@anionex/dsh-tool-search 0.1.0

package/lib/types/shared.d.ts

@@ -0,0 +1,31 @@
+/** Values shared by the Host runtime and Web settings client. */
+export declare const TOOL_SEARCH_NAME = "tool_search";
+export declare const TOOL_SEARCH_SETTINGS_NAMESPACE = "tool-search";
+export declare const TOOL_SEARCH_CATALOG_ROUTE = "/_dsh/tool-search/catalog";
+export declare const DEFAULT_RESULT_LIMIT = 5;
+export declare const MAX_RESULT_LIMIT = 20;
+/**
+ * Stable bootstrap surface for current DSH releases. Unknown future first-party
+ * names are deferred until this list or the user allowlist is updated because
+ * ToolDefinition does not expose package provenance.
+ */
+export declare const DEFAULT_CORE_TOOLS: readonly ["apply_patch", "ask_user_question", "bash", "create_goal", "dsh_im_return_file", "exit_plan_mode", "get_goal", "interrupt_agent", "job_kill", "job_list", "job_output", "list_agents", "ralph", "report", "send_message", "skill", "subagent", "subagent_fork", "todo_write", "update_goal", "workflow"];
+export interface ToolSearchSettings {
+    defaultLimit: number;
+    alwaysVisible: string[];
+    neverSearch: string[];
+}
+export declare const DEFAULT_SETTINGS: Readonly<ToolSearchSettings>;
+export type ToolPolicy = 'always' | 'deferred' | 'blocked';
+export interface CatalogToolSummary {
+    name: string;
+    description: string;
+    policy: ToolPolicy;
+    selectedBy: string[];
+}
+export interface CatalogSnapshot {
+    schemaVersion: 1;
+    generation: number;
+    tools: CatalogToolSummary[];
+}
+//# sourceMappingURL=shared.d.ts.map

package/lib/types/shared.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"shared.d.ts","sourceRoot":"","sources":["../../src/shared.ts"],"names":[],"mappings":"AAAA,iEAAiE;AAEjE,eAAO,MAAM,gBAAgB,gBAAgB,CAAA;AAC7C,eAAO,MAAM,8BAA8B,gBAAgB,CAAA;AAC3D,eAAO,MAAM,yBAAyB,8BAA8B,CAAA;AACpE,eAAO,MAAM,oBAAoB,IAAI,CAAA;AACrC,eAAO,MAAM,gBAAgB,KAAK,CAAA;AAElC;;;;GAIG;AACH,eAAO,MAAM,kBAAkB,oTAsBpB,CAAA;AAEX,MAAM,WAAW,kBAAkB;IACjC,YAAY,EAAE,MAAM,CAAA;IACpB,aAAa,EAAE,MAAM,EAAE,CAAA;IACvB,WAAW,EAAE,MAAM,EAAE,CAAA;CACtB;AAED,eAAO,MAAM,gBAAgB,EAAE,QAAQ,CAAC,kBAAkB,CAIxD,CAAA;AAEF,MAAM,MAAM,UAAU,GAAG,QAAQ,GAAG,UAAU,GAAG,SAAS,CAAA;AAE1D,MAAM,WAAW,kBAAkB;IACjC,IAAI,EAAE,MAAM,CAAA;IACZ,WAAW,EAAE,MAAM,CAAA;IACnB,MAAM,EAAE,UAAU,CAAA;IAClB,UAAU,EAAE,MAAM,EAAE,CAAA;CACrB;AAED,MAAM,WAAW,eAAe;IAC9B,aAAa,EAAE,CAAC,CAAA;IAChB,UAAU,EAAE,MAAM,CAAA;IAClB,KAAK,EAAE,kBAAkB,EAAE,CAAA;CAC5B"}

package/lib/types/web.d.ts

@@ -0,0 +1,5 @@
+/** Read-only live catalog endpoint for the Web settings page. */
+import type { Context } from '@deepseek-ai/cordis';
+import type { ToolSearchRuntime } from './runtime.ts';
+export declare function installCatalogRoute(ctx: Context, runtime: ToolSearchRuntime): void;
+//# sourceMappingURL=web.d.ts.map

package/lib/types/web.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"web.d.ts","sourceRoot":"","sources":["../../src/web.ts"],"names":[],"mappings":"AAAA,iEAAiE;AAGjE,OAAO,KAAK,EAAE,OAAO,EAAE,MAAM,qBAAqB,CAAA;AAGlD,OAAO,KAAK,EAAE,iBAAiB,EAAE,MAAM,cAAc,CAAA;AAYrD,wBAAgB,mBAAmB,CAAC,GAAG,EAAE,OAAO,EAAE,OAAO,EAAE,iBAAiB,GAAG,IAAI,CAelF"}

package/lib/web.js

@@ -0,0 +1,28 @@
+/** Read-only live catalog endpoint for the Web settings page. */
+import { TOOL_SEARCH_CATALOG_ROUTE } from "./shared.js";
+function sendJson(res, status, value) {
+    const body = Buffer.from(JSON.stringify(value));
+    res.setHeader('Content-Type', 'application/json; charset=utf-8');
+    res.setHeader('Content-Length', String(body.length));
+    res.setHeader('Cache-Control', 'no-store');
+    res.setHeader('X-Content-Type-Options', 'nosniff');
+    res.writeHead(status);
+    res.end(body);
+}
+export function installCatalogRoute(ctx, runtime) {
+    ctx.inject(['webServer'], webCtx => {
+        webCtx.effect(() => webCtx.webServer.register({
+            kind: 'exact',
+            path: TOOL_SEARCH_CATALOG_ROUTE,
+            handler: (req, res) => {
+                if (req.method !== 'GET') {
+                    res.setHeader('Allow', 'GET');
+                    sendJson(res, 405, { error: 'method-not-allowed' });
+                    return;
+                }
+                sendJson(res, 200, runtime.snapshot());
+            },
+        }), 'dsh-tool-search: Web catalog route');
+    });
+}
+//# sourceMappingURL=web.js.map

package/lib/web.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"web.js","sourceRoot":"","sources":["../src/web.ts"],"names":[],"mappings":"AAAA,iEAAiE;AAKjE,OAAO,EAAE,yBAAyB,EAAE,MAAM,aAAa,CAAA;AAGvD,SAAS,QAAQ,CAAC,GAAmB,EAAE,MAAc,EAAE,KAAc;IACnE,MAAM,IAAI,GAAG,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,CAAA;IAC/C,GAAG,CAAC,SAAS,CAAC,cAAc,EAAE,iCAAiC,CAAC,CAAA;IAChE,GAAG,CAAC,SAAS,CAAC,gBAAgB,EAAE,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,CAAA;IACpD,GAAG,CAAC,SAAS,CAAC,eAAe,EAAE,UAAU,CAAC,CAAA;IAC1C,GAAG,CAAC,SAAS,CAAC,wBAAwB,EAAE,SAAS,CAAC,CAAA;IAClD,GAAG,CAAC,SAAS,CAAC,MAAM,CAAC,CAAA;IACrB,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;AACf,CAAC;AAED,MAAM,UAAU,mBAAmB,CAAC,GAAY,EAAE,OAA0B;IAC1E,GAAG,CAAC,MAAM,CAAC,CAAC,WAAW,CAAC,EAAE,MAAM,CAAC,EAAE;QACjC,MAAM,CAAC,MAAM,CAAC,GAAG,EAAE,CAAC,MAAM,CAAC,SAAS,CAAC,QAAQ,CAAC;YAC5C,IAAI,EAAE,OAAO;YACb,IAAI,EAAE,yBAAyB;YAC/B,OAAO,EAAE,CAAC,GAAG,EAAE,GAAG,EAAE,EAAE;gBACpB,IAAI,GAAG,CAAC,MAAM,KAAK,KAAK,EAAE,CAAC;oBACzB,GAAG,CAAC,SAAS,CAAC,OAAO,EAAE,KAAK,CAAC,CAAA;oBAC7B,QAAQ,CAAC,GAAG,EAAE,GAAG,EAAE,EAAE,KAAK,EAAE,oBAAoB,EAAE,CAAC,CAAA;oBACnD,OAAM;gBACR,CAAC;gBACD,QAAQ,CAAC,GAAG,EAAE,GAAG,EAAE,OAAO,CAAC,QAAQ,EAAE,CAAC,CAAA;YACxC,CAAC;SACF,CAAC,EAAE,oCAAoC,CAAC,CAAA;IAC3C,CAAC,CAAC,CAAA;AACJ,CAAC"}

package/package.json

@@ -0,0 +1,149 @@
+{
+  "name": "@anionex/dsh-tool-search",
+  "version": "0.1.0",
+  "description": "Codex-style deferred tool loading for DSH with deterministic local BM25 search",
+  "keywords": [
+    "deepseek",
+    "deepseek-harness",
+    "tool-search",
+    "deferred-loading",
+    "bm25"
+  ],
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/Anionex/dsh-tool-search.git"
+  },
+  "bugs": {
+    "url": "https://github.com/Anionex/dsh-tool-search/issues"
+  },
+  "homepage": "https://github.com/Anionex/dsh-tool-search#readme",
+  "type": "module",
+  "packageManager": "pnpm@11.8.0",
+  "engines": {
+    "node": "^22.19.0 || >=24.0.0"
+  },
+  "main": "./lib/index.js",
+  "types": "./lib/types/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./lib/types/index.d.ts",
+      "default": "./lib/index.js"
+    },
+    "./bm25": {
+      "types": "./lib/types/bm25.d.ts",
+      "default": "./lib/bm25.js"
+    },
+    "./catalog": {
+      "types": "./lib/types/catalog.d.ts",
+      "default": "./lib/catalog.js"
+    },
+    "./client": {
+      "types": "./lib/types/client/index.d.ts",
+      "default": "./lib/client.js"
+    },
+    "./package.json": "./package.json"
+  },
+  "files": [
+    "lib",
+    "src",
+    "scripts",
+    "tests",
+    "docs",
+    "cordis.patch.yml",
+    "pnpm-lock.yaml",
+    "pnpm-workspace.yaml",
+    "tsconfig.json",
+    "tsconfig.client.json",
+    "tsconfig.test.json",
+    "tsdown.config.mjs",
+    "README.md",
+    "README.zh.md",
+    "CHANGELOG.md",
+    "LICENSE"
+  ],
+  "scripts": {
+    "build": "node --input-type=module -e \"import { rmSync } from 'node:fs'; for (const path of ['lib', '.client-build']) rmSync(path, { recursive: true, force: true })\" && tsc -p tsconfig.json && tsc -p tsconfig.client.json && tsdown -c tsdown.config.mjs",
+    "check": "tsc -p tsconfig.json --noEmit --pretty false && tsc -p tsconfig.client.json --noEmit --pretty false && tsc -p tsconfig.test.json --noEmit --pretty false",
+    "test": "pnpm run build && vitest run tests",
+    "benchmark": "node scripts/benchmark.mjs --write",
+    "e2e:profile": "node scripts/profile-e2e.mjs",
+    "validate": "pnpm run check && pnpm run test && pnpm run benchmark && node scripts/validate.mjs",
+    "prepack": "pnpm run build"
+  },
+  "dsh": {
+    "bundle": {
+      "patch": "./cordis.patch.yml"
+    },
+    "client": {
+      "platform": "web",
+      "inject": [
+        "@deepseek-ai/dsh-client-ui-renderer",
+        "@deepseek-ai/dsh-client-ui-settings",
+        "@deepseek-ai/dsh-client-locale"
+      ]
+    },
+    "compatibility": {
+      "dsh": "^0.1.1-rc.1 || ^0.1.2-alpha.1",
+      "profiles": [
+        "web",
+        "headless"
+      ]
+    }
+  },
+  "peerDependencies": {
+    "@deepseek-ai/cordis": "^4.0.1",
+    "@deepseek-ai/dsh-agent": "^0.1.0-rc.8 || ^0.1.1-rc.1 || ^0.1.2-alpha.1",
+    "@deepseek-ai/dsh-client-locale": "^0.1.0-rc.8 || ^0.1.1-rc.1 || ^0.1.2-alpha.1",
+    "@deepseek-ai/dsh-client-ui-renderer": "^0.1.0-rc.8 || ^0.1.1-rc.1 || ^0.1.2-alpha.1",
+    "@deepseek-ai/dsh-client-ui-settings": "^0.1.0-rc.8 || ^0.1.1-rc.1 || ^0.1.2-alpha.1",
+    "@deepseek-ai/dsh-host-webserver": "^0.1.0-rc.8 || ^0.1.1-rc.1 || ^0.1.2-alpha.1",
+    "@deepseek-ai/dsh-settings": "^0.1.0-rc.8 || ^0.1.1-rc.1 || ^0.1.2-alpha.1",
+    "@deepseek-ai/dsh-system-prompt": "^0.1.0-rc.8 || ^0.1.1-rc.1 || ^0.1.2-alpha.1",
+    "@deepseek-ai/dsh-tools": "^0.1.0-rc.8 || ^0.1.1-rc.1 || ^0.1.2-alpha.1",
+    "@deepseek-ai/schemastery": "^3.18.1",
+    "react": "^18.2.0"
+  },
+  "peerDependenciesMeta": {
+    "@deepseek-ai/dsh-host-webserver": {
+      "optional": true
+    }
+  },
+  "dependencies": {
+    "wink-porter2-stemmer": "^2.0.1"
+  },
+  "devDependencies": {
+    "@deepseek-ai/dsh": "0.1.2-rc.1",
+    "@deepseek-ai/dsh-agent": "0.1.2-rc.1",
+    "@deepseek-ai/dsh-attachment": "0.1.2-rc.1",
+    "@deepseek-ai/dsh-client-locale": "0.1.2-rc.1",
+    "@deepseek-ai/dsh-client-ui-renderer": "0.1.2-rc.1",
+    "@deepseek-ai/dsh-client-ui-settings": "0.1.2-rc.1",
+    "@deepseek-ai/dsh-code-runtime": "0.1.2-rc.1",
+    "@deepseek-ai/dsh-compaction": "0.1.2-rc.1",
+    "@deepseek-ai/dsh-host-webserver": "0.1.2-rc.1",
+    "@deepseek-ai/dsh-jobs": "0.1.2-rc.1",
+    "@deepseek-ai/dsh-output-retention": "0.1.2-rc.1",
+    "@deepseek-ai/dsh-sandbox": "0.1.2-rc.1",
+    "@deepseek-ai/dsh-session-persistence": "0.1.2-rc.1",
+    "@deepseek-ai/dsh-session-query": "0.1.2-rc.1",
+    "@deepseek-ai/dsh-settings": "0.1.2-rc.1",
+    "@deepseek-ai/dsh-system-prompt": "0.1.2-rc.1",
+    "@deepseek-ai/dsh-tools": "0.1.2-rc.1",
+    "@testing-library/react": "^16.3.2",
+    "@types/node": "^22.20.0",
+    "@types/react": "~18.3.1",
+    "@types/react-dom": "~18.3.0",
+    "gpt-tokenizer": "^4.0.0",
+    "jsdom": "^29.1.1",
+    "react": "^18.3.1",
+    "react-dom": "^18.3.1",
+    "tsdown": "^0.22.2",
+    "typescript": "^5.9.3",
+    "vitest": "^4.1.10"
+  },
+  "publishConfig": {
+    "access": "public",
+    "registry": "https://registry.npmjs.org/"
+  },
+  "license": "MIT"
+}

package/pnpm-workspace.yaml

@@ -0,0 +1,11 @@
+allowBuilds:
+  '@deepseek-ai/dsh-subprocess-local': true
+  '@google/genai': true
+  koffi: true
+  node-pty: true
+  protobufjs: true
+overrides:
+  'jose': 6.2.10
+  'koffi': 3.2.0
+  'undici@^7.0.0': 7.29.0
+  'undici@^8.0.0': 8.10.1

package/scripts/benchmark.mjs

@@ -0,0 +1,124 @@
+import { createHash } from 'node:crypto'
+import { mkdir, readFile, writeFile } from 'node:fs/promises'
+import { dirname, join } from 'node:path'
+import { fileURLToPath } from 'node:url'
+import { encode } from 'gpt-tokenizer'
+
+const root = dirname(dirname(fileURLToPath(import.meta.url)))
+const generator = 'scripts/benchmark.mjs'
+const generatorSource = await readFile(fileURLToPath(import.meta.url))
+const packageJson = JSON.parse(await readFile(join(root, 'package.json'), 'utf8'))
+const sizes = [10, 30, 50, 100]
+
+function generatedTool(index) {
+  const id = String(index + 1).padStart(3, '0')
+  return {
+    name: `integration_${id}_search_records`,
+    description: `Search integration ${id} records with account, date, status, ownership, and pagination filters.`,
+    parameters: {
+      type: 'object',
+      additionalProperties: false,
+      properties: {
+        account_id: {
+          type: 'string',
+          description: 'Exact customer account identifier.',
+        },
+        filters: {
+          type: 'object',
+          description: 'Optional structured record filters.',
+          additionalProperties: false,
+          properties: {
+            created_after: {
+              type: 'string',
+              description: 'ISO 8601 lower date boundary.',
+            },
+            owner: {
+              type: 'string',
+              description: 'Owner email address or stable identifier.',
+            },
+            statuses: {
+              type: 'array',
+              description: 'Accepted workflow states.',
+              items: {
+                type: 'string',
+                description: 'One workflow status.',
+              },
+            },
+          },
+        },
+        limit: {
+          type: 'integer',
+          description: 'Maximum records to return.',
+        },
+        cursor: {
+          type: 'string',
+          description: 'Opaque pagination cursor from the previous result.',
+        },
+      },
+      required: ['account_id'],
+    },
+  }
+}
+
+const searchTool = {
+  name: 'tool_search',
+  description: 'Search deferred tool metadata with deterministic local BM25. Matching tools become available by their real names on the next model call. Results contain summaries, not full schemas.',
+  parameters: {
+    type: 'object',
+    additionalProperties: false,
+    properties: {
+      query: { type: 'string', description: 'Search query for deferred tools.' },
+      limit: { type: 'integer', description: 'Maximum number of tools to return. Defaults to 5.' },
+    },
+    required: ['query'],
+  },
+}
+
+function wire(tools) {
+  return JSON.stringify(tools.map(tool => ({
+    type: 'function',
+    function: tool,
+  })))
+}
+
+function tokenCount(tools) {
+  return encode(wire(tools)).length
+}
+
+const allTools = Array.from({ length: Math.max(...sizes) }, (_value, index) => generatedTool(index))
+const rows = sizes.map(size => {
+  const corpus = allTools.slice(0, size)
+  const fullTokens = tokenCount(corpus)
+  const deferredInitialTokens = tokenCount([searchTool])
+  const afterTop5Tokens = tokenCount([searchTool, ...corpus.slice(0, 5)])
+  return {
+    tools: size,
+    fullTokens,
+    deferredInitialTokens,
+    initialTokensSaved: fullTokens - deferredInitialTokens,
+    initialReductionPercent: Number(((1 - deferredInitialTokens / fullTokens) * 100).toFixed(1)),
+    afterTop5Tokens,
+  }
+})
+
+const report = {
+  schemaVersion: 2,
+  packageVersion: packageJson.version,
+  tokenizer: 'gpt-tokenizer 4.0.0 (o200k_base default encode)',
+  fixture: {
+    description: 'Deterministic nested function schemas; full surface versus tool_search-only initial surface.',
+    generator,
+    generatorSha256: createHash('sha256').update(generatorSource).digest('hex'),
+    corpusSha256: createHash('sha256').update(wire(allTools)).digest('hex'),
+    sizes,
+  },
+  rows,
+}
+
+if (process.argv.includes('--write')) {
+  const output = join(root, 'docs', 'benchmark-results.json')
+  await mkdir(dirname(output), { recursive: true })
+  await writeFile(output, `${JSON.stringify(report, null, 2)}\n`)
+}
+
+process.stdout.write(`${JSON.stringify(report, null, 2)}\n`)