惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

B
Blog
C
Check Point Blog
The GitHub Blog
The GitHub Blog
Y
Y Combinator Blog
SecWiki News
SecWiki News
有赞技术团队
有赞技术团队
Latest news
Latest news
D
DataBreaches.Net
Blog — PlanetScale
Blog — PlanetScale
Project Zero
Project Zero
H
Help Net Security
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
G
GRAHAM CLULEY
Engineering at Meta
Engineering at Meta
T
Threat Research - Cisco Blogs
腾讯CDC
P
Proofpoint News Feed
L
LINUX DO - 热门话题
C
Cisco Blogs
P
Palo Alto Networks Blog
Vercel News
Vercel News
P
Privacy International News Feed
爱范儿
爱范儿
Scott Helme
Scott Helme
L
Lohrmann on Cybersecurity
MyScale Blog
MyScale Blog
K
Kaspersky official blog
B
Blog RSS Feed
美团技术团队
Microsoft Security Blog
Microsoft Security Blog
O
OpenAI News
博客园 - 叶小钗
量子位
T
Tenable Blog
C
Cybersecurity and Infrastructure Security Agency CISA
J
Java Code Geeks
Application and Cybersecurity Blog
Application and Cybersecurity Blog
Hacker News: Ask HN
Hacker News: Ask HN
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
L
LINUX DO - 最新话题
F
Fortinet All Blogs
N
News | PayPal Newsroom
The Hacker News
The Hacker News
C
CXSECURITY Database RSS Feed - CXSecurity.com
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
博客园 - 【当耐特】
N
News and Events Feed by Topic
V
Visual Studio Blog
Google DeepMind News
Google DeepMind News
Last Week in AI
Last Week in AI

Recent Commits to openclaw:main

test: merge chat side-result checks · openclaw/openclaw@ddd2c2a test: merge cron history checks · openclaw/openclaw@f7eb746 test: merge responsive navigation shell checks · openclaw/openclaw@c2e4b47 docs(changelog): add codex oauth fixes · openclaw/openclaw@628e6cd test: merge navigation routing cases · openclaw/openclaw@5d8cecb Tests: mock channel registry bundled fallback · openclaw/openclaw@2b08233 Secrets: avoid broad web search discovery for single plugin config · openclaw/openclaw@a464f59 test: merge config view browser checks · openclaw/openclaw@20cf511 fix(status): align oauth health with runtime · openclaw/openclaw@eed7116 feat: add macOS screen snapshots for monitor preview (#67954) thanks … · openclaw/openclaw@f377db1 fix: report shared auth scopes in hello-ok (#67810) thanks @BunsDev · openclaw/openclaw@0b6c39b Auto-reply: avoid eager bundled route fallback · openclaw/openclaw@3ea1bf4 Tests: narrow session binding contract setup · openclaw/openclaw@54e4e16 fix(macOS): enable undo/redo in webchat composer text input (#34962) · openclaw/openclaw@00951dc Tests: speed up channel setup promotion · openclaw/openclaw@82b529a Docs: refresh agent instructions · openclaw/openclaw@5775fe2 fix(auth): serialize OAuth refresh across agents to fix #26322 (#67876) · openclaw/openclaw@8e79080 test: allow ollama public surface boundary test · openclaw/openclaw@7d4f1a6 Docs: add test performance guardrails · openclaw/openclaw@89706d3 Tests: restore context-engine usage proof · openclaw/openclaw@e4c4f95 Tests: slim context engine runtime coverage · openclaw/openclaw@74c198f ci: retry failed custom checkouts · openclaw/openclaw@0ee5baf test: trim duplicate provider auth onboarding cases · openclaw/openclaw@1ffc02e matrix: fix sessions_spawn --thread subagent session spawning (#67643) · openclaw/openclaw@1ce2596 test: reduce auth choice fixture churn · openclaw/openclaw@857b9cd test: mock health status config boundaries · openclaw/openclaw@9d5ab4a test: mock onboard config io boundary · openclaw/openclaw@299694d test: mock legacy state plugin boundaries · openclaw/openclaw@2713089 test: mock channel install boundaries · openclaw/openclaw@b945248 test: mock doctor preview channel boundaries · openclaw/openclaw@b1a3ad4 test: trim doctor command hotspots · openclaw/openclaw@c66f16a test: isolate agent auth and spawn hotspots · openclaw/openclaw@9285935 test: stabilize MCP startup disposal race · openclaw/openclaw@dd9d2eb test: merge browser contract server suites · openclaw/openclaw@5817a76 test: narrow ollama provider discovery setup · openclaw/openclaw@a0d9598 build: declare qa-lab aimock runtime dependency · openclaw/openclaw@24431e5 test: speed up safe-bins exec harness · openclaw/openclaw@ee856ab test: preserve tool helpers in embedded runner mocks · openclaw/openclaw@acd86a0 refactor: move memory embeddings into provider plugins · openclaw/openclaw@77e6e4c test: reuse system-run temp fixtures · openclaw/openclaw@7e9ff0f test: trim hotspot wait overhead · openclaw/openclaw@12a59b0 Check: avoid duplicate boundary prep · openclaw/openclaw@baf11b8 test: reduce hotspot fixture overhead · openclaw/openclaw@3a59edd feat(ui): overhaul settings and slash command UX (#67819) thanks @Bun… · openclaw/openclaw@2cfb660 QA Matrix: exit cleanly on failure · openclaw/openclaw@42805d2 QA Matrix: isolate scenario coverage · openclaw/openclaw@7e659e1 Matrix: refresh crypto bootstrap state · openclaw/openclaw@94081d8 QA Lab: add provider registry · openclaw/openclaw@bb7e982 Matrix: add plugin changelog · openclaw/openclaw@4acab55 test: trim more hotspot overhead · openclaw/openclaw@f485311 test: trim remaining hotspot tests · openclaw/openclaw@6ba8626 test: narrow hotspot mocks · openclaw/openclaw@dbc8179 test: isolate gemini embedding request helpers · openclaw/openclaw@cd330f5 test: trim memory and mcp hotspots · openclaw/openclaw@fd48dfa test: slim provider registry mocks · openclaw/openclaw@2e08c77 test: harden Parallels update smoke · openclaw/openclaw@1a98090 feat: default Anthropic to Opus 4.7 · openclaw/openclaw@628b454 fix: harden node-host shell payload mutability checks · openclaw/openclaw@75c551e fix: land node-host approval binding for native binaries (#66731) (th… · openclaw/openclaw@29919bb CI: add daily schedule to CodeQL workflow (#67645) · openclaw/openclaw@69d25f5 fix(gateway): capture config hash after plugin auto-enable to prevent… · openclaw/openclaw@8c11210 fix: repair sanitized replay tool results before send (#67620) (thank… · openclaw/openclaw@c3c7a99 fix: restrict HTML timeout short-circuit to transient statuses · openclaw/openclaw@de129a6 fix: keep TUI watchdog bound to active run (#67401) (thanks @xantorres) · openclaw/openclaw@3525273 Gateway/skills: dedupe skills prefix-match + drop dead fallback on log · openclaw/openclaw@d7f489f Extensions/lmstudio: back off inference preload after consecutive fai… · openclaw/openclaw@b555214 TUI/streaming: add watchdog that resets the activity indicator after … · openclaw/openclaw@f44ab20 Agents/tool-loop: enable unknown-tool stream guard by default · openclaw/openclaw@36ed367 Gateway/skills: invalidate session skills snapshot on config write · openclaw/openclaw@b23d59a fix: classify HTML provider error pages correctly (#67642) (thanks @s… · openclaw/openclaw@e588e90 fix(skills): remove unused model-usage import (#67641) · openclaw/openclaw@55f05df docs(changelog): credit codex fix superseded PRs · openclaw/openclaw@e485f24 fix(openai-codex): normalize stale transport metadata in resolution a… · openclaw/openclaw@90801ba CI: pin Docker-related GitHub Actions (#67632) · openclaw/openclaw@f697b01 Android: modernize WebView and discovery API usage (#67627) · openclaw/openclaw@44a6e50 fix(deps): bump hono to 4.12.14 and @hono/node-server to 1.19.14 (GHS… · openclaw/openclaw@fbccc18 fix(deps): bump dompurify to 3.4.0 (#67614) · openclaw/openclaw@2c2dc00 CI: add explicit permissions to all workflow jobs (fixes code-scannin… · openclaw/openclaw@01b7516 fix: register bundled TTS providers and route overrides correctly (#6… · openclaw/openclaw@6ea3cdd fix: align host tilde paths with OS home (#62804) (thanks @stainlu) · openclaw/openclaw@ecfaf64 fix: flush creds queue before reconnect socket open (#67464) (thanks … · openclaw/openclaw@405c63f fix: strip standalone <function> tool call tags from visible text (#6… · openclaw/openclaw@78df859 fix(agents): preserve cli session metadata before transcript persist … · openclaw/openclaw@898fd04 docs(changelog): move cli transcript entry · openclaw/openclaw@c1817c6 fix(agents): normalize cli transcript api field · openclaw/openclaw@3a3fae0 docs(changelog): note cli transcript persistence · openclaw/openclaw@6c343f1 fix(agents): persist cli transcript turns · openclaw/openclaw@b8ef507 fix(msteams): harden security-sensitive flows (#65841) · openclaw/openclaw@c56b56e [Dashboard] Fix exec approval modal overflow for long command content… · openclaw/openclaw@053c5b0 Docs: remove QA changelog entry · openclaw/openclaw@7fd5771 QA: fix private runtime source loading (#67428) · openclaw/openclaw@d5933af docs(gateway): correct protocol.md schema path, hello-ok example, aut… · openclaw/openclaw@489404d CI: pin Node 22 runners to 22.18.0 · openclaw/openclaw@4ffa621 models.authStatus: normalize provider ids + tighten env-backed escape… · openclaw/openclaw@f2fdb9d Update CHANGELOG.md · openclaw/openclaw@7694a92 test(parallels): clean up npm update guard jobs · openclaw/openclaw@045ea7b Plugins: prefer scanDir override paths · openclaw/openclaw@b2974da fix(dreaming): default storage.mode to "separate" so phase blocks sto… · openclaw/openclaw@8c392f0 fix(memory-core): skip dreaming transcript ingestion via session stor… · openclaw/openclaw@a1b01f0 fix: dedupe replayed exec.finished node events (#67281) · openclaw/openclaw@5dcf526
fix codex dynamic tool hooks (#70965) · openclaw/openclaw@81666e5
pashpashpash · 2026-04-24 · via Recent Commits to openclaw:main

@@ -1,6 +1,7 @@

11

import type { AgentToolResult } from "@mariozechner/pi-agent-core";

22

import type { AnyAgentTool } from "openclaw/plugin-sdk/agent-harness";

33

import { afterEach, describe, expect, it, vi } from "vitest";

4+

import { wrapToolWithBeforeToolCallHook } from "../../../../src/agents/pi-tools.before-tool-call.js";

45

import {

56

initializeGlobalHookRunner,

67

resetGlobalHookRunner,

@@ -33,6 +34,13 @@ function mediaResult(mediaUrl: string, audioAsVoice?: boolean): AgentToolResult<

3334

};

3435

}

353637+

function textToolResult(text: string, details: unknown = {}): AgentToolResult<unknown> {

38+

return {

39+

content: [{ type: "text", text }],

40+

details,

41+

};

42+

}

43+3644

function createBridgeWithToolResult(toolName: string, toolResult: AgentToolResult<unknown>) {

3745

return createCodexDynamicToolBridge({

3846

tools: [

@@ -281,4 +289,292 @@ describe("createCodexDynamicToolBridge", () => {

281289

);

282290

});

283291

});

292+293+

it("runs before_tool_call for unwrapped dynamic tools before execution", async () => {

294+

const beforeToolCall = vi.fn(async () => ({ params: { mode: "safe" } }));

295+

const afterToolCall = vi.fn();

296+

initializeGlobalHookRunner(

297+

createMockPluginRegistry([

298+

{ hookName: "before_tool_call", handler: beforeToolCall },

299+

{ hookName: "after_tool_call", handler: afterToolCall },

300+

]),

301+

);

302+303+

const execute = vi.fn(async () => textToolResult("done", { ok: true }));

304+

const bridge = createCodexDynamicToolBridge({

305+

tools: [createTool({ name: "exec", execute })],

306+

signal: new AbortController().signal,

307+

hookContext: {

308+

agentId: "agent-1",

309+

sessionId: "session-1",

310+

sessionKey: "agent:agent-1:session-1",

311+

runId: "run-1",

312+

},

313+

});

314+315+

const result = await bridge.handleToolCall({

316+

threadId: "thread-1",

317+

turnId: "turn-1",

318+

callId: "call-1",

319+

namespace: null,

320+

tool: "exec",

321+

arguments: { command: "pwd" },

322+

});

323+324+

expect(result).toEqual(expectInputText("done"));

325+

expect(beforeToolCall).toHaveBeenCalledWith(

326+

expect.objectContaining({

327+

toolName: "exec",

328+

toolCallId: "call-1",

329+

runId: "run-1",

330+

params: { command: "pwd" },

331+

}),

332+

expect.objectContaining({

333+

agentId: "agent-1",

334+

sessionId: "session-1",

335+

sessionKey: "agent:agent-1:session-1",

336+

runId: "run-1",

337+

toolCallId: "call-1",

338+

}),

339+

);

340+

expect(execute).toHaveBeenCalledWith(

341+

"call-1",

342+

{ command: "pwd", mode: "safe" },

343+

expect.any(AbortSignal),

344+

undefined,

345+

);

346+

await vi.waitFor(() => {

347+

expect(afterToolCall).toHaveBeenCalledWith(

348+

expect.objectContaining({

349+

toolName: "exec",

350+

toolCallId: "call-1",

351+

params: { command: "pwd", mode: "safe" },

352+

result: expect.objectContaining({

353+

content: [{ type: "text", text: "done" }],

354+

details: { ok: true },

355+

}),

356+

}),

357+

expect.objectContaining({

358+

agentId: "agent-1",

359+

sessionId: "session-1",

360+

sessionKey: "agent:agent-1:session-1",

361+

runId: "run-1",

362+

toolCallId: "call-1",

363+

}),

364+

);

365+

});

366+

});

367+368+

it("does not execute dynamic tools blocked by before_tool_call", async () => {

369+

const beforeToolCall = vi.fn(async () => ({

370+

block: true,

371+

blockReason: "blocked by policy",

372+

}));

373+

const afterToolCall = vi.fn();

374+

initializeGlobalHookRunner(

375+

createMockPluginRegistry([

376+

{ hookName: "before_tool_call", handler: beforeToolCall },

377+

{ hookName: "after_tool_call", handler: afterToolCall },

378+

]),

379+

);

380+

const execute = vi.fn(async () => textToolResult("should not run"));

381+

const bridge = createCodexDynamicToolBridge({

382+

tools: [createTool({ name: "message", execute })],

383+

signal: new AbortController().signal,

384+

hookContext: { runId: "run-blocked" },

385+

});

386+387+

const result = await handleMessageToolCall(bridge, {

388+

action: "send",

389+

text: "blocked",

390+

provider: "telegram",

391+

to: "chat-1",

392+

});

393+394+

expect(result).toEqual({

395+

success: false,

396+

contentItems: [{ type: "inputText", text: "blocked by policy" }],

397+

});

398+

expect(execute).not.toHaveBeenCalled();

399+

expect(bridge.telemetry.didSendViaMessagingTool).toBe(false);

400+

await vi.waitFor(() => {

401+

expect(afterToolCall).toHaveBeenCalledWith(

402+

expect.objectContaining({

403+

toolName: "message",

404+

toolCallId: "call-1",

405+

params: {

406+

action: "send",

407+

text: "blocked",

408+

provider: "telegram",

409+

to: "chat-1",

410+

},

411+

error: "blocked by policy",

412+

}),

413+

expect.objectContaining({

414+

runId: "run-blocked",

415+

toolCallId: "call-1",

416+

}),

417+

);

418+

});

419+

});

420+421+

it("applies dynamic tool result middleware before after_tool_call observes the result", async () => {

422+

const events: string[] = [];

423+

const beforeToolCall = vi.fn(async () => {

424+

events.push("before_tool_call");

425+

return { params: { mode: "safe" } };

426+

});

427+

const afterToolCall = vi.fn(async (event) => {

428+

events.push("after_tool_call");

429+

expect(event).toMatchObject({

430+

params: { command: "status", mode: "safe" },

431+

result: {

432+

content: [{ type: "text", text: "compacted output" }],

433+

details: { stage: "middleware" },

434+

},

435+

});

436+

});

437+

initializeGlobalHookRunner(

438+

createMockPluginRegistry([

439+

{ hookName: "before_tool_call", handler: beforeToolCall },

440+

{ hookName: "after_tool_call", handler: afterToolCall },

441+

]),

442+

);

443+

const registry = createEmptyPluginRegistry();

444+

const factory = async (codex: {

445+

on: (

446+

event: "tool_result",

447+

handler: (event: any) => Promise<{ result: AgentToolResult<unknown> }>,

448+

) => void;

449+

}) => {

450+

codex.on("tool_result", async (event) => {

451+

events.push("middleware");

452+

expect(event.args).toEqual({ command: "status" });

453+

return {

454+

result: {

455+

...event.result,

456+

content: [{ type: "text", text: "compacted output" }],

457+

details: { stage: "middleware" },

458+

},

459+

};

460+

});

461+

};

462+

registry.codexAppServerExtensionFactories.push({

463+

pluginId: "tokenjuice",

464+

pluginName: "Tokenjuice",

465+

rawFactory: factory,

466+

factory,

467+

source: "test",

468+

});

469+

setActivePluginRegistry(registry);

470+

const execute = vi.fn(async () => {

471+

events.push("execute");

472+

return textToolResult("raw output", { stage: "execute" });

473+

});

474+

const bridge = createCodexDynamicToolBridge({

475+

tools: [createTool({ name: "exec", execute })],

476+

signal: new AbortController().signal,

477+

hookContext: { runId: "run-middleware" },

478+

});

479+480+

const result = await bridge.handleToolCall({

481+

threadId: "thread-1",

482+

turnId: "turn-1",

483+

callId: "call-1",

484+

namespace: null,

485+

tool: "exec",

486+

arguments: { command: "status" },

487+

});

488+489+

expect(result).toEqual(expectInputText("compacted output"));

490+

await vi.waitFor(() => {

491+

expect(events).toEqual(["before_tool_call", "execute", "middleware", "after_tool_call"]);

492+

});

493+

});

494+495+

it("reports dynamic tool execution errors through after_tool_call without stranding the turn", async () => {

496+

const beforeToolCall = vi.fn(async () => ({ params: { timeoutSec: 1 } }));

497+

const afterToolCall = vi.fn();

498+

initializeGlobalHookRunner(

499+

createMockPluginRegistry([

500+

{ hookName: "before_tool_call", handler: beforeToolCall },

501+

{ hookName: "after_tool_call", handler: afterToolCall },

502+

]),

503+

);

504+

const execute = vi.fn(async () => {

505+

throw new Error("tool failed");

506+

});

507+

const bridge = createCodexDynamicToolBridge({

508+

tools: [createTool({ name: "exec", execute })],

509+

signal: new AbortController().signal,

510+

hookContext: { runId: "run-error" },

511+

});

512+513+

const result = await bridge.handleToolCall({

514+

threadId: "thread-1",

515+

turnId: "turn-1",

516+

callId: "call-err",

517+

namespace: null,

518+

tool: "exec",

519+

arguments: { command: "false" },

520+

});

521+522+

expect(result).toEqual({

523+

success: false,

524+

contentItems: [{ type: "inputText", text: "tool failed" }],

525+

});

526+

expect(execute).toHaveBeenCalledWith(

527+

"call-err",

528+

{ command: "false", timeoutSec: 1 },

529+

expect.any(AbortSignal),

530+

undefined,

531+

);

532+

await vi.waitFor(() => {

533+

expect(afterToolCall).toHaveBeenCalledWith(

534+

expect.objectContaining({

535+

toolName: "exec",

536+

toolCallId: "call-err",

537+

params: { command: "false", timeoutSec: 1 },

538+

error: "tool failed",

539+

}),

540+

expect.objectContaining({

541+

runId: "run-error",

542+

toolCallId: "call-err",

543+

}),

544+

);

545+

});

546+

});

547+548+

it("does not double-wrap dynamic tools that already have before_tool_call", async () => {

549+

const beforeToolCall = vi.fn(async () => ({ params: { mode: "safe" } }));

550+

initializeGlobalHookRunner(

551+

createMockPluginRegistry([{ hookName: "before_tool_call", handler: beforeToolCall }]),

552+

);

553+

const execute = vi.fn(async () => textToolResult("done"));

554+

const tool = wrapToolWithBeforeToolCallHook(createTool({ name: "exec", execute }), {

555+

runId: "run-wrapped",

556+

});

557+

const bridge = createCodexDynamicToolBridge({

558+

tools: [tool],

559+

signal: new AbortController().signal,

560+

hookContext: { runId: "run-wrapped" },

561+

});

562+563+

await bridge.handleToolCall({

564+

threadId: "thread-1",

565+

turnId: "turn-1",

566+

callId: "call-wrapped",

567+

namespace: null,

568+

tool: "exec",

569+

arguments: { command: "pwd" },

570+

});

571+572+

expect(beforeToolCall).toHaveBeenCalledTimes(1);

573+

expect(execute).toHaveBeenCalledWith(

574+

"call-wrapped",

575+

{ command: "pwd", mode: "safe" },

576+

expect.any(AbortSignal),

577+

undefined,

578+

);

579+

});

284580

});