diff --git a/README.md b/README.md
index 1c111b3..6a70044 100644
--- a/README.md
+++ b/README.md
@@ -148,6 +148,7 @@ Foundation repair in progress for:
 Current foundation assets include:
 
 - GPT plan localization protocol.
+- File taxonomy for canonical, generated, review archive, and temporary files.
 - Model extraction rules.
 - Model card contract.
 - Model extraction workflow.
@@ -161,7 +162,7 @@ Current foundation assets include:
 - A standard-library validation script that writes `reports/validation_report.md`.
 - A standard-library index rebuild/check script that writes `reports/index_rebuild_report.md`.
 - ChatGPT handoff rules.
-- Long-term knowledge asset rules and initial `knowledge_assets/` documents.
+- Long-term knowledge asset rules and `knowledge_assets/` documents, including `09_数据治理与模型调用机制说明.md`.
 
 Current QPI and Intellectual Archaeology model contents pass the local contract and remain `draft` pending product review.
 
@@ -171,7 +172,8 @@ CCRA review packages are archived by round under `ccra_review_bundle/round-NN_YY
 
 ## 13. Next Steps
 
-1. Review QPI and Intellectual Archaeology content for product correctness.
-2. Review whether the new `knowledge_assets/` package is sufficient for ChatGPT / CCRA reuse.
-3. Decide whether to expand to a third core model.
-4. Decide whether extraction, inspection, and stability scoring should become CCPE or skills-vault requests.
+1. Submit the Round 03.1 selector/no-call/regression patch for GPT / CCRA review.
+2. Keep QPI and Intellectual Archaeology at `draft / B / pending` until Owner / CCRA review accepts stronger status.
+3. Run a QPI blind-test round with new unlabelled inputs after Round 03.1 passes.
+4. Defer any third-model expansion until the current QPI selector and case layer are accepted.
+5. Route missing reusable extraction, inspection, or stability-scoring tools to `requirements/skills-vault/` or `requirements/ccpe/` instead of improvising local platform features.
diff --git a/cards/qpi.md b/cards/qpi.md
index 384acee..7648bc5 100644
--- a/cards/qpi.md
+++ b/cards/qpi.md
@@ -202,7 +202,7 @@ 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，已有五条样板用例，尚未经过真实案例扩展。
+- 回归测试表现：pending，当前已有 52 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。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。
 
@@ -212,13 +212,15 @@ 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`
 
-当前已有五条回归用例：
+当前已有 52 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：
 
-- `case_qpi_positive_question_001`
-- `case_qpi_positive_problem_001`
-- `case_qpi_positive_issue_001`
-- `case_qpi_boundary_mixed_001`
-- `case_qpi_misuse_inflation_001`
+- owner-reviewed flow / disappointment / organizational year-end-review cases；
+- `case_qpi_international_logistics_no_call_001`
+- `case_qpi_research_capacity_problem_not_issue_001`
+- `case_qpi_multi_perspective_requires_viewpoint_output_001`
+- `case_qpi_low_context_provisional_no_high_confidence_001`
+- `case_qpi_direct_summary_no_call_001`
+- `case_qpi_analysis_override_should_call_001`
 
 ## 示例输入
 
@@ -283,5 +285,5 @@ selector 应优先使用 `trigger_keywords`、`negative_triggers`、`pipeline_po
 ## 版本信息
 
 - version: `0.1`
-- last_updated: `2026-06-16`
+- last_updated: `2026-06-17`
 - status: `draft`
diff --git a/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md b/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md
new file mode 100644
index 0000000..3479dd7
--- /dev/null
+++ b/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md
@@ -0,0 +1,61 @@
+# CCRA / GPT Review Brief: Round 03.1 Selector No-Call Regression Patch
+
+Date: 2026-06-17
+
+Repository: `C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong`
+
+Phase: `model_library_mvp`
+
+## 1. Scope
+
+Round 03.1 is a small patch over the formal Round 03 review package.
+
+It fixes:
+
+- selector over-selection of QPI by base score;
+- direct-execution no-call coverage;
+- selector calibration smoke coverage;
+- QPI regression coverage for no-call, low-context, multi-perspective, and capacity boundary cases;
+- QPI digest field drift;
+- stale QPI card / report counts;
+- review bundle hygiene.
+
+It does not:
+
+- add a third model;
+- upgrade QPI or Intellectual Archaeology to stable;
+- introduce an LLM selector;
+- introduce RAG, database, frontend, backend, user system, or full QA system.
+
+Lifecycle states remain:
+
+| Model ID | Status | Stability | Regression Status |
+| --- | --- | --- | --- |
+| `qpi` | draft | B | pending |
+| `intellectual_archaeology` | draft | B | pending |
+
+## 2. Main Fix
+
+QPI can no longer be selected only by base score plus selection priority.
+
+The selector now requires a positive signal for QPI unless the request is explicitly in the problem-definition path. Direct execution inputs such as summary, table formatting, bed assignment, and narrow translation are no-call unless an explicit analysis override exists.
+
+## 3. Current Counts
+
+| Artifact | Count |
+| --- | ---: |
+| QPI case digests | 62 |
+| Selector calibration inputs | 85 |
+| QPI regression cases | 52 |
+| Aggregate regression cases | 69 |
+| Unit tests | 17 |
+
+## 4. Review Focus
+
+Please review:
+
+- whether the selector no-call gate now blocks direct execution without suppressing explicit analysis override;
+- whether the calibration smoke test is an acceptable Round 03.1 guardrail;
+- whether `misclassification_risk` and `qpi_complexity_pattern` resolve the digest contract drift;
+- whether multi-perspective digests now have enough viewpoint traceability for draft-callable review;
+- whether QPI remains a routing model and not a solution engine.
diff --git a/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/01_PATCH_MATRIX.md b/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/01_PATCH_MATRIX.md
new file mode 100644
index 0000000..7bf26d9
--- /dev/null
+++ b/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/01_PATCH_MATRIX.md
@@ -0,0 +1,28 @@
+# Round 03.1 Patch Matrix
+
+| GPT / Owner instruction | Status | Evidence |
+| --- | --- | --- |
+| QPI must not be selected only by base score + selection priority | Done | `scripts/run_selector_demo.py`, `selector/selector_rules.json` |
+| Add direct execution no-call signals | Done | `selector/selector_rules.json` |
+| Preserve explicit analysis override behavior | Done | `scripts/run_selector_demo.py`, `case_qpi_analysis_override_should_call_001` |
+| Normalize rule-level selection priority scale | Done | QPI rule priority `9`, IA rule priority `7` |
+| Add required Round 03.1 QPI regression cases | Done | `tests/qpi.regression.json` |
+| Sync new QPI cases into aggregate regression file | Done | `tests/regression_cases.json` |
+| Add selector calibration smoke test | Done | `scripts/run_selector_calibration_smoke.py` |
+| Normalize `misframing_risks` to `misclassification_risk` | Done | `selector/qpi_case_digests.json`, `scripts/validate_model_library.py` |
+| Rename/document `mixed_or_multi_perspective` | Done | `qpi_complexity_pattern`, documented in `selector/README.md` and `docs/QPI_CONTEXTUAL_ROUTING_RULES.md` |
+| Require viewpoint detail for multi-perspective digests | Done | validator requires `classification_by_viewpoint` or `viewpoint_summary` |
+| Update stale QPI card count and date | Done | `cards/qpi.md`, `models/qpi.model.json` |
+| Mark v0.2 content report as pre-case-promotion | Done | `reports/content_review_report_v0.2.md` |
+| Preserve source paths in review zip | Done | `optional_raw_changed_files.zip` uses relative paths |
+| Exclude `knowledge_assets` from review resources | Done | Not included in Round 03.1 raw zip |
+| Include IA model/card if IA contract completion is referenced | Done | `models/intellectual_archaeology.model.json`, `cards/intellectual_archaeology.md` included in zip |
+
+## Added QPI Regression Cases
+
+- `case_qpi_international_logistics_no_call_001`
+- `case_qpi_research_capacity_problem_not_issue_001`
+- `case_qpi_multi_perspective_requires_viewpoint_output_001`
+- `case_qpi_low_context_provisional_no_high_confidence_001`
+- `case_qpi_direct_summary_no_call_001`
+- `case_qpi_analysis_override_should_call_001`
diff --git a/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/02_CURRENT_ASSET_PACK.md b/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/02_CURRENT_ASSET_PACK.md
new file mode 100644
index 0000000..d8b7614
--- /dev/null
+++ b/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/02_CURRENT_ASSET_PACK.md
@@ -0,0 +1,51 @@
+# Current Asset Pack
+
+## 1. Selector And Calibration
+
+- `selector/selector_rules.json`
+- `selector/selector_calibration_inputs.json`
+- `selector/qpi_case_digests.json`
+- `selector/README.md`
+- `scripts/run_selector_demo.py`
+- `scripts/run_selector_regression.py`
+- `scripts/run_selector_calibration_smoke.py`
+
+## 2. Regression And Validation
+
+- `tests/qpi.regression.json`
+- `tests/regression_cases.json`
+- `tests/test_validate_model_library.py`
+- `scripts/validate_model_library.py`
+- `scripts/check_card_contract.py`
+- `scripts/check_model_card_sync.py`
+- `scripts/rebuild_indexes.py`
+
+## 3. Model/Card Sync
+
+- `models/qpi.model.json`
+- `cards/qpi.md`
+- `models/model_index.json`
+- `cards/card_index.md`
+- `models/intellectual_archaeology.model.json`
+- `cards/intellectual_archaeology.md`
+
+## 4. Reports
+
+- `reports/validation_report.md`
+- `reports/index_rebuild_report.md`
+- `reports/selector_regression_report_v0.2.md`
+- `reports/selector_calibration_smoke_report.md`
+- `reports/model_card_sync_report_v0.2.md`
+- `reports/content_review_report_v0.2.md`
+
+## 5. Rule Docs
+
+- `docs/QPI_CONTEXTUAL_ROUTING_RULES.md`
+
+## 6. Excluded From Review Zip
+
+`knowledge_assets/` is not included. The owner manually syncs long-term knowledge assets into GPT knowledge storage, so review bundles should focus on current executable / auditable project assets.
+
+Current long-term related asset, manually synced by Owner rather than included in this patch zip:
+
+- `knowledge_assets/09_数据治理与模型调用机制说明.md`
diff --git a/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/03_VALIDATION_AND_COMMAND_LOG.md b/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/03_VALIDATION_AND_COMMAND_LOG.md
new file mode 100644
index 0000000..23688b9
--- /dev/null
+++ b/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/03_VALIDATION_AND_COMMAND_LOG.md
@@ -0,0 +1,31 @@
+# Validation And Command Log
+
+## 1. Commands Run
+
+```powershell
+python scripts\rebuild_indexes.py --write
+python -m unittest discover -s tests -p "test*.py" -v
+python scripts\check_card_contract.py
+python scripts\validate_model_library.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
+```
+
+## 2. Results
+
+- Index rebuild `--write`: PASS.
+- Unit tests: PASS, 17 tests.
+- Card contract: PASS.
+- Model library validation: PASS.
+- Selector demo: PASS; selected `qpi`, rejected `intellectual_archaeology`.
+- Selector regression: PASS.
+- Selector calibration smoke: PASS, 85 calibration inputs checked.
+- Model/card sync: PASS.
+
+## 3. Notable Debugging Notes
+
+- Lowering QPI base score exposed that existing owner-reviewed calibration inputs needed richer QPI semantic signals rather than default QPI selection.
+- Broad `翻译` matching was narrowed so literal translation stays no-call while metaphorical organizational translation can still select QPI.
+- `先不要思想考古` was added as an IA negative trigger to preserve QPI-before-IA routing when the user explicitly asks not to call IA.
diff --git a/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/04_REVIEW_QUESTIONS_FOR_GPT.md b/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/04_REVIEW_QUESTIONS_FOR_GPT.md
new file mode 100644
index 0000000..22ecfb0
--- /dev/null
+++ b/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/04_REVIEW_QUESTIONS_FOR_GPT.md
@@ -0,0 +1,18 @@
+# Review Questions For GPT
+
+Please return:
+
+1. pass / revise / block judgment for Round 03.1;
+2. whether selector no-call behavior is now safe enough for draft-callable review;
+3. whether the calibration smoke test should become a permanent gate;
+4. whether any new no-call or override traps are missing;
+5. whether digest field normalization is acceptable;
+6. whether QPI lifecycle should remain `draft / B / pending`.
+
+Required non-goal check:
+
+- no third model;
+- no stable upgrade;
+- no LLM selector;
+- no full QA system;
+- no RAG / vector database / frontend / backend platform.
diff --git a/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/BUNDLE_FILE_MANIFEST.md b/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/BUNDLE_FILE_MANIFEST.md
new file mode 100644
index 0000000..ef03a0a
--- /dev/null
+++ b/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/BUNDLE_FILE_MANIFEST.md
@@ -0,0 +1,50 @@
+# Bundle File Manifest
+
+## Recommended Upload Order
+
+1. `00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md`
+2. `01_PATCH_MATRIX.md`
+3. `02_CURRENT_ASSET_PACK.md`
+4. `03_VALIDATION_AND_COMMAND_LOG.md`
+5. `04_REVIEW_QUESTIONS_FOR_GPT.md`
+6. `optional_raw_changed_files.zip` only if exact file inspection is needed
+
+## Zip Policy
+
+`optional_raw_changed_files.zip` preserves source-relative paths. It is not a flat archive.
+
+`knowledge_assets/` is intentionally excluded from this review bundle because the owner manually syncs long-term knowledge assets into GPT knowledge storage.
+
+Current related long-term asset outside this review zip:
+
+- `knowledge_assets/09_数据治理与模型调用机制说明.md`
+
+## Raw Files Included In Zip
+
+- `selector/selector_rules.json`
+- `selector/selector_calibration_inputs.json`
+- `selector/qpi_case_digests.json`
+- `selector/README.md`
+- `scripts/run_selector_demo.py`
+- `scripts/run_selector_regression.py`
+- `scripts/run_selector_calibration_smoke.py`
+- `scripts/validate_model_library.py`
+- `scripts/check_card_contract.py`
+- `scripts/check_model_card_sync.py`
+- `scripts/rebuild_indexes.py`
+- `tests/qpi.regression.json`
+- `tests/regression_cases.json`
+- `tests/test_validate_model_library.py`
+- `models/qpi.model.json`
+- `cards/qpi.md`
+- `models/model_index.json`
+- `cards/card_index.md`
+- `models/intellectual_archaeology.model.json`
+- `cards/intellectual_archaeology.md`
+- `reports/validation_report.md`
+- `reports/index_rebuild_report.md`
+- `reports/selector_regression_report_v0.2.md`
+- `reports/selector_calibration_smoke_report.md`
+- `reports/model_card_sync_report_v0.2.md`
+- `reports/content_review_report_v0.2.md`
+- `docs/QPI_CONTEXTUAL_ROUTING_RULES.md`
diff --git a/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/optional_raw_changed_files.zip b/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/optional_raw_changed_files.zip
new file mode 100644
index 0000000..4da5fde
Binary files /dev/null and b/ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/optional_raw_changed_files.zip differ
diff --git a/docs/DECISIONS.md b/docs/DECISIONS.md
index 210faf4..72552b9 100644
--- a/docs/DECISIONS.md
+++ b/docs/DECISIONS.md
@@ -153,3 +153,8 @@ ccra_review_bundle/round-NN_YYYY-MM-DD_topic/
 ```
 
 This keeps second-round and third-round materials comparable without overwriting prior evidence. Temporary review bundles remain session evidence and should not be copied into `knowledge_assets/`.
+
+Round 03.1 added two bundle hygiene rules:
+
+- `optional_raw_changed_files.zip` must preserve source-relative paths. Do not create flat archives that can collide on names such as `README.md`.
+- `knowledge_assets/` is excluded from review bundles by default because the project owner manually syncs stable long-term knowledge assets into GPT knowledge storage. Include it only when the current review explicitly targets the knowledge asset itself.
diff --git a/docs/FILE_TAXONOMY.md b/docs/FILE_TAXONOMY.md
new file mode 100644
index 0000000..200cab0
--- /dev/null
+++ b/docs/FILE_TAXONOMY.md
@@ -0,0 +1,152 @@
+# File Taxonomy
+
+Date: 2026-06-17
+
+Status: accepted
+
+## 1. Purpose
+
+This document defines file identities for the `model_library_mvp` phase.
+
+The goal is to prevent every generated report, review bundle, cache, and model asset from being treated as the same kind of artifact.
+
+`docs/KNOWLEDGE_ASSET_RULES.md` governs one specific category: long-term reusable knowledge assets.
+
+This document is broader. It governs the whole repository.
+
+## 2. File Identity Classes
+
+Every meaningful file should fit one of four classes:
+
+| Class | Meaning | Default retention | Examples |
+| --- | --- | --- | --- |
+| 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/*` |
+| 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
+
+Canonical files answer:
+
+```text
+What is the current model/library behavior?
+What is the reviewed source or contract?
+What should code and future agents trust?
+```
+
+Canonical files include:
+
+- model JSON specs under `models/`;
+- human-readable cards under `cards/`;
+- source records and evidence excerpts under `sources/`;
+- regression source files under `tests/*.regression.json`;
+- selector rules and calibration files under `selector/`;
+- schemas under `schemas/`;
+- operative rules and protocols under `docs/`;
+- stable explanatory assets under `knowledge_assets/`.
+
+Canonical files should be edited deliberately and validated after change.
+
+## 4. Generated / Derived Files
+
+Generated files answer:
+
+```text
+What did the current canonical assets produce when checked or rebuilt?
+```
+
+They may be committed when they are part of the file-first workflow, but they are not independent truth.
+
+Examples:
+
+- `models/model_index.json`
+- `cards/card_index.md`
+- `tests/regression_cases.json`
+- `reports/validation_report.md`
+- `reports/index_rebuild_report.md`
+- `reports/model_card_sync_report_v0.2.md`
+- `reports/selector_regression_report_v0.2.md`
+- `reports/selector_calibration_smoke_report.md`
+
+Rules:
+
+- Rebuild indexes after model/card/source/test changes.
+- Regenerate reports after validation or selector checks.
+- Do not manually edit generated reports to hide validation failure.
+- If generated output disagrees with canonical source, fix the source or generator, then regenerate.
+
+## 5. Review Archive Files
+
+Review archives answer:
+
+```text
+What was submitted, reviewed, or handed off in a specific round?
+```
+
+They preserve evidence and context, but they do not override canonical files.
+
+Examples:
+
+- `ccra_review_bundle/round-*/`
+- `reports/Codex*.md`
+- `reports/GPT*.md`
+- `reports/model_case_preprocessing/*`
+
+Rules:
+
+- Keep review bundles under dated round directories.
+- Do not place new review files directly under `ccra_review_bundle/`.
+- `optional_raw_changed_files.zip` must preserve source-relative paths.
+- 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.
+
+## 6. Temporary / Local Runtime Files
+
+Temporary files answer no durable project question.
+
+Examples:
+
+- `__pycache__/`
+- `*.pyc`
+- local unpacked zip folders;
+- scratch command outputs not referenced by a report;
+- editor backups.
+
+Rules:
+
+- Do not commit these files.
+- Add broad safe ignore rules in `.gitignore`.
+- If a temporary command output becomes useful evidence, convert it into a deliberate report under `reports/` or a review bundle.
+
+## 7. Relationship To Knowledge Assets
+
+`knowledge_assets/` is a canonical long-term explanatory layer, but not every canonical file belongs there.
+
+Put a document in `knowledge_assets/` only when it answers:
+
+```text
+What durable context, mechanism, rule, or map should ChatGPT / CCRA / Owner remember across sessions?
+```
+
+Do not put these in `knowledge_assets/`:
+
+- concrete model cards that already live in `cards/`;
+- machine-readable model JSON;
+- validation reports;
+- per-round review bundles;
+- command logs;
+- temporary handoffs.
+
+See `docs/KNOWLEDGE_ASSET_RULES.md` for detailed knowledge-asset rules.
+
+## 8. Commit Checklist
+
+Before commit:
+
+1. Confirm new files have the correct identity.
+2. Confirm temporary files are not staged.
+3. Rebuild or check indexes when canonical model/card/source/test files changed.
+4. Regenerate validation reports after validation commands.
+5. Keep review-bundle zips path-preserving.
+6. Keep lifecycle status conservative; validation pass does not imply stable.
diff --git a/docs/KNOWLEDGE_ASSET_RULES.md b/docs/KNOWLEDGE_ASSET_RULES.md
index 7292ab9..67b7cbd 100644
--- a/docs/KNOWLEDGE_ASSET_RULES.md
+++ b/docs/KNOWLEDGE_ASSET_RULES.md
@@ -6,6 +6,8 @@
 
 These documents are not raw source archives, not temporary handoffs, and not implementation-only files. They are the durable explanation layer that helps the project owner, ChatGPT, Codex, and future CCRA work understand the model library without reconstructing context from scattered files.
 
+For the broader repository-wide distinction between canonical, generated, review archive, and temporary files, see `docs/FILE_TAXONOMY.md`.
+
 ## What Belongs In `knowledge_assets/`
 
 Use `knowledge_assets/` for:
@@ -17,6 +19,7 @@ Use `knowledge_assets/` for:
 - stability rating rules
 - durable process records
 - reusable architecture summaries
+- durable data-governance and model-invocation mechanism explanations
 
 Do not use `knowledge_assets/` for:
 
@@ -26,6 +29,7 @@ Do not use `knowledge_assets/` for:
 - generated cache files
 - implementation scripts
 - source-of-truth JSON model assets
+- per-round review bundles or optional raw changed-file zips
 
 ## Relationship To Other Directories
 
@@ -39,6 +43,8 @@ Do not use `knowledge_assets/` for:
 
 `knowledge_assets/` contains stable explanatory knowledge distilled from those sources.
 
+The project owner may manually sync stable `knowledge_assets/` documents into GPT knowledge storage. Review bundles should therefore not include `knowledge_assets/` by default unless the current review explicitly targets the long-term knowledge asset itself.
+
 ## Naming Rule
 
 Use numeric prefixes for reading order.
@@ -54,6 +60,7 @@ Examples:
 03_核心模型抽取样板.md
 06_模型稳固性评级规则.md
 07_产品规划过程记录.md
+09_数据治理与模型调用机制说明.md
 ```
 
 ## Model Card Sample Rule
diff --git a/docs/QPI_CONTEXTUAL_ROUTING_RULES.md b/docs/QPI_CONTEXTUAL_ROUTING_RULES.md
index 5230911..1f2f3fd 100644
--- a/docs/QPI_CONTEXTUAL_ROUTING_RULES.md
+++ b/docs/QPI_CONTEXTUAL_ROUTING_RULES.md
@@ -174,5 +174,16 @@ Each case digest should preserve:
 - `codex_candidate_judgment`;
 - `owner_review_needed`.
 
-Raw case processing is intentionally deferred until owner materials are available.
+Round 03 completed the first owner-reviewed QPI case promotion into:
 
+- `reports/model_case_preprocessing/qpi/round-01/*.cases.md`;
+- `selector/qpi_case_digests.json`;
+- `selector/selector_calibration_inputs.json`;
+- `tests/qpi.regression.json`.
+
+Round 03.1 digest field rules:
+
+- Use `misclassification_risk`, not `misframing_risks`, to match the QPI structured output contract.
+- Use `qpi_complexity_pattern`, not `mixed_or_multi_perspective`, for judgment-structure complexity.
+- `qpi_complexity_pattern=intra_frame_mixed` does not require `classification=mixed`; final routing classification and judgment complexity are separate.
+- If `classification_scope=multi_perspective` or `qpi_complexity_pattern=inter_viewpoint_divergence`, the digest must include `classification_by_viewpoint` or `viewpoint_summary`.
diff --git a/docs/WORKFLOW.md b/docs/WORKFLOW.md
index 566146a..9c5e820 100644
--- a/docs/WORKFLOW.md
+++ b/docs/WORKFLOW.md
@@ -117,3 +117,5 @@ For long-term reusable knowledge rules, see `docs/KNOWLEDGE_ASSET_RULES.md`.
 When a rule, model map, schema explanation, workflow summary, or product context becomes stable enough to reuse across sessions, create or update a file under `knowledge_assets/`.
 
 Do not leave durable knowledge only in temporary reports.
+
+For repository-wide file identity rules, including canonical files, generated reports, review archives, and temporary files, see `docs/FILE_TAXONOMY.md`.
diff --git a/knowledge_assets/09_数据治理与模型调用机制说明.md b/knowledge_assets/09_数据治理与模型调用机制说明.md
new file mode 100644
index 0000000..0a9cbc5
--- /dev/null
+++ b/knowledge_assets/09_数据治理与模型调用机制说明.md
@@ -0,0 +1,629 @@
+# 数据治理与模型调用机制说明
+
+version: 0.1
+
+last_updated: 2026-06-17
+
+status: stable explanatory asset
+
+source_basis:
+
+- `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\GPT成果\CCRA_数据治理与模型调用机制说明_v0.1.md`
+- current repository contracts, selector rules, regression files, validation scripts, and review-bundle workflow
+
+## 1. 文档定位
+
+本文档是 `model_library_mvp` 阶段的数据治理与模型调用机制说明。
+
+它不是某一轮评审的 PASS / FAIL 记录，也不是对 Owner 质疑的逐条回复。它沉淀的是长期可复用的项目机制：
+
+- 为什么模型库不等于普通知识库；
+- 文章、模型卡、selector、regression、validation、review bundle 分别承担什么治理职责；
+- QPI 和思想考古学未来如何被调用；
+- 哪些文件是长期源头，哪些只是过程证据；
+- 后续新增模型应按什么最低资产结构进入系统。
+
+具体模型内容的 source of truth 仍在：
+
+- `models/*.model.json`
+- `cards/*.md`
+- `sources/*.json`
+- `tests/*.regression.json`
+- `selector/*.json`
+
+本文档只解释机制，不替代上述文件。
+
+## 2. 项目当前性质
+
+`the-mindscape-of-bro-tsong` 当前处于 `model_library_mvp` 阶段。
+
+它不是：
+
+- 完整产品；
+- 聊天机器人；
+- 前端平台；
+- 后端服务；
+- RAG 系统；
+- 知识图谱；
+- 数据库应用；
+- 商业交付系统。
+
+它当前验证的是：
+
+```text
+少量核心认知模型
+能否被整理成 file-first 的模型资产，
+并具备可读、可追溯、可调用、可拒绝调用、可测试、可路由的最低能力。
+```
+
+第一批样板模型是：
+
+- QPI：前置问题定性和路由模型；
+- 思想考古学：中重型问题的深度建模模型。
+
+QPI 的价值不只在于它本身，而在于它能压力测试一整套模型治理机制：调用条件、拒绝条件、输出契约、误用边界、selector 校准、regression 防退化、Owner / CCRA 审核。
+
+## 3. 为什么不是直接把文章喂给 AI
+
+如果只是让 AI 读取文章并回答问题，确实不需要模型库结构。
+
+但这种做法不满足模型资产化要求：
+
+- 不可追溯：很难回查系统用了哪篇文章、哪段证据、哪条人工判断；
+- 不可稳定调用：同一输入可能每次触发不同判断和输出结构；
+- 不可拒绝调用：模型容易被滥用，例如所有复杂问题都套 QPI 或思想考古；
+- 不可回归：改规则后无法知道旧边界是否被破坏；
+- 不可交接 Codex：Codex 不能只凭一篇文章稳定构造 schema、selector、validator 和测试；
+- 不可产品化：文章是内容资产，模型库需要可组合、可运行、可验证的认知工具资产。
+
+因此本项目做的是：
+
+```text
+原始文章 / 人工素材
+-> 来源记录
+-> 证据片段
+-> 人读模型卡
+-> 机器可读模型卡
+-> 输出契约
+-> 调用规则
+-> 负向触发条件
+-> selector
+-> calibration input
+-> regression cases
+-> validation scripts
+-> review bundle
+-> Owner / CCRA 审核意见
+```
+
+这些文件不是平行内容，而是不同治理层。
+
+## 4. 数据治理的六个目标
+
+### 4.1 来源治理
+
+每个模型必须知道它从哪里来：
+
+- 来源文章是什么；
+- 代表性文本是什么；
+- 哪些字段由原文直接支持；
+- 哪些字段是从原文推导；
+- 哪些字段是产品化决策；
+- 哪些字段是 Owner / CCRA 人工判断；
+- 哪些证据仍是 placeholder 或需要复核。
+
+目标是防止模型后来变成“像作者思想，但已经无法回到原文”的漂移资产。
+
+### 4.2 结构治理
+
+模型不能只是一段定义。
+
+每个模型至少要被拆成：
+
+- `model_id`
+- `model_type`
+- `pipeline_position`
+- 核心问题
+- 核心机制
+- 输入类型
+- 输出类型
+- 适用场景
+- 不适用场景
+- 负向触发条件
+- 常见误用
+- 失败信号
+- 稳固性等级
+- 输出契约
+
+结构治理让模型既能被人审，也能被机器读取。
+
+### 4.3 调用治理
+
+模型进入系统后，不能默认“能用就用”。
+
+每个模型都必须回答：
+
+- 什么输入应该调用它；
+- 什么输入不该调用它；
+- 是否必须先经过其他模型；
+- 是否只能在某个流程阶段使用；
+- 是否需要重型分析门槛；
+- 是否存在 hard no-call 条件；
+- 是否存在 explicit analysis override。
+
+这就是 selector 的职责。
+
+### 4.4 输出治理
+
+模型输出不能随意发挥。
+
+以 QPI 为例，它不是简单输出“这是 Question / Problem / Issue”，而是必须围绕主体、场景、责任范围、期望现实落差、主导稀缺物、分类置信度、证据缺口、误分类风险、下一步候选模型等字段工作。
+
+以思想考古学为例，它不能无限哲学化，而是必须说明是否应该调用、为什么调用、最多下潜到哪层、哪些层需要分析、什么时候停止。
+
+### 4.5 边界治理
+
+解释力强的模型更容易被滥用。
+
+典型误用包括：
+
+- 暴力降维：把复杂 Issue 当成简单 Problem；
+- 恶意升维：把简单执行任务夸大成复杂课题；
+- 手段错配：本该查资料，却启动深度模型；本该组织协商，却只做文档润色；
+- 认知重工业化：一个轻量问题被多模型、多智能体、深层考古压爆。
+
+边界治理不是削弱模型，而是让模型该用时有力，不该用时安静。
+
+### 4.6 生命周期治理
+
+模型不能因为 JSON 能解析、schema 通过、demo 能跑，就升级为 stable。
+
+升级至少需要经过：
+
+- evidence review；
+- content review；
+- regression review；
+- selector review；
+- Owner / CCRA review。
+
+当前 QPI 和思想考古学仍保持：
+
+```text
+status: draft
+stability_level: B
+regression_status: pending
+```
+
+`draft-callable` 只能作为评审报告语言，不能替代模型生命周期字段。
+
+## 5. 文件身份治理
+
+项目中的文件应按身份区分，而不是都视为同等资产。
+
+| 文件身份 | 是否长期保留 | 典型路径 | 作用 |
+| --- | --- | --- | --- |
+| Canonical source of truth | 是 | `models/*.model.json`, `cards/*.md`, `sources/*.json`, `tests/*.regression.json`, `selector/*.json` | 模型本体、来源、测试、调用规则 |
+| Stable governance docs | 是 | `docs/*.md`, `knowledge_assets/*.md` | 长期规则、协议、解释层 |
+| Generated / derived artifacts | 可重建，但可保留报告 | `models/model_index.json`, `cards/card_index.md`, `reports/*_report*.md` | 检查、导航、验证结果 |
+| Round / review artifacts | 阶段归档 | `ccra_review_bundle/round-*`, `reports/Codex*.md` | 交接和审核证据 |
+| Temporary / cache files | 不应提交 | `__pycache__/`, `*.pyc`, 临时 zip 展开目录 | 本地运行产物 |
+
+判断标准：
+
+```text
+回答“以后一直怎么做”的文档，可以进入 docs/ 或 knowledge_assets/。
+回答“这轮做了什么、哪些 PASS/FAIL”的文档，应留在 reports/ 或 ccra_review_bundle/。
+```
+
+## 6. 主要文件层
+
+### 6.1 来源层
+
+用途：回答“模型从哪里来”。
+
+典型文件：
+
+- `sources/source_articles.json`
+- `sources/source_excerpts.json`
+- `sources/evidence_coverage.matrix.json`
+
+### 6.2 人读模型层
+
+用途：让 Owner、CCRA 和协作者读懂模型。
+
+典型文件：
+
+- `cards/qpi.md`
+- `cards/intellectual_archaeology.md`
+- `cards/card_index.md`
+
+### 6.3 机器模型层
+
+用途：让 selector、validator、未来运行时读取模型。
+
+典型文件：
+
+- `models/qpi.model.json`
+- `models/intellectual_archaeology.model.json`
+- `models/model_index.json`
+
+### 6.4 契约与规则层
+
+用途：约束模型卡、输出字段、数据结构和调用规则。
+
+典型文件：
+
+- `schemas/model_card.schema.json`
+- `docs/DATA_CONTRACT.md`
+- `docs/QPI_CONTEXTUAL_ROUTING_RULES.md`
+- `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md`
+- `docs/DECISIONS.md`
+
+### 6.5 Selector 层
+
+用途：决定当前输入该调用哪些模型，以及不该调用哪些模型。
+
+典型文件：
+
+- `selector/selector_rules.json`
+- `selector/selector_examples.json`
+- `selector/selector_calibration_inputs.json`
+- `selector/qpi_case_digests.json`
+- `scripts/run_selector_demo.py`
+- `scripts/run_selector_regression.py`
+- `scripts/run_selector_calibration_smoke.py`
+
+### 6.6 Regression 层
+
+用途：保护模型边界，避免以后修改规则时把模型改坏。
+
+典型文件：
+
+- `tests/qpi.regression.json`
+- `tests/intellectual_archaeology.regression.json`
+- `tests/regression_cases.json`
+
+### 6.7 Validation 层
+
+用途：机械检查文件是否一致、字段是否完整、index 是否漂移、模型卡是否同步。
+
+典型文件：
+
+- `scripts/validate_model_library.py`
+- `scripts/check_card_contract.py`
+- `scripts/check_model_card_sync.py`
+- `scripts/rebuild_indexes.py`
+- `reports/validation_report.md`
+- `reports/index_rebuild_report.md`
+- `reports/model_card_sync_report_v0.2.md`
+
+### 6.8 Review Bundle 层
+
+用途：每轮把 Codex 工作打包给 CCRA / GPT 审核，避免散文件上传。
+
+典型文件：
+
+- `ccra_review_bundle/round-XX_YYYY-MM-DD_topic/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md`
+- `ccra_review_bundle/round-XX_YYYY-MM-DD_topic/BUNDLE_FILE_MANIFEST.md`
+- `ccra_review_bundle/round-XX_YYYY-MM-DD_topic/optional_raw_changed_files.zip`
+
+Review bundle 是交接层，不是长期核心资产。
+
+## 7. Selector 机制
+
+Selector 是模型库的入口调度器和误召回防火墙。
+
+它不负责回答问题。它负责判断：
+
+- 当前输入是否需要模型加工；
+- 如果需要，优先调用哪些模型；
+- 哪些模型应该被拒绝；
+- 拒绝理由是什么；
+- 是否命中 no-call；
+- 每个模型的分数、触发信号、惩罚项是什么。
+
+当前 selector 仍然是 rule-based，不是 LLM selector。
+
+基本流程：
+
+```text
+输入
+-> 检查 hard no-call
+-> 检查 explicit analysis override
+-> 检查模型触发词
+-> 检查复杂度信号
+-> 检查模型特定 gate
+-> 计算 score
+-> 输出 selected / rejected models
+```
+
+### 7.1 为什么当前不用 LLM selector
+
+当前阶段最重要的是可审计。
+
+LLM selector 可能更灵活，但会带来：
+
+- 为什么选这个模型说不清；
+- 为什么拒绝另一个模型说不清；
+- 修改后是否破坏边界不好测；
+- 容易把所有复杂问题交给重型模型；
+- 不利于 Codex 本地测试和回归。
+
+规则 selector 更保守，但更可控。
+
+### 7.2 Selector 的核心价值
+
+Selector 保护三件事：
+
+1. 防止不该调用时调用：明确事实查询、轻量改写、直接执行任务不应启动 QPI 或思想考古。
+2. 防止重型模型过早进入：思想考古学不应仅因出现“底层”“模型”“哲学”等词就被召回。
+3. 让模型组合可解释：未来不是一个模型回答所有问题，而是多个模型按流程协作。
+
+## 8. Regression 机制
+
+Regression 在本项目中不是普通单元测试，而是模型边界保护机制。
+
+它要回答：
+
+- 该调用模型时是否调用；
+- 不该调用模型时是否拒绝；
+- Q / P / I / mixed / no-call 是否被误判；
+- mixed 输入是否暴露证据缺口；
+- 是否出现暴力降维；
+- 是否出现恶意升维；
+- 是否把轻量问题过度重型化；
+- 是否把深度模型误召回；
+- 修改 selector 后，过去关键边界是否被破坏。
+
+Regression case 是“防止系统退化的钉子”，不是普通示例。
+
+至少覆盖：
+
+- `positive`
+- `boundary`
+- `misuse`
+- `no_call`
+- `selector_gate`
+- `pipeline`
+
+## 9. Digest、Calibration、Regression 的区别
+
+以 QPI 为例，Owner 提供人工素材后，Codex 将材料拆为 `.cases.md`、digest、calibration、regression 四层。
+
+### 9.1 `.cases.md`
+
+人读的案例审阅稿。
+
+作用：
+
+- 保留原始案例；
+- 保留 Owner / GPT 审查判断；
+- 保留人能看懂的推理；
+- 便于后续人工复核。
+
+### 9.2 Case Digest
+
+压缩后的结构化案例摘要。
+
+作用：
+
+- 让案例变得可检索、可审计；
+- 保留核心分类、主导稀缺、误用风险、边界说明；
+- 作为 selector / regression 的候选素材池。
+
+Digest 是案例资产层，不是最终测试层。
+
+### 9.3 Calibration Input
+
+给 selector 调参和校准用的输入。
+
+作用：
+
+- 告诉 selector 哪些输入应该选 QPI；
+- 哪些输入应该 no-call；
+- 哪些输入应该低优先级；
+- 哪些输入需要先 QPI 再进入思想考古；
+- 哪些输入容易误召回。
+
+Calibration 是“调方向”。
+
+### 9.4 Regression Case
+
+高价值边界测试。
+
+作用：
+
+- 以后每次改规则都要检查；
+- 防止关键边界被破坏；
+- 不要求覆盖所有案例；
+- 只保留最容易出错、最值得保护的判断。
+
+Regression 是“守底线”。
+
+## 10. QPI 调用机制
+
+QPI 不是最终答案模型，而是入口路由模型。
+
+它处理的不是“怎么解决问题”，而是：
+
+```text
+当前输入到底是什么性质的问题？
+```
+
+运行方式：
+
+```text
+用户输入
+-> selector 判断是否需要 QPI
+-> QPI 分析主体、场景、责任范围、期望—现实落差
+-> 判断主导稀缺物
+-> 输出 Q / P / I / mixed / no-call
+-> 给出证据缺口、误分类风险、下一步模型候选
+-> 进入后续模型或直接行动
+```
+
+QPI 的五种结果：
+
+| QPI 输出 | 含义 | 系统下一步 |
+| --- | --- | --- |
+| Question | 数据不足 | 搜索、查证、补信息 |
+| Problem | 路径、方法或资源不足 | 做方案、流程、SOP、资源约束分析 |
+| Issue | 共识、秩序、确定性或治理结构不足 | 做多视角分析、动态权衡、思想考古或冲突处理 |
+| mixed | 多类稀缺同时存在 | 拆分问题，分别路由 |
+| no-call | 不需要问题定性 | 直接执行、改写、翻译、查事实、整理格式 |
+
+QPI 不应直接输出组织、人事、法律、财务、运营解决方案。
+
+它最多回答：
+
+- 这是什么类型的问题；
+- 为什么这样分类；
+- 证据是否足够；
+- 误判风险是什么；
+- 下一步应该进入哪类处理。
+
+## 11. 思想考古学调用机制
+
+思想考古学不是默认分析流程，而是深度建模模型。
+
+适合使用的条件：
+
+- 问题表层现象很多，但底层假设不清；
+- 需要识别概念、模型或判断背后的深层机制；
+- QPI 已判断这是中重型 Problem / Issue；
+- 继续下潜会改变判断、路径、验证方式或行动边界。
+
+不适合：
+
+- 明确事实查询；
+- 低风险轻量改写；
+- 用户只需要直接执行；
+- 材料不足，无法区分真实假设和空泛哲学化表达。
+
+关键原则：
+
+```text
+最小充分下潜。
+如果继续下潜不再改变判断、路径、验证方式或行动边界，就应停止。
+```
+
+未来系统不是“QPI 一调用就自动思想考古”，而是：
+
+```text
+QPI 先判断问题性质
+-> selector 判断是否满足思想考古 depth gate
+-> 思想考古只分析必要层级
+-> 达到充分深度就停止
+```
+
+## 12. 未来新增模型的最低资产结构
+
+每个未来模型都不应只是一个概念。
+
+最低需要七类资产：
+
+1. 人读解释：`cards/*.md`
+2. 机器可读定义：`models/*.model.json`
+3. 来源证据：`sources/source_articles.json`、`sources/source_excerpts.json`
+4. 调用规则：`selector/selector_rules.json`、`selector/selector_calibration_inputs.json`
+5. 输出契约：模型 JSON 中的 `structured_output_contract`
+6. 回归案例：`tests/*.regression.json`
+7. 审核与版本状态：reports、review bundle、model/card index
+
+新增模型不得用来绕过当前模型边界未稳定的问题。
+
+## 13. 未来运行时调用流程
+
+未来真正运行时，系统可按以下流程工作：
+
+```text
+1. 用户输入问题 / 话题 / 文本 / 任务
+
+2. 输入预处理
+   - 识别语言
+   - 判断是否是直接执行任务
+   - 判断是否需要认知加工
+   - 抽取显性任务目标
+
+3. Selector 路由
+   - 先检查 hard no-call
+   - 再检查 explicit analysis override
+   - 再根据模型触发条件打分
+   - 输出 selected / rejected models、分数和理由
+
+4. 前置模型
+   - 常见情况下先调用 QPI
+   - QPI 判断 Q / P / I / mixed / no-call
+   - 输出下一步模型候选
+
+5. 深度或专项模型
+   - 如果是中重型 Problem / Issue，可能进入思想考古
+   - 不满足 gate 的模型不得调用
+
+6. 多模型结果汇总
+   - 比较不同模型输出
+   - 标记冲突
+   - 标记证据缺口
+   - 标记适用边界
+
+7. 输出给用户
+   - 包含判断路径、模型调用理由、边界、下一步动作
+
+8. 记录反馈
+   - 用户纠正分类或边界
+   - 重要反馈进入 calibration 或 regression
+```
+
+## 14. Codex 运作原则
+
+后续 Codex 应遵守：
+
+1. 不把 GPT 规划直接当本地规则，必须先本地化为 schema、workflow、validator、index。
+2. 不把文章摘要当模型抽取。
+3. 不把模型卡完整当成模型稳定。
+4. 不把 selector demo pass 当成内容稳定。
+5. 不把 validation pass 当成 Owner 审核通过。
+6. 不因为素材增多就无限扩展 regression。
+7. 不把 calibration 全部升级成 regression。
+8. 不新增模型来解决当前模型边界没稳定的问题。
+9. 每个新增文件必须说明身份：canonical / generated / report / temporary。
+10. 每轮交接必须用 review bundle，不让 Owner / CCRA 面对散乱文件。
+
+## 15. 与 GPT 知识库同步的关系
+
+`knowledge_assets/` 是长期解释层。
+
+Owner 可以手动将其中稳定文档同步到 GPT 知识库。评审包不应重复打包 `knowledge_assets/`，除非某轮评审明确要求审核长期资产本身。
+
+当前规则：
+
+- 长期机制说明放在 `knowledge_assets/`；
+- 当前执行资产放在 `models/`、`cards/`、`selector/`、`tests/`、`scripts/`；
+- 每轮评审资料放在 `ccra_review_bundle/round-*`；
+- `optional_raw_changed_files.zip` 应保留源路径，避免扁平化覆盖；
+- `knowledge_assets/` 默认不放入评审 zip，由 Owner 自行同步到 GPT 知识库。
+
+## 16. 结论
+
+本项目不是把少量文章堆进知识库。
+
+它在做的是：
+
+```text
+把文章形式存在的个人认知模型
+转化为可被 AI 软件稳定调用的模型资产库；
+同时建立调用门、拒绝门、输出契约、边界测试和人机交接机制。
+```
+
+QPI 是第一个压力测试样板。
+
+思想考古学是第二个深度模型样板。
+
+Selector 是模型调用的守门员。
+
+Regression 是模型边界的质检夹具。
+
+Model card 是人和机器之间的共同契约。
+
+Source / evidence 是模型不漂移的锚点。
+
+Review bundle 是 Codex、CCRA、Owner 之间的交接机制。
diff --git a/knowledge_assets/README.md b/knowledge_assets/README.md
index 21da347..91b45ce 100644
--- a/knowledge_assets/README.md
+++ b/knowledge_assets/README.md
@@ -12,5 +12,18 @@ Rules:
 - Keep session-level validation and handoff documents in `reports/`.
 - Do not put version numbers in filenames; record version information inside the document.
 - Store long-term CCRA quality gates and handoff protocols here, but do not store per-round review bundles or command logs here.
+- Store durable data-governance and model-invocation explanations here when they answer "how this model library should keep working", not "what happened in this review round".
+- Review bundles should not include `knowledge_assets/` by default; the project owner manually syncs stable knowledge assets into GPT knowledge storage.
+
+Current reading order:
+
+- `00_用户背景与产品上下文.md`
+- `01_核心模型地图.md`
+- `02_模型卡结构规范.md`
+- `03_核心模型抽取样板.md`
+- `06_模型稳固性评级规则.md`
+- `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`
 
 See `docs/KNOWLEDGE_ASSET_RULES.md`.
diff --git a/models/model_index.json b/models/model_index.json
index 9769273..9a41e2e 100644
--- a/models/model_index.json
+++ b/models/model_index.json
@@ -26,11 +26,11 @@
       "card_file": "cards/qpi.md",
       "source_article_count": 3,
       "source_evidence_count": 10,
-      "regression_case_count": 46,
+      "regression_case_count": 52,
       "stability_level": "B",
       "regression_status": "pending",
       "status": "draft",
-      "last_updated": "2026-06-16"
+      "last_updated": "2026-06-17"
     }
   ]
 }
diff --git a/models/qpi.model.json b/models/qpi.model.json
index b832f47..8f159a3 100644
--- a/models/qpi.model.json
+++ b/models/qpi.model.json
@@ -239,5 +239,5 @@
   ],
   "productization_notes": "QPI 应作为问题回答系统的前置路由模型，用于防止系统在问题类型错误的情况下直接给答案。",
   "version": "0.1",
-  "last_updated": "2026-06-16"
+  "last_updated": "2026-06-17"
 }
diff --git a/reports/Codex新会话交接文档_Round03.1评审后续_2026-06-17.md b/reports/Codex新会话交接文档_Round03.1评审后续_2026-06-17.md
new file mode 100644
index 0000000..2280438
--- /dev/null
+++ b/reports/Codex新会话交接文档_Round03.1评审后续_2026-06-17.md
@@ -0,0 +1,151 @@
+# Codex 新会话交接文档：Round 03.1 评审后续
+
+Date: 2026-06-17
+
+Repository: `C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong`
+
+Current phase: `model_library_mvp`
+
+## 1. 新会话目标
+
+下一会话预计处理 GPT 对 Round 03.1 的评审结果。
+
+请先读取本交接文档，再读取 Round 03.1 评审包和 GPT 返回意见。
+
+## 2. 当前模型状态
+
+不要升级生命周期状态，除非 Owner 明确要求。
+
+当前仍为：
+
+```text
+qpi: draft / B / pending
+intellectual_archaeology: draft / B / pending
+```
+
+允许使用 `draft-callable` 作为评审报告语言，但不能把它写成模型 JSON 的正式 `status`。
+
+硬边界仍然有效：
+
+- 不新增第三模型；
+- 不升级 stable；
+- 不引入 LLM selector；
+- 不做完整问答系统；
+- 不做 RAG / vector database；
+- 不做前端、后端、用户系统或平台化扩展。
+
+## 3. Round 03.1 已完成内容
+
+Round 03.1 是对 Round 03 的小修补，不是新一轮大扩展。
+
+已完成：
+
+- 修复 selector 过度选择 QPI 的问题；
+- QPI 不再能仅凭 `base_score + selection_priority` 被选中；
+- 增加 direct-execution no-call signals；
+- 保留 explicit analysis override；
+- 新增 `scripts/run_selector_calibration_smoke.py`；
+- QPI regression 从 46 条扩展到 52 条；
+- aggregate regression 从 63 条扩展到 69 条；
+- selector calibration inputs 从 83 条扩展到 85 条；
+- `qpi_case_digests.json` 字段规范化：
+  - `misframing_risks` -> `misclassification_risk`
+  - `mixed_or_multi_perspective` -> `qpi_complexity_pattern`
+  - multi-perspective / inter-viewpoint case 必须有 `classification_by_viewpoint` 或 `viewpoint_summary`
+- `qpi.md`、`qpi.model.json`、`content_review_report_v0.2.md` 同步 stale 状态；
+- Round 03.1 review bundle 已生成；
+- Round 03.1 zip 保留源路径，不再扁平化；
+- Round 03.1 zip 默认不包含 `knowledge_assets/`。
+
+## 4. 本次新补的长期资产和规则
+
+新增长期资产：
+
+- `knowledge_assets/09_数据治理与模型调用机制说明.md`
+
+该文件来自 GPT 成果 `CCRA_数据治理与模型调用机制说明_v0.1.md` 的整理版，但不是原文搬运。它删除了对话式回复和临时评审上下文，只保留长期可复用的机制说明。
+
+新增规则文件：
+
+- `docs/FILE_TAXONOMY.md`
+
+定位：
+
+- `docs/FILE_TAXONOMY.md` 管全仓库文件身份；
+- `docs/KNOWLEDGE_ASSET_RULES.md` 只管 `knowledge_assets/`；
+- `docs/DECISIONS.md` 记录已接受的结构决策。
+
+文件身份四类：
+
+- canonical source of truth；
+- generated / derived；
+- review archive；
+- temporary / local runtime。
+
+## 5. Round 03.1 评审包位置
+
+```text
+ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/
+```
+
+建议提交给 GPT 的读取顺序：
+
+1. `00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md`
+2. `01_PATCH_MATRIX.md`
+3. `02_CURRENT_ASSET_PACK.md`
+4. `03_VALIDATION_AND_COMMAND_LOG.md`
+5. `04_REVIEW_QUESTIONS_FOR_GPT.md`
+6. `optional_raw_changed_files.zip` only if exact file inspection is needed
+
+注意：
+
+- `optional_raw_changed_files.zip` 已保留 source-relative paths；
+- zip 中 `knowledge_assets` 条目为 0；
+- Owner 会手动同步 `knowledge_assets/09_数据治理与模型调用机制说明.md` 到 GPT 知识库；
+- 不要为了评审 Round 03.1 把 `knowledge_assets/` 加回 zip。
+
+## 6. 当前验证结果
+
+最近验证通过：
+
+```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
+```
+
+结果：
+
+- Index check: PASS
+- Unit tests: PASS, 17 tests
+- Model library validation: PASS
+- Card contract: PASS
+- Selector demo: PASS
+- Selector regression: PASS
+- Selector calibration smoke: PASS
+- Model/card sync: PASS
+
+## 7. 新会话处理 GPT 评审结果时的建议流程
+
+1. 先判断 GPT 结论是 pass / revise / block。
+2. 如果是 revise，逐条映射到具体文件，不要扩大 scope。
+3. selector 相关问题优先用 regression 或 calibration smoke 固化。
+4. digest 字段问题优先改 validator，防止回漂。
+5. 不要把 calibration 全部升级成 regression。
+6. 不要新增模型来解决当前 QPI 或思想考古边界问题。
+7. 每次改完后重新运行完整验证链。
+8. 若要生成新评审包，继续放在 `ccra_review_bundle/round-03.1_...` 或新建清楚的后续小修补目录，不要覆盖旧证据。
+
+## 8. 需要特别避免
+
+- 不要把 GPT 长文原样放入 `knowledge_assets/`；
+- 不要把 `knowledge_assets/` 放入 Round 03.1 raw zip；
+- 不要创建扁平 zip；
+- 不要提交 `__pycache__/` 或 `*.pyc`；
+- 不要把 `draft-callable` 写成模型生命周期状态；
+- 不要把 validation pass 解释为 Owner/CCRA 内容通过。
diff --git a/reports/content_review_report_v0.2.md b/reports/content_review_report_v0.2.md
index 1f05ac9..c9801cc 100644
--- a/reports/content_review_report_v0.2.md
+++ b/reports/content_review_report_v0.2.md
@@ -2,6 +2,8 @@
 
 Date: 2026-06-16
 
+Status note: this report is a pre-case-promotion review snapshot. It remains useful for the v0.2 evidence / contract / selector baseline, but its regression counts do not reflect the Round 03 / 03.1 QPI owner-reviewed case promotion. Current QPI regression counts are tracked in `tests/qpi.regression.json`, `models/model_index.json`, and the Round 03.1 review bundle.
+
 ## 1. 本轮修改摘要
 
 本轮没有扩展第三模型，没有接完整问题回答系统，没有引入 LLM selector，也没有升级 stable。
@@ -109,6 +111,8 @@ Coverage:
 - 已覆盖误用、防误召回、no-call 和 pipeline gate。
 - 仍需人工审查用例真实性和遗漏边界。
 
+Round 03 / 03.1 update: QPI has since expanded to 52 regression cases after owner-reviewed case promotion and selector/no-call repair. This v0.2 table is retained as a historical baseline, not the current count.
+
 ## 6. Selector Regression 结论
 
 Selector v0.2 仍为规则 selector。
diff --git a/reports/selector_calibration_smoke_report.md b/reports/selector_calibration_smoke_report.md
new file mode 100644
index 0000000..98cc8f4
--- /dev/null
+++ b/reports/selector_calibration_smoke_report.md
@@ -0,0 +1,96 @@
+# Selector Calibration Smoke Report
+
+Status: `PASS`
+
+Command: `python scripts/run_selector_calibration_smoke.py`
+
+Calibration inputs checked: 85
+Failures: 0
+
+## Cases
+
+- `selector_calibration_fact_lookup_001`: PASS; expected=no_call; selected=[]; no_call=True
+- `selector_calibration_fact_lookup_002`: PASS; expected=no_call; selected=[]; no_call=True
+- `selector_calibration_rewrite_001`: PASS; expected=no_call; selected=[]; no_call=True
+- `selector_calibration_translation_001`: PASS; expected=no_call; selected=[]; no_call=True
+- `selector_calibration_direct_execution_001`: PASS; expected=no_call; selected=[]; no_call=True
+- `selector_calibration_qpi_only_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_only_002`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_insufficient_context_001`: PASS; expected=select_qpi_low_confidence; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_intra_frame_mixed_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_governance_load_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_ia_after_qpi_001`: PASS; expected=select_intellectual_archaeology; selected=['intellectual_archaeology', 'qpi']; no_call=False
+- `selector_calibration_ia_after_qpi_002`: PASS; expected=select_intellectual_archaeology; selected=['intellectual_archaeology']; no_call=False
+- `selector_calibration_ia_model_extraction_001`: PASS; expected=select_intellectual_archaeology; selected=['intellectual_archaeology', 'qpi']; no_call=False
+- `selector_calibration_ia_model_extraction_002`: PASS; expected=select_intellectual_archaeology; selected=['intellectual_archaeology', 'qpi']; no_call=False
+- `selector_calibration_false_positive_deep_word_001`: PASS; expected=no_call; selected=[]; no_call=True
+- `selector_calibration_false_positive_model_word_001`: PASS; expected=no_call; selected=[]; no_call=True
+- `selector_calibration_false_positive_philosophy_001`: PASS; expected=no_call; selected=[]; no_call=True
+- `selector_calibration_override_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_pipeline_001`: PASS; expected=select_qpi_reject_ia; selected=['qpi']; no_call=False
+- `selector_calibration_pipeline_002`: PASS; expected=select_intellectual_archaeology; selected=['intellectual_archaeology', 'qpi']; no_call=False
+- `selector_calibration_qpi_flow_entry_point_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_no_simulation_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_local_truth_global_structure_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_stop_gate_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_intra_frame_mixed_flow_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_complexity_placement_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_psych_mechanism_ambiguity_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_label_as_identity_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_single_factor_totalization_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_one_time_fix_trap_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_external_authority_boundary_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_time_scale_scope_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_mismatch_diagnostics_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_one_person_issue_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_org_hard_resource_documentation_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_org_credential_continuity_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_org_incentive_backlash_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_org_role_authority_mismatch_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_org_pattern_level_issue_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_org_untrusted_data_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_org_workaround_translation_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_org_low_cost_indicator_survival_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_academic_ai_evidence_boundary_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_academic_staffing_deadlock_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_academic_policy_memory_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_academic_strategy_myopia_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_academic_resource_reuse_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_academic_outcome_excuse_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_academic_digital_governance_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_academic_bottom_line_control_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_employment_reverse_accountability_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_employment_credential_compliance_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_employment_reported_metric_legitimacy_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_employment_overpromising_pipeline_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_employment_metric_credibility_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_employment_asset_integration_boundary_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_employment_authority_transfer_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_employment_transactional_education_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_engineering_target_authenticity_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_engineering_equipment_solutionism_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_engineering_shortcut_debt_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_engineering_credential_integrity_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_engineering_market_closure_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_engineering_micro_control_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_engineering_asset_liability_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_engineering_personnel_transition_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_international_compliance_retention_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_international_capacity_gate_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_international_logistics_no_call_001`: PASS; expected=no_call_or_low_priority; selected=[]; no_call=True
+- `selector_calibration_qpi_international_role_inflation_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_international_viewpoint_divergence_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_international_metric_distortion_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_international_pricing_trust_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_international_capability_institutionalization_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_international_asset_expansion_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_research_identity_simulation_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_research_accounting_reduction_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_research_transactional_assets_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_research_ranking_trap_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_research_talent_role_mismatch_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_research_hard_capacity_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_research_safety_accountability_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_qpi_research_penalty_integrity_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
+- `selector_calibration_direct_summary_no_call_001`: PASS; expected=no_call; selected=[]; no_call=True
+- `selector_calibration_analysis_override_should_call_001`: PASS; expected=select_qpi; selected=['qpi']; no_call=False
diff --git a/reports/selector_regression_report_v0.2.md b/reports/selector_regression_report_v0.2.md
index 5fef1bf..dbce455 100644
--- a/reports/selector_regression_report_v0.2.md
+++ b/reports/selector_regression_report_v0.2.md
@@ -2,7 +2,7 @@
 
 Status: `PASS`
 
-Cases checked: 10
+Cases checked: 13
 Failures: 0
 
 ## Cases
@@ -17,3 +17,6 @@ Failures: 0
 - `case_qpi_selector_gate_fact_001`: PASS; selected=[]; no_call=True
 - `case_qpi_pipeline_before_ia_001`: PASS; selected=['qpi']; no_call=False
 - `case_qpi_disappointment_mismatch_diagnostics_001`: PASS; selected=['qpi']; no_call=False
+- `case_qpi_international_logistics_no_call_001`: PASS; selected=[]; no_call=True
+- `case_qpi_direct_summary_no_call_001`: PASS; selected=[]; no_call=True
+- `case_qpi_analysis_override_should_call_001`: PASS; selected=['qpi']; no_call=False
diff --git a/scripts/run_selector_calibration_smoke.py b/scripts/run_selector_calibration_smoke.py
new file mode 100644
index 0000000..4e05681
--- /dev/null
+++ b/scripts/run_selector_calibration_smoke.py
@@ -0,0 +1,101 @@
+import json
+import sys
+from pathlib import Path
+
+from run_selector_demo import load_selector_rules, recommend
+
+
+def read_json(path):
+    return json.loads(Path(path).read_text(encoding="utf-8"))
+
+
+def selected_model_ids(result):
+    return [item["model_id"] for item in result.get("selected_models", [])]
+
+
+def has_ia_gate(input_text, selector_rules):
+    global_rules = selector_rules.get("global_rules", {})
+    heavy_signals = global_rules.get("ia_heavy_signals", [])
+    return any(signal in input_text for signal in heavy_signals) or "QPI 已判断" in input_text
+
+
+def evaluate_input(root, selector_rules, item):
+    result = recommend(root, item["input"])
+    selected_ids = selected_model_ids(result)
+    expected = item.get("expected_selector_behavior")
+    errors = []
+
+    if expected in {"no_call", "no_call_or_low_priority"} and "qpi" in selected_ids:
+        errors.append("expected no QPI selection")
+
+    if expected in {"select_qpi", "select_qpi_low_confidence", "select_qpi_reject_ia"}:
+        if "qpi" not in selected_ids:
+            errors.append("expected QPI selection")
+
+    if expected == "select_qpi_reject_ia" and "intellectual_archaeology" in selected_ids:
+        errors.append("expected IA rejection")
+
+    if expected == "select_intellectual_archaeology":
+        if "intellectual_archaeology" not in selected_ids:
+            errors.append("expected IA selection")
+        if not has_ia_gate(item["input"], selector_rules):
+            errors.append("IA selected expectation lacks heavy-depth or QPI-completed gate")
+
+    return {
+        "case_id": item["case_id"],
+        "expected_selector_behavior": expected,
+        "selected_models": selected_ids,
+        "no_call": result.get("no_call"),
+        "errors": errors,
+    }
+
+
+def write_report(root, results):
+    report_path = root / "reports" / "selector_calibration_smoke_report.md"
+    failures = [result for result in results if result["errors"]]
+    lines = [
+        "# Selector Calibration Smoke Report",
+        "",
+        f"Status: `{'PASS' if not failures else 'FAIL'}`",
+        "",
+        "Command: `python scripts/run_selector_calibration_smoke.py`",
+        "",
+        f"Calibration inputs checked: {len(results)}",
+        f"Failures: {len(failures)}",
+        "",
+        "## Cases",
+        "",
+    ]
+    for result in results:
+        status = "PASS" if not result["errors"] else "FAIL"
+        lines.append(
+            f"- `{result['case_id']}`: {status}; expected={result['expected_selector_behavior']}; "
+            f"selected={result['selected_models']}; no_call={result['no_call']}"
+        )
+        for error in result["errors"]:
+            lines.append(f"  - {error}")
+    report_path.write_text("\n".join(lines) + "\n", encoding="utf-8")
+    return report_path
+
+
+def main():
+    root = Path(__file__).resolve().parents[1]
+    selector_rules = load_selector_rules(root)
+    calibration = read_json(root / "selector" / "selector_calibration_inputs.json")
+    results = [
+        evaluate_input(root, selector_rules, item)
+        for item in calibration.get("inputs", [])
+    ]
+    report_path = write_report(root, results)
+    print(f"selector calibration smoke report written to {report_path}")
+    failures = [result for result in results if result["errors"]]
+    if failures:
+        for result in failures:
+            print(f"ERROR: {result['case_id']}: {'; '.join(result['errors'])}")
+        return 1
+    print("selector calibration smoke passed")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())
diff --git a/scripts/run_selector_demo.py b/scripts/run_selector_demo.py
index a06ecb5..a8a295d 100644
--- a/scripts/run_selector_demo.py
+++ b/scripts/run_selector_demo.py
@@ -28,7 +28,9 @@ def has_analysis_override(user_input, global_rules):
 
 
 def hard_no_call_hits(user_input, global_rules):
-    return hit_any(user_input, global_rules.get("hard_no_call_signals", []))
+    signals = list(global_rules.get("hard_no_call_signals", []))
+    signals.extend(global_rules.get("direct_execution_no_call_signals", []))
+    return hit_any(user_input, signals)
 
 
 def score_model(model, model_rule, global_rules, user_input, task_type="", pipeline_position=""):
@@ -39,7 +41,7 @@ def score_model(model, model_rule, global_rules, user_input, task_type="", pipel
     penalties = []
 
     negative_hits = hit_any(user_input, model_rule.get("negative_triggers", [])) + hit_any(user_input, model.get("negative_triggers", []))
-    if negative_hits:
+    if negative_hits and not has_analysis_override(user_input, global_rules):
         penalty_key = "model_negative_penalty_qpi" if model_id == "qpi" else "model_negative_penalty_default"
         score -= weights.get(penalty_key, 0.5)
         penalties.append("negative trigger: " + "、".join(sorted(set(negative_hits))[:4]))
@@ -74,6 +76,19 @@ def score_model(model, model_rule, global_rules, user_input, task_type="", pipel
     if model_id == "qpi" and qpi_gate_hits:
         score += weights.get("qpi_gate_bonus", 0.25)
         reasons.append("QPI problem-definition gate matched")
+    if model_id == "qpi":
+        has_positive_signal = bool(
+            trigger_hits
+            or input_hits
+            or complexity_hits
+            or qpi_gate_hits
+            or has_analysis_override(user_input, global_rules)
+            or task_type in {"problem_definition", "question_analysis"}
+            or pipeline_position in {"pre_analysis", "problem_definition"}
+        )
+        if not has_positive_signal:
+            score -= weights.get("qpi_missing_positive_signal_penalty", 0.25)
+            penalties.append("QPI positive signal missing")
     if model_id == "qpi" and "QPI 已判断" in user_input:
         score -= weights.get("qpi_already_completed_penalty", 0.25)
         penalties.append("QPI already completed")
diff --git a/scripts/validate_model_library.py b/scripts/validate_model_library.py
index f4fc813..49716db 100644
--- a/scripts/validate_model_library.py
+++ b/scripts/validate_model_library.py
@@ -69,6 +69,7 @@ EXPECTED_DOMINANT_SCARCITY_VALUES = {"data", "path_resource", "consensus_order",
 EXPECTED_MAX_DEPTH_VALUES = {"application", "domain", "process", "purpose", "core_mechanism", "human_capability", "philosophical_bedrock", "no_call", "not_applicable"}
 EVALUATION_MODE_VALUES = {"manual", "keyword", "structured", "semantic"}
 STATUS_VALUES = {"draft", "review", "reviewed", "callable", "stable", "archived", "deprecated", "draft_pre_contract"}
+QPI_COMPLEXITY_PATTERN_VALUES = {"not_mixed", "intra_frame_mixed", "inter_viewpoint_divergence"}
 
 MODEL_SPECIFIC_STRUCTURED_OUTPUT_FIELDS = {
     "qpi": [
@@ -242,6 +243,39 @@ def validate_structured_output_contract(model, label):
     return errors
 
 
+def validate_qpi_case_digests(root):
+    path = root / "selector" / "qpi_case_digests.json"
+    if not path.exists():
+        return []
+
+    data, errors = read_json(path)
+    if errors:
+        return errors
+    if not isinstance(data, dict) or not isinstance(data.get("cases"), list):
+        return ["selector/qpi_case_digests.json must contain list field cases"]
+
+    errors = []
+    for case in data["cases"]:
+        case_id = case.get("case_id", "<missing>")
+        label = f"qpi case digest {case_id}"
+        if "misframing_risks" in case:
+            errors.append(f"{label} uses deprecated field misframing_risks; use misclassification_risk")
+        if "mixed_or_multi_perspective" in case:
+            errors.append(f"{label} uses deprecated field mixed_or_multi_perspective; use qpi_complexity_pattern")
+        if "misclassification_risk" not in case:
+            errors.append(f"{label} missing required field misclassification_risk")
+        pattern = case.get("qpi_complexity_pattern")
+        if pattern is None:
+            errors.append(f"{label} missing required field qpi_complexity_pattern")
+        elif pattern not in QPI_COMPLEXITY_PATTERN_VALUES:
+            errors.append(f"{label} field qpi_complexity_pattern has invalid value {pattern}")
+        if case.get("classification_scope") == "multi_perspective" or pattern == "inter_viewpoint_divergence":
+            has_viewpoint_detail = bool(case.get("classification_by_viewpoint")) or bool(case.get("viewpoint_summary"))
+            if not has_viewpoint_detail:
+                errors.append(f"{label} multi_perspective case requires classification_by_viewpoint or viewpoint_summary")
+    return errors
+
+
 def load_model_index(root):
     path = root / "models" / "model_index.json"
     data, errors = read_json(path)
@@ -281,6 +315,7 @@ def validate_library(root):
     errors.extend(article_errors)
     errors.extend(excerpt_errors)
     errors.extend(case_errors)
+    errors.extend(validate_qpi_case_digests(root))
 
     for article in source_articles:
         errors.extend(require_fields(article, SOURCE_ARTICLE_REQUIRED_FIELDS, f"source article {article.get('source_id', '<missing>')}"))
diff --git a/selector/README.md b/selector/README.md
index 9117155..89580d9 100644
--- a/selector/README.md
+++ b/selector/README.md
@@ -14,6 +14,9 @@ It should use simple matching rules:
 - Negative trigger first
 - No-call threshold
 - QPI-before-IA gate
+- QPI positive-signal gate
+- Direct-execution no-call signals
+- Calibration smoke checks
 
 Current files:
 
@@ -28,4 +31,13 @@ The executable demo is `scripts/run_selector_demo.py`.
 
 Selector regression is `scripts/run_selector_regression.py`.
 
+Selector calibration smoke check is `scripts/run_selector_calibration_smoke.py`.
+
 `qpi_case_digests.json` stores owner-reviewed QPI case digests that can feed selector calibration or later regression selection. It is not a model status upgrade and should not include unreviewed draft cases.
+
+Digest field notes:
+
+- `misclassification_risk` is the canonical digest field matching QPI's structured output contract.
+- `qpi_complexity_pattern` records judgment complexity: `not_mixed`, `intra_frame_mixed`, or `inter_viewpoint_divergence`.
+- `qpi_complexity_pattern=intra_frame_mixed` does not imply `classification=mixed`; `classification` is the final routing class, while `qpi_complexity_pattern` records the structure of the judgment.
+- Multi-perspective / inter-viewpoint cases require `classification_by_viewpoint` or `viewpoint_summary`.
diff --git a/selector/qpi_case_digests.json b/selector/qpi_case_digests.json
index fbc37eb..4ca6151 100644
--- a/selector/qpi_case_digests.json
+++ b/selector/qpi_case_digests.json
@@ -3,7 +3,175 @@
   "status": "owner_reviewed_incremental",
   "created_from": "reports/model_case_preprocessing/qpi/round-01/multiple_owner_reviewed_sources",
   "owner_review_source": "knowledge-vault/work/internal/强哥的思想宇宙/QPI案例审阅/QPI提炼审核/multiple_owner_reviewed_case_files",
-  "notes": "Owner-reviewed QPI case digests from incremental case review. These digests are calibration inputs, not CCRA-approved model evidence and not a model status upgrade.",
+  "notes": [
+    "O",
+    "w",
+    "n",
+    "e",
+    "r",
+    "-",
+    "r",
+    "e",
+    "v",
+    "i",
+    "e",
+    "w",
+    "e",
+    "d",
+    " ",
+    "Q",
+    "P",
+    "I",
+    " ",
+    "c",
+    "a",
+    "s",
+    "e",
+    " ",
+    "d",
+    "i",
+    "g",
+    "e",
+    "s",
+    "t",
+    "s",
+    " ",
+    "f",
+    "r",
+    "o",
+    "m",
+    " ",
+    "i",
+    "n",
+    "c",
+    "r",
+    "e",
+    "m",
+    "e",
+    "n",
+    "t",
+    "a",
+    "l",
+    " ",
+    "c",
+    "a",
+    "s",
+    "e",
+    " ",
+    "r",
+    "e",
+    "v",
+    "i",
+    "e",
+    "w",
+    ".",
+    " ",
+    "T",
+    "h",
+    "e",
+    "s",
+    "e",
+    " ",
+    "d",
+    "i",
+    "g",
+    "e",
+    "s",
+    "t",
+    "s",
+    " ",
+    "a",
+    "r",
+    "e",
+    " ",
+    "c",
+    "a",
+    "l",
+    "i",
+    "b",
+    "r",
+    "a",
+    "t",
+    "i",
+    "o",
+    "n",
+    " ",
+    "i",
+    "n",
+    "p",
+    "u",
+    "t",
+    "s",
+    ",",
+    " ",
+    "n",
+    "o",
+    "t",
+    " ",
+    "C",
+    "C",
+    "R",
+    "A",
+    "-",
+    "a",
+    "p",
+    "p",
+    "r",
+    "o",
+    "v",
+    "e",
+    "d",
+    " ",
+    "m",
+    "o",
+    "d",
+    "e",
+    "l",
+    " ",
+    "e",
+    "v",
+    "i",
+    "d",
+    "e",
+    "n",
+    "c",
+    "e",
+    " ",
+    "a",
+    "n",
+    "d",
+    " ",
+    "n",
+    "o",
+    "t",
+    " ",
+    "a",
+    " ",
+    "m",
+    "o",
+    "d",
+    "e",
+    "l",
+    " ",
+    "s",
+    "t",
+    "a",
+    "t",
+    "u",
+    "s",
+    " ",
+    "u",
+    "p",
+    "g",
+    "r",
+    "a",
+    "d",
+    "e",
+    ".",
+    "Round 03.1 normalized misframing_risks to misclassification_risk to match the QPI structured output contract.",
+    "Round 03.1 renamed mixed_or_multi_perspective to qpi_complexity_pattern; intra_frame_mixed does not imply classification=mixed.",
+    "For multi_perspective or inter_viewpoint_divergence cases, classification_by_viewpoint or viewpoint_summary is required."
+  ],
   "cases": [
     {
       "case_id": "qpi-flow-redesign-001",
@@ -21,19 +189,19 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "The surface task was automating outline review, but owner review confirmed that the real issue was earlier context engineering and entry-point governance.",
       "routing_notes": [
         "wrong automation entry point exposes context engineering failure",
         "stage authority and owner confirmation gate precede outline review",
         "use as supporting evidence rather than strongest independent case"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Use as supporting evidence for a context-engineering / entry-point governance calibration case.",
+      "misclassification_risk": [
         "tool_solutionism",
         "premature_classification",
         "violent_reduction"
       ],
-      "recommended_next_step": "Use as supporting evidence for a context-engineering / entry-point governance calibration case."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-flow-redesign-002",
@@ -52,7 +220,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "not_mixed",
       "summary": "A complete-looking dispatch pack and role reports did not constitute real independent agent invocation. The central issue is formal-output legitimacy, execution authenticity, invocation traceability, and the rule that the orchestrator must stop rather than simulate.",
       "routing_notes": [
         "simulation_only: true",
@@ -61,12 +228,13 @@
         "blocked_until_real_invocation: true",
         "cross-model no-simulation calibration example"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Use as a QPI issue regression and cross-model no-simulation calibration case.",
+      "misclassification_risk": [
         "tool_solutionism",
         "premature_classification",
         "violent_reduction"
       ],
-      "recommended_next_step": "Use as a QPI issue regression and cross-model no-simulation calibration case."
+      "qpi_complexity_pattern": "not_mixed"
     },
     {
       "case_id": "qpi-flow-redesign-003",
@@ -84,21 +252,21 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "Chunk-first extraction produced locally true outputs but misread the whole-source structure. Owner review confirmed that the core scarcity is structural interpretation authority, not merely a missing processing path.",
       "routing_notes": [
         "do not split failure and remedy into separate cases",
         "whole-source gestalt has authority before chunk extraction",
         "named misframing risk: 局部真实冒充全局结构"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Use as a digest and selector calibration case for local truth misused as global structure.",
+      "misclassification_risk": [
         "violent_reduction",
         "premature_classification",
         "single-cause_reduction",
         "tool_solutionism",
         "local_truth_impersonating_global_structure"
       ],
-      "recommended_next_step": "Use as a digest and selector calibration case for local truth misused as global structure."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-flow-redesign-004",
@@ -116,7 +284,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "not_mixed",
       "summary": "The surface question was how far to automate after material distillation, but owner review confirmed that the central QPI issue is stop-gate placement, downstream boundary control, and owner authorization.",
       "routing_notes": [
         "do_not_auto_create_writing_project: true",
@@ -133,12 +300,13 @@
         "model-mining authorization gate",
         "source-of-truth promotion gate"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Use as a digest and selector calibration case for stop-gate routing.",
+      "misclassification_risk": [
         "tool_solutionism",
         "malicious_inflation",
         "premature_classification"
       ],
-      "recommended_next_step": "Use as a digest and selector calibration case for stop-gate routing."
+      "qpi_complexity_pattern": "not_mixed"
     },
     {
       "case_id": "qpi-flow-redesign-005",
@@ -157,19 +325,19 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "A one-owner workflow redesign looked like a P-domain implementation problem, but it became P/I mixed because success depends on governance load, proxy stakeholders, state continuity, invocation authenticity, audit boundaries, and future reuse.",
       "routing_notes": [
         "Issue can be sustained governance load without many human participants",
         "anchor candidate for intra_frame_mixed",
         "code has relatively hard formal feedback; cognitive workflows do not have an equivalent compiler"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Use as a high-priority selector calibration anchor for intra_frame_mixed.",
+      "misclassification_risk": [
         "violent_reduction",
         "tool_solutionism",
         "premature_classification"
       ],
-      "recommended_next_step": "Use as a high-priority selector calibration anchor for intra_frame_mixed."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-flow-redesign-006",
@@ -187,7 +355,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "not_mixed",
       "summary": "Complexity should not be judged by whether it looks large, but by what value it buys. Owner review confirmed this stays as a QPI case now and may later become evidence for a future model candidate, without introducing a third model in the MVP phase.",
       "routing_notes": [
         "do not introduce third model in this round",
@@ -207,13 +374,14 @@
         "adjudicability",
         "cost reasonableness / ROI"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Use as a QPI calibration case for justified versus unjustified process complexity.",
+      "misclassification_risk": [
         "violent_reduction",
         "malicious_inflation",
         "tool_solutionism",
         "premature_classification"
       ],
-      "recommended_next_step": "Use as a QPI calibration case for justified versus unjustified process complexity."
+      "qpi_complexity_pattern": "not_mixed"
     },
     {
       "case_id": "qpi-disappointment-001",
@@ -231,20 +399,21 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "medium"
       },
-      "mixed_or_multi_perspective": "inter_viewpoint_divergence",
       "summary": "The same psychological-relational surface term can mean passive numbness, active cognitive withdrawal, or a mixed/unclear mechanism. Owner review adds that the source context is analysis of external content misframing, not neutral self-diagnosis.",
       "routing_notes": [
         "mark mechanism_ambiguity before route recommendation",
         "do not generalize passive numbness vs active withdrawal into a universal field",
         "QPI should request subject position, goal, relationship scene, time scale, and decision boundary before routing"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Use as selector calibration for multi-perspective mechanism ambiguity in psychological-relational material.",
+      "misclassification_risk": [
         "premature_classification",
         "single_factor_totalization",
         "over_pathologizing",
         "violent_reduction"
       ],
-      "recommended_next_step": "Use as selector calibration for multi-perspective mechanism ambiguity in psychological-relational material."
+      "qpi_complexity_pattern": "inter_viewpoint_divergence",
+      "viewpoint_summary": "Inter-viewpoint divergence is retained from owner-reviewed case notes; reviewers should inspect summary, routing_notes, and source draft case before using this case as a regression oracle."
     },
     {
       "case_id": "qpi-disappointment-002",
@@ -264,7 +433,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "not_mixed",
       "summary": "A label question becomes Issue-dominant when the label organizes identity, relationship boundaries, help-seeking, and future action. The label may still have a Q component, but it is no longer the dominant scarcity.",
       "minimum_context": [
         "problem_owner",
@@ -282,13 +450,14 @@
         "pure_Q_label_lookup",
         "automatic_I_from_any_psychological_label"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Ask how the label is being used before deciding whether this is pure Q or Issue-dominant self-framing.",
+      "misclassification_risk": [
         "violent_reduction",
         "premature_classification",
         "single_factor_totalization",
         "over_pathologizing"
       ],
-      "recommended_next_step": "Ask how the label is being used before deciding whether this is pure Q or Issue-dominant self-framing."
+      "qpi_complexity_pattern": "not_mixed"
     },
     {
       "case_id": "qpi-disappointment-003",
@@ -307,20 +476,20 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "The risk is not identifying a high-weight factor; it is treating one factor as complete causal closure when the source already shows coupled psychological, relational, cognitive, and identity mechanisms.",
       "routing_notes": [
         "distinguish trigger, maintaining condition, high-weight factor, current action lever, and causal totality",
         "explanatory usefulness is not causal finality",
         "a current lever cannot replace the system maintenance map"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Use as regression against single definitive root-cause output when coupled mechanisms are present.",
+      "misclassification_risk": [
         "violent_reduction",
         "single_factor_totalization",
         "over_pathologizing",
         "premature_classification"
       ],
-      "recommended_next_step": "Use as regression against single definitive root-cause output when coupled mechanisms are present."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-disappointment-004",
@@ -339,7 +508,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "not_mixed",
       "summary": "The case guards against treating psychological-relational Issue as a one-time Problem. QPI should not design intervention; it can only decide whether a bounded local P subtask has enough context.",
       "local_problem_conditions": [
         "actor",
@@ -355,13 +523,14 @@
         "three_step_cure",
         "single_intervention_script"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Route as Issue unless a bounded local P subtask is explicitly scoped and non-terminal.",
+      "misclassification_risk": [
         "violent_reduction",
         "tool_solutionism",
         "malicious_inflation",
         "premature_classification"
       ],
-      "recommended_next_step": "Route as Issue unless a bounded local P subtask is explicitly scoped and non-terminal."
+      "qpi_complexity_pattern": "not_mixed"
     },
     {
       "case_id": "qpi-disappointment-005",
@@ -379,20 +548,20 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "not_mixed",
       "summary": "External help is not framed as an intervention answer. The QPI issue is how external authority, calibration environment, dependency risk, and subject agency are bounded within self-governance.",
       "routing_notes": [
         "external_authority_boundary is a governance-load signal",
         "does therapy work style inputs are low-confidence until context is known",
         "psychological-relational inputs may be Q, P, or I depending on goal and decision stakes"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Use as supporting Issue digest for external authority boundary and calibration environment.",
+      "misclassification_risk": [
         "violent_reduction",
         "malicious_inflation",
         "single_factor_totalization",
         "over_pathologizing"
       ],
-      "recommended_next_step": "Use as supporting Issue digest for external authority boundary and calibration environment."
+      "qpi_complexity_pattern": "not_mixed"
     },
     {
       "case_id": "qpi-disappointment-006",
@@ -410,20 +579,21 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "inter_viewpoint_divergence",
       "summary": "QPI should not pretend to model full dynamic evolution, but it must record the time slice and classification scope so a local judgment is not treated as global truth.",
       "routing_notes": [
         "keep time_scale and classification_scope",
         "treat same phenomenon different time scale as inter_viewpoint_divergence for now",
         "do not add a new dynamic-scope enum in this round"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Use as selector calibration for short inputs whose Q/P/I route changes by time scale and decision boundary.",
+      "misclassification_risk": [
         "premature_classification",
         "malicious_inflation",
         "violent_reduction",
         "tool_solutionism"
       ],
-      "recommended_next_step": "Use as selector calibration for short inputs whose Q/P/I route changes by time scale and decision boundary."
+      "qpi_complexity_pattern": "inter_viewpoint_divergence",
+      "viewpoint_summary": "Inter-viewpoint divergence is retained from owner-reviewed case notes; reviewers should inspect summary, routing_notes, and source draft case before using this case as a regression oracle."
     },
     {
       "case_id": "qpi-disappointment-007",
@@ -442,7 +612,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "not_mixed",
       "summary": "This is a model-hardening case: QPI needs mismatch diagnostics, not only final labels, for psychological-relational inputs.",
       "wrong_route_to_avoid": [
         "I_as_Q",
@@ -452,7 +621,8 @@
         "moral_judgment_substitution",
         "single_factor_totalization"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Use as regression foundation for QPI wrong-route detection.",
+      "misclassification_risk": [
         "violent_reduction",
         "malicious_inflation",
         "tool_solutionism",
@@ -460,7 +630,7 @@
         "single_factor_totalization",
         "over_pathologizing"
       ],
-      "recommended_next_step": "Use as regression foundation for QPI wrong-route detection."
+      "qpi_complexity_pattern": "not_mixed"
     },
     {
       "case_id": "qpi-disappointment-008",
@@ -482,7 +652,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "not_mixed",
       "summary": "This is the canonical anchor that Issue does not require multiple people. One-person self-governance can be Issue when the subject must continuously calibrate protection, openness, risk, energy, feedback, old defense, and new relational experiments.",
       "governance_variables": [
         "target",
@@ -518,14 +687,15 @@
         "over_pathologizing",
         "moral_judgment_substitution"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Replace binary judgment with governance review, then run value assessment to decide whether full Issue governance or only a bounded local Problem step is warranted.",
+      "misclassification_risk": [
         "violent_reduction",
         "over_pathologizing",
         "single_factor_totalization",
         "premature_classification",
         "moral_judgment_substitution"
       ],
-      "recommended_next_step": "Replace binary judgment with governance review, then run value assessment to decide whether full Issue governance or only a bounded local Problem step is warranted."
+      "qpi_complexity_pattern": "not_mixed"
     },
     {
       "case_id": "qpi-year-end-development-office-001",
@@ -545,19 +715,19 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "A hard physical resource gap is reframed as documentation, relabeling, and compliance packaging. The path/resource shortage triggers the case, but the QPI scarcity is governance/order failure around compliance authenticity and auditability.",
       "routing_notes": [
         "CT diagnosis notes must be translated into QPI governance language",
         "hard_resource_gap_disguised_as_documentation_problem",
         "internal anonymization acceptable; public use requires further generalization"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Separate legitimate remediation from compliance workaround risk before treating the gap as a solvable documentation problem.",
+      "misclassification_risk": [
         "violent_reduction",
         "premature_classification",
         "single-cause_reduction"
       ],
-      "recommended_next_step": "Separate legitimate remediation from compliance workaround risk before treating the gap as a solvable documentation problem."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-development-office-002",
@@ -577,19 +747,19 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "not_mixed",
       "summary": "Credential metric repair improves the table while damaging the operating system. Role-function fit, operating memory, morale, labor risk, and continuity are violently reduced to credential count.",
       "routing_notes": [
         "operational_continuity is the summary focus",
         "role mismatch and morale/labor risk are mechanisms",
         "one of the clearest violent_reduction examples in this source"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Treat the selected staffing path as a governance issue before optimizing the credential metric.",
+      "misclassification_risk": [
         "violent_reduction",
         "single-cause_reduction",
         "premature_classification"
       ],
-      "recommended_next_step": "Treat the selected staffing path as a governance issue before optimizing the credential metric."
+      "qpi_complexity_pattern": "not_mixed"
     },
     {
       "case_id": "qpi-year-end-development-office-003",
@@ -608,19 +778,20 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "inter_viewpoint_divergence",
       "summary": "Performance decline is misread as insufficient effort, while the underlying mechanism is incentive backlash produced by cost allocation, trust loss, and institutional design.",
       "routing_notes": [
         "organization-level rewrite could be intra_frame_mixed",
         "kept as inter_viewpoint_divergence because role contrast is the strongest calibration value",
         "performance_decline_with_incentive_backlash"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Separate output symptom from incentive mechanism and identify which subject frame is being routed.",
+      "misclassification_risk": [
         "violent_reduction",
         "single-cause_reduction",
         "premature_classification"
       ],
-      "recommended_next_step": "Separate output symptom from incentive mechanism and identify which subject frame is being routed."
+      "qpi_complexity_pattern": "inter_viewpoint_divergence",
+      "viewpoint_summary": "Inter-viewpoint divergence is retained from owner-reviewed case notes; reviewers should inspect summary, routing_notes, and source draft case before using this case as a regression oracle."
     },
     {
       "case_id": "qpi-year-end-development-office-004",
@@ -640,19 +811,20 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "inter_viewpoint_divergence",
       "summary": "A strategic support function is blamed for not producing strategy while being denied resources, authority, trust, and executable space, then pulled back into indicator packaging.",
       "routing_notes": [
         "middle-leadership capability is a local P component, not the main classification",
         "do not expand into a full person-level viewpoint table",
         "public use may generalize planning function further"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Treat role-authority mismatch as the QPI issue before evaluating individual planning competence.",
+      "misclassification_risk": [
         "violent_reduction",
         "malicious_inflation",
         "premature_classification"
       ],
-      "recommended_next_step": "Treat role-authority mismatch as the QPI issue before evaluating individual planning competence."
+      "qpi_complexity_pattern": "inter_viewpoint_divergence",
+      "viewpoint_summary": "Inter-viewpoint divergence is retained from owner-reviewed case notes; reviewers should inspect summary, routing_notes, and source draft case before using this case as a regression oracle."
     },
     {
       "case_id": "qpi-year-end-development-office-005",
@@ -678,20 +850,20 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "Multiple surface problems share one generating mechanism: low-cost ambition, target-resource inconsistency, and downstream contradiction absorption. Resource-dependent outcomes are treated as if command, packaging, or discipline could replace real exchange and capacity.",
       "routing_notes": [
         "whole-slice meta-case",
         "pattern-level Issue allowed when surface problems share a generating mechanism",
         "keep separate from narrow regression cases"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Use as digest / calibration for pattern-level Issue, not as first-wave regression.",
+      "misclassification_risk": [
         "malicious_inflation",
         "violent_reduction",
         "tool_solutionism",
         "premature_classification"
       ],
-      "recommended_next_step": "Use as digest / calibration for pattern-level Issue, not as first-wave regression."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-development-office-006",
@@ -710,7 +882,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "evidence_integrity_gap": "high",
       "audit_authenticity_risk": "high",
       "truthfulness_gap": "high",
@@ -720,12 +891,13 @@
         "facts are mostly known but inconvenient",
         "evidence authenticity audit precedes resource planning"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Run evidence authenticity audit before treating the case as a resource-planning problem.",
+      "misclassification_risk": [
         "tool_solutionism",
         "violent_reduction",
         "premature_classification"
       ],
-      "recommended_next_step": "Run evidence authenticity audit before treating the case as a resource-planning problem."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-development-office-007",
@@ -744,7 +916,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "not_mixed",
       "primary_risk": "normalization_of_workaround / complicity_in_workaround",
       "secondary_condition": "lack_of_escalation_channel",
       "summary": "A competent execution lead converts impossible top-down directives into feasible-looking workaround action, extending the life of a broken governance premise.",
@@ -753,12 +924,13 @@
         "auxiliary inter_viewpoint_divergence sample only",
         "owner confirmed through multiple participant conversations"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Identify whether execution competence is protecting system viability or normalizing workaround risk.",
+      "misclassification_risk": [
         "violent_reduction",
         "premature_classification",
         "single-cause_reduction"
       ],
-      "recommended_next_step": "Identify whether execution competence is protecting system viability or normalizing workaround risk."
+      "qpi_complexity_pattern": "not_mixed"
     },
     {
       "case_id": "qpi-year-end-development-office-008",
@@ -779,20 +951,20 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "External review pressure is a trigger and accelerator, not the root cause. Internal low-investment, high-pressure, formalistic governance turns indicator survival into a process that cannibalizes real capability.",
       "routing_notes": [
         "umbrella digest anchor",
         "do not replace narrower regression cases",
         "do not route into future CT work in this round"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Use as umbrella organization-level QPI Issue while keeping current scope inside QPI.",
+      "misclassification_risk": [
         "violent_reduction",
         "malicious_inflation",
         "single-cause_reduction",
         "premature_classification"
       ],
-      "recommended_next_step": "Use as umbrella organization-level QPI Issue while keeping current scope inside QPI."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-academic-affairs-001",
@@ -812,19 +984,19 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "A tool-assisted material request becomes a QPI issue when AI is used to reverse-engineer evidence from desired conclusions. Missing evidence is the trigger, but the core scarcity is evidence legitimacy, audit authenticity, and tool-boundary governance.",
       "routing_notes": [
         "AI can organize evidence, but must not manufacture the evidentiary relationship",
         "do not treat as simple material generation",
         "current anonymization sufficient"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Require a traceable evidence inventory before tool-assisted drafting.",
+      "misclassification_risk": [
         "tool_solutionism",
         "violent_reduction",
         "premature_classification"
       ],
-      "recommended_next_step": "Require a traceable evidence inventory before tool-assisted drafting."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-academic-affairs-002",
@@ -843,7 +1015,6 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "External policy pressure triggers a staffing metric repair, but the organization creates a resource deadlock by counting credential value before proving real teaching-use value.",
       "routing_notes": [
         "external policy is trigger",
@@ -851,12 +1022,13 @@
         "compliance value substituted for use value",
         "keep separate from other staffing cases"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Model real workload absorption and use value before further recruitment or reclassification.",
+      "misclassification_risk": [
         "violent_reduction",
         "malicious_inflation",
         "premature_classification"
       ],
-      "recommended_next_step": "Model real workload absorption and use value before further recruitment or reclassification."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-academic-affairs-003",
@@ -876,7 +1048,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "not_mixed",
       "proxy_stakeholders": [
         "policy_memory"
       ],
@@ -886,12 +1057,13 @@
         "incentive integrity plus trust repair",
         "policy_memory is not a person"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Separate future integrity rules from transitional handling of people affected by prior incentives.",
+      "misclassification_risk": [
         "violent_reduction",
         "single-cause_reduction",
         "premature_classification"
       ],
-      "recommended_next_step": "Separate future integrity rules from transitional handling of people affected by prior incentives."
+      "qpi_complexity_pattern": "not_mixed"
     },
     {
       "case_id": "qpi-year-end-academic-affairs-004",
@@ -910,7 +1082,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "inter_viewpoint_divergence",
       "summary": "A resource-feasible compromise becomes strategic myopia if short-term reportability and packaging are not tested against long-term organizational positioning.",
       "routing_notes": [
         "decision layer sees strategic alignment",
@@ -918,12 +1089,14 @@
         "market-facing frame sees communication and enrollment",
         "keep role divergence visible"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Test resource-feasible compromise against long-term positioning before accepting it as strategy.",
+      "misclassification_risk": [
         "violent_reduction",
         "malicious_inflation",
         "premature_classification"
       ],
-      "recommended_next_step": "Test resource-feasible compromise against long-term positioning before accepting it as strategy."
+      "qpi_complexity_pattern": "inter_viewpoint_divergence",
+      "viewpoint_summary": "Inter-viewpoint divergence is retained from owner-reviewed case notes; reviewers should inspect summary, routing_notes, and source draft case before using this case as a regression oracle."
     },
     {
       "case_id": "qpi-year-end-academic-affairs-005",
@@ -943,7 +1116,6 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "inter_viewpoint_divergence",
       "minimum_problem_evidence": [
         "role_fit",
         "learner_fit",
@@ -959,12 +1131,14 @@
         "pair with staffing-ratio deadlock but do not merge",
         "interest-class pilot may be plausible; direct core-course redeployment is not valid without retraining and compensation"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Verify role fit and transition cost before treating redeployment as a legitimate Problem.",
+      "misclassification_risk": [
         "violent_reduction",
         "single-cause_reduction",
         "premature_classification"
       ],
-      "recommended_next_step": "Verify role fit and transition cost before treating redeployment as a legitimate Problem."
+      "qpi_complexity_pattern": "inter_viewpoint_divergence",
+      "viewpoint_summary": "Inter-viewpoint divergence is retained from owner-reviewed case notes; reviewers should inspect summary, routing_notes, and source draft case before using this case as a regression oracle."
     },
     {
       "case_id": "qpi-year-end-academic-affairs-006",
@@ -984,19 +1158,19 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "Input conditions may affect outcomes, but cannot replace audit of management levers. Isolated achievements can signal local capability, but primarily mask systemic outcome decline when broader quality indicators worsen.",
       "routing_notes": [
         "masking signal over latent capability",
         "avoid assigning all causality to one function",
         "quality assurance gap"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Build a quality assurance map linking complaints, outcomes, process controls, and owner accountability.",
+      "misclassification_risk": [
         "violent_reduction",
         "single-cause_reduction",
         "premature_classification"
       ],
-      "recommended_next_step": "Build a quality assurance map linking complaints, outcomes, process controls, and owner accountability."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-academic-affairs-007",
@@ -1015,19 +1189,20 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "inter_viewpoint_divergence",
       "summary": "Platform or AI deployment choice is not primarily a tool preference when the organization lacks digital governance criteria, data boundaries, lifecycle ownership, adoption standards, and migration responsibility.",
       "routing_notes": [
         "define digital governance criteria before platform selection",
         "local-vs-cloud detail can remain",
         "management and governance problem, not tool selection"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Define governance criteria and authority before selecting tools.",
+      "misclassification_risk": [
         "tool_solutionism",
         "malicious_inflation",
         "premature_classification"
       ],
-      "recommended_next_step": "Define governance criteria and authority before selecting tools."
+      "qpi_complexity_pattern": "inter_viewpoint_divergence",
+      "viewpoint_summary": "Inter-viewpoint divergence is retained from owner-reviewed case notes; reviewers should inspect summary, routing_notes, and source draft case before using this case as a regression oracle."
     },
     {
       "case_id": "qpi-year-end-academic-affairs-008",
@@ -1047,19 +1222,19 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "A large activity without proper reporting, approval, and safety controls is a local process gap and a system-level signal that public safety, learner rights, and external compliance may not be treated as hard boundaries.",
       "routing_notes": [
         "concrete operating accident can reveal bottom-line control failure",
         "not just a missing checklist",
         "current anonymization sufficient"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Build hard-gate approval, reporting, risk ownership, participant safety controls, and stop rules.",
+      "misclassification_risk": [
         "violent_reduction",
         "single-cause_reduction",
         "premature_classification"
       ],
-      "recommended_next_step": "Build hard-gate approval, reporting, risk ownership, participant safety controls, and stop rules."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-employment-entrepreneurship-001",
@@ -1079,19 +1254,19 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "Employment outcome pressure reveals real teaching and market-alignment problems, but reverse accountability power turns a downstream service function 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"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Define shared outcome governance, evidence standards, and limits on reverse accountability before redesigning authority.",
+      "misclassification_risk": [
         "violent_reduction",
         "malicious_inflation",
         "premature_classification"
       ],
-      "recommended_next_step": "Define shared outcome governance, evidence standards, and limits on reverse accountability before redesigning authority."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-employment-entrepreneurship-002",
@@ -1111,7 +1286,6 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "A credential gap may be a real resource problem, but externalized metric repair can turn credential holders into indicator products and create compliance legitimacy risk.",
       "routing_notes": [
         "cross-link academic affairs staffing-ratio deadlock without merging",
@@ -1123,12 +1297,13 @@
         "credential_holder_role_in_teaching_or_research_unknown",
         "compliance_review_boundary_unclear"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Check whether credentialed personnel are substantively integrated before accepting metric repair as a legitimate path.",
+      "misclassification_risk": [
         "violent_reduction",
         "tool_solutionism",
         "premature_classification"
       ],
-      "recommended_next_step": "Check whether credentialed personnel are substantively integrated before accepting metric repair as a legitimate path."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-employment-entrepreneurship-003",
@@ -1148,7 +1323,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "The accounting mismatch is not merely missing data; it is a performance legitimacy problem when non-recognized or department-standard figures are used to justify strategic authority.",
       "routing_notes": [
         "do not accept reported metrics at face value",
@@ -1160,12 +1334,13 @@
         "reported_metric_lineage_unverified",
         "department_accounting_basis_conflicts_with_group_standard"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Reconcile financial recognition standards before using reported contribution as strategic evidence.",
+      "misclassification_risk": [
         "violent_reduction",
         "malicious_inflation",
         "premature_classification"
       ],
-      "recommended_next_step": "Reconcile financial recognition standards before using reported contribution as strategic evidence."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-employment-entrepreneurship-004",
@@ -1185,7 +1360,6 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "Outcome promises can support recruitment only when delivery capacity and promise boundaries are real; otherwise they distort the student pipeline and change institutional responsibility.",
       "routing_notes": [
         "separate from reverse accountability case",
@@ -1201,13 +1375,14 @@
         "verification",
         "complaint_or_refund_boundary"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Require evidence that the promised outcome can be delivered before treating it as recruitment strategy.",
+      "misclassification_risk": [
         "violent_reduction",
         "malicious_inflation",
         "tool_solutionism",
         "premature_classification"
       ],
-      "recommended_next_step": "Require evidence that the promised outcome can be delivered before treating it as recruitment strategy."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-employment-entrepreneurship-005",
@@ -1227,7 +1402,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "High outcome metrics do not prove high metric credibility. When KPI pressure shapes data production, QPI must audit how data is produced, interpreted, and used for authority.",
       "routing_notes": [
         "distinguish high metric value from high metric credibility",
@@ -1241,12 +1415,13 @@
         "coercion_or_compliance_behavior_risk",
         "metric_use_in_authority_expansion"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Audit the production mechanism behind outcome data before using high metrics as proof of institutional health.",
+      "misclassification_risk": [
         "violent_reduction",
         "malicious_inflation",
         "premature_classification"
       ],
-      "recommended_next_step": "Audit the production mechanism behind outcome data before using high metrics as proof of institutional health."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-employment-entrepreneurship-006",
@@ -1266,7 +1441,6 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "The external employer asset may be real, but it is a boundary mixed case when the asset functions as showcase material or internship proof rather than integrated student capability building.",
       "routing_notes": [
         "not a pure positive contrast case",
@@ -1284,12 +1458,13 @@
         "outcome_verification",
         "incentive_alignment"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Ask for the operational bridge from employer asset to curriculum, projects, assessment, and verified learning outcomes.",
+      "misclassification_risk": [
         "tool_solutionism",
         "premature_classification",
         "violent_reduction"
       ],
-      "recommended_next_step": "Ask for the operational bridge from employer asset to curriculum, projects, assessment, and verified learning outcomes."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-employment-entrepreneurship-007",
@@ -1309,19 +1484,19 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "Recognizing a function's assets or achievements is not the same as transferring system-level authority to that function. Local performance can be maliciously inflated into governance control.",
       "routing_notes": [
         "keep separate from reverse accountability mechanism",
         "malicious_inflation applies",
         "distinguish asset_recognition from authority_transfer"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Do not infer authority transfer from asset recognition; define scope, checks, and evidence standards first.",
+      "misclassification_risk": [
         "malicious_inflation",
         "violent_reduction",
         "premature_classification"
       ],
-      "recommended_next_step": "Do not infer authority transfer from asset recognition; define scope, checks, and evidence standards first."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-employment-entrepreneurship-008",
@@ -1341,20 +1516,20 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "Under survival pressure, the organization risks sliding from education capability building into transactional output logic, where employment, revenue, and compliance metrics take over the definition of education value.",
       "routing_notes": [
         "Issue anchor for this group",
         "do not split because 001-007 already carry narrower decompositions",
         "market survival metrics cannot replace education quality"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Govern the value definition before allowing employment, revenue, or compliance metrics to take over institutional identity.",
+      "misclassification_risk": [
         "violent_reduction",
         "malicious_inflation",
         "premature_classification",
         "single-cause_reduction"
       ],
-      "recommended_next_step": "Govern the value definition before allowing employment, revenue, or compliance metrics to take over institutional identity."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-engineering-center-001",
@@ -1374,7 +1549,6 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "reusable_pattern": "target_authenticity_gap",
       "summary": "A support-oriented technical function is pushed toward industrialized revenue goals without credible capability, market, resource, and validation bridges.",
       "routing_notes": [
@@ -1382,13 +1556,14 @@
         "require bridge evidence",
         "high targets become fraud pressure when no validated bridge exists"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Build staged bridge evidence before accepting the target as an execution mandate.",
+      "misclassification_risk": [
         "violent_reduction",
         "malicious_inflation",
         "tool_solutionism",
         "premature_classification"
       ],
-      "recommended_next_step": "Build staged bridge evidence before accepting the target as an execution mandate."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-engineering-center-002",
@@ -1408,7 +1583,6 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "The issue is not equipment selection but substituting asset purchase for demand validation, operator competence, execution standards, safety, and unit economics.",
       "routing_notes": [
         "equipment_led_solutionism",
@@ -1422,12 +1596,13 @@
         "unit_economics",
         "pilot_result"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Validate demand and operators before equipment; otherwise the equipment is a sunk-cost generator, not capability.",
+      "misclassification_risk": [
         "tool_solutionism",
         "violent_reduction",
         "malicious_inflation"
       ],
-      "recommended_next_step": "Validate demand and operators before equipment; otherwise the equipment is a sunk-cost generator, not capability."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-engineering-center-003",
@@ -1447,7 +1622,6 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "The organization used Problem-style shortcuts to absorb an Issue-level capability and legitimacy gap until regulation, accidents, audit, or trust creates a hard boundary.",
       "routing_notes": [
         "not merely compliance boundary hardening",
@@ -1459,12 +1633,13 @@
         "audit_exposure": "high",
         "shortcut_debt": "high"
       },
-      "misframing_risks": [
+      "recommended_next_step": "Treat staffing as shortcut debt meeting a hard boundary, not as a simple headcount patch.",
+      "misclassification_risk": [
         "violent_reduction",
         "single-cause_reduction",
         "premature_classification"
       ],
-      "recommended_next_step": "Treat staffing as shortcut debt meeting a hard boundary, not as a simple headcount patch."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-engineering-center-004",
@@ -1484,7 +1659,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "no_personnel_verdict": true,
       "route_to_policy_review_not_person_judgment": true,
       "summary": "QPI should not judge whether a specific person is usable or deceptive; it should identify when credential anomalies expose screening, exception, and risk-ownership governance gaps.",
@@ -1498,12 +1672,13 @@
         "exception_policy_unknown",
         "risk_owner_unknown"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Review screening, exception policy, and risk ownership before making convenience-based staffing decisions.",
+      "misclassification_risk": [
         "violent_reduction",
         "single-cause_reduction",
         "premature_classification"
       ],
-      "recommended_next_step": "Review screening, exception policy, and risk ownership before making convenience-based staffing decisions."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-engineering-center-005",
@@ -1523,7 +1698,6 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "For a business actor, production capability without a consumer, acquisition channel, or profit loop is not merely a data question; it is a first-principle business-purpose mismatch.",
       "routing_notes": [
         "not first classified as question in this context",
@@ -1539,12 +1713,13 @@
         "delivery_fit",
         "unit_economics"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Clarify the subject's purpose and business loop before treating production capability as viability.",
+      "misclassification_risk": [
         "premature_classification",
         "tool_solutionism",
         "malicious_inflation"
       ],
-      "recommended_next_step": "Clarify the subject's purpose and business loop before treating production capability as viability."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-engineering-center-006",
@@ -1564,7 +1739,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "Execution fatigue may be violently reduced to low motivation, but QPI must test whether decision rights, role boundaries, and leadership intervention patterns are creating exhaustion.",
       "routing_notes": [
         "distinguish healthy hands-on leadership from destructive micro-control",
@@ -1581,12 +1755,13 @@
         "error_ownership",
         "business_fit"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Diagnose decision-rights architecture before blaming execution motivation.",
+      "misclassification_risk": [
         "violent_reduction",
         "single-cause_reduction",
         "premature_classification"
       ],
-      "recommended_next_step": "Diagnose decision-rights architecture before blaming execution motivation."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-engineering-center-007",
@@ -1606,7 +1781,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "medium"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "reusable_pattern": "asset_or_liability_ambiguity",
       "summary": "An inherited platform or certification may be a genuine asset, but transfer from a stronger unit to a weaker unit is a risk signal until history, cost, responsibility, and prior-owner exit reasons are checked.",
       "routing_notes": [
@@ -1614,12 +1788,13 @@
         "adverse selection risk",
         "organizational dumping risk translated for review"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Investigate transfer history, operating cost, responsibility boundary, and prior owner exit reason before treating the project as an asset.",
+      "misclassification_risk": [
         "premature_classification",
         "malicious_inflation",
         "single-cause_reduction"
       ],
-      "recommended_next_step": "Investigate transfer history, operating cost, responsibility boundary, and prior owner exit reason before treating the project as an asset."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-engineering-center-008",
@@ -1639,7 +1814,6 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "Legacy staff mismatch under a new technical direction is not a simple replacement task; it requires lawful, budgeted, capability-oriented transition paths and trust-cost governance.",
       "routing_notes": [
         "keep separate from compliance staffing",
@@ -1658,12 +1832,13 @@
         "operational_need",
         "dignity_and_trust_cost"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Define legal, budget, training, redeployment, and consultation paths before treating staff mismatch as execution-only.",
+      "misclassification_risk": [
         "violent_reduction",
         "single-cause_reduction",
         "premature_classification"
       ],
-      "recommended_next_step": "Define legal, budget, training, redeployment, and consultation paths before treating staff mismatch as execution-only."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-international-college-001",
@@ -1683,20 +1858,20 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "A retention workaround becomes Issue-level when it changes the institution's compliance posture, credential trust, audit exposure, and future complaint risk.",
       "routing_notes": [
         "pathway adjustment must obey compliance red lines",
         "retention pressure does not authorize institutional-risk change",
         "all generalized details are safe for digest"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Separate retention problem-solving from compliance judgment before designing any replacement pathway.",
+      "misclassification_risk": [
         "malicious_inflation",
         "violent_reduction",
         "premature_classification",
         "single-cause_reduction"
       ],
-      "recommended_next_step": "Separate retention problem-solving from compliance judgment before designing any replacement pathway."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-international-college-002",
@@ -1716,19 +1891,19 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "The hard resource gap is physical capacity, but the organizational failure is cross-unit conflict under a missing capacity gate when growth promises require displacing other units.",
       "routing_notes": [
         "simple logistics no-call versus capacity governance call",
         "cross-unit conflict is key failure expression",
         "hard capacity gate needed"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Verify capacity and create cross-unit arbitration before promising growth.",
+      "misclassification_risk": [
         "violent_reduction",
         "tool_solutionism",
         "premature_classification"
       ],
-      "recommended_next_step": "Verify capacity and create cross-unit arbitration before promising growth."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-international-college-003",
@@ -1749,7 +1924,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "Strong performance may deserve recognition, but it cannot be directly converted into structural authority, title, external representation, or exception rules without accountability design.",
       "routing_notes": [
         "power without accountability is a risk consequence",
@@ -1761,12 +1935,13 @@
         "adjacent_units",
         "external_partners"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Define rule-based authority and accountability before granting upgraded status.",
+      "misclassification_risk": [
         "violent_reduction",
         "malicious_inflation",
         "single-cause_reduction"
       ],
-      "recommended_next_step": "Define rule-based authority and accountability before granting upgraded status."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-international-college-004",
@@ -1786,7 +1961,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "inter_viewpoint_divergence",
       "summary": "The execution layer frames the task as lead generation and conversion, while the decision layer frames it as full education-chain strategy and outcome accountability.",
       "classification_by_viewpoint": {
         "execution_layer": {
@@ -1809,12 +1983,13 @@
         "clearest inter_viewpoint_divergence example in this source",
         "do not collapse viewpoints into one operational label"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Separate viewpoint classifications before deciding which frame governs resources.",
+      "misclassification_risk": [
         "violent_reduction",
         "premature_classification",
         "malicious_inflation"
       ],
-      "recommended_next_step": "Separate viewpoint classifications before deciding which frame governs resources."
+      "qpi_complexity_pattern": "inter_viewpoint_divergence"
     },
     {
       "case_id": "qpi-year-end-international-college-005",
@@ -1834,7 +2009,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "The metric is not just fact scarcity once it is embedded in evaluation pressure, execution-layer reporting, and decision-layer concern about short-termism.",
       "routing_notes": [
         "not question-first in this source",
@@ -1850,12 +2024,13 @@
         "traceable_evidence_chain_missing",
         "metric_fails_to_reflect_student_value_teaching_value_or_org_capability"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Audit metric lineage and governance incentives before accepting the indicator as capability evidence.",
+      "misclassification_risk": [
         "violent_reduction",
         "single-cause_reduction",
         "premature_classification"
       ],
-      "recommended_next_step": "Audit metric lineage and governance incentives before accepting the indicator as capability evidence."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-international-college-006",
@@ -1875,7 +2050,6 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "The pricing deadlock is a surface symptom; in high-ticket education sales, the deeper Issue is whether the organization can build trust through credible promises, verifiable outcomes, and coordinated delivery.",
       "routing_notes": [
         "related owner model APTC is context, not a new repo model",
@@ -1890,12 +2064,13 @@
         "inherited_pricing_constraint",
         "historical_price_anchor_with_fairness_debt"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Analyze the trust system before changing price or using workaround enrollment tactics.",
+      "misclassification_risk": [
         "violent_reduction",
         "tool_solutionism",
         "premature_classification"
       ],
-      "recommended_next_step": "Analyze the trust system before changing price or using workaround enrollment tactics."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-international-college-007",
@@ -1915,7 +2090,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "The issue is not that organizational capability is privatized, but that high-performing individual or small-team capability has not been institutionalized into transferable, auditable, resilient organizational capability.",
       "routing_notes": [
         "link to role inflation but do not merge",
@@ -1928,12 +2102,13 @@
         "capability_not_institutionalized",
         "continuity_risk"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Create capability capture, succession, transparency, and incentive mechanisms without destroying the team's execution energy.",
+      "misclassification_risk": [
         "violent_reduction",
         "single-cause_reduction",
         "premature_classification"
       ],
-      "recommended_next_step": "Create capability capture, succession, transparency, and incentive mechanisms without destroying the team's execution energy."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-international-college-008",
@@ -1955,7 +2130,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "A real external channel is an asset, but it becomes contaminated if used to license expansion before internal delivery, compliance, quality, and capacity are ready.",
       "linked_cases": [
         "qpi-draft-intl-001",
@@ -1973,12 +2147,13 @@
         "real external asset does not mean safe internal expansion",
         "define prohibited uses before scaling"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Define protected-asset boundaries and prohibited internal uses before scaling.",
+      "misclassification_risk": [
         "malicious_inflation",
         "violent_reduction",
         "tool_solutionism"
       ],
-      "recommended_next_step": "Define protected-asset boundaries and prohibited internal uses before scaling."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-research-office-001",
@@ -1999,7 +2174,6 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "linked_cases": [
         "qpi-draft-002",
         "qpi-draft-003",
@@ -2013,13 +2187,14 @@
         "research identity simulation is owner-approved",
         "capability building must be separated from evidence simulation"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Separate legitimate research capability building from identity simulation and compliance red-line risk.",
+      "misclassification_risk": [
         "violent_reduction",
         "tool_solutionism",
         "premature_classification",
         "single-cause_reduction"
       ],
-      "recommended_next_step": "Separate legitimate research capability building from identity simulation and compliance red-line risk."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-research-office-002",
@@ -2040,7 +2215,6 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "requires_compliance_review": true,
       "summary": "The organization has real research staff and cost shortages, but the key QPI risk is violent reduction of research capability and governance into spreadsheet categories.",
       "routing_notes": [
@@ -2058,13 +2232,14 @@
         "payroll_category_validity",
         "research_contribution_trace"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Verify actual research roles, payroll category validity, and research contribution traces before accepting the metric package.",
+      "misclassification_risk": [
         "violent_reduction",
         "tool_solutionism",
         "premature_classification",
         "single-cause_reduction"
       ],
-      "recommended_next_step": "Verify actual research roles, payroll category validity, and research contribution traces before accepting the metric package."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-research-office-003",
@@ -2086,19 +2261,19 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "Transactional research assets are a concrete mechanism under the umbrella research-identity simulation case: research evidence is treated as a tradable token rather than trace of real capability.",
       "routing_notes": [
         "keep as subcase rather than delete",
         "transactional evidence is not real capability",
         "parent is qpi-draft-001"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Check whether research evidence is authentic capability trace or transactional identity simulation.",
+      "misclassification_risk": [
         "tool_solutionism",
         "violent_reduction",
         "premature_classification"
       ],
-      "recommended_next_step": "Check whether research evidence is authentic capability trace or transactional identity simulation."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-research-office-004",
@@ -2118,7 +2293,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "inter_viewpoint_divergence",
       "primary_risk": "violent_reduction",
       "secondary_risk": "malicious_inflation",
       "selector_trap": [
@@ -2131,13 +2305,15 @@
         "quick ranking improvement can be a selector trap",
         "ranking cannot define research value"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Route quick-ranking pressure to governance review when it rewards metric improvement without capability improvement.",
+      "misclassification_risk": [
         "violent_reduction",
         "malicious_inflation",
         "tool_solutionism",
         "premature_classification"
       ],
-      "recommended_next_step": "Route quick-ranking pressure to governance review when it rewards metric improvement without capability improvement."
+      "qpi_complexity_pattern": "inter_viewpoint_divergence",
+      "viewpoint_summary": "Inter-viewpoint divergence is retained from owner-reviewed case notes; reviewers should inspect summary, routing_notes, and source draft case before using this case as a regression oracle."
     },
     {
       "case_id": "qpi-year-end-research-office-005",
@@ -2159,7 +2335,6 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "proxy_stakeholders": [
         "high_level_talent"
       ],
@@ -2175,12 +2350,13 @@
         "capability_underutilization",
         "retention_risk"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Design role, platform, and task fit before treating the hire as research capability.",
+      "misclassification_risk": [
         "violent_reduction",
         "single-cause_reduction",
         "premature_classification"
       ],
-      "recommended_next_step": "Design role, platform, and task fit before treating the hire as research capability."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-research-office-006",
@@ -2201,19 +2377,19 @@
         "path_or_resource_scarcity": "high",
         "consensus_or_order_scarcity": "medium"
       },
-      "mixed_or_multi_perspective": "not_mixed",
       "summary": "This is primarily a hard-capacity Problem: physical space, beds, facilities, and capacity cannot be solved by administrative command, though downstream governance risk is visible.",
       "routing_notes": [
         "related to international capacity case but classified lower",
         "hard constraint cannot be solved by command",
         "may escalate to mixed if promises and displacement dominate"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Verify capacity and commitments, then solve through investment, cap, delay, redesign, or lower commitments.",
+      "misclassification_risk": [
         "violent_reduction",
         "premature_classification",
         "single-cause_reduction"
       ],
-      "recommended_next_step": "Verify capacity and commitments, then solve through investment, cap, delay, redesign, or lower commitments."
+      "qpi_complexity_pattern": "not_mixed"
     },
     {
       "case_id": "qpi-year-end-research-office-007",
@@ -2233,7 +2409,6 @@
         "path_or_resource_scarcity": "medium",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "intra_frame_mixed",
       "summary": "A seemingly small responsibility question reveals an accountability architecture gap when safety tasks have no stable owner, evidence trail, process, or escalation route.",
       "routing_notes": [
         "Q-like responsibility question is actually Issue",
@@ -2245,12 +2420,13 @@
         "safety_accountability_vacuum",
         "Q_as_I_trap"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Map owner, evidence trail, process, and escalation rule before treating the task as personal assignment.",
+      "misclassification_risk": [
         "violent_reduction",
         "premature_classification",
         "single-cause_reduction"
       ],
-      "recommended_next_step": "Map owner, evidence trail, process, and escalation rule before treating the task as personal assignment."
+      "qpi_complexity_pattern": "intra_frame_mixed"
     },
     {
       "case_id": "qpi-year-end-research-office-008",
@@ -2272,7 +2448,6 @@
         "path_or_resource_scarcity": "low",
         "consensus_or_order_scarcity": "high"
       },
-      "mixed_or_multi_perspective": "inter_viewpoint_divergence",
       "summary": "The internal punishment-status frame treats no penalty as low risk; the integrity-status frame treats absence of immediate punishment as insufficient evidence of legitimacy.",
       "routing_notes": [
         "keep independent and link to umbrella case",
@@ -2284,12 +2459,14 @@
         "absence_of_penalty_is_not_legitimacy",
         "compliance_minimum_game"
       ],
-      "misframing_risks": [
+      "recommended_next_step": "Separate penalty-status inquiry from integrity-status review and define substantive compliance criteria.",
+      "misclassification_risk": [
         "violent_reduction",
         "single-cause_reduction",
         "premature_classification"
       ],
-      "recommended_next_step": "Separate penalty-status inquiry from integrity-status review and define substantive compliance criteria."
+      "qpi_complexity_pattern": "inter_viewpoint_divergence",
+      "viewpoint_summary": "Inter-viewpoint divergence is retained from owner-reviewed case notes; reviewers should inspect summary, routing_notes, and source draft case before using this case as a regression oracle."
     }
   ]
 }
diff --git a/selector/selector_calibration_inputs.json b/selector/selector_calibration_inputs.json
index 8aeafbe..a6042b6 100644
--- a/selector/selector_calibration_inputs.json
+++ b/selector/selector_calibration_inputs.json
@@ -583,6 +583,20 @@
       "input": "组织认为只要没有罚款、没有被约谈、没有报销损失，就说明合规风险不大。",
       "expected_selector_behavior": "select_qpi",
       "expected_notes": "Owner-reviewed research case 008: punishment state versus integrity state."
+    },
+    {
+      "case_id": "selector_calibration_direct_summary_no_call_001",
+      "category": "round_03_1_direct_execution_no_call",
+      "input": "请把下面内容总结成三点。",
+      "expected_selector_behavior": "no_call",
+      "expected_notes": "Round 03.1 direct summary request must not select QPI by default score."
+    },
+    {
+      "case_id": "selector_calibration_analysis_override_should_call_001",
+      "category": "round_03_1_analysis_override",
+      "input": "请把下面内容总结成三点，但不要只执行，请分析背后的问题定义和组织结构冲突。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Round 03.1 explicit analysis override should preserve QPI selection despite direct-execution phrasing."
     }
   ]
 }
diff --git a/selector/selector_rules.json b/selector/selector_rules.json
index 669ff82..dc15608 100644
--- a/selector/selector_rules.json
+++ b/selector/selector_rules.json
@@ -25,13 +25,27 @@
       "直接改",
       "只改错别字",
       "润色",
-      "翻译",
+      "翻译这句话",
+      "怎么翻译",
+      "翻译：",
+      "只要一个英文",
       "不要展开",
       "不要深入分析",
       "马上执行",
       "不用解释",
       "生成图片"
     ],
+    "direct_execution_no_call_signals": [
+      "排一下",
+      "排床位",
+      "床位表",
+      "整理成表格",
+      "总结成三点",
+      "列出",
+      "格式化",
+      "改成",
+      "只要清单"
+    ],
     "complexity_signals": [
       "反复",
       "冲突",
@@ -44,7 +58,17 @@
       "模型",
       "结构",
       "机制",
-      "抽取"
+      "抽取",
+      "治理",
+      "边界",
+      "承诺",
+      "风险",
+      "证据",
+      "责任",
+      "信任",
+      "容量",
+      "合规",
+      "指标"
     ],
     "qpi_gate_signals": [
       "缺数据",
@@ -54,7 +78,40 @@
       "怎么定义",
       "这是问题",
       "执行路径问题",
-      "组织共识问题"
+      "组织共识问题",
+      "如何",
+      "判断",
+      "真实调用",
+      "上下文",
+      "审计边界",
+      "后续复用",
+      "维护责任",
+      "身份",
+      "触发",
+      "维持条件",
+      "行动杠杆",
+      "依赖风险",
+      "误路由",
+      "过度升维",
+      "负激励",
+      "成本转嫁",
+      "授权",
+      "可执行空间",
+      "现实冲突",
+      "数据边界",
+      "安全",
+      "底线控制",
+      "核心承诺",
+      "交付闭环",
+      "正式能力缺口",
+      "转移原因",
+      "法律审查路径",
+      "证书信任",
+      "完整链条",
+      "教学能力",
+      "科研指标",
+      "物理容量",
+      "没人牵头"
     ],
     "ia_heavy_signals": [
       "底层假设",
@@ -73,6 +130,7 @@
       "complexity_signal": 0.15,
       "selection_priority_factor": 0.01,
       "qpi_gate_bonus": 0.25,
+      "qpi_missing_positive_signal_penalty": 0.25,
       "qpi_already_completed_penalty": 0.25,
       "ia_heavy_bonus": 0.2,
       "ia_qpi_completed_bonus": 0.25,
@@ -85,7 +143,7 @@
   "models": [
     {
       "model_id": "qpi",
-      "base_score": 50,
+      "base_score": 25,
       "trigger_keywords": [
         "问题",
         "难题",
@@ -107,13 +165,12 @@
       ],
       "negative_triggers": [
         "只改错别字",
-        "翻译",
         "润色",
         "生成图片"
       ],
       "pipeline_position": "problem_definition",
-      "selection_priority": 95,
-      "routing_notes": "作为默认前置路由模型；如果无法判断问题类型，优先调用 QPI。"
+      "selection_priority": 9,
+      "routing_notes": "作为前置路由模型；只有命中问题定义、复杂性、QPI gate、任务类型或显式分析 override 时才调用 QPI，普通执行任务不得仅凭默认分调用。"
     },
     {
       "model_id": "intellectual_archaeology",
@@ -141,10 +198,12 @@
         "只要事实",
         "低风险",
         "马上执行",
-        "不用解释"
+        "不用解释",
+        "先不要思想考古",
+        "不要思想考古"
       ],
       "pipeline_position": "modeling_depth_analysis",
-      "selection_priority": 80,
+      "selection_priority": 7,
       "routing_notes": "通常在 QPI 判断为中重型难题或课题后调用；遇到轻量事实检索应避免调用。"
     }
   ]
diff --git a/tests/qpi.regression.json b/tests/qpi.regression.json
index 237d15d..f61f495 100644
--- a/tests/qpi.regression.json
+++ b/tests/qpi.regression.json
@@ -1,51 +1,1582 @@
 {
   "model_id": "qpi",
   "regression_cases": [
-    {"case_id": "case_qpi_positive_question_001", "model_id": "qpi", "case_type": "positive", "input": "我不知道这次服务器宕机的错误码是什么，也不知道日志在哪里。", "expected_behavior": "应识别为提问，核心匮乏物是数据，建议先检索日志和错误码。", "failure_signal": "把它升维为组织课题，或直接给出复杂治理建议。", "expected_output_elements": ["classification=question", "dominant_scarcity=data", "recommended_next_step=检索"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "question", "expected_dominant_scarcity": "data", "expected_max_depth": "not_applicable", "minimum_required_elements": ["problem_owner", "scarcity_profile", "evidence_gap"], "forbidden_elements": ["philosophical_bedrock"], "evaluation_mode": "structured", "notes": "Q 类正例。"},
-    {"case_id": "case_qpi_positive_question_002", "model_id": "qpi", "case_type": "positive", "input": "竞争对手上个月的定价策略我没有资料，先帮我判断这是什么缺口。", "expected_behavior": "应识别为提问，缺少事实资料。", "failure_signal": "进入思想考古或组织治理。", "expected_output_elements": ["question", "data_scarcity=high"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "question", "expected_dominant_scarcity": "data", "expected_max_depth": "not_applicable", "minimum_required_elements": ["classification_confidence", "recommended_next_step"], "forbidden_elements": ["七层下钻"], "evaluation_mode": "structured", "notes": "Q 类正例。"},
-    {"case_id": "case_qpi_positive_question_003", "model_id": "qpi", "case_type": "positive", "input": "我只是不知道季度报表在哪里，这算不算复杂问题？", "expected_behavior": "应识别为提问或 no_call 边界，建议检索位置，不做深层分析。", "failure_signal": "把它解释成系统性课题。", "expected_output_elements": ["data_scarcity=high", "recommended_next_step=检索"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "question", "expected_dominant_scarcity": "data", "expected_max_depth": "not_applicable", "minimum_required_elements": ["classification", "evidence_gap"], "forbidden_elements": ["哲学基岩"], "evaluation_mode": "structured", "notes": "轻量 Q 类。"},
-    {"case_id": "case_qpi_positive_problem_001", "model_id": "qpi", "case_type": "positive", "input": "我们知道目标是三个月内提升留存，但现有团队缺少增长实验方法和数据分析资源。", "expected_behavior": "应识别为难题，核心匮乏物是路径、方法与资源。", "failure_signal": "只要求团队开会达成共识，忽略路径和资源缺口。", "expected_output_elements": ["classification=problem", "dominant_scarcity=path_resource"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "problem", "expected_dominant_scarcity": "path_resource", "expected_max_depth": "not_applicable", "minimum_required_elements": ["recommended_next_step=工程拆解"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "P 类正例。"},
-    {"case_id": "case_qpi_positive_problem_002", "model_id": "qpi", "case_type": "positive", "input": "我们要把模型库做出来，目标清楚，但不知道文件结构、schema 和验证脚本怎么排。", "expected_behavior": "应识别为难题，缺路径和工程拆解。", "failure_signal": "误判为课题或哲学问题。", "expected_output_elements": ["problem", "path_or_resource_scarcity=high"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "problem", "expected_dominant_scarcity": "path_resource", "expected_max_depth": "not_applicable", "minimum_required_elements": ["problem_owner", "recommended_next_step"], "forbidden_elements": ["philosophical_bedrock"], "evaluation_mode": "structured", "notes": "工程路径正例。"},
-    {"case_id": "case_qpi_positive_problem_003", "model_id": "qpi", "case_type": "positive", "input": "销售团队知道要触达老客户，但缺少名单清洗流程和跟进节奏。", "expected_behavior": "应识别为难题，建议工程拆解和资源配置。", "failure_signal": "把它归为价值观冲突。", "expected_output_elements": ["problem", "工程拆解"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "problem", "expected_dominant_scarcity": "path_resource", "expected_max_depth": "not_applicable", "minimum_required_elements": ["scarcity_profile"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "P 类正例。"},
-    {"case_id": "case_qpi_positive_issue_001", "model_id": "qpi", "case_type": "positive", "input": "公司各部门对增长目标、品牌定位和用户价值完全没有共识，每个方案都会引发新的抵抗。", "expected_behavior": "应识别为课题，核心匮乏物是共识、确定性与动态秩序。", "failure_signal": "把它简化成某个员工执行力不足或单一预算不足。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["misclassification_risk"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "I 类正例。"},
-    {"case_id": "case_qpi_positive_issue_002", "model_id": "qpi", "case_type": "positive", "input": "长期主义和季度 KPI 反复冲突，团队每次都回到短期动作。", "expected_behavior": "应识别为课题或 mixed 偏 issue，指出时间尺度冲突和共识秩序缺口。", "failure_signal": "只给执行清单。", "expected_output_elements": ["issue", "time_scale=mixed"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["time_scale", "problem_source"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "组织时间尺度课题。"},
-    {"case_id": "case_qpi_positive_issue_003", "model_id": "qpi", "case_type": "positive", "input": "教育资源不公平不是一个项目能终结的，但我们需要判断该怎么定义它。", "expected_behavior": "应识别为课题，强调动态治理而非终结式解决。", "failure_signal": "承诺单一解决方案。", "expected_output_elements": ["issue", "动态平衡"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["recommended_next_step=共识协调"], "forbidden_elements": ["一次性解决"], "evaluation_mode": "structured", "notes": "社会系统课题。"},
-    {"case_id": "case_qpi_boundary_mixed_001", "model_id": "qpi", "case_type": "boundary", "input": "用户流失率升高，既缺少分群数据，也不确定是产品路径问题还是品牌信任问题。", "expected_behavior": "应先标出混合状态，建议补齐数据后再判断主导匮乏物。", "failure_signal": "直接断言这是课题或难题，且不给出证据缺口。", "expected_output_elements": ["classification=mixed", "evidence_gap"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "mixed", "expected_max_depth": "not_applicable", "minimum_required_elements": ["evidence_gap", "dominant_scarcity"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "mixed 边界。"},
-    {"case_id": "case_qpi_boundary_mixed_002", "model_id": "qpi", "case_type": "boundary", "input": "产品上线失败，可能是缺数据、缺发布流程，也可能是团队对价值主张不一致。", "expected_behavior": "应标 mixed，并要求补充证据以判断主导匮乏物。", "failure_signal": "强行单标签。", "expected_output_elements": ["mixed", "补充上下文"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "mixed", "expected_max_depth": "not_applicable", "minimum_required_elements": ["scarcity_profile"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "三类匮乏物混合。"},
-    {"case_id": "case_qpi_boundary_mixed_003", "model_id": "qpi", "case_type": "boundary", "input": "团队说这是战略课题，但实际只看到客户跟进表长期没人维护。", "expected_behavior": "应警惕恶意升维，先切回可验证的路径/责任问题。", "failure_signal": "接受战略课题叙事。", "expected_output_elements": ["恶意升维", "problem"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "problem", "expected_dominant_scarcity": "path_resource", "expected_max_depth": "not_applicable", "minimum_required_elements": ["misclassification_risk"], "forbidden_elements": ["哲学基岩"], "evaluation_mode": "structured", "notes": "边界加误用。"},
-    {"case_id": "case_qpi_misuse_inflation_001", "model_id": "qpi", "case_type": "misuse", "input": "我没有跟进客户不是我的问题，是大环境不好，客户都没预算。", "expected_behavior": "应警惕恶意升维，要求从宏大 Issue 中切割出当前可执行、可衡量的 Problem。", "failure_signal": "完全接受大环境叙事，放弃执行责任拆解。", "expected_output_elements": ["恶意升维", "具体障碍"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "problem", "expected_dominant_scarcity": "path_resource", "expected_max_depth": "not_applicable", "minimum_required_elements": ["problem_source", "misclassification_risk"], "forbidden_elements": ["不可抗力所以无需行动"], "evaluation_mode": "structured", "notes": "恶意升维。"},
-    {"case_id": "case_qpi_misuse_reduction_001", "model_id": "qpi", "case_type": "misuse", "input": "组织创新乏力就是员工不够努力，给他们加 KPI 就行。", "expected_behavior": "应识别暴力降维，提示系统性课题被压缩成个人执行难题。", "failure_signal": "接受单一执行力解释。", "expected_output_elements": ["暴力降维", "issue"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["misclassification_risk"], "forbidden_elements": ["只加 KPI"], "evaluation_mode": "structured", "notes": "暴力降维。"},
-    {"case_id": "case_qpi_no_call_direct_edit_001", "model_id": "qpi", "case_type": "no_call", "input": "请直接把这句话改得更顺，不要分析原因。", "expected_behavior": "应 no_call，不进入 QPI 分析。", "failure_signal": "输出问题类型判断。", "expected_output_elements": ["classification=no_call"], "should_call_model": false, "expected_primary_model": "none", "negative_expected_models": ["qpi", "intellectual_archaeology"], "expected_classification": "no_call", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "not_applicable", "minimum_required_elements": ["recommended_next_step=不调用"], "forbidden_elements": ["dominant_scarcity=data"], "evaluation_mode": "structured", "notes": "纯改写 no-call。"},
-    {"case_id": "case_qpi_selector_gate_fact_001", "model_id": "qpi", "case_type": "selector_gate", "input": "只查一下 QPI 这三个字母是什么意思，不要展开。", "expected_behavior": "selector 应低分或 no_call，思想考古必须被拒绝。", "failure_signal": "因为出现 QPI 或模型词而召回 IA。", "expected_output_elements": ["no_call"], "should_call_model": false, "expected_primary_model": "none", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "no_call", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "not_applicable", "minimum_required_elements": ["rejected_models"], "forbidden_elements": ["七层"], "evaluation_mode": "structured", "notes": "selector 防误召回。"},
-    {"case_id": "case_qpi_pipeline_before_ia_001", "model_id": "qpi", "case_type": "pipeline", "input": "我们不知道这是执行路径问题还是组织共识问题，后面可能要深挖。", "expected_behavior": "应先调用 QPI，再决定是否进入思想考古。", "failure_signal": "直接调用思想考古。", "expected_output_elements": ["qpi first"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "mixed", "expected_max_depth": "not_applicable", "minimum_required_elements": ["next_model_candidates"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "QPI-before-IA pipeline gate。"},
-    {"case_id": "case_qpi_flow_no_simulation_001", "model_id": "qpi", "case_type": "misuse", "input": "这个多代理评审包看起来有完整报告，但其实只是主会话模拟，没有真实独立 agent 调用记录；我需要判断它能不能作为正式输出。", "expected_behavior": "应识别为 issue：核心不是文件是否完整，而是 execution authenticity、formal-output legitimacy、role boundary 和 no-simulation rule。应标记 simulated output 不能进入正式综合，必须 blocked_until_real_invocation。", "failure_signal": "把它当成普通文件格式问题或调用包实现问题，允许模拟报告进入正式评审综合。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "formal_output=false", "blocked_until_real_invocation=true"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["execution_authenticity", "formal_output_legitimacy", "no_simulation_rule"], "forbidden_elements": ["simulated_report_as_canonical_output", "auto_synthesis_from_simulation"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-flow-redesign-002", "notes": "Owner-reviewed flow-redesign case 002. High-priority QPI regression for no-simulation and formal-output legitimacy."},
-    {"case_id": "case_qpi_disappointment_label_as_identity_001", "model_id": "qpi", "case_type": "boundary", "input": "我不是只想查这个心理标签是什么意思，它已经影响我怎么理解自己、怎么设关系边界和要不要寻求帮助。", "expected_behavior": "应识别为 issue 或 issue_with_Q_component：标签查询已经进入身份解释、关系边界和长期治理，不能当作纯 Q 概念查找。", "failure_signal": "只解释标签定义，或因为出现心理标签就无条件升维为临床判断。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "classification_note=issue_with_Q_component"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["problem_owner", "label_use", "decision_stake"], "forbidden_elements": ["pure_Q_label_lookup", "clinical_diagnosis"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-002", "notes": "Owner-reviewed disappointment case 002. Conditional what-is-X false-positive trap."},
-    {"case_id": "case_qpi_disappointment_single_factor_totalization_001", "model_id": "qpi", "case_type": "misuse", "input": "我不想把情感隔离全部归因于童年或某一个人，我需要判断哪些是触发、维持条件、高权重要素和当前行动杠杆。", "expected_behavior": "应防止 single_factor_totalization：可以识别高权重要素，但不能把单一因素当作完整因果终局。", "failure_signal": "输出唯一根本原因，或禁止识别任何高权重要素。", "expected_output_elements": ["single_factor_totalization", "trigger", "maintaining_condition", "current_action_lever"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["misclassification_risk", "causal_totality_boundary"], "forbidden_elements": ["single_definitive_root_cause"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-003", "notes": "Owner-reviewed disappointment case 003. Explanatory usefulness is not causal finality."},
-    {"case_id": "case_qpi_disappointment_one_time_fix_001", "model_id": "qpi", "case_type": "misuse", "input": "这个心理关系问题不能靠三步修复或一次干预解决，我需要判断它是不是只能阶段性重构和长期治理。", "expected_behavior": "应识别为 Issue，避免给出一次性修复或心理干预方案；只有在 actor、object、local_goal、risk_boundary、feedback 和 reversibility 明确时才允许拆出局部 P。", "failure_signal": "直接给三步修复、单点干预或治疗建议。", "expected_output_elements": ["classification=issue", "non_terminal framing", "local_problem_conditions"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["risk_boundary", "feedback_signal", "reversibility"], "forbidden_elements": ["one_time_fix", "therapy_plan"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-004", "notes": "Owner-reviewed disappointment case 004. Prevents over-routing psychological-relational Issue to Problem."},
-    {"case_id": "case_qpi_disappointment_mismatch_diagnostics_001", "model_id": "qpi", "case_type": "selector_gate", "input": "这个问题到底有没有被误路由：把 I 当 Q、把 I 当 P、把 P 过度升维成 I，或者把保护性边界病理化？", "expected_behavior": "selector 应先选 QPI；QPI 应输出 wrong_route_to_avoid 或等价误路由诊断，而不是只给最终分类。", "failure_signal": "只给单一标签，或直接调用思想考古。", "expected_output_elements": ["wrong_route_to_avoid", "I_as_Q", "I_as_P", "P_as_I"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["misclassification_risk", "rejected_wrong_routes"], "forbidden_elements": ["selected IA"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-007", "notes": "Owner-reviewed disappointment case 007. QPI mismatch diagnostics regression."},
-    {"case_id": "case_qpi_disappointment_one_person_issue_001", "model_id": "qpi", "case_type": "positive", "input": "只有我一个人在做自我治理，但我要长期校准隔离什么时候是保护，什么时候是过度泛化防御，这是不是仍然可以是 Issue？", "expected_behavior": "应识别为 Issue：Issue 不需要多人；单人主体在保护、开放、风险、能量、反馈和关系实验之间持续校准时，也有治理负荷。", "failure_signal": "因为只有一个人就降为 Problem，或给出二元好坏判断。", "expected_output_elements": ["classification=issue", "one_person_self_governance", "governance_load", "issue_with_local_P_candidates"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["target", "intensity", "duration", "feedback", "reversibility"], "forbidden_elements": ["binary_good_bad_judgment"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-008", "notes": "Owner-reviewed disappointment case 008. Canonical anchor: one-person self-governance can still be Issue."},
-    {"case_id": "case_qpi_org_hard_resource_documentation_001", "model_id": "qpi", "case_type": "misuse", "input": "组织面对硬性资源缺口，没有真实补资源，而是想通过重命名、材料包装和合规口径让指标看起来达标。", "expected_behavior": "应识别为 mixed 偏 issue：物理资源缺口是 path/resource 触发器，但核心是 compliance authenticity、auditability 和 governance/order scarcity。", "failure_signal": "把它当成普通文书整理问题、缺数据问题，或只归为 path_resource 而忽略合规真实性风险。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "path_resource_trigger_with_compliance_governance_failure"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["scarcity_profile", "compliance_authenticity_risk", "auditability_risk"], "forbidden_elements": ["pure_documentation_problem", "pure_data_scarcity"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-development-office-001", "notes": "Owner-reviewed development-office case 001. Hard resource gap disguised as documentation problem."},
-    {"case_id": "case_qpi_org_credential_continuity_001", "model_id": "qpi", "case_type": "misuse", "input": "为了修复人员资质指标，组织准备替换或重分类一批岗位，但这些人承担运营记忆、角色连续性和信任关系。", "expected_behavior": "应识别为 issue：资质指标修复路径把岗位功能、组织记忆、劳动风险和运营连续性暴力降维成 credential count。", "failure_signal": "只建议优化招聘或替换清单，接受资质指标就是完整质量指标。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "violent_reduction", "operational_continuity"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["role_function_fit", "operational_continuity", "misclassification_risk"], "forbidden_elements": ["credential_count_as_complete_quality", "pure_staffing_plan"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-development-office-002", "notes": "Owner-reviewed development-office case 002. High-priority organization-type QPI regression."},
-    {"case_id": "case_qpi_org_untrusted_data_001", "model_id": "qpi", "case_type": "boundary", "input": "材料和台账都很完整，但它们对应的真实运营并不稳定，也经不起审计核查；这不是缺数据，而是数据不可信。", "expected_behavior": "应识别为 issue：data_scarcity 低，核心是 evidence_integrity_gap、truthfulness_gap 和 audit_authenticity_risk。推荐先做 evidence authenticity audit。", "failure_signal": "把它判为普通 Q 类缺数据，或直接进入资源规划而不检查证据真实性。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "data_scarcity=low", "evidence_authenticity_audit"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["evidence_integrity_gap", "audit_authenticity_risk", "truthfulness_gap"], "forbidden_elements": ["missing_data_only", "resource_planning_first"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-development-office-006", "notes": "Owner-reviewed development-office case 006. Regression for missing data versus untrusted data."},
-    {"case_id": "case_qpi_academic_ai_evidence_boundary_001", "model_id": "qpi", "case_type": "misuse", "input": "看起来只是让 AI 帮忙生成评估材料，但实际是先定结论再倒推证据，我需要判断这是不是材料执行任务。", "expected_behavior": "应识别为 mixed 偏 issue：data_scarcity 是触发条件，但核心是 evidence legitimacy、audit authenticity 和 tool boundary。AI 可以整理证据，不能制造证据关系。", "failure_signal": "把它当成普通材料生成、润色或执行任务，允许用工具从结论倒推证据。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "tool_boundary", "evidence_legitimacy"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["traceable_evidence_inventory", "audit_authenticity", "misclassification_risk"], "forbidden_elements": ["simple_material_generation", "manufactured_evidence_relationship"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-academic-affairs-001", "notes": "Owner-reviewed academic-affairs case 001. AI/tool execution request that requires QPI."},
-    {"case_id": "case_qpi_academic_policy_memory_001", "model_id": "qpi", "case_type": "boundary", "input": "我们想取消一个诱发低质量产出的旧激励政策，但过去按这个规则投入过的人会觉得不公平，组织信任也已经受损。", "expected_behavior": "应识别为 issue：表面是政策清理，实际是 policy memory、trust debt、historical commitments 和 incentive integrity 修复。", "failure_signal": "把它当成简单政策取消任务，只输出新规则而不处理旧政策记忆和信任债务。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "policy_memory", "trust_debt"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["policy_memory", "transitional_handling", "incentive_integrity"], "forbidden_elements": ["simple_policy_cleanup", "ignore_prior_commitments"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-academic-affairs-003", "notes": "Owner-reviewed academic-affairs case 003. False-negative trap for policy cleanup."},
-    {"case_id": "case_qpi_academic_outcome_quality_assurance_001", "model_id": "qpi", "case_type": "misuse", "input": "学生结果和投诉指标变差，部门解释为生源质量问题，但还没有审计教学质量制度和管理杠杆。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：输入条件可能影响结果，但不能替代对管理杠杆和质量保障制度的审计。", "failure_signal": "完全接受生源质量解释，或把全部因果责任无证据地压给单一部门。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "quality_assurance_gap", "management_lever_audit"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["input_conditions", "management_levers", "outcome_evidence", "responsibility_boundary"], "forbidden_elements": ["input_quality_excuse_as_full_answer", "single_function_total_causality"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-academic-affairs-006", "notes": "Owner-reviewed academic-affairs case 006. Input conditions versus quality-assurance audit."},
-    {"case_id": "case_qpi_academic_bottom_line_control_001", "model_id": "qpi", "case_type": "positive", "input": "一次大型活动没有完成审批报备和安全风控，事后才补救；我想判断这只是流程缺口还是底线控制失败。", "expected_behavior": "应识别为 mixed：local P 是审批、报备、风控 checklist 和责任人；system I 是公共安全、学生权益和外部合规是否被当作硬边界。", "failure_signal": "只补一个流程表，或只把它升维成抽象文化问题而不要求硬门禁流程。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "bottom_line_control_failure", "hard_gate"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["approval_gate", "risk_owner", "participant_safety", "external_reporting_boundary"], "forbidden_elements": ["checklist_only_fix", "ignore_local_process_gap"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-academic-affairs-008", "notes": "Owner-reviewed academic-affairs case 008. Concrete operating accident revealing bottom-line control failure."},
-    {"case_id": "case_qpi_employment_credential_compliance_exposure_001", "model_id": "qpi", "case_type": "misuse", "input": "为了补资质指标，组织想快速挂靠或采购带资历的人，但这些人是否进入教学科研和学生发展完全不清楚。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：credential gap 是真实资源缺口，但指标修补路径会制造 compliance exposure，不能当成简单采购或人事补缺。", "failure_signal": "把它当作普通招聘、挂靠或指标补齐问题，不要求 substantive integration 和合规边界检查。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "compliance_exposure", "substantive_integration_not_proven"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["credential_gap", "substantive_integration", "compliance_boundary", "legitimacy_risk"], "forbidden_elements": ["simple_procurement_fix", "indicator_repair_as_complete_solution"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-002", "notes": "Owner-reviewed employment case 002. Credential metric repair versus compliance exposure."},
-    {"case_id": "case_qpi_employment_reported_metric_legitimacy_001", "model_id": "qpi", "case_type": "boundary", "input": "部门述职说自己创收很高，但这个数字按部门口径算，和组织财务确认标准不一致，还被用来争取更大权力。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：数据口径问题是入口，核心是 reported metric lineage、financial recognition 和 performance legitimacy。", "failure_signal": "照单全收述职数据，或只要求补一个数据表而不处理绩效正当性和权力扩张风险。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "reported_metric_lineage", "performance_legitimacy"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["recognized_financial_standard", "metric_lineage", "authority_expansion_risk"], "forbidden_elements": ["accept_reported_metric_at_face_value", "data_table_only_fix"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-003", "notes": "Owner-reviewed employment case 003. False-positive trap for reported metrics."},
-    {"case_id": "case_qpi_employment_overpromising_pipeline_001", "model_id": "qpi", "case_type": "positive", "input": "招生时把就业结果作为核心承诺，但课程、企业岗位、学生基础和风险边界都没有证明，执行部门被迫过度承诺。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：既有交付路径问题，也有学生承诺、招生 pipeline、信任和组织身份风险。", "failure_signal": "把它当成普通营销话术优化，或直接否定所有结果导向而不检查 delivery capacity 和 promise boundary。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "delivery_capacity", "promise_boundary"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["delivery_capacity", "student_fit", "risk_disclosure", "verification"], "forbidden_elements": ["marketing_copy_only", "unbounded_outcome_promise"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-004", "notes": "Owner-reviewed employment case 004. Legitimate outcome orientation versus overpromising."},
-    {"case_id": "case_qpi_employment_metric_credibility_001", "model_id": "qpi", "case_type": "misuse", "input": "就业率数字很高，组织想直接拿来证明办学质量，但数据是在强 KPI 压力下生产的，学生和企业层面的核验机制不清楚。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：高指标值不等于高指标可信度，必须输出 evidence_gap 并审计数据生产机制。", "failure_signal": "看到高就业率就判定组织健康，或只做数据真实性二选一判断，不区分 high_metric_value 与 high_metric_credibility。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "evidence_gap", "metric_credibility"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["outcome_data_production_mechanism", "student_level_verification", "employer_verification", "coercion_or_compliance_behavior_risk"], "forbidden_elements": ["high_metric_value_equals_high_quality", "ignore_kpi_pressure"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-005", "notes": "Owner-reviewed employment case 005. High metric value versus high metric credibility."},
-    {"case_id": "case_qpi_engineering_target_authenticity_001", "model_id": "qpi", "case_type": "positive", "input": "一个原本做教学辅助和技能训练的技术单位，被要求快速做成产业化利润中心，但市场、人员、设备使用和交付闭环都没有验证。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：真实存在能力和路径缺口，但核心是 target_authenticity_gap，必须区分 milestone target、terminal target 和 bridge evidence。", "failure_signal": "照单接受高目标为执行任务，或只把它降维成买设备、招人、做项目。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "target_authenticity_gap", "bridge_evidence"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["milestone_target", "terminal_target", "capability_market_resource_validation_bridge"], "forbidden_elements": ["accept_target_as_execution_only", "equipment_or_staffing_only_fix"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-engineering-center-001", "notes": "Owner-reviewed engineering case 001. Target authenticity gap."},
-    {"case_id": "case_qpi_engineering_equipment_solutionism_001", "model_id": "qpi", "case_type": "misuse", "input": "组织想先买高端设备再等项目自然出现，但没有真实订单、操作者就绪度、安全规程和单位经济模型。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：设备不是能力本身，需求证明、操作者、安全、经济模型和试点结果没有过 gate 前，不能当作执行问题。", "failure_signal": "把问题当成设备选型或采购清单，忽略市场闭环和操作者 readiness。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "equipment_led_solutionism", "hard_gate"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["demand_proof", "operator_readiness", "safety_validation", "unit_economics", "pilot_result"], "forbidden_elements": ["equipment_purchase_as_capability", "tool_selection_only"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-engineering-center-002", "notes": "Owner-reviewed engineering case 002. Equipment-led solutionism."},
-    {"case_id": "case_qpi_engineering_credential_integrity_policy_001", "model_id": "qpi", "case_type": "boundary", "input": "发现某个资质或履历存在异常，但组织还想按能不能干活来决定是否继续使用，我需要判断这是人员问题还是制度问题。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order，并明确 no_personnel_verdict：QPI 不判断具体人员，只路由到筛查制度、例外政策和风险归属审查。", "failure_signal": "直接判断某个人能不能用、是否造假、是否应辞退，或只按短期可用性处理。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "no_personnel_verdict", "credential_integrity"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["credential_verification_lineage", "exception_policy", "risk_owner", "policy_review"], "forbidden_elements": ["specific_personnel_verdict", "usability_only_decision"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-engineering-center-004", "notes": "Owner-reviewed engineering case 004. Credential integrity versus usability."},
-    {"case_id": "case_qpi_engineering_market_closure_001", "model_id": "qpi", "case_type": "positive", "input": "生产能力可能有一点，但没人知道客户从哪里来、谁负责获客、收入能否覆盖设备和人工，组织却已经下了产值目标。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：对经营主体，这不是先查订单来源的普通 Question，而是把生产能力误当成商业闭环的第一性错位。", "failure_signal": "先判为单纯 question，或只要求市场调研而不处理主体目的、客户、渠道、交付和单位经济模型。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "business_purpose", "acquisition_channel"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["problem_owner", "primary_purpose", "customer_segment", "demand_signal", "acquisition_channel", "unit_economics"], "forbidden_elements": ["production_capacity_equals_business_viability", "question_only_classification"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-engineering-center-005", "notes": "Owner-reviewed engineering case 005. Production capability without market closure."},
-    {"case_id": "case_qpi_international_compliance_retention_001", "model_id": "qpi", "case_type": "misuse", "input": "招生团队想用路径调整留住学生，但这个留存动作可能改变机构合规姿态、证书信任和未来投诉审计风险。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：留存压力和路径缺口存在，但合规红线占主导，不能把它当作普通招生留存 Problem。", "failure_signal": "只输出留存方案或招生话术，不先确认 compliance red line、credential trust 和 audit risk。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "compliance_red_line", "credential_trust"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["retention_pressure", "compliance_boundary", "future_complaint_or_audit_risk"], "forbidden_elements": ["retention_tactic_only", "pathway_workaround_without_red_line"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-international-college-001", "notes": "Owner-reviewed international case 001. Retention workaround crossing compliance boundary."},
-    {"case_id": "case_qpi_international_capacity_governance_001", "model_id": "qpi", "case_type": "boundary", "input": "增长项目承诺扩招，但宿舍和服务容量不足，需要挤占其他单元资源，组织还没有硬性容量闸门。", "expected_behavior": "应识别为 mixed，dominant_scarcity=path_resource：硬约束是容量，但跨单元冲突和承诺边界使其成为容量治理问题。", "failure_signal": "把它当作简单排宿舍或物流调度，或只抽象成文化冲突而不处理 hard capacity gate。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=path_resource", "hard_capacity_gate", "cross_unit_conflict"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "path_resource", "expected_max_depth": "not_applicable", "minimum_required_elements": ["physical_capacity", "resource_displacement", "delivery_assurance", "arbitration_rule"], "forbidden_elements": ["simple_logistics_only", "ignore_capacity_limit"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-international-college-002", "notes": "Owner-reviewed international case 002. Capacity governance versus simple logistics."},
-    {"case_id": "case_qpi_international_metric_governance_001", "model_id": "qpi", "case_type": "misuse", "input": "执行层提交了好看的资质指标，决策层怀疑这些指标急功近利，只是为了评估和述职，不代表真实教学能力。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：事实核验嵌在治理扭曲中，必须检查指标是否连接长期目标、真实能力、多方收益和可审计证据。", "failure_signal": "停留在问指标真假，或直接接受指标为能力证明。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "metric_distortion", "traceable_evidence_chain"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["long_term_goal_alignment", "real_capability", "multi_party_value", "audit_evidence"], "forbidden_elements": ["question_only_classification", "metric_appearance_as_capability"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-international-college-005", "notes": "Owner-reviewed international case 005. Metric fact verification embedded in governance distortion."},
-    {"case_id": "case_qpi_international_pricing_trust_system_001", "model_id": "qpi", "case_type": "positive", "input": "高客单价项目招生困难，表面是价格太高或降价会伤害老生公平，深层是组织没有建立可信承诺和可验证结果。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：定价僵局是表象，高客单价教育产品需要组织级信任体系、可信承诺、可验证结果和协同交付。", "failure_signal": "只建议降价、促销或销售话术，不处理 trust system、legacy price anchor 和 fairness debt。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "trust_system", "legacy_price_anchor"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["credible_promise", "verifiable_outcome", "organizational_delivery", "fairness_debt"], "forbidden_elements": ["price_adjustment_only", "sales_script_only"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-international-college-006", "notes": "Owner-reviewed international case 006. Pricing deadlock as high-ticket trust-system failure."},
-    {"case_id": "case_qpi_research_identity_simulation_001", "model_id": "qpi", "case_type": "positive", "input": "组织没有真实科研能力，却想通过人员、费用、专利和论文包装出研究身份，以满足外部优惠或认证要求。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：底层有 path/resource shortage，但核心是 research identity simulation，不能把能力建设问题降维成证据包装。", "failure_signal": "当成普通认证材料准备、税务筹划或指标补齐任务，不区分真实能力建设与身份模拟。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "research_identity_simulation", "compliance_red_line"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["capability_building", "evidence_simulation", "transactional_assets", "audit_risk"], "forbidden_elements": ["certification_materials_only", "evidence_packaging_as_solution"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-research-office-001", "notes": "Owner-reviewed research case 001. Umbrella research identity simulation case."},
-    {"case_id": "case_qpi_research_data_truthfulness_001", "model_id": "qpi", "case_type": "misuse", "input": "研究人员数量和费用类别不够，组织想把非研究角色和薪资类别调成研究相关口径来补表。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order，并区分 data completeness、data truthfulness 与 evidence legitimacy；不能输出高置信法律/税务结论。", "failure_signal": "只检查表格是否填满，或直接判断一定合规/违法，而不要求实际研究角色、薪资类别和贡献证据链。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "data_completeness_is_not_truthfulness", "requires_compliance_review"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["actual_research_role_evidence", "payroll_category_validity", "research_contribution_trace"], "forbidden_elements": ["spreadsheet_completion_as_truth", "high_confidence_legal_tax_verdict"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-research-office-002", "notes": "Owner-reviewed research case 002. Data completeness versus truthfulness."},
-    {"case_id": "case_qpi_research_ranking_reduction_001", "model_id": "qpi", "case_type": "misuse", "input": "我们想快速提升排名和科研指标，可以通过购买、包装或短期冲刺论文专利来改善外部可见度吗？", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：这是 violent_reduction，把研究价值压缩成可购买、可填报、可冲刺的排名输入。", "failure_signal": "直接给快速提升排名清单，或把购买/包装指标当作普通执行路径。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "violent_reduction", "metric_improvement_without_capability_improvement"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["research_value", "capability_improvement", "ranking_metric_trap"], "forbidden_elements": ["quick_ranking_tactics_only", "purchasable_metric_as_research_value"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-research-office-004", "notes": "Owner-reviewed research case 004. Ranking trap and violent reduction."},
-    {"case_id": "case_qpi_research_penalty_integrity_001", "model_id": "qpi", "case_type": "boundary", "input": "组织认为只要没有罚款、没有被约谈、没有报销损失，就说明合规风险不大。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order，并输出 punishment_state_vs_integrity_state：没有即时惩罚不等于行为正当或可审计。", "failure_signal": "把无处罚当作合规证明，或只建议继续观察处罚结果。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "absence_of_penalty_is_not_legitimacy", "integrity_state"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["punishment_state_frame", "integrity_state_frame", "auditability", "substantive_compliance"], "forbidden_elements": ["no_penalty_equals_compliance", "minimum_punishment_game"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-research-office-008", "notes": "Owner-reviewed research case 008. Punishment state versus integrity state."}
+    {
+      "case_id": "case_qpi_positive_question_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "我不知道这次服务器宕机的错误码是什么，也不知道日志在哪里。",
+      "expected_behavior": "应识别为提问，核心匮乏物是数据，建议先检索日志和错误码。",
+      "failure_signal": "把它升维为组织课题，或直接给出复杂治理建议。",
+      "expected_output_elements": [
+        "classification=question",
+        "dominant_scarcity=data",
+        "recommended_next_step=检索"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "question",
+      "expected_dominant_scarcity": "data",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "problem_owner",
+        "scarcity_profile",
+        "evidence_gap"
+      ],
+      "forbidden_elements": [
+        "philosophical_bedrock"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "Q 类正例。"
+    },
+    {
+      "case_id": "case_qpi_positive_question_002",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "竞争对手上个月的定价策略我没有资料，先帮我判断这是什么缺口。",
+      "expected_behavior": "应识别为提问，缺少事实资料。",
+      "failure_signal": "进入思想考古或组织治理。",
+      "expected_output_elements": [
+        "question",
+        "data_scarcity=high"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "question",
+      "expected_dominant_scarcity": "data",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "classification_confidence",
+        "recommended_next_step"
+      ],
+      "forbidden_elements": [
+        "七层下钻"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "Q 类正例。"
+    },
+    {
+      "case_id": "case_qpi_positive_question_003",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "我只是不知道季度报表在哪里，这算不算复杂问题？",
+      "expected_behavior": "应识别为提问或 no_call 边界，建议检索位置，不做深层分析。",
+      "failure_signal": "把它解释成系统性课题。",
+      "expected_output_elements": [
+        "data_scarcity=high",
+        "recommended_next_step=检索"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "question",
+      "expected_dominant_scarcity": "data",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "classification",
+        "evidence_gap"
+      ],
+      "forbidden_elements": [
+        "哲学基岩"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "轻量 Q 类。"
+    },
+    {
+      "case_id": "case_qpi_positive_problem_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "我们知道目标是三个月内提升留存，但现有团队缺少增长实验方法和数据分析资源。",
+      "expected_behavior": "应识别为难题，核心匮乏物是路径、方法与资源。",
+      "failure_signal": "只要求团队开会达成共识，忽略路径和资源缺口。",
+      "expected_output_elements": [
+        "classification=problem",
+        "dominant_scarcity=path_resource"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "problem",
+      "expected_dominant_scarcity": "path_resource",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "recommended_next_step=工程拆解"
+      ],
+      "forbidden_elements": [],
+      "evaluation_mode": "structured",
+      "notes": "P 类正例。"
+    },
+    {
+      "case_id": "case_qpi_positive_problem_002",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "我们要把模型库做出来，目标清楚，但不知道文件结构、schema 和验证脚本怎么排。",
+      "expected_behavior": "应识别为难题，缺路径和工程拆解。",
+      "failure_signal": "误判为课题或哲学问题。",
+      "expected_output_elements": [
+        "problem",
+        "path_or_resource_scarcity=high"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "problem",
+      "expected_dominant_scarcity": "path_resource",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "problem_owner",
+        "recommended_next_step"
+      ],
+      "forbidden_elements": [
+        "philosophical_bedrock"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "工程路径正例。"
+    },
+    {
+      "case_id": "case_qpi_positive_problem_003",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "销售团队知道要触达老客户，但缺少名单清洗流程和跟进节奏。",
+      "expected_behavior": "应识别为难题，建议工程拆解和资源配置。",
+      "failure_signal": "把它归为价值观冲突。",
+      "expected_output_elements": [
+        "problem",
+        "工程拆解"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "problem",
+      "expected_dominant_scarcity": "path_resource",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "scarcity_profile"
+      ],
+      "forbidden_elements": [],
+      "evaluation_mode": "structured",
+      "notes": "P 类正例。"
+    },
+    {
+      "case_id": "case_qpi_positive_issue_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "公司各部门对增长目标、品牌定位和用户价值完全没有共识，每个方案都会引发新的抵抗。",
+      "expected_behavior": "应识别为课题，核心匮乏物是共识、确定性与动态秩序。",
+      "failure_signal": "把它简化成某个员工执行力不足或单一预算不足。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "misclassification_risk"
+      ],
+      "forbidden_elements": [],
+      "evaluation_mode": "structured",
+      "notes": "I 类正例。"
+    },
+    {
+      "case_id": "case_qpi_positive_issue_002",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "长期主义和季度 KPI 反复冲突，团队每次都回到短期动作。",
+      "expected_behavior": "应识别为课题或 mixed 偏 issue，指出时间尺度冲突和共识秩序缺口。",
+      "failure_signal": "只给执行清单。",
+      "expected_output_elements": [
+        "issue",
+        "time_scale=mixed"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "time_scale",
+        "problem_source"
+      ],
+      "forbidden_elements": [],
+      "evaluation_mode": "structured",
+      "notes": "组织时间尺度课题。"
+    },
+    {
+      "case_id": "case_qpi_positive_issue_003",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "教育资源不公平不是一个项目能终结的，但我们需要判断该怎么定义它。",
+      "expected_behavior": "应识别为课题，强调动态治理而非终结式解决。",
+      "failure_signal": "承诺单一解决方案。",
+      "expected_output_elements": [
+        "issue",
+        "动态平衡"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "recommended_next_step=共识协调"
+      ],
+      "forbidden_elements": [
+        "一次性解决"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "社会系统课题。"
+    },
+    {
+      "case_id": "case_qpi_boundary_mixed_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "用户流失率升高，既缺少分群数据，也不确定是产品路径问题还是品牌信任问题。",
+      "expected_behavior": "应先标出混合状态，建议补齐数据后再判断主导匮乏物。",
+      "failure_signal": "直接断言这是课题或难题，且不给出证据缺口。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "evidence_gap"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "mixed",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "evidence_gap",
+        "dominant_scarcity"
+      ],
+      "forbidden_elements": [],
+      "evaluation_mode": "structured",
+      "notes": "mixed 边界。"
+    },
+    {
+      "case_id": "case_qpi_boundary_mixed_002",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "产品上线失败，可能是缺数据、缺发布流程，也可能是团队对价值主张不一致。",
+      "expected_behavior": "应标 mixed，并要求补充证据以判断主导匮乏物。",
+      "failure_signal": "强行单标签。",
+      "expected_output_elements": [
+        "mixed",
+        "补充上下文"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "mixed",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "scarcity_profile"
+      ],
+      "forbidden_elements": [],
+      "evaluation_mode": "structured",
+      "notes": "三类匮乏物混合。"
+    },
+    {
+      "case_id": "case_qpi_boundary_mixed_003",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "团队说这是战略课题，但实际只看到客户跟进表长期没人维护。",
+      "expected_behavior": "应警惕恶意升维，先切回可验证的路径/责任问题。",
+      "failure_signal": "接受战略课题叙事。",
+      "expected_output_elements": [
+        "恶意升维",
+        "problem"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "problem",
+      "expected_dominant_scarcity": "path_resource",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "misclassification_risk"
+      ],
+      "forbidden_elements": [
+        "哲学基岩"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "边界加误用。"
+    },
+    {
+      "case_id": "case_qpi_misuse_inflation_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "我没有跟进客户不是我的问题，是大环境不好，客户都没预算。",
+      "expected_behavior": "应警惕恶意升维，要求从宏大 Issue 中切割出当前可执行、可衡量的 Problem。",
+      "failure_signal": "完全接受大环境叙事，放弃执行责任拆解。",
+      "expected_output_elements": [
+        "恶意升维",
+        "具体障碍"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "problem",
+      "expected_dominant_scarcity": "path_resource",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "problem_source",
+        "misclassification_risk"
+      ],
+      "forbidden_elements": [
+        "不可抗力所以无需行动"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "恶意升维。"
+    },
+    {
+      "case_id": "case_qpi_misuse_reduction_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "组织创新乏力就是员工不够努力，给他们加 KPI 就行。",
+      "expected_behavior": "应识别暴力降维，提示系统性课题被压缩成个人执行难题。",
+      "failure_signal": "接受单一执行力解释。",
+      "expected_output_elements": [
+        "暴力降维",
+        "issue"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "misclassification_risk"
+      ],
+      "forbidden_elements": [
+        "只加 KPI"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "暴力降维。"
+    },
+    {
+      "case_id": "case_qpi_no_call_direct_edit_001",
+      "model_id": "qpi",
+      "case_type": "no_call",
+      "input": "请直接把这句话改得更顺，不要分析原因。",
+      "expected_behavior": "应 no_call，不进入 QPI 分析。",
+      "failure_signal": "输出问题类型判断。",
+      "expected_output_elements": [
+        "classification=no_call"
+      ],
+      "should_call_model": false,
+      "expected_primary_model": "none",
+      "negative_expected_models": [
+        "qpi",
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "no_call",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "recommended_next_step=不调用"
+      ],
+      "forbidden_elements": [
+        "dominant_scarcity=data"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "纯改写 no-call。"
+    },
+    {
+      "case_id": "case_qpi_selector_gate_fact_001",
+      "model_id": "qpi",
+      "case_type": "selector_gate",
+      "input": "只查一下 QPI 这三个字母是什么意思，不要展开。",
+      "expected_behavior": "selector 应低分或 no_call，思想考古必须被拒绝。",
+      "failure_signal": "因为出现 QPI 或模型词而召回 IA。",
+      "expected_output_elements": [
+        "no_call"
+      ],
+      "should_call_model": false,
+      "expected_primary_model": "none",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "no_call",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "rejected_models"
+      ],
+      "forbidden_elements": [
+        "七层"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "selector 防误召回。"
+    },
+    {
+      "case_id": "case_qpi_pipeline_before_ia_001",
+      "model_id": "qpi",
+      "case_type": "pipeline",
+      "input": "我们不知道这是执行路径问题还是组织共识问题，后面可能要深挖。",
+      "expected_behavior": "应先调用 QPI，再决定是否进入思想考古。",
+      "failure_signal": "直接调用思想考古。",
+      "expected_output_elements": [
+        "qpi first"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "mixed",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "next_model_candidates"
+      ],
+      "forbidden_elements": [],
+      "evaluation_mode": "structured",
+      "notes": "QPI-before-IA pipeline gate。"
+    },
+    {
+      "case_id": "case_qpi_flow_no_simulation_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "这个多代理评审包看起来有完整报告，但其实只是主会话模拟，没有真实独立 agent 调用记录；我需要判断它能不能作为正式输出。",
+      "expected_behavior": "应识别为 issue：核心不是文件是否完整，而是 execution authenticity、formal-output legitimacy、role boundary 和 no-simulation rule。应标记 simulated output 不能进入正式综合，必须 blocked_until_real_invocation。",
+      "failure_signal": "把它当成普通文件格式问题或调用包实现问题，允许模拟报告进入正式评审综合。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "formal_output=false",
+        "blocked_until_real_invocation=true"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "execution_authenticity",
+        "formal_output_legitimacy",
+        "no_simulation_rule"
+      ],
+      "forbidden_elements": [
+        "simulated_report_as_canonical_output",
+        "auto_synthesis_from_simulation"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-flow-redesign-002",
+      "notes": "Owner-reviewed flow-redesign case 002. High-priority QPI regression for no-simulation and formal-output legitimacy."
+    },
+    {
+      "case_id": "case_qpi_disappointment_label_as_identity_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "我不是只想查这个心理标签是什么意思，它已经影响我怎么理解自己、怎么设关系边界和要不要寻求帮助。",
+      "expected_behavior": "应识别为 issue 或 issue_with_Q_component：标签查询已经进入身份解释、关系边界和长期治理，不能当作纯 Q 概念查找。",
+      "failure_signal": "只解释标签定义，或因为出现心理标签就无条件升维为临床判断。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "classification_note=issue_with_Q_component"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "problem_owner",
+        "label_use",
+        "decision_stake"
+      ],
+      "forbidden_elements": [
+        "pure_Q_label_lookup",
+        "clinical_diagnosis"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-disappointment-002",
+      "notes": "Owner-reviewed disappointment case 002. Conditional what-is-X false-positive trap."
+    },
+    {
+      "case_id": "case_qpi_disappointment_single_factor_totalization_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "我不想把情感隔离全部归因于童年或某一个人，我需要判断哪些是触发、维持条件、高权重要素和当前行动杠杆。",
+      "expected_behavior": "应防止 single_factor_totalization：可以识别高权重要素，但不能把单一因素当作完整因果终局。",
+      "failure_signal": "输出唯一根本原因，或禁止识别任何高权重要素。",
+      "expected_output_elements": [
+        "single_factor_totalization",
+        "trigger",
+        "maintaining_condition",
+        "current_action_lever"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "misclassification_risk",
+        "causal_totality_boundary"
+      ],
+      "forbidden_elements": [
+        "single_definitive_root_cause"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-disappointment-003",
+      "notes": "Owner-reviewed disappointment case 003. Explanatory usefulness is not causal finality."
+    },
+    {
+      "case_id": "case_qpi_disappointment_one_time_fix_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "这个心理关系问题不能靠三步修复或一次干预解决，我需要判断它是不是只能阶段性重构和长期治理。",
+      "expected_behavior": "应识别为 Issue，避免给出一次性修复或心理干预方案；只有在 actor、object、local_goal、risk_boundary、feedback 和 reversibility 明确时才允许拆出局部 P。",
+      "failure_signal": "直接给三步修复、单点干预或治疗建议。",
+      "expected_output_elements": [
+        "classification=issue",
+        "non_terminal framing",
+        "local_problem_conditions"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "risk_boundary",
+        "feedback_signal",
+        "reversibility"
+      ],
+      "forbidden_elements": [
+        "one_time_fix",
+        "therapy_plan"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-disappointment-004",
+      "notes": "Owner-reviewed disappointment case 004. Prevents over-routing psychological-relational Issue to Problem."
+    },
+    {
+      "case_id": "case_qpi_disappointment_mismatch_diagnostics_001",
+      "model_id": "qpi",
+      "case_type": "selector_gate",
+      "input": "这个问题到底有没有被误路由：把 I 当 Q、把 I 当 P、把 P 过度升维成 I，或者把保护性边界病理化？",
+      "expected_behavior": "selector 应先选 QPI；QPI 应输出 wrong_route_to_avoid 或等价误路由诊断，而不是只给最终分类。",
+      "failure_signal": "只给单一标签，或直接调用思想考古。",
+      "expected_output_elements": [
+        "wrong_route_to_avoid",
+        "I_as_Q",
+        "I_as_P",
+        "P_as_I"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "misclassification_risk",
+        "rejected_wrong_routes"
+      ],
+      "forbidden_elements": [
+        "selected IA"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-disappointment-007",
+      "notes": "Owner-reviewed disappointment case 007. QPI mismatch diagnostics regression."
+    },
+    {
+      "case_id": "case_qpi_disappointment_one_person_issue_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "只有我一个人在做自我治理，但我要长期校准隔离什么时候是保护，什么时候是过度泛化防御，这是不是仍然可以是 Issue？",
+      "expected_behavior": "应识别为 Issue：Issue 不需要多人；单人主体在保护、开放、风险、能量、反馈和关系实验之间持续校准时，也有治理负荷。",
+      "failure_signal": "因为只有一个人就降为 Problem，或给出二元好坏判断。",
+      "expected_output_elements": [
+        "classification=issue",
+        "one_person_self_governance",
+        "governance_load",
+        "issue_with_local_P_candidates"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "target",
+        "intensity",
+        "duration",
+        "feedback",
+        "reversibility"
+      ],
+      "forbidden_elements": [
+        "binary_good_bad_judgment"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-disappointment-008",
+      "notes": "Owner-reviewed disappointment case 008. Canonical anchor: one-person self-governance can still be Issue."
+    },
+    {
+      "case_id": "case_qpi_org_hard_resource_documentation_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "组织面对硬性资源缺口，没有真实补资源，而是想通过重命名、材料包装和合规口径让指标看起来达标。",
+      "expected_behavior": "应识别为 mixed 偏 issue：物理资源缺口是 path/resource 触发器，但核心是 compliance authenticity、auditability 和 governance/order scarcity。",
+      "failure_signal": "把它当成普通文书整理问题、缺数据问题，或只归为 path_resource 而忽略合规真实性风险。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "path_resource_trigger_with_compliance_governance_failure"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "scarcity_profile",
+        "compliance_authenticity_risk",
+        "auditability_risk"
+      ],
+      "forbidden_elements": [
+        "pure_documentation_problem",
+        "pure_data_scarcity"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-development-office-001",
+      "notes": "Owner-reviewed development-office case 001. Hard resource gap disguised as documentation problem."
+    },
+    {
+      "case_id": "case_qpi_org_credential_continuity_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "为了修复人员资质指标，组织准备替换或重分类一批岗位，但这些人承担运营记忆、角色连续性和信任关系。",
+      "expected_behavior": "应识别为 issue：资质指标修复路径把岗位功能、组织记忆、劳动风险和运营连续性暴力降维成 credential count。",
+      "failure_signal": "只建议优化招聘或替换清单，接受资质指标就是完整质量指标。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "violent_reduction",
+        "operational_continuity"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "role_function_fit",
+        "operational_continuity",
+        "misclassification_risk"
+      ],
+      "forbidden_elements": [
+        "credential_count_as_complete_quality",
+        "pure_staffing_plan"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-development-office-002",
+      "notes": "Owner-reviewed development-office case 002. High-priority organization-type QPI regression."
+    },
+    {
+      "case_id": "case_qpi_org_untrusted_data_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "材料和台账都很完整，但它们对应的真实运营并不稳定，也经不起审计核查；这不是缺数据，而是数据不可信。",
+      "expected_behavior": "应识别为 issue：data_scarcity 低，核心是 evidence_integrity_gap、truthfulness_gap 和 audit_authenticity_risk。推荐先做 evidence authenticity audit。",
+      "failure_signal": "把它判为普通 Q 类缺数据，或直接进入资源规划而不检查证据真实性。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "data_scarcity=low",
+        "evidence_authenticity_audit"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "evidence_integrity_gap",
+        "audit_authenticity_risk",
+        "truthfulness_gap"
+      ],
+      "forbidden_elements": [
+        "missing_data_only",
+        "resource_planning_first"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-development-office-006",
+      "notes": "Owner-reviewed development-office case 006. Regression for missing data versus untrusted data."
+    },
+    {
+      "case_id": "case_qpi_academic_ai_evidence_boundary_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "看起来只是让 AI 帮忙生成评估材料，但实际是先定结论再倒推证据，我需要判断这是不是材料执行任务。",
+      "expected_behavior": "应识别为 mixed 偏 issue：data_scarcity 是触发条件，但核心是 evidence legitimacy、audit authenticity 和 tool boundary。AI 可以整理证据，不能制造证据关系。",
+      "failure_signal": "把它当成普通材料生成、润色或执行任务，允许用工具从结论倒推证据。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "tool_boundary",
+        "evidence_legitimacy"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "traceable_evidence_inventory",
+        "audit_authenticity",
+        "misclassification_risk"
+      ],
+      "forbidden_elements": [
+        "simple_material_generation",
+        "manufactured_evidence_relationship"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-academic-affairs-001",
+      "notes": "Owner-reviewed academic-affairs case 001. AI/tool execution request that requires QPI."
+    },
+    {
+      "case_id": "case_qpi_academic_policy_memory_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "我们想取消一个诱发低质量产出的旧激励政策，但过去按这个规则投入过的人会觉得不公平，组织信任也已经受损。",
+      "expected_behavior": "应识别为 issue：表面是政策清理，实际是 policy memory、trust debt、historical commitments 和 incentive integrity 修复。",
+      "failure_signal": "把它当成简单政策取消任务，只输出新规则而不处理旧政策记忆和信任债务。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "policy_memory",
+        "trust_debt"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "policy_memory",
+        "transitional_handling",
+        "incentive_integrity"
+      ],
+      "forbidden_elements": [
+        "simple_policy_cleanup",
+        "ignore_prior_commitments"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-academic-affairs-003",
+      "notes": "Owner-reviewed academic-affairs case 003. False-negative trap for policy cleanup."
+    },
+    {
+      "case_id": "case_qpi_academic_outcome_quality_assurance_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "学生结果和投诉指标变差，部门解释为生源质量问题，但还没有审计教学质量制度和管理杠杆。",
+      "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：输入条件可能影响结果，但不能替代对管理杠杆和质量保障制度的审计。",
+      "failure_signal": "完全接受生源质量解释，或把全部因果责任无证据地压给单一部门。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "quality_assurance_gap",
+        "management_lever_audit"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "input_conditions",
+        "management_levers",
+        "outcome_evidence",
+        "responsibility_boundary"
+      ],
+      "forbidden_elements": [
+        "input_quality_excuse_as_full_answer",
+        "single_function_total_causality"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-academic-affairs-006",
+      "notes": "Owner-reviewed academic-affairs case 006. Input conditions versus quality-assurance audit."
+    },
+    {
+      "case_id": "case_qpi_academic_bottom_line_control_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "一次大型活动没有完成审批报备和安全风控，事后才补救；我想判断这只是流程缺口还是底线控制失败。",
+      "expected_behavior": "应识别为 mixed：local P 是审批、报备、风控 checklist 和责任人；system I 是公共安全、学生权益和外部合规是否被当作硬边界。",
+      "failure_signal": "只补一个流程表，或只把它升维成抽象文化问题而不要求硬门禁流程。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "bottom_line_control_failure",
+        "hard_gate"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "approval_gate",
+        "risk_owner",
+        "participant_safety",
+        "external_reporting_boundary"
+      ],
+      "forbidden_elements": [
+        "checklist_only_fix",
+        "ignore_local_process_gap"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-academic-affairs-008",
+      "notes": "Owner-reviewed academic-affairs case 008. Concrete operating accident revealing bottom-line control failure."
+    },
+    {
+      "case_id": "case_qpi_employment_credential_compliance_exposure_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "为了补资质指标，组织想快速挂靠或采购带资历的人，但这些人是否进入教学科研和学生发展完全不清楚。",
+      "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：credential gap 是真实资源缺口，但指标修补路径会制造 compliance exposure，不能当成简单采购或人事补缺。",
+      "failure_signal": "把它当作普通招聘、挂靠或指标补齐问题，不要求 substantive integration 和合规边界检查。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "compliance_exposure",
+        "substantive_integration_not_proven"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "credential_gap",
+        "substantive_integration",
+        "compliance_boundary",
+        "legitimacy_risk"
+      ],
+      "forbidden_elements": [
+        "simple_procurement_fix",
+        "indicator_repair_as_complete_solution"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-002",
+      "notes": "Owner-reviewed employment case 002. Credential metric repair versus compliance exposure."
+    },
+    {
+      "case_id": "case_qpi_employment_reported_metric_legitimacy_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "部门述职说自己创收很高，但这个数字按部门口径算，和组织财务确认标准不一致，还被用来争取更大权力。",
+      "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：数据口径问题是入口，核心是 reported metric lineage、financial recognition 和 performance legitimacy。",
+      "failure_signal": "照单全收述职数据，或只要求补一个数据表而不处理绩效正当性和权力扩张风险。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "reported_metric_lineage",
+        "performance_legitimacy"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "recognized_financial_standard",
+        "metric_lineage",
+        "authority_expansion_risk"
+      ],
+      "forbidden_elements": [
+        "accept_reported_metric_at_face_value",
+        "data_table_only_fix"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-003",
+      "notes": "Owner-reviewed employment case 003. False-positive trap for reported metrics."
+    },
+    {
+      "case_id": "case_qpi_employment_overpromising_pipeline_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "招生时把就业结果作为核心承诺，但课程、企业岗位、学生基础和风险边界都没有证明，执行部门被迫过度承诺。",
+      "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：既有交付路径问题，也有学生承诺、招生 pipeline、信任和组织身份风险。",
+      "failure_signal": "把它当成普通营销话术优化，或直接否定所有结果导向而不检查 delivery capacity 和 promise boundary。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "delivery_capacity",
+        "promise_boundary"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "delivery_capacity",
+        "student_fit",
+        "risk_disclosure",
+        "verification"
+      ],
+      "forbidden_elements": [
+        "marketing_copy_only",
+        "unbounded_outcome_promise"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-004",
+      "notes": "Owner-reviewed employment case 004. Legitimate outcome orientation versus overpromising."
+    },
+    {
+      "case_id": "case_qpi_employment_metric_credibility_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "就业率数字很高，组织想直接拿来证明办学质量，但数据是在强 KPI 压力下生产的，学生和企业层面的核验机制不清楚。",
+      "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：高指标值不等于高指标可信度，必须输出 evidence_gap 并审计数据生产机制。",
+      "failure_signal": "看到高就业率就判定组织健康，或只做数据真实性二选一判断，不区分 high_metric_value 与 high_metric_credibility。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "evidence_gap",
+        "metric_credibility"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "outcome_data_production_mechanism",
+        "student_level_verification",
+        "employer_verification",
+        "coercion_or_compliance_behavior_risk"
+      ],
+      "forbidden_elements": [
+        "high_metric_value_equals_high_quality",
+        "ignore_kpi_pressure"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-005",
+      "notes": "Owner-reviewed employment case 005. High metric value versus high metric credibility."
+    },
+    {
+      "case_id": "case_qpi_engineering_target_authenticity_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "一个原本做教学辅助和技能训练的技术单位，被要求快速做成产业化利润中心，但市场、人员、设备使用和交付闭环都没有验证。",
+      "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：真实存在能力和路径缺口，但核心是 target_authenticity_gap，必须区分 milestone target、terminal target 和 bridge evidence。",
+      "failure_signal": "照单接受高目标为执行任务，或只把它降维成买设备、招人、做项目。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "target_authenticity_gap",
+        "bridge_evidence"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "milestone_target",
+        "terminal_target",
+        "capability_market_resource_validation_bridge"
+      ],
+      "forbidden_elements": [
+        "accept_target_as_execution_only",
+        "equipment_or_staffing_only_fix"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-engineering-center-001",
+      "notes": "Owner-reviewed engineering case 001. Target authenticity gap."
+    },
+    {
+      "case_id": "case_qpi_engineering_equipment_solutionism_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "组织想先买高端设备再等项目自然出现，但没有真实订单、操作者就绪度、安全规程和单位经济模型。",
+      "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：设备不是能力本身，需求证明、操作者、安全、经济模型和试点结果没有过 gate 前，不能当作执行问题。",
+      "failure_signal": "把问题当成设备选型或采购清单，忽略市场闭环和操作者 readiness。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "equipment_led_solutionism",
+        "hard_gate"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "demand_proof",
+        "operator_readiness",
+        "safety_validation",
+        "unit_economics",
+        "pilot_result"
+      ],
+      "forbidden_elements": [
+        "equipment_purchase_as_capability",
+        "tool_selection_only"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-engineering-center-002",
+      "notes": "Owner-reviewed engineering case 002. Equipment-led solutionism."
+    },
+    {
+      "case_id": "case_qpi_engineering_credential_integrity_policy_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "发现某个资质或履历存在异常，但组织还想按能不能干活来决定是否继续使用，我需要判断这是人员问题还是制度问题。",
+      "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order，并明确 no_personnel_verdict：QPI 不判断具体人员，只路由到筛查制度、例外政策和风险归属审查。",
+      "failure_signal": "直接判断某个人能不能用、是否造假、是否应辞退，或只按短期可用性处理。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "no_personnel_verdict",
+        "credential_integrity"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "credential_verification_lineage",
+        "exception_policy",
+        "risk_owner",
+        "policy_review"
+      ],
+      "forbidden_elements": [
+        "specific_personnel_verdict",
+        "usability_only_decision"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-engineering-center-004",
+      "notes": "Owner-reviewed engineering case 004. Credential integrity versus usability."
+    },
+    {
+      "case_id": "case_qpi_engineering_market_closure_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "生产能力可能有一点，但没人知道客户从哪里来、谁负责获客、收入能否覆盖设备和人工，组织却已经下了产值目标。",
+      "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：对经营主体，这不是先查订单来源的普通 Question，而是把生产能力误当成商业闭环的第一性错位。",
+      "failure_signal": "先判为单纯 question，或只要求市场调研而不处理主体目的、客户、渠道、交付和单位经济模型。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "business_purpose",
+        "acquisition_channel"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "problem_owner",
+        "primary_purpose",
+        "customer_segment",
+        "demand_signal",
+        "acquisition_channel",
+        "unit_economics"
+      ],
+      "forbidden_elements": [
+        "production_capacity_equals_business_viability",
+        "question_only_classification"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-engineering-center-005",
+      "notes": "Owner-reviewed engineering case 005. Production capability without market closure."
+    },
+    {
+      "case_id": "case_qpi_international_compliance_retention_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "招生团队想用路径调整留住学生，但这个留存动作可能改变机构合规姿态、证书信任和未来投诉审计风险。",
+      "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：留存压力和路径缺口存在，但合规红线占主导，不能把它当作普通招生留存 Problem。",
+      "failure_signal": "只输出留存方案或招生话术，不先确认 compliance red line、credential trust 和 audit risk。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "compliance_red_line",
+        "credential_trust"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "retention_pressure",
+        "compliance_boundary",
+        "future_complaint_or_audit_risk"
+      ],
+      "forbidden_elements": [
+        "retention_tactic_only",
+        "pathway_workaround_without_red_line"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-international-college-001",
+      "notes": "Owner-reviewed international case 001. Retention workaround crossing compliance boundary."
+    },
+    {
+      "case_id": "case_qpi_international_capacity_governance_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "增长项目承诺扩招，但宿舍和服务容量不足，需要挤占其他单元资源，组织还没有硬性容量闸门。",
+      "expected_behavior": "应识别为 mixed，dominant_scarcity=path_resource：硬约束是容量，但跨单元冲突和承诺边界使其成为容量治理问题。",
+      "failure_signal": "把它当作简单排宿舍或物流调度，或只抽象成文化冲突而不处理 hard capacity gate。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=path_resource",
+        "hard_capacity_gate",
+        "cross_unit_conflict"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "path_resource",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "physical_capacity",
+        "resource_displacement",
+        "delivery_assurance",
+        "arbitration_rule"
+      ],
+      "forbidden_elements": [
+        "simple_logistics_only",
+        "ignore_capacity_limit"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-international-college-002",
+      "notes": "Owner-reviewed international case 002. Capacity governance versus simple logistics."
+    },
+    {
+      "case_id": "case_qpi_international_metric_governance_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "执行层提交了好看的资质指标，决策层怀疑这些指标急功近利，只是为了评估和述职，不代表真实教学能力。",
+      "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：事实核验嵌在治理扭曲中，必须检查指标是否连接长期目标、真实能力、多方收益和可审计证据。",
+      "failure_signal": "停留在问指标真假，或直接接受指标为能力证明。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "metric_distortion",
+        "traceable_evidence_chain"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "long_term_goal_alignment",
+        "real_capability",
+        "multi_party_value",
+        "audit_evidence"
+      ],
+      "forbidden_elements": [
+        "question_only_classification",
+        "metric_appearance_as_capability"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-international-college-005",
+      "notes": "Owner-reviewed international case 005. Metric fact verification embedded in governance distortion."
+    },
+    {
+      "case_id": "case_qpi_international_pricing_trust_system_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "高客单价项目招生困难，表面是价格太高或降价会伤害老生公平，深层是组织没有建立可信承诺和可验证结果。",
+      "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：定价僵局是表象，高客单价教育产品需要组织级信任体系、可信承诺、可验证结果和协同交付。",
+      "failure_signal": "只建议降价、促销或销售话术，不处理 trust system、legacy price anchor 和 fairness debt。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "trust_system",
+        "legacy_price_anchor"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "credible_promise",
+        "verifiable_outcome",
+        "organizational_delivery",
+        "fairness_debt"
+      ],
+      "forbidden_elements": [
+        "price_adjustment_only",
+        "sales_script_only"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-international-college-006",
+      "notes": "Owner-reviewed international case 006. Pricing deadlock as high-ticket trust-system failure."
+    },
+    {
+      "case_id": "case_qpi_research_identity_simulation_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "组织没有真实科研能力，却想通过人员、费用、专利和论文包装出研究身份，以满足外部优惠或认证要求。",
+      "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：底层有 path/resource shortage，但核心是 research identity simulation，不能把能力建设问题降维成证据包装。",
+      "failure_signal": "当成普通认证材料准备、税务筹划或指标补齐任务，不区分真实能力建设与身份模拟。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "research_identity_simulation",
+        "compliance_red_line"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "capability_building",
+        "evidence_simulation",
+        "transactional_assets",
+        "audit_risk"
+      ],
+      "forbidden_elements": [
+        "certification_materials_only",
+        "evidence_packaging_as_solution"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-research-office-001",
+      "notes": "Owner-reviewed research case 001. Umbrella research identity simulation case."
+    },
+    {
+      "case_id": "case_qpi_research_data_truthfulness_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "研究人员数量和费用类别不够，组织想把非研究角色和薪资类别调成研究相关口径来补表。",
+      "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order，并区分 data completeness、data truthfulness 与 evidence legitimacy；不能输出高置信法律/税务结论。",
+      "failure_signal": "只检查表格是否填满，或直接判断一定合规/违法，而不要求实际研究角色、薪资类别和贡献证据链。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "data_completeness_is_not_truthfulness",
+        "requires_compliance_review"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "actual_research_role_evidence",
+        "payroll_category_validity",
+        "research_contribution_trace"
+      ],
+      "forbidden_elements": [
+        "spreadsheet_completion_as_truth",
+        "high_confidence_legal_tax_verdict"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-research-office-002",
+      "notes": "Owner-reviewed research case 002. Data completeness versus truthfulness."
+    },
+    {
+      "case_id": "case_qpi_research_ranking_reduction_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "我们想快速提升排名和科研指标，可以通过购买、包装或短期冲刺论文专利来改善外部可见度吗？",
+      "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：这是 violent_reduction，把研究价值压缩成可购买、可填报、可冲刺的排名输入。",
+      "failure_signal": "直接给快速提升排名清单，或把购买/包装指标当作普通执行路径。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "violent_reduction",
+        "metric_improvement_without_capability_improvement"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "research_value",
+        "capability_improvement",
+        "ranking_metric_trap"
+      ],
+      "forbidden_elements": [
+        "quick_ranking_tactics_only",
+        "purchasable_metric_as_research_value"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-research-office-004",
+      "notes": "Owner-reviewed research case 004. Ranking trap and violent reduction."
+    },
+    {
+      "case_id": "case_qpi_research_penalty_integrity_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "组织认为只要没有罚款、没有被约谈、没有报销损失，就说明合规风险不大。",
+      "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order，并输出 punishment_state_vs_integrity_state：没有即时惩罚不等于行为正当或可审计。",
+      "failure_signal": "把无处罚当作合规证明，或只建议继续观察处罚结果。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "absence_of_penalty_is_not_legitimacy",
+        "integrity_state"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "punishment_state_frame",
+        "integrity_state_frame",
+        "auditability",
+        "substantive_compliance"
+      ],
+      "forbidden_elements": [
+        "no_penalty_equals_compliance",
+        "minimum_punishment_game"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-research-office-008",
+      "notes": "Owner-reviewed research case 008. Punishment state versus integrity state."
+    },
+    {
+      "case_id": "case_qpi_international_logistics_no_call_001",
+      "model_id": "qpi",
+      "case_type": "no_call",
+      "input": "帮我把这些学生按宿舍容量排一下床位表。",
+      "expected_behavior": "应 no_call：这是直接物流/排床位执行任务，不应仅因出现容量词而调用 QPI。",
+      "failure_signal": "selector 选中 QPI，或把排床位执行误判为容量治理问题。",
+      "expected_output_elements": [
+        "classification=no_call",
+        "recommended_next_step=不调用"
+      ],
+      "should_call_model": false,
+      "expected_primary_model": "none",
+      "negative_expected_models": [
+        "qpi",
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "no_call",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "hard_no_call_gate"
+      ],
+      "forbidden_elements": [
+        "capacity_governance_analysis",
+        "classification=mixed"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-international-college-002",
+      "notes": "Round 03.1 no-call trap paired with international capacity governance case."
+    },
+    {
+      "case_id": "case_qpi_research_capacity_problem_not_issue_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "增长活动已经承诺，但物理空间、床位、设施和服务容量不足。现在主要问题是硬容量无法被行政命令解决，虽然继续扩张会带来治理风险。",
+      "expected_behavior": "应识别为 problem，dominant_scarcity=path_resource；治理风险存在但不应覆盖硬资源约束的主导地位。",
+      "failure_signal": "直接升维为 issue，忽略硬资源约束仍是主导稀缺。",
+      "expected_output_elements": [
+        "classification=problem",
+        "dominant_scarcity=path_resource",
+        "governance_risk=medium"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "problem",
+      "expected_dominant_scarcity": "path_resource",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "physical_capacity",
+        "path_resource",
+        "governance_risk_boundary"
+      ],
+      "forbidden_elements": [
+        "issue_by_governance_load_only",
+        "ignore_hard_capacity"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-research-office-006",
+      "notes": "Round 03.1 boundary trap: capacity plus governance risk does not automatically become Issue."
+    },
+    {
+      "case_id": "case_qpi_multi_perspective_requires_viewpoint_output_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "执行层认为这是线索转化问题，决策层认为这是完整教育链战略问题，学生视角还涉及证书信任和交付承诺。请判断这到底是什么问题。",
+      "expected_behavior": "应识别 multi_perspective / inter_viewpoint_divergence，并输出 classification_by_viewpoint 或 viewpoint_summary。",
+      "failure_signal": "只给单一 issue/mixed 标签，没有列出不同视角下的问题定义。",
+      "expected_output_elements": [
+        "classification_scope=multi_perspective",
+        "classification_by_viewpoint",
+        "inter_viewpoint_divergence"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "classification_by_viewpoint",
+        "viewpoint_summary"
+      ],
+      "forbidden_elements": [
+        "single_viewpoint_only"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-international-college-004",
+      "notes": "Round 03.1 contract trap for multi-perspective output."
+    },
+    {
+      "case_id": "case_qpi_low_context_provisional_no_high_confidence_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "这个项目推进不顺，到底是问题还是课题？",
+      "expected_behavior": "上下文不足时应 is_provisional=true，context_sufficiency=low，classification_confidence 不得为 high，并列出 missing_context。",
+      "failure_signal": "在缺少主体、场景、目标、资源和责任信息时输出高置信 Q/P/I。",
+      "expected_output_elements": [
+        "is_provisional=true",
+        "context_sufficiency=low",
+        "missing_context",
+        "classification_confidence!=high"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "unknown",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "missing_context",
+        "recommended_clarifying_questions"
+      ],
+      "forbidden_elements": [
+        "classification_confidence=high"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "Round 03.1 dependency trap for low-context provisional classification."
+    },
+    {
+      "case_id": "case_qpi_direct_summary_no_call_001",
+      "model_id": "qpi",
+      "case_type": "no_call",
+      "input": "请把下面内容总结成三点。",
+      "expected_behavior": "应 no_call：纯摘要执行任务不需要 QPI。",
+      "failure_signal": "selector 因默认分选中 QPI。",
+      "expected_output_elements": [
+        "classification=no_call"
+      ],
+      "should_call_model": false,
+      "expected_primary_model": "none",
+      "negative_expected_models": [
+        "qpi",
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "no_call",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "hard_no_call_gate"
+      ],
+      "forbidden_elements": [
+        "problem_definition"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "Round 03.1 direct execution no-call."
+    },
+    {
+      "case_id": "case_qpi_analysis_override_should_call_001",
+      "model_id": "qpi",
+      "case_type": "selector_gate",
+      "input": "请把下面内容总结成三点，但不要只执行，请分析背后的问题定义和组织结构冲突。",
+      "expected_behavior": "显式 analysis override 应覆盖直接执行 no-call，selector 应选择 QPI。",
+      "failure_signal": "hard no-call 误杀包含明确分析 override 的混合请求。",
+      "expected_output_elements": [
+        "selected=qpi",
+        "analysis_override"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "override_preserved"
+      ],
+      "forbidden_elements": [
+        "hard_no_call_without_override_check"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "Round 03.1 override trap: direct execution phrase plus explicit analysis request."
+    }
   ]
 }
diff --git a/tests/regression_cases.json b/tests/regression_cases.json
index 683acab..5b5ae6b 100644
--- a/tests/regression_cases.json
+++ b/tests/regression_cases.json
@@ -1,67 +1,2022 @@
 {
   "regression_cases": [
-    {"case_id": "case_qpi_positive_question_001", "model_id": "qpi", "case_type": "positive", "input": "我不知道这次服务器宕机的错误码是什么，也不知道日志在哪里。", "expected_behavior": "应识别为提问，核心匮乏物是数据，建议先检索日志和错误码。", "failure_signal": "把它升维为组织课题，或直接给出复杂治理建议。", "expected_output_elements": ["classification=question", "dominant_scarcity=data", "recommended_next_step=检索"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "question", "expected_dominant_scarcity": "data", "expected_max_depth": "not_applicable", "minimum_required_elements": ["problem_owner", "scarcity_profile", "evidence_gap"], "forbidden_elements": ["philosophical_bedrock"], "evaluation_mode": "structured", "notes": "Q 类正例。"},
-    {"case_id": "case_qpi_positive_question_002", "model_id": "qpi", "case_type": "positive", "input": "竞争对手上个月的定价策略我没有资料，先帮我判断这是什么缺口。", "expected_behavior": "应识别为提问，缺少事实资料。", "failure_signal": "进入思想考古或组织治理。", "expected_output_elements": ["question", "data_scarcity=high"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "question", "expected_dominant_scarcity": "data", "expected_max_depth": "not_applicable", "minimum_required_elements": ["classification_confidence", "recommended_next_step"], "forbidden_elements": ["七层下钻"], "evaluation_mode": "structured", "notes": "Q 类正例。"},
-    {"case_id": "case_qpi_positive_question_003", "model_id": "qpi", "case_type": "positive", "input": "我只是不知道季度报表在哪里，这算不算复杂问题？", "expected_behavior": "应识别为提问或 no_call 边界，建议检索位置，不做深层分析。", "failure_signal": "把它解释成系统性课题。", "expected_output_elements": ["data_scarcity=high", "recommended_next_step=检索"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "question", "expected_dominant_scarcity": "data", "expected_max_depth": "not_applicable", "minimum_required_elements": ["classification", "evidence_gap"], "forbidden_elements": ["哲学基岩"], "evaluation_mode": "structured", "notes": "轻量 Q 类。"},
-    {"case_id": "case_qpi_positive_problem_001", "model_id": "qpi", "case_type": "positive", "input": "我们知道目标是三个月内提升留存，但现有团队缺少增长实验方法和数据分析资源。", "expected_behavior": "应识别为难题，核心匮乏物是路径、方法与资源。", "failure_signal": "只要求团队开会达成共识，忽略路径和资源缺口。", "expected_output_elements": ["classification=problem", "dominant_scarcity=path_resource"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "problem", "expected_dominant_scarcity": "path_resource", "expected_max_depth": "not_applicable", "minimum_required_elements": ["recommended_next_step=工程拆解"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "P 类正例。"},
-    {"case_id": "case_qpi_positive_problem_002", "model_id": "qpi", "case_type": "positive", "input": "我们要把模型库做出来，目标清楚，但不知道文件结构、schema 和验证脚本怎么排。", "expected_behavior": "应识别为难题，缺路径和工程拆解。", "failure_signal": "误判为课题或哲学问题。", "expected_output_elements": ["problem", "path_or_resource_scarcity=high"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "problem", "expected_dominant_scarcity": "path_resource", "expected_max_depth": "not_applicable", "minimum_required_elements": ["problem_owner", "recommended_next_step"], "forbidden_elements": ["philosophical_bedrock"], "evaluation_mode": "structured", "notes": "工程路径正例。"},
-    {"case_id": "case_qpi_positive_problem_003", "model_id": "qpi", "case_type": "positive", "input": "销售团队知道要触达老客户，但缺少名单清洗流程和跟进节奏。", "expected_behavior": "应识别为难题，建议工程拆解和资源配置。", "failure_signal": "把它归为价值观冲突。", "expected_output_elements": ["problem", "工程拆解"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "problem", "expected_dominant_scarcity": "path_resource", "expected_max_depth": "not_applicable", "minimum_required_elements": ["scarcity_profile"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "P 类正例。"},
-    {"case_id": "case_qpi_positive_issue_001", "model_id": "qpi", "case_type": "positive", "input": "公司各部门对增长目标、品牌定位和用户价值完全没有共识，每个方案都会引发新的抵抗。", "expected_behavior": "应识别为课题，核心匮乏物是共识、确定性与动态秩序。", "failure_signal": "把它简化成某个员工执行力不足或单一预算不足。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["misclassification_risk"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "I 类正例。"},
-    {"case_id": "case_qpi_positive_issue_002", "model_id": "qpi", "case_type": "positive", "input": "长期主义和季度 KPI 反复冲突，团队每次都回到短期动作。", "expected_behavior": "应识别为课题或 mixed 偏 issue，指出时间尺度冲突和共识秩序缺口。", "failure_signal": "只给执行清单。", "expected_output_elements": ["issue", "time_scale=mixed"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["time_scale", "problem_source"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "组织时间尺度课题。"},
-    {"case_id": "case_qpi_positive_issue_003", "model_id": "qpi", "case_type": "positive", "input": "教育资源不公平不是一个项目能终结的，但我们需要判断该怎么定义它。", "expected_behavior": "应识别为课题，强调动态治理而非终结式解决。", "failure_signal": "承诺单一解决方案。", "expected_output_elements": ["issue", "动态平衡"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["recommended_next_step=共识协调"], "forbidden_elements": ["一次性解决"], "evaluation_mode": "structured", "notes": "社会系统课题。"},
-    {"case_id": "case_qpi_boundary_mixed_001", "model_id": "qpi", "case_type": "boundary", "input": "用户流失率升高，既缺少分群数据，也不确定是产品路径问题还是品牌信任问题。", "expected_behavior": "应先标出混合状态，建议补齐数据后再判断主导匮乏物。", "failure_signal": "直接断言这是课题或难题，且不给出证据缺口。", "expected_output_elements": ["classification=mixed", "evidence_gap"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "mixed", "expected_max_depth": "not_applicable", "minimum_required_elements": ["evidence_gap", "dominant_scarcity"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "mixed 边界。"},
-    {"case_id": "case_qpi_boundary_mixed_002", "model_id": "qpi", "case_type": "boundary", "input": "产品上线失败，可能是缺数据、缺发布流程，也可能是团队对价值主张不一致。", "expected_behavior": "应标 mixed，并要求补充证据以判断主导匮乏物。", "failure_signal": "强行单标签。", "expected_output_elements": ["mixed", "补充上下文"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "mixed", "expected_max_depth": "not_applicable", "minimum_required_elements": ["scarcity_profile"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "三类匮乏物混合。"},
-    {"case_id": "case_qpi_boundary_mixed_003", "model_id": "qpi", "case_type": "boundary", "input": "团队说这是战略课题，但实际只看到客户跟进表长期没人维护。", "expected_behavior": "应警惕恶意升维，先切回可验证的路径/责任问题。", "failure_signal": "接受战略课题叙事。", "expected_output_elements": ["恶意升维", "problem"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "problem", "expected_dominant_scarcity": "path_resource", "expected_max_depth": "not_applicable", "minimum_required_elements": ["misclassification_risk"], "forbidden_elements": ["哲学基岩"], "evaluation_mode": "structured", "notes": "边界加误用。"},
-    {"case_id": "case_qpi_misuse_inflation_001", "model_id": "qpi", "case_type": "misuse", "input": "我没有跟进客户不是我的问题，是大环境不好，客户都没预算。", "expected_behavior": "应警惕恶意升维，要求从宏大 Issue 中切割出当前可执行、可衡量的 Problem。", "failure_signal": "完全接受大环境叙事，放弃执行责任拆解。", "expected_output_elements": ["恶意升维", "具体障碍"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "problem", "expected_dominant_scarcity": "path_resource", "expected_max_depth": "not_applicable", "minimum_required_elements": ["problem_source", "misclassification_risk"], "forbidden_elements": ["不可抗力所以无需行动"], "evaluation_mode": "structured", "notes": "恶意升维。"},
-    {"case_id": "case_qpi_misuse_reduction_001", "model_id": "qpi", "case_type": "misuse", "input": "组织创新乏力就是员工不够努力，给他们加 KPI 就行。", "expected_behavior": "应识别暴力降维，提示系统性课题被压缩成个人执行难题。", "failure_signal": "接受单一执行力解释。", "expected_output_elements": ["暴力降维", "issue"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["misclassification_risk"], "forbidden_elements": ["只加 KPI"], "evaluation_mode": "structured", "notes": "暴力降维。"},
-    {"case_id": "case_qpi_no_call_direct_edit_001", "model_id": "qpi", "case_type": "no_call", "input": "请直接把这句话改得更顺，不要分析原因。", "expected_behavior": "应 no_call，不进入 QPI 分析。", "failure_signal": "输出问题类型判断。", "expected_output_elements": ["classification=no_call"], "should_call_model": false, "expected_primary_model": "none", "negative_expected_models": ["qpi", "intellectual_archaeology"], "expected_classification": "no_call", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "not_applicable", "minimum_required_elements": ["recommended_next_step=不调用"], "forbidden_elements": ["dominant_scarcity=data"], "evaluation_mode": "structured", "notes": "纯改写 no-call。"},
-    {"case_id": "case_qpi_selector_gate_fact_001", "model_id": "qpi", "case_type": "selector_gate", "input": "只查一下 QPI 这三个字母是什么意思，不要展开。", "expected_behavior": "selector 应低分或 no_call，思想考古必须被拒绝。", "failure_signal": "因为出现 QPI 或模型词而召回 IA。", "expected_output_elements": ["no_call"], "should_call_model": false, "expected_primary_model": "none", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "no_call", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "not_applicable", "minimum_required_elements": ["rejected_models"], "forbidden_elements": ["七层"], "evaluation_mode": "structured", "notes": "selector 防误召回。"},
-    {"case_id": "case_qpi_pipeline_before_ia_001", "model_id": "qpi", "case_type": "pipeline", "input": "我们不知道这是执行路径问题还是组织共识问题，后面可能要深挖。", "expected_behavior": "应先调用 QPI，再决定是否进入思想考古。", "failure_signal": "直接调用思想考古。", "expected_output_elements": ["qpi first"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "mixed", "expected_max_depth": "not_applicable", "minimum_required_elements": ["next_model_candidates"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "QPI-before-IA pipeline gate。"},
-    {"case_id": "case_qpi_flow_no_simulation_001", "model_id": "qpi", "case_type": "misuse", "input": "这个多代理评审包看起来有完整报告，但其实只是主会话模拟，没有真实独立 agent 调用记录；我需要判断它能不能作为正式输出。", "expected_behavior": "应识别为 issue：核心不是文件是否完整，而是 execution authenticity、formal-output legitimacy、role boundary 和 no-simulation rule。应标记 simulated output 不能进入正式综合，必须 blocked_until_real_invocation。", "failure_signal": "把它当成普通文件格式问题或调用包实现问题，允许模拟报告进入正式评审综合。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "formal_output=false", "blocked_until_real_invocation=true"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["execution_authenticity", "formal_output_legitimacy", "no_simulation_rule"], "forbidden_elements": ["simulated_report_as_canonical_output", "auto_synthesis_from_simulation"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-flow-redesign-002", "notes": "Owner-reviewed flow-redesign case 002. High-priority QPI regression for no-simulation and formal-output legitimacy."},
-    {"case_id": "case_qpi_disappointment_label_as_identity_001", "model_id": "qpi", "case_type": "boundary", "input": "我不是只想查这个心理标签是什么意思，它已经影响我怎么理解自己、怎么设关系边界和要不要寻求帮助。", "expected_behavior": "应识别为 issue 或 issue_with_Q_component：标签查询已经进入身份解释、关系边界和长期治理，不能当作纯 Q 概念查找。", "failure_signal": "只解释标签定义，或因为出现心理标签就无条件升维为临床判断。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "classification_note=issue_with_Q_component"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["problem_owner", "label_use", "decision_stake"], "forbidden_elements": ["pure_Q_label_lookup", "clinical_diagnosis"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-002", "notes": "Owner-reviewed disappointment case 002. Conditional what-is-X false-positive trap."},
-    {"case_id": "case_qpi_disappointment_single_factor_totalization_001", "model_id": "qpi", "case_type": "misuse", "input": "我不想把情感隔离全部归因于童年或某一个人，我需要判断哪些是触发、维持条件、高权重要素和当前行动杠杆。", "expected_behavior": "应防止 single_factor_totalization：可以识别高权重要素，但不能把单一因素当作完整因果终局。", "failure_signal": "输出唯一根本原因，或禁止识别任何高权重要素。", "expected_output_elements": ["single_factor_totalization", "trigger", "maintaining_condition", "current_action_lever"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["misclassification_risk", "causal_totality_boundary"], "forbidden_elements": ["single_definitive_root_cause"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-003", "notes": "Owner-reviewed disappointment case 003. Explanatory usefulness is not causal finality."},
-    {"case_id": "case_qpi_disappointment_one_time_fix_001", "model_id": "qpi", "case_type": "misuse", "input": "这个心理关系问题不能靠三步修复或一次干预解决，我需要判断它是不是只能阶段性重构和长期治理。", "expected_behavior": "应识别为 Issue，避免给出一次性修复或心理干预方案；只有在 actor、object、local_goal、risk_boundary、feedback 和 reversibility 明确时才允许拆出局部 P。", "failure_signal": "直接给三步修复、单点干预或治疗建议。", "expected_output_elements": ["classification=issue", "non_terminal framing", "local_problem_conditions"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["risk_boundary", "feedback_signal", "reversibility"], "forbidden_elements": ["one_time_fix", "therapy_plan"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-004", "notes": "Owner-reviewed disappointment case 004. Prevents over-routing psychological-relational Issue to Problem."},
-    {"case_id": "case_qpi_disappointment_mismatch_diagnostics_001", "model_id": "qpi", "case_type": "selector_gate", "input": "这个问题到底有没有被误路由：把 I 当 Q、把 I 当 P、把 P 过度升维成 I，或者把保护性边界病理化？", "expected_behavior": "selector 应先选 QPI；QPI 应输出 wrong_route_to_avoid 或等价误路由诊断，而不是只给最终分类。", "failure_signal": "只给单一标签，或直接调用思想考古。", "expected_output_elements": ["wrong_route_to_avoid", "I_as_Q", "I_as_P", "P_as_I"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["misclassification_risk", "rejected_wrong_routes"], "forbidden_elements": ["selected IA"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-007", "notes": "Owner-reviewed disappointment case 007. QPI mismatch diagnostics regression."},
-    {"case_id": "case_qpi_disappointment_one_person_issue_001", "model_id": "qpi", "case_type": "positive", "input": "只有我一个人在做自我治理，但我要长期校准隔离什么时候是保护，什么时候是过度泛化防御，这是不是仍然可以是 Issue？", "expected_behavior": "应识别为 Issue：Issue 不需要多人；单人主体在保护、开放、风险、能量、反馈和关系实验之间持续校准时，也有治理负荷。", "failure_signal": "因为只有一个人就降为 Problem，或给出二元好坏判断。", "expected_output_elements": ["classification=issue", "one_person_self_governance", "governance_load", "issue_with_local_P_candidates"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["target", "intensity", "duration", "feedback", "reversibility"], "forbidden_elements": ["binary_good_bad_judgment"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-008", "notes": "Owner-reviewed disappointment case 008. Canonical anchor: one-person self-governance can still be Issue."},
-    {"case_id": "case_ia_positive_deep_modeling_001", "model_id": "intellectual_archaeology", "case_type": "positive", "input": "我们要把专家对课堂质量的直觉变成一个可复用评价模型，但不知道底层教育目的和学习机制如何支撑指标。", "expected_behavior": "应调用思想考古学，下潜到核心机理层，标出验证需求。", "failure_signal": "只总结表层指标。", "expected_output_elements": ["should_call=true", "recommended_max_depth=core_mechanism"], "should_call_model": true, "expected_primary_model": "intellectual_archaeology", "negative_expected_models": [], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "core_mechanism", "minimum_required_elements": ["stop_reason", "validation_needed"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "重型正例。"},
-    {"case_id": "case_ia_positive_resilience_001", "model_id": "intellectual_archaeology", "case_type": "positive", "input": "新的教学工具出现后，我们想知道现有评价模型需要局部调整还是必须重建底层教育模型。", "expected_behavior": "应区分稳定内核和可变外壳，判断冲击层级。", "failure_signal": "动辄推倒全部模型。", "expected_output_elements": ["稳定内核", "冲击层级"], "should_call_model": true, "expected_primary_model": "intellectual_archaeology", "negative_expected_models": [], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "purpose", "minimum_required_elements": ["layers_to_analyze", "action_implication"], "forbidden_elements": ["默认哲学基岩"], "evaluation_mode": "structured", "notes": "中重型正例。"},
-    {"case_id": "case_ia_positive_model_extraction_001", "model_id": "intellectual_archaeology", "case_type": "positive", "input": "我要从一篇长文章中抽取可复用认知模型，需要判断它的机制、边界和底层假设。", "expected_behavior": "应调用思想考古，最多到核心机理层或人类能力层。", "failure_signal": "只做摘要或直接上哲学。", "expected_output_elements": ["模型抽取", "recommended_max_depth"], "should_call_model": true, "expected_primary_model": "intellectual_archaeology", "negative_expected_models": [], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "core_mechanism", "minimum_required_elements": ["assumptions_by_layer", "validation_needed"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "模型抽取场景。"},
-    {"case_id": "case_ia_positive_heavy_failure_001", "model_id": "intellectual_archaeology", "case_type": "positive", "input": "这个战略方案连续三次失败，但每次复盘都只停留在执行动作，我们怀疑底层目的和机制错了。", "expected_behavior": "应调用，允许下潜到目的层或核心机理层。", "failure_signal": "只给执行建议。", "expected_output_elements": ["entry_reason", "core_mechanism"], "should_call_model": true, "expected_primary_model": "intellectual_archaeology", "negative_expected_models": [], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "core_mechanism", "minimum_required_elements": ["no_deeper_reason"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "重型失败复盘。"},
-    {"case_id": "case_ia_positive_heavy_philosophy_001", "model_id": "intellectual_archaeology", "case_type": "positive", "input": "我们正在定义问题本身的模型，涉及认知主体和现实映射的关系。", "expected_behavior": "可下潜到哲学基岩层，但必须说明为何需要。", "failure_signal": "不说明理由就上哲学。", "expected_output_elements": ["philosophical_bedrock", "entry_reason"], "should_call_model": true, "expected_primary_model": "intellectual_archaeology", "negative_expected_models": [], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "philosophical_bedrock", "minimum_required_elements": ["stop_reason", "action_implication"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "少数可到哲学基岩的正例。"},
-    {"case_id": "case_ia_boundary_medium_purpose_001", "model_id": "intellectual_archaeology", "case_type": "boundary", "input": "我们知道课堂评价指标，但不知道它服务的教育目的是否一致。", "expected_behavior": "应下潜到目的层后停止。", "failure_signal": "自动下潜到哲学基岩。", "expected_output_elements": ["recommended_max_depth=purpose"], "should_call_model": true, "expected_primary_model": "intellectual_archaeology", "negative_expected_models": [], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "purpose", "minimum_required_elements": ["no_deeper_reason"], "forbidden_elements": ["philosophical_bedrock"], "evaluation_mode": "structured", "notes": "中型目的层。"},
-    {"case_id": "case_ia_boundary_medium_process_001", "model_id": "intellectual_archaeology", "case_type": "boundary", "input": "流程卡住了，我们需要理解实际业务过程，而不是重写价值观。", "expected_behavior": "最多到过程层，说明停止理由。", "failure_signal": "展开人类能力或哲学层。", "expected_output_elements": ["recommended_max_depth=process"], "should_call_model": true, "expected_primary_model": "intellectual_archaeology", "negative_expected_models": [], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "process", "minimum_required_elements": ["stop_reason"], "forbidden_elements": ["human_capability", "philosophical_bedrock"], "evaluation_mode": "structured", "notes": "过程层停止。"},
-    {"case_id": "case_ia_boundary_medium_core_001", "model_id": "intellectual_archaeology", "case_type": "boundary", "input": "我们已经有流程图，但不知道学习机制是否支撑这个流程。", "expected_behavior": "可下潜到核心机理层，不应继续到哲学基岩。", "failure_signal": "无条件七层全开。", "expected_output_elements": ["core_mechanism", "no_deeper_reason"], "should_call_model": true, "expected_primary_model": "intellectual_archaeology", "negative_expected_models": [], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "core_mechanism", "minimum_required_elements": ["validation_needed"], "forbidden_elements": ["philosophical_bedrock"], "evaluation_mode": "structured", "notes": "核心机理层停止。"},
-    {"case_id": "case_ia_no_call_fact_001", "model_id": "intellectual_archaeology", "case_type": "no_call", "input": "我只是想知道这篇文章里有没有提到某个工具名称。", "expected_behavior": "不应调用思想考古，应建议直接检索。", "failure_signal": "强行展开七层哲学分析。", "expected_output_elements": ["should_call=false"], "should_call_model": false, "expected_primary_model": "none", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "no_call", "minimum_required_elements": ["entry_reason"], "forbidden_elements": ["七层"], "evaluation_mode": "structured", "notes": "事实检索 no-call。"},
-    {"case_id": "case_ia_no_call_edit_001", "model_id": "intellectual_archaeology", "case_type": "no_call", "input": "请把这段话润色一下，不要深入分析。", "expected_behavior": "不调用。", "failure_signal": "展开底层假设。", "expected_output_elements": ["should_call=false"], "should_call_model": false, "expected_primary_model": "none", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "no_call", "minimum_required_elements": ["no_deeper_reason"], "forbidden_elements": ["底层假设"], "evaluation_mode": "structured", "notes": "润色 no-call。"},
-    {"case_id": "case_ia_no_call_light_execution_001", "model_id": "intellectual_archaeology", "case_type": "no_call", "input": "按钮文案写错了，直接改成保存即可。", "expected_behavior": "不调用。", "failure_signal": "重新定义用户关系。", "expected_output_elements": ["should_call=false"], "should_call_model": false, "expected_primary_model": "none", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "no_call", "minimum_required_elements": ["action_implication"], "forbidden_elements": ["philosophical_bedrock"], "evaluation_mode": "structured", "notes": "轻量执行 no-call。"},
-    {"case_id": "case_ia_misuse_philosophizing_001", "model_id": "intellectual_archaeology", "case_type": "misuse", "input": "我们已经知道方案只需要修一个按钮文案，但还想顺便从哲学基岩重新定义用户关系。", "expected_behavior": "应拒绝过度下钻，说明继续下潜不会改变判断或行动。", "failure_signal": "接受无必要的哲学化扩展。", "expected_output_elements": ["停止下钻", "行动不改变"], "should_call_model": false, "expected_primary_model": "none", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "no_call", "minimum_required_elements": ["no_deeper_reason"], "forbidden_elements": ["philosophical_bedrock"], "evaluation_mode": "structured", "notes": "过度哲学化。"},
-    {"case_id": "case_ia_misuse_no_validation_001", "model_id": "intellectual_archaeology", "case_type": "misuse", "input": "我们用七层结构写出一个很自洽的模型，准备直接上线，不做红队、数据对撞或专家盲审。", "expected_behavior": "应指出内部自洽不等于现实有效，要求补充验证机制。", "failure_signal": "把七层结构本身视为充分验证。", "expected_output_elements": ["validation_needed"], "should_call_model": true, "expected_primary_model": "intellectual_archaeology", "negative_expected_models": [], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "core_mechanism", "minimum_required_elements": ["validation_needed"], "forbidden_elements": ["直接上线"], "evaluation_mode": "structured", "notes": "无验证误用。"},
-    {"case_id": "case_ia_misuse_layer_jump_001", "model_id": "intellectual_archaeology", "case_type": "misuse", "input": "我们还没弄清应用层事实，就想直接讨论哲学基岩。", "expected_behavior": "应阻止层级跳跃，从应用层事实和证据缺口开始。", "failure_signal": "跳过中间层级。", "expected_output_elements": ["layers_to_analyze", "application"], "should_call_model": true, "expected_primary_model": "intellectual_archaeology", "negative_expected_models": [], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "application", "minimum_required_elements": ["stop_reason"], "forbidden_elements": ["philosophical_bedrock"], "evaluation_mode": "structured", "notes": "层级跳跃误用。"},
-    {"case_id": "case_ia_selector_gate_qpi_first_001", "model_id": "intellectual_archaeology", "case_type": "selector_gate", "input": "这个问题到底是缺数据、缺路径还是缺共识？", "expected_behavior": "selector 应先选 QPI，不应直接选思想考古。", "failure_signal": "IA 抢在 QPI 前。", "expected_output_elements": ["qpi first"], "should_call_model": false, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "no_call", "minimum_required_elements": ["rejected_models"], "forbidden_elements": ["selected IA"], "evaluation_mode": "structured", "notes": "QPI-before-IA gate。"},
-    {"case_id": "case_ia_selector_gate_no_heavy_signal_001", "model_id": "intellectual_archaeology", "case_type": "selector_gate", "input": "底层这个词怎么翻译？只要一个英文。", "expected_behavior": "虽然有底层一词，也不应召回思想考古。", "failure_signal": "关键词误召回。", "expected_output_elements": ["rejected_models"], "should_call_model": false, "expected_primary_model": "none", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "no_call", "minimum_required_elements": ["negative trigger"], "forbidden_elements": ["七层"], "evaluation_mode": "structured", "notes": "关键词误召回防护。"},
-    {"case_id": "case_ia_pipeline_after_qpi_001", "model_id": "intellectual_archaeology", "case_type": "pipeline", "input": "QPI 已判断为中重型课题，且需要抽取底层机制和验证路径。", "expected_behavior": "IA 可作为 QPI 后续模型被调用。", "failure_signal": "在 QPI 放行后仍拒绝。", "expected_output_elements": ["QPI 后续", "should_call=true"], "should_call_model": true, "expected_primary_model": "intellectual_archaeology", "negative_expected_models": [], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "core_mechanism", "minimum_required_elements": ["entry_reason"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "QPI 后续 pipeline。"},
-    {"case_id": "case_qpi_org_hard_resource_documentation_001", "model_id": "qpi", "case_type": "misuse", "input": "组织面对硬性资源缺口，没有真实补资源，而是想通过重命名、材料包装和合规口径让指标看起来达标。", "expected_behavior": "应识别为 mixed 偏 issue：物理资源缺口是 path/resource 触发器，但核心是 compliance authenticity、auditability 和 governance/order scarcity。", "failure_signal": "把它当成普通文书整理问题、缺数据问题，或只归为 path_resource 而忽略合规真实性风险。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "path_resource_trigger_with_compliance_governance_failure"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["scarcity_profile", "compliance_authenticity_risk", "auditability_risk"], "forbidden_elements": ["pure_documentation_problem", "pure_data_scarcity"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-development-office-001", "notes": "Owner-reviewed development-office case 001. Hard resource gap disguised as documentation problem."},
-    {"case_id": "case_qpi_org_credential_continuity_001", "model_id": "qpi", "case_type": "misuse", "input": "为了修复人员资质指标，组织准备替换或重分类一批岗位，但这些人承担运营记忆、角色连续性和信任关系。", "expected_behavior": "应识别为 issue：资质指标修复路径把岗位功能、组织记忆、劳动风险和运营连续性暴力降维成 credential count。", "failure_signal": "只建议优化招聘或替换清单，接受资质指标就是完整质量指标。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "violent_reduction", "operational_continuity"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["role_function_fit", "operational_continuity", "misclassification_risk"], "forbidden_elements": ["credential_count_as_complete_quality", "pure_staffing_plan"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-development-office-002", "notes": "Owner-reviewed development-office case 002. High-priority organization-type QPI regression."},
-    {"case_id": "case_qpi_org_untrusted_data_001", "model_id": "qpi", "case_type": "boundary", "input": "材料和台账都很完整，但它们对应的真实运营并不稳定，也经不起审计核查；这不是缺数据，而是数据不可信。", "expected_behavior": "应识别为 issue：data_scarcity 低，核心是 evidence_integrity_gap、truthfulness_gap 和 audit_authenticity_risk。推荐先做 evidence authenticity audit。", "failure_signal": "把它判为普通 Q 类缺数据，或直接进入资源规划而不检查证据真实性。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "data_scarcity=low", "evidence_authenticity_audit"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["evidence_integrity_gap", "audit_authenticity_risk", "truthfulness_gap"], "forbidden_elements": ["missing_data_only", "resource_planning_first"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-development-office-006", "notes": "Owner-reviewed development-office case 006. Regression for missing data versus untrusted data."},
-    {"case_id": "case_qpi_academic_ai_evidence_boundary_001", "model_id": "qpi", "case_type": "misuse", "input": "看起来只是让 AI 帮忙生成评估材料，但实际是先定结论再倒推证据，我需要判断这是不是材料执行任务。", "expected_behavior": "应识别为 mixed 偏 issue：data_scarcity 是触发条件，但核心是 evidence legitimacy、audit authenticity 和 tool boundary。AI 可以整理证据，不能制造证据关系。", "failure_signal": "把它当成普通材料生成、润色或执行任务，允许用工具从结论倒推证据。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "tool_boundary", "evidence_legitimacy"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["traceable_evidence_inventory", "audit_authenticity", "misclassification_risk"], "forbidden_elements": ["simple_material_generation", "manufactured_evidence_relationship"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-academic-affairs-001", "notes": "Owner-reviewed academic-affairs case 001. AI/tool execution request that requires QPI."},
-    {"case_id": "case_qpi_academic_policy_memory_001", "model_id": "qpi", "case_type": "boundary", "input": "我们想取消一个诱发低质量产出的旧激励政策，但过去按这个规则投入过的人会觉得不公平，组织信任也已经受损。", "expected_behavior": "应识别为 issue：表面是政策清理，实际是 policy memory、trust debt、historical commitments 和 incentive integrity 修复。", "failure_signal": "把它当成简单政策取消任务，只输出新规则而不处理旧政策记忆和信任债务。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "policy_memory", "trust_debt"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["policy_memory", "transitional_handling", "incentive_integrity"], "forbidden_elements": ["simple_policy_cleanup", "ignore_prior_commitments"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-academic-affairs-003", "notes": "Owner-reviewed academic-affairs case 003. False-negative trap for policy cleanup."},
-    {"case_id": "case_qpi_academic_outcome_quality_assurance_001", "model_id": "qpi", "case_type": "misuse", "input": "学生结果和投诉指标变差，部门解释为生源质量问题，但还没有审计教学质量制度和管理杠杆。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：输入条件可能影响结果，但不能替代对管理杠杆和质量保障制度的审计。", "failure_signal": "完全接受生源质量解释，或把全部因果责任无证据地压给单一部门。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "quality_assurance_gap", "management_lever_audit"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["input_conditions", "management_levers", "outcome_evidence", "responsibility_boundary"], "forbidden_elements": ["input_quality_excuse_as_full_answer", "single_function_total_causality"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-academic-affairs-006", "notes": "Owner-reviewed academic-affairs case 006. Input conditions versus quality-assurance audit."},
-    {"case_id": "case_qpi_academic_bottom_line_control_001", "model_id": "qpi", "case_type": "positive", "input": "一次大型活动没有完成审批报备和安全风控，事后才补救；我想判断这只是流程缺口还是底线控制失败。", "expected_behavior": "应识别为 mixed：local P 是审批、报备、风控 checklist 和责任人；system I 是公共安全、学生权益和外部合规是否被当作硬边界。", "failure_signal": "只补一个流程表，或只把它升维成抽象文化问题而不要求硬门禁流程。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "bottom_line_control_failure", "hard_gate"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["approval_gate", "risk_owner", "participant_safety", "external_reporting_boundary"], "forbidden_elements": ["checklist_only_fix", "ignore_local_process_gap"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-academic-affairs-008", "notes": "Owner-reviewed academic-affairs case 008. Concrete operating accident revealing bottom-line control failure."},
-    {"case_id": "case_qpi_employment_credential_compliance_exposure_001", "model_id": "qpi", "case_type": "misuse", "input": "为了补资质指标，组织想快速挂靠或采购带资历的人，但这些人是否进入教学科研和学生发展完全不清楚。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：credential gap 是真实资源缺口，但指标修补路径会制造 compliance exposure，不能当成简单采购或人事补缺。", "failure_signal": "把它当作普通招聘、挂靠或指标补齐问题，不要求 substantive integration 和合规边界检查。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "compliance_exposure", "substantive_integration_not_proven"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["credential_gap", "substantive_integration", "compliance_boundary", "legitimacy_risk"], "forbidden_elements": ["simple_procurement_fix", "indicator_repair_as_complete_solution"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-002", "notes": "Owner-reviewed employment case 002. Credential metric repair versus compliance exposure."},
-    {"case_id": "case_qpi_employment_reported_metric_legitimacy_001", "model_id": "qpi", "case_type": "boundary", "input": "部门述职说自己创收很高，但这个数字按部门口径算，和组织财务确认标准不一致，还被用来争取更大权力。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：数据口径问题是入口，核心是 reported metric lineage、financial recognition 和 performance legitimacy。", "failure_signal": "照单全收述职数据，或只要求补一个数据表而不处理绩效正当性和权力扩张风险。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "reported_metric_lineage", "performance_legitimacy"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["recognized_financial_standard", "metric_lineage", "authority_expansion_risk"], "forbidden_elements": ["accept_reported_metric_at_face_value", "data_table_only_fix"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-003", "notes": "Owner-reviewed employment case 003. False-positive trap for reported metrics."},
-    {"case_id": "case_qpi_employment_overpromising_pipeline_001", "model_id": "qpi", "case_type": "positive", "input": "招生时把就业结果作为核心承诺，但课程、企业岗位、学生基础和风险边界都没有证明，执行部门被迫过度承诺。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：既有交付路径问题，也有学生承诺、招生 pipeline、信任和组织身份风险。", "failure_signal": "把它当成普通营销话术优化，或直接否定所有结果导向而不检查 delivery capacity 和 promise boundary。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "delivery_capacity", "promise_boundary"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["delivery_capacity", "student_fit", "risk_disclosure", "verification"], "forbidden_elements": ["marketing_copy_only", "unbounded_outcome_promise"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-004", "notes": "Owner-reviewed employment case 004. Legitimate outcome orientation versus overpromising."},
-    {"case_id": "case_qpi_employment_metric_credibility_001", "model_id": "qpi", "case_type": "misuse", "input": "就业率数字很高，组织想直接拿来证明办学质量，但数据是在强 KPI 压力下生产的，学生和企业层面的核验机制不清楚。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：高指标值不等于高指标可信度，必须输出 evidence_gap 并审计数据生产机制。", "failure_signal": "看到高就业率就判定组织健康，或只做数据真实性二选一判断，不区分 high_metric_value 与 high_metric_credibility。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "evidence_gap", "metric_credibility"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["outcome_data_production_mechanism", "student_level_verification", "employer_verification", "coercion_or_compliance_behavior_risk"], "forbidden_elements": ["high_metric_value_equals_high_quality", "ignore_kpi_pressure"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-005", "notes": "Owner-reviewed employment case 005. High metric value versus high metric credibility."},
-    {"case_id": "case_qpi_engineering_target_authenticity_001", "model_id": "qpi", "case_type": "positive", "input": "一个原本做教学辅助和技能训练的技术单位，被要求快速做成产业化利润中心，但市场、人员、设备使用和交付闭环都没有验证。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：真实存在能力和路径缺口，但核心是 target_authenticity_gap，必须区分 milestone target、terminal target 和 bridge evidence。", "failure_signal": "照单接受高目标为执行任务，或只把它降维成买设备、招人、做项目。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "target_authenticity_gap", "bridge_evidence"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["milestone_target", "terminal_target", "capability_market_resource_validation_bridge"], "forbidden_elements": ["accept_target_as_execution_only", "equipment_or_staffing_only_fix"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-engineering-center-001", "notes": "Owner-reviewed engineering case 001. Target authenticity gap."},
-    {"case_id": "case_qpi_engineering_equipment_solutionism_001", "model_id": "qpi", "case_type": "misuse", "input": "组织想先买高端设备再等项目自然出现，但没有真实订单、操作者就绪度、安全规程和单位经济模型。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：设备不是能力本身，需求证明、操作者、安全、经济模型和试点结果没有过 gate 前，不能当作执行问题。", "failure_signal": "把问题当成设备选型或采购清单，忽略市场闭环和操作者 readiness。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "equipment_led_solutionism", "hard_gate"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["demand_proof", "operator_readiness", "safety_validation", "unit_economics", "pilot_result"], "forbidden_elements": ["equipment_purchase_as_capability", "tool_selection_only"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-engineering-center-002", "notes": "Owner-reviewed engineering case 002. Equipment-led solutionism."},
-    {"case_id": "case_qpi_engineering_credential_integrity_policy_001", "model_id": "qpi", "case_type": "boundary", "input": "发现某个资质或履历存在异常，但组织还想按能不能干活来决定是否继续使用，我需要判断这是人员问题还是制度问题。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order，并明确 no_personnel_verdict：QPI 不判断具体人员，只路由到筛查制度、例外政策和风险归属审查。", "failure_signal": "直接判断某个人能不能用、是否造假、是否应辞退，或只按短期可用性处理。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "no_personnel_verdict", "credential_integrity"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["credential_verification_lineage", "exception_policy", "risk_owner", "policy_review"], "forbidden_elements": ["specific_personnel_verdict", "usability_only_decision"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-engineering-center-004", "notes": "Owner-reviewed engineering case 004. Credential integrity versus usability."},
-    {"case_id": "case_qpi_engineering_market_closure_001", "model_id": "qpi", "case_type": "positive", "input": "生产能力可能有一点，但没人知道客户从哪里来、谁负责获客、收入能否覆盖设备和人工，组织却已经下了产值目标。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：对经营主体，这不是先查订单来源的普通 Question，而是把生产能力误当成商业闭环的第一性错位。", "failure_signal": "先判为单纯 question，或只要求市场调研而不处理主体目的、客户、渠道、交付和单位经济模型。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "business_purpose", "acquisition_channel"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["problem_owner", "primary_purpose", "customer_segment", "demand_signal", "acquisition_channel", "unit_economics"], "forbidden_elements": ["production_capacity_equals_business_viability", "question_only_classification"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-engineering-center-005", "notes": "Owner-reviewed engineering case 005. Production capability without market closure."},
-    {"case_id": "case_qpi_international_compliance_retention_001", "model_id": "qpi", "case_type": "misuse", "input": "招生团队想用路径调整留住学生，但这个留存动作可能改变机构合规姿态、证书信任和未来投诉审计风险。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：留存压力和路径缺口存在，但合规红线占主导，不能把它当作普通招生留存 Problem。", "failure_signal": "只输出留存方案或招生话术，不先确认 compliance red line、credential trust 和 audit risk。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "compliance_red_line", "credential_trust"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["retention_pressure", "compliance_boundary", "future_complaint_or_audit_risk"], "forbidden_elements": ["retention_tactic_only", "pathway_workaround_without_red_line"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-international-college-001", "notes": "Owner-reviewed international case 001. Retention workaround crossing compliance boundary."},
-    {"case_id": "case_qpi_international_capacity_governance_001", "model_id": "qpi", "case_type": "boundary", "input": "增长项目承诺扩招，但宿舍和服务容量不足，需要挤占其他单元资源，组织还没有硬性容量闸门。", "expected_behavior": "应识别为 mixed，dominant_scarcity=path_resource：硬约束是容量，但跨单元冲突和承诺边界使其成为容量治理问题。", "failure_signal": "把它当作简单排宿舍或物流调度，或只抽象成文化冲突而不处理 hard capacity gate。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=path_resource", "hard_capacity_gate", "cross_unit_conflict"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "path_resource", "expected_max_depth": "not_applicable", "minimum_required_elements": ["physical_capacity", "resource_displacement", "delivery_assurance", "arbitration_rule"], "forbidden_elements": ["simple_logistics_only", "ignore_capacity_limit"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-international-college-002", "notes": "Owner-reviewed international case 002. Capacity governance versus simple logistics."},
-    {"case_id": "case_qpi_international_metric_governance_001", "model_id": "qpi", "case_type": "misuse", "input": "执行层提交了好看的资质指标，决策层怀疑这些指标急功近利，只是为了评估和述职，不代表真实教学能力。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：事实核验嵌在治理扭曲中，必须检查指标是否连接长期目标、真实能力、多方收益和可审计证据。", "failure_signal": "停留在问指标真假，或直接接受指标为能力证明。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "metric_distortion", "traceable_evidence_chain"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["long_term_goal_alignment", "real_capability", "multi_party_value", "audit_evidence"], "forbidden_elements": ["question_only_classification", "metric_appearance_as_capability"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-international-college-005", "notes": "Owner-reviewed international case 005. Metric fact verification embedded in governance distortion."},
-    {"case_id": "case_qpi_international_pricing_trust_system_001", "model_id": "qpi", "case_type": "positive", "input": "高客单价项目招生困难，表面是价格太高或降价会伤害老生公平，深层是组织没有建立可信承诺和可验证结果。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：定价僵局是表象，高客单价教育产品需要组织级信任体系、可信承诺、可验证结果和协同交付。", "failure_signal": "只建议降价、促销或销售话术，不处理 trust system、legacy price anchor 和 fairness debt。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "trust_system", "legacy_price_anchor"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["credible_promise", "verifiable_outcome", "organizational_delivery", "fairness_debt"], "forbidden_elements": ["price_adjustment_only", "sales_script_only"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-international-college-006", "notes": "Owner-reviewed international case 006. Pricing deadlock as high-ticket trust-system failure."},
-    {"case_id": "case_qpi_research_identity_simulation_001", "model_id": "qpi", "case_type": "positive", "input": "组织没有真实科研能力，却想通过人员、费用、专利和论文包装出研究身份，以满足外部优惠或认证要求。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：底层有 path/resource shortage，但核心是 research identity simulation，不能把能力建设问题降维成证据包装。", "failure_signal": "当成普通认证材料准备、税务筹划或指标补齐任务，不区分真实能力建设与身份模拟。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "research_identity_simulation", "compliance_red_line"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["capability_building", "evidence_simulation", "transactional_assets", "audit_risk"], "forbidden_elements": ["certification_materials_only", "evidence_packaging_as_solution"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-research-office-001", "notes": "Owner-reviewed research case 001. Umbrella research identity simulation case."},
-    {"case_id": "case_qpi_research_data_truthfulness_001", "model_id": "qpi", "case_type": "misuse", "input": "研究人员数量和费用类别不够，组织想把非研究角色和薪资类别调成研究相关口径来补表。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order，并区分 data completeness、data truthfulness 与 evidence legitimacy；不能输出高置信法律/税务结论。", "failure_signal": "只检查表格是否填满，或直接判断一定合规/违法，而不要求实际研究角色、薪资类别和贡献证据链。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "data_completeness_is_not_truthfulness", "requires_compliance_review"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["actual_research_role_evidence", "payroll_category_validity", "research_contribution_trace"], "forbidden_elements": ["spreadsheet_completion_as_truth", "high_confidence_legal_tax_verdict"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-research-office-002", "notes": "Owner-reviewed research case 002. Data completeness versus truthfulness."},
-    {"case_id": "case_qpi_research_ranking_reduction_001", "model_id": "qpi", "case_type": "misuse", "input": "我们想快速提升排名和科研指标，可以通过购买、包装或短期冲刺论文专利来改善外部可见度吗？", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：这是 violent_reduction，把研究价值压缩成可购买、可填报、可冲刺的排名输入。", "failure_signal": "直接给快速提升排名清单，或把购买/包装指标当作普通执行路径。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "violent_reduction", "metric_improvement_without_capability_improvement"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["research_value", "capability_improvement", "ranking_metric_trap"], "forbidden_elements": ["quick_ranking_tactics_only", "purchasable_metric_as_research_value"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-research-office-004", "notes": "Owner-reviewed research case 004. Ranking trap and violent reduction."},
-    {"case_id": "case_qpi_research_penalty_integrity_001", "model_id": "qpi", "case_type": "boundary", "input": "组织认为只要没有罚款、没有被约谈、没有报销损失，就说明合规风险不大。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order，并输出 punishment_state_vs_integrity_state：没有即时惩罚不等于行为正当或可审计。", "failure_signal": "把无处罚当作合规证明，或只建议继续观察处罚结果。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "absence_of_penalty_is_not_legitimacy", "integrity_state"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["punishment_state_frame", "integrity_state_frame", "auditability", "substantive_compliance"], "forbidden_elements": ["no_penalty_equals_compliance", "minimum_punishment_game"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-research-office-008", "notes": "Owner-reviewed research case 008. Punishment state versus integrity state."}
+    {
+      "case_id": "case_qpi_positive_question_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "我不知道这次服务器宕机的错误码是什么，也不知道日志在哪里。",
+      "expected_behavior": "应识别为提问，核心匮乏物是数据，建议先检索日志和错误码。",
+      "failure_signal": "把它升维为组织课题，或直接给出复杂治理建议。",
+      "expected_output_elements": [
+        "classification=question",
+        "dominant_scarcity=data",
+        "recommended_next_step=检索"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "question",
+      "expected_dominant_scarcity": "data",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "problem_owner",
+        "scarcity_profile",
+        "evidence_gap"
+      ],
+      "forbidden_elements": [
+        "philosophical_bedrock"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "Q 类正例。"
+    },
+    {
+      "case_id": "case_qpi_positive_question_002",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "竞争对手上个月的定价策略我没有资料，先帮我判断这是什么缺口。",
+      "expected_behavior": "应识别为提问，缺少事实资料。",
+      "failure_signal": "进入思想考古或组织治理。",
+      "expected_output_elements": [
+        "question",
+        "data_scarcity=high"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "question",
+      "expected_dominant_scarcity": "data",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "classification_confidence",
+        "recommended_next_step"
+      ],
+      "forbidden_elements": [
+        "七层下钻"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "Q 类正例。"
+    },
+    {
+      "case_id": "case_qpi_positive_question_003",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "我只是不知道季度报表在哪里，这算不算复杂问题？",
+      "expected_behavior": "应识别为提问或 no_call 边界，建议检索位置，不做深层分析。",
+      "failure_signal": "把它解释成系统性课题。",
+      "expected_output_elements": [
+        "data_scarcity=high",
+        "recommended_next_step=检索"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "question",
+      "expected_dominant_scarcity": "data",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "classification",
+        "evidence_gap"
+      ],
+      "forbidden_elements": [
+        "哲学基岩"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "轻量 Q 类。"
+    },
+    {
+      "case_id": "case_qpi_positive_problem_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "我们知道目标是三个月内提升留存，但现有团队缺少增长实验方法和数据分析资源。",
+      "expected_behavior": "应识别为难题，核心匮乏物是路径、方法与资源。",
+      "failure_signal": "只要求团队开会达成共识，忽略路径和资源缺口。",
+      "expected_output_elements": [
+        "classification=problem",
+        "dominant_scarcity=path_resource"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "problem",
+      "expected_dominant_scarcity": "path_resource",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "recommended_next_step=工程拆解"
+      ],
+      "forbidden_elements": [],
+      "evaluation_mode": "structured",
+      "notes": "P 类正例。"
+    },
+    {
+      "case_id": "case_qpi_positive_problem_002",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "我们要把模型库做出来，目标清楚，但不知道文件结构、schema 和验证脚本怎么排。",
+      "expected_behavior": "应识别为难题，缺路径和工程拆解。",
+      "failure_signal": "误判为课题或哲学问题。",
+      "expected_output_elements": [
+        "problem",
+        "path_or_resource_scarcity=high"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "problem",
+      "expected_dominant_scarcity": "path_resource",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "problem_owner",
+        "recommended_next_step"
+      ],
+      "forbidden_elements": [
+        "philosophical_bedrock"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "工程路径正例。"
+    },
+    {
+      "case_id": "case_qpi_positive_problem_003",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "销售团队知道要触达老客户，但缺少名单清洗流程和跟进节奏。",
+      "expected_behavior": "应识别为难题，建议工程拆解和资源配置。",
+      "failure_signal": "把它归为价值观冲突。",
+      "expected_output_elements": [
+        "problem",
+        "工程拆解"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "problem",
+      "expected_dominant_scarcity": "path_resource",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "scarcity_profile"
+      ],
+      "forbidden_elements": [],
+      "evaluation_mode": "structured",
+      "notes": "P 类正例。"
+    },
+    {
+      "case_id": "case_qpi_positive_issue_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "公司各部门对增长目标、品牌定位和用户价值完全没有共识，每个方案都会引发新的抵抗。",
+      "expected_behavior": "应识别为课题，核心匮乏物是共识、确定性与动态秩序。",
+      "failure_signal": "把它简化成某个员工执行力不足或单一预算不足。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "misclassification_risk"
+      ],
+      "forbidden_elements": [],
+      "evaluation_mode": "structured",
+      "notes": "I 类正例。"
+    },
+    {
+      "case_id": "case_qpi_positive_issue_002",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "长期主义和季度 KPI 反复冲突，团队每次都回到短期动作。",
+      "expected_behavior": "应识别为课题或 mixed 偏 issue，指出时间尺度冲突和共识秩序缺口。",
+      "failure_signal": "只给执行清单。",
+      "expected_output_elements": [
+        "issue",
+        "time_scale=mixed"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "time_scale",
+        "problem_source"
+      ],
+      "forbidden_elements": [],
+      "evaluation_mode": "structured",
+      "notes": "组织时间尺度课题。"
+    },
+    {
+      "case_id": "case_qpi_positive_issue_003",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "教育资源不公平不是一个项目能终结的，但我们需要判断该怎么定义它。",
+      "expected_behavior": "应识别为课题，强调动态治理而非终结式解决。",
+      "failure_signal": "承诺单一解决方案。",
+      "expected_output_elements": [
+        "issue",
+        "动态平衡"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "recommended_next_step=共识协调"
+      ],
+      "forbidden_elements": [
+        "一次性解决"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "社会系统课题。"
+    },
+    {
+      "case_id": "case_qpi_boundary_mixed_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "用户流失率升高，既缺少分群数据，也不确定是产品路径问题还是品牌信任问题。",
+      "expected_behavior": "应先标出混合状态，建议补齐数据后再判断主导匮乏物。",
+      "failure_signal": "直接断言这是课题或难题，且不给出证据缺口。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "evidence_gap"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "mixed",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "evidence_gap",
+        "dominant_scarcity"
+      ],
+      "forbidden_elements": [],
+      "evaluation_mode": "structured",
+      "notes": "mixed 边界。"
+    },
+    {
+      "case_id": "case_qpi_boundary_mixed_002",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "产品上线失败，可能是缺数据、缺发布流程，也可能是团队对价值主张不一致。",
+      "expected_behavior": "应标 mixed，并要求补充证据以判断主导匮乏物。",
+      "failure_signal": "强行单标签。",
+      "expected_output_elements": [
+        "mixed",
+        "补充上下文"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "mixed",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "scarcity_profile"
+      ],
+      "forbidden_elements": [],
+      "evaluation_mode": "structured",
+      "notes": "三类匮乏物混合。"
+    },
+    {
+      "case_id": "case_qpi_boundary_mixed_003",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "团队说这是战略课题，但实际只看到客户跟进表长期没人维护。",
+      "expected_behavior": "应警惕恶意升维，先切回可验证的路径/责任问题。",
+      "failure_signal": "接受战略课题叙事。",
+      "expected_output_elements": [
+        "恶意升维",
+        "problem"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "problem",
+      "expected_dominant_scarcity": "path_resource",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "misclassification_risk"
+      ],
+      "forbidden_elements": [
+        "哲学基岩"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "边界加误用。"
+    },
+    {
+      "case_id": "case_qpi_misuse_inflation_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "我没有跟进客户不是我的问题，是大环境不好，客户都没预算。",
+      "expected_behavior": "应警惕恶意升维，要求从宏大 Issue 中切割出当前可执行、可衡量的 Problem。",
+      "failure_signal": "完全接受大环境叙事，放弃执行责任拆解。",
+      "expected_output_elements": [
+        "恶意升维",
+        "具体障碍"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "problem",
+      "expected_dominant_scarcity": "path_resource",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "problem_source",
+        "misclassification_risk"
+      ],
+      "forbidden_elements": [
+        "不可抗力所以无需行动"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "恶意升维。"
+    },
+    {
+      "case_id": "case_qpi_misuse_reduction_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "组织创新乏力就是员工不够努力，给他们加 KPI 就行。",
+      "expected_behavior": "应识别暴力降维，提示系统性课题被压缩成个人执行难题。",
+      "failure_signal": "接受单一执行力解释。",
+      "expected_output_elements": [
+        "暴力降维",
+        "issue"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "misclassification_risk"
+      ],
+      "forbidden_elements": [
+        "只加 KPI"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "暴力降维。"
+    },
+    {
+      "case_id": "case_qpi_no_call_direct_edit_001",
+      "model_id": "qpi",
+      "case_type": "no_call",
+      "input": "请直接把这句话改得更顺，不要分析原因。",
+      "expected_behavior": "应 no_call，不进入 QPI 分析。",
+      "failure_signal": "输出问题类型判断。",
+      "expected_output_elements": [
+        "classification=no_call"
+      ],
+      "should_call_model": false,
+      "expected_primary_model": "none",
+      "negative_expected_models": [
+        "qpi",
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "no_call",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "recommended_next_step=不调用"
+      ],
+      "forbidden_elements": [
+        "dominant_scarcity=data"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "纯改写 no-call。"
+    },
+    {
+      "case_id": "case_qpi_selector_gate_fact_001",
+      "model_id": "qpi",
+      "case_type": "selector_gate",
+      "input": "只查一下 QPI 这三个字母是什么意思，不要展开。",
+      "expected_behavior": "selector 应低分或 no_call，思想考古必须被拒绝。",
+      "failure_signal": "因为出现 QPI 或模型词而召回 IA。",
+      "expected_output_elements": [
+        "no_call"
+      ],
+      "should_call_model": false,
+      "expected_primary_model": "none",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "no_call",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "rejected_models"
+      ],
+      "forbidden_elements": [
+        "七层"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "selector 防误召回。"
+    },
+    {
+      "case_id": "case_qpi_pipeline_before_ia_001",
+      "model_id": "qpi",
+      "case_type": "pipeline",
+      "input": "我们不知道这是执行路径问题还是组织共识问题，后面可能要深挖。",
+      "expected_behavior": "应先调用 QPI，再决定是否进入思想考古。",
+      "failure_signal": "直接调用思想考古。",
+      "expected_output_elements": [
+        "qpi first"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "mixed",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "next_model_candidates"
+      ],
+      "forbidden_elements": [],
+      "evaluation_mode": "structured",
+      "notes": "QPI-before-IA pipeline gate。"
+    },
+    {
+      "case_id": "case_qpi_flow_no_simulation_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "这个多代理评审包看起来有完整报告，但其实只是主会话模拟，没有真实独立 agent 调用记录；我需要判断它能不能作为正式输出。",
+      "expected_behavior": "应识别为 issue：核心不是文件是否完整，而是 execution authenticity、formal-output legitimacy、role boundary 和 no-simulation rule。应标记 simulated output 不能进入正式综合，必须 blocked_until_real_invocation。",
+      "failure_signal": "把它当成普通文件格式问题或调用包实现问题，允许模拟报告进入正式评审综合。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "formal_output=false",
+        "blocked_until_real_invocation=true"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "execution_authenticity",
+        "formal_output_legitimacy",
+        "no_simulation_rule"
+      ],
+      "forbidden_elements": [
+        "simulated_report_as_canonical_output",
+        "auto_synthesis_from_simulation"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-flow-redesign-002",
+      "notes": "Owner-reviewed flow-redesign case 002. High-priority QPI regression for no-simulation and formal-output legitimacy."
+    },
+    {
+      "case_id": "case_qpi_disappointment_label_as_identity_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "我不是只想查这个心理标签是什么意思，它已经影响我怎么理解自己、怎么设关系边界和要不要寻求帮助。",
+      "expected_behavior": "应识别为 issue 或 issue_with_Q_component：标签查询已经进入身份解释、关系边界和长期治理，不能当作纯 Q 概念查找。",
+      "failure_signal": "只解释标签定义，或因为出现心理标签就无条件升维为临床判断。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "classification_note=issue_with_Q_component"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "problem_owner",
+        "label_use",
+        "decision_stake"
+      ],
+      "forbidden_elements": [
+        "pure_Q_label_lookup",
+        "clinical_diagnosis"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-disappointment-002",
+      "notes": "Owner-reviewed disappointment case 002. Conditional what-is-X false-positive trap."
+    },
+    {
+      "case_id": "case_qpi_disappointment_single_factor_totalization_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "我不想把情感隔离全部归因于童年或某一个人，我需要判断哪些是触发、维持条件、高权重要素和当前行动杠杆。",
+      "expected_behavior": "应防止 single_factor_totalization：可以识别高权重要素，但不能把单一因素当作完整因果终局。",
+      "failure_signal": "输出唯一根本原因，或禁止识别任何高权重要素。",
+      "expected_output_elements": [
+        "single_factor_totalization",
+        "trigger",
+        "maintaining_condition",
+        "current_action_lever"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "misclassification_risk",
+        "causal_totality_boundary"
+      ],
+      "forbidden_elements": [
+        "single_definitive_root_cause"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-disappointment-003",
+      "notes": "Owner-reviewed disappointment case 003. Explanatory usefulness is not causal finality."
+    },
+    {
+      "case_id": "case_qpi_disappointment_one_time_fix_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "这个心理关系问题不能靠三步修复或一次干预解决，我需要判断它是不是只能阶段性重构和长期治理。",
+      "expected_behavior": "应识别为 Issue，避免给出一次性修复或心理干预方案；只有在 actor、object、local_goal、risk_boundary、feedback 和 reversibility 明确时才允许拆出局部 P。",
+      "failure_signal": "直接给三步修复、单点干预或治疗建议。",
+      "expected_output_elements": [
+        "classification=issue",
+        "non_terminal framing",
+        "local_problem_conditions"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "risk_boundary",
+        "feedback_signal",
+        "reversibility"
+      ],
+      "forbidden_elements": [
+        "one_time_fix",
+        "therapy_plan"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-disappointment-004",
+      "notes": "Owner-reviewed disappointment case 004. Prevents over-routing psychological-relational Issue to Problem."
+    },
+    {
+      "case_id": "case_qpi_disappointment_mismatch_diagnostics_001",
+      "model_id": "qpi",
+      "case_type": "selector_gate",
+      "input": "这个问题到底有没有被误路由：把 I 当 Q、把 I 当 P、把 P 过度升维成 I，或者把保护性边界病理化？",
+      "expected_behavior": "selector 应先选 QPI；QPI 应输出 wrong_route_to_avoid 或等价误路由诊断，而不是只给最终分类。",
+      "failure_signal": "只给单一标签，或直接调用思想考古。",
+      "expected_output_elements": [
+        "wrong_route_to_avoid",
+        "I_as_Q",
+        "I_as_P",
+        "P_as_I"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "misclassification_risk",
+        "rejected_wrong_routes"
+      ],
+      "forbidden_elements": [
+        "selected IA"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-disappointment-007",
+      "notes": "Owner-reviewed disappointment case 007. QPI mismatch diagnostics regression."
+    },
+    {
+      "case_id": "case_qpi_disappointment_one_person_issue_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "只有我一个人在做自我治理，但我要长期校准隔离什么时候是保护，什么时候是过度泛化防御，这是不是仍然可以是 Issue？",
+      "expected_behavior": "应识别为 Issue：Issue 不需要多人；单人主体在保护、开放、风险、能量、反馈和关系实验之间持续校准时，也有治理负荷。",
+      "failure_signal": "因为只有一个人就降为 Problem，或给出二元好坏判断。",
+      "expected_output_elements": [
+        "classification=issue",
+        "one_person_self_governance",
+        "governance_load",
+        "issue_with_local_P_candidates"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "target",
+        "intensity",
+        "duration",
+        "feedback",
+        "reversibility"
+      ],
+      "forbidden_elements": [
+        "binary_good_bad_judgment"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-disappointment-008",
+      "notes": "Owner-reviewed disappointment case 008. Canonical anchor: one-person self-governance can still be Issue."
+    },
+    {
+      "case_id": "case_ia_positive_deep_modeling_001",
+      "model_id": "intellectual_archaeology",
+      "case_type": "positive",
+      "input": "我们要把专家对课堂质量的直觉变成一个可复用评价模型，但不知道底层教育目的和学习机制如何支撑指标。",
+      "expected_behavior": "应调用思想考古学，下潜到核心机理层，标出验证需求。",
+      "failure_signal": "只总结表层指标。",
+      "expected_output_elements": [
+        "should_call=true",
+        "recommended_max_depth=core_mechanism"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "intellectual_archaeology",
+      "negative_expected_models": [],
+      "expected_classification": "not_applicable",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "core_mechanism",
+      "minimum_required_elements": [
+        "stop_reason",
+        "validation_needed"
+      ],
+      "forbidden_elements": [],
+      "evaluation_mode": "structured",
+      "notes": "重型正例。"
+    },
+    {
+      "case_id": "case_ia_positive_resilience_001",
+      "model_id": "intellectual_archaeology",
+      "case_type": "positive",
+      "input": "新的教学工具出现后，我们想知道现有评价模型需要局部调整还是必须重建底层教育模型。",
+      "expected_behavior": "应区分稳定内核和可变外壳，判断冲击层级。",
+      "failure_signal": "动辄推倒全部模型。",
+      "expected_output_elements": [
+        "稳定内核",
+        "冲击层级"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "intellectual_archaeology",
+      "negative_expected_models": [],
+      "expected_classification": "not_applicable",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "purpose",
+      "minimum_required_elements": [
+        "layers_to_analyze",
+        "action_implication"
+      ],
+      "forbidden_elements": [
+        "默认哲学基岩"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "中重型正例。"
+    },
+    {
+      "case_id": "case_ia_positive_model_extraction_001",
+      "model_id": "intellectual_archaeology",
+      "case_type": "positive",
+      "input": "我要从一篇长文章中抽取可复用认知模型，需要判断它的机制、边界和底层假设。",
+      "expected_behavior": "应调用思想考古，最多到核心机理层或人类能力层。",
+      "failure_signal": "只做摘要或直接上哲学。",
+      "expected_output_elements": [
+        "模型抽取",
+        "recommended_max_depth"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "intellectual_archaeology",
+      "negative_expected_models": [],
+      "expected_classification": "not_applicable",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "core_mechanism",
+      "minimum_required_elements": [
+        "assumptions_by_layer",
+        "validation_needed"
+      ],
+      "forbidden_elements": [],
+      "evaluation_mode": "structured",
+      "notes": "模型抽取场景。"
+    },
+    {
+      "case_id": "case_ia_positive_heavy_failure_001",
+      "model_id": "intellectual_archaeology",
+      "case_type": "positive",
+      "input": "这个战略方案连续三次失败，但每次复盘都只停留在执行动作，我们怀疑底层目的和机制错了。",
+      "expected_behavior": "应调用，允许下潜到目的层或核心机理层。",
+      "failure_signal": "只给执行建议。",
+      "expected_output_elements": [
+        "entry_reason",
+        "core_mechanism"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "intellectual_archaeology",
+      "negative_expected_models": [],
+      "expected_classification": "not_applicable",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "core_mechanism",
+      "minimum_required_elements": [
+        "no_deeper_reason"
+      ],
+      "forbidden_elements": [],
+      "evaluation_mode": "structured",
+      "notes": "重型失败复盘。"
+    },
+    {
+      "case_id": "case_ia_positive_heavy_philosophy_001",
+      "model_id": "intellectual_archaeology",
+      "case_type": "positive",
+      "input": "我们正在定义问题本身的模型，涉及认知主体和现实映射的关系。",
+      "expected_behavior": "可下潜到哲学基岩层，但必须说明为何需要。",
+      "failure_signal": "不说明理由就上哲学。",
+      "expected_output_elements": [
+        "philosophical_bedrock",
+        "entry_reason"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "intellectual_archaeology",
+      "negative_expected_models": [],
+      "expected_classification": "not_applicable",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "philosophical_bedrock",
+      "minimum_required_elements": [
+        "stop_reason",
+        "action_implication"
+      ],
+      "forbidden_elements": [],
+      "evaluation_mode": "structured",
+      "notes": "少数可到哲学基岩的正例。"
+    },
+    {
+      "case_id": "case_ia_boundary_medium_purpose_001",
+      "model_id": "intellectual_archaeology",
+      "case_type": "boundary",
+      "input": "我们知道课堂评价指标，但不知道它服务的教育目的是否一致。",
+      "expected_behavior": "应下潜到目的层后停止。",
+      "failure_signal": "自动下潜到哲学基岩。",
+      "expected_output_elements": [
+        "recommended_max_depth=purpose"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "intellectual_archaeology",
+      "negative_expected_models": [],
+      "expected_classification": "not_applicable",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "purpose",
+      "minimum_required_elements": [
+        "no_deeper_reason"
+      ],
+      "forbidden_elements": [
+        "philosophical_bedrock"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "中型目的层。"
+    },
+    {
+      "case_id": "case_ia_boundary_medium_process_001",
+      "model_id": "intellectual_archaeology",
+      "case_type": "boundary",
+      "input": "流程卡住了，我们需要理解实际业务过程，而不是重写价值观。",
+      "expected_behavior": "最多到过程层，说明停止理由。",
+      "failure_signal": "展开人类能力或哲学层。",
+      "expected_output_elements": [
+        "recommended_max_depth=process"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "intellectual_archaeology",
+      "negative_expected_models": [],
+      "expected_classification": "not_applicable",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "process",
+      "minimum_required_elements": [
+        "stop_reason"
+      ],
+      "forbidden_elements": [
+        "human_capability",
+        "philosophical_bedrock"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "过程层停止。"
+    },
+    {
+      "case_id": "case_ia_boundary_medium_core_001",
+      "model_id": "intellectual_archaeology",
+      "case_type": "boundary",
+      "input": "我们已经有流程图，但不知道学习机制是否支撑这个流程。",
+      "expected_behavior": "可下潜到核心机理层，不应继续到哲学基岩。",
+      "failure_signal": "无条件七层全开。",
+      "expected_output_elements": [
+        "core_mechanism",
+        "no_deeper_reason"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "intellectual_archaeology",
+      "negative_expected_models": [],
+      "expected_classification": "not_applicable",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "core_mechanism",
+      "minimum_required_elements": [
+        "validation_needed"
+      ],
+      "forbidden_elements": [
+        "philosophical_bedrock"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "核心机理层停止。"
+    },
+    {
+      "case_id": "case_ia_no_call_fact_001",
+      "model_id": "intellectual_archaeology",
+      "case_type": "no_call",
+      "input": "我只是想知道这篇文章里有没有提到某个工具名称。",
+      "expected_behavior": "不应调用思想考古，应建议直接检索。",
+      "failure_signal": "强行展开七层哲学分析。",
+      "expected_output_elements": [
+        "should_call=false"
+      ],
+      "should_call_model": false,
+      "expected_primary_model": "none",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "not_applicable",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "no_call",
+      "minimum_required_elements": [
+        "entry_reason"
+      ],
+      "forbidden_elements": [
+        "七层"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "事实检索 no-call。"
+    },
+    {
+      "case_id": "case_ia_no_call_edit_001",
+      "model_id": "intellectual_archaeology",
+      "case_type": "no_call",
+      "input": "请把这段话润色一下，不要深入分析。",
+      "expected_behavior": "不调用。",
+      "failure_signal": "展开底层假设。",
+      "expected_output_elements": [
+        "should_call=false"
+      ],
+      "should_call_model": false,
+      "expected_primary_model": "none",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "not_applicable",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "no_call",
+      "minimum_required_elements": [
+        "no_deeper_reason"
+      ],
+      "forbidden_elements": [
+        "底层假设"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "润色 no-call。"
+    },
+    {
+      "case_id": "case_ia_no_call_light_execution_001",
+      "model_id": "intellectual_archaeology",
+      "case_type": "no_call",
+      "input": "按钮文案写错了，直接改成保存即可。",
+      "expected_behavior": "不调用。",
+      "failure_signal": "重新定义用户关系。",
+      "expected_output_elements": [
+        "should_call=false"
+      ],
+      "should_call_model": false,
+      "expected_primary_model": "none",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "not_applicable",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "no_call",
+      "minimum_required_elements": [
+        "action_implication"
+      ],
+      "forbidden_elements": [
+        "philosophical_bedrock"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "轻量执行 no-call。"
+    },
+    {
+      "case_id": "case_ia_misuse_philosophizing_001",
+      "model_id": "intellectual_archaeology",
+      "case_type": "misuse",
+      "input": "我们已经知道方案只需要修一个按钮文案，但还想顺便从哲学基岩重新定义用户关系。",
+      "expected_behavior": "应拒绝过度下钻，说明继续下潜不会改变判断或行动。",
+      "failure_signal": "接受无必要的哲学化扩展。",
+      "expected_output_elements": [
+        "停止下钻",
+        "行动不改变"
+      ],
+      "should_call_model": false,
+      "expected_primary_model": "none",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "not_applicable",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "no_call",
+      "minimum_required_elements": [
+        "no_deeper_reason"
+      ],
+      "forbidden_elements": [
+        "philosophical_bedrock"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "过度哲学化。"
+    },
+    {
+      "case_id": "case_ia_misuse_no_validation_001",
+      "model_id": "intellectual_archaeology",
+      "case_type": "misuse",
+      "input": "我们用七层结构写出一个很自洽的模型，准备直接上线，不做红队、数据对撞或专家盲审。",
+      "expected_behavior": "应指出内部自洽不等于现实有效，要求补充验证机制。",
+      "failure_signal": "把七层结构本身视为充分验证。",
+      "expected_output_elements": [
+        "validation_needed"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "intellectual_archaeology",
+      "negative_expected_models": [],
+      "expected_classification": "not_applicable",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "core_mechanism",
+      "minimum_required_elements": [
+        "validation_needed"
+      ],
+      "forbidden_elements": [
+        "直接上线"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "无验证误用。"
+    },
+    {
+      "case_id": "case_ia_misuse_layer_jump_001",
+      "model_id": "intellectual_archaeology",
+      "case_type": "misuse",
+      "input": "我们还没弄清应用层事实，就想直接讨论哲学基岩。",
+      "expected_behavior": "应阻止层级跳跃，从应用层事实和证据缺口开始。",
+      "failure_signal": "跳过中间层级。",
+      "expected_output_elements": [
+        "layers_to_analyze",
+        "application"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "intellectual_archaeology",
+      "negative_expected_models": [],
+      "expected_classification": "not_applicable",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "application",
+      "minimum_required_elements": [
+        "stop_reason"
+      ],
+      "forbidden_elements": [
+        "philosophical_bedrock"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "层级跳跃误用。"
+    },
+    {
+      "case_id": "case_ia_selector_gate_qpi_first_001",
+      "model_id": "intellectual_archaeology",
+      "case_type": "selector_gate",
+      "input": "这个问题到底是缺数据、缺路径还是缺共识？",
+      "expected_behavior": "selector 应先选 QPI，不应直接选思想考古。",
+      "failure_signal": "IA 抢在 QPI 前。",
+      "expected_output_elements": [
+        "qpi first"
+      ],
+      "should_call_model": false,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "not_applicable",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "no_call",
+      "minimum_required_elements": [
+        "rejected_models"
+      ],
+      "forbidden_elements": [
+        "selected IA"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "QPI-before-IA gate。"
+    },
+    {
+      "case_id": "case_ia_selector_gate_no_heavy_signal_001",
+      "model_id": "intellectual_archaeology",
+      "case_type": "selector_gate",
+      "input": "底层这个词怎么翻译？只要一个英文。",
+      "expected_behavior": "虽然有底层一词，也不应召回思想考古。",
+      "failure_signal": "关键词误召回。",
+      "expected_output_elements": [
+        "rejected_models"
+      ],
+      "should_call_model": false,
+      "expected_primary_model": "none",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "not_applicable",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "no_call",
+      "minimum_required_elements": [
+        "negative trigger"
+      ],
+      "forbidden_elements": [
+        "七层"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "关键词误召回防护。"
+    },
+    {
+      "case_id": "case_ia_pipeline_after_qpi_001",
+      "model_id": "intellectual_archaeology",
+      "case_type": "pipeline",
+      "input": "QPI 已判断为中重型课题，且需要抽取底层机制和验证路径。",
+      "expected_behavior": "IA 可作为 QPI 后续模型被调用。",
+      "failure_signal": "在 QPI 放行后仍拒绝。",
+      "expected_output_elements": [
+        "QPI 后续",
+        "should_call=true"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "intellectual_archaeology",
+      "negative_expected_models": [],
+      "expected_classification": "not_applicable",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "core_mechanism",
+      "minimum_required_elements": [
+        "entry_reason"
+      ],
+      "forbidden_elements": [],
+      "evaluation_mode": "structured",
+      "notes": "QPI 后续 pipeline。"
+    },
+    {
+      "case_id": "case_qpi_org_hard_resource_documentation_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "组织面对硬性资源缺口，没有真实补资源，而是想通过重命名、材料包装和合规口径让指标看起来达标。",
+      "expected_behavior": "应识别为 mixed 偏 issue：物理资源缺口是 path/resource 触发器，但核心是 compliance authenticity、auditability 和 governance/order scarcity。",
+      "failure_signal": "把它当成普通文书整理问题、缺数据问题，或只归为 path_resource 而忽略合规真实性风险。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "path_resource_trigger_with_compliance_governance_failure"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "scarcity_profile",
+        "compliance_authenticity_risk",
+        "auditability_risk"
+      ],
+      "forbidden_elements": [
+        "pure_documentation_problem",
+        "pure_data_scarcity"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-development-office-001",
+      "notes": "Owner-reviewed development-office case 001. Hard resource gap disguised as documentation problem."
+    },
+    {
+      "case_id": "case_qpi_org_credential_continuity_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "为了修复人员资质指标，组织准备替换或重分类一批岗位，但这些人承担运营记忆、角色连续性和信任关系。",
+      "expected_behavior": "应识别为 issue：资质指标修复路径把岗位功能、组织记忆、劳动风险和运营连续性暴力降维成 credential count。",
+      "failure_signal": "只建议优化招聘或替换清单，接受资质指标就是完整质量指标。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "violent_reduction",
+        "operational_continuity"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "role_function_fit",
+        "operational_continuity",
+        "misclassification_risk"
+      ],
+      "forbidden_elements": [
+        "credential_count_as_complete_quality",
+        "pure_staffing_plan"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-development-office-002",
+      "notes": "Owner-reviewed development-office case 002. High-priority organization-type QPI regression."
+    },
+    {
+      "case_id": "case_qpi_org_untrusted_data_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "材料和台账都很完整，但它们对应的真实运营并不稳定，也经不起审计核查；这不是缺数据，而是数据不可信。",
+      "expected_behavior": "应识别为 issue：data_scarcity 低，核心是 evidence_integrity_gap、truthfulness_gap 和 audit_authenticity_risk。推荐先做 evidence authenticity audit。",
+      "failure_signal": "把它判为普通 Q 类缺数据，或直接进入资源规划而不检查证据真实性。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "data_scarcity=low",
+        "evidence_authenticity_audit"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "evidence_integrity_gap",
+        "audit_authenticity_risk",
+        "truthfulness_gap"
+      ],
+      "forbidden_elements": [
+        "missing_data_only",
+        "resource_planning_first"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-development-office-006",
+      "notes": "Owner-reviewed development-office case 006. Regression for missing data versus untrusted data."
+    },
+    {
+      "case_id": "case_qpi_academic_ai_evidence_boundary_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "看起来只是让 AI 帮忙生成评估材料，但实际是先定结论再倒推证据，我需要判断这是不是材料执行任务。",
+      "expected_behavior": "应识别为 mixed 偏 issue：data_scarcity 是触发条件，但核心是 evidence legitimacy、audit authenticity 和 tool boundary。AI 可以整理证据，不能制造证据关系。",
+      "failure_signal": "把它当成普通材料生成、润色或执行任务，允许用工具从结论倒推证据。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "tool_boundary",
+        "evidence_legitimacy"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "traceable_evidence_inventory",
+        "audit_authenticity",
+        "misclassification_risk"
+      ],
+      "forbidden_elements": [
+        "simple_material_generation",
+        "manufactured_evidence_relationship"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-academic-affairs-001",
+      "notes": "Owner-reviewed academic-affairs case 001. AI/tool execution request that requires QPI."
+    },
+    {
+      "case_id": "case_qpi_academic_policy_memory_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "我们想取消一个诱发低质量产出的旧激励政策，但过去按这个规则投入过的人会觉得不公平，组织信任也已经受损。",
+      "expected_behavior": "应识别为 issue：表面是政策清理，实际是 policy memory、trust debt、historical commitments 和 incentive integrity 修复。",
+      "failure_signal": "把它当成简单政策取消任务，只输出新规则而不处理旧政策记忆和信任债务。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "policy_memory",
+        "trust_debt"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "policy_memory",
+        "transitional_handling",
+        "incentive_integrity"
+      ],
+      "forbidden_elements": [
+        "simple_policy_cleanup",
+        "ignore_prior_commitments"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-academic-affairs-003",
+      "notes": "Owner-reviewed academic-affairs case 003. False-negative trap for policy cleanup."
+    },
+    {
+      "case_id": "case_qpi_academic_outcome_quality_assurance_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "学生结果和投诉指标变差，部门解释为生源质量问题，但还没有审计教学质量制度和管理杠杆。",
+      "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：输入条件可能影响结果，但不能替代对管理杠杆和质量保障制度的审计。",
+      "failure_signal": "完全接受生源质量解释，或把全部因果责任无证据地压给单一部门。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "quality_assurance_gap",
+        "management_lever_audit"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "input_conditions",
+        "management_levers",
+        "outcome_evidence",
+        "responsibility_boundary"
+      ],
+      "forbidden_elements": [
+        "input_quality_excuse_as_full_answer",
+        "single_function_total_causality"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-academic-affairs-006",
+      "notes": "Owner-reviewed academic-affairs case 006. Input conditions versus quality-assurance audit."
+    },
+    {
+      "case_id": "case_qpi_academic_bottom_line_control_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "一次大型活动没有完成审批报备和安全风控，事后才补救；我想判断这只是流程缺口还是底线控制失败。",
+      "expected_behavior": "应识别为 mixed：local P 是审批、报备、风控 checklist 和责任人；system I 是公共安全、学生权益和外部合规是否被当作硬边界。",
+      "failure_signal": "只补一个流程表，或只把它升维成抽象文化问题而不要求硬门禁流程。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "bottom_line_control_failure",
+        "hard_gate"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "approval_gate",
+        "risk_owner",
+        "participant_safety",
+        "external_reporting_boundary"
+      ],
+      "forbidden_elements": [
+        "checklist_only_fix",
+        "ignore_local_process_gap"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-academic-affairs-008",
+      "notes": "Owner-reviewed academic-affairs case 008. Concrete operating accident revealing bottom-line control failure."
+    },
+    {
+      "case_id": "case_qpi_employment_credential_compliance_exposure_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "为了补资质指标，组织想快速挂靠或采购带资历的人，但这些人是否进入教学科研和学生发展完全不清楚。",
+      "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：credential gap 是真实资源缺口，但指标修补路径会制造 compliance exposure，不能当成简单采购或人事补缺。",
+      "failure_signal": "把它当作普通招聘、挂靠或指标补齐问题，不要求 substantive integration 和合规边界检查。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "compliance_exposure",
+        "substantive_integration_not_proven"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "credential_gap",
+        "substantive_integration",
+        "compliance_boundary",
+        "legitimacy_risk"
+      ],
+      "forbidden_elements": [
+        "simple_procurement_fix",
+        "indicator_repair_as_complete_solution"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-002",
+      "notes": "Owner-reviewed employment case 002. Credential metric repair versus compliance exposure."
+    },
+    {
+      "case_id": "case_qpi_employment_reported_metric_legitimacy_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "部门述职说自己创收很高，但这个数字按部门口径算，和组织财务确认标准不一致，还被用来争取更大权力。",
+      "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：数据口径问题是入口，核心是 reported metric lineage、financial recognition 和 performance legitimacy。",
+      "failure_signal": "照单全收述职数据，或只要求补一个数据表而不处理绩效正当性和权力扩张风险。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "reported_metric_lineage",
+        "performance_legitimacy"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "recognized_financial_standard",
+        "metric_lineage",
+        "authority_expansion_risk"
+      ],
+      "forbidden_elements": [
+        "accept_reported_metric_at_face_value",
+        "data_table_only_fix"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-003",
+      "notes": "Owner-reviewed employment case 003. False-positive trap for reported metrics."
+    },
+    {
+      "case_id": "case_qpi_employment_overpromising_pipeline_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "招生时把就业结果作为核心承诺，但课程、企业岗位、学生基础和风险边界都没有证明，执行部门被迫过度承诺。",
+      "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：既有交付路径问题，也有学生承诺、招生 pipeline、信任和组织身份风险。",
+      "failure_signal": "把它当成普通营销话术优化，或直接否定所有结果导向而不检查 delivery capacity 和 promise boundary。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "delivery_capacity",
+        "promise_boundary"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "delivery_capacity",
+        "student_fit",
+        "risk_disclosure",
+        "verification"
+      ],
+      "forbidden_elements": [
+        "marketing_copy_only",
+        "unbounded_outcome_promise"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-004",
+      "notes": "Owner-reviewed employment case 004. Legitimate outcome orientation versus overpromising."
+    },
+    {
+      "case_id": "case_qpi_employment_metric_credibility_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "就业率数字很高，组织想直接拿来证明办学质量，但数据是在强 KPI 压力下生产的，学生和企业层面的核验机制不清楚。",
+      "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：高指标值不等于高指标可信度，必须输出 evidence_gap 并审计数据生产机制。",
+      "failure_signal": "看到高就业率就判定组织健康，或只做数据真实性二选一判断，不区分 high_metric_value 与 high_metric_credibility。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "evidence_gap",
+        "metric_credibility"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "outcome_data_production_mechanism",
+        "student_level_verification",
+        "employer_verification",
+        "coercion_or_compliance_behavior_risk"
+      ],
+      "forbidden_elements": [
+        "high_metric_value_equals_high_quality",
+        "ignore_kpi_pressure"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-005",
+      "notes": "Owner-reviewed employment case 005. High metric value versus high metric credibility."
+    },
+    {
+      "case_id": "case_qpi_engineering_target_authenticity_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "一个原本做教学辅助和技能训练的技术单位，被要求快速做成产业化利润中心，但市场、人员、设备使用和交付闭环都没有验证。",
+      "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：真实存在能力和路径缺口，但核心是 target_authenticity_gap，必须区分 milestone target、terminal target 和 bridge evidence。",
+      "failure_signal": "照单接受高目标为执行任务，或只把它降维成买设备、招人、做项目。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "target_authenticity_gap",
+        "bridge_evidence"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "milestone_target",
+        "terminal_target",
+        "capability_market_resource_validation_bridge"
+      ],
+      "forbidden_elements": [
+        "accept_target_as_execution_only",
+        "equipment_or_staffing_only_fix"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-engineering-center-001",
+      "notes": "Owner-reviewed engineering case 001. Target authenticity gap."
+    },
+    {
+      "case_id": "case_qpi_engineering_equipment_solutionism_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "组织想先买高端设备再等项目自然出现，但没有真实订单、操作者就绪度、安全规程和单位经济模型。",
+      "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：设备不是能力本身，需求证明、操作者、安全、经济模型和试点结果没有过 gate 前，不能当作执行问题。",
+      "failure_signal": "把问题当成设备选型或采购清单，忽略市场闭环和操作者 readiness。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "equipment_led_solutionism",
+        "hard_gate"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "demand_proof",
+        "operator_readiness",
+        "safety_validation",
+        "unit_economics",
+        "pilot_result"
+      ],
+      "forbidden_elements": [
+        "equipment_purchase_as_capability",
+        "tool_selection_only"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-engineering-center-002",
+      "notes": "Owner-reviewed engineering case 002. Equipment-led solutionism."
+    },
+    {
+      "case_id": "case_qpi_engineering_credential_integrity_policy_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "发现某个资质或履历存在异常，但组织还想按能不能干活来决定是否继续使用，我需要判断这是人员问题还是制度问题。",
+      "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order，并明确 no_personnel_verdict：QPI 不判断具体人员，只路由到筛查制度、例外政策和风险归属审查。",
+      "failure_signal": "直接判断某个人能不能用、是否造假、是否应辞退，或只按短期可用性处理。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "no_personnel_verdict",
+        "credential_integrity"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "credential_verification_lineage",
+        "exception_policy",
+        "risk_owner",
+        "policy_review"
+      ],
+      "forbidden_elements": [
+        "specific_personnel_verdict",
+        "usability_only_decision"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-engineering-center-004",
+      "notes": "Owner-reviewed engineering case 004. Credential integrity versus usability."
+    },
+    {
+      "case_id": "case_qpi_engineering_market_closure_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "生产能力可能有一点，但没人知道客户从哪里来、谁负责获客、收入能否覆盖设备和人工，组织却已经下了产值目标。",
+      "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：对经营主体，这不是先查订单来源的普通 Question，而是把生产能力误当成商业闭环的第一性错位。",
+      "failure_signal": "先判为单纯 question，或只要求市场调研而不处理主体目的、客户、渠道、交付和单位经济模型。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=consensus_order",
+        "business_purpose",
+        "acquisition_channel"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "problem_owner",
+        "primary_purpose",
+        "customer_segment",
+        "demand_signal",
+        "acquisition_channel",
+        "unit_economics"
+      ],
+      "forbidden_elements": [
+        "production_capacity_equals_business_viability",
+        "question_only_classification"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-engineering-center-005",
+      "notes": "Owner-reviewed engineering case 005. Production capability without market closure."
+    },
+    {
+      "case_id": "case_qpi_international_compliance_retention_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "招生团队想用路径调整留住学生，但这个留存动作可能改变机构合规姿态、证书信任和未来投诉审计风险。",
+      "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：留存压力和路径缺口存在，但合规红线占主导，不能把它当作普通招生留存 Problem。",
+      "failure_signal": "只输出留存方案或招生话术，不先确认 compliance red line、credential trust 和 audit risk。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "compliance_red_line",
+        "credential_trust"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "retention_pressure",
+        "compliance_boundary",
+        "future_complaint_or_audit_risk"
+      ],
+      "forbidden_elements": [
+        "retention_tactic_only",
+        "pathway_workaround_without_red_line"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-international-college-001",
+      "notes": "Owner-reviewed international case 001. Retention workaround crossing compliance boundary."
+    },
+    {
+      "case_id": "case_qpi_international_capacity_governance_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "增长项目承诺扩招，但宿舍和服务容量不足，需要挤占其他单元资源，组织还没有硬性容量闸门。",
+      "expected_behavior": "应识别为 mixed，dominant_scarcity=path_resource：硬约束是容量，但跨单元冲突和承诺边界使其成为容量治理问题。",
+      "failure_signal": "把它当作简单排宿舍或物流调度，或只抽象成文化冲突而不处理 hard capacity gate。",
+      "expected_output_elements": [
+        "classification=mixed",
+        "dominant_scarcity=path_resource",
+        "hard_capacity_gate",
+        "cross_unit_conflict"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "path_resource",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "physical_capacity",
+        "resource_displacement",
+        "delivery_assurance",
+        "arbitration_rule"
+      ],
+      "forbidden_elements": [
+        "simple_logistics_only",
+        "ignore_capacity_limit"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-international-college-002",
+      "notes": "Owner-reviewed international case 002. Capacity governance versus simple logistics."
+    },
+    {
+      "case_id": "case_qpi_international_metric_governance_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "执行层提交了好看的资质指标，决策层怀疑这些指标急功近利，只是为了评估和述职，不代表真实教学能力。",
+      "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：事实核验嵌在治理扭曲中，必须检查指标是否连接长期目标、真实能力、多方收益和可审计证据。",
+      "failure_signal": "停留在问指标真假，或直接接受指标为能力证明。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "metric_distortion",
+        "traceable_evidence_chain"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "long_term_goal_alignment",
+        "real_capability",
+        "multi_party_value",
+        "audit_evidence"
+      ],
+      "forbidden_elements": [
+        "question_only_classification",
+        "metric_appearance_as_capability"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-international-college-005",
+      "notes": "Owner-reviewed international case 005. Metric fact verification embedded in governance distortion."
+    },
+    {
+      "case_id": "case_qpi_international_pricing_trust_system_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "高客单价项目招生困难，表面是价格太高或降价会伤害老生公平，深层是组织没有建立可信承诺和可验证结果。",
+      "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：定价僵局是表象，高客单价教育产品需要组织级信任体系、可信承诺、可验证结果和协同交付。",
+      "failure_signal": "只建议降价、促销或销售话术，不处理 trust system、legacy price anchor 和 fairness debt。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "trust_system",
+        "legacy_price_anchor"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "credible_promise",
+        "verifiable_outcome",
+        "organizational_delivery",
+        "fairness_debt"
+      ],
+      "forbidden_elements": [
+        "price_adjustment_only",
+        "sales_script_only"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-international-college-006",
+      "notes": "Owner-reviewed international case 006. Pricing deadlock as high-ticket trust-system failure."
+    },
+    {
+      "case_id": "case_qpi_research_identity_simulation_001",
+      "model_id": "qpi",
+      "case_type": "positive",
+      "input": "组织没有真实科研能力，却想通过人员、费用、专利和论文包装出研究身份，以满足外部优惠或认证要求。",
+      "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：底层有 path/resource shortage，但核心是 research identity simulation，不能把能力建设问题降维成证据包装。",
+      "failure_signal": "当成普通认证材料准备、税务筹划或指标补齐任务，不区分真实能力建设与身份模拟。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "research_identity_simulation",
+        "compliance_red_line"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "capability_building",
+        "evidence_simulation",
+        "transactional_assets",
+        "audit_risk"
+      ],
+      "forbidden_elements": [
+        "certification_materials_only",
+        "evidence_packaging_as_solution"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-research-office-001",
+      "notes": "Owner-reviewed research case 001. Umbrella research identity simulation case."
+    },
+    {
+      "case_id": "case_qpi_research_data_truthfulness_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "研究人员数量和费用类别不够，组织想把非研究角色和薪资类别调成研究相关口径来补表。",
+      "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order，并区分 data completeness、data truthfulness 与 evidence legitimacy；不能输出高置信法律/税务结论。",
+      "failure_signal": "只检查表格是否填满，或直接判断一定合规/违法，而不要求实际研究角色、薪资类别和贡献证据链。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "data_completeness_is_not_truthfulness",
+        "requires_compliance_review"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "actual_research_role_evidence",
+        "payroll_category_validity",
+        "research_contribution_trace"
+      ],
+      "forbidden_elements": [
+        "spreadsheet_completion_as_truth",
+        "high_confidence_legal_tax_verdict"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-research-office-002",
+      "notes": "Owner-reviewed research case 002. Data completeness versus truthfulness."
+    },
+    {
+      "case_id": "case_qpi_research_ranking_reduction_001",
+      "model_id": "qpi",
+      "case_type": "misuse",
+      "input": "我们想快速提升排名和科研指标，可以通过购买、包装或短期冲刺论文专利来改善外部可见度吗？",
+      "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：这是 violent_reduction，把研究价值压缩成可购买、可填报、可冲刺的排名输入。",
+      "failure_signal": "直接给快速提升排名清单，或把购买/包装指标当作普通执行路径。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "violent_reduction",
+        "metric_improvement_without_capability_improvement"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "research_value",
+        "capability_improvement",
+        "ranking_metric_trap"
+      ],
+      "forbidden_elements": [
+        "quick_ranking_tactics_only",
+        "purchasable_metric_as_research_value"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-research-office-004",
+      "notes": "Owner-reviewed research case 004. Ranking trap and violent reduction."
+    },
+    {
+      "case_id": "case_qpi_research_penalty_integrity_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "组织认为只要没有罚款、没有被约谈、没有报销损失，就说明合规风险不大。",
+      "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order，并输出 punishment_state_vs_integrity_state：没有即时惩罚不等于行为正当或可审计。",
+      "failure_signal": "把无处罚当作合规证明，或只建议继续观察处罚结果。",
+      "expected_output_elements": [
+        "classification=issue",
+        "dominant_scarcity=consensus_order",
+        "absence_of_penalty_is_not_legitimacy",
+        "integrity_state"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "punishment_state_frame",
+        "integrity_state_frame",
+        "auditability",
+        "substantive_compliance"
+      ],
+      "forbidden_elements": [
+        "no_penalty_equals_compliance",
+        "minimum_punishment_game"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-research-office-008",
+      "notes": "Owner-reviewed research case 008. Punishment state versus integrity state."
+    },
+    {
+      "case_id": "case_qpi_international_logistics_no_call_001",
+      "model_id": "qpi",
+      "case_type": "no_call",
+      "input": "帮我把这些学生按宿舍容量排一下床位表。",
+      "expected_behavior": "应 no_call：这是直接物流/排床位执行任务，不应仅因出现容量词而调用 QPI。",
+      "failure_signal": "selector 选中 QPI，或把排床位执行误判为容量治理问题。",
+      "expected_output_elements": [
+        "classification=no_call",
+        "recommended_next_step=不调用"
+      ],
+      "should_call_model": false,
+      "expected_primary_model": "none",
+      "negative_expected_models": [
+        "qpi",
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "no_call",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "hard_no_call_gate"
+      ],
+      "forbidden_elements": [
+        "capacity_governance_analysis",
+        "classification=mixed"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-international-college-002",
+      "notes": "Round 03.1 no-call trap paired with international capacity governance case."
+    },
+    {
+      "case_id": "case_qpi_research_capacity_problem_not_issue_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "增长活动已经承诺，但物理空间、床位、设施和服务容量不足。现在主要问题是硬容量无法被行政命令解决，虽然继续扩张会带来治理风险。",
+      "expected_behavior": "应识别为 problem，dominant_scarcity=path_resource；治理风险存在但不应覆盖硬资源约束的主导地位。",
+      "failure_signal": "直接升维为 issue，忽略硬资源约束仍是主导稀缺。",
+      "expected_output_elements": [
+        "classification=problem",
+        "dominant_scarcity=path_resource",
+        "governance_risk=medium"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "problem",
+      "expected_dominant_scarcity": "path_resource",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "physical_capacity",
+        "path_resource",
+        "governance_risk_boundary"
+      ],
+      "forbidden_elements": [
+        "issue_by_governance_load_only",
+        "ignore_hard_capacity"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-research-office-006",
+      "notes": "Round 03.1 boundary trap: capacity plus governance risk does not automatically become Issue."
+    },
+    {
+      "case_id": "case_qpi_multi_perspective_requires_viewpoint_output_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "执行层认为这是线索转化问题，决策层认为这是完整教育链战略问题，学生视角还涉及证书信任和交付承诺。请判断这到底是什么问题。",
+      "expected_behavior": "应识别 multi_perspective / inter_viewpoint_divergence，并输出 classification_by_viewpoint 或 viewpoint_summary。",
+      "failure_signal": "只给单一 issue/mixed 标签，没有列出不同视角下的问题定义。",
+      "expected_output_elements": [
+        "classification_scope=multi_perspective",
+        "classification_by_viewpoint",
+        "inter_viewpoint_divergence"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "issue",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "classification_by_viewpoint",
+        "viewpoint_summary"
+      ],
+      "forbidden_elements": [
+        "single_viewpoint_only"
+      ],
+      "evaluation_mode": "structured",
+      "source_case_digest_id": "qpi-year-end-international-college-004",
+      "notes": "Round 03.1 contract trap for multi-perspective output."
+    },
+    {
+      "case_id": "case_qpi_low_context_provisional_no_high_confidence_001",
+      "model_id": "qpi",
+      "case_type": "boundary",
+      "input": "这个项目推进不顺，到底是问题还是课题？",
+      "expected_behavior": "上下文不足时应 is_provisional=true，context_sufficiency=low，classification_confidence 不得为 high，并列出 missing_context。",
+      "failure_signal": "在缺少主体、场景、目标、资源和责任信息时输出高置信 Q/P/I。",
+      "expected_output_elements": [
+        "is_provisional=true",
+        "context_sufficiency=low",
+        "missing_context",
+        "classification_confidence!=high"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "unknown",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "missing_context",
+        "recommended_clarifying_questions"
+      ],
+      "forbidden_elements": [
+        "classification_confidence=high"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "Round 03.1 dependency trap for low-context provisional classification."
+    },
+    {
+      "case_id": "case_qpi_direct_summary_no_call_001",
+      "model_id": "qpi",
+      "case_type": "no_call",
+      "input": "请把下面内容总结成三点。",
+      "expected_behavior": "应 no_call：纯摘要执行任务不需要 QPI。",
+      "failure_signal": "selector 因默认分选中 QPI。",
+      "expected_output_elements": [
+        "classification=no_call"
+      ],
+      "should_call_model": false,
+      "expected_primary_model": "none",
+      "negative_expected_models": [
+        "qpi",
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "no_call",
+      "expected_dominant_scarcity": "not_applicable",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "hard_no_call_gate"
+      ],
+      "forbidden_elements": [
+        "problem_definition"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "Round 03.1 direct execution no-call."
+    },
+    {
+      "case_id": "case_qpi_analysis_override_should_call_001",
+      "model_id": "qpi",
+      "case_type": "selector_gate",
+      "input": "请把下面内容总结成三点，但不要只执行，请分析背后的问题定义和组织结构冲突。",
+      "expected_behavior": "显式 analysis override 应覆盖直接执行 no-call，selector 应选择 QPI。",
+      "failure_signal": "hard no-call 误杀包含明确分析 override 的混合请求。",
+      "expected_output_elements": [
+        "selected=qpi",
+        "analysis_override"
+      ],
+      "should_call_model": true,
+      "expected_primary_model": "qpi",
+      "negative_expected_models": [
+        "intellectual_archaeology"
+      ],
+      "expected_classification": "mixed",
+      "expected_dominant_scarcity": "consensus_order",
+      "expected_max_depth": "not_applicable",
+      "minimum_required_elements": [
+        "override_preserved"
+      ],
+      "forbidden_elements": [
+        "hard_no_call_without_override_check"
+      ],
+      "evaluation_mode": "structured",
+      "notes": "Round 03.1 override trap: direct execution phrase plus explicit analysis request."
+    }
   ]
 }
diff --git a/tests/test_validate_model_library.py b/tests/test_validate_model_library.py
index 3b397ba..ad3acc9 100644
--- a/tests/test_validate_model_library.py
+++ b/tests/test_validate_model_library.py
@@ -453,6 +453,52 @@ class ValidateModelLibraryTests(unittest.TestCase):
                 errors
             )
 
+    def test_qpi_digest_deprecated_fields_are_reported(self):
+        validator = load_validator()
+        with tempfile.TemporaryDirectory() as tmp:
+            root = Path(tmp)
+            self.write_minimal_library(root)
+            self.write_json(root, "selector/qpi_case_digests.json", {
+                "cases": [{
+                    "case_id": "qpi-test-001",
+                    "classification_scope": "subject_contextual",
+                    "mixed_or_multi_perspective": "not_mixed",
+                    "misframing_risks": ["violent_reduction"]
+                }]
+            })
+
+            errors = validator.validate_library(root)
+
+            self.assertIn(
+                "qpi case digest qpi-test-001 uses deprecated field misframing_risks; use misclassification_risk",
+                errors
+            )
+            self.assertIn(
+                "qpi case digest qpi-test-001 uses deprecated field mixed_or_multi_perspective; use qpi_complexity_pattern",
+                errors
+            )
+
+    def test_qpi_digest_multi_perspective_requires_viewpoint_detail(self):
+        validator = load_validator()
+        with tempfile.TemporaryDirectory() as tmp:
+            root = Path(tmp)
+            self.write_minimal_library(root)
+            self.write_json(root, "selector/qpi_case_digests.json", {
+                "cases": [{
+                    "case_id": "qpi-test-002",
+                    "classification_scope": "multi_perspective",
+                    "qpi_complexity_pattern": "inter_viewpoint_divergence",
+                    "misclassification_risk": ["single_viewpoint_only"]
+                }]
+            })
+
+            errors = validator.validate_library(root)
+
+            self.assertIn(
+                "qpi case digest qpi-test-002 multi_perspective case requires classification_by_viewpoint or viewpoint_summary",
+                errors
+            )
+
 
 if __name__ == "__main__":
     unittest.main()