`mcp/checkout.test.ts` and `mcp/reviewComments.test.ts` previously hit
live GitHub on every run via `acquireNewToken()`, requiring `GH_TOKEN`
or `GITHUB_APP_ID` + `GITHUB_PRIVATE_KEY` in the env. that made them:
- cred-gated — the action runtime filters `_KEY$` / `_TOKEN$` from
subprocess env, so the husky pre-push hook (which runs
`pnpm -r test`) blocked Pullfrog agents from pushing branches. issues
#562, #563, #564, #566 all hit this exact blocker and never got their
fixes pushed.
- non-deterministic and slow (network round-trips for a snapshot test).
both tests are really snapshot tests of pure formatters
(`formatFilesWithLineNumbers`, plus `parseFilePatches` /
`buildThreadBlocks` / `formatReviewThreads` for review data). the live
fetches were just an inefficient way to obtain fixtures.
changes:
1. extract a pure `formatReviewData({ review, threads, prFiles, ... })`
from `getReviewData` in `mcp/reviewComments.ts`. `getReviewData`
becomes thin orchestration: fetch + call formatter. preserves the
"skip listFiles when no threads" perf optimization.
2. add `action/mcp/__fixtures__/` with checked-in JSON captures for the
three fixture test cases (pullfrog/test-repo#1 listFiles,
pullfrog/scratch#49 review 3485940013, pullfrog/scratch#64 review
3531000326). ~14KB total. fixtures store only the fields the
formatter reads — volatile fields (sha, blob_url, etc.) are dropped.
3. rewrite both test files to load the fixtures and call the pure
formatters directly. snapshot keys updated; snapshot content
unchanged (verified by running existing snapshots against the
refactored tests).
4. add `action/scripts/refresh-test-fixtures.ts` to re-fetch the
fixtures from live GitHub on demand:
`node action/scripts/refresh-test-fixtures.ts` (with creds in
`.env` or env). re-run when the GitHub API response shape changes
and review the snapshot diff.
trade-off: a silent change to GitHub's `pulls.listFiles` /
`pulls.getReview` / GraphQL `reviewThreads` response shape would no
longer break this test on every push. that tradeoff is worth it: shape
drift on those endpoints is rare (years between changes), and a
dedicated cron that runs the refresh script and opens a PR on diff is
a far better signal than a flaky cred-gated pre-push hook.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Add "Fix it" link for body-only PR reviews
When a PR review has only body-level feedback (no inline comments),
the footer now includes a "Fix it" link that triggers the fix flow.
Also fetches the review body in the fix action's prompt so the agent
can address body-level feedback even when there are no inline comments.
* Move review body fetching into `get_review_comments` tool
Instead of fetching the review body in the trigger page and appending
it to the prompt, the `get_review_comments` MCP tool now fetches the
review body via the GitHub API and includes it in its markdown output
under a "Review Body" section. This keeps the trigger page simple and
lets the tool provide all review context in one place.
* fetch body early
* get reviewer from a better place
* cleanup structure to reuse more in test
* simplify
* simplify
* typecheck
* fetch review body via REST API; skip listFiles for body-only reviews
* update snapshot
* formatting
* cleanup
* fix line counting with `countNewlines` utility using `indexOf` loop
* rename `countNewlines` to `countLines` with 1-based line counting
* suppress biome lint warning for assignment in while condition
* remove unused `body` field from GraphQL review query and type
* add `approved` parameter to `create_pull_request_review` and skip fix links for approvals
* vibe instructions
* tighten up prompting
---------
Co-authored-by: pullfrog[bot] <226033991+pullfrog[bot]@users.noreply.github.com>
Co-authored-by: Mateusz Burzyński <mateuszburzynski@gmail.com>
* refactor get_review_comments to use reviewThreads graphql api with full thread context and proper diff extraction
* Improve get_review_comments output
* Improve tests and diffs
* GH_TOKEN
* Added back approved_by
* Fix CI
David Blass