feat(document-review): collapse batch_confirm tier into auto (#432)

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Trevin Chow
2026-03-28 17:03:05 -07:00
committed by GitHub
parent 3706a9764b
commit 0f5715d562
4 changed files with 41 additions and 79 deletions

View File

@@ -15,22 +15,15 @@ Use this **exact format** when presenting synthesized review findings. Findings
- security-lens -- plan adds public API endpoint with auth flow
- scope-guardian -- plan has 15 requirements across 3 priority levels
Applied 3 auto-fixes. Batched 2 fixes for approval. 4 findings to consider (2 errors, 2 omissions).
Applied 5 auto-fixes. 4 findings to consider (2 errors, 2 omissions).
### Auto-fixes Applied
- Standardized "pipeline"/"workflow" terminology to "pipeline" throughout (coherence)
- Fixed cross-reference: Section 4 referenced "Section 3.2" which is actually "Section 3.1" (coherence)
- Updated unit count from "6 units" to "7 units" to match listed units (coherence)
### Batch Confirm
These fixes have one clear correct answer but touch document meaning. Apply all?
| # | Section | Fix | Reviewer |
|---|---------|-----|----------|
| 1 | Unit 4 | Add "update API rate-limit config" step -- implied by Unit 3's rate-limit introduction | feasibility |
| 2 | Verification | Add auth token refresh to test scenarios -- required by Unit 2's token expiry handling | security-lens |
- Added "update API rate-limit config" step to Unit 4 -- implied by Unit 3's rate-limit introduction (feasibility)
- Added auth token refresh to test scenarios -- required by Unit 2's token expiry handling (security-lens)
### P0 -- Must Fix
@@ -76,22 +69,21 @@ These fixes have one clear correct answer but touch document meaning. Apply all?
### Coverage
| Persona | Status | Findings | Auto | Batch | Present | Residual |
|---------|--------|----------|------|-------|---------|----------|
| coherence | completed | 3 | 2 | 0 | 1 | 0 |
| feasibility | completed | 2 | 0 | 1 | 1 | 1 |
| security-lens | completed | 2 | 0 | 1 | 1 | 0 |
| scope-guardian | completed | 1 | 0 | 0 | 1 | 0 |
| product-lens | not activated | -- | -- | -- | -- | -- |
| design-lens | not activated | -- | -- | -- | -- | -- |
| Persona | Status | Findings | Auto | Present | Residual |
|---------|--------|----------|------|---------|----------|
| coherence | completed | 4 | 3 | 1 | 0 |
| feasibility | completed | 2 | 1 | 1 | 1 |
| security-lens | completed | 2 | 1 | 1 | 0 |
| scope-guardian | completed | 1 | 0 | 1 | 0 |
| product-lens | not activated | -- | -- | -- | -- |
| design-lens | not activated | -- | -- | -- | -- |
```
## Section Rules
- **Summary line**: Always present after the reviewer list. Format: "Applied N auto-fixes. Batched M fixes for approval. K findings to consider (X errors, Y omissions)." Omit any zero clause.
- **Auto-fixes Applied**: List fixes that were applied automatically (auto class). Omit section if none.
- **Batch Confirm**: Group `batch_confirm` findings for a single yes/no/select approval. Omit section if none.
- **Summary line**: Always present after the reviewer list. Format: "Applied N auto-fixes. K findings to consider (X errors, Y omissions)." Omit any zero clause.
- **Auto-fixes Applied**: List all fixes that were applied automatically (auto class). Include enough detail per fix to convey the substance -- especially for fixes that add content or touch document meaning. Omit section if none.
- **P0-P3 sections**: Only include sections that have findings. Omit empty severity levels. Within each severity, separate into **Errors** and **Omissions** sub-headers. Omit a sub-header if that severity has none of that type.
- **Residual Concerns**: Findings below confidence threshold that were promoted by cross-persona corroboration, plus unpromoted residual risks. Omit if none.
- **Deferred Questions**: Questions for later workflow stages. Omit if none.
- **Coverage**: Always include. All counts are **post-synthesis**. **Findings** must equal Auto + Batch + Present exactly -- if deduplication merged a finding across personas, attribute it to the persona with the highest confidence and reduce the other persona's count. **Residual** = count of `residual_risks` from this persona's raw output (not the promoted subset in the Residual Concerns section).
- **Coverage**: Always include. All counts are **post-synthesis**. **Findings** must equal Auto + Present exactly -- if deduplication merged a finding across personas, attribute it to the persona with the highest confidence and reduce the other persona's count. **Residual** = count of `residual_risks` from this persona's raw output (not the promoted subset in the Residual Concerns section).