Add local CCRA review workflow
This commit is contained in:
parent
3f6f00a82e
commit
ab59e3ce48
|
|
@ -79,6 +79,7 @@ tests/
|
|||
selector/
|
||||
scripts/
|
||||
reports/
|
||||
local_ccra_reviews/
|
||||
```
|
||||
|
||||
Each folder should contain a README explaining its purpose.
|
||||
|
|
@ -221,6 +222,7 @@ At minimum, keep these files consistent:
|
|||
- `docs/WORKFLOW.md`
|
||||
- `docs/DECISIONS.md`
|
||||
- `PROJECTS.md`
|
||||
- `local_ccra_reviews/README.md` when Local CCRA review process changes
|
||||
|
||||
## 13. Cross-Repository Collaboration Rules
|
||||
|
||||
|
|
@ -241,6 +243,10 @@ Use installed runnable Skills from:
|
|||
C:\Users\wangq\.agents\skills
|
||||
```
|
||||
|
||||
Local CCRA review runs belong in `local_ccra_reviews/`, but the `ccra-local-reviewer` Agent Spec, review rubric, Runtime Spec, invocation protocol, session-continuation contract, and companion capability classification belong in `ccpe-system`.
|
||||
|
||||
Do not create a `skills-vault` request for Local CCRA companion automation until CCPE or the project owner classifies the operation as reusable deterministic automation.
|
||||
|
||||
If a missing capability blocks model extraction:
|
||||
|
||||
1. Classify whether it is a CCPE need or a skills-vault need.
|
||||
|
|
|
|||
|
|
@ -22,6 +22,7 @@ This repository owns:
|
|||
- Selector rules and examples for this product
|
||||
- Application implementation when the project later adopts frameworks such as CrewAI, LangGraph, or a server runtime
|
||||
- Project-specific requirements, handoffs, validation reports, and decision records
|
||||
- Local CCRA review run records under `local_ccra_reviews/`
|
||||
|
||||
This repository does not own canonical expert-agent specifications, reusable automation Skill source, or upstream source archives.
|
||||
|
||||
|
|
@ -60,6 +61,9 @@ requirements/ccpe/
|
|||
Use this channel when the project needs:
|
||||
|
||||
- Expert-agent definition
|
||||
- Local CCRA reviewer Agent Spec
|
||||
- CCPE Agent Runtime invocation protocol
|
||||
- Runtime session-continuation contract
|
||||
- CCPE-Lite prompt card
|
||||
- Agent Spec
|
||||
- Committee Spec
|
||||
|
|
@ -71,6 +75,8 @@ Use this channel when the project needs:
|
|||
|
||||
Do not store canonical CCPE artifacts in this repository. Store the request here, then let `ccpe-system` own the supplied artifact.
|
||||
|
||||
For Local CCRA, this repository stores only review run inputs, runtime session metadata, local review reports, Owner decisions, and action registers. The `ccra-local-reviewer` Agent Spec and Runtime protocol belong in `ccpe-system`.
|
||||
|
||||
### skills-vault Requests
|
||||
|
||||
Use:
|
||||
|
|
@ -92,6 +98,8 @@ Use this channel when the project needs:
|
|||
|
||||
Do not store reusable automation Skill source in this repository. Store the request here, then let `skills-vault` own the implementation source if the need becomes stable and reusable.
|
||||
|
||||
For Local CCRA companion automation, route the capability through `requirements/ccpe/` first when it is unclear whether the need is Agent-specific, Runtime-specific, product-local, or reusable. Create a `skills-vault` request only after the operation has been abstracted as deterministic, reusable automation.
|
||||
|
||||
## Model Extraction Work Mode
|
||||
|
||||
Model extraction is a duplex workflow:
|
||||
|
|
|
|||
|
|
@ -79,7 +79,8 @@ selector/ Rule-based selector configuration and examples.
|
|||
scripts/ Local validation and selector demo scripts.
|
||||
reports/ Validation reports, extraction notes, and concrete session handoffs.
|
||||
knowledge_assets/ Stable long-term reusable knowledge distilled from local project artifacts.
|
||||
ccra_review_bundle/ Per-round CCRA review packages; each round must live in its own dated subdirectory.
|
||||
ccra_review_bundle/ Per-round Web CCRA / GPT review packages; each round must live in its own dated subdirectory.
|
||||
local_ccra_reviews/ File-first Local CCRA review runs, including runtime invocation packets, child-session metadata, local review reports, Owner decisions, and action registers.
|
||||
```
|
||||
|
||||
## 7. Data Format
|
||||
|
|
@ -174,11 +175,13 @@ Files intended for GPT / CCRA upload inside a review bundle should include the r
|
|||
|
||||
Use the installed `bundle-zip` Skill for review bundle raw zips. Do not hand-roll source-relative zip creation with PowerShell `Compress-Archive` when directory paths matter.
|
||||
|
||||
Local CCRA first-pass reviews are recorded under `local_ccra_reviews/<public-round>/<local-pass>/`. They run through a real CCPE Agent Runtime child session and normally use the same-child `review_turn` plus `planning_turn` pattern. Local CCRA output is formal local first review, but it does not replace Owner or Web CCRA judgment. Formal Web CCRA bundles do not include the local review report by default.
|
||||
|
||||
## 13. Next Steps
|
||||
|
||||
1. Round 03 is closed after the Round 03.2a CCRA / GPT pass decision.
|
||||
2. Keep QPI and Intellectual Archaeology at `draft / B / pending` until Owner / CCRA review accepts stronger status.
|
||||
3. Round 04.1 is closed after GPT review acceptance and closeout documentation. The closeout records `R04-BI-022` as an accepted collateral depth-limited QPI override and adds it to regression.
|
||||
4. Round 05 discussion should start from the handoff report in a new session; do not treat Round 04.1 closure as a model lifecycle upgrade.
|
||||
4. The next round discussion should start from Owner / Web CCRA planning; do not treat Round 04.1 closure as a model lifecycle upgrade or as a predefined Round 05 scope.
|
||||
5. Defer any third-model expansion until the current QPI selector and case layer are accepted.
|
||||
6. Route missing reusable extraction, inspection, or stability-scoring tools to `requirements/skills-vault/` or `requirements/ccpe/` instead of improvising local platform features.
|
||||
|
|
|
|||
|
|
@ -141,3 +141,42 @@ Engineering validation does not imply content stability.
|
|||
Before content stabilization review, every core model should have at least 15 regression cases and field-level evidence coverage.
|
||||
|
||||
Source excerpts must distinguish exact quotes from condensed or paraphrased excerpts with `quote_status`.
|
||||
|
||||
## 10. Local CCRA Review Run Contract
|
||||
|
||||
Local CCRA review runs are process records, not model assets.
|
||||
|
||||
They live under:
|
||||
|
||||
```text
|
||||
local_ccra_reviews/<public-round>/<local-pass>/
|
||||
```
|
||||
|
||||
Each local pass should contain:
|
||||
|
||||
- `run-notes.md`
|
||||
- `review-metadata.json`
|
||||
- `gate-manifest.yaml`
|
||||
- `lifecycle-guard-config.yaml`
|
||||
- `agent-invocation-packet.md`
|
||||
- `prompt-to-send.md`
|
||||
- `turn-prompts/`
|
||||
- `review-context.md`
|
||||
- `review-file-manifest.json`
|
||||
- `helper-outputs/`
|
||||
- `04_LOCAL_CCRA_REVIEW_REPORT.md`
|
||||
- `next-review-requirements.md`
|
||||
- `returned-output.md`
|
||||
- `owner-decision.md`
|
||||
|
||||
`review-metadata.json`, `review-file-manifest.json`, and helper JSON outputs are machine-readable process records.
|
||||
|
||||
Markdown files in the run directory are human-readable process records.
|
||||
|
||||
`04_LOCAL_CCRA_REVIEW_REPORT.md` is the `review_turn` judgment output.
|
||||
|
||||
`next-review-requirements.md` is the same-child `planning_turn` output and should not be treated as Owner approval or proof that a patch worked.
|
||||
|
||||
Local CCRA review records must not become source of truth for model status, selector behavior, regression cases, or source evidence. Accepted actions must be applied back to the canonical project files and validated there.
|
||||
|
||||
Formal Web CCRA upload bundles exclude the Local CCRA report by default unless the owner explicitly asks to include it.
|
||||
|
|
|
|||
|
|
@ -247,3 +247,70 @@ Closeout:
|
|||
- IA remains rejected for `R04-BI-022`.
|
||||
- `R04-BI-022` is added to selector regression as a QPI gate / IA anti-recall trap.
|
||||
- Closing Round 04.1 does not upgrade either model lifecycle status.
|
||||
|
||||
## Decision 018: Keep Local CCRA review runs inside this project
|
||||
|
||||
Status: Accepted
|
||||
|
||||
Reason:
|
||||
|
||||
The first Local CCRA version serves only `the-mindscape-of-bro-tsong`.
|
||||
|
||||
Creating a separate reviewer project would add synchronization cost before there is a cross-project review workload. The useful separation is runtime isolation, not directory isolation.
|
||||
|
||||
This repository therefore records Local CCRA review runs under:
|
||||
|
||||
```text
|
||||
local_ccra_reviews/<public-round>/<local-pass>/
|
||||
```
|
||||
|
||||
The public round label follows Owner / Web CCRA round versions such as `round-05`, `round-04.1`, or `round-03.2a`. The local pass number records repeated internal review passes, such as `01/` and `02/`.
|
||||
|
||||
Local CCRA output is formal local first review, but it does not replace Owner judgment or Web CCRA judgment at key product and lifecycle gates.
|
||||
|
||||
Formal Web CCRA bundles under `ccra_review_bundle/` exclude `04_LOCAL_CCRA_REVIEW_REPORT.md` by default. The local report is included only when the owner explicitly asks Web CCRA to review local findings.
|
||||
|
||||
## Decision 019: Route Local CCRA Agent Runtime and companion capability classification to CCPE first
|
||||
|
||||
Status: Accepted
|
||||
|
||||
Reason:
|
||||
|
||||
Local CCRA requires a real child review session, runtime session continuation, a reviewer role contract, review rubric, lifecycle guard policy, and file-first invocation protocol.
|
||||
|
||||
These are CCPE responsibilities, not product-local implementation details and not automatically `skills-vault` automation.
|
||||
|
||||
This repository will request a `ccra-local-reviewer` Agent Spec and Runtime protocol from `ccpe-system`. Companion capabilities such as routing diff audit, review bundle audit, lifecycle guard scan, round initialization context building, and regression gate running should be classified by CCPE first.
|
||||
|
||||
Only capabilities that are abstracted into reusable deterministic operations should be routed to `skills-vault`. Reusable Skill names should describe the generic operation, as with `bundle-zip`, rather than this project's review context.
|
||||
|
||||
## Decision 020: Treat Local CCRA v0.1.1 as usable for formal local first review with non-blocking Patch 2 hardening
|
||||
|
||||
Status: Accepted
|
||||
|
||||
Reason:
|
||||
|
||||
Round 04 Local CCRA `pilot-02` tested CCPE Patch 1 with a real child session and the same historical Round 04 materials.
|
||||
|
||||
The same child session completed both required turns:
|
||||
|
||||
- `review_turn`: produced `local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md`.
|
||||
- `planning_turn`: produced `local_ccra_reviews/round-04/pilot-02/next-review-requirements.md`.
|
||||
|
||||
The three-way comparison against Web CCRA baseline and `pilot-01` showed that Patch 1 fixed the main Local CCRA gap: the reviewer now combines Web-style issue mechanism diagnosis with local full-file audit.
|
||||
|
||||
Decision:
|
||||
|
||||
- Local CCRA v0.1.1 can be used as this project's formal local first-review lane after Owner and Web CCRA define the next round's work.
|
||||
- It does not replace Owner judgment, Web CCRA final review, or lifecycle authority.
|
||||
- Patch 2 is still needed as runtime/helper hardening, but it is non-blocking if Patch 1 behavior remains intact.
|
||||
- A third historical pilot is not required unless CCPE changes mechanism diagnosis, patch scope judgment, same-child-session continuation, mandatory knowledge-base use, or authority boundaries.
|
||||
- Full Round-level automation is a separate workflow/orchestrator design problem and should not be mixed into the `ccra-local-reviewer` reviewer contract.
|
||||
|
||||
Patch 2 should focus on:
|
||||
|
||||
- CCRA-aware review bundle audit profile.
|
||||
- Explicit gate-runner `dry_run / run / owner_waived / not_applicable` policy.
|
||||
- Mandatory routing behavior diff when before/after patch evidence exists.
|
||||
- Scoped lifecycle/status scan and triage.
|
||||
- Short Owner-facing `returned-output.md` summary.
|
||||
|
|
|
|||
|
|
@ -22,7 +22,7 @@ Every meaningful file should fit one of four classes:
|
|||
| --- | --- | --- | --- |
|
||||
| Canonical source of truth | Files that define model/library behavior or reviewed content | Keep and version | `models/*.model.json`, `cards/*.md`, `sources/*.json`, `tests/*.regression.json`, `selector/*.json`, `schemas/*.json`, operative `docs/*.md` |
|
||||
| Generated / derived | Files rebuilt or checked from canonical assets | Keep when useful, rebuild at handoff/release | `models/model_index.json`, `cards/card_index.md`, `reports/validation_report.md`, `reports/index_rebuild_report.md`, `reports/model_card_sync_report_v0.2.md`, `reports/selector_regression_report_v0.2.md` |
|
||||
| Review archive | Per-round evidence for Owner / CCRA / GPT review | Keep by round, do not treat as runtime truth | `ccra_review_bundle/round-*`, `reports/Codex*.md`, `reports/GPT*.md`, `reports/model_case_preprocessing/*` |
|
||||
| Review archive | Per-round evidence for Owner / CCRA / GPT review | Keep by round, do not treat as runtime truth | `ccra_review_bundle/round-*`, `local_ccra_reviews/round-*`, `reports/Codex*.md`, `reports/GPT*.md`, `reports/model_case_preprocessing/*` |
|
||||
| Temporary / local runtime | Caches or local command byproducts | Do not commit | `__pycache__/`, `*.pyc`, temporary extraction folders, ad hoc local scratch files |
|
||||
|
||||
## 3. Canonical Source Of Truth
|
||||
|
|
@ -89,6 +89,7 @@ They preserve evidence and context, but they do not override canonical files.
|
|||
Examples:
|
||||
|
||||
- `ccra_review_bundle/round-*/`
|
||||
- `local_ccra_reviews/round-*/`
|
||||
- `reports/Codex*.md`
|
||||
- `reports/GPT*.md`
|
||||
- `reports/model_case_preprocessing/*`
|
||||
|
|
@ -101,6 +102,8 @@ Rules:
|
|||
- GPT / CCRA upload files inside review bundles must include the round version in the filename, for example `_03.2`, to avoid same-name ambiguity when multiple rounds are uploaded in one Web ChatGPT conversation.
|
||||
- Do not flatten zip contents, because duplicate filenames such as `README.md` can collide.
|
||||
- `knowledge_assets/` is excluded from review zips by default because the Owner manually syncs stable knowledge assets into GPT knowledge storage.
|
||||
- `local_ccra_reviews/` records local first-pass review runs and is not copied into Web CCRA bundles by default.
|
||||
- `04_LOCAL_CCRA_REVIEW_REPORT.md` is excluded from Web CCRA bundles by default unless the Owner explicitly asks to include it.
|
||||
|
||||
## 6. Temporary / Local Runtime Files
|
||||
|
||||
|
|
|
|||
|
|
@ -38,7 +38,18 @@ Task:
|
|||
|
||||
-
|
||||
|
||||
## 10. Suggested Next Tasks
|
||||
## 10. Local CCRA Status
|
||||
|
||||
- Local review run:
|
||||
- Runtime session id:
|
||||
- Local CCRA report:
|
||||
- Owner decision:
|
||||
- Returned output:
|
||||
- Helper outputs:
|
||||
- Accepted actions:
|
||||
- Deferred or escalated findings:
|
||||
|
||||
## 11. Suggested Next Tasks
|
||||
|
||||
1.
|
||||
2.
|
||||
|
|
|
|||
|
|
@ -63,3 +63,16 @@ This repository is separate from but related to:
|
|||
- `video-workbench`: dimensional output workspace.
|
||||
|
||||
This project may reference artifacts from those repositories, but its own boundary is the model asset foundation for The Mindscape of Bro Tsong.
|
||||
|
||||
## 7. Local CCRA First Review
|
||||
|
||||
The project may use Local CCRA review as a file-first first-pass review loop before Web CCRA review.
|
||||
|
||||
First-version constraints:
|
||||
|
||||
- Local CCRA serves only this project.
|
||||
- Local CCRA review runs are stored under `local_ccra_reviews/`.
|
||||
- The reviewer runs through CCPE Agent Runtime in a real child review session.
|
||||
- Formal local review normally uses the same-child `review_turn` plus `planning_turn` pattern.
|
||||
- Local CCRA output is formal local first review, but it does not replace Owner or Web CCRA judgment.
|
||||
- The `ccra-local-reviewer` Agent Spec and Runtime protocol belong in `ccpe-system`.
|
||||
|
|
|
|||
|
|
@ -88,6 +88,55 @@ Required properties:
|
|||
|
||||
Do not use `Compress-Archive` for review raw zips where directory paths matter; it can flatten file-list paths.
|
||||
|
||||
## 5.2 Local CCRA Review Workflow
|
||||
|
||||
Local CCRA review is a file-first first-pass review loop inside this project.
|
||||
|
||||
Use:
|
||||
|
||||
```text
|
||||
local_ccra_reviews/<public-round>/<local-pass>/
|
||||
```
|
||||
|
||||
Examples:
|
||||
|
||||
```text
|
||||
local_ccra_reviews/round-05_selector-calibration-policy/01/
|
||||
local_ccra_reviews/round-05_selector-calibration-policy/02/
|
||||
local_ccra_reviews/round-04/pilot-01/
|
||||
local_ccra_reviews/round-04/pilot-02/
|
||||
local_ccra_reviews/round-03.2a_depth-limiting-qpi-override-patch/01/
|
||||
```
|
||||
|
||||
Workflow:
|
||||
|
||||
1. Owner decides whether the public round needs Local CCRA review.
|
||||
2. Codex creates the next numbered local review run directory.
|
||||
3. Codex writes `run-notes.md`, `review-metadata.json`, `gate-manifest.yaml`, and `lifecycle-guard-config.yaml`.
|
||||
4. Codex runs `review-context-builder` and applicable helper Skills, recording skipped helpers in `run-notes.md`.
|
||||
5. Codex writes `agent-invocation-packet.md`, `prompt-to-send.md`, and `turn-prompts/`.
|
||||
6. Codex invokes CCPE Agent Runtime / Codex child thread as `ccra-local-reviewer`.
|
||||
7. The runtime child session id or carrier id is recorded in `run-notes.md`.
|
||||
8. `review_turn` writes `04_LOCAL_CCRA_REVIEW_REPORT.md` and `returned-output.md`.
|
||||
9. `planning_turn` continues the same child session and writes `next-review-requirements.md` when next-review planning is needed.
|
||||
10. Owner records accepted, rejected, deferred, or escalated findings in `owner-decision.md`.
|
||||
11. Codex executes accepted actions in the main project session.
|
||||
12. A follow-up Local CCRA review uses the next local pass label, such as `02/`.
|
||||
13. After Local CCRA and Owner acceptance, Codex creates the formal Web CCRA bundle under `ccra_review_bundle/round-NN_YYYY-MM-DD_topic/`.
|
||||
|
||||
Rules:
|
||||
|
||||
- Local CCRA output is formal local first review, not Owner approval and not Web CCRA approval.
|
||||
- `ccra-local-reviewer` is read-only and must not modify product files.
|
||||
- Review inputs and outputs should be exchanged through local files, not chat summaries.
|
||||
- Runtime child session id and continuation state belong in `run-notes.md` and `agent-invocation-packet.md`.
|
||||
- The default formal pattern is same-child `review_turn` followed by `planning_turn`.
|
||||
- Formal Web CCRA bundles exclude `04_LOCAL_CCRA_REVIEW_REPORT.md` by default.
|
||||
- Include the local report in Web CCRA upload packages only when the owner explicitly asks for Web CCRA to review local findings.
|
||||
- CCPE owns the Agent Spec, Runtime Spec, invocation protocol, review rubric, and companion-capability classification.
|
||||
- Full Round-level automation is a separate workflow/orchestrator design topic, not part of the Local CCRA reviewer contract.
|
||||
- `skills-vault` receives a request only after CCPE or the owner decides that a companion operation is reusable deterministic automation.
|
||||
|
||||
## 6. Supplier Request Workflow
|
||||
|
||||
When this repository needs a capability owned by a neighboring repository:
|
||||
|
|
|
|||
|
|
@ -0,0 +1,247 @@
|
|||
# 本地 CCRA 评审机制说明
|
||||
|
||||
version: 0.2
|
||||
|
||||
last_updated: 2026-06-19
|
||||
|
||||
status: stable explanatory asset
|
||||
|
||||
## 1. 文档定位
|
||||
|
||||
本文档说明 `the-mindscape-of-bro-tsong` 项目如何使用 Local CCRA 做本地第一轮评审。
|
||||
|
||||
它只解释项目侧机制，不定义 `ccra-local-reviewer` Agent 本体。
|
||||
|
||||
Agent Spec、Runtime Spec、调用协议、会话保持机制、评审 rubric 和配套能力归属判定属于 `ccpe-system`。
|
||||
|
||||
## 2. 为什么需要 Local CCRA
|
||||
|
||||
当前项目已经有 Web CCRA / GPT 评审流程，但人工搬运成本较高。
|
||||
|
||||
Local CCRA 的目标是把以下工作本地化：
|
||||
|
||||
- 审核资料的第一轮审查；
|
||||
- 轮次目标是否被偷换的检查；
|
||||
- 工程通过与产品判断之间的差距识别；
|
||||
- selector 规则变更后的非目标行为变化识别；
|
||||
- 模型生命周期是否被过早升级的守门；
|
||||
- 下一轮应修、应延后、应进入 calibration 或 regression 的建议。
|
||||
|
||||
Local CCRA 是正式本地初审，但不替代 Owner 或 Web CCRA 的关键节点判断。
|
||||
|
||||
## 3. 第一版范围
|
||||
|
||||
第一版只服务：
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong
|
||||
```
|
||||
|
||||
不建立独立 reviewer 项目。
|
||||
|
||||
原因是当前没有跨项目评审需求。正交性来自真实子会话 / Agent Runtime 隔离，而不是来自另建目录或另建项目。
|
||||
|
||||
## 4. 项目侧目录
|
||||
|
||||
Local CCRA 运行记录放在：
|
||||
|
||||
```text
|
||||
local_ccra_reviews/
|
||||
```
|
||||
|
||||
路径规则：
|
||||
|
||||
```text
|
||||
local_ccra_reviews/<public-round>/<local-pass>/
|
||||
```
|
||||
|
||||
示例：
|
||||
|
||||
```text
|
||||
local_ccra_reviews/round-05_selector-calibration-policy/01/
|
||||
local_ccra_reviews/round-05_selector-calibration-policy/02/
|
||||
local_ccra_reviews/round-04/pilot-01/
|
||||
local_ccra_reviews/round-03.2a_depth-limiting-qpi-override-patch/01/
|
||||
```
|
||||
|
||||
`<public-round>` 跟随 Owner / Web CCRA 共同确定的公共轮次，例如 `round-05`、`round-04.1`、`round-03.2a`。
|
||||
|
||||
`<local-pass>` 是 Local CCRA 内部评审次数，例如 `01/`、`02/`。
|
||||
|
||||
## 5. 每次评审的文件
|
||||
|
||||
每个本地评审目录应包含：
|
||||
|
||||
```text
|
||||
run-notes.md
|
||||
review-metadata.json
|
||||
gate-manifest.yaml
|
||||
lifecycle-guard-config.yaml
|
||||
agent-invocation-packet.md
|
||||
prompt-to-send.md
|
||||
turn-prompts/
|
||||
review-context.md
|
||||
review-file-manifest.json
|
||||
helper-outputs/
|
||||
04_LOCAL_CCRA_REVIEW_REPORT.md
|
||||
next-review-requirements.md
|
||||
returned-output.md
|
||||
05_WEB_LOCAL_CCRA_COMPARISON.md
|
||||
owner-decision.md
|
||||
```
|
||||
|
||||
关键含义：
|
||||
|
||||
- `run-notes.md`：记录本轮运行、helper 命令、跳过项、dispatch 和 resume 信息。
|
||||
- `review-metadata.json`：记录本轮目标、范围、非目标和开放问题。
|
||||
- `agent-invocation-packet.md`：交给 CCPE Agent Runtime 的文件优先调用包。
|
||||
- `prompt-to-send.md`：通过 Codex 子线程等 carrier 调用时使用的提示词。
|
||||
- `turn-prompts/`：保存 `review_turn`、`planning_turn`、必要时的 `comparison_turn` 提示。
|
||||
- `review-context.md` / `review-file-manifest.json`：由 `review-context-builder` 生成的文件优先上下文索引。
|
||||
- `04_LOCAL_CCRA_REVIEW_REPORT.md`：`ccra-local-reviewer` 唯一判断输出。
|
||||
- `next-review-requirements.md`：同一子会话第二回合产出的下一轮评审要求与提交资料规划。
|
||||
- `returned-output.md`：子会话返回内容或报告路径记录。
|
||||
- `05_WEB_LOCAL_CCRA_COMPARISON.md`：可选的主会话比较笔记，用于把 Local CCRA 输出与 Web CCRA / GPT 反馈对照后调优。
|
||||
- `owner-decision.md`：Owner 对 findings 的接受、拒绝、延后或升级判断。
|
||||
|
||||
## 6. 运行流程
|
||||
|
||||
推荐流程：
|
||||
|
||||
```text
|
||||
Owner 决定需要本地评审
|
||||
-> Codex 创建 local_ccra_reviews/<round>/<pass>/
|
||||
-> Codex 运行 review-context-builder 和适用 helper Skill
|
||||
-> Codex 生成 Runtime invocation packet 和 prompt-to-send
|
||||
-> Codex 调起 CCPE Agent Runtime 子会话并记录 child_session_id
|
||||
-> review_turn: ccra-local-reviewer 只读评审资料并写本地评审报告
|
||||
-> planning_turn: 同一 child_session_id 继续，写下一轮评审要求与提交资料规划
|
||||
-> Owner 写 decision
|
||||
-> Codex 根据 accepted findings 修复
|
||||
-> 必要时进入下一次本地评审
|
||||
-> 通过后生成正式 Web CCRA bundle
|
||||
```
|
||||
|
||||
`ccra-local-reviewer` 只输出评审意见，不做任何项目文件调整。
|
||||
|
||||
当前推荐的正式使用模式是两回合：
|
||||
|
||||
1. `review_turn`：评审本轮资料，识别问题、机制、证据缺口、补丁范围和是否需要本地修复。
|
||||
2. `planning_turn`：复用同一个 `child_session_id`，基于第一回合报告和 Owner decision，规划下一轮评审要求和应提交资料。
|
||||
|
||||
`planning_turn` 不应重新完整评审当前 bundle，除非 Owner 明确要求或新增证据已经进入评审目录。
|
||||
|
||||
运行时长与工具使用原则：
|
||||
|
||||
- Local CCRA 是深度文件优先评审，不是快速聊天摘要。
|
||||
- 成熟运行的目标耗时可按 Web CCRA 的常见 5-10 分钟理解，具体取决于客户端和 API / runtime 配置。
|
||||
- 子会话可以按需使用本地工具解压、检索、读取 manifest、运行 helper Skill，并在 Owner 或运行包允许时执行回归 / 验证命令。
|
||||
- 主会话不应仅因为子会话阅读文件或运行工具持续数分钟就中断评审。
|
||||
- 每次运行应在 `run-notes.md` 记录可观察耗时，便于后续区分正常深度评审和 runtime 异常。
|
||||
|
||||
## 7. 正式使用条件
|
||||
|
||||
基于 Round 04 `pilot-02` 的三方对比，Local CCRA v0.1.1 可以作为本项目正式本地初审使用，但带条件：
|
||||
|
||||
- 必须真实调起子会话，不允许主会话角色扮演。
|
||||
- 必须记录并复用 `child_session_id`。
|
||||
- 必须使用 `knowledge_assets/` 作为强制知识库路径。
|
||||
- 默认采用 `review_turn` + `planning_turn` 两回合模式。
|
||||
- helper 输出只能作为证据线索，必须标注置信度、噪声和适用范围。
|
||||
- 当评审对象包含补丁或 post-patch 证据时，必须要求 before / after 行为对比。
|
||||
- Local CCRA 不能替代 Owner decision、Web CCRA final review 或模型生命周期升级判断。
|
||||
|
||||
Patch 2 属于硬化需求，不是进入下一轮本地初审的前置门槛。它主要改善 helper profile、gate runner 策略、routing diff 强制化、lifecycle scan 范围和短摘要输出。
|
||||
|
||||
如果 Patch 2 不改变机制诊断、补丁范围判断、同子会话延续、强制知识库或权限边界，则不需要第三次历史试运行。可以在下一次 Owner / Web CCRA 已确定目标的真实本地初审中验证。
|
||||
|
||||
## 8. 与 Web CCRA Bundle 的关系
|
||||
|
||||
正式 Web CCRA / GPT 上传包仍放在：
|
||||
|
||||
```text
|
||||
ccra_review_bundle/round-NN_YYYY-MM-DD_topic/
|
||||
```
|
||||
|
||||
不要使用简写路径，例如：
|
||||
|
||||
```text
|
||||
ccra_review_bundle/05/
|
||||
```
|
||||
|
||||
正式 Web CCRA 包默认不包含：
|
||||
|
||||
```text
|
||||
04_LOCAL_CCRA_REVIEW_REPORT.md
|
||||
```
|
||||
|
||||
只有 Owner 明确要求 Web CCRA 复核本地评审意见时，才把本地评审报告纳入正式上传包。
|
||||
|
||||
## 9. 与 CCPE 和 skills-vault 的分工
|
||||
|
||||
`ccpe-system` 负责：
|
||||
|
||||
- `ccra-local-reviewer` Agent Spec；
|
||||
- CCPE Agent Runtime 接口；
|
||||
- 子会话创建与继续协议；
|
||||
- 评审 rubric；
|
||||
- 生命周期守门规则；
|
||||
- 文件优先评审协议；
|
||||
- 配套能力是否应转交 `skills-vault` 的判定。
|
||||
|
||||
`skills-vault` 只负责：
|
||||
|
||||
- 已经被抽象为可复用、确定性、跨项目自动化的工具；
|
||||
- 例如 `bundle-zip` 这种与具体 CCRA 角色无关的通用文件处理能力。
|
||||
|
||||
Local CCRA 的 companion automation 不直接提交给 `skills-vault`。应先由 CCPE 判定它是 Agent 专属、Runtime 配套、项目本地 helper，还是可抽公共 Skill。
|
||||
|
||||
## 10. 自动化边界
|
||||
|
||||
当前 Local CCRA 机制只定义本地初审的 reviewer/runtime 使用方式，不定义完整轮次自动化。
|
||||
|
||||
完整 Round 级自动化，例如：
|
||||
|
||||
```text
|
||||
Owner/Web 确定 Round N 规划
|
||||
-> 项目自动执行 Round N 工作
|
||||
-> 自动提交 Local CCRA 初审
|
||||
-> 自动修复 N.1 / N.2 / N.x
|
||||
-> 自动汇总本地变化并构造 Web CCRA 正式评审包
|
||||
```
|
||||
|
||||
属于后续的 workflow / orchestrator 设计问题，应另开会话或另写需求讨论。
|
||||
|
||||
原因是这会涉及：
|
||||
|
||||
- Owner 参与点；
|
||||
- 自动修复边界；
|
||||
- Local CCRA findings 的接受 / 拒绝 / 延后协议；
|
||||
- 多次本地评审的停止条件；
|
||||
- 正式 Web bundle 的生成策略；
|
||||
- 是否需要项目侧 runtime、CCPE runtime 或 skills-vault deterministic helper。
|
||||
|
||||
这些内容不应混入 `ccra-local-reviewer` 本体定义。
|
||||
|
||||
## 11. 非目标
|
||||
|
||||
Local CCRA 不做：
|
||||
|
||||
- Owner 最终决策；
|
||||
- Web CCRA 关键节点复审替代；
|
||||
- 模型生命周期升级；
|
||||
- selector 规则修改；
|
||||
- model card 修改；
|
||||
- regression case 修改；
|
||||
- review bundle 创建；
|
||||
- Round 级自动化编排；
|
||||
- 第三模型扩展；
|
||||
- LLM selector、RAG、数据库、前端、后端或平台化功能。
|
||||
|
||||
## 12. 结论
|
||||
|
||||
Local CCRA 是本项目的本地第一轮审查机制。
|
||||
|
||||
它的价值不是复制 Web GPT，而是把 CCRA 的审查原则本地文件化、运行时隔离化、报告归档化。
|
||||
|
||||
项目侧负责保存 review runs；CCPE 负责定义 reviewer 和 runtime；skills-vault 只承接被抽象后的通用自动化。
|
||||
|
|
@ -25,5 +25,6 @@ Current reading order:
|
|||
- `07_产品规划过程记录.md`
|
||||
- `08_CCRA模型库MVP质量门与交接协议.md`
|
||||
- `09_数据治理与模型调用机制说明.md`
|
||||
- `10_本地CCRA评审机制说明.md`
|
||||
|
||||
See `docs/KNOWLEDGE_ASSET_RULES.md`.
|
||||
|
|
|
|||
|
|
@ -0,0 +1,190 @@
|
|||
# Local CCRA Reviews
|
||||
|
||||
## 1. Purpose
|
||||
|
||||
`local_ccra_reviews/` records first-pass Local CCRA reviews for this project.
|
||||
|
||||
The directory is a project-side review run archive. It is not the canonical CCRA Agent definition, not a reusable Skill source tree, and not the formal Web CCRA upload bundle.
|
||||
|
||||
First-version scope:
|
||||
|
||||
- Serves only `the-mindscape-of-bro-tsong`.
|
||||
- Uses CCPE Agent Runtime to create or continue a real child review session.
|
||||
- Passes primary inputs and outputs through local files, not through main-session chat summaries.
|
||||
- Treats Local CCRA output as formal local first review, but not as Owner or Web CCRA final judgment.
|
||||
|
||||
## 2. Ownership
|
||||
|
||||
This repository owns:
|
||||
|
||||
- Local review run directories.
|
||||
- Input file lists and review packets for a specific project round.
|
||||
- Runtime session metadata for continuing child review sessions.
|
||||
- Local CCRA reports, Owner decisions, and action registers.
|
||||
|
||||
`ccpe-system` owns:
|
||||
|
||||
- `ccra-local-reviewer` Agent Spec.
|
||||
- CCPE Agent Runtime contract.
|
||||
- Review rubric, lifecycle gate policy, invocation protocol, and report format.
|
||||
- Decisions about whether companion automation should stay Agent-specific or be routed to `skills-vault`.
|
||||
|
||||
`skills-vault` owns only automation that CCPE or the owner explicitly abstracts as reusable, deterministic, cross-project tooling.
|
||||
|
||||
## 3. Directory Convention
|
||||
|
||||
Use the public Owner / Web CCRA round as the first directory level, then use a Local CCRA pass label.
|
||||
|
||||
Examples:
|
||||
|
||||
```text
|
||||
local_ccra_reviews/
|
||||
round-05_selector-calibration-policy/
|
||||
01/
|
||||
02/
|
||||
round-04/
|
||||
pilot-01/
|
||||
pilot-02/
|
||||
round-03.2a_depth-limiting-qpi-override-patch/
|
||||
01/
|
||||
```
|
||||
|
||||
The public round label follows the same semantic round version as the review bundle, such as `round-05`, `round-04.1`, or `round-03.2a`.
|
||||
|
||||
The child directory records the local review pass:
|
||||
|
||||
- `01/`: first Local CCRA review for that public round.
|
||||
- `02/`: second Local CCRA review after accepted fixes.
|
||||
- `pilot-01/`: historical pilot used to test invocation authenticity, persistence, and report quality before formal use.
|
||||
- `pilot-02/`: historical pilot used to test Patch 1 two-turn review/planning behavior before formal use.
|
||||
- Later numbers are allowed only when the owner explicitly asks for another local review pass.
|
||||
|
||||
## 4. Run Directory Files
|
||||
|
||||
Each run directory should use these files:
|
||||
|
||||
```text
|
||||
run-notes.md
|
||||
review-metadata.json
|
||||
gate-manifest.yaml
|
||||
lifecycle-guard-config.yaml
|
||||
agent-invocation-packet.md
|
||||
prompt-to-send.md
|
||||
turn-prompts/
|
||||
review-context.md
|
||||
review-file-manifest.json
|
||||
helper-outputs/
|
||||
bundle-audit.md
|
||||
bundle-audit.json
|
||||
routing-behavior-diff.md
|
||||
routing-behavior-diff.json
|
||||
gate-run-report.md
|
||||
gate-run-report.json
|
||||
logs/
|
||||
lifecycle-status-guard-scan.md
|
||||
lifecycle-status-guard-scan.json
|
||||
04_LOCAL_CCRA_REVIEW_REPORT.md
|
||||
next-review-requirements.md
|
||||
returned-output.md
|
||||
05_WEB_LOCAL_CCRA_COMPARISON.md
|
||||
owner-decision.md
|
||||
```
|
||||
|
||||
File roles:
|
||||
|
||||
- `run-notes.md`: run setup, helper commands, skipped helpers, dispatch record, child session id, and resume notes.
|
||||
- `review-metadata.json`: review goal, scope, non-goals, open questions, target reviewer, and output paths.
|
||||
- `gate-manifest.yaml`: project-owned validation gates for `regression-validation-gate-runner`; use `dry_run` until the owner approves execution.
|
||||
- `lifecycle-guard-config.yaml`: lifecycle and status overclaim scan configuration.
|
||||
- `agent-invocation-packet.md`: file-first packet for CCPE Agent Runtime.
|
||||
- `prompt-to-send.md`: prompt used when invoking a Codex child thread or equivalent carrier.
|
||||
- `turn-prompts/`: one prompt file per runtime turn, such as `review_turn`, `planning_turn`, and optional `comparison_turn`.
|
||||
- `review-context.md` and `review-file-manifest.json`: deterministic context index generated by `review-context-builder`.
|
||||
- `helper-outputs/`: deterministic evidence generated by registered helper Skills. Missing optional helper outputs must be recorded in `run-notes.md`.
|
||||
- `04_LOCAL_CCRA_REVIEW_REPORT.md`: the only judgment output from `ccra-local-reviewer`.
|
||||
- `next-review-requirements.md`: same-child-session planning output that defines the next review's required materials, evidence, and open Owner/Web decisions.
|
||||
- `returned-output.md`: the raw returned output from the child reviewer, or a pointer to the report if the report is the returned output.
|
||||
- `05_WEB_LOCAL_CCRA_COMPARISON.md`: optional main-session comparison between Local CCRA output and Web CCRA / GPT feedback for pilot tuning.
|
||||
- `owner-decision.md`: accepted, rejected, deferred, or escalated findings.
|
||||
|
||||
## 5. Runtime Rules
|
||||
|
||||
When the owner asks for Local CCRA review:
|
||||
|
||||
1. The main Codex session prepares a new local review run directory.
|
||||
2. The main session invokes CCPE Agent Runtime to create or continue a child review session.
|
||||
3. The runtime session id is recorded in `run-notes.md` and `agent-invocation-packet.md`.
|
||||
4. `review_turn`: `ccra-local-reviewer` reads the review run inputs and referenced project files.
|
||||
5. `review_turn`: `ccra-local-reviewer` writes `04_LOCAL_CCRA_REVIEW_REPORT.md`.
|
||||
6. `planning_turn`: the same child session continues from the first-turn report and writes `next-review-requirements.md` when next-round planning is requested.
|
||||
7. `ccra-local-reviewer` does not modify product files, selector rules, model cards, regression cases, review bundles, or Owner decisions.
|
||||
|
||||
The default formal pattern is two turns in the same child session:
|
||||
|
||||
- `review_turn`: judge the current materials, findings, evidence gaps, and action recommendation.
|
||||
- `planning_turn`: convert the first-turn judgment plus Owner decisions into next-review requirements and submitted-material guidance.
|
||||
|
||||
`planning_turn` should not re-review the full current bundle unless new evidence was added or the owner explicitly asks for re-review.
|
||||
|
||||
Expected run behavior:
|
||||
|
||||
- A useful Local CCRA pass is a deep file-first review, not a quick chat summary.
|
||||
- The normal target budget for a mature run is roughly 5-10 minutes, comparable to Web CCRA review and dependent on the client/runtime configuration.
|
||||
- The child reviewer may use local tools to inspect archives, query manifests, run deterministic helper Skills, and execute owner-approved regression or validation gates.
|
||||
- The main session should avoid interrupting a running child review only because it spends several minutes reading files or running tools.
|
||||
- `run-notes.md` should record observed duration when available so later tuning can distinguish normal review time from runtime problems.
|
||||
|
||||
The project follows the CCPE setup guide at:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-runtime-setup.md
|
||||
```
|
||||
|
||||
## 6. Review Loop
|
||||
|
||||
Recommended flow:
|
||||
|
||||
```text
|
||||
Owner requests Local CCRA review
|
||||
-> create local_ccra_reviews/<round>/<pass>/
|
||||
-> run review-context-builder and applicable helper Skills
|
||||
-> invoke CCPE Agent Runtime child session
|
||||
-> review_turn writes LOCAL_CCRA_REVIEW_REPORT
|
||||
-> planning_turn writes next-review-requirements when needed
|
||||
-> Owner records decision
|
||||
-> Codex executes accepted actions
|
||||
-> next local review pass uses the next pass label if needed
|
||||
-> accepted material is packaged for Web CCRA when the owner asks
|
||||
```
|
||||
|
||||
Major public rounds normally should receive Local CCRA review after Owner / Web CCRA define the round goal. Patch rounds such as `round-03.2a` are optional and owner-directed.
|
||||
|
||||
After `pilot-02`, Local CCRA v0.1.1 is usable as the formal local first-review lane with conditions. CCPE Patch 2 remains a non-blocking hardening request for helper profile, gate execution policy, routing diff requirements, lifecycle scan scope, and short returned summaries.
|
||||
|
||||
## 7. Relationship To Web CCRA Bundles
|
||||
|
||||
`ccra_review_bundle/` remains the formal Web CCRA / GPT upload archive.
|
||||
|
||||
After a Local CCRA pass is accepted, create the formal Web CCRA bundle under the existing dated bundle convention:
|
||||
|
||||
```text
|
||||
ccra_review_bundle/round-NN_YYYY-MM-DD_topic/
|
||||
```
|
||||
|
||||
Do not create shorthand bundle directories such as `ccra_review_bundle/05/`.
|
||||
|
||||
By default, the formal Web CCRA bundle does not include `04_LOCAL_CCRA_REVIEW_REPORT.md`. Include the local report only when the owner explicitly wants Web CCRA to review the local findings.
|
||||
|
||||
## 8. Non-Goals
|
||||
|
||||
Local CCRA review must not:
|
||||
|
||||
- Replace Owner judgment.
|
||||
- Replace Web CCRA at key product or lifecycle gates.
|
||||
- Upgrade model lifecycle status.
|
||||
- Add a third model.
|
||||
- Add LLM selector, RAG, database, frontend, backend, user system, or platform behavior.
|
||||
- Turn `ccra-local-reviewer` into an implementer.
|
||||
- Implement full Round-level automation or autonomous multi-pass repair loops.
|
||||
- Store canonical CCPE artifacts in this repository.
|
||||
- Store reusable Skill source in this repository.
|
||||
|
|
@ -0,0 +1,507 @@
|
|||
# Local CCRA Review Report
|
||||
|
||||
## 1. Return Metadata
|
||||
|
||||
- project_id: the-mindscape-of-bro-tsong
|
||||
- review_round: round-04
|
||||
- local_pass: pilot-01
|
||||
- runtime_id: ccra-local-review
|
||||
- runtime_version: 0.1.0
|
||||
- agent_id: ccra-local-reviewer
|
||||
- agent_version: 0.1.0
|
||||
- invocation_mode: prompt_path_reference
|
||||
- carrier_type: codex_thread
|
||||
- child_session_id: 019edca7-48f3-79d3-be4a-550f4df0f13c
|
||||
- persistent_available: yes, if this Codex child thread is resumed
|
||||
- execution_status: returned
|
||||
- simulation_only: false
|
||||
- report_path: local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md
|
||||
- returned_output_path: local_ccra_reviews/round-04/pilot-01/returned-output.md
|
||||
- generated_at: 2026-06-19
|
||||
|
||||
## 2. Review Scope
|
||||
|
||||
- primary_question: Does Local CCRA produce Web CCRA-level review quality when it can inspect the full local Round 04 evidence set?
|
||||
- scope_statement: Review Round 04 blind routing evaluation evidence as a historical pilot, focusing on invocation authenticity, persistence, report quality, evidence coverage, non-target behavior awareness, lifecycle/scope discipline, and readiness gaps for future Round 05 use.
|
||||
- non_goals:
|
||||
- Do not decide Owner approval.
|
||||
- Do not replace Web CCRA final review.
|
||||
- Do not promote lifecycle status.
|
||||
- Do not modify selector rules, model cards, model JSON, regression cases, review bundles, or Owner decision files.
|
||||
- Do not treat this pilot as Round 05 acceptance.
|
||||
- local_tuning_stage: historical_pilot
|
||||
- web_final_review_target: none_for_this_pilot
|
||||
|
||||
## 3. Inputs Actually Received
|
||||
|
||||
- `local_ccra_reviews/round-04/pilot-01/prompt-to-send.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/agent-invocation-packet.md`
|
||||
- canonical CCPE Agent, Runtime, setup, template, and helper integration files from `C:/Users/wangq/Documents/Codex/ccpe-system`
|
||||
- required knowledge base path: `knowledge_assets/`
|
||||
- review context and manifest: `review-context.md`, `review-file-manifest.json`
|
||||
- Round 04 primary evidence: `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`, `selector/round04_blind_inputs.json`, `selector/selector_rules.json`
|
||||
- optional Round 04.1 post-patch evidence: `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md`, `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/`
|
||||
- helper outputs under `local_ccra_reviews/round-04/pilot-01/helper-outputs/`
|
||||
|
||||
## 4. Files Actually Read
|
||||
|
||||
### Invocation And CCPE Runtime
|
||||
|
||||
- `local_ccra_reviews/round-04/pilot-01/prompt-to-send.md` - dispatch prompt and hard constraints.
|
||||
- `local_ccra_reviews/round-04/pilot-01/agent-invocation-packet.md` - formal invocation packet and output contract.
|
||||
- `C:/Users/wangq/Documents/Codex/ccpe-system/agents/agent-specs/ccra-local-reviewer.agent.md` - reviewer role, source policy, authority boundaries, and reporting requirements.
|
||||
- `C:/Users/wangq/Documents/Codex/ccpe-system/runtimes/hybrid/ccra-local-review.runtime.md` - runtime stages, child-session and helper rules.
|
||||
- `C:/Users/wangq/Documents/Codex/ccpe-system/runtimes/hybrid/ccra-local-review-runtime-setup.md` - setup sequence and helper command contracts.
|
||||
- `C:/Users/wangq/Documents/Codex/ccpe-system/runtimes/hybrid/ccra-local-review-report.template.md` - required report sections.
|
||||
- `C:/Users/wangq/Documents/Codex/ccpe-system/integrations/skills-vault/ccra-local-review-helpers.integration.md` - helper registration and helper-output authority.
|
||||
|
||||
### Project Governance And Knowledge Assets
|
||||
|
||||
- `README.md`
|
||||
- `AGENTS.md`
|
||||
- `PROJECTS.md`
|
||||
- `docs/WORKFLOW.md`
|
||||
- `docs/DECISIONS.md`
|
||||
- `docs/QPI_CONTEXTUAL_ROUTING_RULES.md`
|
||||
- `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md`
|
||||
- `knowledge_assets/README.md`
|
||||
- `knowledge_assets/00_用户背景与产品上下文.md`
|
||||
- `knowledge_assets/01_核心模型地图.md`
|
||||
- `knowledge_assets/02_模型卡结构规范.md`
|
||||
- `knowledge_assets/03_核心模型抽取样板.md`
|
||||
- `knowledge_assets/06_模型稳固性评级规则.md`
|
||||
- `knowledge_assets/07_产品规划过程记录.md`
|
||||
- `knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md`
|
||||
- `knowledge_assets/09_数据治理与模型调用机制说明.md`
|
||||
- `knowledge_assets/10_本地CCRA评审机制说明.md`
|
||||
|
||||
### Local Review Run Records And Helper Outputs
|
||||
|
||||
- `local_ccra_reviews/round-04/pilot-01/run-notes.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/review-metadata.json`
|
||||
- `local_ccra_reviews/round-04/pilot-01/review-context.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/review-file-manifest.json`
|
||||
- `local_ccra_reviews/round-04/pilot-01/owner-decision.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/gate-manifest.yaml`
|
||||
- `local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml`
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.json`
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.json`
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json`
|
||||
|
||||
### Round 04 And Round 04.1 Evidence
|
||||
|
||||
- `reports/Round04_blind_input_candidates_2026-06-18.md`
|
||||
- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
|
||||
- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md`
|
||||
- `reports/selector_regression_report_v0.2.md`
|
||||
- `reports/selector_calibration_smoke_report.md`
|
||||
- `reports/validation_report.md`
|
||||
- `reports/index_rebuild_report.md`
|
||||
- `reports/model_card_sync_report_v0.2.md`
|
||||
- `reports/content_review_report_v0.2.md`
|
||||
- `reports/Codex新会话交接文档_Round04.1关闭与Round05准备_2026-06-18.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/BUNDLE_FILE_MANIFEST_04.1.md`
|
||||
|
||||
### Selector, Tests, Scripts, And Model Status
|
||||
|
||||
- `selector/README.md`
|
||||
- `selector/selector_rules.json`
|
||||
- `selector/round04_blind_inputs.json`
|
||||
- `selector/selector_calibration_inputs.json`
|
||||
- `tests/README.md`
|
||||
- `tests/test_round04_blind_routing.py`
|
||||
- `tests/test_round04_post_patch_verification.py`
|
||||
- `tests/qpi.regression.json`
|
||||
- `tests/intellectual_archaeology.regression.json`
|
||||
- `tests/regression_cases.json`
|
||||
- `scripts/run_selector_demo.py`
|
||||
- `scripts/run_round04_blind_routing.py`
|
||||
- `scripts/run_round04_post_patch_verification.py`
|
||||
- `models/qpi.model.json`
|
||||
- `models/intellectual_archaeology.model.json`
|
||||
- `models/model_index.json`
|
||||
|
||||
## 5. Automation Outputs Used
|
||||
|
||||
- helper_id: review-context-builder
|
||||
- output_path: `local_ccra_reviews/round-04/pilot-01/review-context.md`
|
||||
- status: available
|
||||
- how_used: navigation index only; it did not replace direct file reading.
|
||||
- helper_id: review-bundle-audit
|
||||
- output_path: `local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.md`
|
||||
- status: available_with_findings
|
||||
- how_used: evidence that the generic audit profile reported two blocking findings against the Round 04 bundle.
|
||||
- helper_id: regression-validation-gate-runner
|
||||
- output_path: `local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.md`
|
||||
- status: dry_run
|
||||
- how_used: evidence that three gates were declared but not executed in this pilot helper run.
|
||||
- helper_id: lifecycle-status-guard-scan
|
||||
- output_path: `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md`
|
||||
- status: available_with_findings
|
||||
- how_used: candidate lifecycle/status overclaim list only; final lifecycle assessment below is reviewer judgment.
|
||||
- helper_id: routing-behavior-diff-audit
|
||||
- output_path: none
|
||||
- status: skipped
|
||||
- how_used: not used; this is a tuning gap because Round 04.1 has before/after behavior evidence.
|
||||
|
||||
## 6. Executive Summary
|
||||
|
||||
Result: `needs_more_local_tuning`.
|
||||
|
||||
Local evidence was materially stronger than a limited Web upload would be. This child session could inspect project rules, the full knowledge base, Round 04 and Round 04.1 bundles, reports, selector rules, tests, scripts, helper outputs, and current model status directly. That local access is enough to produce a stronger first-pass review than a compressed upload-only review.
|
||||
|
||||
The Round 04 evidence also shows Local CCRA tuning gaps that should be addressed before formal Round 05 use. The largest gaps are not product-source blockers for this historical pilot; they are runtime/helper/report-quality gaps: the bundle audit profile produced generic-profile blockers against versioned bundle names, the validation helper was dry-run only, routing diff audit was skipped even though before/after routing evidence exists, and the lifecycle scan produced broad findings that need triage rather than automatic blocking.
|
||||
|
||||
Round 04.1's selector repair looks appropriately scoped: four target cases passed, `R04-BI-022` was documented as collateral behavior and regression-covered, and both models remain `draft / B / pending`. However, Round 04 also exposed unresolved calibration questions around governance, capacity/resource/path, ambiguous low-context inputs, and natural Intellectual Archaeology under-selection. Those should be treated as future calibration or Round 05 scope decisions, not silently patched inside this pilot.
|
||||
|
||||
This report is suitable for later comparison against Web CCRA feedback if it is used as pilot-local reviewer output, not as Owner approval, Web CCRA approval, lifecycle promotion, or Round 05 acceptance.
|
||||
|
||||
## 7. Findings
|
||||
|
||||
### Finding LCCRA-R04-P01-F01
|
||||
|
||||
Classification: major
|
||||
|
||||
Title: Local file access produced a stronger review surface than a limited upload bundle.
|
||||
|
||||
Evidence:
|
||||
|
||||
- `review-file-manifest.json` reports no missing source roots and 77 included files across docs, knowledge assets, reports, selector, tests, and review bundles.
|
||||
- `knowledge_assets/10_本地CCRA评审机制说明.md` defines Local CCRA as formal local first review that reads project evidence directly.
|
||||
- `README.md`, `PROJECTS.md`, and `docs/WORKFLOW.md` define Local CCRA run records, review bundle boundaries, and Owner/Web authority boundaries.
|
||||
- Direct reads included `knowledge_assets/`, Round 04 reports, Round 04.1 reports, selector rules, scripts, tests, and helper outputs.
|
||||
|
||||
Why It Matters:
|
||||
|
||||
The pilot question asks whether Local CCRA can do better than a limited Web upload. For this round, the answer is yes: the reviewer could inspect surrounding governance and runtime context that a compressed Web bundle would usually omit or summarize.
|
||||
|
||||
Recommended Action:
|
||||
|
||||
Keep Local CCRA as a file-first first-pass review lane, but require the report to cite exact files read and separate helper evidence from reviewer judgment.
|
||||
|
||||
Owner Decision Required: yes
|
||||
|
||||
Blocks Web Final Review: no
|
||||
|
||||
Blocks Lifecycle Change: yes, because Local CCRA evidence does not itself authorize lifecycle promotion.
|
||||
|
||||
### Finding LCCRA-R04-P01-F02
|
||||
|
||||
Classification: major
|
||||
|
||||
Title: Helper outputs are not yet reliable enough for formal Round 05 without tuning.
|
||||
|
||||
Evidence:
|
||||
|
||||
- `helper-outputs/bundle-audit.md` reports `FAIL`, missing `manifest` and `validation_sidecar`, while the bundle itself has `BUNDLE_FILE_MANIFEST_04.md`.
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md` exists and lists the Round 04 bundle files.
|
||||
- `helper-outputs/gate-run-report.md` reports `DRY_RUN`, with three declared gates and zero commands run.
|
||||
- `agent-invocation-packet.md` records `routing-behavior-diff-audit` as skipped.
|
||||
- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md` contains exactly the kind of before/after routing evidence that a routing diff helper should consume.
|
||||
|
||||
Why It Matters:
|
||||
|
||||
The helper layer is useful, but in this pilot it produced evidence that requires reviewer interpretation. A generic bundle profile treated versioned bundle naming as missing manifest evidence, and dry-run gate output cannot be cited as fresh validation execution.
|
||||
|
||||
Recommended Action:
|
||||
|
||||
Before Round 05, tune helper profiles to recognize versioned bundle names, decide whether zip validation sidecars are required for each bundle type, run gates in approved `run` mode when fresh validation is required, and run routing-behavior-diff-audit when before/after routing reports exist.
|
||||
|
||||
Owner Decision Required: yes, for whether helper execution should be mandatory before formal Round 05.
|
||||
|
||||
Blocks Web Final Review: no for this historical pilot; yes if Round 05 claims fresh local gate execution without running it.
|
||||
|
||||
Blocks Lifecycle Change: yes.
|
||||
|
||||
### Finding LCCRA-R04-P01-F03
|
||||
|
||||
Classification: calibration
|
||||
|
||||
Title: Round 04.1 fixed reviewed failures without broadening QPI into every organization-like input.
|
||||
|
||||
Evidence:
|
||||
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md` limits target labels to `R04-BI-002`, `R04-BI-024`, `R04-BI-035`, and `R04-BI-036`.
|
||||
- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md` reports four targeted cases checked, zero targeted failures, and five behavior changes.
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md` states that governance, capacity, and ambiguous-context cases are not patched in 04.1.
|
||||
- `selector/README.md` records the Round 04.1 selector rule as translation no-call, instruction/payload separation, IA hard exclusion variants, and depth-limited QPI override.
|
||||
|
||||
Why It Matters:
|
||||
|
||||
This is good scope discipline. Round 04.1 did not turn QPI into a generic detector for every governance, organization, capacity, or ambiguous input. That preserves the project's non-goal boundary and lets future calibration decide recall expansion deliberately.
|
||||
|
||||
Recommended Action:
|
||||
|
||||
Treat the unpatched Round 04 categories as future calibration candidates. Do not broaden QPI or IA recall until Owner/Web CCRA identifies which category should become Round 05 scope.
|
||||
|
||||
Owner Decision Required: yes
|
||||
|
||||
Blocks Web Final Review: no for the historical pilot; potentially yes for a future claim that selector calibration is complete.
|
||||
|
||||
Blocks Lifecycle Change: yes.
|
||||
|
||||
### Finding LCCRA-R04-P01-F04
|
||||
|
||||
Classification: calibration
|
||||
|
||||
Title: `R04-BI-022` is a non-target behavior change, but it is documented and regression-covered.
|
||||
|
||||
Evidence:
|
||||
|
||||
- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md` records `R04-BI-022` before patch as `selected_models=[]` and `no_call=True`.
|
||||
- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md` records `R04-BI-022` after patch as `selected_models=['qpi']`, rejected IA, and `no_call=False`.
|
||||
- `reports/Codex新会话交接文档_Round04.1关闭与Round05准备_2026-06-18.md` records the rationale: the user rejected deeper expansion, not lightweight dominant-scarcity judgment.
|
||||
- `tests/qpi.regression.json` contains `case_qpi_round04_depth_limited_assumption_scarcity_001`.
|
||||
|
||||
Why It Matters:
|
||||
|
||||
This is exactly the kind of collateral behavior Local CCRA should catch. The current evidence handles it correctly: it is not hidden, not retroactively made a target case, and not left without regression protection.
|
||||
|
||||
Recommended Action:
|
||||
|
||||
Keep `R04-BI-022` as documented collateral behavior and preserve its regression case. In future Local CCRA runs, require a deterministic routing diff helper to surface similar non-target changes automatically.
|
||||
|
||||
Owner Decision Required: yes, if the Owner wants to reclassify the collateral judgment.
|
||||
|
||||
Blocks Web Final Review: no.
|
||||
|
||||
Blocks Lifecycle Change: yes.
|
||||
|
||||
### Finding LCCRA-R04-P01-F05
|
||||
|
||||
Classification: major
|
||||
|
||||
Title: Lifecycle/status guard findings require triage before formal Round 05 use.
|
||||
|
||||
Evidence:
|
||||
|
||||
- `helper-outputs/lifecycle-status-guard-scan.md` reports 21 blocking findings, mostly approval-claim phrase candidates involving hyphenated Owner-approval wording.
|
||||
- `docs/QPI_CONTEXTUAL_ROUTING_RULES.md`, `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md`, `models/qpi.model.json`, `models/intellectual_archaeology.model.json`, and `models/model_index.json` all keep QPI and IA at `draft / B / pending`.
|
||||
- `knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md` states that engineering contract pass does not equal content stability and that QPI/IA must not be upgraded to stable from validation alone.
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md` explicitly says Round 04 alone must not upgrade lifecycle status.
|
||||
|
||||
Why It Matters:
|
||||
|
||||
The model lifecycle boundary is currently preserved, but the scan findings show that the status guard needs a triage workflow. Some findings appear to be policy or draft-case phrasing rather than direct lifecycle field changes. Formal Round 05 should not inherit an unresolved `FAIL` scan without reviewer triage.
|
||||
|
||||
Recommended Action:
|
||||
|
||||
Before Round 05, classify lifecycle scan findings into true overclaims, policy/example language, source review metadata, and accepted decision records. Tune the config or report template so a helper `FAIL` becomes reviewable evidence, not automatic rejection.
|
||||
|
||||
Owner Decision Required: yes, for any wording repairs or scan-scope decisions.
|
||||
|
||||
Blocks Web Final Review: yes if unresolved findings are included in the claimed review scope.
|
||||
|
||||
Blocks Lifecycle Change: yes.
|
||||
|
||||
### Finding LCCRA-R04-P01-F06
|
||||
|
||||
Classification: calibration
|
||||
|
||||
Title: Invocation authenticity is adequate for this pilot, but return-state bookkeeping remains orchestrator work.
|
||||
|
||||
Evidence:
|
||||
|
||||
- `run-notes.md` records `carrier_type: codex_thread`, `invocation_mode: prompt_path_reference`, `child_session_id: 019edca7-48f3-79d3-be4a-550f4df0f13c`, and `dispatch_status: dispatched`.
|
||||
- `agent-invocation-packet.md` requires a real child session or equivalent isolated participant context and sets `simulation_allowed: false`.
|
||||
- This report and `returned-output.md` are written by the invoked child session under the exact output contract.
|
||||
- `run-notes.md` still records `return_status: pending`; this reviewer did not modify it because the user constrained writes to the two required output files.
|
||||
|
||||
Why It Matters:
|
||||
|
||||
The pilot tests real child-session behavior. The dispatch record is present, but final run bookkeeping still needs the main project session to record return completion after consuming this report.
|
||||
|
||||
Recommended Action:
|
||||
|
||||
Have the orchestrating main session update `run-notes.md` after receiving this report. Keep reviewer writes limited to the formal output files unless the invocation packet explicitly authorizes run-note updates.
|
||||
|
||||
Owner Decision Required: no for bookkeeping; yes for accepting invocation validity if there is any carrier-id mismatch.
|
||||
|
||||
Blocks Web Final Review: no.
|
||||
|
||||
Blocks Lifecycle Change: yes.
|
||||
|
||||
### Finding LCCRA-R04-P01-F07
|
||||
|
||||
Classification: minor
|
||||
|
||||
Title: Review context includes cache/binary artifacts that should be excluded from future context manifests.
|
||||
|
||||
Evidence:
|
||||
|
||||
- `review-context.md` and `review-file-manifest.json` include `tests/__pycache__/*.pyc` and optional raw zip files.
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md` states raw zip files are optional and excludes cache files from raw zip contents.
|
||||
|
||||
Why It Matters:
|
||||
|
||||
Cache and binary artifacts increase manifest noise and may distract future reviewers. They do not block this pilot because source files were still available and read directly.
|
||||
|
||||
Recommended Action:
|
||||
|
||||
Tune `review-context-builder` profiles to exclude `__pycache__/`, `*.pyc`, and optionally list zip archives as binary side artifacts rather than normal review files.
|
||||
|
||||
Owner Decision Required: no, unless the Owner wants zip contents audited as mandatory evidence.
|
||||
|
||||
Blocks Web Final Review: no.
|
||||
|
||||
Blocks Lifecycle Change: no, but lifecycle remains unpromoted for other reasons.
|
||||
|
||||
## 8. Non-Target Behavior Changes
|
||||
|
||||
Observed non-target or collateral behavior from Round 04.1:
|
||||
|
||||
- `R04-BI-022`: before `selected=[]`, `no_call=True`; after `selected=['qpi']`, rejected IA, `no_call=False`. Assessment: documented collateral behavior, regression-covered, not a hidden failure.
|
||||
|
||||
Target changes recorded in the same before/after pool:
|
||||
|
||||
- `R04-BI-002`: translation task moved from QPI selection to no-call.
|
||||
- `R04-BI-024`: explicit IA refusal moved from IA+QPI selection to QPI-only with IA rejected.
|
||||
- `R04-BI-035`: depth-limited dominant-scarcity request moved from no-call to QPI.
|
||||
- `R04-BI-036`: depth-limited scarcity-set request moved from no-call to QPI.
|
||||
|
||||
Unpatched Round 04 categories to keep visible for future calibration:
|
||||
|
||||
- governance / responsibility / consensus cases: `R04-BI-010` through `R04-BI-013`
|
||||
- capacity / resource / path cases: `R04-BI-014`, `R04-BI-015`, `R04-BI-017`, with `R04-BI-016` already selecting QPI
|
||||
- natural IA boundary cases: `R04-BI-026`, `R04-BI-027`, `R04-BI-038`
|
||||
- ambiguous low-context and growth how-to cases: `R04-BI-028` through `R04-BI-030`, `R04-BI-037`
|
||||
|
||||
These are not Round 04.1 failures unless Owner/Web CCRA defines expected labels for them.
|
||||
|
||||
## 9. Engineering Pass vs Product Judgment
|
||||
|
||||
What engineering evidence shows:
|
||||
|
||||
- Round 04 first blind run preserved no-answer-key discipline and wrote a routing report over 38 frozen inputs.
|
||||
- Round 04.1 added targeted regression cases, patched selector rules, reran the frozen pool, and reported zero targeted failures across four reviewed cases.
|
||||
- Current reports show index check, validation, selector regression, selector calibration smoke, and model/card sync as PASS in existing project reports.
|
||||
- Current model JSON status remains `draft / B / pending` for QPI and Intellectual Archaeology.
|
||||
|
||||
What product/model-governance question remains:
|
||||
|
||||
- Which Round 04 unpatched cases should become calibration inputs, regression cases, or future selector changes?
|
||||
- Should natural IA boundary cases such as `R04-BI-026`, `R04-BI-027`, and `R04-BI-038` continue to route through QPI first, or should IA recall be broadened with a stricter depth gate?
|
||||
- Should governance and capacity cases that currently no-call become low-confidence QPI candidates, or stay unpatched to avoid over-selecting QPI?
|
||||
- Which lifecycle-scan findings are true wording risks versus helper false positives or acceptable policy language?
|
||||
|
||||
What evidence would close the gap:
|
||||
|
||||
- Owner/Web CCRA expected labels for selected Round 04 unpatched cases.
|
||||
- A routing-behavior-diff-audit report over Round 04 before/after behavior.
|
||||
- A non-dry-run gate report, if fresh validation is required for Round 05.
|
||||
- A triaged lifecycle-status scan report.
|
||||
- Owner decision entries for accepted, rejected, deferred, and escalated Local CCRA findings.
|
||||
|
||||
## 10. Lifecycle And Scope Guard
|
||||
|
||||
Claim: QPI and Intellectual Archaeology remain draft / B / pending.
|
||||
|
||||
- Evidence: `models/qpi.model.json`, `models/intellectual_archaeology.model.json`, `models/model_index.json`, `docs/QPI_CONTEXTUAL_ROUTING_RULES.md`, `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md`.
|
||||
- Required authority: Owner and Web/CCRA review for any lifecycle change.
|
||||
- Assessment: Preserved. No lifecycle promotion should be inferred from Round 04, Round 04.1, or this Local CCRA pilot.
|
||||
|
||||
Claim: Round 04.1 closeout does not start or accept Round 05.
|
||||
|
||||
- Evidence: `reports/Codex新会话交接文档_Round04.1关闭与Round05准备_2026-06-18.md` says Round 04.1 closeout did not enter Round 05.
|
||||
- Required authority: Owner decision for Round 05 start/scope.
|
||||
- Assessment: Preserved. This pilot is comparison/tuning evidence only.
|
||||
|
||||
Claim: Engineering PASS means product acceptance.
|
||||
|
||||
- Evidence: `knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md`, `knowledge_assets/09_数据治理与模型调用机制说明.md`, and `content_review_report_v0.2.md` explicitly reject that equivalence.
|
||||
- Required authority: Owner/Web CCRA content and lifecycle review.
|
||||
- Assessment: Not supported. Engineering evidence is necessary but insufficient.
|
||||
|
||||
Claim: Local CCRA report equals Web CCRA final approval.
|
||||
|
||||
- Evidence: `knowledge_assets/10_本地CCRA评审机制说明.md`, `docs/WORKFLOW.md`, and `ccra-local-review.runtime.md` say Local CCRA does not replace Owner or Web CCRA.
|
||||
- Required authority: Owner decides whether to include this report in any Web CCRA upload.
|
||||
- Assessment: Not supported.
|
||||
|
||||
## 11. Local Tuning Recommendations
|
||||
|
||||
1. Add a routing-behavior-diff-audit step for Round 04.1-style before/after reports, including target and non-target behavior classification.
|
||||
2. Tune `review-bundle-audit` for this project's versioned bundle names, or add a `the-mindscape-round-bundle` profile that recognizes `BUNDLE_FILE_MANIFEST_04.md` and optional sidecar rules.
|
||||
3. Decide whether gate-runner should run declared gates before formal Round 05 Local CCRA; if yes, run in approved `run` mode and cite logs.
|
||||
4. Triage lifecycle scan findings and update the guard config or wording rules so policy examples and true approval claims are separated.
|
||||
5. Add a required report subsection for unresolved calibration candidates, especially governance/capacity inputs and natural IA boundary cases.
|
||||
6. Exclude cache and binary artifacts from review-context manifests unless the round explicitly audits packaging.
|
||||
7. Have the main project session update `run-notes.md` after report return; the child reviewer should remain read-only except for contracted outputs.
|
||||
|
||||
## 12. Web Final Review Readiness
|
||||
|
||||
Choice: `ready_after_local_repairs`
|
||||
|
||||
Explanation:
|
||||
|
||||
This historical pilot report is ready for later comparison against Web CCRA feedback. It is not a Web final review package and should not be used as Round 05 acceptance. Before formal Round 05 Local CCRA use, the project should repair helper profiles, run or explicitly waive fresh gates, add routing diff helper output where before/after behavior exists, and triage lifecycle findings.
|
||||
|
||||
For the Round 04 / 04.1 historical evidence itself, no additional selector patch is recommended by this Local CCRA report. The next product step should be Owner/Web CCRA scoping for Round 05, not automatic selector expansion.
|
||||
|
||||
## 13. Owner Decision Points
|
||||
|
||||
- decision_id: OD-LCCRA-R04-P01-001
|
||||
- decision_needed: Accept this child-session output as valid Local CCRA pilot output?
|
||||
- options: accept / rerun in another child session / mark invalid
|
||||
- recommended_default: accept, because run notes record a child session id and this report reads local files directly.
|
||||
|
||||
- decision_id: OD-LCCRA-R04-P01-002
|
||||
- decision_needed: Should Local CCRA helper execution be mandatory before Round 05?
|
||||
- options: mandatory run mode / dry-run acceptable / helper outputs optional
|
||||
- recommended_default: mandatory for context, bundle, lifecycle, and routing diff; gate execution depends on Owner approval.
|
||||
|
||||
- decision_id: OD-LCCRA-R04-P01-003
|
||||
- decision_needed: Which Round 04 unpatched categories should become Round 05 calibration scope?
|
||||
- options: governance/capacity QPI recall / natural IA recall / ambiguous context policy / no selector work
|
||||
- recommended_default: decide scope explicitly before changing selector rules.
|
||||
|
||||
- decision_id: OD-LCCRA-R04-P01-004
|
||||
- decision_needed: Should this Local CCRA report be sent to Web CCRA for comparison?
|
||||
- options: include full report / include summary only / keep local-only
|
||||
- recommended_default: keep local-only until Owner provides Web CCRA feedback to compare.
|
||||
|
||||
## 14. Limits And Uncertainty
|
||||
|
||||
- I did not modify any project file except this report and `returned-output.md`.
|
||||
- I did not update `run-notes.md`; the main project session should record return completion.
|
||||
- I did not execute validation gates during this child review. The helper gate report was dry-run only, while existing project reports record prior PASS evidence.
|
||||
- I did not inspect zip contents manually beyond the helper's readable-zip evidence and bundle manifests.
|
||||
- No Web CCRA feedback for this pilot was supplied yet, so comparison quality can only be judged prospectively.
|
||||
- I did not decide Owner approval, Web approval, lifecycle promotion, or Round 05 acceptance.
|
||||
|
||||
## 15. Resume Instructions
|
||||
|
||||
Resume this same child session when comparing against later Web CCRA feedback or tuning the `ccra-local-reviewer` report style.
|
||||
|
||||
For a same-session resume, provide:
|
||||
|
||||
- this report path
|
||||
- `returned-output.md`
|
||||
- any Owner decision file updates
|
||||
- the Web CCRA feedback file or pasted path
|
||||
- a list of changed evidence since this report
|
||||
|
||||
For a new child session, include:
|
||||
|
||||
- `local_ccra_reviews/round-04/pilot-01/agent-invocation-packet.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/returned-output.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/owner-decision.md` if filled
|
||||
- `local_ccra_reviews/round-04/pilot-01/review-context.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/review-file-manifest.json`
|
||||
- helper outputs under `local_ccra_reviews/round-04/pilot-01/helper-outputs/`
|
||||
- any Web CCRA comparison material supplied by the Owner
|
||||
|
|
@ -0,0 +1,139 @@
|
|||
# Web CCRA And Local CCRA Comparison Notes
|
||||
|
||||
## Scope
|
||||
|
||||
- comparison_target: Round 04 / Round 04.1 planning and review-quality comparison
|
||||
- web_source: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\讨论\2026-06-18产品交流-GPT.md`
|
||||
- web_source_range: lines 1-214 only
|
||||
- local_source: `local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md`
|
||||
- comparison_date: 2026-06-19
|
||||
|
||||
This note compares the first two Web CCRA/GPT exchanges with the Local CCRA pilot report. It does not use later Web exchanges after line 214.
|
||||
|
||||
## High-Level Judgment
|
||||
|
||||
The Web review is stronger at product diagnosis and next-action framing. It quickly identifies the actual Round 04 issue class, selects the four cases that should define Round 04.1, and says exactly what the post-patch review bundle must contain.
|
||||
|
||||
The Local CCRA report is stronger at full-file evidence coverage, auditability, runtime/helper risk discovery, lifecycle guard review, and before/after evidence preservation. Its main weakness is that it reviewed from the already-built Round 04.1 evidence set, so it reads more like a local governance and readiness audit than the original Web-style product diagnosis that decided what Round 04.1 should be.
|
||||
|
||||
## Where Web Was Better
|
||||
|
||||
### 1. Product Diagnosis
|
||||
|
||||
Web CCRA immediately classifies `R04-BI-002` as a rule-based selector no-call coverage problem, not an LLM understanding failure.
|
||||
|
||||
It also names the real mechanism: the selector did not distinguish instruction from payload, so words inside a translation payload triggered QPI.
|
||||
|
||||
Local CCRA agrees with the final outcome, but it does not reconstruct this diagnosis with the same sharpness. It mainly records that `R04-BI-002` moved from QPI selection to no-call after Round 04.1.
|
||||
|
||||
### 2. Repair Scope Selection
|
||||
|
||||
Web identifies the right repair set:
|
||||
|
||||
- `R04-BI-002`: translation should become no-call.
|
||||
- `R04-BI-024`: explicit refusal of Intellectual Archaeology should reject IA.
|
||||
- `R04-BI-035` and `R04-BI-036`: depth-limited requests should allow lightweight QPI, not hard no-call.
|
||||
|
||||
Local CCRA confirms these four target cases and verifies that Round 04.1 did not broaden QPI too aggressively. But Web is better at explaining why these four, and not the broader governance/capacity cases, should define the patch.
|
||||
|
||||
### 3. Review Package Requirements
|
||||
|
||||
Web is clearer that Round 04.1 must include a post-patch routing verification report, not only rule diffs.
|
||||
|
||||
It specifies three verification layers:
|
||||
|
||||
- targeted regression for the four cases;
|
||||
- full Round 04 rerun as post-patch comparison;
|
||||
- existing selector regression / calibration smoke / unit tests.
|
||||
|
||||
Local CCRA notices that this evidence exists and points out that routing diff automation should consume it. But Web gives the better owner-facing instruction before the materials are prepared.
|
||||
|
||||
## Where Local Was Better
|
||||
|
||||
### 1. Evidence Coverage
|
||||
|
||||
Local CCRA read the project rules, knowledge assets, Round 04 and Round 04.1 bundles, reports, selector rules, tests, scripts, helper outputs, and model status directly.
|
||||
|
||||
This gives Local CCRA a broader review surface than the Web exchange, especially for checking whether the produced Round 04.1 materials actually match the earlier Web instructions.
|
||||
|
||||
### 2. Non-Target Behavior Tracking
|
||||
|
||||
Local CCRA explicitly identifies `R04-BI-022` as a non-target behavior change after Round 04.1:
|
||||
|
||||
- before: no-call;
|
||||
- after: QPI selected, IA rejected;
|
||||
- assessment: documented collateral behavior and regression-covered.
|
||||
|
||||
This is a strong local advantage. Web lines 1-214 define the need for before/after comparison, but they do not yet see or judge this collateral behavior because that evidence appears only after Round 04.1 is produced.
|
||||
|
||||
### 3. Runtime And Helper Quality
|
||||
|
||||
Local CCRA finds process-level issues that Web does not cover in the first two exchanges:
|
||||
|
||||
- generic `review-bundle-audit` profile does not recognize versioned manifests;
|
||||
- gate runner was dry-run only;
|
||||
- `routing-behavior-diff-audit` was skipped even though before/after routing evidence existed;
|
||||
- lifecycle/status scan requires triage rather than automatic blocking;
|
||||
- context manifest contains cache/binary noise.
|
||||
|
||||
These findings matter for making Local CCRA useful in Round 05, because they affect repeatability and the trustworthiness of future local reports.
|
||||
|
||||
### 4. Lifecycle And Authority Discipline
|
||||
|
||||
Both Web and Local preserve the rule that Round 04 / 04.1 do not upgrade QPI or Intellectual Archaeology.
|
||||
|
||||
Local CCRA adds stronger file-backed checks: model JSON, model index, lifecycle guard, knowledge assets, and project workflow docs all keep the status boundary visible.
|
||||
|
||||
## Key Difference
|
||||
|
||||
Web CCRA acted like the product reviewer at the moment of deciding what to fix next.
|
||||
|
||||
Local CCRA acted like a file-first auditor after the fix existed.
|
||||
|
||||
That difference is acceptable for this pilot, but for Round 05 the Local CCRA should be tuned to include both modes:
|
||||
|
||||
1. diagnose the next product decision as sharply as Web CCRA;
|
||||
2. audit the full file evidence more thoroughly than Web CCRA can.
|
||||
|
||||
## Local CCRA Tuning Implications
|
||||
|
||||
For the next pilot or formal Round 05 run, tune `ccra-local-reviewer` to require:
|
||||
|
||||
1. A Web-style "issue mechanism" section:
|
||||
- what failed;
|
||||
- why it failed;
|
||||
- why it is not a different category of failure.
|
||||
|
||||
2. A "patch scope" section:
|
||||
- must-fix cases;
|
||||
- same-class boundary cases;
|
||||
- calibration-only cases;
|
||||
- cases explicitly not patched.
|
||||
|
||||
3. A mandatory before/after behavior section when post-patch evidence exists:
|
||||
- target behavior changes;
|
||||
- non-target behavior changes;
|
||||
- accepted collateral changes;
|
||||
- unexpected regressions.
|
||||
|
||||
4. A helper-output confidence section:
|
||||
- helper output used as evidence;
|
||||
- helper false positive or profile mismatch;
|
||||
- dry-run versus executed validation;
|
||||
- missing helper that should have run.
|
||||
|
||||
5. A final recommendation shape that mirrors Web CCRA:
|
||||
- fix now;
|
||||
- document only;
|
||||
- defer to calibration;
|
||||
- do not open another small patch round.
|
||||
|
||||
## Practical Conclusion
|
||||
|
||||
Local CCRA is not worse than Web CCRA, but its current prompt/report shape is biased toward governance audit. Web CCRA is better at the early product-review judgment that decides what the next repair round should be.
|
||||
|
||||
The target for Round 05 should be:
|
||||
|
||||
- Web remains the planning and final review partner.
|
||||
- Local CCRA performs the deep local first review with full file access.
|
||||
- Local CCRA must include a Web-style diagnosis and repair-scope judgment so it can reduce small follow-up rounds instead of only auditing them after they happen.
|
||||
|
|
@ -0,0 +1,224 @@
|
|||
---
|
||||
packet_type: local-ccra-agent-invocation-packet
|
||||
runtime_id: ccra-local-review
|
||||
agent_id: ccra-local-reviewer
|
||||
runtime_version: 0.1.0
|
||||
agent_version: 0.1.0
|
||||
review_id: round-04-pilot-01
|
||||
status: ready_for_dispatch
|
||||
---
|
||||
|
||||
# Local CCRA Agent Invocation Packet
|
||||
|
||||
## 1. Invocation Metadata
|
||||
|
||||
```yaml
|
||||
packet_id: round-04-pilot-01
|
||||
created_at: 2026-06-19
|
||||
client_project_root: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong
|
||||
knowledge_base_path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets
|
||||
review_round: round-04
|
||||
local_pass: pilot-01
|
||||
review_run_dir: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01
|
||||
invocation_mode: prompt_path_reference
|
||||
carrier_type: codex_thread
|
||||
child_session_id: pending
|
||||
persistent_child_session_required: true
|
||||
simulation_allowed: false
|
||||
```
|
||||
|
||||
## 2. Canonical Artifacts
|
||||
|
||||
```yaml
|
||||
canonical_agent_path: C:\Users\wangq\Documents\Codex\ccpe-system\agents\agent-specs\ccra-local-reviewer.agent.md
|
||||
canonical_runtime_path: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review.runtime.md
|
||||
runtime_setup_path: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-runtime-setup.md
|
||||
report_template_path: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-report.template.md
|
||||
integration_registration_path: C:\Users\wangq\Documents\Codex\ccpe-system\integrations\skills-vault\ccra-local-review-helpers.integration.md
|
||||
```
|
||||
|
||||
## 3. Role Integrity Requirement
|
||||
|
||||
The invoked participant must act as `ccra-local-reviewer`.
|
||||
|
||||
The reviewer must:
|
||||
|
||||
```text
|
||||
read local evidence directly
|
||||
cite files actually read
|
||||
use helper outputs only as evidence
|
||||
write the report to the requested output contract
|
||||
preserve Owner/Web CCRA authority boundaries
|
||||
avoid project file edits except the required report and returned output
|
||||
avoid lifecycle promotion
|
||||
avoid main-session roleplay
|
||||
```
|
||||
|
||||
If this packet cannot be dispatched to a real child session or equivalent isolated participant context, the valid state is:
|
||||
|
||||
```text
|
||||
blocked_waiting_for_participant_output
|
||||
```
|
||||
|
||||
## 4. Task Context
|
||||
|
||||
```yaml
|
||||
primary_question: Does Local CCRA produce Web CCRA-level review quality when it can inspect the full local Round 04 evidence set?
|
||||
scope_statement: Review Round 04 blind routing evaluation evidence as a historical pilot. Focus on invocation authenticity, persistence, report quality, evidence coverage, non-target behavior awareness, lifecycle/scope discipline, and readiness gaps for future Round 05 use.
|
||||
non_goals:
|
||||
- Do not decide Owner approval.
|
||||
- Do not replace Web CCRA final review.
|
||||
- Do not promote lifecycle status.
|
||||
- Do not modify selector rules, model cards, model JSON, regression cases, or review bundles.
|
||||
- Do not treat this pilot as Round 05 acceptance.
|
||||
local_tuning_stage: historical_pilot
|
||||
web_final_review_target: none_for_this_pilot
|
||||
known_prior_rounds:
|
||||
- round-03
|
||||
- round-03.1
|
||||
- round-03.2
|
||||
- round-03.2a
|
||||
- round-04
|
||||
- round-04.1
|
||||
owner_supplied_notes: Compare later against Web CCRA feedback supplied by Owner. Pilot should test child-session reality, resumability, and report quality.
|
||||
```
|
||||
|
||||
## 5. Input Files
|
||||
|
||||
Required:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\README.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\AGENTS.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets\README.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets\
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\review-context.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\review-file-manifest.json
|
||||
```
|
||||
|
||||
Project and round-specific evidence:
|
||||
|
||||
```text
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\PROJECTS.md
|
||||
purpose: project boundary and supplier rules
|
||||
required: true
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets
|
||||
purpose: required Local CCRA knowledge base; do not duplicate into run directory
|
||||
required: true
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\docs\WORKFLOW.md
|
||||
purpose: workflow and review rules
|
||||
required: true
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\docs\DECISIONS.md
|
||||
purpose: accepted selector and lifecycle decisions
|
||||
required: true
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\reports\Round04_blind_routing_evaluation_report_2026-06-18.md
|
||||
purpose: Round 04 evaluation report
|
||||
required: true
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\reports\Round04_1_post_patch_routing_verification_report_2026-06-18.md
|
||||
purpose: post-patch verification context for collateral behavior awareness
|
||||
required: false
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\selector\round04_blind_inputs.json
|
||||
purpose: full Round 04 blind input set
|
||||
required: true
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\selector\selector_rules.json
|
||||
purpose: current selector rules
|
||||
required: true
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\tests\test_round04_blind_routing.py
|
||||
purpose: Round 04 test surface
|
||||
required: false
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\tests\test_round04_post_patch_verification.py
|
||||
purpose: Round 04.1 post-patch test surface
|
||||
required: false
|
||||
```
|
||||
|
||||
Review bundles:
|
||||
|
||||
```text
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\ccra_review_bundle\round-04_2026-06-18_blind-input-routing-evaluation
|
||||
purpose: primary Round 04 Web CCRA review bundle
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\ccra_review_bundle\round-04.1_2026-06-18_selector-rule-patch
|
||||
purpose: optional post-patch context for understanding later accepted changes
|
||||
```
|
||||
|
||||
Helper outputs:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\helper-outputs\bundle-audit.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\helper-outputs\bundle-audit.json
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\helper-outputs\gate-run-report.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\helper-outputs\gate-run-report.json
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\helper-outputs\lifecycle-status-guard-scan.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\helper-outputs\lifecycle-status-guard-scan.json
|
||||
```
|
||||
|
||||
Unavailable helper outputs:
|
||||
|
||||
```text
|
||||
- routing-behavior-diff-audit: skipped for initial pilot unless before/after routing result files are supplied or identified.
|
||||
```
|
||||
|
||||
## 6. Output Contract
|
||||
|
||||
The reviewer must write:
|
||||
|
||||
```yaml
|
||||
primary_report_path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\04_LOCAL_CCRA_REVIEW_REPORT.md
|
||||
returned_output_path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\returned-output.md
|
||||
required_report_template: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-report.template.md
|
||||
```
|
||||
|
||||
The report must include:
|
||||
|
||||
```text
|
||||
return metadata
|
||||
review scope
|
||||
inputs actually received
|
||||
files actually read
|
||||
automation outputs used
|
||||
executive summary
|
||||
findings
|
||||
non-target behavior changes
|
||||
engineering pass vs product judgment
|
||||
lifecycle and scope guard
|
||||
local tuning recommendations
|
||||
Web final review readiness
|
||||
Owner decision points
|
||||
limits and uncertainty
|
||||
resume instructions
|
||||
```
|
||||
|
||||
## 7. Continuity Policy
|
||||
|
||||
```yaml
|
||||
same_child_session_preferred: true
|
||||
resume_allowed: true
|
||||
resume_requires:
|
||||
- previous report
|
||||
- owner-decision.md when present
|
||||
- new or changed evidence list
|
||||
- unchanged-evidence statement
|
||||
```
|
||||
|
||||
Follow-up review should inspect changed or newly supplied evidence first. Full rerun is required when invocation evidence is invalid, required evidence was missing, or the Owner requests a full rerun.
|
||||
|
||||
## 8. Session Logging
|
||||
|
||||
The project main session must record dispatch method, child session id, helper commands, exit codes, files written, skipped helpers, and manual approvals in:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\run-notes.md
|
||||
```
|
||||
|
||||
## 9. No-Simulation Requirement
|
||||
|
||||
Formal Local CCRA output must not be simulated in the project main session.
|
||||
|
||||
If a simulated dry run is explicitly requested, label it:
|
||||
|
||||
```text
|
||||
simulation-only
|
||||
excluded-from-synthesis
|
||||
not-a-formal-report
|
||||
```
|
||||
|
||||
Simulation-only output cannot be used as the Local CCRA report.
|
||||
|
|
@ -0,0 +1,32 @@
|
|||
gates:
|
||||
- gate_id: index-check
|
||||
command:
|
||||
- python
|
||||
- scripts\rebuild_indexes.py
|
||||
- --check
|
||||
working_directory: .
|
||||
expected_exit_code: 0
|
||||
log_file: logs/index-check.log
|
||||
timeout_seconds: 120
|
||||
required_before_review: true
|
||||
- gate_id: model-library-validation
|
||||
command:
|
||||
- python
|
||||
- scripts\validate_model_library.py
|
||||
working_directory: .
|
||||
expected_exit_code: 0
|
||||
log_file: logs/model-library-validation.log
|
||||
timeout_seconds: 120
|
||||
required_before_review: true
|
||||
- gate_id: round04-blind-routing-tests
|
||||
command:
|
||||
- python
|
||||
- -m
|
||||
- pytest
|
||||
- tests\test_round04_blind_routing.py
|
||||
- tests\test_round04_post_patch_verification.py
|
||||
working_directory: .
|
||||
expected_exit_code: 0
|
||||
log_file: logs/round04-blind-routing-tests.log
|
||||
timeout_seconds: 240
|
||||
required_before_review: false
|
||||
|
|
@ -0,0 +1,74 @@
|
|||
{
|
||||
"bundle_root": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\ccra_review_bundle\\round-04_2026-06-18_blind-input-routing-evaluation",
|
||||
"profile": "generic",
|
||||
"files_discovered": [
|
||||
"00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md",
|
||||
"01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md",
|
||||
"02_BLIND_INPUT_SET_04.md",
|
||||
"03_ROUTING_EVALUATION_REPORT_04.md",
|
||||
"04_REVIEW_QUESTIONS_FOR_GPT_04.md",
|
||||
"BUNDLE_FILE_MANIFEST_04.md",
|
||||
"optional_raw_changed_files_04.zip"
|
||||
],
|
||||
"required_files_present": {
|
||||
"brief": [
|
||||
"00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md"
|
||||
]
|
||||
},
|
||||
"required_files_missing": [
|
||||
"manifest",
|
||||
"validation_sidecar"
|
||||
],
|
||||
"optional_files_present": {
|
||||
"report": [
|
||||
"03_ROUTING_EVALUATION_REPORT_04.md"
|
||||
],
|
||||
"zip": [
|
||||
"optional_raw_changed_files_04.zip"
|
||||
]
|
||||
},
|
||||
"manifest_status": {
|
||||
"status": "missing",
|
||||
"files": []
|
||||
},
|
||||
"zip_status": {
|
||||
"status": "readable",
|
||||
"files": [
|
||||
"optional_raw_changed_files_04.zip"
|
||||
],
|
||||
"entry_counts": {
|
||||
"optional_raw_changed_files_04.zip": 29
|
||||
}
|
||||
},
|
||||
"validation_sidecar_status": {
|
||||
"status": "missing",
|
||||
"files": []
|
||||
},
|
||||
"report_status": {
|
||||
"status": "present",
|
||||
"files": [
|
||||
"03_ROUTING_EVALUATION_REPORT_04.md"
|
||||
]
|
||||
},
|
||||
"warnings": [
|
||||
"Extra file not matched by profile: 01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md",
|
||||
"Extra file not matched by profile: 02_BLIND_INPUT_SET_04.md",
|
||||
"Extra file not matched by profile: 04_REVIEW_QUESTIONS_FOR_GPT_04.md",
|
||||
"Extra file not matched by profile: BUNDLE_FILE_MANIFEST_04.md"
|
||||
],
|
||||
"blocking_errors": [
|
||||
"Missing required manifest file.",
|
||||
"Missing required validation_sidecar file."
|
||||
],
|
||||
"machine_readable_summary": {
|
||||
"status": "FAIL",
|
||||
"files_discovered_count": 7,
|
||||
"required_missing_count": 2,
|
||||
"warning_count": 4,
|
||||
"blocking_error_count": 2,
|
||||
"manifest_status": "missing",
|
||||
"zip_status": "readable",
|
||||
"validation_sidecar_status": "missing",
|
||||
"report_status": "present"
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# Review Bundle Audit
|
||||
|
||||
## Summary
|
||||
|
||||
- Status: `FAIL`
|
||||
- Bundle root: `C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\ccra_review_bundle\round-04_2026-06-18_blind-input-routing-evaluation`
|
||||
- Profile: `generic`
|
||||
- Files discovered: 7
|
||||
- Required files missing: 2
|
||||
- Warnings: 4
|
||||
- Blocking errors: 2
|
||||
|
||||
## Required Files
|
||||
|
||||
- `brief`: `00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md`
|
||||
|
||||
Missing:
|
||||
- `manifest`
|
||||
- `validation_sidecar`
|
||||
|
||||
## Package Status
|
||||
|
||||
- `manifest_status`: `missing` (none)
|
||||
- `validation_sidecar_status`: `missing` (none)
|
||||
- `zip_status`: `readable` (`optional_raw_changed_files_04.zip`)
|
||||
- `report_status`: `present` (`03_ROUTING_EVALUATION_REPORT_04.md`)
|
||||
|
||||
## Blocking Errors
|
||||
|
||||
- Missing required manifest file.
|
||||
- Missing required validation_sidecar file.
|
||||
|
||||
## Warnings
|
||||
|
||||
- Extra file not matched by profile: 01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md
|
||||
- Extra file not matched by profile: 02_BLIND_INPUT_SET_04.md
|
||||
- Extra file not matched by profile: 04_REVIEW_QUESTIONS_FOR_GPT_04.md
|
||||
- Extra file not matched by profile: BUNDLE_FILE_MANIFEST_04.md
|
||||
|
||||
## Files Discovered
|
||||
|
||||
- `00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md`
|
||||
- `01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md`
|
||||
- `02_BLIND_INPUT_SET_04.md`
|
||||
- `03_ROUTING_EVALUATION_REPORT_04.md`
|
||||
- `04_REVIEW_QUESTIONS_FOR_GPT_04.md`
|
||||
- `BUNDLE_FILE_MANIFEST_04.md`
|
||||
- `optional_raw_changed_files_04.zip`
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
{
|
||||
"project_root": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
|
||||
"gate_manifest_path": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\local_ccra_reviews\\round-04\\pilot-01\\gate-manifest.yaml",
|
||||
"mode": "dry_run",
|
||||
"commands_declared": [
|
||||
"index-check",
|
||||
"model-library-validation",
|
||||
"round04-blind-routing-tests"
|
||||
],
|
||||
"commands_run": [],
|
||||
"commands_skipped": [
|
||||
{
|
||||
"gate_id": "index-check",
|
||||
"reason": "dry_run"
|
||||
},
|
||||
{
|
||||
"gate_id": "model-library-validation",
|
||||
"reason": "dry_run"
|
||||
},
|
||||
{
|
||||
"gate_id": "round04-blind-routing-tests",
|
||||
"reason": "dry_run"
|
||||
}
|
||||
],
|
||||
"exit_codes": {},
|
||||
"pass_fail_status": "DRY_RUN",
|
||||
"duration": 0.0,
|
||||
"log_paths": {},
|
||||
"environment_notes": [
|
||||
"Commands are declared by the manifest.",
|
||||
"Passing gates are engineering evidence only; they do not imply product acceptance or lifecycle approval.",
|
||||
"python: 3.11.15",
|
||||
"platform: Windows-10-10.0.26200-SP0"
|
||||
],
|
||||
"gate_results": [],
|
||||
"manifest_errors": [],
|
||||
"changed_files": [],
|
||||
"machine_readable_summary": {
|
||||
"status": "DRY_RUN",
|
||||
"commands_declared_count": 3,
|
||||
"commands_run_count": 0,
|
||||
"commands_skipped_count": 3,
|
||||
"manifest_error_count": 0,
|
||||
"failed_count": 0,
|
||||
"timeout_count": 0,
|
||||
"changed_file_count": 0
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,28 @@
|
|||
# Gate Run Report
|
||||
|
||||
## Summary
|
||||
|
||||
- Status: `DRY_RUN`
|
||||
- Commands declared: 3
|
||||
- Commands run: 0
|
||||
- Commands skipped: 3
|
||||
- Manifest errors: 0
|
||||
- Changed files: 0
|
||||
|
||||
## Gate Results
|
||||
|
||||
- None
|
||||
|
||||
## Skipped Gates
|
||||
|
||||
- `index-check`: dry_run
|
||||
- `model-library-validation`: dry_run
|
||||
- `round04-blind-routing-tests`: dry_run
|
||||
|
||||
## Manifest Errors
|
||||
|
||||
- None
|
||||
|
||||
## Changed Files
|
||||
|
||||
- None
|
||||
|
|
@ -0,0 +1,965 @@
|
|||
{
|
||||
"scan_root": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
|
||||
"config_path": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\local_ccra_reviews\\round-04\\pilot-01\\lifecycle-guard-config.yaml",
|
||||
"files_scanned": [
|
||||
"AGENTS.md",
|
||||
"cards/card_index.md",
|
||||
"cards/intellectual_archaeology.md",
|
||||
"cards/qpi.md",
|
||||
"cards/README.md",
|
||||
"ccra_review_bundle/round-02_2026-06-16_second-audit/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md",
|
||||
"ccra_review_bundle/round-02_2026-06-16_second-audit/01_GUIDANCE_PACK_AND_COMPLIANCE_MATRIX.md",
|
||||
"ccra_review_bundle/round-02_2026-06-16_second-audit/02_CURRENT_ASSET_PACK.md",
|
||||
"ccra_review_bundle/round-02_2026-06-16_second-audit/03_REPORTS_DIFF_AND_COMMAND_LOG.md",
|
||||
"ccra_review_bundle/round-02_2026-06-16_second-audit/BUNDLE_FILE_MANIFEST.md",
|
||||
"ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF03.1.md",
|
||||
"ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/01_PATCH_MATRIX_03.1.md",
|
||||
"ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/02_CURRENT_ASSET_PACK03.1.md",
|
||||
"ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/03_VALIDATION_AND_COMMAND_LOG03.1.md",
|
||||
"ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/04_REVIEW_QUESTIONS_FOR_GPT03.1.md",
|
||||
"ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/BUNDLE_FILE_MANIFEST03.1.md",
|
||||
"ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_03.2.md",
|
||||
"ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/01_PATCH_MATRIX_03.2.md",
|
||||
"ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/02_CURRENT_ASSET_PACK_03.2.md",
|
||||
"ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/03_VALIDATION_AND_COMMAND_LOG_03.2.md",
|
||||
"ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/04_REVIEW_QUESTIONS_FOR_GPT_03.2.md",
|
||||
"ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/BUNDLE_FILE_MANIFEST_03.2.md",
|
||||
"ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_03.2a.md",
|
||||
"ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/01_PATCH_MATRIX_03.2a.md",
|
||||
"ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/02_CURRENT_ASSET_PACK_03.2a.md",
|
||||
"ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/03_VALIDATION_AND_COMMAND_LOG_03.2a.md",
|
||||
"ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/04_REVIEW_QUESTIONS_FOR_GPT_03.2a.md",
|
||||
"ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/BUNDLE_FILE_MANIFEST_03.2a.md",
|
||||
"ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md",
|
||||
"ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/01_GUIDANCE_PACK_AND_COMPLIANCE_MATRIX.md",
|
||||
"ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/02_CURRENT_ASSET_PACK.md",
|
||||
"ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/03_REPORTS_DIFF_AND_COMMAND_LOG.md",
|
||||
"ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/04_QPI_CASE_PROMOTION_SUMMARY_AND_REVIEW_GUIDE.md",
|
||||
"ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/05_REVIEW_QUESTIONS_FOR_GPT.md",
|
||||
"ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/BUNDLE_FILE_MANIFEST.md",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.1.md",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/BUNDLE_FILE_MANIFEST_04.1.md",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md",
|
||||
"docs/CHATGPT_HANDOFF_RULES.md",
|
||||
"docs/CONTENT_STABILIZATION_PROTOCOL.md",
|
||||
"docs/DATA_CONTRACT.md",
|
||||
"docs/DECISIONS.md",
|
||||
"docs/FILE_TAXONOMY.md",
|
||||
"docs/GPT_PLAN_LOCALIZATION_PROTOCOL.md",
|
||||
"docs/HANDOFF_TEMPLATE.md",
|
||||
"docs/INDEX_MAINTENANCE_PROTOCOL.md",
|
||||
"docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md",
|
||||
"docs/KNOWLEDGE_ASSET_RULES.md",
|
||||
"docs/MODEL_CARD_CONTRACT.md",
|
||||
"docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md",
|
||||
"docs/model_case_preprocessing/qpi/README.md",
|
||||
"docs/model_case_preprocessing/README.md",
|
||||
"docs/MODEL_EXTRACTION_RULES.md",
|
||||
"docs/MODEL_EXTRACTION_WORKFLOW.md",
|
||||
"docs/NON_GOALS.md",
|
||||
"docs/PROJECT_BRIEF.md",
|
||||
"docs/QPI_CONTEXTUAL_ROUTING_RULES.md",
|
||||
"docs/superpowers/plans/2026-06-16-model-extraction-contract-and-workflow.md",
|
||||
"docs/superpowers/plans/2026-06-16-project-initialization.md",
|
||||
"docs/superpowers/plans/2026-06-17-contract-hardening-selector-calibration.md",
|
||||
"docs/superpowers/plans/2026-06-18-round04-1-selector-rule-patch.md",
|
||||
"docs/superpowers/plans/2026-06-18-round04-blind-routing-evaluation.md",
|
||||
"docs/WORKFLOW.md",
|
||||
"knowledge_assets/00_用户背景与产品上下文.md",
|
||||
"knowledge_assets/01_核心模型地图.md",
|
||||
"knowledge_assets/02_模型卡结构规范.md",
|
||||
"knowledge_assets/03_核心模型抽取样板.md",
|
||||
"knowledge_assets/06_模型稳固性评级规则.md",
|
||||
"knowledge_assets/07_产品规划过程记录.md",
|
||||
"knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md",
|
||||
"knowledge_assets/09_数据治理与模型调用机制说明.md",
|
||||
"knowledge_assets/10_本地CCRA评审机制说明.md",
|
||||
"knowledge_assets/README.md",
|
||||
"local_ccra_reviews/README.md",
|
||||
"local_ccra_reviews/round-04/pilot-01/agent-invocation-packet.md",
|
||||
"local_ccra_reviews/round-04/pilot-01/gate-manifest.yaml",
|
||||
"local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.json",
|
||||
"local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.md",
|
||||
"local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.json",
|
||||
"local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.md",
|
||||
"local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml",
|
||||
"local_ccra_reviews/round-04/pilot-01/owner-decision.md",
|
||||
"local_ccra_reviews/round-04/pilot-01/prompt-to-send.md",
|
||||
"local_ccra_reviews/round-04/pilot-01/review-metadata.json",
|
||||
"local_ccra_reviews/round-04/pilot-01/run-notes.md",
|
||||
"models/intellectual_archaeology.model.json",
|
||||
"models/model_index.json",
|
||||
"models/qpi.model.json",
|
||||
"models/README.md",
|
||||
"PROJECTS.md",
|
||||
"README.md",
|
||||
"reports/baseline_before_content_stabilization_v0.2.md",
|
||||
"reports/changed_files_manifest.md",
|
||||
"reports/ChatGPT交接文档_模型库MVP_2026-06-16.md",
|
||||
"reports/ChatGPT交接文档_模型库MVP_第二轮内容稳定化_2026-06-16.md",
|
||||
"reports/Codex_工程产物摘要_v0.1.md",
|
||||
"reports/Codex_本地CCRA规划落地_2026-06-19.md",
|
||||
"reports/Codex_模型资产链路摘要_v0.1.md",
|
||||
"reports/Codex新会话交接文档_CCRA评审后处理_2026-06-16.md",
|
||||
"reports/Codex新会话交接文档_QPI案例草稿审阅与第三轮后续_2026-06-17.md",
|
||||
"reports/Codex新会话交接文档_Round03.1评审后续_2026-06-17.md",
|
||||
"reports/Codex新会话交接文档_Round03.2a评审准备_2026-06-17.md",
|
||||
"reports/Codex新会话交接文档_Round03.2评审准备_2026-06-17.md",
|
||||
"reports/Codex新会话交接文档_Round04.1关闭与Round05准备_2026-06-18.md",
|
||||
"reports/Codex新会话交接文档_模型库MVP_2026-06-16.md",
|
||||
"reports/command_log.md",
|
||||
"reports/content_review_report.md",
|
||||
"reports/content_review_report_v0.2.md",
|
||||
"reports/evidence_coverage_matrix.md",
|
||||
"reports/evidence_coverage_report_v0.2.md",
|
||||
"reports/GPT规划落地差异检查_v0.1.md",
|
||||
"reports/GPT讨论上下文_QPI草稿案例审阅_2026-06-17.md",
|
||||
"reports/index_check_report.md",
|
||||
"reports/index_rebuild_report.md",
|
||||
"reports/model_card_sync_report_v0.2.md",
|
||||
"reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md",
|
||||
"reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md",
|
||||
"reports/model_case_preprocessing/qpi/round-01/README.md",
|
||||
"reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
|
||||
"reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md",
|
||||
"reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md",
|
||||
"reports/model_case_preprocessing/qpi/round-01/year-end-review-engineering-center.cases.md",
|
||||
"reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md",
|
||||
"reports/model_case_preprocessing/qpi/round-01/year-end-review-research-office.cases.md",
|
||||
"reports/model_review_status.json",
|
||||
"reports/next_action_register_v0.2.md",
|
||||
"reports/open_questions_for_CCRA.md",
|
||||
"reports/README.md",
|
||||
"reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md",
|
||||
"reports/Round04_blind_input_candidates_2026-06-18.md",
|
||||
"reports/Round04_blind_routing_evaluation_report_2026-06-18.md",
|
||||
"reports/schema_change_notes.md",
|
||||
"reports/selector_calibration_smoke_report.md",
|
||||
"reports/selector_regression_report.md",
|
||||
"reports/selector_regression_report_v0.2.md",
|
||||
"reports/selector_score_breakdown.md",
|
||||
"reports/validation_report.md",
|
||||
"reports/内容修复检查摘要_v0.1.md",
|
||||
"reports/内容修复检查摘要_v0.2.md",
|
||||
"reports/规则Schema工作流检查摘要_v0.1.md",
|
||||
"requirements/ccpe/2026-06-19-ccra-local-reviewer-runtime.md",
|
||||
"requirements/ccpe/README.md",
|
||||
"requirements/skills-vault/2026-06-18-review-bundle-zip-packager.md",
|
||||
"requirements/skills-vault/README.md",
|
||||
"schemas/card_index.schema.json",
|
||||
"schemas/model_card.schema.json",
|
||||
"schemas/model_index.schema.json",
|
||||
"schemas/model_spec.schema.json",
|
||||
"schemas/README.md",
|
||||
"schemas/regression_case.schema.json",
|
||||
"schemas/source_article.schema.json",
|
||||
"schemas/source_excerpt.schema.json",
|
||||
"scripts/README.md",
|
||||
"selector/qpi_case_digests.json",
|
||||
"selector/README.md",
|
||||
"selector/round04_blind_inputs.json",
|
||||
"selector/selector_calibration_inputs.json",
|
||||
"selector/selector_examples.json",
|
||||
"selector/selector_rules.json",
|
||||
"sources/evidence_coverage.matrix.json",
|
||||
"sources/README.md",
|
||||
"sources/source_articles.json",
|
||||
"sources/source_excerpts.json",
|
||||
"tests/intellectual_archaeology.regression.json",
|
||||
"tests/qpi.regression.json",
|
||||
"tests/README.md",
|
||||
"tests/regression_cases.json",
|
||||
"tests/regression_index.json"
|
||||
],
|
||||
"possible_overclaims": [
|
||||
{
|
||||
"file": "ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/03_VALIDATION_AND_COMMAND_LOG_03.2.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 59,
|
||||
"column": 58,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "on_report.md` - `reports/selector_regression_report_v0.2.md` - `reports/selector_calibration_smoke_report.md` - `reports/model_card_sync_report_v0.2.md` ## Important Interpretation Validation pass does not mean model content is stable or owner-approved. It only means the Round 03.2 selector negative-gate patch is structurally consistent and passes current local checks.",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/03_VALIDATION_AND_COMMAND_LOG_03.2a.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 47,
|
||||
"column": 58,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "ct: PASS - Selector demo: PASS - Selector regression: PASS - Selector calibration smoke: PASS, 95 inputs, 0 failures, 0 warnings - Model/card sync: PASS ## Important Interpretation Validation pass does not mean model content is stable or owner-approved. It only means the Round 03.2a selector precedence patch is structurally consistent and passes current local checks.",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "docs/DECISIONS.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 175,
|
||||
"column": 154,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "such as `先不要思想考古` could still lose to positive IA signals and QPI-completed bonuses. A user instruction that names a model and refuses it should not be represented as a normal score penalty. It must hard-exclude that model unless a later owner-approved rule defines an explicit reversal phrase. The current Round 03.2 implementation keeps this scoped: - It rejects only the explicitly refused model. - It does not create a global no-call. - It does not add an LLM selector, RAG, database, s",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 160,
|
||||
"column": 27,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "Do not: - write selector JSON directly; - update regression cases directly; - upgrade model status; - create a third model; - summarize the whole source instead of extracting cases; - quote long source passages; - pretend draft cases are owner-approved. ## 7. Promotion Path The promotion path is: ```text raw source -> Markdown case drafts -> owner review and correction -> case digest JSON -> selector calibration inputs or regression cases ``` Only owner-reviewed cases may become mach",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 263,
|
||||
"column": 8,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "w Questions - Should QPI explicitly mark \"single-cause reduction\" as a subtype of violent reduction? - Should this case be used to test that QPI does not output a single definitive cause when the source provides coupled mechanisms? - What owner-approved language should be used to distinguish explanatory usefulness from causal finality? ### 13. Owner Review Decision - Keep the case, but avoid the overbroad rule \"all single-cause attribution is wrong.\" - Rename the risk to `single_facto",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 275,
|
||||
"column": 3,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "n. - Prevent QPI from outputting a single definitive root cause when coupled mechanisms are already present. - Require distinction between trigger, maintaining condition, high-weight factor, current action lever, and causal totality. - Owner-approved language: - \"This factor has explanatory usefulness, but it is not causal finality.\" - \"It may be a high-weight factor or current lever, not the complete cause.\" - \"It can be prioritized in this context, but it cannot replace the sys",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 11,
|
||||
"column": 150,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "h: `C:\\Users\\wangq\\Documents\\Codex\\knowledge-vault\\work\\internal\\强哥的思想宇宙\\QPI案例分析\\流程改造.md` source_note: Raw source remains outside this repository. These are reviewable QPI case drafts only; they are not selector JSON, regression cases, or owner-approved calibration data. ## Case qpi-draft-001: Outline Review Was Not The Real Entry Point status: owner_reviewed owner_approved_for_digest: true digest_role: supporting_evidence_for_context_engineering_entry_point_case source_path: `C:\\Use",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 11,
|
||||
"column": 436,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "locations, titles, exact numbers, and sensitive operational details have been removed or generalized. Ancient-style cognitive-anchor names from the source are intentionally omitted. These drafts are not selector JSON, regression cases, or owner-approved calibration data. anonymization_note: People are represented as generic roles such as `decision_maker`, `execution_lead`, `technical_staff`, `frontline_staff`, and `affected_learners`. The organization is represented as `the organization`",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 100,
|
||||
"column": 3,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "overnance. - Keep `classification: mixed` because the same case contains data scarcity and governance scarcity. - Use as selector calibration and high-priority regression for AI/tool requests that must not be treated as simple execution. - Owner-approved wording: \"AI can organize evidence, but must not manufacture the evidentiary relationship.\" - Current anonymization is sufficient. ## Case qpi-draft-002: Credential Metric Repair Creates Staffing Ratio Deadlock status: owner_reviewed o",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 357,
|
||||
"column": 3,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "rtability and application feasibility. - Market-facing frame sees communication and enrollment value. - Long-term organization frame sees strategic myopia risk. - Keep `classification: issue` and `dominant_scarcity: consensus_order`. - Owner-approved wording: \"A resource-feasible compromise becomes strategic myopia if it is not tested against long-term positioning.\" - Use as calibration for short-term reportability or packaging substituting for long-term strategic planning. ## Case qp",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 519,
|
||||
"column": 8,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "as dominant scarcity] - Should isolated achievements be treated as evidence of latent capability or as masking signals? [answered: prioritize as masking signal; they may indicate local capability but cannot offset systemic decline] - What owner-approved wording should be used to avoid over-claiming causal responsibility? [answered: input conditions may affect outcomes but cannot replace audit of management levers] ### 13. Owner Review Decision - Keep `classification: mixed` and `dominan",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 528,
|
||||
"column": 3,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "upported or whether academic affairs is treated as cost, revenue, or reporting function. - Treat isolated achievements primarily as masking signals. - They may indicate local capability, but they cannot offset systemic outcome decline. - Owner-approved wording: - \"Input conditions may affect outcomes, but cannot replace audit of management levers.\" - \"Learner quality can explain part of the difficulty, but it cannot automatically exempt quality-assurance responsibility.\" - \"Isolate",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 618,
|
||||
"column": 3,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "y, adoption incentives, and digital governance level. - Keep `dominant_scarcity: consensus_order`. - Path/resource cost exists, but the missing object is shared governance criteria and authority. - Local versus cloud detail can remain. - Owner-approved wording: \"Define digital governance criteria before platform selection.\" ## Case qpi-draft-008: Public Safety Compliance Gap Reveals Bottom-Line Control Failure status: owner_reviewed owner_approved_for_digest: true digest_role: botto",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 11,
|
||||
"column": 408,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "s, institutions, timestamps, locations, titles, and exact numeric details have been removed or generalized. Ancient-style cognitive anchors from the source are intentionally omitted. These drafts are not selector JSON, regression cases, or owner-approved calibration data. anonymization_note: People are represented as roles such as `decision_maker`, `execution_lead`, `strategy_staff`, `functional_department`, and `frontline_staff`. The organization is represented as `the organization`; the",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 7,
|
||||
"column": 428,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "estamps, places, titles, exact numbers, and sensitive operational details have been removed or generalized. Ancient-style cognitive anchors from the source are intentionally omitted. These drafts are not selector JSON, regression cases, or owner-approved calibration data. owner_review_source: `C:/Users/wangq/Documents/Codex/knowledge-vault/work/internal/强哥的思想宇宙/QPI案例审阅/QPI提炼审核/year-end-review-employment-entrepreneurship.cases-GPT.md` owner_review_note: Owner/GPT review approved all eight",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 698,
|
||||
"column": 8,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "ich replace education value with transactional output metrics. ### 12. Owner Review Questions - Is this case too broad for calibration, or useful as an Issue anchor? - Should it be decomposed into several narrower P/I mixed cases? - What owner-approved wording should be used for the anonymized identity-shift risk? ### 13. Owner Review Decision - owner_review_status: owner_reviewed - owner_approved_for_digest: true - digest_role: transactional_education_issue_anchor - selector_calibrati",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 81,
|
||||
"column": 64,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "nant scarcity here correctly placed on consensus/order rather than path/resource? - Should this be treated as Issue rather than mixed because the compliance boundary dominates? - Which details, if any, are safe enough to retain in a future owner-approved case digest? ### 13. Owner Review Decision - owner_review_status: owner_reviewed - owner_approved_for_digest: true - digest_role: compliance_boundary_retention_issue_regression_case - regression_candidate: high_priority - classification:",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 618,
|
||||
"column": 8,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "e design without killing execution energy. ### 12. Owner Review Questions - Is \"privatization of organizational capability\" the right abstraction here? - Should this case be connected with the role-inflation case or kept separate? - What owner-approved signal distinguishes healthy recognition from dangerous private capture? ### 13. Owner Review Decision - owner_review_status: owner_reviewed - owner_approved_for_digest: true - digest_role: non_institutionalized_capability_calibration_ca",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-research-office.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 7,
|
||||
"column": 397,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "departments, institutions, timestamps, locations, titles, ancient-style cognitive anchors, exact numeric details, and sensitive operational details have been removed or generalized. These drafts are not selector JSON, regression cases, or owner-approved calibration data. owner_review_source: `C:/Users/wangq/Documents/Codex/knowledge-vault/work/internal/强哥的思想宇宙/QPI案例审阅/QPI提炼审核/year-end-review-research-office.cases-GPT.md` owner_review_note: Owner/GPT review approved all eight cases for d",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "selector/qpi_case_digests.json",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 1261,
|
||||
"column": 42,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "into an upstream authority over teaching.\", \"routing_notes\": [ \"hard outcome metric hiding authority redesign\", \"separate outcome improvement from teaching authority transfer\", \"reverse accountability power is owner-approved wording\" ], \"recommended_next_step\": \"Define shared outcome governance, evidence standards, and limits on reverse accountability before redesigning authority.\", \"misclassification_risk\": [ \"violent_reduction\",",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "selector/qpi_case_digests.json",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 2187,
|
||||
"column": 42,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "mulate research identity through people, expenses, patents, papers, and evidence packaging to obtain external preferential status.\", \"routing_notes\": [ \"umbrella case for this source\", \"research identity simulation is owner-approved\", \"capability building must be separated from evidence simulation\" ], \"recommended_next_step\": \"Separate legitimate research capability building from identity simulation and compliance red-line risk.\", \"misclassif",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
}
|
||||
],
|
||||
"field_level_findings": [],
|
||||
"phrase_level_findings": [
|
||||
{
|
||||
"file": "ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/03_VALIDATION_AND_COMMAND_LOG_03.2.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 59,
|
||||
"column": 58,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "on_report.md` - `reports/selector_regression_report_v0.2.md` - `reports/selector_calibration_smoke_report.md` - `reports/model_card_sync_report_v0.2.md` ## Important Interpretation Validation pass does not mean model content is stable or owner-approved. It only means the Round 03.2 selector negative-gate patch is structurally consistent and passes current local checks.",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/03_VALIDATION_AND_COMMAND_LOG_03.2a.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 47,
|
||||
"column": 58,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "ct: PASS - Selector demo: PASS - Selector regression: PASS - Selector calibration smoke: PASS, 95 inputs, 0 failures, 0 warnings - Model/card sync: PASS ## Important Interpretation Validation pass does not mean model content is stable or owner-approved. It only means the Round 03.2a selector precedence patch is structurally consistent and passes current local checks.",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "docs/DECISIONS.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 175,
|
||||
"column": 154,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "such as `先不要思想考古` could still lose to positive IA signals and QPI-completed bonuses. A user instruction that names a model and refuses it should not be represented as a normal score penalty. It must hard-exclude that model unless a later owner-approved rule defines an explicit reversal phrase. The current Round 03.2 implementation keeps this scoped: - It rejects only the explicitly refused model. - It does not create a global no-call. - It does not add an LLM selector, RAG, database, s",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 160,
|
||||
"column": 27,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "Do not: - write selector JSON directly; - update regression cases directly; - upgrade model status; - create a third model; - summarize the whole source instead of extracting cases; - quote long source passages; - pretend draft cases are owner-approved. ## 7. Promotion Path The promotion path is: ```text raw source -> Markdown case drafts -> owner review and correction -> case digest JSON -> selector calibration inputs or regression cases ``` Only owner-reviewed cases may become mach",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 263,
|
||||
"column": 8,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "w Questions - Should QPI explicitly mark \"single-cause reduction\" as a subtype of violent reduction? - Should this case be used to test that QPI does not output a single definitive cause when the source provides coupled mechanisms? - What owner-approved language should be used to distinguish explanatory usefulness from causal finality? ### 13. Owner Review Decision - Keep the case, but avoid the overbroad rule \"all single-cause attribution is wrong.\" - Rename the risk to `single_facto",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 275,
|
||||
"column": 3,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "n. - Prevent QPI from outputting a single definitive root cause when coupled mechanisms are already present. - Require distinction between trigger, maintaining condition, high-weight factor, current action lever, and causal totality. - Owner-approved language: - \"This factor has explanatory usefulness, but it is not causal finality.\" - \"It may be a high-weight factor or current lever, not the complete cause.\" - \"It can be prioritized in this context, but it cannot replace the sys",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 11,
|
||||
"column": 150,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "h: `C:\\Users\\wangq\\Documents\\Codex\\knowledge-vault\\work\\internal\\强哥的思想宇宙\\QPI案例分析\\流程改造.md` source_note: Raw source remains outside this repository. These are reviewable QPI case drafts only; they are not selector JSON, regression cases, or owner-approved calibration data. ## Case qpi-draft-001: Outline Review Was Not The Real Entry Point status: owner_reviewed owner_approved_for_digest: true digest_role: supporting_evidence_for_context_engineering_entry_point_case source_path: `C:\\Use",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 11,
|
||||
"column": 436,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "locations, titles, exact numbers, and sensitive operational details have been removed or generalized. Ancient-style cognitive-anchor names from the source are intentionally omitted. These drafts are not selector JSON, regression cases, or owner-approved calibration data. anonymization_note: People are represented as generic roles such as `decision_maker`, `execution_lead`, `technical_staff`, `frontline_staff`, and `affected_learners`. The organization is represented as `the organization`",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 100,
|
||||
"column": 3,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "overnance. - Keep `classification: mixed` because the same case contains data scarcity and governance scarcity. - Use as selector calibration and high-priority regression for AI/tool requests that must not be treated as simple execution. - Owner-approved wording: \"AI can organize evidence, but must not manufacture the evidentiary relationship.\" - Current anonymization is sufficient. ## Case qpi-draft-002: Credential Metric Repair Creates Staffing Ratio Deadlock status: owner_reviewed o",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 357,
|
||||
"column": 3,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "rtability and application feasibility. - Market-facing frame sees communication and enrollment value. - Long-term organization frame sees strategic myopia risk. - Keep `classification: issue` and `dominant_scarcity: consensus_order`. - Owner-approved wording: \"A resource-feasible compromise becomes strategic myopia if it is not tested against long-term positioning.\" - Use as calibration for short-term reportability or packaging substituting for long-term strategic planning. ## Case qp",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 519,
|
||||
"column": 8,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "as dominant scarcity] - Should isolated achievements be treated as evidence of latent capability or as masking signals? [answered: prioritize as masking signal; they may indicate local capability but cannot offset systemic decline] - What owner-approved wording should be used to avoid over-claiming causal responsibility? [answered: input conditions may affect outcomes but cannot replace audit of management levers] ### 13. Owner Review Decision - Keep `classification: mixed` and `dominan",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 528,
|
||||
"column": 3,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "upported or whether academic affairs is treated as cost, revenue, or reporting function. - Treat isolated achievements primarily as masking signals. - They may indicate local capability, but they cannot offset systemic outcome decline. - Owner-approved wording: - \"Input conditions may affect outcomes, but cannot replace audit of management levers.\" - \"Learner quality can explain part of the difficulty, but it cannot automatically exempt quality-assurance responsibility.\" - \"Isolate",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 618,
|
||||
"column": 3,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "y, adoption incentives, and digital governance level. - Keep `dominant_scarcity: consensus_order`. - Path/resource cost exists, but the missing object is shared governance criteria and authority. - Local versus cloud detail can remain. - Owner-approved wording: \"Define digital governance criteria before platform selection.\" ## Case qpi-draft-008: Public Safety Compliance Gap Reveals Bottom-Line Control Failure status: owner_reviewed owner_approved_for_digest: true digest_role: botto",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 11,
|
||||
"column": 408,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "s, institutions, timestamps, locations, titles, and exact numeric details have been removed or generalized. Ancient-style cognitive anchors from the source are intentionally omitted. These drafts are not selector JSON, regression cases, or owner-approved calibration data. anonymization_note: People are represented as roles such as `decision_maker`, `execution_lead`, `strategy_staff`, `functional_department`, and `frontline_staff`. The organization is represented as `the organization`; the",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 7,
|
||||
"column": 428,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "estamps, places, titles, exact numbers, and sensitive operational details have been removed or generalized. Ancient-style cognitive anchors from the source are intentionally omitted. These drafts are not selector JSON, regression cases, or owner-approved calibration data. owner_review_source: `C:/Users/wangq/Documents/Codex/knowledge-vault/work/internal/强哥的思想宇宙/QPI案例审阅/QPI提炼审核/year-end-review-employment-entrepreneurship.cases-GPT.md` owner_review_note: Owner/GPT review approved all eight",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 698,
|
||||
"column": 8,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "ich replace education value with transactional output metrics. ### 12. Owner Review Questions - Is this case too broad for calibration, or useful as an Issue anchor? - Should it be decomposed into several narrower P/I mixed cases? - What owner-approved wording should be used for the anonymized identity-shift risk? ### 13. Owner Review Decision - owner_review_status: owner_reviewed - owner_approved_for_digest: true - digest_role: transactional_education_issue_anchor - selector_calibrati",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 81,
|
||||
"column": 64,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "nant scarcity here correctly placed on consensus/order rather than path/resource? - Should this be treated as Issue rather than mixed because the compliance boundary dominates? - Which details, if any, are safe enough to retain in a future owner-approved case digest? ### 13. Owner Review Decision - owner_review_status: owner_reviewed - owner_approved_for_digest: true - digest_role: compliance_boundary_retention_issue_regression_case - regression_candidate: high_priority - classification:",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 618,
|
||||
"column": 8,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "e design without killing execution energy. ### 12. Owner Review Questions - Is \"privatization of organizational capability\" the right abstraction here? - Should this case be connected with the role-inflation case or kept separate? - What owner-approved signal distinguishes healthy recognition from dangerous private capture? ### 13. Owner Review Decision - owner_review_status: owner_reviewed - owner_approved_for_digest: true - digest_role: non_institutionalized_capability_calibration_ca",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-research-office.cases.md",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 7,
|
||||
"column": 397,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "departments, institutions, timestamps, locations, titles, ancient-style cognitive anchors, exact numeric details, and sensitive operational details have been removed or generalized. These drafts are not selector JSON, regression cases, or owner-approved calibration data. owner_review_source: `C:/Users/wangq/Documents/Codex/knowledge-vault/work/internal/强哥的思想宇宙/QPI案例审阅/QPI提炼审核/year-end-review-research-office.cases-GPT.md` owner_review_note: Owner/GPT review approved all eight cases for d",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "selector/qpi_case_digests.json",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 1261,
|
||||
"column": 42,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "into an upstream authority over teaching.\", \"routing_notes\": [ \"hard outcome metric hiding authority redesign\", \"separate outcome improvement from teaching authority transfer\", \"reverse accountability power is owner-approved wording\" ], \"recommended_next_step\": \"Define shared outcome governance, evidence standards, and limits on reverse accountability before redesigning authority.\", \"misclassification_risk\": [ \"violent_reduction\",",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
},
|
||||
{
|
||||
"file": "selector/qpi_case_digests.json",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 2187,
|
||||
"column": 42,
|
||||
"severity": "blocking",
|
||||
"evidence_present": false,
|
||||
"context": "mulate research identity through people, expenses, patents, papers, and evidence packaging to obtain external preferential status.\", \"routing_notes\": [ \"umbrella case for this source\", \"research identity simulation is owner-approved\", \"capability building must be separated from evidence simulation\" ], \"recommended_next_step\": \"Separate legitimate research capability building from identity simulation and compliance red-line risk.\", \"misclassif",
|
||||
"message": "Approval claim phrase lacks nearby evidence marker."
|
||||
}
|
||||
],
|
||||
"missing_evidence_markers": [
|
||||
{
|
||||
"file": "ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/03_VALIDATION_AND_COMMAND_LOG_03.2.md",
|
||||
"line": 59,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/03_VALIDATION_AND_COMMAND_LOG_03.2a.md",
|
||||
"line": 47,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "docs/DECISIONS.md",
|
||||
"line": 175,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md",
|
||||
"line": 160,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md",
|
||||
"line": 263,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md",
|
||||
"line": 275,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md",
|
||||
"line": 11,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
|
||||
"line": 11,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
|
||||
"line": 100,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
|
||||
"line": 357,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
|
||||
"line": 519,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
|
||||
"line": 528,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md",
|
||||
"line": 618,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md",
|
||||
"line": 11,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md",
|
||||
"line": 7,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md",
|
||||
"line": 698,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md",
|
||||
"line": 81,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md",
|
||||
"line": 618,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "reports/model_case_preprocessing/qpi/round-01/year-end-review-research-office.cases.md",
|
||||
"line": 7,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "selector/qpi_case_digests.json",
|
||||
"line": 1261,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "selector/qpi_case_digests.json",
|
||||
"line": 2187,
|
||||
"phrase": "owner-approved",
|
||||
"required_evidence_markers": [
|
||||
"owner_decision",
|
||||
"owner decision",
|
||||
"ccra_review",
|
||||
"ccra review",
|
||||
"web ccra"
|
||||
]
|
||||
}
|
||||
],
|
||||
"warnings": [],
|
||||
"blocking_errors": [
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker.",
|
||||
"Approval claim phrase lacks nearby evidence marker."
|
||||
],
|
||||
"observations": [
|
||||
{
|
||||
"file": "local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml",
|
||||
"source": "text",
|
||||
"phrase": "owner-approved",
|
||||
"line": 14,
|
||||
"column": 5,
|
||||
"severity": "observation",
|
||||
"evidence_present": true,
|
||||
"context": "watched_paths: - \"**/*.md\" - \"**/*.json\" - \"**/*.yaml\" - \"**/*.yml\" status_fields: - status - lifecycle - model.status - model.lifecycle forbidden_status_values: - stable - accepted - owner-approved - ccra-approved warning_status_values: - candidate - ready-for-review required_evidence_markers: - owner_decision - owner decision - ccra_review - ccra review - web ccra approved_phrases: - owner-approved - ccra-approve",
|
||||
"message": "Approval claim phrase has nearby evidence marker; approval validity is not decided by this scan.",
|
||||
"kind": "evidence_present_claim"
|
||||
},
|
||||
{
|
||||
"file": "local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml",
|
||||
"source": "text",
|
||||
"phrase": "ccra-approved",
|
||||
"line": 15,
|
||||
"column": 5,
|
||||
"severity": "observation",
|
||||
"evidence_present": true,
|
||||
"context": "watched_paths: - \"**/*.md\" - \"**/*.json\" - \"**/*.yaml\" - \"**/*.yml\" status_fields: - status - lifecycle - model.status - model.lifecycle forbidden_status_values: - stable - accepted - owner-approved - ccra-approved warning_status_values: - candidate - ready-for-review required_evidence_markers: - owner_decision - owner decision - ccra_review - ccra review - web ccra approved_phrases: - owner-approved - ccra-approved - Owner approv",
|
||||
"message": "Approval claim phrase has nearby evidence marker; approval validity is not decided by this scan.",
|
||||
"kind": "evidence_present_claim"
|
||||
}
|
||||
],
|
||||
"machine_readable_summary": {
|
||||
"status": "FAIL",
|
||||
"files_scanned_count": 178,
|
||||
"field_finding_count": 0,
|
||||
"phrase_finding_count": 21,
|
||||
"missing_evidence_count": 21,
|
||||
"warning_count": 0,
|
||||
"blocking_count": 21,
|
||||
"observation_count": 2
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,223 @@
|
|||
# Lifecycle Status Guard Scan
|
||||
|
||||
## Summary
|
||||
|
||||
- Status: `FAIL`
|
||||
- Files scanned: 178
|
||||
- Blocking findings: 21
|
||||
- Warnings: 0
|
||||
- Evidence-present observations: 2
|
||||
|
||||
## Blocking Findings
|
||||
|
||||
- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/03_VALIDATION_AND_COMMAND_LOG_03.2.md` line 59: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/03_VALIDATION_AND_COMMAND_LOG_03.2a.md` line 47: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `docs/DECISIONS.md` line 175: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md` line 160: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md` line 263: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md` line 275: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md` line 11: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 11: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 100: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 357: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 519: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 528: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 618: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md` line 11: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md` line 7: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md` line 698: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md` line 81: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md` line 618: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-research-office.cases.md` line 7: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `selector/qpi_case_digests.json` line 1261: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `selector/qpi_case_digests.json` line 2187: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
|
||||
## Warnings
|
||||
|
||||
- None
|
||||
|
||||
## Observations
|
||||
|
||||
- `local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml` line 14: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml` line 15: `ccra-approved` - evidence marker present; approval validity not decided.
|
||||
|
||||
## Files Scanned
|
||||
|
||||
- `AGENTS.md`
|
||||
- `cards/card_index.md`
|
||||
- `cards/intellectual_archaeology.md`
|
||||
- `cards/qpi.md`
|
||||
- `cards/README.md`
|
||||
- `ccra_review_bundle/round-02_2026-06-16_second-audit/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md`
|
||||
- `ccra_review_bundle/round-02_2026-06-16_second-audit/01_GUIDANCE_PACK_AND_COMPLIANCE_MATRIX.md`
|
||||
- `ccra_review_bundle/round-02_2026-06-16_second-audit/02_CURRENT_ASSET_PACK.md`
|
||||
- `ccra_review_bundle/round-02_2026-06-16_second-audit/03_REPORTS_DIFF_AND_COMMAND_LOG.md`
|
||||
- `ccra_review_bundle/round-02_2026-06-16_second-audit/BUNDLE_FILE_MANIFEST.md`
|
||||
- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF03.1.md`
|
||||
- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/01_PATCH_MATRIX_03.1.md`
|
||||
- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/02_CURRENT_ASSET_PACK03.1.md`
|
||||
- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/03_VALIDATION_AND_COMMAND_LOG03.1.md`
|
||||
- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/04_REVIEW_QUESTIONS_FOR_GPT03.1.md`
|
||||
- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/BUNDLE_FILE_MANIFEST03.1.md`
|
||||
- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_03.2.md`
|
||||
- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/01_PATCH_MATRIX_03.2.md`
|
||||
- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/02_CURRENT_ASSET_PACK_03.2.md`
|
||||
- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/03_VALIDATION_AND_COMMAND_LOG_03.2.md`
|
||||
- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/04_REVIEW_QUESTIONS_FOR_GPT_03.2.md`
|
||||
- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/BUNDLE_FILE_MANIFEST_03.2.md`
|
||||
- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_03.2a.md`
|
||||
- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/01_PATCH_MATRIX_03.2a.md`
|
||||
- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/02_CURRENT_ASSET_PACK_03.2a.md`
|
||||
- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/03_VALIDATION_AND_COMMAND_LOG_03.2a.md`
|
||||
- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/04_REVIEW_QUESTIONS_FOR_GPT_03.2a.md`
|
||||
- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/BUNDLE_FILE_MANIFEST_03.2a.md`
|
||||
- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md`
|
||||
- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/01_GUIDANCE_PACK_AND_COMPLIANCE_MATRIX.md`
|
||||
- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/02_CURRENT_ASSET_PACK.md`
|
||||
- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/03_REPORTS_DIFF_AND_COMMAND_LOG.md`
|
||||
- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/04_QPI_CASE_PROMOTION_SUMMARY_AND_REVIEW_GUIDE.md`
|
||||
- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/05_REVIEW_QUESTIONS_FOR_GPT.md`
|
||||
- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/BUNDLE_FILE_MANIFEST.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/BUNDLE_FILE_MANIFEST_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md`
|
||||
- `docs/CHATGPT_HANDOFF_RULES.md`
|
||||
- `docs/CONTENT_STABILIZATION_PROTOCOL.md`
|
||||
- `docs/DATA_CONTRACT.md`
|
||||
- `docs/DECISIONS.md`
|
||||
- `docs/FILE_TAXONOMY.md`
|
||||
- `docs/GPT_PLAN_LOCALIZATION_PROTOCOL.md`
|
||||
- `docs/HANDOFF_TEMPLATE.md`
|
||||
- `docs/INDEX_MAINTENANCE_PROTOCOL.md`
|
||||
- `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md`
|
||||
- `docs/KNOWLEDGE_ASSET_RULES.md`
|
||||
- `docs/MODEL_CARD_CONTRACT.md`
|
||||
- `docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md`
|
||||
- `docs/model_case_preprocessing/qpi/README.md`
|
||||
- `docs/model_case_preprocessing/README.md`
|
||||
- `docs/MODEL_EXTRACTION_RULES.md`
|
||||
- `docs/MODEL_EXTRACTION_WORKFLOW.md`
|
||||
- `docs/NON_GOALS.md`
|
||||
- `docs/PROJECT_BRIEF.md`
|
||||
- `docs/QPI_CONTEXTUAL_ROUTING_RULES.md`
|
||||
- `docs/superpowers/plans/2026-06-16-model-extraction-contract-and-workflow.md`
|
||||
- `docs/superpowers/plans/2026-06-16-project-initialization.md`
|
||||
- `docs/superpowers/plans/2026-06-17-contract-hardening-selector-calibration.md`
|
||||
- `docs/superpowers/plans/2026-06-18-round04-1-selector-rule-patch.md`
|
||||
- `docs/superpowers/plans/2026-06-18-round04-blind-routing-evaluation.md`
|
||||
- `docs/WORKFLOW.md`
|
||||
- `knowledge_assets/00_用户背景与产品上下文.md`
|
||||
- `knowledge_assets/01_核心模型地图.md`
|
||||
- `knowledge_assets/02_模型卡结构规范.md`
|
||||
- `knowledge_assets/03_核心模型抽取样板.md`
|
||||
- `knowledge_assets/06_模型稳固性评级规则.md`
|
||||
- `knowledge_assets/07_产品规划过程记录.md`
|
||||
- `knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md`
|
||||
- `knowledge_assets/09_数据治理与模型调用机制说明.md`
|
||||
- `knowledge_assets/10_本地CCRA评审机制说明.md`
|
||||
- `knowledge_assets/README.md`
|
||||
- `local_ccra_reviews/README.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/agent-invocation-packet.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/gate-manifest.yaml`
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.json`
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.json`
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml`
|
||||
- `local_ccra_reviews/round-04/pilot-01/owner-decision.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/prompt-to-send.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/review-metadata.json`
|
||||
- `local_ccra_reviews/round-04/pilot-01/run-notes.md`
|
||||
- `models/intellectual_archaeology.model.json`
|
||||
- `models/model_index.json`
|
||||
- `models/qpi.model.json`
|
||||
- `models/README.md`
|
||||
- `PROJECTS.md`
|
||||
- `README.md`
|
||||
- `reports/baseline_before_content_stabilization_v0.2.md`
|
||||
- `reports/changed_files_manifest.md`
|
||||
- `reports/ChatGPT交接文档_模型库MVP_2026-06-16.md`
|
||||
- `reports/ChatGPT交接文档_模型库MVP_第二轮内容稳定化_2026-06-16.md`
|
||||
- `reports/Codex_工程产物摘要_v0.1.md`
|
||||
- `reports/Codex_本地CCRA规划落地_2026-06-19.md`
|
||||
- `reports/Codex_模型资产链路摘要_v0.1.md`
|
||||
- `reports/Codex新会话交接文档_CCRA评审后处理_2026-06-16.md`
|
||||
- `reports/Codex新会话交接文档_QPI案例草稿审阅与第三轮后续_2026-06-17.md`
|
||||
- `reports/Codex新会话交接文档_Round03.1评审后续_2026-06-17.md`
|
||||
- `reports/Codex新会话交接文档_Round03.2a评审准备_2026-06-17.md`
|
||||
- `reports/Codex新会话交接文档_Round03.2评审准备_2026-06-17.md`
|
||||
- `reports/Codex新会话交接文档_Round04.1关闭与Round05准备_2026-06-18.md`
|
||||
- `reports/Codex新会话交接文档_模型库MVP_2026-06-16.md`
|
||||
- `reports/command_log.md`
|
||||
- `reports/content_review_report.md`
|
||||
- `reports/content_review_report_v0.2.md`
|
||||
- `reports/evidence_coverage_matrix.md`
|
||||
- `reports/evidence_coverage_report_v0.2.md`
|
||||
- `reports/GPT规划落地差异检查_v0.1.md`
|
||||
- `reports/GPT讨论上下文_QPI草稿案例审阅_2026-06-17.md`
|
||||
- `reports/index_check_report.md`
|
||||
- `reports/index_rebuild_report.md`
|
||||
- `reports/model_card_sync_report_v0.2.md`
|
||||
- `reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md`
|
||||
- `reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md`
|
||||
- `reports/model_case_preprocessing/qpi/round-01/README.md`
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md`
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md`
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md`
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-engineering-center.cases.md`
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md`
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-research-office.cases.md`
|
||||
- `reports/model_review_status.json`
|
||||
- `reports/next_action_register_v0.2.md`
|
||||
- `reports/open_questions_for_CCRA.md`
|
||||
- `reports/README.md`
|
||||
- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md`
|
||||
- `reports/Round04_blind_input_candidates_2026-06-18.md`
|
||||
- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
|
||||
- `reports/schema_change_notes.md`
|
||||
- `reports/selector_calibration_smoke_report.md`
|
||||
- `reports/selector_regression_report.md`
|
||||
- `reports/selector_regression_report_v0.2.md`
|
||||
- `reports/selector_score_breakdown.md`
|
||||
- `reports/validation_report.md`
|
||||
- `reports/内容修复检查摘要_v0.1.md`
|
||||
- `reports/内容修复检查摘要_v0.2.md`
|
||||
- `reports/规则Schema工作流检查摘要_v0.1.md`
|
||||
- `requirements/ccpe/2026-06-19-ccra-local-reviewer-runtime.md`
|
||||
- `requirements/ccpe/README.md`
|
||||
- `requirements/skills-vault/2026-06-18-review-bundle-zip-packager.md`
|
||||
- `requirements/skills-vault/README.md`
|
||||
- `schemas/card_index.schema.json`
|
||||
- `schemas/model_card.schema.json`
|
||||
- `schemas/model_index.schema.json`
|
||||
- `schemas/model_spec.schema.json`
|
||||
- `schemas/README.md`
|
||||
- `schemas/regression_case.schema.json`
|
||||
- `schemas/source_article.schema.json`
|
||||
- `schemas/source_excerpt.schema.json`
|
||||
- `scripts/README.md`
|
||||
- `selector/qpi_case_digests.json`
|
||||
- `selector/README.md`
|
||||
- `selector/round04_blind_inputs.json`
|
||||
- `selector/selector_calibration_inputs.json`
|
||||
- `selector/selector_examples.json`
|
||||
- `selector/selector_rules.json`
|
||||
- `sources/evidence_coverage.matrix.json`
|
||||
- `sources/README.md`
|
||||
- `sources/source_articles.json`
|
||||
- `sources/source_excerpts.json`
|
||||
- `tests/intellectual_archaeology.regression.json`
|
||||
- `tests/qpi.regression.json`
|
||||
- `tests/README.md`
|
||||
- `tests/regression_cases.json`
|
||||
- `tests/regression_index.json`
|
||||
|
|
@ -0,0 +1,38 @@
|
|||
watched_paths:
|
||||
- "**/*.md"
|
||||
- "**/*.json"
|
||||
- "**/*.yaml"
|
||||
- "**/*.yml"
|
||||
status_fields:
|
||||
- status
|
||||
- lifecycle
|
||||
- model.status
|
||||
- model.lifecycle
|
||||
forbidden_status_values:
|
||||
- stable
|
||||
- accepted
|
||||
- owner-approved
|
||||
- ccra-approved
|
||||
warning_status_values:
|
||||
- candidate
|
||||
- ready-for-review
|
||||
required_evidence_markers:
|
||||
- owner_decision
|
||||
- owner decision
|
||||
- ccra_review
|
||||
- ccra review
|
||||
- web ccra
|
||||
approved_phrases:
|
||||
- owner-approved
|
||||
- ccra-approved
|
||||
- Owner approved
|
||||
- CCRA approved
|
||||
forbidden_phrases:
|
||||
- production-ready
|
||||
- released to production
|
||||
- final approved
|
||||
allowed_contexts:
|
||||
- do not say
|
||||
- must not claim
|
||||
- example:
|
||||
evidence_window_chars: 240
|
||||
|
|
@ -0,0 +1,23 @@
|
|||
# Owner Decision
|
||||
|
||||
Status: pending
|
||||
|
||||
## Accepted Findings
|
||||
|
||||
-
|
||||
|
||||
## Rejected Findings
|
||||
|
||||
-
|
||||
|
||||
## Deferred Findings
|
||||
|
||||
-
|
||||
|
||||
## Escalated To Web CCRA
|
||||
|
||||
-
|
||||
|
||||
## Notes
|
||||
|
||||
This file should be filled only after `04_LOCAL_CCRA_REVIEW_REPORT.md` is returned.
|
||||
|
|
@ -0,0 +1,52 @@
|
|||
# Prompt To Send: CCRA Local Review Pilot
|
||||
|
||||
You are being invoked as a real child review session for `ccra-local-reviewer`.
|
||||
|
||||
This is not main-session roleplay. If you cannot comply with the file-first invocation packet, report that you are blocked.
|
||||
|
||||
Read and follow:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\agent-invocation-packet.md
|
||||
```
|
||||
|
||||
Canonical CCPE artifacts:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\ccpe-system\agents\agent-specs\ccra-local-reviewer.agent.md
|
||||
C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review.runtime.md
|
||||
C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-report.template.md
|
||||
```
|
||||
|
||||
Required project knowledge base:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets
|
||||
```
|
||||
|
||||
Use this path directly. Do not create a second Local CCRA copy of the knowledge base.
|
||||
|
||||
Required output:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\04_LOCAL_CCRA_REVIEW_REPORT.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-01\returned-output.md
|
||||
```
|
||||
|
||||
Hard constraints:
|
||||
|
||||
- Read local files directly.
|
||||
- Read the required `knowledge_assets/` knowledge base.
|
||||
- Cite the files actually read.
|
||||
- Use helper outputs only as evidence, not as judgment.
|
||||
- Do not modify project files except the two required output files above.
|
||||
- Do not edit selector rules, model cards, model JSON, regression cases, review bundles, or Owner decision files.
|
||||
- Do not upgrade model lifecycle status.
|
||||
- Do not treat this pilot as Round 05 acceptance.
|
||||
|
||||
Pilot review questions:
|
||||
|
||||
1. Was enough local evidence available to produce a stronger review than a limited Web upload?
|
||||
2. Does the Round 04 evidence show local tuning gaps that should be addressed before Round 05?
|
||||
3. What should be tuned in the Local CCRA Agent, Runtime, helper outputs, invocation packet, or report template before formal Round 05 use?
|
||||
4. Is this pilot report suitable for comparison against Web CCRA feedback supplied later by the Owner?
|
||||
|
|
@ -0,0 +1,41 @@
|
|||
# Returned Output
|
||||
|
||||
## Return Metadata
|
||||
|
||||
- project_id: the-mindscape-of-bro-tsong
|
||||
- review_round: round-04
|
||||
- local_pass: pilot-01
|
||||
- runtime_id: ccra-local-review
|
||||
- runtime_version: 0.1.0
|
||||
- agent_id: ccra-local-reviewer
|
||||
- agent_version: 0.1.0
|
||||
- invocation_mode: prompt_path_reference
|
||||
- carrier_type: codex_thread
|
||||
- child_session_id: 019edca7-48f3-79d3-be4a-550f4df0f13c
|
||||
- execution_status: returned
|
||||
- simulation_only: false
|
||||
- generated_at: 2026-06-19
|
||||
|
||||
## Output Files
|
||||
|
||||
- primary_report_path: `local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md`
|
||||
- returned_output_path: `local_ccra_reviews/round-04/pilot-01/returned-output.md`
|
||||
|
||||
## Result
|
||||
|
||||
The Local CCRA pilot report was written successfully.
|
||||
|
||||
Practical result: `needs_more_local_tuning`.
|
||||
|
||||
Summary:
|
||||
|
||||
- Local evidence was strong enough to produce a richer first-pass review than a limited Web upload.
|
||||
- Round 04.1 target fixes are documented and regression-covered.
|
||||
- `R04-BI-022` is a documented collateral behavior change, not a hidden behavior drift.
|
||||
- Helper/profile tuning is needed before formal Round 05 Local CCRA use.
|
||||
- QPI and Intellectual Archaeology remain `draft / B / pending`.
|
||||
- This pilot is not Owner approval, Web CCRA approval, lifecycle promotion, or Round 05 acceptance.
|
||||
|
||||
## Main Follow-Up
|
||||
|
||||
The main project session should read `04_LOCAL_CCRA_REVIEW_REPORT.md`, then update run bookkeeping and Owner decisions outside this child reviewer output contract.
|
||||
|
|
@ -0,0 +1,183 @@
|
|||
# Review Context
|
||||
|
||||
This context is an index. It does not replace reading source files.
|
||||
|
||||
## Metadata
|
||||
|
||||
- Review ID: `round-04-pilot-01`
|
||||
- Context profile: `ccra-local-review`
|
||||
- Status: `PASS`
|
||||
|
||||
## Source Roots
|
||||
|
||||
- `README.md`
|
||||
- `AGENTS.md`
|
||||
- `PROJECTS.md`
|
||||
- `knowledge_assets`
|
||||
- `docs`
|
||||
- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
|
||||
- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md`
|
||||
- `selector`
|
||||
- `tests`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch`
|
||||
|
||||
## Files Included
|
||||
|
||||
- `AGENTS.md` (8063 bytes)
|
||||
- `PROJECTS.md` (6784 bytes)
|
||||
- `README.md` (7915 bytes)
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.1.md` (2245 bytes)
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md` (2223 bytes)
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md` (1124 bytes)
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md` (7956 bytes)
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md` (3364 bytes)
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/BUNDLE_FILE_MANIFEST_04.1.md` (2171 bytes)
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip` (207917 bytes)
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json` (1921 bytes)
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/raw_file_list_04.1.txt` (1337 bytes)
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md` (1476 bytes)
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md` (2211 bytes)
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md` (1495 bytes)
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md` (29841 bytes)
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md` (1614 bytes)
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md` (1710 bytes)
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/optional_raw_changed_files_04.zip` (176893 bytes)
|
||||
- `docs/CHATGPT_HANDOFF_RULES.md` (2175 bytes)
|
||||
- `docs/CONTENT_STABILIZATION_PROTOCOL.md` (2331 bytes)
|
||||
- `docs/DATA_CONTRACT.md` (4225 bytes)
|
||||
- `docs/DECISIONS.md` (13018 bytes)
|
||||
- `docs/FILE_TAXONOMY.md` (5864 bytes)
|
||||
- `docs/GPT_PLAN_LOCALIZATION_PROTOCOL.md` (3185 bytes)
|
||||
- `docs/HANDOFF_TEMPLATE.md` (527 bytes)
|
||||
- `docs/INDEX_MAINTENANCE_PROTOCOL.md` (3539 bytes)
|
||||
- `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md` (3319 bytes)
|
||||
- `docs/KNOWLEDGE_ASSET_RULES.md` (3357 bytes)
|
||||
- `docs/MODEL_CARD_CONTRACT.md` (2692 bytes)
|
||||
- `docs/MODEL_EXTRACTION_RULES.md` (5596 bytes)
|
||||
- `docs/MODEL_EXTRACTION_WORKFLOW.md` (2940 bytes)
|
||||
- `docs/NON_GOALS.md` (802 bytes)
|
||||
- `docs/PROJECT_BRIEF.md` (2832 bytes)
|
||||
- `docs/QPI_CONTEXTUAL_ROUTING_RULES.md` (6769 bytes)
|
||||
- `docs/WORKFLOW.md` (7121 bytes)
|
||||
- `docs/model_case_preprocessing/README.md` (651 bytes)
|
||||
- `docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md` (4210 bytes)
|
||||
- `docs/model_case_preprocessing/qpi/README.md` (398 bytes)
|
||||
- `docs/superpowers/plans/2026-06-16-model-extraction-contract-and-workflow.md` (25201 bytes)
|
||||
- `docs/superpowers/plans/2026-06-16-project-initialization.md` (4262 bytes)
|
||||
- `docs/superpowers/plans/2026-06-17-contract-hardening-selector-calibration.md` (4352 bytes)
|
||||
- `docs/superpowers/plans/2026-06-18-round04-1-selector-rule-patch.md` (5170 bytes)
|
||||
- `docs/superpowers/plans/2026-06-18-round04-blind-routing-evaluation.md` (6590 bytes)
|
||||
- `knowledge_assets/00_用户背景与产品上下文.md` (1550 bytes)
|
||||
- `knowledge_assets/01_核心模型地图.md` (1643 bytes)
|
||||
- `knowledge_assets/02_模型卡结构规范.md` (1514 bytes)
|
||||
- `knowledge_assets/03_核心模型抽取样板.md` (2271 bytes)
|
||||
- `knowledge_assets/06_模型稳固性评级规则.md` (1473 bytes)
|
||||
- `knowledge_assets/07_产品规划过程记录.md` (1813 bytes)
|
||||
- `knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md` (9052 bytes)
|
||||
- `knowledge_assets/09_数据治理与模型调用机制说明.md` (18643 bytes)
|
||||
- `knowledge_assets/10_本地CCRA评审机制说明.md` (5415 bytes)
|
||||
- `knowledge_assets/README.md` (1382 bytes)
|
||||
- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md` (7956 bytes)
|
||||
- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md` (29841 bytes)
|
||||
- `selector/README.md` (3310 bytes)
|
||||
- `selector/qpi_case_digests.json` (108415 bytes)
|
||||
- `selector/round04_blind_inputs.json` (12470 bytes)
|
||||
- `selector/selector_calibration_inputs.json` (42665 bytes)
|
||||
- `selector/selector_examples.json` (2087 bytes)
|
||||
- `selector/selector_rules.json` (7042 bytes)
|
||||
- `tests/README.md` (846 bytes)
|
||||
- `tests/__pycache__/test_card_contract.cpython-310.pyc` (1771 bytes)
|
||||
- `tests/__pycache__/test_rebuild_indexes.cpython-310.pyc` (3739 bytes)
|
||||
- `tests/__pycache__/test_round04_blind_routing.cpython-310.pyc` (3426 bytes)
|
||||
- `tests/__pycache__/test_round04_post_patch_verification.cpython-310.pyc` (2420 bytes)
|
||||
- `tests/__pycache__/test_validate_model_library.cpython-310.pyc` (16887 bytes)
|
||||
- `tests/intellectual_archaeology.regression.json` (16743 bytes)
|
||||
- `tests/qpi.regression.json` (79553 bytes)
|
||||
- `tests/regression_cases.json` (99522 bytes)
|
||||
- `tests/regression_index.json` (797 bytes)
|
||||
- `tests/test_card_contract.py` (1255 bytes)
|
||||
- `tests/test_rebuild_indexes.py` (3291 bytes)
|
||||
- `tests/test_round04_blind_routing.py` (2680 bytes)
|
||||
- `tests/test_round04_post_patch_verification.py` (1807 bytes)
|
||||
- `tests/test_validate_model_library.py` (23038 bytes)
|
||||
|
||||
## Files Excluded
|
||||
|
||||
- None
|
||||
|
||||
## Important Reports
|
||||
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/BUNDLE_FILE_MANIFEST_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/raw_file_list_04.1.txt`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/optional_raw_changed_files_04.zip`
|
||||
- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md`
|
||||
- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
|
||||
|
||||
## Test Or Validation Outputs
|
||||
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json`
|
||||
- `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md`
|
||||
- `tests/README.md`
|
||||
- `tests/__pycache__/test_card_contract.cpython-310.pyc`
|
||||
- `tests/__pycache__/test_rebuild_indexes.cpython-310.pyc`
|
||||
- `tests/__pycache__/test_round04_blind_routing.cpython-310.pyc`
|
||||
- `tests/__pycache__/test_round04_post_patch_verification.cpython-310.pyc`
|
||||
- `tests/__pycache__/test_validate_model_library.cpython-310.pyc`
|
||||
- `tests/intellectual_archaeology.regression.json`
|
||||
- `tests/qpi.regression.json`
|
||||
- `tests/regression_cases.json`
|
||||
- `tests/regression_index.json`
|
||||
- `tests/test_card_contract.py`
|
||||
- `tests/test_rebuild_indexes.py`
|
||||
- `tests/test_round04_blind_routing.py`
|
||||
- `tests/test_round04_post_patch_verification.py`
|
||||
- `tests/test_validate_model_library.py`
|
||||
|
||||
## Diff Or Changed File References
|
||||
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/optional_raw_changed_files_04.zip`
|
||||
|
||||
## Prior Decision References
|
||||
|
||||
- `docs/DECISIONS.md`
|
||||
|
||||
## Known Non Goals
|
||||
|
||||
- `Do not decide Owner approval.`
|
||||
- `Do not replace Web CCRA final review.`
|
||||
- `Do not promote lifecycle status.`
|
||||
- `Do not modify selector rules, model cards, model JSON, regression cases, or review bundles.`
|
||||
- `Do not treat this pilot as Round 05 acceptance.`
|
||||
|
||||
## Open Questions For Reviewer Or Agent
|
||||
|
||||
- `Was a real child session invoked?`
|
||||
- `Can the child session be resumed?`
|
||||
- `Does the report quality reach Web CCRA level?`
|
||||
- `Which runtime, prompt, helper, or report-template adjustments are needed before Round 05?`
|
||||
|
||||
## Blocking Errors
|
||||
|
||||
- None
|
||||
|
||||
## Machine Readable Manifest
|
||||
|
||||
- `review-file-manifest.json`
|
||||
|
|
@ -0,0 +1,517 @@
|
|||
{
|
||||
"review_id": "round-04-pilot-01",
|
||||
"context_profile": "ccra-local-review",
|
||||
"project_root": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
|
||||
"source_roots": [
|
||||
"README.md",
|
||||
"AGENTS.md",
|
||||
"PROJECTS.md",
|
||||
"knowledge_assets",
|
||||
"docs",
|
||||
"reports/Round04_blind_routing_evaluation_report_2026-06-18.md",
|
||||
"reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md",
|
||||
"selector",
|
||||
"tests",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
|
||||
],
|
||||
"missing_source_roots": [],
|
||||
"files_included": [
|
||||
{
|
||||
"path": "AGENTS.md",
|
||||
"size_bytes": 8063,
|
||||
"source_root": "AGENTS.md"
|
||||
},
|
||||
{
|
||||
"path": "PROJECTS.md",
|
||||
"size_bytes": 6784,
|
||||
"source_root": "PROJECTS.md"
|
||||
},
|
||||
{
|
||||
"path": "README.md",
|
||||
"size_bytes": 7915,
|
||||
"source_root": "README.md"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.1.md",
|
||||
"size_bytes": 2245,
|
||||
"source_root": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md",
|
||||
"size_bytes": 2223,
|
||||
"source_root": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md",
|
||||
"size_bytes": 1124,
|
||||
"source_root": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md",
|
||||
"size_bytes": 7956,
|
||||
"source_root": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md",
|
||||
"size_bytes": 3364,
|
||||
"source_root": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/BUNDLE_FILE_MANIFEST_04.1.md",
|
||||
"size_bytes": 2171,
|
||||
"source_root": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip",
|
||||
"size_bytes": 207917,
|
||||
"source_root": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json",
|
||||
"size_bytes": 1921,
|
||||
"source_root": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/raw_file_list_04.1.txt",
|
||||
"size_bytes": 1337,
|
||||
"source_root": "ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md",
|
||||
"size_bytes": 1476,
|
||||
"source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md",
|
||||
"size_bytes": 2211,
|
||||
"source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md",
|
||||
"size_bytes": 1495,
|
||||
"source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md",
|
||||
"size_bytes": 29841,
|
||||
"source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md",
|
||||
"size_bytes": 1614,
|
||||
"source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md",
|
||||
"size_bytes": 1710,
|
||||
"source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/optional_raw_changed_files_04.zip",
|
||||
"size_bytes": 176893,
|
||||
"source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
|
||||
},
|
||||
{
|
||||
"path": "docs/CHATGPT_HANDOFF_RULES.md",
|
||||
"size_bytes": 2175,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/CONTENT_STABILIZATION_PROTOCOL.md",
|
||||
"size_bytes": 2331,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/DATA_CONTRACT.md",
|
||||
"size_bytes": 4225,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/DECISIONS.md",
|
||||
"size_bytes": 13018,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/FILE_TAXONOMY.md",
|
||||
"size_bytes": 5864,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/GPT_PLAN_LOCALIZATION_PROTOCOL.md",
|
||||
"size_bytes": 3185,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/HANDOFF_TEMPLATE.md",
|
||||
"size_bytes": 527,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/INDEX_MAINTENANCE_PROTOCOL.md",
|
||||
"size_bytes": 3539,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md",
|
||||
"size_bytes": 3319,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/KNOWLEDGE_ASSET_RULES.md",
|
||||
"size_bytes": 3357,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/MODEL_CARD_CONTRACT.md",
|
||||
"size_bytes": 2692,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/MODEL_EXTRACTION_RULES.md",
|
||||
"size_bytes": 5596,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/MODEL_EXTRACTION_WORKFLOW.md",
|
||||
"size_bytes": 2940,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/NON_GOALS.md",
|
||||
"size_bytes": 802,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/PROJECT_BRIEF.md",
|
||||
"size_bytes": 2832,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/QPI_CONTEXTUAL_ROUTING_RULES.md",
|
||||
"size_bytes": 6769,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/WORKFLOW.md",
|
||||
"size_bytes": 7121,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/model_case_preprocessing/README.md",
|
||||
"size_bytes": 651,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md",
|
||||
"size_bytes": 4210,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/model_case_preprocessing/qpi/README.md",
|
||||
"size_bytes": 398,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/superpowers/plans/2026-06-16-model-extraction-contract-and-workflow.md",
|
||||
"size_bytes": 25201,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/superpowers/plans/2026-06-16-project-initialization.md",
|
||||
"size_bytes": 4262,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/superpowers/plans/2026-06-17-contract-hardening-selector-calibration.md",
|
||||
"size_bytes": 4352,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/superpowers/plans/2026-06-18-round04-1-selector-rule-patch.md",
|
||||
"size_bytes": 5170,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "docs/superpowers/plans/2026-06-18-round04-blind-routing-evaluation.md",
|
||||
"size_bytes": 6590,
|
||||
"source_root": "docs"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/00_用户背景与产品上下文.md",
|
||||
"size_bytes": 1550,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/01_核心模型地图.md",
|
||||
"size_bytes": 1643,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/02_模型卡结构规范.md",
|
||||
"size_bytes": 1514,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/03_核心模型抽取样板.md",
|
||||
"size_bytes": 2271,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/06_模型稳固性评级规则.md",
|
||||
"size_bytes": 1473,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/07_产品规划过程记录.md",
|
||||
"size_bytes": 1813,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md",
|
||||
"size_bytes": 9052,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/09_数据治理与模型调用机制说明.md",
|
||||
"size_bytes": 18643,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/10_本地CCRA评审机制说明.md",
|
||||
"size_bytes": 5415,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/README.md",
|
||||
"size_bytes": 1382,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md",
|
||||
"size_bytes": 7956,
|
||||
"source_root": "reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md"
|
||||
},
|
||||
{
|
||||
"path": "reports/Round04_blind_routing_evaluation_report_2026-06-18.md",
|
||||
"size_bytes": 29841,
|
||||
"source_root": "reports/Round04_blind_routing_evaluation_report_2026-06-18.md"
|
||||
},
|
||||
{
|
||||
"path": "selector/README.md",
|
||||
"size_bytes": 3310,
|
||||
"source_root": "selector"
|
||||
},
|
||||
{
|
||||
"path": "selector/qpi_case_digests.json",
|
||||
"size_bytes": 108415,
|
||||
"source_root": "selector"
|
||||
},
|
||||
{
|
||||
"path": "selector/round04_blind_inputs.json",
|
||||
"size_bytes": 12470,
|
||||
"source_root": "selector"
|
||||
},
|
||||
{
|
||||
"path": "selector/selector_calibration_inputs.json",
|
||||
"size_bytes": 42665,
|
||||
"source_root": "selector"
|
||||
},
|
||||
{
|
||||
"path": "selector/selector_examples.json",
|
||||
"size_bytes": 2087,
|
||||
"source_root": "selector"
|
||||
},
|
||||
{
|
||||
"path": "selector/selector_rules.json",
|
||||
"size_bytes": 7042,
|
||||
"source_root": "selector"
|
||||
},
|
||||
{
|
||||
"path": "tests/README.md",
|
||||
"size_bytes": 846,
|
||||
"source_root": "tests"
|
||||
},
|
||||
{
|
||||
"path": "tests/__pycache__/test_card_contract.cpython-310.pyc",
|
||||
"size_bytes": 1771,
|
||||
"source_root": "tests"
|
||||
},
|
||||
{
|
||||
"path": "tests/__pycache__/test_rebuild_indexes.cpython-310.pyc",
|
||||
"size_bytes": 3739,
|
||||
"source_root": "tests"
|
||||
},
|
||||
{
|
||||
"path": "tests/__pycache__/test_round04_blind_routing.cpython-310.pyc",
|
||||
"size_bytes": 3426,
|
||||
"source_root": "tests"
|
||||
},
|
||||
{
|
||||
"path": "tests/__pycache__/test_round04_post_patch_verification.cpython-310.pyc",
|
||||
"size_bytes": 2420,
|
||||
"source_root": "tests"
|
||||
},
|
||||
{
|
||||
"path": "tests/__pycache__/test_validate_model_library.cpython-310.pyc",
|
||||
"size_bytes": 16887,
|
||||
"source_root": "tests"
|
||||
},
|
||||
{
|
||||
"path": "tests/intellectual_archaeology.regression.json",
|
||||
"size_bytes": 16743,
|
||||
"source_root": "tests"
|
||||
},
|
||||
{
|
||||
"path": "tests/qpi.regression.json",
|
||||
"size_bytes": 79553,
|
||||
"source_root": "tests"
|
||||
},
|
||||
{
|
||||
"path": "tests/regression_cases.json",
|
||||
"size_bytes": 99522,
|
||||
"source_root": "tests"
|
||||
},
|
||||
{
|
||||
"path": "tests/regression_index.json",
|
||||
"size_bytes": 797,
|
||||
"source_root": "tests"
|
||||
},
|
||||
{
|
||||
"path": "tests/test_card_contract.py",
|
||||
"size_bytes": 1255,
|
||||
"source_root": "tests"
|
||||
},
|
||||
{
|
||||
"path": "tests/test_rebuild_indexes.py",
|
||||
"size_bytes": 3291,
|
||||
"source_root": "tests"
|
||||
},
|
||||
{
|
||||
"path": "tests/test_round04_blind_routing.py",
|
||||
"size_bytes": 2680,
|
||||
"source_root": "tests"
|
||||
},
|
||||
{
|
||||
"path": "tests/test_round04_post_patch_verification.py",
|
||||
"size_bytes": 1807,
|
||||
"source_root": "tests"
|
||||
},
|
||||
{
|
||||
"path": "tests/test_validate_model_library.py",
|
||||
"size_bytes": 23038,
|
||||
"source_root": "tests"
|
||||
}
|
||||
],
|
||||
"files_excluded": [],
|
||||
"important_reports": [
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.1.md",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/BUNDLE_FILE_MANIFEST_04.1.md",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/raw_file_list_04.1.txt",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/optional_raw_changed_files_04.zip",
|
||||
"reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md",
|
||||
"reports/Round04_blind_routing_evaluation_report_2026-06-18.md"
|
||||
],
|
||||
"test_or_validation_outputs": [
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json",
|
||||
"docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md",
|
||||
"tests/README.md",
|
||||
"tests/__pycache__/test_card_contract.cpython-310.pyc",
|
||||
"tests/__pycache__/test_rebuild_indexes.cpython-310.pyc",
|
||||
"tests/__pycache__/test_round04_blind_routing.cpython-310.pyc",
|
||||
"tests/__pycache__/test_round04_post_patch_verification.cpython-310.pyc",
|
||||
"tests/__pycache__/test_validate_model_library.cpython-310.pyc",
|
||||
"tests/intellectual_archaeology.regression.json",
|
||||
"tests/qpi.regression.json",
|
||||
"tests/regression_cases.json",
|
||||
"tests/regression_index.json",
|
||||
"tests/test_card_contract.py",
|
||||
"tests/test_rebuild_indexes.py",
|
||||
"tests/test_round04_blind_routing.py",
|
||||
"tests/test_round04_post_patch_verification.py",
|
||||
"tests/test_validate_model_library.py"
|
||||
],
|
||||
"diff_or_changed_file_references": [
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/optional_raw_changed_files_04.zip"
|
||||
],
|
||||
"prior_decision_references": [
|
||||
"docs/DECISIONS.md"
|
||||
],
|
||||
"known_non_goals": [
|
||||
"Do not decide Owner approval.",
|
||||
"Do not replace Web CCRA final review.",
|
||||
"Do not promote lifecycle status.",
|
||||
"Do not modify selector rules, model cards, model JSON, regression cases, or review bundles.",
|
||||
"Do not treat this pilot as Round 05 acceptance."
|
||||
],
|
||||
"open_questions_for_reviewer_or_agent": [
|
||||
"Was a real child session invoked?",
|
||||
"Can the child session be resumed?",
|
||||
"Does the report quality reach Web CCRA level?",
|
||||
"Which runtime, prompt, helper, or report-template adjustments are needed before Round 05?"
|
||||
],
|
||||
"metadata": {
|
||||
"review_id": "round-04-pilot-01",
|
||||
"project_id": "the-mindscape-of-bro-tsong",
|
||||
"review_round": "round-04",
|
||||
"local_pass": "pilot-01",
|
||||
"runtime_id": "ccra-local-review",
|
||||
"runtime_version": "0.1.0",
|
||||
"agent_id": "ccra-local-reviewer",
|
||||
"agent_version": "0.1.0",
|
||||
"knowledge_base_path": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\knowledge_assets",
|
||||
"review_goal": "Use existing Round 04 blind routing evaluation material to pilot Local CCRA invocation, persistence, and report quality.",
|
||||
"primary_question": "Does Local CCRA produce Web CCRA-level review quality when it can inspect the full local Round 04 evidence set?",
|
||||
"scope_statement": "Review Round 04 blind routing evaluation evidence as a historical pilot. Focus on review quality, evidence coverage, non-target behavior awareness, lifecycle/scope discipline, and readiness gaps for future Round 05 use.",
|
||||
"non_goals": [
|
||||
"Do not decide Owner approval.",
|
||||
"Do not replace Web CCRA final review.",
|
||||
"Do not promote lifecycle status.",
|
||||
"Do not modify selector rules, model cards, model JSON, regression cases, or review bundles.",
|
||||
"Do not treat this pilot as Round 05 acceptance."
|
||||
],
|
||||
"open_questions": [
|
||||
"Was a real child session invoked?",
|
||||
"Can the child session be resumed?",
|
||||
"Does the report quality reach Web CCRA level?",
|
||||
"Which runtime, prompt, helper, or report-template adjustments are needed before Round 05?"
|
||||
],
|
||||
"target_reviewer": "ccra-local-reviewer",
|
||||
"review_bundle_paths": [
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
|
||||
],
|
||||
"web_final_review_policy": "owner_must_approve_inclusion",
|
||||
"output_report_path": "local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md",
|
||||
"returned_output_path": "local_ccra_reviews/round-04/pilot-01/returned-output.md",
|
||||
"created_at": "2026-06-19"
|
||||
},
|
||||
"blocking_errors": [],
|
||||
"machine_readable_summary": {
|
||||
"status": "PASS",
|
||||
"source_roots_count": 11,
|
||||
"missing_source_roots_count": 0,
|
||||
"files_included_count": 77,
|
||||
"files_excluded_count": 0,
|
||||
"important_reports_count": 18,
|
||||
"validation_outputs_count": 18,
|
||||
"diff_references_count": 4,
|
||||
"prior_decisions_count": 1,
|
||||
"blocking_error_count": 0
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,35 @@
|
|||
{
|
||||
"review_id": "round-04-pilot-01",
|
||||
"project_id": "the-mindscape-of-bro-tsong",
|
||||
"review_round": "round-04",
|
||||
"local_pass": "pilot-01",
|
||||
"runtime_id": "ccra-local-review",
|
||||
"runtime_version": "0.1.0",
|
||||
"agent_id": "ccra-local-reviewer",
|
||||
"agent_version": "0.1.0",
|
||||
"knowledge_base_path": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\knowledge_assets",
|
||||
"review_goal": "Use existing Round 04 blind routing evaluation material to pilot Local CCRA invocation, persistence, and report quality.",
|
||||
"primary_question": "Does Local CCRA produce Web CCRA-level review quality when it can inspect the full local Round 04 evidence set?",
|
||||
"scope_statement": "Review Round 04 blind routing evaluation evidence as a historical pilot. Focus on review quality, evidence coverage, non-target behavior awareness, lifecycle/scope discipline, and readiness gaps for future Round 05 use.",
|
||||
"non_goals": [
|
||||
"Do not decide Owner approval.",
|
||||
"Do not replace Web CCRA final review.",
|
||||
"Do not promote lifecycle status.",
|
||||
"Do not modify selector rules, model cards, model JSON, regression cases, or review bundles.",
|
||||
"Do not treat this pilot as Round 05 acceptance."
|
||||
],
|
||||
"open_questions": [
|
||||
"Was a real child session invoked?",
|
||||
"Can the child session be resumed?",
|
||||
"Does the report quality reach Web CCRA level?",
|
||||
"Which runtime, prompt, helper, or report-template adjustments are needed before Round 05?"
|
||||
],
|
||||
"target_reviewer": "ccra-local-reviewer",
|
||||
"review_bundle_paths": [
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
|
||||
],
|
||||
"web_final_review_policy": "owner_must_approve_inclusion",
|
||||
"output_report_path": "local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md",
|
||||
"returned_output_path": "local_ccra_reviews/round-04/pilot-01/returned-output.md",
|
||||
"created_at": "2026-06-19"
|
||||
}
|
||||
|
|
@ -0,0 +1,83 @@
|
|||
# Local CCRA Run Notes
|
||||
|
||||
## Run Identity
|
||||
|
||||
- review_round: round-04
|
||||
- local_pass: pilot-01
|
||||
- review_run_dir: `local_ccra_reviews/round-04/pilot-01`
|
||||
- runtime_id: ccra-local-review
|
||||
- runtime_version: 0.1.0
|
||||
- agent_id: ccra-local-reviewer
|
||||
- agent_version: 0.1.0
|
||||
- pilot_status: setup_in_progress
|
||||
|
||||
## Purpose
|
||||
|
||||
Historical pilot for Round 04 blind routing evaluation material.
|
||||
|
||||
This pilot checks:
|
||||
|
||||
1. Whether a real child session can be invoked.
|
||||
2. Whether the child session id can be recorded and reused.
|
||||
3. Whether Local CCRA report quality is comparable to Web CCRA feedback.
|
||||
4. Whether helper outputs improve file-first review without replacing reviewer judgment.
|
||||
|
||||
This pilot is not Round 05 acceptance.
|
||||
|
||||
## Source Evidence
|
||||
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/`
|
||||
- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
|
||||
- `selector/round04_blind_inputs.json`
|
||||
- `selector/selector_rules.json`
|
||||
- `selector/selector_calibration_inputs.json`
|
||||
- `tests/test_round04_blind_routing.py`
|
||||
- `tests/test_round04_post_patch_verification.py`
|
||||
|
||||
## Helper Commands
|
||||
|
||||
- `review-context-builder`: exit 0. Initial run completed before `knowledge_assets/` became required; rerun required with `--source-root knowledge_assets`.
|
||||
- `review-context-builder` rerun with `--source-root knowledge_assets`: exit 0. `review-context.md` and `review-file-manifest.json` now include required knowledge base files.
|
||||
- `review-bundle-audit`: exit 1. Report written; helper found blocking bundle-audit findings for the generic profile.
|
||||
- `regression-validation-gate-runner --mode dry_run`: exit 0. Report written; three gates declared and skipped as dry run.
|
||||
- `lifecycle-status-guard-scan`: exit 1. Report written; helper found blocking lifecycle/status candidates for reviewer judgment.
|
||||
|
||||
## Skipped Helpers
|
||||
|
||||
- `routing-behavior-diff-audit`: initially skipped unless before/after routing output files are supplied or identified.
|
||||
|
||||
## Dispatch Record
|
||||
|
||||
- carrier_type: codex_thread
|
||||
- invocation_mode: prompt_path_reference
|
||||
- child_session_id: 019edca7-48f3-79d3-be4a-550f4df0f13c
|
||||
- dispatch_status: dispatched
|
||||
|
||||
## Return Record
|
||||
|
||||
- report_path: `local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md`
|
||||
- returned_output_path: `local_ccra_reviews/round-04/pilot-01/returned-output.md`
|
||||
- return_status: returned
|
||||
- returned_at: 2026-06-19
|
||||
|
||||
## Observed Timing
|
||||
|
||||
- child_turn_duration_ms: 552064
|
||||
- child_turn_duration_human: about 9 minutes 12 seconds
|
||||
- timing_note: Within the expected mature-run 5-10 minute budget, and consistent with a first pilot that performed file-first evidence reading, helper-output inspection, and output self-checks.
|
||||
|
||||
## Web / Local Comparison
|
||||
|
||||
- comparison_path: `local_ccra_reviews/round-04/pilot-01/05_WEB_LOCAL_CCRA_COMPARISON.md`
|
||||
- comparison_scope: `2026-06-18产品交流-GPT.md` lines 1-214 versus `04_LOCAL_CCRA_REVIEW_REPORT.md`.
|
||||
- comparison_status: drafted
|
||||
|
||||
## CCPE Patch Request
|
||||
|
||||
- request_path: `requirements/ccpe/2026-06-19-ccra-local-reviewer-runtime-patch1.md`
|
||||
- request_status: drafted
|
||||
- requested_improvement: Make `ccra-local-reviewer` combine Web-style product diagnosis with Local CCRA full-file audit.
|
||||
|
||||
## Resume Notes
|
||||
|
||||
After dispatch, continue the same child session when comparing report quality or tuning `ccra-local-reviewer`.
|
||||
|
|
@ -0,0 +1,647 @@
|
|||
# Local CCRA Review Report
|
||||
|
||||
## 1. Return Metadata
|
||||
|
||||
- project_id: `the-mindscape-of-bro-tsong`
|
||||
- review_round: `round-04`
|
||||
- local_pass: `pilot-02`
|
||||
- turn_type: `review_turn`
|
||||
- runtime_id: `ccra-local-review`
|
||||
- runtime_version: `0.1.1`
|
||||
- agent_id: `ccra-local-reviewer`
|
||||
- agent_version: `0.1.1`
|
||||
- invocation_mode: `prompt_path_reference`
|
||||
- carrier_type: `codex_thread`
|
||||
- child_session_id: `019edcde-24be-7593-99b2-5cf014467340`
|
||||
- persistent_available: `yes_for_requested_followup_if_same_thread_is_resumed`
|
||||
- execution_status: `returned`
|
||||
- simulation_only: `false`
|
||||
- report_path: `local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md`
|
||||
- returned_output_path: `local_ccra_reviews/round-04/pilot-02/returned-output.md`
|
||||
- generated_at: `2026-06-19`
|
||||
|
||||
## 2. Review Scope
|
||||
|
||||
- primary_question: Can Patch 1 Local CCRA identify Round 04 product/routing issues with Web-style diagnosis while retaining local file-first audit strength?
|
||||
- scope_statement: Review initial Round 04 blind routing evidence only. Do not use Round 04.1 post-patch outcomes as this turn's judgment basis.
|
||||
- non_goals: no Owner approval, no Web CCRA replacement, no lifecycle promotion, no project file repair, no selector/model/regression edits, no Round 05 acceptance.
|
||||
- local_tuning_stage: `historical_pilot_patch1_retest`
|
||||
- web_final_review_target: `none_for_this_pilot`
|
||||
- knowledge_base_path: `C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets`
|
||||
- previous_turn_report_path: none
|
||||
|
||||
Important scope note: current project files such as `README.md`, `docs/DECISIONS.md`, `selector/README.md`, and `selector/selector_rules.json` contain later Round 04.1 language. They were read because the invocation packet required them, but this report does not use those post-patch statements as evidence that the initial Round 04 behavior was fixed or accepted.
|
||||
|
||||
## 3. Inputs Actually Received
|
||||
|
||||
- Invocation and run files:
|
||||
- `local_ccra_reviews/round-04/pilot-02/prompt-to-send.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/turn-prompts/review-turn.prompt.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/agent-invocation-packet.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/run-notes.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/review-metadata.json`
|
||||
- `local_ccra_reviews/round-04/pilot-02/review-context.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/review-file-manifest.json`
|
||||
- `local_ccra_reviews/round-04/pilot-02/owner-decision.md`
|
||||
- Required project knowledge base:
|
||||
- `knowledge_assets/`
|
||||
- Initial Round 04 evidence:
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/`
|
||||
- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
|
||||
- `reports/Round04_blind_input_candidates_2026-06-18.md`
|
||||
- `selector/round04_blind_inputs.json`
|
||||
- `selector/selector_rules.json`
|
||||
- `selector/README.md`
|
||||
- `tests/test_round04_blind_routing.py`
|
||||
- `scripts/run_round04_blind_routing.py`
|
||||
- Helper outputs:
|
||||
- `helper-outputs/bundle-audit.md`
|
||||
- `helper-outputs/bundle-audit.json`
|
||||
- `helper-outputs/gate-run-report.md`
|
||||
- `helper-outputs/gate-run-report.json`
|
||||
- `helper-outputs/lifecycle-status-guard-scan.md`
|
||||
- Missing or intentionally unavailable:
|
||||
- `routing-behavior-diff-audit` output: skipped by design because no after-patch evidence is allowed in this turn.
|
||||
- Executed gate logs: unavailable; gate runner was dry-run only.
|
||||
- Round 04.1 post-patch evidence: intentionally excluded.
|
||||
|
||||
## 4. Files Actually Read
|
||||
|
||||
```text
|
||||
- C:\Users\wangq\Documents\Codex\ccpe-system\agents\agent-specs\ccra-local-reviewer.agent.md
|
||||
purpose: Local CCRA reviewer role, source policy, report requirements, authority boundary
|
||||
- C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review.runtime.md
|
||||
purpose: runtime turn contract, helper usage, stop conditions
|
||||
- C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-report.template.md
|
||||
purpose: Patch 1 report template
|
||||
- C:\Users\wangq\Documents\Codex\ccpe-system\integrations\skills-vault\ccra-local-review-helpers.integration.md
|
||||
purpose: helper output confidence rules
|
||||
- README.md
|
||||
purpose: project identity and non-goals
|
||||
- AGENTS.md
|
||||
purpose: repository operating instructions
|
||||
- PROJECTS.md
|
||||
purpose: cross-repository authority boundaries
|
||||
- docs/WORKFLOW.md
|
||||
purpose: Local CCRA workflow and review bundle workflow
|
||||
- docs/DECISIONS.md
|
||||
purpose: selector, lifecycle, Local CCRA, and boundary decisions; post-04.1 statements excluded from review_turn judgment
|
||||
- docs/QPI_CONTEXTUAL_ROUTING_RULES.md
|
||||
purpose: QPI no-call, subject-context, issue/governance, and lifecycle boundary rules
|
||||
- docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md
|
||||
purpose: IA depth gate, no-call, and status boundary
|
||||
- knowledge_assets/README.md
|
||||
purpose: knowledge asset navigation
|
||||
- knowledge_assets/00_用户背景与产品上下文.md
|
||||
purpose: product boundary and source of truth map
|
||||
- knowledge_assets/01_核心模型地图.md
|
||||
purpose: QPI and IA status and routing relationship
|
||||
- knowledge_assets/02_模型卡结构规范.md
|
||||
purpose: model card structure and validation background
|
||||
- knowledge_assets/03_核心模型抽取样板.md
|
||||
purpose: model extraction and selector v0.2 background
|
||||
- knowledge_assets/06_模型稳固性评级规则.md
|
||||
purpose: stability/lifecycle guard
|
||||
- knowledge_assets/07_产品规划过程记录.md
|
||||
purpose: planning history and boundary
|
||||
- knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md
|
||||
purpose: CCRA quality gates and selector v0.2 principles
|
||||
- knowledge_assets/09_数据治理与模型调用机制说明.md
|
||||
purpose: selector/regression/calling mechanism
|
||||
- knowledge_assets/10_本地CCRA评审机制说明.md
|
||||
purpose: Local CCRA project-side process
|
||||
- ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md
|
||||
purpose: Round 04 brief
|
||||
- ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md
|
||||
purpose: Round 04 scope and non-goals
|
||||
- ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md
|
||||
purpose: frozen blind input set summary
|
||||
- ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md
|
||||
purpose: initial Round 04 observed routing behavior
|
||||
- ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md
|
||||
purpose: requested review questions
|
||||
- ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md
|
||||
purpose: bundle manifest and optional zip scope
|
||||
- reports/Round04_blind_input_candidates_2026-06-18.md
|
||||
purpose: candidate intent and coverage labels
|
||||
- reports/Round04_blind_routing_evaluation_report_2026-06-18.md
|
||||
purpose: direct initial routing evidence
|
||||
- selector/round04_blind_inputs.json
|
||||
purpose: frozen blind input metadata without expected labels
|
||||
- selector/selector_rules.json
|
||||
purpose: required read; not used as initial Round 04 behavior evidence where it reflects later changes
|
||||
- selector/README.md
|
||||
purpose: selector contract; post-04.1 statements excluded from review_turn judgment
|
||||
- tests/test_round04_blind_routing.py
|
||||
purpose: initial runner test surface
|
||||
- scripts/run_round04_blind_routing.py
|
||||
purpose: report generation and blind input evaluation mechanics
|
||||
- local_ccra_reviews/round-04/pilot-02/helper-outputs/*
|
||||
purpose: helper evidence and confidence assessment
|
||||
```
|
||||
|
||||
## 5. Automation Outputs Used
|
||||
|
||||
```text
|
||||
- helper_id: review-context-builder
|
||||
output_path: local_ccra_reviews/round-04/pilot-02/review-context.md; review-file-manifest.json
|
||||
status: available
|
||||
how_used: navigation index only; direct source files were still read
|
||||
- helper_id: review-bundle-audit
|
||||
output_path: local_ccra_reviews/round-04/pilot-02/helper-outputs/bundle-audit.md; bundle-audit.json
|
||||
status: failed_profile_mismatch
|
||||
how_used: evidence that generic profile did not recognize the versioned bundle manifest; not accepted as automatic bundle failure
|
||||
- helper_id: regression-validation-gate-runner
|
||||
output_path: local_ccra_reviews/round-04/pilot-02/helper-outputs/gate-run-report.md; gate-run-report.json
|
||||
status: dry_run
|
||||
how_used: evidence that gates are declared, not evidence that gates passed
|
||||
- helper_id: lifecycle-status-guard-scan
|
||||
output_path: local_ccra_reviews/round-04/pilot-02/helper-outputs/lifecycle-status-guard-scan.md
|
||||
status: failed_broad_scan
|
||||
how_used: lifecycle overclaim candidate list only; many findings are outside the initial Round 04 scope
|
||||
- helper_id: routing-behavior-diff-audit
|
||||
output_path: none
|
||||
status: skipped
|
||||
how_used: not applicable for review_turn because after-patch evidence is intentionally excluded
|
||||
```
|
||||
|
||||
## 6. Executive Summary
|
||||
|
||||
Review result: `needs_more_local_tuning`.
|
||||
|
||||
Final action recommendation: `fix_now`.
|
||||
|
||||
Patch 1 Local CCRA can identify the important Round 04 routing issues with file-first evidence. The clearest initial Round 04 failures are not model-content failures and not LLM-understanding failures. They are selector rule-boundary failures:
|
||||
|
||||
- direct transformation / translation requests can be misread because payload complexity words such as `模型` leak into routing;
|
||||
- explicit IA refusal variants are not all enforced as model-level hard exclusions;
|
||||
- depth-limiting phrases such as `不要展开` and `不要深入分析` can incorrectly suppress lightweight QPI requests for `主导稀缺` or `缺信息 / 缺路径 / 缺共识`.
|
||||
|
||||
Initial Round 04 evidence is enough to open a scoped selector patch requirement. It is not enough to claim Web final readiness, Round 05 readiness, lifecycle promotion, or product acceptance. A second `planning_turn` is needed to specify the post-patch verification package and submitted-material requirements.
|
||||
|
||||
## 7. Issue Mechanism Diagnosis
|
||||
|
||||
### Issue ID: R04-LCR-001
|
||||
|
||||
- Case / Material: `R04-BI-002`
|
||||
- What failed: pure translation request selected `qpi`.
|
||||
- Why it failed: the selector treated payload word `模型` as a complexity signal even though the instruction was direct translation. This is an instruction/payload boundary failure, not an indication that QPI should classify the user's problem frame.
|
||||
- Why it is not a different failure category: this is not model-content failure, because QPI did not generate content. It is not LLM understanding failure, because the selector is explicitly rule-based and no LLM is called. It is not an IA issue because IA was rejected.
|
||||
- Failure category: `rule_boundary_problem`
|
||||
- Selector-specific type: `no-call false negative`; `QPI over-selection`; `rule-based selector failure`
|
||||
- Evidence:
|
||||
- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md` records `R04-BI-002` selected `qpi` with reason `complexity signal: 模型`.
|
||||
- `selector/round04_blind_inputs.json` states the case was included to test pure translation as no-call.
|
||||
- `docs/QPI_CONTEXTUAL_ROUTING_RULES.md` says translation should be `classification_scope=no_call`.
|
||||
|
||||
### Issue ID: R04-LCR-002
|
||||
|
||||
- Case / Material: `R04-BI-024`
|
||||
- What failed: explicit `不要进入思想考古` still selected `intellectual_archaeology`.
|
||||
- Why it failed: the model-level exclusion surface did not cover this refusal variant in the initial behavior. The selector allowed the model name and boundary/责任 complexity signals to overcome the user's explicit refusal.
|
||||
- Why it is not a different failure category: this is not a QPI-before-IA gate failure alone, because the user explicitly refused IA. It is not a model-content failure, because IA was only routed, not executed.
|
||||
- Failure category: `rule_boundary_problem`
|
||||
- Selector-specific type: `model-level exclusion failure`; `IA over-selection`
|
||||
- Evidence:
|
||||
- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md` records both `intellectual_archaeology` and `qpi` selected for `R04-BI-024`.
|
||||
- `reports/Round04_blind_input_candidates_2026-06-18.md` states this case tests model-level hard exclusion for IA while preserving QPI-like routing.
|
||||
- `selector/README.md` describes explicit model refusal as a model-level hard exclusion; later Round 04.1 language in the same file is excluded as proof of repair.
|
||||
|
||||
### Issue ID: R04-LCR-003
|
||||
|
||||
- Case / Material: `R04-BI-035`, `R04-BI-036`, same-class boundary `R04-BI-022`
|
||||
- What failed: depth-limiting language caused global no-call even when the user asked for lightweight QPI classification.
|
||||
- Why it failed: global hard no-call matched `不要深入分析` or `不要展开` before QPI-limited intent was recognized. The selector conflated "do not go deep" with "do not do lightweight problem definition".
|
||||
- Why it is not a different failure category: this is not user refusal of QPI. The requested action is exactly QPI-shaped: identify dominant scarcity or choose among missing information/path/consensus. It is also not IA under-selection, because IA should remain rejected.
|
||||
- Failure category: `rule_boundary_problem`
|
||||
- Selector-specific type: `depth-limiting override failure`; `no-call false positive`; `QPI under-selection`
|
||||
- Evidence:
|
||||
- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md` records `R04-BI-035` and `R04-BI-036` as hard no-call with QPI rejected.
|
||||
- `selector/round04_blind_inputs.json` states these cases test QPI-limited routing while rejecting deeper modeling.
|
||||
- `docs/QPI_CONTEXTUAL_ROUTING_RULES.md` defines QPI as front-routing / scarcity framing and does not require deep analysis.
|
||||
|
||||
### Issue ID: R04-LCR-004
|
||||
|
||||
- Case / Material: governance and capacity cases `R04-BI-010` through `R04-BI-017`
|
||||
- What failed: several plausible QPI problem/issue inputs no-called because no explicit positive QPI phrase appeared.
|
||||
- Why it failed: the initial selector appears too dependent on lexical QPI gate phrases such as `问题`, `缺路径`, or `缺共识`, and under-detects semantically clear governance, responsibility, capacity, or path scarcity. This is a product-routing risk, but not all such cases should be patched mechanically.
|
||||
- Why it is not a different failure category: coverage labels are not answer keys, and some statements lack an explicit user request. The correct behavior may be QPI, clarification, or low-confidence provisional routing depending on Owner policy.
|
||||
- Failure category: `product_routing_problem`
|
||||
- Selector-specific type: `possible QPI under-selection`; `calibration boundary`
|
||||
- Evidence:
|
||||
- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md` records no-call for `R04-BI-010`, `011`, `012`, `013`, `014`, `015`, and `017`; `R04-BI-016` selected QPI because it contains explicit `问题`.
|
||||
- `docs/QPI_CONTEXTUAL_ROUTING_RULES.md` states issue weight rises around responsibility, authority, role boundary, governance, and consensus load.
|
||||
- `reports/Round04_blind_input_candidates_2026-06-18.md` includes these cases to test governance, responsibility, consensus, resource, and path scarcity.
|
||||
|
||||
### Issue ID: R04-LCR-005
|
||||
|
||||
- Case / Material: likely IA and model extraction cases `R04-BI-018`, `R04-BI-026`, `R04-BI-027`, `R04-BI-038`
|
||||
- What failed: several likely depth-modeling inputs selected only QPI and rejected IA.
|
||||
- Why it failed: the initial IA heavy-depth gate is conservative and depends on a narrow set of lexical heavy signals. That protects against IA over-selection but may under-select natural model extraction or deep mechanism requests that avoid exact trigger phrases.
|
||||
- Why it is not a different failure category: not all likely IA cases should become immediate IA positives. Some may need QPI first. Some may need Owner/Web calibration on whether IA should be directly selected or only recommended after QPI.
|
||||
- Failure category: `product_routing_problem`
|
||||
- Selector-specific type: `possible IA under-selection`; `QPI-before-IA calibration`
|
||||
- Evidence:
|
||||
- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md` records QPI-only routing for the listed cases.
|
||||
- `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md` supports IA when repeated patterns, core mechanisms, assumptions, or action boundaries require deeper modeling, while also warning IA is not default.
|
||||
- `reports/Round04_blind_input_candidates_2026-06-18.md` marks `R04-BI-026` as a high-value natural boundary sample and `R04-BI-018` as a positive control.
|
||||
|
||||
## 8. Patch Scope Judgment
|
||||
|
||||
```text
|
||||
must_fix_cases:
|
||||
- case_id: R04-BI-002
|
||||
reason: direct translation should no-call even when payload contains model-library vocabulary.
|
||||
required_evidence: targeted before/after result plus frozen-pool rerun showing no new direct-execution regressions.
|
||||
- case_id: R04-BI-024
|
||||
reason: explicit IA refusal must hard-exclude IA while preserving QPI if the remaining request is QPI-shaped.
|
||||
required_evidence: targeted before/after result plus regression coverage for IA refusal variants.
|
||||
- case_id: R04-BI-035
|
||||
reason: depth-limiting language paired with dominant-scarcity request should allow lightweight QPI and reject IA.
|
||||
required_evidence: targeted before/after result plus regression coverage.
|
||||
- case_id: R04-BI-036
|
||||
reason: depth-limiting language paired with缺信息/缺路径/缺共识 should allow QPI and reject IA.
|
||||
required_evidence: targeted before/after result plus regression coverage.
|
||||
|
||||
same_class_boundary_cases:
|
||||
- case_id: R04-BI-022
|
||||
reason: same depth-limiting plus QPI-limited intent mechanism as R04-BI-035/036; initial behavior is no-call.
|
||||
patch_with_current_round: yes, if Owner accepts "主导稀缺" as sufficient QPI-limited intent despite limited object context.
|
||||
- case_id: R04-BI-018
|
||||
reason: model-extraction positive control selected QPI only; IA direct-selection policy needs calibration.
|
||||
patch_with_current_round: no, unless Owner defines model extraction as immediate IA route.
|
||||
- case_id: R04-BI-026/R04-BI-027/R04-BI-038
|
||||
reason: natural IA boundary examples may need broader IA signals, but broadening can create over-selection.
|
||||
patch_with_current_round: no; use calibration first.
|
||||
- case_id: R04-BI-010 through R04-BI-017
|
||||
reason: governance/capacity language may be QPI-relevant without explicit QPI terms.
|
||||
patch_with_current_round: no; define provisional QPI vs clarification policy first.
|
||||
|
||||
calibration_only_cases:
|
||||
- case_id: R04-BI-010/R04-BI-011/R04-BI-012/R04-BI-013
|
||||
reason: likely issue/governance QPI cases, but no explicit user request. Owner should decide whether descriptive statements trigger QPI, clarification, or no-call.
|
||||
- case_id: R04-BI-014/R04-BI-015/R04-BI-017
|
||||
reason: capacity/path scarcity semantics should be calibrated before adding broad keywords.
|
||||
- case_id: R04-BI-018/R04-BI-026/R04-BI-027/R04-BI-038
|
||||
reason: IA under-selection risk needs policy on direct IA vs QPI-first.
|
||||
- case_id: R04-BI-030
|
||||
reason: "老问题" is prior-context dependent; QPI selection may be acceptable only as low-confidence/provisional.
|
||||
- case_id: R04-BI-037
|
||||
reason: "如何提高这个账号的流量" maps to the QPI insufficient-context example but may require clarification instead of no-call or confident QPI.
|
||||
|
||||
explicitly_not_patched:
|
||||
- case_id: R04-BI-001/R04-BI-003/R04-BI-004/R04-BI-005/R04-BI-031/R04-BI-032/R04-BI-033
|
||||
reason: initial no-call behavior is consistent with direct fact, rewrite, formatting, tool how-to, and word-meaning no-call rules.
|
||||
- case_id: R04-BI-021
|
||||
reason: initial behavior correctly preserves QPI and rejects IA for explicit "先不要思想考古".
|
||||
- case_id: R04-BI-025
|
||||
reason: explicit post-QPI depth handoff selected IA; no initial failure found.
|
||||
- case_id: R04-BI-034
|
||||
reason: direct execution with explicit analysis override selected QPI; no immediate patch needed.
|
||||
|
||||
should_not_open_another_small_patch_round:
|
||||
- issue_or_case: all governance/capacity/IA natural-language under-selection candidates
|
||||
reason: these should be bundled into calibration policy and next blind/calibration evaluation, not patched one keyword at a time.
|
||||
```
|
||||
|
||||
## 9. Verification Evidence Requirements
|
||||
|
||||
Required for a selector/routing patch based on this review:
|
||||
|
||||
```text
|
||||
targeted_regression_for_confirmed_target_cases: required for R04-BI-002, R04-BI-024, R04-BI-035, R04-BI-036, and any accepted same-class boundary such as R04-BI-022.
|
||||
full_frozen_pool_rerun_or_before_after_comparison: required; must show all 38 Round 04 cases before/after with selected, rejected, no-call, scores, reasons, and routing notes.
|
||||
existing_selector_regression: required; existing no-call, model-level exclusion, QPI-before-IA, and depth-limiting tests must still pass.
|
||||
calibration_smoke: required; direct-execution no-call and QPI/IA boundary samples must remain sane.
|
||||
unit_tests: required for the Round 04 runner and any selector helper changed by the patch.
|
||||
command_log_or_validation_report: required; dry-run is not sufficient for a post-patch verification claim.
|
||||
dry_run_vs_executed_gate_status: must be explicit. Current `gate-run-report` is dry-run only.
|
||||
rule_diff_only_is_sufficient: no.
|
||||
missing_evidence: after-patch routing results, routing behavior diff, executed gate logs, and Owner/Web calibration decisions are not available in this review_turn by design.
|
||||
```
|
||||
|
||||
## 10. Before / After Behavior Review
|
||||
|
||||
No post-patch or before/after evidence is allowed in this `review_turn`. The initial Round 04 behavior below is the only valid "before" evidence. The "after" column is intentionally unavailable.
|
||||
|
||||
```text
|
||||
target_behavior_changes:
|
||||
- case_id: R04-BI-002
|
||||
before: selected qpi; no_call false.
|
||||
after: not available in review_turn.
|
||||
assessment: target fix required; expected after should be no-call with QPI and IA rejected.
|
||||
- case_id: R04-BI-024
|
||||
before: selected intellectual_archaeology and qpi.
|
||||
after: not available in review_turn.
|
||||
assessment: target fix required; expected after should hard-exclude IA and preserve QPI if Owner accepts lightweight QPI request.
|
||||
- case_id: R04-BI-035
|
||||
before: hard no-call; QPI and IA rejected.
|
||||
after: not available in review_turn.
|
||||
assessment: target fix required; expected after should allow QPI and reject IA.
|
||||
- case_id: R04-BI-036
|
||||
before: hard no-call; QPI and IA rejected.
|
||||
after: not available in review_turn.
|
||||
assessment: target fix required; expected after should allow QPI and reject IA.
|
||||
|
||||
non_target_behavior_changes:
|
||||
- case_id: not observable
|
||||
before: initial-only evidence.
|
||||
after: not available in review_turn.
|
||||
assessment: routing-behavior-diff-audit is correctly skipped for this turn but must be run for any patch verification turn.
|
||||
|
||||
accepted_collateral_behavior_changes:
|
||||
- case_id: none accepted in this review_turn.
|
||||
rationale: Owner decisions are pending; post-patch evidence is excluded.
|
||||
regression_or_documentation: required after Owner decision.
|
||||
|
||||
unexpected_regressions:
|
||||
- case_id: not observable.
|
||||
evidence: no after evidence in scope.
|
||||
action: require frozen-pool rerun and before/after comparison in planning_turn.
|
||||
|
||||
owner_or_web_calibration_needed:
|
||||
- case_id: R04-BI-022
|
||||
question: should "主导稀缺" plus depth-limiting wording be enough to allow QPI without more object context?
|
||||
- case_id: R04-BI-010 through R04-BI-017
|
||||
question: should descriptive governance/capacity statements route to provisional QPI, ask clarification, or no-call?
|
||||
- case_id: R04-BI-018/R04-BI-026/R04-BI-027/R04-BI-038
|
||||
question: should natural model-extraction/depth-modeling requests directly select IA or require QPI first?
|
||||
```
|
||||
|
||||
## 11. Non-Target Behavior Changes
|
||||
|
||||
Non-target behavior changes are not observable from initial-only evidence.
|
||||
|
||||
For any later patch, non-target checks must at minimum prove:
|
||||
|
||||
- direct no-call cases `R04-BI-001`, `003`, `004`, `005`, `031`, `032`, `033` remain no-call;
|
||||
- `R04-BI-021` continues to reject IA while selecting QPI;
|
||||
- `R04-BI-025` continues to select IA for explicit post-QPI depth handoff;
|
||||
- `R04-BI-034` continues to escape direct-execution no-call because it asks for problem definition;
|
||||
- broader translation/direct-transformation rules do not suppress legitimate model-library analysis requests.
|
||||
|
||||
## 12. Calibration-Only Candidates
|
||||
|
||||
- `R04-BI-010` through `R04-BI-013`: governance/responsibility/consensus semantics are QPI-relevant, but the round lacks expected labels. Risk if patched now: over-selecting QPI for every organizational complaint.
|
||||
- `R04-BI-014`, `R04-BI-015`, `R04-BI-017`: capacity/path scarcity semantics need product policy before keyword expansion. Risk if patched now: broad "目标/方向/时间/产出" keywords may over-route operational updates.
|
||||
- `R04-BI-018`, `R04-BI-026`, `R04-BI-027`, `R04-BI-038`: likely IA under-selection candidates. Risk if patched now: IA becomes too easy to summon from words like "结构", "长期", or "机制".
|
||||
- `R04-BI-030`: prior-context dependency. Risk if patched now: short frustration phrases become confident QPI route without subject/scenario context.
|
||||
- `R04-BI-037`: generic growth how-to. Risk if patched now: "如何提高流量" may either over-trigger QPI or incorrectly stay no-call; better policy is likely low-confidence/provisional QPI or clarification.
|
||||
|
||||
## 13. Helper Output Confidence
|
||||
|
||||
```text
|
||||
helper_id: review-context-builder
|
||||
output_used_as_evidence: yes
|
||||
confidence: high
|
||||
status: executed
|
||||
confidence_notes: Source roots included required knowledge_assets and Round 04 files; no missing roots. Used only as navigation.
|
||||
blocks_current_review: no
|
||||
requires_runtime_tuning: no
|
||||
|
||||
helper_id: review-bundle-audit
|
||||
output_used_as_evidence: yes
|
||||
confidence: low
|
||||
status: failed; generic_profile; profile_mismatch; false_positive_candidate
|
||||
confidence_notes: Generic profile reports missing manifest and validation_sidecar, but the Round 04 bundle contains `BUNDLE_FILE_MANIFEST_04.md` and the review turn can directly read the files. The helper usefully reports zip readability and discovered files, but its FAIL is not an automatic review blocker.
|
||||
blocks_current_review: no
|
||||
requires_runtime_tuning: yes
|
||||
|
||||
helper_id: regression-validation-gate-runner
|
||||
output_used_as_evidence: yes
|
||||
confidence: low
|
||||
status: dry_run
|
||||
confidence_notes: Proves gate manifest readability and declared commands only. It does not prove index check, validation, or tests passed in this pilot run.
|
||||
blocks_current_review: no
|
||||
requires_runtime_tuning: yes
|
||||
|
||||
helper_id: lifecycle-status-guard-scan
|
||||
output_used_as_evidence: yes
|
||||
confidence: low
|
||||
status: failed; broad_scope; false_positive_candidate
|
||||
confidence_notes: Scan covers 200 files, including older rounds, prior pilot outputs, and post-04.1 files that are outside this review_turn evidence scope. It is a useful overclaim locator but not a Round 04 blocker by itself.
|
||||
blocks_current_review: no
|
||||
requires_runtime_tuning: yes
|
||||
|
||||
helper_id: routing-behavior-diff-audit
|
||||
output_used_as_evidence: no
|
||||
confidence: not_used
|
||||
status: skipped
|
||||
confidence_notes: Appropriate for initial-only review_turn. It becomes required for any post-patch verification turn.
|
||||
blocks_current_review: no
|
||||
requires_runtime_tuning: no
|
||||
```
|
||||
|
||||
## 14. Findings
|
||||
|
||||
### Finding ID: F-R04-P2-001
|
||||
|
||||
- Classification: `major`
|
||||
- Title: Translation/direct transformation no-call has payload leakage.
|
||||
- Evidence: `R04-BI-002` selected `qpi` due `complexity signal: 模型`; input metadata says pure translation should test no-call.
|
||||
- Why It Matters: If payload words drive routing, direct transformation tasks can summon cognitive models even when the user asked only for translation or formatting.
|
||||
- Recommended Action: Add instruction/payload boundary handling for direct transformation requests and verify against frozen pool.
|
||||
- Final Action Recommendation: `fix_now`
|
||||
- Owner Decision Required: yes
|
||||
- Blocks Web Final Review: yes, for a selector-patch round
|
||||
- Blocks Lifecycle Change: yes
|
||||
|
||||
### Finding ID: F-R04-P2-002
|
||||
|
||||
- Classification: `major`
|
||||
- Title: IA refusal variant was not enforced as hard exclusion.
|
||||
- Evidence: `R04-BI-024` selected `intellectual_archaeology` despite `不要进入思想考古`.
|
||||
- Why It Matters: Explicit model refusal is a hard user boundary. Violating it undermines selector trust more than an ordinary scoring error.
|
||||
- Recommended Action: Expand model-level IA hard exclusion variants and verify QPI remains available where the residual request is QPI-shaped.
|
||||
- Final Action Recommendation: `fix_now`
|
||||
- Owner Decision Required: yes
|
||||
- Blocks Web Final Review: yes
|
||||
- Blocks Lifecycle Change: yes
|
||||
|
||||
### Finding ID: F-R04-P2-003
|
||||
|
||||
- Classification: `major`
|
||||
- Title: Depth-limiting phrases suppress lightweight QPI requests.
|
||||
- Evidence: `R04-BI-035` and `R04-BI-036` no-called despite explicit dominant-scarcity / missing-information-path-consensus requests.
|
||||
- Why It Matters: "Do not go deep" should protect against IA or long analysis, not block the front-routing model the user is requesting.
|
||||
- Recommended Action: Treat accepted QPI-limited phrases as override to depth-limiting no-call while keeping IA rejected.
|
||||
- Final Action Recommendation: `fix_now`
|
||||
- Owner Decision Required: yes
|
||||
- Blocks Web Final Review: yes
|
||||
- Blocks Lifecycle Change: yes
|
||||
|
||||
### Finding ID: F-R04-P2-004
|
||||
|
||||
- Classification: `calibration`
|
||||
- Title: Governance and capacity descriptions reveal QPI under-selection risk.
|
||||
- Evidence: `R04-BI-010` through `R04-BI-017` mostly no-call unless explicit `问题` appears.
|
||||
- Why It Matters: QPI is supposed to detect responsibility, consensus, path, and scarcity frames. But broad keyword patching could over-route ordinary statements.
|
||||
- Recommended Action: Defer to Owner/Web calibration policy; do not open a tiny patch for every governance word.
|
||||
- Final Action Recommendation: `defer_to_calibration`
|
||||
- Owner Decision Required: yes
|
||||
- Blocks Web Final Review: no for the narrow selector patch; yes for broader selector maturity claims
|
||||
- Blocks Lifecycle Change: yes
|
||||
|
||||
### Finding ID: F-R04-P2-005
|
||||
|
||||
- Classification: `calibration`
|
||||
- Title: Natural IA/depth-modeling requests may be under-selected.
|
||||
- Evidence: `R04-BI-018`, `R04-BI-026`, `R04-BI-027`, and `R04-BI-038` did not select IA except when exact stronger triggers appeared in other cases.
|
||||
- Why It Matters: IA must not be default, but a too-narrow gate may miss the model extraction and deep mechanism work it exists to support.
|
||||
- Recommended Action: Calibrate direct IA route vs QPI-first route before expanding IA triggers.
|
||||
- Final Action Recommendation: `defer_to_calibration`
|
||||
- Owner Decision Required: yes
|
||||
- Blocks Web Final Review: no for the narrow patch; yes for IA selector maturity claims
|
||||
- Blocks Lifecycle Change: yes
|
||||
|
||||
### Finding ID: F-R04-P2-006
|
||||
|
||||
- Classification: `major`
|
||||
- Title: Post-patch verification evidence is absent from the allowed review_turn scope.
|
||||
- Evidence: helper gate output is dry-run; routing diff helper was skipped; after-patch files are intentionally excluded.
|
||||
- Why It Matters: Rule diffs or targeted examples alone cannot prove the patch did not create collateral routing regressions.
|
||||
- Recommended Action: `planning_turn` must require targeted regression, full frozen pool rerun, before/after diff, and executed gate evidence.
|
||||
- Final Action Recommendation: `fix_now`
|
||||
- Owner Decision Required: yes
|
||||
- Blocks Web Final Review: yes
|
||||
- Blocks Lifecycle Change: yes
|
||||
|
||||
### Finding ID: F-R04-P2-007
|
||||
|
||||
- Classification: `minor`
|
||||
- Title: Helper profiles need runtime tuning before formal repeated use.
|
||||
- Evidence: bundle audit generic profile treats `BUNDLE_FILE_MANIFEST_04.md` as extra and reports manifest missing; lifecycle scan includes broad out-of-scope files.
|
||||
- Why It Matters: Helper exit codes can become noisy and should not be treated as automatic Local CCRA conclusions.
|
||||
- Recommended Action: Tune helper profiles or document profile limitations in the next Local CCRA planning output.
|
||||
- Final Action Recommendation: `document_only`
|
||||
- Owner Decision Required: no for the current review judgment; yes for runtime tuning priority
|
||||
- Blocks Web Final Review: no
|
||||
- Blocks Lifecycle Change: no
|
||||
|
||||
## 15. Engineering Pass vs Product Judgment
|
||||
|
||||
```text
|
||||
What engineering evidence shows:
|
||||
- The frozen blind input pool has 38 inputs and intentionally lacks expected routing labels.
|
||||
- The Round 04 runner records selected models, rejected models, no-call status, scores, reasons, and penalties.
|
||||
- The test file verifies loader/report behavior and absence of answer-key fields.
|
||||
- The helper gate manifest declares index, validation, and test gates, but the actual helper run was dry-run.
|
||||
|
||||
What product/model-governance question remains:
|
||||
- Which observed routes are incorrect, which are acceptable conservative no-calls, and which should become calibration rather than immediate regression?
|
||||
- How broad should QPI semantics be for governance/capacity statements without explicit user requests?
|
||||
- When should IA be selected directly versus routed as a next model after QPI?
|
||||
|
||||
What evidence would close the gap:
|
||||
- Owner/Web classification of target failures.
|
||||
- Post-patch full frozen-pool before/after routing report.
|
||||
- Executed selector regression, calibration smoke, unit tests, index check, and validation.
|
||||
- Explicit documentation of collateral changes and accepted calibration-only cases.
|
||||
```
|
||||
|
||||
## 16. Lifecycle And Scope Guard
|
||||
|
||||
```text
|
||||
Claim: QPI and Intellectual Archaeology remain draft / B / pending.
|
||||
Evidence: Round 04 bundle scope file, knowledge_assets model map, stability rules, and QPI/IA docs.
|
||||
Required authority: Owner / CCRA / Web CCRA for any lifecycle change.
|
||||
Assessment: compliant. No lifecycle promotion should occur.
|
||||
|
||||
Claim: Round 04 initial report does not score correctness and does not upgrade model status.
|
||||
Evidence: `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`.
|
||||
Required authority: Owner / CCRA for post-review labels and patch acceptance.
|
||||
Assessment: compliant.
|
||||
|
||||
Claim: helper lifecycle scan reports many blocking findings.
|
||||
Evidence: `helper-outputs/lifecycle-status-guard-scan.md`.
|
||||
Required authority: Local CCRA judgment plus Owner decision before treating any candidate as accepted finding.
|
||||
Assessment: low-confidence broad scan for this turn; not a current Round 04 blocker without triage.
|
||||
|
||||
Claim: current docs contain later Round 04.1 closure language.
|
||||
Evidence: `README.md`, `docs/DECISIONS.md`, `selector/README.md`, `selector/selector_rules.json`.
|
||||
Required authority: excluded from review_turn initial Round 04 judgment.
|
||||
Assessment: read but not used as proof of initial issue resolution or lifecycle readiness.
|
||||
```
|
||||
|
||||
## 17. Local Tuning Recommendations
|
||||
|
||||
1. Open a scoped selector patch requirement for `R04-BI-002`, `R04-BI-024`, `R04-BI-035`, and `R04-BI-036`; include `R04-BI-022` only if Owner accepts it as same-class QPI-limited intent.
|
||||
2. Require full frozen Round 04 before/after behavior comparison before claiming repair.
|
||||
3. Convert accepted target failures into regression cases after Owner/Web classification, not before.
|
||||
4. Keep governance/capacity and natural IA examples in calibration until product policy is explicit.
|
||||
5. Tune helper profiles so versioned manifests and out-of-scope lifecycle scans do not appear as automatic blockers.
|
||||
|
||||
## 18. Web Final Review Readiness
|
||||
|
||||
Choice: `not_ready`.
|
||||
|
||||
Reason: initial Round 04 evidence shows clear selector patch needs, but the allowed review scope contains no post-patch behavior, no executed gates, no before/after diff, and no Owner decision. The material can proceed to a `planning_turn` for next-review requirements; it should not be treated as ready for Web final review or Round 05 acceptance.
|
||||
|
||||
## 19. Final Action Recommendation
|
||||
|
||||
Choice: `fix_now`.
|
||||
|
||||
Next should happen:
|
||||
|
||||
- Continue to `planning_turn` in the same child session.
|
||||
- Define the exact post-patch verification evidence required for the target cases and same-class boundaries.
|
||||
- Preserve Round 04.1/post-patch materials outside this review_turn until the planning turn or a dedicated post-patch verification turn asks for them.
|
||||
|
||||
Next should not happen:
|
||||
|
||||
- Do not promote QPI or IA lifecycle status.
|
||||
- Do not treat Local CCRA output as Owner approval.
|
||||
- Do not treat the helper exit codes as automatic review conclusions.
|
||||
- Do not open broad keyword patches for all calibration-only cases.
|
||||
- Do not claim Round 05 or Web final readiness from this historical pilot.
|
||||
|
||||
## 20. Owner Decision Points
|
||||
|
||||
```text
|
||||
- decision_id: OD-R04-001
|
||||
decision_needed: accept the four must-fix initial Round 04 target failures.
|
||||
options: accept_all | accept_subset | request_web_baseline_comparison_first
|
||||
recommended_default: accept_all
|
||||
|
||||
- decision_id: OD-R04-002
|
||||
decision_needed: classify R04-BI-022 as must-fix same-class, calibration-only, or acceptable conservative no-call.
|
||||
options: include_in_patch | calibration_only | leave_no_call
|
||||
recommended_default: include_in_patch, because "主导稀缺" is QPI-shaped.
|
||||
|
||||
- decision_id: OD-R04-003
|
||||
decision_needed: define policy for descriptive governance/capacity statements without explicit requests.
|
||||
options: provisional_qpi | ask_clarifying_question | no_call_until_request
|
||||
recommended_default: ask_clarifying_question or provisional_qpi with low confidence.
|
||||
|
||||
- decision_id: OD-R04-004
|
||||
decision_needed: define direct IA versus QPI-first route for natural model-extraction/deep-mechanism inputs.
|
||||
options: direct_ia_when_depth_intent_clear | qpi_first_always | qpi_plus_ia_when_both_signals_present
|
||||
recommended_default: qpi_plus_ia_when both clear depth intent and model-extraction intent appear.
|
||||
|
||||
- decision_id: OD-R04-005
|
||||
decision_needed: decide whether helper profile tuning is required before formal Round 05 Local CCRA use.
|
||||
options: tune_now | document_limitations | defer
|
||||
recommended_default: document_limitations for this pilot, tune before repeated formal use.
|
||||
```
|
||||
|
||||
## 21. Limits And Uncertainty
|
||||
|
||||
- I did not read or use `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md`.
|
||||
- I did not read or use `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/`.
|
||||
- I did not inspect `optional_raw_changed_files_04.zip` beyond helper-reported readability and direct reads of source files already available in the repository.
|
||||
- I did not run validation or tests; helper evidence is dry-run only and the user requested review output, not repairs.
|
||||
- I did not compare against Web CCRA/GPT baseline lines 1-214 because this `review_turn` was scoped to local file-first review output. That comparison belongs to the later comparison plan.
|
||||
- Some required current project files contain post-04.1 statements. Those files were read, but post-04.1 conclusions were excluded from this turn's Round 04 initial judgment.
|
||||
|
||||
## 22. Resume Instructions
|
||||
|
||||
```text
|
||||
turn_type: planning_turn
|
||||
same_child_session_id: 019edcde-24be-7593-99b2-5cf014467340
|
||||
first_turn_report_path: local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md
|
||||
owner_decision_path: local_ccra_reviews/round-04/pilot-02/owner-decision.md
|
||||
next_review_target: Round 04.1 post-patch routing verification requirements
|
||||
planning_output_path: local_ccra_reviews/round-04/pilot-02/next-review-requirements.md
|
||||
```
|
||||
|
||||
Planning turn should not re-review the full initial Round 04 bundle unless Owner adds new evidence or changes the scope. It should translate this report into required submitted materials, target cases, evidence gates, helper expectations, and Web/Owner calibration questions for the next review.
|
||||
|
|
@ -0,0 +1,111 @@
|
|||
# Web / Local CCRA Three-Way Comparison
|
||||
|
||||
## Scope
|
||||
|
||||
This note compares three review outputs for the same Round 04 source problem:
|
||||
|
||||
1. Web CCRA / GPT baseline: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\讨论\2026-06-18产品交流-GPT.md`, lines 1-214 only.
|
||||
2. Local CCRA pilot-01: `local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md` and `local_ccra_reviews/round-04/pilot-01/05_WEB_LOCAL_CCRA_COMPARISON.md`.
|
||||
3. Local CCRA pilot-02 after CCPE Patch 1:
|
||||
- `local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/next-review-requirements.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/returned-output.md`
|
||||
|
||||
This comparison does not use Web baseline material after line 214, because later content belongs to the Round 04.1 review and closeout.
|
||||
|
||||
## High-Level Judgment
|
||||
|
||||
Pilot-02 is materially better than pilot-01 and is now close enough to Web CCRA's first-review quality for formal local first-review use in this project, with explicit limits.
|
||||
|
||||
The important improvement is not only format. Pilot-02 now performs the same core judgment Web made:
|
||||
|
||||
- `R04-BI-002` is a rule-based selector no-call / instruction-payload boundary failure, not an LLM understanding failure.
|
||||
- `R04-BI-024` is an explicit Intellectual Archaeology refusal / model-level exclusion failure.
|
||||
- `R04-BI-035` and `R04-BI-036` are depth-limiting override failures: "do not go deep" should not become global no-call when the user asks for lightweight QPI.
|
||||
- governance, capacity, and natural IA boundary cases should be calibration work, not another small keyword patch.
|
||||
- Round 04.1 must include post-patch verification, not only a rule diff.
|
||||
|
||||
Pilot-02 also adds local-only strengths that Web cannot reliably provide from a limited upload: file-first evidence coverage, helper-output confidence classification, lifecycle / authority guard checks, and same-child-session continuation into a planning turn.
|
||||
|
||||
## Outcome Matrix
|
||||
|
||||
| Dimension | Web Baseline | Pilot-01 | Pilot-02 |
|
||||
|---|---|---|---|
|
||||
| Product mechanism diagnosis | Strong. Immediately identifies selector boundary failure and no LLM involvement. | Weaker. Mostly audits already-produced Round 04.1 evidence. | Strong. Reconstructs the same mechanism from initial Round 04 evidence. |
|
||||
| Patch scope judgment | Strong. Selects 002, 024, 035, 036 and keeps wider cases for calibration. | Partial. Confirms later target set but less useful before the fix. | Strong. Separates must-fix, same-class boundary, calibration-only, and explicitly-not-patched cases. |
|
||||
| Next review requirements | Strong. Requires targeted regression, full rerun, existing regression, and command logs. | Partial. Notes missing helper/runtime risks. | Strong. Produces `next-review-requirements.md` with submitted-material checklist and evidence requirements. |
|
||||
| Local file audit | Limited by upload and conversation context. | Strong. Reads broad local evidence and helper outputs. | Strong. Reads required knowledge base, Round 04 evidence, helper outputs, and runtime contract. |
|
||||
| Helper confidence | Not covered in baseline. | Finds helper/runtime risks, but this dominates the report. | Better balanced. Classifies helper outputs as evidence with confidence limits. |
|
||||
| Conversation persistence | Not applicable. | One review child session. | Verified two-turn same-child workflow: `review_turn` then `planning_turn`. |
|
||||
| Formal readiness | Web remains final reviewer. | Needs more local tuning before formal use. | Ready for formal local first review under listed conditions. |
|
||||
|
||||
## Where Pilot-02 Now Matches Web
|
||||
|
||||
Pilot-02 matches the Web baseline on the central Round 04 diagnosis. It says the initial failures are selector rule-boundary failures:
|
||||
|
||||
- direct transformation / translation requests can leak payload terms such as `模型` into QPI routing;
|
||||
- IA refusal variants must hard-exclude IA;
|
||||
- depth-limiting language should suppress IA depth, not suppress lightweight QPI.
|
||||
|
||||
It also matches Web on the next-step shape: do not introduce an LLM selector, do not upgrade QPI or Intellectual Archaeology, do not broaden governance / capacity cases by keyword, and do require a Round 04.1 post-patch verification pass.
|
||||
|
||||
This fixes the main pilot-01 gap. Pilot-01 acted like a file-first auditor after the fix existed. Pilot-02 acts like a product reviewer before the fix, then a local planning reviewer after the first judgment.
|
||||
|
||||
## Where Pilot-02 Is Better Than Web
|
||||
|
||||
Pilot-02 is stronger in evidence discipline:
|
||||
|
||||
- It records the exact child session id: `019edcde-24be-7593-99b2-5cf014467340`.
|
||||
- It reads the mandatory project knowledge base path.
|
||||
- It explicitly excludes Round 04.1 post-patch evidence from `review_turn`, preserving fair historical comparison.
|
||||
- It detects that current files may contain later Round 04.1 language and avoids using that as initial Round 04 proof.
|
||||
- It separates helper outputs from reviewer judgment and labels confidence limits.
|
||||
- It produces a second-turn package plan instead of leaving the Owner to convert findings into review materials manually.
|
||||
|
||||
The `planning_turn` output is especially useful for reducing small Web sub-rounds. It requires a rule patch summary, target labels / Owner decisions, full 38-case frozen-pool before/after comparison, targeted regression, existing selector regression, calibration smoke, executed command logs, bundle manifest, and carry-forward Owner/Web calibration questions.
|
||||
|
||||
## Remaining Weaknesses
|
||||
|
||||
Pilot-02 still has operational limits:
|
||||
|
||||
- `review-bundle-audit` used a generic profile and misclassified the versioned Round 04 manifest pattern.
|
||||
- `regression-validation-gate-runner` evidence was dry-run only in this setup.
|
||||
- `lifecycle-status-guard-scan` produced broad whole-repo noise that requires human or reviewer triage.
|
||||
- `routing-behavior-diff-audit` was correctly skipped for the initial no-hindsight review, but must be required when before/after evidence exists.
|
||||
- The report is long. It is good as an audit artifact, but formal routine use should keep the short returned summary visible for the Owner.
|
||||
|
||||
These are not blockers for using Local CCRA as a formal local first-review lane. They are helper/runtime maturity issues that should remain documented and be improved as the workflow repeats.
|
||||
|
||||
## Readiness Recommendation
|
||||
|
||||
Recommendation: `ready_for_formal_local_first_review_with_conditions`.
|
||||
|
||||
Local CCRA v0.1.1 is ready to use for this project as the formal local first review before Web final review. It should not replace Owner judgment or Web CCRA final review.
|
||||
|
||||
Conditions for formal use:
|
||||
|
||||
1. Always run a real child session and record `child_session_id`.
|
||||
2. Use the two-turn pattern by default: `review_turn` for findings, then same-child `planning_turn` for next review requirements and submitted-material guidance.
|
||||
3. Keep `knowledge_base_path` mandatory and point it to `knowledge_assets/`.
|
||||
4. Treat helper outputs as evidence only, with explicit confidence / noise classification.
|
||||
5. Require before/after routing diff evidence whenever the reviewed material includes a patch or post-patch verification.
|
||||
6. Keep Local CCRA reports local by default; include them in Web CCRA upload only when Owner explicitly decides to.
|
||||
7. Do not claim lifecycle promotion, Round 05 acceptance, or Web approval from Local CCRA alone.
|
||||
|
||||
## Further Tuning
|
||||
|
||||
CCPE Patch 2 is recommended as a non-blocking hardening patch. It is not required before the next Owner/Web-defined local first-review run if Patch 1 behavior remains intact.
|
||||
|
||||
Recommended Patch 2 improvements:
|
||||
|
||||
- add a project-aware or CCRA-aware bundle audit profile for versioned manifests;
|
||||
- decide when gate runner should execute rather than dry-run;
|
||||
- make routing behavior diff mandatory for patch verification turns;
|
||||
- tune lifecycle scan scope so broad historical findings do not dominate current review;
|
||||
- add a short Owner-facing executive summary template on top of the long audit report.
|
||||
|
||||
## Final Conclusion
|
||||
|
||||
Pilot-02 achieved the intended Patch 1 target. It preserves Local CCRA's file-first advantages while recovering the Web-style mechanism diagnosis and repair-scope judgment that pilot-01 lacked.
|
||||
|
||||
The practical path is to start using Local CCRA for formal local first review in the current project after the Owner and Web CCRA define the next round's work, keep Web as planning / final review partner, and use the first real run as live validation of Patch 2 hardening if CCPE updates it.
|
||||
|
|
@ -0,0 +1,234 @@
|
|||
---
|
||||
packet_type: local-ccra-agent-invocation-packet
|
||||
runtime_id: ccra-local-review
|
||||
agent_id: ccra-local-reviewer
|
||||
runtime_version: 0.1.1
|
||||
agent_version: 0.1.1
|
||||
review_id: round-04-pilot-02
|
||||
status: ready_for_dispatch
|
||||
---
|
||||
|
||||
# Local CCRA Agent Invocation Packet
|
||||
|
||||
## 1. Invocation Metadata
|
||||
|
||||
```yaml
|
||||
packet_id: round-04-pilot-02
|
||||
created_at: 2026-06-19
|
||||
client_project_root: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong
|
||||
knowledge_base_path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets
|
||||
review_round: round-04
|
||||
local_pass: pilot-02
|
||||
review_run_dir: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02
|
||||
turn_type: review_turn
|
||||
invocation_mode: prompt_path_reference
|
||||
carrier_type: codex_thread
|
||||
child_session_id: 019edcde-24be-7593-99b2-5cf014467340
|
||||
persistent_child_session_required: true
|
||||
same_child_session_as_review_turn_required: false
|
||||
simulation_allowed: false
|
||||
```
|
||||
|
||||
## 2. Canonical Artifacts
|
||||
|
||||
```yaml
|
||||
canonical_agent_path: C:\Users\wangq\Documents\Codex\ccpe-system\agents\agent-specs\ccra-local-reviewer.agent.md
|
||||
canonical_runtime_path: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review.runtime.md
|
||||
runtime_setup_path: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-runtime-setup.md
|
||||
report_template_path: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-report.template.md
|
||||
planning_template_path: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-next-review-requirements.template.md
|
||||
integration_registration_path: C:\Users\wangq\Documents\Codex\ccpe-system\integrations\skills-vault\ccra-local-review-helpers.integration.md
|
||||
```
|
||||
|
||||
## 3. Role Integrity Requirement
|
||||
|
||||
The invoked participant must act as `ccra-local-reviewer`.
|
||||
|
||||
The reviewer must:
|
||||
|
||||
```text
|
||||
read local evidence directly
|
||||
cite files actually read
|
||||
use helper outputs only as evidence
|
||||
respect the requested turn_type
|
||||
write the report to the requested output contract
|
||||
preserve Owner/Web CCRA authority boundaries
|
||||
avoid project file edits except contracted output files
|
||||
avoid lifecycle promotion
|
||||
avoid main-session roleplay
|
||||
```
|
||||
|
||||
If this packet cannot be dispatched to a real child session or equivalent isolated participant context, the valid state is:
|
||||
|
||||
```text
|
||||
blocked_waiting_for_participant_output
|
||||
```
|
||||
|
||||
## 4. Task Context
|
||||
|
||||
```yaml
|
||||
turn_type: review_turn
|
||||
primary_question: Can Patch 1 Local CCRA identify Round 04 product/routing issues with Web-style diagnosis while retaining local file-first audit strength?
|
||||
scope_statement: Review the initial Round 04 blind routing evaluation material as a historical pilot. Do not use Round 04.1 post-patch outcome evidence during review_turn. After review_turn, the same child session will be continued with planning_turn.
|
||||
non_goals:
|
||||
- Do not decide Owner approval.
|
||||
- Do not replace Web CCRA final review.
|
||||
- Do not promote lifecycle status.
|
||||
- Do not modify selector rules, model cards, model JSON, regression cases, or review bundles.
|
||||
- Do not treat this pilot as Round 05 acceptance.
|
||||
- Do not use Round 04.1 post-patch result files as review_turn evidence.
|
||||
local_tuning_stage: historical_pilot_patch1_retest
|
||||
web_final_review_target: none_for_this_pilot
|
||||
known_prior_rounds:
|
||||
- round-03
|
||||
- round-03.1
|
||||
- round-03.2
|
||||
- round-03.2a
|
||||
- round-04
|
||||
owner_supplied_notes: Compare later against Web CCRA baseline lines 1-214 and pilot-01. This review_turn should not read the later Round 04.1 post-patch evidence.
|
||||
first_turn_report_path:
|
||||
owner_decision_path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\owner-decision.md
|
||||
next_review_target: Round 04.1 post-patch routing verification requirements
|
||||
web_comparison_source: C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\讨论\2026-06-18产品交流-GPT.md
|
||||
web_comparison_source_range: lines 1-214
|
||||
```
|
||||
|
||||
## 5. Input Files
|
||||
|
||||
Required:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\README.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\AGENTS.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\PROJECTS.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets\README.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets\
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\review-context.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\review-file-manifest.json
|
||||
```
|
||||
|
||||
Project and round-specific evidence:
|
||||
|
||||
```text
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\docs\WORKFLOW.md
|
||||
purpose: workflow and review rules
|
||||
required: true
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\docs\DECISIONS.md
|
||||
purpose: accepted selector and lifecycle decisions
|
||||
required: true
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\docs\QPI_CONTEXTUAL_ROUTING_RULES.md
|
||||
purpose: QPI routing boundary
|
||||
required: true
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\docs\INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md
|
||||
purpose: IA depth gate boundary
|
||||
required: true
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\reports\Round04_blind_routing_evaluation_report_2026-06-18.md
|
||||
purpose: Round 04 initial evaluation report
|
||||
required: true
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\reports\Round04_blind_input_candidates_2026-06-18.md
|
||||
purpose: blind input candidate context
|
||||
required: true
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\selector\round04_blind_inputs.json
|
||||
purpose: full Round 04 blind input set
|
||||
required: true
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\selector\selector_rules.json
|
||||
purpose: current selector rules at the time of local retest
|
||||
required: true
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\selector\README.md
|
||||
purpose: selector operating contract
|
||||
required: true
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\tests\test_round04_blind_routing.py
|
||||
purpose: Round 04 test surface
|
||||
required: false
|
||||
```
|
||||
|
||||
Review bundles:
|
||||
|
||||
```text
|
||||
- path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\ccra_review_bundle\round-04_2026-06-18_blind-input-routing-evaluation
|
||||
purpose: primary Round 04 Web CCRA review bundle
|
||||
```
|
||||
|
||||
Excluded from `review_turn`:
|
||||
|
||||
```text
|
||||
- reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md
|
||||
- ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/
|
||||
```
|
||||
|
||||
Reason: avoid hindsight in comparison with Web CCRA baseline lines 1-214.
|
||||
|
||||
Helper outputs:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\helper-outputs\bundle-audit.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\helper-outputs\bundle-audit.json
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\helper-outputs\gate-run-report.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\helper-outputs\gate-run-report.json
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\helper-outputs\lifecycle-status-guard-scan.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\helper-outputs\lifecycle-status-guard-scan.json
|
||||
```
|
||||
|
||||
Unavailable helper outputs:
|
||||
|
||||
```text
|
||||
- routing-behavior-diff-audit: skipped for review_turn because no post-patch before/after evidence is included in the initial Round 04 evidence scope.
|
||||
```
|
||||
|
||||
## 6. Output Contract
|
||||
|
||||
The reviewer must write:
|
||||
|
||||
```yaml
|
||||
review_turn_report_path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\04_LOCAL_CCRA_REVIEW_REPORT.md
|
||||
planning_turn_output_path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\next-review-requirements.md
|
||||
comparison_turn_output_path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\05_WEB_LOCAL_CCRA_COMPARISON.md
|
||||
returned_output_path: C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\returned-output.md
|
||||
required_report_template: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-report.template.md
|
||||
required_planning_template: C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-next-review-requirements.template.md
|
||||
```
|
||||
|
||||
Output mapping:
|
||||
|
||||
```text
|
||||
review_turn -> 04_LOCAL_CCRA_REVIEW_REPORT.md
|
||||
planning_turn -> next-review-requirements.md
|
||||
comparison_turn -> 05_WEB_LOCAL_CCRA_COMPARISON.md or project-defined comparison path
|
||||
```
|
||||
|
||||
## 7. Continuity Policy
|
||||
|
||||
```yaml
|
||||
same_child_session_preferred: true
|
||||
resume_allowed: true
|
||||
planning_turn_requires_same_child_session: true
|
||||
resume_requires:
|
||||
- previous report
|
||||
- owner-decision.md when present
|
||||
- new or changed evidence list
|
||||
- unchanged-evidence statement
|
||||
```
|
||||
|
||||
For `planning_turn`, continue the same `child_session_id`, reference the first-turn report, and do not re-review the full current bundle unless new evidence was added or the Owner explicitly asks.
|
||||
|
||||
## 8. Session Logging
|
||||
|
||||
The project main session must record dispatch method, child session id, helper commands, exit codes, files written, skipped helpers, and manual approvals in:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\run-notes.md
|
||||
```
|
||||
|
||||
## 9. No-Simulation Requirement
|
||||
|
||||
Formal Local CCRA output must not be simulated in the project main session.
|
||||
|
||||
If a simulated dry run is explicitly requested, label it:
|
||||
|
||||
```text
|
||||
simulation-only
|
||||
excluded-from-synthesis
|
||||
not-a-formal-report
|
||||
```
|
||||
|
||||
Simulation-only output cannot be used as the Local CCRA report.
|
||||
|
|
@ -0,0 +1,31 @@
|
|||
gates:
|
||||
- gate_id: index-check
|
||||
command:
|
||||
- python
|
||||
- scripts\rebuild_indexes.py
|
||||
- --check
|
||||
working_directory: .
|
||||
expected_exit_code: 0
|
||||
log_file: logs/index-check.log
|
||||
timeout_seconds: 120
|
||||
required_before_review: true
|
||||
- gate_id: model-library-validation
|
||||
command:
|
||||
- python
|
||||
- scripts\validate_model_library.py
|
||||
working_directory: .
|
||||
expected_exit_code: 0
|
||||
log_file: logs/model-library-validation.log
|
||||
timeout_seconds: 120
|
||||
required_before_review: true
|
||||
- gate_id: round04-blind-routing-tests
|
||||
command:
|
||||
- python
|
||||
- -m
|
||||
- pytest
|
||||
- tests\test_round04_blind_routing.py
|
||||
working_directory: .
|
||||
expected_exit_code: 0
|
||||
log_file: logs/round04-blind-routing-tests.log
|
||||
timeout_seconds: 240
|
||||
required_before_review: false
|
||||
|
|
@ -0,0 +1,74 @@
|
|||
{
|
||||
"bundle_root": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\ccra_review_bundle\\round-04_2026-06-18_blind-input-routing-evaluation",
|
||||
"profile": "generic",
|
||||
"files_discovered": [
|
||||
"00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md",
|
||||
"01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md",
|
||||
"02_BLIND_INPUT_SET_04.md",
|
||||
"03_ROUTING_EVALUATION_REPORT_04.md",
|
||||
"04_REVIEW_QUESTIONS_FOR_GPT_04.md",
|
||||
"BUNDLE_FILE_MANIFEST_04.md",
|
||||
"optional_raw_changed_files_04.zip"
|
||||
],
|
||||
"required_files_present": {
|
||||
"brief": [
|
||||
"00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md"
|
||||
]
|
||||
},
|
||||
"required_files_missing": [
|
||||
"manifest",
|
||||
"validation_sidecar"
|
||||
],
|
||||
"optional_files_present": {
|
||||
"report": [
|
||||
"03_ROUTING_EVALUATION_REPORT_04.md"
|
||||
],
|
||||
"zip": [
|
||||
"optional_raw_changed_files_04.zip"
|
||||
]
|
||||
},
|
||||
"manifest_status": {
|
||||
"status": "missing",
|
||||
"files": []
|
||||
},
|
||||
"zip_status": {
|
||||
"status": "readable",
|
||||
"files": [
|
||||
"optional_raw_changed_files_04.zip"
|
||||
],
|
||||
"entry_counts": {
|
||||
"optional_raw_changed_files_04.zip": 29
|
||||
}
|
||||
},
|
||||
"validation_sidecar_status": {
|
||||
"status": "missing",
|
||||
"files": []
|
||||
},
|
||||
"report_status": {
|
||||
"status": "present",
|
||||
"files": [
|
||||
"03_ROUTING_EVALUATION_REPORT_04.md"
|
||||
]
|
||||
},
|
||||
"warnings": [
|
||||
"Extra file not matched by profile: 01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md",
|
||||
"Extra file not matched by profile: 02_BLIND_INPUT_SET_04.md",
|
||||
"Extra file not matched by profile: 04_REVIEW_QUESTIONS_FOR_GPT_04.md",
|
||||
"Extra file not matched by profile: BUNDLE_FILE_MANIFEST_04.md"
|
||||
],
|
||||
"blocking_errors": [
|
||||
"Missing required manifest file.",
|
||||
"Missing required validation_sidecar file."
|
||||
],
|
||||
"machine_readable_summary": {
|
||||
"status": "FAIL",
|
||||
"files_discovered_count": 7,
|
||||
"required_missing_count": 2,
|
||||
"warning_count": 4,
|
||||
"blocking_error_count": 2,
|
||||
"manifest_status": "missing",
|
||||
"zip_status": "readable",
|
||||
"validation_sidecar_status": "missing",
|
||||
"report_status": "present"
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# Review Bundle Audit
|
||||
|
||||
## Summary
|
||||
|
||||
- Status: `FAIL`
|
||||
- Bundle root: `C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\ccra_review_bundle\round-04_2026-06-18_blind-input-routing-evaluation`
|
||||
- Profile: `generic`
|
||||
- Files discovered: 7
|
||||
- Required files missing: 2
|
||||
- Warnings: 4
|
||||
- Blocking errors: 2
|
||||
|
||||
## Required Files
|
||||
|
||||
- `brief`: `00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md`
|
||||
|
||||
Missing:
|
||||
- `manifest`
|
||||
- `validation_sidecar`
|
||||
|
||||
## Package Status
|
||||
|
||||
- `manifest_status`: `missing` (none)
|
||||
- `validation_sidecar_status`: `missing` (none)
|
||||
- `zip_status`: `readable` (`optional_raw_changed_files_04.zip`)
|
||||
- `report_status`: `present` (`03_ROUTING_EVALUATION_REPORT_04.md`)
|
||||
|
||||
## Blocking Errors
|
||||
|
||||
- Missing required manifest file.
|
||||
- Missing required validation_sidecar file.
|
||||
|
||||
## Warnings
|
||||
|
||||
- Extra file not matched by profile: 01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md
|
||||
- Extra file not matched by profile: 02_BLIND_INPUT_SET_04.md
|
||||
- Extra file not matched by profile: 04_REVIEW_QUESTIONS_FOR_GPT_04.md
|
||||
- Extra file not matched by profile: BUNDLE_FILE_MANIFEST_04.md
|
||||
|
||||
## Files Discovered
|
||||
|
||||
- `00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md`
|
||||
- `01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md`
|
||||
- `02_BLIND_INPUT_SET_04.md`
|
||||
- `03_ROUTING_EVALUATION_REPORT_04.md`
|
||||
- `04_REVIEW_QUESTIONS_FOR_GPT_04.md`
|
||||
- `BUNDLE_FILE_MANIFEST_04.md`
|
||||
- `optional_raw_changed_files_04.zip`
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
{
|
||||
"project_root": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
|
||||
"gate_manifest_path": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\local_ccra_reviews\\round-04\\pilot-02\\gate-manifest.yaml",
|
||||
"mode": "dry_run",
|
||||
"commands_declared": [
|
||||
"index-check",
|
||||
"model-library-validation",
|
||||
"round04-blind-routing-tests"
|
||||
],
|
||||
"commands_run": [],
|
||||
"commands_skipped": [
|
||||
{
|
||||
"gate_id": "index-check",
|
||||
"reason": "dry_run"
|
||||
},
|
||||
{
|
||||
"gate_id": "model-library-validation",
|
||||
"reason": "dry_run"
|
||||
},
|
||||
{
|
||||
"gate_id": "round04-blind-routing-tests",
|
||||
"reason": "dry_run"
|
||||
}
|
||||
],
|
||||
"exit_codes": {},
|
||||
"pass_fail_status": "DRY_RUN",
|
||||
"duration": 0.0,
|
||||
"log_paths": {},
|
||||
"environment_notes": [
|
||||
"Commands are declared by the manifest.",
|
||||
"Passing gates are engineering evidence only; they do not imply product acceptance or lifecycle approval.",
|
||||
"python: 3.11.15",
|
||||
"platform: Windows-10-10.0.26200-SP0"
|
||||
],
|
||||
"gate_results": [],
|
||||
"manifest_errors": [],
|
||||
"changed_files": [],
|
||||
"machine_readable_summary": {
|
||||
"status": "DRY_RUN",
|
||||
"commands_declared_count": 3,
|
||||
"commands_run_count": 0,
|
||||
"commands_skipped_count": 3,
|
||||
"manifest_error_count": 0,
|
||||
"failed_count": 0,
|
||||
"timeout_count": 0,
|
||||
"changed_file_count": 0
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,28 @@
|
|||
# Gate Run Report
|
||||
|
||||
## Summary
|
||||
|
||||
- Status: `DRY_RUN`
|
||||
- Commands declared: 3
|
||||
- Commands run: 0
|
||||
- Commands skipped: 3
|
||||
- Manifest errors: 0
|
||||
- Changed files: 0
|
||||
|
||||
## Gate Results
|
||||
|
||||
- None
|
||||
|
||||
## Skipped Gates
|
||||
|
||||
- `index-check`: dry_run
|
||||
- `model-library-validation`: dry_run
|
||||
- `round04-blind-routing-tests`: dry_run
|
||||
|
||||
## Manifest Errors
|
||||
|
||||
- None
|
||||
|
||||
## Changed Files
|
||||
|
||||
- None
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,387 @@
|
|||
# Lifecycle Status Guard Scan
|
||||
|
||||
## Summary
|
||||
|
||||
- Status: `FAIL`
|
||||
- Files scanned: 200
|
||||
- Blocking findings: 115
|
||||
- Warnings: 0
|
||||
- Evidence-present observations: 50
|
||||
|
||||
## Blocking Findings
|
||||
|
||||
- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/03_VALIDATION_AND_COMMAND_LOG_03.2.md` line 59: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/03_VALIDATION_AND_COMMAND_LOG_03.2a.md` line 47: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `docs/DECISIONS.md` line 175: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md` line 160: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 204: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 210: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 215: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 221: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 226: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 232: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 237: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 243: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 248: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 254: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 259: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 265: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 270: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 276: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 281: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 287: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 292: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 298: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 303: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 309: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 314: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 320: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 325: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 331: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 336: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 342: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 347: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 353: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 358: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 364: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 369: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 375: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 380: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 386: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 391: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 397: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 402: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 408: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 413: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 438: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 444: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 449: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 455: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 460: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 466: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 471: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 477: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 482: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 488: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 493: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 499: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 504: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 510: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 515: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 521: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 526: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 532: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 537: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 543: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 548: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 554: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 559: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 565: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 570: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 576: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 581: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 587: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 592: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 598: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 603: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 609: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 614: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 620: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 625: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 631: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 636: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 642: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 647: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 16: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 17: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 18: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 19: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 20: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 21: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 22: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 23: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 24: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 25: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 26: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 27: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 28: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 29: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 30: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 31: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md` line 263: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md` line 275: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md` line 11: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 11: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 100: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 357: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 519: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 528: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md` line 618: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md` line 11: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md` line 7: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md` line 698: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md` line 81: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md` line 618: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-research-office.cases.md` line 7: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `selector/qpi_case_digests.json` line 1261: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
- `selector/qpi_case_digests.json` line 2187: `owner-approved` - Approval claim phrase lacks nearby evidence marker.
|
||||
|
||||
## Warnings
|
||||
|
||||
- None
|
||||
|
||||
## Observations
|
||||
|
||||
- `local_ccra_reviews/README.md` line 119: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 188: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 193: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 199: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 422: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 427: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 433: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 655: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 667: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 679: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 691: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 703: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 715: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 727: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 739: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 751: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 763: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 775: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 787: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 799: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 811: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 823: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 835: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 847: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 859: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 871: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 883: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 895: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 933: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 938: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 938: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 950: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 950: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 938: `ccra-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 945: `ccra-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 950: `ccra-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 950: `ccra-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 938: `CCRA approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json` line 950: `CCRA approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 13: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 14: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 15: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 32: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 33: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 41: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md` line 42: `ccra-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml` line 14: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml` line 15: `ccra-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-02/lifecycle-guard-config.yaml` line 14: `owner-approved` - evidence marker present; approval validity not decided.
|
||||
- `local_ccra_reviews/round-04/pilot-02/lifecycle-guard-config.yaml` line 15: `ccra-approved` - evidence marker present; approval validity not decided.
|
||||
|
||||
## Files Scanned
|
||||
|
||||
- `AGENTS.md`
|
||||
- `cards/card_index.md`
|
||||
- `cards/intellectual_archaeology.md`
|
||||
- `cards/qpi.md`
|
||||
- `cards/README.md`
|
||||
- `ccra_review_bundle/round-02_2026-06-16_second-audit/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md`
|
||||
- `ccra_review_bundle/round-02_2026-06-16_second-audit/01_GUIDANCE_PACK_AND_COMPLIANCE_MATRIX.md`
|
||||
- `ccra_review_bundle/round-02_2026-06-16_second-audit/02_CURRENT_ASSET_PACK.md`
|
||||
- `ccra_review_bundle/round-02_2026-06-16_second-audit/03_REPORTS_DIFF_AND_COMMAND_LOG.md`
|
||||
- `ccra_review_bundle/round-02_2026-06-16_second-audit/BUNDLE_FILE_MANIFEST.md`
|
||||
- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF03.1.md`
|
||||
- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/01_PATCH_MATRIX_03.1.md`
|
||||
- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/02_CURRENT_ASSET_PACK03.1.md`
|
||||
- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/03_VALIDATION_AND_COMMAND_LOG03.1.md`
|
||||
- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/04_REVIEW_QUESTIONS_FOR_GPT03.1.md`
|
||||
- `ccra_review_bundle/round-03.1_2026-06-17_selector-no-call-regression-patch/BUNDLE_FILE_MANIFEST03.1.md`
|
||||
- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_03.2.md`
|
||||
- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/01_PATCH_MATRIX_03.2.md`
|
||||
- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/02_CURRENT_ASSET_PACK_03.2.md`
|
||||
- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/03_VALIDATION_AND_COMMAND_LOG_03.2.md`
|
||||
- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/04_REVIEW_QUESTIONS_FOR_GPT_03.2.md`
|
||||
- `ccra_review_bundle/round-03.2_2026-06-17_selector-negative-gate-patch/BUNDLE_FILE_MANIFEST_03.2.md`
|
||||
- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_03.2a.md`
|
||||
- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/01_PATCH_MATRIX_03.2a.md`
|
||||
- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/02_CURRENT_ASSET_PACK_03.2a.md`
|
||||
- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/03_VALIDATION_AND_COMMAND_LOG_03.2a.md`
|
||||
- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/04_REVIEW_QUESTIONS_FOR_GPT_03.2a.md`
|
||||
- `ccra_review_bundle/round-03.2a_2026-06-17_depth-limiting-qpi-override-patch/BUNDLE_FILE_MANIFEST_03.2a.md`
|
||||
- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md`
|
||||
- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/01_GUIDANCE_PACK_AND_COMPLIANCE_MATRIX.md`
|
||||
- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/02_CURRENT_ASSET_PACK.md`
|
||||
- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/03_REPORTS_DIFF_AND_COMMAND_LOG.md`
|
||||
- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/04_QPI_CASE_PROMOTION_SUMMARY_AND_REVIEW_GUIDE.md`
|
||||
- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/05_REVIEW_QUESTIONS_FOR_GPT.md`
|
||||
- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/BUNDLE_FILE_MANIFEST.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/01_RULE_PATCH_SUMMARY_AND_DIFF_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/02_EXPECTED_ROUTING_LABELS_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/03_POST_PATCH_ROUTING_VERIFICATION_REPORT_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/04_REGRESSION_AND_COMMAND_LOG_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/BUNDLE_FILE_MANIFEST_04.1.md`
|
||||
- `ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch/optional_raw_changed_files_04.1.zip.validation.json`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md`
|
||||
- `docs/CHATGPT_HANDOFF_RULES.md`
|
||||
- `docs/CONTENT_STABILIZATION_PROTOCOL.md`
|
||||
- `docs/DATA_CONTRACT.md`
|
||||
- `docs/DECISIONS.md`
|
||||
- `docs/FILE_TAXONOMY.md`
|
||||
- `docs/GPT_PLAN_LOCALIZATION_PROTOCOL.md`
|
||||
- `docs/HANDOFF_TEMPLATE.md`
|
||||
- `docs/INDEX_MAINTENANCE_PROTOCOL.md`
|
||||
- `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md`
|
||||
- `docs/KNOWLEDGE_ASSET_RULES.md`
|
||||
- `docs/MODEL_CARD_CONTRACT.md`
|
||||
- `docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md`
|
||||
- `docs/model_case_preprocessing/qpi/README.md`
|
||||
- `docs/model_case_preprocessing/README.md`
|
||||
- `docs/MODEL_EXTRACTION_RULES.md`
|
||||
- `docs/MODEL_EXTRACTION_WORKFLOW.md`
|
||||
- `docs/NON_GOALS.md`
|
||||
- `docs/PROJECT_BRIEF.md`
|
||||
- `docs/QPI_CONTEXTUAL_ROUTING_RULES.md`
|
||||
- `docs/superpowers/plans/2026-06-16-model-extraction-contract-and-workflow.md`
|
||||
- `docs/superpowers/plans/2026-06-16-project-initialization.md`
|
||||
- `docs/superpowers/plans/2026-06-17-contract-hardening-selector-calibration.md`
|
||||
- `docs/superpowers/plans/2026-06-18-round04-1-selector-rule-patch.md`
|
||||
- `docs/superpowers/plans/2026-06-18-round04-blind-routing-evaluation.md`
|
||||
- `docs/WORKFLOW.md`
|
||||
- `knowledge_assets/00_用户背景与产品上下文.md`
|
||||
- `knowledge_assets/01_核心模型地图.md`
|
||||
- `knowledge_assets/02_模型卡结构规范.md`
|
||||
- `knowledge_assets/03_核心模型抽取样板.md`
|
||||
- `knowledge_assets/06_模型稳固性评级规则.md`
|
||||
- `knowledge_assets/07_产品规划过程记录.md`
|
||||
- `knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md`
|
||||
- `knowledge_assets/09_数据治理与模型调用机制说明.md`
|
||||
- `knowledge_assets/10_本地CCRA评审机制说明.md`
|
||||
- `knowledge_assets/README.md`
|
||||
- `local_ccra_reviews/README.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/05_WEB_LOCAL_CCRA_COMPARISON.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/agent-invocation-packet.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/gate-manifest.yaml`
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.json`
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/bundle-audit.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.json`
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/gate-run-report.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.json`
|
||||
- `local_ccra_reviews/round-04/pilot-01/helper-outputs/lifecycle-status-guard-scan.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/lifecycle-guard-config.yaml`
|
||||
- `local_ccra_reviews/round-04/pilot-01/owner-decision.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/prompt-to-send.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/returned-output.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/review-context.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/review-file-manifest.json`
|
||||
- `local_ccra_reviews/round-04/pilot-01/review-metadata.json`
|
||||
- `local_ccra_reviews/round-04/pilot-01/run-notes.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/agent-invocation-packet.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/gate-manifest.yaml`
|
||||
- `local_ccra_reviews/round-04/pilot-02/helper-outputs/bundle-audit.json`
|
||||
- `local_ccra_reviews/round-04/pilot-02/helper-outputs/bundle-audit.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/helper-outputs/gate-run-report.json`
|
||||
- `local_ccra_reviews/round-04/pilot-02/helper-outputs/gate-run-report.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/lifecycle-guard-config.yaml`
|
||||
- `local_ccra_reviews/round-04/pilot-02/owner-decision.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/prompt-to-send.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/review-metadata.json`
|
||||
- `local_ccra_reviews/round-04/pilot-02/run-notes.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/turn-prompts/comparison-turn.prompt.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/turn-prompts/planning-turn.prompt.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/turn-prompts/review-turn.prompt.md`
|
||||
- `models/intellectual_archaeology.model.json`
|
||||
- `models/model_index.json`
|
||||
- `models/qpi.model.json`
|
||||
- `models/README.md`
|
||||
- `PROJECTS.md`
|
||||
- `README.md`
|
||||
- `reports/baseline_before_content_stabilization_v0.2.md`
|
||||
- `reports/changed_files_manifest.md`
|
||||
- `reports/ChatGPT交接文档_模型库MVP_2026-06-16.md`
|
||||
- `reports/ChatGPT交接文档_模型库MVP_第二轮内容稳定化_2026-06-16.md`
|
||||
- `reports/Codex_工程产物摘要_v0.1.md`
|
||||
- `reports/Codex_本地CCRA规划落地_2026-06-19.md`
|
||||
- `reports/Codex_模型资产链路摘要_v0.1.md`
|
||||
- `reports/Codex新会话交接文档_CCRA评审后处理_2026-06-16.md`
|
||||
- `reports/Codex新会话交接文档_QPI案例草稿审阅与第三轮后续_2026-06-17.md`
|
||||
- `reports/Codex新会话交接文档_Round03.1评审后续_2026-06-17.md`
|
||||
- `reports/Codex新会话交接文档_Round03.2a评审准备_2026-06-17.md`
|
||||
- `reports/Codex新会话交接文档_Round03.2评审准备_2026-06-17.md`
|
||||
- `reports/Codex新会话交接文档_Round04.1关闭与Round05准备_2026-06-18.md`
|
||||
- `reports/Codex新会话交接文档_模型库MVP_2026-06-16.md`
|
||||
- `reports/command_log.md`
|
||||
- `reports/content_review_report.md`
|
||||
- `reports/content_review_report_v0.2.md`
|
||||
- `reports/evidence_coverage_matrix.md`
|
||||
- `reports/evidence_coverage_report_v0.2.md`
|
||||
- `reports/GPT规划落地差异检查_v0.1.md`
|
||||
- `reports/GPT讨论上下文_QPI草稿案例审阅_2026-06-17.md`
|
||||
- `reports/index_check_report.md`
|
||||
- `reports/index_rebuild_report.md`
|
||||
- `reports/model_card_sync_report_v0.2.md`
|
||||
- `reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md`
|
||||
- `reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md`
|
||||
- `reports/model_case_preprocessing/qpi/round-01/README.md`
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md`
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md`
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md`
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-engineering-center.cases.md`
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md`
|
||||
- `reports/model_case_preprocessing/qpi/round-01/year-end-review-research-office.cases.md`
|
||||
- `reports/model_review_status.json`
|
||||
- `reports/next_action_register_v0.2.md`
|
||||
- `reports/open_questions_for_CCRA.md`
|
||||
- `reports/README.md`
|
||||
- `reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md`
|
||||
- `reports/Round04_blind_input_candidates_2026-06-18.md`
|
||||
- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
|
||||
- `reports/schema_change_notes.md`
|
||||
- `reports/selector_calibration_smoke_report.md`
|
||||
- `reports/selector_regression_report.md`
|
||||
- `reports/selector_regression_report_v0.2.md`
|
||||
- `reports/selector_score_breakdown.md`
|
||||
- `reports/validation_report.md`
|
||||
- `reports/内容修复检查摘要_v0.1.md`
|
||||
- `reports/内容修复检查摘要_v0.2.md`
|
||||
- `reports/规则Schema工作流检查摘要_v0.1.md`
|
||||
- `requirements/ccpe/2026-06-19-ccra-local-reviewer-runtime-patch1.md`
|
||||
- `requirements/ccpe/2026-06-19-ccra-local-reviewer-runtime.md`
|
||||
- `requirements/ccpe/README.md`
|
||||
- `requirements/skills-vault/2026-06-18-review-bundle-zip-packager.md`
|
||||
- `requirements/skills-vault/README.md`
|
||||
- `schemas/card_index.schema.json`
|
||||
- `schemas/model_card.schema.json`
|
||||
- `schemas/model_index.schema.json`
|
||||
- `schemas/model_spec.schema.json`
|
||||
- `schemas/README.md`
|
||||
- `schemas/regression_case.schema.json`
|
||||
- `schemas/source_article.schema.json`
|
||||
- `schemas/source_excerpt.schema.json`
|
||||
- `scripts/README.md`
|
||||
- `selector/qpi_case_digests.json`
|
||||
- `selector/README.md`
|
||||
- `selector/round04_blind_inputs.json`
|
||||
- `selector/selector_calibration_inputs.json`
|
||||
- `selector/selector_examples.json`
|
||||
- `selector/selector_rules.json`
|
||||
- `sources/evidence_coverage.matrix.json`
|
||||
- `sources/README.md`
|
||||
- `sources/source_articles.json`
|
||||
- `sources/source_excerpts.json`
|
||||
- `tests/intellectual_archaeology.regression.json`
|
||||
- `tests/qpi.regression.json`
|
||||
- `tests/README.md`
|
||||
- `tests/regression_cases.json`
|
||||
- `tests/regression_index.json`
|
||||
|
|
@ -0,0 +1,38 @@
|
|||
watched_paths:
|
||||
- "**/*.md"
|
||||
- "**/*.json"
|
||||
- "**/*.yaml"
|
||||
- "**/*.yml"
|
||||
status_fields:
|
||||
- status
|
||||
- lifecycle
|
||||
- model.status
|
||||
- model.lifecycle
|
||||
forbidden_status_values:
|
||||
- stable
|
||||
- accepted
|
||||
- owner-approved
|
||||
- ccra-approved
|
||||
warning_status_values:
|
||||
- candidate
|
||||
- ready-for-review
|
||||
required_evidence_markers:
|
||||
- owner_decision
|
||||
- owner decision
|
||||
- ccra_review
|
||||
- ccra review
|
||||
- web ccra
|
||||
approved_phrases:
|
||||
- owner-approved
|
||||
- ccra-approved
|
||||
- Owner approved
|
||||
- CCRA approved
|
||||
forbidden_phrases:
|
||||
- production-ready
|
||||
- released to production
|
||||
- final approved
|
||||
allowed_contexts:
|
||||
- do not say
|
||||
- must not claim
|
||||
- example:
|
||||
evidence_window_chars: 240
|
||||
|
|
@ -0,0 +1,300 @@
|
|||
# Local CCRA Next Review Requirements
|
||||
|
||||
## 1. Return Metadata
|
||||
|
||||
- project_id: `the-mindscape-of-bro-tsong`
|
||||
- review_round: `round-04`
|
||||
- local_pass: `pilot-02`
|
||||
- turn_type: `planning_turn`
|
||||
- runtime_id: `ccra-local-review`
|
||||
- runtime_version: `0.1.1`
|
||||
- agent_id: `ccra-local-reviewer`
|
||||
- agent_version: `0.1.1`
|
||||
- invocation_mode: `prompt_path_reference`
|
||||
- carrier_type: `codex_thread`
|
||||
- child_session_id: `019edcde-24be-7593-99b2-5cf014467340`
|
||||
- same_child_session_as_review_turn: `yes`
|
||||
- first_turn_report_path: `local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md`
|
||||
- owner_decision_path: `local_ccra_reviews/round-04/pilot-02/owner-decision.md`
|
||||
- planning_output_path: `local_ccra_reviews/round-04/pilot-02/next-review-requirements.md`
|
||||
- generated_at: `2026-06-19`
|
||||
|
||||
## 2. Planning Scope
|
||||
|
||||
- next_review_goal: define the submitted materials and verification evidence required for a Round 04.1 post-patch routing verification / regression pass.
|
||||
- target_round_or_pass: `round-04.1_selector-rule-patch_verification`
|
||||
- planning_basis:
|
||||
- `local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/owner-decision.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/agent-invocation-packet.md`
|
||||
- explicit_non_goals:
|
||||
- Do not re-review the full initial Round 04 bundle in this planning turn.
|
||||
- Do not use this planning output as Owner approval.
|
||||
- Do not treat Round 04.1 verification as Round 05 acceptance.
|
||||
- Do not promote QPI or Intellectual Archaeology lifecycle status.
|
||||
- Do not modify selector rules, tests, knowledge assets, model files, or review bundles in this turn.
|
||||
|
||||
Owner decision status is still `pending`. This plan therefore defines required review materials and recommended defaults; it does not convert the first-turn findings into accepted work.
|
||||
|
||||
## 3. Required Submitted Materials
|
||||
|
||||
```text
|
||||
- material_id: M-01-review-brief
|
||||
required_path_or_bundle_slot: ccra_review_bundle/<round-04.1>/00_OPEN_THIS_FIRST_*.md
|
||||
purpose: state the review goal, target failures, non-goals, and authority boundary.
|
||||
required: yes
|
||||
notes: Must say this is a post-patch verification pass, not a second blind test and not lifecycle promotion.
|
||||
|
||||
- material_id: M-02-rule-patch-summary-and-diff
|
||||
required_path_or_bundle_slot: ccra_review_bundle/<round-04.1>/01_RULE_PATCH_SUMMARY_AND_DIFF_*.md
|
||||
purpose: show exactly what selector rule surfaces changed and why.
|
||||
required: yes
|
||||
notes: Must map changes to R04-BI-002, R04-BI-024, R04-BI-035, R04-BI-036, and any accepted same-class case such as R04-BI-022.
|
||||
|
||||
- material_id: M-03-expected-routing-labels-or-owner-decisions
|
||||
required_path_or_bundle_slot: ccra_review_bundle/<round-04.1>/02_EXPECTED_ROUTING_LABELS_*.md or owner-decision-backed equivalent
|
||||
purpose: prevent Web CCRA from inferring target labels from prose.
|
||||
required: yes
|
||||
notes: Must separate must-fix, same-class boundary, calibration-only, and explicitly-not-patched cases.
|
||||
|
||||
- material_id: M-04-post-patch-routing-verification-report
|
||||
required_path_or_bundle_slot: reports/Round04_1_post_patch_routing_verification_report_*.md and bundle copy
|
||||
purpose: provide full frozen-pool rerun after the patch.
|
||||
required: yes
|
||||
notes: Must include all 38 Round 04 inputs, not only target cases.
|
||||
|
||||
- material_id: M-05-before-after-routing-diff
|
||||
required_path_or_bundle_slot: helper-outputs/routing-behavior-diff.md or a report section with equivalent table
|
||||
purpose: show target changes, non-target changes, accepted collateral behavior, and regressions.
|
||||
required: yes
|
||||
notes: If the helper cannot run, include a manual before/after table and explain the missing helper risk.
|
||||
|
||||
- material_id: M-06-regression-and-command-log
|
||||
required_path_or_bundle_slot: ccra_review_bundle/<round-04.1>/04_REGRESSION_AND_COMMAND_LOG_*.md
|
||||
purpose: prove executed tests and validation gates, not dry-run declarations.
|
||||
required: yes
|
||||
notes: Include exact commands, exit codes, timestamps or run context, and changed-file impact.
|
||||
|
||||
- material_id: M-07-existing-selector-regression
|
||||
required_path_or_bundle_slot: reports/selector_regression_report*.md or command log section
|
||||
purpose: prove existing no-call, model-exclusion, QPI-before-IA, and depth-limiting protections still pass.
|
||||
required: yes
|
||||
notes: Must not rely only on targeted target-case checks.
|
||||
|
||||
- material_id: M-08-calibration-smoke
|
||||
required_path_or_bundle_slot: reports/selector_calibration_smoke_report*.md or command log section
|
||||
purpose: prove direct-execution, QPI, and IA boundaries remain sane after patch.
|
||||
required: yes
|
||||
notes: Especially watch translation/direct transformation and IA trigger over-expansion.
|
||||
|
||||
- material_id: M-09-bundle-manifest
|
||||
required_path_or_bundle_slot: ccra_review_bundle/<round-04.1>/BUNDLE_FILE_MANIFEST_*.md
|
||||
purpose: let reviewers inspect package completeness without relying on upload order.
|
||||
required: yes
|
||||
notes: Use versioned filenames to avoid Web ChatGPT file confusion.
|
||||
|
||||
- material_id: M-10-optional-raw-changed-files
|
||||
required_path_or_bundle_slot: ccra_review_bundle/<round-04.1>/optional_raw_changed_files_<round>.zip
|
||||
purpose: allow exact inspection of selector, tests, scripts, reports, and relevant docs.
|
||||
required: yes
|
||||
notes: Preserve source-relative paths. Include zip validation/readback summary.
|
||||
|
||||
- material_id: M-11-local-ccra-first-turn-report
|
||||
required_path_or_bundle_slot: local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md
|
||||
purpose: optional context for Web CCRA on why these verification requirements exist.
|
||||
required: no
|
||||
notes: Include in Web upload only if Owner explicitly asks Web CCRA to review Local CCRA findings.
|
||||
|
||||
- material_id: M-12-owner-decision-record
|
||||
required_path_or_bundle_slot: local_ccra_reviews/round-04/pilot-02/owner-decision.md or round-specific decision note
|
||||
purpose: show which findings and same-class boundaries Owner accepted, rejected, or deferred.
|
||||
required: yes before final acceptance claims
|
||||
notes: Current status is pending; absence blocks acceptance language, not evidence collection.
|
||||
```
|
||||
|
||||
## 4. Required Verification Evidence
|
||||
|
||||
```text
|
||||
targeted_regression:
|
||||
required: yes
|
||||
cases: R04-BI-002, R04-BI-024, R04-BI-035, R04-BI-036
|
||||
conditional_cases: R04-BI-022 if Owner accepts it as same-class QPI-limited intent
|
||||
expected: target failures change in the intended direction only.
|
||||
|
||||
full_frozen_pool_rerun_or_before_after_comparison:
|
||||
required: yes
|
||||
scope: all 38 Round 04 inputs
|
||||
expected: selected_models, rejected_models, no_call, score, reasons, penalties, and routing_notes before/after.
|
||||
|
||||
existing_regression_or_unit_tests:
|
||||
required: yes
|
||||
minimum: round04 runner tests, selector regression, any post-patch verification tests, and touched selector helper tests.
|
||||
expected: executed, not dry-run.
|
||||
|
||||
calibration_smoke:
|
||||
required: yes
|
||||
expected: no-call, direct execution, QPI problem-definition, IA refusal, QPI-before-IA, and depth-limiting smoke coverage.
|
||||
|
||||
validation_report:
|
||||
required: yes
|
||||
minimum: index check and model library validation if package claims model-library consistency.
|
||||
expected: no lifecycle upgrade from validation pass.
|
||||
|
||||
command_log:
|
||||
required: yes
|
||||
minimum: command, working directory, exit code, output file path, and whether files changed.
|
||||
expected: dry-run must be labeled dry-run and cannot support pass claims.
|
||||
|
||||
dry_run_acceptable: no for final verification; yes only for planning/preflight manifest readability.
|
||||
```
|
||||
|
||||
## 5. Expected Before / After Comparisons
|
||||
|
||||
```text
|
||||
- comparison_id: C-01-target-fixes
|
||||
before_source: reports/Round04_blind_routing_evaluation_report_2026-06-18.md
|
||||
after_source: reports/Round04_1_post_patch_routing_verification_report_<date>.md
|
||||
expected_fields: input_id, input_text, selected_models, rejected_models, no_call, score, reasons, penalties, routing_notes
|
||||
target_cases: R04-BI-002, R04-BI-024, R04-BI-035, R04-BI-036
|
||||
non_target_cases_to_watch: R04-BI-001, R04-BI-003, R04-BI-004, R04-BI-005, R04-BI-021, R04-BI-025, R04-BI-031, R04-BI-032, R04-BI-033, R04-BI-034
|
||||
|
||||
- comparison_id: C-02-same-class-boundary
|
||||
before_source: reports/Round04_blind_routing_evaluation_report_2026-06-18.md
|
||||
after_source: post-patch frozen-pool rerun
|
||||
expected_fields: no_call, QPI selected/rejected, IA selected/rejected, exclusion reason
|
||||
target_cases: R04-BI-022 if accepted into patch scope
|
||||
non_target_cases_to_watch: all depth-limiting and IA-refusal cases, especially R04-BI-021 and R04-BI-023
|
||||
|
||||
- comparison_id: C-03-direct-execution-collateral
|
||||
before_source: initial Round 04 report plus existing selector regression
|
||||
after_source: post-patch report plus regression output
|
||||
expected_fields: no_call status and reasons for fact lookup, translation, rewrite, formatting, direct execution, how-to, dictionary judgment
|
||||
target_cases: R04-BI-002
|
||||
non_target_cases_to_watch: R04-BI-001, R04-BI-003, R04-BI-004, R04-BI-005, R04-BI-031, R04-BI-032, R04-BI-033, R04-BI-034
|
||||
|
||||
- comparison_id: C-04-calibration-not-patched
|
||||
before_source: first-turn report section 12
|
||||
after_source: post-patch report calibration section
|
||||
expected_fields: unchanged/deferred status, reason, Owner/Web question
|
||||
target_cases: none
|
||||
non_target_cases_to_watch: R04-BI-010 through R04-BI-017, R04-BI-018, R04-BI-026, R04-BI-027, R04-BI-030, R04-BI-037, R04-BI-038
|
||||
```
|
||||
|
||||
## 6. Open Owner Decisions
|
||||
|
||||
```text
|
||||
- decision_id: OD-R04-001
|
||||
decision_needed: accept the four must-fix initial Round 04 target failures as the patch target.
|
||||
options: accept_all | accept_subset | request_web_baseline_comparison_first
|
||||
recommended_default: accept_all
|
||||
blocks_next_review: no for evidence collection; yes for final acceptance language.
|
||||
|
||||
- decision_id: OD-R04-002
|
||||
decision_needed: classify R04-BI-022 as must-fix same-class, calibration-only, or acceptable conservative no-call.
|
||||
options: include_in_patch | calibration_only | leave_no_call
|
||||
recommended_default: include_in_patch
|
||||
blocks_next_review: yes if the next package claims R04-BI-022 as accepted collateral or target behavior.
|
||||
|
||||
- decision_id: OD-R04-003
|
||||
decision_needed: define policy for descriptive governance/capacity statements without explicit requests.
|
||||
options: provisional_qpi | ask_clarifying_question | no_call_until_request
|
||||
recommended_default: ask_clarifying_question or provisional_qpi with low confidence.
|
||||
blocks_next_review: no for narrow patch verification; yes for broader selector maturity claims.
|
||||
|
||||
- decision_id: OD-R04-004
|
||||
decision_needed: define direct IA versus QPI-first route for natural model-extraction/deep-mechanism inputs.
|
||||
options: direct_ia_when_depth_intent_clear | qpi_first_always | qpi_plus_ia_when_both_signals_present
|
||||
recommended_default: qpi_plus_ia_when both clear depth intent and model-extraction intent appear.
|
||||
blocks_next_review: no for narrow patch verification; yes for IA route maturity claims.
|
||||
|
||||
- decision_id: OD-R04-005
|
||||
decision_needed: decide whether helper profile tuning is required before formal Round 05 Local CCRA use.
|
||||
options: tune_now | document_limitations | defer
|
||||
recommended_default: document_limitations for this pilot, tune before repeated formal use.
|
||||
blocks_next_review: no, if limitations are explicit.
|
||||
```
|
||||
|
||||
## 7. Explicit Non-Goals
|
||||
|
||||
```text
|
||||
- non_goal: no lifecycle status upgrade
|
||||
reason: QPI and Intellectual Archaeology remain draft / B / pending until Owner / CCRA lifecycle authority changes that.
|
||||
|
||||
- non_goal: no Round 05 acceptance claim
|
||||
reason: Round 04.1 verification only proves a scoped selector patch if evidence passes.
|
||||
|
||||
- non_goal: no second blind test claim
|
||||
reason: after expected labels and target cases exist, this is a post-patch verification pass, not blind evaluation.
|
||||
|
||||
- non_goal: no broad governance/capacity keyword patch
|
||||
reason: those cases are calibration-only until Owner/Web policy is explicit.
|
||||
|
||||
- non_goal: no IA trigger broadening without calibration
|
||||
reason: IA is a deep model and should not become default because of words like structure, mechanism, long-term, or model.
|
||||
|
||||
- non_goal: no LLM selector, RAG, database, frontend, backend, user system, or third model
|
||||
reason: outside model_library_mvp selector patch scope.
|
||||
|
||||
- non_goal: no helper exit-code absolutism
|
||||
reason: helper output is evidence only; profile mismatch, dry-run, and broad scans must be judged by the reviewer.
|
||||
```
|
||||
|
||||
## 8. Recommended Web CCRA Review Questions
|
||||
|
||||
1. Do the Round 04.1 submitted materials prove the four target cases were fixed without creating non-target regressions across the full frozen 38-case pool?
|
||||
2. Should `R04-BI-022` be treated as an accepted same-class QPI-limited override, calibration-only, or conservative no-call?
|
||||
3. Are governance/capacity descriptive cases (`R04-BI-010` through `R04-BI-017`) better handled as provisional QPI, clarification, or no-call until the user asks for analysis?
|
||||
4. Should natural model-extraction/deep-mechanism cases (`R04-BI-018`, `026`, `027`, `038`) directly select IA, select QPI first, or select both when depth intent is explicit?
|
||||
5. Is the verification package sufficient to avoid a further small patch round, or should remaining boundary issues be deferred into a broader calibration round?
|
||||
6. Does any wording in the package imply lifecycle promotion, Round 05 acceptance, or Owner/Web approval beyond the evidence?
|
||||
|
||||
## 9. Material Package Checklist
|
||||
|
||||
```text
|
||||
review_brief:
|
||||
required: yes
|
||||
pass_condition: states target scope, non-goals, and post-patch verification identity.
|
||||
|
||||
rule_or_model_diff:
|
||||
required: yes
|
||||
pass_condition: selector rule changes mapped to target cases; no model content/lifecycle changes unless separately justified.
|
||||
|
||||
expected_labels_or_decisions:
|
||||
required: yes
|
||||
pass_condition: target, same-class, calibration-only, and explicitly-not-patched cases are separated.
|
||||
|
||||
post_patch_verification_report:
|
||||
required: yes
|
||||
pass_condition: all 38 frozen inputs rerun with score/reason details.
|
||||
|
||||
regression_and_command_log:
|
||||
required: yes
|
||||
pass_condition: commands executed with exit codes; no dry-run used as pass evidence.
|
||||
|
||||
bundle_manifest:
|
||||
required: yes
|
||||
pass_condition: versioned manifest names recognized by human reviewer even if generic helper profile is noisy.
|
||||
|
||||
optional_raw_changed_files:
|
||||
required: yes
|
||||
pass_condition: source-relative zip entries and readback/validation summary included.
|
||||
|
||||
local_ccra_report:
|
||||
required: optional
|
||||
pass_condition: included only with Owner approval; otherwise referenced locally, not uploaded as formal Web evidence.
|
||||
|
||||
owner_decision_record:
|
||||
required: yes before acceptance claims
|
||||
pass_condition: records accepted, rejected, deferred, or escalated findings; current `pending` is not acceptance.
|
||||
```
|
||||
|
||||
## 10. Limits And Carry-Forward Risks
|
||||
|
||||
- Owner decision remains pending. The next package may gather evidence, but it should not claim accepted fixes without a decision record.
|
||||
- The first-turn report identified clear `fix_now` targets but did not inspect any post-patch evidence. The next review must not cite this plan as proof that the patch worked.
|
||||
- `routing-behavior-diff-audit` was skipped in review_turn for good reason, but before/after routing comparison is required for the post-patch pass.
|
||||
- `regression-validation-gate-runner` was dry-run only. The next package needs executed gates if it claims verification.
|
||||
- `review-bundle-audit` used a generic profile that did not recognize versioned bundle manifests. Human-readable bundle manifest evidence is still required, and helper profile limitations should be documented.
|
||||
- `lifecycle-status-guard-scan` was broad and noisy. The next review should include a lifecycle/scope guard section focused on the submitted package, not a whole-repository false-positive dump.
|
||||
- Calibration-only cases must stay explicitly out of the narrow patch acceptance claim. They can be listed as next-round policy questions, not evidence that the patch is incomplete.
|
||||
- Current project docs may contain later Round 04.1 language. The next review should clearly distinguish source evidence, patch evidence, closeout language, and lifecycle claims.
|
||||
|
|
@ -0,0 +1,9 @@
|
|||
# Owner Decision
|
||||
|
||||
## Status
|
||||
|
||||
- decision_status: pending
|
||||
|
||||
## Notes
|
||||
|
||||
This is a Patch 1 retest pilot. No Local CCRA finding is accepted until Owner records a decision here or in a later instruction.
|
||||
|
|
@ -0,0 +1,40 @@
|
|||
# Prompt To Send: CCRA Local Review Patch 1 Pilot
|
||||
|
||||
You are being invoked as a real child review session for `ccra-local-reviewer`.
|
||||
|
||||
This is not main-session roleplay. If you cannot comply with the file-first invocation packet, report that you are blocked.
|
||||
|
||||
Start with the review turn prompt:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\turn-prompts\review-turn.prompt.md
|
||||
```
|
||||
|
||||
Read and follow the invocation packet:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\agent-invocation-packet.md
|
||||
```
|
||||
|
||||
Required project knowledge base:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets
|
||||
```
|
||||
|
||||
Use this path directly. Do not create a second Local CCRA copy of the knowledge base.
|
||||
|
||||
Hard constraints:
|
||||
|
||||
- `turn_type: review_turn`.
|
||||
- Read local files directly.
|
||||
- Read the required `knowledge_assets/` knowledge base.
|
||||
- Cite the files actually read.
|
||||
- Use helper outputs only as evidence, not as judgment.
|
||||
- Do not modify project files except the contracted output files:
|
||||
- `local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/returned-output.md`
|
||||
- Do not read or use Round 04.1 post-patch outcome files during this review turn.
|
||||
- Do not edit selector rules, model cards, model JSON, regression cases, review bundles, or Owner decision files.
|
||||
- Do not upgrade model lifecycle status.
|
||||
- Do not treat this pilot as Round 05 acceptance.
|
||||
|
|
@ -0,0 +1,25 @@
|
|||
# Returned Output
|
||||
|
||||
- review_round: `round-04`
|
||||
- local_pass: `pilot-02`
|
||||
- child_session_id: `019edcde-24be-7593-99b2-5cf014467340`
|
||||
- execution_status: `returned`
|
||||
- simulation_only: `false`
|
||||
|
||||
## Review Turn
|
||||
|
||||
Patch 1 Local CCRA can identify the initial Round 04 routing issues with file-first evidence. The reviewed material suggests `fix_now` for the scoped selector patch class: translation/direct transformation no-call leakage, IA refusal hard-exclusion failure, and depth-limiting phrases incorrectly suppressing lightweight QPI requests.
|
||||
|
||||
The material is not ready for Web final review, Round 05 acceptance, or lifecycle promotion from this review turn. Governance/capacity and natural IA boundary cases should go to calibration rather than immediate broad keyword patching.
|
||||
|
||||
- turn_type: `review_turn`
|
||||
- report_path: `local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md`
|
||||
|
||||
## Planning Turn
|
||||
|
||||
The same child session completed `planning_turn` and wrote the next-review requirements for Round 04.1 post-patch routing verification / regression pass.
|
||||
|
||||
- turn_type: `planning_turn`
|
||||
- planning_output_path: `local_ccra_reviews/round-04/pilot-02/next-review-requirements.md`
|
||||
- planning_conclusion: next package must submit rule patch summary, target labels/decisions, full 38-case frozen-pool before/after comparison, targeted regression, existing selector regression, calibration smoke, executed command logs, bundle manifest, and carry-forward Owner/Web calibration questions.
|
||||
- owner_decision_status: `pending`
|
||||
|
|
@ -0,0 +1,114 @@
|
|||
# Review Context
|
||||
|
||||
This context is an index. It does not replace reading source files.
|
||||
|
||||
## Metadata
|
||||
|
||||
- Review ID: `round-04-pilot-02`
|
||||
- Context profile: `ccra-local-review`
|
||||
- Status: `PASS`
|
||||
|
||||
## Source Roots
|
||||
|
||||
- `README.md`
|
||||
- `AGENTS.md`
|
||||
- `PROJECTS.md`
|
||||
- `knowledge_assets`
|
||||
- `docs/WORKFLOW.md`
|
||||
- `docs/DECISIONS.md`
|
||||
- `docs/QPI_CONTEXTUAL_ROUTING_RULES.md`
|
||||
- `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation`
|
||||
- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
|
||||
- `reports/Round04_blind_input_candidates_2026-06-18.md`
|
||||
- `selector/round04_blind_inputs.json`
|
||||
- `selector/selector_rules.json`
|
||||
- `selector/README.md`
|
||||
- `tests/test_round04_blind_routing.py`
|
||||
|
||||
## Files Included
|
||||
|
||||
- `AGENTS.md` (8063 bytes)
|
||||
- `PROJECTS.md` (6784 bytes)
|
||||
- `README.md` (7915 bytes)
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md` (1476 bytes)
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md` (2211 bytes)
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md` (1495 bytes)
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md` (29841 bytes)
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md` (1614 bytes)
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md` (1710 bytes)
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/optional_raw_changed_files_04.zip` (176893 bytes)
|
||||
- `docs/DECISIONS.md` (13018 bytes)
|
||||
- `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md` (3319 bytes)
|
||||
- `docs/QPI_CONTEXTUAL_ROUTING_RULES.md` (6769 bytes)
|
||||
- `docs/WORKFLOW.md` (7121 bytes)
|
||||
- `knowledge_assets/00_用户背景与产品上下文.md` (1550 bytes)
|
||||
- `knowledge_assets/01_核心模型地图.md` (1643 bytes)
|
||||
- `knowledge_assets/02_模型卡结构规范.md` (1514 bytes)
|
||||
- `knowledge_assets/03_核心模型抽取样板.md` (2271 bytes)
|
||||
- `knowledge_assets/06_模型稳固性评级规则.md` (1473 bytes)
|
||||
- `knowledge_assets/07_产品规划过程记录.md` (1813 bytes)
|
||||
- `knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md` (9052 bytes)
|
||||
- `knowledge_assets/09_数据治理与模型调用机制说明.md` (18643 bytes)
|
||||
- `knowledge_assets/10_本地CCRA评审机制说明.md` (6204 bytes)
|
||||
- `knowledge_assets/README.md` (1382 bytes)
|
||||
- `reports/Round04_blind_input_candidates_2026-06-18.md` (13018 bytes)
|
||||
- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md` (29841 bytes)
|
||||
- `selector/README.md` (3310 bytes)
|
||||
- `selector/round04_blind_inputs.json` (12470 bytes)
|
||||
- `selector/selector_rules.json` (7042 bytes)
|
||||
- `tests/test_round04_blind_routing.py` (2680 bytes)
|
||||
|
||||
## Files Excluded
|
||||
|
||||
- None
|
||||
|
||||
## Important Reports
|
||||
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md`
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/optional_raw_changed_files_04.zip`
|
||||
- `reports/Round04_blind_input_candidates_2026-06-18.md`
|
||||
- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
|
||||
|
||||
## Test Or Validation Outputs
|
||||
|
||||
- `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md`
|
||||
- `tests/test_round04_blind_routing.py`
|
||||
|
||||
## Diff Or Changed File References
|
||||
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/optional_raw_changed_files_04.zip`
|
||||
|
||||
## Prior Decision References
|
||||
|
||||
- `docs/DECISIONS.md`
|
||||
|
||||
## Known Non Goals
|
||||
|
||||
- `Do not decide Owner approval.`
|
||||
- `Do not replace Web CCRA final review.`
|
||||
- `Do not promote lifecycle status.`
|
||||
- `Do not modify selector rules, model cards, model JSON, regression cases, or review bundles.`
|
||||
- `Do not treat this pilot as Round 05 acceptance.`
|
||||
- `Do not use Round 04.1 post-patch result files as review_turn evidence.`
|
||||
|
||||
## Open Questions For Reviewer Or Agent
|
||||
|
||||
- `Does review_turn diagnose the Round 04 issue mechanism as sharply as Web CCRA lines 1-214?`
|
||||
- `Does review_turn separate must-fix, same-class boundary, calibration-only, and explicitly-not-patched cases?`
|
||||
- `Does planning_turn specify the next review requirements and submitted materials?`
|
||||
- `Does the same child session persist across review_turn and planning_turn?`
|
||||
- `Is the patched runtime ready for formal use, or does it need another CCPE tuning pass?`
|
||||
|
||||
## Blocking Errors
|
||||
|
||||
- None
|
||||
|
||||
## Machine Readable Manifest
|
||||
|
||||
- `review-file-manifest.json`
|
||||
|
|
@ -0,0 +1,270 @@
|
|||
{
|
||||
"review_id": "round-04-pilot-02",
|
||||
"context_profile": "ccra-local-review",
|
||||
"project_root": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong",
|
||||
"source_roots": [
|
||||
"README.md",
|
||||
"AGENTS.md",
|
||||
"PROJECTS.md",
|
||||
"knowledge_assets",
|
||||
"docs/WORKFLOW.md",
|
||||
"docs/DECISIONS.md",
|
||||
"docs/QPI_CONTEXTUAL_ROUTING_RULES.md",
|
||||
"docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation",
|
||||
"reports/Round04_blind_routing_evaluation_report_2026-06-18.md",
|
||||
"reports/Round04_blind_input_candidates_2026-06-18.md",
|
||||
"selector/round04_blind_inputs.json",
|
||||
"selector/selector_rules.json",
|
||||
"selector/README.md",
|
||||
"tests/test_round04_blind_routing.py"
|
||||
],
|
||||
"missing_source_roots": [],
|
||||
"files_included": [
|
||||
{
|
||||
"path": "AGENTS.md",
|
||||
"size_bytes": 8063,
|
||||
"source_root": "AGENTS.md"
|
||||
},
|
||||
{
|
||||
"path": "PROJECTS.md",
|
||||
"size_bytes": 6784,
|
||||
"source_root": "PROJECTS.md"
|
||||
},
|
||||
{
|
||||
"path": "README.md",
|
||||
"size_bytes": 7915,
|
||||
"source_root": "README.md"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md",
|
||||
"size_bytes": 1476,
|
||||
"source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md",
|
||||
"size_bytes": 2211,
|
||||
"source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md",
|
||||
"size_bytes": 1495,
|
||||
"source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md",
|
||||
"size_bytes": 29841,
|
||||
"source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md",
|
||||
"size_bytes": 1614,
|
||||
"source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md",
|
||||
"size_bytes": 1710,
|
||||
"source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
|
||||
},
|
||||
{
|
||||
"path": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/optional_raw_changed_files_04.zip",
|
||||
"size_bytes": 176893,
|
||||
"source_root": "ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
|
||||
},
|
||||
{
|
||||
"path": "docs/DECISIONS.md",
|
||||
"size_bytes": 13018,
|
||||
"source_root": "docs/DECISIONS.md"
|
||||
},
|
||||
{
|
||||
"path": "docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md",
|
||||
"size_bytes": 3319,
|
||||
"source_root": "docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md"
|
||||
},
|
||||
{
|
||||
"path": "docs/QPI_CONTEXTUAL_ROUTING_RULES.md",
|
||||
"size_bytes": 6769,
|
||||
"source_root": "docs/QPI_CONTEXTUAL_ROUTING_RULES.md"
|
||||
},
|
||||
{
|
||||
"path": "docs/WORKFLOW.md",
|
||||
"size_bytes": 7121,
|
||||
"source_root": "docs/WORKFLOW.md"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/00_用户背景与产品上下文.md",
|
||||
"size_bytes": 1550,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/01_核心模型地图.md",
|
||||
"size_bytes": 1643,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/02_模型卡结构规范.md",
|
||||
"size_bytes": 1514,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/03_核心模型抽取样板.md",
|
||||
"size_bytes": 2271,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/06_模型稳固性评级规则.md",
|
||||
"size_bytes": 1473,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/07_产品规划过程记录.md",
|
||||
"size_bytes": 1813,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md",
|
||||
"size_bytes": 9052,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/09_数据治理与模型调用机制说明.md",
|
||||
"size_bytes": 18643,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/10_本地CCRA评审机制说明.md",
|
||||
"size_bytes": 6204,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "knowledge_assets/README.md",
|
||||
"size_bytes": 1382,
|
||||
"source_root": "knowledge_assets"
|
||||
},
|
||||
{
|
||||
"path": "reports/Round04_blind_input_candidates_2026-06-18.md",
|
||||
"size_bytes": 13018,
|
||||
"source_root": "reports/Round04_blind_input_candidates_2026-06-18.md"
|
||||
},
|
||||
{
|
||||
"path": "reports/Round04_blind_routing_evaluation_report_2026-06-18.md",
|
||||
"size_bytes": 29841,
|
||||
"source_root": "reports/Round04_blind_routing_evaluation_report_2026-06-18.md"
|
||||
},
|
||||
{
|
||||
"path": "selector/README.md",
|
||||
"size_bytes": 3310,
|
||||
"source_root": "selector/README.md"
|
||||
},
|
||||
{
|
||||
"path": "selector/round04_blind_inputs.json",
|
||||
"size_bytes": 12470,
|
||||
"source_root": "selector/round04_blind_inputs.json"
|
||||
},
|
||||
{
|
||||
"path": "selector/selector_rules.json",
|
||||
"size_bytes": 7042,
|
||||
"source_root": "selector/selector_rules.json"
|
||||
},
|
||||
{
|
||||
"path": "tests/test_round04_blind_routing.py",
|
||||
"size_bytes": 2680,
|
||||
"source_root": "tests/test_round04_blind_routing.py"
|
||||
}
|
||||
],
|
||||
"files_excluded": [],
|
||||
"important_reports": [
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF_04.md",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/01_ROUND03_CLOSURE_AND_ROUND04_SCOPE_04.md",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/02_BLIND_INPUT_SET_04.md",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/03_ROUTING_EVALUATION_REPORT_04.md",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/04_REVIEW_QUESTIONS_FOR_GPT_04.md",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/BUNDLE_FILE_MANIFEST_04.md",
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/optional_raw_changed_files_04.zip",
|
||||
"reports/Round04_blind_input_candidates_2026-06-18.md",
|
||||
"reports/Round04_blind_routing_evaluation_report_2026-06-18.md"
|
||||
],
|
||||
"test_or_validation_outputs": [
|
||||
"docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md",
|
||||
"tests/test_round04_blind_routing.py"
|
||||
],
|
||||
"diff_or_changed_file_references": [
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/optional_raw_changed_files_04.zip"
|
||||
],
|
||||
"prior_decision_references": [
|
||||
"docs/DECISIONS.md"
|
||||
],
|
||||
"known_non_goals": [
|
||||
"Do not decide Owner approval.",
|
||||
"Do not replace Web CCRA final review.",
|
||||
"Do not promote lifecycle status.",
|
||||
"Do not modify selector rules, model cards, model JSON, regression cases, or review bundles.",
|
||||
"Do not treat this pilot as Round 05 acceptance.",
|
||||
"Do not use Round 04.1 post-patch result files as review_turn evidence."
|
||||
],
|
||||
"open_questions_for_reviewer_or_agent": [
|
||||
"Does review_turn diagnose the Round 04 issue mechanism as sharply as Web CCRA lines 1-214?",
|
||||
"Does review_turn separate must-fix, same-class boundary, calibration-only, and explicitly-not-patched cases?",
|
||||
"Does planning_turn specify the next review requirements and submitted materials?",
|
||||
"Does the same child session persist across review_turn and planning_turn?",
|
||||
"Is the patched runtime ready for formal use, or does it need another CCPE tuning pass?"
|
||||
],
|
||||
"metadata": {
|
||||
"review_id": "round-04-pilot-02",
|
||||
"project_id": "the-mindscape-of-bro-tsong",
|
||||
"review_round": "round-04",
|
||||
"local_pass": "pilot-02",
|
||||
"turn_type": "review_turn",
|
||||
"runtime_id": "ccra-local-review",
|
||||
"runtime_version": "0.1.1",
|
||||
"agent_id": "ccra-local-reviewer",
|
||||
"agent_version": "0.1.1",
|
||||
"knowledge_base_path": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\knowledge_assets",
|
||||
"review_goal": "Rerun Local CCRA after CCPE Patch 1 using initial Round 04 evidence only, then continue the same child session for next-review planning.",
|
||||
"primary_question": "Can Patch 1 Local CCRA identify Round 04 product/routing issues with Web-style diagnosis while retaining local file-first audit strength?",
|
||||
"scope_statement": "Review the initial Round 04 blind routing evaluation material as a historical pilot. Do not use Round 04.1 post-patch outcome evidence during review_turn. After review_turn, continue the same child session with planning_turn to specify the next review requirements and submitted materials.",
|
||||
"non_goals": [
|
||||
"Do not decide Owner approval.",
|
||||
"Do not replace Web CCRA final review.",
|
||||
"Do not promote lifecycle status.",
|
||||
"Do not modify selector rules, model cards, model JSON, regression cases, or review bundles.",
|
||||
"Do not treat this pilot as Round 05 acceptance.",
|
||||
"Do not use Round 04.1 post-patch result files as review_turn evidence."
|
||||
],
|
||||
"open_questions": [
|
||||
"Does review_turn diagnose the Round 04 issue mechanism as sharply as Web CCRA lines 1-214?",
|
||||
"Does review_turn separate must-fix, same-class boundary, calibration-only, and explicitly-not-patched cases?",
|
||||
"Does planning_turn specify the next review requirements and submitted materials?",
|
||||
"Does the same child session persist across review_turn and planning_turn?",
|
||||
"Is the patched runtime ready for formal use, or does it need another CCPE tuning pass?"
|
||||
],
|
||||
"target_reviewer": "ccra-local-reviewer",
|
||||
"review_bundle_paths": [
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
|
||||
],
|
||||
"excluded_hindsight_evidence": [
|
||||
"reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
|
||||
],
|
||||
"web_baseline_source": "C:\\Users\\wangq\\Documents\\Codex\\knowledge-vault\\work\\internal\\强哥的思想宇宙\\讨论\\2026-06-18产品交流-GPT.md",
|
||||
"web_baseline_range": "lines 1-214",
|
||||
"web_final_review_policy": "owner_must_approve_inclusion",
|
||||
"output_report_path": "local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md",
|
||||
"planning_output_path": "local_ccra_reviews/round-04/pilot-02/next-review-requirements.md",
|
||||
"returned_output_path": "local_ccra_reviews/round-04/pilot-02/returned-output.md",
|
||||
"created_at": "2026-06-19"
|
||||
},
|
||||
"blocking_errors": [],
|
||||
"machine_readable_summary": {
|
||||
"status": "PASS",
|
||||
"source_roots_count": 15,
|
||||
"missing_source_roots_count": 0,
|
||||
"files_included_count": 30,
|
||||
"files_excluded_count": 0,
|
||||
"important_reports_count": 9,
|
||||
"validation_outputs_count": 2,
|
||||
"diff_references_count": 1,
|
||||
"prior_decisions_count": 1,
|
||||
"blocking_error_count": 0
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,45 @@
|
|||
{
|
||||
"review_id": "round-04-pilot-02",
|
||||
"project_id": "the-mindscape-of-bro-tsong",
|
||||
"review_round": "round-04",
|
||||
"local_pass": "pilot-02",
|
||||
"turn_type": "review_turn",
|
||||
"runtime_id": "ccra-local-review",
|
||||
"runtime_version": "0.1.1",
|
||||
"agent_id": "ccra-local-reviewer",
|
||||
"agent_version": "0.1.1",
|
||||
"knowledge_base_path": "C:\\Users\\wangq\\Documents\\Codex\\work-projects\\the-mindscape-of-bro-tsong\\knowledge_assets",
|
||||
"review_goal": "Rerun Local CCRA after CCPE Patch 1 using initial Round 04 evidence only, then continue the same child session for next-review planning.",
|
||||
"primary_question": "Can Patch 1 Local CCRA identify Round 04 product/routing issues with Web-style diagnosis while retaining local file-first audit strength?",
|
||||
"scope_statement": "Review the initial Round 04 blind routing evaluation material as a historical pilot. Do not use Round 04.1 post-patch outcome evidence during review_turn. After review_turn, continue the same child session with planning_turn to specify the next review requirements and submitted materials.",
|
||||
"non_goals": [
|
||||
"Do not decide Owner approval.",
|
||||
"Do not replace Web CCRA final review.",
|
||||
"Do not promote lifecycle status.",
|
||||
"Do not modify selector rules, model cards, model JSON, regression cases, or review bundles.",
|
||||
"Do not treat this pilot as Round 05 acceptance.",
|
||||
"Do not use Round 04.1 post-patch result files as review_turn evidence."
|
||||
],
|
||||
"open_questions": [
|
||||
"Does review_turn diagnose the Round 04 issue mechanism as sharply as Web CCRA lines 1-214?",
|
||||
"Does review_turn separate must-fix, same-class boundary, calibration-only, and explicitly-not-patched cases?",
|
||||
"Does planning_turn specify the next review requirements and submitted materials?",
|
||||
"Does the same child session persist across review_turn and planning_turn?",
|
||||
"Is the patched runtime ready for formal use, or does it need another CCPE tuning pass?"
|
||||
],
|
||||
"target_reviewer": "ccra-local-reviewer",
|
||||
"review_bundle_paths": [
|
||||
"ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation"
|
||||
],
|
||||
"excluded_hindsight_evidence": [
|
||||
"reports/Round04_1_post_patch_routing_verification_report_2026-06-18.md",
|
||||
"ccra_review_bundle/round-04.1_2026-06-18_selector-rule-patch"
|
||||
],
|
||||
"web_baseline_source": "C:\\Users\\wangq\\Documents\\Codex\\knowledge-vault\\work\\internal\\强哥的思想宇宙\\讨论\\2026-06-18产品交流-GPT.md",
|
||||
"web_baseline_range": "lines 1-214",
|
||||
"web_final_review_policy": "owner_must_approve_inclusion",
|
||||
"output_report_path": "local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md",
|
||||
"planning_output_path": "local_ccra_reviews/round-04/pilot-02/next-review-requirements.md",
|
||||
"returned_output_path": "local_ccra_reviews/round-04/pilot-02/returned-output.md",
|
||||
"created_at": "2026-06-19"
|
||||
}
|
||||
|
|
@ -0,0 +1,92 @@
|
|||
# Local CCRA Run Notes
|
||||
|
||||
## Run Identity
|
||||
|
||||
- review_round: round-04
|
||||
- local_pass: pilot-02
|
||||
- review_run_dir: `local_ccra_reviews/round-04/pilot-02`
|
||||
- runtime_id: ccra-local-review
|
||||
- runtime_version: 0.1.1
|
||||
- agent_id: ccra-local-reviewer
|
||||
- agent_version: 0.1.1
|
||||
- pilot_status: setup_in_progress
|
||||
|
||||
## Purpose
|
||||
|
||||
Second historical pilot after CCPE Patch 1.
|
||||
|
||||
This pilot checks:
|
||||
|
||||
1. Whether Patch 1 improves Web-style product diagnosis while preserving local full-file audit.
|
||||
2. Whether `review_turn` can identify Round 04 issues without using Round 04.1 hindsight evidence.
|
||||
3. Whether the same child session can continue with `planning_turn`.
|
||||
4. Whether `planning_turn` can produce next-review requirements and submitted-material guidance.
|
||||
5. Whether the output improves against pilot-01 and Web CCRA baseline lines 1-214.
|
||||
|
||||
This pilot is not Round 05 acceptance.
|
||||
|
||||
## Source Evidence Scope
|
||||
|
||||
Primary review-turn evidence:
|
||||
|
||||
- `ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/`
|
||||
- `reports/Round04_blind_routing_evaluation_report_2026-06-18.md`
|
||||
- `reports/Round04_blind_input_candidates_2026-06-18.md`
|
||||
- `selector/round04_blind_inputs.json`
|
||||
- `selector/selector_rules.json`
|
||||
- `selector/README.md`
|
||||
- `tests/test_round04_blind_routing.py`
|
||||
|
||||
Required knowledge base:
|
||||
|
||||
- `knowledge_assets/`
|
||||
|
||||
Fair-comparison exclusion:
|
||||
|
||||
- Round 04.1 post-patch result files are intentionally excluded from `review_turn` evidence. The purpose is to compare with the Web CCRA / GPT initial Round 04 review baseline, `2026-06-18产品交流-GPT.md` lines 1-214, without giving the child reviewer hindsight from the later patch result.
|
||||
|
||||
## Helper Commands
|
||||
|
||||
- `review-context-builder`: exit 0. `review-context.md` and `review-file-manifest.json` generated; no missing source roots; required `knowledge_assets/` included.
|
||||
- `review-bundle-audit`: exit 1. Generic profile reports missing `manifest` and `validation_sidecar`; `BUNDLE_FILE_MANIFEST_04.md` exists but is treated as extra by the generic profile.
|
||||
- `routing-behavior-diff-audit`: skipped for `review_turn`; no before/after patch result is included in the initial Round 04 evidence scope.
|
||||
- `regression-validation-gate-runner --mode dry_run`: exit 0. Three gates declared and skipped as dry run.
|
||||
- `lifecycle-status-guard-scan`: exit 1. Scan reports blocking lifecycle/status candidates; many are broad-scope findings from older review materials and pilot-01 helper outputs, so reviewer must classify confidence/noise rather than treat the helper result as automatic judgment.
|
||||
|
||||
## Dispatch Record
|
||||
|
||||
- carrier_type: codex_thread
|
||||
- invocation_mode: prompt_path_reference
|
||||
- child_session_id: `019edcde-24be-7593-99b2-5cf014467340`
|
||||
- review_turn_status: returned
|
||||
- planning_turn_status: returned
|
||||
- review_turn_duration_ms: 512317
|
||||
- planning_turn_duration_ms: 342925
|
||||
|
||||
## Return Record
|
||||
|
||||
- review_report_path: `local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md`
|
||||
- planning_output_path: `local_ccra_reviews/round-04/pilot-02/next-review-requirements.md`
|
||||
- returned_output_path: `local_ccra_reviews/round-04/pilot-02/returned-output.md`
|
||||
- return_status: review_and_planning_returned
|
||||
|
||||
## Comparison Plan
|
||||
|
||||
After both child turns return, compare:
|
||||
|
||||
1. Web baseline: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\讨论\2026-06-18产品交流-GPT.md` lines 1-214.
|
||||
2. Local pilot-01: `local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md`.
|
||||
3. Local pilot-02 review turn: `local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md`.
|
||||
4. Local pilot-02 planning turn: `local_ccra_reviews/round-04/pilot-02/next-review-requirements.md`.
|
||||
|
||||
## Comparison Result
|
||||
|
||||
- comparison_report_path: `local_ccra_reviews/round-04/pilot-02/05_WEB_LOCAL_CCRA_COMPARISON.md`
|
||||
- comparison_status: completed
|
||||
- readiness_recommendation: `ready_for_formal_local_first_review_with_conditions`
|
||||
- follow_up_ccpe_patch_request: `requirements/ccpe/2026-06-19-ccra-local-reviewer-runtime-patch2.md`
|
||||
- follow_up_patch_type: non-blocking hardening
|
||||
|
||||
## Resume Notes
|
||||
|
||||
For `planning_turn`, continue the same child session recorded above and provide the first-turn report path.
|
||||
|
|
@ -0,0 +1,15 @@
|
|||
# Comparison Turn Prompt
|
||||
|
||||
## Turn Metadata
|
||||
|
||||
- turn_type: comparison_turn
|
||||
- runtime_id: ccra-local-review
|
||||
- runtime_version: 0.1.1
|
||||
- agent_id: ccra-local-reviewer
|
||||
- agent_version: 0.1.1
|
||||
- review_round: round-04
|
||||
- local_pass: pilot-02
|
||||
|
||||
## Status
|
||||
|
||||
This prompt is reserved. The main project session will perform the three-way comparison unless the Owner explicitly asks to continue the child session with `comparison_turn`.
|
||||
|
|
@ -0,0 +1,69 @@
|
|||
# Planning Turn Prompt
|
||||
|
||||
## Turn Metadata
|
||||
|
||||
- turn_type: planning_turn
|
||||
- runtime_id: ccra-local-review
|
||||
- runtime_version: 0.1.1
|
||||
- agent_id: ccra-local-reviewer
|
||||
- agent_version: 0.1.1
|
||||
- review_round: round-04
|
||||
- local_pass: pilot-02
|
||||
- same_child_session_as_review_turn_required: true
|
||||
- child_session_id: 019edcde-24be-7593-99b2-5cf014467340
|
||||
- simulation_allowed: false
|
||||
|
||||
## Task
|
||||
|
||||
Continue the same child session after `review_turn`.
|
||||
|
||||
Using the first-turn report and the unchanged initial Round 04 evidence scope, plan the next review requirements and submitted materials for:
|
||||
|
||||
```text
|
||||
Round 04.1 post-patch routing verification / regression pass
|
||||
```
|
||||
|
||||
Do not re-review the full current bundle unless new evidence has been added or the Owner explicitly asks for re-review.
|
||||
|
||||
## Required Inputs
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\04_LOCAL_CCRA_REVIEW_REPORT.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\owner-decision.md
|
||||
C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-next-review-requirements.template.md
|
||||
```
|
||||
|
||||
## Required Output
|
||||
|
||||
Write:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\next-review-requirements.md
|
||||
```
|
||||
|
||||
Update or append to:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\returned-output.md
|
||||
```
|
||||
|
||||
## Required Planning Sections
|
||||
|
||||
Use the Patch 1 planning template and include:
|
||||
|
||||
- next review goal;
|
||||
- required submitted materials;
|
||||
- required verification evidence;
|
||||
- expected before / after comparisons;
|
||||
- open Owner decisions;
|
||||
- explicit non-goals;
|
||||
- recommended Web CCRA review questions;
|
||||
- material package checklist;
|
||||
- carry-forward risks.
|
||||
|
||||
## Constraints
|
||||
|
||||
- Continue the same child session id.
|
||||
- Base the plan on the first-turn report.
|
||||
- Do not treat Local CCRA planning as Owner approval.
|
||||
- Do not modify project files outside the two contracted output files for this turn.
|
||||
|
|
@ -0,0 +1,97 @@
|
|||
# Review Turn Prompt
|
||||
|
||||
## Turn Metadata
|
||||
|
||||
- turn_type: review_turn
|
||||
- runtime_id: ccra-local-review
|
||||
- runtime_version: 0.1.1
|
||||
- agent_id: ccra-local-reviewer
|
||||
- agent_version: 0.1.1
|
||||
- review_round: round-04
|
||||
- local_pass: pilot-02
|
||||
- simulation_allowed: false
|
||||
|
||||
## Task
|
||||
|
||||
Perform the Patch 1 Local CCRA review turn for Round 04 using initial Round 04 evidence only.
|
||||
|
||||
Your primary question:
|
||||
|
||||
```text
|
||||
Can Patch 1 Local CCRA identify Round 04 product/routing issues with Web-style diagnosis while retaining local file-first audit strength?
|
||||
```
|
||||
|
||||
## Required Reads
|
||||
|
||||
Read and follow:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\agent-invocation-packet.md
|
||||
C:\Users\wangq\Documents\Codex\ccpe-system\agents\agent-specs\ccra-local-reviewer.agent.md
|
||||
C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review.runtime.md
|
||||
C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-report.template.md
|
||||
C:\Users\wangq\Documents\Codex\ccpe-system\integrations\skills-vault\ccra-local-review-helpers.integration.md
|
||||
```
|
||||
|
||||
Read the required knowledge base:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\knowledge_assets
|
||||
```
|
||||
|
||||
Use `review-context.md` and `review-file-manifest.json` as navigation aids only. They do not replace direct evidence reads.
|
||||
|
||||
## Evidence Scope
|
||||
|
||||
Use initial Round 04 evidence:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\ccra_review_bundle\round-04_2026-06-18_blind-input-routing-evaluation
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\reports\Round04_blind_routing_evaluation_report_2026-06-18.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\reports\Round04_blind_input_candidates_2026-06-18.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\selector\round04_blind_inputs.json
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\selector\selector_rules.json
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\selector\README.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\tests\test_round04_blind_routing.py
|
||||
```
|
||||
|
||||
Do not use these Round 04.1 hindsight files during review_turn:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\reports\Round04_1_post_patch_routing_verification_report_2026-06-18.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\ccra_review_bundle\round-04.1_2026-06-18_selector-rule-patch
|
||||
```
|
||||
|
||||
The exclusion is intentional for fair comparison with the Web CCRA / GPT baseline lines 1-214.
|
||||
|
||||
## Required Output
|
||||
|
||||
Write:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\04_LOCAL_CCRA_REVIEW_REPORT.md
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong\local_ccra_reviews\round-04\pilot-02\returned-output.md
|
||||
```
|
||||
|
||||
Use the Patch 1 report template and include:
|
||||
|
||||
- issue mechanism diagnosis;
|
||||
- patch scope judgment;
|
||||
- verification evidence requirements;
|
||||
- before / after behavior review, if applicable;
|
||||
- non-target behavior changes, if observable from the allowed evidence;
|
||||
- calibration-only candidates;
|
||||
- helper output confidence;
|
||||
- final action recommendation.
|
||||
|
||||
## Required Emphasis
|
||||
|
||||
Your report should decide whether the current material suggests:
|
||||
|
||||
- `fix_now`;
|
||||
- `document_only`;
|
||||
- `defer_to_calibration`;
|
||||
- `do_not_open_patch_round`;
|
||||
- `ready_for_web_review_after_local_repairs`.
|
||||
|
||||
Do not make the primary output a next-round planning document. Planning will be requested in a second turn in the same child session after this report is returned.
|
||||
|
|
@ -1,6 +1,6 @@
|
|||
{
|
||||
"index_version": "0.1",
|
||||
"last_updated": "2026-06-18",
|
||||
"last_updated": "2026-06-19",
|
||||
"models": [
|
||||
{
|
||||
"model_id": "intellectual_archaeology",
|
||||
|
|
|
|||
|
|
@ -0,0 +1,163 @@
|
|||
# Codex 本地 CCRA 规划落地摘要
|
||||
|
||||
Date: 2026-06-19
|
||||
|
||||
## 1. 当前阶段
|
||||
|
||||
项目仍处于 `model_library_mvp`。
|
||||
|
||||
本次工作已从项目侧结构规划推进到历史试运行验证。
|
||||
|
||||
Local CCRA v0.1.1 已通过 Round 04 `pilot-02` 的两回合历史试运行，可作为本项目正式本地初审使用，但不替代 Owner / Web CCRA。
|
||||
|
||||
本次仍不新增 selector、模型、RAG、前端、后端或完整 Round 级自动化平台。
|
||||
|
||||
## 2. 本轮目标
|
||||
|
||||
把已确认的 Local CCRA 规划转成当前仓库内可执行的文件规则：
|
||||
|
||||
- 第一版只服务 `the-mindscape-of-bro-tsong`。
|
||||
- Local CCRA 是正式本地初审，但不替代 Owner / Web CCRA 关键节点判断。
|
||||
- 本地评审必须通过真实 CCPE Agent Runtime 子会话，不做主会话模拟。
|
||||
- 本地评审按公共 round 版本加内部 pass 编号归档。
|
||||
- skills / companion automation 需求先交给 CCPE 分类，再决定是否转给 `skills-vault`。
|
||||
- 正式 Web CCRA 包默认不包含 Local CCRA review report。
|
||||
|
||||
## 3. 已完成内容
|
||||
|
||||
1. 新增 `local_ccra_reviews/` 运行区说明。
|
||||
2. 新增 CCPE 需求单，请求 `ccra-local-reviewer` Agent Spec、Runtime invocation protocol、session continuation contract 和 companion capability classification。
|
||||
3. 更新项目边界、工作流、数据契约、文件身份、决策日志、项目简报和 handoff 模板。
|
||||
4. 新增长期知识资产，说明项目侧 Local CCRA 机制。
|
||||
5. 运行索引与验证命令。
|
||||
6. 完成 `pilot-01` 与 Web baseline 的对比，识别 Patch 1 需求。
|
||||
7. CCPE 完成 Patch 1 后，完成 `pilot-02` 两回合试运行。
|
||||
8. 完成 Web baseline / pilot-01 / pilot-02 三方对比。
|
||||
9. 新增 Patch 2 非阻塞硬化需求单。
|
||||
10. 更新本地机制知识资产到 v0.2。
|
||||
|
||||
## 4. 关键文件路径
|
||||
|
||||
- `local_ccra_reviews/README.md`
|
||||
- `requirements/ccpe/2026-06-19-ccra-local-reviewer-runtime.md`
|
||||
- `requirements/ccpe/2026-06-19-ccra-local-reviewer-runtime-patch1.md`
|
||||
- `requirements/ccpe/2026-06-19-ccra-local-reviewer-runtime-patch2.md`
|
||||
- `knowledge_assets/10_本地CCRA评审机制说明.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md`
|
||||
- `local_ccra_reviews/round-04/pilot-01/05_WEB_LOCAL_CCRA_COMPARISON.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/next-review-requirements.md`
|
||||
- `local_ccra_reviews/round-04/pilot-02/05_WEB_LOCAL_CCRA_COMPARISON.md`
|
||||
- `docs/WORKFLOW.md`
|
||||
- `docs/DECISIONS.md`
|
||||
- `docs/DATA_CONTRACT.md`
|
||||
- `docs/FILE_TAXONOMY.md`
|
||||
- `docs/HANDOFF_TEMPLATE.md`
|
||||
- `PROJECTS.md`
|
||||
- `README.md`
|
||||
- `AGENTS.md`
|
||||
|
||||
## 5. 关键规则
|
||||
|
||||
Local CCRA run path:
|
||||
|
||||
```text
|
||||
local_ccra_reviews/<public-round>/<local-pass>/
|
||||
```
|
||||
|
||||
Example:
|
||||
|
||||
```text
|
||||
local_ccra_reviews/round-05_selector-calibration-policy/01/
|
||||
local_ccra_reviews/round-05_selector-calibration-policy/02/
|
||||
```
|
||||
|
||||
Run directory contract:
|
||||
|
||||
```text
|
||||
run-notes.md
|
||||
review-metadata.json
|
||||
gate-manifest.yaml
|
||||
lifecycle-guard-config.yaml
|
||||
agent-invocation-packet.md
|
||||
prompt-to-send.md
|
||||
turn-prompts/
|
||||
review-context.md
|
||||
review-file-manifest.json
|
||||
helper-outputs/
|
||||
04_LOCAL_CCRA_REVIEW_REPORT.md
|
||||
next-review-requirements.md
|
||||
returned-output.md
|
||||
owner-decision.md
|
||||
```
|
||||
|
||||
Formal Web CCRA bundle path remains:
|
||||
|
||||
```text
|
||||
ccra_review_bundle/round-NN_YYYY-MM-DD_topic/
|
||||
```
|
||||
|
||||
Default Web CCRA upload behavior:
|
||||
|
||||
```text
|
||||
Do not include 04_LOCAL_CCRA_REVIEW_REPORT.md unless Owner explicitly asks.
|
||||
```
|
||||
|
||||
## 6. Assumptions Made
|
||||
|
||||
- CCPE will later provide the Runtime interface documentation and invocation contract.
|
||||
- This repository should not define Runtime command details before CCPE supplies them.
|
||||
- Local CCRA companion tooling should not be sent directly to `skills-vault` until CCPE or Owner classifies the capability as reusable deterministic automation.
|
||||
- The new knowledge asset documents project-side workflow only, not the canonical Agent definition.
|
||||
|
||||
## 7. Current Local CCRA Runtime Status
|
||||
|
||||
- CCPE has supplied Patch 1-level `ccra-local-reviewer` / `ccra-local-review` behavior.
|
||||
- `pilot-02` verified real child-session invocation and same-child `review_turn` + `planning_turn`.
|
||||
- `pilot-02` child session id: `019edcde-24be-7593-99b2-5cf014467340`.
|
||||
- `review_turn` duration: 512317 ms.
|
||||
- `planning_turn` duration: 342925 ms.
|
||||
- Readiness: `ready_for_formal_local_first_review_with_conditions`.
|
||||
|
||||
Remaining hardening needs are captured in:
|
||||
|
||||
```text
|
||||
requirements/ccpe/2026-06-19-ccra-local-reviewer-runtime-patch2.md
|
||||
```
|
||||
|
||||
Patch 2 is non-blocking if Patch 1 behavior remains intact.
|
||||
|
||||
## 8. Needs Product / CCPE Judgment
|
||||
|
||||
- CCPE should process Patch 2 hardening: bundle audit profile, gate runner execution policy, routing diff requirement, lifecycle scan scope, and short returned summary.
|
||||
- Owner must decide per round whether Local CCRA review is required.
|
||||
- Owner must decide whether any Local CCRA report should be included in a Web CCRA upload package.
|
||||
- Owner / Web CCRA still need to define the next round's work before this project starts that round.
|
||||
- Full Round-level automation should be discussed separately as workflow/orchestrator design.
|
||||
|
||||
## 9. Validation Results
|
||||
|
||||
Commands run:
|
||||
|
||||
```powershell
|
||||
python scripts\rebuild_indexes.py --write
|
||||
python scripts\rebuild_indexes.py --check
|
||||
python scripts\validate_model_library.py
|
||||
```
|
||||
|
||||
Results:
|
||||
|
||||
- `rebuild_indexes.py --write`: PASS; refreshed `models/model_index.json` generated date and `cards/card_index.md` consistency.
|
||||
- `rebuild_indexes.py --check`: PASS.
|
||||
- `validate_model_library.py`: PASS.
|
||||
|
||||
Note:
|
||||
|
||||
The first `--check` run reported drift because `models/model_index.json.last_updated` was still `2026-06-18` while the generator uses the current date. Model entries and counts were not the source of drift. Running `--write` reconciled the generated index.
|
||||
|
||||
## 10. Suggested Next Tasks
|
||||
|
||||
1. Send `requirements/ccpe/2026-06-19-ccra-local-reviewer-runtime-patch2.md` to `ccpe-system`.
|
||||
2. Sync `knowledge_assets/10_本地CCRA评审机制说明.md` v0.2 to the Web CCRA / GPT knowledge side.
|
||||
3. Do not run a third historical pilot unless CCPE changes mechanism diagnosis, patch scope judgment, same-child continuation, mandatory knowledge-base use, or authority boundaries.
|
||||
4. Discuss full Round-level automation in a new conversation, because it is a workflow/orchestrator topic rather than a Local CCRA reviewer patch.
|
||||
|
|
@ -0,0 +1,368 @@
|
|||
# CCPE Patch Request: Local CCRA Reviewer Runtime Patch 1
|
||||
|
||||
Date: 2026-06-19
|
||||
|
||||
Client repository:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong
|
||||
```
|
||||
|
||||
Requested supplier repository:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\ccpe-system
|
||||
```
|
||||
|
||||
Related prior request:
|
||||
|
||||
```text
|
||||
requirements/ccpe/2026-06-19-ccra-local-reviewer-runtime.md
|
||||
```
|
||||
|
||||
## 1. Product Context
|
||||
|
||||
The first Local CCRA pilot has been executed against historical Round 04 material.
|
||||
|
||||
Pilot run directory:
|
||||
|
||||
```text
|
||||
local_ccra_reviews/round-04/pilot-01/
|
||||
```
|
||||
|
||||
The pilot used a real Codex child session and wrote:
|
||||
|
||||
```text
|
||||
local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md
|
||||
local_ccra_reviews/round-04/pilot-01/returned-output.md
|
||||
local_ccra_reviews/round-04/pilot-01/05_WEB_LOCAL_CCRA_COMPARISON.md
|
||||
```
|
||||
|
||||
The comparison note found a clear division:
|
||||
|
||||
- Web CCRA / GPT was stronger at product diagnosis and next-action framing.
|
||||
- Local CCRA was stronger at full-file evidence coverage, auditability, runtime/helper risk discovery, lifecycle guard review, and before/after evidence preservation.
|
||||
|
||||
The desired Local CCRA target is not to replace Web CCRA. The goal is to reduce small follow-up review rounds such as `04.1` and `04.2` by improving local first-pass review quality before Web final review.
|
||||
|
||||
## 2. Source Evidence For This Patch
|
||||
|
||||
Use these project-side files as the primary evidence for the patch:
|
||||
|
||||
```text
|
||||
local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md
|
||||
local_ccra_reviews/round-04/pilot-01/05_WEB_LOCAL_CCRA_COMPARISON.md
|
||||
local_ccra_reviews/round-04/pilot-01/run-notes.md
|
||||
local_ccra_reviews/README.md
|
||||
knowledge_assets/10_本地CCRA评审机制说明.md
|
||||
```
|
||||
|
||||
Use this Web CCRA / GPT record for the comparison baseline:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\讨论\2026-06-18产品交流-GPT.md
|
||||
```
|
||||
|
||||
Important source-range rule:
|
||||
|
||||
```text
|
||||
Only lines 1-214 are the Web discussion for initial Round 04 review and Round 04.1 requirements.
|
||||
Lines after 214 are later Round 04.1 review and closeout discussion, and should not be mixed into the initial comparison baseline.
|
||||
```
|
||||
|
||||
The owner records AI discussions as one file per conversation. First-level numbered headings such as `# 1`, `# 2`, `# 3` mark discussion rounds inside the same conversation file. CCPE should preserve this interpretation when referencing Web / GPT discussion records.
|
||||
|
||||
## 3. Needed Capability Change
|
||||
|
||||
Patch `ccra-local-reviewer` and `ccra-local-review` so Local CCRA can combine two review modes in one formal local review:
|
||||
|
||||
1. Web-style product diagnosis mode.
|
||||
2. Local file-first audit mode.
|
||||
|
||||
The current pilot leaned too far toward governance/readiness audit after the repair already existed. Patch 1 should make the reviewer produce a sharper product diagnosis before or during the repair-planning stage, while preserving the local audit advantages.
|
||||
|
||||
Patch 1 should also support a two-turn usage pattern inside the same child review session:
|
||||
|
||||
1. Turn 1: review the current round material and identify issues.
|
||||
2. Turn 2: continue the same child session to plan the next review requirements and the material package that should be submitted.
|
||||
|
||||
This is a session-continuity requirement. The second turn should reuse the same child session id instead of starting a fresh reviewer context.
|
||||
|
||||
## 4. Required Reviewer Behavior
|
||||
|
||||
### 4.0 Two-Turn Review And Planning Protocol
|
||||
|
||||
The Local CCRA runtime should support two explicit prompts against the same child session.
|
||||
|
||||
Turn 1 is the review turn:
|
||||
|
||||
- input: current round review material, review bundle, project knowledge base, reports, tests, helper outputs, and owner-provided review question;
|
||||
- task: inspect the current material, find issues, classify findings, identify evidence gaps, and recommend whether current material is ready for Web CCRA / Owner decision / another local iteration;
|
||||
- primary output: Local CCRA review report;
|
||||
- prohibited focus: do not make the main output a next-round planning document before the current material has been judged.
|
||||
|
||||
Turn 2 is the planning turn:
|
||||
|
||||
- input: the same child session id, the Turn 1 report, any Owner decision on findings, and the target of the next review round;
|
||||
- task: plan the next review requirements and specify the materials that should be prepared or submitted;
|
||||
- primary output: next-review requirements / submission-material plan;
|
||||
- prohibited focus: do not re-review the full current bundle unless new evidence has been added or the owner explicitly asks for re-review.
|
||||
|
||||
Required runtime behavior:
|
||||
|
||||
- preserve `child_session_id` across Turn 1 and Turn 2;
|
||||
- record both turn prompts and output paths in the run metadata or run notes;
|
||||
- make the turn type explicit, for example `review_turn` and `planning_turn`;
|
||||
- require the second turn to reference the first-turn report rather than relying on main-session chat summaries;
|
||||
- allow the second turn to produce a separate file such as `next-review-requirements.md` or another CCPE-defined filename.
|
||||
|
||||
This two-turn pattern mirrors the intended owner workflow: first ask Local CCRA what is wrong with the current materials, then ask the same reviewer context what the next review should require.
|
||||
|
||||
### 4.1 Web-Style Product Diagnosis
|
||||
|
||||
For each material issue, the reviewer must identify:
|
||||
|
||||
- what failed;
|
||||
- why it failed;
|
||||
- why it is not a different failure category;
|
||||
- whether it is a product routing problem, rule boundary problem, model-content problem, runtime problem, or lifecycle/governance problem.
|
||||
|
||||
For Round 04, Web CCRA did this well by identifying `R04-BI-002` as a rule-based selector no-call / instruction-payload boundary problem, not an LLM-understanding problem.
|
||||
|
||||
### 4.2 Patch Scope Judgment
|
||||
|
||||
The report must explicitly separate:
|
||||
|
||||
- must-fix cases;
|
||||
- same-class boundary cases;
|
||||
- calibration-only cases;
|
||||
- cases explicitly not patched;
|
||||
- cases that should not open another small patch round.
|
||||
|
||||
For Round 04, the expected pattern was:
|
||||
|
||||
- `R04-BI-002`: must-fix translation no-call case.
|
||||
- `R04-BI-024`: same-class model-level exclusion boundary case.
|
||||
- `R04-BI-035` and `R04-BI-036`: same-class depth-limiting override cases.
|
||||
- governance / capacity / ambiguous low-context cases: defer to calibration, not immediate broadening.
|
||||
|
||||
### 4.3 Verification-First Review Package Requirements
|
||||
|
||||
When a patch is proposed or already exists, the reviewer must say whether the review package contains enough verification evidence.
|
||||
|
||||
For selector patches, Local CCRA should require:
|
||||
|
||||
- targeted regression for confirmed target cases;
|
||||
- full frozen-pool rerun as post-patch comparison;
|
||||
- existing selector regression / calibration smoke / unit tests;
|
||||
- command log or validation report that distinguishes dry-run from executed gates.
|
||||
|
||||
The reviewer should explicitly state that rule diffs alone are insufficient.
|
||||
|
||||
### 4.4 Before / After Behavior Review
|
||||
|
||||
When before/after routing evidence exists, the report must include:
|
||||
|
||||
- target behavior changes;
|
||||
- non-target behavior changes;
|
||||
- accepted collateral behavior changes;
|
||||
- unexpected regressions;
|
||||
- cases needing Owner/Web CCRA calibration labels.
|
||||
|
||||
For Round 04.1, `R04-BI-022` is the key example: it was a non-target behavior change that was documented and regression-covered. Local CCRA found this well; Patch 1 should make this section mandatory whenever post-patch evidence exists.
|
||||
|
||||
### 4.5 Full-File Local Audit
|
||||
|
||||
Preserve the local strengths from pilot 01:
|
||||
|
||||
- read full local review material directly from files;
|
||||
- use `knowledge_assets/` as the mandatory knowledge base;
|
||||
- inspect review bundles, reports, selector rules, tests, scripts, helper outputs, and model status;
|
||||
- cite files actually read;
|
||||
- distinguish helper evidence from reviewer judgment;
|
||||
- preserve Owner / Web CCRA / lifecycle authority boundaries.
|
||||
|
||||
### 4.6 Helper-Output Confidence
|
||||
|
||||
The report must include a helper-output confidence section:
|
||||
|
||||
- helper output used as evidence;
|
||||
- helper output that appears stale, generic, false-positive, or profile-mismatched;
|
||||
- dry-run versus executed validation;
|
||||
- missing helper that should have run;
|
||||
- whether helper findings block the current review or only require runtime tuning.
|
||||
|
||||
For pilot 01, relevant examples were:
|
||||
|
||||
- `review-bundle-audit` generic profile did not recognize versioned bundle manifests.
|
||||
- `regression-validation-gate-runner` ran in dry-run mode only.
|
||||
- `routing-behavior-diff-audit` was skipped even though before/after evidence existed.
|
||||
- `lifecycle-status-guard-scan` produced broad findings requiring triage.
|
||||
|
||||
## 5. Runtime / Template Changes Requested
|
||||
|
||||
CCPE should update or patch these artifact families as needed:
|
||||
|
||||
- `ccra-local-reviewer` Agent Spec.
|
||||
- `ccra-local-review` Runtime Spec.
|
||||
- invocation packet template.
|
||||
- report template.
|
||||
- runtime setup guide.
|
||||
- helper integration guide.
|
||||
|
||||
The runtime and templates should explicitly distinguish these invocation modes:
|
||||
|
||||
```text
|
||||
review_turn
|
||||
planning_turn
|
||||
comparison_turn
|
||||
```
|
||||
|
||||
Minimum expected file contract:
|
||||
|
||||
```text
|
||||
review_turn -> 04_LOCAL_CCRA_REVIEW_REPORT.md
|
||||
planning_turn -> next-review-requirements.md or a CCPE-defined equivalent
|
||||
comparison_turn -> optional Web / Local comparison note, if requested by the owner
|
||||
```
|
||||
|
||||
The exact filenames can be defined by CCPE, but the contract must avoid treating all child-session follow-up turns as new independent reviews.
|
||||
|
||||
The exact CCPE paths are supplier-owned, but the currently known artifacts are:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\ccpe-system\agents\agent-specs\ccra-local-reviewer.agent.md
|
||||
C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review.runtime.md
|
||||
C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-runtime-setup.md
|
||||
C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-invocation-packet.template.md
|
||||
C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccra-local-review-report.template.md
|
||||
C:\Users\wangq\Documents\Codex\ccpe-system\integrations\skills-vault\ccra-local-review-helpers.integration.md
|
||||
```
|
||||
|
||||
## 6. Required Report Shape
|
||||
|
||||
Patch 1 should make these sections required or strongly required when applicable:
|
||||
|
||||
1. `Issue Mechanism Diagnosis`
|
||||
2. `Patch Scope Judgment`
|
||||
3. `Verification Evidence Requirements`
|
||||
4. `Before / After Behavior Review`
|
||||
5. `Non-Target Behavior Changes`
|
||||
6. `Calibration-Only Candidates`
|
||||
7. `Helper Output Confidence`
|
||||
8. `Final Action Recommendation`
|
||||
|
||||
For planning turns, Patch 1 should provide a separate planning output shape with at least:
|
||||
|
||||
1. `Next Review Goal`
|
||||
2. `Required Submitted Materials`
|
||||
3. `Required Verification Evidence`
|
||||
4. `Expected Before / After Comparisons`
|
||||
5. `Open Owner Decisions`
|
||||
6. `Explicit Non-Goals`
|
||||
7. `Recommended Web CCRA Review Questions`
|
||||
|
||||
`Final Action Recommendation` should use a compact decision shape:
|
||||
|
||||
```text
|
||||
fix_now
|
||||
document_only
|
||||
defer_to_calibration
|
||||
do_not_open_patch_round
|
||||
ready_for_web_review_after_local_repairs
|
||||
```
|
||||
|
||||
## 7. Runtime Time Budget
|
||||
|
||||
Local CCRA is a deep file-first review, not a quick chat summary.
|
||||
|
||||
Expected mature-run duration:
|
||||
|
||||
```text
|
||||
5-10 minutes
|
||||
```
|
||||
|
||||
The exact duration depends on client/API/runtime configuration and on whether tools, helper Skills, archive inspection, and validation commands run.
|
||||
|
||||
The runtime should not treat several minutes of file reading or tool execution as abnormal by itself.
|
||||
|
||||
## 8. Prohibited Behavior
|
||||
|
||||
Patch 1 must not change these boundaries:
|
||||
|
||||
- Local CCRA does not replace Owner judgment.
|
||||
- Local CCRA does not replace Web CCRA final review at key gates.
|
||||
- Local CCRA must not upgrade model lifecycle status.
|
||||
- Local CCRA must not edit project files other than its contracted report outputs.
|
||||
- Local CCRA must not introduce LLM selector, RAG, database, frontend, backend, user system, or platform behavior.
|
||||
- Local CCRA must not turn helper output into automatic judgment.
|
||||
|
||||
## 9. Acceptance Criteria
|
||||
|
||||
CCPE patch is acceptable when:
|
||||
|
||||
1. The updated reviewer contract explicitly requires Web-style issue mechanism diagnosis.
|
||||
2. The updated reviewer contract explicitly requires patch-scope separation.
|
||||
3. The updated report template can surface both product diagnosis and full-file audit findings.
|
||||
4. Before/after behavior review is required when post-patch evidence exists.
|
||||
5. Helper-output confidence is required and distinguishes dry-run, executed validation, skipped helper, and profile mismatch.
|
||||
6. The runtime supports a two-turn same-child-session workflow: review current material first, then plan next review requirements.
|
||||
7. Turn type and output paths are recorded so `review_turn`, `planning_turn`, and optional `comparison_turn` are not confused.
|
||||
8. The second turn references the first-turn report and continues the same child session id.
|
||||
9. The mandatory `knowledge_base_path` requirement remains intact.
|
||||
10. The expected duration is documented as 5-10 minutes and client/runtime dependent.
|
||||
11. No canonical CCPE artifact is copied into this product repository.
|
||||
|
||||
## 10. Suggested Re-Test After CCPE Patch
|
||||
|
||||
After CCPE completes Patch 1, rerun the Local CCRA pilot against the same Round 04 material.
|
||||
|
||||
Suggested run directory:
|
||||
|
||||
```text
|
||||
local_ccra_reviews/round-04/pilot-02/
|
||||
```
|
||||
|
||||
Use the same primary Round 04 input bundle:
|
||||
|
||||
```text
|
||||
ccra_review_bundle/round-04_2026-06-18_blind-input-routing-evaluation/
|
||||
```
|
||||
|
||||
Use the same mandatory knowledge base:
|
||||
|
||||
```text
|
||||
knowledge_assets/
|
||||
```
|
||||
|
||||
Then compare:
|
||||
|
||||
1. Web CCRA baseline: `2026-06-18产品交流-GPT.md` lines 1-214.
|
||||
2. Old Local CCRA output: `local_ccra_reviews/round-04/pilot-01/04_LOCAL_CCRA_REVIEW_REPORT.md`.
|
||||
3. New Local CCRA output: `local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md`.
|
||||
|
||||
Expected improvement:
|
||||
|
||||
- new Local CCRA should retain the full-file audit advantages from pilot 01;
|
||||
- new Local CCRA should produce a sharper Web-style product diagnosis;
|
||||
- new Local CCRA should clearly say whether a small follow-up patch round is needed, or whether the right next step is calibration / Web final review.
|
||||
- the same child session should support a second planning prompt that outputs next-review requirements and required submission materials.
|
||||
|
||||
## 11. Human Gate
|
||||
|
||||
Owner approval is required before:
|
||||
|
||||
- accepting the patched Local CCRA behavior as the default for Round 05;
|
||||
- making helper execution mandatory in formal runs;
|
||||
- routing any deterministic helper improvement to `skills-vault`;
|
||||
- treating Local CCRA findings as accepted project work.
|
||||
|
||||
## 12. Urgency And Dependency
|
||||
|
||||
Urgency: high before formal Round 05 Local CCRA use.
|
||||
|
||||
Dependency:
|
||||
|
||||
- Current pilot proved real child-session invocation and full-file audit value.
|
||||
- Patch 1 is needed to improve product-diagnosis quality before relying on Local CCRA to reduce Web CCRA sub-rounds.
|
||||
- Formal Round 05 Local CCRA should wait until CCPE either completes this patch or explicitly declines it with an alternative reviewer contract.
|
||||
|
|
@ -0,0 +1,321 @@
|
|||
# CCPE Patch Request: Local CCRA Reviewer Runtime Patch 2
|
||||
|
||||
Date: 2026-06-19
|
||||
|
||||
Client repository:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong
|
||||
```
|
||||
|
||||
Requested supplier repository:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\ccpe-system
|
||||
```
|
||||
|
||||
Related prior requests:
|
||||
|
||||
```text
|
||||
requirements/ccpe/2026-06-19-ccra-local-reviewer-runtime.md
|
||||
requirements/ccpe/2026-06-19-ccra-local-reviewer-runtime-patch1.md
|
||||
```
|
||||
|
||||
## 1. Product Context
|
||||
|
||||
CCPE Patch 1 has been tested with a second historical Local CCRA pilot.
|
||||
|
||||
Pilot run directory:
|
||||
|
||||
```text
|
||||
local_ccra_reviews/round-04/pilot-02/
|
||||
```
|
||||
|
||||
The same real Codex child session completed both required turns:
|
||||
|
||||
```text
|
||||
child_session_id: 019edcde-24be-7593-99b2-5cf014467340
|
||||
review_turn_duration_ms: 512317
|
||||
planning_turn_duration_ms: 342925
|
||||
```
|
||||
|
||||
Primary outputs:
|
||||
|
||||
```text
|
||||
local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md
|
||||
local_ccra_reviews/round-04/pilot-02/next-review-requirements.md
|
||||
local_ccra_reviews/round-04/pilot-02/05_WEB_LOCAL_CCRA_COMPARISON.md
|
||||
local_ccra_reviews/round-04/pilot-02/returned-output.md
|
||||
local_ccra_reviews/round-04/pilot-02/run-notes.md
|
||||
```
|
||||
|
||||
Pilot 02 achieved the main Patch 1 target:
|
||||
|
||||
- it used the mandatory project knowledge base;
|
||||
- it preserved no-hindsight review scope for initial Round 04 evidence;
|
||||
- it reproduced the Web CCRA-style issue mechanism diagnosis;
|
||||
- it separated must-fix, same-class boundary, calibration-only, and explicitly-not-patched cases;
|
||||
- it produced a same-child-session `planning_turn` output for next review requirements.
|
||||
|
||||
The project-side conclusion is:
|
||||
|
||||
```text
|
||||
ready_for_formal_local_first_review_with_conditions
|
||||
```
|
||||
|
||||
Patch 2 is therefore a hardening patch, not a blocker before the next Owner/Web-defined round. It should improve repeatability and helper reliability before Local CCRA is used repeatedly.
|
||||
|
||||
## 2. Source Evidence For This Patch
|
||||
|
||||
Use these project files as the primary evidence:
|
||||
|
||||
```text
|
||||
local_ccra_reviews/round-04/pilot-02/04_LOCAL_CCRA_REVIEW_REPORT.md
|
||||
local_ccra_reviews/round-04/pilot-02/next-review-requirements.md
|
||||
local_ccra_reviews/round-04/pilot-02/05_WEB_LOCAL_CCRA_COMPARISON.md
|
||||
local_ccra_reviews/round-04/pilot-02/run-notes.md
|
||||
local_ccra_reviews/round-04/pilot-02/returned-output.md
|
||||
local_ccra_reviews/round-04/pilot-02/helper-outputs/
|
||||
knowledge_assets/10_本地CCRA评审机制说明.md
|
||||
```
|
||||
|
||||
The comparison baseline remains:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\讨论\2026-06-18产品交流-GPT.md
|
||||
```
|
||||
|
||||
Source range rule:
|
||||
|
||||
```text
|
||||
Only lines 1-214 are the Web baseline for initial Round 04 review and Round 04.1 requirements.
|
||||
Lines after 214 belong to later Round 04.1 review / closeout and must not be mixed into the initial comparison baseline.
|
||||
```
|
||||
|
||||
## 3. Needed Capability Changes
|
||||
|
||||
Patch 2 should improve Local CCRA runtime reliability in five areas:
|
||||
|
||||
1. project-aware review bundle audit profile;
|
||||
2. explicit gate-runner execution policy;
|
||||
3. mandatory routing behavior diff for patch verification;
|
||||
4. scoped lifecycle/status scan and triage;
|
||||
5. short Owner-facing summary for long audit reports.
|
||||
|
||||
Patch 2 should not redesign the full round automation/orchestration workflow. Round-level automation is a separate design topic.
|
||||
|
||||
## 4. Required Changes
|
||||
|
||||
### 4.1 Project-Aware Review Bundle Audit Profile
|
||||
|
||||
Problem observed in pilot 02:
|
||||
|
||||
```text
|
||||
review-bundle-audit: exit 1
|
||||
generic profile reports missing manifest and validation_sidecar
|
||||
BUNDLE_FILE_MANIFEST_04.md exists but is treated as extra by the generic profile
|
||||
```
|
||||
|
||||
Requested behavior:
|
||||
|
||||
- Local CCRA should distinguish real review bundle blockers from generic-profile mismatches.
|
||||
- Versioned manifest names such as `BUNDLE_FILE_MANIFEST_04.md`, `BUNDLE_FILE_MANIFEST_04.1.md`, and similar round-specific forms should be recognized.
|
||||
- If a validation sidecar is optional for a given review profile, absence should be recorded as `profile_warning` or `not_applicable`, not automatically as a blocker.
|
||||
- Helper confidence should name the active profile, recognized manifest path, missing required files, extra files, and whether the result blocks review.
|
||||
|
||||
Acceptance criteria:
|
||||
|
||||
- The helper integration guide or runtime setup guide defines a CCRA-aware bundle audit profile or an equivalent profile contract.
|
||||
- Local CCRA report wording does not claim a bundle failed merely because the generic profile does not understand project-specific versioned filenames.
|
||||
|
||||
### 4.2 Gate Runner Execution Policy
|
||||
|
||||
Problem observed in pilot 02:
|
||||
|
||||
```text
|
||||
regression-validation-gate-runner ran in dry_run mode only
|
||||
dry-run output is useful for planning but cannot support pass claims
|
||||
```
|
||||
|
||||
Requested behavior:
|
||||
|
||||
- Runtime input contract should include a gate execution policy:
|
||||
|
||||
```text
|
||||
gate_execution_mode: dry_run | run | owner_waived | not_applicable
|
||||
```
|
||||
|
||||
- `dry_run` means the reviewer may inspect planned gates but must not claim they passed.
|
||||
- `run` means the reviewer or runtime is allowed to execute declared validation/regression commands and cite command logs.
|
||||
- `owner_waived` means the owner explicitly chose not to run gates; the report must preserve that as an evidence limitation.
|
||||
- `not_applicable` means the reviewed material has no executable gates in scope.
|
||||
|
||||
Acceptance criteria:
|
||||
|
||||
- Report templates distinguish `planned`, `executed`, `skipped`, and `waived` gates.
|
||||
- `Final Action Recommendation` cannot use dry-run evidence as a passing validation result.
|
||||
- Planning output requires executed command logs when a patch verification package is being prepared.
|
||||
|
||||
### 4.3 Mandatory Routing Behavior Diff For Patch Verification
|
||||
|
||||
Problem observed in pilot 02:
|
||||
|
||||
```text
|
||||
routing-behavior-diff-audit was correctly skipped for no-hindsight review_turn
|
||||
but before/after routing diff should be required when post-patch evidence exists
|
||||
```
|
||||
|
||||
Requested behavior:
|
||||
|
||||
- For `review_turn` on initial evidence with no allowed after-patch material, routing diff may be skipped with explicit reason.
|
||||
- For any patch, post-patch verification, or comparison review where before/after outputs exist, routing behavior diff is required.
|
||||
- If the helper cannot run, the report must require a manual equivalent table.
|
||||
|
||||
Minimum required diff categories:
|
||||
|
||||
```text
|
||||
target_behavior_changes
|
||||
non_target_behavior_changes
|
||||
accepted_collateral_changes
|
||||
unexpected_regressions
|
||||
unchanged_expected_behavior
|
||||
cases_needing_owner_or_web_calibration
|
||||
```
|
||||
|
||||
Acceptance criteria:
|
||||
|
||||
- Runtime/report template includes a conditional requirement for routing diff.
|
||||
- `planning_turn` output asks for full frozen-pool before/after comparison when selector behavior changed.
|
||||
- Missing routing diff is surfaced as an evidence gap, not silently ignored.
|
||||
|
||||
### 4.4 Scoped Lifecycle / Status Scan And Triage
|
||||
|
||||
Problem observed in pilot 02:
|
||||
|
||||
```text
|
||||
lifecycle-status-guard-scan scanned broad repository scope
|
||||
it reported many findings from older review materials and pilot-01 helper outputs
|
||||
the output is useful but noisy
|
||||
```
|
||||
|
||||
Requested behavior:
|
||||
|
||||
- Lifecycle/status scan should support scope modes:
|
||||
|
||||
```text
|
||||
current_review_bundle
|
||||
changed_files
|
||||
knowledge_assets
|
||||
model_library_state
|
||||
whole_repo
|
||||
```
|
||||
|
||||
- Whole-repo scan should be treated as broad audit mode, not default blocker mode.
|
||||
- Findings should be triaged into:
|
||||
|
||||
```text
|
||||
current_scope_blocker
|
||||
owner_decision_needed
|
||||
historical_or_archive_noise
|
||||
policy_reference_not_claim
|
||||
false_positive_or_low_confidence
|
||||
```
|
||||
|
||||
Acceptance criteria:
|
||||
|
||||
- Helper integration guide defines recommended scan scope for Local CCRA `review_turn`, `planning_turn`, and `comparison_turn`.
|
||||
- Report template requires lifecycle findings to be triaged before they block review readiness.
|
||||
- The reviewer must not turn historical review chatter into current lifecycle blocker without explaining the path to current scope.
|
||||
|
||||
### 4.5 Short Owner-Facing Summary
|
||||
|
||||
Problem observed in pilot 02:
|
||||
|
||||
```text
|
||||
04_LOCAL_CCRA_REVIEW_REPORT.md is high-quality but long
|
||||
routine use needs a compact Owner-facing return shape
|
||||
```
|
||||
|
||||
Requested behavior:
|
||||
|
||||
- Keep the long audit report for traceability.
|
||||
- Add or formalize a short summary shape in `returned-output.md`.
|
||||
|
||||
Minimum summary fields:
|
||||
|
||||
```text
|
||||
review_round
|
||||
local_pass
|
||||
turn_type
|
||||
child_session_id
|
||||
main_conclusion
|
||||
final_action_recommendation
|
||||
blocks_web_review
|
||||
blocks_owner_acceptance
|
||||
required_next_action
|
||||
output_paths
|
||||
evidence_limitations
|
||||
```
|
||||
|
||||
Acceptance criteria:
|
||||
|
||||
- Runtime/report templates preserve both long report and short return summary.
|
||||
- Main session can read `returned-output.md` quickly without parsing the entire audit report.
|
||||
|
||||
## 5. Explicit Non-Goals
|
||||
|
||||
Patch 2 must not:
|
||||
|
||||
- replace Owner judgment;
|
||||
- replace Web CCRA final review;
|
||||
- change the already accepted Patch 1 two-turn pattern;
|
||||
- introduce LLM selector, RAG, database, frontend, backend, user system, or platform behavior;
|
||||
- implement full Round 5 automation or multi-pass autonomous project execution;
|
||||
- copy canonical CCPE artifacts into this product repository;
|
||||
- route deterministic helper implementation directly to `skills-vault` unless CCPE classifies the operation as reusable automation.
|
||||
|
||||
## 6. Acceptance Criteria
|
||||
|
||||
Patch 2 is acceptable when:
|
||||
|
||||
1. CCRA-aware bundle audit profile or profile contract is documented.
|
||||
2. Gate execution policy is explicit and prevents dry-run pass claims.
|
||||
3. Routing behavior diff is mandatory when before/after patch evidence exists.
|
||||
4. Lifecycle/status scan scope and triage categories are documented.
|
||||
5. Short Owner-facing `returned-output.md` shape is defined.
|
||||
6. Helper-output confidence language covers profile mismatch, dry-run, skipped helper, broad-scope noise, and missing helper.
|
||||
7. No change weakens Patch 1 requirements: mandatory `knowledge_base_path`, `review_turn`, `planning_turn`, same-child session reuse, and file-first evidence remain intact.
|
||||
8. Patch 2 is described as hardening, not as a required third historical pilot.
|
||||
|
||||
## 7. Validation / Re-Test Policy
|
||||
|
||||
A third historical pilot is not required after Patch 2 unless CCPE changes one of these core behaviors:
|
||||
|
||||
- issue mechanism diagnosis;
|
||||
- patch scope judgment;
|
||||
- same-child-session turn continuation;
|
||||
- mandatory knowledge base use;
|
||||
- authority boundaries.
|
||||
|
||||
If Patch 2 only changes helper policy, report summary shape, and runtime setup guidance, validate by:
|
||||
|
||||
1. CCPE-side spec/template review;
|
||||
2. checking the updated setup guide against `pilot-02` evidence;
|
||||
3. using the next real Owner/Web-defined Local CCRA run as the first live validation.
|
||||
|
||||
## 8. Human Gate
|
||||
|
||||
Owner approval is required before:
|
||||
|
||||
- treating any helper execution mode as mandatory in all formal runs;
|
||||
- sending Local CCRA reports to Web CCRA as part of formal upload;
|
||||
- accepting Local CCRA findings as project work;
|
||||
- designing the larger Round-level automation workflow.
|
||||
|
||||
## 9. Urgency And Dependency
|
||||
|
||||
Urgency: medium-high.
|
||||
|
||||
Patch 2 is recommended before repeated formal Local CCRA use, but it should not block the next Owner/Web-defined round if Patch 1 behavior remains intact.
|
||||
|
||||
The next larger topic is round-level automation/orchestration. That should be discussed separately from this Patch 2 hardening request.
|
||||
|
|
@ -0,0 +1,198 @@
|
|||
# CCPE Request: Local CCRA Reviewer Agent Runtime
|
||||
|
||||
Date: 2026-06-19
|
||||
|
||||
Client repository:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong
|
||||
```
|
||||
|
||||
Requested supplier repository:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\ccpe-system
|
||||
```
|
||||
|
||||
## 1. Product Context
|
||||
|
||||
The Mindscape of Bro Tsong is building a file-first cognitive model library MVP.
|
||||
|
||||
The project already produces CCRA / GPT review bundles under:
|
||||
|
||||
```text
|
||||
ccra_review_bundle/
|
||||
```
|
||||
|
||||
The owner wants to reduce manual transfer work by adding a first-pass Local CCRA review loop inside the project. Local CCRA review should use a real CCPE Agent Runtime child session, not main-session roleplay.
|
||||
|
||||
The first version serves only this repository.
|
||||
|
||||
## 2. Needed Capability
|
||||
|
||||
Provide a `ccra-local-reviewer` capability that can be invoked from this project through CCPE Agent Runtime.
|
||||
|
||||
The capability must include:
|
||||
|
||||
- Agent Spec for `ccra-local-reviewer`.
|
||||
- Runtime Spec or invocation protocol for creating and continuing a child review session.
|
||||
- File-first input and output contract for local review run directories.
|
||||
- Review report template.
|
||||
- Findings classification rubric.
|
||||
- Lifecycle and scope guard rules.
|
||||
- Guidance for whether companion automation stays CCPE-owned or should be routed to `skills-vault`.
|
||||
|
||||
## 3. Why This Belongs In CCPE
|
||||
|
||||
This request is primarily about expert-agent role definition, review governance, invocation protocol, runtime session continuation, and model lifecycle gate judgment.
|
||||
|
||||
Those are CCPE responsibilities.
|
||||
|
||||
This repository should only store product-side review runs and supplier requests. It should not become the canonical source for the CCRA Agent definition or runtime protocol.
|
||||
|
||||
## 4. Current Blocked Task
|
||||
|
||||
The project can document `local_ccra_reviews/` now, but it cannot run official Local CCRA review until CCPE supplies the Agent Spec and Runtime interface.
|
||||
|
||||
Concrete blocked action:
|
||||
|
||||
```text
|
||||
Owner asks main Codex session to run Local CCRA review
|
||||
-> main session creates local_ccra_reviews/<round>/<nn>/
|
||||
-> main session invokes CCPE Agent Runtime
|
||||
-> child session writes local review report
|
||||
```
|
||||
|
||||
The final runtime invocation command or tool contract is intentionally not defined in this repository.
|
||||
|
||||
## 5. Input Files And Source Paths
|
||||
|
||||
Relevant project-side paths:
|
||||
|
||||
```text
|
||||
README.md
|
||||
AGENTS.md
|
||||
PROJECTS.md
|
||||
docs/WORKFLOW.md
|
||||
docs/DECISIONS.md
|
||||
docs/DATA_CONTRACT.md
|
||||
docs/HANDOFF_TEMPLATE.md
|
||||
knowledge_assets/
|
||||
ccra_review_bundle/
|
||||
local_ccra_reviews/README.md
|
||||
```
|
||||
|
||||
Relevant upstream CCRA source material:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\knowledge-vault\prompts\GPT\认知科学产品规划架构师\认知科学产品规划架构师.md
|
||||
C:\Users\wangq\Documents\Codex\knowledge-vault\prompts\GPT\认知科学产品规划架构师\
|
||||
C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\讨论\2026-06-18产品交流-GPT.md
|
||||
C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\讨论\Local-Agent\0.1本地的CCRA放在哪儿.md
|
||||
```
|
||||
|
||||
Reference implementation pattern:
|
||||
|
||||
```text
|
||||
C:\Users\wangq\Documents\Codex\knowledge-vault\skills\knowledge-processing\viewpoint-discussion-distillation
|
||||
```
|
||||
|
||||
This reference is for the existence of prior CCPE Runtime invocation and session-continuation patterns. Do not copy it into this repository.
|
||||
|
||||
## 6. Expected Output Artifacts
|
||||
|
||||
CCPE should produce or register:
|
||||
|
||||
1. `ccra-local-reviewer` Agent Spec.
|
||||
2. CCPE Agent Runtime invocation protocol for this Agent.
|
||||
3. Session persistence contract covering child session id, continuation state, and resume behavior.
|
||||
4. File-first review run contract compatible with:
|
||||
|
||||
```text
|
||||
local_ccra_reviews/<public-round>/<local-pass>/
|
||||
```
|
||||
|
||||
5. Local CCRA report template.
|
||||
6. Findings classification rubric, including at least:
|
||||
|
||||
```text
|
||||
blocker
|
||||
major
|
||||
minor
|
||||
calibration
|
||||
defer
|
||||
```
|
||||
|
||||
7. Capability routing decision for companion automation:
|
||||
|
||||
- keep as Agent-specific CCPE runtime support;
|
||||
- implement locally in this product repository;
|
||||
- or abstract as reusable deterministic automation and route to `skills-vault`.
|
||||
|
||||
## 7. Required Review Behavior
|
||||
|
||||
`ccra-local-reviewer` must:
|
||||
|
||||
- Run in a child session or equivalent isolated runtime context.
|
||||
- Read primary evidence from files, not from main-session summaries.
|
||||
- Prioritize review bundle files, reports, tests, selector rules, regression cases, and diffs before Codex explanations.
|
||||
- Output review findings, risks, evidence references, and recommended next actions.
|
||||
- Identify non-target behavior changes.
|
||||
- Identify engineering-pass versus product-judgment gaps.
|
||||
- Identify lifecycle overclaims.
|
||||
- Preserve the distinction between Local CCRA first review, Owner decision, and Web CCRA final review.
|
||||
|
||||
## 8. Prohibited Behavior
|
||||
|
||||
`ccra-local-reviewer` must not:
|
||||
|
||||
- Modify project files.
|
||||
- Edit selector rules.
|
||||
- Edit model cards.
|
||||
- Edit model JSON.
|
||||
- Edit regression cases.
|
||||
- Create review bundles.
|
||||
- Upgrade model lifecycle status.
|
||||
- Add a third model.
|
||||
- Introduce LLM selector, RAG, database, frontend, backend, user system, or platform behavior.
|
||||
- Treat its own output as Owner approval.
|
||||
- Treat its own output as Web CCRA approval.
|
||||
|
||||
## 9. Companion Capability Candidates
|
||||
|
||||
The following needs were discovered while planning Local CCRA. They should not be sent directly to `skills-vault` from this repository yet. CCPE should first classify them.
|
||||
|
||||
Candidates:
|
||||
|
||||
- Routing behavior diff audit after selector changes.
|
||||
- Review bundle completeness audit.
|
||||
- Lifecycle status guard scan.
|
||||
- Round initialization context builder.
|
||||
- Regression and validation gate runner.
|
||||
|
||||
Classification options:
|
||||
|
||||
1. Agent-specific support inside `ccra-local-reviewer` Runtime.
|
||||
2. Product-local deterministic helper.
|
||||
3. Reusable deterministic Skill request to `skills-vault`.
|
||||
|
||||
If a candidate becomes a `skills-vault` request, it should be named by its reusable operation rather than by this project-specific review context.
|
||||
|
||||
## 10. Human Gate
|
||||
|
||||
Owner approval is required before:
|
||||
|
||||
- Treating Local CCRA findings as accepted work.
|
||||
- Copying accepted materials into a formal Web CCRA review bundle.
|
||||
- Including `04_LOCAL_CCRA_REVIEW_REPORT.md` in any Web CCRA upload package.
|
||||
- Upgrading model lifecycle status.
|
||||
- Routing any companion capability to `skills-vault`.
|
||||
|
||||
## 11. Urgency And Dependency
|
||||
|
||||
Urgency: high for future review-loop efficiency, but not blocking current model library validation.
|
||||
|
||||
Dependency:
|
||||
|
||||
- Local review run folders can be documented now.
|
||||
- Official Local CCRA execution waits for CCPE Agent Spec and Runtime interface.
|
||||
Loading…
Reference in New Issue