profit/lakehouse
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix: layer-2 Langfuse filter used meaningless ternary

Browse Source 
Caught by running a side-test through LLM Team's run_codereview
flow (gpt-oss:120b reviewer) against this fixture, 2026-04-22.

BEFORE:
  const ourStart = Date.parse(
    l1.evidence.match(/tokens=/) ? result.ran_at : result.ran_at
  );
  // Both branches return result.ran_at — the ternary is meaningless.
  // result.ran_at is the fixture start time, NOT the moment we fired
  // /v1/chat. Any trace created between fixture-start and chat-fetch
  // would false-negative.

AFTER:
  const chat_request_sent_ms = Date.now();  // captured before layer 1
  // ...
  const recent = items.filter(t =>
    Date.parse(t.timestamp) >= chat_request_sent_ms
  );

Re-ran the fixture against the live stack — layers 1,2,4 still pass
(no regression); layer 2 trace matched at age=2494ms which is within
the chat-to-trace propagation window. Layers 3,5 still fail for the
original unrelated reasons (UpsertOutcome serde panic + Phase 45
slice 3 endpoint not built).

First concrete act-on-finding from a code-checker run. The process
works.
This commit is contained in:
profit 2026-04-22 03:44:36 -05:00
parent 9c893fbb8c
commit 5bbcaf4c33
1 changed files with 15 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
auditor/fixtures/hybrid_38_40_45.ts
View File

@ -102,6 +102,15 @@ export async function runHybridFixture(): Promise<FixtureResult> {
// ========================================================================
// Layer 1 — Phase 38: POST /v1/chat returns valid OpenAI shape
// ========================================================================
// Captured HERE, immediately before the chat layer runs, so layer 2's
// Langfuse-trace filter uses the actual moment the chat call was
// attempted — not the fixture start time. Earlier draft had a
// meaningless ternary returning result.ran_at on both branches; the
// LLM-Team codereview (2026-04-22) caught this and flagged it as a
// false-negative window on traces created between fixture-start and
// chat-fetch.
const chat_request_sent_ms = Date.now();
const l1 = await measureLayer("phase38_chat", "38", async () => {
const r = await fetch(`${GATEWAY}/v1/chat`, {
method: "POST",
@ -150,11 +159,13 @@ export async function runHybridFixture(): Promise<FixtureResult> {
if (!r.ok) throw new Error(`langfuse ${r.status}: ${await r.text()}`);
const j: any = await r.json();
const items = Array.isArray(j.data) ? j.data : [];
// Find a trace newer than our l1 start timestamp.
const ourStart = Date.parse(l1.evidence.match(/tokens=/) ? result.ran_at : result.ran_at);
const recent = items.filter((t: any) => Date.parse(t.timestamp) >= ourStart);
// Filter on the chat-request timestamp captured above. A Langfuse
// trace must be newer than the moment we fired /v1/chat to plausibly
// belong to our request. Using fixture start time (result.ran_at)
// was wrong and could false-negative on slow fixtures.
const recent = items.filter((t: any) => Date.parse(t.timestamp) >= chat_request_sent_ms);
if (recent.length === 0) {
throw new Error(`no v1.chat:ollama trace since ${new Date(ourStart).toISOString()} (${items.length} older traces visible, Langfuse reachable — tracing is not firing)`);
throw new Error(`no v1.chat:ollama trace since ${new Date(chat_request_sent_ms).toISOString()} (${items.length} older traces visible, Langfuse reachable — tracing is not firing)`);
}
const trace = recent[0];
return {