deer-flow/frontend/tests/e2e-record/record-write-read-file.spec.ts
Xinmin Zeng 88759015e4
test(e2e): deterministic record/replay front-back contract verification (#3365)
* test(e2e): record/replay front-back contract verification

Guards the front-back contract with a deterministic, key-free record/replay
harness (mirrors open-design's golden-trace approach):

- ReplayChatModel (tests/replay_provider.py): replays recorded LLM turns by a
  normalized hash of the model input. Strips <system-reminder>/date/uuid/tmp-path
  so one fixture replays across days and from both the browser and direct-POST
  paths; a miss raises loudly (no silent divergence).
- Recording is record-through-browser (scripts/record_gateway.py +
  build_fixture_from_jsonl.py + frontend/tests/e2e-record): a real run is driven
  through the real frontend so captured inputs match exactly what the browser
  sends; fixtures contain no API key.
- Layer 1 — backend golden (tests/test_replay_golden.py): replay through the real
  gateway, assert the SSE event sequence == committed golden.
- Layer 2 — full-stack render (frontend/tests/e2e-real-backend): real Next.js +
  real gateway (replay model) + Chromium; assert the replayed auto-title and
  follow-up suggestions render. DOM assertions are the gate; visual regression is
  a local dev gate (CI uploads the render as an artifact).
- CI (.github/workflows/replay-e2e.yml): both layers, triggered on EITHER side of
  the contract (frontend/** or backend gateway/harness/fixtures).

* test(e2e): multi-run render-order cross-stack scenario (#3352)

Guards the dangerous front-back class where a backend ordering change
silently breaks a frontend assumption while both sides' unit tests stay
green. Reproduces issue #3352: backend list_by_thread returns runs
newest-first (#2932) and the frontend prepended per-run pages, inverting
chronological order once the checkpoint no longer held the older messages.

- tests/seed_runs_router.py: test-only seeder, mounted on the replay
  gateway only when DEERFLOW_ENABLE_TEST_SEED=1 (never in the production
  app). Seeds a thread with >=2 runs + per-run message events and no
  checkpoint -- the #3352 precondition -- so the frontend per-run reload
  path is the sole source of truth and the prepend inversion is observable.
- frontend/tests/e2e-real-backend/multi-run-order.spec.ts: drives the real
  frontend against the real gateway, asserts the first run renders above
  the second. Reverting the #3354 fix turns it red.
- replay-e2e.yml: trigger on the new replay test-infra paths.
- docs: REPLAY_E2E.md cross-stack scenario section.

* test(e2e): address Copilot review on the replay harness

- Fix stale recorder references (scripts/record_traces.py ->
  scripts/record_gateway.py + scripts/build_fixture_from_jsonl.py) in
  replay_provider.py, test_replay_golden.py, _replay_fixture.py.
- MODE_CONTEXT['ultra']: thinking_enabled False -> True, mirroring the
  frontend's `context.mode !== 'flash'` (hooks.ts). It did not affect the
  hashed input (Layer 1 golden still green), but the table now matches the
  real frontend context it claims to mirror.
- replay_provider.py docstring: stop claiming memory is recorded-enabled;
  the replay config disables memory/summarization for determinism (title
  stays, as an in-graph deterministic call).
- record_gateway.py / run_replay_gateway.py: override DEER_FLOW_HOME instead
  of setdefault, so an outer value can't leak into the hermetic harness.
- record_gateway.py: clear error when DEERFLOW_RECORD_OUT is unset (was a
  bare KeyError).
- playwright.record.config.ts: forward OPENAI_*/DEERFLOW_RECORD_OUT only when
  set, so the gateway raises a clear 'missing env' error instead of getting ''.

* test(e2e): address Copilot review round 2

- seed_runs_router.py: constrain SeedMessage.role to Literal['human','ai']
  so a bad value is a clean 422 at the boundary instead of a 500
  (KeyError on _EVENT_TYPE).
- record-write-read-file.spec.ts: waitForCaptureStable now throws on
  timeout instead of returning the last count, so a truncated/partial
  recording can't pass silently.
- real-backend-render.spec.ts: guard the suggestions JSON.parse; a
  bracket-prefixed non-JSON turn falls back to '' so the existing
  not.toBe('') assertion fails clearly instead of a generic parse throw.
2026-06-08 12:35:03 +08:00

116 lines
3.8 KiB
TypeScript

import { existsSync, readFileSync, writeFileSync } from "node:fs";
import { expect, test } from "@playwright/test";
/**
* RECORD driver (Plan A): drive the real frontend through the write/read-file
* scenario against the real-model gateway. The gateway captures every model
* call to DEERFLOW_RECORD_OUT; this just needs to drive the flow and wait until
* the captures stop arriving (main turns + in-graph title + follow-up
* suggestions all fired). It asserts nothing about content — it produces the
* fixture, it doesn't verify it.
*/
const APP = "http://localhost:3000";
const SCENARIO = "write_read_file";
const MODE = "ultra";
const PROMPT =
"Using your own file tools directly, create the file /mnt/user-data/outputs/note.txt " +
"with exactly this content: hi from replay. Then read that same file back and reply with its " +
"exact contents. Do NOT delegate to a subagent and do NOT use the task tool — do it yourself. " +
"Do not ask any clarifying questions.";
function countLines(path: string): number {
return existsSync(path)
? readFileSync(path, "utf-8")
.split("\n")
.filter((l) => l.trim()).length
: 0;
}
async function waitForCaptureStable(
path: string,
{ stableMs = 12_000, maxMs = 160_000 } = {},
): Promise<number> {
const start = Date.now();
let last = -1;
let lastChange = Date.now();
while (Date.now() - start < maxMs) {
const n = countLines(path);
if (n !== last) {
last = n;
lastChange = Date.now();
} else if (n > 0 && Date.now() - lastChange > stableMs) {
return n;
}
await new Promise((r) => setTimeout(r, 1000));
}
// Hard failure on timeout: returning the last count here would let a
// truncated/partial recording pass silently (captured > 0). A recording must
// stabilize, or it is not trustworthy.
throw new Error(
`[record] captures never stabilized within ${maxMs}ms (last count=${last}); ` +
`the recording may be truncated — raise maxMs or check the record gateway.`,
);
}
test.describe.configure({ timeout: 220_000 });
test("record write/read-file run through the real frontend", async ({
page,
context,
}) => {
const out = process.env.DEERFLOW_RECORD_OUT;
expect(out, "DEERFLOW_RECORD_OUT must be set").toBeTruthy();
// The context the frontend derives for ultra mode (core/threads/hooks.ts). The
// backend-direct golden test (Layer 1) POSTs this so its prompt — hence the
// recorded input hashes — matches the browser run. thinking/reasoning don't
// affect the prompt; is_plan_mode + subagent_enabled add the todo/task tools.
const CONTEXT = {
is_bootstrap: false,
mode: MODE,
thinking_enabled: true,
is_plan_mode: true,
subagent_enabled: true,
};
writeFileSync(
`${out}.meta.json`,
JSON.stringify({
scenario: SCENARIO,
mode: MODE,
prompt: PROMPT,
context: CONTEXT,
}),
"utf-8",
);
const reg = await context.request.post(`${APP}/api/v1/auth/register`, {
data: {
email: `rec-${Date.now()}@example.com`,
password: "very-strong-password-123",
},
});
expect(reg.status(), await reg.text()).toBe(201);
await page.addInitScript(() => {
window.localStorage.setItem(
"deerflow.local-settings",
JSON.stringify({ context: { mode: "ultra" } }),
);
});
await page.goto("/workspace/chats/new");
const textarea = page.getByPlaceholder(/how can i assist you/i);
await expect(textarea).toBeVisible({ timeout: 30_000 });
await textarea.fill(PROMPT);
await textarea.press("Enter");
const captured = await waitForCaptureStable(out!);
console.log(
`[record] captures stabilized at ${captured} model call(s) -> ${out}`,
);
expect(
captured,
"expected at least the agent turns to be captured",
).toBeGreaterThan(0);
});