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

Blog — PlanetScale
Blog — PlanetScale
Y
Y Combinator Blog
G
Google Developers Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
L
LangChain Blog
S
SegmentFault 最新的问题
J
Java Code Geeks
V
Visual Studio Blog
H
Help Net Security
Stack Overflow Blog
Stack Overflow Blog
aimingoo的专栏
aimingoo的专栏
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
T
Tailwind CSS Blog
Microsoft Azure Blog
Microsoft Azure Blog
博客园_首页
H
Hackread – Cybersecurity News, Data Breaches, AI and More
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
博客园 - Franky
B
Blog RSS Feed
The Cloudflare Blog
MyScale Blog
MyScale Blog
月光博客
月光博客
Microsoft Security Blog
Microsoft Security Blog
美团技术团队

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
fix: preserve Kimi tool call ids (#70693) (#70693) · open...
geri4 · 2026-04-24 · via Recent Commits to openclaw:main

@@ -3,6 +3,7 @@ import { describe, expect, it } from "vitest";

33

import { castAgentMessages } from "./test-helpers/agent-message-fixtures.js";

44

import {

55

isValidCloudCodeAssistToolId,

6+

sanitizeToolCallId,

67

sanitizeToolCallIdsForCloudCodeAssist,

78

} from "./tool-call-id.js";

89

@@ -448,6 +449,103 @@ describe("sanitizeToolCallIdsForCloudCodeAssist", () => {

448449

expect(aId).not.toMatch(/[_-]/);

449450

expect(bId).not.toMatch(/[_-]/);

450451

});

452+453+

it("preserves native Kimi function ids in direct strict sanitization", () => {

454+

expect(sanitizeToolCallId("functions.read:0", "strict")).toBe("functions.read:0");

455+

expect(sanitizeToolCallId("functions.bash_tool:12", "strict")).toBe("functions.bash_tool:12");

456+

expect(sanitizeToolCallId("functions.edit-file:3", "strict")).toBe("functions.edit-file:3");

457+

expect(isValidCloudCodeAssistToolId("functions.read:0", "strict")).toBe(true);

458+

expect(isValidCloudCodeAssistToolId("functions.read:0", "strict9")).toBe(false);

459+

});

460+461+

it("preserves native Kimi function ids across assistant/toolResult pairs", () => {

462+

const input = castAgentMessages([

463+

{

464+

role: "assistant",

465+

content: [{ type: "toolCall", id: "functions.read:0", name: "read", arguments: {} }],

466+

},

467+

{

468+

role: "toolResult",

469+

toolCallId: "functions.read:0",

470+

toolName: "read",

471+

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

472+

},

473+

]);

474+475+

const out = sanitizeToolCallIdsForCloudCodeAssist(input, "strict");

476+

expect(out).toBe(input);

477+

});

478+479+

it("preserves native Kimi ids while sanitizing non-Kimi siblings", () => {

480+

const input = castAgentMessages([

481+

{

482+

role: "assistant",

483+

content: [

484+

{ type: "toolCall", id: "functions.read:0", name: "read", arguments: {} },

485+

{ type: "toolCall", id: "call_a|b", name: "read", arguments: {} },

486+

],

487+

},

488+

buildToolResult({ toolCallId: "functions.read:0", text: "native" }),

489+

buildToolResult({ toolCallId: "call_a|b", text: "sanitized" }),

490+

]);

491+492+

const out = sanitizeToolCallIdsForCloudCodeAssist(input, "strict");

493+

expect(out).not.toBe(input);

494+

const assistant = out[0] as Extract<AgentMessage, { role: "assistant" }>;

495+

const native = assistant.content?.[0] as { id?: string };

496+

const sibling = assistant.content?.[1] as { id?: string };

497+

expect(native.id).toBe("functions.read:0");

498+

expect(sibling.id).toBe("callab");

499+

expect((out[1] as Extract<AgentMessage, { role: "toolResult" }>).toolCallId).toBe(

500+

"functions.read:0",

501+

);

502+

expect((out[2] as Extract<AgentMessage, { role: "toolResult" }>).toolCallId).toBe("callab");

503+

});

504+505+

it("disambiguates repeated native Kimi ids after preserving the first occurrence", () => {

506+

const input = castAgentMessages([

507+

{

508+

role: "assistant",

509+

content: [{ type: "toolCall", id: "functions.read:0", name: "read", arguments: {} }],

510+

},

511+

buildToolResult({ toolCallId: "functions.read:0", text: "one" }),

512+

{

513+

role: "assistant",

514+

content: [{ type: "toolCall", id: "functions.read:0", name: "read", arguments: {} }],

515+

},

516+

buildToolResult({ toolCallId: "functions.read:0", text: "two" }),

517+

]);

518+519+

const out = sanitizeToolCallIdsForCloudCodeAssist(input, "strict");

520+

expect(out).not.toBe(input);

521+

const first = (out[0] as Extract<AgentMessage, { role: "assistant" }>).content?.[0] as {

522+

id?: string;

523+

};

524+

const second = (out[2] as Extract<AgentMessage, { role: "assistant" }>).content?.[0] as {

525+

id?: string;

526+

};

527+

expect(first.id).toBe("functions.read:0");

528+

expect(second.id).not.toBe("functions.read:0");

529+

expect(isValidCloudCodeAssistToolId(second.id as string, "strict")).toBe(true);

530+

expect((out[1] as Extract<AgentMessage, { role: "toolResult" }>).toolCallId).toBe(

531+

"functions.read:0",

532+

);

533+

expect((out[3] as Extract<AgentMessage, { role: "toolResult" }>).toolCallId).toBe(second.id);

534+

});

535+536+

it("does not preserve malformed Kimi-like ids", () => {

537+

for (const bad of [

538+

"functions.read",

539+

"functions.:0",

540+

"functions.read:",

541+

"functions.read:x",

542+

"functions.read:0:extra",

543+

"xfunctions.read:0",

544+

]) {

545+

expect(sanitizeToolCallId(bad, "strict")).not.toBe(bad);

546+

expect(isValidCloudCodeAssistToolId(bad, "strict")).toBe(false);

547+

}

548+

});

451549

});

452550453551

describe("strict9 mode (Mistral tool call IDs)", () => {

@@ -510,5 +608,19 @@ describe("sanitizeToolCallIdsForCloudCodeAssist", () => {

510608

expect(out).not.toBe(input);

511609

expectStrict9IdLengths(expectToolUseIdsFollowDistinctToolCallIds(out, "strict9"));

512610

});

611+612+

it("rewrites native Kimi function ids in strict9 mode", () => {

613+

const input = castAgentMessages([

614+

{

615+

role: "assistant",

616+

content: [{ type: "toolCall", id: "functions.read:0", name: "read", arguments: {} }],

617+

},

618+

buildToolResult({ toolCallId: "functions.read:0", text: "ok" }),

619+

]);

620+621+

const out = sanitizeToolCallIdsForCloudCodeAssist(input, "strict9");

622+

expect(out).not.toBe(input);

623+

expectSingleToolCallRewrite(out, "functions", "strict9");

624+

});

513625

});

514626

});