claude-eidetic 0.1.2 → 0.1.3

package/README.md

@@ -1,333 +1,333 @@
-# claude-eidetic
-
-
-[![tests](https://img.shields.io/github/actions/workflow/status/eidetics/claude-eidetic/ci.yml?style=flat-square&label=tests)](https://github.com/eidetics/claude-eidetic/actions/workflows/ci.yml)
-[![npm](https://img.shields.io/npm/v/claude-eidetic)](https://www.npmjs.com/package/claude-eidetic)
-[![MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
-
-Semantic code search, persistent memory, and session continuity for Claude Code. One plugin, not three.
-
----
-
-## 🚀 Quick Start
-
-```bash
-claude plugin install eidetics/claude-eidetic
-```
-
-```bash
-export OPENAI_API_KEY=sk-...         # for embeddings (default)
-export ANTHROPIC_API_KEY=sk-ant-...  # for memory extraction (default)
-```
-
-Index your codebase once, then search by meaning:
-
-```
-index_codebase(path="/your/project")
-search_code("how does authentication work")
-```
-
----
-
-## ✨ Features
-
-### 🔍 Semantic Code Search
-
-**Find code by meaning, not keywords.** Search across your entire codebase with natural language, returning the most relevant functions and classes, not a list of files to read.
-
-```
-search_code("how does the retry logic work")
-search_code("authentication middleware", extensionFilter=[".ts"])
-search_code(project="backend", query="auth flow")
-```
-
-### 🏗️ Architecture at a Glance
-
-**Get every class, function, and method in one call.** `browse_structure` returns a condensed map of your codebase with signatures, grouped by file, replacing a Glob + Read cascade with a single tool call.
-
-```
-browse_structure(path="/my/project", kind="class")
-list_symbols(path="/my/project", nameFilter="handle")
-```
-
-### 📚 Documentation Cache
-
-**Fetch docs once, search them forever.** Cache external documentation as searchable embeddings. Retrieve relevant passages instantly, far cheaper than re-fetching the same page each session.
-
-```
-index_document(content=..., library="react", topic="hooks", source="https://...")
-search_documents("React useCallback dependencies", library="react")
-```
-
-### 🧠 Persistent Memory
-
-**Claude remembers your preferences between sessions.** `add_memory` uses an LLM to extract structured facts from conversation text (coding style, architecture decisions, debugging insights) and deduplicates them semantically. Not a static config file you forget to update.
-
-```
-add_memory("Always use absolute imports, never relative")
-search_memory("how does this team handle errors")
-```
-
-### 🔄 Session Continuity
-
-**Every session picks up where the last one left off.** When a session ends (or context compacts mid-session), Eidetic automatically writes a structured note capturing files changed, tasks, commands, and decisions. `/catchup` at the start of a new session reconstructs exactly where you were. No user action required.
-
-### 👻 Invisible Optimizations
-
-Eight hook events fire automatically, nudging toward cheaper tools, redirecting file reads for 15-20% token savings, tracking changed files, and saving session state on exit.
-
-<details>
-<summary><strong>Hook event details</strong></summary>
-
-| Hook | Trigger | What it does |
-|---|---|---|
-| `SessionStart` | Session opens | Validates config, injects last-session context |
-| `UserPromptSubmit` | Every message | Nudges toward `search_code` over Grep/Explore for conceptual queries |
-| `PreToolUse` (Read) | Before every Read | Blocks Read for text files, redirects to `read_file` for 15-20% token savings |
-| `PreToolUse` (WebFetch / query-docs) | Before doc fetches | Suggests `search_documents` if library is cached (allows fetch either way) |
-| `PostToolUse` (Write / Edit) | After every file write | Tracks changed files in a shadow git index |
-| `Stop` | After Claude responds | Commits shadow index; triggers targeted re-index of changed files only |
-| `PreCompact` | Before context compaction | Captures session state to notes before memory is lost |
-| `SessionEnd` | Session closes | Writes session note (files, tasks, commands); extracts developer memories via LLM |
-
-</details>
-
----
-
-## 🗺️ When to Use What
-
-| Need | Use | Notes |
-|---|---|---|
-| Find implementations by concept | `search_code` | Semantic, natural language queries |
-| Exact string or regex match | Grep | Grep wins for exact matches |
-| Find file by exact name | Glob | Glob wins for name patterns |
-| Understand module structure | `browse_structure` | One call vs Glob + Read cascade |
-| Read a specific known file | `read_file` | Cheaper than built-in Read for code files |
-| Search cached documentation | `search_documents` | Far cheaper than re-fetching |
-| Recall project conventions | `search_memory` | Global across all projects and sessions |
-
----
-
-## 📖 Skills Reference
-
-| Skill | What it does |
-|---|---|
-| `/search` | Guided semantic search with best-practice prompts |
-| `/index` | Index or re-index a codebase with dry-run option |
-| `/cache-docs` | Fetch and cache external documentation |
-| `/catchup` | Search session notes and reconstruct where you left off |
-| `/wrapup` | Extract decisions, rationale, open questions, and next actions from the conversation |
-
----
-
-<details>
-<summary><strong>🔥 Why does this exist? (The Problem)</strong></summary>
-
-Every new Claude Code session starts cold. You re-explain the architecture. You re-fetch the same docs. Claude reads the same files repeatedly, burning tokens just to get back to where you were.
-
-| Task | Without Eidetic | With Eidetic |
-|---|---|---|
-| Find where auth errors are handled | Grep cascade, read 8 files, ~10,700 tokens | `search_code("auth error handling")` ~220 tokens |
-| Resume after context compaction | Re-explain 20 min of context, ~2,000 tokens | `/catchup` ~200 tokens |
-| Look up React hooks docs | Fetch docs page, ~5,000 tokens | `search_documents("React useEffect")` ~20 tokens |
-| Read a 400-line file | Built-in Read with line numbers, ~900 tokens | `read_file(path)` ~740 tokens |
-
-</details>
-
----
-
-## 📦 Installation
-
-### Plugin (recommended)
-
-```bash
-claude plugin install eidetics/claude-eidetic
-```
-
-The plugin auto-starts the MCP server, installs skills, and configures hooks.
-
-### npx (manual MCP config)
-
-Add to your `.mcp.json`:
-
-```json
-{
-  "mcpServers": {
-    "claude-eidetic": {
-      "command": "npx",
-      "args": ["-y", "claude-eidetic"],
-      "env": {
-        "OPENAI_API_KEY": "sk-...",
-        "ANTHROPIC_API_KEY": "sk-ant-..."
-      }
-    }
-  }
-}
-```
-
-`ANTHROPIC_API_KEY` is needed for the memory LLM (default provider). Omit it if using `MEMORY_LLM_PROVIDER=openai` or `ollama`.
-
-### Global install
-
-```bash
-npm install -g claude-eidetic
-```
-
-### From source
-
-```bash
-git clone https://github.com/eidetics/claude-eidetic
-cd claude-eidetic
-npm install && npx tsc && npm start
-```
-
-### Requirements
-
-- Node.js >= 20.0.0
-- An API key (OpenAI for embeddings, Anthropic for memory extraction, or Ollama for both free)
-- Docker (optional): Qdrant auto-provisions via Docker if not already running
-- C/C++ build tools: required by tree-sitter native bindings (`node-gyp`)
-
----
-
-## ⚙️ Configuration
-
-All configuration is via environment variables. No config files.
-
-### Using Ollama (free, local)
-
-```bash
-export EMBEDDING_PROVIDER=ollama
-export MEMORY_LLM_PROVIDER=ollama
-# No API keys needed
-```
-
-<details>
-<summary><strong>Full configuration reference</strong></summary>
-
-| Variable | Default | Description |
-|---|---|---|
-| `OPENAI_API_KEY` | _(required for openai)_ | OpenAI API key for embeddings and/or memory |
-| `ANTHROPIC_API_KEY` | _(required for anthropic memory)_ | Anthropic API key for memory LLM |
-| `EMBEDDING_PROVIDER` | `openai` | `openai`, `ollama`, or `local` |
-| `EMBEDDING_MODEL` | `text-embedding-3-small` (openai) / `nomic-embed-text` (ollama) | Embedding model name |
-| `EMBEDDING_BATCH_SIZE` | `100` | Batch size for embedding requests (1-2048) |
-| `INDEXING_CONCURRENCY` | `8` | Parallel file indexing workers (1-32) |
-| `OPENAI_BASE_URL` | _(none)_ | Custom OpenAI-compatible endpoint |
-| `OLLAMA_BASE_URL` | `http://localhost:11434/v1` | Ollama server URL |
-| `VECTORDB_PROVIDER` | `qdrant` | `qdrant` or `milvus` |
-| `QDRANT_URL` | `http://localhost:6333` | Qdrant server URL |
-| `QDRANT_API_KEY` | _(none)_ | Qdrant API key (for remote/cloud instances) |
-| `MILVUS_ADDRESS` | `localhost:19530` | Milvus server address |
-| `MILVUS_TOKEN` | _(none)_ | Milvus authentication token |
-| `EIDETIC_DATA_DIR` | `~/.eidetic/` | Data root for snapshots, memory DB, registry |
-| `CUSTOM_EXTENSIONS` | `[]` | JSON array of extra file extensions to index (e.g., `[".dart",".arb"]`) |
-| `CUSTOM_IGNORE_PATTERNS` | `[]` | JSON array of glob patterns to exclude |
-| `MEMORY_LLM_PROVIDER` | `anthropic` | `anthropic`, `openai`, or `ollama` |
-| `MEMORY_LLM_MODEL` | `claude-haiku-4-5-20251001` (anthropic) / `gpt-4o-mini` (openai) / `llama3.2` (ollama) | Model for memory extraction |
-| `MEMORY_LLM_BASE_URL` | _(none)_ | Custom base URL for memory LLM |
-| `MEMORY_LLM_API_KEY` | _(none)_ | API key override for memory LLM |
-
-</details>
-
----
-
-<details>
-<summary><strong>🔧 Tool Reference</strong></summary>
-
-### 🔍 Code Search
-
-| Tool | Description |
-|---|---|
-| `search_code` | Hybrid semantic search over indexed codebase. Returns compact results by default. |
-| `index_codebase` | Index a directory. Supports `dryRun`, `force`, `customExtensions`, `customIgnorePatterns`. |
-| `list_indexed` | List all indexed codebases with file/chunk counts and status. |
-| `get_indexing_status` | Check indexing progress for a path or project. |
-| `clear_index` | Remove the search index for a codebase. |
-| `cleanup_vectors` | Remove orphaned vectors for deleted files. No re-embedding cost. |
-| `browse_structure` | Condensed structural map: classes, functions, methods with signatures, grouped by file. |
-| `list_symbols` | Compact symbol table with name/kind/file/line. Supports name, kind, and path filters. |
-
-### 📄 File Reading
-
-| Tool | Description |
-|---|---|
-| `read_file` | Read file without line-number overhead. Cheaper than built-in Read for code files. |
-
-### 📚 Documentation Cache
-
-| Tool | Description |
-|---|---|
-| `index_document` | Cache external documentation for semantic search. Supports TTL for staleness tracking. |
-| `search_documents` | Search cached docs. Far cheaper than re-fetching the same page. |
-
-### 🧠 Memory
-
-| Tool | Description |
-|---|---|
-| `add_memory` | LLM-extracted facts from text. Auto-deduplicates. Seven categories. |
-| `search_memory` | Semantic search over stored memories. Filterable by category. |
-| `list_memories` | List all memories, optionally filtered by category. |
-| `delete_memory` | Delete a specific memory by UUID. |
-| `memory_history` | View change history for a memory (additions, updates, deletions). |
-
-</details>
-
----
-
-## 🌐 Supported Languages
-
-**AST-aware** (functions and classes chunked intact):
-
-<p>
-  <img src="https://img.shields.io/badge/JavaScript-F7DF1E?style=flat-square&logo=javascript&logoColor=black" alt="JavaScript"/>
-  <img src="https://img.shields.io/badge/TypeScript-3178C6?style=flat-square&logo=typescript&logoColor=white" alt="TypeScript"/>
-  <img src="https://img.shields.io/badge/React_(JSX/TSX)-61DAFB?style=flat-square&logo=react&logoColor=black" alt="JSX/TSX"/>
-  <img src="https://img.shields.io/badge/Python-3776AB?style=flat-square&logo=python&logoColor=white" alt="Python"/>
-  <img src="https://img.shields.io/badge/Go-00ADD8?style=flat-square&logo=go&logoColor=white" alt="Go"/>
-  <img src="https://img.shields.io/badge/Java-ED8B00?style=flat-square&logo=openjdk&logoColor=white" alt="Java"/>
-  <img src="https://img.shields.io/badge/Rust-000000?style=flat-square&logo=rust&logoColor=white" alt="Rust"/>
-  <img src="https://img.shields.io/badge/C-A8B9CC?style=flat-square&logo=c&logoColor=black" alt="C"/>
-  <img src="https://img.shields.io/badge/C++-00599C?style=flat-square&logo=cplusplus&logoColor=white" alt="C++"/>
-  <img src="https://img.shields.io/badge/C%23-512BD4?style=flat-square&logo=csharp&logoColor=white" alt="C#"/>
-</p>
-
-**Line-based fallback** (sliding window chunking for everything else):
-
-<p>
-  <img src="https://img.shields.io/badge/Markdown-000000?style=flat-square&logo=markdown&logoColor=white" alt="Markdown"/>
-  <img src="https://img.shields.io/badge/YAML-CB171E?style=flat-square&logo=yaml&logoColor=white" alt="YAML"/>
-  <img src="https://img.shields.io/badge/JSON-000000?style=flat-square&logo=json&logoColor=white" alt="JSON"/>
-  <img src="https://img.shields.io/badge/Ruby-CC342D?style=flat-square&logo=ruby&logoColor=white" alt="Ruby"/>
-  <img src="https://img.shields.io/badge/PHP-777BB4?style=flat-square&logo=php&logoColor=white" alt="PHP"/>
-  <img src="https://img.shields.io/badge/Swift-F05138?style=flat-square&logo=swift&logoColor=white" alt="Swift"/>
-  <img src="https://img.shields.io/badge/Kotlin-7F52FF?style=flat-square&logo=kotlin&logoColor=white" alt="Kotlin"/>
-  <img src="https://img.shields.io/badge/and_more...-30363d?style=flat-square" alt="and more"/>
-</p>
-
----
-
-## 🛠️ Development
-
-```bash
-npm install && npx tsc    # install and build
-npm run dev               # watch mode (tsx)
-npm test                  # unit tests (no external services needed)
-npm run test:integration  # requires Qdrant at localhost:6333 + OPENAI_API_KEY
-```
-
-**Commit format:** `type(scope): description`
-Types: `feat`, `fix`, `docs`, `refactor`, `perf`, `chore`, `test`
-Scopes: `embedding`, `vectordb`, `splitter`, `indexer`, `mcp`, `infra`, `config`
-
----
-
-## 🙏 Acknowledgements
-
-Heavily inspired by [mem0](https://github.com/mem0ai/mem0), [claude-mem](https://github.com/thedotmack/claude-mem), and [claude-context](https://github.com/zilliztech/claude-context). Documentation retrieval powered by [context7](https://github.com/upstash/context7).
-
----
-
-## 📄 License
-
-MIT
+# claude-eidetic
+
+
+[![tests](https://img.shields.io/github/actions/workflow/status/eidetics/claude-eidetic/ci.yml?style=flat-square&label=tests)](https://github.com/eidetics/claude-eidetic/actions/workflows/ci.yml)
+[![npm](https://img.shields.io/npm/v/claude-eidetic)](https://www.npmjs.com/package/claude-eidetic)
+[![MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
+
+Semantic code search, persistent memory, and session continuity for Claude Code. One plugin, not three.
+
+---
+
+## 🚀 Quick Start
+
+```bash
+claude plugin install eidetics/claude-eidetic
+```
+
+```bash
+export OPENAI_API_KEY=sk-...         # for embeddings (default)
+export ANTHROPIC_API_KEY=sk-ant-...  # for memory extraction (default)
+```
+
+Index your codebase once, then search by meaning:
+
+```
+index_codebase(path="/your/project")
+search_code("how does authentication work")
+```
+
+---
+
+## ✨ Features
+
+### 🔍 Semantic Code Search
+
+**Find code by meaning, not keywords.** Search across your entire codebase with natural language, returning the most relevant functions and classes, not a list of files to read.
+
+```
+search_code("how does the retry logic work")
+search_code("authentication middleware", extensionFilter=[".ts"])
+search_code(project="backend", query="auth flow")
+```
+
+### 🏗️ Architecture at a Glance
+
+**Get every class, function, and method in one call.** `browse_structure` returns a condensed map of your codebase with signatures, grouped by file, replacing a Glob + Read cascade with a single tool call.
+
+```
+browse_structure(path="/my/project", kind="class")
+list_symbols(path="/my/project", nameFilter="handle")
+```
+
+### 📚 Documentation Cache
+
+**Fetch docs once, search them forever.** Cache external documentation as searchable embeddings. Retrieve relevant passages instantly, far cheaper than re-fetching the same page each session.
+
+```
+index_document(content=..., library="react", topic="hooks", source="https://...")
+search_documents("React useCallback dependencies", library="react")
+```
+
+### 🧠 Persistent Memory
+
+**Claude remembers your preferences between sessions.** `add_memory` uses an LLM to extract structured facts from conversation text (coding style, architecture decisions, debugging insights) and deduplicates them semantically. Not a static config file you forget to update.
+
+```
+add_memory("Always use absolute imports, never relative")
+search_memory("how does this team handle errors")
+```
+
+### 🔄 Session Continuity
+
+**Every session picks up where the last one left off.** When a session ends (or context compacts mid-session), Eidetic automatically writes a structured note capturing files changed, tasks, commands, and decisions. `/catchup` at the start of a new session reconstructs exactly where you were. No user action required.
+
+### 👻 Invisible Optimizations
+
+Eight hook events fire automatically, nudging toward cheaper tools, redirecting file reads for 15-20% token savings, tracking changed files, and saving session state on exit.
+
+<details>
+<summary><strong>Hook event details</strong></summary>
+
+| Hook | Trigger | What it does |
+|---|---|---|
+| `SessionStart` | Session opens | Validates config, injects last-session context |
+| `UserPromptSubmit` | Every message | Nudges toward `search_code` over Grep/Explore for conceptual queries |
+| `PreToolUse` (Read) | Before every Read | Blocks Read for text files, redirects to `read_file` for 15-20% token savings |
+| `PreToolUse` (WebFetch / query-docs) | Before doc fetches | Suggests `search_documents` if library is cached (allows fetch either way) |
+| `PostToolUse` (Write / Edit) | After every file write | Tracks changed files in a shadow git index |
+| `Stop` | After Claude responds | Commits shadow index; triggers targeted re-index of changed files only |
+| `PreCompact` | Before context compaction | Captures session state to notes before memory is lost |
+| `SessionEnd` | Session closes | Writes session note (files, tasks, commands); extracts developer memories via LLM |
+
+</details>
+
+---
+
+## 🗺️ When to Use What
+
+| Need | Use | Notes |
+|---|---|---|
+| Find implementations by concept | `search_code` | Semantic, natural language queries |
+| Exact string or regex match | Grep | Grep wins for exact matches |
+| Find file by exact name | Glob | Glob wins for name patterns |
+| Understand module structure | `browse_structure` | One call vs Glob + Read cascade |
+| Read a specific known file | `read_file` | Cheaper than built-in Read for code files |
+| Search cached documentation | `search_documents` | Far cheaper than re-fetching |
+| Recall project conventions | `search_memory` | Global across all projects and sessions |
+
+---
+
+## 📖 Skills Reference
+
+| Skill | What it does |
+|---|---|
+| `/search` | Guided semantic search with best-practice prompts |
+| `/index` | Index or re-index a codebase with dry-run option |
+| `/cache-docs` | Fetch and cache external documentation |
+| `/catchup` | Search session notes and reconstruct where you left off |
+| `/wrapup` | Extract decisions, rationale, open questions, and next actions from the conversation |
+
+---
+
+<details>
+<summary><strong>🔥 Why does this exist? (The Problem)</strong></summary>
+
+Every new Claude Code session starts cold. You re-explain the architecture. You re-fetch the same docs. Claude reads the same files repeatedly, burning tokens just to get back to where you were.
+
+| Task | Without Eidetic | With Eidetic |
+|---|---|---|
+| Find where auth errors are handled | Grep cascade, read 8 files, ~10,700 tokens | `search_code("auth error handling")` ~220 tokens |
+| Resume after context compaction | Re-explain 20 min of context, ~2,000 tokens | `/catchup` ~200 tokens |
+| Look up React hooks docs | Fetch docs page, ~5,000 tokens | `search_documents("React useEffect")` ~20 tokens |
+| Read a 400-line file | Built-in Read with line numbers, ~900 tokens | `read_file(path)` ~740 tokens |
+
+</details>
+
+---
+
+## 📦 Installation
+
+### Plugin (recommended)
+
+```bash
+claude plugin install eidetics/claude-eidetic
+```
+
+The plugin auto-starts the MCP server, installs skills, and configures hooks.
+
+### npx (manual MCP config)
+
+Add to your `.mcp.json`:
+
+```json
+{
+  "mcpServers": {
+    "claude-eidetic": {
+      "command": "npx",
+      "args": ["-y", "claude-eidetic"],
+      "env": {
+        "OPENAI_API_KEY": "sk-...",
+        "ANTHROPIC_API_KEY": "sk-ant-..."
+      }
+    }
+  }
+}
+```
+
+`ANTHROPIC_API_KEY` is needed for the memory LLM (default provider). Omit it if using `MEMORY_LLM_PROVIDER=openai` or `ollama`.
+
+### Global install
+
+```bash
+npm install -g claude-eidetic
+```
+
+### From source
+
+```bash
+git clone https://github.com/eidetics/claude-eidetic
+cd claude-eidetic
+npm install && npx tsc && npm start
+```
+
+### Requirements
+
+- Node.js >= 20.0.0
+- An API key (OpenAI for embeddings, Anthropic for memory extraction, or Ollama for both free)
+- Docker (optional): Qdrant auto-provisions via Docker if not already running
+- C/C++ build tools: required by tree-sitter native bindings (`node-gyp`)
+
+---
+
+## ⚙️ Configuration
+
+All configuration is via environment variables. No config files.
+
+### Using Ollama (free, local)
+
+```bash
+export EMBEDDING_PROVIDER=ollama
+export MEMORY_LLM_PROVIDER=ollama
+# No API keys needed
+```
+
+<details>
+<summary><strong>Full configuration reference</strong></summary>
+
+| Variable | Default | Description |
+|---|---|---|
+| `OPENAI_API_KEY` | _(required for openai)_ | OpenAI API key for embeddings and/or memory |
+| `ANTHROPIC_API_KEY` | _(required for anthropic memory)_ | Anthropic API key for memory LLM |
+| `EMBEDDING_PROVIDER` | `openai` | `openai`, `ollama`, or `local` |
+| `EMBEDDING_MODEL` | `text-embedding-3-small` (openai) / `nomic-embed-text` (ollama) | Embedding model name |
+| `EMBEDDING_BATCH_SIZE` | `100` | Batch size for embedding requests (1-2048) |
+| `INDEXING_CONCURRENCY` | `8` | Parallel file indexing workers (1-32) |
+| `OPENAI_BASE_URL` | _(none)_ | Custom OpenAI-compatible endpoint |
+| `OLLAMA_BASE_URL` | `http://localhost:11434/v1` | Ollama server URL |
+| `VECTORDB_PROVIDER` | `qdrant` | `qdrant` or `milvus` |
+| `QDRANT_URL` | `http://localhost:6333` | Qdrant server URL |
+| `QDRANT_API_KEY` | _(none)_ | Qdrant API key (for remote/cloud instances) |
+| `MILVUS_ADDRESS` | `localhost:19530` | Milvus server address |
+| `MILVUS_TOKEN` | _(none)_ | Milvus authentication token |
+| `EIDETIC_DATA_DIR` | `~/.eidetic/` | Data root for snapshots, memory DB, registry |
+| `CUSTOM_EXTENSIONS` | `[]` | JSON array of extra file extensions to index (e.g., `[".dart",".arb"]`) |
+| `CUSTOM_IGNORE_PATTERNS` | `[]` | JSON array of glob patterns to exclude |
+| `MEMORY_LLM_PROVIDER` | `anthropic` | `anthropic`, `openai`, or `ollama` |
+| `MEMORY_LLM_MODEL` | `claude-haiku-4-5-20251001` (anthropic) / `gpt-4o-mini` (openai) / `llama3.2` (ollama) | Model for memory extraction |
+| `MEMORY_LLM_BASE_URL` | _(none)_ | Custom base URL for memory LLM |
+| `MEMORY_LLM_API_KEY` | _(none)_ | API key override for memory LLM |
+
+</details>
+
+---
+
+<details>
+<summary><strong>🔧 Tool Reference</strong></summary>
+
+### 🔍 Code Search
+
+| Tool | Description |
+|---|---|
+| `search_code` | Hybrid semantic search over indexed codebase. Returns compact results by default. |
+| `index_codebase` | Index a directory. Supports `dryRun`, `force`, `customExtensions`, `customIgnorePatterns`. |
+| `list_indexed` | List all indexed codebases with file/chunk counts and status. |
+| `get_indexing_status` | Check indexing progress for a path or project. |
+| `clear_index` | Remove the search index for a codebase. |
+| `cleanup_vectors` | Remove orphaned vectors for deleted files. No re-embedding cost. |
+| `browse_structure` | Condensed structural map: classes, functions, methods with signatures, grouped by file. |
+| `list_symbols` | Compact symbol table with name/kind/file/line. Supports name, kind, and path filters. |
+
+### 📄 File Reading
+
+| Tool | Description |
+|---|---|
+| `read_file` | Read file without line-number overhead. Cheaper than built-in Read for code files. |
+
+### 📚 Documentation Cache
+
+| Tool | Description |
+|---|---|
+| `index_document` | Cache external documentation for semantic search. Supports TTL for staleness tracking. |
+| `search_documents` | Search cached docs. Far cheaper than re-fetching the same page. |
+
+### 🧠 Memory
+
+| Tool | Description |
+|---|---|
+| `add_memory` | LLM-extracted facts from text. Auto-deduplicates. Seven categories. |
+| `search_memory` | Semantic search over stored memories. Filterable by category. |
+| `list_memories` | List all memories, optionally filtered by category. |
+| `delete_memory` | Delete a specific memory by UUID. |
+| `memory_history` | View change history for a memory (additions, updates, deletions). |
+
+</details>
+
+---
+
+## 🌐 Supported Languages
+
+**AST-aware** (functions and classes chunked intact):
+
+<p>
+  <img src="https://img.shields.io/badge/JavaScript-F7DF1E?style=flat-square&logo=javascript&logoColor=black" alt="JavaScript"/>
+  <img src="https://img.shields.io/badge/TypeScript-3178C6?style=flat-square&logo=typescript&logoColor=white" alt="TypeScript"/>
+  <img src="https://img.shields.io/badge/React_(JSX/TSX)-61DAFB?style=flat-square&logo=react&logoColor=black" alt="JSX/TSX"/>
+  <img src="https://img.shields.io/badge/Python-3776AB?style=flat-square&logo=python&logoColor=white" alt="Python"/>
+  <img src="https://img.shields.io/badge/Go-00ADD8?style=flat-square&logo=go&logoColor=white" alt="Go"/>
+  <img src="https://img.shields.io/badge/Java-ED8B00?style=flat-square&logo=openjdk&logoColor=white" alt="Java"/>
+  <img src="https://img.shields.io/badge/Rust-000000?style=flat-square&logo=rust&logoColor=white" alt="Rust"/>
+  <img src="https://img.shields.io/badge/C-A8B9CC?style=flat-square&logo=c&logoColor=black" alt="C"/>
+  <img src="https://img.shields.io/badge/C++-00599C?style=flat-square&logo=cplusplus&logoColor=white" alt="C++"/>
+  <img src="https://img.shields.io/badge/C%23-512BD4?style=flat-square&logo=csharp&logoColor=white" alt="C#"/>
+</p>
+
+**Line-based fallback** (sliding window chunking for everything else):
+
+<p>
+  <img src="https://img.shields.io/badge/Markdown-000000?style=flat-square&logo=markdown&logoColor=white" alt="Markdown"/>
+  <img src="https://img.shields.io/badge/YAML-CB171E?style=flat-square&logo=yaml&logoColor=white" alt="YAML"/>
+  <img src="https://img.shields.io/badge/JSON-000000?style=flat-square&logo=json&logoColor=white" alt="JSON"/>
+  <img src="https://img.shields.io/badge/Ruby-CC342D?style=flat-square&logo=ruby&logoColor=white" alt="Ruby"/>
+  <img src="https://img.shields.io/badge/PHP-777BB4?style=flat-square&logo=php&logoColor=white" alt="PHP"/>
+  <img src="https://img.shields.io/badge/Swift-F05138?style=flat-square&logo=swift&logoColor=white" alt="Swift"/>
+  <img src="https://img.shields.io/badge/Kotlin-7F52FF?style=flat-square&logo=kotlin&logoColor=white" alt="Kotlin"/>
+  <img src="https://img.shields.io/badge/and_more...-30363d?style=flat-square" alt="and more"/>
+</p>
+
+---
+
+## 🛠️ Development
+
+```bash
+npm install && npx tsc    # install and build
+npm run dev               # watch mode (tsx)
+npm test                  # unit tests (no external services needed)
+npm run test:integration  # requires Qdrant at localhost:6333 + OPENAI_API_KEY
+```
+
+**Commit format:** `type(scope): description`
+Types: `feat`, `fix`, `docs`, `refactor`, `perf`, `chore`, `test`
+Scopes: `embedding`, `vectordb`, `splitter`, `indexer`, `mcp`, `infra`, `config`
+
+---
+
+## 🙏 Acknowledgements
+
+Heavily inspired by [mem0](https://github.com/mem0ai/mem0), [claude-mem](https://github.com/thedotmack/claude-mem), and [claude-context](https://github.com/zilliztech/claude-context). Documentation retrieval powered by [context7](https://github.com/upstash/context7).
+
+---
+
+## 📄 License
+
+MIT

package/dist/index.js

@@ -21,48 +21,48 @@ import { getSetupErrorMessage } from './setup-message.js';
 import { MemoryStore } from './memory/store.js';
 import { MemoryHistory } from './memory/history.js';
 import { getMemoryDbPath } from './paths.js';
-const WORKFLOW_GUIDANCE = `# Eidetic Code Search Workflow
-
-**Before searching:** Ensure the codebase is indexed.
-- \`list_indexed\` → see what's already indexed
-- \`index_codebase(path="...", dryRun=true)\` → preview before indexing
-- \`index_codebase(path="...")\` → index (incremental, only re-embeds changed files)
-
-**Searching efficiently:**
-- \`search_code(query="...")\` → returns compact table by default (~20 tokens/result)
-- Review the table, then use Read tool to fetch full code for interesting results
-- Add \`compact=false\` only when you need all code snippets immediately
-- Use \`extensionFilter\` to narrow by file type
-- Use \`project\` param instead of \`path\` for convenience
-- Start with specific queries, broaden if no results
-
-**Reading files efficiently:**
-- \`read_file(path="...")\` → raw content without line-number overhead (~15-20% fewer tokens for code, more for short-line files)
-- Use \`offset\` and \`limit\` to page through large files
-- Add \`lineNumbers=true\` only when you need line references for editing
-
-**After first index:**
-- Re-indexing is incremental (only changed files re-embedded)
-- Use \`project\` param instead of \`path\` for convenience
-- Use \`get_indexing_status\` to check progress during long indexes
-- Use \`cleanup_vectors(path="...", dryRun=true)\` to preview stale vectors, then without dryRun to remove them (no embedding cost)
-
-**Cross-project search:**
-- Index multiple projects, each with its own path
-- Search across any indexed project regardless of current working directory
-
-**Documentation caching (saves ~5K tokens per repeated doc fetch):**
-- After fetching docs via query-docs or WebFetch, cache them: \`index_document(content="...", source="<url>", library="<name>", topic="<topic>")\`
-- Next time you need the same docs: \`search_documents(query="...", library="<name>")\` (~20 tokens/result)
-- Docs are grouped by library — one collection per library, searchable across topics
-- Stale docs (past TTL) still return results but are flagged \`[STALE]\`
-
-**Persistent memory (cross-session developer knowledge):**
-- \`add_memory(content="...")\` → extracts facts about coding style, tools, architecture, etc.
-- \`search_memory(query="...")\` → find relevant memories by semantic search
-- \`list_memories()\` → see all stored memories grouped by category
-- \`delete_memory(id="...")\` → remove a specific memory
-- \`memory_history(id="...")\` → view change log for a memory
+const WORKFLOW_GUIDANCE = `# Eidetic Code Search Workflow
+
+**Before searching:** Ensure the codebase is indexed.
+- \`list_indexed\` → see what's already indexed
+- \`index_codebase(path="...", dryRun=true)\` → preview before indexing
+- \`index_codebase(path="...")\` → index (incremental, only re-embeds changed files)
+
+**Searching efficiently:**
+- \`search_code(query="...")\` → returns compact table by default (~20 tokens/result)
+- Review the table, then use Read tool to fetch full code for interesting results
+- Add \`compact=false\` only when you need all code snippets immediately
+- Use \`extensionFilter\` to narrow by file type
+- Use \`project\` param instead of \`path\` for convenience
+- Start with specific queries, broaden if no results
+
+**Reading files efficiently:**
+- \`read_file(path="...")\` → raw content without line-number overhead (~15-20% fewer tokens for code, more for short-line files)
+- Use \`offset\` and \`limit\` to page through large files
+- Add \`lineNumbers=true\` only when you need line references for editing
+
+**After first index:**
+- Re-indexing is incremental (only changed files re-embedded)
+- Use \`project\` param instead of \`path\` for convenience
+- Use \`get_indexing_status\` to check progress during long indexes
+- Use \`cleanup_vectors(path="...", dryRun=true)\` to preview stale vectors, then without dryRun to remove them (no embedding cost)
+
+**Cross-project search:**
+- Index multiple projects, each with its own path
+- Search across any indexed project regardless of current working directory
+
+**Documentation caching (saves ~5K tokens per repeated doc fetch):**
+- After fetching docs via query-docs or WebFetch, cache them: \`index_document(content="...", source="<url>", library="<name>", topic="<topic>")\`
+- Next time you need the same docs: \`search_documents(query="...", library="<name>")\` (~20 tokens/result)
+- Docs are grouped by library — one collection per library, searchable across topics
+- Stale docs (past TTL) still return results but are flagged \`[STALE]\`
+
+**Persistent memory (cross-session developer knowledge):**
+- \`add_memory(content="...")\` → extracts facts about coding style, tools, architecture, etc.
+- \`search_memory(query="...")\` → find relevant memories by semantic search
+- \`list_memories()\` → see all stored memories grouped by category
+- \`delete_memory(id="...")\` → remove a specific memory
+- \`memory_history(id="...")\` → view change log for a memory
 - Memories are automatically deduplicated — adding similar facts updates existing ones`;
 async function main() {
     const config = loadConfig();

package/dist/memory/history.js

@@ -7,24 +7,24 @@ export class MemoryHistory {
         mkdirSync(dirname(dbPath), { recursive: true });
         this.db = new Database(dbPath);
         this.db.pragma('journal_mode = WAL');
-        this.db.exec(`
-      CREATE TABLE IF NOT EXISTS memory_history (
-        id INTEGER PRIMARY KEY AUTOINCREMENT,
-        memory_id TEXT NOT NULL,
-        previous_value TEXT,
-        new_value TEXT,
-        event TEXT NOT NULL,
-        created_at TEXT NOT NULL,
-        updated_at TEXT,
-        source TEXT
-      )
+        this.db.exec(`
+      CREATE TABLE IF NOT EXISTS memory_history (
+        id INTEGER PRIMARY KEY AUTOINCREMENT,
+        memory_id TEXT NOT NULL,
+        previous_value TEXT,
+        new_value TEXT,
+        event TEXT NOT NULL,
+        created_at TEXT NOT NULL,
+        updated_at TEXT,
+        source TEXT
+      )
     `);
     }
     log(memoryId, event, newValue, previousValue = null, source = null, updatedAt = null) {
         this.db
-            .prepare(`
-      INSERT INTO memory_history (memory_id, previous_value, new_value, event, created_at, updated_at, source)
-      VALUES (?, ?, ?, ?, ?, ?, ?)
+            .prepare(`
+      INSERT INTO memory_history (memory_id, previous_value, new_value, event, created_at, updated_at, source)
+      VALUES (?, ?, ?, ?, ?, ?, ?)
     `)
             .run(memoryId, previousValue, newValue, event, new Date().toISOString(), updatedAt, source);
     }

package/dist/memory/prompts.js

@@ -1,30 +1,30 @@
-export const FACT_EXTRACTION_SYSTEM_PROMPT = `You are a developer knowledge extractor. Your job is to extract discrete, factual statements from conversations about software development.
-
-Extract facts about:
-- **coding_style**: Formatting preferences (tabs/spaces, naming conventions, line length), code style rules
-- **tools**: Preferred tools, frameworks, libraries, test runners, bundlers, linters, editors
-- **architecture**: Design patterns, architectural decisions, system design preferences
-- **conventions**: Project conventions, commit message formats, branch naming, PR workflows
-- **debugging**: Solutions to specific bugs, debugging techniques, known issues
-- **workflow**: Development habits, deployment processes, review preferences
-- **preferences**: General preferences, opinions, requirements that don't fit other categories
-
-Rules:
-1. Extract only factual, concrete statements — not vague observations
-2. Each fact should be a single, self-contained statement
-3. Use third person ("The user prefers..." or state the fact directly)
-4. If the input contains no extractable facts, return an empty array
-5. Do NOT extract facts about the conversation itself (e.g., "the user asked about...")
-6. Do NOT extract temporary or session-specific information
-7. Prefer specific facts over general ones
-
-Respond with JSON: { "facts": [{ "fact": "...", "category": "..." }] }
-
+export const FACT_EXTRACTION_SYSTEM_PROMPT = `You are a developer knowledge extractor. Your job is to extract discrete, factual statements from conversations about software development.
+
+Extract facts about:
+- **coding_style**: Formatting preferences (tabs/spaces, naming conventions, line length), code style rules
+- **tools**: Preferred tools, frameworks, libraries, test runners, bundlers, linters, editors
+- **architecture**: Design patterns, architectural decisions, system design preferences
+- **conventions**: Project conventions, commit message formats, branch naming, PR workflows
+- **debugging**: Solutions to specific bugs, debugging techniques, known issues
+- **workflow**: Development habits, deployment processes, review preferences
+- **preferences**: General preferences, opinions, requirements that don't fit other categories
+
+Rules:
+1. Extract only factual, concrete statements — not vague observations
+2. Each fact should be a single, self-contained statement
+3. Use third person ("The user prefers..." or state the fact directly)
+4. If the input contains no extractable facts, return an empty array
+5. Do NOT extract facts about the conversation itself (e.g., "the user asked about...")
+6. Do NOT extract temporary or session-specific information
+7. Prefer specific facts over general ones
+
+Respond with JSON: { "facts": [{ "fact": "...", "category": "..." }] }
+
 Categories: coding_style, tools, architecture, conventions, debugging, workflow, preferences`;
-export const FACT_EXTRACTION_USER_TEMPLATE = `Extract developer knowledge facts from this text:
-
-<text>
-{content}
+export const FACT_EXTRACTION_USER_TEMPLATE = `Extract developer knowledge facts from this text:
+
+<text>
+{content}
 </text>`;
 export function buildSystemPrompt() {
     const today = new Date().toISOString().slice(0, 10);

package/dist/tool-schemas.js

@@ -1,58 +1,58 @@
-const READ_FILE_DESCRIPTION = `\
-Read a file and return raw content without line-number overhead (~15-20% fewer tokens than built-in Read for code, more for short-line files).
-
-Use offset and limit to page through large files. \
+const READ_FILE_DESCRIPTION = `\
+Read a file and return raw content without line-number overhead (~15-20% fewer tokens than built-in Read for code, more for short-line files).
+
+Use offset and limit to page through large files. \
 Add lineNumbers=true only when you need line references for editing.`;
-const INDEX_DOCUMENT_DESCRIPTION = `\
-Cache external documentation (from query-docs, WebFetch, etc.) for cheap semantic search later.
-
-After fetching documentation from an external source, call this tool to store it. \
-Subsequent queries about the same library will use search_documents (~20 tokens/result) \
-instead of re-fetching (~5K+ tokens).
-
-The content is split into chunks, embedded, and stored in a vector collection grouped by library. \
+const INDEX_DOCUMENT_DESCRIPTION = `\
+Cache external documentation (from query-docs, WebFetch, etc.) for cheap semantic search later.
+
+After fetching documentation from an external source, call this tool to store it. \
+Subsequent queries about the same library will use search_documents (~20 tokens/result) \
+instead of re-fetching (~5K+ tokens).
+
+The content is split into chunks, embedded, and stored in a vector collection grouped by library. \
 A TTL tracks staleness — stale docs still return results but are flagged.`;
-const SEARCH_DOCUMENTS_DESCRIPTION = `\
-Search cached documentation using natural language queries.
-
-Returns results from previously cached documentation (via index_document). \
-Much cheaper than re-fetching docs (~20 tokens/result vs ~5K+ tokens/fetch).
-
-If a specific library is provided, searches only that library's collection. \
+const SEARCH_DOCUMENTS_DESCRIPTION = `\
+Search cached documentation using natural language queries.
+
+Returns results from previously cached documentation (via index_document). \
+Much cheaper than re-fetching docs (~20 tokens/result vs ~5K+ tokens/fetch).
+
+If a specific library is provided, searches only that library's collection. \
 Otherwise searches across all cached documentation. Results include staleness indicators.`;
-const CLEANUP_DESCRIPTION = `\
-Remove orphaned vectors for files that no longer exist on disk. Lightweight alternative to re-indexing — no embedding cost.
-
-Provide either \`path\` (absolute) or \`project\` (name). Use \`list_indexed\` to see registered projects.
-
+const CLEANUP_DESCRIPTION = `\
+Remove orphaned vectors for files that no longer exist on disk. Lightweight alternative to re-indexing — no embedding cost.
+
+Provide either \`path\` (absolute) or \`project\` (name). Use \`list_indexed\` to see registered projects.
+
 Use \`dryRun=true\` first to preview which files would be cleaned without making any changes.`;
-const INDEX_DESCRIPTION = `\
-Index a codebase directory to enable semantic search using a configurable code splitter.
-
-Provide either \`path\` (absolute) or \`project\` (name). Use \`list_indexed\` to see registered projects.
-
-Usage Guidance:
-- Use dryRun=true first to preview what files would be indexed and catch configuration issues before committing to a full index.
-- This tool is typically used when search fails due to an unindexed codebase.
-- If indexing is attempted on an already indexed path, and a conflict is detected, \
+const INDEX_DESCRIPTION = `\
+Index a codebase directory to enable semantic search using a configurable code splitter.
+
+Provide either \`path\` (absolute) or \`project\` (name). Use \`list_indexed\` to see registered projects.
+
+Usage Guidance:
+- Use dryRun=true first to preview what files would be indexed and catch configuration issues before committing to a full index.
+- This tool is typically used when search fails due to an unindexed codebase.
+- If indexing is attempted on an already indexed path, and a conflict is detected, \
 you MUST prompt the user to confirm whether to proceed with a force index.`;
-const SEARCH_DESCRIPTION = `\
-Search the indexed codebase using natural language queries.
-Prefer over Grep for conceptual/semantic queries — returns ~20 tokens/result vs ~100+ for Grep.
-Try before launching an Explore agent — faster and cheaper for understanding code.
-
-Provide either \`path\` (absolute) or \`project\` (name). Use \`list_indexed\` to see registered projects.
-
-When to Use:
-- Code search: Find specific functions, classes, or implementations
-- Context-aware assistance: Gather relevant code context before making changes
-- Issue identification: Locate problematic code sections or bugs
-- Code review: Understand existing implementations and patterns
-- Refactoring: Find all related code pieces that need to be updated
-- Feature development: Understand existing architecture and similar implementations
-- Duplicate detection: Identify redundant or duplicated code patterns
-
-If the codebase is not indexed, this tool will return a clear error message \
+const SEARCH_DESCRIPTION = `\
+Search the indexed codebase using natural language queries.
+Prefer over Grep for conceptual/semantic queries — returns ~20 tokens/result vs ~100+ for Grep.
+Try before launching an Explore agent — faster and cheaper for understanding code.
+
+Provide either \`path\` (absolute) or \`project\` (name). Use \`list_indexed\` to see registered projects.
+
+When to Use:
+- Code search: Find specific functions, classes, or implementations
+- Context-aware assistance: Gather relevant code context before making changes
+- Issue identification: Locate problematic code sections or bugs
+- Code review: Understand existing implementations and patterns
+- Refactoring: Find all related code pieces that need to be updated
+- Feature development: Understand existing architecture and similar implementations
+- Duplicate detection: Identify redundant or duplicated code patterns
+
+If the codebase is not indexed, this tool will return a clear error message \
 indicating that indexing is required first.`;
 export const TOOL_DEFINITIONS = [
     {

package/messages.yaml

@@ -1,50 +1,50 @@
-# Eidetic user-facing messages — edit here, everything else reads from this file.
-
-setup:
-  missing:
-    header: "Eidetic setup required: No API key configured."
-    diagnosis: >
-      `OPENAI_API_KEY` is not set and no alternative provider is configured.
-    step1: "**Get an API key**: https://platform.openai.com/api-keys"
-
-  invalid:
-    header: "Eidetic setup failed: {error}"
-    diagnosis: >
-      Key/provider is configured but initialization failed.
-      The key may be invalid, expired, or the provider may be unreachable.
-    step1: "**Verify your key** is valid and has embedding permissions"
-
-  unknown:
-    header: "Eidetic setup failed: {error}"
-    diagnosis: ""
-    step1: "**Get an API key**: https://platform.openai.com/api-keys"
-
-  # Shared across all contexts
-  config_instructions: |
-    ### Windows
-    ```
-      setx OPENAI_API_KEY sk-your-key-here
-    ```
-
-    ### macOS / Linux
-    Add to your shell profile (`~/.bashrc`, `~/.zshrc`, etc.):
-    ```
-      export OPENAI_API_KEY="sk-your-key-here"
-    ```
-
-    ### Manual
-
-    Edit `~/.claude/plugins/claude-eidetic/config.json`:
-    ```json
-    {
-      "env": {
-        "OPENAI_API_KEY": "sk-your-key-here"
-      }
-    }
-    ```
-
-    ### Using Ollama instead (free, local)
-
-    Set `EMBEDDING_PROVIDER=ollama` in the same env block (requires Ollama running locally with `nomic-embed-text`).
-
-  footer: "**Restart Claude Code** for changes to take effect."
+# Eidetic user-facing messages — edit here, everything else reads from this file.
+
+setup:
+  missing:
+    header: "Eidetic setup required: No API key configured."
+    diagnosis: >
+      `OPENAI_API_KEY` is not set and no alternative provider is configured.
+    step1: "**Get an API key**: https://platform.openai.com/api-keys"
+
+  invalid:
+    header: "Eidetic setup failed: {error}"
+    diagnosis: >
+      Key/provider is configured but initialization failed.
+      The key may be invalid, expired, or the provider may be unreachable.
+    step1: "**Verify your key** is valid and has embedding permissions"
+
+  unknown:
+    header: "Eidetic setup failed: {error}"
+    diagnosis: ""
+    step1: "**Get an API key**: https://platform.openai.com/api-keys"
+
+  # Shared across all contexts
+  config_instructions: |
+    ### Windows
+    ```
+      setx OPENAI_API_KEY sk-your-key-here
+    ```
+
+    ### macOS / Linux
+    Add to your shell profile (`~/.bashrc`, `~/.zshrc`, etc.):
+    ```
+      export OPENAI_API_KEY="sk-your-key-here"
+    ```
+
+    ### Manual
+
+    Edit `~/.claude/plugins/claude-eidetic/config.json`:
+    ```json
+    {
+      "env": {
+        "OPENAI_API_KEY": "sk-your-key-here"
+      }
+    }
+    ```
+
+    ### Using Ollama instead (free, local)
+
+    Set `EMBEDDING_PROVIDER=ollama` in the same env block (requires Ollama running locally with `nomic-embed-text`).
+
+  footer: "**Restart Claude Code** for changes to take effect."

package/package.json

@@ -1,87 +1,87 @@
-{
-  "name": "claude-eidetic",
-  "version": "0.1.2",
-  "description": "Semantic code search MCP server — lean, correct, fast",
-  "type": "module",
-  "main": "dist/index.js",
-  "bin": {
-    "claude-eidetic": "dist/index.js"
-  },
-  "files": [
-    "dist/**/*.js",
-    "dist/**/*.d.ts",
-    "!dist/**/*.test.*",
-    "!dist/__tests__/**",
-    "!dist/**/tests/**",
-    "!dist/e2e/**",
-    "messages.yaml"
-  ],
-  "scripts": {
-    "build": "tsc",
-    "dev": "tsx --watch src/index.ts",
-    "start": "node dist/index.js",
-    "clean": "rimraf dist",
-    "lint": "eslint src/",
-    "lint:fix": "eslint src/ --fix",
-    "format": "prettier --write \"src/**/*.ts\"",
-    "format:check": "prettier --check \"src/**/*.ts\"",
-    "typecheck": "tsc --noEmit",
-    "test": "vitest run",
-    "test:watch": "vitest",
-    "test:coverage": "vitest run --coverage",
-    "test:integration": "vitest run --config vitest.integration.config.ts",
-    "test:all": "vitest run && vitest run --config vitest.integration.config.ts",
-    "test:eval": "tsx scripts/eval/recall-at-k.ts && tsx scripts/eval/fusion-lift.ts && tsx scripts/eval/ndcg.ts",
-    "test:eval:generate": "tsx scripts/eval/generate-queries.ts",
-    "prepublishOnly": "npm run clean && npm run build",
-    "release": "bash scripts/release.sh"
-  },
-  "dependencies": {
-    "@anthropic-ai/sdk": "^0.78.0",
-    "@modelcontextprotocol/sdk": "^1.12.1",
-    "@qdrant/js-client-rest": "^1.13.0",
-    "better-sqlite3": "^12.6.2",
-    "glob": "^11.0.0",
-    "openai": "^5.1.1",
-    "tree-sitter": "^0.21.1",
-    "tree-sitter-c-sharp": "^0.21.0",
-    "tree-sitter-cpp": "^0.22.0",
-    "tree-sitter-go": "^0.21.0",
-    "tree-sitter-java": "^0.21.0",
-    "tree-sitter-javascript": "^0.21.0",
-    "tree-sitter-python": "^0.21.0",
-    "tree-sitter-rust": "^0.21.0",
-    "tree-sitter-typescript": "^0.21.0",
-    "yaml": "^2.8.2",
-    "zod": "^3.25.0"
-  },
-  "optionalDependencies": {
-    "@zilliz/milvus2-sdk-node": "^2.5.10"
-  },
-  "devDependencies": {
-    "@eslint/js": "^9.39.3",
-    "@types/better-sqlite3": "^7.6.13",
-    "@types/node": "^20.0.0",
-    "@vitest/coverage-v8": "^4.0.18",
-    "eslint": "^9.39.3",
-    "eslint-config-prettier": "^10.1.8",
-    "prettier": "^3.8.1",
-    "rimraf": "^6.0.1",
-    "tsx": "^4.19.4",
-    "typescript": "^5.8.3",
-    "typescript-eslint": "^8.56.0",
-    "vitest": "^4.0.18"
-  },
-  "overrides": {
-    "minimatch": "^10.2.1",
-    "@grpc/grpc-js": "^1.8.22"
-  },
-  "engines": {
-    "node": ">=20.0.0"
-  },
-  "repository": {
-    "type": "git",
-    "url": "https://github.com/eidetics/claude-eidetic"
-  },
-  "license": "MIT"
-}
+{
+  "name": "claude-eidetic",
+  "version": "0.1.3",
+  "description": "Semantic code search MCP server — lean, correct, fast",
+  "type": "module",
+  "main": "dist/index.js",
+  "bin": {
+    "claude-eidetic": "dist/index.js"
+  },
+  "files": [
+    "dist/**/*.js",
+    "dist/**/*.d.ts",
+    "!dist/**/*.test.*",
+    "!dist/__tests__/**",
+    "!dist/**/tests/**",
+    "!dist/e2e/**",
+    "messages.yaml"
+  ],
+  "scripts": {
+    "build": "tsc",
+    "dev": "tsx --watch src/index.ts",
+    "start": "node dist/index.js",
+    "clean": "rimraf dist",
+    "lint": "eslint src/",
+    "lint:fix": "eslint src/ --fix",
+    "format": "prettier --write \"src/**/*.ts\"",
+    "format:check": "prettier --check \"src/**/*.ts\"",
+    "typecheck": "tsc --noEmit",
+    "test": "vitest run",
+    "test:watch": "vitest",
+    "test:coverage": "vitest run --coverage",
+    "test:integration": "vitest run --config vitest.integration.config.ts",
+    "test:all": "vitest run && vitest run --config vitest.integration.config.ts",
+    "test:eval": "tsx scripts/eval/recall-at-k.ts && tsx scripts/eval/fusion-lift.ts && tsx scripts/eval/ndcg.ts",
+    "test:eval:generate": "tsx scripts/eval/generate-queries.ts",
+    "prepublishOnly": "npm run clean && npm run build",
+    "release": "bash scripts/release.sh"
+  },
+  "dependencies": {
+    "@anthropic-ai/sdk": "^0.78.0",
+    "@modelcontextprotocol/sdk": "^1.12.1",
+    "@qdrant/js-client-rest": "^1.13.0",
+    "better-sqlite3": "^12.6.2",
+    "glob": "^11.0.0",
+    "openai": "^5.1.1",
+    "tree-sitter": "^0.21.1",
+    "tree-sitter-c-sharp": "^0.21.0",
+    "tree-sitter-cpp": "^0.22.0",
+    "tree-sitter-go": "^0.21.0",
+    "tree-sitter-java": "^0.21.0",
+    "tree-sitter-javascript": "^0.21.0",
+    "tree-sitter-python": "^0.21.0",
+    "tree-sitter-rust": "^0.21.0",
+    "tree-sitter-typescript": "^0.21.0",
+    "yaml": "^2.8.2",
+    "zod": "^3.25.0"
+  },
+  "optionalDependencies": {
+    "@zilliz/milvus2-sdk-node": "^2.5.10"
+  },
+  "devDependencies": {
+    "@eslint/js": "^9.39.3",
+    "@types/better-sqlite3": "^7.6.13",
+    "@types/node": "^20.0.0",
+    "@vitest/coverage-v8": "^4.0.18",
+    "eslint": "^9.39.3",
+    "eslint-config-prettier": "^10.1.8",
+    "prettier": "^3.8.1",
+    "rimraf": "^6.0.1",
+    "tsx": "^4.19.4",
+    "typescript": "^5.8.3",
+    "typescript-eslint": "^8.56.0",
+    "vitest": "^4.0.18"
+  },
+  "overrides": {
+    "minimatch": "^10.2.1",
+    "@grpc/grpc-js": "^1.8.22"
+  },
+  "engines": {
+    "node": ">=20.0.0"
+  },
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/eidetics/claude-eidetic"
+  },
+  "license": "MIT"
+}