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
feat(config): add reasoningDefault to agents.defaults · openclaw/openclaw@0c9f844
deepujain · 2026-04-29 · via Recent Commits to openclaw:main

@@ -34,6 +34,33 @@ function makeTypingController() {

34343535

function parseInlineDirectivesForTest(body: string) {

3636

const normalized = body.trim();

37+

if (normalized === "/reasoning stream") {

38+

return {

39+

cleaned: "",

40+

hasThinkDirective: false,

41+

hasVerboseDirective: false,

42+

hasTraceDirective: false,

43+

traceLevel: undefined,

44+

rawTraceLevel: undefined,

45+

hasFastDirective: false,

46+

hasReasoningDirective: true,

47+

reasoningLevel: "stream",

48+

rawReasoningLevel: "stream",

49+

hasElevatedDirective: false,

50+

hasExecDirective: false,

51+

hasModelDirective: false,

52+

hasQueueDirective: false,

53+

hasStatusDirective: false,

54+

queueReset: false,

55+

thinkLevel: undefined,

56+

verboseLevel: undefined,

57+

fastMode: undefined,

58+

elevatedLevel: undefined,

59+

rawElevatedLevel: undefined,

60+

rawModelDirective: undefined,

61+

execSecurity: undefined,

62+

};

63+

}

3764

if (normalized === "/trace on") {

3865

return {

3966

cleaned: "",

@@ -89,7 +116,11 @@ function parseInlineDirectivesForTest(body: string) {

89116

async function resolveHelloWithModelDefaults(params: {

90117

defaultThinking: "off" | "low";

91118

defaultReasoning: "on";

119+

body?: string;

92120

sessionEntry?: SessionEntry;

121+

agentCfg?: { reasoningDefault?: "off" | "on" | "stream" };

122+

commandAuthorized?: boolean;

123+

ctx?: Parameters<typeof buildTestCtx>[0];

93124

}) {

94125

const resolveDefaultThinkingLevel = vi.fn(async () => params.defaultThinking);

95126

const resolveDefaultReasoningLevel = vi.fn(async () => params.defaultReasoning);

@@ -105,19 +136,20 @@ async function resolveHelloWithModelDefaults(params: {

105136106137

const result = await resolveReplyDirectives({

107138

ctx: buildTestCtx({

108-

Body: "hello",

109-

CommandBody: "hello",

139+

Body: params.body ?? "hello",

140+

CommandBody: params.body ?? "hello",

141+

...params.ctx,

110142

}),

111143

cfg: {},

112144

agentId: "main",

113145

agentDir: "/tmp/main-agent",

114146

workspaceDir: "/tmp",

115-

agentCfg: {},

147+

agentCfg: params.agentCfg ?? {},

116148

sessionCtx: {

117-

Body: "hello",

118-

BodyStripped: "hello",

119-

BodyForAgent: "hello",

120-

CommandBody: "hello",

149+

Body: params.body ?? "hello",

150+

BodyStripped: params.body ?? "hello",

151+

BodyForAgent: params.body ?? "hello",

152+

CommandBody: params.body ?? "hello",

121153

Provider: "whatsapp",

122154

} as TemplateContext,

123155

sessionEntry: params.sessionEntry ?? makeSessionEntry(),

@@ -129,7 +161,7 @@ async function resolveHelloWithModelDefaults(params: {

129161

isGroup: false,

130162

triggerBodyNormalized: "hello",

131163

resetTriggered: false,

132-

commandAuthorized: false,

164+

commandAuthorized: params.commandAuthorized ?? false,

133165

defaultProvider: "openai",

134166

defaultModel: "gpt-4o-mini",

135167

aliasIndex: { byAlias: new Map(), byKey: new Map() },

@@ -169,13 +201,13 @@ vi.mock("../commands-text-routing.js", () => ({

169201

}));

170202171203

vi.mock("./commands-context.js", () => ({

172-

buildCommandContext: vi.fn(() => ({

204+

buildCommandContext: vi.fn((params: { commandAuthorized?: boolean }) => ({

173205

surface: "whatsapp",

174206

channel: "whatsapp",

175207

channelId: "whatsapp",

176208

ownerList: [],

177209

senderIsOwner: false,

178-

isAuthorizedSender: false,

210+

isAuthorizedSender: params.commandAuthorized === true,

179211

senderId: undefined,

180212

abortKey: "abort-key",

181213

rawBodyNormalized: "hello",

@@ -304,7 +336,7 @@ describe("resolveReplyDirectives", () => {

304336

isGroup: false,

305337

triggerBodyNormalized: "hello",

306338

resetTriggered: false,

307-

commandAuthorized: false,

339+

commandAuthorized: true,

308340

defaultProvider: "openai",

309341

defaultModel: "gpt-4o-mini",

310342

aliasIndex: { byAlias: new Map(), byKey: new Map() },

@@ -465,6 +497,122 @@ describe("resolveReplyDirectives", () => {

465497

expect(resolveDefaultReasoningLevel).not.toHaveBeenCalled();

466498

});

467499500+

it("does not re-enable model reasoning when agentCfg reasoningDefault is explicitly off", async () => {

501+

const { result, resolveDefaultReasoningLevel } = await resolveHelloWithModelDefaults({

502+

defaultThinking: "off",

503+

defaultReasoning: "on",

504+

agentCfg: { reasoningDefault: "off" },

505+

});

506+507+

expect(result).toEqual({

508+

kind: "continue",

509+

result: expect.objectContaining({

510+

resolvedThinkLevel: "off",

511+

resolvedReasoningLevel: "off",

512+

}),

513+

});

514+

expect(resolveDefaultReasoningLevel).not.toHaveBeenCalled();

515+

});

516+517+

it("does not expose configured reasoning defaults to untrusted senders", async () => {

518+

const { result, resolveDefaultReasoningLevel } = await resolveHelloWithModelDefaults({

519+

defaultThinking: "off",

520+

defaultReasoning: "on",

521+

agentCfg: { reasoningDefault: "stream" },

522+

});

523+524+

expect(result).toEqual({

525+

kind: "continue",

526+

result: expect.objectContaining({

527+

resolvedReasoningLevel: "off",

528+

}),

529+

});

530+

expect(resolveDefaultReasoningLevel).not.toHaveBeenCalled();

531+

});

532+533+

it("ignores inline reasoning directives from untrusted senders", async () => {

534+

const { result, resolveDefaultReasoningLevel } = await resolveHelloWithModelDefaults({

535+

body: "/reasoning stream",

536+

defaultThinking: "off",

537+

defaultReasoning: "on",

538+

});

539+540+

expect(result).toEqual({

541+

kind: "continue",

542+

result: expect.objectContaining({

543+

resolvedReasoningLevel: "off",

544+

}),

545+

});

546+

expect(resolveDefaultReasoningLevel).not.toHaveBeenCalled();

547+

});

548+549+

it("does not expose session reasoning state to untrusted senders", async () => {

550+

const { result, resolveDefaultReasoningLevel } = await resolveHelloWithModelDefaults({

551+

defaultThinking: "off",

552+

defaultReasoning: "on",

553+

sessionEntry: makeSessionEntry({ reasoningLevel: "stream" }),

554+

});

555+556+

expect(result).toEqual({

557+

kind: "continue",

558+

result: expect.objectContaining({

559+

resolvedReasoningLevel: "off",

560+

}),

561+

});

562+

expect(resolveDefaultReasoningLevel).not.toHaveBeenCalled();

563+

});

564+565+

it("allows session reasoning state for authorized senders", async () => {

566+

const { result, resolveDefaultReasoningLevel } = await resolveHelloWithModelDefaults({

567+

defaultThinking: "off",

568+

defaultReasoning: "on",

569+

sessionEntry: makeSessionEntry({ reasoningLevel: "stream" }),

570+

commandAuthorized: true,

571+

});

572+573+

expect(result).toEqual({

574+

kind: "continue",

575+

result: expect.objectContaining({

576+

resolvedReasoningLevel: "stream",

577+

}),

578+

});

579+

expect(resolveDefaultReasoningLevel).not.toHaveBeenCalled();

580+

});

581+582+

it("allows configured reasoning defaults for operator gateway clients", async () => {

583+

const { result, resolveDefaultReasoningLevel } = await resolveHelloWithModelDefaults({

584+

defaultThinking: "off",

585+

defaultReasoning: "on",

586+

agentCfg: { reasoningDefault: "stream" },

587+

ctx: { GatewayClientScopes: ["operator.admin"] },

588+

});

589+590+

expect(result).toEqual({

591+

kind: "continue",

592+

result: expect.objectContaining({

593+

resolvedReasoningLevel: "stream",

594+

}),

595+

});

596+

expect(resolveDefaultReasoningLevel).not.toHaveBeenCalled();

597+

});

598+599+

it("allows configured reasoning defaults for authorized senders", async () => {

600+

const { result, resolveDefaultReasoningLevel } = await resolveHelloWithModelDefaults({

601+

defaultThinking: "off",

602+

defaultReasoning: "on",

603+

agentCfg: { reasoningDefault: "stream" },

604+

commandAuthorized: true,

605+

});

606+607+

expect(result).toEqual({

608+

kind: "continue",

609+

result: expect.objectContaining({

610+

resolvedReasoningLevel: "stream",

611+

}),

612+

});

613+

expect(resolveDefaultReasoningLevel).not.toHaveBeenCalled();

614+

});

615+468616

it("keeps consumed text reset triggers empty after directive cleanup", async () => {

469617

const sessionCtx = {

470618

Body: "",