sorokin.oleg.edu/learnharness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity

Fix turn-usage keying: idempotent per request turn id, not messageId

Browse Source 
Live smoke exposed two bugs in the turn usage log:
- onFinish messages carry no ids (withMessageIds fills copies inside
  persistTurn), so fresh turns keyed messageId "" — provenance lost.
- The SDK coalesces continuation turns into ONE response message (a whole
  probe conversation lands in a single assistant message), so per-messageId
  idempotency swallowed every continuation turn's usage.

TurnUsage gains id: string (unique per request, the append idempotency
key); messageId stays as transcript provenance, taken from the id-filled
list. appendTurnUsage dedupes by id; continuation turns with the same
messageId each keep their usage.
This commit is contained in:
amosblomqvist
2026-09-11 04:16:05 +03:00
parent f4abad3f15
commit 741ff416d6
6 changed files with 38 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/render-stats-bar.test.tsx
+1
View File
@@ -15,6 +15,7 @@ function step(inputTokens: number, outputTokens: number, over: Record<string, nu
function turn(over: Partial<TurnUsage> = {}): TurnUsage {
return {
id: "t1",
messageId: "m1",
at: "2026-09-09T12:00:00Z",
model: "z-ai/glm-5.3-flash",
tests/usage.test.ts
+9 -5
View File
@@ -62,6 +62,7 @@ test("callCost: unknown model and absent fields are null, never zero", () => {
test("turnCost sums steps; sessionCost reports unpriced turns", () => {
const turn: TurnUsage = {
id: "t1",
messageId: "m1",
at: "2026-09-09T00:00:00Z",
model: "z-ai/glm-5.3-flash",
@@ -69,7 +70,7 @@ test("turnCost sums steps; sessionCost reports unpriced turns", () => {
};
assert.ok(turnCost(turn) !== null);
const totals = sessionCost({
turns: [turn, { messageId: "m2", at: "x", model: "not/a-model", steps: [call({ inputTokens: 1, outputTokens: 1 })] }],
turns: [turn, { id: "t2", messageId: "m2", at: "x", model: "not/a-model", steps: [call({ inputTokens: 1, outputTokens: 1 })] }],
});
assert.equal(totals.unpriced, 1);
assert.ok(totals.cost > 0);
@@ -78,8 +79,8 @@ test("turnCost sums steps; sessionCost reports unpriced turns", () => {
test("contextWindow: last call's footprint against the model's limit", () => {
const cw = contextWindow({
turns: [
{ messageId: "m1", at: "x", model: "z-ai/glm-5.3-flash", steps: [call({ inputTokens: 9_000, outputTokens: 1_000 })] },
{ messageId: "m2", at: "x", model: "z-ai/glm-5.3-flash", steps: [call({ inputTokens: 90_000, outputTokens: 10_000 })] },
{ id: "t1", messageId: "m1", at: "x", model: "z-ai/glm-5.3-flash", steps: [call({ inputTokens: 9_000, outputTokens: 1_000 })] },
{ id: "t2", messageId: "m2", at: "x", model: "z-ai/glm-5.3-flash", steps: [call({ inputTokens: 90_000, outputTokens: 10_000 })] },
],
});
assert.ok(cw);
@@ -108,9 +109,10 @@ test("jobCost: null without usage, computed with it", () => {
// ─── the store seam ──────────────────────────────────────────────────────────
test("appendTurnUsage: appends, is idempotent per messageId, survives saveMessages", () => {
test("appendTurnUsage: appends, idempotent per turn id, continuation turns (same message) all kept, survives saveMessages", () => {
const record = chatStore.createChat("usage test chat");
const entry: TurnUsage = {
id: "turn_1",
messageId: "msg_a",
at: "2026-09-09T00:00:00Z",
model: "z-ai/glm-5.3-flash",
@@ -118,7 +120,9 @@ test("appendTurnUsage: appends, is idempotent per messageId, survives saveMessag
};
chatStore.appendTurnUsage(record.id, entry);
chatStore.appendTurnUsage(record.id, entry); // replay (abort/retry) → no-op
chatStore.appendTurnUsage(record.id, { ...entry, messageId: "msg_b" });
// continuation turn: SAME response message (SDK coalesces), new turn id —
// usage must survive, not collapse into the first entry
chatStore.appendTurnUsage(record.id, { ...entry, id: "turn_2" });
let reread = chatStore.getChat(record.id);
assert.equal(reread?.turns?.length, 2);