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
@@ -172,10 +173,18 @@ CCRA review packages are archived by round under `ccra_review_bundle/round-NN_YY
 
 Files intended for GPT / CCRA upload inside a review bundle should include the round version in the filename, for example `_03.2`. Raw changed-file zips should also include the round version while preserving source-relative paths inside the archive.
 
+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. Start Round 04 blind input routing evaluation only after an explicit owner instruction; do not modify selector rules before that evaluation.
+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. Defer any third-model expansion until the current QPI selector and case layer are accepted.
+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. Route missing reusable extraction, inspection, or stability-scoring tools to `requirements/skills-vault/` or `requirements/ccpe/` instead of improvising local platform features.
+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.

cards/intellectual_archaeology.md

@@ -175,7 +175,7 @@
 - 机制稳定性：中等，七层结构清晰，但层级之间的真实递进关系需要更多案例验证。
 - 边界清晰度：中等，最小充分下潜原则已明确，但执行时容易过度下钻。
 - 来源证据质量：较高，核心定义和七层结构来自原文，停止条件来自综合应用材料。
-- 回归测试表现：pending，当前已有 19 条回归用例，已覆盖 positive、boundary、misuse、no_call、selector_gate 和 pipeline；Round 03.2 已纳入明确拒绝思想考古的模型级 hard exclusion 陷阱。
+- 回归测试表现：pending，当前已有 20 条回归用例，已覆盖 positive、boundary、misuse、no_call、selector_gate 和 pipeline；Round 03.2 已纳入明确拒绝思想考古的模型级 hard exclusion 陷阱，Round 04.1 已纳入 `不要进入思想考古` hard exclusion 变体。
 
 评级理由：纵向下潜机制清晰，适合深度建模，但七层结构和停止条件需要进一步稳定。
 
@@ -185,11 +185,15 @@
 
 `pending`
 
-当前已有 19 条回归用例，覆盖 positive、boundary、misuse、no_call、selector_gate 和 pipeline。Round 03.2 重点新增：
+当前已有 20 条回归用例，覆盖 positive、boundary、misuse、no_call、selector_gate 和 pipeline。Round 03.2 重点新增：
 
 - `case_ia_negative_explicit_do_not_call_001`
 - `case_ia_negative_only_qpi_001`
 
+Round 04.1 重点新增：
+
+- `case_ia_round04_do_not_enter_archaeology_001`
+
 ## 示例输入
 
 - “我想把过去文章中的认知模型抽取出来，但不知道这些模型到底稳不稳，应该怎么判断？”

cards/qpi.md

@@ -204,7 +204,7 @@ QPI 的三分结构、核心匮乏物、主体性和动态性有清晰来源支
 - 机制稳定性：中高，扫描匮乏物和匹配处理范式的机制明确。
 - 边界清晰度：中等，混合型问题、多视角分歧和上下文不足场景仍需更多测试。
 - 来源证据质量：较高，主体性和动态性来自 2025 原文，核心匮乏物和误框定规则来自 2026 原文，应用规则来自综合文档。
-- 回归测试表现：pending，当前已有 58 条 QPI 回归用例；其中 Round 03 / 03.1 已纳入 owner-reviewed case layer、selector no-call、multi-perspective 和低上下文 provisional 边界用例，Round 03.2 已纳入普通 how-to / 词义判断 no-call 陷阱，Round 03.2a 已纳入 depth-limiting QPI override 陷阱。生命周期仍保持 draft。
+- 回归测试表现：pending，当前已有 62 条 QPI 回归用例；其中 Round 03 / 03.1 已纳入 owner-reviewed case layer、selector no-call、multi-perspective 和低上下文 provisional 边界用例，Round 03.2 已纳入普通 how-to / 词义判断 no-call 陷阱，Round 03.2a 已纳入 depth-limiting QPI override 陷阱，Round 04.1 已纳入 translation payload no-call、depth-limiting QPI override 和 IA heavy-signal anti-recall 陷阱。生命周期仍保持 draft。
 
 评级理由：三分结构清晰，适合作为入口路由模型，但需要补充大量边界案例，防止过度升维或降维。
 
@@ -214,7 +214,7 @@ QPI 的三分结构、核心匮乏物、主体性和动态性有清晰来源支
 
 `pending`
 
-当前已有 58 条 QPI 回归用例，覆盖 positive、boundary、misuse、no_call、selector_gate 和 pipeline。Round 03 / 03.1 重点新增：
+当前已有 62 条 QPI 回归用例，覆盖 positive、boundary、misuse、no_call、selector_gate 和 pipeline。Round 03 / 03.1 重点新增：
 
 - owner-reviewed flow / disappointment / organizational year-end-review cases；
 - `case_qpi_international_logistics_no_call_001`
@@ -236,6 +236,13 @@ Round 03.2a 重点新增：
 - `case_qpi_depth_limited_problem_definition_001`
 - `case_qpi_depth_limited_dominant_scarcity_001`
 
+Round 04.1 重点新增：
+
+- `case_qpi_round04_translation_payload_no_call_001`
+- `case_qpi_round04_depth_limited_specific_scarcity_001`
+- `case_qpi_round04_depth_limited_scarcity_set_001`
+- `case_qpi_round04_depth_limited_assumption_scarcity_001`
+
 ## 示例输入
 
 - “我们团队每次都说要长期主义，但一到季度 KPI 就回到短期动作，这到底是什么问题？”

ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.1.md

@@ -0,0 +1,53 @@
+# Round 04.1 CCRA Review Brief
+
+Date: 2026-06-18
+
+Repository: `C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong`
+
+Round: `04.1`
+
+Topic: Selector no-call, hard exclusion, and depth-limiting patch
+
+## 1. Review Goal
+
+Round 04.1 fixes the owner / GPT reviewed failures from the Round 04 blind routing run.
+
+This is a selector rule patch and post-patch verification round. It is not a second blind test.
+
+## 2. Target Failures
+
+- `R04-BI-002`: translation task selected QPI because the payload contained `模型`.
+- `R04-BI-024`: explicit `不要进入思想考古` did not hard-exclude Intellectual Archaeology.
+- `R04-BI-035`: `不要深入分析` plus dominant-scarcity judgment was hard no-called.
+- `R04-BI-036`: `不要展开` plus scarcity-set judgment was hard no-called.
+
+## 3. What Changed
+
+- Added targeted regression cases for the four reviewed failures.
+- Added translation / instruction-task no-call coverage.
+- Added minimal instruction / payload separation for no-call routing.
+- Added IA hard-exclusion variants such as `不要进入思想考古`.
+- Expanded depth-limiting QPI override phrases.
+- Generated post-patch routing verification against the frozen 38-input Round 04 pool.
+- Closeout records `R04-BI-022` as an accepted collateral change and adds it to QPI regression.
+
+## 4. What Did Not Change
+
+- The original Round 04 blind routing report was not rewritten.
+- No LLM selector was introduced.
+- No third model was added.
+- QPI and Intellectual Archaeology were not upgraded.
+- No RAG, vector database, frontend, backend, user account, or QA product was introduced.
+
+## 5. Closeout Note
+
+GPT review accepted Round 04.1 and did not request a 04.2 rule patch. The only closeout addition is documentation / regression hardening for `R04-BI-022`: it moved from no-call to lightweight QPI after the depth-limiting override patch, IA remains rejected, and this is treated as semantically correct collateral behavior.
+
+## 6. Read Order
+
+1. `01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md`
+2. `02_EXPECTED_ROUTING_LABELS_04.1.md`
+3. `03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md`
+4. `04_REGRESSION_AND_COMMAND_LOG_04.1.md`
+
+Use `optional_raw_changed_files_04.1.zip` only when exact file inspection is needed.

ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md

@@ -0,0 +1,75 @@
+# Round 04.1 Rule Patch Summary and Diff Guide
+
+## 1. Patch Scope
+
+Round 04.1 patches selector rules only. It does not change model lifecycle status.
+
+## 2. Rule Changes
+
+### Translation / Direct Transformation No-Call
+
+Added `instruction_task_no_call_signals` to `selector/selector_rules.json`:
+
+```text
+翻译成
+翻译为
+把这句话翻译
+翻译下面
+译成英文
+译成中文
+```
+
+These are checked against the task instruction segment so payload words such as `模型` do not trigger QPI when the user is asking for translation.
+
+### Instruction / Payload Separation
+
+Added `instruction_segment()` in `scripts/run_selector_demo.py`.
+
+For no-call routing, the selector can inspect the segment before `：`, `:`, or newline as the task instruction. This is intentionally minimal and does not introduce semantic parsing or LLM routing.
+
+### IA Hard Exclusion Variants
+
+Added model-level hard exclusion variants:
+
+```text
+不要进入思想考古
+不进入思想考古
+先不进入思想考古
+不要做思想考古
+不做思想考古
+```
+
+This fixes cases where the user explicitly refuses IA but uses phrasing not covered by Round 03.2.
+
+### Depth-Limiting QPI Override
+
+Expanded QPI-limited override and IA exclusion phrases for:
+
+```text
+主导稀缺
+只判断这件事的主导稀缺
+只判断现在是缺信息
+缺信息、缺路径还是缺共识
+```
+
+This keeps `不要展开` / `不要深入分析` as no-call by default, but allows QPI when the user asks for a narrow scarcity judgment.
+
+## 3. Regression Changes
+
+Added:
+
+- `case_qpi_round04_translation_payload_no_call_001`
+- `case_qpi_round04_depth_limited_specific_scarcity_001`
+- `case_qpi_round04_depth_limited_scarcity_set_001`
+- `case_ia_round04_do_not_enter_archaeology_001`
+- Closeout addition: `case_qpi_round04_depth_limited_assumption_scarcity_001` from `R04-BI-022`
+
+Counts after patch:
+
+- QPI regression cases: 62
+- Intellectual Archaeology regression cases: 20
+- Aggregate regression cases: 82
+
+## 4. Review Notes
+
+The rule patch is intentionally conservative. It does not expand QPI into all governance, capacity, or organization-like inputs from Round 04. Those remain calibration discussion items unless owner / CCRA approves a later patch.

ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md

@@ -0,0 +1,20 @@
+# Round 04.1 Expected Routing Labels
+
+These labels are added after owner / GPT review of the Round 04 blind output.
+
+They apply only to the four targeted patch cases and do not convert the entire Round 04 blind pool into regression.
+
+## Target Labels
+
+| Case ID | Expected Routing | Failure Type Addressed |
+| --- | --- | --- |
+| `R04-BI-002` | `selected_models=[]`, `no_call=true` | translation no-call false negative; QPI over-selection |
+| `R04-BI-024` | `selected_models` may include `qpi`; must reject `intellectual_archaeology`; `no_call=false` | IA hard exclusion failure |
+| `R04-BI-035` | selected `qpi`; reject `intellectual_archaeology`; `no_call=false` | depth-limiting override failure |
+| `R04-BI-036` | selected `qpi`; reject `intellectual_archaeology`; `no_call=false` | depth-limiting override failure |
+
+## Non-Target Notes
+
+Round 04 governance, responsibility, capacity, and ambiguous-context cases are not patched in 04.1.
+
+They may indicate future QPI under-selection or calibration questions, but broadening QPI recall in this patch would risk turning QPI into a generic organization-problem detector.

ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md

@@ -0,0 +1,175 @@
+# Round 04.1 Post-Patch Routing Verification Report
+
+Date: 2026-06-18
+
+This is not a second blind test.
+
+Frozen input set: `round04_blind_inputs_2026-06-18_v0.1`
+Original before-report: `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
+
+## Scope
+
+- Round 04.1 verifies selector rule patches after owner / GPT review.
+- It reruns the frozen 38-input Round 04 pool for comparison.
+- Expected routing labels are limited to the four review-approved target cases.
+- It does not generate final answers and does not upgrade model status.
+
+## Summary
+
+Frozen inputs rerun: 38
+Post-patch no-call results: 18
+Targeted cases checked: 4
+Targeted failures: 0
+Behavior changes recorded: 5
+
+## Targeted Case Results
+
+### R04-BI-002
+
+- status: `PASS`
+- review_label: translation no-call; payload complexity must not trigger QPI
+- before_selected_models: `['qpi']`
+- before_no_call: `False`
+- after_selected_models: `[]`
+- after_rejected_models: `['intellectual_archaeology', 'qpi']`
+- after_no_call: `True`
+
+After selected model details:
+- none
+
+### R04-BI-024
+
+- status: `PASS`
+- review_label: explicit IA refusal should hard-exclude IA while allowing QPI
+- before_selected_models: `['intellectual_archaeology', 'qpi']`
+- before_no_call: `False`
+- after_selected_models: `['qpi']`
+- after_rejected_models: `['intellectual_archaeology']`
+- after_no_call: `False`
+
+After selected model details:
+- `qpi` score=0.74 decision=selected
+  - reasons: trigger keyword matched: 问题; complexity signal: 边界、责任; selection_priority=9
+
+### R04-BI-035
+
+- status: `PASS`
+- review_label: depth-limiting plus dominant-scarcity judgment should allow QPI
+- before_selected_models: `[]`
+- before_no_call: `True`
+- after_selected_models: `['qpi']`
+- after_rejected_models: `['intellectual_archaeology']`
+- after_no_call: `False`
+
+After selected model details:
+- `qpi` score=0.59 decision=selected
+  - reasons: selection_priority=9; QPI problem-definition gate matched
+
+### R04-BI-036
+
+- status: `PASS`
+- review_label: depth-limiting plus scarcity-set judgment should allow QPI
+- before_selected_models: `[]`
+- before_no_call: `True`
+- after_selected_models: `['qpi']`
+- after_rejected_models: `['intellectual_archaeology']`
+- after_no_call: `False`
+
+After selected model details:
+- `qpi` score=0.99 decision=selected
+  - reasons: trigger keyword matched: 缺路径、缺共识; complexity signal: 共识、底层; selection_priority=9; QPI problem-definition gate matched
+
+## Non-target Behavior Diff / Accepted Collateral Change
+
+The frozen 38-input pool was rerun for comparison. Expected routing labels remain limited to the four target cases above, but the full rerun records five behavior changes from the original Round 04 report.
+
+### R04-BI-002
+
+- label: target fix: translation no-call
+- before_selected_models: `['qpi']`
+- before_no_call: `False`
+- after_selected_models: `[]`
+- after_rejected_models: `['intellectual_archaeology', 'qpi']`
+- after_no_call: `True`
+- closeout_judgment: Expected target change; translation instruction should not be routed to QPI because the payload contains `模型`.
+
+### R04-BI-022
+
+- label: accepted collateral change: depth-limited QPI override
+- before_selected_models: `[]`
+- before_no_call: `True`
+- after_selected_models: `['qpi']`
+- after_rejected_models: `['intellectual_archaeology']`
+- after_no_call: `False`
+- closeout_judgment: Not a new failure. The request rejects deeper IA-style expansion while asking for dominant scarcity judgment, so lightweight QPI is acceptable and IA should remain rejected. Added to regression as a QPI selector-gate trap.
+
+### R04-BI-024
+
+- label: target fix: explicit IA refusal
+- before_selected_models: `['intellectual_archaeology', 'qpi']`
+- before_no_call: `False`
+- after_selected_models: `['qpi']`
+- after_rejected_models: `['intellectual_archaeology']`
+- after_no_call: `False`
+- closeout_judgment: Expected target change; explicit refusal should hard-exclude IA while allowing lightweight QPI.
+
+### R04-BI-035
+
+- label: target fix: dominant-scarcity depth limit
+- before_selected_models: `[]`
+- before_no_call: `True`
+- after_selected_models: `['qpi']`
+- after_rejected_models: `['intellectual_archaeology']`
+- after_no_call: `False`
+- closeout_judgment: Expected target change; depth-limiting language should not block lightweight QPI scarcity judgment.
+
+### R04-BI-036
+
+- label: target fix: scarcity-set depth limit
+- before_selected_models: `[]`
+- before_no_call: `True`
+- after_selected_models: `['qpi']`
+- after_rejected_models: `['intellectual_archaeology']`
+- after_no_call: `False`
+- closeout_judgment: Expected target change; depth-limiting language should not block QPI scarcity-set judgment.
+
+## Full Pool Rerun Summary
+
+- `R04-BI-001`: selected=[]; no_call=True; category=explicit_no_call_fact_lookup
+- `R04-BI-002`: selected=[]; no_call=True; category=explicit_no_call_translation
+- `R04-BI-003`: selected=[]; no_call=True; category=explicit_no_call_rewrite
+- `R04-BI-004`: selected=[]; no_call=True; category=explicit_no_call_formatting
+- `R04-BI-005`: selected=[]; no_call=True; category=explicit_no_call_direct_execution
+- `R04-BI-006`: selected=['qpi']; no_call=False; category=qpi_light_problem_definition
+- `R04-BI-007`: selected=['qpi']; no_call=False; category=qpi_light_problem_definition
+- `R04-BI-008`: selected=['qpi']; no_call=False; category=qpi_light_problem_definition
+- `R04-BI-009`: selected=['qpi']; no_call=False; category=qpi_light_problem_definition
+- `R04-BI-010`: selected=[]; no_call=True; category=governance_responsibility_consensus
+- `R04-BI-011`: selected=[]; no_call=True; category=governance_responsibility_consensus
+- `R04-BI-012`: selected=[]; no_call=True; category=governance_responsibility_consensus
+- `R04-BI-013`: selected=[]; no_call=True; category=governance_responsibility_consensus
+- `R04-BI-014`: selected=[]; no_call=True; category=capacity_resource_path
+- `R04-BI-015`: selected=[]; no_call=True; category=capacity_resource_path
+- `R04-BI-016`: selected=['qpi']; no_call=False; category=capacity_resource_path
+- `R04-BI-017`: selected=[]; no_call=True; category=capacity_resource_path
+- `R04-BI-018`: selected=['qpi']; no_call=False; category=model_extraction_or_depth_modeling
+- `R04-BI-019`: selected=['qpi', 'intellectual_archaeology']; no_call=False; category=model_extraction_or_depth_modeling
+- `R04-BI-020`: selected=['qpi']; no_call=False; category=model_extraction_or_depth_modeling
+- `R04-BI-021`: selected=['qpi']; no_call=False; category=qpi_allowed_ia_refused
+- `R04-BI-022`: selected=['qpi']; no_call=False; category=qpi_allowed_ia_refused
+- `R04-BI-023`: selected=['qpi']; no_call=False; category=qpi_allowed_ia_refused
+- `R04-BI-024`: selected=['qpi']; no_call=False; category=qpi_allowed_ia_refused
+- `R04-BI-025`: selected=['intellectual_archaeology', 'qpi']; no_call=False; category=likely_intellectual_archaeology
+- `R04-BI-026`: selected=['qpi']; no_call=False; category=likely_intellectual_archaeology
+- `R04-BI-027`: selected=['qpi']; no_call=False; category=likely_intellectual_archaeology
+- `R04-BI-028`: selected=[]; no_call=True; category=ambiguous_low_context
+- `R04-BI-029`: selected=[]; no_call=True; category=ambiguous_low_context
+- `R04-BI-030`: selected=['qpi']; no_call=False; category=ambiguous_low_context
+- `R04-BI-031`: selected=[]; no_call=True; category=explicit_no_call_how_to
+- `R04-BI-032`: selected=[]; no_call=True; category=explicit_no_call_how_to
+- `R04-BI-033`: selected=[]; no_call=True; category=explicit_no_call_dictionary_judgment
+- `R04-BI-034`: selected=['qpi']; no_call=False; category=direct_execution_with_analysis_override
+- `R04-BI-035`: selected=['qpi']; no_call=False; category=qpi_allowed_depth_limited
+- `R04-BI-036`: selected=['qpi']; no_call=False; category=qpi_allowed_depth_limited
+- `R04-BI-037`: selected=[]; no_call=True; category=ambiguous_growth_how_to
+- `R04-BI-038`: selected=['qpi']; no_call=False; category=likely_intellectual_archaeology

ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md

@@ -0,0 +1,98 @@
+# Round 04.1 Regression and Command Log
+
+Date: 2026-06-18
+
+## 1. Red Evidence
+
+After adding the four Round 04.1 regression cases and before patching selector rules:
+
+```powershell
+python scripts\run_selector_regression.py
+```
+
+Failed as expected:
+
+- `case_ia_round04_do_not_enter_archaeology_001`: expected primary QPI, got IA; IA selected despite explicit refusal.
+- `case_qpi_round04_translation_payload_no_call_001`: expected no selected model, got QPI.
+- `case_qpi_round04_depth_limited_specific_scarcity_001`: expected QPI, got none.
+- `case_qpi_round04_depth_limited_scarcity_set_001`: expected QPI, got none.
+
+## 2. Targeted Green Evidence
+
+After the patch:
+
+```powershell
+python scripts\run_selector_regression.py
+python -m unittest tests.test_round04_post_patch_verification -v
+python scripts\run_round04_post_patch_verification.py
+```
+
+Observed:
+
+- Selector regression passed.
+- Round 04.1 post-patch verification test passed, 2 tests.
+- Post-patch report generated with 4 targeted cases checked and 0 targeted failures.
+- Closeout report records 5 behavior changes, including accepted collateral change `R04-BI-022`.
+- `R04-BI-022` was added to QPI regression as `case_qpi_round04_depth_limited_assumption_scarcity_001`.
+
+## 3. Full Verification
+
+The following commands passed after the Round 04.1 patch:
+
+```powershell
+python scripts\rebuild_indexes.py --check
+python -m unittest discover -s tests -p "test*.py" -v
+python scripts\validate_model_library.py
+python scripts\check_card_contract.py
+python scripts\run_selector_demo.py
+python scripts\run_selector_regression.py
+python scripts\run_selector_calibration_smoke.py
+python scripts\check_model_card_sync.py
+```
+
+Results:
+
+- Index check: PASS
+- Unit tests: PASS, 22 tests
+- Model library validation: PASS
+- Card contract: PASS
+- Selector demo: PASS
+- Selector regression: PASS, 26 cases
+- Selector calibration smoke: PASS
+- Model/card sync: PASS
+
+## 4. Lifecycle Status
+
+QPI and Intellectual Archaeology remain:
+
+```text
+draft / B / pending
+```
+
+## 5. Bundle Zip Verification
+
+The raw changed-files zip was generated with the installed `bundle-zip` Skill:
+
+```powershell
+python C:\Users\wangq\.agents\skills\bundle-zip\scripts\bundle_zip.py --file-list ccra_review_bundle\round-04.1_2026-06-18_selector-rule-patch\raw_file_list_04.1.txt --relative-root-marker the-mindscape-of-bro-tsong --output C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\ccra_review_bundle\round-04.1_2026-06-18_selector-rule-patch\optional_raw_changed_files_04.1.zip --verify --json-output ccra_review_bundle\round-04.1_2026-06-18_selector-rule-patch\optional_raw_changed_files_04.1.zip.validation.json
+```
+
+Result:
+
+- Status: PASS
+- Source files: 37
+- Zip entries: 37
+- Path mode: source-relative entries under `the-mindscape-of-bro-tsong`
+- Validation sidecar: `optional_raw_changed_files_04.1.zip.validation.json`
+
+## 6. Closeout Note
+
+Round 04.1 is closed after GPT review acceptance and this closeout note.
+
+No additional selector rule patch was made during closeout. The only closeout behavior change is documentation / regression hardening for `R04-BI-022`:
+
+- It is not treated as a new failure.
+- It is accepted as a depth-limiting QPI override collateral change.
+- IA should continue to be rejected.
+- Lightweight QPI routing is acceptable.
+- The case is now covered by selector regression.

ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/BUNDLE_FILE_MANIFEST_04.1.md

@@ -0,0 +1,59 @@
+# Round 04.1 Bundle File Manifest
+
+## Review Files
+
+- `00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.1.md`
+- `01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md`
+- `02_EXPECTED_ROUTING_LABELS_04.1.md`
+- `03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md`
+- `04_REGRESSION_AND_COMMAND_LOG_04.1.md`
+- `BUNDLE_FILE_MANIFEST_04.1.md`
+- `raw_file_list_04.1.txt`
+- `optional_raw_changed_files_04.1.zip`
+- `optional_raw_changed_files_04.1.zip.validation.json`
+
+## Optional Raw Changed Files
+
+The zip is optional and should be used only if exact file inspection is needed.
+
+It is generated with the installed `bundle-zip` Skill and preserves source-relative paths.
+
+## Source-Relative Files Included in Raw Zip
+
+- `README.md`
+- `docs/DECISIONS.md`
+- `docs/WORKFLOW.md`
+- `docs/superpowers/plans/2026-06-18-round04-1-selector-rule-patch.md`
+- `selector/README.md`
+- `selector/selector_rules.json`
+- `selector/selector_calibration_inputs.json`
+- `selector/round04_blind_inputs.json`
+- `scripts/README.md`
+- `scripts/run_selector_demo.py`
+- `scripts/run_selector_regression.py`
+- `scripts/run_selector_calibration_smoke.py`
+- `scripts/run_round04_blind_routing.py`
+- `scripts/run_round04_post_patch_verification.py`
+- `tests/qpi.regression.json`
+- `tests/intellectual_archaeology.regression.json`
+- `tests/regression_cases.json`
+- `tests/regression_index.json`
+- `tests/test_round04_blind_routing.py`
+- `tests/test_round04_post_patch_verification.py`
+- `models/model_index.json`
+- `models/qpi.model.json`
+- `models/intellectual_archaeology.model.json`
+- `cards/card_index.md`
+- `cards/qpi.md`
+- `cards/intellectual_archaeology.md`
+- `reports/README.md`
+- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
+- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md`
+- `reports/Codex新会话交接文档_Round04.1关闭与Round05准备_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`
+- `requirements/skills-vault/2026-06-18-review-bundle-zip-packager.md`

ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json

@@ -0,0 +1,47 @@
+{
+  "status": "PASS",
+  "output_zip": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\ccra_review_bundle\\round-04.1_2026-06-18_selector-rule-patch\\optional_raw_changed_files_04.1.zip",
+  "source_file_count": 37,
+  "zip_entry_count": 37,
+  "entries": [
+    "README.md",
+    "docs/DECISIONS.md",
+    "docs/WORKFLOW.md",
+    "docs/superpowers/plans/2026-06-18-round04-1-selector-rule-patch.md",
+    "selector/README.md",
+    "selector/selector_rules.json",
+    "selector/selector_calibration_inputs.json",
+    "selector/round04_blind_inputs.json",
+    "scripts/README.md",
+    "scripts/run_selector_demo.py",
+    "scripts/run_selector_regression.py",
+    "scripts/run_selector_calibration_smoke.py",
+    "scripts/run_round04_blind_routing.py",
+    "scripts/run_round04_post_patch_verification.py",
+    "tests/qpi.regression.json",
+    "tests/intellectual_archaeology.regression.json",
+    "tests/regression_cases.json",
+    "tests/regression_index.json",
+    "tests/test_round04_blind_routing.py",
+    "tests/test_round04_post_patch_verification.py",
+    "models/model_index.json",
+    "models/qpi.model.json",
+    "models/intellectual_archaeology.model.json",
+    "cards/card_index.md",
+    "cards/qpi.md",
+    "cards/intellectual_archaeology.md",
+    "reports/README.md",
+    "reports/Round04_blind_routing_evaluation_report_2026-06-18.md",
+    "reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md",
+    "reports/Codex新会话交接文档_Round04.1关闭与Round05准备_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",
+    "requirements/skills-vault/2026-06-18-review-bundle-zip-packager.md"
+  ],
+  "warnings": [],
+  "errors": []
+}

ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/raw_file_list_04.1.txt

@@ -0,0 +1,37 @@
+README.md
+docs/DECISIONS.md
+docs/WORKFLOW.md
+docs/superpowers/plans/2026-06-18-round04-1-selector-rule-patch.md
+selector/README.md
+selector/selector_rules.json
+selector/selector_calibration_inputs.json
+selector/round04_blind_inputs.json
+scripts/README.md
+scripts/run_selector_demo.py
+scripts/run_selector_regression.py
+scripts/run_selector_calibration_smoke.py
+scripts/run_round04_blind_routing.py
+scripts/run_round04_post_patch_verification.py
+tests/qpi.regression.json
+tests/intellectual_archaeology.regression.json
+tests/regression_cases.json
+tests/regression_index.json
+tests/test_round04_blind_routing.py
+tests/test_round04_post_patch_verification.py
+models/model_index.json
+models/qpi.model.json
+models/intellectual_archaeology.model.json
+cards/card_index.md
+cards/qpi.md
+cards/intellectual_archaeology.md
+reports/README.md
+reports/Round04_blind_routing_evaluation_report_2026-06-18.md
+reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md
+reports/Codex新会话交接文档_Round04.1关闭与Round05准备_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
+requirements/skills-vault/2026-06-18-review-bundle-zip-packager.md

ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md

@@ -0,0 +1,40 @@
+# Round 04 CCRA Review Brief
+
+Date: 2026-06-18
+
+Repository: `C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong`
+
+Round: `04`
+
+Topic: Blind input routing evaluation
+
+## 1. Review Goal
+
+Round 04 tests whether the current rule-based selector, QPI routing contract, and Intellectual Archaeology gate behave stably on new inputs.
+
+This is a routing evaluation only. It does not evaluate final answer quality.
+
+## 2. What Changed
+
+- Updated `reports/Round04_blind_input_candidates_2026-06-18.md` from owner review notes.
+- Added frozen blind input pool: `selector/round04_blind_inputs.json`.
+- Added standard-library runner: `scripts/run_round04_blind_routing.py`.
+- Added tests for the runner: `tests/test_round04_blind_routing.py`.
+- Ran the first blind routing pass and wrote `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`.
+
+## 3. What Did Not Change
+
+- `selector/selector_rules.json` was not modified.
+- QPI and Intellectual Archaeology model JSON lifecycle status was not upgraded.
+- No third model was added.
+- No LLM selector, RAG, vector database, frontend, backend, account system, or QA product was introduced.
+- No expected routing labels were added before the first blind run.
+
+## 4. Files To Read
+
+1. `01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md`
+2. `02_BLIND_INPUT_SET_04.md`
+3. `03_ROUTING_EVALUATION_REPORT_04.md`
+4. `04_REVIEW_QUESTIONS_FOR_GPT_04.md`
+
+The optional raw zip contains source-relative files for exact inspection.

ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md

@@ -0,0 +1,81 @@
+# Round 03 Closure and Round 04 Scope
+
+## 1. Round 03 Closure Summary
+
+```text
+Round 03 closed after 03.2a.
+
+QPI and Intellectual Archaeology remain draft / B / pending.
+QPI is accepted as a draft-callable routing asset at report level.
+Selector v0.2 passes:
+- no-call gate
+- calibration smoke
+- model-level IA exclusion
+- QPI-before-IA gate
+- depth-limiting override gate
+
+Proceed to Round 04 blind input routing evaluation.
+```
+
+`draft-callable` is review language only. It does not change JSON lifecycle status. Validation pass, schema compliance, selector demo pass, or report-level acceptance cannot upgrade either model to stable.
+
+## 2. Round 04 Target
+
+Round 04 verifies:
+
+```text
+真实新输入下，selector + QPI + IA gate 的路由是否稳定。
+```
+
+This means:
+
+- selected model IDs
+- rejected model IDs
+- no-call behavior
+- model-level hard exclusions
+- QPI-before-IA gate behavior
+- depth-limiting override behavior
+
+It does not mean final answer quality.
+
+## 3. Round 04 Non-Goals
+
+```text
+Do not add a third model.
+Do not upgrade QPI or Intellectual Archaeology.
+Do not introduce LLM selector.
+Do not implement RAG, vector database, frontend, backend, user account, or QA product.
+Do not modify selector rules before blind test.
+Run first, analyze failures later.
+```
+
+## 4. Current Runtime Asset Set
+
+The optional raw zip includes:
+
+```text
+selector/selector_rules.json
+selector/selector_calibration_inputs.json
+selector/round04_blind_inputs.json
+models/qpi.model.json
+models/intellectual_archaeology.model.json
+models/model_index.json
+cards/qpi.md
+cards/intellectual_archaeology.md
+cards/card_index.md
+tests/qpi.regression.json
+tests/intellectual_archaeology.regression.json
+tests/regression_cases.json
+tests/test_round04_blind_routing.py
+scripts/run_selector_demo.py
+scripts/run_selector_regression.py
+scripts/run_selector_calibration_smoke.py
+scripts/run_round04_blind_routing.py
+reports/Round04_blind_input_candidates_2026-06-18.md
+reports/Round04_blind_routing_evaluation_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
+```

ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md

@@ -0,0 +1,48 @@
+# Round 04 Blind Input Set
+
+Source: `selector/round04_blind_inputs.json`
+
+Human-readable source: `reports/Round04_blind_input_candidates_2026-06-18.md`
+
+Status: `frozen_for_first_blind_run_after_owner_review`
+
+## 1. Blindness Rules
+
+- No expected routing labels are included.
+- Category labels are coverage labels, not answer keys.
+- The input pool must not be merged into `selector/selector_calibration_inputs.json` before review.
+- Selector rules must not be modified before the first blind run.
+
+## 2. Count
+
+Total inputs: 38
+
+Control notes:
+
+- `R04-BI-018`: positive control for obvious model-extraction / depth-modeling intent.
+- `R04-BI-021`: model-name-exposed control case.
+- `R04-BI-025`: model-name-exposed control case.
+- `R04-BI-026`: high-value natural boundary sample, because it avoids explicit model names while suggesting IA or QPI-to-IA routing.
+
+## 3. Category Coverage
+
+- explicit no-call fact / translation / rewrite / formatting / direct execution
+- ordinary how-to no-call traps
+- dictionary / word-meaning judgment no-call trap
+- QPI lightweight problem definition
+- governance / responsibility / consensus
+- capacity / resource / path
+- model extraction / depth modeling
+- IA refused but QPI allowed
+- depth-limiting but QPI allowed
+- likely Intellectual Archaeology
+- ambiguous / low context
+- ambiguous growth how-to boundary
+
+## 4. Full Input IDs
+
+```text
+R04-BI-001 through R04-BI-038
+```
+
+Use `selector/round04_blind_inputs.json` for exact input text and metadata.

ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md

@@ -0,0 +1,771 @@
+# Round 04 Blind Routing Evaluation Report
+
+Date: 2026-06-18
+
+Blind input set: `round04_blind_inputs_2026-06-18_v0.1`
+
+Expected routing labels: `not included before first blind run`
+
+This report records current selector routing only. It does not score correctness, does not generate final answers, does not modify selector rules, and does not upgrade model status.
+
+## Scope
+
+- Round 04 target: test routing stability on new inputs.
+- Runtime surface: current rule-based selector plus model-level QPI / IA gates.
+- QPI contract status: represented here by QPI selection and routing details; no full QPI answer generation is performed.
+- IA status: represented here by selector selection / rejection only; no Intellectual Archaeology answer generation is performed.
+
+## Summary
+
+Inputs evaluated: 38
+No-call results: 20
+
+### Selected Model Distribution
+
+- `intellectual_archaeology`: 3
+- `none`: 20
+- `qpi`: 18
+
+### Coverage Categories
+
+- `ambiguous_growth_how_to`: 1
+- `ambiguous_low_context`: 3
+- `capacity_resource_path`: 4
+- `direct_execution_with_analysis_override`: 1
+- `explicit_no_call_dictionary_judgment`: 1
+- `explicit_no_call_direct_execution`: 1
+- `explicit_no_call_fact_lookup`: 1
+- `explicit_no_call_formatting`: 1
+- `explicit_no_call_how_to`: 2
+- `explicit_no_call_rewrite`: 1
+- `explicit_no_call_translation`: 1
+- `governance_responsibility_consensus`: 4
+- `likely_intellectual_archaeology`: 4
+- `model_extraction_or_depth_modeling`: 3
+- `qpi_allowed_depth_limited`: 2
+- `qpi_allowed_ia_refused`: 4
+- `qpi_light_problem_definition`: 4
+
+## Case Results
+
+### R04-BI-001
+
+- category_for_owner_review: `explicit_no_call_fact_lookup`
+- input_text: `查一下《原则》这本书的作者是谁，只要事实，不要分析。`
+- selected_models: `[]`
+- rejected_models: `['intellectual_archaeology', 'qpi']`
+- no_call: `True`
+- routing_notes: hard no-call gate matched; explicit analysis override was not present.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.0 decision=rejected
+    - penalties: hard no-call signal: 只要事实、查一下
+  - `qpi` score=0.0 decision=rejected
+    - penalties: hard no-call signal: 只要事实、查一下
+
+### R04-BI-002
+
+- category_for_owner_review: `explicit_no_call_translation`
+- input_text: `把这句话翻译成英文：这个模型还处在草稿阶段。`
+- selected_models: `['qpi']`
+- rejected_models: `['intellectual_archaeology']`
+- no_call: `False`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - `qpi` score=0.49 decision=selected
+    - reasons: complexity signal: 模型; selection_priority=9
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.17 decision=rejected
+    - reasons: complexity signal: 模型; selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-003
+
+- category_for_owner_review: `explicit_no_call_rewrite`
+- input_text: `请把这段话润色得更顺一点，不要改变意思，也不要解释原因。`
+- selected_models: `[]`
+- rejected_models: `['intellectual_archaeology', 'qpi']`
+- no_call: `True`
+- routing_notes: hard no-call gate matched; explicit analysis override was not present.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.0 decision=rejected
+    - penalties: hard no-call signal: 润色
+  - `qpi` score=0.0 decision=rejected
+    - penalties: hard no-call signal: 润色
+
+### R04-BI-004
+
+- category_for_owner_review: `explicit_no_call_formatting`
+- input_text: `把下面这组要点整理成 Markdown 表格，直接给结果。`
+- selected_models: `[]`
+- rejected_models: `['qpi', 'intellectual_archaeology']`
+- no_call: `True`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `qpi` score=0.09 decision=rejected
+    - reasons: selection_priority=9
+    - penalties: QPI positive signal missing
+  - `intellectual_archaeology` score=0.02 decision=rejected
+    - reasons: selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-005
+
+- category_for_owner_review: `explicit_no_call_direct_execution`
+- input_text: `把这个 JSON 压缩成单行，不用说明：{"status":"draft","level":"B"}`
+- selected_models: `[]`
+- rejected_models: `['qpi', 'intellectual_archaeology']`
+- no_call: `True`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `qpi` score=0.09 decision=rejected
+    - reasons: selection_priority=9
+    - penalties: QPI positive signal missing
+  - `intellectual_archaeology` score=0.02 decision=rejected
+    - reasons: selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-006
+
+- category_for_owner_review: `qpi_light_problem_definition`
+- input_text: `我们现在反复开会但没有推进，我想先判断这是缺信息、缺路径，还是缺共识。`
+- selected_models: `['qpi']`
+- rejected_models: `['intellectual_archaeology']`
+- no_call: `False`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - `qpi` score=0.99 decision=selected
+    - reasons: trigger keyword matched: 缺路径、缺共识; complexity signal: 反复、共识; selection_priority=9; QPI problem-definition gate matched
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.0 decision=rejected
+    - reasons: complexity signal: 反复、共识; selection_priority=7
+    - penalties: QPI-before-IA gate: 缺路径、缺共识; no IA heavy-depth gate
+
+### R04-BI-007
+
+- category_for_owner_review: `qpi_light_problem_definition`
+- input_text: `这个项目卡住了，我不确定到底是问题没定义清楚，还是执行方案不够。`
+- selected_models: `['qpi']`
+- rejected_models: `['intellectual_archaeology']`
+- no_call: `False`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - `qpi` score=0.59 decision=selected
+    - reasons: trigger keyword matched: 问题; selection_priority=9
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.02 decision=rejected
+    - reasons: selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-008
+
+- category_for_owner_review: `qpi_light_problem_definition`
+- input_text: `我们有一堆材料，但不知道下一步该问什么问题，先帮我定性一下。`
+- selected_models: `['qpi']`
+- rejected_models: `['intellectual_archaeology']`
+- no_call: `False`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - `qpi` score=0.59 decision=selected
+    - reasons: trigger keyword matched: 问题; selection_priority=9
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.02 decision=rejected
+    - reasons: selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-009
+
+- category_for_owner_review: `qpi_light_problem_definition`
+- input_text: `这件事到底算一个简单问题、复杂问题，还是已经变成组织议题？`
+- selected_models: `['qpi']`
+- rejected_models: `['intellectual_archaeology']`
+- no_call: `False`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - `qpi` score=0.89 decision=selected
+    - reasons: trigger keyword matched: 问题; input type matched: 复杂问题; complexity signal: 组织、复杂; selection_priority=9
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.32 decision=rejected
+    - reasons: input type matched: 复杂问题; complexity signal: 组织、复杂; selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-010
+
+- category_for_owner_review: `governance_responsibility_consensus`
+- input_text: `每个部门都说支持这个项目，但一到分工就没人愿意承担主责。`
+- selected_models: `[]`
+- rejected_models: `['qpi', 'intellectual_archaeology']`
+- no_call: `True`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `qpi` score=0.09 decision=rejected
+    - reasons: selection_priority=9
+    - penalties: QPI positive signal missing
+  - `intellectual_archaeology` score=0.02 decision=rejected
+    - reasons: selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-011
+
+- category_for_owner_review: `governance_responsibility_consensus`
+- input_text: `老板要创新，财务要控成本，业务要短期业绩，最后方案总是被折中到没有方向。`
+- selected_models: `[]`
+- rejected_models: `['qpi', 'intellectual_archaeology']`
+- no_call: `True`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `qpi` score=0.09 decision=rejected
+    - reasons: selection_priority=9
+    - penalties: QPI positive signal missing
+  - `intellectual_archaeology` score=0.02 decision=rejected
+    - reasons: selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-012
+
+- category_for_owner_review: `governance_responsibility_consensus`
+- input_text: `我们不是不知道怎么做，而是每个人都在等别人先表态。`
+- selected_models: `[]`
+- rejected_models: `['qpi', 'intellectual_archaeology']`
+- no_call: `True`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `qpi` score=0.09 decision=rejected
+    - reasons: selection_priority=9
+    - penalties: QPI positive signal missing
+  - `intellectual_archaeology` score=0.02 decision=rejected
+    - reasons: selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-013
+
+- category_for_owner_review: `governance_responsibility_consensus`
+- input_text: `这个流程改造牵涉教务、学院和信息化部门，谁都能提意见，但没人能拍板。`
+- selected_models: `[]`
+- rejected_models: `['qpi', 'intellectual_archaeology']`
+- no_call: `True`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `qpi` score=0.09 decision=rejected
+    - reasons: selection_priority=9
+    - penalties: QPI positive signal missing
+  - `intellectual_archaeology` score=0.02 decision=rejected
+    - reasons: selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-014
+
+- category_for_owner_review: `capacity_resource_path`
+- input_text: `团队现在知道目标，也认可方向，但只有两个人能做关键模块，进度一直被产能卡住。`
+- selected_models: `[]`
+- rejected_models: `['qpi', 'intellectual_archaeology']`
+- no_call: `True`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `qpi` score=0.09 decision=rejected
+    - reasons: selection_priority=9
+    - penalties: QPI positive signal missing
+  - `intellectual_archaeology` score=0.02 decision=rejected
+    - reasons: selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-015
+
+- category_for_owner_review: `capacity_resource_path`
+- input_text: `我们知道要做知识库，也有材料，但不知道从哪条最小路径开始。`
+- selected_models: `[]`
+- rejected_models: `['qpi', 'intellectual_archaeology']`
+- no_call: `True`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `qpi` score=0.09 decision=rejected
+    - reasons: selection_priority=9
+    - penalties: QPI positive signal missing
+  - `intellectual_archaeology` score=0.02 decision=rejected
+    - reasons: selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-016
+
+- category_for_owner_review: `capacity_resource_path`
+- input_text: `预算不是最大问题，问题是现有系统、权限和审批流程都接不上。`
+- selected_models: `['qpi']`
+- rejected_models: `['intellectual_archaeology']`
+- no_call: `False`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - `qpi` score=0.74 decision=selected
+    - reasons: trigger keyword matched: 问题; complexity signal: 系统; selection_priority=9
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.17 decision=rejected
+    - reasons: complexity signal: 系统; selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-017
+
+- category_for_owner_review: `capacity_resource_path`
+- input_text: `这件事大家都觉得重要，但每周只能挤出零散时间，所以一直没有稳定产出。`
+- selected_models: `[]`
+- rejected_models: `['qpi', 'intellectual_archaeology']`
+- no_call: `True`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `qpi` score=0.09 decision=rejected
+    - reasons: selection_priority=9
+    - penalties: QPI positive signal missing
+  - `intellectual_archaeology` score=0.02 decision=rejected
+    - reasons: selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-018
+
+- category_for_owner_review: `model_extraction_or_depth_modeling`
+- control_case_type: `positive_control`
+- input_text: `请从这篇长文里抽取一个可复用的认知模型，重点看它的核心机制和适用边界。`
+- selected_models: `['qpi']`
+- rejected_models: `['intellectual_archaeology']`
+- no_call: `False`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - `qpi` score=0.49 decision=selected
+    - reasons: complexity signal: 模型、机制、抽取、边界; selection_priority=9
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.17 decision=rejected
+    - reasons: complexity signal: 模型、机制、抽取、边界; selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-019
+
+- category_for_owner_review: `model_extraction_or_depth_modeling`
+- input_text: `这套说法背后好像有一个稳定结构，不只是观点总结，帮我判断它能不能沉淀成模型。`
+- selected_models: `['qpi', 'intellectual_archaeology']`
+- rejected_models: `[]`
+- no_call: `False`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - `qpi` score=0.49 decision=selected
+    - reasons: complexity signal: 模型、结构; selection_priority=9
+  - `intellectual_archaeology` score=0.42 decision=selected
+    - reasons: trigger keyword matched: 沉淀成模型; complexity signal: 模型、结构; selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+Rejected model details:
+  - none
+
+### R04-BI-020
+
+- category_for_owner_review: `model_extraction_or_depth_modeling`
+- input_text: `我想把这段讨论拆成原始判断、隐含假设、适用条件和误用边界。`
+- selected_models: `['qpi']`
+- rejected_models: `['intellectual_archaeology']`
+- no_call: `False`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - `qpi` score=0.49 decision=selected
+    - reasons: complexity signal: 边界; selection_priority=9
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.17 decision=rejected
+    - reasons: complexity signal: 边界; selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-021
+
+- category_for_owner_review: `qpi_allowed_ia_refused`
+- control_case_type: `model_name_exposed`
+- input_text: `先不要思想考古，只判断这是不是一个 QPI 意义上的问题。`
+- selected_models: `['qpi']`
+- rejected_models: `['intellectual_archaeology']`
+- no_call: `False`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - `qpi` score=0.59 decision=selected
+    - reasons: trigger keyword matched: 问题; selection_priority=9
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.0 decision=rejected
+    - reasons: trigger keyword matched: 思想考古; selection_priority=7; IA heavy-depth signal: 思想考古
+    - penalties: negative trigger: 不要思想考古、先不要思想考古; model hard exclusion signal: 不要思想考古、先不要思想考古
+
+### R04-BI-022
+
+- category_for_owner_review: `qpi_allowed_ia_refused`
+- input_text: `不要展开到底层假设，只帮我看主导稀缺是什么。`
+- selected_models: `[]`
+- rejected_models: `['intellectual_archaeology', 'qpi']`
+- no_call: `True`
+- routing_notes: hard no-call gate matched; explicit analysis override was not present.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.0 decision=rejected
+    - penalties: hard no-call signal: 不要展开
+  - `qpi` score=0.0 decision=rejected
+    - penalties: hard no-call signal: 不要展开
+
+### R04-BI-023
+
+- category_for_owner_review: `qpi_allowed_ia_refused`
+- input_text: `这次先不做深度建模，只做问题定性，看它是缺数据、缺路径还是缺共识。`
+- selected_models: `['qpi']`
+- rejected_models: `['intellectual_archaeology']`
+- no_call: `False`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - `qpi` score=0.99 decision=selected
+    - reasons: trigger keyword matched: 问题、缺数据、缺路径、缺共识; complexity signal: 共识; selection_priority=9; QPI problem-definition gate matched
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.0 decision=rejected
+    - reasons: complexity signal: 共识; selection_priority=7
+    - penalties: QPI-before-IA gate: 缺数据、缺路径、缺共识; no IA heavy-depth gate; model hard exclusion signal: 只做问题定性
+
+### R04-BI-024
+
+- category_for_owner_review: `qpi_allowed_ia_refused`
+- input_text: `不要进入思想考古，我只要一个轻量判断：现在应该先问问题、找路径，还是处理责任边界？`
+- selected_models: `['intellectual_archaeology', 'qpi']`
+- rejected_models: `[]`
+- no_call: `False`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - `intellectual_archaeology` score=0.97 decision=selected
+    - reasons: trigger keyword matched: 思想考古; complexity signal: 边界、责任; selection_priority=7; IA heavy-depth signal: 思想考古
+  - `qpi` score=0.74 decision=selected
+    - reasons: trigger keyword matched: 问题; complexity signal: 边界、责任; selection_priority=9
+
+Rejected model details:
+  - none
+
+### R04-BI-025
+
+- category_for_owner_review: `likely_intellectual_archaeology`
+- control_case_type: `model_name_exposed`
+- input_text: `QPI 已经判断这是中重型课题，现在请继续分析它背后的底层假设、生成机制和长期稳定结构。`
+- selected_models: `['intellectual_archaeology', 'qpi']`
+- rejected_models: `[]`
+- no_call: `False`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - `intellectual_archaeology` score=0.97 decision=selected
+    - reasons: trigger keyword matched: 底层假设; complexity signal: 长期、底层、结构、机制; selection_priority=7; IA heavy-depth signal: 底层假设
+  - `qpi` score=0.74 decision=selected
+    - reasons: trigger keyword matched: 课题; complexity signal: 长期、底层、结构、机制; selection_priority=9
+
+Rejected model details:
+  - none
+
+### R04-BI-026
+
+- category_for_owner_review: `likely_intellectual_archaeology`
+- input_text: `这个现象反复出现在不同项目里，我想知道它背后的思想结构是什么，而不是只做问题分类。`
+- selected_models: `['qpi']`
+- rejected_models: `['intellectual_archaeology']`
+- no_call: `False`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - `qpi` score=0.74 decision=selected
+    - reasons: trigger keyword matched: 问题; complexity signal: 反复、结构; selection_priority=9
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.17 decision=rejected
+    - reasons: complexity signal: 反复、结构; selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-027
+
+- category_for_owner_review: `likely_intellectual_archaeology`
+- input_text: `请分析这套判断为什么会长期成立，它依赖哪些世界观、因果假设和行动边界。`
+- selected_models: `['qpi']`
+- rejected_models: `['intellectual_archaeology']`
+- no_call: `False`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - `qpi` score=0.49 decision=selected
+    - reasons: complexity signal: 长期、边界; selection_priority=9
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.17 decision=rejected
+    - reasons: complexity signal: 长期、边界; selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-028
+
+- category_for_owner_review: `ambiguous_low_context`
+- input_text: `这个不太对。`
+- selected_models: `[]`
+- rejected_models: `['qpi', 'intellectual_archaeology']`
+- no_call: `True`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `qpi` score=0.09 decision=rejected
+    - reasons: selection_priority=9
+    - penalties: QPI positive signal missing
+  - `intellectual_archaeology` score=0.02 decision=rejected
+    - reasons: selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-029
+
+- category_for_owner_review: `ambiguous_low_context`
+- input_text: `怎么又卡住了？`
+- selected_models: `[]`
+- rejected_models: `['qpi', 'intellectual_archaeology']`
+- no_call: `True`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `qpi` score=0.09 decision=rejected
+    - reasons: selection_priority=9
+    - penalties: QPI positive signal missing
+  - `intellectual_archaeology` score=0.02 decision=rejected
+    - reasons: selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-030
+
+- category_for_owner_review: `ambiguous_low_context`
+- input_text: `还是那个老问题。`
+- selected_models: `['qpi']`
+- rejected_models: `['intellectual_archaeology']`
+- no_call: `False`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - `qpi` score=0.59 decision=selected
+    - reasons: trigger keyword matched: 问题; selection_priority=9
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.02 decision=rejected
+    - reasons: selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-031
+
+- category_for_owner_review: `explicit_no_call_how_to`
+- input_text: `如何在 Excel 里冻结首行？`
+- selected_models: `[]`
+- rejected_models: `['qpi', 'intellectual_archaeology']`
+- no_call: `True`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `qpi` score=0.09 decision=rejected
+    - reasons: selection_priority=9
+    - penalties: QPI positive signal missing
+  - `intellectual_archaeology` score=0.02 decision=rejected
+    - reasons: selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-032
+
+- category_for_owner_review: `explicit_no_call_how_to`
+- input_text: `怎么把 Markdown 文件转成 PDF？`
+- selected_models: `[]`
+- rejected_models: `['qpi', 'intellectual_archaeology']`
+- no_call: `True`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `qpi` score=0.09 decision=rejected
+    - reasons: selection_priority=9
+    - penalties: QPI positive signal missing
+  - `intellectual_archaeology` score=0.02 decision=rejected
+    - reasons: selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-033
+
+- category_for_owner_review: `explicit_no_call_dictionary_judgment`
+- input_text: `判断一下“alignment”在这句话里是什么意思。`
+- selected_models: `[]`
+- rejected_models: `['qpi', 'intellectual_archaeology']`
+- no_call: `True`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `qpi` score=0.09 decision=rejected
+    - reasons: selection_priority=9
+    - penalties: QPI positive signal missing
+  - `intellectual_archaeology` score=0.02 decision=rejected
+    - reasons: selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-034
+
+- category_for_owner_review: `direct_execution_with_analysis_override`
+- input_text: `请把下面内容总结成三点，但不要只执行，先判断它背后的问题定义。`
+- selected_models: `['qpi']`
+- rejected_models: `['intellectual_archaeology']`
+- no_call: `False`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - `qpi` score=0.59 decision=selected
+    - reasons: trigger keyword matched: 问题; selection_priority=9
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.02 decision=rejected
+    - reasons: selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-035
+
+- category_for_owner_review: `qpi_allowed_depth_limited`
+- input_text: `不要深入分析，只判断这件事的主导稀缺是什么。`
+- selected_models: `[]`
+- rejected_models: `['intellectual_archaeology', 'qpi']`
+- no_call: `True`
+- routing_notes: hard no-call gate matched; explicit analysis override was not present.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.0 decision=rejected
+    - penalties: hard no-call signal: 不要深入分析
+  - `qpi` score=0.0 decision=rejected
+    - penalties: hard no-call signal: 不要深入分析
+
+### R04-BI-036
+
+- category_for_owner_review: `qpi_allowed_depth_limited`
+- input_text: `不要展开到底层理论，只判断现在是缺信息、缺路径还是缺共识。`
+- selected_models: `[]`
+- rejected_models: `['intellectual_archaeology', 'qpi']`
+- no_call: `True`
+- routing_notes: hard no-call gate matched; explicit analysis override was not present.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.0 decision=rejected
+    - penalties: hard no-call signal: 不要展开
+  - `qpi` score=0.0 decision=rejected
+    - penalties: hard no-call signal: 不要展开
+
+### R04-BI-037
+
+- category_for_owner_review: `ambiguous_growth_how_to`
+- input_text: `如何提高这个账号的流量？`
+- selected_models: `[]`
+- rejected_models: `['qpi', 'intellectual_archaeology']`
+- no_call: `True`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - none
+
+Rejected model details:
+  - `qpi` score=0.09 decision=rejected
+    - reasons: selection_priority=9
+    - penalties: QPI positive signal missing
+  - `intellectual_archaeology` score=0.02 decision=rejected
+    - reasons: selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+### R04-BI-038
+
+- category_for_owner_review: `likely_intellectual_archaeology`
+- input_text: `这类失败在不同项目里反复出现，我想抽出它背后稳定的生成机制和可迁移框架。`
+- selected_models: `['qpi']`
+- rejected_models: `['intellectual_archaeology']`
+- no_call: `False`
+- routing_notes: selector is rule-based and driven by selector/selector_rules.json; no LLM, no vector search, no answer generation.
+
+Selected model details:
+  - `qpi` score=0.49 decision=selected
+    - reasons: complexity signal: 反复、机制; selection_priority=9
+
+Rejected model details:
+  - `intellectual_archaeology` score=0.17 decision=rejected
+    - reasons: complexity signal: 反复、机制; selection_priority=7
+    - penalties: no IA heavy-depth gate
+
+## Review Reminder
+
+This is the first blind routing output. Failure labels, expected routing, and rule changes should be added only after owner / GPT / CCRA review of these observed results.

ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md

@@ -0,0 +1,41 @@
+# Round 04 Review Questions for GPT / CCRA
+
+## 1. Scope Check
+
+1. Did Round 04 preserve the rule that selector rules are not modified before the first blind run?
+2. Did the blind input set avoid expected routing labels before first execution?
+3. Is it acceptable that model-name-exposed control cases are retained as controls rather than natural blind inputs?
+
+## 2. Routing Evaluation
+
+For each observed routing result, classify failures or risks as needed:
+
+- selector false positive
+- selector false negative
+- no-call false positive
+- no-call false negative
+- QPI over-selection
+- QPI under-selection
+- IA over-selection
+- IA under-selection
+- QPI-before-IA gate failure
+- model-level exclusion failure
+- depth-limiting override failure
+- insufficient-context handling risk
+- control-case-only behavior, not natural-input behavior
+
+## 3. Specific Review Prompts
+
+1. Which Round 04 cases should become regression cases?
+2. Which cases should become calibration inputs?
+3. Which cases should remain as non-regression discussion examples?
+4. Does any observed routing require a selector rule patch?
+5. If a rule patch is needed, should it be Round 04.1 rather than part of Round 04?
+6. Does any result imply that QPI or Intellectual Archaeology model content needs revision?
+7. Are any blind inputs too artificial and should be removed from future rounds?
+
+## 4. Lifecycle Guard
+
+Do not upgrade QPI or Intellectual Archaeology model lifecycle status from this Round 04 result alone.
+
+Model status changes still require evidence review, content review, regression review, selector review, and owner / CCRA review.

ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md

@@ -0,0 +1,56 @@
+# Round 04 Bundle File Manifest
+
+## Review Files
+
+- `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`
+
+## Optional Raw Changed Files
+
+The zip is optional and should be used only if exact file inspection is needed.
+
+It preserves source-relative paths.
+
+It excludes:
+
+- `knowledge_assets/`
+- `__pycache__/`
+- `*.pyc`
+- previous review bundle zip files
+
+## Source-Relative Files Included in Raw Zip
+
+- `README.md`
+- `selector/README.md`
+- `selector/selector_rules.json`
+- `selector/selector_calibration_inputs.json`
+- `selector/round04_blind_inputs.json`
+- `models/qpi.model.json`
+- `models/intellectual_archaeology.model.json`
+- `models/model_index.json`
+- `cards/qpi.md`
+- `cards/intellectual_archaeology.md`
+- `cards/card_index.md`
+- `tests/qpi.regression.json`
+- `tests/intellectual_archaeology.regression.json`
+- `tests/regression_cases.json`
+- `tests/test_round04_blind_routing.py`
+- `scripts/README.md`
+- `scripts/run_selector_demo.py`
+- `scripts/run_selector_regression.py`
+- `scripts/run_selector_calibration_smoke.py`
+- `scripts/run_round04_blind_routing.py`
+- `reports/README.md`
+- `reports/Round04_blind_input_candidates_2026-06-18.md`
+- `reports/Round04_blind_routing_evaluation_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`
+- `docs/superpowers/plans/2026-06-18-round04-blind-routing-evaluation.md`

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:
 
@@ -214,3 +214,180 @@ Closure statement:
 - QPI is accepted as a draft-callable routing asset at report level only; this does not change JSON model lifecycle status.
 - Selector v0.2 passes no-call, calibration smoke, model-level exclusion, QPI-before-IA, and depth-limiting override gates.
 - Round 04 blind input routing evaluation is the next candidate phase, but it is not started by this closure.
+
+## Decision 017: Treat Round 04.1 as selector rule patch verification, not a second blind test
+
+Status: Accepted
+
+Reason:
+
+Round 04 first-run blind routing evaluation found review-approved selector failures:
+
+- R04-BI-002: translation task over-selected QPI because payload text contained `模型`.
+- R04-BI-024: explicit `不要进入思想考古` did not hard-exclude Intellectual Archaeology.
+- R04-BI-035 / R04-BI-036: depth-limiting phrases blocked lightweight QPI scarcity judgment.
+
+Round 04.1 therefore patches selector rules and verifies the patch against frozen Round 04 inputs. It is not a second blind test because expected labels now exist for the four owner / GPT reviewed target cases.
+
+The patch remains scoped:
+
+- It adds translation / direct transformation no-call coverage.
+- It separates task instruction from payload for no-call matching before payload complexity scoring.
+- It expands IA model-level hard exclusion variants.
+- It expands depth-limiting QPI override phrases for `主导稀缺` and `缺信息 / 缺路径 / 缺共识`.
+- It does not add a new model, lifecycle upgrade, LLM selector, RAG, database, service, frontend, backend, user system, or QA product.
+
+QPI and Intellectual Archaeology remain `draft / B / pending`.
+
+Closeout:
+
+- GPT review accepted Round 04.1 and did not request a 04.2 selector patch.
+- `R04-BI-022` is documented as an accepted collateral behavior change: it moved from no-call to lightweight QPI after the depth-limiting override patch.
+- This is not a new failure because the user rejects deeper IA-style expansion but asks for dominant-scarcity judgment.
+- 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

@@ -74,6 +74,96 @@ python scripts\rebuild_indexes.py --check
 python scripts\validate_model_library.py
 ```
 
+## 5.1 Review Bundle Zip Workflow
+
+When creating optional raw changed-file zips for GPT / CCRA review bundles, use the installed `bundle-zip` Skill instead of ad hoc PowerShell or Python compression.
+
+Required properties:
+
+1. Provide an explicit file list.
+2. Use the repository root marker, for example `the-mindscape-of-bro-tsong`.
+3. Preserve source-relative paths inside the zip.
+4. Verify the zip by reading it back.
+5. Keep the `bundle-zip` JSON summary with the review bundle when useful.
+
+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.
-

docs/superpowers/plans/2026-06-18-round04-1-selector-rule-patch.md

@@ -0,0 +1,108 @@
+# Round 04.1 Selector Rule Patch Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Fix Round 04 selector boundary failures without changing model lifecycle status or introducing an LLM selector.
+
+**Architecture:** Add targeted regression cases from Round 04 review, patch rule-based selector configuration and minimal selector logic, rerun the frozen Round 04 input pool as post-patch verification, and package 04.1 review materials. The original Round 04 blind output remains frozen; 04.1 produces comparison reports.
+
+**Tech Stack:** JSON, Markdown, Python standard library, existing selector scripts, installed `bundle-zip` Skill.
+
+## Global Constraints
+
+- Do not change the original Round 04 blind routing report.
+- Do not introduce an LLM selector.
+- Do not add a third model.
+- Do not upgrade QPI or Intellectual Archaeology.
+- Do not implement RAG, vector database, frontend, backend, user account, or QA product.
+- Treat Round 04.1 as post-patch routing verification, not a second blind test.
+- Use `bundle-zip` for source-relative review bundle zips.
+
+---
+
+### Task 1: Add Targeted Regression Cases
+
+**Files:**
+- Modify: `tests/qpi.regression.json`
+- Modify: `tests/intellectual_archaeology.regression.json`
+- Modify: `tests/regression_cases.json`
+
+**Interfaces:**
+- Consumes: Round 04 review cases R04-BI-002, R04-BI-024, R04-BI-035, R04-BI-036.
+- Produces: selector regression failures before patch.
+
+- [ ] Add R04-BI-002 as a QPI no-call regression.
+- [ ] Add R04-BI-024 as an IA hard-exclusion regression with QPI allowed.
+- [ ] Add R04-BI-035 and R04-BI-036 as depth-limiting QPI override regressions.
+- [ ] Run `python scripts\run_selector_regression.py` and confirm expected failures.
+
+### Task 2: Patch Selector Rules and Minimal Logic
+
+**Files:**
+- Modify: `selector/selector_rules.json`
+- Modify if needed: `scripts/run_selector_demo.py`
+- Modify: `selector/README.md`
+- Modify: `docs/DECISIONS.md`
+
+**Interfaces:**
+- Consumes: failing regression cases from Task 1.
+- Produces: selector behavior that passes targeted regressions.
+
+- [ ] Add translation no-call intent phrases beyond one exact wording.
+- [ ] Add instruction / payload separation for direct transformation tasks before scoring payload complexity.
+- [ ] Add IA hard-exclusion variants such as `不要进入思想考古`.
+- [ ] Add depth-limiting QPI override phrases for `主导稀缺` and `缺信息 / 缺路径 / 缺共识` forms.
+- [ ] Document the rule patch.
+
+### Task 3: Post-Patch Routing Comparison
+
+**Files:**
+- Create: `scripts/run_round04_post_patch_verification.py`
+- Create: `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md`
+- Test: `tests/test_round04_blind_routing.py` or new focused test if needed.
+
+**Interfaces:**
+- Consumes: frozen `selector/round04_blind_inputs.json` and frozen Round 04 report.
+- Produces: before / after comparison for targeted expected routing labels.
+
+- [ ] Generate current post-patch results for all 38 frozen inputs.
+- [ ] Compare targeted cases R04-BI-002, R04-BI-024, R04-BI-035, R04-BI-036 against expected labels.
+- [ ] Include original selected models / no-call from Round 04 and new selected models / no-call.
+
+### Task 4: Build Round 04.1 Review Bundle
+
+**Files:**
+- Create: `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.1.md`
+- Create: `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md`
+- Create: `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md`
+- Create: `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md`
+- Create: `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md`
+- Create: `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/BUNDLE_FILE_MANIFEST_04.1.md`
+- Create: `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip`
+
+**Interfaces:**
+- Consumes: patch diffs, post-patch report, validation output, source file list.
+- Produces: GPT / CCRA review package.
+
+- [ ] Write required review files.
+- [ ] Use `bundle-zip` to create source-relative raw zip.
+- [ ] Verify zip output using `bundle-zip` JSON summary.
+
+### Task 5: Verify
+
+**Files:**
+- Read: full changed set.
+
+**Interfaces:**
+- Consumes: completed 04.1 patch and review bundle.
+- Produces: verification evidence.
+
+- [ ] Run `python scripts\rebuild_indexes.py --check`.
+- [ ] Run `python -m unittest discover -s tests -p "test*.py" -v`.
+- [ ] Run `python scripts\validate_model_library.py`.
+- [ ] Run `python scripts\check_card_contract.py`.
+- [ ] Run `python scripts\run_selector_demo.py`.
+- [ ] Run `python scripts\run_selector_regression.py`.
+- [ ] Run `python scripts\run_selector_calibration_smoke.py`.
+- [ ] Run `python scripts\check_model_card_sync.py`.
+- [ ] Confirm model JSON status remains `draft / B / pending`.

docs/superpowers/plans/2026-06-18-round04-blind-routing-evaluation.md

@@ -0,0 +1,172 @@
+# Round 04 Blind Routing Evaluation Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Prepare and run Round 04 blind input routing evaluation without changing selector rules or model lifecycle status.
+
+**Architecture:** Round 04 uses a reviewed blind input pool as source material, freezes it into a machine-readable JSON input set, runs the existing rule-based selector through a thin batch runner, and packages the outputs for GPT / CCRA review. The runner reuses `scripts/run_selector_demo.py::recommend` and does not add answer generation, LLM selector logic, or expected routing labels.
+
+**Tech Stack:** Markdown, JSON, Python standard library, existing selector scripts.
+
+## Global Constraints
+
+- Do not modify `selector/selector_rules.json` before the blind evaluation.
+- Do not merge blind inputs into `selector/selector_calibration_inputs.json`.
+- Do not add expected behavior before the first blind run.
+- Do not add a third model.
+- Do not upgrade QPI or Intellectual Archaeology.
+- Do not introduce an LLM selector.
+- Do not implement RAG, vector database, frontend, backend, user account, or QA product.
+- Run first, analyze failures later.
+
+---
+
+### Task 1: Revise Human-Readable Blind Input Source
+
+**Files:**
+- Modify: `reports/Round04_blind_input_candidates_2026-06-18.md`
+
+**Interfaces:**
+- Consumes: owner review notes for R04-BI-018, R04-BI-021, R04-BI-025, R04-BI-026, and new R04-BI-031 through R04-BI-038.
+- Produces: 38 candidate inputs with review-only metadata and no expected routing labels.
+
+- [ ] **Step 1: Mark control-case notes**
+
+Add metadata notes:
+- R04-BI-021 and R04-BI-025: `model-name-exposed control case`
+- R04-BI-018: `positive control`
+- R04-BI-026: natural IA / QPI-to-IA boundary sample
+
+- [ ] **Step 2: Add R04-BI-031 through R04-BI-038**
+
+Add the eight owner-proposed cases exactly, preserving their categories, input text, and inclusion rationale.
+
+- [ ] **Step 3: Update coverage**
+
+Set total to 38 candidate inputs and include a short note that 2 inputs expose model names by design.
+
+### Task 2: Freeze Machine-Readable Blind Input JSON
+
+**Files:**
+- Create: `selector/round04_blind_inputs.json`
+
+**Interfaces:**
+- Consumes: reviewed Markdown source from Task 1.
+- Produces: JSON with `blind_input_set_id`, `status`, `source_document`, `constraints`, and `inputs`.
+
+- [ ] **Step 1: Create JSON without expected routing**
+
+Each input object contains:
+- `input_id`
+- `category_for_owner_review`
+- `input_text`
+- `why_included`
+- optional `control_case_type`
+
+- [ ] **Step 2: Preserve blindness constraints**
+
+Include top-level notes that no expected behavior is present and that selector rules must not be modified before first run.
+
+### Task 3: Add Failing Tests for the Round 04 Runner
+
+**Files:**
+- Create: `tests/test_round04_blind_routing.py`
+- Create later in Task 4: `scripts/run_round04_blind_routing.py`
+
+**Interfaces:**
+- Consumes: `selector/round04_blind_inputs.json`
+- Produces: test expectations for load, evaluation shape, and report content.
+
+- [ ] **Step 1: Write tests before implementation**
+
+Test that a blind input item can be loaded, evaluated through `recommend`, and rendered without expected routing labels.
+
+- [ ] **Step 2: Run tests and confirm failure**
+
+Run: `python -m unittest tests.test_round04_blind_routing -v`
+
+Expected: failure because `scripts.run_round04_blind_routing` does not exist.
+
+### Task 4: Implement and Run the Round 04 Runner
+
+**Files:**
+- Create: `scripts/run_round04_blind_routing.py`
+- Create: `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
+
+**Interfaces:**
+- Consumes: `selector/round04_blind_inputs.json`, `scripts/run_selector_demo.py::recommend`
+- Produces: JSON-shaped evaluation results and Markdown report.
+
+- [ ] **Step 1: Implement standard-library runner**
+
+Provide functions:
+- `load_blind_inputs(root)`
+- `evaluate_blind_input(root, item)`
+- `write_report(root, input_set, results)`
+- `main()`
+
+- [ ] **Step 2: Run focused tests**
+
+Run: `python -m unittest tests.test_round04_blind_routing -v`
+
+- [ ] **Step 3: Run blind evaluation**
+
+Run: `python scripts\run_round04_blind_routing.py`
+
+Expected: report written; command exits 0.
+
+### Task 5: Build Round 04 Review Bundle
+
+**Files:**
+- Create: `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md`
+- Create: `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md`
+- Create: `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md`
+- Create: `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md`
+- Create: `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md`
+- Create: `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md`
+- Create: `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/optional_raw_changed_files_04.zip`
+
+**Interfaces:**
+- Consumes: Round 03 closure summary, frozen blind input JSON, runner output report, current runtime assets.
+- Produces: GPT / CCRA review package.
+
+- [ ] **Step 1: Write brief and scope files**
+
+Include Round 03 closure summary, Round 04 target, and non-goals.
+
+- [ ] **Step 2: Write input and evaluation mirrors**
+
+Mirror the frozen blind input set and routing evaluation report for upload.
+
+- [ ] **Step 3: Create raw zip**
+
+Include current runtime assets, blind input set, runner, tests, and reports. Preserve source-relative paths.
+
+### Task 6: Verify
+
+**Files:**
+- Read: all changed files
+
+**Interfaces:**
+- Consumes: full working tree after Tasks 1-5.
+- Produces: verification evidence.
+
+- [ ] **Step 1: Run focused Round 04 test**
+
+Run: `python -m unittest tests.test_round04_blind_routing -v`
+
+- [ ] **Step 2: Run existing validation gates**
+
+Run:
+- `python scripts\rebuild_indexes.py --check`
+- `python -m unittest discover -s tests -p "test*.py" -v`
+- `python scripts\validate_model_library.py`
+- `python scripts\check_card_contract.py`
+- `python scripts\run_selector_demo.py`
+- `python scripts\run_selector_regression.py`
+- `python scripts\run_selector_calibration_smoke.py`
+- `python scripts\check_model_card_sync.py`
+
+- [ ] **Step 3: Inspect git diff**
+
+Confirm no selector rule changes and no model lifecycle status changes.

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`