98 lines
3.6 KiB
Markdown
98 lines
3.6 KiB
Markdown
# 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.
|