Files
openclaw/src/commitments/runtime.test.ts
Peter Steinberger bb46b79d3c refactor: internalize OpenClaw agent runtime (#85341)
* refactor: extract agent core package

Introduce packages/agent-core as the OpenClaw-owned home for reusable agent loop, harness, session, prompt, and runtime dependency contracts.

* refactor: extract shared llm runtime

Move provider model registries, stream wrappers, OAuth helpers, and LLM utilities into src/llm with plugin-sdk barrels instead of depending on the old embedded runtime layout.

* refactor: remove pi runtime internals

Rename remaining Pi-shaped agent surfaces to OpenClaw agent runtime names, delete obsolete Pi docs and package graph checks, and add the third-party notice for incorporated code.

* refactor: tighten agent session runtime

Make agent-core/runtime dependencies explicit, consolidate compaction and session transcript helpers, and move model/session helpers behind OpenClaw-owned contracts.

* refactor: remove static model and pi auth paths

Drop static model catalogs and Pi auth bridges, move model/provider facts to manifest-owned runtime contracts, and harden internal embedded-agent utilities.

* refactor: remove legacy provider compat paths

* docs: remove agent parity notes

* fix: skip provider wildcard metadata parsing

* refactor: share session extension sdk loading

* refactor: inline acpx proxy error formatter

* refactor: fold edit recovery into edit tool

* fix: accept extension batch separator

* test: align startup provider plugin expectations

* fix: restore provider-scoped release discovery

* test: align static asset packaging expectations

* fix: run static provider catalogs during scoped discovery

* fix: add provider entry catalogs for scoped live discovery

* fix: load lightweight provider catalog entries

* fix: refresh provider-scoped plugin metadata

* fix: keep provider catalog entries on release live path

* fix: keep static manifest models in release live checks

* fix: harden release model discovery

* fix: reduce OpenAI live cache probe reasoning

* fix: disable OpenAI cache probe reasoning

* ci: extend OpenAI gateway live timeout

* fix: extend live gateway model budget

* fix: stabilize release validation regressions

* fix: honor provider aliases in model rows

* fix: stabilize release validation lanes

* fix: stabilize release memory qa

* ci: stabilize release validation lanes

* ci: prefer ipv4 for live docker node calls

* fix: restore shared tool-call stream wrapper

* ci: remove legacy pi test shard alias

* fix: clean up embedded agent test drift

* fix: stabilize runtime alias status

* fix: clean up embedded agent ci drift

* fix: restore release ci invariants

* fix: clean up post-rebase runtime drift

* fix: restore release ci checks

* fix: restore release ci after rebase

* fix: remove stale pi runtime path

* test: align compaction runtime expectations

* test: update plugin prerelease expectations

* fix: handle claude live tool approvals

* fix: stabilize release validation gates

* fix: finish agent runtime import

* test: finish post-rebase agent runtime mocks

* fix: keep codex compaction native

* fix: stabilize codex app-server hook tests

* test: isolate codex diagnostic active run

* test: remove codex diagnostic completion race

# Conflicts:
#	extensions/codex/src/app-server/run-attempt.test.ts

* ci: fix full release manifest performance run id

* refactor: narrow llm plugin sdk boundary

* chore: drop generated google boundary stamps

* fix: repair rebase fallout

* fix: clean up rebased runtime references

* fix: decode codex jwt payloads as base64url

* fix: preserve shipped pi runtime alias

* fix: add scoped sdk virtual modules

* fix: decode llm codex oauth jwt as base64url

* fix: avoid stale vertex adc negative cache

* fix: harden tool arg decoding and codeql path

* fix: keep vertex adc negative checks live

* refactor: consolidate codex jwt and edit helpers

* fix: await codex oauth node runtime imports

* fix: preserve sdk tool and notice contracts

* fix: preserve shipped compat config boundaries

* fix: align codex oauth callback host

* fix: terminate agent-core loop streams on failure

* fix: keep codex oauth callback alive during fallback

* ci: include session tools in critical codeql scans

* fix: keep Cloudflare Anthropic provider auth header

* docs: redirect legacy pi runtime pages

* fix: honor bundled web provider compat discovery

* fix: protect session output spill files

* fix: keep legacy agent dir env blocked

* fix: contain auto-discovered skill symlinks

* fix: harden agent core sdk proxy surfaces

* fix: restore approval reaction sdk compat

* fix: keep live docker runs bounded

* fix: keep codex oauth redirect host aligned

* fix: resolve post-rebase agent runtime drift

* fix: redact anthropic oauth parse failures

* fix: preserve responses strict tool shaping

* fix: repair agent runtime rebase cleanup

* docs: redirect retired parity pages

* fix: bound auto-discovered resources to roots

* fix: repair post-rebase agent test drift

* fix: preserve bundled provider allowlist migration

* fix: preserve manifest-owned provider aliases

* fix: declare photon image dependency

* fix: keep provider headers out of proxy body

* fix: preserve shipped env aliases

* fix: refresh control ui i18n generated state

* fix: quote read fallback paths

* fix: preview edits through configured backend

* test: satisfy core test typecheck

* fix: preserve ZAI usage auth fallback

* test: repair codex diagnostic test

* fix: repair agent runtime rebase drift

* test: finish embedded runner import rename

* fix: repair agent runtime rebase integrations

* test: align compaction oauth fallback expectations

* fix: allow sdk-auth session models

* fix: update doctor tool schema import

* fix: preserve bedrock plugin region

* fix: stream harmony-like prose immediately

* ci: include session runtime in codeql shards

* fix: repair latest rebase integrations

* fix: honor explicit codex websocket transport

* fix: keep openai-compatible credentials provider-scoped

* fix: refresh sdk api baseline after rebase

* fix: route cli runtime aliases through openclaw harness

* test: rename stale harness mock expectation

* test: rename embedded agent overflow calls

* test: clean embedded auth test wording

* test: use openclaw stream types in deepinfra cache test

* fix: refresh sdk api baseline on latest main

* fix: honor bundled discovery compat allowlists

* fix: refresh sdk api baseline after latest rebase

* fix: remove stale rebase imports

* test: rename stale model catalog mock

* test: mock renamed doctor runtime modules

* fix: map canonical kimi env auth

* fix: use internal model registry in bench script

* fix: migrate deepinfra provider catalog entry

* fix: enforce builtin tool suppression

* fix: route compaction auth and proxy payloads safely

* refactor: prune unused llm registry leftovers

* test: update codex hooks session import

* test: fix model picker ci coverage

* test: align model picker auth mock types
2026-05-27 19:24:04 +01:00

352 lines
11 KiB
TypeScript

import fs from "node:fs/promises";
import os from "node:os";
import path from "node:path";
import { afterEach, describe, expect, it, vi } from "vitest";
import type { OpenClawConfig } from "../config/config.js";
import { DEFAULT_COMMITMENT_EXTRACTION_QUEUE_MAX_ITEMS } from "./config.js";
import {
configureCommitmentExtractionRuntime,
drainCommitmentExtractionQueue,
enqueueCommitmentExtraction,
resetCommitmentExtractionRuntimeForTests,
} from "./runtime.js";
import { loadCommitmentStore } from "./store.js";
import type { CommitmentExtractionBatchResult, CommitmentExtractionItem } from "./types.js";
const runEmbeddedAgentMock = vi.hoisted(() => vi.fn());
const resolveDefaultModelMock = vi.hoisted(() => vi.fn());
vi.mock("../agents/embedded-agent.js", () => ({
runEmbeddedAgent: runEmbeddedAgentMock,
}));
vi.mock("./model-selection.runtime.js", () => ({
resolveCommitmentDefaultModelRef: resolveDefaultModelMock,
}));
function requireFirstEmbeddedAgentRequest(): {
provider?: string;
model?: string;
disableTools?: boolean;
} {
const [call] = runEmbeddedAgentMock.mock.calls;
if (!call) {
throw new Error("expected embedded OpenClaw agent extraction request");
}
const [request] = call;
if (!request || typeof request !== "object" || Array.isArray(request)) {
throw new Error("expected embedded OpenClaw agent extraction request");
}
return request as { provider?: string; model?: string; disableTools?: boolean };
}
describe("commitment extraction runtime", () => {
const tmpDirs: string[] = [];
const nowMs = Date.parse("2026-04-29T16:00:00.000Z");
afterEach(async () => {
resetCommitmentExtractionRuntimeForTests();
runEmbeddedAgentMock.mockReset();
resolveDefaultModelMock.mockReset();
vi.useRealTimers();
vi.unstubAllEnvs();
await Promise.all(tmpDirs.map((dir) => fs.rm(dir, { recursive: true, force: true })));
tmpDirs.length = 0;
});
async function createConfig(): Promise<OpenClawConfig> {
const tmpDir = await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-commitment-runtime-"));
tmpDirs.push(tmpDir);
vi.stubEnv("OPENCLAW_STATE_DIR", tmpDir);
return {
commitments: {
enabled: true,
},
};
}
it("does not enqueue background extraction in test mode unless forced", async () => {
const cfg = await createConfig();
expect(
enqueueCommitmentExtraction({
cfg,
nowMs,
agentId: "main",
sessionKey: "agent:main:telegram:user-1",
channel: "telegram",
userText: "Interview tomorrow.",
assistantText: "Good luck.",
}),
).toBe(false);
});
it("keeps hidden extraction opt-in by default", () => {
const cfg: OpenClawConfig = {
commitments: {},
};
configureCommitmentExtractionRuntime({
forceInTests: true,
setTimer: () => ({ unref() {} }) as ReturnType<typeof setTimeout>,
clearTimer: () => undefined,
});
expect(
enqueueCommitmentExtraction({
cfg,
nowMs,
agentId: "main",
sessionKey: "agent:main:telegram:user-1",
channel: "telegram",
userText: "Interview tomorrow.",
assistantText: "Good luck.",
}),
).toBe(false);
});
it("micro-batches queued turns into one extractor call", async () => {
const cfg = await createConfig();
const extractBatch = vi.fn(async ({ items }: { items: CommitmentExtractionItem[] }) => ({
candidates: items.map((item, index) => ({
itemId: item.itemId,
kind: "event_check_in" as const,
sensitivity: "routine" as const,
source: "inferred_user_context" as const,
reason: `Follow up ${index + 1}`,
suggestedText: `How did item ${index + 1} go?`,
dedupeKey: `event:${index + 1}`,
confidence: 0.93,
dueWindow: {
earliest: "2026-04-30T17:00:00.000Z",
latest: "2026-04-30T23:00:00.000Z",
timezone: "America/Los_Angeles",
},
})),
}));
configureCommitmentExtractionRuntime({
forceInTests: true,
extractBatch,
setTimer: () => ({ unref() {} }) as ReturnType<typeof setTimeout>,
clearTimer: () => undefined,
});
expect(
enqueueCommitmentExtraction({
cfg,
nowMs,
agentId: "main",
sessionKey: "agent:main:telegram:user-1",
channel: "telegram",
to: "15551234567",
sourceMessageId: "m1",
userText: "I have an interview tomorrow.",
assistantText: "Good luck.",
}),
).toBe(true);
expect(
enqueueCommitmentExtraction({
cfg,
nowMs: nowMs + 1,
agentId: "main",
sessionKey: "agent:main:telegram:user-1",
channel: "telegram",
to: "15551234567",
sourceMessageId: "m2",
userText: "I have a dentist appointment tomorrow.",
assistantText: "Hope it goes smoothly.",
}),
).toBe(true);
await expect(drainCommitmentExtractionQueue()).resolves.toBe(2);
const store = await loadCommitmentStore();
expect(extractBatch).toHaveBeenCalledTimes(1);
const [extractCall] = extractBatch.mock.calls;
if (!extractCall) {
throw new Error("Expected commitment extraction batch call");
}
const batchItems = extractCall[0].items;
expect(batchItems).toHaveLength(2);
const [firstBatchItem] = batchItems;
if (!firstBatchItem) {
throw new Error("Expected first commitment extraction batch item");
}
expect(firstBatchItem.itemId).not.toContain("main");
expect(firstBatchItem.itemId).not.toContain("telegram");
expect(firstBatchItem.itemId).not.toContain("15551234567");
expect(firstBatchItem.itemId).not.toContain("m1");
expect(store.commitments.map((commitment) => commitment.dedupeKey)).toEqual([
"event:1",
"event:2",
]);
expect(store.commitments[0]).not.toHaveProperty("sourceUserText");
expect(store.commitments[0]).not.toHaveProperty("sourceAssistantText");
});
it("uses the configured agent model for the hidden extractor run", async () => {
const cfg = await createConfig();
cfg.agents = {
defaults: {
model: {
primary: "openai-codex/gpt-5.5",
},
},
};
runEmbeddedAgentMock.mockResolvedValue({
payloads: [{ text: '{"candidates":[]}' }],
});
resolveDefaultModelMock.mockReturnValue({
provider: "openai-codex",
model: "gpt-5.5",
});
configureCommitmentExtractionRuntime({
forceInTests: true,
setTimer: () => ({ unref() {} }) as ReturnType<typeof setTimeout>,
clearTimer: () => undefined,
});
expect(
enqueueCommitmentExtraction({
cfg,
nowMs,
agentId: "main",
sessionKey: "agent:main:discord:channel-1",
channel: "discord",
userText: "I have an interview tomorrow.",
assistantText: "Good luck.",
}),
).toBe(true);
await expect(drainCommitmentExtractionQueue()).resolves.toBe(1);
expect(resolveDefaultModelMock).toHaveBeenCalledWith({ cfg, agentId: "main" });
expect(runEmbeddedAgentMock).toHaveBeenCalledTimes(1);
const request = requireFirstEmbeddedAgentRequest();
expect(request.provider).toBe("openai-codex");
expect(request.model).toBe("gpt-5.5");
expect(request.disableTools).toBe(true);
});
it("backs off hidden extraction after terminal model or auth failures", async () => {
vi.useFakeTimers();
vi.setSystemTime(nowMs);
const cfg = await createConfig();
const extractBatch = vi.fn(async () => {
throw new Error(
'No API key found for provider "openai". You are authenticated with OpenAI Codex OAuth.',
);
});
configureCommitmentExtractionRuntime({
forceInTests: true,
extractBatch,
setTimer: () => ({ unref() {} }) as ReturnType<typeof setTimeout>,
clearTimer: () => undefined,
});
expect(
enqueueCommitmentExtraction({
cfg,
nowMs,
agentId: "main",
sessionKey: "agent:main:discord:channel-1",
channel: "discord",
userText: "I have an interview tomorrow.",
assistantText: "Good luck.",
}),
).toBe(true);
await expect(drainCommitmentExtractionQueue()).rejects.toThrow("No API key found");
expect(extractBatch).toHaveBeenCalledTimes(1);
expect(
enqueueCommitmentExtraction({
cfg,
nowMs: nowMs + 1,
agentId: "main",
sessionKey: "agent:main:discord:channel-1",
channel: "discord",
userText: "The interview is tomorrow.",
assistantText: "I hope it goes well.",
}),
).toBe(false);
expect(
enqueueCommitmentExtraction({
cfg,
nowMs: nowMs + 1,
agentId: "other",
sessionKey: "agent:other:discord:channel-2",
channel: "discord",
userText: "The demo is tomorrow.",
assistantText: "I hope it goes well.",
}),
).toBe(true);
vi.setSystemTime(nowMs + 16 * 60_000);
expect(
enqueueCommitmentExtraction({
cfg,
nowMs: nowMs + 16 * 60_000,
agentId: "main",
sessionKey: "agent:main:discord:channel-1",
channel: "discord",
userText: "The interview is tomorrow.",
assistantText: "I hope it goes well.",
}),
).toBe(true);
});
it("bounds hidden extraction queue growth before spending extractor tokens", async () => {
const cfg = await createConfig();
const extractBatch = vi.fn(
async (_params: {
items: CommitmentExtractionItem[];
}): Promise<CommitmentExtractionBatchResult> => ({
candidates: [],
}),
);
configureCommitmentExtractionRuntime({
forceInTests: true,
extractBatch,
setTimer: () => ({ unref() {} }) as ReturnType<typeof setTimeout>,
clearTimer: () => undefined,
});
for (let index = 0; index < DEFAULT_COMMITMENT_EXTRACTION_QUEUE_MAX_ITEMS; index += 1) {
expect(
enqueueCommitmentExtraction({
cfg,
nowMs: nowMs + index,
agentId: "main",
sessionKey: "agent:main:telegram:user-1",
channel: "telegram",
to: "15551234567",
sourceMessageId: `m${index}`,
userText: `Commitment candidate ${index}`,
assistantText: "I will follow up.",
}),
).toBe(true);
}
expect(
enqueueCommitmentExtraction({
cfg,
nowMs: nowMs + DEFAULT_COMMITMENT_EXTRACTION_QUEUE_MAX_ITEMS,
agentId: "main",
sessionKey: "agent:main:telegram:user-1",
channel: "telegram",
to: "15551234567",
sourceMessageId: "overflow",
userText: "Overflow candidate",
assistantText: "I will follow up.",
}),
).toBe(false);
await expect(drainCommitmentExtractionQueue()).resolves.toBe(
DEFAULT_COMMITMENT_EXTRACTION_QUEUE_MAX_ITEMS,
);
const processed = extractBatch.mock.calls.reduce(
(count, call) => count + (call[0]?.items.length ?? 0),
0,
);
expect(processed).toBe(DEFAULT_COMMITMENT_EXTRACTION_QUEUE_MAX_ITEMS);
});
});