diff --git a/.github/workflows/codec-carver-hourly-review-repair.yml b/.github/workflows/codec-carver-hourly-review-repair.yml new file mode 100644 index 000000000..61d77507b --- /dev/null +++ b/.github/workflows/codec-carver-hourly-review-repair.yml @@ -0,0 +1,32 @@ +name: Codec-Carver Hourly Review Repair + +on: + schedule: + # Minute 5 avoids Clearfolio (23), DiskSage (37), fast-mlsirm (49), + # BandScope (53), naruon (11), Inkspan (47), orchestrator (17), + # Wardnet (7), and Keyverse (29). + - cron: "5 * * * *" + +concurrency: + group: codec-carver-hourly-review-repair + # A later heartbeat must not cancel an in-flight STT/codec RCA or repair. + cancel-in-progress: false + +permissions: + contents: read + +jobs: + dispatch-review-repair: + permissions: + contents: read + id-token: write + uses: ./.github/workflows/pr-review-fix-scheduler.yml + with: + target_repository: ContextualWisdomLab/codec-carver + base_branch: main + max_prs: "50" + max_dispatches: "1" + retry_hours: "2" + secrets: + PR_REVIEW_MERGE_TOKEN: ${{ secrets.PR_REVIEW_MERGE_TOKEN }} + OPENCODE_APPROVE_TOKEN: ${{ secrets.OPENCODE_APPROVE_TOKEN }} diff --git a/.github/workflows/hourly-nvidia-nim-review-repair.yml b/.github/workflows/hourly-nvidia-nim-review-repair.yml index 9eb450619..2f87142b7 100644 --- a/.github/workflows/hourly-nvidia-nim-review-repair.yml +++ b/.github/workflows/hourly-nvidia-nim-review-repair.yml @@ -13,6 +13,7 @@ on: - .github/workflows/github-hourly-review-repair.yml - .github/workflows/governance-risk-compliance-hourly-review-repair.yml - .github/workflows/hourly-nvidia-nim-review-repair.yml + - .github/workflows/codec-carver-hourly-review-repair.yml - .github/workflows/nonnest2-hourly-review-repair.yml - .github/workflows/orgmetra-hourly-review-repair.yml - .github/workflows/originweave-hourly-review-repair.yml @@ -29,6 +30,7 @@ on: - tests/test_orgmetra_hourly_review_caller.py - tests/test_originweave_hourly_review_caller.py - tests/test_quarantine_sandbox_hourly_review_caller.py + - tests/test_codec_carver_hourly_review_caller.py - tests/test_hourly_autofix_context_quality_gate.py - tests/test_pr_review_conflict_scope.py - tests/test_pr_review_conflict_scope_control_files.py @@ -54,6 +56,7 @@ on: - docs/doctoring/orgmetra-hourly-review-caller.md - docs/doctoring/originweave-hourly-review-caller.md - docs/doctoring/quarantine-sandbox-hourly-review-caller.md + - docs/doctoring/codec-carver-hourly-review-caller.md push: paths: - .github/workflows/pr-review-fix-scheduler.yml @@ -66,6 +69,7 @@ on: - .github/workflows/github-hourly-review-repair.yml - .github/workflows/governance-risk-compliance-hourly-review-repair.yml - .github/workflows/hourly-nvidia-nim-review-repair.yml + - .github/workflows/codec-carver-hourly-review-repair.yml - .github/workflows/nonnest2-hourly-review-repair.yml - .github/workflows/orgmetra-hourly-review-repair.yml - .github/workflows/originweave-hourly-review-repair.yml @@ -82,6 +86,7 @@ on: - tests/test_orgmetra_hourly_review_caller.py - tests/test_originweave_hourly_review_caller.py - tests/test_quarantine_sandbox_hourly_review_caller.py + - tests/test_codec_carver_hourly_review_caller.py - tests/test_hourly_autofix_context_quality_gate.py - tests/test_pr_review_conflict_scope.py - tests/test_pr_review_conflict_scope_control_files.py @@ -107,6 +112,7 @@ on: - docs/doctoring/orgmetra-hourly-review-caller.md - docs/doctoring/originweave-hourly-review-caller.md - docs/doctoring/quarantine-sandbox-hourly-review-caller.md + - docs/doctoring/codec-carver-hourly-review-caller.md permissions: contents: read @@ -164,6 +170,7 @@ jobs: tests/test_orgmetra_hourly_review_caller.py \ tests/test_originweave_hourly_review_caller.py \ tests/test_quarantine_sandbox_hourly_review_caller.py \ + tests/test_codec_carver_hourly_review_caller.py \ tests/test_pr_review_conflict_scope_control_files.py \ tests/test_hourly_autofix_context_quality_gate.py \ tests/test_pr_review_conflict_scope_git_executable.py \ diff --git a/ARCHITECTURE.md b/ARCHITECTURE.md index c48db831f..273226363 100644 --- a/ARCHITECTURE.md +++ b/ARCHITECTURE.md @@ -39,6 +39,13 @@ only established scheduler credentials, and grants job-scoped only established scheduler credentials, and grants job-scoped `id-token: write`. The reusable engine stays product-neutral. +## Codec-carver hourly caller + +`codec-carver-hourly-review-repair.yml` is a thin, read-only caller at minute +5. It names `ContextualWisdomLab/codec-carver` and protected `main`, maps +only established scheduler credentials, and grants job-scoped +`id-token: write`. The reusable engine stays product-neutral. + ## Hourly NVIDIA NIM repair gate ```mermaid diff --git a/CHANGELOG.md b/CHANGELOG.md index e42afe76a..625e44f62 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -11,6 +11,7 @@ Semantic Versioning where the repository publishes a release. - Added an hourly organization commercial-readiness coordinator that discovers writable repositories, honors enabled dedicated writer leases and fully paginated live writer runs, refetches exact repository/workflow/run/PR state before dispatch, rotates bounded review-repair and opt-in NVIDIA OpenCode product-development targets, fails nonzero on fleet-wide inspection or dispatch outages, retains three-day JSON receipts, and keeps the existing 15-minute merge scheduler authoritative. - Added a dedicated Quarantine Sandbox Runtime hourly caller at minute 14 that targets protected `develop`, dispatches at most one exact-head repair, applies a two-hour same-head retry floor, preserves non-cancelling single-flight execution, and maps only the established scheduler credentials with job-scoped OIDC. - Added a dedicated OriginWeave hourly caller that invokes the product-neutral central scheduler with the exact repository, protected `main` branch, one-dispatch budget, two-hour same-head retry floor, non-cancelling single-flight heartbeat, job-scoped OIDC, and only the established scheduler credentials. +- Added a dedicated codec-carver hourly caller that invokes the product-neutral central scheduler with the exact repository, protected `main` branch, one-dispatch budget, two-hour same-head retry floor, non-cancelling single-flight heartbeat, job-scoped OIDC, and only the established scheduler credentials. - Added a trusted pull-request comment router for `@cwl-noema-review` and review-only `@opencode-agent` dispatches, with an organization sweep, exact-head receipts, repository allowlisting, fixed runners, immutable checkout pins, and a permanent 100% statement/branch/docstring quality gate. - Added an organization-owned reusable exact-artifact SBOM attestation boundary that validates inert six-file wheel/sdist evidence, binds CycloneDX 1.7 predicates to exact SHA-256 subjects, signs through least-privilege GitHub artifact attestations, and exports online and offline verification bundles. - Added exact-base `uv.lock` materialization that reconstructs standalone nested projects with a checksum-pinned official `uv` exporter, isolated frozen/offline execution, strict exact-pin and SHA-256 output validation, and complete Python 3.10/3.14 quality evidence. diff --git a/docs/doctoring/codec-carver-hourly-review-caller.md b/docs/doctoring/codec-carver-hourly-review-caller.md new file mode 100644 index 000000000..103d14240 --- /dev/null +++ b/docs/doctoring/codec-carver-hourly-review-caller.md @@ -0,0 +1,139 @@ +# Codec-carver hourly review-repair caller + +검토 기준일: **2026-08-17** + +## Decision + +ContextualWisdomLab operates one protected hourly caller for +`ContextualWisdomLab/codec-carver` (omni-modal speech-and-video codec: +STT, speaker diarization, consented voiceprint, and conversion for LLM +input). The caller runs at minute 5, delegates to the product-neutral +central review-fix scheduler, inspects at most 50 open pull requests +targeting protected `main`, and dispatches at most one bounded repair +per heartbeat. + +A paying buyer of the codec would feel live codec-carver pull requests +stalling while hourly NVIDIA NIM repair scanned only Clearfolio, DiskSage, +and fast-mlsirm. Live heads such as ContextualWisdomLab/codec-carver#435 +(HMAC Unicode DoS), ContextualWisdomLab/codec-carver#437 (SQLite WAL +journal), and ContextualWisdomLab/codec-carver#434 (search performance) +target `main` and never enter those other callers. + +The caller does not implement review or mutation logic itself. +Codec-carver remains standalone; naruon consumes converted media without +owning the codec runtime. Privileged automation stays in +`ContextualWisdomLab/.github`. + +## Root-cause analysis and remediation feasibility + +The reusable worker performs exact-head root-cause analysis and tests +remediation feasibility before it edits. The reusable worker must: + +1. Refetch the exact live head, base, reviews, checks, changed paths, and + writer state. +2. Establish the causal chain rather than repeat the terminal symptom. +3. Enumerate materially distinct minimal remedies. +4. Reject remedies that lack writer authority, cross sealed paths, require + unavailable credentials or protected-setting changes, violate stack + order, cannot be verified, or do not alter the diagnosed cause. +5. Dispatch at most one feasible repair. Otherwise leave the tree + unchanged. + +A queued or pending check remains a merge blocker but is not itself a +code finding. The independent non-author approval remains an external +authorization gate and is never synthesized by the repair worker. The +worker cannot approve, merge, release, resolve review findings by +inference, change protection, or manufacture passing checks. + +## Cadence and concurrency + +The caller uses a single concurrency group and `cancel-in-progress: false`. +This preserves an in-flight bounded RCA instead of discarding codec +evidence when the next hourly heartbeat arrives. The reusable scheduler +cancels only its own superseded short queue scan. + +The caller sets a **two-hour same-head retry floor**. Central OpenCode and +NVIDIA NIM work, plus codec conversion or HMAC verification analysis, can +legitimately approach two hours. An hourly redispatch of the same +unchanged head would create duplicate writer pressure rather than faster +remediation. + +GitHub scheduled workflows can be delayed under load and execute only +from the default branch. The cron expression is a heartbeat, not a +real-time SLA. + +## Credential and model boundary + +The caller keeps workflow `GITHUB_TOKEN` at `contents: read` and grants +the reusable job `id-token: write` so the central scheduler can mint the +OpenCode GitHub App token from GitHub OIDC when the mapped PAT is absent +(GitHub, n.d.-c). It maps only `PR_REVIEW_MERGE_TOKEN` and +`OPENCODE_APPROVE_TOKEN`. It never uses `secrets: inherit`, receives +`NVIDIA_NIM_API_KEY`, or introduces `COPILOT_GITHUB_TOKEN`. CWE-250 +forbids executing the caller with write or model privileges it does not +need (MITRE, 2026). + +Model execution remains inside the central worker. The model credential +is the GitHub Secret `NVIDIA_NIM_API_KEY`; the caller does not receive or +forward it. + +Before protected-main activation, the repository variable +`OPENCODE_REPOSITORY_DISPATCH_TARGETS` must contain the exact +`ContextualWisdomLab/codec-carver` target. Missing or mismatched +configuration fails before mutation credential materialization. + +## Security, standalone operation, and modularity + +The caller adds no codec-carver runtime dependency, database object, +network endpoint, tenant authority, or product credential. Codec-carver +continues to run as a standalone conversion service. Naruon and other CWL +services may consume its output, but they cannot weaken its exact-head, +approval, or security gates. + +## Verification and rollback + +Machine-checkable contracts require the exact target/base, minute 5 +cadence, non-cancelling single-flight group, one dispatch, two-hour +retry floor, explicit secret mapping, read-only contents plus job-scoped +`id-token: write`, focused path-filter coverage, and absence of model or +Copilot credentials. Independent `pull_request`, `push`, and `compileall` +path blocks must each name the caller, doctoring, or contract they own. + +After source integration, closure requires a scheduled or manual +protected-main consumer run proving the exact codec-carver repository and +`main` base. Source checks alone are not protected-main operational acceptance. +Merge still requires zero unresolved valid findings and a +qualifying independent non-author approval. + +Rollback removes the codec-carver caller, its focused test, doctoring, and +central path-filter/documentation entries. It must not remove scheduler +dispatch validation or affect independent product callers. + +## APA 7th references + +GitHub, Inc. (n.d.-a). *Events that trigger workflows*. GitHub Docs. +Retrieved August 17, 2026, from +https://docs.github.com/en/actions/reference/workflows-and-actions/events-that-trigger-workflows#schedule + +GitHub, Inc. (n.d.-b). *Reuse workflows*. GitHub Docs. Retrieved August +17, 2026, from +https://docs.github.com/en/actions/how-tos/sharing-automations/reuse-workflows + +GitHub, Inc. (n.d.-c). *Automatic token authentication*. GitHub Docs. +Retrieved August 17, 2026, from +https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#permissions-for-the-github_token + +MITRE. (2026). *CWE-250: Execution with unnecessary privileges*. +https://cwe.mitre.org/data/definitions/250.html + +National Institute of Standards and Technology. (2022). *Secure software +development framework (SSDF) version 1.1: Recommendations for mitigating +the risk of software vulnerabilities* (NIST Special Publication 800-218). +https://doi.org/10.6028/NIST.SP.800-218 + +NVIDIA. (n.d.). *NVIDIA NIM for large language models documentation*. +Retrieved August 17, 2026, from +https://docs.nvidia.com/nim/large-language-models/latest/ + +OpenCode. (n.d.). *OpenCode documentation*. Retrieved August 17, 2026, +from https://opencode.ai/docs/ diff --git a/requirements-pip-audit-ci-hashes.txt b/requirements-pip-audit-ci-hashes.txt index ade197a49..0ae099d8f 100644 --- a/requirements-pip-audit-ci-hashes.txt +++ b/requirements-pip-audit-ci-hashes.txt @@ -213,9 +213,9 @@ packaging==26.2 \ # via # pip-audit # pip-requirements-parser -pip==26.1.2 \ - --hash=sha256:382ff9f685ee3bc25864f820aa50505825f10f5458ffff07e30a6d96e5715cab \ - --hash=sha256:f49cd134c61cf2fd75e0ce2676db03e4054504a5a4986d00f8299ae632dc4605 +pip==26.2.1 \ + --hash=sha256:71138adf1f4ca900cdb7d289c21b7494329f2332b6d85f0e1c42108c0384ed3e \ + --hash=sha256:f6ad667e89a1fe78046c8f13232b247200f5258d7828f3f7883d660878e0813f # via pip-api pip-api==0.0.34 \ --hash=sha256:8b2d7d7c37f2447373aa2cf8b1f60a2f2b27a84e1e9e0294a3f6ef10eb3ba6bb \ diff --git a/scripts/ci/test_strix_quick_gate.sh b/scripts/ci/test_strix_quick_gate.sh index ac9ce1d8b..04f58bf31 100755 --- a/scripts/ci/test_strix_quick_gate.sh +++ b/scripts/ci/test_strix_quick_gate.sh @@ -1506,8 +1506,8 @@ assert_pr_review_merge_scheduler_uses_github_actions_bot_token() { assert_file_contains "$workflow_file" "github.event_name == 'pull_request_target' && format('pr-{0}', github.event.pull_request.number)" "scheduler scopes pull_request_target concurrency to the active PR" assert_file_contains "$workflow_file" "github.event_name == 'workflow_run' && github.event.workflow_run.pull_requests[0].number && format('pr-{0}', github.event.workflow_run.pull_requests[0].number)" "scheduler scopes workflow_run concurrency to the completed review PR" assert_file_contains "$workflow_file" "github.event_name == 'schedule' && format('schedule-{0}', github.event.schedule)" "scheduler isolates the 15-minute organization sweep from the separate 30-minute scheduled scan" - assert_file_contains "$workflow_file" "github.event_name == 'repository_dispatch' && github.run_id" "scheduler keeps manual queue scans isolated per run" - assert_file_contains "$workflow_file" "cancel-in-progress: \${{ github.event_name == 'pull_request_target' || github.event_name == 'pull_request_review' || github.event_name == 'repository_dispatch' }}" "scheduler cancels stale PR/review/manual queue scans instead of accumulating merge/update attempts" + assert_file_contains "$workflow_file" "github.event_name == 'repository_dispatch' && format('repo-dispatch-{0}', github.repository)" "scheduler keeps manual queue scans isolated per repository dispatch target" + assert_file_contains "$workflow_file" "cancel-in-progress: \${{ github.event_name == 'pull_request_target' || github.event_name == 'pull_request_review' || github.event_name == 'repository_dispatch' || (github.event_name == 'workflow_run' && !github.event.workflow_run.pull_requests[0].number) }}" "scheduler cancels stale PR/review/manual queue scans instead of accumulating merge/update attempts" assert_file_contains "$workflow_file" "timeout-minutes: 60" "organization sweep has enough headroom to finish the complete repository walk" assert_file_contains "$workflow_file" "ORG_SWEEP_TRIGGER_REVIEWS: \${{ github.event_name == 'schedule' ||" "scheduled organization sweeps retry missing current-head OpenCode reviews" assert_file_contains "$workflow_file" "ORG_SWEEP_ENABLE_AUTO_MERGE: \${{ github.event_name == 'schedule' ||" "scheduled organization sweeps merge approved current heads" diff --git a/tests/test_codec_carver_hourly_review_caller.py b/tests/test_codec_carver_hourly_review_caller.py new file mode 100644 index 000000000..bea992066 --- /dev/null +++ b/tests/test_codec_carver_hourly_review_caller.py @@ -0,0 +1,165 @@ +"""Contract tests for codec-carver's bounded hourly review-repair caller.""" + +from pathlib import Path + + +CALLER = Path(".github/workflows/codec-carver-hourly-review-repair.yml") +DOCTORING = Path("docs/doctoring/codec-carver-hourly-review-caller.md") +QUALITY_WORKFLOW = Path(".github/workflows/hourly-nvidia-nim-review-repair.yml") +SCHEDULER = Path(".github/workflows/pr-review-fix-scheduler.yml") + + +def _read(path: Path) -> str: + """Return one repository contract file as UTF-8 text.""" + return path.read_text(encoding="utf-8") + + +def _yaml_path_entries(block: str) -> set[str]: + """Return dashed YAML path entries from one trigger or compileall block.""" + entries: set[str] = set() + for raw_line in block.splitlines(): + stripped = raw_line.strip() + if stripped.startswith("- "): + entries.add(stripped[2:].strip()) + elif stripped.startswith("tests/") or stripped.startswith("scripts/"): + entries.add(stripped.rstrip(" \\")) + return entries + + +def _trigger_path_block(quality: str, trigger: str) -> str: + """Return the dashed path list under one named workflow trigger.""" + marker = f" {trigger}:\n paths:\n" + start = quality.index(marker) + len(marker) + lines: list[str] = [] + for line in quality[start:].splitlines(): + if line.startswith(" - "): + lines.append(line) + continue + if line.strip() == "": + continue + break + return "\n".join(lines) + + +def _compileall_block(quality: str) -> str: + """Return the compileall argument list from the focused quality job.""" + marker = "python -m compileall -q \\" + start = quality.index(marker) + remainder = quality[start:] + end = remainder.find("\n git ") + return remainder if end < 0 else remainder[:end] + + +def test_codec_carver_caller_is_hourly_bounded_and_non_cancelling() -> None: + """Codec-carver receives one realistic conversion repair without cancellation.""" + caller = _read(CALLER) + + assert 'cron: "5 * * * *"' in caller + assert "group: codec-carver-hourly-review-repair" in caller + assert "cancel-in-progress: false" in caller + assert "uses: ./.github/workflows/pr-review-fix-scheduler.yml" in caller + assert "target_repository: ContextualWisdomLab/codec-carver" in caller + assert "base_branch: main" in caller + assert 'max_prs: "50"' in caller + assert 'max_dispatches: "1"' in caller + assert 'retry_hours: "2"' in caller + + +def test_codec_carver_caller_preserves_oidc_and_explicit_secret_scope() -> None: + """The queue scanner maps established credentials without model secrets.""" + caller = _read(CALLER) + workflow_scope, jobs_scope = caller.split("\njobs:\n", maxsplit=1) + + assert "\npermissions:\n contents: read\n" in workflow_scope + assert ( + "\n permissions:\n contents: read\n id-token: write\n" + in jobs_scope + ) + assert "PR_REVIEW_MERGE_TOKEN: ${{ secrets.PR_REVIEW_MERGE_TOKEN }}" in caller + assert "OPENCODE_APPROVE_TOKEN: ${{ secrets.OPENCODE_APPROVE_TOKEN }}" in caller + assert "secrets: inherit" not in caller + assert "NVIDIA_NIM_API_KEY" not in caller + assert "COPILOT_GITHUB_TOKEN" not in caller + for forbidden in ( + "actions: write", + "contents: write", + "issues: write", + "pull-requests: write", + "statuses: write", + ): + assert forbidden not in caller + + +def test_codec_carver_target_is_not_hard_coded_in_shared_scheduler() -> None: + """Product identity remains in the thin caller rather than the engine.""" + assert "ContextualWisdomLab/codec-carver" not in _read(SCHEDULER) + + +def test_codec_carver_doctoring_records_codec_activation_and_credentials() -> None: + """Operators retain target-allowlist, codec, and approval prerequisites.""" + doctoring = _read(DOCTORING) + + for phrase in ( + "ContextualWisdomLab/codec-carver", + "OPENCODE_REPOSITORY_DISPATCH_TARGETS", + "independent non-author approval", + "NVIDIA_NIM_API_KEY", + "COPILOT_GITHUB_TOKEN", + "id-token: write", + "two-hour same-head retry floor", + "root-cause analysis", + "remediation feasibility", + "protected-main operational acceptance", + "APA 7th references", + "ContextualWisdomLab/codec-carver#435", + "ContextualWisdomLab/codec-carver#437", + "ContextualWisdomLab/codec-carver#434", + ): + assert phrase in doctoring + + +def test_path_block_helpers_keep_trigger_and_compileall_sets_disjoint() -> None: + """A path listed only under push or compileall must not satisfy pull_request.""" + quality = ( + "on:\n" + " pull_request:\n" + " paths:\n" + " - .github/workflows/codec-carver-hourly-review-repair.yml\n" + " push:\n" + " paths:\n" + " - docs/doctoring/codec-carver-hourly-review-caller.md\n" + " python -m compileall -q \\\n" + " tests/test_codec_carver_hourly_review_caller.py\n" + " git diff --check\n" + ) + + pull_request_paths = _yaml_path_entries(_trigger_path_block(quality, "pull_request")) + push_paths = _yaml_path_entries(_trigger_path_block(quality, "push")) + compileall_paths = _yaml_path_entries(_compileall_block(quality)) + + assert pull_request_paths == {".github/workflows/codec-carver-hourly-review-repair.yml"} + assert push_paths == {"docs/doctoring/codec-carver-hourly-review-caller.md"} + assert compileall_paths == {"tests/test_codec_carver_hourly_review_caller.py"} + assert "docs/doctoring/codec-carver-hourly-review-caller.md" not in pull_request_paths + assert ".github/workflows/codec-carver-hourly-review-repair.yml" not in compileall_paths + + +def test_focused_quality_workflow_tracks_codec_carver_contracts() -> None: + """Caller, test, and doctoring edits always rerun the focused gate.""" + quality = _read(QUALITY_WORKFLOW) + pull_request_paths = _yaml_path_entries(_trigger_path_block(quality, "pull_request")) + push_paths = _yaml_path_entries(_trigger_path_block(quality, "push")) + compileall_paths = _yaml_path_entries(_compileall_block(quality)) + caller = ".github/workflows/codec-carver-hourly-review-repair.yml" + doctoring = "docs/doctoring/codec-carver-hourly-review-caller.md" + contract = "tests/test_codec_carver_hourly_review_caller.py" + + assert caller in pull_request_paths + assert doctoring in pull_request_paths + assert contract in pull_request_paths + assert caller in push_paths + assert doctoring in push_paths + assert contract in push_paths + assert contract in compileall_paths + assert caller not in compileall_paths + assert doctoring not in compileall_paths