* docs: tighten PR review expectations in CONTRIBUTING and AGENTS guides
- Add drift caveat to CodeRabbit findings: verify suggestions against
PR intent before applying; decline out-of-scope with justification
or ask a maintainer; never silently ignore findings
- Add Keep Your Branch Current subsection (rebase duty, fix-churn warning)
- Require full local CI-equivalent suite green before every push, with
cross-platform exception
- Add ignored/filler PR template submissions to close-without-review list
- Expand follow-up guidance: multi-round review is normal, repeated fix
requests signal root-cause investigation and better agent prompting
- Mirror all of the above in AGENTS.md for coding agents
* docs: address CodeRabbit findings on review-expectations guides
- Make CONTRIBUTING.md Validation the single authoritative pre-push
validation contract mirroring .github/workflows/pr-checks.yml exactly:
--frozen-lockfile install, launcher compatibility checks, provider
recommendation via npm as CI does, web job carve-out
- Remove conflicting 'relevant subset' wording; cross-platform exception
is the only carve-out from the full suite
- AGENTS.md now defers to the CONTRIBUTING contract instead of defining
a divergent core-checks list
- Reword ambiguous 'submit the PR template ignored' bullet to 'submit a
PR with the PR template ignored'
* docs: align pre-push validation suite with CI semantics
- Drop standalone 'bun run test:full'; bun run check already includes it
- Document web workspace install (bun install --cwd web --frozen-lockfile)
before web checks, matching the web CI job
- Pass explicit --base/--head to security:pr-scan so local scans target
the PR merge-base like CI does instead of script defaults
* docs: use PR base commit ref for local security scan parity
Replace git merge-base computation with origin/main and document the
required invariant (fetch + keep branch rebased onto current origin/main)
so the local scan matches CI's PR base.sha instead of diverging.
* docs: use exact PR base for security scan
* docs: make local validation contract portable
* docs: scope local checks and baseline waivers
* docs: harden contributor workflow guidance
* docs: pin contributor safety contracts
* fix(web): add 0.27 release entry
* test(web): cover 0.27 release entry
* fix(web): clarify 0.27 permission-timeout highlight
* docs: ban drive-by edits to web/src/data/releases.ts
Tell agents and contributors that the curated changelog is owned by
the release/web process, and stop verify-dist from instructing unrelated
PRs to patch it when npm publishes ahead of the site.
* test(web): locate curated release by version
* test(web): enforce newest-first release order
Remove the unused Python helper island under python/, including the standalone Ollama adapter, smart router, pytest tests, and Python requirements file.
Drop the corresponding Python setup, dependency install, and pytest steps from the PR checks workflow now that no repo-level Python helper suite remains.
Clean contributor-facing references in README, AGENTS.md, and CONTRIBUTING.md so the repository map and validation guidance no longer point at deleted Python helper code.
Validation:
- bun run build: passed
- bun run typecheck: passed
- bun run typecheck:type-tests: passed
- bun run test:provider-recommendation: passed
- bun run security:pr-scan -- --base upstream/main --head HEAD: passed
- bun run check: failed in existing broader test suites unrelated to this removal (bughunter git context, Conversation Arc Scale and Stability, xAI OAuth callback)
- bun run test:provider: failed in existing xAI OAuth callback tests
Co-authored-by: jatmn <jatmn@users.noreply.github.com>
Add AGENTS.md with repository-specific guidance for AI coding agents, including runtime conventions, validation commands, provider-change expectations, and limits on new Python work.
Update CONTRIBUTING.md with maintainer-directed contribution expectations, CodeRabbit follow-up requirements, duplicate PR guidance, and a link to AGENTS.md.
JATMNandGitHub
