fix(review): give the publish gate the same evidence file as the model pool#317
Conversation
…succeeds Follow-up to the pool-cycling fix. opencode_review_normalize_output.py rewrites its input in place and is NOT idempotent, and the publish step normalizes the selected output again. The pool was normalizing (mutating) the very file it then handed to the publish step, so a model whose FIRST normalize passed (recorded as the pool's success) failed the publish step's SECOND normalize — ending the run in "Selected successful OpenCode output did not include a valid control conclusion" instead of the review completing. Normalize/approve-gate a throwaway ANSI-stripped copy and leave the model output pristine, so the publish step performs the one-and-only normalize of that content and its result matches the pool's decision. Verified locally against a non-idempotent normalizer stub: pool passes, output stays pristine, publish normalize passes. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01RTAMs4bpSZS77Xe3RQjv9P
…l pool Root cause of reviews failing with "Selected successful OpenCode output did not include a valid control conclusion": for an APPROVE, valid_control() repairs the summary by filling the required review labels from the bounded evidence file resolved via OPENCODE_EVIDENCE_FILE / OPENCODE_APPROVAL_REPAIR_EVIDENCE_FILE. The model pool step sets OPENCODE_EVIDENCE_FILE, so the pool accepts a repaired APPROVE and records success. The publish step did NOT set it, so its re-run of the normalizer could not repair the same summary, rejected it (NO_CONCLUSION, exit 4), and failed the whole review — even though a model had produced a valid APPROVE. This surfaced once non-reasoning models (which emit a bare APPROVE summary) were ordered first. Expose the same OPENCODE_EVIDENCE_FILE in the publish step so both steps repair and validate identically. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01RTAMs4bpSZS77Xe3RQjv9P
![opencode-agent[bot]](https://avatars.githubusercontent.com/in/1549082?s=60&v=4){kind=small}
There was a problem hiding this comment.
Pull request overview
OpenCode reviewed the current-head bounded evidence and found no blocking issues.
Findings
No blocking findings.
Summary
Approval sufficiency: bounded evidence supplied affirmative approval evidence for changed files, coverage/docstring posture, risk surfaces, and current-head verification; approval is not based merely on the absence of known blockers.
Verification posture: CodeGraph evidence was initialized and bounded current-head evidence reviewed for changed-file evidence including .github/workflows/opencode-review.yml, scripts/ci/run_opencode_review_model_pool.sh.
Linter/static: workflow/static review evidence is bounded by the current-head GitHub Checks gate and changed-file evidence.
TDD/regression: coverage execution evidence and focused changed hunks were reviewed from bounded-review-evidence.md.
Coverage: coverage execution evidence reports test coverage as not applicable because no supported changed source files or package manifests were found.
Docstring coverage: coverage execution evidence reports docstring coverage as not applicable because no supported changed source files or package manifests were found.
DAG: CodeGraph/source-backed behavior map connects .github/workflows/opencode-review.yml to the affected review, runtime, or workflow path and required checks.
PoC/execution: coverage-evidence job executed on the current head and reported PASS.
DDD/domain: workflow and repository-governance invariants were reviewed against changed files in bounded evidence.
CDD/context: CodeGraph evidence, changed-file history, and focused hunks were reviewed from bounded-review-evidence.md.
Similar issues: changed-file history evidence was reviewed for comparable local precedents.
Claim/concept check: bounded evidence, repository source, current-head workflow evidence, and, where numeric, scientific, statistical, or literature-backed claims are affected, original-paper/formula evidence and parameter-recovery expectations were used for claims.
Standards search: standards and external-source checks are delegated to configured OpenCode web_search/Context7/DeepWiki sources when applicable; no evidence-backed standards blocker is present in bounded evidence.
Compatibility/convention: changed workflow/script conventions, object naming, and reserved-word safety for schema/API/config/code surfaces were checked in bounded evidence.
Breaking-change/backcompat: deployment evidence and changed-file history were checked for backward-compatibility risk.
Performance: changed surfaces were checked for performance risk in bounded evidence.
Developer experience: changed automation, review, test, setup, and maintenance surfaces were checked for helpful or obstructive DX impact in bounded evidence.
User experience: connected user, operator, API, CLI, documentation, review-comment, status-check, rendering, and workflow-reader behavior was checked for contradictions against code, docs, and tests in bounded evidence.
Visual/DOM: Playwright visual, DOM locator, ARIA snapshot, console, and responsive evidence were checked when a web UI surface was present; for non-web surfaces, API/CLI/log/docs/workflow interaction evidence was reviewed instead.
Accessibility/i18n: accessibility, localization, and human-readable text surfaces were checked where UI, CLI, API message, docs, logs, or review text changed.
Supply-chain/license: dependency, package, model, container, and external-tool changes were checked in bounded evidence.
Packaging: package, build, test, lint, and security contracts were checked in bounded evidence.
Security/privacy: workflow-token, review-gate, and repository-automation security/privacy boundaries were checked in bounded evidence.
- Result: APPROVE
- Reason: The changes ensure consistency in evidence file handling between the model pool and publish gate, resolving a previous validation issue.
- Head SHA:
13ce9bfe3fe2361e1f5fddba0058c11b63bda841 - Workflow run: 28742457026
- Workflow attempt: 1
Changed-File Evidence Map
flowchart LR
PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
Evidence --> S1["Workflow: opencode-review.yml"]
S1 --> I1["GitHub Actions review job"]
I1 --> R1["Review risk: Workflow: opencode-review.yml"]
R1 --> V1["actionlint plus required checks"]
Evidence --> S2["CI script: run_opencode_review_model_pool.sh"]
S2 --> I2["review and security gate shell path"]
I2 --> R2["Review risk: CI script: run_opencode_review_model_pool.sh"]
R2 --> V2["bash -n plus Strix self-test"]
OpenCode Review Overview
Pull request overviewOpenCode reviewed the current-head bounded evidence and found no blocking issues. FindingsNo blocking findings. SummaryApproval sufficiency: bounded evidence supplied affirmative approval evidence for changed files, coverage/docstring posture, risk surfaces, and current-head verification; approval is not based merely on the absence of known blockers.
Changed-File Evidence Mapflowchart LR
PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
Evidence --> S1["Workflow: opencode-review.yml"]
S1 --> I1["GitHub Actions review job"]
I1 --> R1["Review risk: Workflow: opencode-review.yml"]
R1 --> V1["actionlint plus required checks"]
Evidence --> S2["CI script: run_opencode_review_model_pool.sh"]
S2 --> I2["review and security gate shell path"]
I2 --> R2["Review risk: CI script: run_opencode_review_model_pool.sh"]
R2 --> V2["bash -n plus Strix self-test"]
|
1 participant
근본 원인 (CI 정밀 디버그로 확정)
리뷰 실패 "Selected successful OpenCode output did not include a valid control conclusion"의 원인: APPROVE 검증 시
valid_control()이repair_approval_summary()로 누락된 24개 리뷰 라벨을 bounded evidence 파일에서 채웁니다. evidence 파일은OPENCODE_EVIDENCE_FILEenv로 찾습니다.OPENCODE_EVIDENCE_FILE설정 → repair 성공 → 성공 기록OPENCODE_EVIDENCE_FILE미설정 → repair 불가 → 라벨 없음 → NO_CONCLUSION(exit 4) → 리뷰 실패비추론 모델(bare APPROVE summary)을 쿼터순 1순위로 올리자 표면화됨.
수정
publish 스텝 env에 풀 스텝과 동일한
OPENCODE_EVIDENCE_FILE추가 → 두 스텝이 동일하게 repair·검증. 이제 유효 APPROVE가 실제로 게시됨.🤖 Generated with Claude Code