claude-bot/EJClaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Clarify reviewer verification evidence

Browse Source
This commit is contained in:
ejclaw
2026-05-19 14:17:34 +09:00
parent 55dd0f9b63
commit ef16e82b05
2 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
prompts/claude-paired-room.md
View File

@@ -38,6 +38,7 @@ If you see a materially better design, debugging path, or scoping choice, propos
- Treat `EJCLAW_WORK_DIR` as the canonical verification root for this turn. You may inspect other local paths for context, but final review findings must be re-checked against `EJCLAW_WORK_DIR` - Treat `EJCLAW_WORK_DIR` as the canonical verification root for this turn. You may inspect other local paths for context, but final review findings must be re-checked against `EJCLAW_WORK_DIR`
- Do not use a different clone, canonical repo path, or cached session path as the sole basis for `BLOCKED`, `DONE_WITH_CONCERNS`, or change requests. If another path disagrees with `EJCLAW_WORK_DIR`, prefer `EJCLAW_WORK_DIR` and explicitly call out the mismatch - Do not use a different clone, canonical repo path, or cached session path as the sole basis for `BLOCKED`, `DONE_WITH_CONCERNS`, or change requests. If another path disagrees with `EJCLAW_WORK_DIR`, prefer `EJCLAW_WORK_DIR` and explicitly call out the mismatch
- When test/typecheck/build/lint evidence is needed, prefer the dedicated verification path (`run_verification`) over assuming the reviewer workspace should execute the full project locally - When test/typecheck/build/lint evidence is needed, prefer the dedicated verification path (`run_verification`) over assuming the reviewer workspace should execute the full project locally
- If direct execution is unavailable, request `run_verification` or owner-provided evidence. Do not present static analysis as completed verification
- Separate correctness issues from improvement ideas. If something is only a better alternative, label it as optional instead of blocking the owner unnecessarily - Separate correctness issues from improvement ideas. If something is only a better alternative, label it as optional instead of blocking the owner unnecessarily
- Stagnation: **Spinning** (same error 3+), **Oscillation** (alternating approaches), **Diminishing returns** (shrinking improvement), **No progress** (discussion without change) — name the pattern and report: **Status**, **Attempted**, **Recommendation** - Stagnation: **Spinning** (same error 3+), **Oscillation** (alternating approaches), **Diminishing returns** (shrinking improvement), **No progress** (discussion without change) — name the pattern and report: **Status**, **Attempted**, **Recommendation**
- Implementation, commits, and pushes require agreement from both sides. Either can veto - Implementation, commits, and pushes require agreement from both sides. Either can veto

3
src/platform-prompts.test.ts
View File

@@ -83,6 +83,9 @@ describe('platform-prompts', () => {
expect(codexPairedPrompt).toContain( expect(codexPairedPrompt).toContain(
'Separate correctness issues from improvement ideas', 'Separate correctness issues from improvement ideas',
); );
expect(codexPairedPrompt).toContain(
'Do not present static analysis as completed verification',
);
expect(codexPairedPrompt).toContain('Keep reviewer output owner-facing'); expect(codexPairedPrompt).toContain('Keep reviewer output owner-facing');
expect(codexPairedPrompt).toContain('prefer 3-6 lines'); expect(codexPairedPrompt).toContain('prefer 3-6 lines');
expect(codexPairedPrompt).not.toContain('owner-side paired agent'); expect(codexPairedPrompt).not.toContain('owner-side paired agent');