token-pilot 0.46.0 → 0.47.0

package/.claude-plugin/marketplace.json

@@ -6,14 +6,14 @@
   },
   "metadata": {
     "description": "Token Pilot — save 60-90% tokens when AI reads code",
-    "version": "0.46.0"
+    "version": "0.47.0"
   },
   "plugins": [
     {
       "name": "token-pilot",
       "source": "./",
-      "description": "Reduces token consumption by 60-90% via AST-aware lazy file reading, structural symbol navigation, and cross-session tool-usage analytics. 23 MCP tools + 25 subagents + budget watchdog hooks.",
-      "version": "0.46.0",
+      "description": "Reduces token consumption by 60-90% via AST-aware lazy file reading, structural symbol navigation, and cross-session tool-usage analytics. 24 MCP tools + 25 subagents + budget watchdog hooks.",
+      "version": "0.47.0",
       "author": {
         "name": "Digital-Threads"
       },

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "token-pilot",
-  "version": "0.46.0",
+  "version": "0.47.0",
   "description": "Saves 60-90% tokens on AI code reading. AST-aware lazy reads, symbol navigation, find_usages, structural git diff/log, edit-safety guard, Task-routing matcher, cross-session telemetry (errors + diagnostics), 25 tp-* subagents tiered to haiku/sonnet/opus with budget watchdog.",
   "author": {
     "name": "Digital-Threads",

package/CHANGELOG.md

@@ -5,6 +5,60 @@ All notable changes to Token Pilot will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.47.0] - 2026-06-24
+
+### Added — `explore` tool: one-shot ranked context + graph blast-radius
+
+New MCP tool **`explore`** wraps ast-index 3.48's `explore` command: for a query
+it returns ranked relevant symbols, the source heads of the top files, **graph
+neighbours (callers + subclasses — the blast radius, via RWR over the
+call/inheritance graph)**, and related test files — in a single compact block.
+Replaces the common `find_usages` → `read_symbol` → `call_tree` chain with one
+call. `graph` defaults on; `max_files` caps the source heads. Falls back to a
+clear "requires ast-index >= 3.48" message when an older binary is resolved.
+
+### Changed — bump `@ast-index/cli` to 3.48.1
+
+Picks up the upstream TypeScript-indexing fix, the rebuild **swap-and-restore**
+guard (a failed rebuild no longer wipes the index), memory caps, and FUSE-safe
+canonicalisation. `npm audit` stays at 0 vulnerabilities.
+
+### Changed — `buildIndex` trusts swap-and-restore
+
+When a rebuild fails, `buildIndex` now checks for the index the binary preserved
+and uses it (instead of throwing and falling back to raw reads). The lock-case
+and generic-failure recovery paths are unified.
+
+_Deferred:_ `--local` / subtree query scoping (to re-enable ast-index on
+multi-repo / worktree parents instead of disabling it) needs a rooting-model
+rework and ships separately.
+
+## [0.46.1] - 2026-06-18
+
+### Fixed — node:test (`node --test`) TAP output parsing
+
+`test_summary` did not recognise `node --test`: `detectRunner` had no `node`
+case, so node:test output fell through to the generic parser. node:test emits a
+TAP footer (`# pass N` / `# fail N`, number after the word) and `ok N - name`
+points (`ok` before the number), which the generic `<N> passed` regex never
+matches — a green 2/2 run was reported as 0 passed. Added a `node` runner:
+detected by command (`node --test` / `node:test`) or by the TAP footer, parsing
+pass/fail/skipped/tests from the footer with a fallback to counting `ok` /
+`not ok` lines; failure names come from `not ok N - name`. Purely additive — no
+existing parser touched.
+
+### Changed — dev-dependency security + decoupled registry publish (no shipped change)
+
+- Bump `vitest` / `@vitest/coverage-v8` to 4.x — clears the 6 remaining
+  dev-only high advisories in the vitest/vite/esbuild chain. `npm audit` now
+  reports **0 vulnerabilities** (dev + prod). No runtime/package change: dev
+  deps are not shipped to npm consumers; the full 1402-test suite is green on
+  vitest 4.
+- `publish-mcp.yml`: the MCP Registry job no longer hard-depends on npm-job
+  **success** (`if: !cancelled()`). A failed npm publish (e.g. EOTP on a
+  manual-token release) no longer blocks the registry update; re-run the job
+  via `workflow_dispatch` after a manual `npm publish`.
+
 ## [0.46.0] - 2026-06-13
 
 ### Added — UserPromptSubmit per-turn reinforcement (caveman-style awareness)

package/README.md

@@ -2,7 +2,7 @@
 
 **Token-efficient AI coding, enforced.** Cuts context consumption in AI coding assistants by up to **90%** without changing the way you work.
 
-> **Why it matters more now:** as frontier models move up in price — Claude's Fable 5 is the most capable (and most expensive-per-token) tier yet — the tokens you *don't* spend reading code are worth more, not less. The savings are in tokens; the value is in tokens × price. Token Pilot keeps the expensive main thread lean so the premium model spends its budget on reasoning, not on re-reading files.
+> **Why it matters more now:** as frontier models move up in price, the tokens you *don't* spend reading code are worth more, not less. The savings are in tokens; the value is in tokens × price. Token Pilot keeps the expensive main thread lean so the premium model spends its budget on reasoning, not on re-reading files.
 
 Three layers, each useful on its own, stronger together:
 

package/agents/tp-api-surface-tracker.md

@@ -9,7 +9,7 @@ tools:
   - mcp__token-pilot__read_symbol
   - Bash
 model: haiku
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: dd184501203fa7f3c73f419c4ffbe33c4be75400cb64a7a51733a3fe23f6e085
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-audit-scanner.md

@@ -11,7 +11,7 @@ tools:
   - Grep
   - Read
 model: sonnet
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: d172f600bf32277ea6eb4cbbee4542ddd698a986dcd96997d33930561964569b
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-commit-writer.md

@@ -8,7 +8,7 @@ tools:
   - mcp__token-pilot__test_summary
   - mcp__token-pilot__outline
   - Bash
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: de64a406b5176de19f7422619c7de7949b1f28865f225402c9cea9255f377428
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-context-engineer.md

@@ -13,7 +13,7 @@ tools:
   - Edit
   - Glob
 model: sonnet
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: 68b32af2dacd82ebe52c4eec93edb903d452688274c3065218270627c564d8b0
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-dead-code-finder.md

@@ -11,7 +11,7 @@ tools:
   - Grep
   - Read
 model: sonnet
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: d9b7f5b7ae6f4ae21305c775361bcab097cc774370a6d976c093571d46d55021
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-debugger.md

@@ -12,7 +12,7 @@ tools:
   - Read
   - Bash
 model: sonnet
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: 052413de8d92377edcde6ae5c823f5378db304baccfa29e8866467f42553a500
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-dep-health.md

@@ -9,7 +9,7 @@ tools:
   - Bash
   - Read
 model: haiku
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: e14dc57493d816f8c2e017963e2ef5f66bea50fd0b805a80e8a0d97c968427e7
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-doc-writer.md

@@ -13,7 +13,7 @@ tools:
   - Edit
   - Glob
 model: haiku
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: 57d741794ab40e31a7ac49c68ea39a9088f5827cdef866ce81bfca1b7c9180cf
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-history-explorer.md

@@ -10,7 +10,7 @@ tools:
   - Bash
   - Read
 model: haiku
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: 7b70fa76a60e3c58a1de4f56c32c0f166424137e203a0cf1c8654e7c9235d904
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-impact-analyzer.md

@@ -12,7 +12,7 @@ tools:
   - mcp__token-pilot__read_symbols
   - Read
 model: sonnet
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: 351a987e11eba63852f5431a16d8eb53104f4f689f82fdcc5a2bf4db948ba92f
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-incident-timeline.md

@@ -8,7 +8,7 @@ tools:
   - mcp__token-pilot__read_symbol
   - Bash
 model: inherit
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: de5722bfea374eaab096c1ae635c37879e7a91370ee3cd0532f4240be03c91eb
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-incremental-builder.md

@@ -13,7 +13,7 @@ tools:
   - Edit
   - Bash
 model: sonnet
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: 375a824d0d847bb5453ec594c7a62ad566ee7e4d92717b0473f771f1a0477c60
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-migration-scout.md

@@ -11,7 +11,7 @@ tools:
   - Grep
   - Glob
 model: sonnet
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: 0334de1bf99b431b65359637d125cda7c44c6f780eb92c57cc538715b1939536
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-onboard.md

@@ -10,7 +10,7 @@ tools:
   - mcp__token-pilot__smart_read
   - mcp__token-pilot__smart_read_many
   - mcp__token-pilot__read_section
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: 832e95633fbc8e9b0c10f3e540a327d4be062fb4b3f17a6cce6be13f414e2927
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-performance-profiler.md

@@ -11,7 +11,7 @@ tools:
   - Bash
   - Read
 model: sonnet
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: b61f06380d80798fa2e49d37bcba0653495bee04dd6bdbc1feff9a75607b0508
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-pr-reviewer.md

@@ -11,7 +11,7 @@ tools:
   - mcp__token-pilot__read_for_edit
   - Read
 model: sonnet
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: f83f50d05b4f70285ae7afed2b1a406fc436df56e61a0aedbfb31edc7f2b6e66
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-refactor-planner.md

@@ -8,7 +8,7 @@ tools:
   - mcp__token-pilot__outline
   - mcp__token-pilot__read_symbol
 model: sonnet
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: c5f6fc122c89e16e5cf774045f92169ee3468555320b898171ba13eca5323550
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-review-impact.md

@@ -9,7 +9,7 @@ tools:
   - mcp__token-pilot__module_info
   - Bash
 model: sonnet
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: 8ef3c3341cbfed4eb8dd130126a9683edc57e378c92ff0ca764d584fd941c55c
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-run.md

@@ -16,7 +16,7 @@ tools:
   - Glob
   - Bash
 model: haiku
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: 2b08618d34a61f00aafccbda9fed6d83243296dedb83440edbd2d5c28bb6dbc4
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-session-restorer.md

@@ -9,7 +9,7 @@ tools:
   - mcp__token-pilot__session_budget
   - Bash
   - Read
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: 529374ed728f5eed5b758b3be3da65624783c0bf0c1a253d7d661a843eb5f767
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-ship-coordinator.md

@@ -11,7 +11,7 @@ tools:
   - Read
   - Grep
 model: sonnet
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: a60f6ae110eb3138064bce074e8ba26fa0ce5f4659df1624a9d9d3646803391b
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-spec-writer.md

@@ -9,7 +9,7 @@ tools:
   - Read
   - Write
 model: sonnet
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: c7a4e8b39228fd5158528f389c924c5ff2d98c4b9b05ee0106d54a26c5dc1350
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-test-coverage-gapper.md

@@ -10,7 +10,7 @@ tools:
   - mcp__token-pilot__test_summary
   - Glob
   - Grep
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: be81eed53a3720d146cf89e4a14a7a56577633f7c84c234c412ab70d64c05b11
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-test-triage.md

@@ -8,7 +8,7 @@ tools:
   - mcp__token-pilot__find_usages
   - mcp__token-pilot__read_symbol
 model: sonnet
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: 362ecf4cb03b059421ea26933473700900073dc38b3a7fe271208dfb1ae14f90
 requiredMcpServers:
   - "token-pilot"

package/agents/tp-test-writer.md

@@ -13,7 +13,7 @@ tools:
   - Edit
   - Bash
 model: sonnet
-token_pilot_version: "0.46.0"
+token_pilot_version: "0.47.0"
 token_pilot_body_hash: 269f2fe22ff4517c277d3f56ca67d8a5527b93290ab21079a83ba7af22c1b5a9
 requiredMcpServers:
   - "token-pilot"

package/dist/ast-index/client.d.ts

@@ -1,5 +1,5 @@
 import type { FileStructure } from "../types.js";
-import type { AstIndexSymbolDetail, AstIndexSearchResult, AstIndexUsageResult, AstIndexImplementation, AstIndexHierarchyNode, AstIndexRefsResponse, AstIndexMapResponse, AstIndexConventionsResponse, AstIndexCallerEntry, AstIndexCallTreeNode, AstIndexChangedEntry, AstIndexUnusedSymbol, AstIndexImportEntry, AstIndexAgrepMatch, AstIndexTodoEntry, AstIndexDeprecatedEntry, AstIndexAnnotationEntry, AstIndexModuleEntry, AstIndexModuleDep, AstIndexUnusedDep, AstIndexModuleApi } from "./types.js";
+import type { AstIndexSymbolDetail, AstIndexSearchResult, AstIndexUsageResult, AstIndexImplementation, AstIndexHierarchyNode, AstIndexRefsResponse, AstIndexMapResponse, AstIndexConventionsResponse, AstIndexCallerEntry, AstIndexCallTreeNode, AstIndexChangedEntry, AstIndexUnusedSymbol, AstIndexImportEntry, AstIndexAgrepMatch, AstIndexTodoEntry, AstIndexDeprecatedEntry, AstIndexAnnotationEntry, AstIndexModuleEntry, AstIndexModuleDep, AstIndexUnusedDep, AstIndexModuleApi, AstIndexExploreResult } from "./types.js";
 export declare class AstIndexClient {
     private static readonly MAX_INDEX_FILES;
     private binaryPath;
@@ -34,6 +34,10 @@ export declare class AstIndexClient {
         fuzzy?: boolean;
     }): Promise<AstIndexSearchResult[]>;
     usages(symbolName: string): Promise<AstIndexUsageResult[]>;
+    explore(query: string, options?: {
+        maxFiles?: number;
+        graph?: boolean;
+    }): Promise<AstIndexExploreResult>;
     implementations(name: string): Promise<AstIndexImplementation[]>;
     hierarchy(name: string, options?: {
         inFile?: string;

package/dist/ast-index/client.js

@@ -128,16 +128,22 @@ export class AstIndexClient {
         }
         catch (buildErr) {
             const errMsg = buildErr instanceof Error ? buildErr.message : String(buildErr);
-            if (errMsg.includes("lock") || errMsg.includes("already running")) {
-                const count = parseFileCount(await this.exec(["--format", "json", "stats"]).catch(() => ""));
-                if (count > 0 && count <= AstIndexClient.MAX_INDEX_FILES) {
-                    this.indexed = true;
-                    console.error(`[token-pilot] ast-index: using existing index (${count} files, rebuild skipped due to lock)`);
-                    return;
-                }
-                if (count > AstIndexClient.MAX_INDEX_FILES) {
-                    return this.handleOversizedIndex(count);
-                }
+            // ast-index 3.46+ preserves the previous index when a rebuild aborts
+            // (swap-and-restore guard). Before giving up, query stats once: if a
+            // usable index survived, use it instead of losing all indexed tools and
+            // falling back to raw reads. Covers both the lock / already-running case
+            // and any generic rebuild failure the binary recovered from.
+            const lockCase = errMsg.includes("lock") || errMsg.includes("already running");
+            const count = parseFileCount(await this.exec(["--format", "json", "stats"]).catch(() => ""));
+            if (count > 0 && count <= AstIndexClient.MAX_INDEX_FILES) {
+                this.indexed = true;
+                console.error(lockCase
+                    ? `[token-pilot] ast-index: using existing index (${count} files, rebuild skipped due to lock)`
+                    : `[token-pilot] ast-index: rebuild failed but previous index preserved (${count} files) — using it`);
+                return;
+            }
+            if (count > AstIndexClient.MAX_INDEX_FILES) {
+                return this.handleOversizedIndex(count);
             }
             console.error(`[token-pilot] ast-index: rebuild failed — ${errMsg}`);
             throw buildErr;
@@ -328,6 +334,80 @@ export class AstIndexClient {
             return [];
         }
     }
+    async explore(query, options) {
+        await this.ensureIndex();
+        const empty = {
+            query,
+            dominantLanguage: "",
+            symbols: [],
+            files: [],
+            neighbours: [],
+            tests: [],
+        };
+        const args = ["explore", query, "--format", "json"];
+        if (options?.maxFiles)
+            args.push("-f", String(options.maxFiles));
+        // Default graph ON — call/inheritance blast-radius is the value-add;
+        // callers opt out with graph: false.
+        if (options?.graph !== false)
+            args.push("--rwr");
+        try {
+            const result = await this.exec(args);
+            const parsed = JSON.parse(result);
+            return {
+                query: typeof parsed.query === "string" ? parsed.query : query,
+                dominantLanguage: typeof parsed.dominant_language === "string"
+                    ? parsed.dominant_language
+                    : "",
+                symbols: Array.isArray(parsed.symbols)
+                    ? parsed.symbols.map((s) => ({
+                        name: s.name,
+                        kind: s.kind,
+                        path: s.path,
+                        line: s.line,
+                        score: s.score,
+                        vendor: s.vendor === true,
+                    }))
+                    : [],
+                files: Array.isArray(parsed.files)
+                    ? parsed.files.map((f) => ({
+                        path: f.path,
+                        line: f.line,
+                        source: f.source,
+                    }))
+                    : [],
+                neighbours: Array.isArray(parsed.neighbours)
+                    ? parsed.neighbours.map((n) => ({
+                        name: n.name,
+                        kind: n.kind,
+                        path: n.path,
+                        line: n.line,
+                        link: n.link,
+                    }))
+                    : [],
+                tests: Array.isArray(parsed.tests)
+                    ? parsed.tests.map((t) => ({
+                        source: t.source,
+                        tests: Array.isArray(t.tests) ? t.tests : [],
+                    }))
+                    : [],
+            };
+        }
+        catch (err) {
+            const msg = err instanceof Error ? err.message : String(err);
+            console.error(`[token-pilot] ast-index explore failed: ${msg}`);
+            // `explore` landed in ast-index 3.48. An older resolved binary reports
+            // "unrecognized subcommand 'explore'" — surface that instead of an
+            // indistinguishable empty result, so the caller knows to update.
+            if (/unrecognized subcommand|unexpected argument/.test(msg)) {
+                return {
+                    ...empty,
+                    error: "explore requires ast-index >= 3.48 — update the binary",
+                };
+            }
+            return empty;
+        }
+    }
     async implementations(name) {
         await this.ensureIndex();
         try {

package/dist/ast-index/types.d.ts

@@ -208,4 +208,73 @@ export interface AstIndexModuleApi {
     file: string;
     line: number;
 }
+/** ast-index explore — one ranked symbol */
+export interface AstIndexExploreSymbol {
+    name: string;
+    kind: string;
+    path: string;
+    line: number;
+    score: number;
+    vendor: boolean;
+}
+/** ast-index explore — one ranked file head (source is line-numbered) */
+export interface AstIndexExploreFile {
+    path: string;
+    line: number;
+    source: string;
+}
+/** ast-index explore — one graph neighbour (blast radius, requires --rwr) */
+export interface AstIndexExploreNeighbour {
+    name: string;
+    kind: string;
+    path: string;
+    line: number;
+    /** "caller" | "subclass" | string */
+    link: string;
+}
+/** ast-index explore — tests grouped by source file */
+export interface AstIndexExploreTestGroup {
+    source: string;
+    tests: string[];
+}
+/** ast-index explore — mapped result */
+export interface AstIndexExploreResult {
+    query: string;
+    dominantLanguage: string;
+    symbols: AstIndexExploreSymbol[];
+    files: AstIndexExploreFile[];
+    neighbours: AstIndexExploreNeighbour[];
+    tests: AstIndexExploreTestGroup[];
+    /** Set when the run failed (e.g. binary too old for `explore`). */
+    error?: string;
+}
+/** ast-index explore — raw json shape from the binary (snake_case) */
+export interface AstIndexExploreRaw {
+    query?: string;
+    dominant_language?: string;
+    symbols?: Array<{
+        name: string;
+        kind: string;
+        path: string;
+        line: number;
+        score: number;
+        vendor?: boolean;
+    }>;
+    files?: Array<{
+        path: string;
+        line: number;
+        source: string;
+    }>;
+    neighbours?: Array<{
+        name: string;
+        kind: string;
+        path: string;
+        line: number;
+        link: string;
+    }>;
+    tests?: Array<{
+        source: string;
+        tests?: string[];
+    }>;
+}
 //# sourceMappingURL=types.d.ts.map

package/dist/core/event-log.d.ts

@@ -56,6 +56,13 @@ export interface HookEvent {
      * Optional — absent when no workflow is active.
      */
     workflow_id?: string;
+    /**
+     * Loom spine link — id of the Loom task this event belongs to, when the
+     * session was launched by Loom (LOOM_TASK_ID set). Lets Loom attribute token
+     * savings to a task exactly. Optional — absent outside Loom, so standalone
+     * token-pilot events stay byte-identical to before.
+     */
+    task_id?: string;
     event: "denied" | "allowed" | "bypass" | "pass-through" | "task" | "diagnostic" | string;
     file: string;
     lines: number;

package/dist/core/event-log.js

@@ -115,8 +115,16 @@ export async function appendEvent(projectRoot, event) {
         const wf = event.workflow_id ??
             process.env.TOKEN_PILOT_WORKFLOW_ID ??
             process.env.CLAUDE_CODE_WORKFLOW_ID ??
+            process.env.LOOM_WORKFLOW_ID ??
             undefined;
-        const tagged = wf ? { ...event, workflow_id: wf } : event;
+        // Loom spine: tag the task id when the session was launched by Loom.
+        // Env-driven so call sites stay unchanged; absent outside Loom → no field.
+        const taskId = event.task_id ?? process.env.LOOM_TASK_ID ?? undefined;
+        let tagged = event;
+        if (wf)
+            tagged = { ...tagged, workflow_id: wf };
+        if (taskId)
+            tagged = { ...tagged, task_id: taskId };
         await ensureLogDir(projectRoot);
         await rotateIfNeeded(projectRoot);
         const line = JSON.stringify(tagged) + "\n";

package/dist/core/validation.d.ts

@@ -179,6 +179,12 @@ export interface ExploreAreaArgs {
     include?: Array<"outline" | "imports" | "tests" | "changes">;
 }
 export declare function validateExploreAreaArgs(args: unknown): ExploreAreaArgs;
+export interface ExploreArgs {
+    query: string;
+    max_files?: number;
+    graph?: boolean;
+}
+export declare function validateExploreArgs(args: unknown): ExploreArgs;
 export interface SmartLogArgs {
     path?: string;
     count?: number;

package/dist/core/validation.js

@@ -533,6 +533,24 @@ export function validateExploreAreaArgs(args) {
     }
     return { path: a.path };
 }
+export function validateExploreArgs(args) {
+    if (!args || typeof args !== "object") {
+        throw new Error('Arguments must be an object with a "query" parameter.');
+    }
+    const a = args;
+    if (typeof a.query !== "string" || a.query.length === 0) {
+        throw new Error('Required parameter "query" must be a non-empty string.');
+    }
+    const max_files = optionalNumber(a.max_files, "max_files");
+    if (max_files !== undefined && max_files < 1) {
+        throw new Error('"max_files" must be at least 1.');
+    }
+    return {
+        query: a.query,
+        max_files,
+        graph: optionalBool(a.graph, "graph"),
+    };
+}
 export function validateSmartLogArgs(args) {
     if (!args || typeof args !== "object")
         return {};

package/dist/handlers/explore.d.ts

@@ -0,0 +1,17 @@
+import type { AstIndexClient } from "../ast-index/client.js";
+import type { ExploreArgs } from "../core/validation.js";
+export interface ExploreMeta {
+    query: string;
+    symbolCount: number;
+    fileCount: number;
+    neighbourCount: number;
+    testCount: number;
+}
+export declare function handleExplore(args: ExploreArgs, projectRoot: string, astIndex: AstIndexClient): Promise<{
+    content: Array<{
+        type: "text";
+        text: string;
+    }>;
+    meta: ExploreMeta;
+}>;
+//# sourceMappingURL=explore.d.ts.map

package/dist/handlers/explore.js

@@ -0,0 +1,90 @@
+// ──────────────────────────────────────────────
+// Constants
+// ──────────────────────────────────────────────
+const MAX_RANKED_SYMBOLS = 12;
+// ──────────────────────────────────────────────
+// Handler — one-shot ranked context + graph blast-radius.
+// Mirrors the shape of handleExploreArea: build a compact, token-efficient
+// text block and return it with lightweight meta.
+// ──────────────────────────────────────────────
+export async function handleExplore(args, projectRoot, astIndex) {
+    void projectRoot; // explore runs against the index root, not a path
+    const result = await astIndex.explore(args.query, {
+        maxFiles: args.max_files,
+        graph: args.graph,
+    });
+    const lines = [];
+    lines.push(`# explore: "${result.query}"  (lang: ${result.dominantLanguage || "?"})`);
+    // Ranked symbols
+    if (result.symbols.length > 0) {
+        lines.push("");
+        lines.push("## Ranked symbols");
+        for (const s of result.symbols.slice(0, MAX_RANKED_SYMBOLS)) {
+            const vendorTag = s.vendor ? " [vendor]" : "";
+            lines.push(`${Math.round(s.score)}  ${s.kind} ${s.name}  ${s.path}:${s.line}${vendorTag}`);
+        }
+    }
+    // Source — file heads (source is already line-numbered)
+    if (result.files.length > 0) {
+        lines.push("");
+        lines.push("## Source");
+        for (const f of result.files) {
+            lines.push(`${f.path}:${f.line}`);
+            lines.push("```");
+            lines.push(f.source.replace(/\n+$/, ""));
+            lines.push("```");
+        }
+    }
+    // Graph neighbours (blast radius) — only with --rwr
+    if (result.neighbours.length > 0) {
+        lines.push("");
+        lines.push("## Graph neighbours (blast radius)");
+        for (const n of result.neighbours) {
+            lines.push(`${n.link}  ${n.kind} ${n.name}  ${n.path}:${n.line}`);
+        }
+    }
+    // Tests grouped by source
+    if (result.tests.length > 0) {
+        lines.push("");
+        lines.push("## Tests");
+        for (const t of result.tests) {
+            lines.push(`${t.source}:`);
+            for (const test of t.tests) {
+                lines.push(`  ${test}`);
+            }
+        }
+    }
+    const empty = result.symbols.length === 0 &&
+        result.files.length === 0 &&
+        result.neighbours.length === 0 &&
+        result.tests.length === 0;
+    if (empty) {
+        const reason = result.error ?? "No results — index unavailable or query matched nothing.";
+        return {
+            content: [
+                {
+                    type: "text",
+                    text: `# explore: "${result.query}"\n\n${reason}`,
+                },
+            ],
+            meta: {
+                query: result.query,
+                symbolCount: 0,
+                fileCount: 0,
+                neighbourCount: 0,
+                testCount: 0,
+            },
+        };
+    }
+    return {
+        content: [{ type: "text", text: lines.join("\n") }],
+        meta: {
+            query: result.query,
+            symbolCount: result.symbols.length,
+            fileCount: result.files.length,
+            neighbourCount: result.neighbours.length,
+            testCount: result.tests.reduce((n, t) => n + t.tests.length, 0),
+        },
+    };
+}
+//# sourceMappingURL=explore.js.map

package/dist/handlers/test-summary.js

@@ -73,6 +73,8 @@ export function detectRunner(command, output) {
         return 'rspec';
     if (cmd.includes('mocha'))
         return 'mocha';
+    if (cmd.includes('node --test') || cmd.includes('node:test'))
+        return 'node';
     // Detect from output
     const lower = output.toLowerCase();
     if (lower.includes('vitest') || lower.includes('vite'))
@@ -85,6 +87,9 @@ export function detectRunner(command, output) {
         return 'phpunit';
     if (lower.includes('--- fail:') || lower.includes('--- pass:') || lower.includes('ok  \t'))
         return 'go';
+    // node:test prints a TAP summary footer: "# tests N" + "# pass N" + "# fail N".
+    if (/^#\s*tests\s+\d+/m.test(output) && /^#\s*pass\s+\d+/m.test(output))
+        return 'node';
     return 'generic';
 }
 // ──────────────────────────────────────────────
@@ -103,6 +108,8 @@ export function parseTestOutput(output, runner) {
             return parseGoTest(output);
         case 'cargo':
             return parseCargoTest(output);
+        case 'node':
+            return parseNodeTest(output);
         default:
             return parseGeneric(output);
     }
@@ -243,6 +250,41 @@ function parseGoTest(output) {
     }
     return result;
 }
+function parseNodeTest(output) {
+    const result = { total: 0, passed: 0, failed: 0, skipped: 0, failures: [] };
+    // node:test (`node --test`) prints a TAP summary footer:
+    //   # tests 2
+    //   # pass 2
+    //   # fail 0
+    //   # skipped 0
+    const num = (re) => {
+        const m = output.match(re);
+        return m ? parseInt(m[1], 10) : null;
+    };
+    const pass = num(/^#\s*pass\s+(\d+)/m);
+    const fail = num(/^#\s*fail\s+(\d+)/m);
+    const skip = num(/^#\s*skipped\s+(\d+)/m);
+    const tests = num(/^#\s*tests\s+(\d+)/m);
+    if (pass !== null || fail !== null) {
+        result.passed = pass ?? 0;
+        result.failed = fail ?? 0;
+        result.skipped = skip ?? 0;
+        result.total = tests ?? result.passed + result.failed + result.skipped;
+    }
+    else {
+        // No footer (truncated output) — count the TAP point lines instead.
+        result.passed = (output.match(/^ok\s+\d+/gm) ?? []).length;
+        result.failed = (output.match(/^not ok\s+\d+/gm) ?? []).length;
+        result.total = result.passed + result.failed + result.skipped;
+    }
+    // Failure names come from the TAP point: "not ok 3 - the test name".
+    const failPattern = /^not ok\s+\d+\s*-\s*(.+)$/gm;
+    let match;
+    while ((match = failPattern.exec(output)) !== null) {
+        result.failures.push({ name: match[1].trim(), error: '' });
+    }
+    return result;
+}
 function parseCargoTest(output) {
     const result = { total: 0, passed: 0, failed: 0, skipped: 0, failures: [] };
     // test result: ok. 5 passed; 0 failed; 1 ignored; 0 measured; 0 filtered out

package/dist/server/tool-definitions.d.ts

@@ -100,6 +100,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -191,6 +194,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -276,6 +282,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -357,6 +366,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -429,6 +441,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -501,6 +516,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -597,6 +615,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -678,6 +699,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -768,6 +792,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -841,6 +868,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -910,6 +940,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -985,6 +1018,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -1054,6 +1090,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -1126,6 +1165,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -1201,6 +1243,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -1283,6 +1328,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -1356,6 +1404,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -1445,6 +1496,9 @@ export declare const TOOL_DEFINITIONS: ({
             pattern?: undefined;
             name?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -1521,6 +1575,9 @@ export declare const TOOL_DEFINITIONS: ({
             maxDepth?: undefined;
             viaKind?: undefined;
             format?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -1597,6 +1654,87 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
+            count?: undefined;
+            command?: undefined;
+            runner?: undefined;
+            timeout?: undefined;
+            goal?: undefined;
+            decisions?: undefined;
+            confirmed?: undefined;
+            files?: undefined;
+            blocked?: undefined;
+            next?: undefined;
+            sessionId?: undefined;
+        };
+        required: string[];
+    };
+} | {
+    name: string;
+    description: string;
+    inputSchema: {
+        type: "object";
+        properties: {
+            query: {
+                type: string;
+                description: string;
+            };
+            max_files: {
+                type: string;
+                description: string;
+            };
+            graph: {
+                type: string;
+                description: string;
+            };
+            path?: undefined;
+            show_imports?: undefined;
+            show_docs?: undefined;
+            depth?: undefined;
+            scope?: undefined;
+            max_tokens?: undefined;
+            session_id?: undefined;
+            force?: undefined;
+            symbol?: undefined;
+            context_before?: undefined;
+            context_after?: undefined;
+            show?: undefined;
+            include_edit_context?: undefined;
+            symbols?: undefined;
+            start_line?: undefined;
+            end_line?: undefined;
+            heading?: undefined;
+            context_lines?: undefined;
+            line?: undefined;
+            context?: undefined;
+            include_callers?: undefined;
+            include_tests?: undefined;
+            include_changes?: undefined;
+            section?: undefined;
+            paths?: undefined;
+            kind?: undefined;
+            limit?: undefined;
+            lang?: undefined;
+            mode?: undefined;
+            include?: undefined;
+            recursive?: undefined;
+            max_depth?: undefined;
+            verbose?: undefined;
+            module?: undefined;
+            export_only?: undefined;
+            check?: undefined;
+            pattern?: undefined;
+            name?: undefined;
+            from?: undefined;
+            to?: undefined;
+            all?: undefined;
+            maxPaths?: undefined;
+            maxDepth?: undefined;
+            viaKind?: undefined;
+            format?: undefined;
+            ref?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -1673,6 +1811,9 @@ export declare const TOOL_DEFINITIONS: ({
             maxDepth?: undefined;
             viaKind?: undefined;
             format?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             command?: undefined;
             runner?: undefined;
             timeout?: undefined;
@@ -1751,6 +1892,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             goal?: undefined;
             decisions?: undefined;
@@ -1847,6 +1991,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;
@@ -1911,6 +2058,9 @@ export declare const TOOL_DEFINITIONS: ({
             viaKind?: undefined;
             format?: undefined;
             ref?: undefined;
+            query?: undefined;
+            max_files?: undefined;
+            graph?: undefined;
             count?: undefined;
             command?: undefined;
             runner?: undefined;

package/dist/server/tool-definitions.js

@@ -670,6 +670,28 @@ export const TOOL_DEFINITIONS = [
             required: ["path"],
         },
     },
+    {
+        name: "explore",
+        description: "One-shot ranked context + call/inheritance graph blast-radius for a query. Returns ranked symbols, the source heads of the top-ranked files, graph neighbours (callers + subclasses — the blast radius), and related test files in a single compact block. Use INSTEAD OF separate find_usages + read_symbol + call_tree when you need to understand an area fast — cheaper than chaining those three.",
+        inputSchema: {
+            type: "object",
+            properties: {
+                query: {
+                    type: "string",
+                    description: "Search terms (the binary splits the string into terms itself), e.g. \"AstIndexClient buildIndex\"",
+                },
+                max_files: {
+                    type: "number",
+                    description: "Cap on the number of source file heads returned (default: binary's own limit)",
+                },
+                graph: {
+                    type: "boolean",
+                    description: "Include call/inheritance graph neighbours (blast radius). Default: true. Set false to skip the graph walk.",
+                },
+            },
+            required: ["query"],
+        },
+    },
     {
         name: "smart_log",
         description: "Use INSTEAD OF raw git log. Structured commit history with category detection (feat/fix/refactor/docs), file stats, author breakdown. Filters by path and ref. HEADS UP: two verification runs measured this tool at ~39% token reduction (borderline — vs 95-99% for outline/smart_diff). Cumulative data being gathered — tool may be dropped or redesigned in v0.30.0 if numbers don't improve. Prefer scoping with `path` or `count` to tighten savings.",

package/dist/server/tool-profiles.js

@@ -60,6 +60,7 @@ export const NAV_TOOLS = new Set([
     "module_info",
     "related_files",
     "explore_area",
+    "explore",
     "smart_log",
     "smart_diff",
     "read_section", // v0.30.0: section reading is nav-class (read-only, no edit prep)

package/dist/server.js

@@ -38,6 +38,7 @@ import { handleModuleInfo } from "./handlers/module-info.js";
 import { handleModuleRoute } from "./handlers/module-route.js";
 import { handleSmartDiff } from "./handlers/smart-diff.js";
 import { handleExploreArea } from "./handlers/explore-area.js";
+import { handleExplore } from "./handlers/explore.js";
 import { handleSmartLog } from "./handlers/smart-log.js";
 import { handleTestSummary } from "./handlers/test-summary.js";
 import { handleSessionSnapshot } from "./handlers/session-snapshot.js";
@@ -52,7 +53,7 @@ import { getMcpInstructions, TOOL_DEFINITIONS, } from "./server/tool-definitions
 import { filterToolsByProfile, parseProfileEnv, } from "./server/tool-profiles.js";
 import { STRICT_SMART_READ_MAX_TOKENS, STRICT_EXPLORE_AREA_INCLUDE, } from "./server/enforcement-mode.js";
 import { createTokenEstimates } from "./server/token-estimates.js";
-import { validateSmartReadArgs, validateReadSymbolArgs, validateReadSymbolsArgs, validateReadRangeArgs, validateReadDiffArgs, validateFindUsagesArgs, validateSmartReadManyArgs, validateReadForEditArgs, validateRelatedFilesArgs, validateOutlineArgs, validateFindUnusedArgs, validateCallTreeArgs, validateCodeAuditArgs, validateProjectOverviewArgs, validateModuleInfoArgs, validateModuleRouteArgs, validateSmartDiffArgs, validateExploreAreaArgs, validateSmartLogArgs, validateTestSummaryArgs, validateReadSectionArgs, } from "./core/validation.js";
+import { validateSmartReadArgs, validateReadSymbolArgs, validateReadSymbolsArgs, validateReadRangeArgs, validateReadDiffArgs, validateFindUsagesArgs, validateSmartReadManyArgs, validateReadForEditArgs, validateRelatedFilesArgs, validateOutlineArgs, validateFindUnusedArgs, validateCallTreeArgs, validateCodeAuditArgs, validateProjectOverviewArgs, validateModuleInfoArgs, validateModuleRouteArgs, validateSmartDiffArgs, validateExploreAreaArgs, validateExploreArgs, validateSmartLogArgs, validateTestSummaryArgs, validateReadSectionArgs, } from "./core/validation.js";
 export async function createServer(projectRoot, options) {
     const mode = options?.enforcementMode ?? "deny";
     // v0.43.0 — the real Claude Code session id. CC exports it to every
@@ -967,6 +968,40 @@ export async function createServer(projectRoot, options) {
                     }
                     return eaResult;
                 }
+                case "explore": {
+                    const exArgs = validateExploreArgs(args);
+                    const cachedEx = sessionCache?.get("explore", exArgs);
+                    if (cachedEx) {
+                        recordWithTrace({
+                            tool: "explore",
+                            path: exArgs.query,
+                            tokensReturned: cachedEx.tokenEstimate,
+                            tokensWouldBe: cachedEx.tokensWouldBe ?? cachedEx.tokenEstimate,
+                            timestamp: Date.now(),
+                            sessionCacheHit: true,
+                            savingsCategory: "cache",
+                            args: exArgs,
+                        });
+                        return cachedEx.result;
+                    }
+                    const exResult = await handleExplore(exArgs, projectRoot, astIndex);
+                    const exText = exResult.content[0]?.text ?? "";
+                    const exTokens = estimateTokens(exText);
+                    // explore replaces a find_usages + read_symbol + call_tree chain;
+                    // approximate that baseline as ~3x the compacted output.
+                    const exWouldBe = exTokens * 3;
+                    sessionCache?.set("explore", exArgs, exResult, { dependsOnAst: true }, exTokens, exWouldBe || exTokens);
+                    recordWithTrace({
+                        tool: "explore",
+                        path: exArgs.query,
+                        tokensReturned: exTokens,
+                        tokensWouldBe: exWouldBe || exTokens,
+                        timestamp: Date.now(),
+                        savingsCategory: "compression",
+                        args: exArgs,
+                    });
+                    return exResult;
+                }
                 case "smart_log": {
                     const slArgs = validateSmartLogArgs(args);
                     // v0.30.0 strict mode: bound count to 20 when caller didn't set it.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "token-pilot",
-  "version": "0.46.0",
+  "version": "0.47.0",
   "description": "Save up to 80% tokens when AI reads code — MCP server for token-efficient code navigation, AST-aware structural reading instead of dumping full files into context window",
   "type": "module",
   "main": "dist/index.js",
@@ -67,15 +67,15 @@
   "mcpName": "io.github.Digital-Threads/token-pilot",
   "license": "MIT",
   "dependencies": {
+    "@ast-index/cli": "^3.48.1",
     "@modelcontextprotocol/sdk": "^1.12.0",
-    "@ast-index/cli": "^3.44.0",
     "chokidar": "^4.0.3"
   },
   "devDependencies": {
-    "@vitest/coverage-v8": "^3.2.4",
     "@types/node": "^22.0.0",
+    "@vitest/coverage-v8": "^4.1.8",
     "typescript": "^5.7.0",
-    "vitest": "^3.0.0"
+    "vitest": "^4.1.8"
   },
   "engines": {
     "node": ">=18.0.0"