Files
codegraph/__tests__/mcp-staleness-banner.test.ts
T
b48170e69f feat(mcp): per-file staleness banner + tunable watcher debounce (#403) (#428)
Two coupled changes addressing the issue's underlying ask — "how does the
agent know when the index lags" — without resorting to a static wait.

Per-file staleness banner
-------------------------
FileWatcher now tracks per-path `pendingFiles` (path, firstSeenMs,
lastSeenMs, indexing) — events since the last successful sync, cleared
only after a sync whose `syncStartedMs >= lastSeenMs` commits. Chokidar
initial-scan events are gated behind a `ready` flag (with `waitUntilReady()`
exposed so tests can deterministically wait through it) so a fresh startup
doesn't falsely flag every existing file as pending.

ToolHandler now wraps every code-returning response (search, context,
callers, callees, impact, trace, explore, node, files) with
`withStalenessNotice`: intersects "files referenced in the response" with
`getPendingFiles()` and emits a hybrid signal —

  * banner at the top for files referenced AND pending (with edit age +
    indexing/pending-sync state, telling the agent to Read those specific
    files directly; the rest of the response stays fresh and codegraph
    stays authoritative for it),
  * compact footer for pending files elsewhere in the project not
    referenced above (capped at 5).

Cost is one boolean check + N substring matches when pending; zero
allocation when idle. `codegraph_status` surfaces the same data as a
first-class `### Pending sync:` section so the agent can ask "is the index
caught up?" in one call.

Cross-project quirk: when an agent passes `projectPath` matching the
default session's project, the staleness wrapper switches from the cached
cross-project CodeGraph (no watcher) to the default one (with watcher) so
the signal still fires. Same fix applied to `handleStatus`.

CODEGRAPH_WATCH_DEBOUNCE_MS
---------------------------
MCP `serve --mcp` now reads `CODEGRAPH_WATCH_DEBOUNCE_MS` and forwards it
to `cg.watch({ debounceMs })`. Clamped to [100ms, 60s]; out-of-range or
non-numeric values fall back to the FileWatcher default (2000ms). Active
value is logged to stderr on watcher startup so it's discoverable. The
docs in `server-instructions.ts`, `installer/instructions-template.ts`,
and `.cursor/rules/codegraph.mdc` no longer claim "~500ms"; they now
describe the banner mechanism instead — since per-file staleness replaces
the "wait N ms" guidance entirely, the docs become accurate at any
debounce value.

Validation
----------
* 847 unit/integration tests pass (added 15 new ones — pending-file
  tracking, banner/footer routing, status section, env-var parsing).
* Direct MCP probe through a real `codegraph serve --mcp` process: edit a
  file, query within the debounce window, banner fires naming the
  edited file with edit-age.
* Real Claude TUI session via `scripts/agent-eval/itrun.sh` with
  `CODEGRAPH_WATCH_DEBOUNCE_MS=10000`: agent edits `math.ts`, calls
  `codegraph_explore`, reads the banner, **and discloses it unprompted in
  its final reply**: "note: symbol index is mid-sync for the new `divide`,
  but the source it returned is verbatim from disk."

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-25 23:48:10 -05:00

154 lines
5.9 KiB
TypeScript

/**
* Per-file staleness banner on MCP tool responses (issue #403).
*
* The watcher tracks every file event since the last successful sync; the
* tool dispatcher intersects "files referenced in this response" with that
* pending set and prepends a banner ("⚠️ Some files referenced below were
* edited since the last index sync…") plus an optional footer ("(Note: N
* file(s) elsewhere in this project are pending index sync…)").
*
* No auto-flush, no static wait — the response is instant and the agent
* decides whether to Read the specific stale file. These tests exercise
* the full real path: real watcher + real CodeGraph index + real
* ToolHandler.execute().
*/
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
import * as fs from 'fs';
import * as path from 'path';
import * as os from 'os';
import CodeGraph from '../src/index';
import { ToolHandler } from '../src/mcp/tools';
function waitFor(condition: () => boolean, timeoutMs = 5000, intervalMs = 50): Promise<void> {
return new Promise((resolve, reject) => {
const start = Date.now();
const tick = () => {
if (condition()) return resolve();
if (Date.now() - start > timeoutMs) return reject(new Error('waitFor timed out'));
setTimeout(tick, intervalMs);
};
tick();
});
}
describe('MCP staleness banner', () => {
let testDir: string;
let cg: CodeGraph;
let handler: ToolHandler;
beforeEach(async () => {
testDir = fs.mkdtempSync(path.join(os.tmpdir(), 'codegraph-stale-banner-'));
fs.mkdirSync(path.join(testDir, 'src'));
// Three isolated files with no cross-references — keeps each test's
// "which path does the response mention?" assertion unambiguous. If the
// files shared imports/calls, codegraph_search responses would surface
// multiple file paths and the banner-vs-footer split would be racy.
fs.writeFileSync(
path.join(testDir, 'src', 'alpha-only.ts'),
'export function alphaOnly() { return 1; }\n',
);
fs.writeFileSync(
path.join(testDir, 'src', 'bravo-only.ts'),
'export function bravoOnly() { return 2; }\n',
);
fs.writeFileSync(
path.join(testDir, 'src', 'charlie-only.ts'),
'export function charlieOnly() { return 3; }\n',
);
cg = CodeGraph.initSync(testDir, { config: { include: ['**/*.ts'], exclude: [] } });
await cg.indexAll();
handler = new ToolHandler(cg);
});
afterEach(() => {
try { cg.unwatch(); } catch { /* ignore */ }
try { cg.close(); } catch { /* ignore */ }
if (fs.existsSync(testDir)) fs.rmSync(testDir, { recursive: true, force: true });
});
it('prepends a stale banner when the response references a pending file', async () => {
// Long debounce so the edit lingers in pendingFiles while we query.
cg.watch({ debounceMs: 4000 });
await cg.waitUntilWatcherReady();
fs.writeFileSync(
path.join(testDir, 'src', 'alpha-only.ts'),
'export function alphaOnly() { return 99; }\n',
);
await waitFor(() => cg.getPendingFiles().some((p) => p.path === 'src/alpha-only.ts'), 8000);
const res = await handler.execute('codegraph_search', { query: 'alphaOnly' });
expect(res.isError).toBeFalsy();
const text = res.content[0].text;
// Banner shape: warning glyph + filename + actionable instruction.
expect(text.startsWith('⚠️')).toBe(true);
expect(text).toContain('src/alpha-only.ts');
expect(text).toMatch(/edited \d+ms ago/);
expect(text).toMatch(/Read them directly/);
// The actual result must still follow the banner.
expect(text).toMatch(/alphaOnly/);
});
it('uses the footer (not the banner) when pending files are not referenced', async () => {
cg.watch({ debounceMs: 4000 });
await cg.waitUntilWatcherReady();
// Edit bravo-only.ts but search for the alphaOnly symbol, whose hit is
// only in alpha-only.ts. The two files share no imports/calls so the
// response text won't mention bravo-only.ts.
fs.writeFileSync(
path.join(testDir, 'src', 'bravo-only.ts'),
'export function bravoOnly() { return 22; }\n',
);
await waitFor(() => cg.getPendingFiles().some((p) => p.path === 'src/bravo-only.ts'), 8000);
const res = await handler.execute('codegraph_search', { query: 'alphaOnly' });
const text = res.content[0].text;
expect(text.startsWith('⚠️')).toBe(false);
expect(text).toMatch(/elsewhere in this project are pending index sync/);
expect(text).toContain('src/bravo-only.ts');
});
it('drops the banner once the sync completes and clears the pending entry', async () => {
cg.watch({ debounceMs: 200 });
await cg.waitUntilWatcherReady();
fs.writeFileSync(
path.join(testDir, 'src', 'alpha-only.ts'),
'export function alphaOnly() { return 7; }\n',
);
await waitFor(() => cg.getPendingFiles().length === 0, 5000);
const res = await handler.execute('codegraph_search', { query: 'alphaOnly' });
const text = res.content[0].text;
expect(text.startsWith('⚠️')).toBe(false);
expect(text).not.toMatch(/elsewhere in this project are pending index sync/);
});
it('lists pending files under "Pending sync" in codegraph_status', async () => {
cg.watch({ debounceMs: 4000 });
await cg.waitUntilWatcherReady();
fs.writeFileSync(
path.join(testDir, 'src', 'charlie-only.ts'),
'export function charlieOnly() { return 33; }\n',
);
await waitFor(() => cg.getPendingFiles().some((p) => p.path === 'src/charlie-only.ts'), 8000);
const res = await handler.execute('codegraph_status', {});
const text = res.content[0].text;
expect(text).toContain('### Pending sync:');
expect(text).toContain('src/charlie-only.ts');
// Status embeds the info first-class, so the auto-banner is suppressed.
expect(text.startsWith('⚠️')).toBe(false);
});
it('returns zero pending files when no watcher is active', () => {
expect(cg.getPendingFiles()).toEqual([]);
});
});