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

A
About on SuperTechFans
C
Cybersecurity and Infrastructure Security Agency CISA
N
News and Events Feed by Topic
C
Cisco Blogs
Cisco Talos Blog
Cisco Talos Blog
A
Arctic Wolf
Scott Helme
Scott Helme
P
Palo Alto Networks Blog
S
Schneier on Security
D
Darknet – Hacking Tools, Hacker News & Cyber Security
T
Tor Project blog
量子位
G
Google Developers Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
B
Blog RSS Feed
NISL@THU
NISL@THU
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
AWS News Blog
AWS News Blog
爱范儿
爱范儿
Last Week in AI
Last Week in AI
Y
Y Combinator Blog
L
LINUX DO - 最新话题
Security Archives - TechRepublic
Security Archives - TechRepublic
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
S
Secure Thoughts
Cloudbric
Cloudbric
aimingoo的专栏
aimingoo的专栏
L
Lohrmann on Cybersecurity
TaoSecurity Blog
TaoSecurity Blog
Recent Commits to openclaw:main
Recent Commits to openclaw:main
Hacker News: Ask HN
Hacker News: Ask HN
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
The GitHub Blog
The GitHub Blog
有赞技术团队
有赞技术团队
S
Security @ Cisco Blogs
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
C
Cyber Attacks, Cyber Crime and Cyber Security
G
GRAHAM CLULEY
P
Proofpoint News Feed
V
V2EX
Martin Fowler
Martin Fowler
C
CERT Recently Published Vulnerability Notes
Attack and Defense Labs
Attack and Defense Labs
C
CXSECURITY Database RSS Feed - CXSecurity.com
The Cloudflare Blog
SecWiki News
SecWiki News
罗磊的独立博客
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
小众软件
小众软件
The Last Watchdog
The Last Watchdog

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: dedupe mirrored memory and deepseek tests · openclaw/openclaw@577438c
steipete · 2026-04-29 · via Recent Commits to openclaw:main

@@ -10,6 +10,48 @@ import { runSingleProviderCatalog } from "../test-support/provider-model-test-he

1010

import deepseekPlugin from "./index.js";

1111

import { createDeepSeekV4ThinkingWrapper } from "./stream.js";

121213+

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

14+15+

type PayloadCapture = {

16+

payload?: Record<string, unknown>;

17+

};

18+19+

function deepSeekV4Model(id: "deepseek-v4-flash" | "deepseek-v4-pro"): OpenAICompletionsModel {

20+

return {

21+

provider: "deepseek",

22+

id,

23+

name: id === "deepseek-v4-flash" ? "DeepSeek V4 Flash" : "DeepSeek V4 Pro",

24+

api: "openai-completions",

25+

baseUrl: "https://api.deepseek.com",

26+

reasoning: true,

27+

input: ["text"],

28+

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

29+

contextWindow: 1_000_000,

30+

maxTokens: 384_000,

31+

compat: {

32+

supportsUsageInStreaming: true,

33+

supportsReasoningEffort: true,

34+

maxTokensField: "max_tokens",

35+

},

36+

} as OpenAICompletionsModel;

37+

}

38+39+

function createPayloadCapturingStream(capture: PayloadCapture) {

40+

return (

41+

streamModel: OpenAICompletionsModel,

42+

streamContext: Context,

43+

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

44+

) => {

45+

capture.payload = buildOpenAICompletionsParams(streamModel, streamContext, {

46+

reasoning: "high",

47+

} as never);

48+

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

49+

const stream = createAssistantMessageEventStream();

50+

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

51+

return stream;

52+

};

53+

}

54+1355

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

1456

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

1557

const provider = await registerSingleProviderPlugin(deepseekPlugin);

@@ -119,24 +161,8 @@ describe("deepseek provider plugin", () => {

119161

});

120162121163

it("preserves replayed reasoning_content when DeepSeek V4 thinking is enabled", async () => {

122-

let capturedPayload: Record<string, unknown> | undefined;

123-

const model = {

124-

provider: "deepseek",

125-

id: "deepseek-v4-flash",

126-

name: "DeepSeek V4 Flash",

127-

api: "openai-completions",

128-

baseUrl: "https://api.deepseek.com",

129-

reasoning: true,

130-

input: ["text"],

131-

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

132-

contextWindow: 1_000_000,

133-

maxTokens: 384_000,

134-

compat: {

135-

supportsUsageInStreaming: true,

136-

supportsReasoningEffort: true,

137-

maxTokensField: "max_tokens",

138-

},

139-

} as Model<"openai-completions">;

164+

const capture: PayloadCapture = {};

165+

const model = deepSeekV4Model("deepseek-v4-flash");

140166

const context = {

141167

messages: [

142168

{ role: "user", content: "hi", timestamp: 1 },

@@ -181,29 +207,17 @@ describe("deepseek provider plugin", () => {

181207

},

182208

],

183209

} as Context;

184-

const baseStreamFn = (

185-

streamModel: Model<"openai-completions">,

186-

streamContext: Context,

187-

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

188-

) => {

189-

capturedPayload = buildOpenAICompletionsParams(streamModel, streamContext, {

190-

reasoning: "high",

191-

} as never);

192-

options?.onPayload?.(capturedPayload, streamModel);

193-

const stream = createAssistantMessageEventStream();

194-

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

195-

return stream;

196-

};

210+

const baseStreamFn = createPayloadCapturingStream(capture);

197211198212

const wrapThinkingHigh = createDeepSeekV4ThinkingWrapper(baseStreamFn as never, "high");

199213

expect(wrapThinkingHigh).toBeDefined();

200214

await wrapThinkingHigh?.(model, context, {});

201215202-

expect(capturedPayload).toMatchObject({

216+

expect(capture.payload).toMatchObject({

203217

thinking: { type: "enabled" },

204218

reasoning_effort: "high",

205219

});

206-

expect((capturedPayload?.messages as Array<Record<string, unknown>>)[1]).toMatchObject({

220+

expect((capture.payload?.messages as Array<Record<string, unknown>>)[1]).toMatchObject({

207221

role: "assistant",

208222

reasoning_content: "call reasoning",

209223

tool_calls: [

@@ -220,24 +234,8 @@ describe("deepseek provider plugin", () => {

220234

});

221235222236

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

223-

let capturedPayload: Record<string, unknown> | undefined;

224-

const model = {

225-

provider: "deepseek",

226-

id: "deepseek-v4-pro",

227-

name: "DeepSeek V4 Pro",

228-

api: "openai-completions",

229-

baseUrl: "https://api.deepseek.com",

230-

reasoning: true,

231-

input: ["text"],

232-

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

233-

contextWindow: 1_000_000,

234-

maxTokens: 384_000,

235-

compat: {

236-

supportsUsageInStreaming: true,

237-

supportsReasoningEffort: true,

238-

maxTokensField: "max_tokens",

239-

},

240-

} as Model<"openai-completions">;

237+

const capture: PayloadCapture = {};

238+

const model = deepSeekV4Model("deepseek-v4-pro");

241239

const context = {

242240

messages: [

243241

{ role: "user", content: "hi", timestamp: 1 },

@@ -275,25 +273,13 @@ describe("deepseek provider plugin", () => {

275273

},

276274

],

277275

} as Context;

278-

const baseStreamFn = (

279-

streamModel: Model<"openai-completions">,

280-

streamContext: Context,

281-

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

282-

) => {

283-

capturedPayload = buildOpenAICompletionsParams(streamModel, streamContext, {

284-

reasoning: "high",

285-

} as never);

286-

options?.onPayload?.(capturedPayload, streamModel);

287-

const stream = createAssistantMessageEventStream();

288-

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

289-

return stream;

290-

};

276+

const baseStreamFn = createPayloadCapturingStream(capture);

291277292278

const wrapThinkingHigh = createDeepSeekV4ThinkingWrapper(baseStreamFn as never, "high");

293279

expect(wrapThinkingHigh).toBeDefined();

294280

await wrapThinkingHigh?.(model, context, {});

295281296-

expect((capturedPayload?.messages as Array<Record<string, unknown>>)[1]).toMatchObject({

282+

expect((capture.payload?.messages as Array<Record<string, unknown>>)[1]).toMatchObject({

297283

role: "assistant",

298284

reasoning_content: "",

299285

tool_calls: [

@@ -310,24 +296,8 @@ describe("deepseek provider plugin", () => {

310296

});

311297312298

it("adds blank reasoning_content for replayed plain assistant messages", async () => {

313-

let capturedPayload: Record<string, unknown> | undefined;

314-

const model = {

315-

provider: "deepseek",

316-

id: "deepseek-v4-pro",

317-

name: "DeepSeek V4 Pro",

318-

api: "openai-completions",

319-

baseUrl: "https://api.deepseek.com",

320-

reasoning: true,

321-

input: ["text"],

322-

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

323-

contextWindow: 1_000_000,

324-

maxTokens: 384_000,

325-

compat: {

326-

supportsUsageInStreaming: true,

327-

supportsReasoningEffort: true,

328-

maxTokensField: "max_tokens",

329-

},

330-

} as Model<"openai-completions">;

299+

const capture: PayloadCapture = {};

300+

const model = deepSeekV4Model("deepseek-v4-pro");

331301

const context = {

332302

messages: [

333303

{ role: "user", content: "hi", timestamp: 1 },

@@ -351,50 +321,22 @@ describe("deepseek provider plugin", () => {

351321

{ role: "user", content: "next", timestamp: 3 },

352322

],

353323

} as Context;

354-

const baseStreamFn = (

355-

streamModel: Model<"openai-completions">,

356-

streamContext: Context,

357-

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

358-

) => {

359-

capturedPayload = buildOpenAICompletionsParams(streamModel, streamContext, {

360-

reasoning: "high",

361-

} as never);

362-

options?.onPayload?.(capturedPayload, streamModel);

363-

const stream = createAssistantMessageEventStream();

364-

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

365-

return stream;

366-

};

324+

const baseStreamFn = createPayloadCapturingStream(capture);

367325368326

const wrapThinkingHigh = createDeepSeekV4ThinkingWrapper(baseStreamFn as never, "high");

369327

expect(wrapThinkingHigh).toBeDefined();

370328

await wrapThinkingHigh?.(model, context, {});

371329372-

expect((capturedPayload?.messages as Array<Record<string, unknown>>)[1]).toMatchObject({

330+

expect((capture.payload?.messages as Array<Record<string, unknown>>)[1]).toMatchObject({

373331

role: "assistant",

374332

content: "Hello.",

375333

reasoning_content: "",

376334

});

377335

});

378336379337

it("strips replayed reasoning_content when DeepSeek V4 thinking is disabled", async () => {

380-

let capturedPayload: Record<string, unknown> | undefined;

381-

const model = {

382-

provider: "deepseek",

383-

id: "deepseek-v4-flash",

384-

name: "DeepSeek V4 Flash",

385-

api: "openai-completions",

386-

baseUrl: "https://api.deepseek.com",

387-

reasoning: true,

388-

input: ["text"],

389-

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

390-

contextWindow: 1_000_000,

391-

maxTokens: 384_000,

392-

compat: {

393-

supportsUsageInStreaming: true,

394-

supportsReasoningEffort: true,

395-

maxTokensField: "max_tokens",

396-

},

397-

} as Model<"openai-completions">;

338+

const capture: PayloadCapture = {};

339+

const model = deepSeekV4Model("deepseek-v4-flash");

398340

const context = {

399341

messages: [

400342

{ role: "user", content: "hi", timestamp: 1 },

@@ -439,19 +381,7 @@ describe("deepseek provider plugin", () => {

439381

},

440382

],

441383

} as Context;

442-

const baseStreamFn = (

443-

streamModel: Model<"openai-completions">,

444-

streamContext: Context,

445-

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

446-

) => {

447-

capturedPayload = buildOpenAICompletionsParams(streamModel, streamContext, {

448-

reasoning: "high",

449-

} as never);

450-

options?.onPayload?.(capturedPayload, streamModel);

451-

const stream = createAssistantMessageEventStream();

452-

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

453-

return stream;

454-

};

384+

const baseStreamFn = createPayloadCapturingStream(capture);

455385456386

const wrapThinkingNone = createDeepSeekV4ThinkingWrapper(

457387

baseStreamFn as never,

@@ -460,9 +390,9 @@ describe("deepseek provider plugin", () => {

460390

expect(wrapThinkingNone).toBeDefined();

461391

await wrapThinkingNone?.(model, context, {});

462392463-

expect(capturedPayload).toMatchObject({ thinking: { type: "disabled" } });

464-

expect(capturedPayload).not.toHaveProperty("reasoning_effort");

465-

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

393+

expect(capture.payload).toMatchObject({ thinking: { type: "disabled" } });

394+

expect(capture.payload).not.toHaveProperty("reasoning_effort");

395+

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

466396

"reasoning_content",

467397

);

468398

});