426e9eeabd
Voice Workbench / headless workbench (mocked backends) (push) Has been cancelled
Voice Workbench / real acoustic lane (nightly, provisioned only) (push) Has been cancelled
ci / test (push) Has been cancelled
ci / lint-and-format (push) Has been cancelled
ci / build (push) Has been cancelled
ci / dev-startup (push) Has been cancelled
gitleaks / gitleaks (push) Has been cancelled
Markdown Links / Relative Markdown Links (push) Has been cancelled
Quality (Extended) / Homepage Build (PR smoke) (push) Has been cancelled
Quality (Extended) / Comment-only diff guard (push) Has been cancelled
Quality (Extended) / Format + Type Safety Ratchet (push) Has been cancelled
Quality (Extended) / Develop Gate (secret scan + UI determinism) (push) Has been cancelled
Quality (Extended) / Develop Gate (lint) (push) Has been cancelled
Chat shell gestures / Chat shell gesture + parity e2e (push) Has been cancelled
Cloud Gateway Discord / Test (push) Has been cancelled
Benchmark Bridge Tests / benchmark (bunx @biomejs/biome check packages/lifeops-bench/src, benchmark-lint) (push) Has been cancelled
Benchmark Bridge Tests / benchmark (bunx vitest run --config packages/lifeops-bench/vitest.config.ts --root packages/lifeops-bench --passWithNoTests, benchmark-tests) (push) Has been cancelled
Build Agent Image / build-and-push (push) Has been cancelled
Dev Smoke / bun run dev onboarding chat (push) Has been cancelled
Dev Smoke / Vite HMR dependency-level smoke (push) Has been cancelled
Electrobun Submodule Guard / electrobun gitlink is fetchable (push) Has been cancelled
Publish @elizaos/example-code / check_npm (push) Has been cancelled
Publish @elizaos/example-code / publish_npm (push) Has been cancelled
Publish @elizaos/plugin-elizacloud / verify_version (push) Has been cancelled
Publish @elizaos/plugin-elizacloud / publish_npm (push) Has been cancelled
Sandbox Live Smoke / Sandbox live smoke (push) Has been cancelled
Snap Build & Test / Build Snap (amd64) (push) Has been cancelled
Snap Build & Test / Build Snap (arm64) (push) Has been cancelled
Test Packaging / elizaos CLI global-install smoke (node + bun) (push) Has been cancelled
Cloud Gateway Webhook / Test (push) Has been cancelled
Cloud Tests / lint-and-types (push) Has been cancelled
Cloud Tests / unit-tests (push) Has been cancelled
Cloud Tests / integration-tests (push) Has been cancelled
Cloud Tests / e2e-tests (push) Has been cancelled
CodeQL Advanced / Analyze (javascript-typescript) (push) Has been cancelled
Deploy Apps Worker (Product 2) / Determine environment (push) Has been cancelled
Deploy Apps Worker (Product 2) / Deploy apps worker to apps-control host (${{ needs.determine-env.outputs.environment }}) (push) Has been cancelled
Deploy Eliza Provisioning Worker / Determine environment (push) Has been cancelled
Deploy Eliza Provisioning Worker / Deploy worker to Hetzner host (${{ needs.determine-env.outputs.environment }} @ ${{ needs.determine-env.outputs.deployment_sha }}) (push) Has been cancelled
Dev Smoke / Classify changed paths (push) Has been cancelled
supply-chain / sbom (push) Has been cancelled
supply-chain / vulnerability-scan (push) Has been cancelled
Build, Push & Deploy to Phala Cloud / build-and-push (push) Has been cancelled
Test Packaging / Validate Packaging Configs (push) Has been cancelled
Test Packaging / Build & Test PyPI Package (push) Has been cancelled
Test Packaging / PyPI on Python ${{ matrix.python }} (push) Has been cancelled
Test Packaging / Pack & Test JS Tarballs (push) Has been cancelled
UI Fixture E2E / ui-fixture-e2e (push) Has been cancelled
UI Fixture E2E / fixture-e2e (push) Has been cancelled
UI Story Gate / story-gate (push) Has been cancelled
vault-ci / test (macos-latest) (push) Has been cancelled
vault-ci / test (ubuntu-latest) (push) Has been cancelled
vault-ci / test (windows-latest) (push) Has been cancelled
vault-ci / app-core wiring tests (push) Has been cancelled
verify-patches / verify patches/CHECKSUMS.sha256 (push) Has been cancelled
Voice Benchmark Smoke / voice-emotion fixture smoke (push) Has been cancelled
Voice Benchmark Smoke / voiceagentbench fixture smoke (push) Has been cancelled
Voice Benchmark Smoke / voicebench-quality unit smoke (push) Has been cancelled
Voice Benchmark Smoke / voicebench TypeScript unit (no audio) (push) Has been cancelled
Voice Benchmark Smoke / voice bench smoke summary (push) Has been cancelled
Windows CI / windows ([bun run --cwd packages/app-core test bun run --cwd packages/elizaos test bun run --cwd packages/cloud/shared test], app-and-cli) (push) Has been cancelled
Windows CI / windows ([bun run --cwd packages/scenario-runner test bun run --cwd packages/vault test bun run --cwd packages/security test bun run --cwd plugins/plugin-coding-tools test], framework-packages) (push) Has been cancelled
Windows CI / windows ([bun run --cwd plugins/plugin-elizacloud test bun run --cwd plugins/plugin-discord test bun run --cwd plugins/plugin-anthropic test bun run --cwd plugins/plugin-openai test bun run --cwd plugins/plugin-app-control test bun run --cwd plugins/pl… (push) Has been cancelled
Windows CI / windows ([node packages/scripts/run-turbo.mjs run build --filter=@elizaos/core --filter=@elizaos/shared --filter=@elizaos/agent --concurrency=4 node packages/scripts/run-bash-linux-only.mjs scripts/verify-riscv64-buildpaths.sh node packages/scripts/run… (push) Has been cancelled
Windows CI / windows ([node packages/scripts/run-turbo.mjs run typecheck --filter=@elizaos/core --filter=@elizaos/shared --filter=@elizaos/cloud-shared --concurrency=4 bun run --cwd packages/core test bun run --cwd packages/shared test], core-runtime, 75) (push) Has been cancelled
199 lines
5.8 KiB
TypeScript
199 lines
5.8 KiB
TypeScript
/**
|
|
* Integration test: simulates the realtime trajectory progression and asserts
|
|
* that `summarizePhases` produces the right phase status sequence as the
|
|
* runtime fires LLM calls / tool events one at a time.
|
|
*
|
|
* This is the static analogue of "open the app, talk to the agent, watch
|
|
* phases flip" — without needing a dev server. It feeds the classifier the
|
|
* same sequence of detail responses the polling hook would receive and
|
|
* checks each snapshot.
|
|
*/
|
|
|
|
import { describe, expect, it } from "vitest";
|
|
import type {
|
|
TrajectoryDetail,
|
|
TrajectoryListItem,
|
|
UIEvaluationEvent,
|
|
UILlmCall,
|
|
UIToolEvent,
|
|
} from "../src/api-client";
|
|
import { summarizePhases } from "../src/phases";
|
|
|
|
let counter = 0;
|
|
const nextId = (prefix: string) => `${prefix}-${++counter}`;
|
|
|
|
function emptyDetail(active = true): TrajectoryDetail {
|
|
const trajectory: TrajectoryListItem = {
|
|
id: "t-001",
|
|
status: active ? "active" : "completed",
|
|
llmCallCount: 0,
|
|
};
|
|
return {
|
|
trajectory,
|
|
llmCalls: [],
|
|
providerAccesses: [],
|
|
toolEvents: [],
|
|
evaluationEvents: [],
|
|
};
|
|
}
|
|
|
|
function call(overrides: Partial<UILlmCall>): UILlmCall {
|
|
return {
|
|
id: nextId("c"),
|
|
model: "test-model",
|
|
response: "",
|
|
purpose: "",
|
|
actionType: "",
|
|
stepType: "",
|
|
...overrides,
|
|
};
|
|
}
|
|
|
|
function tool(overrides: Partial<UIToolEvent>): UIToolEvent {
|
|
return { id: nextId("e"), type: "tool_call", ...overrides };
|
|
}
|
|
|
|
function evaluator(overrides: Partial<UIEvaluationEvent>): UIEvaluationEvent {
|
|
return { id: nextId("ev"), ...overrides };
|
|
}
|
|
|
|
function statusOf(
|
|
phases: ReturnType<typeof summarizePhases>,
|
|
name: string,
|
|
): string {
|
|
return phases.find((p) => p.phase === name)?.status ?? "missing";
|
|
}
|
|
|
|
describe("realtime trajectory progression", () => {
|
|
it("walks HANDLE → PLAN → ACTION → EVALUATE as the agent emits each step", () => {
|
|
// Snapshot 0: empty active trajectory. All idle.
|
|
const t0 = emptyDetail(true);
|
|
const p0 = summarizePhases(t0, { trajectoryActive: true });
|
|
expect(statusOf(p0, "HANDLE")).toBe("idle");
|
|
expect(statusOf(p0, "PLAN")).toBe("idle");
|
|
expect(statusOf(p0, "ACTION")).toBe("idle");
|
|
expect(statusOf(p0, "EVALUATE")).toBe("idle");
|
|
|
|
// Snapshot 1: should_respond fired with RESPOND. HANDLE flips to active
|
|
// (it's the most-recently-finished phase with no tail data yet).
|
|
const t1: TrajectoryDetail = {
|
|
...t0,
|
|
llmCalls: [
|
|
call({
|
|
id: "c-1",
|
|
stepType: "should_respond",
|
|
response: '{"action":"RESPOND"}',
|
|
}),
|
|
],
|
|
};
|
|
const p1 = summarizePhases(t1, { trajectoryActive: true });
|
|
expect(statusOf(p1, "HANDLE")).toBe("active");
|
|
expect(statusOf(p1, "PLAN")).toBe("idle");
|
|
|
|
// Snapshot 2: response (PLAN) fires with REPLY. HANDLE done, PLAN active.
|
|
const t2: TrajectoryDetail = {
|
|
...t1,
|
|
llmCalls: [
|
|
...t1.llmCalls,
|
|
call({
|
|
id: "c-2",
|
|
stepType: "response",
|
|
actionType: "REPLY",
|
|
response: "{}",
|
|
}),
|
|
],
|
|
};
|
|
const p2 = summarizePhases(t2, { trajectoryActive: true });
|
|
expect(statusOf(p2, "HANDLE")).toBe("done");
|
|
expect(statusOf(p2, "PLAN")).toBe("active");
|
|
expect(p2.find((p) => p.phase === "PLAN")?.summary).toBe("REPLY");
|
|
|
|
// Snapshot 3: action runs and returns success. PLAN done, ACTION active.
|
|
const t3: TrajectoryDetail = {
|
|
...t2,
|
|
toolEvents: [
|
|
tool({
|
|
id: "e-1",
|
|
actionName: "REPLY",
|
|
type: "tool_result",
|
|
success: true,
|
|
}),
|
|
],
|
|
};
|
|
const p3 = summarizePhases(t3, { trajectoryActive: true });
|
|
expect(statusOf(p3, "HANDLE")).toBe("done");
|
|
expect(statusOf(p3, "PLAN")).toBe("done");
|
|
expect(statusOf(p3, "ACTION")).toBe("active");
|
|
expect(p3.find((p) => p.phase === "ACTION")?.summary).toBe("REPLY");
|
|
|
|
// Snapshot 4: evaluator returns CONTINUE. EVALUATE flips to done.
|
|
const t4: TrajectoryDetail = {
|
|
...t3,
|
|
evaluationEvents: [
|
|
evaluator({
|
|
id: "ev-1",
|
|
evaluatorName: "REFLECTION",
|
|
decision: "continue",
|
|
success: true,
|
|
}),
|
|
],
|
|
};
|
|
const p4 = summarizePhases(t4, { trajectoryActive: true });
|
|
expect(statusOf(p4, "ACTION")).toBe("done");
|
|
expect(statusOf(p4, "EVALUATE")).toBe("done");
|
|
expect(p4.find((p) => p.phase === "EVALUATE")?.summary).toBe(
|
|
"REFLECTION: continue",
|
|
);
|
|
});
|
|
|
|
it("flips HANDLE to skipped on IGNORE, leaving the rest idle", () => {
|
|
const detail: TrajectoryDetail = {
|
|
...emptyDetail(false),
|
|
llmCalls: [
|
|
call({
|
|
id: "c-x",
|
|
stepType: "should_respond",
|
|
response: '{"action":"IGNORE","reasoning":"not relevant"}',
|
|
}),
|
|
],
|
|
};
|
|
const phases = summarizePhases(detail, { trajectoryActive: false });
|
|
expect(statusOf(phases, "HANDLE")).toBe("skipped");
|
|
expect(statusOf(phases, "PLAN")).toBe("idle");
|
|
expect(statusOf(phases, "ACTION")).toBe("idle");
|
|
expect(statusOf(phases, "EVALUATE")).toBe("idle");
|
|
});
|
|
|
|
it("surfaces an action error under ACTION", () => {
|
|
const detail: TrajectoryDetail = {
|
|
...emptyDetail(false),
|
|
llmCalls: [
|
|
call({
|
|
id: "c-1",
|
|
stepType: "should_respond",
|
|
response: '{"action":"RESPOND"}',
|
|
}),
|
|
call({
|
|
id: "c-2",
|
|
stepType: "response",
|
|
actionType: "POSTGRES_QUERY",
|
|
response: "{}",
|
|
}),
|
|
],
|
|
toolEvents: [
|
|
tool({
|
|
id: "e-1",
|
|
actionName: "POSTGRES_QUERY",
|
|
type: "tool_error",
|
|
error: "ECONNREFUSED",
|
|
}),
|
|
],
|
|
};
|
|
const phases = summarizePhases(detail, { trajectoryActive: false });
|
|
expect(statusOf(phases, "ACTION")).toBe("error");
|
|
expect(phases.find((p) => p.phase === "ACTION")?.summary).toBe(
|
|
"POSTGRES_QUERY",
|
|
);
|
|
});
|
|
});
|