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

D
Docker
爱范儿
爱范儿
人人都是产品经理
人人都是产品经理
博客园 - 司徒正美
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
量子位
罗磊的独立博客
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
小众软件
小众软件
C
Cybersecurity and Infrastructure Security Agency CISA
Cyberwarzone
Cyberwarzone
大猫的无限游戏
大猫的无限游戏
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
雷峰网
雷峰网
Simon Willison's Weblog
Simon Willison's Weblog
The Cloudflare Blog
博客园 - 三生石上(FineUI控件)
D
Darknet – Hacking Tools, Hacker News & Cyber Security
C
Cyber Attacks, Cyber Crime and Cyber Security
博客园_首页
博客园 - 叶小钗
V
Vulnerabilities – Threatpost
T
The Exploit Database - CXSecurity.com
T
Tailwind CSS Blog
IT之家
IT之家
博客园 - 聂微东
Spread Privacy
Spread Privacy
V2EX - 技术
V2EX - 技术
S
Security Affairs
宝玉的分享
宝玉的分享
V
V2EX
C
Cisco Blogs
博客园 - Franky
美团技术团队
酷 壳 – CoolShell
酷 壳 – CoolShell
月光博客
月光博客
S
Securelist
J
Java Code Geeks
Webroot Blog
Webroot Blog
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
P
Proofpoint News Feed
Last Week in AI
Last Week in AI
L
LINUX DO - 热门话题
NISL@THU
NISL@THU
WordPress大学
WordPress大学
W
WeLiveSecurity
T
Threatpost
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
腾讯CDC
阮一峰的网络日志
阮一峰的网络日志

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: preserve Gemini compat tool signatures · openclaw/openclaw@382c87c
steipete · 2026-04-24 · via Recent Commits to openclaw:main

@@ -1654,6 +1654,232 @@ describe("openai transport stream", () => {

16541654

expect(params.tools?.[0]?.function?.strict).toBe(false);

16551655

});

165616561657+

describe("Gemini thought_signature round-trip on OpenAI-compatible completions", () => {

1658+

const geminiModel = {

1659+

id: "gemini-3-flash-preview",

1660+

name: "Gemini 3 Flash Preview",

1661+

api: "openai-completions",

1662+

provider: "google",

1663+

baseUrl: "https://generativelanguage.googleapis.com/v1beta/openai",

1664+

reasoning: true,

1665+

input: ["text"],

1666+

cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },

1667+

contextWindow: 1_000_000,

1668+

maxTokens: 8192,

1669+

} satisfies Model<"openai-completions">;

1670+1671+

function makeAssistantOutput(model: Model<"openai-completions">) {

1672+

return {

1673+

role: "assistant" as const,

1674+

content: [] as Array<Record<string, unknown>>,

1675+

api: model.api,

1676+

provider: model.provider,

1677+

model: model.id,

1678+

usage: {

1679+

input: 0,

1680+

output: 0,

1681+

cacheRead: 0,

1682+

cacheWrite: 0,

1683+

totalTokens: 0,

1684+

cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },

1685+

},

1686+

stopReason: "stop",

1687+

timestamp: Date.now(),

1688+

};

1689+

}

1690+1691+

it("captures thought_signature from streamed Google tool_calls", async () => {

1692+

const output = makeAssistantOutput(geminiModel);

1693+

const chunks = [

1694+

{

1695+

id: "chatcmpl-gemini",

1696+

object: "chat.completion.chunk" as const,

1697+

created: 1,

1698+

model: geminiModel.id,

1699+

choices: [

1700+

{

1701+

index: 0,

1702+

delta: {

1703+

tool_calls: [

1704+

{

1705+

index: 0,

1706+

id: "call_abc",

1707+

type: "function",

1708+

function: { name: "echo_value", arguments: "" },

1709+

extra_content: { google: { thought_signature: "SIG-OPAQUE-ABC==" } },

1710+

},

1711+

],

1712+

},

1713+

logprobs: null,

1714+

finish_reason: null,

1715+

},

1716+

],

1717+

},

1718+

{

1719+

id: "chatcmpl-gemini",

1720+

object: "chat.completion.chunk" as const,

1721+

created: 1,

1722+

model: geminiModel.id,

1723+

choices: [

1724+

{

1725+

index: 0,

1726+

delta: {

1727+

tool_calls: [{ index: 0, function: { arguments: '{"value":"repro"}' } }],

1728+

},

1729+

logprobs: null,

1730+

finish_reason: "tool_calls" as const,

1731+

},

1732+

],

1733+

},

1734+

] as const;

1735+

async function* mockStream() {

1736+

for (const chunk of chunks) {

1737+

yield chunk as never;

1738+

}

1739+

}

1740+1741+

await __testing.processOpenAICompletionsStream(mockStream(), output, geminiModel, {

1742+

push() {},

1743+

});

1744+1745+

expect(output.content[0]).toMatchObject({

1746+

type: "toolCall",

1747+

id: "call_abc",

1748+

name: "echo_value",

1749+

arguments: { value: "repro" },

1750+

thoughtSignature: "SIG-OPAQUE-ABC==",

1751+

});

1752+

});

1753+1754+

it("re-emits captured thought_signature for same Google route tool-call replay", () => {

1755+

const params = buildOpenAICompletionsParams(

1756+

geminiModel,

1757+

{

1758+

messages: [

1759+

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

1760+

{

1761+

role: "assistant",

1762+

api: geminiModel.api,

1763+

provider: geminiModel.provider,

1764+

model: geminiModel.id,

1765+

usage: {

1766+

input: 0,

1767+

output: 0,

1768+

cacheRead: 0,

1769+

cacheWrite: 0,

1770+

totalTokens: 0,

1771+

cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },

1772+

},

1773+

stopReason: "toolUse",

1774+

timestamp: 1,

1775+

content: [

1776+

{

1777+

type: "toolCall",

1778+

id: "call_abc",

1779+

name: "echo_value",

1780+

arguments: { value: "repro" },

1781+

thoughtSignature: "SIG-OPAQUE-ABC==",

1782+

},

1783+

],

1784+

},

1785+

{

1786+

role: "toolResult",

1787+

toolCallId: "call_abc",

1788+

toolName: "echo_value",

1789+

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

1790+

isError: false,

1791+

},

1792+

],

1793+

tools: [],

1794+

} as never,

1795+

undefined,

1796+

) as { messages: Array<Record<string, unknown>> };

1797+1798+

const assistant = params.messages.find((message) => message.role === "assistant") as

1799+

| { tool_calls?: Array<{ extra_content?: { google?: { thought_signature?: string } } }> }

1800+

| undefined;

1801+

expect(assistant?.tool_calls?.[0]?.extra_content?.google?.thought_signature).toBe(

1802+

"SIG-OPAQUE-ABC==",

1803+

);

1804+

});

1805+1806+

it("does not replay thought_signature across a different API surface", () => {

1807+

const params = buildOpenAICompletionsParams(

1808+

geminiModel,

1809+

{

1810+

messages: [

1811+

{

1812+

role: "assistant",

1813+

api: "google-generative-ai",

1814+

provider: geminiModel.provider,

1815+

model: geminiModel.id,

1816+

usage: {

1817+

input: 0,

1818+

output: 0,

1819+

cacheRead: 0,

1820+

cacheWrite: 0,

1821+

totalTokens: 0,

1822+

cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },

1823+

},

1824+

stopReason: "toolUse",

1825+

timestamp: 1,

1826+

content: [

1827+

{

1828+

type: "toolCall",

1829+

id: "call_abc",

1830+

name: "echo_value",

1831+

arguments: { value: "repro" },

1832+

thoughtSignature: "SIG-OPAQUE-ABC==",

1833+

},

1834+

],

1835+

},

1836+

],

1837+

tools: [],

1838+

} as never,

1839+

undefined,

1840+

) as { messages: Array<Record<string, unknown>> };

1841+1842+

const assistant = params.messages.find((message) => message.role === "assistant") as

1843+

| { tool_calls?: Array<{ extra_content?: unknown }> }

1844+

| undefined;

1845+

expect(assistant?.tool_calls?.[0]?.extra_content).toBeUndefined();

1846+

});

1847+1848+

it("does not emit extra_content when no thought_signature was captured", () => {

1849+

const params = buildOpenAICompletionsParams(

1850+

geminiModel,

1851+

{

1852+

messages: [

1853+

{

1854+

role: "assistant",

1855+

api: geminiModel.api,

1856+

provider: geminiModel.provider,

1857+

model: geminiModel.id,

1858+

usage: {

1859+

input: 0,

1860+

output: 0,

1861+

cacheRead: 0,

1862+

cacheWrite: 0,

1863+

totalTokens: 0,

1864+

cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },

1865+

},

1866+

stopReason: "toolUse",

1867+

timestamp: 1,

1868+

content: [{ type: "toolCall", id: "call_abc", name: "echo_value", arguments: {} }],

1869+

},

1870+

],

1871+

tools: [],

1872+

} as never,

1873+

undefined,

1874+

) as { messages: Array<Record<string, unknown>> };

1875+1876+

const assistant = params.messages.find((message) => message.role === "assistant") as

1877+

| { tool_calls?: Array<{ extra_content?: unknown }> }

1878+

| undefined;

1879+

expect(assistant?.tool_calls?.[0]?.extra_content).toBeUndefined();

1880+

});

1881+

});

1882+16571883

it("uses Mistral compat defaults for direct Mistral completions providers", () => {

16581884

const params = buildOpenAICompletionsParams(

16591885

{