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

www.infosecurity-magazine.com
www.infosecurity-magazine.com
D
DataBreaches.Net
T
Tailwind CSS Blog
M
MIT News - Artificial intelligence
Stack Overflow Blog
Stack Overflow Blog
F
Full Disclosure
V2EX - 技术
V2EX - 技术
N
News and Events Feed by Topic
Help Net Security
Help Net Security
L
LangChain Blog
Y
Y Combinator Blog
宝玉的分享
宝玉的分享
Google Online Security Blog
Google Online Security Blog
P
Proofpoint News Feed
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
T
The Blog of Author Tim Ferriss
Google DeepMind News
Google DeepMind News
The Register - Security
The Register - Security
B
Blog RSS Feed
N
Netflix TechBlog - Medium
N
News | PayPal Newsroom
TaoSecurity Blog
TaoSecurity Blog
酷 壳 – CoolShell
酷 壳 – CoolShell
V
Vulnerabilities – Threatpost
B
Blog
C
Cyber Attacks, Cyber Crime and Cyber Security
I
Intezer
H
Hackread – Cybersecurity News, Data Breaches, AI and More
博客园_首页
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
AI
AI
aimingoo的专栏
aimingoo的专栏
大猫的无限游戏
大猫的无限游戏
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
Cyberwarzone
Cyberwarzone
P
Proofpoint News Feed
Google DeepMind News
Google DeepMind News
G
GRAHAM CLULEY
Vercel News
Vercel News
罗磊的独立博客
MyScale Blog
MyScale Blog
Last Week in AI
Last Week in AI
博客园 - 司徒正美
C
CERT Recently Published Vulnerability Notes
GbyAI
GbyAI
Scott Helme
Scott Helme
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
T
Troy Hunt's Blog
A
About on SuperTechFans
P
Privacy International News Feed

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(agents): prefer real tool results over repair synthetics · openclaw/openclaw@5636252
Jerry-Xin · 2026-06-01 · via Recent Commits to openclaw:main
11

import type { AgentMessage } from "openclaw/plugin-sdk/agent-core";

22

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

33

import {

4+

DEFAULT_MISSING_TOOL_RESULT_TEXT,

45

sanitizeToolCallInputs,

56

sanitizeToolUseResultPairing,

67

repairToolUseResultPairing,

@@ -417,6 +418,251 @@ describe("sanitizeToolUseResultPairing", () => {

417418

});

418419

});

419420421+

describe("repairToolUseResultPairing prefers real result over synthetic error", () => {

422+

function makeSyntheticResult(toolCallId: string) {

423+

return {

424+

role: "toolResult" as const,

425+

toolCallId,

426+

toolName: "read",

427+

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

428+

isError: true,

429+

};

430+

}

431+432+

function makeCustomSyntheticResult(toolCallId: string, text: string) {

433+

return {

434+

role: "toolResult" as const,

435+

toolCallId,

436+

toolName: "read",

437+

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

438+

details: { openclawSyntheticMissingToolResult: true },

439+

isError: true,

440+

};

441+

}

442+443+

function makeRealResult(toolCallId: string, text = "real output") {

444+

return {

445+

role: "toolResult" as const,

446+

toolCallId,

447+

toolName: "read",

448+

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

449+

isError: false,

450+

};

451+

}

452+453+

function makeAssistant(toolCallId: string) {

454+

return {

455+

role: "assistant" as const,

456+

content: [{ type: "toolCall", id: toolCallId, name: "read", arguments: {} }],

457+

};

458+

}

459+460+

it("synthetic first, real second → keeps real", () => {

461+

const input = castAgentMessages([

462+

makeAssistant("call_1"),

463+

makeSyntheticResult("call_1"),

464+

makeRealResult("call_1"),

465+

]);

466+467+

const result = repairToolUseResultPairing(input);

468+469+

const toolResults = result.messages.filter((m) => m.role === "toolResult") as Array<{

470+

isError?: boolean;

471+

content?: Array<{ text?: string }>;

472+

}>;

473+

expect(toolResults).toHaveLength(1);

474+

expect(toolResults[0]?.isError).not.toBe(true);

475+

expect(toolResults[0]?.content?.[0]?.text).toBe("real output");

476+

});

477+478+

it("custom synthetic text first, real second → keeps real when configured", () => {

479+

const input = castAgentMessages([

480+

makeAssistant("call_1"),

481+

makeCustomSyntheticResult("call_1", "aborted"),

482+

makeRealResult("call_1"),

483+

]);

484+485+

const result = repairToolUseResultPairing(input, { missingToolResultText: "aborted" });

486+487+

const toolResults = result.messages.filter((m) => m.role === "toolResult") as Array<{

488+

isError?: boolean;

489+

content?: Array<{ text?: string }>;

490+

}>;

491+

expect(toolResults).toHaveLength(1);

492+

expect(toolResults[0]?.isError).not.toBe(true);

493+

expect(toolResults[0]?.content?.[0]?.text).toBe("real output");

494+

});

495+496+

it("real error matching custom synthetic text stays first without marker", () => {

497+

const input = castAgentMessages([

498+

makeAssistant("call_1"),

499+

{

500+

role: "toolResult" as const,

501+

toolCallId: "call_1",

502+

toolName: "read",

503+

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

504+

isError: true,

505+

},

506+

makeRealResult("call_1"),

507+

]);

508+509+

const result = repairToolUseResultPairing(input, { missingToolResultText: "aborted" });

510+511+

const toolResults = result.messages.filter((m) => m.role === "toolResult") as Array<{

512+

isError?: boolean;

513+

content?: Array<{ text?: string }>;

514+

}>;

515+

expect(toolResults).toHaveLength(1);

516+

expect(toolResults[0]?.isError).toBe(true);

517+

expect(toolResults[0]?.content?.[0]?.text).toBe("aborted");

518+

});

519+520+

it("real first, synthetic second → keeps real", () => {

521+

const input = castAgentMessages([

522+

makeAssistant("call_1"),

523+

makeRealResult("call_1"),

524+

makeSyntheticResult("call_1"),

525+

]);

526+527+

const result = repairToolUseResultPairing(input);

528+529+

const toolResults = result.messages.filter((m) => m.role === "toolResult") as Array<{

530+

isError?: boolean;

531+

content?: Array<{ text?: string }>;

532+

}>;

533+

expect(toolResults).toHaveLength(1);

534+

expect(toolResults[0]?.isError).not.toBe(true);

535+

expect(toolResults[0]?.content?.[0]?.text).toBe("real output");

536+

});

537+538+

it("late real result after another assistant turn replaces prior synthetic", () => {

539+

const input = castAgentMessages([

540+

makeAssistant("call_1"),

541+

makeSyntheticResult("call_1"),

542+

{

543+

role: "assistant" as const,

544+

content: [{ type: "toolCall", id: "call_2", name: "write", arguments: {} }],

545+

},

546+

makeRealResult("call_1"),

547+

{

548+

role: "toolResult" as const,

549+

toolCallId: "call_2",

550+

toolName: "write",

551+

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

552+

isError: false,

553+

},

554+

]);

555+556+

const result = repairToolUseResultPairing(input);

557+558+

const toolResults = result.messages.filter((m) => m.role === "toolResult") as Array<{

559+

toolCallId?: string;

560+

isError?: boolean;

561+

content?: Array<{ text?: string }>;

562+

}>;

563+

expect(toolResults).toHaveLength(2);

564+

expect(toolResults[0]?.toolCallId).toBe("call_1");

565+

expect(toolResults[0]?.isError).not.toBe(true);

566+

expect(toolResults[0]?.content?.[0]?.text).toBe("real output");

567+

expect(toolResults[1]?.toolCallId).toBe("call_2");

568+

expect(toolResults[1]?.content?.[0]?.text).toBe("second output");

569+

});

570+571+

it("two real results → keeps first (unchanged behavior)", () => {

572+

const input = castAgentMessages([

573+

makeAssistant("call_1"),

574+

makeRealResult("call_1", "first real"),

575+

makeRealResult("call_1", "second real"),

576+

]);

577+578+

const result = repairToolUseResultPairing(input);

579+580+

const toolResults = result.messages.filter((m) => m.role === "toolResult") as Array<{

581+

content?: Array<{ text?: string }>;

582+

}>;

583+

expect(toolResults).toHaveLength(1);

584+

expect(toolResults[0]?.content?.[0]?.text).toBe("first real");

585+

});

586+587+

it("two synthetic errors → keeps first (unchanged behavior)", () => {

588+

const input = castAgentMessages([

589+

makeAssistant("call_1"),

590+

makeSyntheticResult("call_1"),

591+

makeSyntheticResult("call_1"),

592+

]);

593+594+

const result = repairToolUseResultPairing(input);

595+596+

const toolResults = result.messages.filter((m) => m.role === "toolResult") as Array<{

597+

isError?: boolean;

598+

content?: Array<{ text?: string }>;

599+

}>;

600+

expect(toolResults).toHaveLength(1);

601+

expect(toolResults[0]?.isError).toBe(true);

602+

expect(toolResults[0]?.content?.[0]?.text).toBe(DEFAULT_MISSING_TOOL_RESULT_TEXT);

603+

});

604+605+

it("span-level: synthetic then real in span → picks real", () => {

606+

const input = castAgentMessages([

607+

makeAssistant("call_1"),

608+

makeSyntheticResult("call_1"),

609+

makeRealResult("call_1"),

610+

{ role: "user", content: "next" },

611+

]);

612+613+

const result = repairToolUseResultPairing(input);

614+615+

const toolResults = result.messages.filter((m) => m.role === "toolResult") as Array<{

616+

isError?: boolean;

617+

content?: Array<{ text?: string }>;

618+

}>;

619+

expect(toolResults).toHaveLength(1);

620+

expect(toolResults[0]?.isError).not.toBe(true);

621+

expect(toolResults[0]?.content?.[0]?.text).toBe("real output");

622+

});

623+624+

it("does not treat real error containing marker substring as synthetic", () => {

625+

const input = castAgentMessages([

626+

makeAssistant("call_1"),

627+

{

628+

role: "toolResult" as const,

629+

toolCallId: "call_1",

630+

toolName: "read",

631+

content: [

632+

{

633+

type: "text",

634+

text: DEFAULT_MISSING_TOOL_RESULT_TEXT + " (extra context from real error)",

635+

},

636+

],

637+

isError: true,

638+

},

639+

makeRealResult("call_1"),

640+

]);

641+642+

const result = repairToolUseResultPairing(input);

643+644+

const toolResults = result.messages.filter((m) => m.role === "toolResult") as Array<{

645+

isError?: boolean;

646+

content?: Array<{ text?: string }>;

647+

}>;

648+

expect(toolResults).toHaveLength(1);

649+

expect(toolResults[0]?.content?.[0]?.text).toContain("extra context from real error");

650+

});

651+652+

it("changed flag is true when duplicates are dropped", () => {

653+

const input = castAgentMessages([

654+

makeAssistant("call_1"),

655+

makeRealResult("call_1"),

656+

makeRealResult("call_1", "duplicate"),

657+

]);

658+659+

const result = repairToolUseResultPairing(input);

660+661+

expect(result.messages).not.toBe(input);

662+

expect(result.droppedDuplicateCount).toBeGreaterThan(0);

663+

});

664+

});

665+420666

describe("sanitizeToolCallInputs legacy block filtering", () => {

421667

it("drops malformed snake_case tool call blocks", () => {

422668

const input = castAgentMessages([