Commit Graph
8 Commits
Author SHA1 Message Date
Philippe Loulidi 792e3d0b24 stack-aware review: confirm upstack requalifications against the real patch 2026-07-31 20:30:07 -07:00
Philippe Loulidi 6992933354 stack-aware review: requalify findings addressed in stacked PRs
Add root-only, off-by-default stack-aware requalification: walk the
open PRs stacked on top of the current one, inject a paths-only
manifest into the coordinator, and let it mark absence-style findings
as addressed by a later PR. Requalified findings stay visible and
counted but stop blocking. Grounding strips forged, hallucinated, or
protected (critical/secrets/security) requalifications deterministically,
after verify and before suppress.
2026-07-31 20:30:07 -07:00
Philippe Loulidi 6bbc1fbd7a Adopt LLP: design docs in llp/, @ref annotations, ref-check in CI (#38)
Retrofit of https://github.com/ccheever/llp. Ten LLP docs capture the
design rationale (trust model, engine pipeline, runtimes, config,
verification, sources/reporters, CLI, templates); 161 @ref comments link
code to the sections that explain it. ref-check (copied from upstream,
dependency-free) validates refs and metadata on every push and PR.
Every rationale claim is tagged [observed] with its evidence.
2026-07-31 01:20:51 -06:00
Brent Vatne 601b19afc1 Trusted base-commit configuration by default; isolate the runtime from PR-head config
ecr ci now loads all review configuration (config.jsonc, routing, prompts,
models, auth mapping) from the PR's immutable base commit, materialized via
the GitHub API — never from the PR head — failing closed with one terminal
comment when the base can't be materialized. The PR head is materialized
separately (pinned to its immutable OID, mandatory in CI) purely as source
content, and is scrubbed of ambient runtime config (opencode.json{,c},
.opencode/ plugins, AGENTS.md, CLAUDE.md, .claude/, .mcp.json, .cursor*,
.env*) before the OpenCode server starts, closing a fork-reachable code
execution path through the /review command workflow.

- git fetches append `-c credential.helper=!gh auth git-credential` so
  base-SHA checkouts with persist-credentials:false still fetch private repos
  (token never in argv or .git/config)
- run log + patch workspace anchor at the workspace (runsDir), never the
  temporary trusted root, so the artifact upload path keeps resolving
- a scope config that is new in a PR reviews with the root config and
  activates after merge (hasScopeConfig fallback)
- scaffolded workflows check out the base SHA with persist-credentials:false;
  the repo's own self-review workflow runs the engine from base source
- escape hatch: ecr ci --unsafe-config-from-head (loud warning, never
  scaffolded, removal scheduled)
2026-07-26 22:29:18 -07:00
Philippe Loulidi 4cfe919a8c Add scoped fingerprints, aggregate rendering, and reporter/review plumbing (inert) (#17)
* Add routing manifest schemas + scope config loading (inert)

* Add scoped fingerprints, aggregate rendering, and reporter/review fan-out plumbing (inert)
2026-07-24 14:27:06 -06:00
expo-tuft[bot]andbrentvatne 97473bab52 Add oxlint + oxfmt and wire into CI (#10)
Co-authored-by: brentvatne <[email protected]>
2026-07-23 11:08:33 -07:00
Brent Vatne dbd52eff2b Review the PR-head tree on --pr runs (verification fidelity) (#1) 2026-07-22 23:30:30 -07:00
Brent Vatne fed362b2ad Initial commit: @expo/code-review-cli
Config-driven, multi-agent AI code reviewer engine. Extracted from
expo/eas-cli (PR #4022, packages/expo-code-review-cli) into its own repo so
it can be published as @expo/code-review-cli and iterated independently.

The engine is repo-agnostic: consuming repos supply their own agents and
settings under .expo-code-review/. Built on the OpenCode SDK.
2026-07-22 18:18:43 -07:00