Constraint: User explicitly requested all roadmap PRs be merged when correct and mapped into the Ultragoal backlog when not immediately mergeable.
Rejected: leaving the PR inventory as ignored OMX-only state | roadmap merge obligations need a tracked handoff for later G011/G012 gates.
Confidence: high
Scope-risk: narrow
Directive: Refresh this intake after each roadmap PR merge batch and regenerate the CC2 board if ROADMAP.md changes.
Tested: gh pr list --state open --search roadmap in:title --json number,title,author,mergeable,isDraft,statusCheckRollup,headRefName,baseRefName,updatedAt,url --limit 200
Not-tested: individual PR mergeability was not forced in this intake commit.
Co-authored-by: OmX <omx@oh-my-codex.dev>
Constraint: Task 5 is reporting/map ownership only; worker-1 owns implementation changes and shared security/path tests.\nRejected: Editing runtime enforcement failures from this lane | shared implementation/test ownership belongs to other workers unless re-scoped.\nConfidence: high\nScope-risk: narrow\nDirective: Keep this artifact synchronized with exact verification output before leader aggregation.\nTested: python3 scripts/validate_cc2_board.py --board .omx/cc2/board.json; python3 .omx/cc2/validate_issue_parity_intake.py .omx/cc2/issue-parity-intake.json; scripts/fmt.sh --check; cargo check --workspace; targeted runtime permission/path tests; mock parity harness.\nNot-tested: Full clippy and cargo test --workspace are not green due pre-existing/shared runtime/CLI failures documented in the artifact.
The Ultragoal now has an explicit repository-operations gate so final completion cannot rely only on roadmap implementation while correct PRs or resolvable issues remain unhandled.
Constraint: The user explicitly added that all PRs should be merged and all issues resolved when they are correct and resolvable.
Rejected: Treating the existing roadmap board as sufficient | it did not require per-PR and per-issue final triage evidence.
Confidence: high
Scope-risk: narrow
Directive: Refresh GitHub PR and issue snapshots at the final gate; do not merge unsafe or incorrect PRs merely to reduce counts.
Tested: gh auth status; gh pr list --state open --limit 200 captured 50 records; gh issue list --state open --limit 1000 captured 1000 records.
Not-tested: Full PR/issue triage is deferred to the dedicated gate and later streams.
Co-authored-by: OmX <omx@oh-my-codex.dev>
Created comprehensive MODEL_COMPATIBILITY.md documenting:
- Kimi models is_error exclusion (prevents 400 Bad Request)
- Reasoning models tuning parameter stripping (o1, o3, o4, grok-3-mini, qwen-qwq)
- GPT-5 max_completion_tokens requirement
- Qwen model routing through DashScope
Includes implementation details, key functions table, guide for adding new
models, and testing commands. Cross-referenced with existing code comments.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add a checked-in Containerfile plus container-first documentation so Docker and Podman users have a canonical image build, bind-mount, and cargo test entrypoint. The README now links directly to the new guide.
Constraint: The repo already had runtime container detection but no checked-in Dockerfile, Containerfile, or devcontainer config
Rejected: Put all container steps inline in README only | harder to maintain and less reusable than a dedicated guide plus Containerfile
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Keep docs/container.md and Containerfile aligned whenever Rust workspace prerequisites change
Tested: docker build -t claw-code-dev-docs-verify -f Containerfile .
Tested: cargo test --workspace (host, in rust/)
Not-tested: Podman commands were documented but not executed in this environment
Not-tested: Repeated in-container cargo test --workspace currently trips crates/tools PowerShell stub detection on this minimal image even though host cargo test passes
