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

AI
AI
O
OpenAI News
Engineering at Meta
Engineering at Meta
F
Fortinet All Blogs
Jina AI
Jina AI
D
Docker
N
News and Events Feed by Topic
TaoSecurity Blog
TaoSecurity Blog
雷峰网
雷峰网
V
V2EX
小众软件
小众软件
N
News | PayPal Newsroom
GbyAI
GbyAI
Recorded Future
Recorded Future
SecWiki News
SecWiki News
WordPress大学
WordPress大学
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
酷 壳 – CoolShell
酷 壳 – CoolShell
Security Latest
Security Latest
Google DeepMind News
Google DeepMind News
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
Hacker News: Ask HN
Hacker News: Ask HN
Project Zero
Project Zero
Cyberwarzone
Cyberwarzone
MyScale Blog
MyScale Blog
T
The Blog of Author Tim Ferriss
U
Unit 42
The Last Watchdog
The Last Watchdog
V
Visual Studio Blog
C
Cisco Blogs
T
Tor Project blog
Google Online Security Blog
Google Online Security Blog
I
InfoQ
Attack and Defense Labs
Attack and Defense Labs
Y
Y Combinator Blog
博客园 - 聂微东
L
LangChain Blog
Blog — PlanetScale
Blog — PlanetScale
Apple Machine Learning Research
Apple Machine Learning Research
S
Schneier on Security
S
Securelist
博客园_首页
W
WeLiveSecurity
P
Privacy International News Feed
S
SegmentFault 最新的问题
博客园 - 【当耐特】
L
LINUX DO - 热门话题
Latest news
Latest news
大猫的无限游戏
大猫的无限游戏
M
MIT News - Artificial intelligence

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(gateway): avoid cold-loading providers for MCP inventory · openclaw/openclaw@d78b081
vincentkoc · 2026-05-29 · via Recent Commits to openclaw:main
1+

import type { OpenClawConfig } from "../config/types.openclaw.js";

2+

import type { ProviderRuntimeModel } from "../plugins/provider-runtime-model.types.js";

3+

import { getActivePluginRegistry } from "../plugins/runtime.js";

4+

import { buildPluginToolMetadataKey, getPluginToolMeta } from "../plugins/tools.js";

5+

import {

6+

normalizeLowercaseStringOrEmpty,

7+

normalizeOptionalString,

8+

} from "../shared/string-coerce.js";

9+

import { getChannelAgentToolMeta } from "./channel-tools.js";

10+

import { normalizeAgentRuntimeTools } from "./runtime-plan/tools.js";

11+

import { summarizeToolDescriptionText } from "./tool-description-summary.js";

12+

import { resolveToolDisplay } from "./tool-display.js";

13+

import {

14+

filterRuntimeCompatibleTools,

15+

type RuntimeToolSchemaDiagnostic,

16+

} from "./tool-schema-projection.js";

17+

import { buildEffectiveToolInventoryGroups } from "./tools-effective-inventory-groups.js";

18+

import type {

19+

EffectiveToolInventoryEntry,

20+

EffectiveToolInventoryNotice,

21+

EffectiveToolSource,

22+

} from "./tools-effective-inventory.types.js";

23+

import type { AnyAgentTool } from "./tools/common.js";

24+25+

function resolveEffectiveToolLabel(tool: AnyAgentTool): string {

26+

const rawLabel = normalizeOptionalString(tool.label) ?? "";

27+

if (

28+

rawLabel &&

29+

normalizeLowercaseStringOrEmpty(rawLabel) !== normalizeLowercaseStringOrEmpty(tool.name)

30+

) {

31+

return rawLabel;

32+

}

33+

return resolveToolDisplay({ name: tool.name }).title;

34+

}

35+36+

function resolveRawToolDescription(tool: AnyAgentTool): string {

37+

return normalizeOptionalString(tool.description) ?? "";

38+

}

39+40+

function summarizeToolDescription(tool: AnyAgentTool): string {

41+

return summarizeToolDescriptionText({

42+

rawDescription: resolveRawToolDescription(tool),

43+

displaySummary: tool.displaySummary,

44+

});

45+

}

46+47+

function resolveEffectiveToolSource(

48+

tool: AnyAgentTool,

49+

fallbackTool?: AnyAgentTool,

50+

): {

51+

source: EffectiveToolSource;

52+

pluginId?: string;

53+

channelId?: string;

54+

} {

55+

const pluginMeta =

56+

getPluginToolMeta(tool) ?? (fallbackTool ? getPluginToolMeta(fallbackTool) : undefined);

57+

if (pluginMeta) {

58+

if (pluginMeta.pluginId === "bundle-mcp") {

59+

return { source: "mcp", pluginId: pluginMeta.pluginId };

60+

}

61+

return { source: "plugin", pluginId: pluginMeta.pluginId };

62+

}

63+

const channelMeta =

64+

getChannelAgentToolMeta(tool as never) ??

65+

(fallbackTool ? getChannelAgentToolMeta(fallbackTool as never) : undefined);

66+

if (channelMeta) {

67+

return { source: "channel", channelId: channelMeta.channelId };

68+

}

69+

return { source: "core" };

70+

}

71+72+

function buildUnsupportedToolSchemaNotice(params: {

73+

diagnostic: RuntimeToolSchemaDiagnostic;

74+

tool: AnyAgentTool | undefined;

75+

fallbackTool: AnyAgentTool | undefined;

76+

}): EffectiveToolInventoryNotice {

77+

const source = params.tool

78+

? resolveEffectiveToolSource(params.tool, params.fallbackTool)

79+

: { source: "core" as const };

80+

const owner =

81+

source.source === "plugin" && source.pluginId

82+

? ` from plugin "${source.pluginId}"`

83+

: source.source === "channel" && source.channelId

84+

? ` from channel "${source.channelId}"`

85+

: "";

86+

return {

87+

id: `unsupported-tool-schema:${params.diagnostic.toolName}`,

88+

severity: "warning",

89+

message: `Tool "${params.diagnostic.toolName}"${owner} has an unsupported runtime input schema (${params.diagnostic.violations.join(", ")}) and was quarantined before model projection. Fix or disable the owner, or remove the tool from active allowlists.`,

90+

};

91+

}

92+93+

function buildUnsupportedToolSchemaNotices(params: {

94+

diagnostics: readonly RuntimeToolSchemaDiagnostic[];

95+

tools: readonly AnyAgentTool[];

96+

rawToolsByName: ReadonlyMap<string, AnyAgentTool>;

97+

}): EffectiveToolInventoryNotice[] {

98+

return params.diagnostics.map((diagnostic) =>

99+

buildUnsupportedToolSchemaNotice({

100+

diagnostic,

101+

tool: params.tools[diagnostic.toolIndex],

102+

fallbackTool: params.rawToolsByName.get(diagnostic.toolName),

103+

}),

104+

);

105+

}

106+107+

function disambiguateLabels(entries: EffectiveToolInventoryEntry[]): EffectiveToolInventoryEntry[] {

108+

const counts = new Map<string, number>();

109+

for (const entry of entries) {

110+

counts.set(entry.label, (counts.get(entry.label) ?? 0) + 1);

111+

}

112+

return entries.map((entry) => {

113+

if ((counts.get(entry.label) ?? 0) < 2) {

114+

return entry;

115+

}

116+

const suffix = entry.pluginId ?? entry.channelId ?? entry.id;

117+

return { ...entry, label: `${entry.label} (${suffix})` };

118+

});

119+

}

120+121+

export function buildEffectiveToolInventoryEntries(

122+

tools: readonly AnyAgentTool[],

123+

rawToolsByName: ReadonlyMap<string, AnyAgentTool> = new Map(),

124+

): EffectiveToolInventoryEntry[] {

125+

// Key metadata by plugin ownership and tool name so only the owning plugin can

126+

// project display/risk metadata for its own tool.

127+

const pluginToolMetadata = new Map(

128+

(getActivePluginRegistry()?.toolMetadata ?? []).map((entry) => [

129+

buildPluginToolMetadataKey(entry.pluginId, entry.metadata.toolName),

130+

entry.metadata,

131+

]),

132+

);

133+134+

return disambiguateLabels(

135+

tools

136+

.map((tool) => {

137+

const source = resolveEffectiveToolSource(tool, rawToolsByName.get(tool.name));

138+

const metadata = source.pluginId

139+

? pluginToolMetadata.get(buildPluginToolMetadataKey(source.pluginId, tool.name))

140+

: undefined;

141+

return Object.assign(

142+

{

143+

id: tool.name,

144+

label:

145+

normalizeOptionalString(metadata?.displayName) ?? resolveEffectiveToolLabel(tool),

146+

description:

147+

normalizeOptionalString(metadata?.description) ?? summarizeToolDescription(tool),

148+

rawDescription:

149+

normalizeOptionalString(metadata?.description) ??

150+

resolveRawToolDescription(tool) ??

151+

summarizeToolDescription(tool),

152+

...(metadata?.risk ? { risk: metadata.risk } : {}),

153+

...(metadata?.tags ? { tags: metadata.tags } : {}),

154+

},

155+

source,

156+

) satisfies EffectiveToolInventoryEntry;

157+

})

158+

.toSorted((a, b) => a.label.localeCompare(b.label)),

159+

);

160+

}

161+162+

export function buildRuntimeCompatibleToolInventory(params: {

163+

tools: readonly AnyAgentTool[];

164+

cfg: OpenClawConfig;

165+

workspaceDir?: string;

166+

modelProvider?: string;

167+

modelId?: string;

168+

modelApi?: string | null;

169+

runtimeModel?: ProviderRuntimeModel;

170+

}): {

171+

entries: EffectiveToolInventoryEntry[];

172+

notices: EffectiveToolInventoryNotice[];

173+

} {

174+

const rawToolsByName = new Map(params.tools.map((tool) => [tool.name, tool]));

175+

const normalizedTools = normalizeAgentRuntimeTools({

176+

// Schema normalization can replace tool definitions, so hand the runtime

177+

// policy a mutable copy while keeping this inventory API readonly.

178+

tools: [...params.tools],

179+

provider: params.modelProvider ?? "",

180+

config: params.cfg,

181+

workspaceDir: params.workspaceDir,

182+

modelId: params.modelId,

183+

modelApi: params.modelApi ?? undefined,

184+

model: params.runtimeModel,

185+

});

186+

const projection = filterRuntimeCompatibleTools(normalizedTools);

187+

return {

188+

entries: buildEffectiveToolInventoryEntries(projection.tools, rawToolsByName),

189+

notices: buildUnsupportedToolSchemaNotices({

190+

diagnostics: projection.diagnostics,

191+

tools: normalizedTools,

192+

rawToolsByName,

193+

}),

194+

};

195+

}

196+197+

export { buildEffectiveToolInventoryGroups };