summaryrefslogtreecommitdiffhomepage
path: root/src/core/metrics/format.test.ts
diff options
context:
space:
mode:
authorAdam Malczewski <[email protected]>2026-06-10 10:06:27 +0900
committerAdam Malczewski <[email protected]>2026-06-10 10:06:27 +0900
commitf8bf715abc8a89ec0c6370b40403c509b1ce2870 (patch)
tree915600a766e042a8491ac57423542cde1dda1eb6 /src/core/metrics/format.test.ts
parentccfd2f4157c1cbbb3d8aeceee94d9e963a82ab03 (diff)
downloaddispatch-web-f8bf715abc8a89ec0c6370b40403c509b1ce2870.tar.gz
dispatch-web-f8bf715abc8a89ec0c6370b40403c509b1ce2870.zip
feat(metrics): per-turn + per-step token/timing metrics bubbles
Consume [email protected] / [email protected] metrics: usage.stepId, step-complete (ttft/decode/genTotal), done.durationMs/usage, and the durable GET /conversations/:id/metrics endpoint. - core/metrics: pure live-fold + durable-merge reducer; decode-rate TPS; head-aligned, stable placement; progressive per-step rows (each shown as its step ends) with the turn-total row gated on the done event. - features/chat: store folds metric events + hydrates durable TurnMetrics; ChatView renders inline step bubbles + a turn-total bubble. - app: MetricsSync HTTP effect (tolerates 404) injected into chat stores. - scripts/live-probe: drives the metrics path; live-verified 17/17 vs bin/up. - docs: regenerate .dispatch wire/transport mirrors to 0.4.0; glossary terms (turn/step metrics, TTFT, decode time, TPS, metrics bubble); trim handoff.
Diffstat (limited to 'src/core/metrics/format.test.ts')
-rw-r--r--src/core/metrics/format.test.ts199
1 files changed, 199 insertions, 0 deletions
diff --git a/src/core/metrics/format.test.ts b/src/core/metrics/format.test.ts
new file mode 100644
index 0000000..9881e50
--- /dev/null
+++ b/src/core/metrics/format.test.ts
@@ -0,0 +1,199 @@
+import type { StepId, StepMetrics, TurnMetrics } from "@dispatch/wire";
+import { describe, expect, it } from "vitest";
+import { computeTps, viewStepMetrics, viewTurnMetrics } from "./format";
+
+describe("computeTps", () => {
+ it("null when elapsed missing", () => {
+ expect(computeTps(100, undefined)).toBeNull();
+ });
+
+ it("null when elapsed is zero", () => {
+ expect(computeTps(100, 0)).toBeNull();
+ });
+
+ it("null when elapsed is negative", () => {
+ expect(computeTps(100, -100)).toBeNull();
+ });
+
+ it("computes tokens per second", () => {
+ expect(computeTps(1000, 2000)).toBe(500);
+ });
+
+ it("computes fractional tps", () => {
+ expect(computeTps(100, 3000)).toBeCloseTo(33.33, 1);
+ });
+});
+
+describe("viewStepMetrics", () => {
+ it("formats tokens with thousands separator, tps, and durations", () => {
+ const step: StepMetrics = {
+ stepId: "s1" as StepId,
+ usage: { inputTokens: 1234, outputTokens: 567 },
+ ttftMs: 820,
+ decodeMs: 1200,
+ genTotalMs: 2020,
+ };
+ const view = viewStepMetrics(step, 0);
+ expect(view.label).toBe("step 1");
+ expect(view.tokensLabel).toBe("1,801 tok");
+ expect(view.tps).toBe("473 tok/s");
+ expect(view.ttft).toBe("820ms");
+ expect(view.decode).toBe("1.2s");
+ expect(view.genTotal).toBe("2.0s");
+ });
+
+ it("handles missing timing fields", () => {
+ const step: StepMetrics = {
+ stepId: "s1" as StepId,
+ usage: { inputTokens: 100, outputTokens: 50 },
+ };
+ const view = viewStepMetrics(step, 0);
+ expect(view.tps).toBeNull();
+ expect(view.ttft).toBeNull();
+ expect(view.decode).toBeNull();
+ expect(view.genTotal).toBeNull();
+ });
+
+ it("formats duration < 1s as ms", () => {
+ const step: StepMetrics = {
+ stepId: "s1" as StepId,
+ usage: { inputTokens: 10, outputTokens: 5 },
+ ttftMs: 42,
+ };
+ const view = viewStepMetrics(step, 0);
+ expect(view.ttft).toBe("42ms");
+ });
+
+ it("formats duration >= 1s as seconds", () => {
+ const step: StepMetrics = {
+ stepId: "s1" as StepId,
+ usage: { inputTokens: 10, outputTokens: 5 },
+ genTotalMs: 3200,
+ };
+ const view = viewStepMetrics(step, 0);
+ expect(view.genTotal).toBe("3.2s");
+ });
+
+ it("uses step index for label", () => {
+ const step: StepMetrics = {
+ stepId: "s1" as StepId,
+ usage: { inputTokens: 10, outputTokens: 5 },
+ };
+ expect(viewStepMetrics(step, 2).label).toBe("step 3");
+ });
+
+ it("tps uses decodeMs (not genTotalMs)", () => {
+ const step: StepMetrics = {
+ stepId: "s1" as StepId,
+ usage: { inputTokens: 100, outputTokens: 50 },
+ decodeMs: 500,
+ genTotalMs: 800,
+ };
+ const view = viewStepMetrics(step, 0);
+ // 50 / (500/1000) = 100 tok/s, NOT 50/(800/1000)=62.5
+ expect(view.tps).toBe("100 tok/s");
+ });
+
+ it("tps falls back to genTotalMs when decodeMs absent", () => {
+ const step: StepMetrics = {
+ stepId: "s1" as StepId,
+ usage: { inputTokens: 100, outputTokens: 50 },
+ genTotalMs: 800,
+ };
+ const view = viewStepMetrics(step, 0);
+ // 50 / (800/1000) = 62.5 → rounds to 63
+ expect(view.tps).toBe("63 tok/s");
+ });
+});
+
+describe("viewTurnMetrics", () => {
+ it("formats total tokens and breakdown", () => {
+ const turn: TurnMetrics = {
+ turnId: "t1",
+ usage: { inputTokens: 1000, outputTokens: 234 },
+ durationMs: 5000,
+ steps: [
+ {
+ stepId: "s1" as StepId,
+ usage: { inputTokens: 1000, outputTokens: 234 },
+ decodeMs: 3000,
+ genTotalMs: 4000,
+ },
+ ],
+ };
+ const view = viewTurnMetrics(turn);
+ expect(view.tokensLabel).toBe("1,234 tok");
+ expect(view.breakdown).toBe("1,000 in / 234 out");
+ expect(view.tps).toBe("78 tok/s");
+ expect(view.duration).toBe("5.0s");
+ });
+
+ it("breakdown includes cache only when present", () => {
+ const turn: TurnMetrics = {
+ turnId: "t1",
+ usage: { inputTokens: 1000, outputTokens: 234, cacheReadTokens: 500 },
+ steps: [],
+ };
+ const view = viewTurnMetrics(turn);
+ expect(view.breakdown).toBe("1,000 in / 234 out / 500 cache");
+ });
+
+ it("breakdown omits cache when not present", () => {
+ const turn: TurnMetrics = {
+ turnId: "t1",
+ usage: { inputTokens: 100, outputTokens: 50 },
+ steps: [],
+ };
+ const view = viewTurnMetrics(turn);
+ expect(view.breakdown).toBe("100 in / 50 out");
+ });
+
+ it("tps is null when no step has decodeMs or genTotalMs", () => {
+ const turn: TurnMetrics = {
+ turnId: "t1",
+ usage: { inputTokens: 100, outputTokens: 50 },
+ steps: [
+ {
+ stepId: "s1" as StepId,
+ usage: { inputTokens: 100, outputTokens: 50 },
+ },
+ ],
+ };
+ const view = viewTurnMetrics(turn);
+ expect(view.tps).toBeNull();
+ });
+
+ it("duration is null when durationMs absent", () => {
+ const turn: TurnMetrics = {
+ turnId: "t1",
+ usage: { inputTokens: 100, outputTokens: 50 },
+ steps: [],
+ };
+ const view = viewTurnMetrics(turn);
+ expect(view.duration).toBeNull();
+ });
+
+ it("sums decodeMs across steps (fallback genTotalMs per step) for tps", () => {
+ const turn: TurnMetrics = {
+ turnId: "t1",
+ usage: { inputTokens: 300, outputTokens: 150 },
+ steps: [
+ {
+ stepId: "s1" as StepId,
+ usage: { inputTokens: 100, outputTokens: 50 },
+ decodeMs: 800,
+ genTotalMs: 1000,
+ },
+ {
+ stepId: "s2" as StepId,
+ usage: { inputTokens: 200, outputTokens: 100 },
+ genTotalMs: 2000,
+ },
+ ],
+ };
+ const view = viewTurnMetrics(turn);
+ // step1 uses decodeMs=800, step2 falls back to genTotalMs=2000 → total=2800ms
+ // 150 / (2800/1000) = 53.57 → rounds to 54
+ expect(view.tps).toBe("54 tok/s");
+ });
+});