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

V
Vulnerabilities – Threatpost
aimingoo的专栏
aimingoo的专栏
B
Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
GbyAI
GbyAI
阮一峰的网络日志
阮一峰的网络日志
Engineering at Meta
Engineering at Meta
IT之家
IT之家
V
Visual Studio Blog
The Cloudflare Blog
酷 壳 – CoolShell
酷 壳 – CoolShell
A
About on SuperTechFans
博客园 - 聂微东
Blog — PlanetScale
Blog — PlanetScale
N
News and Events Feed by Topic
A
Arctic Wolf
WordPress大学
WordPress大学
小众软件
小众软件
C
CERT Recently Published Vulnerability Notes
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
D
Darknet – Hacking Tools, Hacker News & Cyber Security
F
Fortinet All Blogs
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
Y
Y Combinator Blog
T
Threat Research - Cisco Blogs
Latest news
Latest news
Simon Willison's Weblog
Simon Willison's Weblog
Cyberwarzone
Cyberwarzone
S
Schneier on Security
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
L
Lohrmann on Cybersecurity
Stack Overflow Blog
Stack Overflow Blog
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
P
Privacy International News Feed
J
Java Code Geeks
Spread Privacy
Spread Privacy
宝玉的分享
宝玉的分享
I
Intezer
L
LangChain Blog
Hacker News - Newest:
Hacker News - Newest: "LLM"
G
GRAHAM CLULEY
博客园 - 叶小钗
博客园 - 三生石上(FineUI控件)
The GitHub Blog
The GitHub Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
N
News and Events Feed by Topic
AWS News Blog
AWS News Blog
Attack and Defense Labs
Attack and Defense Labs
Security Archives - TechRepublic
Security Archives - TechRepublic
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO

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: dogfood tool plugin helpers · openclaw/openclaw@ae17274
plugins-authoring-command.test.ts · 2026-05-17 · via Recent Commits to openclaw:main
Original file line numberDiff line numberDiff line change

@@ -651,6 +651,18 @@

651651

"source": "Plugin SDK",

652652

"target": "插件 SDK"

653653

},

654+

{

655+

"source": "Tool plugins",

656+

"target": "工具插件"

657+

},

658+

{

659+

"source": "Plugin SDK subpaths",

660+

"target": "插件 SDK 子路径"

661+

},

662+

{

663+

"source": "Plugins CLI",

664+

"target": "插件 CLI"

665+

},

654666

{

655667

"source": "Plugins",

656668

"target": "插件"

Original file line numberDiff line numberDiff line change

@@ -253,6 +253,12 @@ See [Plugin hooks](/plugins/hooks) for examples and the hook reference.

253253

Tools are typed functions the LLM can call. They can be required (always

254254

available) or optional (user opt-in):

255255
256+

For simple plugins that only own a fixed set of tools, prefer

257+

[`defineToolPlugin`](/plugins/tool-plugins). It generates manifest metadata and

258+

keeps `contracts.tools` aligned. Use the lower-level `api.registerTool(...)`

259+

surface when the plugin also owns channels, providers, hooks, services,

260+

commands, or fully dynamic tool registration.

261+
256262

```typescript

257263

register(api) {

258264

// Required tool - always available

Original file line numberDiff line numberDiff line change

@@ -107,6 +107,10 @@ methods:

107107
108108

### Tools and commands

109109
110+

Use [`defineToolPlugin`](/plugins/tool-plugins) for simple tool-only plugins

111+

with fixed tool names. Use `api.registerTool(...)` directly for mixed plugins

112+

or fully dynamic tool registration.

113+
110114

| Method | What it registers |

111115

| ------------------------------- | --------------------------------------------- |

112116

| `api.registerTool(tool, opts?)` | Agent tool (required or `{ optional: true }`) |

Original file line numberDiff line numberDiff line change

@@ -109,6 +109,48 @@ export default defineToolPlugin({

109109

Tool names are the stable API. Pick names that are unique, lowercase, and

110110

specific enough to avoid collisions with core tools or other plugins.

111111
112+

## Optional and factory tools

113+
114+

Set `optional: true` when users should explicitly allowlist the tool before it

115+

is sent to a model:

116+
117+

```typescript

118+

tool({

119+

name: "workflow_run",

120+

description: "Run an external workflow.",

121+

parameters: Type.Object({ goal: Type.String() }),

122+

optional: true,

123+

execute: ({ goal }) => ({ queued: true, goal }),

124+

});

125+

```

126+
127+

`openclaw plugins build` writes the matching `toolMetadata.<tool>.optional`

128+

manifest entry, so OpenClaw can discover the tool without loading plugin

129+

runtime code.

130+
131+

Use `factory` when a tool needs the runtime tool context before it can be

132+

created. The factory keeps metadata static while letting the tool opt out for a

133+

specific run, inspect sandbox state, or bind runtime helpers.

134+
135+

```typescript

136+

tool({

137+

name: "local_workflow",

138+

description: "Run a local workflow outside sandboxed sessions.",

139+

parameters: Type.Object({ goal: Type.String() }),

140+

optional: true,

141+

factory({ api, toolContext }) {

142+

if (toolContext.sandboxed) {

143+

return null;

144+

}

145+

return createLocalWorkflowTool(api);

146+

},

147+

});

148+

```

149+
150+

Factories are still for fixed tool names. Use `definePluginEntry` directly when

151+

the plugin computes tool names dynamically or combines tools with hooks,

152+

services, providers, commands, or other runtime surfaces.

153+
112154

## Return values

113155
114156

`defineToolPlugin` wraps plain return values into the OpenClaw tool-result

@@ -140,10 +182,10 @@ tool({

140182

});

141183

```

142184
143-

Use `definePluginEntry` instead of `defineToolPlugin` when you need to return a

144-

custom `AgentToolResult`, stream custom progress semantics, register dynamic

145-

tools, or combine tools with hooks, services, providers, commands, or other

146-

advanced surfaces.

185+

Use a factory tool when you need to return a custom `AgentToolResult` or reuse

186+

an existing `api.registerTool` implementation. Use `definePluginEntry` instead

187+

of `defineToolPlugin` when you need fully dynamic tools or mixed plugin

188+

capabilities.

147189
148190

## Configuration

149191
Original file line numberDiff line numberDiff line change

@@ -1,11 +1,32 @@

1-

import { definePluginEntry, type AnyAgentTool, type OpenClawPluginApi } from "./api.js";

2-

import { createLlmTaskTool } from "./src/llm-task-tool.js";

1+

import { defineToolPlugin } from "openclaw/plugin-sdk/tool-plugin";

2+

import { Type } from "typebox";

3+

import type { AnyAgentTool } from "./api.js";

4+

import { createLlmTaskTool, llmTaskToolDefinition } from "./src/llm-task-tool.js";

35
4-

export default definePluginEntry({

6+

export default defineToolPlugin({

57

id: "llm-task",

68

name: "LLM Task",

7-

description: "Optional tool for structured subtask execution",

8-

register(api: OpenClawPluginApi) {

9-

api.registerTool(createLlmTaskTool(api) as unknown as AnyAgentTool, { optional: true });

10-

},

9+

description: "Generic JSON-only LLM tool for structured tasks callable from workflows.",

10+

configSchema: Type.Object(

11+

{

12+

defaultProvider: Type.Optional(Type.String()),

13+

defaultModel: Type.Optional(Type.String()),

14+

defaultAuthProfileId: Type.Optional(Type.String()),

15+

allowedModels: Type.Optional(

16+

Type.Array(Type.String(), {

17+

description: "Allowlist of provider/model keys like openai-codex/gpt-5.2.",

18+

}),

19+

),

20+

maxTokens: Type.Optional(Type.Number()),

21+

timeoutMs: Type.Optional(Type.Number()),

22+

},

23+

{ additionalProperties: false },

24+

),

25+

tools: (tool) => [

26+

tool({

27+

...llmTaskToolDefinition,

28+

optional: true,

29+

factory: ({ api }) => createLlmTaskTool(api) as unknown as AnyAgentTool,

30+

}),

31+

],

1132

});

Original file line numberDiff line numberDiff line change

@@ -106,6 +106,29 @@ type LlmTaskParams = {

106106
107107

type ThinkingPolicy = ReturnType<OpenClawPluginApi["runtime"]["agent"]["resolveThinkingPolicy"]>;

108108
109+

export const llmTaskToolDefinition = {

110+

name: "llm-task",

111+

label: "LLM Task",

112+

description:

113+

"Run a generic JSON-only LLM task and return schema-validated JSON. Designed for orchestration from Lobster workflows via openclaw.invoke.",

114+

parameters: Type.Object({

115+

prompt: Type.String({ description: "Task instruction for the LLM." }),

116+

input: Type.Optional(Type.Unknown({ description: "Optional input payload for the task." })),

117+

schema: Type.Optional(

118+

Type.Unknown({ description: "Optional JSON Schema to validate the returned JSON." }),

119+

),

120+

provider: Type.Optional(

121+

Type.String({ description: "Provider override (e.g. openai-codex, anthropic)." }),

122+

),

123+

model: Type.Optional(Type.String({ description: "Model id override." })),

124+

thinking: Type.Optional(Type.String({ description: "Thinking level override." })),

125+

authProfileId: Type.Optional(Type.String({ description: "Auth profile override." })),

126+

temperature: Type.Optional(Type.Number({ description: "Best-effort temperature override." })),

127+

maxTokens: Type.Optional(Type.Number({ description: "Best-effort maxTokens override." })),

128+

timeoutMs: Type.Optional(Type.Number({ description: "Timeout for the LLM run." })),

129+

}),

130+

};

131+
109132

function formatThinkingPolicy(policy: ThinkingPolicy): string {

110133

return policy.levels.map((level) => level.label).join(", ");

111134

}

@@ -119,26 +142,7 @@ function supportsThinkingPolicyLevel(

119142
120143

export function createLlmTaskTool(api: OpenClawPluginApi) {

121144

return {

122-

name: "llm-task",

123-

label: "LLM Task",

124-

description:

125-

"Run a generic JSON-only LLM task and return schema-validated JSON. Designed for orchestration from Lobster workflows via openclaw.invoke.",

126-

parameters: Type.Object({

127-

prompt: Type.String({ description: "Task instruction for the LLM." }),

128-

input: Type.Optional(Type.Unknown({ description: "Optional input payload for the task." })),

129-

schema: Type.Optional(

130-

Type.Unknown({ description: "Optional JSON Schema to validate the returned JSON." }),

131-

),

132-

provider: Type.Optional(

133-

Type.String({ description: "Provider override (e.g. openai-codex, anthropic)." }),

134-

),

135-

model: Type.Optional(Type.String({ description: "Model id override." })),

136-

thinking: Type.Optional(Type.String({ description: "Thinking level override." })),

137-

authProfileId: Type.Optional(Type.String({ description: "Auth profile override." })),

138-

temperature: Type.Optional(Type.Number({ description: "Best-effort temperature override." })),

139-

maxTokens: Type.Optional(Type.Number({ description: "Best-effort maxTokens override." })),

140-

timeoutMs: Type.Optional(Type.Number({ description: "Timeout for the LLM run." })),

141-

}),

145+

...llmTaskToolDefinition,

142146
143147

async execute(_id: string, params: LlmTaskParams) {

144148

const prompt = typeof params.prompt === "string" ? params.prompt : "";

Original file line numberDiff line numberDiff line change

@@ -33,6 +33,28 @@ function createDemoMetadata() {

3333

return metadata;

3434

}

3535
36+

function createOptionalDemoMetadata() {

37+

const entry = defineToolPlugin({

38+

id: "optional-demo-tools",

39+

name: "Optional Demo Tools",

40+

description: "Optional demo tool plugin.",

41+

tools: (tool) => [

42+

tool({

43+

name: "demo_optional_echo",

44+

description: "Echo input.",

45+

parameters: Type.Object({ input: Type.String() }),

46+

optional: true,

47+

execute: ({ input }) => ({ input }),

48+

}),

49+

],

50+

});

51+

const metadata = getToolPluginMetadata(entry);

52+

if (!metadata) {

53+

throw new Error("missing metadata");

54+

}

55+

return metadata;

56+

}

57+
3658

describe("plugin authoring commands", () => {

3759

it("generates manifest metadata from defineToolPlugin metadata", () => {

3860

const metadata = createDemoMetadata();

@@ -52,6 +74,27 @@ describe("plugin authoring commands", () => {

5274

});

5375

});

5476
77+

it("generates optional tool metadata for optional tool plugins", () => {

78+

const metadata = createOptionalDemoMetadata();

79+
80+

expect(buildToolPluginManifest({ metadata, packageManifest: { version: "1.2.3" } })).toEqual({

81+

id: "optional-demo-tools",

82+

name: "Optional Demo Tools",

83+

description: "Optional demo tool plugin.",

84+

version: "1.2.3",

85+

configSchema: {

86+

type: "object",

87+

additionalProperties: false,

88+

properties: {},

89+

},

90+

activation: { onStartup: true },

91+

contracts: { tools: ["demo_optional_echo"] },

92+

toolMetadata: {

93+

demo_optional_echo: { optional: true },

94+

},

95+

});

96+

});

97+
5598

it("aligns package metadata with the selected runtime extension entry", () => {

5699

expect(

57100

buildToolPluginPackageManifest({

Original file line numberDiff line numberDiff line change

@@ -117,6 +117,7 @@ export function buildToolPluginManifest(params: {

117117

metadata: ToolPluginMetadata;

118118

packageManifest: JsonObject;

119119

}): JsonObject {

120+

const optionalTools = params.metadata.tools.filter((tool) => tool.optional);

120121

return {

121122

id: params.metadata.id,

122123

name: params.metadata.name,

@@ -128,6 +129,13 @@ export function buildToolPluginManifest(params: {

128129

contracts: {

129130

tools: params.metadata.tools.map((tool) => tool.name),

130131

},

132+

...(optionalTools.length > 0

133+

? {

134+

toolMetadata: Object.fromEntries(

135+

optionalTools.map((tool) => [tool.name, { optional: true }]),

136+

),

137+

}

138+

: {}),

131139

};

132140

}

133141
Original file line numberDiff line numberDiff line change

@@ -74,6 +74,98 @@ describe("defineToolPlugin", () => {

7474

});

7575

});

7676
77+

it("passes optional tools through to runtime registration and metadata", () => {

78+

const entry = defineToolPlugin({

79+

id: "optional-tools",

80+

name: "Optional Tools",

81+

description: "Optional tool demo.",

82+

tools: (tool) => [

83+

tool({

84+

name: "optional_echo",

85+

description: "Echo input.",

86+

parameters: Type.Object({ input: Type.String() }),

87+

optional: true,

88+

execute: ({ input }) => input,

89+

}),

90+

],

91+

});

92+

const captured = createCapturedPluginRegistration({ id: "optional-tools" });

93+

const registerTool = vi.fn();

94+

captured.api.registerTool = registerTool as typeof captured.api.registerTool;

95+
96+

entry.register(captured.api);

97+
98+

expect(registerTool).toHaveBeenCalledWith(expect.objectContaining({ name: "optional_echo" }), {

99+

optional: true,

100+

});

101+

expect(getToolPluginMetadata(entry)?.tools).toMatchObject([

102+

{ name: "optional_echo", optional: true },

103+

]);

104+

});

105+
106+

it("supports context factories while keeping static tool metadata", () => {

107+

const entry = defineToolPlugin({

108+

id: "factory-tools",

109+

name: "Factory Tools",

110+

description: "Factory tool demo.",

111+

configSchema: Type.Object({ prefix: Type.String() }),

112+

tools: (tool) => [

113+

tool({

114+

name: "factory_echo",

115+

label: "Factory Echo",

116+

description: "Echo input.",

117+

parameters: Type.Object({ input: Type.String() }),

118+

optional: true,

119+

factory({ config, toolContext }) {

120+

if (toolContext.sandboxed) {

121+

return null;

122+

}

123+

return {

124+

name: "factory_echo",

125+

label: "Factory Echo",

126+

description: "Echo input.",

127+

parameters: Type.Object({ input: Type.String() }),

128+

async execute(_toolCallId: string, params: { input?: unknown }) {

129+

const input = typeof params.input === "string" ? params.input : "";

130+

return {

131+

content: [

132+

{

133+

type: "text",

134+

text: `${config.prefix}:${input}`,

135+

},

136+

],

137+

details: undefined,

138+

};

139+

},

140+

};

141+

},

142+

}),

143+

],

144+

});

145+

const captured = createCapturedPluginRegistration({ id: "factory-tools" });

146+

captured.api.pluginConfig = { prefix: "ctx" };

147+

const registerTool = vi.fn();

148+

captured.api.registerTool = registerTool as typeof captured.api.registerTool;

149+
150+

entry.register(captured.api);

151+
152+

expect(registerTool).toHaveBeenCalledWith(expect.any(Function), {

153+

name: "factory_echo",

154+

optional: true,

155+

});

156+

expect(getToolPluginMetadata(entry)?.tools).toMatchObject([

157+

{

158+

name: "factory_echo",

159+

label: "Factory Echo",

160+

optional: true,

161+

},

162+

]);

163+
164+

const factory = registerTool.mock.calls[0]?.[0] as (ctx: { sandboxed?: boolean }) => unknown;

165+

expect(factory({ sandboxed: true })).toBeNull();

166+

expect(factory({ sandboxed: false })).toMatchObject({ name: "factory_echo" });

167+

});

168+
77169

it("defaults author config to a strict empty object schema", () => {

78170

const entry = defineToolPlugin({

79171

id: "empty-config",