feat(ci): add Noema LLM review gate

[seonghobae]

Summary

• Add Required Noema Review as a central LLM review workflow for ContextualWisdomLab repositories.
• Exchange GitHub Actions OIDC tokens through the Noema Cloudflare Worker to obtain a distinct Noema GitHub App installation token.
• Run an independent Noema LLM diff review before submitting an APPROVE, REQUEST_CHANGES, or COMMENT verdict.

Required configuration

• NOEMA_TOKEN_EXCHANGE_URL: Noema Worker /exchange endpoint, expected shape https://noema.contextualwisdomlab.workers.dev/exchange after the Workers subdomain change.
• NOEMA_OIDC_AUDIENCE: optional override, defaults to cwl-noema-review.
• NOEMA_LLM_API_URL: OpenAI-compatible chat completions endpoint.
• NOEMA_LLM_MODEL: model name for Noema review.
• NOEMA_LLM_API_KEY: secret API key for the LLM endpoint.

Notes

• Noema is intentionally separate from OpenCode Agent so GitHub receives a different review actor.
• The workflow skips review when the Noema app token or LLM configuration is unavailable.
• The Noema GitHub App needs pull request write, checks read, and contents read permissions.

[opencode-agent]

OpenCode Review Overview

• Head SHA: cc62cb263a5c4f4dae376ad873b63971fa5fe9a6
• Workflow run: 28433947943
• Workflow attempt: 1
• Gate result: APPROVE (approval step)

Pull request overview

OpenCode reviewed the current-head bounded evidence and found no blocking issues.

Findings

No blocking findings.

Summary

Added secondary LLM review workflow with comprehensive tests. Verification: Linter/static: N/A (no lint commands), TDD/regression: PASS (122 tests), Coverage: 100%, Docstring coverage: 99.5% (advisory), DAG: New workflow triggers after OpenCode/Strix, PoC/execution: Sandboxed test failed due to socket issue (non-blocking), DDD/domain: Aligns with CI governance, CDD/context: Matches existing patterns, Similar issues: None found, Standards search: Cloudflare OIDC standard, Compatibility/convention: Consistent with repo, Breaking-change/backcompat: None, Performance: Minimal resource impact, Developer experience: Improves review quality, User experience: Adds secondary safety check, Accessibility/i18n: N/A, Supply-chain/license: Python dependencies audited, Packaging: Complete Python package contract.

Verification posture: CodeGraph evidence was initialized and bounded current-head evidence reviewed for changed-file evidence including .github/workflows/noema-review.yml, scripts/ci/noema_review_gate.py, tests/test_noema_review_gate.py.
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 supported repository test suites passed.
Docstring coverage: coverage execution evidence reports configured repository docstring gates passed or docstring coverage was advisory.
DAG: Change Flow DAG maps .github/workflows/noema-review.yml through bounded evidence, review risk, 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, and current-head workflow evidence 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 and compatibility 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, and maintenance surfaces were checked for helpful or obstructive DX impact in bounded evidence.
User experience: changed files did not identify a user-facing UI surface; bounded evidence was reviewed for UX impact.
Security/privacy: workflow-token, review-gate, and repository-automation security/privacy boundaries were checked in bounded evidence.

• Result: APPROVE
• Reason: No blocking issues found
• Head SHA: cc62cb263a5c4f4dae376ad873b63971fa5fe9a6
• Workflow run: 28433947943
• Workflow attempt: 1

Change Flow DAG

flowchart LR
  PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
  Evidence --> S1["Workflow: noema-review.yml"]
  S1 --> I1["GitHub Actions review job"]
  I1 --> R1["Review risk: Workflow: noema-review.yml"]
  R1 --> V1["actionlint plus required checks"]
  Evidence --> S2["CI script: noema_review_gate.py"]
  S2 --> I2["review and security gate shell path"]
  I2 --> R2["Review risk: CI script: noema_review_gate.py"]
  R2 --> V2["bash -n plus Strix self-test"]
  Evidence --> S3["Test: test_noema_review_gate.py"]
  S3 --> I3["regression suite"]
  I3 --> R3["Review risk: Test: test_noema_review_gate.py"]
  R3 --> V3["targeted test run"]

Loading

[opencode-agent]

Pull request overview

OpenCode reviewed the current-head bounded evidence and found no blocking issues.

Findings

No blocking findings.

Summary

Added secondary LLM review workflow with comprehensive tests. Verification: Linter/static: N/A (no lint commands), TDD/regression: PASS (122 tests), Coverage: 100%, Docstring coverage: 99.5% (advisory), DAG: New workflow triggers after OpenCode/Strix, PoC/execution: Sandboxed test failed due to socket issue (non-blocking), DDD/domain: Aligns with CI governance, CDD/context: Matches existing patterns, Similar issues: None found, Standards search: Cloudflare OIDC standard, Compatibility/convention: Consistent with repo, Breaking-change/backcompat: None, Performance: Minimal resource impact, Developer experience: Improves review quality, User experience: Adds secondary safety check, Accessibility/i18n: N/A, Supply-chain/license: Python dependencies audited, Packaging: Complete Python package contract.

Verification posture: CodeGraph evidence was initialized and bounded current-head evidence reviewed for changed-file evidence including .github/workflows/noema-review.yml, scripts/ci/noema_review_gate.py, tests/test_noema_review_gate.py.
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 supported repository test suites passed.
Docstring coverage: coverage execution evidence reports configured repository docstring gates passed or docstring coverage was advisory.
DAG: Change Flow DAG maps .github/workflows/noema-review.yml through bounded evidence, review risk, 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, and current-head workflow evidence 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 and compatibility 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, and maintenance surfaces were checked for helpful or obstructive DX impact in bounded evidence.
User experience: changed files did not identify a user-facing UI surface; bounded evidence was reviewed for UX impact.
Security/privacy: workflow-token, review-gate, and repository-automation security/privacy boundaries were checked in bounded evidence.

• Result: APPROVE
• Reason: No blocking issues found
• Head SHA: cc62cb263a5c4f4dae376ad873b63971fa5fe9a6
• Workflow run: 28433947943
• Workflow attempt: 1

Change Flow DAG

flowchart LR
  PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
  Evidence --> S1["Workflow: noema-review.yml"]
  S1 --> I1["GitHub Actions review job"]
  I1 --> R1["Review risk: Workflow: noema-review.yml"]
  R1 --> V1["actionlint plus required checks"]
  Evidence --> S2["CI script: noema_review_gate.py"]
  S2 --> I2["review and security gate shell path"]
  I2 --> R2["Review risk: CI script: noema_review_gate.py"]
  R2 --> V2["bash -n plus Strix self-test"]
  Evidence --> S3["Test: test_noema_review_gate.py"]
  S3 --> I3["regression suite"]
  I3 --> R3["Review risk: Test: test_noema_review_gate.py"]
  R3 --> V3["targeted test run"]

Loading