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

cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
V
Visual Studio Blog
The GitHub Blog
The GitHub Blog
Apple Machine Learning Research
Apple Machine Learning Research
J
Java Code Geeks
T
Tailwind CSS Blog
大猫的无限游戏
大猫的无限游戏
Jina AI
Jina AI
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Hugging Face - Blog
Hugging Face - Blog
WordPress大学
WordPress大学
宝玉的分享
宝玉的分享
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
罗磊的独立博客
人人都是产品经理
人人都是产品经理
H
Heimdal Security Blog
Last Week in AI
Last Week in AI
博客园 - 【当耐特】
Cyberwarzone
Cyberwarzone
Google DeepMind News
Google DeepMind News
雷峰网
雷峰网
Hacker News: Ask HN
Hacker News: Ask HN
Webroot Blog
Webroot Blog
Microsoft Azure Blog
Microsoft Azure Blog
MyScale Blog
MyScale Blog
A
About on SuperTechFans
V2EX - 技术
V2EX - 技术
小众软件
小众软件
博客园 - Franky
博客园 - 司徒正美
P
Privacy International News Feed
爱范儿
爱范儿
U
Unit 42
博客园 - 叶小钗
The Hacker News
The Hacker News
C
Check Point Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Simon Willison's Weblog
Simon Willison's Weblog
N
News and Events Feed by Topic
D
Docker
T
Threatpost
MongoDB | Blog
MongoDB | 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
H
Help Net Security
L
LINUX DO - 最新话题
Security Latest
Security Latest
T
The Exploit Database - CXSecurity.com
S
SegmentFault 最新的问题
A
Arctic Wolf
Spread Privacy
Spread Privacy

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
test(xiaomi): add MiMo thinking profile, stream wrapper, and reasonin… · openclaw/openclaw@7958eb0
jimdawdy-hub · 2026-05-15 · via Recent Commits to openclaw:main

@@ -0,0 +1,317 @@

1+

import type { Context, Model } from "@earendil-works/pi-ai";

2+

import { createAssistantMessageEventStream } from "@earendil-works/pi-ai";

3+

import {

4+

registerSingleProviderPlugin,

5+

resolveProviderPluginChoice,

6+

} from "openclaw/plugin-sdk/plugin-test-runtime";

7+

import { buildOpenAICompletionsParams } from "openclaw/plugin-sdk/provider-transport-runtime";

8+

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

9+

import { runSingleProviderCatalog } from "../test-support/provider-model-test-helpers.js";

10+

import xiaomiPlugin from "./index.js";

11+

import { createMiMoThinkingWrapper } from "./stream.js";

12+13+

type OpenAICompletionsModel = Model<"openai-completions">;

14+15+

type PayloadCapture = {

16+

payload?: Record<string, unknown>;

17+

};

18+19+

type ThinkingPayload = {

20+

type?: unknown;

21+

};

22+23+

type ReplayToolCall = {

24+

id?: unknown;

25+

type?: unknown;

26+

function?: {

27+

name?: unknown;

28+

arguments?: unknown;

29+

};

30+

};

31+32+

type RegisteredProvider = Awaited<ReturnType<typeof registerSingleProviderPlugin>>;

33+34+

const emptyUsage = {

35+

input: 0,

36+

output: 0,

37+

cacheRead: 0,

38+

cacheWrite: 0,

39+

totalTokens: 0,

40+

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

41+

};

42+43+

function requireThinkingProfileResolver(

44+

provider: RegisteredProvider,

45+

): NonNullable<RegisteredProvider["resolveThinkingProfile"]> {

46+

if (!provider.resolveThinkingProfile) {

47+

throw new Error("Xiaomi provider did not register a thinking profile resolver");

48+

}

49+

return provider.resolveThinkingProfile;

50+

}

51+52+

const readToolCall = { type: "toolCall", id: "call_1", name: "read", arguments: {} };

53+

const readToolResult = {

54+

role: "toolResult",

55+

toolCallId: "call_1",

56+

toolName: "read",

57+

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

58+

isError: false,

59+

timestamp: 3,

60+

};

61+

const readTool = {

62+

name: "read",

63+

description: "Read data",

64+

parameters: { type: "object", properties: {}, required: [], additionalProperties: false },

65+

};

66+67+

function mimoReasoningModel(

68+

id: "mimo-v2-pro" | "mimo-v2-omni" | "mimo-v2.5" | "mimo-v2.5-pro",

69+

): OpenAICompletionsModel {

70+

return {

71+

provider: "xiaomi",

72+

id,

73+

name: id,

74+

api: "openai-completions",

75+

baseUrl: "https://api.xiaomimimo.com/v1",

76+

reasoning: true,

77+

input: ["text"],

78+

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

79+

contextWindow: 1_048_576,

80+

maxTokens: 32_000,

81+

compat: {},

82+

} as OpenAICompletionsModel;

83+

}

84+85+

function replayAssistantMessage(params: {

86+

provider: string;

87+

model: string;

88+

content: Array<Record<string, unknown>>;

89+

stopReason: "stop" | "toolUse";

90+

}) {

91+

return {

92+

role: "assistant",

93+

api: "openai-completions",

94+

provider: params.provider,

95+

model: params.model,

96+

content: params.content,

97+

usage: emptyUsage,

98+

stopReason: params.stopReason,

99+

timestamp: 2,

100+

};

101+

}

102+103+

function readToolReplayContext(assistantMessage: ReturnType<typeof replayAssistantMessage>) {

104+

return {

105+

messages: [{ role: "user", content: "hi", timestamp: 1 }, assistantMessage, readToolResult],

106+

tools: [readTool],

107+

} as Context;

108+

}

109+110+

function mimoReasoningToolReplayContext() {

111+

return readToolReplayContext(

112+

replayAssistantMessage({

113+

provider: "xiaomi",

114+

model: "mimo-v2.5-pro",

115+

content: [

116+

{

117+

type: "thinking",

118+

thinking: "call reasoning",

119+

thinkingSignature: "reasoning_content",

120+

},

121+

readToolCall,

122+

],

123+

stopReason: "toolUse",

124+

}),

125+

);

126+

}

127+128+

function createPayloadCapturingStream(capture: PayloadCapture, model: OpenAICompletionsModel) {

129+

return (

130+

_streamModel: OpenAICompletionsModel,

131+

streamContext: Context,

132+

options?: { onPayload?: (payload: unknown, m: unknown) => unknown },

133+

) => {

134+

capture.payload = buildOpenAICompletionsParams(model, streamContext, {

135+

reasoning: "high",

136+

} as never);

137+

options?.onPayload?.(capture.payload, model);

138+

const stream = createAssistantMessageEventStream();

139+

queueMicrotask(() => stream.end());

140+

return stream;

141+

};

142+

}

143+144+

function requireThinkingWrapper(

145+

wrapper: ReturnType<typeof createMiMoThinkingWrapper>,

146+

label: string,

147+

): NonNullable<ReturnType<typeof createMiMoThinkingWrapper>> {

148+

if (!wrapper) {

149+

throw new Error(`expected MiMo thinking wrapper for ${label}`);

150+

}

151+

return wrapper;

152+

}

153+154+

function readThinking(payload: Record<string, unknown> | undefined): ThinkingPayload | undefined {

155+

return payload?.thinking as ThinkingPayload | undefined;

156+

}

157+158+

function readPayloadMessage(

159+

capture: PayloadCapture,

160+

index: number,

161+

): Record<string, unknown> | undefined {

162+

return (capture.payload?.messages as Array<Record<string, unknown>> | undefined)?.[index];

163+

}

164+165+

function readFirstToolCall(

166+

message: Record<string, unknown> | undefined,

167+

): ReplayToolCall | undefined {

168+

return (message?.tool_calls as ReplayToolCall[] | undefined)?.[0];

169+

}

170+171+

describe("xiaomi provider plugin", () => {

172+

it("registers Xiaomi with api-key auth metadata", async () => {

173+

const provider = await registerSingleProviderPlugin(xiaomiPlugin);

174+

const resolved = resolveProviderPluginChoice({

175+

providers: [provider],

176+

choice: "xiaomi-api-key",

177+

});

178+179+

expect(provider.id).toBe("xiaomi");

180+

expect(provider.label).toBe("Xiaomi");

181+

expect(provider.envVars).toEqual(["XIAOMI_API_KEY"]);

182+

expect(provider.auth).toHaveLength(1);

183+

if (!resolved) {

184+

throw new Error("expected Xiaomi api-key auth choice");

185+

}

186+

expect(resolved.provider.id).toBe("xiaomi");

187+

expect(resolved.method.id).toBe("api-key");

188+

});

189+190+

it("builds the static Xiaomi model catalog with reasoning flags", async () => {

191+

const provider = await registerSingleProviderPlugin(xiaomiPlugin);

192+

const catalogProvider = await runSingleProviderCatalog(provider);

193+194+

expect(catalogProvider.api).toBe("openai-completions");

195+

expect(catalogProvider.baseUrl).toBe("https://api.xiaomimimo.com/v1");

196+197+

const modelIds = catalogProvider.models?.map((m) => m.id);

198+

expect(modelIds).toContain("mimo-v2-pro");

199+

expect(modelIds).toContain("mimo-v2-omni");

200+

expect(modelIds).toContain("mimo-v2.5");

201+

expect(modelIds).toContain("mimo-v2.5-pro");

202+

expect(modelIds).toContain("mimo-v2-flash");

203+204+

expect(catalogProvider.models?.find((m) => m.id === "mimo-v2-pro")?.reasoning).toBe(true);

205+

expect(catalogProvider.models?.find((m) => m.id === "mimo-v2.5-pro")?.reasoning).toBe(true);

206+

expect(catalogProvider.models?.find((m) => m.id === "mimo-v2-flash")?.reasoning).toBeFalsy();

207+

});

208+209+

it("owns OpenAI-compatible replay policy", async () => {

210+

const provider = await registerSingleProviderPlugin(xiaomiPlugin);

211+212+

const replayPolicy = provider.buildReplayPolicy?.({ modelApi: "openai-completions" } as never);

213+

expect(replayPolicy?.sanitizeToolCallIds).toBe(true);

214+

expect(replayPolicy?.toolCallIdMode).toBe("strict");

215+

expect(replayPolicy?.validateGeminiTurns).toBe(true);

216+

expect(replayPolicy?.validateAnthropicTurns).toBe(true);

217+

});

218+219+

it("advertises thinking profiles for MiMo reasoning models only", async () => {

220+

const provider = await registerSingleProviderPlugin(xiaomiPlugin);

221+

const resolveThinkingProfile = requireThinkingProfileResolver(provider);

222+

const expectedLevels = ["off", "minimal", "low", "medium", "high", "xhigh", "max"];

223+224+

for (const modelId of ["mimo-v2-pro", "mimo-v2-omni", "mimo-v2.5", "mimo-v2.5-pro"]) {

225+

const profile = resolveThinkingProfile({ provider: "xiaomi", modelId } as never);

226+

expect(profile?.levels.map((l) => l.id)).toEqual(expectedLevels);

227+

expect(profile?.defaultLevel).toBe("high");

228+

}

229+230+

expect(resolveThinkingProfile({ provider: "xiaomi", modelId: "mimo-v2-flash" } as never)).toBe(

231+

undefined,

232+

);

233+

});

234+235+

it("isModernModelRef returns true only for MiMo reasoning models", async () => {

236+

const provider = await registerSingleProviderPlugin(xiaomiPlugin);

237+238+

expect(

239+

provider.isModernModelRef?.({ provider: "xiaomi", modelId: "mimo-v2.5-pro" } as never),

240+

).toBe(true);

241+

expect(

242+

provider.isModernModelRef?.({ provider: "xiaomi", modelId: "mimo-v2-pro" } as never),

243+

).toBe(true);

244+

expect(

245+

provider.isModernModelRef?.({ provider: "xiaomi", modelId: "mimo-v2-flash" } as never),

246+

).toBe(false);

247+

});

248+249+

it("adds blank reasoning_content for replayed tool calls from non-xiaomi turns", async () => {

250+

const capture: PayloadCapture = {};

251+

const model = mimoReasoningModel("mimo-v2.5-pro");

252+

const context = readToolReplayContext(

253+

replayAssistantMessage({

254+

provider: "openai",

255+

model: "gpt-5.5",

256+

content: [readToolCall],

257+

stopReason: "toolUse",

258+

}),

259+

);

260+

const baseStreamFn = createPayloadCapturingStream(capture, model);

261+262+

const wrapThinkingHigh = requireThinkingWrapper(

263+

createMiMoThinkingWrapper(baseStreamFn as never, "high"),

264+

"high",

265+

);

266+

await wrapThinkingHigh(model, context, {});

267+268+

const assistantMessage = readPayloadMessage(capture, 1);

269+

expect(assistantMessage?.role).toBe("assistant");

270+

expect(assistantMessage?.reasoning_content).toBe("");

271+

const toolCall = readFirstToolCall(assistantMessage);

272+

expect(toolCall?.id).toBe("call_1");

273+

expect(toolCall?.type).toBe("function");

274+

expect(toolCall?.function?.name).toBe("read");

275+

expect(toolCall?.function?.arguments).toBe("{}");

276+

});

277+278+

it("preserves replayed reasoning_content when MiMo thinking is enabled", async () => {

279+

const capture: PayloadCapture = {};

280+

const model = mimoReasoningModel("mimo-v2.5-pro");

281+

const context = mimoReasoningToolReplayContext();

282+

const baseStreamFn = createPayloadCapturingStream(capture, model);

283+284+

const wrapThinkingHigh = requireThinkingWrapper(

285+

createMiMoThinkingWrapper(baseStreamFn as never, "high"),

286+

"high",

287+

);

288+

await wrapThinkingHigh(model, context, {});

289+290+

expect(readThinking(capture.payload)?.type).toBe("enabled");

291+

const assistantMessage = readPayloadMessage(capture, 1);

292+

expect(assistantMessage?.role).toBe("assistant");

293+

expect(assistantMessage?.reasoning_content).toBe("call reasoning");

294+

const toolCall = readFirstToolCall(assistantMessage);

295+

expect(toolCall?.id).toBe("call_1");

296+

expect(toolCall?.type).toBe("function");

297+

expect(toolCall?.function?.name).toBe("read");

298+

});

299+300+

it("strips reasoning_content when MiMo thinking is disabled", async () => {

301+

const capture: PayloadCapture = {};

302+

const model = mimoReasoningModel("mimo-v2-pro");

303+

const context = mimoReasoningToolReplayContext();

304+

const baseStreamFn = createPayloadCapturingStream(capture, model);

305+306+

const wrapThinkingNone = requireThinkingWrapper(

307+

createMiMoThinkingWrapper(baseStreamFn as never, "none" as never),

308+

"none",

309+

);

310+

await wrapThinkingNone(model, context, {});

311+312+

expect(readThinking(capture.payload)?.type).toBe("disabled");

313+

expect((capture.payload?.messages as Array<Record<string, unknown>>)[1]).not.toHaveProperty(

314+

"reasoning_content",

315+

);

316+

});

317+

});