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

Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
C
CXSECURITY Database RSS Feed - CXSecurity.com
L
LINUX DO - 热门话题
S
Secure Thoughts
TaoSecurity Blog
TaoSecurity Blog
Security Archives - TechRepublic
Security Archives - TechRepublic
T
Threat Research - Cisco Blogs
AI
AI
B
Blog RSS Feed
S
Schneier on Security
雷峰网
雷峰网
Schneier on Security
Schneier on Security
Help Net Security
Help Net Security
Cloudbric
Cloudbric
L
LINUX DO - 最新话题
罗磊的独立博客
有赞技术团队
有赞技术团队
Recent Commits to openclaw:main
Recent Commits to openclaw:main
Apple Machine Learning Research
Apple Machine Learning Research
P
Proofpoint News Feed
酷 壳 – CoolShell
酷 壳 – CoolShell
The Hacker News
The Hacker News
博客园 - Franky
Attack and Defense Labs
Attack and Defense Labs
The Cloudflare Blog
Webroot Blog
Webroot Blog
Last Week in AI
Last Week in AI
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
博客园 - 叶小钗
美团技术团队
L
Lohrmann on Cybersecurity
T
The Blog of Author Tim Ferriss
The Last Watchdog
The Last Watchdog
T
Troy Hunt's Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
Vercel News
Vercel News
Know Your Adversary
Know Your Adversary
O
OpenAI News
博客园 - 【当耐特】
Hacker News - Newest:
Hacker News - Newest: "LLM"
C
Cybersecurity and Infrastructure Security Agency CISA
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
www.infosecurity-magazine.com
www.infosecurity-magazine.com
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
PCI Perspectives
PCI Perspectives
H
Heimdal Security Blog
I
InfoQ
GbyAI
GbyAI
T
Threatpost
C
Cisco Blogs

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(plugins): compose live hook registry view for tool-call hooks · openclaw/openclaw@23eadfa
amknight · 2026-06-18 · via Recent Commits to openclaw:main

@@ -3,13 +3,25 @@

33

*

44

* Singleton hook runner that's initialized when plugins are loaded

55

* and can be called from anywhere in the codebase.

6+

*

7+

* The runner is created once and resolves hooks live on every dispatch from a

8+

* composed view of the registries that are currently live: the most recently

9+

* initialized registry, the active registry, and the pinned channel/http-route

10+

* surfaces. Freezing one registry caused scoped mid-run activations (harness

11+

* and memory ensures) to rebind the runner to a narrow registry and silently

12+

* drop other plugins' tool-call hooks (#91918). Composing live also preserves

13+

* the older contract that hooks pushed into a registry after initialization

14+

* (e.g. the SDK `addTestHook` helper) dispatch immediately.

615

*/

716817

import { createSubsystemLogger } from "../logging/subsystem.js";

918

import { resolveGlobalSingleton } from "../shared/global-singleton.js";

1019

import type { GlobalHookRunnerRegistry } from "./hook-registry.types.js";

1120

import type { PluginHookGatewayContext, PluginHookGatewayStopEvent } from "./hook-types.js";

1221

import { createHookRunner, type HookRunner } from "./hooks.js";

22+

import { isPluginRegistryRetired } from "./registry-lifecycle.js";

23+

import type { PluginRegistry } from "./registry-types.js";

24+

import { collectLivePluginRegistries } from "./runtime.js";

13251426

type HookRunnerGlobalState = {

1527

hookRunner: HookRunner | null;

@@ -25,27 +37,153 @@ const getState = () =>

25372638

const getLog = () => createSubsystemLogger("plugins");

273940+

function collectHookRegistrySources(

41+

lastInitialized: GlobalHookRunnerRegistry | null,

42+

): GlobalHookRunnerRegistry[] {

43+

const ordered: GlobalHookRunnerRegistry[] = [];

44+

const seen = new Set<GlobalHookRunnerRegistry>();

45+

const add = (registry: GlobalHookRunnerRegistry | null) => {

46+

if (!registry || seen.has(registry)) {

47+

return;

48+

}

49+

// Retired registries were superseded by a newer activation; dispatching

50+

// their hooks would resurrect stale config closures. Only lastInitialized

51+

// can be retired here (the live registries below are active/pinned, never

52+

// retired); SDK-supplied registries are not PluginRegistry and never match.

53+

if (isPluginRegistryRetired(registry as PluginRegistry)) {

54+

return;

55+

}

56+

seen.add(registry);

57+

ordered.push(registry);

58+

};

59+

// Precedence: the explicitly initialized registry wins so an SDK caller that

60+

// initializes an isolated registry stays authoritative; in the gateway it is

61+

// the same object as the active registry, so this just dedupes.

62+

add(lastInitialized);

63+

for (const registry of collectLivePluginRegistries()) {

64+

add(registry);

65+

}

66+

return ordered;

67+

}

68+69+

function composeLiveHookRegistry(

70+

lastInitialized: GlobalHookRunnerRegistry | null,

71+

): GlobalHookRunnerRegistry {

72+

const sources = collectHookRegistrySources(lastInitialized);

73+

// One source registry owns a plugin's entire contribution (status + hooks),

74+

// so handlers never double-fire across registries and a plugin's hooks stay

75+

// paired with the status the inbound-claim path reads.

76+

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

77+

const claimOwner = (pluginId: string, index: number) => {

78+

if (!ownerSourceIndexByPluginId.has(pluginId)) {

79+

ownerSourceIndexByPluginId.set(pluginId, index);

80+

}

81+

};

82+

// pluginIds each source actually contributes a hook for, so ownership can

83+

// prefer a source that carries the plugin's hooks over a same-plugin record

84+

// that loaded without any (e.g. a setup-runtime channel load registers the

85+

// channel but not the plugin's api.on(...) hooks).

86+

const hookPluginIdsBySource = sources.map((registry) => {

87+

const ids = new Set<string>();

88+

for (const hook of registry.typedHooks) {

89+

ids.add(hook.pluginId);

90+

}

91+

for (const hook of registry.hooks) {

92+

ids.add(hook.pluginId);

93+

}

94+

return ids;

95+

});

96+

// Prefer the highest-precedence source where the plugin loaded AND actually

97+

// contributes a hook, so a loaded-but-hookless record (failed/disabled scoped

98+

// reload, or a setup-runtime channel load) cannot shadow a lower-precedence

99+

// registration that still carries a fail-closed tool-call gate.

100+

sources.forEach((registry, index) => {

101+

for (const plugin of registry.plugins) {

102+

if (plugin.status === "loaded" && hookPluginIdsBySource[index].has(plugin.id)) {

103+

claimOwner(plugin.id, index);

104+

}

105+

}

106+

});

107+

// Then a loaded record owns the plugin's status when no live source

108+

// contributes a hook for it, keeping status paired with a single owner.

109+

sources.forEach((registry, index) => {

110+

for (const plugin of registry.plugins) {

111+

if (plugin.status === "loaded") {

112+

claimOwner(plugin.id, index);

113+

}

114+

}

115+

});

116+

sources.forEach((registry, index) => {

117+

for (const plugin of registry.plugins) {

118+

claimOwner(plugin.id, index);

119+

}

120+

});

121+

// Defensive: claim any hook whose plugin record is absent from .plugins so a

122+

// malformed registry never silently drops a registered hook.

123+

sources.forEach((registry, index) => {

124+

for (const hook of registry.typedHooks) {

125+

claimOwner(hook.pluginId, index);

126+

}

127+

for (const hook of registry.hooks) {

128+

claimOwner(hook.pluginId, index);

129+

}

130+

});

131+

return {

132+

hooks: sources.flatMap((registry, index) =>

133+

registry.hooks.filter((hook) => ownerSourceIndexByPluginId.get(hook.pluginId) === index),

134+

),

135+

typedHooks: sources.flatMap((registry, index) =>

136+

registry.typedHooks.filter((hook) => ownerSourceIndexByPluginId.get(hook.pluginId) === index),

137+

),

138+

plugins: sources.flatMap((registry, index) =>

139+

registry.plugins.filter((plugin) => ownerSourceIndexByPluginId.get(plugin.id) === index),

140+

),

141+

};

142+

}

143+144+

function createComposedHookRegistryFacade(state: HookRunnerGlobalState): GlobalHookRunnerRegistry {

145+

// Live getters: createHookRunner reads these on every hasHooks/getHooksForName

146+

// call, so the runner always dispatches the current live registry set rather

147+

// than a snapshot captured at initialization. Composition is bounded by the

148+

// small live registry set and runs on hook-paced events, not tight loops.

149+

return {

150+

get hooks() {

151+

return composeLiveHookRegistry(state.registry).hooks;

152+

},

153+

get typedHooks() {

154+

return composeLiveHookRegistry(state.registry).typedHooks;

155+

},

156+

get plugins() {

157+

return composeLiveHookRegistry(state.registry).plugins;

158+

},

159+

};

160+

}

161+28162

/**

29163

* Initialize the global hook runner with a plugin registry.

30-

* Called once when plugins are loaded during gateway startup.

164+

* Called on every plugin registry activation and by SDK consumers. The runner

165+

* instance stays stable so references captured mid-run keep seeing current

166+

* hooks; the passed registry becomes the highest-precedence composition source.

31167

*/

32168

export function initializeGlobalHookRunner(registry: GlobalHookRunnerRegistry): void {

33169

const state = getState();

34170

const log = getLog();

35171

state.registry = registry;

36-

state.hookRunner = createHookRunner(registry, {

37-

logger: {

38-

debug: (msg) => log.debug(msg),

39-

warn: (msg) => log.warn(msg),

40-

error: (msg) => log.error(msg),

41-

},

42-

catchErrors: true,

43-

failurePolicyByHook: {

44-

before_agent_run: "fail-closed",

45-

before_install: "fail-closed",

46-

before_tool_call: "fail-closed",

47-

},

48-

});

172+

if (!state.hookRunner) {

173+

state.hookRunner = createHookRunner(createComposedHookRegistryFacade(state), {

174+

logger: {

175+

debug: (msg) => log.debug(msg),

176+

warn: (msg) => log.warn(msg),

177+

error: (msg) => log.error(msg),

178+

},

179+

catchErrors: true,

180+

failurePolicyByHook: {

181+

before_agent_run: "fail-closed",

182+

before_install: "fail-closed",

183+

before_tool_call: "fail-closed",

184+

},

185+

});

186+

}

4918750188

const hookCount = registry.hooks.length;

51189

if (hookCount > 0) {

@@ -62,8 +200,9 @@ export function getGlobalHookRunner(): HookRunner | null {

62200

}

6320164202

/**

65-

* Get the global plugin registry.

66-

* Returns null if plugins haven't been loaded yet.

203+

* Get the registry from the most recent activation or explicit initialization.

204+

* Returns null if plugins haven't been loaded yet. Hook dispatch does not use

205+

* this single registry; the runner resolves hooks from the live composed view.

67206

*/

68207

export function getGlobalPluginRegistry(): GlobalHookRunnerRegistry | null {

69208

return getState().registry;