Files
openclaw/src/auto-reply/reply/session-hooks-context.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

358 lines
12 KiB
TypeScript

import fs from "node:fs/promises";
import os from "node:os";
import path from "node:path";
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
import type { OpenClawConfig } from "../../config/config.js";
import type { SessionEntry } from "../../config/sessions.js";
import type { HookRunner } from "../../plugins/hooks.js";
import { initSessionState } from "./session.js";
const hookRunnerMocks = vi.hoisted(() => ({
hasHooks: vi.fn<HookRunner["hasHooks"]>(),
runSessionStart: vi.fn<HookRunner["runSessionStart"]>(),
runSessionEnd: vi.fn<HookRunner["runSessionEnd"]>(),
}));
const sessionCleanupMocks = vi.hoisted(() => ({
closeTrackedBrowserTabsForSessions: vi.fn(async () => 0),
resetRegisteredAgentHarnessSessions: vi.fn(async () => undefined),
retireSessionMcpRuntime: vi.fn(async () => false),
}));
vi.mock("../../plugins/hook-runner-global.js", () => ({
getGlobalHookRunner: () =>
({
hasHooks: hookRunnerMocks.hasHooks,
runSessionStart: hookRunnerMocks.runSessionStart,
runSessionEnd: hookRunnerMocks.runSessionEnd,
}) as unknown as HookRunner,
}));
vi.mock("../../agents/harness/registry.js", () => ({
resetRegisteredAgentHarnessSessions: sessionCleanupMocks.resetRegisteredAgentHarnessSessions,
}));
vi.mock("../../agents/agent-bundle-mcp-tools.js", () => ({
retireSessionMcpRuntime: sessionCleanupMocks.retireSessionMcpRuntime,
}));
vi.mock("../../plugin-sdk/browser-maintenance.js", () => ({
closeTrackedBrowserTabsForSessions: sessionCleanupMocks.closeTrackedBrowserTabsForSessions,
}));
vi.mock("../../agents/session-write-lock.js", async () => {
const actual = await vi.importActual<typeof import("../../agents/session-write-lock.js")>(
"../../agents/session-write-lock.js",
);
return {
...actual,
acquireSessionWriteLock: vi.fn(async () => ({ release: async () => {} })),
resolveSessionLockMaxHoldFromTimeout: vi.fn(
({
timeoutMs,
graceMs = 2 * 60 * 1000,
minMs = 5 * 60 * 1000,
}: {
timeoutMs: number;
graceMs?: number;
minMs?: number;
}) => Math.max(minMs, timeoutMs + graceMs),
),
};
});
async function createStorePath(prefix: string): Promise<string> {
const root = await fs.mkdtemp(path.join(os.tmpdir(), `${prefix}-`));
return path.join(root, "sessions.json");
}
async function writeStore(
storePath: string,
store: Record<string, SessionEntry | Record<string, unknown>>,
): Promise<void> {
await fs.mkdir(path.dirname(storePath), { recursive: true });
await fs.writeFile(storePath, JSON.stringify(store), "utf-8");
}
async function writeTranscript(
storePath: string,
sessionId: string,
text = "hello",
): Promise<string> {
const transcriptPath = path.join(path.dirname(storePath), `${sessionId}.jsonl`);
await fs.writeFile(
transcriptPath,
`${JSON.stringify({
type: "message",
id: `${sessionId}-m1`,
message: { role: "user", content: text },
})}\n`,
"utf-8",
);
return transcriptPath;
}
async function createStoredSession(params: {
prefix: string;
sessionKey: string;
sessionId: string;
text?: string;
updatedAt?: number;
}): Promise<{ storePath: string; transcriptPath: string }> {
const storePath = await createStorePath(params.prefix);
const transcriptPath = await writeTranscript(storePath, params.sessionId, params.text);
await writeStore(storePath, {
[params.sessionKey]: {
sessionId: params.sessionId,
sessionFile: transcriptPath,
updatedAt: params.updatedAt ?? Date.now(),
},
});
return { storePath, transcriptPath };
}
type SessionResetConfig = NonNullable<NonNullable<OpenClawConfig["session"]>["reset"]>;
async function initStoredSessionState(params: {
prefix: string;
sessionKey: string;
sessionId: string;
text: string;
updatedAt: number;
reset?: SessionResetConfig;
}): Promise<void> {
const { storePath } = await createStoredSession(params);
const cfg = {
session: {
store: storePath,
...(params.reset ? { reset: params.reset } : {}),
},
} as OpenClawConfig;
await initSessionState({
ctx: { Body: "hello", SessionKey: params.sessionKey },
cfg,
commandAuthorized: true,
});
}
function expectFields(value: unknown, expected: Record<string, unknown>): void {
if (!value || typeof value !== "object") {
throw new Error("expected fields object");
}
const record = value as Record<string, unknown>;
for (const [key, expectedValue] of Object.entries(expected)) {
expect(record[key], key).toEqual(expectedValue);
}
}
function requireHookCall(
mock: ReturnType<typeof vi.fn>,
label: string,
): readonly [Record<string, unknown>, Record<string, unknown> | undefined] {
const call = mock.mock.calls[0];
if (!call) {
throw new Error(`expected ${label} hook call`);
}
const [event, context] = call;
if (!event || typeof event !== "object") {
throw new Error(`expected ${label} hook event`);
}
if (context !== undefined && (!context || typeof context !== "object")) {
throw new Error(`expected ${label} hook context`);
}
return [event as Record<string, unknown>, context as Record<string, unknown> | undefined];
}
describe("session hook context wiring", () => {
beforeEach(() => {
hookRunnerMocks.hasHooks.mockReset();
hookRunnerMocks.runSessionStart.mockReset();
hookRunnerMocks.runSessionEnd.mockReset();
sessionCleanupMocks.closeTrackedBrowserTabsForSessions.mockClear();
sessionCleanupMocks.resetRegisteredAgentHarnessSessions.mockClear();
sessionCleanupMocks.retireSessionMcpRuntime.mockClear();
hookRunnerMocks.runSessionStart.mockResolvedValue(undefined);
hookRunnerMocks.runSessionEnd.mockResolvedValue(undefined);
hookRunnerMocks.hasHooks.mockImplementation(
(hookName) => hookName === "session_start" || hookName === "session_end",
);
});
afterEach(() => {
vi.restoreAllMocks();
});
it("passes sessionKey to session_start hook context", async () => {
const sessionKey = "agent:main:telegram:direct:123";
const storePath = await createStorePath("openclaw-session-hook-start");
await writeStore(storePath, {});
const cfg = { session: { store: storePath } } as OpenClawConfig;
await initSessionState({
ctx: { Body: "hello", SessionKey: sessionKey },
cfg,
commandAuthorized: true,
});
expect(hookRunnerMocks.runSessionStart).toHaveBeenCalledTimes(1);
const [event, context] = requireHookCall(hookRunnerMocks.runSessionStart, "session_start");
expectFields(event, { sessionKey });
expectFields(context, { sessionKey, agentId: "main", sessionId: event?.sessionId });
});
it("passes sessionKey to session_end hook context on reset", async () => {
const sessionKey = "agent:main:telegram:direct:123";
const { storePath } = await createStoredSession({
prefix: "openclaw-session-hook-end",
sessionKey,
sessionId: "old-session",
});
const cfg = { session: { store: storePath } } as OpenClawConfig;
await initSessionState({
ctx: { Body: "/new", SessionKey: sessionKey },
cfg,
commandAuthorized: true,
});
expect(hookRunnerMocks.runSessionEnd).toHaveBeenCalledTimes(1);
expect(hookRunnerMocks.runSessionStart).toHaveBeenCalledTimes(1);
const [event, context] = requireHookCall(hookRunnerMocks.runSessionEnd, "session_end");
expectFields(event, {
sessionKey,
reason: "new",
transcriptArchived: true,
});
expectFields(context, { sessionKey, agentId: "main", sessionId: event?.sessionId });
expect(event?.sessionFile).toContain(".jsonl.reset.");
const [startEvent, startContext] = requireHookCall(
hookRunnerMocks.runSessionStart,
"session_start",
);
expectFields(startEvent, { resumedFrom: "old-session" });
expect(event?.nextSessionId).toBe(startEvent?.sessionId);
expectFields(startContext, { sessionId: startEvent?.sessionId });
});
it("marks explicit /reset rollovers with reason reset", async () => {
const sessionKey = "agent:main:telegram:direct:456";
const { storePath } = await createStoredSession({
prefix: "openclaw-session-hook-explicit-reset",
sessionKey,
sessionId: "reset-session",
text: "reset me",
});
const cfg = { session: { store: storePath } } as OpenClawConfig;
await initSessionState({
ctx: { Body: "/reset", SessionKey: sessionKey },
cfg,
commandAuthorized: true,
});
const [event] = requireHookCall(hookRunnerMocks.runSessionEnd, "session_end");
expectFields(event, { reason: "reset" });
});
it("maps custom reset trigger aliases to the new-session reason", async () => {
const sessionKey = "agent:main:telegram:direct:alias";
const { storePath } = await createStoredSession({
prefix: "openclaw-session-hook-reset-alias",
sessionKey,
sessionId: "alias-session",
text: "alias me",
});
const cfg = {
session: {
store: storePath,
resetTriggers: ["/fresh"],
},
} as OpenClawConfig;
await initSessionState({
ctx: { Body: "/fresh", SessionKey: sessionKey },
cfg,
commandAuthorized: true,
});
const [event] = requireHookCall(hookRunnerMocks.runSessionEnd, "session_end");
expectFields(event, { reason: "new" });
});
it("marks daily stale rollovers and exposes the archived transcript path", async () => {
vi.useFakeTimers();
try {
vi.setSystemTime(new Date(2026, 0, 18, 5, 0, 0));
const sessionKey = "agent:main:telegram:direct:daily";
await initStoredSessionState({
prefix: "openclaw-session-hook-daily",
sessionKey,
sessionId: "daily-session",
text: "daily",
updatedAt: new Date(2026, 0, 18, 3, 0, 0).getTime(),
});
const [event] = requireHookCall(hookRunnerMocks.runSessionEnd, "session_end");
const [startEvent] = requireHookCall(hookRunnerMocks.runSessionStart, "session_start");
expectFields(event, {
reason: "daily",
transcriptArchived: true,
});
expect(event?.sessionFile).toContain(".jsonl.reset.");
expect(event?.nextSessionId).toBe(startEvent?.sessionId);
} finally {
vi.useRealTimers();
}
});
it("marks idle stale rollovers with reason idle", async () => {
vi.useFakeTimers();
try {
vi.setSystemTime(new Date(2026, 0, 18, 5, 0, 0));
const sessionKey = "agent:main:telegram:direct:idle";
await initStoredSessionState({
prefix: "openclaw-session-hook-idle",
sessionKey,
sessionId: "idle-session",
text: "idle",
updatedAt: new Date(2026, 0, 18, 3, 0, 0).getTime(),
reset: {
mode: "idle",
idleMinutes: 30,
},
});
const [event] = requireHookCall(hookRunnerMocks.runSessionEnd, "session_end");
expectFields(event, { reason: "idle" });
} finally {
vi.useRealTimers();
}
});
it("prefers idle over daily when both rollover conditions are true", async () => {
vi.useFakeTimers();
try {
vi.setSystemTime(new Date(2026, 0, 18, 5, 30, 0));
const sessionKey = "agent:main:telegram:direct:overlap";
await initStoredSessionState({
prefix: "openclaw-session-hook-overlap",
sessionKey,
sessionId: "overlap-session",
text: "overlap",
updatedAt: new Date(2026, 0, 18, 4, 45, 0).getTime(),
reset: {
mode: "daily",
atHour: 4,
idleMinutes: 30,
},
});
const [event] = requireHookCall(hookRunnerMocks.runSessionEnd, "session_end");
expectFields(event, { reason: "idle" });
} finally {
vi.useRealTimers();
}
});
});