Files
OmniRoute/tests/unit/chatcore-context-editing-telemetry.test.ts
Diego Rodrigues de Sa e Souza 3d4f3e4960 test(infra): retry recursive temp-dir removal instead of failing a shard on ENOTEMPTY (#11966) (#11968)
* test(infra): retry recursive temp-dir removal instead of failing a shard on ENOTEMPTY (#11966)

Two shards on release/v3.8.51 went red in one day with the same signature —
"ENOTEMPTY, Directory not empty: /tmp/omniroute-<test>-XXXXXX" — from
combo-same-provider-cascade (Unit Tests fast-path 4/4, on a PR that touches only
.github/) and auth-policy-embeddings-webfetch-7785 (the 20k-test TIA step). Both pass
alone and on re-run: the cleanup races something still writing into the directory
(SQLite WAL/-shm checkpoint, a worker, the backup) and under a loaded hosted runner
the window opens. 1154 test files do their own cleanup with
fs.rmSync(dir, { recursive: true, force: true }); 57 already asked for retries.

One-shot codemod (scripts/ad-hoc/codemod-rm-maxretries.mjs, kept for the record):
every rm / rmSync / rmdirSync option object with `recursive: true` and no
`maxRetries` gains `maxRetries: 5, retryDelay: 100` — Node itself then retries
ENOTEMPTY/EBUSY/EPERM for up to ~0.5 s before giving up. 2243 call sites in 1292
files under tests/, the shared tests/_setup/isolateDataDir.ts exit hook included.
Only the option object changes: no call site, assertion or import is touched.

Validation: prettier and ESLint (with the frozen suppressions) clean on all 1292
files; a random 20-file sample runs green (quota-redis-store hangs identically on
the untouched tree — it needs a Redis on localhost, an environment matter). The
four unit shards on this PR are the full run.

* fix(quality): let check-forgotten-sibling-tests read a 1,000-file diff

The gate shells out to `git diff` through execFileSync with Node's default 1 MB
maxBuffer; the 1,292-file codemod in this PR is the first diff large enough to
overflow it, and the gate died with `spawnSync git ENOBUFS` before comparing
anything. 64 MB is far above any real PR and costs nothing when unused.
2026-08-29 01:17:40 -03:00

106 lines
3.2 KiB
TypeScript

// Characterization of recordContextEditingTelemetryHook — the Claude-only context-editing
// telemetry hook extracted from handleChatCore's non-streaming success path (chatCore god-file
// decomposition, #3501). The work is a fire-and-forget IIFE; uses a real temp DB and polls the
// captured log. Locks: the enabled+claude guard, the no-telemetry no-op, and that a valid
// applied_edits payload records and logs the cleared-token receipt.
import { test, before, after } from "node:test";
import assert from "node:assert/strict";
import fs from "node:fs";
import os from "node:os";
import path from "node:path";
const testDataDir = fs.mkdtempSync(path.join(os.tmpdir(), "omni-ctxedit-test-"));
process.env.DATA_DIR = testDataDir;
const coreDb = await import("../../src/lib/db/core.ts");
const { recordContextEditingTelemetryHook } =
await import("../../open-sse/handlers/chatCore/contextEditingTelemetry.ts");
function makeLog() {
const debug: string[] = [];
return {
log: { debug: (tag: string, msg: string) => debug.push(`${tag} ${msg}`) },
debug,
};
}
const telemetryBody = {
context_management: {
applied_edits: [{ cleared_input_tokens: 120, cleared_tool_uses: 3 }],
},
};
async function waitFor(pred: () => boolean, timeoutMs = 3000): Promise<void> {
const deadline = Date.now() + timeoutMs;
while (Date.now() < deadline && !pred()) {
await new Promise((r) => setTimeout(r, 25));
}
}
before(async () => {
await coreDb.ensureDbInitialized();
});
after(() => {
coreDb.resetDbInstance();
try {
fs.rmSync(testDataDir, { recursive: true, force: true, maxRetries: 5, retryDelay: 100 });
} catch {
// best-effort cleanup
}
});
test("disabled context-editing is a no-op", async () => {
const { log, debug } = makeLog();
recordContextEditingTelemetryHook({
contextEditingEnabled: false,
provider: "claude",
responseBody: telemetryBody,
skillRequestId: "req-1",
log,
});
await new Promise((r) => setTimeout(r, 100));
assert.equal(debug.length, 0);
});
test("non-claude provider is a no-op", async () => {
const { log, debug } = makeLog();
recordContextEditingTelemetryHook({
contextEditingEnabled: true,
provider: "openai",
responseBody: telemetryBody,
skillRequestId: "req-2",
log,
});
await new Promise((r) => setTimeout(r, 100));
assert.equal(debug.length, 0);
});
test("valid applied_edits records and logs the cleared-token receipt", async () => {
const { log, debug } = makeLog();
recordContextEditingTelemetryHook({
contextEditingEnabled: true,
provider: "claude",
responseBody: telemetryBody,
skillRequestId: "req-3",
log,
});
await waitFor(() => debug.length > 0);
assert.ok(debug.length >= 1, "expected a CONTEXT_EDITING debug line");
assert.match(debug[0], /CONTEXT_EDITING/);
assert.match(debug[0], /cleared 120 input tokens \/ 3 tool uses \(1 edits\)/);
});
test("response without applied_edits is a silent no-op (no throw)", async () => {
const { log, debug } = makeLog();
recordContextEditingTelemetryHook({
contextEditingEnabled: true,
provider: "claude",
responseBody: { choices: [] },
skillRequestId: "req-4",
log,
});
await new Promise((r) => setTimeout(r, 100));
assert.equal(debug.length, 0);
});