | False | False | False |
+| R04-BI-002 | unchanged | False | no_call | no_call | False | False | False |
+| R04-BI-003 | unchanged | False | no_call | no_call | False | False | False |
+| R04-BI-004 | unchanged | False | no_call | no_call | False | False | False |
+| R04-BI-005 | unchanged | False | no_call | no_call | False | False | False |
+| R04-BI-006 | unchanged | False | qpi | qpi | False | False | False |
+| R04-BI-007 | unchanged | False | qpi | qpi | False | False | False |
+| R04-BI-008 | unchanged | False | qpi | qpi | False | False | False |
+| R04-BI-009 | unchanged | False | qpi | qpi | False | False | False |
+| R04-BI-010 | route_changed+no_call_changed | True | no_call | qpi | False | False | True |
+| R04-BI-011 | route_changed+no_call_changed | True | no_call | qpi | False | False | True |
+| R04-BI-012 | route_changed+no_call_changed | True | no_call | qpi | False | False | True |
+| R04-BI-013 | route_changed+no_call_changed | True | no_call | qpi | False | False | True |
+| R04-BI-014 | unchanged | True | no_call | no_call | False | False | False |
+| R04-BI-015 | route_changed+no_call_changed | True | no_call | qpi | False | False | True |
+| R04-BI-016 | unchanged | True | qpi | qpi | False | False | False |
+| R04-BI-017 | route_changed+no_call_changed | True | no_call | qpi | False | False | True |
+| R04-BI-018 | unchanged | False | qpi | qpi | False | False | False |
+| R04-BI-019 | unchanged | False | qpi+intellectual_archaeology | qpi+intellectual_archaeology | False | False | False |
+| R04-BI-020 | unchanged | False | qpi | qpi | False | False | False |
+| R04-BI-021 | unchanged | False | qpi | qpi | False | False | False |
+| R04-BI-022 | unchanged | False | qpi | qpi | False | False | False |
+| R04-BI-023 | unchanged | False | qpi | qpi | False | False | False |
+| R04-BI-024 | unchanged | False | qpi | qpi | False | False | False |
+| R04-BI-025 | unchanged | True | intellectual_archaeology+qpi | intellectual_archaeology+qpi | False | False | False |
+| R04-BI-026 | unchanged | True | qpi | qpi | False | False | False |
+| R04-BI-027 | unchanged | True | qpi | qpi | False | False | False |
+| R04-BI-028 | unchanged | True | no_call | no_call | False | False | False |
+| R04-BI-029 | unchanged | True | no_call | no_call | False | False | False |
+| R04-BI-030 | route_changed+no_call_changed | True | qpi | no_call | False | False | True |
+| R04-BI-031 | unchanged | True | no_call | no_call | False | False | False |
+| R04-BI-032 | unchanged | True | no_call | no_call | False | False | False |
+| R04-BI-033 | unchanged | True | no_call | no_call | False | False | False |
+| R04-BI-034 | unchanged | False | qpi | qpi | False | False | False |
+| R04-BI-035 | unchanged | False | qpi | qpi | False | False | False |
+| R04-BI-036 | unchanged | False | qpi | qpi | False | False | False |
+| R04-BI-037 | unchanged | False | no_call | no_call | False | False | False |
+| R04-BI-038 | unchanged | True | qpi | qpi | False | False | False |
+| case_ia_boundary_medium_core_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_ia_boundary_medium_process_001 | unchanged | False | no_call | no_call | False | False | False |
+| case_ia_boundary_medium_purpose_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_ia_misuse_layer_jump_001 | unchanged | False | intellectual_archaeology | intellectual_archaeology | False | False | False |
+| case_ia_misuse_no_validation_001 | unchanged | False | intellectual_archaeology+qpi | intellectual_archaeology+qpi | False | False | False |
+| case_ia_misuse_philosophizing_001 | unchanged | False | intellectual_archaeology | intellectual_archaeology | False | False | False |
+| case_ia_negative_explicit_do_not_call_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_ia_negative_only_qpi_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_ia_no_call_edit_001 | unchanged | False | no_call | no_call | False | False | False |
+| case_ia_no_call_fact_001 | unchanged | False | no_call | no_call | False | False | False |
+| case_ia_no_call_light_execution_001 | unchanged | False | no_call | no_call | False | False | False |
+| case_ia_pipeline_after_qpi_001 | unchanged | False | intellectual_archaeology+qpi | intellectual_archaeology+qpi | False | False | False |
+| case_ia_positive_deep_modeling_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_ia_positive_heavy_failure_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_ia_positive_heavy_philosophy_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_ia_positive_model_extraction_001 | unchanged | False | intellectual_archaeology+qpi | intellectual_archaeology+qpi | False | False | False |
+| case_ia_positive_resilience_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_ia_round04_do_not_enter_archaeology_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_ia_selector_gate_no_heavy_signal_001 | unchanged | False | no_call | no_call | False | False | False |
+| case_ia_selector_gate_qpi_first_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_academic_ai_evidence_boundary_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_academic_bottom_line_control_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_academic_outcome_quality_assurance_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_academic_policy_memory_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_analysis_override_should_call_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_boundary_mixed_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_boundary_mixed_002 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_boundary_mixed_003 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_depth_limited_dominant_scarcity_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_depth_limited_problem_definition_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_depth_limited_qpi_only_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_dictionary_judgment_no_call_001 | unchanged | False | no_call | no_call | False | False | False |
+| case_qpi_direct_summary_no_call_001 | unchanged | False | no_call | no_call | False | False | False |
+| case_qpi_disappointment_label_as_identity_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_disappointment_mismatch_diagnostics_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_disappointment_one_person_issue_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_disappointment_one_time_fix_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_disappointment_single_factor_totalization_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_employment_credential_compliance_exposure_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_employment_metric_credibility_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_employment_overpromising_pipeline_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_employment_reported_metric_legitimacy_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_engineering_credential_integrity_policy_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_engineering_equipment_solutionism_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_engineering_market_closure_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_engineering_target_authenticity_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_flow_no_simulation_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_how_to_excel_no_call_001 | unchanged | False | no_call | no_call | False | False | False |
+| case_qpi_how_to_markdown_pdf_no_call_001 | unchanged | False | no_call | no_call | False | False | False |
+| case_qpi_international_capacity_governance_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_international_compliance_retention_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_international_logistics_no_call_001 | unchanged | False | no_call | no_call | False | False | False |
+| case_qpi_international_metric_governance_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_international_pricing_trust_system_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_low_context_provisional_no_high_confidence_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_misuse_inflation_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_misuse_reduction_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_multi_perspective_requires_viewpoint_output_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_no_call_direct_edit_001 | unchanged | False | no_call | no_call | False | False | False |
+| case_qpi_org_credential_continuity_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_org_hard_resource_documentation_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_org_untrusted_data_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_pipeline_before_ia_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_positive_issue_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_positive_issue_002 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_positive_issue_003 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_positive_problem_001 | unchanged | False | no_call | no_call | False | False | False |
+| case_qpi_positive_problem_002 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_positive_problem_003 | unchanged | False | no_call | no_call | False | False | False |
+| case_qpi_positive_question_001 | unchanged | False | no_call | no_call | False | False | False |
+| case_qpi_positive_question_002 | unchanged | False | no_call | no_call | False | False | False |
+| case_qpi_positive_question_003 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_research_capacity_problem_not_issue_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_research_data_truthfulness_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_research_identity_simulation_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_research_penalty_integrity_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_research_ranking_reduction_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_round04_depth_limited_assumption_scarcity_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_round04_depth_limited_scarcity_set_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_round04_depth_limited_specific_scarcity_001 | unchanged | False | qpi | qpi | False | False | False |
+| case_qpi_round04_translation_payload_no_call_001 | unchanged | False | no_call | no_call | False | False | False |
+| case_qpi_selector_gate_fact_001 | unchanged | False | no_call | no_call | False | False | False |
+| selector_calibration_analysis_override_should_call_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_direct_execution_001 | unchanged | False | no_call | no_call | False | False | False |
+| selector_calibration_direct_summary_no_call_001 | unchanged | False | no_call | no_call | False | False | False |
+| selector_calibration_fact_lookup_001 | unchanged | False | no_call | no_call | False | False | False |
+| selector_calibration_fact_lookup_002 | unchanged | False | no_call | no_call | False | False | False |
+| selector_calibration_false_positive_deep_word_001 | unchanged | False | no_call | no_call | False | False | False |
+| selector_calibration_false_positive_model_word_001 | unchanged | False | no_call | no_call | False | False | False |
+| selector_calibration_false_positive_philosophy_001 | unchanged | False | no_call | no_call | False | False | False |
+| selector_calibration_ia_after_qpi_001 | unchanged | False | intellectual_archaeology+qpi | intellectual_archaeology+qpi | False | False | False |
+| selector_calibration_ia_after_qpi_002 | unchanged | False | intellectual_archaeology | intellectual_archaeology | False | False | False |
+| selector_calibration_ia_model_extraction_001 | unchanged | False | intellectual_archaeology+qpi | intellectual_archaeology+qpi | False | False | False |
+| selector_calibration_ia_model_extraction_002 | unchanged | False | intellectual_archaeology+qpi | intellectual_archaeology+qpi | False | False | False |
+| selector_calibration_ia_negative_explicit_do_not_call_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_ia_negative_only_qpi_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_override_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_pipeline_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_pipeline_002 | unchanged | False | intellectual_archaeology+qpi | intellectual_archaeology+qpi | False | False | False |
+| selector_calibration_qpi_academic_ai_evidence_boundary_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_academic_bottom_line_control_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_academic_digital_governance_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_academic_outcome_excuse_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_academic_policy_memory_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_academic_resource_reuse_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_academic_staffing_deadlock_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_academic_strategy_myopia_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_complexity_placement_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_depth_limited_dominant_scarcity_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_depth_limited_problem_definition_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_depth_limited_problem_definition_002 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_depth_limited_problem_or_issue_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_depth_limited_qpi_only_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_dictionary_judgment_no_call_001 | unchanged | False | no_call | no_call | False | False | False |
+| selector_calibration_qpi_employment_asset_integration_boundary_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_employment_authority_transfer_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_employment_credential_compliance_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_employment_metric_credibility_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_employment_overpromising_pipeline_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_employment_reported_metric_legitimacy_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_employment_reverse_accountability_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_employment_transactional_education_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_engineering_asset_liability_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_engineering_credential_integrity_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_engineering_equipment_solutionism_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_engineering_market_closure_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_engineering_micro_control_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_engineering_personnel_transition_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_engineering_shortcut_debt_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_engineering_target_authenticity_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_external_authority_boundary_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_flow_entry_point_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_governance_load_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_how_to_excel_no_call_001 | unchanged | False | no_call | no_call | False | False | False |
+| selector_calibration_qpi_how_to_markdown_pdf_no_call_001 | unchanged | False | no_call | no_call | False | False | False |
+| selector_calibration_qpi_insufficient_context_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_international_asset_expansion_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_international_capability_institutionalization_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_international_capacity_gate_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_international_compliance_retention_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_international_logistics_no_call_001 | unchanged | False | no_call | no_call | False | False | False |
+| selector_calibration_qpi_international_metric_distortion_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_international_pricing_trust_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_international_role_inflation_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_international_viewpoint_divergence_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_intra_frame_mixed_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_intra_frame_mixed_flow_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_label_as_identity_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_local_truth_global_structure_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_mismatch_diagnostics_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_no_simulation_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_one_person_issue_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_one_time_fix_trap_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_only_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_only_002 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_org_credential_continuity_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_org_hard_resource_documentation_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_org_incentive_backlash_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_org_low_cost_indicator_survival_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_org_pattern_level_issue_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_org_role_authority_mismatch_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_org_untrusted_data_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_org_workaround_translation_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_psych_mechanism_ambiguity_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_research_accounting_reduction_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_research_hard_capacity_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_research_identity_simulation_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_research_penalty_integrity_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_research_ranking_trap_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_research_safety_accountability_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_research_talent_role_mismatch_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_research_transactional_assets_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_single_factor_totalization_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_stop_gate_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_qpi_time_scale_scope_001 | unchanged | False | qpi | qpi | False | False | False |
+| selector_calibration_rewrite_001 | unchanged | False | no_call | no_call | False | False | False |
+| selector_calibration_round05_1_ambiguous_low_context_no_call_028 | missing_before | False |  | no_call |  | False |  |
+| selector_calibration_round05_1_ambiguous_low_context_no_call_029 | missing_before | False |  | no_call |  | False |  |
+| selector_calibration_round05_1_ambiguous_low_context_no_call_030 | missing_before | False |  | no_call |  | False |  |
+| selector_calibration_round05_1_capacity_resource_path_boundary_015 | missing_before | False |  | qpi |  | False |  |
+| selector_calibration_round05_1_capacity_resource_path_boundary_016 | missing_before | False |  | qpi |  | False |  |
+| selector_calibration_round05_1_capacity_resource_path_boundary_017 | missing_before | False |  | qpi |  | False |  |
+| selector_calibration_round05_1_depth_limited_qpi_override_ia_rejected_022 | missing_before | False |  | qpi |  | False |  |
+| selector_calibration_round05_1_direct_execution_no_call_031 | missing_before | False |  | no_call |  | False |  |
+| selector_calibration_round05_1_direct_execution_no_call_032 | missing_before | False |  | no_call |  | False |  |
+| selector_calibration_round05_1_direct_execution_no_call_033 | missing_before | False |  | no_call |  | False |  |
+| selector_calibration_round05_1_direct_ia_exception_candidate_026 | missing_before | False |  | qpi |  | False |  |
+| selector_calibration_round05_1_direct_ia_exception_candidate_027 | missing_before | False |  | qpi |  | False |  |
+| selector_calibration_round05_1_direct_ia_exception_candidate_038 | missing_before | False |  | qpi |  | False |  |
+| selector_calibration_round05_1_execution_constraint_no_call_014 | missing_before | False |  | no_call |  | False |  |
+| selector_calibration_round05_1_governance_responsibility_consensus_qpi_010 | missing_before | False |  | qpi |  | False |  |
+| selector_calibration_round05_1_governance_responsibility_consensus_qpi_011 | missing_before | False |  | qpi |  | False |  |
+| selector_calibration_round05_1_governance_responsibility_consensus_qpi_012 | missing_before | False |  | qpi |  | False |  |
+| selector_calibration_round05_1_governance_responsibility_consensus_qpi_013 | missing_before | False |  | qpi |  | False |  |
+| selector_calibration_round05_1_natural_language_prior_qpi_claim_025 | missing_before | False |  | intellectual_archaeology+qpi |  | False |  |
+| selector_calibration_translation_001 | unchanged | False | no_call | no_call | False | False | False |
+
+## Machine Readable Summary
+
+```json
+{
+  "status": "ATTENTION",
+  "total_cases_compared": 215,
+  "changed_count": 7,
+  "targeted_change_count": 7,
+  "non_target_change_count": 0,
+  "new_failure_count": 0,
+  "resolved_failure_count": 0,
+  "missing_before_count": 19,
+  "missing_after_count": 0
+}
+```

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/lifecycle_scan/lifecycle-guard-config.yaml

@@ -0,0 +1,41 @@
+watched_paths:
+  - "reports/Round05_1_post_patch_closeout_report_2026-06-19.md"
+  - "docs/DECISIONS.md"
+  - "selector/README.md"
+  - "scripts/README.md"
+  - "selector/selector_rules.json"
+  - "selector/selector_calibration_inputs.json"
+  - "models/qpi.model.json"
+  - "models/intellectual_archaeology.model.json"
+status_fields:
+  - status
+  - lifecycle
+  - model.status
+  - model.lifecycle
+forbidden_status_values:
+  - stable
+  - owner-approved
+  - ccra-approved
+warning_status_values:
+  - candidate
+  - ready-for-review
+required_evidence_markers:
+  - owner_decision
+  - owner decision
+  - ccra_review
+  - ccra review
+  - web ccra
+approved_phrases:
+  - owner-approved
+  - ccra-approved
+  - Owner approved
+  - CCRA approved
+forbidden_phrases:
+  - production-ready
+  - released to production
+  - final approved
+allowed_contexts:
+  - do not say
+  - must not claim
+  - example:
+evidence_window_chars: 240

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/lifecycle_scan/lifecycle-status-guard-scan.json

@@ -0,0 +1,44 @@
+{
+  "scan_root": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
+  "config_path": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\reports\\round05_1_lifecycle_status_guard_scan_2026-06-19\\lifecycle-guard-config.yaml",
+  "files_scanned": [
+    "docs/DECISIONS.md",
+    "models/intellectual_archaeology.model.json",
+    "models/qpi.model.json",
+    "reports/Round05_1_post_patch_closeout_report_2026-06-19.md",
+    "scripts/README.md",
+    "selector/README.md",
+    "selector/selector_calibration_inputs.json",
+    "selector/selector_rules.json"
+  ],
+  "possible_overclaims": [],
+  "field_level_findings": [],
+  "phrase_level_findings": [],
+  "missing_evidence_markers": [],
+  "warnings": [],
+  "blocking_errors": [],
+  "observations": [
+    {
+      "file": "reports/Round05_1_post_patch_closeout_report_2026-06-19.md",
+      "source": "text",
+      "phrase": "Owner approved",
+      "line": 7,
+      "column": 1,
+      "severity": "observation",
+      "evidence_present": true,
+      "context": "# Round 05.1 Post-Patch Closeout Report Date: 2026-06-19 ## 1. Scope Owner approved Round 05.1 as a scoped selector calibration implementation based on `ccra_review_bundle/round-05_init_selector-calibration-policy/07_ROUND05_1_PATCH_PLANNING.md`. This was not an open selector redesign. Implemented scope: - Added Round",
+      "message": "Approval claim phrase has nearby evidence marker; approval validity is not decided by this scan.",
+      "kind": "evidence_present_claim"
+    }
+  ],
+  "machine_readable_summary": {
+    "status": "PASS",
+    "files_scanned_count": 8,
+    "field_finding_count": 0,
+    "phrase_finding_count": 0,
+    "missing_evidence_count": 0,
+    "warning_count": 0,
+    "blocking_count": 0,
+    "observation_count": 1
+  }
+}

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/lifecycle_scan/lifecycle-status-guard-scan.md

@@ -0,0 +1,32 @@
+# Lifecycle Status Guard Scan
+
+## Summary
+
+- Status: `PASS`
+- Files scanned: 8
+- Blocking findings: 0
+- Warnings: 0
+- Evidence-present observations: 1
+
+## Blocking Findings
+
+- None
+
+## Warnings
+
+- None
+
+## Observations
+
+- `reports/Round05_1_post_patch_closeout_report_2026-06-19.md` line 7: `Owner approved` - evidence marker present; approval validity not decided.
+
+## Files Scanned
+
+- `docs/DECISIONS.md`
+- `models/intellectual_archaeology.model.json`
+- `models/qpi.model.json`
+- `reports/Round05_1_post_patch_closeout_report_2026-06-19.md`
+- `scripts/README.md`
+- `selector/README.md`
+- `selector/selector_calibration_inputs.json`
+- `selector/selector_rules.json`

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/optional_raw_changed_files_05.1.zip.validation.json

@@ -0,0 +1,73 @@
+{
+  "status": "PASS",
+  "output_zip": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\ccra_review_bundle\\round-05.1_2026-06-19_selector-calibration-scoped-patch\\optional_raw_changed_files_05.1.zip",
+  "source_file_count": 63,
+  "zip_entry_count": 63,
+  "entries": [
+    "README.md",
+    "AGENTS.md",
+    "PROJECTS.md",
+    "docs/DECISIONS.md",
+    "docs/WORKFLOW.md",
+    "docs/ROUND_AUTOMATION_PROTOCOL.md",
+    "selector/README.md",
+    "selector/selector_rules.json",
+    "selector/selector_calibration_inputs.json",
+    "selector/round04_blind_inputs.json",
+    "scripts/README.md",
+    "scripts/init_round05_context.py",
+    "scripts/run_round04_post_patch_verification.py",
+    "scripts/run_round05_1_selector_patch_audit.py",
+    "tests/test_init_round05_context.py",
+    "tests/test_round05_1_selector_patch_audit.py",
+    "tests/regression_cases.json",
+    "tests/qpi.regression.json",
+    "tests/intellectual_archaeology.regression.json",
+    "models/qpi.model.json",
+    "models/intellectual_archaeology.model.json",
+    "cards/qpi.md",
+    "cards/intellectual_archaeology.md",
+    "ccra_review_bundle/round-05_init_selector-calibration-policy/06_ROUND05_POLICY_DECISION_MATRIX.md",
+    "ccra_review_bundle/round-05_init_selector-calibration-policy/07_ROUND05_1_PATCH_PLANNING.md",
+    "reports/Round04_closeout_note_2026-06-18.md",
+    "reports/Round05_1_post_patch_closeout_report_2026-06-19.md",
+    "reports/round05_1_post_patch/01_ROUND05_1_POST_PATCH_CLOSEOUT.md",
+    "reports/round05_1_post_patch/02_ROUND05_1_CHANGED_FILES.md",
+    "reports/round05_1_post_patch/03_ROUND05_1_TARGET_BEHAVIOR_DIFF.md",
+    "reports/round05_1_post_patch/04_ROUND05_1_NON_TARGET_BEHAVIOR_DIFF.md",
+    "reports/round05_1_post_patch/05_ROUND05_1_NON_TARGET_DISPOSITION_TABLE.md",
+    "reports/round05_1_post_patch/06_ROUND05_1_VALIDATION_REPORT.md",
+    "reports/round05_1_post_patch/07_ROUND05_1_REGRESSION_IMPACT.md",
+    "reports/round05_1_post_patch/08_ROUND05_1_LIFECYCLE_GUARD.md",
+    "reports/round05_1_post_patch/09_ROUND05_1_OWNER_DECISION_NEEDED.md",
+    "reports/round05_1_selector_patch_audit/before_selector_behavior.md",
+    "reports/round05_1_selector_patch_audit/before_selector_behavior.json",
+    "reports/round05_1_selector_patch_audit/after_selector_behavior.md",
+    "reports/round05_1_selector_patch_audit/after_selector_behavior.json",
+    "reports/round05_1_selector_patch_audit/round05_1_behavior_diff.md",
+    "reports/round05_1_selector_patch_audit/round05_1_behavior_diff.json",
+    "reports/round05_1_selector_patch_audit/gate-manifest.yaml",
+    "reports/round05_1_selector_patch_audit/skill_routing_diff/routing-behavior-diff.md",
+    "reports/round05_1_selector_patch_audit/skill_routing_diff/routing-behavior-diff.json",
+    "reports/round05_1_selector_patch_audit/gate_runner/gate-run-report.md",
+    "reports/round05_1_selector_patch_audit/gate_runner/gate-run-report.json",
+    "reports/round05_1_selector_patch_audit/gate_runner/logs/round05-1-audit-script-tests.log",
+    "reports/round05_1_selector_patch_audit/gate_runner/logs/full-unittest-discover.log",
+    "reports/round05_1_selector_patch_audit/gate_runner/logs/selector-calibration-smoke.log",
+    "reports/round05_1_selector_patch_audit/gate_runner/logs/rebuild-indexes-check.log",
+    "reports/round05_1_selector_patch_audit/gate_runner/logs/validate-model-library.log",
+    "reports/round05_1_selector_patch_audit/gate_runner/logs/selector-regression.log",
+    "reports/round05_1_selector_patch_audit/gate_runner/logs/card-contract.log",
+    "reports/round05_1_selector_patch_audit/gate_runner/logs/model-card-sync.log",
+    "reports/round05_1_lifecycle_status_guard_scan_2026-06-19/lifecycle-status-guard-scan.md",
+    "reports/round05_1_lifecycle_status_guard_scan_2026-06-19/lifecycle-status-guard-scan.json",
+    "reports/round05_1_lifecycle_status_guard_scan_2026-06-19/lifecycle-guard-config.yaml",
+    "reports/selector_calibration_smoke_report.md",
+    "reports/selector_regression_report_v0.2.md",
+    "reports/validation_report.md",
+    "reports/index_rebuild_report.md",
+    "reports/model_card_sync_report_v0.2.md"
+  ],
+  "warnings": [],
+  "errors": []
+}

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/01_ROUND05_1_POST_PATCH_CLOSEOUT.md

@@ -0,0 +1,24 @@
+# Round 05.1 Post-Patch Closeout
+
+Source: `reports/Round05_1_post_patch_closeout_report_2026-06-19.md`
+
+Round 05.1 executed a scoped selector calibration patch after Owner approval.
+
+Implemented:
+
+- Added Round 05.1 selector calibration rows.
+- Patched selector rules only with narrow QPI gate phrases for governance / responsibility / consensus and capacity / path boundary cases.
+- Added one ambiguous low-context no-call signal.
+- Added before / after selector behavior snapshot and diff tooling.
+- Preserved QPI-before-IA default behavior.
+- Preserved natural-language prior-QPI claims under lightweight QPI review.
+
+Not implemented:
+
+- No third model.
+- No QPI or Intellectual Archaeology lifecycle upgrade.
+- No LLM selector.
+- No RAG, vector database, frontend, backend, accounts, or service layer.
+- No full Round 04 blind pool conversion into regression.
+- No structured `prior_qpi_result` selector support.
+- No new regression cases at the start of Round 05.1.

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/02_ROUND05_1_CHANGED_FILES.md

@@ -0,0 +1,35 @@
+# Round 05.1 Changed Files
+
+Primary implementation files:
+
+- `selector/selector_calibration_inputs.json`
+- `selector/selector_rules.json`
+- `scripts/run_round05_1_selector_patch_audit.py`
+- `scripts/run_round04_post_patch_verification.py`
+- `tests/test_round05_1_selector_patch_audit.py`
+- `selector/README.md`
+- `scripts/README.md`
+- `docs/DECISIONS.md`
+
+Evidence files:
+
+- `reports/Round05_1_post_patch_closeout_report_2026-06-19.md`
+- `reports/round05_1_selector_patch_audit/before_selector_behavior.json`
+- `reports/round05_1_selector_patch_audit/after_selector_behavior.json`
+- `reports/round05_1_selector_patch_audit/round05_1_behavior_diff.json`
+- `reports/round05_1_selector_patch_audit/round05_1_behavior_diff.md`
+- `reports/round05_1_selector_patch_audit/skill_routing_diff/routing-behavior-diff.json`
+- `reports/round05_1_selector_patch_audit/skill_routing_diff/routing-behavior-diff.md`
+- `reports/round05_1_selector_patch_audit/gate_runner/gate-run-report.json`
+- `reports/round05_1_selector_patch_audit/gate_runner/gate-run-report.md`
+- `reports/round05_1_lifecycle_status_guard_scan_2026-06-19/lifecycle-status-guard-scan.md`
+
+Explicitly unchanged:
+
+- `tests/qpi.regression.json`
+- `tests/intellectual_archaeology.regression.json`
+- `tests/regression_cases.json`
+- `models/qpi.model.json`
+- `models/intellectual_archaeology.model.json`
+- `cards/qpi.md`
+- `cards/intellectual_archaeology.md`

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/03_ROUND05_1_TARGET_BEHAVIOR_DIFF.md

@@ -0,0 +1,22 @@
+# Round 05.1 Target Behavior Diff
+
+Source: `reports/round05_1_selector_patch_audit/round05_1_behavior_diff.md`
+
+Diff summary:
+
+- Total cases compared: 215
+- Changed cases: 7
+- Targeted changes: 7
+- Non-target changes: 0
+
+| case_id | before | after | reason |
+| --- | --- | --- | --- |
+| R04-BI-010 | no_call | qpi | responsibility ambiguity / missing primary owner |
+| R04-BI-011 | no_call | qpi | stakeholder conflict collapses direction |
+| R04-BI-012 | no_call | qpi | commitment / consensus scarcity |
+| R04-BI-013 | no_call | qpi | decision authority gap |
+| R04-BI-015 | no_call | qpi | minimum-path uncertainty |
+| R04-BI-017 | no_call | qpi | stable-output blockage from fragmented execution capacity |
+| R04-BI-030 | qpi | no_call | ambiguous low-context old-problem reference |
+
+Changed fields include selected models, rejected models, scores, no-call status, reasons, and penalties.

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/04_ROUND05_1_NON_TARGET_BEHAVIOR_DIFF.md

@@ -0,0 +1,22 @@
+# Round 05.1 Non-Target Behavior Diff
+
+Source: `reports/round05_1_selector_patch_audit/round05_1_behavior_diff.md`
+
+Project diff result:
+
+```text
+Non-target changes: 0
+```
+
+Independent routing diff result:
+
+```text
+Targeted changes: 7
+Non-target changes: 0
+New failures: 0
+Resolved failures: 0
+```
+
+The independent routing diff reports `ATTENTION` because 19 new calibration rows were added after baseline capture and therefore appear as `missing_before_cases`.
+
+This is expected for Round 05.1 because calibration rows were intentionally added after before baseline capture.

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/05_ROUND05_1_NON_TARGET_DISPOSITION_TABLE.md

@@ -0,0 +1,15 @@
+# Round 05.1 Non-Target Disposition Table
+
+No non-target behavior changes were detected.
+
+Required disposition fields:
+
+| case_id | changed_fields | expected_by_policy | owner_disposition | ccra_disposition | follow_up |
+| --- | --- | --- | --- | --- | --- |
+| none | none | not_applicable | not_applicable | not_applicable | no action |
+
+If a later review reclassifies any behavior change as non-target, Owner / CCRA disposition must use:
+
+```text
+accept / reject / defer
+```

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/06_ROUND05_1_VALIDATION_REPORT.md

@@ -0,0 +1,30 @@
+# Round 05.1 Validation Report
+
+Source: `reports/round05_1_selector_patch_audit/gate_runner/gate-run-report.md`
+
+Gate-runner status:
+
+- Status: PASS
+- Commands declared: 8
+- Commands run: 8
+- Commands skipped: 0
+- Manifest errors: 0
+
+Passed gates:
+
+- `python -m unittest tests.test_round05_1_selector_patch_audit -v`
+- `python -m unittest discover -s tests -p test*.py -v`
+- `python scripts\run_selector_calibration_smoke.py`
+- `python scripts\rebuild_indexes.py --check`
+- `python scripts\validate_model_library.py`
+- `python scripts\run_selector_regression.py`
+- `python scripts\check_card_contract.py`
+- `python scripts\check_model_card_sync.py`
+
+Supporting reports:
+
+- `reports/selector_calibration_smoke_report.md`
+- `reports/selector_regression_report_v0.2.md`
+- `reports/index_rebuild_report.md`
+- `reports/validation_report.md`
+- `reports/model_card_sync_report_v0.2.md`

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/07_ROUND05_1_REGRESSION_IMPACT.md

@@ -0,0 +1,15 @@
+# Round 05.1 Regression Impact
+
+No regression JSON was modified in Round 05.1.
+
+Confirmed unchanged:
+
+- `tests/qpi.regression.json`
+- `tests/intellectual_archaeology.regression.json`
+- `tests/regression_cases.json`
+
+Selector regression passed after the scoped patch.
+
+No new high-risk guardrail was added to regression in this round.
+
+Future Owner / CCRA decisions may separately decide whether any Round 05.1 case should become regression.

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/08_ROUND05_1_LIFECYCLE_GUARD.md

@@ -0,0 +1,21 @@
+# Round 05.1 Lifecycle Guard
+
+Source: `reports/round05_1_lifecycle_status_guard_scan_2026-06-19/lifecycle-status-guard-scan.md`
+
+Lifecycle scan result:
+
+- Status: PASS
+- Files scanned: 8
+- Blocking findings: 0
+- Warnings: 0
+
+Model lifecycle files were not modified.
+
+Current state:
+
+| model | status | stability_level | regression_status |
+| --- | --- | --- | --- |
+| qpi | draft | B | pending |
+| intellectual_archaeology | draft | B | pending |
+
+Round 05.1 does not constitute lifecycle upgrade evidence.

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/post_patch_evidence/09_ROUND05_1_OWNER_DECISION_NEEDED.md

@@ -0,0 +1,15 @@
+# Round 05.1 Owner Decision Needed
+
+No blocking non-target behavior change is pending.
+
+Potential future decisions:
+
+1. Whether any Round 05.1 case should later become regression.
+2. Whether to define a structured `prior_qpi_result` / `qpi_context_provided` product contract.
+3. Whether to further narrow direct IA exception policy after more exact case review.
+4. Whether Local CCRA pass 01 is sufficient to proceed toward formal Web CCRA bundle construction.
+
+Current recommendation for this review step:
+
+- Run Local CCRA pass 01.
+- Do not build formal Web CCRA bundle until Local CCRA findings-confirmation and Owner decision are recorded.

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/raw_file_list_05.1.txt

@@ -0,0 +1,63 @@
+README.md
+AGENTS.md
+PROJECTS.md
+docs/DECISIONS.md
+docs/WORKFLOW.md
+docs/ROUND_AUTOMATION_PROTOCOL.md
+selector/README.md
+selector/selector_rules.json
+selector/selector_calibration_inputs.json
+selector/round04_blind_inputs.json
+scripts/README.md
+scripts/init_round05_context.py
+scripts/run_round04_post_patch_verification.py
+scripts/run_round05_1_selector_patch_audit.py
+tests/test_init_round05_context.py
+tests/test_round05_1_selector_patch_audit.py
+tests/regression_cases.json
+tests/qpi.regression.json
+tests/intellectual_archaeology.regression.json
+models/qpi.model.json
+models/intellectual_archaeology.model.json
+cards/qpi.md
+cards/intellectual_archaeology.md
+ccra_review_bundle/round-05_init_selector-calibration-policy/06_ROUND05_POLICY_DECISION_MATRIX.md
+ccra_review_bundle/round-05_init_selector-calibration-policy/07_ROUND05_1_PATCH_PLANNING.md
+reports/Round04_closeout_note_2026-06-18.md
+reports/Round05_1_post_patch_closeout_report_2026-06-19.md
+reports/round05_1_post_patch/01_ROUND05_1_POST_PATCH_CLOSEOUT.md
+reports/round05_1_post_patch/02_ROUND05_1_CHANGED_FILES.md
+reports/round05_1_post_patch/03_ROUND05_1_TARGET_BEHAVIOR_DIFF.md
+reports/round05_1_post_patch/04_ROUND05_1_NON_TARGET_BEHAVIOR_DIFF.md
+reports/round05_1_post_patch/05_ROUND05_1_NON_TARGET_DISPOSITION_TABLE.md
+reports/round05_1_post_patch/06_ROUND05_1_VALIDATION_REPORT.md
+reports/round05_1_post_patch/07_ROUND05_1_REGRESSION_IMPACT.md
+reports/round05_1_post_patch/08_ROUND05_1_LIFECYCLE_GUARD.md
+reports/round05_1_post_patch/09_ROUND05_1_OWNER_DECISION_NEEDED.md
+reports/round05_1_selector_patch_audit/before_selector_behavior.md
+reports/round05_1_selector_patch_audit/before_selector_behavior.json
+reports/round05_1_selector_patch_audit/after_selector_behavior.md
+reports/round05_1_selector_patch_audit/after_selector_behavior.json
+reports/round05_1_selector_patch_audit/round05_1_behavior_diff.md
+reports/round05_1_selector_patch_audit/round05_1_behavior_diff.json
+reports/round05_1_selector_patch_audit/gate-manifest.yaml
+reports/round05_1_selector_patch_audit/skill_routing_diff/routing-behavior-diff.md
+reports/round05_1_selector_patch_audit/skill_routing_diff/routing-behavior-diff.json
+reports/round05_1_selector_patch_audit/gate_runner/gate-run-report.md
+reports/round05_1_selector_patch_audit/gate_runner/gate-run-report.json
+reports/round05_1_selector_patch_audit/gate_runner/logs/round05-1-audit-script-tests.log
+reports/round05_1_selector_patch_audit/gate_runner/logs/full-unittest-discover.log
+reports/round05_1_selector_patch_audit/gate_runner/logs/selector-calibration-smoke.log
+reports/round05_1_selector_patch_audit/gate_runner/logs/rebuild-indexes-check.log
+reports/round05_1_selector_patch_audit/gate_runner/logs/validate-model-library.log
+reports/round05_1_selector_patch_audit/gate_runner/logs/selector-regression.log
+reports/round05_1_selector_patch_audit/gate_runner/logs/card-contract.log
+reports/round05_1_selector_patch_audit/gate_runner/logs/model-card-sync.log
+reports/round05_1_lifecycle_status_guard_scan_2026-06-19/lifecycle-status-guard-scan.md
+reports/round05_1_lifecycle_status_guard_scan_2026-06-19/lifecycle-status-guard-scan.json
+reports/round05_1_lifecycle_status_guard_scan_2026-06-19/lifecycle-guard-config.yaml
+reports/selector_calibration_smoke_report.md
+reports/selector_regression_report_v0.2.md
+reports/validation_report.md
+reports/index_rebuild_report.md
+reports/model_card_sync_report_v0.2.md

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/after_selector_behavior.md

@@ -0,0 +1,25 @@
+# Round 05.1 Selector Behavior Snapshot: after
+
+Selector version: `0.2.2-draft`
+Cases captured: 234
+
+## Sources
+
+- `aggregate_regression_cases`: 82
+- `round04_blind_pool`: 38
+- `selector_calibration_inputs`: 114
+
+## Targeted Cases
+
+- `R04-BI-010`
+- `R04-BI-011`
+- `R04-BI-012`
+- `R04-BI-013`
+- `R04-BI-014`
+- `R04-BI-015`
+- `R04-BI-016`
+- `R04-BI-017`
+- `R04-BI-025`
+- `R04-BI-026`
+- `R04-BI-027`
+- `R04-BI-038`

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/before_selector_behavior.md

@@ -0,0 +1,25 @@
+# Round 05.1 Selector Behavior Snapshot: before
+
+Selector version: `0.2.1-draft`
+Cases captured: 215
+
+## Sources
+
+- `aggregate_regression_cases`: 82
+- `round04_blind_pool`: 38
+- `selector_calibration_inputs`: 95
+
+## Targeted Cases
+
+- `R04-BI-010`
+- `R04-BI-011`
+- `R04-BI-012`
+- `R04-BI-013`
+- `R04-BI-014`
+- `R04-BI-015`
+- `R04-BI-016`
+- `R04-BI-017`
+- `R04-BI-025`
+- `R04-BI-026`
+- `R04-BI-027`
+- `R04-BI-038`

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/gate-manifest.yaml

@@ -0,0 +1,84 @@
+gates:
+  - gate_id: round05-1-audit-script-tests
+    command:
+      - python
+      - -m
+      - unittest
+      - tests.test_round05_1_selector_patch_audit
+      - -v
+    working_directory: .
+    expected_exit_code: 0
+    log_file: logs/round05-1-audit-script-tests.log
+    timeout_seconds: 120
+    required_before_review: true
+  - gate_id: full-unittest-discover
+    command:
+      - python
+      - -m
+      - unittest
+      - discover
+      - -s
+      - tests
+      - -p
+      - test*.py
+      - -v
+    working_directory: .
+    expected_exit_code: 0
+    log_file: logs/full-unittest-discover.log
+    timeout_seconds: 240
+    required_before_review: true
+  - gate_id: selector-calibration-smoke
+    command:
+      - python
+      - scripts\run_selector_calibration_smoke.py
+    working_directory: .
+    expected_exit_code: 0
+    log_file: logs/selector-calibration-smoke.log
+    timeout_seconds: 120
+    required_before_review: true
+  - gate_id: rebuild-indexes-check
+    command:
+      - python
+      - scripts\rebuild_indexes.py
+      - --check
+    working_directory: .
+    expected_exit_code: 0
+    log_file: logs/rebuild-indexes-check.log
+    timeout_seconds: 120
+    required_before_review: true
+  - gate_id: validate-model-library
+    command:
+      - python
+      - scripts\validate_model_library.py
+    working_directory: .
+    expected_exit_code: 0
+    log_file: logs/validate-model-library.log
+    timeout_seconds: 120
+    required_before_review: true
+  - gate_id: selector-regression
+    command:
+      - python
+      - scripts\run_selector_regression.py
+    working_directory: .
+    expected_exit_code: 0
+    log_file: logs/selector-regression.log
+    timeout_seconds: 120
+    required_before_review: true
+  - gate_id: card-contract
+    command:
+      - python
+      - scripts\check_card_contract.py
+    working_directory: .
+    expected_exit_code: 0
+    log_file: logs/card-contract.log
+    timeout_seconds: 120
+    required_before_review: true
+  - gate_id: model-card-sync
+    command:
+      - python
+      - scripts\check_model_card_sync.py
+    working_directory: .
+    expected_exit_code: 0
+    log_file: logs/model-card-sync.log
+    timeout_seconds: 120
+    required_before_review: true

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/selector_behavior_diff/round05_1_behavior_diff.md

@@ -0,0 +1,29 @@
+# Round 05.1 Selector Behavior Diff
+
+Status: `PASS`
+
+Total cases compared: 215
+Changed cases: 7
+Targeted changes: 7
+Non-target changes: 0
+Missing before cases: 19
+Missing after cases: 0
+
+## Targeted Changes
+
+- `R04-BI-010` (round04_blind_pool): changed_fields=['selected_model_ids', 'rejected_model_ids', 'scores', 'no_call', 'reasons', 'penalties']
+- `R04-BI-011` (round04_blind_pool): changed_fields=['selected_model_ids', 'rejected_model_ids', 'scores', 'no_call', 'reasons', 'penalties']
+- `R04-BI-012` (round04_blind_pool): changed_fields=['selected_model_ids', 'rejected_model_ids', 'scores', 'no_call', 'reasons', 'penalties']
+- `R04-BI-013` (round04_blind_pool): changed_fields=['selected_model_ids', 'rejected_model_ids', 'scores', 'no_call', 'reasons', 'penalties']
+- `R04-BI-015` (round04_blind_pool): changed_fields=['selected_model_ids', 'rejected_model_ids', 'scores', 'no_call', 'reasons', 'penalties']
+- `R04-BI-017` (round04_blind_pool): changed_fields=['selected_model_ids', 'rejected_model_ids', 'scores', 'no_call', 'reasons', 'penalties']
+- `R04-BI-030` (round04_blind_pool): changed_fields=['selected_model_ids', 'rejected_model_ids', 'scores', 'no_call', 'reasons', 'penalties']
+
+## Non-Target Changes
+
+- None
+
+## Missing Cases
+
+- missing_before_cases: `['selector_calibration_round05_1_ambiguous_low_context_no_call_028', 'selector_calibration_round05_1_ambiguous_low_context_no_call_029', 'selector_calibration_round05_1_ambiguous_low_context_no_call_030', 'selector_calibration_round05_1_capacity_resource_path_boundary_015', 'selector_calibration_round05_1_capacity_resource_path_boundary_016', 'selector_calibration_round05_1_capacity_resource_path_boundary_017', 'selector_calibration_round05_1_depth_limited_qpi_override_ia_rejected_022', 'selector_calibration_round05_1_direct_execution_no_call_031', 'selector_calibration_round05_1_direct_execution_no_call_032', 'selector_calibration_round05_1_direct_execution_no_call_033', 'selector_calibration_round05_1_direct_ia_exception_candidate_026', 'selector_calibration_round05_1_direct_ia_exception_candidate_027', 'selector_calibration_round05_1_direct_ia_exception_candidate_038', 'selector_calibration_round05_1_execution_constraint_no_call_014', 'selector_calibration_round05_1_governance_responsibility_consensus_qpi_010', 'selector_calibration_round05_1_governance_responsibility_consensus_qpi_011', 'selector_calibration_round05_1_governance_responsibility_consensus_qpi_012', 'selector_calibration_round05_1_governance_responsibility_consensus_qpi_013', 'selector_calibration_round05_1_natural_language_prior_qpi_claim_025']`
+- missing_after_cases: `[]`

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/gate-run-report.json

@@ -0,0 +1,220 @@
+{
+  "project_root": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
+  "gate_manifest_path": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\reports\\round05_1_selector_patch_audit\\gate-manifest.yaml",
+  "mode": "run",
+  "commands_declared": [
+    "round05-1-audit-script-tests",
+    "full-unittest-discover",
+    "selector-calibration-smoke",
+    "rebuild-indexes-check",
+    "validate-model-library",
+    "selector-regression",
+    "card-contract",
+    "model-card-sync"
+  ],
+  "commands_run": [
+    "round05-1-audit-script-tests",
+    "full-unittest-discover",
+    "selector-calibration-smoke",
+    "rebuild-indexes-check",
+    "validate-model-library",
+    "selector-regression",
+    "card-contract",
+    "model-card-sync"
+  ],
+  "commands_skipped": [],
+  "exit_codes": {
+    "round05-1-audit-script-tests": 0,
+    "full-unittest-discover": 0,
+    "selector-calibration-smoke": 0,
+    "rebuild-indexes-check": 0,
+    "validate-model-library": 0,
+    "selector-regression": 0,
+    "card-contract": 0,
+    "model-card-sync": 0
+  },
+  "pass_fail_status": "PASS",
+  "duration": 12.906,
+  "log_paths": {
+    "round05-1-audit-script-tests": "logs/round05-1-audit-script-tests.log",
+    "full-unittest-discover": "logs/full-unittest-discover.log",
+    "selector-calibration-smoke": "logs/selector-calibration-smoke.log",
+    "rebuild-indexes-check": "logs/rebuild-indexes-check.log",
+    "validate-model-library": "logs/validate-model-library.log",
+    "selector-regression": "logs/selector-regression.log",
+    "card-contract": "logs/card-contract.log",
+    "model-card-sync": "logs/model-card-sync.log"
+  },
+  "environment_notes": [
+    "Commands are declared by the manifest.",
+    "Passing gates are engineering evidence only; they do not imply product acceptance or lifecycle approval.",
+    "python: 3.11.15",
+    "platform: Windows-10-10.0.26200-SP0"
+  ],
+  "gate_results": [
+    {
+      "gate_id": "round05-1-audit-script-tests",
+      "command": "python -m unittest tests.test_round05_1_selector_patch_audit -v",
+      "working_directory": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
+      "expected_exit_code": 0,
+      "exit_code": 0,
+      "status": "PASS",
+      "duration": 0.7969999999622814,
+      "log_path": "logs/round05-1-audit-script-tests.log",
+      "required_before_review": true,
+      "timeout": false,
+      "changed_files": [
+        "scripts/__pycache__/run_round05_1_selector_patch_audit.cpython-311.pyc",
+        "scripts/__pycache__/run_selector_demo.cpython-311.pyc",
+        "tests/__pycache__/test_round05_1_selector_patch_audit.cpython-311.pyc"
+      ]
+    },
+    {
+      "gate_id": "full-unittest-discover",
+      "command": "python -m unittest discover -s tests -p test*.py -v",
+      "working_directory": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
+      "expected_exit_code": 0,
+      "exit_code": 0,
+      "status": "PASS",
+      "duration": 1.6089999999967404,
+      "log_path": "logs/full-unittest-discover.log",
+      "required_before_review": true,
+      "timeout": false,
+      "changed_files": [
+        "scripts/__pycache__/check_card_contract.cpython-311.pyc",
+        "scripts/__pycache__/init_round05_context.cpython-311.pyc",
+        "scripts/__pycache__/rebuild_indexes.cpython-311.pyc",
+        "scripts/__pycache__/run_round04_blind_routing.cpython-311.pyc",
+        "scripts/__pycache__/run_round04_post_patch_verification.cpython-311.pyc",
+        "scripts/__pycache__/validate_model_library.cpython-311.pyc",
+        "tests/__pycache__/test_card_contract.cpython-311.pyc",
+        "tests/__pycache__/test_init_round05_context.cpython-311.pyc",
+        "tests/__pycache__/test_rebuild_indexes.cpython-311.pyc",
+        "tests/__pycache__/test_round04_blind_routing.cpython-311.pyc",
+        "tests/__pycache__/test_round04_post_patch_verification.cpython-311.pyc",
+        "tests/__pycache__/test_validate_model_library.cpython-311.pyc"
+      ]
+    },
+    {
+      "gate_id": "selector-calibration-smoke",
+      "command": "python scripts\\run_selector_calibration_smoke.py",
+      "working_directory": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
+      "expected_exit_code": 0,
+      "exit_code": 0,
+      "status": "PASS",
+      "duration": 0.8589999999967404,
+      "log_path": "logs/selector-calibration-smoke.log",
+      "required_before_review": true,
+      "timeout": false,
+      "changed_files": [
+        "reports/selector_calibration_smoke_report.md"
+      ]
+    },
+    {
+      "gate_id": "rebuild-indexes-check",
+      "command": "python scripts\\rebuild_indexes.py --check",
+      "working_directory": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
+      "expected_exit_code": 0,
+      "exit_code": 0,
+      "status": "PASS",
+      "duration": 0.7810000000172295,
+      "log_path": "logs/rebuild-indexes-check.log",
+      "required_before_review": true,
+      "timeout": false,
+      "changed_files": [
+        "reports/index_rebuild_report.md"
+      ]
+    },
+    {
+      "gate_id": "validate-model-library",
+      "command": "python scripts\\validate_model_library.py",
+      "working_directory": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
+      "expected_exit_code": 0,
+      "exit_code": 0,
+      "status": "PASS",
+      "duration": 0.8130000000237487,
+      "log_path": "logs/validate-model-library.log",
+      "required_before_review": true,
+      "timeout": false,
+      "changed_files": [
+        "reports/validation_report.md"
+      ]
+    },
+    {
+      "gate_id": "selector-regression",
+      "command": "python scripts\\run_selector_regression.py",
+      "working_directory": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
+      "expected_exit_code": 0,
+      "exit_code": 0,
+      "status": "PASS",
+      "duration": 0.7970000000204891,
+      "log_path": "logs/selector-regression.log",
+      "required_before_review": true,
+      "timeout": false,
+      "changed_files": [
+        "reports/selector_regression_report_v0.2.md"
+      ]
+    },
+    {
+      "gate_id": "card-contract",
+      "command": "python scripts\\check_card_contract.py",
+      "working_directory": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
+      "expected_exit_code": 0,
+      "exit_code": 0,
+      "status": "PASS",
+      "duration": 0.7970000000204891,
+      "log_path": "logs/card-contract.log",
+      "required_before_review": true,
+      "timeout": false,
+      "changed_files": []
+    },
+    {
+      "gate_id": "model-card-sync",
+      "command": "python scripts\\check_model_card_sync.py",
+      "working_directory": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
+      "expected_exit_code": 0,
+      "exit_code": 0,
+      "status": "PASS",
+      "duration": 0.8280000000377186,
+      "log_path": "logs/model-card-sync.log",
+      "required_before_review": true,
+      "timeout": false,
+      "changed_files": [
+        "reports/model_card_sync_report_v0.2.md"
+      ]
+    }
+  ],
+  "manifest_errors": [],
+  "changed_files": [
+    "reports/index_rebuild_report.md",
+    "reports/model_card_sync_report_v0.2.md",
+    "reports/selector_calibration_smoke_report.md",
+    "reports/selector_regression_report_v0.2.md",
+    "reports/validation_report.md",
+    "scripts/__pycache__/check_card_contract.cpython-311.pyc",
+    "scripts/__pycache__/init_round05_context.cpython-311.pyc",
+    "scripts/__pycache__/rebuild_indexes.cpython-311.pyc",
+    "scripts/__pycache__/run_round04_blind_routing.cpython-311.pyc",
+    "scripts/__pycache__/run_round04_post_patch_verification.cpython-311.pyc",
+    "scripts/__pycache__/run_round05_1_selector_patch_audit.cpython-311.pyc",
+    "scripts/__pycache__/run_selector_demo.cpython-311.pyc",
+    "scripts/__pycache__/validate_model_library.cpython-311.pyc",
+    "tests/__pycache__/test_card_contract.cpython-311.pyc",
+    "tests/__pycache__/test_init_round05_context.cpython-311.pyc",
+    "tests/__pycache__/test_rebuild_indexes.cpython-311.pyc",
+    "tests/__pycache__/test_round04_blind_routing.cpython-311.pyc",
+    "tests/__pycache__/test_round04_post_patch_verification.cpython-311.pyc",
+    "tests/__pycache__/test_round05_1_selector_patch_audit.cpython-311.pyc",
+    "tests/__pycache__/test_validate_model_library.cpython-311.pyc"
+  ],
+  "machine_readable_summary": {
+    "status": "PASS",
+    "commands_declared_count": 8,
+    "commands_run_count": 8,
+    "commands_skipped_count": 0,
+    "manifest_error_count": 0,
+    "failed_count": 0,
+    "timeout_count": 0,
+    "changed_file_count": 20
+  }
+}

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/gate-run-report.md

@@ -0,0 +1,52 @@
+# Gate Run Report
+
+## Summary
+
+- Status: `PASS`
+- Commands declared: 8
+- Commands run: 8
+- Commands skipped: 0
+- Manifest errors: 0
+- Changed files: 20
+
+## Gate Results
+
+- `round05-1-audit-script-tests`: `PASS` exit `0` log `logs/round05-1-audit-script-tests.log`
+- `full-unittest-discover`: `PASS` exit `0` log `logs/full-unittest-discover.log`
+- `selector-calibration-smoke`: `PASS` exit `0` log `logs/selector-calibration-smoke.log`
+- `rebuild-indexes-check`: `PASS` exit `0` log `logs/rebuild-indexes-check.log`
+- `validate-model-library`: `PASS` exit `0` log `logs/validate-model-library.log`
+- `selector-regression`: `PASS` exit `0` log `logs/selector-regression.log`
+- `card-contract`: `PASS` exit `0` log `logs/card-contract.log`
+- `model-card-sync`: `PASS` exit `0` log `logs/model-card-sync.log`
+
+## Skipped Gates
+
+- None
+
+## Manifest Errors
+
+- None
+
+## Changed Files
+
+- `reports/index_rebuild_report.md`
+- `reports/model_card_sync_report_v0.2.md`
+- `reports/selector_calibration_smoke_report.md`
+- `reports/selector_regression_report_v0.2.md`
+- `reports/validation_report.md`
+- `scripts/__pycache__/check_card_contract.cpython-311.pyc`
+- `scripts/__pycache__/init_round05_context.cpython-311.pyc`
+- `scripts/__pycache__/rebuild_indexes.cpython-311.pyc`
+- `scripts/__pycache__/run_round04_blind_routing.cpython-311.pyc`
+- `scripts/__pycache__/run_round04_post_patch_verification.cpython-311.pyc`
+- `scripts/__pycache__/run_round05_1_selector_patch_audit.cpython-311.pyc`
+- `scripts/__pycache__/run_selector_demo.cpython-311.pyc`
+- `scripts/__pycache__/validate_model_library.cpython-311.pyc`
+- `tests/__pycache__/test_card_contract.cpython-311.pyc`
+- `tests/__pycache__/test_init_round05_context.cpython-311.pyc`
+- `tests/__pycache__/test_rebuild_indexes.cpython-311.pyc`
+- `tests/__pycache__/test_round04_blind_routing.cpython-311.pyc`
+- `tests/__pycache__/test_round04_post_patch_verification.cpython-311.pyc`
+- `tests/__pycache__/test_round05_1_selector_patch_audit.cpython-311.pyc`
+- `tests/__pycache__/test_validate_model_library.cpython-311.pyc`

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/card-contract.log

@@ -0,0 +1,13 @@
+gate_id: card-contract
+working_directory: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong
+command: python scripts\check_card_contract.py
+expected_exit_code: 0
+exit_code: 0
+status: PASS
+duration_seconds: 0.797
+
+## stdout
+card contract check passed
+
+
+## stderr

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/full-unittest-discover.log

@@ -0,0 +1,43 @@
+gate_id: full-unittest-discover
+working_directory: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong
+command: python -m unittest discover -s tests -p test*.py -v
+expected_exit_code: 0
+exit_code: 0
+status: PASS
+duration_seconds: 1.609
+
+## stdout
+
+
+## stderr
+test_missing_required_heading_is_reported (test_card_contract.CardContractTests.test_missing_required_heading_is_reported) ... ok
+test_context_document_contains_round05_scope_and_missing_file_section (test_init_round05_context.Round05ContextInitTests.test_context_document_contains_round05_scope_and_missing_file_section) ... ok
+test_required_sources_and_output_path_are_declared (test_init_round05_context.Round05ContextInitTests.test_required_sources_and_output_path_are_declared) ... ok
+test_check_reports_drift_without_writing (test_rebuild_indexes.RebuildIndexesTests.test_check_reports_drift_without_writing) ... ok
+test_write_rebuilds_model_and_card_indexes (test_rebuild_indexes.RebuildIndexesTests.test_write_rebuilds_model_and_card_indexes) ... ok
+test_evaluates_blind_input_without_answer_key_fields (test_round04_blind_routing.Round04BlindRoutingTests.test_evaluates_blind_input_without_answer_key_fields) ... ok
+test_loads_frozen_blind_inputs_without_expected_routing (test_round04_blind_routing.Round04BlindRoutingTests.test_loads_frozen_blind_inputs_without_expected_routing) ... ok
+test_report_states_results_are_not_scored_against_expected_routing (test_round04_blind_routing.Round04BlindRoutingTests.test_report_states_results_are_not_scored_against_expected_routing) ... ok
+test_report_marks_target_cases_pass_after_patch (test_round04_post_patch_verification.Round041PostPatchVerificationTests.test_report_marks_target_cases_pass_after_patch) ... ok
+test_targeted_labels_are_limited_to_review_approved_cases (test_round04_post_patch_verification.Round041PostPatchVerificationTests.test_targeted_labels_are_limited_to_review_approved_cases) ... ok
+test_behavior_record_contains_diff_contract_fields (test_round05_1_selector_patch_audit.Round051SelectorPatchAuditTests.test_behavior_record_contains_diff_contract_fields) ... ok
+test_diff_marks_target_and_non_target_changes_with_deferred_disposition (test_round05_1_selector_patch_audit.Round051SelectorPatchAuditTests.test_diff_marks_target_and_non_target_changes_with_deferred_disposition) ... ok
+test_invalid_model_type_is_reported (test_validate_model_library.ValidateModelLibraryTests.test_invalid_model_type_is_reported) ... ok
+test_invalid_selection_priority_is_reported (test_validate_model_library.ValidateModelLibraryTests.test_invalid_selection_priority_is_reported) ... ok
+test_missing_source_reference_is_reported (test_validate_model_library.ValidateModelLibraryTests.test_missing_source_reference_is_reported) ... ok
+test_missing_stability_reason_is_reported (test_validate_model_library.ValidateModelLibraryTests.test_missing_stability_reason_is_reported) ... ok
+test_missing_status_is_reported (test_validate_model_library.ValidateModelLibraryTests.test_missing_status_is_reported) ... ok
+test_missing_trigger_keywords_is_reported (test_validate_model_library.ValidateModelLibraryTests.test_missing_trigger_keywords_is_reported) ... ok
+test_model_index_count_drift_is_reported (test_validate_model_library.ValidateModelLibraryTests.test_model_index_count_drift_is_reported) ... ok
+test_model_index_missing_file_is_reported (test_validate_model_library.ValidateModelLibraryTests.test_model_index_missing_file_is_reported) ... ok
+test_model_index_state_drift_is_reported (test_validate_model_library.ValidateModelLibraryTests.test_model_index_state_drift_is_reported) ... ok
+test_qpi_digest_deprecated_fields_are_reported (test_validate_model_library.ValidateModelLibraryTests.test_qpi_digest_deprecated_fields_are_reported) ... ok
+test_qpi_digest_multi_perspective_requires_viewpoint_detail (test_validate_model_library.ValidateModelLibraryTests.test_qpi_digest_multi_perspective_requires_viewpoint_detail) ... ok
+test_qpi_missing_structured_output_contract_field_is_reported (test_validate_model_library.ValidateModelLibraryTests.test_qpi_missing_structured_output_contract_field_is_reported) ... ok
+test_regression_case_coverage_is_reported (test_validate_model_library.ValidateModelLibraryTests.test_regression_case_coverage_is_reported) ... ok
+test_valid_library_has_no_errors (test_validate_model_library.ValidateModelLibraryTests.test_valid_library_has_no_errors) ... ok
+
+----------------------------------------------------------------------
+Ran 26 tests in 0.557s
+
+OK

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/model-card-sync.log

@@ -0,0 +1,14 @@
+gate_id: model-card-sync
+working_directory: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong
+command: python scripts\check_model_card_sync.py
+expected_exit_code: 0
+exit_code: 0
+status: PASS
+duration_seconds: 0.828
+
+## stdout
+model/card sync report written to C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\reports\model_card_sync_report_v0.2.md
+model/card sync passed
+
+
+## stderr

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/rebuild-indexes-check.log

@@ -0,0 +1,14 @@
+gate_id: rebuild-indexes-check
+working_directory: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong
+command: python scripts\rebuild_indexes.py --check
+expected_exit_code: 0
+exit_code: 0
+status: PASS
+duration_seconds: 0.781
+
+## stdout
+index rebuild report written to C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\reports\index_rebuild_report.md
+index check passed
+
+
+## stderr

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/round05-1-audit-script-tests.log

@@ -0,0 +1,19 @@
+gate_id: round05-1-audit-script-tests
+working_directory: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong
+command: python -m unittest tests.test_round05_1_selector_patch_audit -v
+expected_exit_code: 0
+exit_code: 0
+status: PASS
+duration_seconds: 0.797
+
+## stdout
+
+
+## stderr
+test_behavior_record_contains_diff_contract_fields (tests.test_round05_1_selector_patch_audit.Round051SelectorPatchAuditTests.test_behavior_record_contains_diff_contract_fields) ... ok
+test_diff_marks_target_and_non_target_changes_with_deferred_disposition (tests.test_round05_1_selector_patch_audit.Round051SelectorPatchAuditTests.test_diff_marks_target_and_non_target_changes_with_deferred_disposition) ... ok
+
+----------------------------------------------------------------------
+Ran 2 tests in 0.024s
+
+OK

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/selector-calibration-smoke.log

@@ -0,0 +1,14 @@
+gate_id: selector-calibration-smoke
+working_directory: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong
+command: python scripts\run_selector_calibration_smoke.py
+expected_exit_code: 0
+exit_code: 0
+status: PASS
+duration_seconds: 0.859
+
+## stdout
+selector calibration smoke report written to C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\reports\selector_calibration_smoke_report.md
+selector calibration smoke passed
+
+
+## stderr

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/selector-regression.log

@@ -0,0 +1,14 @@
+gate_id: selector-regression
+working_directory: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong
+command: python scripts\run_selector_regression.py
+expected_exit_code: 0
+exit_code: 0
+status: PASS
+duration_seconds: 0.797
+
+## stdout
+selector regression report written to C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\reports\selector_regression_report_v0.2.md
+selector regression passed
+
+
+## stderr

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_gates/logs/validate-model-library.log

@@ -0,0 +1,14 @@
+gate_id: validate-model-library
+working_directory: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong
+command: python scripts\validate_model_library.py
+expected_exit_code: 0
+exit_code: 0
+status: PASS
+duration_seconds: 0.813
+
+## stdout
+validation report written to C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\reports\validation_report.md
+validation passed
+
+
+## stderr

ccra_review_bundle/round-05.1_2026-06-19_selector-calibration-scoped-patch/validation_sidecar_05.1.json

@@ -0,0 +1,54 @@
+{
+  "sidecar_id": "round-05.1_web_ccra_validation_sidecar",
+  "generated_at": "2026-06-19",
+  "status": "PASS_WITH_EXPECTED_ATTENTION",
+  "checks": [
+    {
+      "check_id": "raw_zip_validation",
+      "status": "PASS",
+      "evidence": "optional_raw_changed_files_05.1.zip.validation.json",
+      "notes": "63 source files, 63 zip entries, no warnings or errors."
+    },
+    {
+      "check_id": "selector_behavior_diff",
+      "status": "PASS",
+      "evidence": "selector_behavior_diff/round05_1_behavior_diff.json",
+      "notes": "215 compared, 7 changed, 7 targeted, 0 non-target, 19 missing-before calibration rows, 0 missing-after."
+    },
+    {
+      "check_id": "independent_routing_diff",
+      "status": "ATTENTION_EXPECTED",
+      "evidence": "independent_routing_diff/routing-behavior-diff.json",
+      "notes": "Attention is caused by expected missing-before calibration additions, not new failures."
+    },
+    {
+      "check_id": "gate_runner",
+      "status": "PASS",
+      "evidence": "validation_gates/gate-run-report.json",
+      "notes": "8 commands declared and run, 0 skipped."
+    },
+    {
+      "check_id": "lifecycle_status_guard",
+      "status": "PASS",
+      "evidence": "lifecycle_scan/lifecycle-status-guard-scan.json",
+      "notes": "No lifecycle/status blockers."
+    },
+    {
+      "check_id": "local_ccra_gate",
+      "status": "PASS",
+      "evidence": "summarized in 00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_05.1.md",
+      "notes": "Local raw review files intentionally excluded by default."
+    },
+    {
+      "check_id": "web_bundle_audit",
+      "status": "PASS",
+      "evidence": "audit/bundle-audit.json",
+      "notes": "48 files discovered, 0 required files missing, 0 warnings, 0 blocking errors; zip readable."
+    }
+  ],
+  "known_limitations": [
+    "This sidecar is package evidence, not Web CCRA acceptance.",
+    "Local CCRA raw files are not included by default.",
+    "No lifecycle promotion is requested or authorized."
+  ]
+}

ccra_review_bundle/round-05_init_selector-calibration-policy/00_ROUND05_NEW_SESSION_CONTEXT.md

@@ -0,0 +1,111 @@
+# Round 05 New Session Context
+
+Generated: 2026-06-19
+
+Generated by `python scripts/init_round05_context.py`.
+
+This file is a read-only startup context for a new Round 05 conversation. The script does not call an LLM and does not modify selector rules, model cards, model specs, or regression cases.
+
+## Project State
+
+- Current phase: `model_library_mvp`.
+- Current goal: file-first cognitive model library MVP.
+- Current sample models: QPI and Intellectual Archaeology.
+- Current selector: rule-based, backed by `selector/selector_rules.json`.
+- No LLM selector, RAG, vector database, frontend, backend, or service layer is in scope.
+
+Current model lifecycle state:
+
+- QPI: status `draft`, stability_level `B`, regression_status `pending`
+- Intellectual Archaeology: status `draft`, stability_level `B`, regression_status `pending`
+
+Current regression case counts:
+
+- QPI: 62
+- Intellectual Archaeology: 20
+- Aggregate: 82
+
+## Round 04 / 04.1 Closure Summary
+
+- Round 04 was a blind routing evaluation.
+- The original Round 04 blind routing report is preserved and was not rewritten.
+- Round 04.1 was a selector no-call, hard exclusion, and depth-limiting patch plus post-patch verification.
+- Round 04.1 is not a second blind test.
+- Four targeted cases passed post-patch verification.
+- Targeted cases checked: 4.
+- Targeted failures: 0.
+- Behavior changes recorded: 5.
+- No model lifecycle upgrade follows from Round 04 / 04.1.
+- No LLM selector is introduced.
+- QPI and Intellectual Archaeology remain `draft / B / pending`.
+
+Round 04.1 targeted fixes:
+
+- `R04-BI-002`: translation payload must not trigger QPI.
+- `R04-BI-024`: explicit IA refusal must hard-exclude Intellectual Archaeology while allowing lightweight QPI.
+- `R04-BI-035`: depth-limiting plus dominant-scarcity judgment should allow QPI.
+- `R04-BI-036`: depth-limiting plus information / path / consensus scarcity judgment should allow QPI.
+
+`R04-BI-022` closeout note:
+
+- Original result: hard no-call.
+- After patch: QPI selected, IA rejected.
+- Judgment: accepted collateral behavior change from the depth-limiting QPI override.
+- This is not treated as a new failure.
+- It is already represented in QPI regression as `case_qpi_round04_depth_limited_assumption_scarcity_001`.
+- Round 05 should discuss whether it remains regression, also enters calibration, or becomes calibration-only policy material later.
+- Do not open a new patch round only for `R04-BI-022`.
+
+## Round 05: Selector Calibration Policy Review
+
+Round 05 should review selector calibration policy before changing rules.
+
+Round 05 should not directly modify selector rules unless Owner / CCRA explicitly approves a follow-up Round 05.1 patch.
+
+Round 05 should not continue treating Round 04.1 as an unfinished patch round. The policy review starts from the accepted Round 04 / 04.1 closure evidence.
+
+## Round 05 Core Questions
+
+- Should governance / responsibility / consensus inputs more easily enter QPI?
+- For capacity / resource / path inputs, which should remain no-call and which should enter QPI?
+- Should likely Intellectual Archaeology natural-language inputs allow direct IA entry, or must they be QPI-first?
+- When the user says "QPI already judged...", should the selector still select QPI together with IA, or select IA only?
+- How should ambiguous low-context inputs be handled?
+- Is a before/after behavior diff checker needed to list every non-target behavior change automatically?
+- Should `R04-BI-022` stay in regression, move into calibration discussion, or both?
+
+## Files To Read in New Conversation
+
+- `reports/Round04_closeout_note_2026-06-18.md` (present)
+- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md` (present)
+- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md` (present)
+- `selector/round04_blind_inputs.json` (present)
+- `selector/selector_rules.json` (present)
+- `selector/selector_calibration_inputs.json` (present)
+- `tests/qpi.regression.json` (present)
+- `tests/intellectual_archaeology.regression.json` (present)
+- `tests/regression_cases.json` (present)
+- `docs/DECISIONS.md` (present)
+- `docs/WORKFLOW.md` (present)
+
+## Round 05 Non-Goals
+
+- Do not add a third model.
+- Do not upgrade QPI.
+- Do not upgrade Intellectual Archaeology.
+- Do not introduce an LLM selector.
+- Do not introduce RAG, vector database, frontend, or backend.
+- Do not expand all organization problems into QPI recall.
+- Do not convert the full Round 04 blind pool directly into regression.
+
+## Suggested Round 05 Deliverables
+
+- `01_ROUND05_SCOPE_AND_POLICY_QUESTIONS.md`
+- `02_ROUND04_BEHAVIOR_DIFF_FOR_CALIBRATION.md`
+- `03_CANDIDATE_CALIBRATION_CASES.md`
+- `04_CANDIDATE_REGRESSION_CASES.md`
+- `05_CCRA_REVIEW_QUESTIONS_ROUND05.md`
+
+## Missing Files
+
+- None

ccra_review_bundle/round-05_init_selector-calibration-policy/01_ROUND05_SCOPE_AND_POLICY_QUESTIONS.md

@@ -0,0 +1,103 @@
+# Round 05 Scope And Policy Questions
+
+Date: 2026-06-19
+
+## 1. Round Naming
+
+Use the existing public round convention:
+
+- `Round 05` / `round-05`: the first Round 05 activity, focused on selector calibration policy review.
+- `Round 05.1` / `round-05.1`: the first selector patch round after Round 05 policy decisions, if Owner / CCRA explicitly approves a patch.
+
+Do not renumber from zero. In this repository, prior examples already use `Round 03 -> Round 03.1 -> Round 03.2 -> Round 03.2a` and `Round 04 -> Round 04.1`.
+
+## 2. Round 05 Objective
+
+Round 05 is a selector calibration policy review.
+
+The goal is to prepare the evidence, decision questions, and candidate case groupings needed for Owner / CCRA discussion. It does not decide selector rules by itself and does not patch `selector/selector_rules.json`.
+
+Round 05 should answer whether the current rule-based selector should later be calibrated around:
+
+- QPI recall for governance / responsibility / consensus inputs.
+- Capacity / resource / path boundaries between no-call and QPI.
+- QPI-first versus direct Intellectual Archaeology entry.
+- Handling of inputs that claim "QPI already judged...".
+- Before / after behavior diff requirements for future selector patches.
+
+## 3. Non-Goals
+
+Round 05 does not:
+
+- Modify `selector/selector_rules.json`.
+- Modify `tests/qpi.regression.json`.
+- Modify `tests/intellectual_archaeology.regression.json`.
+- Modify `tests/regression_cases.json`.
+- Modify model cards or model specs.
+- Upgrade QPI or Intellectual Archaeology lifecycle status.
+- Add an LLM selector.
+- Add a third model.
+- Add RAG, vector database, frontend, backend, accounts, or a new product module.
+- Convert the full Round 04 blind pool into regression.
+- Treat every organization / governance input as QPI recall.
+
+## 4. Evidence Inputs
+
+Primary local files for this policy review:
+
+- `reports/Round04_closeout_note_2026-06-18.md`
+- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
+- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md`
+- `selector/round04_blind_inputs.json`
+- `selector/selector_rules.json`
+- `selector/selector_calibration_inputs.json`
+- `tests/qpi.regression.json`
+- `tests/intellectual_archaeology.regression.json`
+- `tests/regression_cases.json`
+- `docs/DECISIONS.md`
+- `docs/WORKFLOW.md`
+
+This file summarizes the role of these files. It does not replace reading them.
+
+## 5. Policy Questions
+
+### A. QPI Recall Boundary
+
+- Should governance / responsibility / consensus language become a weak positive QPI signal?
+- Should it trigger QPI only when the input includes scarcity, conflict, responsibility ambiguity, decision authority gaps, or explicit problem-definition intent?
+- How do we prevent "all organization questions are QPI" overreach?
+
+### B. Capacity / Resource / Path Boundary
+
+- When capacity / resource / path is only an execution constraint, should selector stay no-call?
+- When capacity / resource / path changes the problem classification, action path, or responsibility boundary, should selector route to QPI?
+- Should Round 05 define an `execution_constraint_no_call` calibration class?
+
+### C. Intellectual Archaeology Entry
+
+- Should default routing remain QPI-before-IA?
+- Are some inputs strong enough for direct IA when they ask for deep assumptions, core mechanism, reusable structure, or philosophical bedrock?
+- Should `likely_intellectual_archaeology` remain a candidate category rather than a direct selected condition?
+
+### D. QPI-After-QPI Inputs
+
+- Is a natural-language claim that "QPI already judged..." enough to skip QPI?
+- Should skip-QPI require structured prior QPI fields such as `classification`, `dominant_scarcity`, `evidence_gap`, and `next_model_candidates`?
+- Should this repository define a `prior_qpi_result` or `qpi_context_provided` input shape before any IA-only routing change?
+
+### E. Patch Audit
+
+- Should every future selector patch include before / after behavior diff output?
+- Should diff output list selected models, rejected models, score changes, no-call status, reasons, and penalties?
+- Must every non-target behavior change be explicitly accepted, rejected, or deferred by Owner / CCRA?
+
+## 6. Expected Round 05 Output
+
+Round 05 should produce:
+
+- A policy decision set or unresolved question list.
+- A small set of candidate calibration cases.
+- A smaller set of candidate regression cases.
+- A recommendation on whether to proceed to `Round 05.1`.
+
+Only after Owner / CCRA approves a patch should Codex prepare `Round 05.1` implementation materials.

ccra_review_bundle/round-05_init_selector-calibration-policy/02_ROUND04_BEHAVIOR_DIFF_FOR_CALIBRATION.md

@@ -0,0 +1,158 @@
+# Round 04 Behavior Diff For Calibration
+
+Date: 2026-06-19
+
+## 1. Purpose
+
+This file turns Round 04 / 04.1 selector behavior into calibration evidence for Round 05.
+
+It does not score correctness for every blind case, does not modify selector rules, and does not decide which cases become regression.
+
+## 2. Round 04 / 04.1 Summary
+
+Source files:
+
+- `selector/round04_blind_inputs.json`
+- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
+- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md`
+- `reports/Round04_closeout_note_2026-06-18.md`
+
+Round 04:
+
+- First blind routing evaluation.
+- 38 frozen inputs.
+- No expected selector behavior in the blind input JSON.
+- Original report preserved and not rewritten.
+
+Round 04.1:
+
+- Selector rule patch verification, not a second blind test.
+- Four targeted cases checked.
+- Targeted failures: 0.
+- Behavior changes recorded: 5.
+
+## 3. Targeted Fixes
+
+| Case | Before | After | Closeout Meaning |
+| --- | --- | --- | --- |
+| `R04-BI-002` | QPI selected | no-call | Translation payload must not trigger QPI. |
+| `R04-BI-024` | QPI + IA selected | QPI selected, IA rejected | Explicit IA refusal must hard-exclude IA. |
+| `R04-BI-035` | no-call | QPI selected, IA rejected | Depth-limiting phrase should not block lightweight dominant-scarcity QPI. |
+| `R04-BI-036` | no-call | QPI selected, IA rejected | Depth-limiting phrase should not block information / path / consensus QPI. |
+
+These four are already covered by Round 04.1 verification. They should not be reopened as a no-call patch loop in Round 05.
+
+## 4. Accepted Collateral Change
+
+| Case | Before | After | Closeout Meaning |
+| --- | --- | --- | --- |
+| `R04-BI-022` | no-call | QPI selected, IA rejected | Accepted collateral behavior change from depth-limiting QPI override. |
+
+`R04-BI-022` is already represented in QPI regression as:
+
+```text
+case_qpi_round04_depth_limited_assumption_scarcity_001
+```
+
+Round 05 should decide whether it should also be treated as calibration material, remain regression only, or later be moved to a different policy category. Do not open a new patch round only for this case.
+
+## 5. Category-Level Observations For Round 05
+
+### Governance / Responsibility / Consensus
+
+Round 04 cases:
+
+- `R04-BI-010`
+- `R04-BI-011`
+- `R04-BI-012`
+- `R04-BI-013`
+
+Post-patch behavior:
+
+- All four remain no-call.
+
+Calibration issue:
+
+- These cases expose the core Round 05 question: should responsibility ambiguity, consensus scarcity, or decision-authority gaps become weak QPI recall signals, or should selector require explicit problem-definition language?
+
+### Capacity / Resource / Path
+
+Round 04 cases:
+
+- `R04-BI-014`
+- `R04-BI-015`
+- `R04-BI-016`
+- `R04-BI-017`
+
+Post-patch behavior:
+
+- `R04-BI-014`: no-call
+- `R04-BI-015`: no-call
+- `R04-BI-016`: QPI selected
+- `R04-BI-017`: no-call
+
+Calibration issue:
+
+- Current selector distinguishes one operational-path case from three capacity/resource/path cases. Round 05 should decide whether this split is correct, and whether capacity / resource / path should be divided into execution constraint, path uncertainty, hard resource constraint, and responsibility-boundary subtypes.
+
+### Likely Intellectual Archaeology
+
+Round 04 cases:
+
+- `R04-BI-025`
+- `R04-BI-026`
+- `R04-BI-027`
+- `R04-BI-038`
+
+Post-patch behavior:
+
+- `R04-BI-025`: QPI + IA selected
+- `R04-BI-026`: QPI selected, IA rejected
+- `R04-BI-027`: QPI selected, IA rejected
+- `R04-BI-038`: QPI selected, IA rejected
+
+Calibration issue:
+
+- These cases should drive the QPI-first versus IA-direct discussion. Do not infer direct IA eligibility from the category label alone.
+
+### QPI-After-QPI
+
+Main case:
+
+- `R04-BI-025`
+
+Post-patch behavior:
+
+- QPI and IA are both selected.
+
+Calibration issue:
+
+- Round 05 should decide whether a natural-language "QPI already judged..." claim is enough to skip QPI, or whether IA-only routing requires structured prior QPI fields.
+
+### Ambiguous Low Context
+
+Round 04 cases:
+
+- `R04-BI-028`
+- `R04-BI-029`
+- `R04-BI-030`
+
+Post-patch behavior:
+
+- `R04-BI-028`: no-call
+- `R04-BI-029`: no-call
+- `R04-BI-030`: QPI selected
+
+Calibration issue:
+
+- Round 05 should decide when low-context language should stay no-call, when it should route to QPI as provisional, and whether selected QPI must explicitly mark low confidence / missing context.
+
+## 6. Patch Audit Lesson
+
+Round 04.1 had:
+
+- Targeted failures: 0.
+- Behavior changes recorded: 5.
+- One accepted collateral change: `R04-BI-022`.
+
+Round 05 should decide whether future selector patch rounds must include a before / after diff checker as a hard review artifact.

ccra_review_bundle/round-05_init_selector-calibration-policy/03_CANDIDATE_CALIBRATION_CASES.md

@@ -0,0 +1,196 @@
+# Candidate Calibration Cases
+
+Date: 2026-06-19
+
+## 1. Purpose
+
+This file groups candidate calibration material for Round 05 policy discussion.
+
+These are not regression additions and do not modify `selector/selector_calibration_inputs.json`.
+
+## 2. Candidate Groups
+
+### A. Governance / Responsibility / Consensus
+
+Candidate Round 04 cases:
+
+- `R04-BI-010`
+- `R04-BI-011`
+- `R04-BI-012`
+- `R04-BI-013`
+
+Current observed behavior:
+
+- All four are no-call after Round 04.1.
+
+Why they matter:
+
+- They test whether governance, responsibility, decision authority, consensus scarcity, and cross-role ambiguity should be QPI weak-positive signals.
+- They also test the overreach risk: not every organization-related sentence should become QPI.
+
+Decision owner:
+
+- Owner: decide desired product behavior.
+- CCRA: judge whether the behavior preserves QPI as front-routing rather than intervention.
+- Codex: prepare case excerpts and current selector behavior only.
+
+### B. Capacity / Resource / Path
+
+Candidate Round 04 cases:
+
+- `R04-BI-014`
+- `R04-BI-015`
+- `R04-BI-016`
+- `R04-BI-017`
+
+Current observed behavior:
+
+- `R04-BI-014`: no-call
+- `R04-BI-015`: no-call
+- `R04-BI-016`: QPI selected
+- `R04-BI-017`: no-call
+
+Existing calibration reference:
+
+- `selector_calibration_qpi_international_logistics_no_call_001` guards a logistics / execution no-call boundary paired with a capacity governance case.
+
+Why they matter:
+
+- They separate capacity/resource/path as execution constraints from capacity/resource/path as problem-definition evidence.
+
+Candidate subtypes:
+
+- `execution_constraint_no_call`
+- `path_uncertainty_qpi`
+- `hard_resource_constraint_qpi_or_no_call`
+- `responsibility_boundary_qpi`
+
+Decision owner:
+
+- Owner: decide desired product boundary.
+- CCRA: judge whether QPI is over-recalling capacity language.
+- Codex: map candidate cases to current selected / rejected behavior.
+
+### C. Likely Intellectual Archaeology
+
+Candidate Round 04 cases:
+
+- `R04-BI-025`
+- `R04-BI-026`
+- `R04-BI-027`
+- `R04-BI-038`
+
+Current observed behavior:
+
+- `R04-BI-025`: QPI + IA selected
+- `R04-BI-026`: QPI selected, IA rejected
+- `R04-BI-027`: QPI selected, IA rejected
+- `R04-BI-038`: QPI selected, IA rejected
+
+Existing calibration references:
+
+- `selector_calibration_ia_after_qpi_001`
+- `selector_calibration_ia_after_qpi_002`
+- `selector_calibration_ia_model_extraction_001`
+- `selector_calibration_ia_model_extraction_002`
+- `selector_calibration_pipeline_001`
+- `selector_calibration_pipeline_002`
+
+Why they matter:
+
+- They test whether natural-language depth requests should remain QPI-first or allow IA direct.
+- They also test whether explicit model extraction and deep-assumption language are enough to bypass QPI.
+
+Decision owner:
+
+- Owner: decide product expectation for direct IA entry.
+- CCRA: judge lifecycle and overuse risk for IA.
+- Codex: prepare evidence and no-call / QPI / IA current behavior.
+
+### D. QPI-After-QPI
+
+Candidate Round 04 case:
+
+- `R04-BI-025`
+
+Existing calibration references:
+
+- `selector_calibration_ia_after_qpi_001`
+- `selector_calibration_ia_after_qpi_002`
+- `selector_calibration_pipeline_002`
+
+Why it matters:
+
+- Natural-language "QPI already judged..." may be too weak to skip QPI.
+- Structured prior QPI fields may be needed before IA-only routing is safe.
+
+Candidate input protocol to discuss:
+
+```text
+prior_qpi_result:
+  classification
+  dominant_scarcity
+  evidence_gap
+  next_model_candidates
+  confidence_level
+```
+
+Decision owner:
+
+- Owner: decide whether such a protocol is desirable.
+- CCRA: judge whether it preserves QPI-before-IA governance.
+- Codex: do not implement the protocol unless later approved.
+
+### E. Ambiguous Low Context
+
+Candidate Round 04 cases:
+
+- `R04-BI-028`
+- `R04-BI-029`
+- `R04-BI-030`
+- `R04-BI-037`
+
+Current observed behavior:
+
+- `R04-BI-028`: no-call
+- `R04-BI-029`: no-call
+- `R04-BI-030`: QPI selected
+- `R04-BI-037`: no-call
+
+Existing calibration reference:
+
+- `selector_calibration_qpi_insufficient_context_001`
+
+Why they matter:
+
+- They test when the selector should ask for context, stay no-call, or route to provisional QPI.
+
+Decision owner:
+
+- Owner: decide acceptable behavior for short ambiguous user inputs.
+- CCRA: judge whether QPI should require explicit low-context / provisional output.
+- Codex: identify current no-call versus selected outcomes.
+
+### F. Patch Diff / Audit
+
+Candidate evidence:
+
+- `R04-BI-002`
+- `R04-BI-022`
+- `R04-BI-024`
+- `R04-BI-035`
+- `R04-BI-036`
+
+Why they matter:
+
+- They show that targeted cases can pass while non-target behavior changes still occur.
+
+Decision owner:
+
+- Owner: decide whether all non-target behavior changes require explicit accept / reject / defer.
+- CCRA: define review expectations for selector patch audits.
+- Codex: can later implement deterministic diff tooling only after approval.
+
+## 3. Candidate Status
+
+All entries above are candidates for policy discussion. None are promoted to regression or selector calibration JSON by this file.

ccra_review_bundle/round-05_init_selector-calibration-policy/04_CANDIDATE_REGRESSION_CASES.md

@@ -0,0 +1,132 @@
+# Candidate Regression Cases
+
+Date: 2026-06-19
+
+## 1. Purpose
+
+This file identifies possible regression candidates for later Owner / CCRA decision.
+
+It does not modify:
+
+- `tests/qpi.regression.json`
+- `tests/intellectual_archaeology.regression.json`
+- `tests/regression_cases.json`
+- `tests/regression_index.json`
+
+Regression should remain reserved for high-value guardrails, not every disputed Round 04 blind input.
+
+## 2. Already Covered By Regression
+
+Round 04.1 cases already represented in regression:
+
+| Source Case | Regression Case | Purpose |
+| --- | --- | --- |
+| `R04-BI-002` | `case_qpi_round04_translation_payload_no_call_001` | Translation payload must not trigger QPI. |
+| `R04-BI-024` | `case_ia_round04_do_not_enter_archaeology_001` | Explicit IA refusal must hard-exclude IA. |
+| `R04-BI-035` | `case_qpi_round04_depth_limited_specific_scarcity_001` | Depth-limited dominant-scarcity judgment should route to QPI. |
+| `R04-BI-036` | `case_qpi_round04_depth_limited_scarcity_set_001` | Depth-limited scarcity-set judgment should route to QPI. |
+| `R04-BI-022` | `case_qpi_round04_depth_limited_assumption_scarcity_001` | Accepted collateral QPI override; IA rejected. |
+
+Round 05 should not duplicate these unless Owner / CCRA decides a different policy boundary is needed.
+
+## 3. Possible New Regression Candidates
+
+### A. Governance / Responsibility / Consensus
+
+Candidate cases:
+
+- `R04-BI-010`
+- `R04-BI-013`
+
+Possible regression value:
+
+- Guard the chosen policy for responsibility ambiguity and decision-authority gaps.
+
+Do not add yet because:
+
+- Current behavior is no-call.
+- Owner / CCRA has not decided whether such cases should become QPI weak-positive signals.
+
+### B. Capacity / Resource / Path Split
+
+Candidate cases:
+
+- `R04-BI-014`
+- `R04-BI-016`
+- `R04-BI-017`
+
+Possible regression value:
+
+- Guard the distinction between execution constraints and QPI-relevant path/resource scarcity.
+
+Do not add yet because:
+
+- Round 05 must decide whether current behavior is desired.
+- Adding all capacity/resource/path cases would overfit the blind pool.
+
+### C. QPI-After-QPI / Prior QPI Result
+
+Candidate case:
+
+- `R04-BI-025`
+
+Possible regression value:
+
+- Guard whether natural-language "QPI already judged..." remains QPI+IA, or whether structured `prior_qpi_result` permits IA-only.
+
+Do not add yet because:
+
+- The repository has not defined a structured prior-QPI input protocol.
+- The current selector behavior is QPI + IA selected, not IA-only.
+
+### D. Direct IA Entry
+
+Candidate cases:
+
+- `R04-BI-027`
+- `R04-BI-038`
+- `R04-BI-019`
+
+Possible regression value:
+
+- Guard the eventual decision on QPI-first versus direct IA for deep mechanism / reusable structure inputs.
+
+Do not add yet because:
+
+- Direct IA would be a policy change.
+- IA remains draft / B / pending and should not become default heavy-depth routing without explicit approval.
+
+### E. Ambiguous Low Context
+
+Candidate cases:
+
+- `R04-BI-028`
+- `R04-BI-029`
+- `R04-BI-030`
+
+Possible regression value:
+
+- Guard no-call or provisional-QPI behavior for low-context inputs.
+
+Do not add yet because:
+
+- Current behavior is split.
+- Round 05 must decide whether `R04-BI-030` should remain QPI selected or become no-call / clarification.
+
+## 4. Regression Selection Standard
+
+Only promote a candidate to regression if it meets at least one condition:
+
+- It protects a high-risk boundary that is likely to regress.
+- It distinguishes QPI from IA or no-call in a way that product behavior depends on.
+- It prevents a known overreach, such as organization-input over-QPI, IA over-selection, or direct-execution over-analysis.
+- It records an Owner / CCRA decision that should remain stable across future patches.
+
+Do not promote a case only because it appeared in Round 04.
+
+## 5. Suggested Decision Flow
+
+1. Owner / CCRA answers the Round 05 policy questions.
+2. Codex maps accepted policy decisions to a minimal candidate list.
+3. Owner / CCRA approves which candidates become regression.
+4. Only then should Codex modify regression JSON in a later round.

ccra_review_bundle/round-05_init_selector-calibration-policy/05_CCRA_REVIEW_QUESTIONS_ROUND05.md

@@ -0,0 +1,64 @@
+# CCRA Review Questions Round 05
+
+Date: 2026-06-19
+
+## 1. Purpose
+
+This file lists the questions that must be answered before any Round 05 selector patch.
+
+It separates:
+
+- Owner product judgment.
+- CCRA model-governance judgment.
+- Codex mechanical preparation.
+
+Codex should not answer the policy questions by editing selector rules.
+
+## 2. Review Questions
+
+| # | Question | Primary Judgment | Codex Role |
+| --- | --- | --- | --- |
+| 1 | Should governance / responsibility / consensus be a weak positive QPI signal, or only trigger QPI when scarcity, conflict, or responsibility ambiguity is present? | Owner + CCRA | Provide Round 04 examples and current behavior. |
+| 2 | Should consensus / order / uncertainty scarcity become an explicit Issue-type QPI recall reason? | Owner + CCRA | Map to existing QPI contract and examples. |
+| 3 | How should we prevent all organization inputs from becoming QPI? | Owner + CCRA | Identify no-call / low-priority traps. |
+| 4 | Should capacity / resource / path remain no-call when they are only execution constraints? | Owner | Provide examples such as logistics / direct execution boundaries. |
+| 5 | Should capacity / resource / path enter QPI when they alter path choice, responsibility boundary, or problem nature? | Owner + CCRA | Group Round 04 capacity/path cases by current behavior. |
+| 6 | Should `execution_constraint_no_call` become a calibration category? | CCRA + Owner | Draft candidate naming only. |
+| 7 | Should default routing remain QPI-before-IA? | CCRA + Owner | Show current IA gate and existing calibration cases. |
+| 8 | Which natural-language expressions are strong enough for IA direct? | Owner + CCRA | Provide likely IA candidates without changing rules. |
+| 9 | Must IA direct require enough material plus explicit request for deep assumptions, core mechanism, or bottom structure? | CCRA | Map to IA depth gate and no-call risks. |
+| 10 | Should `likely_intellectual_archaeology` be treated only as a candidate signal rather than a selected condition? | CCRA + Owner | Show Round 04 likely IA outcomes. |
+| 11 | Must "QPI already judged..." include structured QPI output before selector can skip QPI? | Owner + CCRA | Draft possible `prior_qpi_result` fields if requested. |
+| 12 | If the user only claims QPI already judged in natural language, should selector still perform lightweight QPI review? | Owner | Provide current `R04-BI-025` behavior. |
+| 13 | Should this repo define a `prior_qpi_result` or `qpi_context_provided` input protocol? | Owner + CCRA | Do not implement until approved. |
+| 14 | Should `R04-BI-022` remain regression, enter calibration, or both? | Owner + CCRA | Report current state: already regression. |
+| 15 | Which Round 04 blind cases are only calibration material and should not become regression? | CCRA + Owner | Provide candidate list by category. |
+| 16 | Should regression remain limited to high-risk guardrails rather than all disputed cases? | CCRA + Owner | Preserve current non-goal. |
+| 17 | Should before / after diff checker be required for all selector patches from Round 05.1 onward? | Owner + CCRA | Prepare mechanism proposal only. |
+| 18 | Must the diff checker list selected / rejected models, scores, no-call status, reasons, and penalties? | CCRA + Codex | Codex can later implement deterministic output if approved. |
+| 19 | Must every non-target behavior change be explicitly accepted, rejected, or deferred by Owner? | Owner + CCRA | Preserve accepted collateral change precedent from `R04-BI-022`. |
+
+## 3. Web CCRA Upload Candidates
+
+If Web CCRA needs exact evidence, upload or excerpt:
+
+- `selector/round04_blind_inputs.json`
+- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
+- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md`
+- `selector/selector_rules.json`
+- `selector/selector_calibration_inputs.json`
+- `tests/qpi.regression.json`
+- `tests/intellectual_archaeology.regression.json`
+- `tests/regression_cases.json`
+
+Do not ask Web CCRA to decide from this question list alone if the decision depends on exact case text.
+
+## 4. Pre-Patch Gate
+
+Before any future `Round 05.1` patch, require:
+
+- Owner / CCRA answers or defers the relevant questions above.
+- Codex records which policy decisions are accepted.
+- Candidate calibration and regression cases are narrowed.
+- A before / after diff artifact is planned.
+- Non-goals are restated.

ccra_review_bundle/round-05_init_selector-calibration-policy/06_ROUND05_POLICY_DECISION_MATRIX.md

@@ -0,0 +1,75 @@
+# Round 05 Policy Decision Matrix
+
+Date: 2026-06-19
+
+## 1. Purpose
+
+This matrix turns the 19 Round 05 review questions into a decision record that Codex can execute later.
+
+It is not a selector patch. It does not modify:
+
+- `selector/selector_rules.json`
+- `selector/selector_calibration_inputs.json`
+- `tests/qpi.regression.json`
+- `tests/intellectual_archaeology.regression.json`
+- `tests/regression_cases.json`
+- model cards
+- model specs
+
+## 2. Decision Field Rules
+
+Decision fields use only:
+
+```text
+accept / reject / defer
+```
+
+Initial values were set to `defer` before Owner / CCRA decisions were recorded.
+
+Round 05 policy review has now recorded Owner / CCRA acceptance for Q01-Q19. This acceptance authorizes policy planning only; it does not authorize selector rule, calibration JSON, regression JSON, model card, or model spec edits.
+
+`recommended_policy` is a proposal for discussion, not an accepted policy.
+
+`exact_case_text_required` means exact Round 04 case text, selector output, or regression/calibration input text should be reviewed before final decision.
+
+## 3. Matrix
+
+| question_id | recommended_policy | owner_decision | ccra_decision | patch_implication | calibration_implication | regression_implication | exact_case_text_required |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Q01 | Treat governance / responsibility / consensus as QPI weak-positive only when scarcity, conflict, responsibility ambiguity, or problem-definition intent is present. | accept | accept | If accepted, later patch may add scoped positive signals; if rejected, keep current no-call bias. | Add calibration split between plain organization facts and responsibility/consensus scarcity. | Possible guardrail from `R04-BI-010` or `R04-BI-013` only after policy approval. | true |
+| Q02 | Recognize consensus / order / uncertainty scarcity as an Issue-type QPI recall reason, while requiring enough context to avoid generic organization recall. | accept | accept | If accepted, later patch may add explicit Issue-type QPI trigger conditions. | Add calibration for consensus/order/uncertainty scarcity versus generic governance text. | Candidate regression only for the clearest accepted Issue-type boundary. | true |
+| Q03 | Keep an explicit anti-overreach rule: organization or governance wording alone is not enough for QPI. | accept | accept | If accepted, later patch should pair any governance recall expansion with negative or low-priority controls. | Add overreach traps for plain organization facts, role descriptions, and generic governance nouns. | Regression should protect overreach traps only if future patch expands governance recall. | true |
+| Q04 | Keep capacity / resource / path as no-call when they are only execution constraints. | accept | accept | If accepted, later patch should preserve or add execution-constraint no-call gates. | Add `execution_constraint_no_call` category candidates. | Candidate no-call regression only for high-risk false positives, not all logistics cases. | true |
+| Q05 | Route capacity / resource / path to QPI when they change path choice, responsibility boundary, or problem nature. | accept | accept | If accepted, later patch may add scoped path/resource QPI triggers. | Split capacity/resource/path calibration into execution constraint, path uncertainty, hard resource constraint, and responsibility boundary. | Candidate regression from `R04-BI-016` or another accepted high-risk boundary. | true |
+| Q06 | Add `execution_constraint_no_call` as a calibration category name, not as a rule change yet. | accept | accept | No selector patch by itself; category may inform later fixtures or docs. | Create candidate calibration rows after Owner / CCRA approves the category. | No direct regression effect unless a specific trap is approved. | false |
+| Q07 | Keep default QPI-before-IA unless a clearly defined direct-IA exception is approved. | accept | accept | If accepted, preserve current QPI-before-IA gate in future patches. | Continue using pipeline calibration cases for QPI-before-IA and IA-after-QPI. | Existing IA/QPI pipeline regression remains protected; new regression only if exception is defined. | false |
+| Q08 | Define direct IA eligibility narrowly: explicit input intent should clearly request deep assumptions, core mechanism, reusable structure, or bottom-structure analysis. | accept | accept | If accepted, later patch may add direct-IA exception signals with safeguards. | Add direct-IA candidate calibration cases from likely IA and model-extraction pools. | Candidate regression only after exact direct-IA wording is approved. | true |
+| Q09 | Require IA direct to satisfy both material sufficiency and explicit deep-analysis intent. | accept | accept | If accepted, later patch must avoid IA selection on thin or direct-execution inputs. | Add sufficiency/intent calibration notes for IA direct candidates. | Possible IA no-call or QPI-first regression if IA over-selection risk is high. | true |
+| Q10 | Treat `likely_intellectual_archaeology` as a candidate review label, not an automatic selected condition. | accept | accept | If accepted, later patch should not route solely on the blind-pool category concept. | Preserve likely-IA cases as calibration candidates requiring exact text review. | No direct regression effect unless a specific likely-IA boundary is approved. | true |
+| Q11 | Require structured prior QPI output before selector can skip QPI. | accept | accept | If accepted, later patch may support IA-only routing only when prior QPI fields are present. | Add calibration cases for natural-language prior-QPI claim versus structured `prior_qpi_result`. | Candidate regression from `R04-BI-025` or a new structured prior-QPI case after protocol approval. | true |
+| Q12 | If the user only claims QPI already judged in natural language, keep lightweight QPI review rather than IA-only. | accept | accept | If accepted, current QPI+IA behavior for `R04-BI-025` may remain acceptable. | Add calibration note that natural-language prior-QPI claim is not enough to skip QPI. | Possible regression for natural-language prior-QPI claim if this becomes a stable boundary. | true |
+| Q13 | Define a `prior_qpi_result` / `qpi_context_provided` input protocol only as a product contract after approval. | accept | accept | If accepted, later work should create protocol docs before selector patch. | Add candidate calibration schema fields after protocol definition. | No regression until a concrete protocol and fixture are approved. | false |
+| Q14 | Keep `R04-BI-022` in regression and also tag it as calibration material for depth-limited QPI override with IA rejection. | accept | accept | No immediate selector patch; current behavior remains documented as accepted collateral in Round 04.1 closeout. | Add or tag calibration material for depth-limited QPI override with IA rejection if calibration JSON updates are separately approved. | Already represented by `case_qpi_round04_depth_limited_assumption_scarcity_001`; avoid duplicate regression. | true |
+| Q15 | Treat most Round 04 blind cases as calibration material unless Owner / CCRA marks a high-risk guardrail. | accept | accept | No patch implication until candidate cases are narrowed. | Use Round 04 cases to populate candidate calibration groups by policy topic. | Prevent full blind pool conversion into regression. | true |
+| Q16 | Keep regression limited to high-risk guardrails, not every disputed case. | accept | accept | No selector patch by itself; constrains later patch closeout. | Calibration can be broader than regression. | Regression additions should require explicit Owner / CCRA approval and a stability rationale. | false |
+| Q17 | Require before / after diff checker for every selector patch from Round 05.1 onward. | accept | accept | If accepted, Round 05.1 patch plan must include deterministic diff output before closeout. | Calibration reports should cite non-target behavior changes. | Regression impact depends on whether collateral changes reveal new guardrails. | false |
+| Q18 | Diff checker should list selected models, rejected models, scores, no-call status, reasons, and penalties. | accept | accept | If accepted, later tooling/report patch should expose these fields for every changed case. | Calibration review can compare behavior dimensions, not only selected model IDs. | Regression candidates can be justified by specific changed behavior fields. | false |
+| Q19 | Require every non-target behavior change to be accepted, rejected, or deferred by Owner / CCRA. | accept | accept | If accepted, future patch closeout must include non-target change disposition. | Calibration should record collateral behavior changes even when targets pass. | Collateral changes may become regression only after explicit approval. | false |
+
+## 4. How Codex Should Use This Matrix Later
+
+Before any `Round 05.1` patch:
+
+1. Update `owner_decision` and `ccra_decision` for the relevant rows.
+2. Keep unanswered rows as `defer`.
+3. Patch only rows where both decision paths are sufficient for implementation.
+4. Convert `patch_implication` into a scoped implementation plan.
+5. Convert `calibration_implication` into explicit calibration changes only if approved.
+6. Convert `regression_implication` into regression changes only if approved.
+7. Preserve non-goals and lifecycle status boundaries.
+
+## 5. Current Decision State
+
+Round 05 policy decisions Q01-Q19 are recorded as Owner accepted and CCRA accepted.
+
+This closes the policy-decision recording step. It does not authorize direct selector patch execution. Round 05.1 may proceed only as patch planning until Owner explicitly approves implementation.

ccra_review_bundle/round-05_init_selector-calibration-policy/07_ROUND05_1_PATCH_PLANNING.md

@@ -0,0 +1,243 @@
+# Round 05.1 Patch Planning
+
+Date: 2026-06-19
+
+## 1. Purpose
+
+This document prepares Round 05.1 patch planning after the Round 05 selector calibration policy decisions were accepted.
+
+Round 05.1 means the first implementation-planning round after Round 05 policy review. It follows the existing project naming pattern where `.1` marks a follow-up repair or implementation round after the base round.
+
+This is not patch execution. It does not modify:
+
+- `selector/selector_rules.json`
+- `selector/selector_calibration_inputs.json`
+- `tests/qpi.regression.json`
+- `tests/intellectual_archaeology.regression.json`
+- `tests/regression_cases.json`
+- model cards
+- model specs
+
+Selector patch execution must wait for explicit Owner approval after this planning file is reviewed.
+
+## 2. Accepted Policy Decisions To Carry Forward
+
+The decision matrix in `06_ROUND05_POLICY_DECISION_MATRIX.md` records Q01-Q19 as Owner accepted and CCRA accepted.
+
+Round 05.1 planning should carry forward these policies:
+
+| policy_area | accepted_policy |
+| --- | --- |
+| Governance / responsibility / consensus | Treat as conditional weak-positive QPI signals only when scarcity, conflict, responsibility ambiguity, or problem-definition intent is present. |
+| Issue-type scarcity | Consensus, order, and uncertainty scarcity may be QPI recall reasons when enough context is present. |
+| Anti-overreach | Organization or governance wording alone is not enough for QPI. |
+| Capacity / resource / path no-call | Keep no-call when these terms only express execution constraints. |
+| Capacity / resource / path QPI | Route to QPI when they change path choice, responsibility boundary, or problem nature. |
+| Execution constraints | Add `execution_constraint_no_call` as a calibration category before any rule-level change. |
+| IA routing default | Preserve QPI-before-IA as the default. |
+| IA direct exception | Allow only narrow direct IA exceptions when explicit input intent requests deep assumptions, core mechanism, reusable structure, or bottom-structure analysis and material is sufficient. |
+| likely IA label | Treat `likely_intellectual_archaeology` as a review label, not an automatic selected condition. |
+| Prior QPI claim | Natural-language "QPI already judged" is not enough to skip QPI. |
+| Structured prior QPI | Define `prior_qpi_result` / `qpi_context_provided` as a product contract before any selector support. |
+| R04-BI-022 | Keep regression coverage and also tag as calibration material for depth-limited QPI override with IA rejection. |
+| Regression scope | Keep regression limited to high-risk guardrails, not all disputed Round 04 cases. |
+| Diff gate | Require before / after behavior diff for every selector patch from Round 05.1 onward. |
+| Non-target changes | Every non-target behavior change must be accepted, rejected, or deferred by Owner / CCRA. |
+
+## 3. Affected Case List
+
+### 3.1 Patch Planning / Calibration Candidates
+
+These cases may inform Round 05.1 calibration and selector patch planning:
+
+| case_id | planning_topic | expected planning use |
+| --- | --- | --- |
+| R04-BI-010 | governance / responsibility | Conditional QPI weak-positive candidate. |
+| R04-BI-011 | governance / conflict | Conditional QPI weak-positive candidate. |
+| R04-BI-012 | consensus / waiting behavior | Conditional QPI weak-positive candidate. |
+| R04-BI-013 | decision authority gap | Conditional QPI weak-positive candidate. |
+| R04-BI-014 | capacity constraint | Execution-constraint no-call candidate. |
+| R04-BI-015 | minimum path | Capacity / path boundary candidate. |
+| R04-BI-016 | permission / approval friction | Path or responsibility-boundary QPI candidate. |
+| R04-BI-017 | fragmented time / execution continuity | Capacity/resource/path boundary candidate. |
+| R04-BI-025 | natural-language prior QPI claim | Keep lightweight QPI review unless structured prior QPI output exists. |
+| R04-BI-026 | likely IA | Direct IA exception candidate, default QPI-first. |
+| R04-BI-027 | likely IA | Direct IA exception candidate, default QPI-first. |
+| R04-BI-038 | likely IA | Direct IA exception candidate, default QPI-first. |
+
+### 3.2 Guardrail / No-Call Protection Candidates
+
+These cases should protect against over-selection if Round 05.1 expands recall:
+
+| case_id | guardrail_topic | expected planning use |
+| --- | --- | --- |
+| R04-BI-028 | ambiguous low context | Prefer no-call or clarification. |
+| R04-BI-029 | ambiguous low context | Prefer no-call or clarification. |
+| R04-BI-030 | ambiguous low context | Avoid over-QPI from vague stuckness alone. |
+| R04-BI-031 | direct how-to / tool use | Preserve no-call for direct execution support. |
+| R04-BI-032 | direct conversion / formatting | Preserve no-call for direct execution support. |
+| R04-BI-033 | word meaning / simple judgment | Preserve no-call for lightweight semantic questions. |
+
+### 3.3 Do Not Reopen In Round 05.1 Planning
+
+These cases are already covered by Round 04.1 closeout or regression and should not be reopened as new Round 05.1 targets:
+
+| case_id | reason |
+| --- | --- |
+| R04-BI-002 | Covered by Round 04.1 target fix and regression. |
+| R04-BI-022 | Accepted collateral behavior change; keep regression and calibration tag. |
+| R04-BI-024 | Covered by Round 04.1 target fix and regression. |
+| R04-BI-035 | Covered by Round 04.1 target fix and regression. |
+| R04-BI-036 | Covered by Round 04.1 target fix and regression. |
+
+## 4. Proposed Calibration Additions
+
+These are planning targets only. Do not edit `selector/selector_calibration_inputs.json` until Owner explicitly approves Round 05.1 implementation.
+
+| proposed_category | candidate_cases | purpose |
+| --- | --- | --- |
+| governance_responsibility_consensus_qpi | R04-BI-010, R04-BI-011, R04-BI-012, R04-BI-013 | Separate conditional QPI recall from generic organization wording. |
+| execution_constraint_no_call | R04-BI-014, selected existing logistics/no-call references | Protect direct execution constraints from QPI over-selection. |
+| capacity_resource_path_boundary | R04-BI-015, R04-BI-016, R04-BI-017 | Separate path uncertainty, hard resource constraint, and responsibility-boundary cases. |
+| natural_language_prior_qpi_claim | R04-BI-025 | Preserve lightweight QPI review when prior QPI output is not structured. |
+| direct_ia_exception_candidate | R04-BI-026, R04-BI-027, R04-BI-038 | Review narrow direct IA eligibility without replacing QPI-first default. |
+| ambiguous_low_context_no_call | R04-BI-028, R04-BI-029, R04-BI-030 | Prevent vague low-context inputs from becoming broad QPI recall. |
+| direct_execution_no_call | R04-BI-031, R04-BI-032, R04-BI-033 | Preserve no-call behavior for how-to, conversion, formatting, and simple meaning tasks. |
+| depth_limited_qpi_override_ia_rejected | R04-BI-022 | Use accepted collateral behavior as calibration anchor without duplicate regression. |
+
+## 5. Proposed Regression Additions
+
+Default recommendation: do not add new regression cases at the start of Round 05.1.
+
+Regression additions should happen only after selector patch scope is approved and a specific case is judged to be a high-risk guardrail.
+
+Possible later candidates:
+
+| candidate_case | possible_regression_purpose | condition_before_adding |
+| --- | --- | --- |
+| R04-BI-010 or R04-BI-013 | Governance / decision-authority QPI boundary. | Add only if the selector patch expands governance recall. |
+| R04-BI-014 | Execution-constraint no-call trap. | Add only if false-positive risk rises after patch. |
+| R04-BI-016 | Path or responsibility-boundary QPI. | Add only if chosen as the canonical capacity/resource/path QPI boundary. |
+| R04-BI-025 | Natural-language prior QPI claim should not skip QPI. | Add only if prior-QPI handling is implemented. |
+| R04-BI-027 or R04-BI-038 | Direct IA exception or QPI-first guardrail. | Add only after direct IA exception policy becomes concrete. |
+| R04-BI-028 or R04-BI-030 | Ambiguous low-context no-call protection. | Add only if recall expansion increases low-context false positives. |
+
+## 6. Selector Patch Scope For Later Approval
+
+If Owner approves Round 05.1 implementation, selector changes should be scoped to:
+
+1. Add conditional weak-positive QPI signals for governance / responsibility / consensus scarcity.
+2. Add anti-overreach checks so organization wording alone does not trigger QPI.
+3. Preserve no-call behavior for execution constraints.
+4. Add narrow QPI triggers for path choice, responsibility boundary, and problem-nature changes.
+5. Preserve QPI-before-IA as default.
+6. Treat direct IA as an exception requiring explicit deep-analysis intent and material sufficiency.
+7. Keep natural-language prior QPI claims under lightweight QPI review.
+8. Do not implement structured `prior_qpi_result` support until a product contract exists.
+
+Out of scope:
+
+- LLM selector
+- third model
+- RAG / vector database
+- frontend / backend
+- model lifecycle upgrade
+- full Round 04 blind pool regression conversion
+- broad QPI recall for all organization, governance, capacity, resource, or path wording
+
+## 7. Before / After Diff Checker Output Contract
+
+Round 05.1 patch execution must include deterministic before / after behavior diff.
+
+Minimum output fields per changed case:
+
+```json
+{
+  "case_id": "R04-BI-010",
+  "targeted": true,
+  "before": {
+    "selected_model_ids": [],
+    "rejected_model_ids": [],
+    "no_call": true,
+    "scores": {},
+    "reasons": [],
+    "penalties": []
+  },
+  "after": {
+    "selected_model_ids": ["qpi"],
+    "rejected_model_ids": [],
+    "no_call": false,
+    "scores": {
+      "qpi": 0
+    },
+    "reasons": [],
+    "penalties": []
+  },
+  "changed_fields": [
+    "selected_model_ids",
+    "no_call",
+    "scores",
+    "reasons",
+    "penalties"
+  ],
+  "disposition_required": true
+}
+```
+
+The actual implementation may use the selector's existing output schema, but it must expose enough information to compare:
+
+- selected models
+- rejected models
+- scores
+- no-call status
+- reasons
+- penalties
+- target versus non-target classification
+
+## 8. Non-Target Behavior Change Disposition
+
+Every non-target behavior change in Round 05.1 must be listed and assigned one disposition:
+
+```text
+accept / reject / defer
+```
+
+Required fields:
+
+| field | meaning |
+| --- | --- |
+| case_id | The changed case. |
+| changed_fields | Behavior dimensions that changed. |
+| expected_by_policy | Whether the change follows an accepted Round 05 policy. |
+| owner_disposition | Owner decision: accept / reject / defer. |
+| ccra_disposition | CCRA decision: accept / reject / defer. |
+| follow_up | Regression candidate, calibration note, rollback requirement, or no action. |
+
+Selector patch closeout must not report only targeted PASS cases.
+
+## 9. Round 05.1 Implementation Gate
+
+Before Codex may edit selector, calibration, or regression files, Owner should explicitly approve:
+
+1. The Round 05.1 implementation target cases.
+2. The calibration additions.
+3. Any regression additions.
+4. The selector patch scope.
+5. The before / after diff checker output contract.
+6. The non-target behavior change disposition protocol.
+
+Until that approval exists, this document is the stopping point.
+
+## 10. Validation Required After Future Patch
+
+If Round 05.1 implementation is later approved, run at minimum:
+
+```powershell
+python scripts\rebuild_indexes.py --check
+python scripts\validate_model_library.py
+python scripts\run_selector_regression.py
+python scripts\check_card_contract.py
+python scripts\check_model_card_sync.py
+```
+
+If selector behavior changes, also run the Round 05.1 before / after diff checker and include both target and non-target behavior changes in the closeout report.

docs/DATA_CONTRACT.md

@@ -141,3 +141,92 @@ Engineering validation does not imply content stability.
 Before content stabilization review, every core model should have at least 15 regression cases and field-level evidence coverage.
 
 Source excerpts must distinguish exact quotes from condensed or paraphrased excerpts with `quote_status`.
+
+## 10. Local CCRA Review Run Contract
+
+Local CCRA review runs are process records, not model assets.
+
+They live under:
+
+```text
+local_ccra_reviews/<public-round>/<local-pass>/
+```
+
+Each local pass should contain:
+
+- `run-notes.md`
+- `review-metadata.json`
+- `gate-manifest.yaml`
+- `lifecycle-guard-config.yaml`
+- `agent-invocation-packet.md`
+- `prompt-to-send.md`
+- `turn-prompts/`
+- `review-context.md`
+- `review-file-manifest.json`
+- `helper-outputs/`
+- `04_LOCAL_CCRA_REVIEW_REPORT.md`
+- `next-review-requirements.md`
+- `returned-output.md`
+- `findings-confirmation.md`
+- `owner-decision.md`
+
+`review-metadata.json`, `review-file-manifest.json`, and helper JSON outputs are machine-readable process records.
+
+Markdown files in the run directory are human-readable process records.
+
+`04_LOCAL_CCRA_REVIEW_REPORT.md` is the `review_turn` judgment output.
+
+`next-review-requirements.md` is the same-child `planning_turn` output and should not be treated as Owner approval or proof that a patch worked.
+
+For Local CCRA v0.1.2 and later, `review-metadata.json` or `agent-invocation-packet.md` must declare:
+
+- `bundle_audit_profile`: `ccra_mindscape_review_bundle`, `generic`, or `not_applicable`.
+- `gate_execution_mode`: `dry_run`, `run`, `owner_waived`, or `not_applicable`.
+- `routing_diff_policy`: `required`, `skipped_no_after_evidence`, `manual_equivalent_required`, or `not_applicable`.
+- `lifecycle_scan_scope`: `current_review_bundle`, `changed_files`, `knowledge_assets`, `model_library_state`, or `whole_repo`.
+
+`returned-output.md` should include the compact Owner-facing summary defined by CCPE v0.1.2, including evidence limitations for the four fields above.
+
+`findings-confirmation.md` is a Chinese Owner-facing decision aid written by the Codex main session after Local CCRA outputs exist. It should extract only core confirmation items, proposed decision states, repair scope, impact, and evidence paths. It must not replace the full Local CCRA report or invent findings that are not grounded in `04_LOCAL_CCRA_REVIEW_REPORT.md`, `next-review-requirements.md`, or `returned-output.md`.
+
+Allowed decision states in `findings-confirmation.md` and `owner-decision.md` are:
+
+- `accept_for_codex_fix`
+- `reject`
+- `defer_to_future_round`
+- `escalate_to_web_ccra`
+- `owner_clarification_required`
+- `accept_as_known_limit`
+
+Codex may implement only findings recorded as `accept_for_codex_fix` in `owner-decision.md`.
+
+Local CCRA review records must not become source of truth for model status, selector behavior, regression cases, or source evidence. Accepted actions must be applied back to the canonical project files and validated there.
+
+Formal Web CCRA upload bundles exclude the Local CCRA report by default unless the owner explicitly asks to include it.
+
+## 11. Round Conductor Process Records
+
+Round automation process records are not model assets.
+
+Round charters and conductor summaries should live under `reports/` and should reference the relevant Local CCRA pass directories rather than copying reviewer outputs wholesale.
+
+Recommended round charter filename:
+
+```text
+reports/RoundNN_round_conductor_charter_YYYY-MM-DD.md
+```
+
+Round Conductor records may describe:
+
+- public round label;
+- Owner / Web CCRA guidance source;
+- in-scope files or asset areas;
+- non-goals;
+- Local CCRA pass paths;
+- Owner decision gates;
+- accepted repair items;
+- deferred or escalated items;
+- validation and before/after behavior evidence;
+- Web bundle readiness.
+
+Round Conductor records must not override canonical project files. If a finding changes model state, selector behavior, regression cases, model cards, or evidence records, that change must be applied to the canonical file and validated there.

docs/DECISIONS.md

@@ -172,7 +172,7 @@ Reason:
 
 Round 03.1 fixed QPI default over-selection, but GPT review found that explicit Intellectual Archaeology refusal phrases such as `先不要思想考古` could still lose to positive IA signals and QPI-completed bonuses.
 
-A user instruction that names a model and refuses it should not be represented as a normal score penalty. It must hard-exclude that model unless a later owner-approved rule defines an explicit reversal phrase.
+A user instruction that names a model and refuses it should not be represented as a normal score penalty. It must hard-exclude that model unless a later Owner-confirmed rule defines an explicit reversal phrase.
 
 The current Round 03.2 implementation keeps this scoped:
 
@@ -247,3 +247,147 @@ Closeout:
 - IA remains rejected for `R04-BI-022`.
 - `R04-BI-022` is added to selector regression as a QPI gate / IA anti-recall trap.
 - Closing Round 04.1 does not upgrade either model lifecycle status.
+
+## Decision 018: Keep Local CCRA review runs inside this project
+
+Status: Accepted
+
+Reason:
+
+The first Local CCRA version serves only `the-mindscape-of-bro-tsong`.
+
+Creating a separate reviewer project would add synchronization cost before there is a cross-project review workload. The useful separation is runtime isolation, not directory isolation.
+
+This repository therefore records Local CCRA review runs under:
+
+```text
+local_ccra_reviews/<public-round>/<local-pass>/
+```
+
+The public round label follows Owner / Web CCRA round versions such as `round-05`, `round-04.1`, or `round-03.2a`. The local pass number records repeated internal review passes, such as `01/` and `02/`.
+
+Local CCRA output is formal local first review, but it does not replace Owner judgment or Web CCRA judgment at key product and lifecycle gates.
+
+Formal Web CCRA bundles under `ccra_review_bundle/` exclude `04_LOCAL_CCRA_REVIEW_REPORT.md` by default. The local report is included only when the owner explicitly asks Web CCRA to review local findings.
+
+## Decision 019: Route Local CCRA Agent Runtime and companion capability classification to CCPE first
+
+Status: Accepted
+
+Reason:
+
+Local CCRA requires a real child review session, runtime session continuation, a reviewer role contract, review rubric, lifecycle guard policy, and file-first invocation protocol.
+
+These are CCPE responsibilities, not product-local implementation details and not automatically `skills-vault` automation.
+
+This repository will request a `ccra-local-reviewer` Agent Spec and Runtime protocol from `ccpe-system`. Companion capabilities such as routing diff audit, review bundle audit, lifecycle guard scan, round initialization context building, and regression gate running should be classified by CCPE first.
+
+Only capabilities that are abstracted into reusable deterministic operations should be routed to `skills-vault`. Reusable Skill names should describe the generic operation, as with `bundle-zip`, rather than this project's review context.
+
+## Decision 020: Treat Local CCRA v0.1.1 as usable for formal local first review with non-blocking Patch 2 hardening
+
+Status: Accepted
+
+Reason:
+
+Round 04 Local CCRA `pilot-02` tested CCPE Patch 1 with a real child session and the same historical Round 04 materials.
+
+The same child session completed both required turns:
+
+- `review_turn`: produced `local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md`.
+- `planning_turn`: produced `local_ccra_reviews/round-04/pilot-02/next-review-requirements.md`.
+
+The three-way comparison against Web CCRA baseline and `pilot-01` showed that Patch 1 fixed the main Local CCRA gap: the reviewer now combines Web-style issue mechanism diagnosis with local full-file audit.
+
+Decision:
+
+- Local CCRA v0.1.1 can be used as this project's formal local first-review lane after Owner and Web CCRA define the next round's work.
+- It does not replace Owner judgment, Web CCRA final review, or lifecycle authority.
+- Patch 2 is still needed as runtime/helper hardening, but it is non-blocking if Patch 1 behavior remains intact.
+- A third historical pilot is not required unless CCPE changes mechanism diagnosis, patch scope judgment, same-child-session continuation, mandatory knowledge-base use, or authority boundaries.
+- Full Round-level automation is a separate workflow/orchestrator design problem and should not be mixed into the `ccra-local-reviewer` reviewer contract.
+
+Patch 2 should focus on:
+
+- CCRA-aware review bundle audit profile.
+- Explicit gate-runner `dry_run / run / owner_waived / not_applicable` policy.
+- Mandatory routing behavior diff when before/after patch evidence exists.
+- Scoped lifecycle/status scan and triage.
+- Short Owner-facing `returned-output.md` summary.
+
+## Decision 021: Adopt Local CCRA v0.1.2 helper/runtime policy contract
+
+Status: Accepted
+
+Reason:
+
+CCPE completed Patch 2 and advanced `ccra-local-reviewer` / `ccra-local-review` to v0.1.2.
+
+Patch 2 did not change the core reviewer behavior accepted after `pilot-02`:
+
+- issue mechanism diagnosis;
+- patch scope judgment;
+- same-child `review_turn` and `planning_turn`;
+- mandatory `knowledge_assets/` knowledge base;
+- Owner / Web CCRA / lifecycle authority boundaries.
+
+It hardens the local runtime contract around helper reliability and return shape.
+
+Decision:
+
+- Future Local CCRA runs should follow CCPE v0.1.2.
+- `review-metadata.json` or `agent-invocation-packet.md` should declare `bundle_audit_profile`, `gate_execution_mode`, `routing_diff_policy`, and `lifecycle_scan_scope`.
+- `returned-output.md` should contain the compact Owner-facing summary expected by v0.1.2.
+- A third historical pilot is not required for this patch because the core reviewer behavior did not change.
+- The next Owner / Web CCRA-defined Local CCRA run should serve as live validation for v0.1.2.
+
+The historical `pilot-01` and `pilot-02` records remain unchanged because they preserve the actual v0.1.1-era test evidence.
+
+## Decision 022: Add a project-local Round Conductor protocol before Round 05
+
+Status: Owner-agreed for Round 05 trial
+
+Reason:
+
+The project needs to reduce manual review-loop labor before scaling from two model assets to a much larger model library.
+
+Local CCRA v0.1.2 is ready for formal local first review with conditions, but the Local CCRA reviewer contract intentionally does not define full Round-level automation or authorize repairs.
+
+Decision:
+
+- Add `docs/ROUND_AUTOMATION_PROTOCOL.md` as the project-local Round Conductor protocol.
+- Use Round automation v0.1 for Local CCRA orchestration, helper execution, real child-session submission, and Chinese `findings-confirmation.md` extraction.
+- Use Round automation v0.2 after Owner decision to let Codex repair only findings marked `accept_for_codex_fix`.
+- Require `owner-decision.md` before any repair starts.
+- Keep `ccra-local-reviewer` read-only; the main Codex session remains the implementer after Owner decision.
+- Do not create a generic reusable Skill yet. Reusable automation should be extracted only after repeated project use proves a deterministic cross-project operation.
+- Keep formal Web CCRA bundle rules unchanged: exclude `04_LOCAL_CCRA_REVIEW_REPORT.md` by default and include it only when Owner explicitly asks Web CCRA to review local findings.
+
+The initial Round 05 use should validate whether the protocol reduces transfer work without weakening Owner / Web CCRA authority boundaries.
+
+## Decision 023: Execute Round 05.1 as a scoped selector calibration patch
+
+Status: Owner-authorized scoped implementation
+
+Reason:
+
+Round 05 resolved selector calibration policy before changing rules. The accepted policy decisions authorize a limited Round 05.1 implementation, not an open selector redesign.
+
+The patch scope is limited to:
+
+- adding Round 05.1 calibration rows;
+- adding narrow QPI signals for governance, responsibility, consensus, minimum-path, and stable-output blockage cases;
+- preserving no-call for execution constraints and ambiguous low-context inputs;
+- preserving QPI-before-IA by default;
+- keeping natural-language prior-QPI claims under lightweight QPI review;
+- generating before / after behavior diff evidence.
+
+The patch does not:
+
+- add a third model;
+- upgrade QPI or Intellectual Archaeology lifecycle status;
+- introduce an LLM selector, RAG, vector database, frontend, backend, accounts, or service layer;
+- convert the full Round 04 blind pool into regression;
+- implement structured `prior_qpi_result` selector support.
+
+Regression additions remain out of scope for the start of Round 05.1 unless later Owner / CCRA review identifies a high-risk guardrail.

docs/FILE_TAXONOMY.md

@@ -22,7 +22,7 @@ Every meaningful file should fit one of four classes:
 | --- | --- | --- | --- |
 | Canonical source of truth | Files that define model/library behavior or reviewed content | Keep and version | `models/*.model.json`, `cards/*.md`, `sources/*.json`, `tests/*.regression.json`, `selector/*.json`, `schemas/*.json`, operative `docs/*.md` |
 | Generated / derived | Files rebuilt or checked from canonical assets | Keep when useful, rebuild at handoff/release | `models/model_index.json`, `cards/card_index.md`, `reports/validation_report.md`, `reports/index_rebuild_report.md`, `reports/model_card_sync_report_v0.2.md`, `reports/selector_regression_report_v0.2.md` |
-| Review archive | Per-round evidence for Owner / CCRA / GPT review | Keep by round, do not treat as runtime truth | `ccra_review_bundle/round-*`, `reports/Codex*.md`, `reports/GPT*.md`, `reports/model_case_preprocessing/*` |
+| Review archive | Per-round evidence for Owner / CCRA / GPT review | Keep by round, do not treat as runtime truth | `ccra_review_bundle/round-*`, `local_ccra_reviews/round-*`, `reports/Codex*.md`, `reports/GPT*.md`, `reports/Round*_round_conductor_*.md`, `reports/model_case_preprocessing/*` |
 | Temporary / local runtime | Caches or local command byproducts | Do not commit | `__pycache__/`, `*.pyc`, temporary extraction folders, ad hoc local scratch files |
 
 ## 3. Canonical Source Of Truth
@@ -89,8 +89,10 @@ They preserve evidence and context, but they do not override canonical files.
 Examples:
 
 - `ccra_review_bundle/round-*/`
+- `local_ccra_reviews/round-*/`
 - `reports/Codex*.md`
 - `reports/GPT*.md`
+- `reports/Round*_round_conductor_*.md`
 - `reports/model_case_preprocessing/*`
 
 Rules:
@@ -101,6 +103,10 @@ Rules:
 - GPT / CCRA upload files inside review bundles must include the round version in the filename, for example `_03.2`, to avoid same-name ambiguity when multiple rounds are uploaded in one Web ChatGPT conversation.
 - Do not flatten zip contents, because duplicate filenames such as `README.md` can collide.
 - `knowledge_assets/` is excluded from review zips by default because the Owner manually syncs stable knowledge assets into GPT knowledge storage.
+- `local_ccra_reviews/` records local first-pass review runs and is not copied into Web CCRA bundles by default.
+- `findings-confirmation.md` inside a Local CCRA run is a Chinese Owner decision aid and does not replace the full review report.
+- Round Conductor reports under `reports/` are process records and do not override canonical model, selector, evidence, or regression files.
+- `04_LOCAL_CCRA_REVIEW_REPORT.md` is excluded from Web CCRA bundles by default unless the Owner explicitly asks to include it.
 
 ## 6. Temporary / Local Runtime Files
 

docs/HANDOFF_TEMPLATE.md

@@ -38,7 +38,34 @@ Task:
 
 -
 
-## 10. Suggested Next Tasks
+## 10. Local CCRA Status
+
+- Local review run:
+- Runtime session id:
+- Local CCRA report:
+- Owner decision:
+- Returned output:
+- Findings confirmation:
+- Helper outputs:
+- Accepted actions:
+- Deferred or escalated findings:
+
+## 11. Round Conductor Status
+
+- Public round:
+- Round charter:
+- Current local pass:
+- Findings awaiting Owner decision:
+- Items accepted for Codex repair:
+- Items rejected:
+- Items deferred:
+- Items escalated to Web CCRA:
+- Validation / routing diff evidence:
+- Stop condition status:
+- Web CCRA bundle path:
+- Local CCRA report included in Web bundle?:
+
+## 12. Suggested Next Tasks
 
 1.
 2.

docs/PROJECT_BRIEF.md

@@ -63,3 +63,31 @@ This repository is separate from but related to:
 - `video-workbench`: dimensional output workspace.
 
 This project may reference artifacts from those repositories, but its own boundary is the model asset foundation for The Mindscape of Bro Tsong.
+
+## 7. Local CCRA First Review
+
+The project may use Local CCRA review as a file-first first-pass review loop before Web CCRA review.
+
+First-version constraints:
+
+- Local CCRA serves only this project.
+- Local CCRA review runs are stored under `local_ccra_reviews/`.
+- The reviewer runs through CCPE Agent Runtime in a real child review session.
+- Formal local review normally uses the same-child `review_turn` plus `planning_turn` pattern.
+- v0.1.2 requires explicit helper/runtime policies for bundle audit profile, gate execution mode, routing diff policy, and lifecycle scan scope.
+- Local CCRA output is formal local first review, but it does not replace Owner or Web CCRA judgment.
+- The `ccra-local-reviewer` Agent Spec and Runtime protocol belong in `ccpe-system`.
+
+## 8. Round Conductor Trial
+
+The project may use the Round Conductor protocol in `docs/ROUND_AUTOMATION_PROTOCOL.md` for Round 05 and later trial runs.
+
+The Round Conductor is the main Codex session acting as a project-local orchestrator. It may prepare round charters, run Local CCRA passes, extract Chinese findings confirmation items, and implement Owner-accepted repairs.
+
+Constraints:
+
+- Owner / Web CCRA defines the public round goal before the conductor starts.
+- Codex must write `findings-confirmation.md` before asking Owner to decide Local CCRA findings.
+- Codex may repair only findings recorded in `owner-decision.md` as `accept_for_codex_fix`.
+- The protocol does not create a generic Skill or move reviewer governance into this repository.
+- Web CCRA remains the formal review lane for key product and lifecycle gates.

docs/ROUND_AUTOMATION_PROTOCOL.md

@@ -0,0 +1,255 @@
+# Round Automation Protocol
+
+version: 0.1
+
+last_updated: 2026-06-19
+
+status: Round 05 trial protocol
+
+## 1. Purpose
+
+This document defines the project-local Round Conductor protocol for reducing manual work around Local CCRA review loops.
+
+It does not define the `ccra-local-reviewer` Agent, CCPE Agent Runtime, or reusable automation Skills.
+
+The goal is to automate low-value file handling, validation, review submission, pass tracking, and Web bundle preparation while keeping Owner judgment at the required gates.
+
+## 2. Scope
+
+Round automation v0.1 covers local review orchestration:
+
+```text
+Owner / Web CCRA defines a public round goal
+-> Codex creates a round charter and local review pass
+-> Codex prepares context, helper outputs, invocation packet, and prompts
+-> Codex invokes the real Local CCRA child review session
+-> Local CCRA writes review and planning outputs
+-> Codex extracts Chinese Owner-facing confirmation items
+-> Owner decides which findings are accepted, rejected, deferred, or escalated
+```
+
+Round automation v0.2 extends the loop after Owner decision:
+
+```text
+Owner accepts findings for Codex repair
+-> Codex applies only accepted fixes
+-> Codex runs validation and before/after checks
+-> Codex opens the next local pass when needed
+-> loop stops by explicit stopping conditions
+-> Codex prepares the formal Web CCRA bundle when Owner requests it
+```
+
+## 3. Roles
+
+### Owner / Web CCRA
+
+Owner and Web CCRA define the public round goal, non-goals, and product judgment questions.
+
+Owner decides:
+
+- whether a finding is accepted for Codex repair;
+- whether a finding is rejected;
+- whether a finding is deferred to a later round;
+- whether a finding needs Web CCRA escalation;
+- whether the local loop is complete enough for formal Web review;
+- whether a Local CCRA report should be included in a Web upload package.
+
+### Codex Main Session
+
+The main Codex session is the Round Conductor.
+
+It may:
+
+- create round-charter and local-pass files;
+- run deterministic helper Skills and project validation;
+- invoke a real child Local CCRA session;
+- summarize Local CCRA findings into Chinese confirmation items;
+- implement Owner-accepted fixes;
+- run post-fix validation and behavior comparisons;
+- prepare a Web CCRA bundle after Owner direction.
+
+It must not:
+
+- treat Local CCRA output as Owner approval;
+- repair findings before Owner decision;
+- expand round scope without confirmation;
+- upgrade model lifecycle status;
+- replace Web CCRA review at key product gates.
+
+### Local CCRA Child Session
+
+The Local CCRA child session is the reviewer.
+
+It is read-only with respect to product files and writes review outputs into the local review run directory.
+
+## 4. Round Charter
+
+Before starting a public round, Codex should create or update a round charter in `reports/` when the Owner / Web CCRA guidance is concrete enough to execute.
+
+Recommended filename:
+
+```text
+reports/Round05_round_conductor_charter_YYYY-MM-DD.md
+```
+
+The charter should include:
+
+- public round label;
+- source of Owner / Web CCRA guidance;
+- round goal;
+- explicit non-goals;
+- in-scope files or asset areas;
+- required validation;
+- expected Local CCRA pass path;
+- stopping conditions;
+- open product questions.
+
+The charter is a process record. It is not a model asset and does not override canonical model JSON, model cards, selector rules, or regression cases.
+
+## 5. Local Pass File Contract
+
+Each Local CCRA pass follows the existing path rule:
+
+```text
+local_ccra_reviews/<public-round>/<local-pass>/
+```
+
+In addition to the existing Local CCRA files, each formal automated pass should contain:
+
+```text
+findings-confirmation.md
+```
+
+`findings-confirmation.md` is written by the Codex main session after reading:
+
+- `04_LOCAL_CCRA_REVIEW_REPORT.md`
+- `next-review-requirements.md`
+- `returned-output.md`
+
+It is not a replacement for the full review report.
+
+## 6. Findings Confirmation Format
+
+`findings-confirmation.md` must be written in Chinese and should extract only the core Owner decision items.
+
+Each item should use this shape:
+
+```text
+### F-001: <中文短标题>
+
+- 核心确认事项：
+- Local CCRA 建议：
+- Codex 建议处理：
+- 建议决策：accept_for_codex_fix | reject | defer_to_future_round | escalate_to_web_ccra | owner_clarification_required | accept_as_known_limit
+- 若接受，Codex 可改范围：
+- 若不接受，影响：
+- 证据路径：
+- 需要 Owner 回答：
+```
+
+Rules:
+
+- Do not copy the whole Local CCRA report.
+- Do not hide uncertainty; if the report is unclear, mark `owner_clarification_required`.
+- Preserve the distinction between Local CCRA recommendation and Codex implementation recommendation.
+- Include enough evidence paths for the Owner to open the original report when needed.
+- Use plain Chinese decision language, not long audit prose.
+
+## 7. Owner Decision Gate
+
+Codex may not start repair for a Local CCRA finding until `owner-decision.md` records the Owner decision.
+
+Allowed decision states:
+
+```text
+accept_for_codex_fix
+reject
+defer_to_future_round
+escalate_to_web_ccra
+owner_clarification_required
+accept_as_known_limit
+```
+
+Codex may only implement findings marked `accept_for_codex_fix`.
+
+For all other states, Codex should preserve the item in the next handoff or Web bundle questions when relevant.
+
+## 8. Repair Loop
+
+After Owner decision, Codex may enter the v0.2 repair loop.
+
+Allowed repair behavior:
+
+- modify only files in the confirmed round scope;
+- keep model JSON, cards, selector rules, regression cases, and reports synchronized;
+- run index checks, model validation, selector checks, routing before/after comparisons, and whitespace checks as applicable;
+- document every change in the round conductor status or handoff report;
+- open the next local pass when validation or Local CCRA requirements call for it.
+
+Forbidden repair behavior:
+
+- adding a third model;
+- adding an LLM selector, RAG system, database, frontend, backend, user system, or platform service;
+- upgrading lifecycle or stability status based only on Local CCRA;
+- modifying Local CCRA reviewer outputs;
+- treating dry-run gates as executed validation;
+- treating helper warnings as automatic blockers without triage.
+
+## 9. Stopping Conditions
+
+The local loop should stop when one of these is true:
+
+- Local CCRA reports no current-scope blocker or major finding, and remaining findings are rejected, deferred, escalated, or accepted as known limits by Owner.
+- The current pass identifies only Web CCRA or product judgment questions.
+- Owner decides the round is ready for Web review.
+- Owner decides to pause the round.
+- The loop reaches three local passes for the same public round without clearing the same blocking class.
+
+If the three-pass limit is reached, Codex should summarize the repeated blocker and ask Owner whether to continue, defer, or escalate.
+
+## 10. Web Bundle Preparation
+
+After the local loop stops and Owner requests Web review, Codex prepares the formal Web CCRA bundle under:
+
+```text
+ccra_review_bundle/round-NN_YYYY-MM-DD_topic/
+```
+
+The Web bundle should summarize:
+
+- public round goal;
+- changes made in the public round and local passes;
+- validation and routing-diff evidence;
+- unresolved Owner / Web CCRA questions;
+- explicit non-goals and deferred items.
+
+By default, do not include `04_LOCAL_CCRA_REVIEW_REPORT.md` in the Web bundle.
+
+Include a Local CCRA report only when Owner explicitly asks Web CCRA to review local findings.
+
+## 11. Supplier Boundary
+
+This protocol is project-local.
+
+Route future needs as follows:
+
+- CCPE: reviewer contract, runtime invocation, session continuation, review rubric, lifecycle authority, stopping-condition governance.
+- skills-vault: only deterministic, reusable automation extracted from repeated project use.
+- this repository: product-specific round state, local pass records, Owner decisions, applied fixes, validation outputs, and Web bundle assembly.
+
+Do not create a reusable Skill merely because this protocol exists. Extract only after repeated use proves a deterministic cross-project operation.
+
+## 12. Round 05 Startup Checklist
+
+At the start of Round 05, the new Codex session should:
+
+1. Read `AGENTS.md`.
+2. Read `reports/Codex新会话交接文档_LocalCCRA自动化讨论上下文_2026-06-19.md`.
+3. Read this protocol.
+4. Read `local_ccra_reviews/README.md`.
+5. Read `knowledge_assets/10_本地CCRA评审机制说明.md`.
+6. Create the Round 05 charter from Owner / Web CCRA guidance.
+7. Confirm the first Local CCRA pass path.
+8. Prepare helper policy fields for v0.1.2.
+9. Run the Local CCRA pass through a real child session.
+10. Produce `findings-confirmation.md` before asking Owner to decide findings.

docs/WORKFLOW.md

@@ -88,6 +88,82 @@ Required properties:
 
 Do not use `Compress-Archive` for review raw zips where directory paths matter; it can flatten file-list paths.
 
+## 5.2 Local CCRA Review Workflow
+
+Local CCRA review is a file-first first-pass review loop inside this project.
+
+Use:
+
+```text
+local_ccra_reviews/<public-round>/<local-pass>/
+```
+
+Examples:
+
+```text
+local_ccra_reviews/round-05_selector-calibration-policy/01/
+local_ccra_reviews/round-05_selector-calibration-policy/02/
+local_ccra_reviews/round-04/pilot-01/
+local_ccra_reviews/round-04/pilot-02/
+local_ccra_reviews/round-03.2a_depth-limiting-qpi-override-patch/01/
+```
+
+Workflow:
+
+1. Owner decides whether the public round needs Local CCRA review.
+2. Codex creates the next numbered local review run directory.
+3. Codex writes `run-notes.md`, `review-metadata.json`, `gate-manifest.yaml`, and `lifecycle-guard-config.yaml`.
+4. Codex declares Local CCRA v0.1.2 helper policies: `bundle_audit_profile`, `gate_execution_mode`, `routing_diff_policy`, and `lifecycle_scan_scope`.
+5. Codex runs `review-context-builder` and applicable helper Skills, recording skipped helpers in `run-notes.md`.
+6. Codex writes `agent-invocation-packet.md`, `prompt-to-send.md`, and `turn-prompts/`.
+7. Codex invokes CCPE Agent Runtime / Codex child thread as `ccra-local-reviewer`.
+8. The runtime child session id or carrier id is recorded in `run-notes.md`.
+9. `review_turn` writes `04_LOCAL_CCRA_REVIEW_REPORT.md` and `returned-output.md`.
+10. `planning_turn` continues the same child session and writes `next-review-requirements.md` when next-review planning is needed.
+11. Codex writes `findings-confirmation.md` in Chinese, extracting the core Owner decision items from the Local CCRA report and planning output.
+12. Owner records accepted, rejected, deferred, escalated, known-limit, or clarification-needed findings in `owner-decision.md`.
+13. Codex executes only Owner-accepted actions in the main project session.
+14. A follow-up Local CCRA review uses the next local pass label, such as `02/`.
+15. After Local CCRA and Owner acceptance, Codex creates the formal Web CCRA bundle under `ccra_review_bundle/round-NN_YYYY-MM-DD_topic/`.
+
+Rules:
+
+- Local CCRA output is formal local first review, not Owner approval and not Web CCRA approval.
+- `ccra-local-reviewer` is read-only and must not modify product files.
+- Review inputs and outputs should be exchanged through local files, not chat summaries.
+- Runtime child session id and continuation state belong in `run-notes.md` and `agent-invocation-packet.md`.
+- The default formal pattern is same-child `review_turn` followed by `planning_turn`.
+- Patch or post-patch review material requires `routing_diff_policy: required` or a manually documented equivalent table.
+- `gate_execution_mode: dry_run` cannot support validation pass claims.
+- `findings-confirmation.md` is an Owner-facing Chinese extraction aid, not a replacement for `04_LOCAL_CCRA_REVIEW_REPORT.md`.
+- Codex must not repair a Local CCRA finding until the Owner decision is recorded in `owner-decision.md`.
+- Formal Web CCRA bundles exclude `04_LOCAL_CCRA_REVIEW_REPORT.md` by default.
+- Include the local report in Web CCRA upload packages only when the owner explicitly asks for Web CCRA to review local findings.
+- CCPE owns the Agent Spec, Runtime Spec, invocation protocol, review rubric, and companion-capability classification.
+- Full Round-level automation is a separate workflow/orchestrator design topic, not part of the Local CCRA reviewer contract.
+- `skills-vault` receives a request only after CCPE or the owner decides that a companion operation is reusable deterministic automation.
+
+## 5.3 Round Conductor Workflow
+
+For the project-local Round Conductor protocol, see `docs/ROUND_AUTOMATION_PROTOCOL.md`.
+
+Round automation v0.1 automates Local CCRA orchestration, file preparation, helper execution, real child-session review submission, and Chinese findings confirmation.
+
+Round automation v0.2 additionally permits Codex to enter a repair loop after Owner decision, but only for findings marked `accept_for_codex_fix`.
+
+Round Conductor rules:
+
+1. Owner / Web CCRA defines the public round goal before Codex starts the round.
+2. Codex records the public round goal, non-goals, validation expectations, and stopping conditions in a round charter under `reports/`.
+3. Codex prepares and runs each Local CCRA pass under `local_ccra_reviews/<public-round>/<local-pass>/`.
+4. Codex writes `findings-confirmation.md` before asking for Owner decision.
+5. Owner records decisions in `owner-decision.md`.
+6. Codex repairs only `accept_for_codex_fix` items.
+7. Codex runs validation and before/after behavior checks appropriate to the change.
+8. Codex starts another local pass only when accepted fixes or Local CCRA requirements justify it.
+9. Codex stops the local loop when the stopping conditions in `docs/ROUND_AUTOMATION_PROTOCOL.md` are met.
+10. Codex prepares the formal Web CCRA bundle only after Owner requests Web review.
+
 ## 6. Supplier Request Workflow
 
 When this repository needs a capability owned by a neighboring repository:

docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md

@@ -157,7 +157,7 @@ Do not:
 - create a third model;
 - summarize the whole source instead of extracting cases;
 - quote long source passages;
-- pretend draft cases are owner-approved.
+- pretend draft cases have Owner confirmation.
 
 ## 7. Promotion Path
 
@@ -172,4 +172,3 @@ raw source
 ```
 
 Only owner-reviewed cases may become machine-readable calibration or regression assets.
-

knowledge_assets/10_本地CCRA评审机制说明.md

@@ -0,0 +1,278 @@
+# 本地 CCRA 评审机制说明
+
+version: 0.4
+
+last_updated: 2026-06-19
+
+status: stable explanatory asset
+
+## 1. 文档定位
+
+本文档说明 `the-mindscape-of-bro-tsong` 项目如何使用 Local CCRA 做本地第一轮评审。
+
+它只解释项目侧机制，不定义 `ccra-local-reviewer` Agent 本体。
+
+Agent Spec、Runtime Spec、调用协议、会话保持机制、评审 rubric 和配套能力归属判定属于 `ccpe-system`。
+
+## 2. 为什么需要 Local CCRA
+
+当前项目已经有 Web CCRA / GPT 评审流程，但人工搬运成本较高。
+
+Local CCRA 的目标是把以下工作本地化：
+
+- 审核资料的第一轮审查；
+- 轮次目标是否被偷换的检查；
+- 工程通过与产品判断之间的差距识别；
+- selector 规则变更后的非目标行为变化识别；
+- 模型生命周期是否被过早升级的守门；
+- 下一轮应修、应延后、应进入 calibration 或 regression 的建议。
+
+Local CCRA 是正式本地初审，但不替代 Owner 或 Web CCRA 的关键节点判断。
+
+## 3. 第一版范围
+
+第一版只服务：
+
+```text
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong
+```
+
+不建立独立 reviewer 项目。
+
+原因是当前没有跨项目评审需求。正交性来自真实子会话 / Agent Runtime 隔离，而不是来自另建目录或另建项目。
+
+## 4. 项目侧目录
+
+Local CCRA 运行记录放在：
+
+```text
+local_ccra_reviews/
+```
+
+路径规则：
+
+```text
+local_ccra_reviews/<public-round>/<local-pass>/
+```
+
+示例：
+
+```text
+local_ccra_reviews/round-05_selector-calibration-policy/01/
+local_ccra_reviews/round-05_selector-calibration-policy/02/
+local_ccra_reviews/round-04/pilot-01/
+local_ccra_reviews/round-03.2a_depth-limiting-qpi-override-patch/01/
+```
+
+`<public-round>` 跟随 Owner / Web CCRA 共同确定的公共轮次，例如 `round-05`、`round-04.1`、`round-03.2a`。
+
+`<local-pass>` 是 Local CCRA 内部评审次数，例如 `01/`、`02/`。
+
+## 5. 每次评审的文件
+
+每个本地评审目录应包含：
+
+```text
+run-notes.md
+review-metadata.json
+gate-manifest.yaml
+lifecycle-guard-config.yaml
+agent-invocation-packet.md
+prompt-to-send.md
+turn-prompts/
+review-context.md
+review-file-manifest.json
+helper-outputs/
+04_LOCAL_CCRA_REVIEW_REPORT.md
+next-review-requirements.md
+returned-output.md
+05_WEB_LOCAL_CCRA_COMPARISON.md
+findings-confirmation.md
+owner-decision.md
+```
+
+关键含义：
+
+- `run-notes.md`：记录本轮运行、helper 命令、跳过项、dispatch 和 resume 信息。
+- `review-metadata.json`：记录本轮目标、范围、非目标和开放问题。
+- `agent-invocation-packet.md`：交给 CCPE Agent Runtime 的文件优先调用包。
+- `prompt-to-send.md`：通过 Codex 子线程等 carrier 调用时使用的提示词。
+- `turn-prompts/`：保存 `review_turn`、`planning_turn`、必要时的 `comparison_turn` 提示。
+- `review-context.md` / `review-file-manifest.json`：由 `review-context-builder` 生成的文件优先上下文索引。
+- `04_LOCAL_CCRA_REVIEW_REPORT.md`：`ccra-local-reviewer` 唯一判断输出。
+- `next-review-requirements.md`：同一子会话第二回合产出的下一轮评审要求与提交资料规划。
+- `returned-output.md`：子会话返回内容或报告路径记录。
+- `05_WEB_LOCAL_CCRA_COMPARISON.md`：可选的主会话比较笔记，用于把 Local CCRA 输出与 Web CCRA / GPT 反馈对照后调优。
+- `findings-confirmation.md`：主会话用中文摘录 Local CCRA findings 的核心确认事项，供 Owner 快速决策。
+- `owner-decision.md`：Owner 对 findings 的接受、拒绝、延后或升级判断。
+
+## 6. 运行流程
+
+推荐流程：
+
+```text
+Owner 决定需要本地评审
+-> Codex 创建 local_ccra_reviews/<round>/<pass>/
+-> Codex 运行 review-context-builder 和适用 helper Skill
+-> Codex 生成 Runtime invocation packet 和 prompt-to-send
+-> Codex 调起 CCPE Agent Runtime 子会话并记录 child_session_id
+-> review_turn: ccra-local-reviewer 只读评审资料并写本地评审报告
+-> planning_turn: 同一 child_session_id 继续，写下一轮评审要求与提交资料规划
+-> Codex 主会话写 findings-confirmation.md，提取中文核心确认事项
+-> Owner 写 decision
+-> Codex 根据 accepted findings 修复
+-> 必要时进入下一次本地评审
+-> 通过后生成正式 Web CCRA bundle
+```
+
+`ccra-local-reviewer` 只输出评审意见，不做任何项目文件调整。
+
+当前推荐的正式使用模式是两回合：
+
+1. `review_turn`：评审本轮资料，识别问题、机制、证据缺口、补丁范围和是否需要本地修复。
+2. `planning_turn`：复用同一个 `child_session_id`，基于第一回合报告和 Owner decision，规划下一轮评审要求和应提交资料。
+
+`planning_turn` 不应重新完整评审当前 bundle，除非 Owner 明确要求或新增证据已经进入评审目录。
+
+运行时长与工具使用原则：
+
+- Local CCRA 是深度文件优先评审，不是快速聊天摘要。
+- 成熟运行的目标耗时可按 Web CCRA 的常见 5-10 分钟理解，具体取决于客户端和 API / runtime 配置。
+- 子会话可以按需使用本地工具解压、检索、读取 manifest、运行 helper Skill，并在 Owner 或运行包允许时执行回归 / 验证命令。
+- 主会话不应仅因为子会话阅读文件或运行工具持续数分钟就中断评审。
+- 每次运行应在 `run-notes.md` 记录可观察耗时，便于后续区分正常深度评审和 runtime 异常。
+
+## 7. 正式使用条件
+
+基于 Round 04 `pilot-02` 的三方对比和 CCPE Patch 2 更新，Local CCRA v0.1.2 可以作为本项目正式本地初审使用，但带条件：
+
+- 必须真实调起子会话，不允许主会话角色扮演。
+- 必须记录并复用 `child_session_id`。
+- 必须使用 `knowledge_assets/` 作为强制知识库路径。
+- 默认采用 `review_turn` + `planning_turn` 两回合模式。
+- helper 输出只能作为证据线索，必须标注置信度、噪声和适用范围。
+- 当评审对象包含补丁或 post-patch 证据时，必须要求 before / after 行为对比。
+- Local CCRA 不能替代 Owner decision、Web CCRA final review 或模型生命周期升级判断。
+
+v0.1.2 已把 Patch 2 硬化项纳入 CCPE runtime 合同。每次运行应明确记录：
+
+```text
+bundle_audit_profile: ccra_mindscape_review_bundle | generic | not_applicable
+gate_execution_mode: dry_run | run | owner_waived | not_applicable
+routing_diff_policy: required | skipped_no_after_evidence | manual_equivalent_required | not_applicable
+lifecycle_scan_scope: current_review_bundle | changed_files | knowledge_assets | model_library_state | whole_repo
+```
+
+这些字段通常写入 `review-metadata.json` 和 `agent-invocation-packet.md`，并在 `returned-output.md` 中摘要返回。
+
+字段含义：
+
+- `bundle_audit_profile`：优先使用 `ccra_mindscape_review_bundle`；若 helper 只能使用 generic profile，必须标注 profile mismatch，不能自动判定 bundle 失败。
+- `gate_execution_mode`：`dry_run` 只能证明 gate 声明可读，不能支持 pass claim；真正验收需要 `run` 或 Owner 记录 `owner_waived`。
+- `routing_diff_policy`：如果评审对象包含 patch 或 before / after 证据，必须有 routing diff 或手工等价表；初始无后验评审可记录为 `skipped_no_after_evidence`。
+- `lifecycle_scan_scope`：whole repo 是广域审计模式，不应默认成为当前评审 blocker；发现项必须做 current-scope triage。
+
+CCPE Patch 2 没有改变机制诊断、补丁范围判断、同子会话延续、强制知识库或权限边界，因此不需要第三次历史试运行。可以在下一次 Owner / Web CCRA 已确定目标的真实本地初审中验证 v0.1.2。
+
+## 8. 与 Web CCRA Bundle 的关系
+
+正式 Web CCRA / GPT 上传包仍放在：
+
+```text
+ccra_review_bundle/round-NN_YYYY-MM-DD_topic/
+```
+
+不要使用简写路径，例如：
+
+```text
+ccra_review_bundle/05/
+```
+
+正式 Web CCRA 包默认不包含：
+
+```text
+04_LOCAL_CCRA_REVIEW_REPORT.md
+```
+
+只有 Owner 明确要求 Web CCRA 复核本地评审意见时，才把本地评审报告纳入正式上传包。
+
+## 9. 与 CCPE 和 skills-vault 的分工
+
+`ccpe-system` 负责：
+
+- `ccra-local-reviewer` Agent Spec；
+- CCPE Agent Runtime 接口；
+- 子会话创建与继续协议；
+- 评审 rubric；
+- 生命周期守门规则；
+- 文件优先评审协议；
+- 配套能力是否应转交 `skills-vault` 的判定。
+
+`skills-vault` 只负责：
+
+- 已经被抽象为可复用、确定性、跨项目自动化的工具；
+- 例如 `bundle-zip` 这种与具体 CCRA 角色无关的通用文件处理能力。
+
+Local CCRA 的 companion automation 不直接提交给 `skills-vault`。应先由 CCPE 判定它是 Agent 专属、Runtime 配套、项目本地 helper，还是可抽公共 Skill。
+
+## 10. 自动化边界
+
+Local CCRA 机制只定义本地初审的 reviewer/runtime 使用方式，不把 `ccra-local-reviewer` 变成执行者。
+
+项目侧可以另行定义 Round Conductor 协议来减少人工搬运和重复操作。当前协议见：
+
+```text
+docs/ROUND_AUTOMATION_PROTOCOL.md
+```
+
+Round Conductor v0.1 范围：
+
+```text
+Owner/Web 确定 Round N 规划
+-> Codex 创建 round charter 和 Local CCRA pass
+-> Codex 准备上下文、helper 输出、调用包和提示词
+-> Codex 调起真实 Local CCRA 子会话
+-> Local CCRA 输出 review_turn / planning_turn
+-> Codex 写 findings-confirmation.md，摘录中文核心确认事项
+-> Owner 写 owner-decision.md
+```
+
+Round Conductor v0.2 范围：
+
+```text
+Owner 接受 findings
+-> Codex 只处理 accept_for_codex_fix 项
+-> Codex 运行验证和 before/after 行为检查
+-> 必要时进入下一次本地评审 pass
+-> 满足停止条件后准备正式 Web CCRA bundle
+```
+
+这仍然不是无人值守自动修复。必须保留：
+
+- Round 目标和非目标的 Owner / Web CCRA 确认；
+- findings 的 Owner decision gate；
+- 生命周期升级、模型范围扩大、第三模型扩展、Web bundle 是否包含 Local CCRA report 的人工判断；
+- Web CCRA 对关键产品节点的正式评审。
+
+## 11. 非目标
+
+Local CCRA 不做：
+
+- Owner 最终决策；
+- Web CCRA 关键节点复审替代；
+- 模型生命周期升级；
+- selector 规则修改；
+- model card 修改；
+- regression case 修改；
+- review bundle 创建；
+- Round Conductor 的 Owner decision 或修复授权；
+- 第三模型扩展；
+- LLM selector、RAG、数据库、前端、后端或平台化功能。
+
+## 12. 结论
+
+Local CCRA 是本项目的本地第一轮审查机制。
+
+它的价值不是复制 Web GPT，而是把 CCRA 的审查原则本地文件化、运行时隔离化、报告归档化。
+
+项目侧负责保存 review runs；CCPE 负责定义 reviewer 和 runtime；skills-vault 只承接被抽象后的通用自动化。

knowledge_assets/README.md

@@ -25,5 +25,6 @@ Current reading order:
 - `07_产品规划过程记录.md`
 - `08_CCRA模型库MVP质量门与交接协议.md`
 - `09_数据治理与模型调用机制说明.md`
+- `10_本地CCRA评审机制说明.md`
 
 See `docs/KNOWLEDGE_ASSET_RULES.md`.

local_ccra_reviews/README.md

@@ -0,0 +1,237 @@
+# Local CCRA Reviews
+
+## 1. Purpose
+
+`local_ccra_reviews/` records first-pass Local CCRA reviews for this project.
+
+The directory is a project-side review run archive. It is not the canonical CCRA Agent definition, not a reusable Skill source tree, and not the formal Web CCRA upload bundle.
+
+First-version scope:
+
+- Serves only `the-mindscape-of-bro-tsong`.
+- Uses CCPE Agent Runtime to create or continue a real child review session.
+- Passes primary inputs and outputs through local files, not through main-session chat summaries.
+- Treats Local CCRA output as formal local first review, but not as Owner or Web CCRA final judgment.
+
+## 2. Ownership
+
+This repository owns:
+
+- Local review run directories.
+- Input file lists and review packets for a specific project round.
+- Runtime session metadata for continuing child review sessions.
+- Local CCRA reports, Owner decisions, and action registers.
+
+`ccpe-system` owns:
+
+- `ccra-local-reviewer` Agent Spec.
+- CCPE Agent Runtime contract.
+- Review rubric, lifecycle gate policy, invocation protocol, and report format.
+- Decisions about whether companion automation should stay Agent-specific or be routed to `skills-vault`.
+
+`skills-vault` owns only automation that CCPE or the owner explicitly abstracts as reusable, deterministic, cross-project tooling.
+
+## 3. Directory Convention
+
+Use the public Owner / Web CCRA round as the first directory level, then use a Local CCRA pass label.
+
+Examples:
+
+```text
+local_ccra_reviews/
+  round-05_selector-calibration-policy/
+    01/
+    02/
+  round-04/
+    pilot-01/
+    pilot-02/
+  round-03.2a_depth-limiting-qpi-override-patch/
+    01/
+```
+
+The public round label follows the same semantic round version as the review bundle, such as `round-05`, `round-04.1`, or `round-03.2a`.
+
+The child directory records the local review pass:
+
+- `01/`: first Local CCRA review for that public round.
+- `02/`: second Local CCRA review after accepted fixes.
+- `pilot-01/`: historical pilot used to test invocation authenticity, persistence, and report quality before formal use.
+- `pilot-02/`: historical pilot used to test Patch 1 two-turn review/planning behavior before formal use.
+- Later numbers are allowed only when the owner explicitly asks for another local review pass.
+
+## 4. Run Directory Files
+
+Each run directory should use these files:
+
+```text
+run-notes.md
+review-metadata.json
+gate-manifest.yaml
+lifecycle-guard-config.yaml
+agent-invocation-packet.md
+prompt-to-send.md
+turn-prompts/
+review-context.md
+review-file-manifest.json
+helper-outputs/
+  bundle-audit.md
+  bundle-audit.json
+  routing-behavior-diff.md
+  routing-behavior-diff.json
+  gate-run-report.md
+  gate-run-report.json
+  logs/
+  lifecycle-status-guard-scan.md
+  lifecycle-status-guard-scan.json
+04_LOCAL_CCRA_REVIEW_REPORT.md
+next-review-requirements.md
+returned-output.md
+05_WEB_LOCAL_CCRA_COMPARISON.md
+findings-confirmation.md
+owner-decision.md
+```
+
+File roles:
+
+- `run-notes.md`: run setup, helper commands, skipped helpers, dispatch record, child session id, and resume notes.
+- `review-metadata.json`: review goal, scope, non-goals, open questions, target reviewer, and output paths.
+- `gate-manifest.yaml`: project-owned validation gates for `regression-validation-gate-runner`; use `dry_run` until the owner approves execution.
+- `lifecycle-guard-config.yaml`: lifecycle and status overclaim scan configuration.
+- `agent-invocation-packet.md`: file-first packet for CCPE Agent Runtime.
+- `prompt-to-send.md`: prompt used when invoking a Codex child thread or equivalent carrier.
+- `turn-prompts/`: one prompt file per runtime turn, such as `review_turn`, `planning_turn`, and optional `comparison_turn`.
+- `review-context.md` and `review-file-manifest.json`: deterministic context index generated by `review-context-builder`.
+- `helper-outputs/`: deterministic evidence generated by registered helper Skills. Missing optional helper outputs must be recorded in `run-notes.md`.
+- `04_LOCAL_CCRA_REVIEW_REPORT.md`: the only judgment output from `ccra-local-reviewer`.
+- `next-review-requirements.md`: same-child-session planning output that defines the next review's required materials, evidence, and open Owner/Web decisions.
+- `returned-output.md`: the raw returned output from the child reviewer, or a pointer to the report if the report is the returned output.
+- `05_WEB_LOCAL_CCRA_COMPARISON.md`: optional main-session comparison between Local CCRA output and Web CCRA / GPT feedback for pilot tuning.
+- `findings-confirmation.md`: Chinese Owner-facing extraction of core findings requiring decision before Codex repair.
+- `owner-decision.md`: Owner decision states for findings, such as `accept_for_codex_fix`, `reject`, `defer_to_future_round`, or `escalate_to_web_ccra`.
+
+## 5. Runtime Rules
+
+When the owner asks for Local CCRA review:
+
+1. The main Codex session prepares a new local review run directory.
+2. The main session invokes CCPE Agent Runtime to create or continue a child review session.
+3. The runtime session id is recorded in `run-notes.md` and `agent-invocation-packet.md`.
+4. `review_turn`: `ccra-local-reviewer` reads the review run inputs and referenced project files.
+5. `review_turn`: `ccra-local-reviewer` writes `04_LOCAL_CCRA_REVIEW_REPORT.md`.
+6. `planning_turn`: the same child session continues from the first-turn report and writes `next-review-requirements.md` when next-round planning is requested.
+7. `ccra-local-reviewer` does not modify product files, selector rules, model cards, regression cases, review bundles, or Owner decisions.
+8. The main Codex session writes `findings-confirmation.md` in Chinese before asking Owner to decide findings.
+9. Codex does not repair a finding until Owner records the decision in `owner-decision.md`.
+
+The default formal pattern is two turns in the same child session:
+
+- `review_turn`: judge the current materials, findings, evidence gaps, and action recommendation.
+- `planning_turn`: convert the first-turn judgment plus Owner decisions into next-review requirements and submitted-material guidance.
+
+`planning_turn` should not re-review the full current bundle unless new evidence was added or the owner explicitly asks for re-review.
+
+Expected run behavior:
+
+- A useful Local CCRA pass is a deep file-first review, not a quick chat summary.
+- The normal target budget for a mature run is roughly 5-10 minutes, comparable to Web CCRA review and dependent on the client/runtime configuration.
+- The child reviewer may use local tools to inspect archives, query manifests, run deterministic helper Skills, and execute owner-approved regression or validation gates.
+- The main session should avoid interrupting a running child review only because it spends several minutes reading files or running tools.
+- `run-notes.md` should record observed duration when available so later tuning can distinguish normal review time from runtime problems.
+
+The project follows the CCPE setup guide at:
+
+```text
+C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-runtime-setup.md
+```
+
+## 6. Review Loop
+
+Recommended flow:
+
+```text
+Owner requests Local CCRA review
+-> create local_ccra_reviews/<round>/<pass>/
+-> run review-context-builder and applicable helper Skills
+-> invoke CCPE Agent Runtime child session
+-> review_turn writes LOCAL_CCRA_REVIEW_REPORT
+-> planning_turn writes next-review-requirements when needed
+-> Codex writes findings-confirmation.md in Chinese
+-> Owner records decision
+-> Codex executes accepted actions
+-> next local review pass uses the next pass label if needed
+-> accepted material is packaged for Web CCRA when the owner asks
+```
+
+Major public rounds normally should receive Local CCRA review after Owner / Web CCRA define the round goal. Patch rounds such as `round-03.2a` are optional and owner-directed.
+
+After `pilot-02` and CCPE Patch 2, Local CCRA v0.1.2 is usable as the formal local first-review lane with conditions.
+
+For v0.1.2, every new run should declare these helper/runtime policy fields in `review-metadata.json` or `agent-invocation-packet.md`:
+
+```text
+bundle_audit_profile: ccra_mindscape_review_bundle | generic | not_applicable
+gate_execution_mode: dry_run | run | owner_waived | not_applicable
+routing_diff_policy: required | skipped_no_after_evidence | manual_equivalent_required | not_applicable
+lifecycle_scan_scope: current_review_bundle | changed_files | knowledge_assets | model_library_state | whole_repo
+```
+
+`returned-output.md` should preserve a compact Owner-facing summary, including final action recommendation, blocking status, required next action, output paths, and evidence limitations.
+
+`findings-confirmation.md` should preserve the Owner decision surface in Chinese. Each item should include:
+
+- core confirmation question;
+- Local CCRA recommendation;
+- Codex implementation recommendation;
+- proposed decision state;
+- allowed repair scope if accepted;
+- impact if not accepted;
+- evidence paths;
+- exact Owner question when clarification is required.
+
+Allowed decision states are:
+
+```text
+accept_for_codex_fix
+reject
+defer_to_future_round
+escalate_to_web_ccra
+owner_clarification_required
+accept_as_known_limit
+```
+
+Only `accept_for_codex_fix` authorizes Codex to modify project files for that finding.
+
+For the broader Round Conductor protocol, see:
+
+```text
+docs/ROUND_AUTOMATION_PROTOCOL.md
+```
+
+## 7. Relationship To Web CCRA Bundles
+
+`ccra_review_bundle/` remains the formal Web CCRA / GPT upload archive.
+
+After a Local CCRA pass is accepted, create the formal Web CCRA bundle under the existing dated bundle convention:
+
+```text
+ccra_review_bundle/round-NN_YYYY-MM-DD_topic/
+```
+
+Do not create shorthand bundle directories such as `ccra_review_bundle/05/`.
+
+By default, the formal Web CCRA bundle does not include `04_LOCAL_CCRA_REVIEW_REPORT.md`. Include the local report only when the owner explicitly wants Web CCRA to review the local findings.
+
+## 8. Non-Goals
+
+Local CCRA review must not:
+
+- Replace Owner judgment.
+- Replace Web CCRA at key product or lifecycle gates.
+- Upgrade model lifecycle status.
+- Add a third model.
+- Add LLM selector, RAG, database, frontend, backend, user system, or platform behavior.
+- Turn `ccra-local-reviewer` into an implementer.
+- Implement full Round-level automation or autonomous multi-pass repair loops.
+- Start repair before Owner decision.
+- Store canonical CCPE artifacts in this repository.
+- Store reusable Skill source in this repository.

local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md

@@ -0,0 +1,507 @@
+# Local CCRA Review Report
+
+## 1. Return Metadata
+
+- project_id: the-mindscape-of-bro-tsong
+- review_round: round-04
+- local_pass: pilot-01
+- runtime_id: ccra-local-review
+- runtime_version: 0.1.0
+- agent_id: ccra-local-reviewer
+- agent_version: 0.1.0
+- invocation_mode: prompt_path_reference
+- carrier_type: codex_thread
+- child_session_id: 019edca7-48f3-79d3-be4a-550f4df0f13c
+- persistent_available: yes, if this Codex child thread is resumed
+- execution_status: returned
+- simulation_only: false
+- report_path: local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md
+- returned_output_path: local_ccra_reviews/round-04/pilot-01/returned-output.md
+- generated_at: 2026-06-19
+
+## 2. Review Scope
+
+- primary_question: Does Local CCRA produce Web CCRA-level review quality when it can inspect the full local Round 04 evidence set?
+- scope_statement: Review Round 04 blind routing evaluation evidence as a historical pilot, focusing on invocation authenticity, persistence, report quality, evidence coverage, non-target behavior awareness, lifecycle/scope discipline, and readiness gaps for future Round 05 use.
+- non_goals:
+  - Do not decide Owner approval.
+  - Do not replace Web CCRA final review.
+  - Do not promote lifecycle status.
+  - Do not modify selector rules, model cards, model JSON, regression cases, review bundles, or Owner decision files.
+  - Do not treat this pilot as Round 05 acceptance.
+- local_tuning_stage: historical_pilot
+- web_final_review_target: none_for_this_pilot
+
+## 3. Inputs Actually Received
+
+- `local_ccra_reviews/round-04/pilot-01/prompt-to-send.md`
+- `local_ccra_reviews/round-04/pilot-01/agent-invocation-packet.md`
+- canonical CCPE Agent, Runtime, setup, template, and helper integration files from `C:/Users/wangq/Documents/Codex/ccpe-system`
+- required knowledge base path: `knowledge_assets/`
+- review context and manifest: `review-context.md`, `review-file-manifest.json`
+- Round 04 primary evidence: `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`, `selector/round04_blind_inputs.json`, `selector/selector_rules.json`
+- optional Round 04.1 post-patch evidence: `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md`, `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/`
+- helper outputs under `local_ccra_reviews/round-04/pilot-01/helper-outputs/`
+
+## 4. Files Actually Read
+
+### Invocation And CCPE Runtime
+
+- `local_ccra_reviews/round-04/pilot-01/prompt-to-send.md` - dispatch prompt and hard constraints.
+- `local_ccra_reviews/round-04/pilot-01/agent-invocation-packet.md` - formal invocation packet and output contract.
+- `C:/Users/wangq/Documents/Codex/ccpe-system/agents/agent-specs/ccra-local-reviewer.agent.md` - reviewer role, source policy, authority boundaries, and reporting requirements.
+- `C:/Users/wangq/Documents/Codex/ccpe-system/runtimes/hybrid/ccra-local-review.runtime.md` - runtime stages, child-session and helper rules.
+- `C:/Users/wangq/Documents/Codex/ccpe-system/runtimes/hybrid/ccra-local-review-runtime-setup.md` - setup sequence and helper command contracts.
+- `C:/Users/wangq/Documents/Codex/ccpe-system/runtimes/hybrid/ccra-local-review-report.template.md` - required report sections.
+- `C:/Users/wangq/Documents/Codex/ccpe-system/integrations/skills-vault/ccra-local-review-helpers.integration.md` - helper registration and helper-output authority.
+
+### Project Governance And Knowledge Assets
+
+- `README.md`
+- `AGENTS.md`
+- `PROJECTS.md`
+- `docs/WORKFLOW.md`
+- `docs/DECISIONS.md`
+- `docs/QPI_CONTEXTUAL_ROUTING_RULES.md`
+- `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md`
+- `knowledge_assets/README.md`
+- `knowledge_assets/00_用户背景与产品上下文.md`
+- `knowledge_assets/01_核心模型地图.md`
+- `knowledge_assets/02_模型卡结构规范.md`
+- `knowledge_assets/03_核心模型抽取样板.md`
+- `knowledge_assets/06_模型稳固性评级规则.md`
+- `knowledge_assets/07_产品规划过程记录.md`
+- `knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md`
+- `knowledge_assets/09_数据治理与模型调用机制说明.md`
+- `knowledge_assets/10_本地CCRA评审机制说明.md`
+
+### Local Review Run Records And Helper Outputs
+
+- `local_ccra_reviews/round-04/pilot-01/run-notes.md`
+- `local_ccra_reviews/round-04/pilot-01/review-metadata.json`
+- `local_ccra_reviews/round-04/pilot-01/review-context.md`
+- `local_ccra_reviews/round-04/pilot-01/review-file-manifest.json`
+- `local_ccra_reviews/round-04/pilot-01/owner-decision.md`
+- `local_ccra_reviews/round-04/pilot-01/gate-manifest.yaml`
+- `local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml`
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.md`
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.json`
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.md`
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.json`
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md`
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json`
+
+### Round 04 And Round 04.1 Evidence
+
+- `reports/Round04_blind_input_candidates_2026-06-18.md`
+- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
+- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md`
+- `reports/selector_regression_report_v0.2.md`
+- `reports/selector_calibration_smoke_report.md`
+- `reports/validation_report.md`
+- `reports/index_rebuild_report.md`
+- `reports/model_card_sync_report_v0.2.md`
+- `reports/content_review_report_v0.2.md`
+- `reports/Codex新会话交接文档_Round04.1关闭与Round05准备_2026-06-18.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/BUNDLE_FILE_MANIFEST_04.1.md`
+
+### Selector, Tests, Scripts, And Model Status
+
+- `selector/README.md`
+- `selector/selector_rules.json`
+- `selector/round04_blind_inputs.json`
+- `selector/selector_calibration_inputs.json`
+- `tests/README.md`
+- `tests/test_round04_blind_routing.py`
+- `tests/test_round04_post_patch_verification.py`
+- `tests/qpi.regression.json`
+- `tests/intellectual_archaeology.regression.json`
+- `tests/regression_cases.json`
+- `scripts/run_selector_demo.py`
+- `scripts/run_round04_blind_routing.py`
+- `scripts/run_round04_post_patch_verification.py`
+- `models/qpi.model.json`
+- `models/intellectual_archaeology.model.json`
+- `models/model_index.json`
+
+## 5. Automation Outputs Used
+
+- helper_id: review-context-builder
+  - output_path: `local_ccra_reviews/round-04/pilot-01/review-context.md`
+  - status: available
+  - how_used: navigation index only; it did not replace direct file reading.
+- helper_id: review-bundle-audit
+  - output_path: `local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.md`
+  - status: available_with_findings
+  - how_used: evidence that the generic audit profile reported two blocking findings against the Round 04 bundle.
+- helper_id: regression-validation-gate-runner
+  - output_path: `local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.md`
+  - status: dry_run
+  - how_used: evidence that three gates were declared but not executed in this pilot helper run.
+- helper_id: lifecycle-status-guard-scan
+  - output_path: `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md`
+  - status: available_with_findings
+  - how_used: candidate lifecycle/status overclaim list only; final lifecycle assessment below is reviewer judgment.
+- helper_id: routing-behavior-diff-audit
+  - output_path: none
+  - status: skipped
+  - how_used: not used; this is a tuning gap because Round 04.1 has before/after behavior evidence.
+
+## 6. Executive Summary
+
+Result: `needs_more_local_tuning`.
+
+Local evidence was materially stronger than a limited Web upload would be. This child session could inspect project rules, the full knowledge base, Round 04 and Round 04.1 bundles, reports, selector rules, tests, scripts, helper outputs, and current model status directly. That local access is enough to produce a stronger first-pass review than a compressed upload-only review.
+
+The Round 04 evidence also shows Local CCRA tuning gaps that should be addressed before formal Round 05 use. The largest gaps are not product-source blockers for this historical pilot; they are runtime/helper/report-quality gaps: the bundle audit profile produced generic-profile blockers against versioned bundle names, the validation helper was dry-run only, routing diff audit was skipped even though before/after routing evidence exists, and the lifecycle scan produced broad findings that need triage rather than automatic blocking.
+
+Round 04.1's selector repair looks appropriately scoped: four target cases passed, `R04-BI-022` was documented as collateral behavior and regression-covered, and both models remain `draft / B / pending`. However, Round 04 also exposed unresolved calibration questions around governance, capacity/resource/path, ambiguous low-context inputs, and natural Intellectual Archaeology under-selection. Those should be treated as future calibration or Round 05 scope decisions, not silently patched inside this pilot.
+
+This report is suitable for later comparison against Web CCRA feedback if it is used as pilot-local reviewer output, not as Owner approval, Web CCRA approval, lifecycle promotion, or Round 05 acceptance.
+
+## 7. Findings
+
+### Finding LCCRA-R04-P01-F01
+
+Classification: major
+
+Title: Local file access produced a stronger review surface than a limited upload bundle.
+
+Evidence:
+
+- `review-file-manifest.json` reports no missing source roots and 77 included files across docs, knowledge assets, reports, selector, tests, and review bundles.
+- `knowledge_assets/10_本地CCRA评审机制说明.md` defines Local CCRA as formal local first review that reads project evidence directly.
+- `README.md`, `PROJECTS.md`, and `docs/WORKFLOW.md` define Local CCRA run records, review bundle boundaries, and Owner/Web authority boundaries.
+- Direct reads included `knowledge_assets/`, Round 04 reports, Round 04.1 reports, selector rules, scripts, tests, and helper outputs.
+
+Why It Matters:
+
+The pilot question asks whether Local CCRA can do better than a limited Web upload. For this round, the answer is yes: the reviewer could inspect surrounding governance and runtime context that a compressed Web bundle would usually omit or summarize.
+
+Recommended Action:
+
+Keep Local CCRA as a file-first first-pass review lane, but require the report to cite exact files read and separate helper evidence from reviewer judgment.
+
+Owner Decision Required: yes
+
+Blocks Web Final Review: no
+
+Blocks Lifecycle Change: yes, because Local CCRA evidence does not itself authorize lifecycle promotion.
+
+### Finding LCCRA-R04-P01-F02
+
+Classification: major
+
+Title: Helper outputs are not yet reliable enough for formal Round 05 without tuning.
+
+Evidence:
+
+- `helper-outputs/bundle-audit.md` reports `FAIL`, missing `manifest` and `validation_sidecar`, while the bundle itself has `BUNDLE_FILE_MANIFEST_04.md`.
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md` exists and lists the Round 04 bundle files.
+- `helper-outputs/gate-run-report.md` reports `DRY_RUN`, with three declared gates and zero commands run.
+- `agent-invocation-packet.md` records `routing-behavior-diff-audit` as skipped.
+- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md` contains exactly the kind of before/after routing evidence that a routing diff helper should consume.
+
+Why It Matters:
+
+The helper layer is useful, but in this pilot it produced evidence that requires reviewer interpretation. A generic bundle profile treated versioned bundle naming as missing manifest evidence, and dry-run gate output cannot be cited as fresh validation execution.
+
+Recommended Action:
+
+Before Round 05, tune helper profiles to recognize versioned bundle names, decide whether zip validation sidecars are required for each bundle type, run gates in approved `run` mode when fresh validation is required, and run routing-behavior-diff-audit when before/after routing reports exist.
+
+Owner Decision Required: yes, for whether helper execution should be mandatory before formal Round 05.
+
+Blocks Web Final Review: no for this historical pilot; yes if Round 05 claims fresh local gate execution without running it.
+
+Blocks Lifecycle Change: yes.
+
+### Finding LCCRA-R04-P01-F03
+
+Classification: calibration
+
+Title: Round 04.1 fixed reviewed failures without broadening QPI into every organization-like input.
+
+Evidence:
+
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md` limits target labels to `R04-BI-002`, `R04-BI-024`, `R04-BI-035`, and `R04-BI-036`.
+- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md` reports four targeted cases checked, zero targeted failures, and five behavior changes.
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md` states that governance, capacity, and ambiguous-context cases are not patched in 04.1.
+- `selector/README.md` records the Round 04.1 selector rule as translation no-call, instruction/payload separation, IA hard exclusion variants, and depth-limited QPI override.
+
+Why It Matters:
+
+This is good scope discipline. Round 04.1 did not turn QPI into a generic detector for every governance, organization, capacity, or ambiguous input. That preserves the project's non-goal boundary and lets future calibration decide recall expansion deliberately.
+
+Recommended Action:
+
+Treat the unpatched Round 04 categories as future calibration candidates. Do not broaden QPI or IA recall until Owner/Web CCRA identifies which category should become Round 05 scope.
+
+Owner Decision Required: yes
+
+Blocks Web Final Review: no for the historical pilot; potentially yes for a future claim that selector calibration is complete.
+
+Blocks Lifecycle Change: yes.
+
+### Finding LCCRA-R04-P01-F04
+
+Classification: calibration
+
+Title: `R04-BI-022` is a non-target behavior change, but it is documented and regression-covered.
+
+Evidence:
+
+- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md` records `R04-BI-022` before patch as `selected_models=[]` and `no_call=True`.
+- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md` records `R04-BI-022` after patch as `selected_models=['qpi']`, rejected IA, and `no_call=False`.
+- `reports/Codex新会话交接文档_Round04.1关闭与Round05准备_2026-06-18.md` records the rationale: the user rejected deeper expansion, not lightweight dominant-scarcity judgment.
+- `tests/qpi.regression.json` contains `case_qpi_round04_depth_limited_assumption_scarcity_001`.
+
+Why It Matters:
+
+This is exactly the kind of collateral behavior Local CCRA should catch. The current evidence handles it correctly: it is not hidden, not retroactively made a target case, and not left without regression protection.
+
+Recommended Action:
+
+Keep `R04-BI-022` as documented collateral behavior and preserve its regression case. In future Local CCRA runs, require a deterministic routing diff helper to surface similar non-target changes automatically.
+
+Owner Decision Required: yes, if the Owner wants to reclassify the collateral judgment.
+
+Blocks Web Final Review: no.
+
+Blocks Lifecycle Change: yes.
+
+### Finding LCCRA-R04-P01-F05
+
+Classification: major
+
+Title: Lifecycle/status guard findings require triage before formal Round 05 use.
+
+Evidence:
+
+- `helper-outputs/lifecycle-status-guard-scan.md` reports 21 blocking findings, mostly approval-claim phrase candidates involving hyphenated Owner-approval wording.
+- `docs/QPI_CONTEXTUAL_ROUTING_RULES.md`, `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md`, `models/qpi.model.json`, `models/intellectual_archaeology.model.json`, and `models/model_index.json` all keep QPI and IA at `draft / B / pending`.
+- `knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md` states that engineering contract pass does not equal content stability and that QPI/IA must not be upgraded to stable from validation alone.
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md` explicitly says Round 04 alone must not upgrade lifecycle status.
+
+Why It Matters:
+
+The model lifecycle boundary is currently preserved, but the scan findings show that the status guard needs a triage workflow. Some findings appear to be policy or draft-case phrasing rather than direct lifecycle field changes. Formal Round 05 should not inherit an unresolved `FAIL` scan without reviewer triage.
+
+Recommended Action:
+
+Before Round 05, classify lifecycle scan findings into true overclaims, policy/example language, source review metadata, and accepted decision records. Tune the config or report template so a helper `FAIL` becomes reviewable evidence, not automatic rejection.
+
+Owner Decision Required: yes, for any wording repairs or scan-scope decisions.
+
+Blocks Web Final Review: yes if unresolved findings are included in the claimed review scope.
+
+Blocks Lifecycle Change: yes.
+
+### Finding LCCRA-R04-P01-F06
+
+Classification: calibration
+
+Title: Invocation authenticity is adequate for this pilot, but return-state bookkeeping remains orchestrator work.
+
+Evidence:
+
+- `run-notes.md` records `carrier_type: codex_thread`, `invocation_mode: prompt_path_reference`, `child_session_id: 019edca7-48f3-79d3-be4a-550f4df0f13c`, and `dispatch_status: dispatched`.
+- `agent-invocation-packet.md` requires a real child session or equivalent isolated participant context and sets `simulation_allowed: false`.
+- This report and `returned-output.md` are written by the invoked child session under the exact output contract.
+- `run-notes.md` still records `return_status: pending`; this reviewer did not modify it because the user constrained writes to the two required output files.
+
+Why It Matters:
+
+The pilot tests real child-session behavior. The dispatch record is present, but final run bookkeeping still needs the main project session to record return completion after consuming this report.
+
+Recommended Action:
+
+Have the orchestrating main session update `run-notes.md` after receiving this report. Keep reviewer writes limited to the formal output files unless the invocation packet explicitly authorizes run-note updates.
+
+Owner Decision Required: no for bookkeeping; yes for accepting invocation validity if there is any carrier-id mismatch.
+
+Blocks Web Final Review: no.
+
+Blocks Lifecycle Change: yes.
+
+### Finding LCCRA-R04-P01-F07
+
+Classification: minor
+
+Title: Review context includes cache/binary artifacts that should be excluded from future context manifests.
+
+Evidence:
+
+- `review-context.md` and `review-file-manifest.json` include `tests/__pycache__/*.pyc` and optional raw zip files.
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md` states raw zip files are optional and excludes cache files from raw zip contents.
+
+Why It Matters:
+
+Cache and binary artifacts increase manifest noise and may distract future reviewers. They do not block this pilot because source files were still available and read directly.
+
+Recommended Action:
+
+Tune `review-context-builder` profiles to exclude `__pycache__/`, `*.pyc`, and optionally list zip archives as binary side artifacts rather than normal review files.
+
+Owner Decision Required: no, unless the Owner wants zip contents audited as mandatory evidence.
+
+Blocks Web Final Review: no.
+
+Blocks Lifecycle Change: no, but lifecycle remains unpromoted for other reasons.
+
+## 8. Non-Target Behavior Changes
+
+Observed non-target or collateral behavior from Round 04.1:
+
+- `R04-BI-022`: before `selected=[]`, `no_call=True`; after `selected=['qpi']`, rejected IA, `no_call=False`. Assessment: documented collateral behavior, regression-covered, not a hidden failure.
+
+Target changes recorded in the same before/after pool:
+
+- `R04-BI-002`: translation task moved from QPI selection to no-call.
+- `R04-BI-024`: explicit IA refusal moved from IA+QPI selection to QPI-only with IA rejected.
+- `R04-BI-035`: depth-limited dominant-scarcity request moved from no-call to QPI.
+- `R04-BI-036`: depth-limited scarcity-set request moved from no-call to QPI.
+
+Unpatched Round 04 categories to keep visible for future calibration:
+
+- governance / responsibility / consensus cases: `R04-BI-010` through `R04-BI-013`
+- capacity / resource / path cases: `R04-BI-014`, `R04-BI-015`, `R04-BI-017`, with `R04-BI-016` already selecting QPI
+- natural IA boundary cases: `R04-BI-026`, `R04-BI-027`, `R04-BI-038`
+- ambiguous low-context and growth how-to cases: `R04-BI-028` through `R04-BI-030`, `R04-BI-037`
+
+These are not Round 04.1 failures unless Owner/Web CCRA defines expected labels for them.
+
+## 9. Engineering Pass vs Product Judgment
+
+What engineering evidence shows:
+
+- Round 04 first blind run preserved no-answer-key discipline and wrote a routing report over 38 frozen inputs.
+- Round 04.1 added targeted regression cases, patched selector rules, reran the frozen pool, and reported zero targeted failures across four reviewed cases.
+- Current reports show index check, validation, selector regression, selector calibration smoke, and model/card sync as PASS in existing project reports.
+- Current model JSON status remains `draft / B / pending` for QPI and Intellectual Archaeology.
+
+What product/model-governance question remains:
+
+- Which Round 04 unpatched cases should become calibration inputs, regression cases, or future selector changes?
+- Should natural IA boundary cases such as `R04-BI-026`, `R04-BI-027`, and `R04-BI-038` continue to route through QPI first, or should IA recall be broadened with a stricter depth gate?
+- Should governance and capacity cases that currently no-call become low-confidence QPI candidates, or stay unpatched to avoid over-selecting QPI?
+- Which lifecycle-scan findings are true wording risks versus helper false positives or acceptable policy language?
+
+What evidence would close the gap:
+
+- Owner/Web CCRA expected labels for selected Round 04 unpatched cases.
+- A routing-behavior-diff-audit report over Round 04 before/after behavior.
+- A non-dry-run gate report, if fresh validation is required for Round 05.
+- A triaged lifecycle-status scan report.
+- Owner decision entries for accepted, rejected, deferred, and escalated Local CCRA findings.
+
+## 10. Lifecycle And Scope Guard
+
+Claim: QPI and Intellectual Archaeology remain draft / B / pending.
+
+- Evidence: `models/qpi.model.json`, `models/intellectual_archaeology.model.json`, `models/model_index.json`, `docs/QPI_CONTEXTUAL_ROUTING_RULES.md`, `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md`.
+- Required authority: Owner and Web/CCRA review for any lifecycle change.
+- Assessment: Preserved. No lifecycle promotion should be inferred from Round 04, Round 04.1, or this Local CCRA pilot.
+
+Claim: Round 04.1 closeout does not start or accept Round 05.
+
+- Evidence: `reports/Codex新会话交接文档_Round04.1关闭与Round05准备_2026-06-18.md` says Round 04.1 closeout did not enter Round 05.
+- Required authority: Owner decision for Round 05 start/scope.
+- Assessment: Preserved. This pilot is comparison/tuning evidence only.
+
+Claim: Engineering PASS means product acceptance.
+
+- Evidence: `knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md`, `knowledge_assets/09_数据治理与模型调用机制说明.md`, and `content_review_report_v0.2.md` explicitly reject that equivalence.
+- Required authority: Owner/Web CCRA content and lifecycle review.
+- Assessment: Not supported. Engineering evidence is necessary but insufficient.
+
+Claim: Local CCRA report equals Web CCRA final approval.
+
+- Evidence: `knowledge_assets/10_本地CCRA评审机制说明.md`, `docs/WORKFLOW.md`, and `ccra-local-review.runtime.md` say Local CCRA does not replace Owner or Web CCRA.
+- Required authority: Owner decides whether to include this report in any Web CCRA upload.
+- Assessment: Not supported.
+
+## 11. Local Tuning Recommendations
+
+1. Add a routing-behavior-diff-audit step for Round 04.1-style before/after reports, including target and non-target behavior classification.
+2. Tune `review-bundle-audit` for this project's versioned bundle names, or add a `the-mindscape-round-bundle` profile that recognizes `BUNDLE_FILE_MANIFEST_04.md` and optional sidecar rules.
+3. Decide whether gate-runner should run declared gates before formal Round 05 Local CCRA; if yes, run in approved `run` mode and cite logs.
+4. Triage lifecycle scan findings and update the guard config or wording rules so policy examples and true approval claims are separated.
+5. Add a required report subsection for unresolved calibration candidates, especially governance/capacity inputs and natural IA boundary cases.
+6. Exclude cache and binary artifacts from review-context manifests unless the round explicitly audits packaging.
+7. Have the main project session update `run-notes.md` after report return; the child reviewer should remain read-only except for contracted outputs.
+
+## 12. Web Final Review Readiness
+
+Choice: `ready_after_local_repairs`
+
+Explanation:
+
+This historical pilot report is ready for later comparison against Web CCRA feedback. It is not a Web final review package and should not be used as Round 05 acceptance. Before formal Round 05 Local CCRA use, the project should repair helper profiles, run or explicitly waive fresh gates, add routing diff helper output where before/after behavior exists, and triage lifecycle findings.
+
+For the Round 04 / 04.1 historical evidence itself, no additional selector patch is recommended by this Local CCRA report. The next product step should be Owner/Web CCRA scoping for Round 05, not automatic selector expansion.
+
+## 13. Owner Decision Points
+
+- decision_id: OD-LCCRA-R04-P01-001
+  - decision_needed: Accept this child-session output as valid Local CCRA pilot output?
+  - options: accept / rerun in another child session / mark invalid
+  - recommended_default: accept, because run notes record a child session id and this report reads local files directly.
+
+- decision_id: OD-LCCRA-R04-P01-002
+  - decision_needed: Should Local CCRA helper execution be mandatory before Round 05?
+  - options: mandatory run mode / dry-run acceptable / helper outputs optional
+  - recommended_default: mandatory for context, bundle, lifecycle, and routing diff; gate execution depends on Owner approval.
+
+- decision_id: OD-LCCRA-R04-P01-003
+  - decision_needed: Which Round 04 unpatched categories should become Round 05 calibration scope?
+  - options: governance/capacity QPI recall / natural IA recall / ambiguous context policy / no selector work
+  - recommended_default: decide scope explicitly before changing selector rules.
+
+- decision_id: OD-LCCRA-R04-P01-004
+  - decision_needed: Should this Local CCRA report be sent to Web CCRA for comparison?
+  - options: include full report / include summary only / keep local-only
+  - recommended_default: keep local-only until Owner provides Web CCRA feedback to compare.
+
+## 14. Limits And Uncertainty
+
+- I did not modify any project file except this report and `returned-output.md`.
+- I did not update `run-notes.md`; the main project session should record return completion.
+- I did not execute validation gates during this child review. The helper gate report was dry-run only, while existing project reports record prior PASS evidence.
+- I did not inspect zip contents manually beyond the helper's readable-zip evidence and bundle manifests.
+- No Web CCRA feedback for this pilot was supplied yet, so comparison quality can only be judged prospectively.
+- I did not decide Owner approval, Web approval, lifecycle promotion, or Round 05 acceptance.
+
+## 15. Resume Instructions
+
+Resume this same child session when comparing against later Web CCRA feedback or tuning the `ccra-local-reviewer` report style.
+
+For a same-session resume, provide:
+
+- this report path
+- `returned-output.md`
+- any Owner decision file updates
+- the Web CCRA feedback file or pasted path
+- a list of changed evidence since this report
+
+For a new child session, include:
+
+- `local_ccra_reviews/round-04/pilot-01/agent-invocation-packet.md`
+- `local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md`
+- `local_ccra_reviews/round-04/pilot-01/returned-output.md`
+- `local_ccra_reviews/round-04/pilot-01/owner-decision.md` if filled
+- `local_ccra_reviews/round-04/pilot-01/review-context.md`
+- `local_ccra_reviews/round-04/pilot-01/review-file-manifest.json`
+- helper outputs under `local_ccra_reviews/round-04/pilot-01/helper-outputs/`
+- any Web CCRA comparison material supplied by the Owner

local_ccra_reviews/round-04/pilot-01/05_WEB_LOCAL_CCRA_COMPARISON.md

@@ -0,0 +1,139 @@
+# Web CCRA And Local CCRA Comparison Notes
+
+## Scope
+
+- comparison_target: Round 04 / Round 04.1 planning and review-quality comparison
+- web_source: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\讨论\2026-06-18产品交流-GPT.md`
+- web_source_range: lines 1-214 only
+- local_source: `local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md`
+- comparison_date: 2026-06-19
+
+This note compares the first two Web CCRA/GPT exchanges with the Local CCRA pilot report. It does not use later Web exchanges after line 214.
+
+## High-Level Judgment
+
+The Web review is stronger at product diagnosis and next-action framing. It quickly identifies the actual Round 04 issue class, selects the four cases that should define Round 04.1, and says exactly what the post-patch review bundle must contain.
+
+The Local CCRA report is stronger at full-file evidence coverage, auditability, runtime/helper risk discovery, lifecycle guard review, and before/after evidence preservation. Its main weakness is that it reviewed from the already-built Round 04.1 evidence set, so it reads more like a local governance and readiness audit than the original Web-style product diagnosis that decided what Round 04.1 should be.
+
+## Where Web Was Better
+
+### 1. Product Diagnosis
+
+Web CCRA immediately classifies `R04-BI-002` as a rule-based selector no-call coverage problem, not an LLM understanding failure.
+
+It also names the real mechanism: the selector did not distinguish instruction from payload, so words inside a translation payload triggered QPI.
+
+Local CCRA agrees with the final outcome, but it does not reconstruct this diagnosis with the same sharpness. It mainly records that `R04-BI-002` moved from QPI selection to no-call after Round 04.1.
+
+### 2. Repair Scope Selection
+
+Web identifies the right repair set:
+
+- `R04-BI-002`: translation should become no-call.
+- `R04-BI-024`: explicit refusal of Intellectual Archaeology should reject IA.
+- `R04-BI-035` and `R04-BI-036`: depth-limited requests should allow lightweight QPI, not hard no-call.
+
+Local CCRA confirms these four target cases and verifies that Round 04.1 did not broaden QPI too aggressively. But Web is better at explaining why these four, and not the broader governance/capacity cases, should define the patch.
+
+### 3. Review Package Requirements
+
+Web is clearer that Round 04.1 must include a post-patch routing verification report, not only rule diffs.
+
+It specifies three verification layers:
+
+- targeted regression for the four cases;
+- full Round 04 rerun as post-patch comparison;
+- existing selector regression / calibration smoke / unit tests.
+
+Local CCRA notices that this evidence exists and points out that routing diff automation should consume it. But Web gives the better owner-facing instruction before the materials are prepared.
+
+## Where Local Was Better
+
+### 1. Evidence Coverage
+
+Local CCRA read the project rules, knowledge assets, Round 04 and Round 04.1 bundles, reports, selector rules, tests, scripts, helper outputs, and model status directly.
+
+This gives Local CCRA a broader review surface than the Web exchange, especially for checking whether the produced Round 04.1 materials actually match the earlier Web instructions.
+
+### 2. Non-Target Behavior Tracking
+
+Local CCRA explicitly identifies `R04-BI-022` as a non-target behavior change after Round 04.1:
+
+- before: no-call;
+- after: QPI selected, IA rejected;
+- assessment: documented collateral behavior and regression-covered.
+
+This is a strong local advantage. Web lines 1-214 define the need for before/after comparison, but they do not yet see or judge this collateral behavior because that evidence appears only after Round 04.1 is produced.
+
+### 3. Runtime And Helper Quality
+
+Local CCRA finds process-level issues that Web does not cover in the first two exchanges:
+
+- generic `review-bundle-audit` profile does not recognize versioned manifests;
+- gate runner was dry-run only;
+- `routing-behavior-diff-audit` was skipped even though before/after routing evidence existed;
+- lifecycle/status scan requires triage rather than automatic blocking;
+- context manifest contains cache/binary noise.
+
+These findings matter for making Local CCRA useful in Round 05, because they affect repeatability and the trustworthiness of future local reports.
+
+### 4. Lifecycle And Authority Discipline
+
+Both Web and Local preserve the rule that Round 04 / 04.1 do not upgrade QPI or Intellectual Archaeology.
+
+Local CCRA adds stronger file-backed checks: model JSON, model index, lifecycle guard, knowledge assets, and project workflow docs all keep the status boundary visible.
+
+## Key Difference
+
+Web CCRA acted like the product reviewer at the moment of deciding what to fix next.
+
+Local CCRA acted like a file-first auditor after the fix existed.
+
+That difference is acceptable for this pilot, but for Round 05 the Local CCRA should be tuned to include both modes:
+
+1. diagnose the next product decision as sharply as Web CCRA;
+2. audit the full file evidence more thoroughly than Web CCRA can.
+
+## Local CCRA Tuning Implications
+
+For the next pilot or formal Round 05 run, tune `ccra-local-reviewer` to require:
+
+1. A Web-style "issue mechanism" section:
+   - what failed;
+   - why it failed;
+   - why it is not a different category of failure.
+
+2. A "patch scope" section:
+   - must-fix cases;
+   - same-class boundary cases;
+   - calibration-only cases;
+   - cases explicitly not patched.
+
+3. A mandatory before/after behavior section when post-patch evidence exists:
+   - target behavior changes;
+   - non-target behavior changes;
+   - accepted collateral changes;
+   - unexpected regressions.
+
+4. A helper-output confidence section:
+   - helper output used as evidence;
+   - helper false positive or profile mismatch;
+   - dry-run versus executed validation;
+   - missing helper that should have run.
+
+5. A final recommendation shape that mirrors Web CCRA:
+   - fix now;
+   - document only;
+   - defer to calibration;
+   - do not open another small patch round.
+
+## Practical Conclusion
+
+Local CCRA is not worse than Web CCRA, but its current prompt/report shape is biased toward governance audit. Web CCRA is better at the early product-review judgment that decides what the next repair round should be.
+
+The target for Round 05 should be:
+
+- Web remains the planning and final review partner.
+- Local CCRA performs the deep local first review with full file access.
+- Local CCRA must include a Web-style diagnosis and repair-scope judgment so it can reduce small follow-up rounds instead of only auditing them after they happen.

local_ccra_reviews/round-04/pilot-01/agent-invocation-packet.md

@@ -0,0 +1,224 @@
+---
+packet_type: local-ccra-agent-invocation-packet
+runtime_id: ccra-local-review
+agent_id: ccra-local-reviewer
+runtime_version: 0.1.0
+agent_version: 0.1.0
+review_id: round-04-pilot-01
+status: ready_for_dispatch
+---
+
+# Local CCRA Agent Invocation Packet
+
+## 1. Invocation Metadata
+
+```yaml
+packet_id: round-04-pilot-01
+created_at: 2026-06-19
+client_project_root: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong
+knowledge_base_path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets
+review_round: round-04
+local_pass: pilot-01
+review_run_dir: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01
+invocation_mode: prompt_path_reference
+carrier_type: codex_thread
+child_session_id: pending
+persistent_child_session_required: true
+simulation_allowed: false
+```
+
+## 2. Canonical Artifacts
+
+```yaml
+canonical_agent_path: C:\Users\wangq\Documents\Codex\ccpe-system\agents\agent-specs\ccra-local-reviewer.agent.md
+canonical_runtime_path: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review.runtime.md
+runtime_setup_path: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-runtime-setup.md
+report_template_path: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-report.template.md
+integration_registration_path: C:\Users\wangq\Documents\Codex\ccpe-system\integrations\skills-vault\ccra-local-review-helpers.integration.md
+```
+
+## 3. Role Integrity Requirement
+
+The invoked participant must act as `ccra-local-reviewer`.
+
+The reviewer must:
+
+```text
+read local evidence directly
+cite files actually read
+use helper outputs only as evidence
+write the report to the requested output contract
+preserve Owner/Web CCRA authority boundaries
+avoid project file edits except the required report and returned output
+avoid lifecycle promotion
+avoid main-session roleplay
+```
+
+If this packet cannot be dispatched to a real child session or equivalent isolated participant context, the valid state is:
+
+```text
+blocked_waiting_for_participant_output
+```
+
+## 4. Task Context
+
+```yaml
+primary_question: Does Local CCRA produce Web CCRA-level review quality when it can inspect the full local Round 04 evidence set?
+scope_statement: Review Round 04 blind routing evaluation evidence as a historical pilot. Focus on invocation authenticity, persistence, report quality, evidence coverage, non-target behavior awareness, lifecycle/scope discipline, and readiness gaps for future Round 05 use.
+non_goals:
+  - Do not decide Owner approval.
+  - Do not replace Web CCRA final review.
+  - Do not promote lifecycle status.
+  - Do not modify selector rules, model cards, model JSON, regression cases, or review bundles.
+  - Do not treat this pilot as Round 05 acceptance.
+local_tuning_stage: historical_pilot
+web_final_review_target: none_for_this_pilot
+known_prior_rounds:
+  - round-03
+  - round-03.1
+  - round-03.2
+  - round-03.2a
+  - round-04
+  - round-04.1
+owner_supplied_notes: Compare later against Web CCRA feedback supplied by Owner. Pilot should test child-session reality, resumability, and report quality.
+```
+
+## 5. Input Files
+
+Required:
+
+```text
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\README.md
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\AGENTS.md
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets\README.md
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets\
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\review-context.md
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\review-file-manifest.json
+```
+
+Project and round-specific evidence:
+
+```text
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\PROJECTS.md
+  purpose: project boundary and supplier rules
+  required: true
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets
+  purpose: required Local CCRA knowledge base; do not duplicate into run directory
+  required: true
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\docs\WORKFLOW.md
+  purpose: workflow and review rules
+  required: true
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\docs\DECISIONS.md
+  purpose: accepted selector and lifecycle decisions
+  required: true
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\reports\Round04_blind_routing_evaluation_report_2026-06-18.md
+  purpose: Round 04 evaluation report
+  required: true
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\reports\Round04_1_post_patch_routing_verification_report_2026-06-18.md
+  purpose: post-patch verification context for collateral behavior awareness
+  required: false
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\selector\round04_blind_inputs.json
+  purpose: full Round 04 blind input set
+  required: true
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\selector\selector_rules.json
+  purpose: current selector rules
+  required: true
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\tests\test_round04_blind_routing.py
+  purpose: Round 04 test surface
+  required: false
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\tests\test_round04_post_patch_verification.py
+  purpose: Round 04.1 post-patch test surface
+  required: false
+```
+
+Review bundles:
+
+```text
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\ccra_review_bundle\round-04_2026-06-18_blind-input-routing-evaluation
+  purpose: primary Round 04 Web CCRA review bundle
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\ccra_review_bundle\round-04.1_2026-06-18_selector-rule-patch
+  purpose: optional post-patch context for understanding later accepted changes
+```
+
+Helper outputs:
+
+```text
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\helper-outputs\bundle-audit.md
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\helper-outputs\bundle-audit.json
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\helper-outputs\gate-run-report.md
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\helper-outputs\gate-run-report.json
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\helper-outputs\lifecycle-status-guard-scan.md
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\helper-outputs\lifecycle-status-guard-scan.json
+```
+
+Unavailable helper outputs:
+
+```text
+- routing-behavior-diff-audit: skipped for initial pilot unless before/after routing result files are supplied or identified.
+```
+
+## 6. Output Contract
+
+The reviewer must write:
+
+```yaml
+primary_report_path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\04_LOCAL_CCRA_REVIEW_REPORT.md
+returned_output_path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\returned-output.md
+required_report_template: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-report.template.md
+```
+
+The report must include:
+
+```text
+return metadata
+review scope
+inputs actually received
+files actually read
+automation outputs used
+executive summary
+findings
+non-target behavior changes
+engineering pass vs product judgment
+lifecycle and scope guard
+local tuning recommendations
+Web final review readiness
+Owner decision points
+limits and uncertainty
+resume instructions
+```
+
+## 7. Continuity Policy
+
+```yaml
+same_child_session_preferred: true
+resume_allowed: true
+resume_requires:
+  - previous report
+  - owner-decision.md when present
+  - new or changed evidence list
+  - unchanged-evidence statement
+```
+
+Follow-up review should inspect changed or newly supplied evidence first. Full rerun is required when invocation evidence is invalid, required evidence was missing, or the Owner requests a full rerun.
+
+## 8. Session Logging
+
+The project main session must record dispatch method, child session id, helper commands, exit codes, files written, skipped helpers, and manual approvals in:
+
+```text
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\run-notes.md
+```
+
+## 9. No-Simulation Requirement
+
+Formal Local CCRA output must not be simulated in the project main session.
+
+If a simulated dry run is explicitly requested, label it:
+
+```text
+simulation-only
+excluded-from-synthesis
+not-a-formal-report
+```
+
+Simulation-only output cannot be used as the Local CCRA report.

local_ccra_reviews/round-04/pilot-01/gate-manifest.yaml

@@ -0,0 +1,32 @@
+gates:
+  - gate_id: index-check
+    command:
+      - python
+      - scripts\rebuild_indexes.py
+      - --check
+    working_directory: .
+    expected_exit_code: 0
+    log_file: logs/index-check.log
+    timeout_seconds: 120
+    required_before_review: true
+  - gate_id: model-library-validation
+    command:
+      - python
+      - scripts\validate_model_library.py
+    working_directory: .
+    expected_exit_code: 0
+    log_file: logs/model-library-validation.log
+    timeout_seconds: 120
+    required_before_review: true
+  - gate_id: round04-blind-routing-tests
+    command:
+      - python
+      - -m
+      - pytest
+      - tests\test_round04_blind_routing.py
+      - tests\test_round04_post_patch_verification.py
+    working_directory: .
+    expected_exit_code: 0
+    log_file: logs/round04-blind-routing-tests.log
+    timeout_seconds: 240
+    required_before_review: false

local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.json

@@ -0,0 +1,74 @@
+{
+  "bundle_root": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\ccra_review_bundle\\round-04_2026-06-18_blind-input-routing-evaluation",
+  "profile": "generic",
+  "files_discovered": [
+    "00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md",
+    "01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md",
+    "02_BLIND_INPUT_SET_04.md",
+    "03_ROUTING_EVALUATION_REPORT_04.md",
+    "04_REVIEW_QUESTIONS_FOR_GPT_04.md",
+    "BUNDLE_FILE_MANIFEST_04.md",
+    "optional_raw_changed_files_04.zip"
+  ],
+  "required_files_present": {
+    "brief": [
+      "00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md"
+    ]
+  },
+  "required_files_missing": [
+    "manifest",
+    "validation_sidecar"
+  ],
+  "optional_files_present": {
+    "report": [
+      "03_ROUTING_EVALUATION_REPORT_04.md"
+    ],
+    "zip": [
+      "optional_raw_changed_files_04.zip"
+    ]
+  },
+  "manifest_status": {
+    "status": "missing",
+    "files": []
+  },
+  "zip_status": {
+    "status": "readable",
+    "files": [
+      "optional_raw_changed_files_04.zip"
+    ],
+    "entry_counts": {
+      "optional_raw_changed_files_04.zip": 29
+    }
+  },
+  "validation_sidecar_status": {
+    "status": "missing",
+    "files": []
+  },
+  "report_status": {
+    "status": "present",
+    "files": [
+      "03_ROUTING_EVALUATION_REPORT_04.md"
+    ]
+  },
+  "warnings": [
+    "Extra file not matched by profile: 01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md",
+    "Extra file not matched by profile: 02_BLIND_INPUT_SET_04.md",
+    "Extra file not matched by profile: 04_REVIEW_QUESTIONS_FOR_GPT_04.md",
+    "Extra file not matched by profile: BUNDLE_FILE_MANIFEST_04.md"
+  ],
+  "blocking_errors": [
+    "Missing required manifest file.",
+    "Missing required validation_sidecar file."
+  ],
+  "machine_readable_summary": {
+    "status": "FAIL",
+    "files_discovered_count": 7,
+    "required_missing_count": 2,
+    "warning_count": 4,
+    "blocking_error_count": 2,
+    "manifest_status": "missing",
+    "zip_status": "readable",
+    "validation_sidecar_status": "missing",
+    "report_status": "present"
+  }
+}

local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.md

@@ -0,0 +1,48 @@
+# Review Bundle Audit
+
+## Summary
+
+- Status: `FAIL`
+- Bundle root: `C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\ccra_review_bundle\round-04_2026-06-18_blind-input-routing-evaluation`
+- Profile: `generic`
+- Files discovered: 7
+- Required files missing: 2
+- Warnings: 4
+- Blocking errors: 2
+
+## Required Files
+
+- `brief`: `00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md`
+
+Missing:
+- `manifest`
+- `validation_sidecar`
+
+## Package Status
+
+- `manifest_status`: `missing` (none)
+- `validation_sidecar_status`: `missing` (none)
+- `zip_status`: `readable` (`optional_raw_changed_files_04.zip`)
+- `report_status`: `present` (`03_ROUTING_EVALUATION_REPORT_04.md`)
+
+## Blocking Errors
+
+- Missing required manifest file.
+- Missing required validation_sidecar file.
+
+## Warnings
+
+- Extra file not matched by profile: 01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md
+- Extra file not matched by profile: 02_BLIND_INPUT_SET_04.md
+- Extra file not matched by profile: 04_REVIEW_QUESTIONS_FOR_GPT_04.md
+- Extra file not matched by profile: BUNDLE_FILE_MANIFEST_04.md
+
+## Files Discovered
+
+- `00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md`
+- `01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md`
+- `02_BLIND_INPUT_SET_04.md`
+- `03_ROUTING_EVALUATION_REPORT_04.md`
+- `04_REVIEW_QUESTIONS_FOR_GPT_04.md`
+- `BUNDLE_FILE_MANIFEST_04.md`
+- `optional_raw_changed_files_04.zip`

local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.json

@@ -0,0 +1,48 @@
+{
+  "project_root": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
+  "gate_manifest_path": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\local_ccra_reviews\\round-04\\pilot-01\\gate-manifest.yaml",
+  "mode": "dry_run",
+  "commands_declared": [
+    "index-check",
+    "model-library-validation",
+    "round04-blind-routing-tests"
+  ],
+  "commands_run": [],
+  "commands_skipped": [
+    {
+      "gate_id": "index-check",
+      "reason": "dry_run"
+    },
+    {
+      "gate_id": "model-library-validation",
+      "reason": "dry_run"
+    },
+    {
+      "gate_id": "round04-blind-routing-tests",
+      "reason": "dry_run"
+    }
+  ],
+  "exit_codes": {},
+  "pass_fail_status": "DRY_RUN",
+  "duration": 0.0,
+  "log_paths": {},
+  "environment_notes": [
+    "Commands are declared by the manifest.",
+    "Passing gates are engineering evidence only; they do not imply product acceptance or lifecycle approval.",
+    "python: 3.11.15",
+    "platform: Windows-10-10.0.26200-SP0"
+  ],
+  "gate_results": [],
+  "manifest_errors": [],
+  "changed_files": [],
+  "machine_readable_summary": {
+    "status": "DRY_RUN",
+    "commands_declared_count": 3,
+    "commands_run_count": 0,
+    "commands_skipped_count": 3,
+    "manifest_error_count": 0,
+    "failed_count": 0,
+    "timeout_count": 0,
+    "changed_file_count": 0
+  }
+}

local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.md

@@ -0,0 +1,28 @@
+# Gate Run Report
+
+## Summary
+
+- Status: `DRY_RUN`
+- Commands declared: 3
+- Commands run: 0
+- Commands skipped: 3
+- Manifest errors: 0
+- Changed files: 0
+
+## Gate Results
+
+- None
+
+## Skipped Gates
+
+- `index-check`: dry_run
+- `model-library-validation`: dry_run
+- `round04-blind-routing-tests`: dry_run
+
+## Manifest Errors
+
+- None
+
+## Changed Files
+
+- None

local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json

@@ -0,0 +1,965 @@
+{
+  "scan_root": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
+  "config_path": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\local_ccra_reviews\\round-04\\pilot-01\\lifecycle-guard-config.yaml",
+  "files_scanned": [
+    "AGENTS.md",
+    "cards/card_index.md",
+    "cards/intellectual_archaeology.md",
+    "cards/qpi.md",
+    "cards/README.md",
+    "ccra_review_bundle/round-02_2026-06-16_second-audit/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md",
+    "ccra_review_bundle/round-02_2026-06-16_second-audit/01_GUIDANCE_PACK_AND_COMPLIANCE_MATRIX.md",
+    "ccra_review_bundle/round-02_2026-06-16_second-audit/02_CURRENT_ASSET_PACK.md",
+    "ccra_review_bundle/round-02_2026-06-16_second-audit/03_REPORTS_DIFF_AND_COMMAND_LOG.md",
+    "ccra_review_bundle/round-02_2026-06-16_second-audit/BUNDLE_FILE_MANIFEST.md",
+    "ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF03.1.md",
+    "ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/01_PATCH_MATRIX_03.1.md",
+    "ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/02_CURRENT_ASSET_PACK03.1.md",
+    "ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/03_VALIDATION_AND_COMMAND_LOG03.1.md",
+    "ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/04_REVIEW_QUESTIONS_FOR_GPT03.1.md",
+    "ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/BUNDLE_FILE_MANIFEST03.1.md",
+    "ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_03.2.md",
+    "ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/01_PATCH_MATRIX_03.2.md",
+    "ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/02_CURRENT_ASSET_PACK_03.2.md",
+    "ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/03_VALIDATION_AND_COMMAND_LOG_03.2.md",
+    "ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/04_REVIEW_QUESTIONS_FOR_GPT_03.2.md",
+    "ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/BUNDLE_FILE_MANIFEST_03.2.md",
+    "ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_03.2a.md",
+    "ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/01_PATCH_MATRIX_03.2a.md",
+    "ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/02_CURRENT_ASSET_PACK_03.2a.md",
+    "ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/03_VALIDATION_AND_COMMAND_LOG_03.2a.md",
+    "ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/04_REVIEW_QUESTIONS_FOR_GPT_03.2a.md",
+    "ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/BUNDLE_FILE_MANIFEST_03.2a.md",
+    "ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md",
+    "ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/01_GUIDANCE_PACK_AND_COMPLIANCE_MATRIX.md",
+    "ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/02_CURRENT_ASSET_PACK.md",
+    "ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/03_REPORTS_DIFF_AND_COMMAND_LOG.md",
+    "ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/04_QPI_CASE_PROMOTION_SUMMARY_AND_REVIEW_GUIDE.md",
+    "ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/05_REVIEW_QUESTIONS_FOR_GPT.md",
+    "ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/BUNDLE_FILE_MANIFEST.md",
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.1.md",
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md",
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md",
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md",
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md",
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/BUNDLE_FILE_MANIFEST_04.1.md",
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json",
+    "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md",
+    "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md",
+    "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md",
+    "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md",
+    "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md",
+    "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md",
+    "docs/CHATGPT_HANDOFF_RULES.md",
+    "docs/CONTENT_STABILIZATION_PROTOCOL.md",
+    "docs/DATA_CONTRACT.md",
+    "docs/DECISIONS.md",
+    "docs/FILE_TAXONOMY.md",
+    "docs/GPT_PLAN_LOCALIZATION_PROTOCOL.md",
+    "docs/HANDOFF_TEMPLATE.md",
+    "docs/INDEX_MAINTENANCE_PROTOCOL.md",
+    "docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md",
+    "docs/KNOWLEDGE_ASSET_RULES.md",
+    "docs/MODEL_CARD_CONTRACT.md",
+    "docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md",
+    "docs/model_case_preprocessing/qpi/README.md",
+    "docs/model_case_preprocessing/README.md",
+    "docs/MODEL_EXTRACTION_RULES.md",
+    "docs/MODEL_EXTRACTION_WORKFLOW.md",
+    "docs/NON_GOALS.md",
+    "docs/PROJECT_BRIEF.md",
+    "docs/QPI_CONTEXTUAL_ROUTING_RULES.md",
+    "docs/superpowers/plans/2026-06-16-model-extraction-contract-and-workflow.md",
+    "docs/superpowers/plans/2026-06-16-project-initialization.md",
+    "docs/superpowers/plans/2026-06-17-contract-hardening-selector-calibration.md",
+    "docs/superpowers/plans/2026-06-18-round04-1-selector-rule-patch.md",
+    "docs/superpowers/plans/2026-06-18-round04-blind-routing-evaluation.md",
+    "docs/WORKFLOW.md",
+    "knowledge_assets/00_用户背景与产品上下文.md",
+    "knowledge_assets/01_核心模型地图.md",
+    "knowledge_assets/02_模型卡结构规范.md",
+    "knowledge_assets/03_核心模型抽取样板.md",
+    "knowledge_assets/06_模型稳固性评级规则.md",
+    "knowledge_assets/07_产品规划过程记录.md",
+    "knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md",
+    "knowledge_assets/09_数据治理与模型调用机制说明.md",
+    "knowledge_assets/10_本地CCRA评审机制说明.md",
+    "knowledge_assets/README.md",
+    "local_ccra_reviews/README.md",
+    "local_ccra_reviews/round-04/pilot-01/agent-invocation-packet.md",
+    "local_ccra_reviews/round-04/pilot-01/gate-manifest.yaml",
+    "local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.json",
+    "local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.md",
+    "local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.json",
+    "local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.md",
+    "local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml",
+    "local_ccra_reviews/round-04/pilot-01/owner-decision.md",
+    "local_ccra_reviews/round-04/pilot-01/prompt-to-send.md",
+    "local_ccra_reviews/round-04/pilot-01/review-metadata.json",
+    "local_ccra_reviews/round-04/pilot-01/run-notes.md",
+    "models/intellectual_archaeology.model.json",
+    "models/model_index.json",
+    "models/qpi.model.json",
+    "models/README.md",
+    "PROJECTS.md",
+    "README.md",
+    "reports/baseline_before_content_stabilization_v0.2.md",
+    "reports/changed_files_manifest.md",
+    "reports/ChatGPT交接文档_模型库MVP_2026-06-16.md",
+    "reports/ChatGPT交接文档_模型库MVP_第二轮内容稳定化_2026-06-16.md",
+    "reports/Codex_工程产物摘要_v0.1.md",
+    "reports/Codex_本地CCRA规划落地_2026-06-19.md",
+    "reports/Codex_模型资产链路摘要_v0.1.md",
+    "reports/Codex新会话交接文档_CCRA评审后处理_2026-06-16.md",
+    "reports/Codex新会话交接文档_QPI案例草稿审阅与第三轮后续_2026-06-17.md",
+    "reports/Codex新会话交接文档_Round03.1评审后续_2026-06-17.md",
+    "reports/Codex新会话交接文档_Round03.2a评审准备_2026-06-17.md",
+    "reports/Codex新会话交接文档_Round03.2评审准备_2026-06-17.md",
+    "reports/Codex新会话交接文档_Round04.1关闭与Round05准备_2026-06-18.md",
+    "reports/Codex新会话交接文档_模型库MVP_2026-06-16.md",
+    "reports/command_log.md",
+    "reports/content_review_report.md",
+    "reports/content_review_report_v0.2.md",
+    "reports/evidence_coverage_matrix.md",
+    "reports/evidence_coverage_report_v0.2.md",
+    "reports/GPT规划落地差异检查_v0.1.md",
+    "reports/GPT讨论上下文_QPI草稿案例审阅_2026-06-17.md",
+    "reports/index_check_report.md",
+    "reports/index_rebuild_report.md",
+    "reports/model_card_sync_report_v0.2.md",
+    "reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md",
+    "reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md",
+    "reports/model_case_preprocessing/qpi/round-01/README.md",
+    "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
+    "reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md",
+    "reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md",
+    "reports/model_case_preprocessing/qpi/round-01/year-end-review-engineering-center.cases.md",
+    "reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md",
+    "reports/model_case_preprocessing/qpi/round-01/year-end-review-research-office.cases.md",
+    "reports/model_review_status.json",
+    "reports/next_action_register_v0.2.md",
+    "reports/open_questions_for_CCRA.md",
+    "reports/README.md",
+    "reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md",
+    "reports/Round04_blind_input_candidates_2026-06-18.md",
+    "reports/Round04_blind_routing_evaluation_report_2026-06-18.md",
+    "reports/schema_change_notes.md",
+    "reports/selector_calibration_smoke_report.md",
+    "reports/selector_regression_report.md",
+    "reports/selector_regression_report_v0.2.md",
+    "reports/selector_score_breakdown.md",
+    "reports/validation_report.md",
+    "reports/内容修复检查摘要_v0.1.md",
+    "reports/内容修复检查摘要_v0.2.md",
+    "reports/规则Schema工作流检查摘要_v0.1.md",
+    "requirements/ccpe/2026-06-19-ccra-local-reviewer-runtime.md",
+    "requirements/ccpe/README.md",
+    "requirements/skills-vault/2026-06-18-review-bundle-zip-packager.md",
+    "requirements/skills-vault/README.md",
+    "schemas/card_index.schema.json",
+    "schemas/model_card.schema.json",
+    "schemas/model_index.schema.json",
+    "schemas/model_spec.schema.json",
+    "schemas/README.md",
+    "schemas/regression_case.schema.json",
+    "schemas/source_article.schema.json",
+    "schemas/source_excerpt.schema.json",
+    "scripts/README.md",
+    "selector/qpi_case_digests.json",
+    "selector/README.md",
+    "selector/round04_blind_inputs.json",
+    "selector/selector_calibration_inputs.json",
+    "selector/selector_examples.json",
+    "selector/selector_rules.json",
+    "sources/evidence_coverage.matrix.json",
+    "sources/README.md",
+    "sources/source_articles.json",
+    "sources/source_excerpts.json",
+    "tests/intellectual_archaeology.regression.json",
+    "tests/qpi.regression.json",
+    "tests/README.md",
+    "tests/regression_cases.json",
+    "tests/regression_index.json"
+  ],
+  "possible_overclaims": [
+    {
+      "file": "ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/03_VALIDATION_AND_COMMAND_LOG_03.2.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 59,
+      "column": 58,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "on_report.md` - `reports/selector_regression_report_v0.2.md` - `reports/selector_calibration_smoke_report.md` - `reports/model_card_sync_report_v0.2.md` ## Important Interpretation Validation pass does not mean model content is stable or owner-approved. It only means the Round 03.2 selector negative-gate patch is structurally consistent and passes current local checks.",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/03_VALIDATION_AND_COMMAND_LOG_03.2a.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 47,
+      "column": 58,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "ct: PASS - Selector demo: PASS - Selector regression: PASS - Selector calibration smoke: PASS, 95 inputs, 0 failures, 0 warnings - Model/card sync: PASS ## Important Interpretation Validation pass does not mean model content is stable or owner-approved. It only means the Round 03.2a selector precedence patch is structurally consistent and passes current local checks.",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "docs/DECISIONS.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 175,
+      "column": 154,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "such as `先不要思想考古` could still lose to positive IA signals and QPI-completed bonuses. A user instruction that names a model and refuses it should not be represented as a normal score penalty. It must hard-exclude that model unless a later owner-approved rule defines an explicit reversal phrase. The current Round 03.2 implementation keeps this scoped: - It rejects only the explicitly refused model. - It does not create a global no-call. - It does not add an LLM selector, RAG, database, s",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 160,
+      "column": 27,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "Do not: - write selector JSON directly; - update regression cases directly; - upgrade model status; - create a third model; - summarize the whole source instead of extracting cases; - quote long source passages; - pretend draft cases are owner-approved. ## 7. Promotion Path The promotion path is: ```text raw source -> Markdown case drafts -> owner review and correction -> case digest JSON -> selector calibration inputs or regression cases ``` Only owner-reviewed cases may become mach",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 263,
+      "column": 8,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "w Questions - Should QPI explicitly mark \"single-cause reduction\" as a subtype of violent reduction? - Should this case be used to test that QPI does not output a single definitive cause when the source provides coupled mechanisms? - What owner-approved language should be used to distinguish explanatory usefulness from causal finality? ### 13. Owner Review Decision - Keep the case, but avoid the overbroad rule \"all single-cause attribution is wrong.\" - Rename the risk to `single_facto",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 275,
+      "column": 3,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "n. - Prevent QPI from outputting a single definitive root cause when coupled mechanisms are already present. - Require distinction between trigger, maintaining condition, high-weight factor, current action lever, and causal totality. - Owner-approved language: - \"This factor has explanatory usefulness, but it is not causal finality.\" - \"It may be a high-weight factor or current lever, not the complete cause.\" - \"It can be prioritized in this context, but it cannot replace the sys",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 11,
+      "column": 150,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "h: `C:\\Users\\wangq\\Documents\\Codex\\knowledge-vault\\work\\internal\\强哥的思想宇宙\\QPI案例分析\\流程改造.md` source_note: Raw source remains outside this repository. These are reviewable QPI case drafts only; they are not selector JSON, regression cases, or owner-approved calibration data. ## Case qpi-draft-001: Outline Review Was Not The Real Entry Point status: owner_reviewed owner_approved_for_digest: true digest_role: supporting_evidence_for_context_engineering_entry_point_case source_path: `C:\\Use",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 11,
+      "column": 436,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "locations, titles, exact numbers, and sensitive operational details have been removed or generalized. Ancient-style cognitive-anchor names from the source are intentionally omitted. These drafts are not selector JSON, regression cases, or owner-approved calibration data. anonymization_note: People are represented as generic roles such as `decision_maker`, `execution_lead`, `technical_staff`, `frontline_staff`, and `affected_learners`. The organization is represented as `the organization`",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 100,
+      "column": 3,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "overnance. - Keep `classification: mixed` because the same case contains data scarcity and governance scarcity. - Use as selector calibration and high-priority regression for AI/tool requests that must not be treated as simple execution. - Owner-approved wording: \"AI can organize evidence, but must not manufacture the evidentiary relationship.\" - Current anonymization is sufficient. ## Case qpi-draft-002: Credential Metric Repair Creates Staffing Ratio Deadlock status: owner_reviewed o",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 357,
+      "column": 3,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "rtability and application feasibility. - Market-facing frame sees communication and enrollment value. - Long-term organization frame sees strategic myopia risk. - Keep `classification: issue` and `dominant_scarcity: consensus_order`. - Owner-approved wording: \"A resource-feasible compromise becomes strategic myopia if it is not tested against long-term positioning.\" - Use as calibration for short-term reportability or packaging substituting for long-term strategic planning. ## Case qp",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 519,
+      "column": 8,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "as dominant scarcity] - Should isolated achievements be treated as evidence of latent capability or as masking signals? [answered: prioritize as masking signal; they may indicate local capability but cannot offset systemic decline] - What owner-approved wording should be used to avoid over-claiming causal responsibility? [answered: input conditions may affect outcomes but cannot replace audit of management levers] ### 13. Owner Review Decision - Keep `classification: mixed` and `dominan",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 528,
+      "column": 3,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "upported or whether academic affairs is treated as cost, revenue, or reporting function. - Treat isolated achievements primarily as masking signals. - They may indicate local capability, but they cannot offset systemic outcome decline. - Owner-approved wording: - \"Input conditions may affect outcomes, but cannot replace audit of management levers.\" - \"Learner quality can explain part of the difficulty, but it cannot automatically exempt quality-assurance responsibility.\" - \"Isolate",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 618,
+      "column": 3,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "y, adoption incentives, and digital governance level. - Keep `dominant_scarcity: consensus_order`. - Path/resource cost exists, but the missing object is shared governance criteria and authority. - Local versus cloud detail can remain. - Owner-approved wording: \"Define digital governance criteria before platform selection.\" ## Case qpi-draft-008: Public Safety Compliance Gap Reveals Bottom-Line Control Failure status: owner_reviewed owner_approved_for_digest: true digest_role: botto",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 11,
+      "column": 408,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "s, institutions, timestamps, locations, titles, and exact numeric details have been removed or generalized. Ancient-style cognitive anchors from the source are intentionally omitted. These drafts are not selector JSON, regression cases, or owner-approved calibration data. anonymization_note: People are represented as roles such as `decision_maker`, `execution_lead`, `strategy_staff`, `functional_department`, and `frontline_staff`. The organization is represented as `the organization`; the",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 7,
+      "column": 428,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "estamps, places, titles, exact numbers, and sensitive operational details have been removed or generalized. Ancient-style cognitive anchors from the source are intentionally omitted. These drafts are not selector JSON, regression cases, or owner-approved calibration data. owner_review_source: `C:/Users/wangq/Documents/Codex/knowledge-vault/work/internal/强哥的思想宇宙/QPI案例审阅/QPI提炼审核/year-end-review-employment-entrepreneurship.cases-GPT.md` owner_review_note: Owner/GPT review approved all eight",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 698,
+      "column": 8,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "ich replace education value with transactional output metrics. ### 12. Owner Review Questions - Is this case too broad for calibration, or useful as an Issue anchor? - Should it be decomposed into several narrower P/I mixed cases? - What owner-approved wording should be used for the anonymized identity-shift risk? ### 13. Owner Review Decision - owner_review_status: owner_reviewed - owner_approved_for_digest: true - digest_role: transactional_education_issue_anchor - selector_calibrati",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 81,
+      "column": 64,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "nant scarcity here correctly placed on consensus/order rather than path/resource? - Should this be treated as Issue rather than mixed because the compliance boundary dominates? - Which details, if any, are safe enough to retain in a future owner-approved case digest? ### 13. Owner Review Decision - owner_review_status: owner_reviewed - owner_approved_for_digest: true - digest_role: compliance_boundary_retention_issue_regression_case - regression_candidate: high_priority - classification:",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 618,
+      "column": 8,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "e design without killing execution energy. ### 12. Owner Review Questions - Is \"privatization of organizational capability\" the right abstraction here? - Should this case be connected with the role-inflation case or kept separate? - What owner-approved signal distinguishes healthy recognition from dangerous private capture? ### 13. Owner Review Decision - owner_review_status: owner_reviewed - owner_approved_for_digest: true - digest_role: non_institutionalized_capability_calibration_ca",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-research-office.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 7,
+      "column": 397,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "departments, institutions, timestamps, locations, titles, ancient-style cognitive anchors, exact numeric details, and sensitive operational details have been removed or generalized. These drafts are not selector JSON, regression cases, or owner-approved calibration data. owner_review_source: `C:/Users/wangq/Documents/Codex/knowledge-vault/work/internal/强哥的思想宇宙/QPI案例审阅/QPI提炼审核/year-end-review-research-office.cases-GPT.md` owner_review_note: Owner/GPT review approved all eight cases for d",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "selector/qpi_case_digests.json",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 1261,
+      "column": 42,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "into an upstream authority over teaching.\", \"routing_notes\": [ \"hard outcome metric hiding authority redesign\", \"separate outcome improvement from teaching authority transfer\", \"reverse accountability power is owner-approved wording\" ], \"recommended_next_step\": \"Define shared outcome governance, evidence standards, and limits on reverse accountability before redesigning authority.\", \"misclassification_risk\": [ \"violent_reduction\",",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "selector/qpi_case_digests.json",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 2187,
+      "column": 42,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "mulate research identity through people, expenses, patents, papers, and evidence packaging to obtain external preferential status.\", \"routing_notes\": [ \"umbrella case for this source\", \"research identity simulation is owner-approved\", \"capability building must be separated from evidence simulation\" ], \"recommended_next_step\": \"Separate legitimate research capability building from identity simulation and compliance red-line risk.\", \"misclassif",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    }
+  ],
+  "field_level_findings": [],
+  "phrase_level_findings": [
+    {
+      "file": "ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/03_VALIDATION_AND_COMMAND_LOG_03.2.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 59,
+      "column": 58,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "on_report.md` - `reports/selector_regression_report_v0.2.md` - `reports/selector_calibration_smoke_report.md` - `reports/model_card_sync_report_v0.2.md` ## Important Interpretation Validation pass does not mean model content is stable or owner-approved. It only means the Round 03.2 selector negative-gate patch is structurally consistent and passes current local checks.",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/03_VALIDATION_AND_COMMAND_LOG_03.2a.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 47,
+      "column": 58,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "ct: PASS - Selector demo: PASS - Selector regression: PASS - Selector calibration smoke: PASS, 95 inputs, 0 failures, 0 warnings - Model/card sync: PASS ## Important Interpretation Validation pass does not mean model content is stable or owner-approved. It only means the Round 03.2a selector precedence patch is structurally consistent and passes current local checks.",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "docs/DECISIONS.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 175,
+      "column": 154,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "such as `先不要思想考古` could still lose to positive IA signals and QPI-completed bonuses. A user instruction that names a model and refuses it should not be represented as a normal score penalty. It must hard-exclude that model unless a later owner-approved rule defines an explicit reversal phrase. The current Round 03.2 implementation keeps this scoped: - It rejects only the explicitly refused model. - It does not create a global no-call. - It does not add an LLM selector, RAG, database, s",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 160,
+      "column": 27,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "Do not: - write selector JSON directly; - update regression cases directly; - upgrade model status; - create a third model; - summarize the whole source instead of extracting cases; - quote long source passages; - pretend draft cases are owner-approved. ## 7. Promotion Path The promotion path is: ```text raw source -> Markdown case drafts -> owner review and correction -> case digest JSON -> selector calibration inputs or regression cases ``` Only owner-reviewed cases may become mach",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 263,
+      "column": 8,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "w Questions - Should QPI explicitly mark \"single-cause reduction\" as a subtype of violent reduction? - Should this case be used to test that QPI does not output a single definitive cause when the source provides coupled mechanisms? - What owner-approved language should be used to distinguish explanatory usefulness from causal finality? ### 13. Owner Review Decision - Keep the case, but avoid the overbroad rule \"all single-cause attribution is wrong.\" - Rename the risk to `single_facto",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 275,
+      "column": 3,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "n. - Prevent QPI from outputting a single definitive root cause when coupled mechanisms are already present. - Require distinction between trigger, maintaining condition, high-weight factor, current action lever, and causal totality. - Owner-approved language: - \"This factor has explanatory usefulness, but it is not causal finality.\" - \"It may be a high-weight factor or current lever, not the complete cause.\" - \"It can be prioritized in this context, but it cannot replace the sys",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 11,
+      "column": 150,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "h: `C:\\Users\\wangq\\Documents\\Codex\\knowledge-vault\\work\\internal\\强哥的思想宇宙\\QPI案例分析\\流程改造.md` source_note: Raw source remains outside this repository. These are reviewable QPI case drafts only; they are not selector JSON, regression cases, or owner-approved calibration data. ## Case qpi-draft-001: Outline Review Was Not The Real Entry Point status: owner_reviewed owner_approved_for_digest: true digest_role: supporting_evidence_for_context_engineering_entry_point_case source_path: `C:\\Use",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 11,
+      "column": 436,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "locations, titles, exact numbers, and sensitive operational details have been removed or generalized. Ancient-style cognitive-anchor names from the source are intentionally omitted. These drafts are not selector JSON, regression cases, or owner-approved calibration data. anonymization_note: People are represented as generic roles such as `decision_maker`, `execution_lead`, `technical_staff`, `frontline_staff`, and `affected_learners`. The organization is represented as `the organization`",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 100,
+      "column": 3,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "overnance. - Keep `classification: mixed` because the same case contains data scarcity and governance scarcity. - Use as selector calibration and high-priority regression for AI/tool requests that must not be treated as simple execution. - Owner-approved wording: \"AI can organize evidence, but must not manufacture the evidentiary relationship.\" - Current anonymization is sufficient. ## Case qpi-draft-002: Credential Metric Repair Creates Staffing Ratio Deadlock status: owner_reviewed o",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 357,
+      "column": 3,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "rtability and application feasibility. - Market-facing frame sees communication and enrollment value. - Long-term organization frame sees strategic myopia risk. - Keep `classification: issue` and `dominant_scarcity: consensus_order`. - Owner-approved wording: \"A resource-feasible compromise becomes strategic myopia if it is not tested against long-term positioning.\" - Use as calibration for short-term reportability or packaging substituting for long-term strategic planning. ## Case qp",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 519,
+      "column": 8,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "as dominant scarcity] - Should isolated achievements be treated as evidence of latent capability or as masking signals? [answered: prioritize as masking signal; they may indicate local capability but cannot offset systemic decline] - What owner-approved wording should be used to avoid over-claiming causal responsibility? [answered: input conditions may affect outcomes but cannot replace audit of management levers] ### 13. Owner Review Decision - Keep `classification: mixed` and `dominan",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 528,
+      "column": 3,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "upported or whether academic affairs is treated as cost, revenue, or reporting function. - Treat isolated achievements primarily as masking signals. - They may indicate local capability, but they cannot offset systemic outcome decline. - Owner-approved wording: - \"Input conditions may affect outcomes, but cannot replace audit of management levers.\" - \"Learner quality can explain part of the difficulty, but it cannot automatically exempt quality-assurance responsibility.\" - \"Isolate",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 618,
+      "column": 3,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "y, adoption incentives, and digital governance level. - Keep `dominant_scarcity: consensus_order`. - Path/resource cost exists, but the missing object is shared governance criteria and authority. - Local versus cloud detail can remain. - Owner-approved wording: \"Define digital governance criteria before platform selection.\" ## Case qpi-draft-008: Public Safety Compliance Gap Reveals Bottom-Line Control Failure status: owner_reviewed owner_approved_for_digest: true digest_role: botto",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 11,
+      "column": 408,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "s, institutions, timestamps, locations, titles, and exact numeric details have been removed or generalized. Ancient-style cognitive anchors from the source are intentionally omitted. These drafts are not selector JSON, regression cases, or owner-approved calibration data. anonymization_note: People are represented as roles such as `decision_maker`, `execution_lead`, `strategy_staff`, `functional_department`, and `frontline_staff`. The organization is represented as `the organization`; the",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 7,
+      "column": 428,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "estamps, places, titles, exact numbers, and sensitive operational details have been removed or generalized. Ancient-style cognitive anchors from the source are intentionally omitted. These drafts are not selector JSON, regression cases, or owner-approved calibration data. owner_review_source: `C:/Users/wangq/Documents/Codex/knowledge-vault/work/internal/强哥的思想宇宙/QPI案例审阅/QPI提炼审核/year-end-review-employment-entrepreneurship.cases-GPT.md` owner_review_note: Owner/GPT review approved all eight",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 698,
+      "column": 8,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "ich replace education value with transactional output metrics. ### 12. Owner Review Questions - Is this case too broad for calibration, or useful as an Issue anchor? - Should it be decomposed into several narrower P/I mixed cases? - What owner-approved wording should be used for the anonymized identity-shift risk? ### 13. Owner Review Decision - owner_review_status: owner_reviewed - owner_approved_for_digest: true - digest_role: transactional_education_issue_anchor - selector_calibrati",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 81,
+      "column": 64,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "nant scarcity here correctly placed on consensus/order rather than path/resource? - Should this be treated as Issue rather than mixed because the compliance boundary dominates? - Which details, if any, are safe enough to retain in a future owner-approved case digest? ### 13. Owner Review Decision - owner_review_status: owner_reviewed - owner_approved_for_digest: true - digest_role: compliance_boundary_retention_issue_regression_case - regression_candidate: high_priority - classification:",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 618,
+      "column": 8,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "e design without killing execution energy. ### 12. Owner Review Questions - Is \"privatization of organizational capability\" the right abstraction here? - Should this case be connected with the role-inflation case or kept separate? - What owner-approved signal distinguishes healthy recognition from dangerous private capture? ### 13. Owner Review Decision - owner_review_status: owner_reviewed - owner_approved_for_digest: true - digest_role: non_institutionalized_capability_calibration_ca",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-research-office.cases.md",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 7,
+      "column": 397,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "departments, institutions, timestamps, locations, titles, ancient-style cognitive anchors, exact numeric details, and sensitive operational details have been removed or generalized. These drafts are not selector JSON, regression cases, or owner-approved calibration data. owner_review_source: `C:/Users/wangq/Documents/Codex/knowledge-vault/work/internal/强哥的思想宇宙/QPI案例审阅/QPI提炼审核/year-end-review-research-office.cases-GPT.md` owner_review_note: Owner/GPT review approved all eight cases for d",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "selector/qpi_case_digests.json",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 1261,
+      "column": 42,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "into an upstream authority over teaching.\", \"routing_notes\": [ \"hard outcome metric hiding authority redesign\", \"separate outcome improvement from teaching authority transfer\", \"reverse accountability power is owner-approved wording\" ], \"recommended_next_step\": \"Define shared outcome governance, evidence standards, and limits on reverse accountability before redesigning authority.\", \"misclassification_risk\": [ \"violent_reduction\",",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    },
+    {
+      "file": "selector/qpi_case_digests.json",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 2187,
+      "column": 42,
+      "severity": "blocking",
+      "evidence_present": false,
+      "context": "mulate research identity through people, expenses, patents, papers, and evidence packaging to obtain external preferential status.\", \"routing_notes\": [ \"umbrella case for this source\", \"research identity simulation is owner-approved\", \"capability building must be separated from evidence simulation\" ], \"recommended_next_step\": \"Separate legitimate research capability building from identity simulation and compliance red-line risk.\", \"misclassif",
+      "message": "Approval claim phrase lacks nearby evidence marker."
+    }
+  ],
+  "missing_evidence_markers": [
+    {
+      "file": "ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/03_VALIDATION_AND_COMMAND_LOG_03.2.md",
+      "line": 59,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/03_VALIDATION_AND_COMMAND_LOG_03.2a.md",
+      "line": 47,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "docs/DECISIONS.md",
+      "line": 175,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md",
+      "line": 160,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md",
+      "line": 263,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md",
+      "line": 275,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md",
+      "line": 11,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
+      "line": 11,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
+      "line": 100,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
+      "line": 357,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
+      "line": 519,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
+      "line": 528,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
+      "line": 618,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md",
+      "line": 11,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md",
+      "line": 7,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md",
+      "line": 698,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md",
+      "line": 81,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md",
+      "line": 618,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-research-office.cases.md",
+      "line": 7,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "selector/qpi_case_digests.json",
+      "line": 1261,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    },
+    {
+      "file": "selector/qpi_case_digests.json",
+      "line": 2187,
+      "phrase": "owner-approved",
+      "required_evidence_markers": [
+        "owner_decision",
+        "owner decision",
+        "ccra_review",
+        "ccra review",
+        "web ccra"
+      ]
+    }
+  ],
+  "warnings": [],
+  "blocking_errors": [
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker.",
+    "Approval claim phrase lacks nearby evidence marker."
+  ],
+  "observations": [
+    {
+      "file": "local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml",
+      "source": "text",
+      "phrase": "owner-approved",
+      "line": 14,
+      "column": 5,
+      "severity": "observation",
+      "evidence_present": true,
+      "context": "watched_paths: - \"**/*.md\" - \"**/*.json\" - \"**/*.yaml\" - \"**/*.yml\" status_fields: - status - lifecycle - model.status - model.lifecycle forbidden_status_values: - stable - accepted - owner-approved - ccra-approved warning_status_values: - candidate - ready-for-review required_evidence_markers: - owner_decision - owner decision - ccra_review - ccra review - web ccra approved_phrases: - owner-approved - ccra-approve",
+      "message": "Approval claim phrase has nearby evidence marker; approval validity is not decided by this scan.",
+      "kind": "evidence_present_claim"
+    },
+    {
+      "file": "local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml",
+      "source": "text",
+      "phrase": "ccra-approved",
+      "line": 15,
+      "column": 5,
+      "severity": "observation",
+      "evidence_present": true,
+      "context": "watched_paths: - \"**/*.md\" - \"**/*.json\" - \"**/*.yaml\" - \"**/*.yml\" status_fields: - status - lifecycle - model.status - model.lifecycle forbidden_status_values: - stable - accepted - owner-approved - ccra-approved warning_status_values: - candidate - ready-for-review required_evidence_markers: - owner_decision - owner decision - ccra_review - ccra review - web ccra approved_phrases: - owner-approved - ccra-approved - Owner approv",
+      "message": "Approval claim phrase has nearby evidence marker; approval validity is not decided by this scan.",
+      "kind": "evidence_present_claim"
+    }
+  ],
+  "machine_readable_summary": {
+    "status": "FAIL",
+    "files_scanned_count": 178,
+    "field_finding_count": 0,
+    "phrase_finding_count": 21,
+    "missing_evidence_count": 21,
+    "warning_count": 0,
+    "blocking_count": 21,
+    "observation_count": 2
+  }
+}

local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md

@@ -0,0 +1,223 @@
+# Lifecycle Status Guard Scan
+
+## Summary
+
+- Status: `FAIL`
+- Files scanned: 178
+- Blocking findings: 21
+- Warnings: 0
+- Evidence-present observations: 2
+
+## Blocking Findings
+
+- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/03_VALIDATION_AND_COMMAND_LOG_03.2.md` line 59: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/03_VALIDATION_AND_COMMAND_LOG_03.2a.md` line 47: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `docs/DECISIONS.md` line 175: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md` line 160: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md` line 263: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md` line 275: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md` line 11: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 11: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 100: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 357: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 519: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 528: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 618: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md` line 11: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md` line 7: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md` line 698: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md` line 81: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md` line 618: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-research-office.cases.md` line 7: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `selector/qpi_case_digests.json` line 1261: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `selector/qpi_case_digests.json` line 2187: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+
+## Warnings
+
+- None
+
+## Observations
+
+- `local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml` line 14: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml` line 15: `ccra-approved` - evidence marker present; approval validity not decided.
+
+## Files Scanned
+
+- `AGENTS.md`
+- `cards/card_index.md`
+- `cards/intellectual_archaeology.md`
+- `cards/qpi.md`
+- `cards/README.md`
+- `ccra_review_bundle/round-02_2026-06-16_second-audit/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md`
+- `ccra_review_bundle/round-02_2026-06-16_second-audit/01_GUIDANCE_PACK_AND_COMPLIANCE_MATRIX.md`
+- `ccra_review_bundle/round-02_2026-06-16_second-audit/02_CURRENT_ASSET_PACK.md`
+- `ccra_review_bundle/round-02_2026-06-16_second-audit/03_REPORTS_DIFF_AND_COMMAND_LOG.md`
+- `ccra_review_bundle/round-02_2026-06-16_second-audit/BUNDLE_FILE_MANIFEST.md`
+- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF03.1.md`
+- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/01_PATCH_MATRIX_03.1.md`
+- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/02_CURRENT_ASSET_PACK03.1.md`
+- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/03_VALIDATION_AND_COMMAND_LOG03.1.md`
+- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/04_REVIEW_QUESTIONS_FOR_GPT03.1.md`
+- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/BUNDLE_FILE_MANIFEST03.1.md`
+- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_03.2.md`
+- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/01_PATCH_MATRIX_03.2.md`
+- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/02_CURRENT_ASSET_PACK_03.2.md`
+- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/03_VALIDATION_AND_COMMAND_LOG_03.2.md`
+- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/04_REVIEW_QUESTIONS_FOR_GPT_03.2.md`
+- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/BUNDLE_FILE_MANIFEST_03.2.md`
+- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_03.2a.md`
+- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/01_PATCH_MATRIX_03.2a.md`
+- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/02_CURRENT_ASSET_PACK_03.2a.md`
+- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/03_VALIDATION_AND_COMMAND_LOG_03.2a.md`
+- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/04_REVIEW_QUESTIONS_FOR_GPT_03.2a.md`
+- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/BUNDLE_FILE_MANIFEST_03.2a.md`
+- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md`
+- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/01_GUIDANCE_PACK_AND_COMPLIANCE_MATRIX.md`
+- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/02_CURRENT_ASSET_PACK.md`
+- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/03_REPORTS_DIFF_AND_COMMAND_LOG.md`
+- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/04_QPI_CASE_PROMOTION_SUMMARY_AND_REVIEW_GUIDE.md`
+- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/05_REVIEW_QUESTIONS_FOR_GPT.md`
+- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/BUNDLE_FILE_MANIFEST.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/BUNDLE_FILE_MANIFEST_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md`
+- `docs/CHATGPT_HANDOFF_RULES.md`
+- `docs/CONTENT_STABILIZATION_PROTOCOL.md`
+- `docs/DATA_CONTRACT.md`
+- `docs/DECISIONS.md`
+- `docs/FILE_TAXONOMY.md`
+- `docs/GPT_PLAN_LOCALIZATION_PROTOCOL.md`
+- `docs/HANDOFF_TEMPLATE.md`
+- `docs/INDEX_MAINTENANCE_PROTOCOL.md`
+- `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md`
+- `docs/KNOWLEDGE_ASSET_RULES.md`
+- `docs/MODEL_CARD_CONTRACT.md`
+- `docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md`
+- `docs/model_case_preprocessing/qpi/README.md`
+- `docs/model_case_preprocessing/README.md`
+- `docs/MODEL_EXTRACTION_RULES.md`
+- `docs/MODEL_EXTRACTION_WORKFLOW.md`
+- `docs/NON_GOALS.md`
+- `docs/PROJECT_BRIEF.md`
+- `docs/QPI_CONTEXTUAL_ROUTING_RULES.md`
+- `docs/superpowers/plans/2026-06-16-model-extraction-contract-and-workflow.md`
+- `docs/superpowers/plans/2026-06-16-project-initialization.md`
+- `docs/superpowers/plans/2026-06-17-contract-hardening-selector-calibration.md`
+- `docs/superpowers/plans/2026-06-18-round04-1-selector-rule-patch.md`
+- `docs/superpowers/plans/2026-06-18-round04-blind-routing-evaluation.md`
+- `docs/WORKFLOW.md`
+- `knowledge_assets/00_用户背景与产品上下文.md`
+- `knowledge_assets/01_核心模型地图.md`
+- `knowledge_assets/02_模型卡结构规范.md`
+- `knowledge_assets/03_核心模型抽取样板.md`
+- `knowledge_assets/06_模型稳固性评级规则.md`
+- `knowledge_assets/07_产品规划过程记录.md`
+- `knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md`
+- `knowledge_assets/09_数据治理与模型调用机制说明.md`
+- `knowledge_assets/10_本地CCRA评审机制说明.md`
+- `knowledge_assets/README.md`
+- `local_ccra_reviews/README.md`
+- `local_ccra_reviews/round-04/pilot-01/agent-invocation-packet.md`
+- `local_ccra_reviews/round-04/pilot-01/gate-manifest.yaml`
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.json`
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.md`
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.json`
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.md`
+- `local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml`
+- `local_ccra_reviews/round-04/pilot-01/owner-decision.md`
+- `local_ccra_reviews/round-04/pilot-01/prompt-to-send.md`
+- `local_ccra_reviews/round-04/pilot-01/review-metadata.json`
+- `local_ccra_reviews/round-04/pilot-01/run-notes.md`
+- `models/intellectual_archaeology.model.json`
+- `models/model_index.json`
+- `models/qpi.model.json`
+- `models/README.md`
+- `PROJECTS.md`
+- `README.md`
+- `reports/baseline_before_content_stabilization_v0.2.md`
+- `reports/changed_files_manifest.md`
+- `reports/ChatGPT交接文档_模型库MVP_2026-06-16.md`
+- `reports/ChatGPT交接文档_模型库MVP_第二轮内容稳定化_2026-06-16.md`
+- `reports/Codex_工程产物摘要_v0.1.md`
+- `reports/Codex_本地CCRA规划落地_2026-06-19.md`
+- `reports/Codex_模型资产链路摘要_v0.1.md`
+- `reports/Codex新会话交接文档_CCRA评审后处理_2026-06-16.md`
+- `reports/Codex新会话交接文档_QPI案例草稿审阅与第三轮后续_2026-06-17.md`
+- `reports/Codex新会话交接文档_Round03.1评审后续_2026-06-17.md`
+- `reports/Codex新会话交接文档_Round03.2a评审准备_2026-06-17.md`
+- `reports/Codex新会话交接文档_Round03.2评审准备_2026-06-17.md`
+- `reports/Codex新会话交接文档_Round04.1关闭与Round05准备_2026-06-18.md`
+- `reports/Codex新会话交接文档_模型库MVP_2026-06-16.md`
+- `reports/command_log.md`
+- `reports/content_review_report.md`
+- `reports/content_review_report_v0.2.md`
+- `reports/evidence_coverage_matrix.md`
+- `reports/evidence_coverage_report_v0.2.md`
+- `reports/GPT规划落地差异检查_v0.1.md`
+- `reports/GPT讨论上下文_QPI草稿案例审阅_2026-06-17.md`
+- `reports/index_check_report.md`
+- `reports/index_rebuild_report.md`
+- `reports/model_card_sync_report_v0.2.md`
+- `reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/README.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-engineering-center.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-research-office.cases.md`
+- `reports/model_review_status.json`
+- `reports/next_action_register_v0.2.md`
+- `reports/open_questions_for_CCRA.md`
+- `reports/README.md`
+- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md`
+- `reports/Round04_blind_input_candidates_2026-06-18.md`
+- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
+- `reports/schema_change_notes.md`
+- `reports/selector_calibration_smoke_report.md`
+- `reports/selector_regression_report.md`
+- `reports/selector_regression_report_v0.2.md`
+- `reports/selector_score_breakdown.md`
+- `reports/validation_report.md`
+- `reports/内容修复检查摘要_v0.1.md`
+- `reports/内容修复检查摘要_v0.2.md`
+- `reports/规则Schema工作流检查摘要_v0.1.md`
+- `requirements/ccpe/2026-06-19-ccra-local-reviewer-runtime.md`
+- `requirements/ccpe/README.md`
+- `requirements/skills-vault/2026-06-18-review-bundle-zip-packager.md`
+- `requirements/skills-vault/README.md`
+- `schemas/card_index.schema.json`
+- `schemas/model_card.schema.json`
+- `schemas/model_index.schema.json`
+- `schemas/model_spec.schema.json`
+- `schemas/README.md`
+- `schemas/regression_case.schema.json`
+- `schemas/source_article.schema.json`
+- `schemas/source_excerpt.schema.json`
+- `scripts/README.md`
+- `selector/qpi_case_digests.json`
+- `selector/README.md`
+- `selector/round04_blind_inputs.json`
+- `selector/selector_calibration_inputs.json`
+- `selector/selector_examples.json`
+- `selector/selector_rules.json`
+- `sources/evidence_coverage.matrix.json`
+- `sources/README.md`
+- `sources/source_articles.json`
+- `sources/source_excerpts.json`
+- `tests/intellectual_archaeology.regression.json`
+- `tests/qpi.regression.json`
+- `tests/README.md`
+- `tests/regression_cases.json`
+- `tests/regression_index.json`

local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml

@@ -0,0 +1,38 @@
+watched_paths:
+  - "**/*.md"
+  - "**/*.json"
+  - "**/*.yaml"
+  - "**/*.yml"
+status_fields:
+  - status
+  - lifecycle
+  - model.status
+  - model.lifecycle
+forbidden_status_values:
+  - stable
+  - accepted
+  - owner-approved
+  - ccra-approved
+warning_status_values:
+  - candidate
+  - ready-for-review
+required_evidence_markers:
+  - owner_decision
+  - owner decision
+  - ccra_review
+  - ccra review
+  - web ccra
+approved_phrases:
+  - owner-approved
+  - ccra-approved
+  - Owner approved
+  - CCRA approved
+forbidden_phrases:
+  - production-ready
+  - released to production
+  - final approved
+allowed_contexts:
+  - do not say
+  - must not claim
+  - example:
+evidence_window_chars: 240

local_ccra_reviews/round-04/pilot-01/owner-decision.md

@@ -0,0 +1,23 @@
+# Owner Decision
+
+Status: pending
+
+## Accepted Findings
+
+-
+
+## Rejected Findings
+
+-
+
+## Deferred Findings
+
+-
+
+## Escalated To Web CCRA
+
+-
+
+## Notes
+
+This file should be filled only after `04_LOCAL_CCRA_REVIEW_REPORT.md` is returned.

local_ccra_reviews/round-04/pilot-01/prompt-to-send.md

@@ -0,0 +1,52 @@
+# Prompt To Send: CCRA Local Review Pilot
+
+You are being invoked as a real child review session for `ccra-local-reviewer`.
+
+This is not main-session roleplay. If you cannot comply with the file-first invocation packet, report that you are blocked.
+
+Read and follow:
+
+```text
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\agent-invocation-packet.md
+```
+
+Canonical CCPE artifacts:
+
+```text
+C:\Users\wangq\Documents\Codex\ccpe-system\agents\agent-specs\ccra-local-reviewer.agent.md
+C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review.runtime.md
+C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-report.template.md
+```
+
+Required project knowledge base:
+
+```text
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets
+```
+
+Use this path directly. Do not create a second Local CCRA copy of the knowledge base.
+
+Required output:
+
+```text
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\04_LOCAL_CCRA_REVIEW_REPORT.md
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\returned-output.md
+```
+
+Hard constraints:
+
+- Read local files directly.
+- Read the required `knowledge_assets/` knowledge base.
+- Cite the files actually read.
+- Use helper outputs only as evidence, not as judgment.
+- Do not modify project files except the two required output files above.
+- Do not edit selector rules, model cards, model JSON, regression cases, review bundles, or Owner decision files.
+- Do not upgrade model lifecycle status.
+- Do not treat this pilot as Round 05 acceptance.
+
+Pilot review questions:
+
+1. Was enough local evidence available to produce a stronger review than a limited Web upload?
+2. Does the Round 04 evidence show local tuning gaps that should be addressed before Round 05?
+3. What should be tuned in the Local CCRA Agent, Runtime, helper outputs, invocation packet, or report template before formal Round 05 use?
+4. Is this pilot report suitable for comparison against Web CCRA feedback supplied later by the Owner?

local_ccra_reviews/round-04/pilot-01/returned-output.md

@@ -0,0 +1,41 @@
+# Returned Output
+
+## Return Metadata
+
+- project_id: the-mindscape-of-bro-tsong
+- review_round: round-04
+- local_pass: pilot-01
+- runtime_id: ccra-local-review
+- runtime_version: 0.1.0
+- agent_id: ccra-local-reviewer
+- agent_version: 0.1.0
+- invocation_mode: prompt_path_reference
+- carrier_type: codex_thread
+- child_session_id: 019edca7-48f3-79d3-be4a-550f4df0f13c
+- execution_status: returned
+- simulation_only: false
+- generated_at: 2026-06-19
+
+## Output Files
+
+- primary_report_path: `local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md`
+- returned_output_path: `local_ccra_reviews/round-04/pilot-01/returned-output.md`
+
+## Result
+
+The Local CCRA pilot report was written successfully.
+
+Practical result: `needs_more_local_tuning`.
+
+Summary:
+
+- Local evidence was strong enough to produce a richer first-pass review than a limited Web upload.
+- Round 04.1 target fixes are documented and regression-covered.
+- `R04-BI-022` is a documented collateral behavior change, not a hidden behavior drift.
+- Helper/profile tuning is needed before formal Round 05 Local CCRA use.
+- QPI and Intellectual Archaeology remain `draft / B / pending`.
+- This pilot is not Owner approval, Web CCRA approval, lifecycle promotion, or Round 05 acceptance.
+
+## Main Follow-Up
+
+The main project session should read `04_LOCAL_CCRA_REVIEW_REPORT.md`, then update run bookkeeping and Owner decisions outside this child reviewer output contract.

local_ccra_reviews/round-04/pilot-01/review-context.md

@@ -0,0 +1,183 @@
+# Review Context
+
+This context is an index. It does not replace reading source files.
+
+## Metadata
+
+- Review ID: `round-04-pilot-01`
+- Context profile: `ccra-local-review`
+- Status: `PASS`
+
+## Source Roots
+
+- `README.md`
+- `AGENTS.md`
+- `PROJECTS.md`
+- `knowledge_assets`
+- `docs`
+- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
+- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md`
+- `selector`
+- `tests`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch`
+
+## Files Included
+
+- `AGENTS.md` (8063 bytes)
+- `PROJECTS.md` (6784 bytes)
+- `README.md` (7915 bytes)
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.1.md` (2245 bytes)
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md` (2223 bytes)
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md` (1124 bytes)
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md` (7956 bytes)
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md` (3364 bytes)
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/BUNDLE_FILE_MANIFEST_04.1.md` (2171 bytes)
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip` (207917 bytes)
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json` (1921 bytes)
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/raw_file_list_04.1.txt` (1337 bytes)
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md` (1476 bytes)
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md` (2211 bytes)
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md` (1495 bytes)
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md` (29841 bytes)
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md` (1614 bytes)
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md` (1710 bytes)
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/optional_raw_changed_files_04.zip` (176893 bytes)
+- `docs/CHATGPT_HANDOFF_RULES.md` (2175 bytes)
+- `docs/CONTENT_STABILIZATION_PROTOCOL.md` (2331 bytes)
+- `docs/DATA_CONTRACT.md` (4225 bytes)
+- `docs/DECISIONS.md` (13018 bytes)
+- `docs/FILE_TAXONOMY.md` (5864 bytes)
+- `docs/GPT_PLAN_LOCALIZATION_PROTOCOL.md` (3185 bytes)
+- `docs/HANDOFF_TEMPLATE.md` (527 bytes)
+- `docs/INDEX_MAINTENANCE_PROTOCOL.md` (3539 bytes)
+- `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md` (3319 bytes)
+- `docs/KNOWLEDGE_ASSET_RULES.md` (3357 bytes)
+- `docs/MODEL_CARD_CONTRACT.md` (2692 bytes)
+- `docs/MODEL_EXTRACTION_RULES.md` (5596 bytes)
+- `docs/MODEL_EXTRACTION_WORKFLOW.md` (2940 bytes)
+- `docs/NON_GOALS.md` (802 bytes)
+- `docs/PROJECT_BRIEF.md` (2832 bytes)
+- `docs/QPI_CONTEXTUAL_ROUTING_RULES.md` (6769 bytes)
+- `docs/WORKFLOW.md` (7121 bytes)
+- `docs/model_case_preprocessing/README.md` (651 bytes)
+- `docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md` (4210 bytes)
+- `docs/model_case_preprocessing/qpi/README.md` (398 bytes)
+- `docs/superpowers/plans/2026-06-16-model-extraction-contract-and-workflow.md` (25201 bytes)
+- `docs/superpowers/plans/2026-06-16-project-initialization.md` (4262 bytes)
+- `docs/superpowers/plans/2026-06-17-contract-hardening-selector-calibration.md` (4352 bytes)
+- `docs/superpowers/plans/2026-06-18-round04-1-selector-rule-patch.md` (5170 bytes)
+- `docs/superpowers/plans/2026-06-18-round04-blind-routing-evaluation.md` (6590 bytes)
+- `knowledge_assets/00_用户背景与产品上下文.md` (1550 bytes)
+- `knowledge_assets/01_核心模型地图.md` (1643 bytes)
+- `knowledge_assets/02_模型卡结构规范.md` (1514 bytes)
+- `knowledge_assets/03_核心模型抽取样板.md` (2271 bytes)
+- `knowledge_assets/06_模型稳固性评级规则.md` (1473 bytes)
+- `knowledge_assets/07_产品规划过程记录.md` (1813 bytes)
+- `knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md` (9052 bytes)
+- `knowledge_assets/09_数据治理与模型调用机制说明.md` (18643 bytes)
+- `knowledge_assets/10_本地CCRA评审机制说明.md` (5415 bytes)
+- `knowledge_assets/README.md` (1382 bytes)
+- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md` (7956 bytes)
+- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md` (29841 bytes)
+- `selector/README.md` (3310 bytes)
+- `selector/qpi_case_digests.json` (108415 bytes)
+- `selector/round04_blind_inputs.json` (12470 bytes)
+- `selector/selector_calibration_inputs.json` (42665 bytes)
+- `selector/selector_examples.json` (2087 bytes)
+- `selector/selector_rules.json` (7042 bytes)
+- `tests/README.md` (846 bytes)
+- `tests/__pycache__/test_card_contract.cpython-310.pyc` (1771 bytes)
+- `tests/__pycache__/test_rebuild_indexes.cpython-310.pyc` (3739 bytes)
+- `tests/__pycache__/test_round04_blind_routing.cpython-310.pyc` (3426 bytes)
+- `tests/__pycache__/test_round04_post_patch_verification.cpython-310.pyc` (2420 bytes)
+- `tests/__pycache__/test_validate_model_library.cpython-310.pyc` (16887 bytes)
+- `tests/intellectual_archaeology.regression.json` (16743 bytes)
+- `tests/qpi.regression.json` (79553 bytes)
+- `tests/regression_cases.json` (99522 bytes)
+- `tests/regression_index.json` (797 bytes)
+- `tests/test_card_contract.py` (1255 bytes)
+- `tests/test_rebuild_indexes.py` (3291 bytes)
+- `tests/test_round04_blind_routing.py` (2680 bytes)
+- `tests/test_round04_post_patch_verification.py` (1807 bytes)
+- `tests/test_validate_model_library.py` (23038 bytes)
+
+## Files Excluded
+
+- None
+
+## Important Reports
+
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/BUNDLE_FILE_MANIFEST_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/raw_file_list_04.1.txt`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/optional_raw_changed_files_04.zip`
+- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md`
+- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
+
+## Test Or Validation Outputs
+
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json`
+- `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md`
+- `tests/README.md`
+- `tests/__pycache__/test_card_contract.cpython-310.pyc`
+- `tests/__pycache__/test_rebuild_indexes.cpython-310.pyc`
+- `tests/__pycache__/test_round04_blind_routing.cpython-310.pyc`
+- `tests/__pycache__/test_round04_post_patch_verification.cpython-310.pyc`
+- `tests/__pycache__/test_validate_model_library.cpython-310.pyc`
+- `tests/intellectual_archaeology.regression.json`
+- `tests/qpi.regression.json`
+- `tests/regression_cases.json`
+- `tests/regression_index.json`
+- `tests/test_card_contract.py`
+- `tests/test_rebuild_indexes.py`
+- `tests/test_round04_blind_routing.py`
+- `tests/test_round04_post_patch_verification.py`
+- `tests/test_validate_model_library.py`
+
+## Diff Or Changed File References
+
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/optional_raw_changed_files_04.zip`
+
+## Prior Decision References
+
+- `docs/DECISIONS.md`
+
+## Known Non Goals
+
+- `Do not decide Owner approval.`
+- `Do not replace Web CCRA final review.`
+- `Do not promote lifecycle status.`
+- `Do not modify selector rules, model cards, model JSON, regression cases, or review bundles.`
+- `Do not treat this pilot as Round 05 acceptance.`
+
+## Open Questions For Reviewer Or Agent
+
+- `Was a real child session invoked?`
+- `Can the child session be resumed?`
+- `Does the report quality reach Web CCRA level?`
+- `Which runtime, prompt, helper, or report-template adjustments are needed before Round 05?`
+
+## Blocking Errors
+
+- None
+
+## Machine Readable Manifest
+
+- `review-file-manifest.json`

local_ccra_reviews/round-04/pilot-01/review-file-manifest.json

@@ -0,0 +1,517 @@
+{
+  "review_id": "round-04-pilot-01",
+  "context_profile": "ccra-local-review",
+  "project_root": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
+  "source_roots": [
+    "README.md",
+    "AGENTS.md",
+    "PROJECTS.md",
+    "knowledge_assets",
+    "docs",
+    "reports/Round04_blind_routing_evaluation_report_2026-06-18.md",
+    "reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md",
+    "selector",
+    "tests",
+    "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation",
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
+  ],
+  "missing_source_roots": [],
+  "files_included": [
+    {
+      "path": "AGENTS.md",
+      "size_bytes": 8063,
+      "source_root": "AGENTS.md"
+    },
+    {
+      "path": "PROJECTS.md",
+      "size_bytes": 6784,
+      "source_root": "PROJECTS.md"
+    },
+    {
+      "path": "README.md",
+      "size_bytes": 7915,
+      "source_root": "README.md"
+    },
+    {
+      "path": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.1.md",
+      "size_bytes": 2245,
+      "source_root": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md",
+      "size_bytes": 2223,
+      "source_root": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md",
+      "size_bytes": 1124,
+      "source_root": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md",
+      "size_bytes": 7956,
+      "source_root": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md",
+      "size_bytes": 3364,
+      "source_root": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/BUNDLE_FILE_MANIFEST_04.1.md",
+      "size_bytes": 2171,
+      "source_root": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip",
+      "size_bytes": 207917,
+      "source_root": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json",
+      "size_bytes": 1921,
+      "source_root": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/raw_file_list_04.1.txt",
+      "size_bytes": 1337,
+      "source_root": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
+    },
+    {
+      "path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md",
+      "size_bytes": 1476,
+      "source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
+    },
+    {
+      "path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md",
+      "size_bytes": 2211,
+      "source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
+    },
+    {
+      "path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md",
+      "size_bytes": 1495,
+      "source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
+    },
+    {
+      "path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md",
+      "size_bytes": 29841,
+      "source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
+    },
+    {
+      "path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md",
+      "size_bytes": 1614,
+      "source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
+    },
+    {
+      "path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md",
+      "size_bytes": 1710,
+      "source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
+    },
+    {
+      "path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/optional_raw_changed_files_04.zip",
+      "size_bytes": 176893,
+      "source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
+    },
+    {
+      "path": "docs/CHATGPT_HANDOFF_RULES.md",
+      "size_bytes": 2175,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/CONTENT_STABILIZATION_PROTOCOL.md",
+      "size_bytes": 2331,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/DATA_CONTRACT.md",
+      "size_bytes": 4225,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/DECISIONS.md",
+      "size_bytes": 13018,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/FILE_TAXONOMY.md",
+      "size_bytes": 5864,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/GPT_PLAN_LOCALIZATION_PROTOCOL.md",
+      "size_bytes": 3185,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/HANDOFF_TEMPLATE.md",
+      "size_bytes": 527,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/INDEX_MAINTENANCE_PROTOCOL.md",
+      "size_bytes": 3539,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md",
+      "size_bytes": 3319,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/KNOWLEDGE_ASSET_RULES.md",
+      "size_bytes": 3357,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/MODEL_CARD_CONTRACT.md",
+      "size_bytes": 2692,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/MODEL_EXTRACTION_RULES.md",
+      "size_bytes": 5596,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/MODEL_EXTRACTION_WORKFLOW.md",
+      "size_bytes": 2940,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/NON_GOALS.md",
+      "size_bytes": 802,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/PROJECT_BRIEF.md",
+      "size_bytes": 2832,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/QPI_CONTEXTUAL_ROUTING_RULES.md",
+      "size_bytes": 6769,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/WORKFLOW.md",
+      "size_bytes": 7121,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/model_case_preprocessing/README.md",
+      "size_bytes": 651,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md",
+      "size_bytes": 4210,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/model_case_preprocessing/qpi/README.md",
+      "size_bytes": 398,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/superpowers/plans/2026-06-16-model-extraction-contract-and-workflow.md",
+      "size_bytes": 25201,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/superpowers/plans/2026-06-16-project-initialization.md",
+      "size_bytes": 4262,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/superpowers/plans/2026-06-17-contract-hardening-selector-calibration.md",
+      "size_bytes": 4352,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/superpowers/plans/2026-06-18-round04-1-selector-rule-patch.md",
+      "size_bytes": 5170,
+      "source_root": "docs"
+    },
+    {
+      "path": "docs/superpowers/plans/2026-06-18-round04-blind-routing-evaluation.md",
+      "size_bytes": 6590,
+      "source_root": "docs"
+    },
+    {
+      "path": "knowledge_assets/00_用户背景与产品上下文.md",
+      "size_bytes": 1550,
+      "source_root": "knowledge_assets"
+    },
+    {
+      "path": "knowledge_assets/01_核心模型地图.md",
+      "size_bytes": 1643,
+      "source_root": "knowledge_assets"
+    },
+    {
+      "path": "knowledge_assets/02_模型卡结构规范.md",
+      "size_bytes": 1514,
+      "source_root": "knowledge_assets"
+    },
+    {
+      "path": "knowledge_assets/03_核心模型抽取样板.md",
+      "size_bytes": 2271,
+      "source_root": "knowledge_assets"
+    },
+    {
+      "path": "knowledge_assets/06_模型稳固性评级规则.md",
+      "size_bytes": 1473,
+      "source_root": "knowledge_assets"
+    },
+    {
+      "path": "knowledge_assets/07_产品规划过程记录.md",
+      "size_bytes": 1813,
+      "source_root": "knowledge_assets"
+    },
+    {
+      "path": "knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md",
+      "size_bytes": 9052,
+      "source_root": "knowledge_assets"
+    },
+    {
+      "path": "knowledge_assets/09_数据治理与模型调用机制说明.md",
+      "size_bytes": 18643,
+      "source_root": "knowledge_assets"
+    },
+    {
+      "path": "knowledge_assets/10_本地CCRA评审机制说明.md",
+      "size_bytes": 5415,
+      "source_root": "knowledge_assets"
+    },
+    {
+      "path": "knowledge_assets/README.md",
+      "size_bytes": 1382,
+      "source_root": "knowledge_assets"
+    },
+    {
+      "path": "reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md",
+      "size_bytes": 7956,
+      "source_root": "reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md"
+    },
+    {
+      "path": "reports/Round04_blind_routing_evaluation_report_2026-06-18.md",
+      "size_bytes": 29841,
+      "source_root": "reports/Round04_blind_routing_evaluation_report_2026-06-18.md"
+    },
+    {
+      "path": "selector/README.md",
+      "size_bytes": 3310,
+      "source_root": "selector"
+    },
+    {
+      "path": "selector/qpi_case_digests.json",
+      "size_bytes": 108415,
+      "source_root": "selector"
+    },
+    {
+      "path": "selector/round04_blind_inputs.json",
+      "size_bytes": 12470,
+      "source_root": "selector"
+    },
+    {
+      "path": "selector/selector_calibration_inputs.json",
+      "size_bytes": 42665,
+      "source_root": "selector"
+    },
+    {
+      "path": "selector/selector_examples.json",
+      "size_bytes": 2087,
+      "source_root": "selector"
+    },
+    {
+      "path": "selector/selector_rules.json",
+      "size_bytes": 7042,
+      "source_root": "selector"
+    },
+    {
+      "path": "tests/README.md",
+      "size_bytes": 846,
+      "source_root": "tests"
+    },
+    {
+      "path": "tests/__pycache__/test_card_contract.cpython-310.pyc",
+      "size_bytes": 1771,
+      "source_root": "tests"
+    },
+    {
+      "path": "tests/__pycache__/test_rebuild_indexes.cpython-310.pyc",
+      "size_bytes": 3739,
+      "source_root": "tests"
+    },
+    {
+      "path": "tests/__pycache__/test_round04_blind_routing.cpython-310.pyc",
+      "size_bytes": 3426,
+      "source_root": "tests"
+    },
+    {
+      "path": "tests/__pycache__/test_round04_post_patch_verification.cpython-310.pyc",
+      "size_bytes": 2420,
+      "source_root": "tests"
+    },
+    {
+      "path": "tests/__pycache__/test_validate_model_library.cpython-310.pyc",
+      "size_bytes": 16887,
+      "source_root": "tests"
+    },
+    {
+      "path": "tests/intellectual_archaeology.regression.json",
+      "size_bytes": 16743,
+      "source_root": "tests"
+    },
+    {
+      "path": "tests/qpi.regression.json",
+      "size_bytes": 79553,
+      "source_root": "tests"
+    },
+    {
+      "path": "tests/regression_cases.json",
+      "size_bytes": 99522,
+      "source_root": "tests"
+    },
+    {
+      "path": "tests/regression_index.json",
+      "size_bytes": 797,
+      "source_root": "tests"
+    },
+    {
+      "path": "tests/test_card_contract.py",
+      "size_bytes": 1255,
+      "source_root": "tests"
+    },
+    {
+      "path": "tests/test_rebuild_indexes.py",
+      "size_bytes": 3291,
+      "source_root": "tests"
+    },
+    {
+      "path": "tests/test_round04_blind_routing.py",
+      "size_bytes": 2680,
+      "source_root": "tests"
+    },
+    {
+      "path": "tests/test_round04_post_patch_verification.py",
+      "size_bytes": 1807,
+      "source_root": "tests"
+    },
+    {
+      "path": "tests/test_validate_model_library.py",
+      "size_bytes": 23038,
+      "source_root": "tests"
+    }
+  ],
+  "files_excluded": [],
+  "important_reports": [
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.1.md",
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md",
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md",
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md",
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md",
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/BUNDLE_FILE_MANIFEST_04.1.md",
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip",
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json",
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/raw_file_list_04.1.txt",
+    "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md",
+    "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md",
+    "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md",
+    "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md",
+    "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md",
+    "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md",
+    "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/optional_raw_changed_files_04.zip",
+    "reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md",
+    "reports/Round04_blind_routing_evaluation_report_2026-06-18.md"
+  ],
+  "test_or_validation_outputs": [
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md",
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json",
+    "docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md",
+    "tests/README.md",
+    "tests/__pycache__/test_card_contract.cpython-310.pyc",
+    "tests/__pycache__/test_rebuild_indexes.cpython-310.pyc",
+    "tests/__pycache__/test_round04_blind_routing.cpython-310.pyc",
+    "tests/__pycache__/test_round04_post_patch_verification.cpython-310.pyc",
+    "tests/__pycache__/test_validate_model_library.cpython-310.pyc",
+    "tests/intellectual_archaeology.regression.json",
+    "tests/qpi.regression.json",
+    "tests/regression_cases.json",
+    "tests/regression_index.json",
+    "tests/test_card_contract.py",
+    "tests/test_rebuild_indexes.py",
+    "tests/test_round04_blind_routing.py",
+    "tests/test_round04_post_patch_verification.py",
+    "tests/test_validate_model_library.py"
+  ],
+  "diff_or_changed_file_references": [
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md",
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip",
+    "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json",
+    "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/optional_raw_changed_files_04.zip"
+  ],
+  "prior_decision_references": [
+    "docs/DECISIONS.md"
+  ],
+  "known_non_goals": [
+    "Do not decide Owner approval.",
+    "Do not replace Web CCRA final review.",
+    "Do not promote lifecycle status.",
+    "Do not modify selector rules, model cards, model JSON, regression cases, or review bundles.",
+    "Do not treat this pilot as Round 05 acceptance."
+  ],
+  "open_questions_for_reviewer_or_agent": [
+    "Was a real child session invoked?",
+    "Can the child session be resumed?",
+    "Does the report quality reach Web CCRA level?",
+    "Which runtime, prompt, helper, or report-template adjustments are needed before Round 05?"
+  ],
+  "metadata": {
+    "review_id": "round-04-pilot-01",
+    "project_id": "the-mindscape-of-bro-tsong",
+    "review_round": "round-04",
+    "local_pass": "pilot-01",
+    "runtime_id": "ccra-local-review",
+    "runtime_version": "0.1.0",
+    "agent_id": "ccra-local-reviewer",
+    "agent_version": "0.1.0",
+    "knowledge_base_path": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\knowledge_assets",
+    "review_goal": "Use existing Round 04 blind routing evaluation material to pilot Local CCRA invocation, persistence, and report quality.",
+    "primary_question": "Does Local CCRA produce Web CCRA-level review quality when it can inspect the full local Round 04 evidence set?",
+    "scope_statement": "Review Round 04 blind routing evaluation evidence as a historical pilot. Focus on review quality, evidence coverage, non-target behavior awareness, lifecycle/scope discipline, and readiness gaps for future Round 05 use.",
+    "non_goals": [
+      "Do not decide Owner approval.",
+      "Do not replace Web CCRA final review.",
+      "Do not promote lifecycle status.",
+      "Do not modify selector rules, model cards, model JSON, regression cases, or review bundles.",
+      "Do not treat this pilot as Round 05 acceptance."
+    ],
+    "open_questions": [
+      "Was a real child session invoked?",
+      "Can the child session be resumed?",
+      "Does the report quality reach Web CCRA level?",
+      "Which runtime, prompt, helper, or report-template adjustments are needed before Round 05?"
+    ],
+    "target_reviewer": "ccra-local-reviewer",
+    "review_bundle_paths": [
+      "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
+    ],
+    "web_final_review_policy": "owner_must_approve_inclusion",
+    "output_report_path": "local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md",
+    "returned_output_path": "local_ccra_reviews/round-04/pilot-01/returned-output.md",
+    "created_at": "2026-06-19"
+  },
+  "blocking_errors": [],
+  "machine_readable_summary": {
+    "status": "PASS",
+    "source_roots_count": 11,
+    "missing_source_roots_count": 0,
+    "files_included_count": 77,
+    "files_excluded_count": 0,
+    "important_reports_count": 18,
+    "validation_outputs_count": 18,
+    "diff_references_count": 4,
+    "prior_decisions_count": 1,
+    "blocking_error_count": 0
+  }
+}

local_ccra_reviews/round-04/pilot-01/review-metadata.json

@@ -0,0 +1,35 @@
+{
+  "review_id": "round-04-pilot-01",
+  "project_id": "the-mindscape-of-bro-tsong",
+  "review_round": "round-04",
+  "local_pass": "pilot-01",
+  "runtime_id": "ccra-local-review",
+  "runtime_version": "0.1.0",
+  "agent_id": "ccra-local-reviewer",
+  "agent_version": "0.1.0",
+  "knowledge_base_path": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\knowledge_assets",
+  "review_goal": "Use existing Round 04 blind routing evaluation material to pilot Local CCRA invocation, persistence, and report quality.",
+  "primary_question": "Does Local CCRA produce Web CCRA-level review quality when it can inspect the full local Round 04 evidence set?",
+  "scope_statement": "Review Round 04 blind routing evaluation evidence as a historical pilot. Focus on review quality, evidence coverage, non-target behavior awareness, lifecycle/scope discipline, and readiness gaps for future Round 05 use.",
+  "non_goals": [
+    "Do not decide Owner approval.",
+    "Do not replace Web CCRA final review.",
+    "Do not promote lifecycle status.",
+    "Do not modify selector rules, model cards, model JSON, regression cases, or review bundles.",
+    "Do not treat this pilot as Round 05 acceptance."
+  ],
+  "open_questions": [
+    "Was a real child session invoked?",
+    "Can the child session be resumed?",
+    "Does the report quality reach Web CCRA level?",
+    "Which runtime, prompt, helper, or report-template adjustments are needed before Round 05?"
+  ],
+  "target_reviewer": "ccra-local-reviewer",
+  "review_bundle_paths": [
+    "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
+  ],
+  "web_final_review_policy": "owner_must_approve_inclusion",
+  "output_report_path": "local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md",
+  "returned_output_path": "local_ccra_reviews/round-04/pilot-01/returned-output.md",
+  "created_at": "2026-06-19"
+}

local_ccra_reviews/round-04/pilot-01/run-notes.md

@@ -0,0 +1,83 @@
+# Local CCRA Run Notes
+
+## Run Identity
+
+- review_round: round-04
+- local_pass: pilot-01
+- review_run_dir: `local_ccra_reviews/round-04/pilot-01`
+- runtime_id: ccra-local-review
+- runtime_version: 0.1.0
+- agent_id: ccra-local-reviewer
+- agent_version: 0.1.0
+- pilot_status: setup_in_progress
+
+## Purpose
+
+Historical pilot for Round 04 blind routing evaluation material.
+
+This pilot checks:
+
+1. Whether a real child session can be invoked.
+2. Whether the child session id can be recorded and reused.
+3. Whether Local CCRA report quality is comparable to Web CCRA feedback.
+4. Whether helper outputs improve file-first review without replacing reviewer judgment.
+
+This pilot is not Round 05 acceptance.
+
+## Source Evidence
+
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/`
+- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
+- `selector/round04_blind_inputs.json`
+- `selector/selector_rules.json`
+- `selector/selector_calibration_inputs.json`
+- `tests/test_round04_blind_routing.py`
+- `tests/test_round04_post_patch_verification.py`
+
+## Helper Commands
+
+- `review-context-builder`: exit 0. Initial run completed before `knowledge_assets/` became required; rerun required with `--source-root knowledge_assets`.
+- `review-context-builder` rerun with `--source-root knowledge_assets`: exit 0. `review-context.md` and `review-file-manifest.json` now include required knowledge base files.
+- `review-bundle-audit`: exit 1. Report written; helper found blocking bundle-audit findings for the generic profile.
+- `regression-validation-gate-runner --mode dry_run`: exit 0. Report written; three gates declared and skipped as dry run.
+- `lifecycle-status-guard-scan`: exit 1. Report written; helper found blocking lifecycle/status candidates for reviewer judgment.
+
+## Skipped Helpers
+
+- `routing-behavior-diff-audit`: initially skipped unless before/after routing output files are supplied or identified.
+
+## Dispatch Record
+
+- carrier_type: codex_thread
+- invocation_mode: prompt_path_reference
+- child_session_id: 019edca7-48f3-79d3-be4a-550f4df0f13c
+- dispatch_status: dispatched
+
+## Return Record
+
+- report_path: `local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md`
+- returned_output_path: `local_ccra_reviews/round-04/pilot-01/returned-output.md`
+- return_status: returned
+- returned_at: 2026-06-19
+
+## Observed Timing
+
+- child_turn_duration_ms: 552064
+- child_turn_duration_human: about 9 minutes 12 seconds
+- timing_note: Within the expected mature-run 5-10 minute budget, and consistent with a first pilot that performed file-first evidence reading, helper-output inspection, and output self-checks.
+
+## Web / Local Comparison
+
+- comparison_path: `local_ccra_reviews/round-04/pilot-01/05_WEB_LOCAL_CCRA_COMPARISON.md`
+- comparison_scope: `2026-06-18产品交流-GPT.md` lines 1-214 versus `04_LOCAL_CCRA_REVIEW_REPORT.md`.
+- comparison_status: drafted
+
+## CCPE Patch Request
+
+- request_path: `requirements/ccpe/2026-06-19-ccra-local-reviewer-runtime-patch1.md`
+- request_status: drafted
+- requested_improvement: Make `ccra-local-reviewer` combine Web-style product diagnosis with Local CCRA full-file audit.
+
+## Resume Notes
+
+After dispatch, continue the same child session when comparing report quality or tuning `ccra-local-reviewer`.

local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md

@@ -0,0 +1,647 @@
+# Local CCRA Review Report
+
+## 1. Return Metadata
+
+- project_id: `the-mindscape-of-bro-tsong`
+- review_round: `round-04`
+- local_pass: `pilot-02`
+- turn_type: `review_turn`
+- runtime_id: `ccra-local-review`
+- runtime_version: `0.1.1`
+- agent_id: `ccra-local-reviewer`
+- agent_version: `0.1.1`
+- invocation_mode: `prompt_path_reference`
+- carrier_type: `codex_thread`
+- child_session_id: `019edcde-24be-7593-99b2-5cf014467340`
+- persistent_available: `yes_for_requested_followup_if_same_thread_is_resumed`
+- execution_status: `returned`
+- simulation_only: `false`
+- report_path: `local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md`
+- returned_output_path: `local_ccra_reviews/round-04/pilot-02/returned-output.md`
+- generated_at: `2026-06-19`
+
+## 2. Review Scope
+
+- primary_question: Can Patch 1 Local CCRA identify Round 04 product/routing issues with Web-style diagnosis while retaining local file-first audit strength?
+- scope_statement: Review initial Round 04 blind routing evidence only. Do not use Round 04.1 post-patch outcomes as this turn's judgment basis.
+- non_goals: no Owner approval, no Web CCRA replacement, no lifecycle promotion, no project file repair, no selector/model/regression edits, no Round 05 acceptance.
+- local_tuning_stage: `historical_pilot_patch1_retest`
+- web_final_review_target: `none_for_this_pilot`
+- knowledge_base_path: `C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets`
+- previous_turn_report_path: none
+
+Important scope note: current project files such as `README.md`, `docs/DECISIONS.md`, `selector/README.md`, and `selector/selector_rules.json` contain later Round 04.1 language. They were read because the invocation packet required them, but this report does not use those post-patch statements as evidence that the initial Round 04 behavior was fixed or accepted.
+
+## 3. Inputs Actually Received
+
+- Invocation and run files:
+  - `local_ccra_reviews/round-04/pilot-02/prompt-to-send.md`
+  - `local_ccra_reviews/round-04/pilot-02/turn-prompts/review-turn.prompt.md`
+  - `local_ccra_reviews/round-04/pilot-02/agent-invocation-packet.md`
+  - `local_ccra_reviews/round-04/pilot-02/run-notes.md`
+  - `local_ccra_reviews/round-04/pilot-02/review-metadata.json`
+  - `local_ccra_reviews/round-04/pilot-02/review-context.md`
+  - `local_ccra_reviews/round-04/pilot-02/review-file-manifest.json`
+  - `local_ccra_reviews/round-04/pilot-02/owner-decision.md`
+- Required project knowledge base:
+  - `knowledge_assets/`
+- Initial Round 04 evidence:
+  - `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/`
+  - `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
+  - `reports/Round04_blind_input_candidates_2026-06-18.md`
+  - `selector/round04_blind_inputs.json`
+  - `selector/selector_rules.json`
+  - `selector/README.md`
+  - `tests/test_round04_blind_routing.py`
+  - `scripts/run_round04_blind_routing.py`
+- Helper outputs:
+  - `helper-outputs/bundle-audit.md`
+  - `helper-outputs/bundle-audit.json`
+  - `helper-outputs/gate-run-report.md`
+  - `helper-outputs/gate-run-report.json`
+  - `helper-outputs/lifecycle-status-guard-scan.md`
+- Missing or intentionally unavailable:
+  - `routing-behavior-diff-audit` output: skipped by design because no after-patch evidence is allowed in this turn.
+  - Executed gate logs: unavailable; gate runner was dry-run only.
+  - Round 04.1 post-patch evidence: intentionally excluded.
+
+## 4. Files Actually Read
+
+```text
+- C:\Users\wangq\Documents\Codex\ccpe-system\agents\agent-specs\ccra-local-reviewer.agent.md
+  purpose: Local CCRA reviewer role, source policy, report requirements, authority boundary
+- C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review.runtime.md
+  purpose: runtime turn contract, helper usage, stop conditions
+- C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-report.template.md
+  purpose: Patch 1 report template
+- C:\Users\wangq\Documents\Codex\ccpe-system\integrations\skills-vault\ccra-local-review-helpers.integration.md
+  purpose: helper output confidence rules
+- README.md
+  purpose: project identity and non-goals
+- AGENTS.md
+  purpose: repository operating instructions
+- PROJECTS.md
+  purpose: cross-repository authority boundaries
+- docs/WORKFLOW.md
+  purpose: Local CCRA workflow and review bundle workflow
+- docs/DECISIONS.md
+  purpose: selector, lifecycle, Local CCRA, and boundary decisions; post-04.1 statements excluded from review_turn judgment
+- docs/QPI_CONTEXTUAL_ROUTING_RULES.md
+  purpose: QPI no-call, subject-context, issue/governance, and lifecycle boundary rules
+- docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md
+  purpose: IA depth gate, no-call, and status boundary
+- knowledge_assets/README.md
+  purpose: knowledge asset navigation
+- knowledge_assets/00_用户背景与产品上下文.md
+  purpose: product boundary and source of truth map
+- knowledge_assets/01_核心模型地图.md
+  purpose: QPI and IA status and routing relationship
+- knowledge_assets/02_模型卡结构规范.md
+  purpose: model card structure and validation background
+- knowledge_assets/03_核心模型抽取样板.md
+  purpose: model extraction and selector v0.2 background
+- knowledge_assets/06_模型稳固性评级规则.md
+  purpose: stability/lifecycle guard
+- knowledge_assets/07_产品规划过程记录.md
+  purpose: planning history and boundary
+- knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md
+  purpose: CCRA quality gates and selector v0.2 principles
+- knowledge_assets/09_数据治理与模型调用机制说明.md
+  purpose: selector/regression/calling mechanism
+- knowledge_assets/10_本地CCRA评审机制说明.md
+  purpose: Local CCRA project-side process
+- ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md
+  purpose: Round 04 brief
+- ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md
+  purpose: Round 04 scope and non-goals
+- ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md
+  purpose: frozen blind input set summary
+- ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md
+  purpose: initial Round 04 observed routing behavior
+- ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md
+  purpose: requested review questions
+- ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md
+  purpose: bundle manifest and optional zip scope
+- reports/Round04_blind_input_candidates_2026-06-18.md
+  purpose: candidate intent and coverage labels
+- reports/Round04_blind_routing_evaluation_report_2026-06-18.md
+  purpose: direct initial routing evidence
+- selector/round04_blind_inputs.json
+  purpose: frozen blind input metadata without expected labels
+- selector/selector_rules.json
+  purpose: required read; not used as initial Round 04 behavior evidence where it reflects later changes
+- selector/README.md
+  purpose: selector contract; post-04.1 statements excluded from review_turn judgment
+- tests/test_round04_blind_routing.py
+  purpose: initial runner test surface
+- scripts/run_round04_blind_routing.py
+  purpose: report generation and blind input evaluation mechanics
+- local_ccra_reviews/round-04/pilot-02/helper-outputs/*
+  purpose: helper evidence and confidence assessment
+```
+
+## 5. Automation Outputs Used
+
+```text
+- helper_id: review-context-builder
+  output_path: local_ccra_reviews/round-04/pilot-02/review-context.md; review-file-manifest.json
+  status: available
+  how_used: navigation index only; direct source files were still read
+- helper_id: review-bundle-audit
+  output_path: local_ccra_reviews/round-04/pilot-02/helper-outputs/bundle-audit.md; bundle-audit.json
+  status: failed_profile_mismatch
+  how_used: evidence that generic profile did not recognize the versioned bundle manifest; not accepted as automatic bundle failure
+- helper_id: regression-validation-gate-runner
+  output_path: local_ccra_reviews/round-04/pilot-02/helper-outputs/gate-run-report.md; gate-run-report.json
+  status: dry_run
+  how_used: evidence that gates are declared, not evidence that gates passed
+- helper_id: lifecycle-status-guard-scan
+  output_path: local_ccra_reviews/round-04/pilot-02/helper-outputs/lifecycle-status-guard-scan.md
+  status: failed_broad_scan
+  how_used: lifecycle overclaim candidate list only; many findings are outside the initial Round 04 scope
+- helper_id: routing-behavior-diff-audit
+  output_path: none
+  status: skipped
+  how_used: not applicable for review_turn because after-patch evidence is intentionally excluded
+```
+
+## 6. Executive Summary
+
+Review result: `needs_more_local_tuning`.
+
+Final action recommendation: `fix_now`.
+
+Patch 1 Local CCRA can identify the important Round 04 routing issues with file-first evidence. The clearest initial Round 04 failures are not model-content failures and not LLM-understanding failures. They are selector rule-boundary failures:
+
+- direct transformation / translation requests can be misread because payload complexity words such as `模型` leak into routing;
+- explicit IA refusal variants are not all enforced as model-level hard exclusions;
+- depth-limiting phrases such as `不要展开` and `不要深入分析` can incorrectly suppress lightweight QPI requests for `主导稀缺` or `缺信息 / 缺路径 / 缺共识`.
+
+Initial Round 04 evidence is enough to open a scoped selector patch requirement. It is not enough to claim Web final readiness, Round 05 readiness, lifecycle promotion, or product acceptance. A second `planning_turn` is needed to specify the post-patch verification package and submitted-material requirements.
+
+## 7. Issue Mechanism Diagnosis
+
+### Issue ID: R04-LCR-001
+
+- Case / Material: `R04-BI-002`
+- What failed: pure translation request selected `qpi`.
+- Why it failed: the selector treated payload word `模型` as a complexity signal even though the instruction was direct translation. This is an instruction/payload boundary failure, not an indication that QPI should classify the user's problem frame.
+- Why it is not a different failure category: this is not model-content failure, because QPI did not generate content. It is not LLM understanding failure, because the selector is explicitly rule-based and no LLM is called. It is not an IA issue because IA was rejected.
+- Failure category: `rule_boundary_problem`
+- Selector-specific type: `no-call false negative`; `QPI over-selection`; `rule-based selector failure`
+- Evidence:
+  - `reports/Round04_blind_routing_evaluation_report_2026-06-18.md` records `R04-BI-002` selected `qpi` with reason `complexity signal: 模型`.
+  - `selector/round04_blind_inputs.json` states the case was included to test pure translation as no-call.
+  - `docs/QPI_CONTEXTUAL_ROUTING_RULES.md` says translation should be `classification_scope=no_call`.
+
+### Issue ID: R04-LCR-002
+
+- Case / Material: `R04-BI-024`
+- What failed: explicit `不要进入思想考古` still selected `intellectual_archaeology`.
+- Why it failed: the model-level exclusion surface did not cover this refusal variant in the initial behavior. The selector allowed the model name and boundary/责任 complexity signals to overcome the user's explicit refusal.
+- Why it is not a different failure category: this is not a QPI-before-IA gate failure alone, because the user explicitly refused IA. It is not a model-content failure, because IA was only routed, not executed.
+- Failure category: `rule_boundary_problem`
+- Selector-specific type: `model-level exclusion failure`; `IA over-selection`
+- Evidence:
+  - `reports/Round04_blind_routing_evaluation_report_2026-06-18.md` records both `intellectual_archaeology` and `qpi` selected for `R04-BI-024`.
+  - `reports/Round04_blind_input_candidates_2026-06-18.md` states this case tests model-level hard exclusion for IA while preserving QPI-like routing.
+  - `selector/README.md` describes explicit model refusal as a model-level hard exclusion; later Round 04.1 language in the same file is excluded as proof of repair.
+
+### Issue ID: R04-LCR-003
+
+- Case / Material: `R04-BI-035`, `R04-BI-036`, same-class boundary `R04-BI-022`
+- What failed: depth-limiting language caused global no-call even when the user asked for lightweight QPI classification.
+- Why it failed: global hard no-call matched `不要深入分析` or `不要展开` before QPI-limited intent was recognized. The selector conflated "do not go deep" with "do not do lightweight problem definition".
+- Why it is not a different failure category: this is not user refusal of QPI. The requested action is exactly QPI-shaped: identify dominant scarcity or choose among missing information/path/consensus. It is also not IA under-selection, because IA should remain rejected.
+- Failure category: `rule_boundary_problem`
+- Selector-specific type: `depth-limiting override failure`; `no-call false positive`; `QPI under-selection`
+- Evidence:
+  - `reports/Round04_blind_routing_evaluation_report_2026-06-18.md` records `R04-BI-035` and `R04-BI-036` as hard no-call with QPI rejected.
+  - `selector/round04_blind_inputs.json` states these cases test QPI-limited routing while rejecting deeper modeling.
+  - `docs/QPI_CONTEXTUAL_ROUTING_RULES.md` defines QPI as front-routing / scarcity framing and does not require deep analysis.
+
+### Issue ID: R04-LCR-004
+
+- Case / Material: governance and capacity cases `R04-BI-010` through `R04-BI-017`
+- What failed: several plausible QPI problem/issue inputs no-called because no explicit positive QPI phrase appeared.
+- Why it failed: the initial selector appears too dependent on lexical QPI gate phrases such as `问题`, `缺路径`, or `缺共识`, and under-detects semantically clear governance, responsibility, capacity, or path scarcity. This is a product-routing risk, but not all such cases should be patched mechanically.
+- Why it is not a different failure category: coverage labels are not answer keys, and some statements lack an explicit user request. The correct behavior may be QPI, clarification, or low-confidence provisional routing depending on Owner policy.
+- Failure category: `product_routing_problem`
+- Selector-specific type: `possible QPI under-selection`; `calibration boundary`
+- Evidence:
+  - `reports/Round04_blind_routing_evaluation_report_2026-06-18.md` records no-call for `R04-BI-010`, `011`, `012`, `013`, `014`, `015`, and `017`; `R04-BI-016` selected QPI because it contains explicit `问题`.
+  - `docs/QPI_CONTEXTUAL_ROUTING_RULES.md` states issue weight rises around responsibility, authority, role boundary, governance, and consensus load.
+  - `reports/Round04_blind_input_candidates_2026-06-18.md` includes these cases to test governance, responsibility, consensus, resource, and path scarcity.
+
+### Issue ID: R04-LCR-005
+
+- Case / Material: likely IA and model extraction cases `R04-BI-018`, `R04-BI-026`, `R04-BI-027`, `R04-BI-038`
+- What failed: several likely depth-modeling inputs selected only QPI and rejected IA.
+- Why it failed: the initial IA heavy-depth gate is conservative and depends on a narrow set of lexical heavy signals. That protects against IA over-selection but may under-select natural model extraction or deep mechanism requests that avoid exact trigger phrases.
+- Why it is not a different failure category: not all likely IA cases should become immediate IA positives. Some may need QPI first. Some may need Owner/Web calibration on whether IA should be directly selected or only recommended after QPI.
+- Failure category: `product_routing_problem`
+- Selector-specific type: `possible IA under-selection`; `QPI-before-IA calibration`
+- Evidence:
+  - `reports/Round04_blind_routing_evaluation_report_2026-06-18.md` records QPI-only routing for the listed cases.
+  - `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md` supports IA when repeated patterns, core mechanisms, assumptions, or action boundaries require deeper modeling, while also warning IA is not default.
+  - `reports/Round04_blind_input_candidates_2026-06-18.md` marks `R04-BI-026` as a high-value natural boundary sample and `R04-BI-018` as a positive control.
+
+## 8. Patch Scope Judgment
+
+```text
+must_fix_cases:
+  - case_id: R04-BI-002
+    reason: direct translation should no-call even when payload contains model-library vocabulary.
+    required_evidence: targeted before/after result plus frozen-pool rerun showing no new direct-execution regressions.
+  - case_id: R04-BI-024
+    reason: explicit IA refusal must hard-exclude IA while preserving QPI if the remaining request is QPI-shaped.
+    required_evidence: targeted before/after result plus regression coverage for IA refusal variants.
+  - case_id: R04-BI-035
+    reason: depth-limiting language paired with dominant-scarcity request should allow lightweight QPI and reject IA.
+    required_evidence: targeted before/after result plus regression coverage.
+  - case_id: R04-BI-036
+    reason: depth-limiting language paired with缺信息/缺路径/缺共识 should allow QPI and reject IA.
+    required_evidence: targeted before/after result plus regression coverage.
+
+same_class_boundary_cases:
+  - case_id: R04-BI-022
+    reason: same depth-limiting plus QPI-limited intent mechanism as R04-BI-035/036; initial behavior is no-call.
+    patch_with_current_round: yes, if Owner accepts "主导稀缺" as sufficient QPI-limited intent despite limited object context.
+  - case_id: R04-BI-018
+    reason: model-extraction positive control selected QPI only; IA direct-selection policy needs calibration.
+    patch_with_current_round: no, unless Owner defines model extraction as immediate IA route.
+  - case_id: R04-BI-026/R04-BI-027/R04-BI-038
+    reason: natural IA boundary examples may need broader IA signals, but broadening can create over-selection.
+    patch_with_current_round: no; use calibration first.
+  - case_id: R04-BI-010 through R04-BI-017
+    reason: governance/capacity language may be QPI-relevant without explicit QPI terms.
+    patch_with_current_round: no; define provisional QPI vs clarification policy first.
+
+calibration_only_cases:
+  - case_id: R04-BI-010/R04-BI-011/R04-BI-012/R04-BI-013
+    reason: likely issue/governance QPI cases, but no explicit user request. Owner should decide whether descriptive statements trigger QPI, clarification, or no-call.
+  - case_id: R04-BI-014/R04-BI-015/R04-BI-017
+    reason: capacity/path scarcity semantics should be calibrated before adding broad keywords.
+  - case_id: R04-BI-018/R04-BI-026/R04-BI-027/R04-BI-038
+    reason: IA under-selection risk needs policy on direct IA vs QPI-first.
+  - case_id: R04-BI-030
+    reason: "老问题" is prior-context dependent; QPI selection may be acceptable only as low-confidence/provisional.
+  - case_id: R04-BI-037
+    reason: "如何提高这个账号的流量" maps to the QPI insufficient-context example but may require clarification instead of no-call or confident QPI.
+
+explicitly_not_patched:
+  - case_id: R04-BI-001/R04-BI-003/R04-BI-004/R04-BI-005/R04-BI-031/R04-BI-032/R04-BI-033
+    reason: initial no-call behavior is consistent with direct fact, rewrite, formatting, tool how-to, and word-meaning no-call rules.
+  - case_id: R04-BI-021
+    reason: initial behavior correctly preserves QPI and rejects IA for explicit "先不要思想考古".
+  - case_id: R04-BI-025
+    reason: explicit post-QPI depth handoff selected IA; no initial failure found.
+  - case_id: R04-BI-034
+    reason: direct execution with explicit analysis override selected QPI; no immediate patch needed.
+
+should_not_open_another_small_patch_round:
+  - issue_or_case: all governance/capacity/IA natural-language under-selection candidates
+    reason: these should be bundled into calibration policy and next blind/calibration evaluation, not patched one keyword at a time.
+```
+
+## 9. Verification Evidence Requirements
+
+Required for a selector/routing patch based on this review:
+
+```text
+targeted_regression_for_confirmed_target_cases: required for R04-BI-002, R04-BI-024, R04-BI-035, R04-BI-036, and any accepted same-class boundary such as R04-BI-022.
+full_frozen_pool_rerun_or_before_after_comparison: required; must show all 38 Round 04 cases before/after with selected, rejected, no-call, scores, reasons, and routing notes.
+existing_selector_regression: required; existing no-call, model-level exclusion, QPI-before-IA, and depth-limiting tests must still pass.
+calibration_smoke: required; direct-execution no-call and QPI/IA boundary samples must remain sane.
+unit_tests: required for the Round 04 runner and any selector helper changed by the patch.
+command_log_or_validation_report: required; dry-run is not sufficient for a post-patch verification claim.
+dry_run_vs_executed_gate_status: must be explicit. Current `gate-run-report` is dry-run only.
+rule_diff_only_is_sufficient: no.
+missing_evidence: after-patch routing results, routing behavior diff, executed gate logs, and Owner/Web calibration decisions are not available in this review_turn by design.
+```
+
+## 10. Before / After Behavior Review
+
+No post-patch or before/after evidence is allowed in this `review_turn`. The initial Round 04 behavior below is the only valid "before" evidence. The "after" column is intentionally unavailable.
+
+```text
+target_behavior_changes:
+  - case_id: R04-BI-002
+    before: selected qpi; no_call false.
+    after: not available in review_turn.
+    assessment: target fix required; expected after should be no-call with QPI and IA rejected.
+  - case_id: R04-BI-024
+    before: selected intellectual_archaeology and qpi.
+    after: not available in review_turn.
+    assessment: target fix required; expected after should hard-exclude IA and preserve QPI if Owner accepts lightweight QPI request.
+  - case_id: R04-BI-035
+    before: hard no-call; QPI and IA rejected.
+    after: not available in review_turn.
+    assessment: target fix required; expected after should allow QPI and reject IA.
+  - case_id: R04-BI-036
+    before: hard no-call; QPI and IA rejected.
+    after: not available in review_turn.
+    assessment: target fix required; expected after should allow QPI and reject IA.
+
+non_target_behavior_changes:
+  - case_id: not observable
+    before: initial-only evidence.
+    after: not available in review_turn.
+    assessment: routing-behavior-diff-audit is correctly skipped for this turn but must be run for any patch verification turn.
+
+accepted_collateral_behavior_changes:
+  - case_id: none accepted in this review_turn.
+    rationale: Owner decisions are pending; post-patch evidence is excluded.
+    regression_or_documentation: required after Owner decision.
+
+unexpected_regressions:
+  - case_id: not observable.
+    evidence: no after evidence in scope.
+    action: require frozen-pool rerun and before/after comparison in planning_turn.
+
+owner_or_web_calibration_needed:
+  - case_id: R04-BI-022
+    question: should "主导稀缺" plus depth-limiting wording be enough to allow QPI without more object context?
+  - case_id: R04-BI-010 through R04-BI-017
+    question: should descriptive governance/capacity statements route to provisional QPI, ask clarification, or no-call?
+  - case_id: R04-BI-018/R04-BI-026/R04-BI-027/R04-BI-038
+    question: should natural model-extraction/depth-modeling requests directly select IA or require QPI first?
+```
+
+## 11. Non-Target Behavior Changes
+
+Non-target behavior changes are not observable from initial-only evidence.
+
+For any later patch, non-target checks must at minimum prove:
+
+- direct no-call cases `R04-BI-001`, `003`, `004`, `005`, `031`, `032`, `033` remain no-call;
+- `R04-BI-021` continues to reject IA while selecting QPI;
+- `R04-BI-025` continues to select IA for explicit post-QPI depth handoff;
+- `R04-BI-034` continues to escape direct-execution no-call because it asks for problem definition;
+- broader translation/direct-transformation rules do not suppress legitimate model-library analysis requests.
+
+## 12. Calibration-Only Candidates
+
+- `R04-BI-010` through `R04-BI-013`: governance/responsibility/consensus semantics are QPI-relevant, but the round lacks expected labels. Risk if patched now: over-selecting QPI for every organizational complaint.
+- `R04-BI-014`, `R04-BI-015`, `R04-BI-017`: capacity/path scarcity semantics need product policy before keyword expansion. Risk if patched now: broad "目标/方向/时间/产出" keywords may over-route operational updates.
+- `R04-BI-018`, `R04-BI-026`, `R04-BI-027`, `R04-BI-038`: likely IA under-selection candidates. Risk if patched now: IA becomes too easy to summon from words like "结构", "长期", or "机制".
+- `R04-BI-030`: prior-context dependency. Risk if patched now: short frustration phrases become confident QPI route without subject/scenario context.
+- `R04-BI-037`: generic growth how-to. Risk if patched now: "如何提高流量" may either over-trigger QPI or incorrectly stay no-call; better policy is likely low-confidence/provisional QPI or clarification.
+
+## 13. Helper Output Confidence
+
+```text
+helper_id: review-context-builder
+output_used_as_evidence: yes
+confidence: high
+status: executed
+confidence_notes: Source roots included required knowledge_assets and Round 04 files; no missing roots. Used only as navigation.
+blocks_current_review: no
+requires_runtime_tuning: no
+
+helper_id: review-bundle-audit
+output_used_as_evidence: yes
+confidence: low
+status: failed; generic_profile; profile_mismatch; false_positive_candidate
+confidence_notes: Generic profile reports missing manifest and validation_sidecar, but the Round 04 bundle contains `BUNDLE_FILE_MANIFEST_04.md` and the review turn can directly read the files. The helper usefully reports zip readability and discovered files, but its FAIL is not an automatic review blocker.
+blocks_current_review: no
+requires_runtime_tuning: yes
+
+helper_id: regression-validation-gate-runner
+output_used_as_evidence: yes
+confidence: low
+status: dry_run
+confidence_notes: Proves gate manifest readability and declared commands only. It does not prove index check, validation, or tests passed in this pilot run.
+blocks_current_review: no
+requires_runtime_tuning: yes
+
+helper_id: lifecycle-status-guard-scan
+output_used_as_evidence: yes
+confidence: low
+status: failed; broad_scope; false_positive_candidate
+confidence_notes: Scan covers 200 files, including older rounds, prior pilot outputs, and post-04.1 files that are outside this review_turn evidence scope. It is a useful overclaim locator but not a Round 04 blocker by itself.
+blocks_current_review: no
+requires_runtime_tuning: yes
+
+helper_id: routing-behavior-diff-audit
+output_used_as_evidence: no
+confidence: not_used
+status: skipped
+confidence_notes: Appropriate for initial-only review_turn. It becomes required for any post-patch verification turn.
+blocks_current_review: no
+requires_runtime_tuning: no
+```
+
+## 14. Findings
+
+### Finding ID: F-R04-P2-001
+
+- Classification: `major`
+- Title: Translation/direct transformation no-call has payload leakage.
+- Evidence: `R04-BI-002` selected `qpi` due `complexity signal: 模型`; input metadata says pure translation should test no-call.
+- Why It Matters: If payload words drive routing, direct transformation tasks can summon cognitive models even when the user asked only for translation or formatting.
+- Recommended Action: Add instruction/payload boundary handling for direct transformation requests and verify against frozen pool.
+- Final Action Recommendation: `fix_now`
+- Owner Decision Required: yes
+- Blocks Web Final Review: yes, for a selector-patch round
+- Blocks Lifecycle Change: yes
+
+### Finding ID: F-R04-P2-002
+
+- Classification: `major`
+- Title: IA refusal variant was not enforced as hard exclusion.
+- Evidence: `R04-BI-024` selected `intellectual_archaeology` despite `不要进入思想考古`.
+- Why It Matters: Explicit model refusal is a hard user boundary. Violating it undermines selector trust more than an ordinary scoring error.
+- Recommended Action: Expand model-level IA hard exclusion variants and verify QPI remains available where the residual request is QPI-shaped.
+- Final Action Recommendation: `fix_now`
+- Owner Decision Required: yes
+- Blocks Web Final Review: yes
+- Blocks Lifecycle Change: yes
+
+### Finding ID: F-R04-P2-003
+
+- Classification: `major`
+- Title: Depth-limiting phrases suppress lightweight QPI requests.
+- Evidence: `R04-BI-035` and `R04-BI-036` no-called despite explicit dominant-scarcity / missing-information-path-consensus requests.
+- Why It Matters: "Do not go deep" should protect against IA or long analysis, not block the front-routing model the user is requesting.
+- Recommended Action: Treat accepted QPI-limited phrases as override to depth-limiting no-call while keeping IA rejected.
+- Final Action Recommendation: `fix_now`
+- Owner Decision Required: yes
+- Blocks Web Final Review: yes
+- Blocks Lifecycle Change: yes
+
+### Finding ID: F-R04-P2-004
+
+- Classification: `calibration`
+- Title: Governance and capacity descriptions reveal QPI under-selection risk.
+- Evidence: `R04-BI-010` through `R04-BI-017` mostly no-call unless explicit `问题` appears.
+- Why It Matters: QPI is supposed to detect responsibility, consensus, path, and scarcity frames. But broad keyword patching could over-route ordinary statements.
+- Recommended Action: Defer to Owner/Web calibration policy; do not open a tiny patch for every governance word.
+- Final Action Recommendation: `defer_to_calibration`
+- Owner Decision Required: yes
+- Blocks Web Final Review: no for the narrow selector patch; yes for broader selector maturity claims
+- Blocks Lifecycle Change: yes
+
+### Finding ID: F-R04-P2-005
+
+- Classification: `calibration`
+- Title: Natural IA/depth-modeling requests may be under-selected.
+- Evidence: `R04-BI-018`, `R04-BI-026`, `R04-BI-027`, and `R04-BI-038` did not select IA except when exact stronger triggers appeared in other cases.
+- Why It Matters: IA must not be default, but a too-narrow gate may miss the model extraction and deep mechanism work it exists to support.
+- Recommended Action: Calibrate direct IA route vs QPI-first route before expanding IA triggers.
+- Final Action Recommendation: `defer_to_calibration`
+- Owner Decision Required: yes
+- Blocks Web Final Review: no for the narrow patch; yes for IA selector maturity claims
+- Blocks Lifecycle Change: yes
+
+### Finding ID: F-R04-P2-006
+
+- Classification: `major`
+- Title: Post-patch verification evidence is absent from the allowed review_turn scope.
+- Evidence: helper gate output is dry-run; routing diff helper was skipped; after-patch files are intentionally excluded.
+- Why It Matters: Rule diffs or targeted examples alone cannot prove the patch did not create collateral routing regressions.
+- Recommended Action: `planning_turn` must require targeted regression, full frozen pool rerun, before/after diff, and executed gate evidence.
+- Final Action Recommendation: `fix_now`
+- Owner Decision Required: yes
+- Blocks Web Final Review: yes
+- Blocks Lifecycle Change: yes
+
+### Finding ID: F-R04-P2-007
+
+- Classification: `minor`
+- Title: Helper profiles need runtime tuning before formal repeated use.
+- Evidence: bundle audit generic profile treats `BUNDLE_FILE_MANIFEST_04.md` as extra and reports manifest missing; lifecycle scan includes broad out-of-scope files.
+- Why It Matters: Helper exit codes can become noisy and should not be treated as automatic Local CCRA conclusions.
+- Recommended Action: Tune helper profiles or document profile limitations in the next Local CCRA planning output.
+- Final Action Recommendation: `document_only`
+- Owner Decision Required: no for the current review judgment; yes for runtime tuning priority
+- Blocks Web Final Review: no
+- Blocks Lifecycle Change: no
+
+## 15. Engineering Pass vs Product Judgment
+
+```text
+What engineering evidence shows:
+- The frozen blind input pool has 38 inputs and intentionally lacks expected routing labels.
+- The Round 04 runner records selected models, rejected models, no-call status, scores, reasons, and penalties.
+- The test file verifies loader/report behavior and absence of answer-key fields.
+- The helper gate manifest declares index, validation, and test gates, but the actual helper run was dry-run.
+
+What product/model-governance question remains:
+- Which observed routes are incorrect, which are acceptable conservative no-calls, and which should become calibration rather than immediate regression?
+- How broad should QPI semantics be for governance/capacity statements without explicit user requests?
+- When should IA be selected directly versus routed as a next model after QPI?
+
+What evidence would close the gap:
+- Owner/Web classification of target failures.
+- Post-patch full frozen-pool before/after routing report.
+- Executed selector regression, calibration smoke, unit tests, index check, and validation.
+- Explicit documentation of collateral changes and accepted calibration-only cases.
+```
+
+## 16. Lifecycle And Scope Guard
+
+```text
+Claim: QPI and Intellectual Archaeology remain draft / B / pending.
+Evidence: Round 04 bundle scope file, knowledge_assets model map, stability rules, and QPI/IA docs.
+Required authority: Owner / CCRA / Web CCRA for any lifecycle change.
+Assessment: compliant. No lifecycle promotion should occur.
+
+Claim: Round 04 initial report does not score correctness and does not upgrade model status.
+Evidence: `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`.
+Required authority: Owner / CCRA for post-review labels and patch acceptance.
+Assessment: compliant.
+
+Claim: helper lifecycle scan reports many blocking findings.
+Evidence: `helper-outputs/lifecycle-status-guard-scan.md`.
+Required authority: Local CCRA judgment plus Owner decision before treating any candidate as accepted finding.
+Assessment: low-confidence broad scan for this turn; not a current Round 04 blocker without triage.
+
+Claim: current docs contain later Round 04.1 closure language.
+Evidence: `README.md`, `docs/DECISIONS.md`, `selector/README.md`, `selector/selector_rules.json`.
+Required authority: excluded from review_turn initial Round 04 judgment.
+Assessment: read but not used as proof of initial issue resolution or lifecycle readiness.
+```
+
+## 17. Local Tuning Recommendations
+
+1. Open a scoped selector patch requirement for `R04-BI-002`, `R04-BI-024`, `R04-BI-035`, and `R04-BI-036`; include `R04-BI-022` only if Owner accepts it as same-class QPI-limited intent.
+2. Require full frozen Round 04 before/after behavior comparison before claiming repair.
+3. Convert accepted target failures into regression cases after Owner/Web classification, not before.
+4. Keep governance/capacity and natural IA examples in calibration until product policy is explicit.
+5. Tune helper profiles so versioned manifests and out-of-scope lifecycle scans do not appear as automatic blockers.
+
+## 18. Web Final Review Readiness
+
+Choice: `not_ready`.
+
+Reason: initial Round 04 evidence shows clear selector patch needs, but the allowed review scope contains no post-patch behavior, no executed gates, no before/after diff, and no Owner decision. The material can proceed to a `planning_turn` for next-review requirements; it should not be treated as ready for Web final review or Round 05 acceptance.
+
+## 19. Final Action Recommendation
+
+Choice: `fix_now`.
+
+Next should happen:
+
+- Continue to `planning_turn` in the same child session.
+- Define the exact post-patch verification evidence required for the target cases and same-class boundaries.
+- Preserve Round 04.1/post-patch materials outside this review_turn until the planning turn or a dedicated post-patch verification turn asks for them.
+
+Next should not happen:
+
+- Do not promote QPI or IA lifecycle status.
+- Do not treat Local CCRA output as Owner approval.
+- Do not treat the helper exit codes as automatic review conclusions.
+- Do not open broad keyword patches for all calibration-only cases.
+- Do not claim Round 05 or Web final readiness from this historical pilot.
+
+## 20. Owner Decision Points
+
+```text
+- decision_id: OD-R04-001
+  decision_needed: accept the four must-fix initial Round 04 target failures.
+  options: accept_all | accept_subset | request_web_baseline_comparison_first
+  recommended_default: accept_all
+
+- decision_id: OD-R04-002
+  decision_needed: classify R04-BI-022 as must-fix same-class, calibration-only, or acceptable conservative no-call.
+  options: include_in_patch | calibration_only | leave_no_call
+  recommended_default: include_in_patch, because "主导稀缺" is QPI-shaped.
+
+- decision_id: OD-R04-003
+  decision_needed: define policy for descriptive governance/capacity statements without explicit requests.
+  options: provisional_qpi | ask_clarifying_question | no_call_until_request
+  recommended_default: ask_clarifying_question or provisional_qpi with low confidence.
+
+- decision_id: OD-R04-004
+  decision_needed: define direct IA versus QPI-first route for natural model-extraction/deep-mechanism inputs.
+  options: direct_ia_when_depth_intent_clear | qpi_first_always | qpi_plus_ia_when_both_signals_present
+  recommended_default: qpi_plus_ia_when both clear depth intent and model-extraction intent appear.
+
+- decision_id: OD-R04-005
+  decision_needed: decide whether helper profile tuning is required before formal Round 05 Local CCRA use.
+  options: tune_now | document_limitations | defer
+  recommended_default: document_limitations for this pilot, tune before repeated formal use.
+```
+
+## 21. Limits And Uncertainty
+
+- I did not read or use `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md`.
+- I did not read or use `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/`.
+- I did not inspect `optional_raw_changed_files_04.zip` beyond helper-reported readability and direct reads of source files already available in the repository.
+- I did not run validation or tests; helper evidence is dry-run only and the user requested review output, not repairs.
+- I did not compare against Web CCRA/GPT baseline lines 1-214 because this `review_turn` was scoped to local file-first review output. That comparison belongs to the later comparison plan.
+- Some required current project files contain post-04.1 statements. Those files were read, but post-04.1 conclusions were excluded from this turn's Round 04 initial judgment.
+
+## 22. Resume Instructions
+
+```text
+turn_type: planning_turn
+same_child_session_id: 019edcde-24be-7593-99b2-5cf014467340
+first_turn_report_path: local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md
+owner_decision_path: local_ccra_reviews/round-04/pilot-02/owner-decision.md
+next_review_target: Round 04.1 post-patch routing verification requirements
+planning_output_path: local_ccra_reviews/round-04/pilot-02/next-review-requirements.md
+```
+
+Planning turn should not re-review the full initial Round 04 bundle unless Owner adds new evidence or changes the scope. It should translate this report into required submitted materials, target cases, evidence gates, helper expectations, and Web/Owner calibration questions for the next review.

local_ccra_reviews/round-04/pilot-02/05_WEB_LOCAL_CCRA_COMPARISON.md

@@ -0,0 +1,111 @@
+# Web / Local CCRA Three-Way Comparison
+
+## Scope
+
+This note compares three review outputs for the same Round 04 source problem:
+
+1. Web CCRA / GPT baseline: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\讨论\2026-06-18产品交流-GPT.md`, lines 1-214 only.
+2. Local CCRA pilot-01: `local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md` and `local_ccra_reviews/round-04/pilot-01/05_WEB_LOCAL_CCRA_COMPARISON.md`.
+3. Local CCRA pilot-02 after CCPE Patch 1:
+   - `local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md`
+   - `local_ccra_reviews/round-04/pilot-02/next-review-requirements.md`
+   - `local_ccra_reviews/round-04/pilot-02/returned-output.md`
+
+This comparison does not use Web baseline material after line 214, because later content belongs to the Round 04.1 review and closeout.
+
+## High-Level Judgment
+
+Pilot-02 is materially better than pilot-01 and is now close enough to Web CCRA's first-review quality for formal local first-review use in this project, with explicit limits.
+
+The important improvement is not only format. Pilot-02 now performs the same core judgment Web made:
+
+- `R04-BI-002` is a rule-based selector no-call / instruction-payload boundary failure, not an LLM understanding failure.
+- `R04-BI-024` is an explicit Intellectual Archaeology refusal / model-level exclusion failure.
+- `R04-BI-035` and `R04-BI-036` are depth-limiting override failures: "do not go deep" should not become global no-call when the user asks for lightweight QPI.
+- governance, capacity, and natural IA boundary cases should be calibration work, not another small keyword patch.
+- Round 04.1 must include post-patch verification, not only a rule diff.
+
+Pilot-02 also adds local-only strengths that Web cannot reliably provide from a limited upload: file-first evidence coverage, helper-output confidence classification, lifecycle / authority guard checks, and same-child-session continuation into a planning turn.
+
+## Outcome Matrix
+
+| Dimension | Web Baseline | Pilot-01 | Pilot-02 |
+|---|---|---|---|
+| Product mechanism diagnosis | Strong. Immediately identifies selector boundary failure and no LLM involvement. | Weaker. Mostly audits already-produced Round 04.1 evidence. | Strong. Reconstructs the same mechanism from initial Round 04 evidence. |
+| Patch scope judgment | Strong. Selects 002, 024, 035, 036 and keeps wider cases for calibration. | Partial. Confirms later target set but less useful before the fix. | Strong. Separates must-fix, same-class boundary, calibration-only, and explicitly-not-patched cases. |
+| Next review requirements | Strong. Requires targeted regression, full rerun, existing regression, and command logs. | Partial. Notes missing helper/runtime risks. | Strong. Produces `next-review-requirements.md` with submitted-material checklist and evidence requirements. |
+| Local file audit | Limited by upload and conversation context. | Strong. Reads broad local evidence and helper outputs. | Strong. Reads required knowledge base, Round 04 evidence, helper outputs, and runtime contract. |
+| Helper confidence | Not covered in baseline. | Finds helper/runtime risks, but this dominates the report. | Better balanced. Classifies helper outputs as evidence with confidence limits. |
+| Conversation persistence | Not applicable. | One review child session. | Verified two-turn same-child workflow: `review_turn` then `planning_turn`. |
+| Formal readiness | Web remains final reviewer. | Needs more local tuning before formal use. | Ready for formal local first review under listed conditions. |
+
+## Where Pilot-02 Now Matches Web
+
+Pilot-02 matches the Web baseline on the central Round 04 diagnosis. It says the initial failures are selector rule-boundary failures:
+
+- direct transformation / translation requests can leak payload terms such as `模型` into QPI routing;
+- IA refusal variants must hard-exclude IA;
+- depth-limiting language should suppress IA depth, not suppress lightweight QPI.
+
+It also matches Web on the next-step shape: do not introduce an LLM selector, do not upgrade QPI or Intellectual Archaeology, do not broaden governance / capacity cases by keyword, and do require a Round 04.1 post-patch verification pass.
+
+This fixes the main pilot-01 gap. Pilot-01 acted like a file-first auditor after the fix existed. Pilot-02 acts like a product reviewer before the fix, then a local planning reviewer after the first judgment.
+
+## Where Pilot-02 Is Better Than Web
+
+Pilot-02 is stronger in evidence discipline:
+
+- It records the exact child session id: `019edcde-24be-7593-99b2-5cf014467340`.
+- It reads the mandatory project knowledge base path.
+- It explicitly excludes Round 04.1 post-patch evidence from `review_turn`, preserving fair historical comparison.
+- It detects that current files may contain later Round 04.1 language and avoids using that as initial Round 04 proof.
+- It separates helper outputs from reviewer judgment and labels confidence limits.
+- It produces a second-turn package plan instead of leaving the Owner to convert findings into review materials manually.
+
+The `planning_turn` output is especially useful for reducing small Web sub-rounds. It requires a rule patch summary, target labels / Owner decisions, full 38-case frozen-pool before/after comparison, targeted regression, existing selector regression, calibration smoke, executed command logs, bundle manifest, and carry-forward Owner/Web calibration questions.
+
+## Remaining Weaknesses
+
+Pilot-02 still has operational limits:
+
+- `review-bundle-audit` used a generic profile and misclassified the versioned Round 04 manifest pattern.
+- `regression-validation-gate-runner` evidence was dry-run only in this setup.
+- `lifecycle-status-guard-scan` produced broad whole-repo noise that requires human or reviewer triage.
+- `routing-behavior-diff-audit` was correctly skipped for the initial no-hindsight review, but must be required when before/after evidence exists.
+- The report is long. It is good as an audit artifact, but formal routine use should keep the short returned summary visible for the Owner.
+
+These are not blockers for using Local CCRA as a formal local first-review lane. They are helper/runtime maturity issues that should remain documented and be improved as the workflow repeats.
+
+## Readiness Recommendation
+
+Recommendation: `ready_for_formal_local_first_review_with_conditions`.
+
+Local CCRA v0.1.1 is ready to use for this project as the formal local first review before Web final review. It should not replace Owner judgment or Web CCRA final review.
+
+Conditions for formal use:
+
+1. Always run a real child session and record `child_session_id`.
+2. Use the two-turn pattern by default: `review_turn` for findings, then same-child `planning_turn` for next review requirements and submitted-material guidance.
+3. Keep `knowledge_base_path` mandatory and point it to `knowledge_assets/`.
+4. Treat helper outputs as evidence only, with explicit confidence / noise classification.
+5. Require before/after routing diff evidence whenever the reviewed material includes a patch or post-patch verification.
+6. Keep Local CCRA reports local by default; include them in Web CCRA upload only when Owner explicitly decides to.
+7. Do not claim lifecycle promotion, Round 05 acceptance, or Web approval from Local CCRA alone.
+
+## Further Tuning
+
+CCPE Patch 2 is recommended as a non-blocking hardening patch. It is not required before the next Owner/Web-defined local first-review run if Patch 1 behavior remains intact.
+
+Recommended Patch 2 improvements:
+
+- add a project-aware or CCRA-aware bundle audit profile for versioned manifests;
+- decide when gate runner should execute rather than dry-run;
+- make routing behavior diff mandatory for patch verification turns;
+- tune lifecycle scan scope so broad historical findings do not dominate current review;
+- add a short Owner-facing executive summary template on top of the long audit report.
+
+## Final Conclusion
+
+Pilot-02 achieved the intended Patch 1 target. It preserves Local CCRA's file-first advantages while recovering the Web-style mechanism diagnosis and repair-scope judgment that pilot-01 lacked.
+
+The practical path is to start using Local CCRA for formal local first review in the current project after the Owner and Web CCRA define the next round's work, keep Web as planning / final review partner, and use the first real run as live validation of Patch 2 hardening if CCPE updates it.

local_ccra_reviews/round-04/pilot-02/agent-invocation-packet.md

@@ -0,0 +1,234 @@
+---
+packet_type: local-ccra-agent-invocation-packet
+runtime_id: ccra-local-review
+agent_id: ccra-local-reviewer
+runtime_version: 0.1.1
+agent_version: 0.1.1
+review_id: round-04-pilot-02
+status: ready_for_dispatch
+---
+
+# Local CCRA Agent Invocation Packet
+
+## 1. Invocation Metadata
+
+```yaml
+packet_id: round-04-pilot-02
+created_at: 2026-06-19
+client_project_root: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong
+knowledge_base_path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets
+review_round: round-04
+local_pass: pilot-02
+review_run_dir: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02
+turn_type: review_turn
+invocation_mode: prompt_path_reference
+carrier_type: codex_thread
+child_session_id: 019edcde-24be-7593-99b2-5cf014467340
+persistent_child_session_required: true
+same_child_session_as_review_turn_required: false
+simulation_allowed: false
+```
+
+## 2. Canonical Artifacts
+
+```yaml
+canonical_agent_path: C:\Users\wangq\Documents\Codex\ccpe-system\agents\agent-specs\ccra-local-reviewer.agent.md
+canonical_runtime_path: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review.runtime.md
+runtime_setup_path: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-runtime-setup.md
+report_template_path: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-report.template.md
+planning_template_path: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-next-review-requirements.template.md
+integration_registration_path: C:\Users\wangq\Documents\Codex\ccpe-system\integrations\skills-vault\ccra-local-review-helpers.integration.md
+```
+
+## 3. Role Integrity Requirement
+
+The invoked participant must act as `ccra-local-reviewer`.
+
+The reviewer must:
+
+```text
+read local evidence directly
+cite files actually read
+use helper outputs only as evidence
+respect the requested turn_type
+write the report to the requested output contract
+preserve Owner/Web CCRA authority boundaries
+avoid project file edits except contracted output files
+avoid lifecycle promotion
+avoid main-session roleplay
+```
+
+If this packet cannot be dispatched to a real child session or equivalent isolated participant context, the valid state is:
+
+```text
+blocked_waiting_for_participant_output
+```
+
+## 4. Task Context
+
+```yaml
+turn_type: review_turn
+primary_question: Can Patch 1 Local CCRA identify Round 04 product/routing issues with Web-style diagnosis while retaining local file-first audit strength?
+scope_statement: Review the initial Round 04 blind routing evaluation material as a historical pilot. Do not use Round 04.1 post-patch outcome evidence during review_turn. After review_turn, the same child session will be continued with planning_turn.
+non_goals:
+  - Do not decide Owner approval.
+  - Do not replace Web CCRA final review.
+  - Do not promote lifecycle status.
+  - Do not modify selector rules, model cards, model JSON, regression cases, or review bundles.
+  - Do not treat this pilot as Round 05 acceptance.
+  - Do not use Round 04.1 post-patch result files as review_turn evidence.
+local_tuning_stage: historical_pilot_patch1_retest
+web_final_review_target: none_for_this_pilot
+known_prior_rounds:
+  - round-03
+  - round-03.1
+  - round-03.2
+  - round-03.2a
+  - round-04
+owner_supplied_notes: Compare later against Web CCRA baseline lines 1-214 and pilot-01. This review_turn should not read the later Round 04.1 post-patch evidence.
+first_turn_report_path:
+owner_decision_path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\owner-decision.md
+next_review_target: Round 04.1 post-patch routing verification requirements
+web_comparison_source: C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\讨论\2026-06-18产品交流-GPT.md
+web_comparison_source_range: lines 1-214
+```
+
+## 5. Input Files
+
+Required:
+
+```text
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\README.md
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\AGENTS.md
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\PROJECTS.md
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets\README.md
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets\
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\review-context.md
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\review-file-manifest.json
+```
+
+Project and round-specific evidence:
+
+```text
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\docs\WORKFLOW.md
+  purpose: workflow and review rules
+  required: true
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\docs\DECISIONS.md
+  purpose: accepted selector and lifecycle decisions
+  required: true
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\docs\QPI_CONTEXTUAL_ROUTING_RULES.md
+  purpose: QPI routing boundary
+  required: true
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\docs\INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md
+  purpose: IA depth gate boundary
+  required: true
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\reports\Round04_blind_routing_evaluation_report_2026-06-18.md
+  purpose: Round 04 initial evaluation report
+  required: true
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\reports\Round04_blind_input_candidates_2026-06-18.md
+  purpose: blind input candidate context
+  required: true
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\selector\round04_blind_inputs.json
+  purpose: full Round 04 blind input set
+  required: true
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\selector\selector_rules.json
+  purpose: current selector rules at the time of local retest
+  required: true
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\selector\README.md
+  purpose: selector operating contract
+  required: true
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\tests\test_round04_blind_routing.py
+  purpose: Round 04 test surface
+  required: false
+```
+
+Review bundles:
+
+```text
+- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\ccra_review_bundle\round-04_2026-06-18_blind-input-routing-evaluation
+  purpose: primary Round 04 Web CCRA review bundle
+```
+
+Excluded from `review_turn`:
+
+```text
+- reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md
+- ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/
+```
+
+Reason: avoid hindsight in comparison with Web CCRA baseline lines 1-214.
+
+Helper outputs:
+
+```text
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\helper-outputs\bundle-audit.md
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\helper-outputs\bundle-audit.json
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\helper-outputs\gate-run-report.md
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\helper-outputs\gate-run-report.json
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\helper-outputs\lifecycle-status-guard-scan.md
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\helper-outputs\lifecycle-status-guard-scan.json
+```
+
+Unavailable helper outputs:
+
+```text
+- routing-behavior-diff-audit: skipped for review_turn because no post-patch before/after evidence is included in the initial Round 04 evidence scope.
+```
+
+## 6. Output Contract
+
+The reviewer must write:
+
+```yaml
+review_turn_report_path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\04_LOCAL_CCRA_REVIEW_REPORT.md
+planning_turn_output_path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\next-review-requirements.md
+comparison_turn_output_path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\05_WEB_LOCAL_CCRA_COMPARISON.md
+returned_output_path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\returned-output.md
+required_report_template: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-report.template.md
+required_planning_template: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-next-review-requirements.template.md
+```
+
+Output mapping:
+
+```text
+review_turn -> 04_LOCAL_CCRA_REVIEW_REPORT.md
+planning_turn -> next-review-requirements.md
+comparison_turn -> 05_WEB_LOCAL_CCRA_COMPARISON.md or project-defined comparison path
+```
+
+## 7. Continuity Policy
+
+```yaml
+same_child_session_preferred: true
+resume_allowed: true
+planning_turn_requires_same_child_session: true
+resume_requires:
+  - previous report
+  - owner-decision.md when present
+  - new or changed evidence list
+  - unchanged-evidence statement
+```
+
+For `planning_turn`, continue the same `child_session_id`, reference the first-turn report, and do not re-review the full current bundle unless new evidence was added or the Owner explicitly asks.
+
+## 8. Session Logging
+
+The project main session must record dispatch method, child session id, helper commands, exit codes, files written, skipped helpers, and manual approvals in:
+
+```text
+C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\run-notes.md
+```
+
+## 9. No-Simulation Requirement
+
+Formal Local CCRA output must not be simulated in the project main session.
+
+If a simulated dry run is explicitly requested, label it:
+
+```text
+simulation-only
+excluded-from-synthesis
+not-a-formal-report
+```
+
+Simulation-only output cannot be used as the Local CCRA report.

local_ccra_reviews/round-04/pilot-02/gate-manifest.yaml

@@ -0,0 +1,31 @@
+gates:
+  - gate_id: index-check
+    command:
+      - python
+      - scripts\rebuild_indexes.py
+      - --check
+    working_directory: .
+    expected_exit_code: 0
+    log_file: logs/index-check.log
+    timeout_seconds: 120
+    required_before_review: true
+  - gate_id: model-library-validation
+    command:
+      - python
+      - scripts\validate_model_library.py
+    working_directory: .
+    expected_exit_code: 0
+    log_file: logs/model-library-validation.log
+    timeout_seconds: 120
+    required_before_review: true
+  - gate_id: round04-blind-routing-tests
+    command:
+      - python
+      - -m
+      - pytest
+      - tests\test_round04_blind_routing.py
+    working_directory: .
+    expected_exit_code: 0
+    log_file: logs/round04-blind-routing-tests.log
+    timeout_seconds: 240
+    required_before_review: false

local_ccra_reviews/round-04/pilot-02/helper-outputs/bundle-audit.json

@@ -0,0 +1,74 @@
+{
+  "bundle_root": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\ccra_review_bundle\\round-04_2026-06-18_blind-input-routing-evaluation",
+  "profile": "generic",
+  "files_discovered": [
+    "00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md",
+    "01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md",
+    "02_BLIND_INPUT_SET_04.md",
+    "03_ROUTING_EVALUATION_REPORT_04.md",
+    "04_REVIEW_QUESTIONS_FOR_GPT_04.md",
+    "BUNDLE_FILE_MANIFEST_04.md",
+    "optional_raw_changed_files_04.zip"
+  ],
+  "required_files_present": {
+    "brief": [
+      "00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md"
+    ]
+  },
+  "required_files_missing": [
+    "manifest",
+    "validation_sidecar"
+  ],
+  "optional_files_present": {
+    "report": [
+      "03_ROUTING_EVALUATION_REPORT_04.md"
+    ],
+    "zip": [
+      "optional_raw_changed_files_04.zip"
+    ]
+  },
+  "manifest_status": {
+    "status": "missing",
+    "files": []
+  },
+  "zip_status": {
+    "status": "readable",
+    "files": [
+      "optional_raw_changed_files_04.zip"
+    ],
+    "entry_counts": {
+      "optional_raw_changed_files_04.zip": 29
+    }
+  },
+  "validation_sidecar_status": {
+    "status": "missing",
+    "files": []
+  },
+  "report_status": {
+    "status": "present",
+    "files": [
+      "03_ROUTING_EVALUATION_REPORT_04.md"
+    ]
+  },
+  "warnings": [
+    "Extra file not matched by profile: 01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md",
+    "Extra file not matched by profile: 02_BLIND_INPUT_SET_04.md",
+    "Extra file not matched by profile: 04_REVIEW_QUESTIONS_FOR_GPT_04.md",
+    "Extra file not matched by profile: BUNDLE_FILE_MANIFEST_04.md"
+  ],
+  "blocking_errors": [
+    "Missing required manifest file.",
+    "Missing required validation_sidecar file."
+  ],
+  "machine_readable_summary": {
+    "status": "FAIL",
+    "files_discovered_count": 7,
+    "required_missing_count": 2,
+    "warning_count": 4,
+    "blocking_error_count": 2,
+    "manifest_status": "missing",
+    "zip_status": "readable",
+    "validation_sidecar_status": "missing",
+    "report_status": "present"
+  }
+}

local_ccra_reviews/round-04/pilot-02/helper-outputs/bundle-audit.md

@@ -0,0 +1,48 @@
+# Review Bundle Audit
+
+## Summary
+
+- Status: `FAIL`
+- Bundle root: `C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\ccra_review_bundle\round-04_2026-06-18_blind-input-routing-evaluation`
+- Profile: `generic`
+- Files discovered: 7
+- Required files missing: 2
+- Warnings: 4
+- Blocking errors: 2
+
+## Required Files
+
+- `brief`: `00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md`
+
+Missing:
+- `manifest`
+- `validation_sidecar`
+
+## Package Status
+
+- `manifest_status`: `missing` (none)
+- `validation_sidecar_status`: `missing` (none)
+- `zip_status`: `readable` (`optional_raw_changed_files_04.zip`)
+- `report_status`: `present` (`03_ROUTING_EVALUATION_REPORT_04.md`)
+
+## Blocking Errors
+
+- Missing required manifest file.
+- Missing required validation_sidecar file.
+
+## Warnings
+
+- Extra file not matched by profile: 01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md
+- Extra file not matched by profile: 02_BLIND_INPUT_SET_04.md
+- Extra file not matched by profile: 04_REVIEW_QUESTIONS_FOR_GPT_04.md
+- Extra file not matched by profile: BUNDLE_FILE_MANIFEST_04.md
+
+## Files Discovered
+
+- `00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md`
+- `01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md`
+- `02_BLIND_INPUT_SET_04.md`
+- `03_ROUTING_EVALUATION_REPORT_04.md`
+- `04_REVIEW_QUESTIONS_FOR_GPT_04.md`
+- `BUNDLE_FILE_MANIFEST_04.md`
+- `optional_raw_changed_files_04.zip`

local_ccra_reviews/round-04/pilot-02/helper-outputs/gate-run-report.json

@@ -0,0 +1,48 @@
+{
+  "project_root": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
+  "gate_manifest_path": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\local_ccra_reviews\\round-04\\pilot-02\\gate-manifest.yaml",
+  "mode": "dry_run",
+  "commands_declared": [
+    "index-check",
+    "model-library-validation",
+    "round04-blind-routing-tests"
+  ],
+  "commands_run": [],
+  "commands_skipped": [
+    {
+      "gate_id": "index-check",
+      "reason": "dry_run"
+    },
+    {
+      "gate_id": "model-library-validation",
+      "reason": "dry_run"
+    },
+    {
+      "gate_id": "round04-blind-routing-tests",
+      "reason": "dry_run"
+    }
+  ],
+  "exit_codes": {},
+  "pass_fail_status": "DRY_RUN",
+  "duration": 0.0,
+  "log_paths": {},
+  "environment_notes": [
+    "Commands are declared by the manifest.",
+    "Passing gates are engineering evidence only; they do not imply product acceptance or lifecycle approval.",
+    "python: 3.11.15",
+    "platform: Windows-10-10.0.26200-SP0"
+  ],
+  "gate_results": [],
+  "manifest_errors": [],
+  "changed_files": [],
+  "machine_readable_summary": {
+    "status": "DRY_RUN",
+    "commands_declared_count": 3,
+    "commands_run_count": 0,
+    "commands_skipped_count": 3,
+    "manifest_error_count": 0,
+    "failed_count": 0,
+    "timeout_count": 0,
+    "changed_file_count": 0
+  }
+}

local_ccra_reviews/round-04/pilot-02/helper-outputs/gate-run-report.md

@@ -0,0 +1,28 @@
+# Gate Run Report
+
+## Summary
+
+- Status: `DRY_RUN`
+- Commands declared: 3
+- Commands run: 0
+- Commands skipped: 3
+- Manifest errors: 0
+- Changed files: 0
+
+## Gate Results
+
+- None
+
+## Skipped Gates
+
+- `index-check`: dry_run
+- `model-library-validation`: dry_run
+- `round04-blind-routing-tests`: dry_run
+
+## Manifest Errors
+
+- None
+
+## Changed Files
+
+- None

local_ccra_reviews/round-04/pilot-02/helper-outputs/lifecycle-status-guard-scan.md

@@ -0,0 +1,387 @@
+# Lifecycle Status Guard Scan
+
+## Summary
+
+- Status: `FAIL`
+- Files scanned: 200
+- Blocking findings: 115
+- Warnings: 0
+- Evidence-present observations: 50
+
+## Blocking Findings
+
+- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/03_VALIDATION_AND_COMMAND_LOG_03.2.md` line 59: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/03_VALIDATION_AND_COMMAND_LOG_03.2a.md` line 47: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `docs/DECISIONS.md` line 175: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md` line 160: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 204: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 210: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 215: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 221: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 226: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 232: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 237: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 243: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 248: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 254: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 259: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 265: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 270: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 276: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 281: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 287: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 292: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 298: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 303: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 309: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 314: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 320: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 325: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 331: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 336: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 342: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 347: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 353: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 358: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 364: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 369: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 375: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 380: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 386: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 391: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 397: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 402: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 408: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 413: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 438: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 444: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 449: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 455: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 460: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 466: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 471: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 477: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 482: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 488: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 493: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 499: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 504: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 510: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 515: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 521: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 526: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 532: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 537: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 543: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 548: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 554: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 559: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 565: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 570: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 576: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 581: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 587: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 592: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 598: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 603: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 609: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 614: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 620: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 625: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 631: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 636: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 642: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 647: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 16: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 17: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 18: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 19: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 20: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 21: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 22: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 23: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 24: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 25: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 26: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 27: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 28: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 29: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 30: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 31: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md` line 263: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md` line 275: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md` line 11: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 11: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 100: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 357: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 519: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 528: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 618: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md` line 11: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md` line 7: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md` line 698: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md` line 81: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md` line 618: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-research-office.cases.md` line 7: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `selector/qpi_case_digests.json` line 1261: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+- `selector/qpi_case_digests.json` line 2187: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
+
+## Warnings
+
+- None
+
+## Observations
+
+- `local_ccra_reviews/README.md` line 119: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 188: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 193: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 199: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 422: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 427: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 433: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 655: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 667: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 679: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 691: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 703: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 715: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 727: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 739: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 751: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 763: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 775: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 787: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 799: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 811: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 823: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 835: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 847: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 859: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 871: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 883: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 895: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 933: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 938: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 938: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 950: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 950: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 938: `ccra-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 945: `ccra-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 950: `ccra-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 950: `ccra-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 938: `CCRA approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 950: `CCRA approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 13: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 14: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 15: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 32: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 33: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 41: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 42: `ccra-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml` line 14: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml` line 15: `ccra-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-02/lifecycle-guard-config.yaml` line 14: `owner-approved` - evidence marker present; approval validity not decided.
+- `local_ccra_reviews/round-04/pilot-02/lifecycle-guard-config.yaml` line 15: `ccra-approved` - evidence marker present; approval validity not decided.
+
+## Files Scanned
+
+- `AGENTS.md`
+- `cards/card_index.md`
+- `cards/intellectual_archaeology.md`
+- `cards/qpi.md`
+- `cards/README.md`
+- `ccra_review_bundle/round-02_2026-06-16_second-audit/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md`
+- `ccra_review_bundle/round-02_2026-06-16_second-audit/01_GUIDANCE_PACK_AND_COMPLIANCE_MATRIX.md`
+- `ccra_review_bundle/round-02_2026-06-16_second-audit/02_CURRENT_ASSET_PACK.md`
+- `ccra_review_bundle/round-02_2026-06-16_second-audit/03_REPORTS_DIFF_AND_COMMAND_LOG.md`
+- `ccra_review_bundle/round-02_2026-06-16_second-audit/BUNDLE_FILE_MANIFEST.md`
+- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF03.1.md`
+- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/01_PATCH_MATRIX_03.1.md`
+- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/02_CURRENT_ASSET_PACK03.1.md`
+- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/03_VALIDATION_AND_COMMAND_LOG03.1.md`
+- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/04_REVIEW_QUESTIONS_FOR_GPT03.1.md`
+- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/BUNDLE_FILE_MANIFEST03.1.md`
+- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_03.2.md`
+- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/01_PATCH_MATRIX_03.2.md`
+- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/02_CURRENT_ASSET_PACK_03.2.md`
+- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/03_VALIDATION_AND_COMMAND_LOG_03.2.md`
+- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/04_REVIEW_QUESTIONS_FOR_GPT_03.2.md`
+- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/BUNDLE_FILE_MANIFEST_03.2.md`
+- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_03.2a.md`
+- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/01_PATCH_MATRIX_03.2a.md`
+- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/02_CURRENT_ASSET_PACK_03.2a.md`
+- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/03_VALIDATION_AND_COMMAND_LOG_03.2a.md`
+- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/04_REVIEW_QUESTIONS_FOR_GPT_03.2a.md`
+- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/BUNDLE_FILE_MANIFEST_03.2a.md`
+- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md`
+- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/01_GUIDANCE_PACK_AND_COMPLIANCE_MATRIX.md`
+- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/02_CURRENT_ASSET_PACK.md`
+- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/03_REPORTS_DIFF_AND_COMMAND_LOG.md`
+- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/04_QPI_CASE_PROMOTION_SUMMARY_AND_REVIEW_GUIDE.md`
+- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/05_REVIEW_QUESTIONS_FOR_GPT.md`
+- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/BUNDLE_FILE_MANIFEST.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/BUNDLE_FILE_MANIFEST_04.1.md`
+- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md`
+- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md`
+- `docs/CHATGPT_HANDOFF_RULES.md`
+- `docs/CONTENT_STABILIZATION_PROTOCOL.md`
+- `docs/DATA_CONTRACT.md`
+- `docs/DECISIONS.md`
+- `docs/FILE_TAXONOMY.md`
+- `docs/GPT_PLAN_LOCALIZATION_PROTOCOL.md`
+- `docs/HANDOFF_TEMPLATE.md`
+- `docs/INDEX_MAINTENANCE_PROTOCOL.md`
+- `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md`
+- `docs/KNOWLEDGE_ASSET_RULES.md`
+- `docs/MODEL_CARD_CONTRACT.md`
+- `docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md`
+- `docs/model_case_preprocessing/qpi/README.md`
+- `docs/model_case_preprocessing/README.md`
+- `docs/MODEL_EXTRACTION_RULES.md`
+- `docs/MODEL_EXTRACTION_WORKFLOW.md`
+- `docs/NON_GOALS.md`
+- `docs/PROJECT_BRIEF.md`
+- `docs/QPI_CONTEXTUAL_ROUTING_RULES.md`
+- `docs/superpowers/plans/2026-06-16-model-extraction-contract-and-workflow.md`
+- `docs/superpowers/plans/2026-06-16-project-initialization.md`
+- `docs/superpowers/plans/2026-06-17-contract-hardening-selector-calibration.md`
+- `docs/superpowers/plans/2026-06-18-round04-1-selector-rule-patch.md`
+- `docs/superpowers/plans/2026-06-18-round04-blind-routing-evaluation.md`
+- `docs/WORKFLOW.md`
+- `knowledge_assets/00_用户背景与产品上下文.md`
+- `knowledge_assets/01_核心模型地图.md`
+- `knowledge_assets/02_模型卡结构规范.md`
+- `knowledge_assets/03_核心模型抽取样板.md`
+- `knowledge_assets/06_模型稳固性评级规则.md`
+- `knowledge_assets/07_产品规划过程记录.md`
+- `knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md`
+- `knowledge_assets/09_数据治理与模型调用机制说明.md`
+- `knowledge_assets/10_本地CCRA评审机制说明.md`
+- `knowledge_assets/README.md`
+- `local_ccra_reviews/README.md`
+- `local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md`
+- `local_ccra_reviews/round-04/pilot-01/05_WEB_LOCAL_CCRA_COMPARISON.md`
+- `local_ccra_reviews/round-04/pilot-01/agent-invocation-packet.md`
+- `local_ccra_reviews/round-04/pilot-01/gate-manifest.yaml`
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.json`
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.md`
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.json`
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.md`
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json`
+- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md`
+- `local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml`
+- `local_ccra_reviews/round-04/pilot-01/owner-decision.md`
+- `local_ccra_reviews/round-04/pilot-01/prompt-to-send.md`
+- `local_ccra_reviews/round-04/pilot-01/returned-output.md`
+- `local_ccra_reviews/round-04/pilot-01/review-context.md`
+- `local_ccra_reviews/round-04/pilot-01/review-file-manifest.json`
+- `local_ccra_reviews/round-04/pilot-01/review-metadata.json`
+- `local_ccra_reviews/round-04/pilot-01/run-notes.md`
+- `local_ccra_reviews/round-04/pilot-02/agent-invocation-packet.md`
+- `local_ccra_reviews/round-04/pilot-02/gate-manifest.yaml`
+- `local_ccra_reviews/round-04/pilot-02/helper-outputs/bundle-audit.json`
+- `local_ccra_reviews/round-04/pilot-02/helper-outputs/bundle-audit.md`
+- `local_ccra_reviews/round-04/pilot-02/helper-outputs/gate-run-report.json`
+- `local_ccra_reviews/round-04/pilot-02/helper-outputs/gate-run-report.md`
+- `local_ccra_reviews/round-04/pilot-02/lifecycle-guard-config.yaml`
+- `local_ccra_reviews/round-04/pilot-02/owner-decision.md`
+- `local_ccra_reviews/round-04/pilot-02/prompt-to-send.md`
+- `local_ccra_reviews/round-04/pilot-02/review-metadata.json`
+- `local_ccra_reviews/round-04/pilot-02/run-notes.md`
+- `local_ccra_reviews/round-04/pilot-02/turn-prompts/comparison-turn.prompt.md`
+- `local_ccra_reviews/round-04/pilot-02/turn-prompts/planning-turn.prompt.md`
+- `local_ccra_reviews/round-04/pilot-02/turn-prompts/review-turn.prompt.md`
+- `models/intellectual_archaeology.model.json`
+- `models/model_index.json`
+- `models/qpi.model.json`
+- `models/README.md`
+- `PROJECTS.md`
+- `README.md`
+- `reports/baseline_before_content_stabilization_v0.2.md`
+- `reports/changed_files_manifest.md`
+- `reports/ChatGPT交接文档_模型库MVP_2026-06-16.md`
+- `reports/ChatGPT交接文档_模型库MVP_第二轮内容稳定化_2026-06-16.md`
+- `reports/Codex_工程产物摘要_v0.1.md`
+- `reports/Codex_本地CCRA规划落地_2026-06-19.md`
+- `reports/Codex_模型资产链路摘要_v0.1.md`
+- `reports/Codex新会话交接文档_CCRA评审后处理_2026-06-16.md`
+- `reports/Codex新会话交接文档_QPI案例草稿审阅与第三轮后续_2026-06-17.md`
+- `reports/Codex新会话交接文档_Round03.1评审后续_2026-06-17.md`
+- `reports/Codex新会话交接文档_Round03.2a评审准备_2026-06-17.md`
+- `reports/Codex新会话交接文档_Round03.2评审准备_2026-06-17.md`
+- `reports/Codex新会话交接文档_Round04.1关闭与Round05准备_2026-06-18.md`
+- `reports/Codex新会话交接文档_模型库MVP_2026-06-16.md`
+- `reports/command_log.md`
+- `reports/content_review_report.md`
+- `reports/content_review_report_v0.2.md`
+- `reports/evidence_coverage_matrix.md`
+- `reports/evidence_coverage_report_v0.2.md`
+- `reports/GPT规划落地差异检查_v0.1.md`
+- `reports/GPT讨论上下文_QPI草稿案例审阅_2026-06-17.md`
+- `reports/index_check_report.md`
+- `reports/index_rebuild_report.md`
+- `reports/model_card_sync_report_v0.2.md`
+- `reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/README.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-engineering-center.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-research-office.cases.md`
+- `reports/model_review_status.json`
+- `reports/next_action_register_v0.2.md`
+- `reports/open_questions_for_CCRA.md`
+- `reports/README.md`
+- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md`
+- `reports/Round04_blind_input_candidates_2026-06-18.md`
+- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
+- `reports/schema_change_notes.md`
+- `reports/selector_calibration_smoke_report.md`
+- `reports/selector_regression_report.md`
+- `reports/selector_regression_report_v0.2.md`
+- `reports/selector_score_breakdown.md`
+- `reports/validation_report.md`
+- `reports/内容修复检查摘要_v0.1.md`
+- `reports/内容修复检查摘要_v0.2.md`
+- `reports/规则Schema工作流检查摘要_v0.1.md`
+- `requirements/ccpe/2026-06-19-ccra-local-reviewer-runtime-patch1.md`
+- `requirements/ccpe/2026-06-19-ccra-local-reviewer-runtime.md`
+- `requirements/ccpe/README.md`
+- `requirements/skills-vault/2026-06-18-review-bundle-zip-packager.md`
+- `requirements/skills-vault/README.md`
+- `schemas/card_index.schema.json`
+- `schemas/model_card.schema.json`
+- `schemas/model_index.schema.json`
+- `schemas/model_spec.schema.json`
+- `schemas/README.md`
+- `schemas/regression_case.schema.json`
+- `schemas/source_article.schema.json`
+- `schemas/source_excerpt.schema.json`
+- `scripts/README.md`
+- `selector/qpi_case_digests.json`
+- `selector/README.md`
+- `selector/round04_blind_inputs.json`
+- `selector/selector_calibration_inputs.json`
+- `selector/selector_examples.json`
+- `selector/selector_rules.json`
+- `sources/evidence_coverage.matrix.json`
+- `sources/README.md`
+- `sources/source_articles.json`
+- `sources/source_excerpts.json`
+- `tests/intellectual_archaeology.regression.json`
+- `tests/qpi.regression.json`
+- `tests/README.md`
+- `tests/regression_cases.json`
+- `tests/regression_index.json`

local_ccra_reviews/round-04/pilot-02/lifecycle-guard-config.yaml

@@ -0,0 +1,38 @@
+watched_paths:
+  - "**/*.md"
+  - "**/*.json"
+  - "**/*.yaml"
+  - "**/*.yml"
+status_fields:
+  - status
+  - lifecycle
+  - model.status
+  - model.lifecycle
+forbidden_status_values:
+  - stable
+  - accepted
+  - owner-approved
+  - ccra-approved
+warning_status_values:
+  - candidate
+  - ready-for-review
+required_evidence_markers:
+  - owner_decision
+  - owner decision
+  - ccra_review
+  - ccra review
+  - web ccra
+approved_phrases:
+  - owner-approved
+  - ccra-approved
+  - Owner approved
+  - CCRA approved
+forbidden_phrases:
+  - production-ready
+  - released to production
+  - final approved
+allowed_contexts:
+  - do not say
+  - must not claim
+  - example:
+evidence_window_chars: 240

local_ccra_reviews/round-04/pilot-02/next-review-requirements.md

@@ -0,0 +1,300 @@
+# Local CCRA Next Review Requirements
+
+## 1. Return Metadata
+
+- project_id: `the-mindscape-of-bro-tsong`
+- review_round: `round-04`
+- local_pass: `pilot-02`
+- turn_type: `planning_turn`
+- runtime_id: `ccra-local-review`
+- runtime_version: `0.1.1`
+- agent_id: `ccra-local-reviewer`
+- agent_version: `0.1.1`
+- invocation_mode: `prompt_path_reference`
+- carrier_type: `codex_thread`
+- child_session_id: `019edcde-24be-7593-99b2-5cf014467340`
+- same_child_session_as_review_turn: `yes`
+- first_turn_report_path: `local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md`
+- owner_decision_path: `local_ccra_reviews/round-04/pilot-02/owner-decision.md`
+- planning_output_path: `local_ccra_reviews/round-04/pilot-02/next-review-requirements.md`
+- generated_at: `2026-06-19`
+
+## 2. Planning Scope
+
+- next_review_goal: define the submitted materials and verification evidence required for a Round 04.1 post-patch routing verification / regression pass.
+- target_round_or_pass: `round-04.1_selector-rule-patch_verification`
+- planning_basis:
+  - `local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md`
+  - `local_ccra_reviews/round-04/pilot-02/owner-decision.md`
+  - `local_ccra_reviews/round-04/pilot-02/agent-invocation-packet.md`
+- explicit_non_goals:
+  - Do not re-review the full initial Round 04 bundle in this planning turn.
+  - Do not use this planning output as Owner approval.
+  - Do not treat Round 04.1 verification as Round 05 acceptance.
+  - Do not promote QPI or Intellectual Archaeology lifecycle status.
+  - Do not modify selector rules, tests, knowledge assets, model files, or review bundles in this turn.
+
+Owner decision status is still `pending`. This plan therefore defines required review materials and recommended defaults; it does not convert the first-turn findings into accepted work.
+
+## 3. Required Submitted Materials
+
+```text
+- material_id: M-01-review-brief
+  required_path_or_bundle_slot: ccra_review_bundle/<round-04.1>/00_OPEN_THIS_FIRST_*.md
+  purpose: state the review goal, target failures, non-goals, and authority boundary.
+  required: yes
+  notes: Must say this is a post-patch verification pass, not a second blind test and not lifecycle promotion.
+
+- material_id: M-02-rule-patch-summary-and-diff
+  required_path_or_bundle_slot: ccra_review_bundle/<round-04.1>/01_RULE_PATCH_SUMMARY_AND_DIFF_*.md
+  purpose: show exactly what selector rule surfaces changed and why.
+  required: yes
+  notes: Must map changes to R04-BI-002, R04-BI-024, R04-BI-035, R04-BI-036, and any accepted same-class case such as R04-BI-022.
+
+- material_id: M-03-expected-routing-labels-or-owner-decisions
+  required_path_or_bundle_slot: ccra_review_bundle/<round-04.1>/02_EXPECTED_ROUTING_LABELS_*.md or owner-decision-backed equivalent
+  purpose: prevent Web CCRA from inferring target labels from prose.
+  required: yes
+  notes: Must separate must-fix, same-class boundary, calibration-only, and explicitly-not-patched cases.
+
+- material_id: M-04-post-patch-routing-verification-report
+  required_path_or_bundle_slot: reports/Round04_1_post_patch_routing_verification_report_*.md and bundle copy
+  purpose: provide full frozen-pool rerun after the patch.
+  required: yes
+  notes: Must include all 38 Round 04 inputs, not only target cases.
+
+- material_id: M-05-before-after-routing-diff
+  required_path_or_bundle_slot: helper-outputs/routing-behavior-diff.md or a report section with equivalent table
+  purpose: show target changes, non-target changes, accepted collateral behavior, and regressions.
+  required: yes
+  notes: If the helper cannot run, include a manual before/after table and explain the missing helper risk.
+
+- material_id: M-06-regression-and-command-log
+  required_path_or_bundle_slot: ccra_review_bundle/<round-04.1>/04_REGRESSION_AND_COMMAND_LOG_*.md
+  purpose: prove executed tests and validation gates, not dry-run declarations.
+  required: yes
+  notes: Include exact commands, exit codes, timestamps or run context, and changed-file impact.
+
+- material_id: M-07-existing-selector-regression
+  required_path_or_bundle_slot: reports/selector_regression_report*.md or command log section
+  purpose: prove existing no-call, model-exclusion, QPI-before-IA, and depth-limiting protections still pass.
+  required: yes
+  notes: Must not rely only on targeted target-case checks.
+
+- material_id: M-08-calibration-smoke
+  required_path_or_bundle_slot: reports/selector_calibration_smoke_report*.md or command log section
+  purpose: prove direct-execution, QPI, and IA boundaries remain sane after patch.
+  required: yes
+  notes: Especially watch translation/direct transformation and IA trigger over-expansion.
+
+- material_id: M-09-bundle-manifest
+  required_path_or_bundle_slot: ccra_review_bundle/<round-04.1>/BUNDLE_FILE_MANIFEST_*.md
+  purpose: let reviewers inspect package completeness without relying on upload order.
+  required: yes
+  notes: Use versioned filenames to avoid Web ChatGPT file confusion.
+
+- material_id: M-10-optional-raw-changed-files
+  required_path_or_bundle_slot: ccra_review_bundle/<round-04.1>/optional_raw_changed_files_<round>.zip
+  purpose: allow exact inspection of selector, tests, scripts, reports, and relevant docs.
+  required: yes
+  notes: Preserve source-relative paths. Include zip validation/readback summary.
+
+- material_id: M-11-local-ccra-first-turn-report
+  required_path_or_bundle_slot: local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md
+  purpose: optional context for Web CCRA on why these verification requirements exist.
+  required: no
+  notes: Include in Web upload only if Owner explicitly asks Web CCRA to review Local CCRA findings.
+
+- material_id: M-12-owner-decision-record
+  required_path_or_bundle_slot: local_ccra_reviews/round-04/pilot-02/owner-decision.md or round-specific decision note
+  purpose: show which findings and same-class boundaries Owner accepted, rejected, or deferred.
+  required: yes before final acceptance claims
+  notes: Current status is pending; absence blocks acceptance language, not evidence collection.
+```
+
+## 4. Required Verification Evidence
+
+```text
+targeted_regression:
+  required: yes
+  cases: R04-BI-002, R04-BI-024, R04-BI-035, R04-BI-036
+  conditional_cases: R04-BI-022 if Owner accepts it as same-class QPI-limited intent
+  expected: target failures change in the intended direction only.
+
+full_frozen_pool_rerun_or_before_after_comparison:
+  required: yes
+  scope: all 38 Round 04 inputs
+  expected: selected_models, rejected_models, no_call, score, reasons, penalties, and routing_notes before/after.
+
+existing_regression_or_unit_tests:
+  required: yes
+  minimum: round04 runner tests, selector regression, any post-patch verification tests, and touched selector helper tests.
+  expected: executed, not dry-run.
+
+calibration_smoke:
+  required: yes
+  expected: no-call, direct execution, QPI problem-definition, IA refusal, QPI-before-IA, and depth-limiting smoke coverage.
+
+validation_report:
+  required: yes
+  minimum: index check and model library validation if package claims model-library consistency.
+  expected: no lifecycle upgrade from validation pass.
+
+command_log:
+  required: yes
+  minimum: command, working directory, exit code, output file path, and whether files changed.
+  expected: dry-run must be labeled dry-run and cannot support pass claims.
+
+dry_run_acceptable: no for final verification; yes only for planning/preflight manifest readability.
+```
+
+## 5. Expected Before / After Comparisons
+
+```text
+- comparison_id: C-01-target-fixes
+  before_source: reports/Round04_blind_routing_evaluation_report_2026-06-18.md
+  after_source: reports/Round04_1_post_patch_routing_verification_report_<date>.md
+  expected_fields: input_id, input_text, selected_models, rejected_models, no_call, score, reasons, penalties, routing_notes
+  target_cases: R04-BI-002, R04-BI-024, R04-BI-035, R04-BI-036
+  non_target_cases_to_watch: R04-BI-001, R04-BI-003, R04-BI-004, R04-BI-005, R04-BI-021, R04-BI-025, R04-BI-031, R04-BI-032, R04-BI-033, R04-BI-034
+
+- comparison_id: C-02-same-class-boundary
+  before_source: reports/Round04_blind_routing_evaluation_report_2026-06-18.md
+  after_source: post-patch frozen-pool rerun
+  expected_fields: no_call, QPI selected/rejected, IA selected/rejected, exclusion reason
+  target_cases: R04-BI-022 if accepted into patch scope
+  non_target_cases_to_watch: all depth-limiting and IA-refusal cases, especially R04-BI-021 and R04-BI-023
+
+- comparison_id: C-03-direct-execution-collateral
+  before_source: initial Round 04 report plus existing selector regression
+  after_source: post-patch report plus regression output
+  expected_fields: no_call status and reasons for fact lookup, translation, rewrite, formatting, direct execution, how-to, dictionary judgment
+  target_cases: R04-BI-002
+  non_target_cases_to_watch: R04-BI-001, R04-BI-003, R04-BI-004, R04-BI-005, R04-BI-031, R04-BI-032, R04-BI-033, R04-BI-034
+
+- comparison_id: C-04-calibration-not-patched
+  before_source: first-turn report section 12
+  after_source: post-patch report calibration section
+  expected_fields: unchanged/deferred status, reason, Owner/Web question
+  target_cases: none
+  non_target_cases_to_watch: R04-BI-010 through R04-BI-017, R04-BI-018, R04-BI-026, R04-BI-027, R04-BI-030, R04-BI-037, R04-BI-038
+```
+
+## 6. Open Owner Decisions
+
+```text
+- decision_id: OD-R04-001
+  decision_needed: accept the four must-fix initial Round 04 target failures as the patch target.
+  options: accept_all | accept_subset | request_web_baseline_comparison_first
+  recommended_default: accept_all
+  blocks_next_review: no for evidence collection; yes for final acceptance language.
+
+- decision_id: OD-R04-002
+  decision_needed: classify R04-BI-022 as must-fix same-class, calibration-only, or acceptable conservative no-call.
+  options: include_in_patch | calibration_only | leave_no_call
+  recommended_default: include_in_patch
+  blocks_next_review: yes if the next package claims R04-BI-022 as accepted collateral or target behavior.
+
+- decision_id: OD-R04-003
+  decision_needed: define policy for descriptive governance/capacity statements without explicit requests.
+  options: provisional_qpi | ask_clarifying_question | no_call_until_request
+  recommended_default: ask_clarifying_question or provisional_qpi with low confidence.
+  blocks_next_review: no for narrow patch verification; yes for broader selector maturity claims.
+
+- decision_id: OD-R04-004
+  decision_needed: define direct IA versus QPI-first route for natural model-extraction/deep-mechanism inputs.
+  options: direct_ia_when_depth_intent_clear | qpi_first_always | qpi_plus_ia_when_both_signals_present
+  recommended_default: qpi_plus_ia_when both clear depth intent and model-extraction intent appear.
+  blocks_next_review: no for narrow patch verification; yes for IA route maturity claims.
+
+- decision_id: OD-R04-005
+  decision_needed: decide whether helper profile tuning is required before formal Round 05 Local CCRA use.
+  options: tune_now | document_limitations | defer
+  recommended_default: document_limitations for this pilot, tune before repeated formal use.
+  blocks_next_review: no, if limitations are explicit.
+```
+
+## 7. Explicit Non-Goals
+
+```text
+- non_goal: no lifecycle status upgrade
+  reason: QPI and Intellectual Archaeology remain draft / B / pending until Owner / CCRA lifecycle authority changes that.
+
+- non_goal: no Round 05 acceptance claim
+  reason: Round 04.1 verification only proves a scoped selector patch if evidence passes.
+
+- non_goal: no second blind test claim
+  reason: after expected labels and target cases exist, this is a post-patch verification pass, not blind evaluation.
+
+- non_goal: no broad governance/capacity keyword patch
+  reason: those cases are calibration-only until Owner/Web policy is explicit.
+
+- non_goal: no IA trigger broadening without calibration
+  reason: IA is a deep model and should not become default because of words like structure, mechanism, long-term, or model.
+
+- non_goal: no LLM selector, RAG, database, frontend, backend, user system, or third model
+  reason: outside model_library_mvp selector patch scope.
+
+- non_goal: no helper exit-code absolutism
+  reason: helper output is evidence only; profile mismatch, dry-run, and broad scans must be judged by the reviewer.
+```
+
+## 8. Recommended Web CCRA Review Questions
+
+1. Do the Round 04.1 submitted materials prove the four target cases were fixed without creating non-target regressions across the full frozen 38-case pool?
+2. Should `R04-BI-022` be treated as an accepted same-class QPI-limited override, calibration-only, or conservative no-call?
+3. Are governance/capacity descriptive cases (`R04-BI-010` through `R04-BI-017`) better handled as provisional QPI, clarification, or no-call until the user asks for analysis?
+4. Should natural model-extraction/deep-mechanism cases (`R04-BI-018`, `026`, `027`, `038`) directly select IA, select QPI first, or select both when depth intent is explicit?
+5. Is the verification package sufficient to avoid a further small patch round, or should remaining boundary issues be deferred into a broader calibration round?
+6. Does any wording in the package imply lifecycle promotion, Round 05 acceptance, or Owner/Web approval beyond the evidence?
+
+## 9. Material Package Checklist
+
+```text
+review_brief:
+  required: yes
+  pass_condition: states target scope, non-goals, and post-patch verification identity.
+
+rule_or_model_diff:
+  required: yes
+  pass_condition: selector rule changes mapped to target cases; no model content/lifecycle changes unless separately justified.
+
+expected_labels_or_decisions:
+  required: yes
+  pass_condition: target, same-class, calibration-only, and explicitly-not-patched cases are separated.
+
+post_patch_verification_report:
+  required: yes
+  pass_condition: all 38 frozen inputs rerun with score/reason details.
+
+regression_and_command_log:
+  required: yes
+  pass_condition: commands executed with exit codes; no dry-run used as pass evidence.
+
+bundle_manifest:
+  required: yes
+  pass_condition: versioned manifest names recognized by human reviewer even if generic helper profile is noisy.
+
+optional_raw_changed_files:
+  required: yes
+  pass_condition: source-relative zip entries and readback/validation summary included.
+
+local_ccra_report:
+  required: optional
+  pass_condition: included only with Owner approval; otherwise referenced locally, not uploaded as formal Web evidence.
+
+owner_decision_record:
+  required: yes before acceptance claims
+  pass_condition: records accepted, rejected, deferred, or escalated findings; current `pending` is not acceptance.
+```
+
+## 10. Limits And Carry-Forward Risks
+
+- Owner decision remains pending. The next package may gather evidence, but it should not claim accepted fixes without a decision record.
+- The first-turn report identified clear `fix_now` targets but did not inspect any post-patch evidence. The next review must not cite this plan as proof that the patch worked.
+- `routing-behavior-diff-audit` was skipped in review_turn for good reason, but before/after routing comparison is required for the post-patch pass.
+- `regression-validation-gate-runner` was dry-run only. The next package needs executed gates if it claims verification.
+- `review-bundle-audit` used a generic profile that did not recognize versioned bundle manifests. Human-readable bundle manifest evidence is still required, and helper profile limitations should be documented.
+- `lifecycle-status-guard-scan` was broad and noisy. The next review should include a lifecycle/scope guard section focused on the submitted package, not a whole-repository false-positive dump.
+- Calibration-only cases must stay explicitly out of the narrow patch acceptance claim. They can be listed as next-round policy questions, not evidence that the patch is incomplete.
+- Current project docs may contain later Round 04.1 language. The next review should clearly distinguish source evidence, patch evidence, closeout language, and lifecycle claims.