Files
OmniRoute/tests/unit/codex-orphaned-tool-outputs-2928.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

139 lines
4.2 KiB
TypeScript

import test from "node:test";
import assert from "node:assert/strict";
import { mkdtempSync, rmSync } from "node:fs";
import { tmpdir } from "node:os";
import { join } from "node:path";
const TEST_DATA_DIR = mkdtempSync(join(tmpdir(), "omniroute-codex-orphaned-2928-"));
process.env.DATA_DIR = TEST_DATA_DIR;
const core = await import("../../src/lib/db/core.ts");
const { CodexExecutor } = await import("../../open-sse/executors/codex.ts");
type InputItem = Record<string, unknown>;
function transform(input: InputItem[]): InputItem[] {
const executor = new CodexExecutor();
const result = executor.transformRequest(
"gpt-5.6-sol",
{
_nativeCodexPassthrough: true,
model: "gpt-5.6-sol",
input,
stream: true,
},
true,
{ requestEndpointPath: "/responses" }
);
assert.ok(Array.isArray(result.input));
return result.input as InputItem[];
}
function toolOutputs(input: InputItem[]): InputItem[] {
return input.filter((item) => item.type === "function_call_output");
}
test.after(() => {
core.resetDbInstance();
rmSync(TEST_DATA_DIR, { recursive: true, force: true, maxRetries: 5, retryDelay: 100 });
});
test("Codex strips function_call_output items without matching function calls", () => {
const result = transform([
{
type: "message",
role: "user",
content: [{ type: "input_text", text: "hi" }],
},
{ type: "function_call_output", call_id: "call_orphan1", output: "result1" },
{ type: "function_call_output", call_id: "call_orphan2", output: "result2" },
]);
assert.deepEqual(toolOutputs(result), []);
});
test("Codex keeps a function_call_output with a matching Responses function_call", () => {
const result = transform([
{
type: "function_call",
call_id: "call_valid",
name: "read_file",
arguments: '{"path":"a.txt"}',
},
{ type: "function_call_output", call_id: "call_valid", output: "file contents" },
]);
assert.deepEqual(toolOutputs(result), [
{ type: "function_call_output", call_id: "call_valid", output: "file contents" },
]);
});
test("Codex keeps matched outputs and removes orphaned outputs from mixed input", () => {
const result = transform([
{ type: "function_call", call_id: "call_keep", name: "read_file", arguments: "{}" },
{ type: "function_call_output", call_id: "call_keep", output: "ok" },
{ type: "function_call_output", call_id: "call_orphan", output: "orphaned" },
]);
assert.equal(result.length, 2);
assert.deepEqual(toolOutputs(result), [
{ type: "function_call_output", call_id: "call_keep", output: "ok" },
]);
});
test("Codex recognizes embedded Chat Completions tool_calls as matching calls", () => {
const result = transform([
{
type: "message",
role: "assistant",
content: [],
tool_calls: [
{ id: "call_cc1", type: "function", function: { name: "read_file", arguments: "{}" } },
],
},
{ type: "function_call_output", call_id: "call_cc1", output: "ok" },
{ type: "function_call_output", call_id: "call_cc2", output: "orphaned" },
]);
assert.deepEqual(toolOutputs(result), [
{ type: "function_call_output", call_id: "call_cc1", output: "ok" },
]);
});
test("Codex preserves tool outputs linked to a remote previous_response_id", () => {
const executor = new CodexExecutor();
const result = executor.transformRequest(
"gpt-5.6-sol",
{
_nativeCodexPassthrough: true,
previous_response_id: "resp_remote_history",
input: [{ type: "function_call_output", call_id: "call_remote", output: "remote result" }],
stream: true,
},
true,
{ requestEndpointPath: "/responses" }
);
assert.deepEqual(result.input, [
{ type: "function_call_output", call_id: "call_remote", output: "remote result" },
]);
});
test("Codex leaves inputs without function_call_output items unchanged", () => {
const input = [
{
type: "message",
role: "user",
content: [{ type: "input_text", text: "hi" }],
},
{ type: "function_call", call_id: "call_1", name: "read_file", arguments: "{}" },
];
assert.deepEqual(transform(input), [
input[0],
input[1],
{ type: "function_call_output", call_id: "call_1", output: "" },
]);
});