test(mcp): make checkout/reviewComments tests offline (fixture-driven) (#575)

`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>

mcp/checkout.test.ts

@@ -1,8 +1,7 @@
-import type { RestEndpointMethodTypes } from "@octokit/rest";
+import { readFileSync } from "node:fs";
+import { resolve } from "node:path";
 import { describe, expect, it } from "vitest";
-import { acquireNewToken, createOctokit } from "../utils/github.ts";
-import { fetchAndFormatPrDiff } from "./checkout.ts";
-import type { ToolContext } from "./server.ts";
+import { type FormatFilesResult, formatFilesWithLineNumbers } from "./checkout.ts";
 
 /**
  * parses TOC entries like "- src/math.ts → lines 7-42 · diff-<hex>" into structured data.
@@ -22,59 +21,50 @@ function parseTocEntries(toc: string) {
   return entries;
 }
 
-async function getToken(): Promise<string> {
-  // prefer explicit GH_TOKEN, fall back to acquiring one via GitHub App credentials
-  if (process.env.GH_TOKEN) return process.env.GH_TOKEN;
-  return await acquireNewToken();
+// fixture captured by action/scripts/refresh-test-fixtures.ts. running
+// the formatter against checked-in JSON keeps this test offline and
+// deterministic — re-fetch the fixture (with creds) when GitHub's
+// pulls.listFiles response shape changes, then review the snapshot diff.
+type DiffFixture = {
+  owner: string;
+  name: string;
+  pullNumber: number;
+  files: Parameters<typeof formatFilesWithLineNumbers>[0];
+};
+
+function loadFixture<T>(file: string): T {
+  return JSON.parse(readFileSync(resolve(import.meta.dirname, "__fixtures__", file), "utf-8")) as T;
 }
 
-describe("fetchAndFormatPrDiff", () => {
-  it(
-    "generates accurate TOC line numbers for pullfrog/test-repo#1",
-    { timeout: 30000 },
-    async () => {
-      const token = await getToken();
-      const octokit = createOctokit(token);
-      const ctx = {
-        octokit,
-        repo: {
-          owner: "pullfrog",
-          name: "test-repo",
-          data: {} as RestEndpointMethodTypes["repos"]["get"]["response"]["data"],
-        },
-      } as ToolContext;
-      const result = await fetchAndFormatPrDiff(ctx, 1);
+describe("formatFilesWithLineNumbers", () => {
+  it("generates accurate TOC line numbers for pullfrog/test-repo#1", () => {
+    const fx = loadFixture<DiffFixture>("pullfrog-test-repo-pr-1.diff.json");
+    const result: FormatFilesResult = formatFilesWithLineNumbers(fx.files);
 
-      // verify content includes TOC at the start
-      expect(result.content.startsWith(result.toc)).toBe(true);
+    expect(result.content.startsWith(result.toc)).toBe(true);
 
-      // parse TOC and validate every entry's line numbers against actual content
-      const contentLines = result.content.split("\n");
-      const tocEntries = parseTocEntries(result.toc);
-      expect(tocEntries.length).toBeGreaterThan(0);
+    const contentLines = result.content.split("\n");
+    const tocEntries = parseTocEntries(result.toc);
+    expect(tocEntries.length).toBeGreaterThan(0);
 
-      for (const entry of tocEntries) {
-        // line numbers are 1-indexed, arrays are 0-indexed
-        const firstLine = contentLines[entry.startLine - 1];
-        expect(firstLine).toBeDefined();
-        // first line of each file section should be the diff header
-        expect(firstLine).toBe(`diff --git a/${entry.filename} b/${entry.filename}`);
+    for (const entry of tocEntries) {
+      // line numbers are 1-indexed, arrays are 0-indexed
+      const firstLine = contentLines[entry.startLine - 1];
+      expect(firstLine).toBeDefined();
+      // first line of each file section should be the diff header
+      expect(firstLine).toBe(`diff --git a/${entry.filename} b/${entry.filename}`);
 
-        // endLine should be within bounds
-        expect(entry.endLine).toBeLessThanOrEqual(contentLines.length);
-      }
-
-      // verify adjacent files don't overlap and are contiguous
-      for (let i = 1; i < tocEntries.length; i++) {
-        const prev = tocEntries[i - 1];
-        const curr = tocEntries[i];
-        // current file starts right after previous file ends
-        expect(curr.startLine).toBe(prev.endLine + 1);
-      }
-
-      // snapshot the full output for regression detection
-      expect(result.toc).toMatchSnapshot("toc");
-      expect(result.content).toMatchSnapshot("content");
+      expect(entry.endLine).toBeLessThanOrEqual(contentLines.length);
     }
-  );
+
+    // verify adjacent files don't overlap and are contiguous
+    for (let i = 1; i < tocEntries.length; i++) {
+      const prev = tocEntries[i - 1];
+      const curr = tocEntries[i];
+      expect(curr.startLine).toBe(prev.endLine + 1);
+    }
+
+    expect(result.toc).toMatchSnapshot("toc");
+    expect(result.content).toMatchSnapshot("content");
+  });
 });