Merge branch 'bugfix/worker'

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

.claude-plugin/marketplace.json

@@ -10,7 +10,7 @@
   "plugins": [
     {
       "name": "claude-mem",
-      "version": "8.1.0",
+      "version": "8.2.3",
       "source": "./plugin",
       "description": "Persistent memory system for Claude Code - context compression across sessions"
     }

docs/public/architecture/pm2-to-bun-migration.mdx

@@ -106,7 +106,7 @@ pm2 logs claude-mem-worker    # View logs
 ```bash
 npm run worker:start    # Start worker
 npm run worker:stop     # Stop worker
-claude-mem restart  # Restart worker
+npm run worker:restart  # Restart worker
 npm run worker:status   # Check status
 npm run worker:logs     # View logs
 ```
@@ -305,7 +305,7 @@ No migration logic runs on subsequent sessions.
 | `pm2 list` | `npm run worker:status` | Shows worker status |
 | `pm2 start <script>` | `npm run worker:start` | Start worker |
 | `pm2 stop claude-mem-worker` | `npm run worker:stop` | Stop worker |
-| `pm2 restart claude-mem-worker` | `claude-mem restart` | Restart worker |
+| `pm2 restart claude-mem-worker` | `npm run worker:restart` | Restart worker |
 | `pm2 delete claude-mem-worker` | `npm run worker:stop` | Remove worker |
 | `pm2 logs claude-mem-worker` | `npm run worker:logs` | View logs |
 | `pm2 describe claude-mem-worker` | `npm run worker:status` | Detailed status |
@@ -451,7 +451,7 @@ pm2 save  # Persist the deletion
 rm ~/.claude-mem/.pm2-migrated
 
 # Restart worker
-claude-mem restart
+npm run worker:restart
 ```
 
 ### Scenario 2: Stale PID File (Process Dead)
@@ -483,7 +483,7 @@ lsof -i :37777
 kill -9 <PID>
 
 # Restart worker
-claude-mem restart
+npm run worker:restart
 ```
 
 ### Common Error Messages

docs/public/architecture/search-architecture.mdx

@@ -416,7 +416,7 @@ If searches fail, check worker service:
 
 ```bash
 npm run worker:status       # Check status
-claude-mem restart      # Restart worker
+npm run worker:restart      # Restart worker
 npm run worker:logs         # View logs
 ```
 

docs/public/architecture/worker-service.mdx

@@ -597,7 +597,7 @@ npm run worker:start
 npm run worker:stop
 
 # Restart worker
-claude-mem restart
+npm run worker:restart
 
 # View logs
 npm run worker:logs

docs/public/configuration.mdx

@@ -13,12 +13,35 @@ Settings are managed in `~/.claude-mem/settings.json`. The file is auto-created
 
 | Setting                       | Default                         | Description                           |
 |-------------------------------|---------------------------------|---------------------------------------|
-| `CLAUDE_MEM_MODEL`            | `sonnet`                        | AI model for processing observations  |
+| `CLAUDE_MEM_MODEL`            | `sonnet`                        | AI model for processing observations (when using Claude) |
+| `CLAUDE_MEM_PROVIDER`         | `claude`                        | AI provider: `claude`, `gemini`, or `openrouter` |
 | `CLAUDE_MEM_MODE`             | `code`                          | Active mode profile (e.g., `code--es`, `email-investigation`) |
 | `CLAUDE_MEM_CONTEXT_OBSERVATIONS` | `50`                        | Number of observations to inject      |
 | `CLAUDE_MEM_WORKER_PORT`      | `37777`                         | Worker service port                   |
 | `CLAUDE_MEM_SKIP_TOOLS`       | `ListMcpResourcesTool,SlashCommand,Skill,TodoWrite,AskUserQuestion` | Comma-separated tools to exclude from observations |
 
+### Gemini Provider Settings
+
+| Setting                       | Default                         | Description                           |
+|-------------------------------|---------------------------------|---------------------------------------|
+| `CLAUDE_MEM_GEMINI_API_KEY`   | —                               | Gemini API key ([get free key](https://aistudio.google.com/app/apikey)) |
+| `CLAUDE_MEM_GEMINI_MODEL`     | `gemini-2.5-flash-lite`          | Gemini model: `gemini-2.5-flash-lite`, `gemini-2.5-flash`, `gemini-3-flash` |
+
+See [Gemini Provider](usage/gemini-provider) for detailed configuration and free tier information.
+
+### OpenRouter Provider Settings
+
+| Setting                                      | Default                     | Description                           |
+|----------------------------------------------|-----------------------------|---------------------------------------|
+| `CLAUDE_MEM_OPENROUTER_API_KEY`              | —                           | OpenRouter API key ([get key](https://openrouter.ai/keys)) |
+| `CLAUDE_MEM_OPENROUTER_MODEL`                | `xiaomi/mimo-v2-flash:free` | Model identifier (supports 100+ models) |
+| `CLAUDE_MEM_OPENROUTER_MAX_CONTEXT_MESSAGES` | `20`                        | Max messages in conversation history  |
+| `CLAUDE_MEM_OPENROUTER_MAX_TOKENS`           | `100000`                    | Token budget safety limit             |
+| `CLAUDE_MEM_OPENROUTER_SITE_URL`             | —                           | Optional: URL for analytics           |
+| `CLAUDE_MEM_OPENROUTER_APP_NAME`             | `claude-mem`                | Optional: App name for analytics      |
+
+See [OpenRouter Provider](usage/openrouter-provider) for detailed configuration, free model list, and usage guide.
+
 ### System Configuration
 
 | Setting                       | Default                         | Description                           |
@@ -117,7 +140,6 @@ ${CLAUDE_PLUGIN_ROOT}/
 │   ├── new-hook.js         # Session creation hook
 │   ├── save-hook.js        # Observation capture hook
 │   ├── summary-hook.js     # Summary generation hook
-│   ├── cleanup-hook.js     # Session cleanup hook
 │   ├── worker-service.cjs  # Worker service (CJS)
 │   └── mcp-server.cjs      # MCP search server (CJS)
 └── ui/
@@ -162,13 +184,6 @@ Hooks are configured in `plugin/hooks/hooks.json`:
         "command": "node ${CLAUDE_PLUGIN_ROOT}/scripts/summary-hook.js",
         "timeout": 120
       }]
-    }],
-    "SessionEnd": [{
-      "hooks": [{
-        "type": "command",
-        "command": "node ${CLAUDE_PLUGIN_ROOT}/scripts/cleanup-hook.js",
-        "timeout": 120
-      }]
     }]
   }
 }
@@ -343,7 +358,7 @@ Edit `~/.claude-mem/settings.json`:
 
 Then restart the worker:
 ```bash
-claude-mem restart
+npm run worker:restart
 ```
 
 ### Custom Model
@@ -358,7 +373,7 @@ Edit `~/.claude-mem/settings.json`:
 Then restart the worker:
 ```bash
 export CLAUDE_MEM_MODEL=opus
-claude-mem restart
+npm run worker:restart
 ```
 
 ### Custom Skip Tools
@@ -415,7 +430,7 @@ Enable debug logging:
 
 ```bash
 export DEBUG=claude-mem:*
-claude-mem restart
+npm run worker:restart
 npm run worker:logs
 ```
 
@@ -433,7 +448,7 @@ npm run worker:logs
 
 1. Restart worker after changes:
    ```bash
-   claude-mem restart
+   npm run worker:restart
    ```
 
 2. Verify environment variables:
@@ -467,7 +482,7 @@ If port 37777 is already in use:
 
 2. Restart worker:
    ```bash
-   claude-mem restart
+   npm run worker:restart
    ```
 
 3. Verify new port:

docs/public/development.mdx

@@ -165,7 +165,7 @@ npm run build
 1. Make changes to React components in `src/ui/viewer/`
 2. Build: `npm run build`
 3. Sync to installed plugin: `npm run sync-marketplace`
-4. Restart worker: `claude-mem restart`
+4. Restart worker: `npm run worker:restart`
 5. Refresh browser at http://localhost:37777
 
 **Hot Reload**: Not currently supported. Full rebuild + restart required for changes.
@@ -395,7 +395,7 @@ When developing new features:
    ```bash
    npm run build
    npm run sync-marketplace
-   claude-mem restart
+   npm run worker:restart
    ```
 
 2. **Test in real session**:
@@ -560,7 +560,7 @@ export async function createObservation(
 
 ```bash
 export DEBUG=claude-mem:*
-claude-mem restart
+npm run worker:restart
 npm run worker:logs
 ```
 

docs/public/docs.json

@@ -36,6 +36,8 @@
           "introduction",
           "installation",
           "usage/getting-started",
+          "usage/openrouter-provider",
+          "usage/gemini-provider",
           "usage/search-tools",
           "usage/claude-desktop",
           "usage/private-tags",

docs/public/endless-mode.mdx

@@ -94,7 +94,7 @@ git checkout beta/endless-mode
 npm install
 
 # Restart the worker
-claude-mem restart
+npm run worker:restart
 ```
 
 **To return to stable:**
@@ -103,7 +103,7 @@ claude-mem restart
 cd ~/.claude/plugins/marketplaces/thedotmack/
 git checkout main
 npm install
-claude-mem restart
+npm run worker:restart
 ```
 
 ## Summary

docs/public/hooks-architecture.mdx

@@ -534,7 +534,7 @@ npm run worker:status
 npm run worker:logs
 
 # Restart
-claude-mem restart
+npm run worker:restart
 
 # Stop
 npm run worker:stop

docs/public/platform-integration.mdx

@@ -57,7 +57,7 @@ CLAUDE_MEM_PYTHON_VERSION=3.13              # Python version for chroma-mcp
 ```bash
 npm run build                 # Compile TypeScript (hooks + worker)
 npm run sync-marketplace      # Copy to ~/.claude/plugins
-claude-mem restart        # Restart worker
+npm run worker:restart        # Restart worker
 npm run worker:logs           # View worker logs
 npm run worker:status         # Check worker status
 ```

docs/public/troubleshooting.mdx

@@ -48,14 +48,14 @@ The skill includes comprehensive diagnostics, automated repair sequences, and de
 
 4. Restart worker service:
    ```bash
-   claude-mem restart
+   npm run worker:restart
    ```
 
 5. Check for port conflicts:
    ```bash
    # If port 37777 is in use by another service
    export CLAUDE_MEM_WORKER_PORT=38000
-   claude-mem restart
+   npm run worker:restart
    ```
 
 ### Theme Toggle Not Persisting
@@ -110,7 +110,7 @@ The skill includes comprehensive diagnostics, automated repair sequences, and de
 
 5. Restart worker and refresh browser:
    ```bash
-   claude-mem restart
+   npm run worker:restart
    ```
 
 ### Chroma/Python Dependency Issues (v5.0.0+)
@@ -225,7 +225,7 @@ The skill includes comprehensive diagnostics, automated repair sequences, and de
 3. Or use a different port:
    ```bash
    export CLAUDE_MEM_WORKER_PORT=38000
-   claude-mem restart
+   npm run worker:restart
    ```
 
 4. Verify new port:
@@ -282,7 +282,7 @@ The skill includes comprehensive diagnostics, automated repair sequences, and de
 
 4. Restart worker:
    ```bash
-   claude-mem restart
+   npm run worker:restart
    ```
 
 ### Manual Recovery for Stuck Observations
@@ -839,7 +839,7 @@ sqlite3 ~/.claude-mem/claude-mem.db "
 
 2. Restart worker:
    ```bash
-   claude-mem restart
+   npm run worker:restart
    ```
 
 3. Clean up old data (see "Database Too Large" above)
@@ -916,7 +916,7 @@ sqlite3 ~/.claude-mem/claude-mem.db "
 
 ```bash
 export DEBUG=claude-mem:*
-claude-mem restart
+npm run worker:restart
 npm run worker:logs
 ```
 
@@ -976,7 +976,7 @@ SELECT created_at, tool_name FROM observations ORDER BY created_at DESC LIMIT 10
 
 **Cause**: Worker not running or port mismatch.
 
-**Solution**: Restart worker with `claude-mem restart`.
+**Solution**: Restart worker with `npm run worker:restart`.
 
 ### "Database is locked"
 

docs/public/usage/gemini-provider.mdx

@@ -0,0 +1,172 @@
+---
+title: "Gemini Provider"
+description: "Use Google's Gemini API as an alternative to Claude for observation extraction"
+---
+
+# Gemini Provider
+
+Claude-mem supports Google's Gemini API as an alternative to the Claude Agent SDK for extracting observations from your sessions. This can significantly reduce costs since Gemini offers a generous free tier.
+
+<Warning>
+**Free Tier Rate Limits**: Without billing enabled, Gemini has strict rate limits (5-10 RPM). Enable billing on your Google Cloud project to unlock 1000-4000 RPM while still using the free quota.
+</Warning>
+
+## Why Use Gemini?
+
+- **Cost savings**: The free tier covers most individual usage patterns
+- **Same quality**: Gemini extracts observations using the same XML format as Claude
+- **Seamless fallback**: Automatically falls back to Claude if Gemini is unavailable
+- **Hot-swappable**: Switch providers without restarting the worker
+
+## Getting a Free API Key
+
+1. Go to the [Google AI Studio API Key page](https://aistudio.google.com/app/apikey)
+2. Sign in with your Google account
+3. Accept the Terms of Service and privacy policies
+4. Click the **Create API key** button
+5. Choose a Google Cloud project or create a new one
+6. Copy and securely store the generated API key
+
+<Tip>
+**No billing required** to get started, but we recommend enabling billing to unlock higher rate limits (1000-4000 RPM vs 5-10 RPM) while still using the free quota.
+</Tip>
+
+## Configuration
+
+### Settings
+
+| Setting | Values | Default | Description |
+|---------|--------|---------|-------------|
+| `CLAUDE_MEM_PROVIDER` | `claude`, `gemini` | `claude` | AI provider for observation extraction |
+| `CLAUDE_MEM_GEMINI_API_KEY` | string | — | Your Gemini API key |
+| `CLAUDE_MEM_GEMINI_MODEL` | `gemini-2.5-flash-lite`, `gemini-2.5-flash`, `gemini-3-flash` | `gemini-2.5-flash-lite` | Gemini model to use |
+| `CLAUDE_MEM_GEMINI_BILLING_ENABLED` | `true`, `false` | `false` | Skip rate limiting if billing is enabled on Google Cloud |
+
+### Using the Settings UI
+
+1. Open the viewer at http://localhost:37777
+2. Click the **gear icon** to open Settings
+3. Under **AI Provider**, select **Gemini**
+4. Enter your Gemini API key
+5. Optionally select a different model
+
+Settings are applied immediately—no restart required.
+
+### Manual Configuration
+
+Edit `~/.claude-mem/settings.json`:
+
+```json
+{
+  "CLAUDE_MEM_PROVIDER": "gemini",
+  "CLAUDE_MEM_GEMINI_API_KEY": "your-api-key-here",
+  "CLAUDE_MEM_GEMINI_MODEL": "gemini-2.5-flash-lite",
+  "CLAUDE_MEM_GEMINI_BILLING_ENABLED": "true"
+}
+```
+
+Alternatively, set the API key via environment variable:
+
+```bash
+export GEMINI_API_KEY="your-api-key-here"
+```
+
+The settings file takes precedence over the environment variable.
+
+## Available Models
+
+| Model | Free Tier RPM | Notes |
+|-------|--------------|-------|
+| `gemini-2.5-flash-lite` | 10 | Default, recommended for free tier (highest RPM) |
+| `gemini-2.5-flash` | 5 | Higher capability, lower rate limit |
+| `gemini-3-flash` | 5 | Latest model, lower rate limit |
+
+## Provider Switching
+
+You can switch between Claude and Gemini at any time:
+
+- **No restart required**: Changes take effect on the next observation
+- **Conversation history preserved**: When switching mid-session, the new provider sees the full conversation context
+- **Seamless transition**: Both providers use the same observation format
+
+### Switching via UI
+
+1. Open Settings in the viewer
+2. Change the **AI Provider** dropdown
+3. The next observation will use the new provider
+
+### Switching via Settings File
+
+```json
+{
+  "CLAUDE_MEM_PROVIDER": "gemini"
+}
+```
+
+## Fallback Behavior
+
+If Gemini is selected but encounters errors, claude-mem automatically falls back to the Claude Agent SDK:
+
+**Triggers fallback:**
+- Rate limiting (HTTP 429)
+- Server errors (HTTP 5xx)
+- Network issues (connection refused, timeout)
+
+**Does not trigger fallback:**
+- Missing API key (logs warning, uses Claude from start)
+- Invalid API key (fails with error)
+
+When fallback occurs:
+1. A warning is logged
+2. Any in-progress messages are reset to pending
+3. Claude SDK takes over with the full conversation context
+
+## Troubleshooting
+
+### "Gemini API key not configured"
+
+Either:
+- Set `CLAUDE_MEM_GEMINI_API_KEY` in `~/.claude-mem/settings.json`, or
+- Set the `GEMINI_API_KEY` environment variable
+
+### Rate Limiting
+
+Google has two rate limit tiers for free usage:
+
+**Without billing (API key only):**
+
+| Model | RPM | TPM |
+|-------|-----|-----|
+| gemini-2.5-flash-lite | 10 | 250K |
+| gemini-2.5-flash | 5 | 250K |
+| gemini-3-flash | 5 | 250K |
+
+Claude-mem enforces these limits automatically with built-in delays between requests. Processing may be slower but stays within limits.
+
+**With billing enabled (still free tier):**
+
+| Model | RPM | TPM |
+|-------|-----|-----|
+| gemini-2.5-flash-lite | 4,000 | 4M |
+| gemini-2.5-flash | 1,000 | 1M |
+| gemini-3-flash | 1,000 | 1M |
+
+<Tip>
+**Recommended**: Enable billing on your Google Cloud project to unlock much higher rate limits. You won't be charged unless you exceed the generous free quota. This allows claude-mem to process observations instantly instead of waiting between requests.
+</Tip>
+
+If you hit rate limits:
+- Claude-mem automatically falls back to Claude SDK
+- Or switch back to Claude as your primary provider
+
+### Observation Quality
+
+If observations seem lower quality with Gemini:
+- Note that Claude typically produces slightly higher quality observations
+- Consider using Gemini for cost savings and Claude for important projects
+
+## Next Steps
+
+- [Configuration](../configuration) - Full settings reference
+- [Getting Started](getting-started) - Basic usage guide
+- [Troubleshooting](../troubleshooting) - Common issues

docs/public/usage/getting-started.mdx

@@ -86,7 +86,7 @@ npm run worker:start
 npm run worker:stop
 
 # Restart worker service
-claude-mem restart
+npm run worker:restart
 
 # View worker logs
 npm run worker:logs

docs/public/usage/manual-recovery.mdx

@@ -258,7 +258,7 @@ sqlite3 ~/.claude-mem/claude-mem.db "
 
 3. **Restart worker**:
    ```bash
-   claude-mem restart
+   npm run worker:restart
    ```
 
 4. **Check database integrity**:
@@ -308,7 +308,7 @@ bun scripts/check-pending-queue.ts --process
 4. **Increase worker memory** (if using custom runner):
    ```bash
    export NODE_OPTIONS="--max-old-space-size=4096"
-   claude-mem restart
+   npm run worker:restart
    ```
 
 ## Advanced Usage

docs/public/usage/openrouter-provider.mdx

@@ -0,0 +1,320 @@
+---
+title: "OpenRouter Provider"
+description: "Access 100+ AI models through OpenRouter's unified API, including free models for cost-effective observation extraction"
+---
+
+# OpenRouter Provider
+
+Claude-mem supports [OpenRouter](https://openrouter.ai) as an alternative provider for observation extraction. OpenRouter provides a unified API to access 100+ models from different providers including Google, Meta, Mistral, DeepSeek, and many others—often with generous free tiers.
+
+<Tip>
+**Free Models Available**: OpenRouter offers several completely free models, making it an excellent choice for reducing observation extraction costs to zero while maintaining quality.
+</Tip>
+
+## Why Use OpenRouter?
+
+- **Access to 100+ models**: Choose from models across multiple providers through one API
+- **Free tier options**: Several high-quality models are completely free to use
+- **Cost flexibility**: Pay-as-you-go pricing on premium models with no commitments
+- **Seamless fallback**: Automatically falls back to Claude if OpenRouter is unavailable
+- **Hot-swappable**: Switch providers without restarting the worker
+- **Multi-turn conversations**: Full conversation history maintained across API calls
+
+## Free Models on OpenRouter
+
+OpenRouter actively supports democratizing AI access by offering free models. These are production-ready models suitable for observation extraction.
+
+### Featured Free Models
+
+| Model | ID | Parameters | Context | Best For |
+|-------|------|------------|---------|----------|
+| **Xiaomi MiMo-V2-Flash** | `xiaomi/mimo-v2-flash:free` | 309B (15B active, MoE) | 256K | Reasoning, coding, agents |
+| **Gemini 2.0 Flash** | `google/gemini-2.0-flash-exp:free` | — | 1M | General purpose |
+| **Gemini 2.5 Flash** | `google/gemini-2.5-flash-preview:free` | — | 1M | Latest capabilities |
+| **DeepSeek R1** | `deepseek/deepseek-r1:free` | 671B | 64K | Reasoning, analysis |
+| **Llama 3.1 70B** | `meta-llama/llama-3.1-70b-instruct:free` | 70B | 128K | General purpose |
+| **Llama 3.1 8B** | `meta-llama/llama-3.1-8b-instruct:free` | 8B | 128K | Fast, lightweight |
+| **Mistral Nemo** | `mistralai/mistral-nemo:free` | 12B | 128K | Efficient performance |
+
+<Note>
+**Default Model**: Claude-mem uses `xiaomi/mimo-v2-flash:free` by default—a 309B parameter mixture-of-experts model that ranks #1 on SWE-bench Verified and excels at coding and reasoning tasks.
+</Note>
+
+### Free Model Considerations
+
+- **Rate limits**: Free models may have stricter rate limits than paid models
+- **Availability**: Free capacity depends on provider partnerships and demand
+- **Queue times**: During peak usage, requests may be queued briefly
+- **Max tokens**: Most free models support 65,536 completion tokens
+
+All free models support:
+- Tool use and function calling
+- Temperature and sampling controls
+- Stop sequences
+- Streaming responses
+
+## Getting an API Key
+
+1. Go to [OpenRouter](https://openrouter.ai)
+2. Sign in with Google, GitHub, or email
+3. Navigate to [API Keys](https://openrouter.ai/keys)
+4. Click **Create Key**
+5. Copy and securely store your API key
+
+<Tip>
+**Free to start**: No credit card required to create an account or use free models. Add credits only if you want to use premium models.
+</Tip>
+
+## Configuration
+
+### Settings
+
+| Setting | Values | Default | Description |
+|---------|--------|---------|-------------|
+| `CLAUDE_MEM_PROVIDER` | `claude`, `gemini`, `openrouter` | `claude` | AI provider for observation extraction |
+| `CLAUDE_MEM_OPENROUTER_API_KEY` | string | — | Your OpenRouter API key |
+| `CLAUDE_MEM_OPENROUTER_MODEL` | string | `xiaomi/mimo-v2-flash:free` | Model identifier (see list above) |
+| `CLAUDE_MEM_OPENROUTER_MAX_CONTEXT_MESSAGES` | number | `20` | Max messages in conversation history |
+| `CLAUDE_MEM_OPENROUTER_MAX_TOKENS` | number | `100000` | Token budget safety limit |
+| `CLAUDE_MEM_OPENROUTER_SITE_URL` | string | — | Optional: URL for analytics attribution |
+| `CLAUDE_MEM_OPENROUTER_APP_NAME` | string | `claude-mem` | Optional: App name for analytics |
+
+### Using the Settings UI
+
+1. Open the viewer at http://localhost:37777
+2. Click the **gear icon** to open Settings
+3. Under **AI Provider**, select **OpenRouter**
+4. Enter your OpenRouter API key
+5. Optionally select a different model
+
+Settings are applied immediately—no restart required.
+
+### Manual Configuration
+
+Edit `~/.claude-mem/settings.json`:
+
+```json
+{
+  "CLAUDE_MEM_PROVIDER": "openrouter",
+  "CLAUDE_MEM_OPENROUTER_API_KEY": "sk-or-v1-your-key-here",
+  "CLAUDE_MEM_OPENROUTER_MODEL": "xiaomi/mimo-v2-flash:free"
+}
+```
+
+Alternatively, set the API key via environment variable:
+
+```bash
+export OPENROUTER_API_KEY="sk-or-v1-your-key-here"
+```
+
+The settings file takes precedence over the environment variable.
+
+## Model Selection Guide
+
+### For Free Usage (No Cost)
+
+**Recommended**: `xiaomi/mimo-v2-flash:free`
+- Best-in-class performance on coding benchmarks
+- 256K context window handles large observations
+- 65K max completion tokens
+- Mixture-of-experts architecture (15B active parameters)
+
+**Alternatives**:
+- `google/gemini-2.0-flash-exp:free` - 1M context, Google's flagship
+- `deepseek/deepseek-r1:free` - Excellent reasoning capabilities
+- `meta-llama/llama-3.1-70b-instruct:free` - Strong general purpose
+
+### For Paid Usage (Higher Quality/Speed)
+
+| Model | Price (per 1M tokens) | Best For |
+|-------|----------------------|----------|
+| `anthropic/claude-3.5-sonnet` | $3 in / $15 out | Highest quality observations |
+| `google/gemini-2.0-flash` | $0.075 in / $0.30 out | Fast, cost-effective |
+| `openai/gpt-4o` | $2.50 in / $10 out | GPT-4 quality |
+
+## Context Window Management
+
+OpenRouter agent implements intelligent context management to prevent runaway costs:
+
+### Automatic Truncation
+
+The agent uses a sliding window strategy:
+1. Checks if message count exceeds `MAX_CONTEXT_MESSAGES` (default: 20)
+2. Checks if estimated tokens exceed `MAX_TOKENS` (default: 100,000)
+3. If limits exceeded, keeps most recent messages only
+4. Logs warnings with dropped message counts
+
+### Token Estimation
+
+- Conservative estimate: 1 token ≈ 4 characters
+- Used for proactive context management
+- Actual usage logged from API response
+
+### Cost Tracking
+
+Logs include detailed usage information:
+
+```
+OpenRouter API usage: {
+  model: "xiaomi/mimo-v2-flash:free",
+  inputTokens: 2500,
+  outputTokens: 1200,
+  totalTokens: 3700,
+  estimatedCostUSD: "0.00",
+  messagesInContext: 8
+}
+```
+
+## Provider Switching
+
+You can switch between providers at any time:
+
+- **No restart required**: Changes take effect on the next observation
+- **Conversation history preserved**: When switching mid-session, the new provider sees the full conversation context
+- **Seamless transition**: All providers use the same observation format
+
+### Switching via UI
+
+1. Open Settings in the viewer
+2. Change the **AI Provider** dropdown
+3. The next observation will use the new provider
+
+### Switching via Settings File
+
+```json
+{
+  "CLAUDE_MEM_PROVIDER": "openrouter"
+}
+```
+
+## Fallback Behavior
+
+If OpenRouter encounters errors, claude-mem automatically falls back to the Claude Agent SDK:
+
+**Triggers fallback:**
+- Rate limiting (HTTP 429)
+- Server errors (HTTP 500, 502, 503)
+- Network issues (connection refused, timeout)
+- Generic fetch failures
+
+**Does not trigger fallback:**
+- Missing API key (logs warning, uses Claude from start)
+- Invalid API key (fails with error)
+
+When fallback occurs:
+1. A warning is logged
+2. Any in-progress messages are reset to pending
+3. Claude SDK takes over with the full conversation context
+
+<Note>
+**Fallback is transparent**: Your observations continue processing without interruption. The fallback preserves all conversation context.
+</Note>
+
+## Multi-Turn Conversation Support
+
+OpenRouter agent maintains full conversation history across API calls:
+
+```
+Session Created
+  ↓
+Load Pending Messages (observations from queue)
+  ↓
+For each message:
+  → Add to conversation history
+  → Call OpenRouter API with FULL history
+  → Parse XML response
+  → Store observations in database
+  → Sync to Chroma vector DB
+  ↓
+Session complete
+```
+
+This enables:
+- Coherent multi-turn exchanges
+- Context preservation across observations
+- Seamless provider switching mid-session
+
+## Troubleshooting
+
+### "OpenRouter API key not configured"
+
+Either:
+- Set `CLAUDE_MEM_OPENROUTER_API_KEY` in `~/.claude-mem/settings.json`, or
+- Set the `OPENROUTER_API_KEY` environment variable
+
+### Rate Limiting
+
+Free models may have rate limits during peak usage. If you hit rate limits:
+- Claude-mem automatically falls back to Claude SDK
+- Consider switching to a different free model
+- Add credits for premium model access
+
+### Model Not Found
+
+Verify the model ID is correct:
+- Check [OpenRouter Models](https://openrouter.ai/models) for current availability
+- Use the `:free` suffix for free model variants
+- Model IDs are case-sensitive
+
+### High Token Usage Warning
+
+If you see warnings about high token usage (>50,000 per request):
+- Reduce `CLAUDE_MEM_OPENROUTER_MAX_CONTEXT_MESSAGES`
+- Reduce `CLAUDE_MEM_OPENROUTER_MAX_TOKENS`
+- Consider a model with larger context window
+
+### Connection Errors
+
+If you see connection errors:
+- Check your internet connection
+- Verify OpenRouter service status at [status.openrouter.ai](https://status.openrouter.ai)
+- The agent will automatically fall back to Claude
+
+## API Details
+
+OpenRouter uses an OpenAI-compatible REST API:
+
+**Endpoint**: `https://openrouter.ai/api/v1/chat/completions`
+
+**Headers**:
+```
+Authorization: Bearer {apiKey}
+HTTP-Referer: https://github.com/thedotmack/claude-mem
+X-Title: claude-mem
+Content-Type: application/json
+```
+
+**Request Format**:
+```json
+{
+  "model": "xiaomi/mimo-v2-flash:free",
+  "messages": [
+    {"role": "system", "content": "..."},
+    {"role": "user", "content": "..."}
+  ],
+  "temperature": 0.3,
+  "max_tokens": 4096
+}
+```
+
+## Comparing Providers
+
+| Feature | Claude (SDK) | Gemini | OpenRouter |
+|---------|-------------|--------|------------|
+| **Cost** | Pay per token | Free tier + paid | Free models + paid |
+| **Models** | Claude only | Gemini only | 100+ models |
+| **Quality** | Highest | High | Varies by model |
+| **Rate limits** | Based on tier | 5-4000 RPM | Varies by model |
+| **Fallback** | N/A (primary) | → Claude | → Claude |
+| **Setup** | Automatic | API key required | API key required |
+
+<Tip>
+**Recommendation**: Start with OpenRouter's free `xiaomi/mimo-v2-flash:free` model for zero-cost observation extraction. If you need higher quality or encounter rate limits, switch to Claude or add OpenRouter credits for premium models.
+</Tip>
+
+## Next Steps
+
+- [Configuration](../configuration) - Full settings reference
+- [Gemini Provider](gemini-provider) - Alternative free provider
+- [Getting Started](getting-started) - Basic usage guide
+- [Troubleshooting](../troubleshooting) - Common issues

docs/public/usage/private-tags.mdx

@@ -176,7 +176,7 @@ This design ensures that private content never reaches the database, search indi
 1. Verify correct syntax: `<private>content</private>`
 2. Check `~/.claude-mem/silent.log` for errors
 3. Ensure worker is running: `npm run worker:status`
-4. Restart worker: `claude-mem restart`
+4. Restart worker: `npm run worker:restart`
 
 ### Partial Content Stored
 

docs/public/usage/search-tools.mdx

@@ -364,7 +364,7 @@ If search isn't working, check the worker service:
 
 ```bash
 npm run worker:status       # Check worker status
-claude-mem restart      # Restart if needed
+npm run worker:restart      # Restart if needed
 npm run worker:logs         # View logs
 ```
 

package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-mem",
-  "version": "8.1.0",
+  "version": "8.2.3",
   "description": "Memory compression system for Claude Code - persist context across sessions",
   "keywords": [
     "claude",
@@ -31,6 +31,7 @@
     "bun": ">=1.0.0"
   },
   "scripts": {
+    "dev": "npm run build-and-sync",
     "build": "node scripts/build-hooks.js",
     "build-and-sync": "npm run build && npm run sync-marketplace && sleep 1 && cd ~/.claude/plugins/marketplaces/thedotmack && npm run worker:restart",
     "sync-marketplace": "node scripts/sync-marketplace.cjs",

plugin/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-mem",
-  "version": "8.1.0",
+  "version": "8.2.3",
   "description": "Persistent memory system for Claude Code - seamlessly preserve context across sessions",
   "author": {
     "name": "Alex Newman"

plugin/hooks/hooks.json

@@ -7,12 +7,17 @@
         "hooks": [
           {
             "type": "command",
-            "command": "bun \"${CLAUDE_PLUGIN_ROOT}/scripts/worker-cli.js\" restart",
-            "timeout": 30
+            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/smart-install.js\"",
+            "timeout": 300
           },
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/smart-install.js\" && node \"${CLAUDE_PLUGIN_ROOT}/scripts/context-hook.js\"",
+            "command": "bun \"${CLAUDE_PLUGIN_ROOT}/scripts/worker-service.cjs\" start",
+            "timeout": 180
+          },
+          {
+            "type": "command",
+            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/context-hook.js\"",
             "timeout": 300
           },
           {
@@ -28,13 +33,13 @@
         "hooks": [
           {
             "type": "command",
-            "command": "bun \"${CLAUDE_PLUGIN_ROOT}/scripts/worker-cli.js\" start",
-            "timeout": 30
+            "command": "bun \"${CLAUDE_PLUGIN_ROOT}/scripts/worker-service.cjs\" start",
+            "timeout": 180
           },
           {
             "type": "command",
             "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/new-hook.js\"",
-            "timeout": 120
+            "timeout": 300
           }
         ]
       }
@@ -45,13 +50,13 @@
         "hooks": [
           {
             "type": "command",
-            "command": "bun \"${CLAUDE_PLUGIN_ROOT}/scripts/worker-cli.js\" start",
-            "timeout": 30
+            "command": "bun \"${CLAUDE_PLUGIN_ROOT}/scripts/worker-service.cjs\" start",
+            "timeout": 180
           },
           {
             "type": "command",
             "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/save-hook.js\"",
-            "timeout": 120
+            "timeout": 300
           }
         ]
       }
@@ -61,13 +66,13 @@
         "hooks": [
           {
             "type": "command",
-            "command": "bun \"${CLAUDE_PLUGIN_ROOT}/scripts/worker-cli.js\" start",
-            "timeout": 30
+            "command": "bun \"${CLAUDE_PLUGIN_ROOT}/scripts/worker-service.cjs\" start",
+            "timeout": 180
           },
           {
             "type": "command",
             "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/summary-hook.js\"",
-            "timeout": 120
+            "timeout": 300
           }
         ]
       }

plugin/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-mem-plugin",
-  "version": "8.1.0",
+  "version": "8.2.3",
   "private": true,
   "description": "Runtime dependencies for claude-mem bundled hooks",
   "type": "module",

plugin/scripts/context-hook.js

@@ -1,14 +1,14 @@
 #!/usr/bin/env bun
-import{stdin as M}from"process";import C from"path";import{homedir as x}from"os";import{readFileSync as b}from"fs";import{readFileSync as $,writeFileSync as v,existsSync as w}from"fs";import{join as P}from"path";import{homedir as W}from"os";var A="bugfix,feature,refactor,discovery,decision,change",d="how-it-works,why-it-exists,what-changed,problem-solution,gotcha,pattern,trade-off";var _=class{static DEFAULTS={CLAUDE_MEM_MODEL:"claude-sonnet-4-5",CLAUDE_MEM_CONTEXT_OBSERVATIONS:"50",CLAUDE_MEM_WORKER_PORT:"37777",CLAUDE_MEM_WORKER_HOST:"127.0.0.1",CLAUDE_MEM_SKIP_TOOLS:"ListMcpResourcesTool,SlashCommand,Skill,TodoWrite,AskUserQuestion",CLAUDE_MEM_DATA_DIR:P(W(),".claude-mem"),CLAUDE_MEM_LOG_LEVEL:"INFO",CLAUDE_MEM_PYTHON_VERSION:"3.13",CLAUDE_CODE_PATH:"",CLAUDE_MEM_MODE:"code",CLAUDE_MEM_CONTEXT_SHOW_READ_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_WORK_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_AMOUNT:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_PERCENT:"true",CLAUDE_MEM_CONTEXT_OBSERVATION_TYPES:A,CLAUDE_MEM_CONTEXT_OBSERVATION_CONCEPTS:d,CLAUDE_MEM_CONTEXT_FULL_COUNT:"5",CLAUDE_MEM_CONTEXT_FULL_FIELD:"narrative",CLAUDE_MEM_CONTEXT_SESSION_COUNT:"10",CLAUDE_MEM_CONTEXT_SHOW_LAST_SUMMARY:"true",CLAUDE_MEM_CONTEXT_SHOW_LAST_MESSAGE:"false"};static getAllDefaults(){return{...this.DEFAULTS}}static get(t){return this.DEFAULTS[t]}static getInt(t){let r=this.get(t);return parseInt(r,10)}static getBool(t){return this.get(t)==="true"}static loadFromFile(t){try{if(!w(t))return this.getAllDefaults();let r=$(t,"utf-8"),e=JSON.parse(r),n=e;if(e.env&&typeof e.env=="object"){n=e.env;try{v(t,JSON.stringify(n,null,2),"utf-8"),E.info("SETTINGS","Migrated settings file from nested to flat schema",{settingsPath:t})}catch(i){E.warn("SETTINGS","Failed to auto-migrate settings file",{settingsPath:t},i)}}let s={...this.DEFAULTS};for(let i of Object.keys(this.DEFAULTS))n[i]!==void 0&&(s[i]=n[i]);return s}catch(r){return E.warn("SETTINGS","Failed to load settings, using defaults",{settingsPath:t},r),this.getAllDefaults()}}};var T=(s=>(s[s.DEBUG=0]="DEBUG",s[s.INFO=1]="INFO",s[s.WARN=2]="WARN",s[s.ERROR=3]="ERROR",s[s.SILENT=4]="SILENT",s))(T||{}),O=class{level=null;useColor;constructor(){this.useColor=process.stdout.isTTY??!1}getLevel(){if(this.level===null){let t=_.get("CLAUDE_MEM_LOG_LEVEL").toUpperCase();this.level=T[t]??1}return this.level}correlationId(t,r){return`obs-${t}-${r}`}sessionId(t){return`session-${t}`}formatData(t){if(t==null)return"";if(typeof t=="string")return t;if(typeof t=="number"||typeof t=="boolean")return t.toString();if(typeof t=="object"){if(t instanceof Error)return this.getLevel()===0?`${t.message}
-${t.stack}`:t.message;if(Array.isArray(t))return`[${t.length} items]`;let r=Object.keys(t);return r.length===0?"{}":r.length<=3?JSON.stringify(t):`{${r.length} keys: ${r.slice(0,3).join(", ")}...}`}return String(t)}formatTool(t,r){if(!r)return t;let e=typeof r=="string"?JSON.parse(r):r;if(t==="Bash"&&e.command)return`${t}(${e.command})`;if(e.file_path)return`${t}(${e.file_path})`;if(e.notebook_path)return`${t}(${e.notebook_path})`;if(t==="Glob"&&e.pattern)return`${t}(${e.pattern})`;if(t==="Grep"&&e.pattern)return`${t}(${e.pattern})`;if(e.url)return`${t}(${e.url})`;if(e.query)return`${t}(${e.query})`;if(t==="Task"){if(e.subagent_type)return`${t}(${e.subagent_type})`;if(e.description)return`${t}(${e.description})`}return t==="Skill"&&e.skill?`${t}(${e.skill})`:t==="LSP"&&e.operation?`${t}(${e.operation})`:t}formatTimestamp(t){let r=t.getFullYear(),e=String(t.getMonth()+1).padStart(2,"0"),n=String(t.getDate()).padStart(2,"0"),s=String(t.getHours()).padStart(2,"0"),i=String(t.getMinutes()).padStart(2,"0"),a=String(t.getSeconds()).padStart(2,"0"),S=String(t.getMilliseconds()).padStart(3,"0");return`${r}-${e}-${n} ${s}:${i}:${a}.${S}`}log(t,r,e,n,s){if(t<this.getLevel())return;let i=this.formatTimestamp(new Date),a=T[t].padEnd(5),S=r.padEnd(6),c="";n?.correlationId?c=`[${n.correlationId}] `:n?.sessionId&&(c=`[session-${n.sessionId}] `);let l="";s!=null&&(this.getLevel()===0&&typeof s=="object"?l=`
-`+JSON.stringify(s,null,2):l=" "+this.formatData(s));let p="";if(n){let{sessionId:B,sdkSessionId:Y,correlationId:J,...L}=n;Object.keys(L).length>0&&(p=` {${Object.entries(L).map(([N,y])=>`${N}=${y}`).join(", ")}}`)}let m=`[${i}] [${a}] [${S}] ${c}${e}${p}${l}`;t===3?console.error(m):console.log(m)}debug(t,r,e,n){this.log(0,t,r,e,n)}info(t,r,e,n){this.log(1,t,r,e,n)}warn(t,r,e,n){this.log(2,t,r,e,n)}error(t,r,e,n){this.log(3,t,r,e,n)}dataIn(t,r,e,n){this.info(t,`\u2192 ${r}`,e,n)}dataOut(t,r,e,n){this.info(t,`\u2190 ${r}`,e,n)}success(t,r,e,n){this.info(t,`\u2713 ${r}`,e,n)}failure(t,r,e,n){this.error(t,`\u2717 ${r}`,e,n)}timing(t,r,e,n){this.info(t,`\u23F1 ${r}`,n,{duration:`${e}ms`})}happyPathError(t,r,e,n,s=""){let c=((new Error().stack||"").split(`
-`)[2]||"").match(/at\s+(?:.*\s+)?\(?([^:]+):(\d+):(\d+)\)?/),l=c?`${c[1].split("/").pop()}:${c[2]}`:"unknown",p={...e,location:l};return this.warn(t,`[HAPPY-PATH] ${r}`,p,n),s}},E=new O;var u={DEFAULT:12e4,HEALTH_CHECK:1e3,WORKER_STARTUP_WAIT:1e3,WORKER_STARTUP_RETRIES:15,PRE_RESTART_SETTLE_DELAY:2e3,WINDOWS_MULTIPLIER:1.5};function D(o){return process.platform==="win32"?Math.round(o*u.WINDOWS_MULTIPLIER):o}function h(o={}){let{port:t,includeSkillFallback:r=!1,customPrefix:e,actualError:n}=o,s=e||"Worker service connection failed.",i=t?` (port ${t})`:"",a=`${s}${i}
+import{stdin as A}from"process";import p from"path";import{homedir as x}from"os";import{readFileSync as b}from"fs";import{readFileSync as P,writeFileSync as $,existsSync as v}from"fs";import{join as w}from"path";import{homedir as W}from"os";var D="bugfix,feature,refactor,discovery,decision,change",m="how-it-works,why-it-exists,what-changed,problem-solution,gotcha,pattern,trade-off";var c=class{static DEFAULTS={CLAUDE_MEM_MODEL:"claude-sonnet-4-5",CLAUDE_MEM_CONTEXT_OBSERVATIONS:"50",CLAUDE_MEM_WORKER_PORT:"37777",CLAUDE_MEM_WORKER_HOST:"127.0.0.1",CLAUDE_MEM_SKIP_TOOLS:"ListMcpResourcesTool,SlashCommand,Skill,TodoWrite,AskUserQuestion",CLAUDE_MEM_PROVIDER:"claude",CLAUDE_MEM_GEMINI_API_KEY:"",CLAUDE_MEM_GEMINI_MODEL:"gemini-2.5-flash-lite",CLAUDE_MEM_GEMINI_RATE_LIMITING_ENABLED:"true",CLAUDE_MEM_OPENROUTER_API_KEY:"",CLAUDE_MEM_OPENROUTER_MODEL:"xiaomi/mimo-v2-flash:free",CLAUDE_MEM_OPENROUTER_SITE_URL:"",CLAUDE_MEM_OPENROUTER_APP_NAME:"claude-mem",CLAUDE_MEM_OPENROUTER_MAX_CONTEXT_MESSAGES:"20",CLAUDE_MEM_OPENROUTER_MAX_TOKENS:"100000",CLAUDE_MEM_DATA_DIR:w(W(),".claude-mem"),CLAUDE_MEM_LOG_LEVEL:"INFO",CLAUDE_MEM_PYTHON_VERSION:"3.13",CLAUDE_CODE_PATH:"",CLAUDE_MEM_MODE:"code",CLAUDE_MEM_CONTEXT_SHOW_READ_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_WORK_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_AMOUNT:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_PERCENT:"true",CLAUDE_MEM_CONTEXT_OBSERVATION_TYPES:D,CLAUDE_MEM_CONTEXT_OBSERVATION_CONCEPTS:m,CLAUDE_MEM_CONTEXT_FULL_COUNT:"5",CLAUDE_MEM_CONTEXT_FULL_FIELD:"narrative",CLAUDE_MEM_CONTEXT_SESSION_COUNT:"10",CLAUDE_MEM_CONTEXT_SHOW_LAST_SUMMARY:"true",CLAUDE_MEM_CONTEXT_SHOW_LAST_MESSAGE:"false"};static getAllDefaults(){return{...this.DEFAULTS}}static get(t){return this.DEFAULTS[t]}static getInt(t){let r=this.get(t);return parseInt(r,10)}static getBool(t){return this.get(t)==="true"}static loadFromFile(t){try{if(!v(t))return this.getAllDefaults();let r=P(t,"utf-8"),e=JSON.parse(r),n=e;if(e.env&&typeof e.env=="object"){n=e.env;try{$(t,JSON.stringify(n,null,2),"utf-8"),_.info("SETTINGS","Migrated settings file from nested to flat schema",{settingsPath:t})}catch(i){_.warn("SETTINGS","Failed to auto-migrate settings file",{settingsPath:t},i)}}let s={...this.DEFAULTS};for(let i of Object.keys(this.DEFAULTS))n[i]!==void 0&&(s[i]=n[i]);return s}catch(r){return _.warn("SETTINGS","Failed to load settings, using defaults",{settingsPath:t},r),this.getAllDefaults()}}};var S=(s=>(s[s.DEBUG=0]="DEBUG",s[s.INFO=1]="INFO",s[s.WARN=2]="WARN",s[s.ERROR=3]="ERROR",s[s.SILENT=4]="SILENT",s))(S||{}),f=class{level=null;useColor;constructor(){this.useColor=process.stdout.isTTY??!1}getLevel(){if(this.level===null){let t=c.get("CLAUDE_MEM_LOG_LEVEL").toUpperCase();this.level=S[t]??1}return this.level}correlationId(t,r){return`obs-${t}-${r}`}sessionId(t){return`session-${t}`}formatData(t){if(t==null)return"";if(typeof t=="string")return t;if(typeof t=="number"||typeof t=="boolean")return t.toString();if(typeof t=="object"){if(t instanceof Error)return this.getLevel()===0?`${t.message}
+${t.stack}`:t.message;if(Array.isArray(t))return`[${t.length} items]`;let r=Object.keys(t);return r.length===0?"{}":r.length<=3?JSON.stringify(t):`{${r.length} keys: ${r.slice(0,3).join(", ")}...}`}return String(t)}formatTool(t,r){if(!r)return t;let e=typeof r=="string"?JSON.parse(r):r;if(t==="Bash"&&e.command)return`${t}(${e.command})`;if(e.file_path)return`${t}(${e.file_path})`;if(e.notebook_path)return`${t}(${e.notebook_path})`;if(t==="Glob"&&e.pattern)return`${t}(${e.pattern})`;if(t==="Grep"&&e.pattern)return`${t}(${e.pattern})`;if(e.url)return`${t}(${e.url})`;if(e.query)return`${t}(${e.query})`;if(t==="Task"){if(e.subagent_type)return`${t}(${e.subagent_type})`;if(e.description)return`${t}(${e.description})`}return t==="Skill"&&e.skill?`${t}(${e.skill})`:t==="LSP"&&e.operation?`${t}(${e.operation})`:t}formatTimestamp(t){let r=t.getFullYear(),e=String(t.getMonth()+1).padStart(2,"0"),n=String(t.getDate()).padStart(2,"0"),s=String(t.getHours()).padStart(2,"0"),i=String(t.getMinutes()).padStart(2,"0"),E=String(t.getSeconds()).padStart(2,"0"),T=String(t.getMilliseconds()).padStart(3,"0");return`${r}-${e}-${n} ${s}:${i}:${E}.${T}`}log(t,r,e,n,s){if(t<this.getLevel())return;let i=this.formatTimestamp(new Date),E=S[t].padEnd(5),T=r.padEnd(6),a="";n?.correlationId?a=`[${n.correlationId}] `:n?.sessionId&&(a=`[session-${n.sessionId}] `);let l="";s!=null&&(this.getLevel()===0&&typeof s=="object"?l=`
+`+JSON.stringify(s,null,2):l=" "+this.formatData(s));let M="";if(n){let{sessionId:Y,sdkSessionId:B,correlationId:J,...L}=n;Object.keys(L).length>0&&(M=` {${Object.entries(L).map(([k,y])=>`${k}=${y}`).join(", ")}}`)}let C=`[${i}] [${E}] [${T}] ${a}${e}${M}${l}`;t===3?console.error(C):console.log(C)}debug(t,r,e,n){this.log(0,t,r,e,n)}info(t,r,e,n){this.log(1,t,r,e,n)}warn(t,r,e,n){this.log(2,t,r,e,n)}error(t,r,e,n){this.log(3,t,r,e,n)}dataIn(t,r,e,n){this.info(t,`\u2192 ${r}`,e,n)}dataOut(t,r,e,n){this.info(t,`\u2190 ${r}`,e,n)}success(t,r,e,n){this.info(t,`\u2713 ${r}`,e,n)}failure(t,r,e,n){this.error(t,`\u2717 ${r}`,e,n)}timing(t,r,e,n){this.info(t,`\u23F1 ${r}`,n,{duration:`${e}ms`})}happyPathError(t,r,e,n,s=""){let a=((new Error().stack||"").split(`
+`)[2]||"").match(/at\s+(?:.*\s+)?\(?([^:]+):(\d+):(\d+)\)?/),l=a?`${a[1].split("/").pop()}:${a[2]}`:"unknown",M={...e,location:l};return this.warn(t,`[HAPPY-PATH] ${r}`,M,n),s}},_=new f;var g={DEFAULT:3e5,HEALTH_CHECK:3e4,WORKER_STARTUP_WAIT:1e3,WORKER_STARTUP_RETRIES:300,PRE_RESTART_SETTLE_DELAY:2e3,WINDOWS_MULTIPLIER:1.5};function R(o){return process.platform==="win32"?Math.round(o*g.WINDOWS_MULTIPLIER):o}function U(o={}){let{port:t,includeSkillFallback:r=!1,customPrefix:e,actualError:n}=o,s=e||"Worker service connection failed.",i=t?` (port ${t})`:"",E=`${s}${i}
 
-`;return a+=`To restart the worker:
-`,a+=`1. Exit Claude Code completely
-`,a+=`2. Run: claude-mem restart
-`,a+="3. Restart Claude Code",r&&(a+=`
+`;return E+=`To restart the worker:
+`,E+=`1. Exit Claude Code completely
+`,E+=`2. Run: npm run worker:restart
+`,E+="3. Restart Claude Code",r&&(E+=`
 
-If that doesn't work, try: /troubleshoot`),n&&(a=`Worker Error: ${n}
+If that doesn't work, try: /troubleshoot`),n&&(E=`Worker Error: ${n}
 
-${a}`),a}var H=C.join(x(),".claude","plugins","marketplaces","thedotmack"),R=D(u.HEALTH_CHECK),f=null;function g(){if(f!==null)return f;let o=C.join(_.get("CLAUDE_MEM_DATA_DIR"),"settings.json"),t=_.loadFromFile(o);return f=parseInt(t.CLAUDE_MEM_WORKER_PORT,10),f}async function F(){let o=g();return(await fetch(`http://127.0.0.1:${o}/api/readiness`,{signal:AbortSignal.timeout(R)})).ok}function K(){let o=C.join(H,"package.json");return JSON.parse(b(o,"utf-8")).version}async function j(){let o=g(),t=await fetch(`http://127.0.0.1:${o}/api/version`,{signal:AbortSignal.timeout(R)});if(!t.ok)throw new Error(`Failed to get worker version: ${t.status}`);return(await t.json()).version}async function X(){let o=K(),t=await j();o!==t&&E.warn("SYSTEM","Worker version mismatch",{pluginVersion:o,workerVersion:t,hint:"Restart worker with: claude-mem worker restart"})}async function U(){for(let r=0;r<25;r++){try{if(await F()){await X();return}}catch{}await new Promise(e=>setTimeout(e,200))}throw new Error(h({port:g(),customPrefix:"Worker did not become ready within 5 seconds."}))}import V from"path";function I(o){if(!o||o.trim()==="")return E.warn("PROJECT_NAME","Empty cwd provided, using fallback",{cwd:o}),"unknown-project";let t=V.basename(o);if(t===""){if(process.platform==="win32"){let e=o.match(/^([A-Z]):\\/i);if(e){let s=`drive-${e[1].toUpperCase()}`;return E.info("PROJECT_NAME","Drive root detected",{cwd:o,projectName:s}),s}}return E.warn("PROJECT_NAME","Root directory detected, using fallback",{cwd:o}),"unknown-project"}return t}async function k(o){await U();let t=o?.cwd??process.cwd(),r=I(t),n=`http://127.0.0.1:${g()}/api/context/inject?project=${encodeURIComponent(r)}`,s=await fetch(n,{signal:AbortSignal.timeout(u.DEFAULT)});if(!s.ok)throw new Error(`Context generation failed: ${s.status}`);return(await s.text()).trim()}var G=process.argv.includes("--colors");if(M.isTTY||G)k(void 0).then(o=>{console.log(o),process.exit(0)});else{let o="";M.on("data",t=>o+=t),M.on("end",async()=>{let t;try{t=o.trim()?JSON.parse(o):void 0}catch(e){throw new Error(`Failed to parse hook input: ${e instanceof Error?e.message:String(e)}`)}let r=await k(t);console.log(JSON.stringify({hookSpecificOutput:{hookEventName:"SessionStart",additionalContext:r}})),process.exit(0)})}
+${E}`),E}var H=p.join(x(),".claude","plugins","marketplaces","thedotmack"),d=R(g.HEALTH_CHECK),O=null;function u(){if(O!==null)return O;let o=p.join(c.get("CLAUDE_MEM_DATA_DIR"),"settings.json"),t=c.loadFromFile(o);return O=parseInt(t.CLAUDE_MEM_WORKER_PORT,10),O}async function F(){let o=u();return(await fetch(`http://127.0.0.1:${o}/api/readiness`,{signal:AbortSignal.timeout(d)})).ok}function G(){let o=p.join(H,"package.json");return JSON.parse(b(o,"utf-8")).version}async function K(){let o=u(),t=await fetch(`http://127.0.0.1:${o}/api/version`,{signal:AbortSignal.timeout(d)});if(!t.ok)throw new Error(`Failed to get worker version: ${t.status}`);return(await t.json()).version}async function X(){let o=G(),t=await K();o!==t&&_.warn("SYSTEM","Worker version mismatch",{pluginVersion:o,workerVersion:t,hint:"Restart worker with: claude-mem worker restart"})}async function N(){for(let r=0;r<25;r++){try{if(await F()){await X();return}}catch{}await new Promise(e=>setTimeout(e,200))}throw new Error(U({port:u(),customPrefix:"Worker did not become ready within 5 seconds."}))}import j from"path";function I(o){if(!o||o.trim()==="")return _.warn("PROJECT_NAME","Empty cwd provided, using fallback",{cwd:o}),"unknown-project";let t=j.basename(o);if(t===""){if(process.platform==="win32"){let e=o.match(/^([A-Z]):\\/i);if(e){let s=`drive-${e[1].toUpperCase()}`;return _.info("PROJECT_NAME","Drive root detected",{cwd:o,projectName:s}),s}}return _.warn("PROJECT_NAME","Root directory detected, using fallback",{cwd:o}),"unknown-project"}return t}async function h(o){await N();let t=o?.cwd??process.cwd(),r=I(t),n=`http://127.0.0.1:${u()}/api/context/inject?project=${encodeURIComponent(r)}`,s=await fetch(n,{signal:AbortSignal.timeout(g.DEFAULT)});if(!s.ok)throw new Error(`Context generation failed: ${s.status}`);return(await s.text()).trim()}var V=process.argv.includes("--colors");if(A.isTTY||V)h(void 0).then(o=>{console.log(o),process.exit(0)});else{let o="";A.on("data",t=>o+=t),A.on("end",async()=>{let t;try{t=o.trim()?JSON.parse(o):void 0}catch(e){throw new Error(`Failed to parse hook input: ${e instanceof Error?e.message:String(e)}`)}let r=await h(t);console.log(JSON.stringify({hookSpecificOutput:{hookEventName:"SessionStart",additionalContext:r}})),process.exit(0)})}

plugin/scripts/new-hook.js

@@ -1,14 +1,14 @@
 #!/usr/bin/env bun
-import{stdin as y}from"process";var f=JSON.stringify({continue:!0,suppressOutput:!0});import C from"path";import{homedir as H}from"os";import{readFileSync as x}from"fs";import{readFileSync as P,writeFileSync as v,existsSync as w}from"fs";import{join as b}from"path";import{homedir as W}from"os";var d="bugfix,feature,refactor,discovery,decision,change",D="how-it-works,why-it-exists,what-changed,problem-solution,gotcha,pattern,trade-off";var g=class{static DEFAULTS={CLAUDE_MEM_MODEL:"claude-sonnet-4-5",CLAUDE_MEM_CONTEXT_OBSERVATIONS:"50",CLAUDE_MEM_WORKER_PORT:"37777",CLAUDE_MEM_WORKER_HOST:"127.0.0.1",CLAUDE_MEM_SKIP_TOOLS:"ListMcpResourcesTool,SlashCommand,Skill,TodoWrite,AskUserQuestion",CLAUDE_MEM_DATA_DIR:b(W(),".claude-mem"),CLAUDE_MEM_LOG_LEVEL:"INFO",CLAUDE_MEM_PYTHON_VERSION:"3.13",CLAUDE_CODE_PATH:"",CLAUDE_MEM_MODE:"code",CLAUDE_MEM_CONTEXT_SHOW_READ_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_WORK_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_AMOUNT:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_PERCENT:"true",CLAUDE_MEM_CONTEXT_OBSERVATION_TYPES:d,CLAUDE_MEM_CONTEXT_OBSERVATION_CONCEPTS:D,CLAUDE_MEM_CONTEXT_FULL_COUNT:"5",CLAUDE_MEM_CONTEXT_FULL_FIELD:"narrative",CLAUDE_MEM_CONTEXT_SESSION_COUNT:"10",CLAUDE_MEM_CONTEXT_SHOW_LAST_SUMMARY:"true",CLAUDE_MEM_CONTEXT_SHOW_LAST_MESSAGE:"false"};static getAllDefaults(){return{...this.DEFAULTS}}static get(t){return this.DEFAULTS[t]}static getInt(t){let r=this.get(t);return parseInt(r,10)}static getBool(t){return this.get(t)==="true"}static loadFromFile(t){try{if(!w(t))return this.getAllDefaults();let r=P(t,"utf-8"),e=JSON.parse(r),n=e;if(e.env&&typeof e.env=="object"){n=e.env;try{v(t,JSON.stringify(n,null,2),"utf-8"),c.info("SETTINGS","Migrated settings file from nested to flat schema",{settingsPath:t})}catch(a){c.warn("SETTINGS","Failed to auto-migrate settings file",{settingsPath:t},a)}}let s={...this.DEFAULTS};for(let a of Object.keys(this.DEFAULTS))n[a]!==void 0&&(s[a]=n[a]);return s}catch(r){return c.warn("SETTINGS","Failed to load settings, using defaults",{settingsPath:t},r),this.getAllDefaults()}}};var T=(s=>(s[s.DEBUG=0]="DEBUG",s[s.INFO=1]="INFO",s[s.WARN=2]="WARN",s[s.ERROR=3]="ERROR",s[s.SILENT=4]="SILENT",s))(T||{}),O=class{level=null;useColor;constructor(){this.useColor=process.stdout.isTTY??!1}getLevel(){if(this.level===null){let t=g.get("CLAUDE_MEM_LOG_LEVEL").toUpperCase();this.level=T[t]??1}return this.level}correlationId(t,r){return`obs-${t}-${r}`}sessionId(t){return`session-${t}`}formatData(t){if(t==null)return"";if(typeof t=="string")return t;if(typeof t=="number"||typeof t=="boolean")return t.toString();if(typeof t=="object"){if(t instanceof Error)return this.getLevel()===0?`${t.message}
-${t.stack}`:t.message;if(Array.isArray(t))return`[${t.length} items]`;let r=Object.keys(t);return r.length===0?"{}":r.length<=3?JSON.stringify(t):`{${r.length} keys: ${r.slice(0,3).join(", ")}...}`}return String(t)}formatTool(t,r){if(!r)return t;let e=typeof r=="string"?JSON.parse(r):r;if(t==="Bash"&&e.command)return`${t}(${e.command})`;if(e.file_path)return`${t}(${e.file_path})`;if(e.notebook_path)return`${t}(${e.notebook_path})`;if(t==="Glob"&&e.pattern)return`${t}(${e.pattern})`;if(t==="Grep"&&e.pattern)return`${t}(${e.pattern})`;if(e.url)return`${t}(${e.url})`;if(e.query)return`${t}(${e.query})`;if(t==="Task"){if(e.subagent_type)return`${t}(${e.subagent_type})`;if(e.description)return`${t}(${e.description})`}return t==="Skill"&&e.skill?`${t}(${e.skill})`:t==="LSP"&&e.operation?`${t}(${e.operation})`:t}formatTimestamp(t){let r=t.getFullYear(),e=String(t.getMonth()+1).padStart(2,"0"),n=String(t.getDate()).padStart(2,"0"),s=String(t.getHours()).padStart(2,"0"),a=String(t.getMinutes()).padStart(2,"0"),i=String(t.getSeconds()).padStart(2,"0"),_=String(t.getMilliseconds()).padStart(3,"0");return`${r}-${e}-${n} ${s}:${a}:${i}.${_}`}log(t,r,e,n,s){if(t<this.getLevel())return;let a=this.formatTimestamp(new Date),i=T[t].padEnd(5),_=r.padEnd(6),E="";n?.correlationId?E=`[${n.correlationId}] `:n?.sessionId&&(E=`[session-${n.sessionId}] `);let l="";s!=null&&(this.getLevel()===0&&typeof s=="object"?l=`
-`+JSON.stringify(s,null,2):l=" "+this.formatData(s));let u="";if(n){let{sessionId:J,sdkSessionId:Y,correlationId:q,...L}=n;Object.keys(L).length>0&&(u=` {${Object.entries(L).map(([I,$])=>`${I}=${$}`).join(", ")}}`)}let M=`[${a}] [${i}] [${_}] ${E}${e}${u}${l}`;t===3?console.error(M):console.log(M)}debug(t,r,e,n){this.log(0,t,r,e,n)}info(t,r,e,n){this.log(1,t,r,e,n)}warn(t,r,e,n){this.log(2,t,r,e,n)}error(t,r,e,n){this.log(3,t,r,e,n)}dataIn(t,r,e,n){this.info(t,`\u2192 ${r}`,e,n)}dataOut(t,r,e,n){this.info(t,`\u2190 ${r}`,e,n)}success(t,r,e,n){this.info(t,`\u2713 ${r}`,e,n)}failure(t,r,e,n){this.error(t,`\u2717 ${r}`,e,n)}timing(t,r,e,n){this.info(t,`\u23F1 ${r}`,n,{duration:`${e}ms`})}happyPathError(t,r,e,n,s=""){let E=((new Error().stack||"").split(`
-`)[2]||"").match(/at\s+(?:.*\s+)?\(?([^:]+):(\d+):(\d+)\)?/),l=E?`${E[1].split("/").pop()}:${E[2]}`:"unknown",u={...e,location:l};return this.warn(t,`[HAPPY-PATH] ${r}`,u,n),s}},c=new O;var m={DEFAULT:12e4,HEALTH_CHECK:1e3,WORKER_STARTUP_WAIT:1e3,WORKER_STARTUP_RETRIES:15,PRE_RESTART_SETTLE_DELAY:2e3,WINDOWS_MULTIPLIER:1.5};function h(o){return process.platform==="win32"?Math.round(o*m.WINDOWS_MULTIPLIER):o}function R(o={}){let{port:t,includeSkillFallback:r=!1,customPrefix:e,actualError:n}=o,s=e||"Worker service connection failed.",a=t?` (port ${t})`:"",i=`${s}${a}
+import{stdin as P}from"process";var T=JSON.stringify({continue:!0,suppressOutput:!0});import A from"path";import{homedir as H}from"os";import{readFileSync as x}from"fs";import{readFileSync as $,writeFileSync as v,existsSync as w}from"fs";import{join as b}from"path";import{homedir as W}from"os";var D="bugfix,feature,refactor,discovery,decision,change",R="how-it-works,why-it-exists,what-changed,problem-solution,gotcha,pattern,trade-off";var g=class{static DEFAULTS={CLAUDE_MEM_MODEL:"claude-sonnet-4-5",CLAUDE_MEM_CONTEXT_OBSERVATIONS:"50",CLAUDE_MEM_WORKER_PORT:"37777",CLAUDE_MEM_WORKER_HOST:"127.0.0.1",CLAUDE_MEM_SKIP_TOOLS:"ListMcpResourcesTool,SlashCommand,Skill,TodoWrite,AskUserQuestion",CLAUDE_MEM_PROVIDER:"claude",CLAUDE_MEM_GEMINI_API_KEY:"",CLAUDE_MEM_GEMINI_MODEL:"gemini-2.5-flash-lite",CLAUDE_MEM_GEMINI_RATE_LIMITING_ENABLED:"true",CLAUDE_MEM_OPENROUTER_API_KEY:"",CLAUDE_MEM_OPENROUTER_MODEL:"xiaomi/mimo-v2-flash:free",CLAUDE_MEM_OPENROUTER_SITE_URL:"",CLAUDE_MEM_OPENROUTER_APP_NAME:"claude-mem",CLAUDE_MEM_OPENROUTER_MAX_CONTEXT_MESSAGES:"20",CLAUDE_MEM_OPENROUTER_MAX_TOKENS:"100000",CLAUDE_MEM_DATA_DIR:b(W(),".claude-mem"),CLAUDE_MEM_LOG_LEVEL:"INFO",CLAUDE_MEM_PYTHON_VERSION:"3.13",CLAUDE_CODE_PATH:"",CLAUDE_MEM_MODE:"code",CLAUDE_MEM_CONTEXT_SHOW_READ_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_WORK_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_AMOUNT:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_PERCENT:"true",CLAUDE_MEM_CONTEXT_OBSERVATION_TYPES:D,CLAUDE_MEM_CONTEXT_OBSERVATION_CONCEPTS:R,CLAUDE_MEM_CONTEXT_FULL_COUNT:"5",CLAUDE_MEM_CONTEXT_FULL_FIELD:"narrative",CLAUDE_MEM_CONTEXT_SESSION_COUNT:"10",CLAUDE_MEM_CONTEXT_SHOW_LAST_SUMMARY:"true",CLAUDE_MEM_CONTEXT_SHOW_LAST_MESSAGE:"false"};static getAllDefaults(){return{...this.DEFAULTS}}static get(t){return this.DEFAULTS[t]}static getInt(t){let r=this.get(t);return parseInt(r,10)}static getBool(t){return this.get(t)==="true"}static loadFromFile(t){try{if(!w(t))return this.getAllDefaults();let r=$(t,"utf-8"),e=JSON.parse(r),n=e;if(e.env&&typeof e.env=="object"){n=e.env;try{v(t,JSON.stringify(n,null,2),"utf-8"),a.info("SETTINGS","Migrated settings file from nested to flat schema",{settingsPath:t})}catch(E){a.warn("SETTINGS","Failed to auto-migrate settings file",{settingsPath:t},E)}}let s={...this.DEFAULTS};for(let E of Object.keys(this.DEFAULTS))n[E]!==void 0&&(s[E]=n[E]);return s}catch(r){return a.warn("SETTINGS","Failed to load settings, using defaults",{settingsPath:t},r),this.getAllDefaults()}}};var O=(s=>(s[s.DEBUG=0]="DEBUG",s[s.INFO=1]="INFO",s[s.WARN=2]="WARN",s[s.ERROR=3]="ERROR",s[s.SILENT=4]="SILENT",s))(O||{}),M=class{level=null;useColor;constructor(){this.useColor=process.stdout.isTTY??!1}getLevel(){if(this.level===null){let t=g.get("CLAUDE_MEM_LOG_LEVEL").toUpperCase();this.level=O[t]??1}return this.level}correlationId(t,r){return`obs-${t}-${r}`}sessionId(t){return`session-${t}`}formatData(t){if(t==null)return"";if(typeof t=="string")return t;if(typeof t=="number"||typeof t=="boolean")return t.toString();if(typeof t=="object"){if(t instanceof Error)return this.getLevel()===0?`${t.message}
+${t.stack}`:t.message;if(Array.isArray(t))return`[${t.length} items]`;let r=Object.keys(t);return r.length===0?"{}":r.length<=3?JSON.stringify(t):`{${r.length} keys: ${r.slice(0,3).join(", ")}...}`}return String(t)}formatTool(t,r){if(!r)return t;let e=typeof r=="string"?JSON.parse(r):r;if(t==="Bash"&&e.command)return`${t}(${e.command})`;if(e.file_path)return`${t}(${e.file_path})`;if(e.notebook_path)return`${t}(${e.notebook_path})`;if(t==="Glob"&&e.pattern)return`${t}(${e.pattern})`;if(t==="Grep"&&e.pattern)return`${t}(${e.pattern})`;if(e.url)return`${t}(${e.url})`;if(e.query)return`${t}(${e.query})`;if(t==="Task"){if(e.subagent_type)return`${t}(${e.subagent_type})`;if(e.description)return`${t}(${e.description})`}return t==="Skill"&&e.skill?`${t}(${e.skill})`:t==="LSP"&&e.operation?`${t}(${e.operation})`:t}formatTimestamp(t){let r=t.getFullYear(),e=String(t.getMonth()+1).padStart(2,"0"),n=String(t.getDate()).padStart(2,"0"),s=String(t.getHours()).padStart(2,"0"),E=String(t.getMinutes()).padStart(2,"0"),i=String(t.getSeconds()).padStart(2,"0"),c=String(t.getMilliseconds()).padStart(3,"0");return`${r}-${e}-${n} ${s}:${E}:${i}.${c}`}log(t,r,e,n,s){if(t<this.getLevel())return;let E=this.formatTimestamp(new Date),i=O[t].padEnd(5),c=r.padEnd(6),_="";n?.correlationId?_=`[${n.correlationId}] `:n?.sessionId&&(_=`[session-${n.sessionId}] `);let l="";s!=null&&(this.getLevel()===0&&typeof s=="object"?l=`
+`+JSON.stringify(s,null,2):l=" "+this.formatData(s));let u="";if(n){let{sessionId:Y,sdkSessionId:J,correlationId:q,...m}=n;Object.keys(m).length>0&&(u=` {${Object.entries(m).map(([k,y])=>`${k}=${y}`).join(", ")}}`)}let L=`[${E}] [${i}] [${c}] ${_}${e}${u}${l}`;t===3?console.error(L):console.log(L)}debug(t,r,e,n){this.log(0,t,r,e,n)}info(t,r,e,n){this.log(1,t,r,e,n)}warn(t,r,e,n){this.log(2,t,r,e,n)}error(t,r,e,n){this.log(3,t,r,e,n)}dataIn(t,r,e,n){this.info(t,`\u2192 ${r}`,e,n)}dataOut(t,r,e,n){this.info(t,`\u2190 ${r}`,e,n)}success(t,r,e,n){this.info(t,`\u2713 ${r}`,e,n)}failure(t,r,e,n){this.error(t,`\u2717 ${r}`,e,n)}timing(t,r,e,n){this.info(t,`\u23F1 ${r}`,n,{duration:`${e}ms`})}happyPathError(t,r,e,n,s=""){let _=((new Error().stack||"").split(`
+`)[2]||"").match(/at\s+(?:.*\s+)?\(?([^:]+):(\d+):(\d+)\)?/),l=_?`${_[1].split("/").pop()}:${_[2]}`:"unknown",u={...e,location:l};return this.warn(t,`[HAPPY-PATH] ${r}`,u,n),s}},a=new M;var f={DEFAULT:3e5,HEALTH_CHECK:3e4,WORKER_STARTUP_WAIT:1e3,WORKER_STARTUP_RETRIES:300,PRE_RESTART_SETTLE_DELAY:2e3,WINDOWS_MULTIPLIER:1.5};function U(o){return process.platform==="win32"?Math.round(o*f.WINDOWS_MULTIPLIER):o}function d(o={}){let{port:t,includeSkillFallback:r=!1,customPrefix:e,actualError:n}=o,s=e||"Worker service connection failed.",E=t?` (port ${t})`:"",i=`${s}${E}
 
 `;return i+=`To restart the worker:
 `,i+=`1. Exit Claude Code completely
-`,i+=`2. Run: claude-mem restart
+`,i+=`2. Run: npm run worker:restart
 `,i+="3. Restart Claude Code",r&&(i+=`
 
 If that doesn't work, try: /troubleshoot`),n&&(i=`Worker Error: ${n}
 
-${i}`),i}var F=C.join(H(),".claude","plugins","marketplaces","thedotmack"),U=h(m.HEALTH_CHECK),S=null;function p(){if(S!==null)return S;let o=C.join(g.get("CLAUDE_MEM_DATA_DIR"),"settings.json"),t=g.loadFromFile(o);return S=parseInt(t.CLAUDE_MEM_WORKER_PORT,10),S}async function K(){let o=p();return(await fetch(`http://127.0.0.1:${o}/api/readiness`,{signal:AbortSignal.timeout(U)})).ok}function j(){let o=C.join(F,"package.json");return JSON.parse(x(o,"utf-8")).version}async function X(){let o=p(),t=await fetch(`http://127.0.0.1:${o}/api/version`,{signal:AbortSignal.timeout(U)});if(!t.ok)throw new Error(`Failed to get worker version: ${t.status}`);return(await t.json()).version}async function V(){let o=j(),t=await X();o!==t&&c.warn("SYSTEM","Worker version mismatch",{pluginVersion:o,workerVersion:t,hint:"Restart worker with: claude-mem worker restart"})}async function N(){for(let r=0;r<25;r++){try{if(await K()){await V();return}}catch{}await new Promise(e=>setTimeout(e,200))}throw new Error(R({port:p(),customPrefix:"Worker did not become ready within 5 seconds."}))}import G from"path";function k(o){if(!o||o.trim()==="")return c.warn("PROJECT_NAME","Empty cwd provided, using fallback",{cwd:o}),"unknown-project";let t=G.basename(o);if(t===""){if(process.platform==="win32"){let e=o.match(/^([A-Z]):\\/i);if(e){let s=`drive-${e[1].toUpperCase()}`;return c.info("PROJECT_NAME","Drive root detected",{cwd:o,projectName:s}),s}}return c.warn("PROJECT_NAME","Root directory detected, using fallback",{cwd:o}),"unknown-project"}return t}async function B(o){if(await N(),!o)throw new Error("newHook requires input");let{session_id:t,cwd:r,prompt:e}=o,n=k(r),s=p(),a=await fetch(`http://127.0.0.1:${s}/api/sessions/init`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({claudeSessionId:t,project:n,prompt:e}),signal:AbortSignal.timeout(5e3)});if(!a.ok)throw new Error(`Session initialization failed: ${a.status}`);let i=await a.json(),_=i.sessionDbId,E=i.promptNumber;if(i.skipped&&i.reason==="private"){console.error(`[new-hook] Session ${_}, prompt #${E} (fully private - skipped)`),console.log(f);return}console.error(`[new-hook] Session ${_}, prompt #${E}`);let l=e.startsWith("/")?e.substring(1):e,u=await fetch(`http://127.0.0.1:${s}/sessions/${_}/init`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({userPrompt:l,promptNumber:E}),signal:AbortSignal.timeout(5e3)});if(!u.ok)throw new Error(`SDK agent start failed: ${u.status}`);console.log(f)}var A="";y.on("data",o=>A+=o);y.on("end",async()=>{let o;try{o=A?JSON.parse(A):void 0}catch(t){throw new Error(`Failed to parse hook input: ${t instanceof Error?t.message:String(t)}`)}await B(o)});
+${i}`),i}var F=A.join(H(),".claude","plugins","marketplaces","thedotmack"),N=U(f.HEALTH_CHECK),S=null;function p(){if(S!==null)return S;let o=A.join(g.get("CLAUDE_MEM_DATA_DIR"),"settings.json"),t=g.loadFromFile(o);return S=parseInt(t.CLAUDE_MEM_WORKER_PORT,10),S}async function K(){let o=p();return(await fetch(`http://127.0.0.1:${o}/api/readiness`,{signal:AbortSignal.timeout(N)})).ok}function G(){let o=A.join(F,"package.json");return JSON.parse(x(o,"utf-8")).version}async function X(){let o=p(),t=await fetch(`http://127.0.0.1:${o}/api/version`,{signal:AbortSignal.timeout(N)});if(!t.ok)throw new Error(`Failed to get worker version: ${t.status}`);return(await t.json()).version}async function j(){let o=G(),t=await X();o!==t&&a.warn("SYSTEM","Worker version mismatch",{pluginVersion:o,workerVersion:t,hint:"Restart worker with: claude-mem worker restart"})}async function I(){for(let r=0;r<25;r++){try{if(await K()){await j();return}}catch{}await new Promise(e=>setTimeout(e,200))}throw new Error(d({port:p(),customPrefix:"Worker did not become ready within 5 seconds."}))}import V from"path";function h(o){if(!o||o.trim()==="")return a.warn("PROJECT_NAME","Empty cwd provided, using fallback",{cwd:o}),"unknown-project";let t=V.basename(o);if(t===""){if(process.platform==="win32"){let e=o.match(/^([A-Z]):\\/i);if(e){let s=`drive-${e[1].toUpperCase()}`;return a.info("PROJECT_NAME","Drive root detected",{cwd:o,projectName:s}),s}}return a.warn("PROJECT_NAME","Root directory detected, using fallback",{cwd:o}),"unknown-project"}return t}async function B(o){if(await I(),!o)throw new Error("newHook requires input");let{session_id:t,cwd:r,prompt:e}=o,n=h(r),s=p(),E=await fetch(`http://127.0.0.1:${s}/api/sessions/init`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({claudeSessionId:t,project:n,prompt:e}),signal:AbortSignal.timeout(5e3)});if(!E.ok)throw new Error(`Session initialization failed: ${E.status}`);let i=await E.json(),c=i.sessionDbId,_=i.promptNumber;if(i.skipped&&i.reason==="private"){console.error(`[new-hook] Session ${c}, prompt #${_} (fully private - skipped)`),console.log(T);return}console.error(`[new-hook] Session ${c}, prompt #${_}`);let l=e.startsWith("/")?e.substring(1):e,u=await fetch(`http://127.0.0.1:${s}/sessions/${c}/init`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({userPrompt:l,promptNumber:_}),signal:AbortSignal.timeout(5e3)});if(!u.ok)throw new Error(`SDK agent start failed: ${u.status}`);console.log(T)}var C="";P.on("data",o=>C+=o);P.on("end",async()=>{let o;try{o=C?JSON.parse(C):void 0}catch(t){throw new Error(`Failed to parse hook input: ${t instanceof Error?t.message:String(t)}`)}await B(o)});

plugin/scripts/save-hook.js

@@ -1,14 +1,14 @@
 #!/usr/bin/env bun
-import{stdin as y}from"process";var m=JSON.stringify({continue:!0,suppressOutput:!0});import{readFileSync as k,writeFileSync as v,existsSync as P}from"fs";import{join as w}from"path";import{homedir as H}from"os";var D="bugfix,feature,refactor,discovery,decision,change",d="how-it-works,why-it-exists,what-changed,problem-solution,gotcha,pattern,trade-off";var c=class{static DEFAULTS={CLAUDE_MEM_MODEL:"claude-sonnet-4-5",CLAUDE_MEM_CONTEXT_OBSERVATIONS:"50",CLAUDE_MEM_WORKER_PORT:"37777",CLAUDE_MEM_WORKER_HOST:"127.0.0.1",CLAUDE_MEM_SKIP_TOOLS:"ListMcpResourcesTool,SlashCommand,Skill,TodoWrite,AskUserQuestion",CLAUDE_MEM_DATA_DIR:w(H(),".claude-mem"),CLAUDE_MEM_LOG_LEVEL:"INFO",CLAUDE_MEM_PYTHON_VERSION:"3.13",CLAUDE_CODE_PATH:"",CLAUDE_MEM_MODE:"code",CLAUDE_MEM_CONTEXT_SHOW_READ_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_WORK_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_AMOUNT:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_PERCENT:"true",CLAUDE_MEM_CONTEXT_OBSERVATION_TYPES:D,CLAUDE_MEM_CONTEXT_OBSERVATION_CONCEPTS:d,CLAUDE_MEM_CONTEXT_FULL_COUNT:"5",CLAUDE_MEM_CONTEXT_FULL_FIELD:"narrative",CLAUDE_MEM_CONTEXT_SESSION_COUNT:"10",CLAUDE_MEM_CONTEXT_SHOW_LAST_SUMMARY:"true",CLAUDE_MEM_CONTEXT_SHOW_LAST_MESSAGE:"false"};static getAllDefaults(){return{...this.DEFAULTS}}static get(t){return this.DEFAULTS[t]}static getInt(t){let r=this.get(t);return parseInt(r,10)}static getBool(t){return this.get(t)==="true"}static loadFromFile(t){try{if(!P(t))return this.getAllDefaults();let r=k(t,"utf-8"),e=JSON.parse(r),n=e;if(e.env&&typeof e.env=="object"){n=e.env;try{v(t,JSON.stringify(n,null,2),"utf-8"),a.info("SETTINGS","Migrated settings file from nested to flat schema",{settingsPath:t})}catch(i){a.warn("SETTINGS","Failed to auto-migrate settings file",{settingsPath:t},i)}}let o={...this.DEFAULTS};for(let i of Object.keys(this.DEFAULTS))n[i]!==void 0&&(o[i]=n[i]);return o}catch(r){return a.warn("SETTINGS","Failed to load settings, using defaults",{settingsPath:t},r),this.getAllDefaults()}}};var f=(o=>(o[o.DEBUG=0]="DEBUG",o[o.INFO=1]="INFO",o[o.WARN=2]="WARN",o[o.ERROR=3]="ERROR",o[o.SILENT=4]="SILENT",o))(f||{}),p=class{level=null;useColor;constructor(){this.useColor=process.stdout.isTTY??!1}getLevel(){if(this.level===null){let t=c.get("CLAUDE_MEM_LOG_LEVEL").toUpperCase();this.level=f[t]??1}return this.level}correlationId(t,r){return`obs-${t}-${r}`}sessionId(t){return`session-${t}`}formatData(t){if(t==null)return"";if(typeof t=="string")return t;if(typeof t=="number"||typeof t=="boolean")return t.toString();if(typeof t=="object"){if(t instanceof Error)return this.getLevel()===0?`${t.message}
-${t.stack}`:t.message;if(Array.isArray(t))return`[${t.length} items]`;let r=Object.keys(t);return r.length===0?"{}":r.length<=3?JSON.stringify(t):`{${r.length} keys: ${r.slice(0,3).join(", ")}...}`}return String(t)}formatTool(t,r){if(!r)return t;let e=typeof r=="string"?JSON.parse(r):r;if(t==="Bash"&&e.command)return`${t}(${e.command})`;if(e.file_path)return`${t}(${e.file_path})`;if(e.notebook_path)return`${t}(${e.notebook_path})`;if(t==="Glob"&&e.pattern)return`${t}(${e.pattern})`;if(t==="Grep"&&e.pattern)return`${t}(${e.pattern})`;if(e.url)return`${t}(${e.url})`;if(e.query)return`${t}(${e.query})`;if(t==="Task"){if(e.subagent_type)return`${t}(${e.subagent_type})`;if(e.description)return`${t}(${e.description})`}return t==="Skill"&&e.skill?`${t}(${e.skill})`:t==="LSP"&&e.operation?`${t}(${e.operation})`:t}formatTimestamp(t){let r=t.getFullYear(),e=String(t.getMonth()+1).padStart(2,"0"),n=String(t.getDate()).padStart(2,"0"),o=String(t.getHours()).padStart(2,"0"),i=String(t.getMinutes()).padStart(2,"0"),E=String(t.getSeconds()).padStart(2,"0"),_=String(t.getMilliseconds()).padStart(3,"0");return`${r}-${e}-${n} ${o}:${i}:${E}.${_}`}log(t,r,e,n,o){if(t<this.getLevel())return;let i=this.formatTimestamp(new Date),E=f[t].padEnd(5),_=r.padEnd(6),l="";n?.correlationId?l=`[${n.correlationId}] `:n?.sessionId&&(l=`[session-${n.sessionId}] `);let u="";o!=null&&(this.getLevel()===0&&typeof o=="object"?u=`
-`+JSON.stringify(o,null,2):u=" "+this.formatData(o));let T="";if(n){let{sessionId:j,sdkSessionId:B,correlationId:Y,...M}=n;Object.keys(M).length>0&&(T=` {${Object.entries(M).map(([N,$])=>`${N}=${$}`).join(", ")}}`)}let L=`[${i}] [${E}] [${_}] ${l}${e}${T}${u}`;t===3?console.error(L):console.log(L)}debug(t,r,e,n){this.log(0,t,r,e,n)}info(t,r,e,n){this.log(1,t,r,e,n)}warn(t,r,e,n){this.log(2,t,r,e,n)}error(t,r,e,n){this.log(3,t,r,e,n)}dataIn(t,r,e,n){this.info(t,`\u2192 ${r}`,e,n)}dataOut(t,r,e,n){this.info(t,`\u2190 ${r}`,e,n)}success(t,r,e,n){this.info(t,`\u2713 ${r}`,e,n)}failure(t,r,e,n){this.error(t,`\u2717 ${r}`,e,n)}timing(t,r,e,n){this.info(t,`\u23F1 ${r}`,n,{duration:`${e}ms`})}happyPathError(t,r,e,n,o=""){let l=((new Error().stack||"").split(`
-`)[2]||"").match(/at\s+(?:.*\s+)?\(?([^:]+):(\d+):(\d+)\)?/),u=l?`${l[1].split("/").pop()}:${l[2]}`:"unknown",T={...e,location:u};return this.warn(t,`[HAPPY-PATH] ${r}`,T,n),o}},a=new p;import C from"path";import{homedir as W}from"os";import{readFileSync as b}from"fs";var g={DEFAULT:12e4,HEALTH_CHECK:1e3,WORKER_STARTUP_WAIT:1e3,WORKER_STARTUP_RETRIES:15,PRE_RESTART_SETTLE_DELAY:2e3,WINDOWS_MULTIPLIER:1.5};function U(s){return process.platform==="win32"?Math.round(s*g.WINDOWS_MULTIPLIER):s}function R(s={}){let{port:t,includeSkillFallback:r=!1,customPrefix:e,actualError:n}=s,o=e||"Worker service connection failed.",i=t?` (port ${t})`:"",E=`${o}${i}
+import{stdin as h}from"process";var D=JSON.stringify({continue:!0,suppressOutput:!0});import{readFileSync as k,writeFileSync as $,existsSync as v}from"fs";import{join as w}from"path";import{homedir as H}from"os";var U="bugfix,feature,refactor,discovery,decision,change",R="how-it-works,why-it-exists,what-changed,problem-solution,gotcha,pattern,trade-off";var c=class{static DEFAULTS={CLAUDE_MEM_MODEL:"claude-sonnet-4-5",CLAUDE_MEM_CONTEXT_OBSERVATIONS:"50",CLAUDE_MEM_WORKER_PORT:"37777",CLAUDE_MEM_WORKER_HOST:"127.0.0.1",CLAUDE_MEM_SKIP_TOOLS:"ListMcpResourcesTool,SlashCommand,Skill,TodoWrite,AskUserQuestion",CLAUDE_MEM_PROVIDER:"claude",CLAUDE_MEM_GEMINI_API_KEY:"",CLAUDE_MEM_GEMINI_MODEL:"gemini-2.5-flash-lite",CLAUDE_MEM_GEMINI_RATE_LIMITING_ENABLED:"true",CLAUDE_MEM_OPENROUTER_API_KEY:"",CLAUDE_MEM_OPENROUTER_MODEL:"xiaomi/mimo-v2-flash:free",CLAUDE_MEM_OPENROUTER_SITE_URL:"",CLAUDE_MEM_OPENROUTER_APP_NAME:"claude-mem",CLAUDE_MEM_OPENROUTER_MAX_CONTEXT_MESSAGES:"20",CLAUDE_MEM_OPENROUTER_MAX_TOKENS:"100000",CLAUDE_MEM_DATA_DIR:w(H(),".claude-mem"),CLAUDE_MEM_LOG_LEVEL:"INFO",CLAUDE_MEM_PYTHON_VERSION:"3.13",CLAUDE_CODE_PATH:"",CLAUDE_MEM_MODE:"code",CLAUDE_MEM_CONTEXT_SHOW_READ_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_WORK_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_AMOUNT:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_PERCENT:"true",CLAUDE_MEM_CONTEXT_OBSERVATION_TYPES:U,CLAUDE_MEM_CONTEXT_OBSERVATION_CONCEPTS:R,CLAUDE_MEM_CONTEXT_FULL_COUNT:"5",CLAUDE_MEM_CONTEXT_FULL_FIELD:"narrative",CLAUDE_MEM_CONTEXT_SESSION_COUNT:"10",CLAUDE_MEM_CONTEXT_SHOW_LAST_SUMMARY:"true",CLAUDE_MEM_CONTEXT_SHOW_LAST_MESSAGE:"false"};static getAllDefaults(){return{...this.DEFAULTS}}static get(t){return this.DEFAULTS[t]}static getInt(t){let r=this.get(t);return parseInt(r,10)}static getBool(t){return this.get(t)==="true"}static loadFromFile(t){try{if(!v(t))return this.getAllDefaults();let r=k(t,"utf-8"),e=JSON.parse(r),n=e;if(e.env&&typeof e.env=="object"){n=e.env;try{$(t,JSON.stringify(n,null,2),"utf-8"),_.info("SETTINGS","Migrated settings file from nested to flat schema",{settingsPath:t})}catch(i){_.warn("SETTINGS","Failed to auto-migrate settings file",{settingsPath:t},i)}}let o={...this.DEFAULTS};for(let i of Object.keys(this.DEFAULTS))n[i]!==void 0&&(o[i]=n[i]);return o}catch(r){return _.warn("SETTINGS","Failed to load settings, using defaults",{settingsPath:t},r),this.getAllDefaults()}}};var M=(o=>(o[o.DEBUG=0]="DEBUG",o[o.INFO=1]="INFO",o[o.WARN=2]="WARN",o[o.ERROR=3]="ERROR",o[o.SILENT=4]="SILENT",o))(M||{}),f=class{level=null;useColor;constructor(){this.useColor=process.stdout.isTTY??!1}getLevel(){if(this.level===null){let t=c.get("CLAUDE_MEM_LOG_LEVEL").toUpperCase();this.level=M[t]??1}return this.level}correlationId(t,r){return`obs-${t}-${r}`}sessionId(t){return`session-${t}`}formatData(t){if(t==null)return"";if(typeof t=="string")return t;if(typeof t=="number"||typeof t=="boolean")return t.toString();if(typeof t=="object"){if(t instanceof Error)return this.getLevel()===0?`${t.message}
+${t.stack}`:t.message;if(Array.isArray(t))return`[${t.length} items]`;let r=Object.keys(t);return r.length===0?"{}":r.length<=3?JSON.stringify(t):`{${r.length} keys: ${r.slice(0,3).join(", ")}...}`}return String(t)}formatTool(t,r){if(!r)return t;let e=typeof r=="string"?JSON.parse(r):r;if(t==="Bash"&&e.command)return`${t}(${e.command})`;if(e.file_path)return`${t}(${e.file_path})`;if(e.notebook_path)return`${t}(${e.notebook_path})`;if(t==="Glob"&&e.pattern)return`${t}(${e.pattern})`;if(t==="Grep"&&e.pattern)return`${t}(${e.pattern})`;if(e.url)return`${t}(${e.url})`;if(e.query)return`${t}(${e.query})`;if(t==="Task"){if(e.subagent_type)return`${t}(${e.subagent_type})`;if(e.description)return`${t}(${e.description})`}return t==="Skill"&&e.skill?`${t}(${e.skill})`:t==="LSP"&&e.operation?`${t}(${e.operation})`:t}formatTimestamp(t){let r=t.getFullYear(),e=String(t.getMonth()+1).padStart(2,"0"),n=String(t.getDate()).padStart(2,"0"),o=String(t.getHours()).padStart(2,"0"),i=String(t.getMinutes()).padStart(2,"0"),E=String(t.getSeconds()).padStart(2,"0"),a=String(t.getMilliseconds()).padStart(3,"0");return`${r}-${e}-${n} ${o}:${i}:${E}.${a}`}log(t,r,e,n,o){if(t<this.getLevel())return;let i=this.formatTimestamp(new Date),E=M[t].padEnd(5),a=r.padEnd(6),l="";n?.correlationId?l=`[${n.correlationId}] `:n?.sessionId&&(l=`[session-${n.sessionId}] `);let g="";o!=null&&(this.getLevel()===0&&typeof o=="object"?g=`
+`+JSON.stringify(o,null,2):g=" "+this.formatData(o));let u="";if(n){let{sessionId:j,sdkSessionId:B,correlationId:Y,...L}=n;Object.keys(L).length>0&&(u=` {${Object.entries(L).map(([y,P])=>`${y}=${P}`).join(", ")}}`)}let C=`[${i}] [${E}] [${a}] ${l}${e}${u}${g}`;t===3?console.error(C):console.log(C)}debug(t,r,e,n){this.log(0,t,r,e,n)}info(t,r,e,n){this.log(1,t,r,e,n)}warn(t,r,e,n){this.log(2,t,r,e,n)}error(t,r,e,n){this.log(3,t,r,e,n)}dataIn(t,r,e,n){this.info(t,`\u2192 ${r}`,e,n)}dataOut(t,r,e,n){this.info(t,`\u2190 ${r}`,e,n)}success(t,r,e,n){this.info(t,`\u2713 ${r}`,e,n)}failure(t,r,e,n){this.error(t,`\u2717 ${r}`,e,n)}timing(t,r,e,n){this.info(t,`\u23F1 ${r}`,n,{duration:`${e}ms`})}happyPathError(t,r,e,n,o=""){let l=((new Error().stack||"").split(`
+`)[2]||"").match(/at\s+(?:.*\s+)?\(?([^:]+):(\d+):(\d+)\)?/),g=l?`${l[1].split("/").pop()}:${l[2]}`:"unknown",u={...e,location:g};return this.warn(t,`[HAPPY-PATH] ${r}`,u,n),o}},_=new f;import A from"path";import{homedir as W}from"os";import{readFileSync as b}from"fs";var T={DEFAULT:3e5,HEALTH_CHECK:3e4,WORKER_STARTUP_WAIT:1e3,WORKER_STARTUP_RETRIES:300,PRE_RESTART_SETTLE_DELAY:2e3,WINDOWS_MULTIPLIER:1.5};function m(s){return process.platform==="win32"?Math.round(s*T.WINDOWS_MULTIPLIER):s}function d(s={}){let{port:t,includeSkillFallback:r=!1,customPrefix:e,actualError:n}=s,o=e||"Worker service connection failed.",i=t?` (port ${t})`:"",E=`${o}${i}
 
 `;return E+=`To restart the worker:
 `,E+=`1. Exit Claude Code completely
-`,E+=`2. Run: claude-mem restart
+`,E+=`2. Run: npm run worker:restart
 `,E+="3. Restart Claude Code",r&&(E+=`
 
 If that doesn't work, try: /troubleshoot`),n&&(E=`Worker Error: ${n}
 
-${E}`),E}var F=C.join(W(),".claude","plugins","marketplaces","thedotmack"),h=U(g.HEALTH_CHECK),O=null;function S(){if(O!==null)return O;let s=C.join(c.get("CLAUDE_MEM_DATA_DIR"),"settings.json"),t=c.loadFromFile(s);return O=parseInt(t.CLAUDE_MEM_WORKER_PORT,10),O}async function x(){let s=S();return(await fetch(`http://127.0.0.1:${s}/api/readiness`,{signal:AbortSignal.timeout(h)})).ok}function K(){let s=C.join(F,"package.json");return JSON.parse(b(s,"utf-8")).version}async function X(){let s=S(),t=await fetch(`http://127.0.0.1:${s}/api/version`,{signal:AbortSignal.timeout(h)});if(!t.ok)throw new Error(`Failed to get worker version: ${t.status}`);return(await t.json()).version}async function V(){let s=K(),t=await X();s!==t&&a.warn("SYSTEM","Worker version mismatch",{pluginVersion:s,workerVersion:t,hint:"Restart worker with: claude-mem worker restart"})}async function I(){for(let r=0;r<25;r++){try{if(await x()){await V();return}}catch{}await new Promise(e=>setTimeout(e,200))}throw new Error(R({port:S(),customPrefix:"Worker did not become ready within 5 seconds."}))}async function G(s){if(await I(),!s)throw new Error("saveHook requires input");let{session_id:t,cwd:r,tool_name:e,tool_input:n,tool_response:o}=s,i=S(),E=a.formatTool(e,n);if(a.dataIn("HOOK",`PostToolUse: ${E}`,{workerPort:i}),!r)throw new Error(`Missing cwd in PostToolUse hook input for session ${t}, tool ${e}`);let _=await fetch(`http://127.0.0.1:${i}/api/sessions/observations`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({claudeSessionId:t,tool_name:e,tool_input:n,tool_response:o,cwd:r}),signal:AbortSignal.timeout(g.DEFAULT)});if(!_.ok)throw new Error(`Observation storage failed: ${_.status}`);a.debug("HOOK","Observation sent successfully",{toolName:e}),console.log(m)}var A="";y.on("data",s=>A+=s);y.on("end",async()=>{let s;try{s=A?JSON.parse(A):void 0}catch(t){throw new Error(`Failed to parse hook input: ${t instanceof Error?t.message:String(t)}`)}await G(s)});
+${E}`),E}var x=A.join(W(),".claude","plugins","marketplaces","thedotmack"),I=m(T.HEALTH_CHECK),S=null;function O(){if(S!==null)return S;let s=A.join(c.get("CLAUDE_MEM_DATA_DIR"),"settings.json"),t=c.loadFromFile(s);return S=parseInt(t.CLAUDE_MEM_WORKER_PORT,10),S}async function F(){let s=O();return(await fetch(`http://127.0.0.1:${s}/api/readiness`,{signal:AbortSignal.timeout(I)})).ok}function K(){let s=A.join(x,"package.json");return JSON.parse(b(s,"utf-8")).version}async function G(){let s=O(),t=await fetch(`http://127.0.0.1:${s}/api/version`,{signal:AbortSignal.timeout(I)});if(!t.ok)throw new Error(`Failed to get worker version: ${t.status}`);return(await t.json()).version}async function X(){let s=K(),t=await G();s!==t&&_.warn("SYSTEM","Worker version mismatch",{pluginVersion:s,workerVersion:t,hint:"Restart worker with: claude-mem worker restart"})}async function N(){for(let r=0;r<25;r++){try{if(await F()){await X();return}}catch{}await new Promise(e=>setTimeout(e,200))}throw new Error(d({port:O(),customPrefix:"Worker did not become ready within 5 seconds."}))}async function V(s){if(await N(),!s)throw new Error("saveHook requires input");let{session_id:t,cwd:r,tool_name:e,tool_input:n,tool_response:o}=s,i=O(),E=_.formatTool(e,n);if(_.dataIn("HOOK",`PostToolUse: ${E}`,{workerPort:i}),!r)throw new Error(`Missing cwd in PostToolUse hook input for session ${t}, tool ${e}`);let a=await fetch(`http://127.0.0.1:${i}/api/sessions/observations`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({claudeSessionId:t,tool_name:e,tool_input:n,tool_response:o,cwd:r}),signal:AbortSignal.timeout(T.DEFAULT)});if(!a.ok)throw new Error(`Observation storage failed: ${a.status}`);_.debug("HOOK","Observation sent successfully",{toolName:e}),console.log(D)}var p="";h.on("data",s=>p+=s);h.on("end",async()=>{let s;try{s=p?JSON.parse(p):void 0}catch(t){throw new Error(`Failed to parse hook input: ${t instanceof Error?t.message:String(t)}`)}await V(s)});

plugin/scripts/smart-install.js

@@ -291,7 +291,7 @@ function installCLI() {
       console.error('📋 Add to PATH (run once in PowerShell as Admin):');
       console.error(`   [Environment]::SetEnvironmentVariable("Path", $env:Path + ";${cliDir}", "User")`);
       console.error('');
-      console.error('   Then restart your terminal and use: claude-mem start|stop|restart|status');
+      console.error('   Then restart your terminal and use: npm run worker:start|stop|restart|status');
     } catch (error) {
       console.error(`⚠️  Could not install CLI: ${error.message}`);
       console.error(`   You can still use: bun "${WORKER_CLI}" <command>`);
@@ -333,9 +333,9 @@ exec "${bunPath}" "${WORKER_CLI}" "$@"
         console.error('📋 Add to PATH (add to ~/.bashrc or ~/.zshrc):');
         console.error('   export PATH="$HOME/.local/bin:$PATH"');
         console.error('');
-        console.error('   Then restart your terminal and use: claude-mem start|stop|restart|status');
+        console.error('   Then restart your terminal and use: npm run worker:start|stop|restart|status');
       } else {
-        console.error('   Usage: claude-mem start|stop|restart|status');
+        console.error('   Usage: npm run worker:start|stop|restart|status');
       }
     } catch (error) {
       console.error(`⚠️  Could not install CLI: ${error.message}`);
@@ -439,8 +439,31 @@ try {
 
   // Step 3: Install dependencies if needed
   if (needsInstall()) {
+    const pkg = JSON.parse(readFileSync(join(ROOT, 'package.json'), 'utf-8'));
+    const newVersion = pkg.version;
+
     installDeps();
     console.error('✅ Dependencies installed');
+
+    // Auto-restart worker to pick up new code
+    const port = process.env.CLAUDE_MEM_WORKER_PORT || 37777;
+    console.error(`[claude-mem] Plugin updated to v${newVersion} - restarting worker...`);
+    try {
+      // Graceful shutdown via HTTP (curl is cross-platform enough)
+      execSync(`curl -s -X POST http://127.0.0.1:${port}/api/admin/shutdown`, {
+        stdio: 'ignore',
+        shell: IS_WINDOWS,
+        timeout: 5000
+      });
+      // Brief wait for port to free
+      execSync(IS_WINDOWS ? 'timeout /t 1 /nobreak >nul' : 'sleep 0.5', {
+        stdio: 'ignore',
+        shell: true
+      });
+    } catch {
+      // Worker wasn't running or already stopped - that's fine
+    }
+    // Worker will be started fresh by next hook in chain (worker-service.cjs start)
   }
 
   // Step 4: Install CLI to PATH

plugin/scripts/summary-hook.js

@@ -1,18 +1,18 @@
 #!/usr/bin/env bun
-import{stdin as N}from"process";var T=JSON.stringify({continue:!0,suppressOutput:!0});import{readFileSync as w,writeFileSync as v,existsSync as H}from"fs";import{join as W}from"path";import{homedir as x}from"os";var d="bugfix,feature,refactor,discovery,decision,change",h="how-it-works,why-it-exists,what-changed,problem-solution,gotcha,pattern,trade-off";var g=class{static DEFAULTS={CLAUDE_MEM_MODEL:"claude-sonnet-4-5",CLAUDE_MEM_CONTEXT_OBSERVATIONS:"50",CLAUDE_MEM_WORKER_PORT:"37777",CLAUDE_MEM_WORKER_HOST:"127.0.0.1",CLAUDE_MEM_SKIP_TOOLS:"ListMcpResourcesTool,SlashCommand,Skill,TodoWrite,AskUserQuestion",CLAUDE_MEM_DATA_DIR:W(x(),".claude-mem"),CLAUDE_MEM_LOG_LEVEL:"INFO",CLAUDE_MEM_PYTHON_VERSION:"3.13",CLAUDE_CODE_PATH:"",CLAUDE_MEM_MODE:"code",CLAUDE_MEM_CONTEXT_SHOW_READ_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_WORK_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_AMOUNT:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_PERCENT:"true",CLAUDE_MEM_CONTEXT_OBSERVATION_TYPES:d,CLAUDE_MEM_CONTEXT_OBSERVATION_CONCEPTS:h,CLAUDE_MEM_CONTEXT_FULL_COUNT:"5",CLAUDE_MEM_CONTEXT_FULL_FIELD:"narrative",CLAUDE_MEM_CONTEXT_SESSION_COUNT:"10",CLAUDE_MEM_CONTEXT_SHOW_LAST_SUMMARY:"true",CLAUDE_MEM_CONTEXT_SHOW_LAST_MESSAGE:"false"};static getAllDefaults(){return{...this.DEFAULTS}}static get(t){return this.DEFAULTS[t]}static getInt(t){let r=this.get(t);return parseInt(r,10)}static getBool(t){return this.get(t)==="true"}static loadFromFile(t){try{if(!H(t))return this.getAllDefaults();let r=w(t,"utf-8"),e=JSON.parse(r),n=e;if(e.env&&typeof e.env=="object"){n=e.env;try{v(t,JSON.stringify(n,null,2),"utf-8"),c.info("SETTINGS","Migrated settings file from nested to flat schema",{settingsPath:t})}catch(a){c.warn("SETTINGS","Failed to auto-migrate settings file",{settingsPath:t},a)}}let o={...this.DEFAULTS};for(let a of Object.keys(this.DEFAULTS))n[a]!==void 0&&(o[a]=n[a]);return o}catch(r){return c.warn("SETTINGS","Failed to load settings, using defaults",{settingsPath:t},r),this.getAllDefaults()}}};var O=(o=>(o[o.DEBUG=0]="DEBUG",o[o.INFO=1]="INFO",o[o.WARN=2]="WARN",o[o.ERROR=3]="ERROR",o[o.SILENT=4]="SILENT",o))(O||{}),m=class{level=null;useColor;constructor(){this.useColor=process.stdout.isTTY??!1}getLevel(){if(this.level===null){let t=g.get("CLAUDE_MEM_LOG_LEVEL").toUpperCase();this.level=O[t]??1}return this.level}correlationId(t,r){return`obs-${t}-${r}`}sessionId(t){return`session-${t}`}formatData(t){if(t==null)return"";if(typeof t=="string")return t;if(typeof t=="number"||typeof t=="boolean")return t.toString();if(typeof t=="object"){if(t instanceof Error)return this.getLevel()===0?`${t.message}
-${t.stack}`:t.message;if(Array.isArray(t))return`[${t.length} items]`;let r=Object.keys(t);return r.length===0?"{}":r.length<=3?JSON.stringify(t):`{${r.length} keys: ${r.slice(0,3).join(", ")}...}`}return String(t)}formatTool(t,r){if(!r)return t;let e=typeof r=="string"?JSON.parse(r):r;if(t==="Bash"&&e.command)return`${t}(${e.command})`;if(e.file_path)return`${t}(${e.file_path})`;if(e.notebook_path)return`${t}(${e.notebook_path})`;if(t==="Glob"&&e.pattern)return`${t}(${e.pattern})`;if(t==="Grep"&&e.pattern)return`${t}(${e.pattern})`;if(e.url)return`${t}(${e.url})`;if(e.query)return`${t}(${e.query})`;if(t==="Task"){if(e.subagent_type)return`${t}(${e.subagent_type})`;if(e.description)return`${t}(${e.description})`}return t==="Skill"&&e.skill?`${t}(${e.skill})`:t==="LSP"&&e.operation?`${t}(${e.operation})`:t}formatTimestamp(t){let r=t.getFullYear(),e=String(t.getMonth()+1).padStart(2,"0"),n=String(t.getDate()).padStart(2,"0"),o=String(t.getHours()).padStart(2,"0"),a=String(t.getMinutes()).padStart(2,"0"),i=String(t.getSeconds()).padStart(2,"0"),_=String(t.getMilliseconds()).padStart(3,"0");return`${r}-${e}-${n} ${o}:${a}:${i}.${_}`}log(t,r,e,n,o){if(t<this.getLevel())return;let a=this.formatTimestamp(new Date),i=O[t].padEnd(5),_=r.padEnd(6),E="";n?.correlationId?E=`[${n.correlationId}] `:n?.sessionId&&(E=`[session-${n.sessionId}] `);let l="";o!=null&&(this.getLevel()===0&&typeof o=="object"?l=`
-`+JSON.stringify(o,null,2):l=" "+this.formatData(o));let S="";if(n){let{sessionId:J,sdkSessionId:q,correlationId:z,...D}=n;Object.keys(D).length>0&&(S=` {${Object.entries(D).map(([$,k])=>`${$}=${k}`).join(", ")}}`)}let L=`[${a}] [${i}] [${_}] ${E}${e}${S}${l}`;t===3?console.error(L):console.log(L)}debug(t,r,e,n){this.log(0,t,r,e,n)}info(t,r,e,n){this.log(1,t,r,e,n)}warn(t,r,e,n){this.log(2,t,r,e,n)}error(t,r,e,n){this.log(3,t,r,e,n)}dataIn(t,r,e,n){this.info(t,`\u2192 ${r}`,e,n)}dataOut(t,r,e,n){this.info(t,`\u2190 ${r}`,e,n)}success(t,r,e,n){this.info(t,`\u2713 ${r}`,e,n)}failure(t,r,e,n){this.error(t,`\u2717 ${r}`,e,n)}timing(t,r,e,n){this.info(t,`\u23F1 ${r}`,n,{duration:`${e}ms`})}happyPathError(t,r,e,n,o=""){let E=((new Error().stack||"").split(`
-`)[2]||"").match(/at\s+(?:.*\s+)?\(?([^:]+):(\d+):(\d+)\)?/),l=E?`${E[1].split("/").pop()}:${E[2]}`:"unknown",S={...e,location:l};return this.warn(t,`[HAPPY-PATH] ${r}`,S,n),o}},c=new m;import C from"path";import{homedir as b}from"os";import{readFileSync as P}from"fs";var u={DEFAULT:12e4,HEALTH_CHECK:1e3,WORKER_STARTUP_WAIT:1e3,WORKER_STARTUP_RETRIES:15,PRE_RESTART_SETTLE_DELAY:2e3,WINDOWS_MULTIPLIER:1.5};function y(s){return process.platform==="win32"?Math.round(s*u.WINDOWS_MULTIPLIER):s}function R(s={}){let{port:t,includeSkillFallback:r=!1,customPrefix:e,actualError:n}=s,o=e||"Worker service connection failed.",a=t?` (port ${t})`:"",i=`${o}${a}
+import{stdin as y}from"process";var M=JSON.stringify({continue:!0,suppressOutput:!0});import{readFileSync as P,writeFileSync as w,existsSync as v}from"fs";import{join as x}from"path";import{homedir as H}from"os";var R="bugfix,feature,refactor,discovery,decision,change",U="how-it-works,why-it-exists,what-changed,problem-solution,gotcha,pattern,trade-off";var c=class{static DEFAULTS={CLAUDE_MEM_MODEL:"claude-sonnet-4-5",CLAUDE_MEM_CONTEXT_OBSERVATIONS:"50",CLAUDE_MEM_WORKER_PORT:"37777",CLAUDE_MEM_WORKER_HOST:"127.0.0.1",CLAUDE_MEM_SKIP_TOOLS:"ListMcpResourcesTool,SlashCommand,Skill,TodoWrite,AskUserQuestion",CLAUDE_MEM_PROVIDER:"claude",CLAUDE_MEM_GEMINI_API_KEY:"",CLAUDE_MEM_GEMINI_MODEL:"gemini-2.5-flash-lite",CLAUDE_MEM_GEMINI_RATE_LIMITING_ENABLED:"true",CLAUDE_MEM_OPENROUTER_API_KEY:"",CLAUDE_MEM_OPENROUTER_MODEL:"xiaomi/mimo-v2-flash:free",CLAUDE_MEM_OPENROUTER_SITE_URL:"",CLAUDE_MEM_OPENROUTER_APP_NAME:"claude-mem",CLAUDE_MEM_OPENROUTER_MAX_CONTEXT_MESSAGES:"20",CLAUDE_MEM_OPENROUTER_MAX_TOKENS:"100000",CLAUDE_MEM_DATA_DIR:x(H(),".claude-mem"),CLAUDE_MEM_LOG_LEVEL:"INFO",CLAUDE_MEM_PYTHON_VERSION:"3.13",CLAUDE_CODE_PATH:"",CLAUDE_MEM_MODE:"code",CLAUDE_MEM_CONTEXT_SHOW_READ_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_WORK_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_AMOUNT:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_PERCENT:"true",CLAUDE_MEM_CONTEXT_OBSERVATION_TYPES:R,CLAUDE_MEM_CONTEXT_OBSERVATION_CONCEPTS:U,CLAUDE_MEM_CONTEXT_FULL_COUNT:"5",CLAUDE_MEM_CONTEXT_FULL_FIELD:"narrative",CLAUDE_MEM_CONTEXT_SESSION_COUNT:"10",CLAUDE_MEM_CONTEXT_SHOW_LAST_SUMMARY:"true",CLAUDE_MEM_CONTEXT_SHOW_LAST_MESSAGE:"false"};static getAllDefaults(){return{...this.DEFAULTS}}static get(t){return this.DEFAULTS[t]}static getInt(t){let r=this.get(t);return parseInt(r,10)}static getBool(t){return this.get(t)==="true"}static loadFromFile(t){try{if(!v(t))return this.getAllDefaults();let r=P(t,"utf-8"),e=JSON.parse(r),n=e;if(e.env&&typeof e.env=="object"){n=e.env;try{w(t,JSON.stringify(n,null,2),"utf-8"),l.info("SETTINGS","Migrated settings file from nested to flat schema",{settingsPath:t})}catch(E){l.warn("SETTINGS","Failed to auto-migrate settings file",{settingsPath:t},E)}}let o={...this.DEFAULTS};for(let E of Object.keys(this.DEFAULTS))n[E]!==void 0&&(o[E]=n[E]);return o}catch(r){return l.warn("SETTINGS","Failed to load settings, using defaults",{settingsPath:t},r),this.getAllDefaults()}}};var f=(o=>(o[o.DEBUG=0]="DEBUG",o[o.INFO=1]="INFO",o[o.WARN=2]="WARN",o[o.ERROR=3]="ERROR",o[o.SILENT=4]="SILENT",o))(f||{}),p=class{level=null;useColor;constructor(){this.useColor=process.stdout.isTTY??!1}getLevel(){if(this.level===null){let t=c.get("CLAUDE_MEM_LOG_LEVEL").toUpperCase();this.level=f[t]??1}return this.level}correlationId(t,r){return`obs-${t}-${r}`}sessionId(t){return`session-${t}`}formatData(t){if(t==null)return"";if(typeof t=="string")return t;if(typeof t=="number"||typeof t=="boolean")return t.toString();if(typeof t=="object"){if(t instanceof Error)return this.getLevel()===0?`${t.message}
+${t.stack}`:t.message;if(Array.isArray(t))return`[${t.length} items]`;let r=Object.keys(t);return r.length===0?"{}":r.length<=3?JSON.stringify(t):`{${r.length} keys: ${r.slice(0,3).join(", ")}...}`}return String(t)}formatTool(t,r){if(!r)return t;let e=typeof r=="string"?JSON.parse(r):r;if(t==="Bash"&&e.command)return`${t}(${e.command})`;if(e.file_path)return`${t}(${e.file_path})`;if(e.notebook_path)return`${t}(${e.notebook_path})`;if(t==="Glob"&&e.pattern)return`${t}(${e.pattern})`;if(t==="Grep"&&e.pattern)return`${t}(${e.pattern})`;if(e.url)return`${t}(${e.url})`;if(e.query)return`${t}(${e.query})`;if(t==="Task"){if(e.subagent_type)return`${t}(${e.subagent_type})`;if(e.description)return`${t}(${e.description})`}return t==="Skill"&&e.skill?`${t}(${e.skill})`:t==="LSP"&&e.operation?`${t}(${e.operation})`:t}formatTimestamp(t){let r=t.getFullYear(),e=String(t.getMonth()+1).padStart(2,"0"),n=String(t.getDate()).padStart(2,"0"),o=String(t.getHours()).padStart(2,"0"),E=String(t.getMinutes()).padStart(2,"0"),i=String(t.getSeconds()).padStart(2,"0"),a=String(t.getMilliseconds()).padStart(3,"0");return`${r}-${e}-${n} ${o}:${E}:${i}.${a}`}log(t,r,e,n,o){if(t<this.getLevel())return;let E=this.formatTimestamp(new Date),i=f[t].padEnd(5),a=r.padEnd(6),_="";n?.correlationId?_=`[${n.correlationId}] `:n?.sessionId&&(_=`[session-${n.sessionId}] `);let g="";o!=null&&(this.getLevel()===0&&typeof o=="object"?g=`
+`+JSON.stringify(o,null,2):g=" "+this.formatData(o));let S="";if(n){let{sessionId:J,sdkSessionId:q,correlationId:z,...D}=n;Object.keys(D).length>0&&(S=` {${Object.entries(D).map(([$,k])=>`${$}=${k}`).join(", ")}}`)}let m=`[${E}] [${i}] [${a}] ${_}${e}${S}${g}`;t===3?console.error(m):console.log(m)}debug(t,r,e,n){this.log(0,t,r,e,n)}info(t,r,e,n){this.log(1,t,r,e,n)}warn(t,r,e,n){this.log(2,t,r,e,n)}error(t,r,e,n){this.log(3,t,r,e,n)}dataIn(t,r,e,n){this.info(t,`\u2192 ${r}`,e,n)}dataOut(t,r,e,n){this.info(t,`\u2190 ${r}`,e,n)}success(t,r,e,n){this.info(t,`\u2713 ${r}`,e,n)}failure(t,r,e,n){this.error(t,`\u2717 ${r}`,e,n)}timing(t,r,e,n){this.info(t,`\u23F1 ${r}`,n,{duration:`${e}ms`})}happyPathError(t,r,e,n,o=""){let _=((new Error().stack||"").split(`
+`)[2]||"").match(/at\s+(?:.*\s+)?\(?([^:]+):(\d+):(\d+)\)?/),g=_?`${_[1].split("/").pop()}:${_[2]}`:"unknown",S={...e,location:g};return this.warn(t,`[HAPPY-PATH] ${r}`,S,n),o}},l=new p;import A from"path";import{homedir as W}from"os";import{readFileSync as b}from"fs";var u={DEFAULT:3e5,HEALTH_CHECK:3e4,WORKER_STARTUP_WAIT:1e3,WORKER_STARTUP_RETRIES:300,PRE_RESTART_SETTLE_DELAY:2e3,WINDOWS_MULTIPLIER:1.5};function d(s){return process.platform==="win32"?Math.round(s*u.WINDOWS_MULTIPLIER):s}function I(s={}){let{port:t,includeSkillFallback:r=!1,customPrefix:e,actualError:n}=s,o=e||"Worker service connection failed.",E=t?` (port ${t})`:"",i=`${o}${E}
 
 `;return i+=`To restart the worker:
 `,i+=`1. Exit Claude Code completely
-`,i+=`2. Run: claude-mem restart
+`,i+=`2. Run: npm run worker:restart
 `,i+="3. Restart Claude Code",r&&(i+=`
 
 If that doesn't work, try: /troubleshoot`),n&&(i=`Worker Error: ${n}
 
-${i}`),i}var F=C.join(b(),".claude","plugins","marketplaces","thedotmack"),U=y(u.HEALTH_CHECK),p=null;function f(){if(p!==null)return p;let s=C.join(g.get("CLAUDE_MEM_DATA_DIR"),"settings.json"),t=g.loadFromFile(s);return p=parseInt(t.CLAUDE_MEM_WORKER_PORT,10),p}async function K(){let s=f();return(await fetch(`http://127.0.0.1:${s}/api/readiness`,{signal:AbortSignal.timeout(U)})).ok}function X(){let s=C.join(F,"package.json");return JSON.parse(P(s,"utf-8")).version}async function V(){let s=f(),t=await fetch(`http://127.0.0.1:${s}/api/version`,{signal:AbortSignal.timeout(U)});if(!t.ok)throw new Error(`Failed to get worker version: ${t.status}`);return(await t.json()).version}async function G(){let s=X(),t=await V();s!==t&&c.warn("SYSTEM","Worker version mismatch",{pluginVersion:s,workerVersion:t,hint:"Restart worker with: claude-mem worker restart"})}async function I(){for(let r=0;r<25;r++){try{if(await K()){await G();return}}catch{}await new Promise(e=>setTimeout(e,200))}throw new Error(R({port:f(),customPrefix:"Worker did not become ready within 5 seconds."}))}import{readFileSync as j,existsSync as B}from"fs";function M(s,t,r=!1){if(!s||!B(s))throw new Error(`Transcript path missing or file does not exist: ${s}`);let e=j(s,"utf-8").trim();if(!e)throw new Error(`Transcript file exists but is empty: ${s}`);let n=e.split(`
-`),o=!1;for(let a=n.length-1;a>=0;a--){let i=JSON.parse(n[a]);if(i.type===t&&(o=!0,i.message?.content)){let _="",E=i.message.content;if(typeof E=="string")_=E;else if(Array.isArray(E))_=E.filter(l=>l.type==="text").map(l=>l.text).join(`
-`);else throw new Error(`Unknown message content format in transcript. Type: ${typeof E}`);return r&&(_=_.replace(/<system-reminder>[\s\S]*?<\/system-reminder>/g,""),_=_.replace(/\n{3,}/g,`
+${i}`),i}var F=A.join(W(),".claude","plugins","marketplaces","thedotmack"),N=d(u.HEALTH_CHECK),T=null;function O(){if(T!==null)return T;let s=A.join(c.get("CLAUDE_MEM_DATA_DIR"),"settings.json"),t=c.loadFromFile(s);return T=parseInt(t.CLAUDE_MEM_WORKER_PORT,10),T}async function K(){let s=O();return(await fetch(`http://127.0.0.1:${s}/api/readiness`,{signal:AbortSignal.timeout(N)})).ok}function G(){let s=A.join(F,"package.json");return JSON.parse(b(s,"utf-8")).version}async function X(){let s=O(),t=await fetch(`http://127.0.0.1:${s}/api/version`,{signal:AbortSignal.timeout(N)});if(!t.ok)throw new Error(`Failed to get worker version: ${t.status}`);return(await t.json()).version}async function V(){let s=G(),t=await X();s!==t&&l.warn("SYSTEM","Worker version mismatch",{pluginVersion:s,workerVersion:t,hint:"Restart worker with: claude-mem worker restart"})}async function h(){for(let r=0;r<25;r++){try{if(await K()){await V();return}}catch{}await new Promise(e=>setTimeout(e,200))}throw new Error(I({port:O(),customPrefix:"Worker did not become ready within 5 seconds."}))}import{readFileSync as j,existsSync as B}from"fs";function L(s,t,r=!1){if(!s||!B(s))throw new Error(`Transcript path missing or file does not exist: ${s}`);let e=j(s,"utf-8").trim();if(!e)throw new Error(`Transcript file exists but is empty: ${s}`);let n=e.split(`
+`),o=!1;for(let E=n.length-1;E>=0;E--){let i=JSON.parse(n[E]);if(i.type===t&&(o=!0,i.message?.content)){let a="",_=i.message.content;if(typeof _=="string")a=_;else if(Array.isArray(_))a=_.filter(g=>g.type==="text").map(g=>g.text).join(`
+`);else throw new Error(`Unknown message content format in transcript. Type: ${typeof _}`);return r&&(a=a.replace(/<system-reminder>[\s\S]*?<\/system-reminder>/g,""),a=a.replace(/\n{3,}/g,`
 
-`).trim()),_}}if(!o)throw new Error(`No message found for role '${t}' in transcript: ${s}`);return""}async function Y(s){if(await I(),!s)throw new Error("summaryHook requires input");let{session_id:t}=s,r=f();if(!s.transcript_path)throw new Error(`Missing transcript_path in Stop hook input for session ${t}`);let e=M(s.transcript_path,"user"),n=M(s.transcript_path,"assistant",!0);c.dataIn("HOOK","Stop: Requesting summary",{workerPort:r,hasLastUserMessage:!!e,hasLastAssistantMessage:!!n});let o=await fetch(`http://127.0.0.1:${r}/api/sessions/summarize`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({claudeSessionId:t,last_user_message:e,last_assistant_message:n}),signal:AbortSignal.timeout(u.DEFAULT)});if(!o.ok)throw console.log(T),new Error(`Summary generation failed: ${o.status}`);c.debug("HOOK","Summary request sent successfully"),console.log(T)}var A="";N.on("data",s=>A+=s);N.on("end",async()=>{let s;try{s=A?JSON.parse(A):void 0}catch(t){throw new Error(`Failed to parse hook input: ${t instanceof Error?t.message:String(t)}`)}await Y(s)});
+`).trim()),a}}if(!o)throw new Error(`No message found for role '${t}' in transcript: ${s}`);return""}async function Y(s){if(await h(),!s)throw new Error("summaryHook requires input");let{session_id:t}=s,r=O();if(!s.transcript_path)throw new Error(`Missing transcript_path in Stop hook input for session ${t}`);let e=L(s.transcript_path,"user"),n=L(s.transcript_path,"assistant",!0);l.dataIn("HOOK","Stop: Requesting summary",{workerPort:r,hasLastUserMessage:!!e,hasLastAssistantMessage:!!n});let o=await fetch(`http://127.0.0.1:${r}/api/sessions/summarize`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({claudeSessionId:t,last_user_message:e,last_assistant_message:n}),signal:AbortSignal.timeout(u.DEFAULT)});if(!o.ok)throw console.log(M),new Error(`Summary generation failed: ${o.status}`);l.debug("HOOK","Summary request sent successfully"),console.log(M)}var C="";y.on("data",s=>C+=s);y.on("end",async()=>{let s;try{s=C?JSON.parse(C):void 0}catch(t){throw new Error(`Failed to parse hook input: ${t instanceof Error?t.message:String(t)}`)}await Y(s)});

plugin/scripts/user-message-hook.js

@@ -1,25 +1,25 @@
 #!/usr/bin/env bun
-import{basename as V}from"path";import C from"path";import{homedir as P}from"os";import{readFileSync as H}from"fs";import{readFileSync as k,writeFileSync as v,existsSync as W}from"fs";import{join as w}from"path";import{homedir as b}from"os";var m="bugfix,feature,refactor,discovery,decision,change",D="how-it-works,why-it-exists,what-changed,problem-solution,gotcha,pattern,trade-off";var _=class{static DEFAULTS={CLAUDE_MEM_MODEL:"claude-sonnet-4-5",CLAUDE_MEM_CONTEXT_OBSERVATIONS:"50",CLAUDE_MEM_WORKER_PORT:"37777",CLAUDE_MEM_WORKER_HOST:"127.0.0.1",CLAUDE_MEM_SKIP_TOOLS:"ListMcpResourcesTool,SlashCommand,Skill,TodoWrite,AskUserQuestion",CLAUDE_MEM_DATA_DIR:w(b(),".claude-mem"),CLAUDE_MEM_LOG_LEVEL:"INFO",CLAUDE_MEM_PYTHON_VERSION:"3.13",CLAUDE_CODE_PATH:"",CLAUDE_MEM_MODE:"code",CLAUDE_MEM_CONTEXT_SHOW_READ_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_WORK_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_AMOUNT:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_PERCENT:"true",CLAUDE_MEM_CONTEXT_OBSERVATION_TYPES:m,CLAUDE_MEM_CONTEXT_OBSERVATION_CONCEPTS:D,CLAUDE_MEM_CONTEXT_FULL_COUNT:"5",CLAUDE_MEM_CONTEXT_FULL_FIELD:"narrative",CLAUDE_MEM_CONTEXT_SESSION_COUNT:"10",CLAUDE_MEM_CONTEXT_SHOW_LAST_SUMMARY:"true",CLAUDE_MEM_CONTEXT_SHOW_LAST_MESSAGE:"false"};static getAllDefaults(){return{...this.DEFAULTS}}static get(t){return this.DEFAULTS[t]}static getInt(t){let r=this.get(t);return parseInt(r,10)}static getBool(t){return this.get(t)==="true"}static loadFromFile(t){try{if(!W(t))return this.getAllDefaults();let r=k(t,"utf-8"),e=JSON.parse(r),n=e;if(e.env&&typeof e.env=="object"){n=e.env;try{v(t,JSON.stringify(n,null,2),"utf-8"),c.info("SETTINGS","Migrated settings file from nested to flat schema",{settingsPath:t})}catch(E){c.warn("SETTINGS","Failed to auto-migrate settings file",{settingsPath:t},E)}}let o={...this.DEFAULTS};for(let E of Object.keys(this.DEFAULTS))n[E]!==void 0&&(o[E]=n[E]);return o}catch(r){return c.warn("SETTINGS","Failed to load settings, using defaults",{settingsPath:t},r),this.getAllDefaults()}}};var p=(o=>(o[o.DEBUG=0]="DEBUG",o[o.INFO=1]="INFO",o[o.WARN=2]="WARN",o[o.ERROR=3]="ERROR",o[o.SILENT=4]="SILENT",o))(p||{}),f=class{level=null;useColor;constructor(){this.useColor=process.stdout.isTTY??!1}getLevel(){if(this.level===null){let t=_.get("CLAUDE_MEM_LOG_LEVEL").toUpperCase();this.level=p[t]??1}return this.level}correlationId(t,r){return`obs-${t}-${r}`}sessionId(t){return`session-${t}`}formatData(t){if(t==null)return"";if(typeof t=="string")return t;if(typeof t=="number"||typeof t=="boolean")return t.toString();if(typeof t=="object"){if(t instanceof Error)return this.getLevel()===0?`${t.message}
-${t.stack}`:t.message;if(Array.isArray(t))return`[${t.length} items]`;let r=Object.keys(t);return r.length===0?"{}":r.length<=3?JSON.stringify(t):`{${r.length} keys: ${r.slice(0,3).join(", ")}...}`}return String(t)}formatTool(t,r){if(!r)return t;let e=typeof r=="string"?JSON.parse(r):r;if(t==="Bash"&&e.command)return`${t}(${e.command})`;if(e.file_path)return`${t}(${e.file_path})`;if(e.notebook_path)return`${t}(${e.notebook_path})`;if(t==="Glob"&&e.pattern)return`${t}(${e.pattern})`;if(t==="Grep"&&e.pattern)return`${t}(${e.pattern})`;if(e.url)return`${t}(${e.url})`;if(e.query)return`${t}(${e.query})`;if(t==="Task"){if(e.subagent_type)return`${t}(${e.subagent_type})`;if(e.description)return`${t}(${e.description})`}return t==="Skill"&&e.skill?`${t}(${e.skill})`:t==="LSP"&&e.operation?`${t}(${e.operation})`:t}formatTimestamp(t){let r=t.getFullYear(),e=String(t.getMonth()+1).padStart(2,"0"),n=String(t.getDate()).padStart(2,"0"),o=String(t.getHours()).padStart(2,"0"),E=String(t.getMinutes()).padStart(2,"0"),i=String(t.getSeconds()).padStart(2,"0"),u=String(t.getMilliseconds()).padStart(3,"0");return`${r}-${e}-${n} ${o}:${E}:${i}.${u}`}log(t,r,e,n,o){if(t<this.getLevel())return;let E=this.formatTimestamp(new Date),i=p[t].padEnd(5),u=r.padEnd(6),a="";n?.correlationId?a=`[${n.correlationId}] `:n?.sessionId&&(a=`[session-${n.sessionId}] `);let l="";o!=null&&(this.getLevel()===0&&typeof o=="object"?l=`
-`+JSON.stringify(o,null,2):l=" "+this.formatData(o));let S="";if(n){let{sessionId:Y,sdkSessionId:J,correlationId:q,...A}=n;Object.keys(A).length>0&&(S=` {${Object.entries(A).map(([$,N])=>`${$}=${N}`).join(", ")}}`)}let M=`[${E}] [${i}] [${u}] ${a}${e}${S}${l}`;t===3?console.error(M):console.log(M)}debug(t,r,e,n){this.log(0,t,r,e,n)}info(t,r,e,n){this.log(1,t,r,e,n)}warn(t,r,e,n){this.log(2,t,r,e,n)}error(t,r,e,n){this.log(3,t,r,e,n)}dataIn(t,r,e,n){this.info(t,`\u2192 ${r}`,e,n)}dataOut(t,r,e,n){this.info(t,`\u2190 ${r}`,e,n)}success(t,r,e,n){this.info(t,`\u2713 ${r}`,e,n)}failure(t,r,e,n){this.error(t,`\u2717 ${r}`,e,n)}timing(t,r,e,n){this.info(t,`\u23F1 ${r}`,n,{duration:`${e}ms`})}happyPathError(t,r,e,n,o=""){let a=((new Error().stack||"").split(`
-`)[2]||"").match(/at\s+(?:.*\s+)?\(?([^:]+):(\d+):(\d+)\)?/),l=a?`${a[1].split("/").pop()}:${a[2]}`:"unknown",S={...e,location:l};return this.warn(t,`[HAPPY-PATH] ${r}`,S,n),o}},c=new f;var O={DEFAULT:12e4,HEALTH_CHECK:1e3,WORKER_STARTUP_WAIT:1e3,WORKER_STARTUP_RETRIES:15,PRE_RESTART_SETTLE_DELAY:2e3,WINDOWS_MULTIPLIER:1.5},d={SUCCESS:0,FAILURE:1,USER_MESSAGE_ONLY:3};function h(s){return process.platform==="win32"?Math.round(s*O.WINDOWS_MULTIPLIER):s}function R(s={}){let{port:t,includeSkillFallback:r=!1,customPrefix:e,actualError:n}=s,o=e||"Worker service connection failed.",E=t?` (port ${t})`:"",i=`${o}${E}
+import{basename as V}from"path";import C from"path";import{homedir as b}from"os";import{readFileSync as x}from"fs";import{readFileSync as k,writeFileSync as P,existsSync as v}from"fs";import{join as W}from"path";import{homedir as w}from"os";var D="bugfix,feature,refactor,discovery,decision,change",U="how-it-works,why-it-exists,what-changed,problem-solution,gotcha,pattern,trade-off";var a=class{static DEFAULTS={CLAUDE_MEM_MODEL:"claude-sonnet-4-5",CLAUDE_MEM_CONTEXT_OBSERVATIONS:"50",CLAUDE_MEM_WORKER_PORT:"37777",CLAUDE_MEM_WORKER_HOST:"127.0.0.1",CLAUDE_MEM_SKIP_TOOLS:"ListMcpResourcesTool,SlashCommand,Skill,TodoWrite,AskUserQuestion",CLAUDE_MEM_PROVIDER:"claude",CLAUDE_MEM_GEMINI_API_KEY:"",CLAUDE_MEM_GEMINI_MODEL:"gemini-2.5-flash-lite",CLAUDE_MEM_GEMINI_RATE_LIMITING_ENABLED:"true",CLAUDE_MEM_OPENROUTER_API_KEY:"",CLAUDE_MEM_OPENROUTER_MODEL:"xiaomi/mimo-v2-flash:free",CLAUDE_MEM_OPENROUTER_SITE_URL:"",CLAUDE_MEM_OPENROUTER_APP_NAME:"claude-mem",CLAUDE_MEM_OPENROUTER_MAX_CONTEXT_MESSAGES:"20",CLAUDE_MEM_OPENROUTER_MAX_TOKENS:"100000",CLAUDE_MEM_DATA_DIR:W(w(),".claude-mem"),CLAUDE_MEM_LOG_LEVEL:"INFO",CLAUDE_MEM_PYTHON_VERSION:"3.13",CLAUDE_CODE_PATH:"",CLAUDE_MEM_MODE:"code",CLAUDE_MEM_CONTEXT_SHOW_READ_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_WORK_TOKENS:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_AMOUNT:"true",CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_PERCENT:"true",CLAUDE_MEM_CONTEXT_OBSERVATION_TYPES:D,CLAUDE_MEM_CONTEXT_OBSERVATION_CONCEPTS:U,CLAUDE_MEM_CONTEXT_FULL_COUNT:"5",CLAUDE_MEM_CONTEXT_FULL_FIELD:"narrative",CLAUDE_MEM_CONTEXT_SESSION_COUNT:"10",CLAUDE_MEM_CONTEXT_SHOW_LAST_SUMMARY:"true",CLAUDE_MEM_CONTEXT_SHOW_LAST_MESSAGE:"false"};static getAllDefaults(){return{...this.DEFAULTS}}static get(t){return this.DEFAULTS[t]}static getInt(t){let r=this.get(t);return parseInt(r,10)}static getBool(t){return this.get(t)==="true"}static loadFromFile(t){try{if(!v(t))return this.getAllDefaults();let r=k(t,"utf-8"),e=JSON.parse(r),n=e;if(e.env&&typeof e.env=="object"){n=e.env;try{P(t,JSON.stringify(n,null,2),"utf-8"),l.info("SETTINGS","Migrated settings file from nested to flat schema",{settingsPath:t})}catch(E){l.warn("SETTINGS","Failed to auto-migrate settings file",{settingsPath:t},E)}}let o={...this.DEFAULTS};for(let E of Object.keys(this.DEFAULTS))n[E]!==void 0&&(o[E]=n[E]);return o}catch(r){return l.warn("SETTINGS","Failed to load settings, using defaults",{settingsPath:t},r),this.getAllDefaults()}}};var O=(o=>(o[o.DEBUG=0]="DEBUG",o[o.INFO=1]="INFO",o[o.WARN=2]="WARN",o[o.ERROR=3]="ERROR",o[o.SILENT=4]="SILENT",o))(O||{}),S=class{level=null;useColor;constructor(){this.useColor=process.stdout.isTTY??!1}getLevel(){if(this.level===null){let t=a.get("CLAUDE_MEM_LOG_LEVEL").toUpperCase();this.level=O[t]??1}return this.level}correlationId(t,r){return`obs-${t}-${r}`}sessionId(t){return`session-${t}`}formatData(t){if(t==null)return"";if(typeof t=="string")return t;if(typeof t=="number"||typeof t=="boolean")return t.toString();if(typeof t=="object"){if(t instanceof Error)return this.getLevel()===0?`${t.message}
+${t.stack}`:t.message;if(Array.isArray(t))return`[${t.length} items]`;let r=Object.keys(t);return r.length===0?"{}":r.length<=3?JSON.stringify(t):`{${r.length} keys: ${r.slice(0,3).join(", ")}...}`}return String(t)}formatTool(t,r){if(!r)return t;let e=typeof r=="string"?JSON.parse(r):r;if(t==="Bash"&&e.command)return`${t}(${e.command})`;if(e.file_path)return`${t}(${e.file_path})`;if(e.notebook_path)return`${t}(${e.notebook_path})`;if(t==="Glob"&&e.pattern)return`${t}(${e.pattern})`;if(t==="Grep"&&e.pattern)return`${t}(${e.pattern})`;if(e.url)return`${t}(${e.url})`;if(e.query)return`${t}(${e.query})`;if(t==="Task"){if(e.subagent_type)return`${t}(${e.subagent_type})`;if(e.description)return`${t}(${e.description})`}return t==="Skill"&&e.skill?`${t}(${e.skill})`:t==="LSP"&&e.operation?`${t}(${e.operation})`:t}formatTimestamp(t){let r=t.getFullYear(),e=String(t.getMonth()+1).padStart(2,"0"),n=String(t.getDate()).padStart(2,"0"),o=String(t.getHours()).padStart(2,"0"),E=String(t.getMinutes()).padStart(2,"0"),i=String(t.getSeconds()).padStart(2,"0"),T=String(t.getMilliseconds()).padStart(3,"0");return`${r}-${e}-${n} ${o}:${E}:${i}.${T}`}log(t,r,e,n,o){if(t<this.getLevel())return;let E=this.formatTimestamp(new Date),i=O[t].padEnd(5),T=r.padEnd(6),_="";n?.correlationId?_=`[${n.correlationId}] `:n?.sessionId&&(_=`[session-${n.sessionId}] `);let c="";o!=null&&(this.getLevel()===0&&typeof o=="object"?c=`
+`+JSON.stringify(o,null,2):c=" "+this.formatData(o));let M="";if(n){let{sessionId:B,sdkSessionId:J,correlationId:q,...L}=n;Object.keys(L).length>0&&(M=` {${Object.entries(L).map(([y,$])=>`${y}=${$}`).join(", ")}}`)}let p=`[${E}] [${i}] [${T}] ${_}${e}${M}${c}`;t===3?console.error(p):console.log(p)}debug(t,r,e,n){this.log(0,t,r,e,n)}info(t,r,e,n){this.log(1,t,r,e,n)}warn(t,r,e,n){this.log(2,t,r,e,n)}error(t,r,e,n){this.log(3,t,r,e,n)}dataIn(t,r,e,n){this.info(t,`\u2192 ${r}`,e,n)}dataOut(t,r,e,n){this.info(t,`\u2190 ${r}`,e,n)}success(t,r,e,n){this.info(t,`\u2713 ${r}`,e,n)}failure(t,r,e,n){this.error(t,`\u2717 ${r}`,e,n)}timing(t,r,e,n){this.info(t,`\u23F1 ${r}`,n,{duration:`${e}ms`})}happyPathError(t,r,e,n,o=""){let _=((new Error().stack||"").split(`
+`)[2]||"").match(/at\s+(?:.*\s+)?\(?([^:]+):(\d+):(\d+)\)?/),c=_?`${_[1].split("/").pop()}:${_[2]}`:"unknown",M={...e,location:c};return this.warn(t,`[HAPPY-PATH] ${r}`,M,n),o}},l=new S;var A={DEFAULT:3e5,HEALTH_CHECK:3e4,WORKER_STARTUP_WAIT:1e3,WORKER_STARTUP_RETRIES:300,PRE_RESTART_SETTLE_DELAY:2e3,WINDOWS_MULTIPLIER:1.5},R={SUCCESS:0,FAILURE:1,USER_MESSAGE_ONLY:3};function m(s){return process.platform==="win32"?Math.round(s*A.WINDOWS_MULTIPLIER):s}function I(s={}){let{port:t,includeSkillFallback:r=!1,customPrefix:e,actualError:n}=s,o=e||"Worker service connection failed.",E=t?` (port ${t})`:"",i=`${o}${E}
 
 `;return i+=`To restart the worker:
 `,i+=`1. Exit Claude Code completely
-`,i+=`2. Run: claude-mem restart
+`,i+=`2. Run: npm run worker:restart
 `,i+="3. Restart Claude Code",r&&(i+=`
 
 If that doesn't work, try: /troubleshoot`),n&&(i=`Worker Error: ${n}
 
-${i}`),i}var x=C.join(P(),".claude","plugins","marketplaces","thedotmack"),U=h(O.HEALTH_CHECK),T=null;function g(){if(T!==null)return T;let s=C.join(_.get("CLAUDE_MEM_DATA_DIR"),"settings.json"),t=_.loadFromFile(s);return T=parseInt(t.CLAUDE_MEM_WORKER_PORT,10),T}async function F(){let s=g();return(await fetch(`http://127.0.0.1:${s}/api/readiness`,{signal:AbortSignal.timeout(U)})).ok}function K(){let s=C.join(x,"package.json");return JSON.parse(H(s,"utf-8")).version}async function X(){let s=g(),t=await fetch(`http://127.0.0.1:${s}/api/version`,{signal:AbortSignal.timeout(U)});if(!t.ok)throw new Error(`Failed to get worker version: ${t.status}`);return(await t.json()).version}async function G(){let s=K(),t=await X();s!==t&&c.warn("SYSTEM","Worker version mismatch",{pluginVersion:s,workerVersion:t,hint:"Restart worker with: claude-mem worker restart"})}async function I(){for(let r=0;r<25;r++){try{if(await F()){await G();return}}catch{}await new Promise(e=>setTimeout(e,200))}throw new Error(R({port:g(),customPrefix:"Worker did not become ready within 5 seconds."}))}await I();var y=g(),j=V(process.cwd()),L=await fetch(`http://127.0.0.1:${y}/api/context/inject?project=${encodeURIComponent(j)}&colors=true`,{method:"GET",signal:AbortSignal.timeout(5e3)});if(!L.ok)throw new Error(`Failed to fetch context: ${L.status}`);var B=await L.text();console.error(`
+${i}`),i}var H=C.join(b(),".claude","plugins","marketplaces","thedotmack"),N=m(A.HEALTH_CHECK),u=null;function g(){if(u!==null)return u;let s=C.join(a.get("CLAUDE_MEM_DATA_DIR"),"settings.json"),t=a.loadFromFile(s);return u=parseInt(t.CLAUDE_MEM_WORKER_PORT,10),u}async function F(){let s=g();return(await fetch(`http://127.0.0.1:${s}/api/readiness`,{signal:AbortSignal.timeout(N)})).ok}function G(){let s=C.join(H,"package.json");return JSON.parse(x(s,"utf-8")).version}async function K(){let s=g(),t=await fetch(`http://127.0.0.1:${s}/api/version`,{signal:AbortSignal.timeout(N)});if(!t.ok)throw new Error(`Failed to get worker version: ${t.status}`);return(await t.json()).version}async function X(){let s=G(),t=await K();s!==t&&l.warn("SYSTEM","Worker version mismatch",{pluginVersion:s,workerVersion:t,hint:"Restart worker with: claude-mem worker restart"})}async function h(){for(let r=0;r<25;r++){try{if(await F()){await X();return}}catch{}await new Promise(e=>setTimeout(e,200))}throw new Error(I({port:g(),customPrefix:"Worker did not become ready within 5 seconds."}))}await h();var d=g(),j=V(process.cwd()),f=await fetch(`http://127.0.0.1:${d}/api/context/inject?project=${encodeURIComponent(j)}&colors=true`,{method:"GET",signal:AbortSignal.timeout(5e3)});if(!f.ok)throw new Error(`Failed to fetch context: ${f.status}`);var Y=await f.text();console.error(`
 
 \u{1F4DD} Claude-Mem Context Loaded
    \u2139\uFE0F  Note: This appears as stderr but is informational only
 
-`+B+`
+`+Y+`
 
 \u{1F4A1} New! Wrap all or part of any message with <private> ... </private> to prevent storing sensitive information in your observation history.
 
 \u{1F4AC} Community https://discord.gg/J4wttp9vDu
-\u{1F4FA} Watch live in browser http://localhost:${y}/
-`);process.exit(d.USER_MESSAGE_ONLY);
+\u{1F4FA} Watch live in browser http://localhost:${d}/
+`);process.exit(R.USER_MESSAGE_ONLY);

plugin/skills/mem-search/operations/formatting.md

@@ -288,7 +288,7 @@ npm run worker:status
 If the worker is stopped, restart it:
 
 ```bash
-claude-mem restart
+npm run worker:restart
 ```
 ```
 

plugin/skills/troubleshoot/operations/automated-fixes.md

@@ -44,7 +44,7 @@ npm run worker:status
 ```bash
 cd ~/.claude/plugins/marketplaces/thedotmack/ && \
 npm install && \
-claude-mem restart
+npm run worker:restart
 ```
 
 ## Fix: Stale PID File
@@ -70,7 +70,7 @@ curl -s http://127.0.0.1:37777/health
 mkdir -p ~/.claude-mem && \
 echo '{"CLAUDE_MEM_WORKER_PORT":"37778"}' > ~/.claude-mem/settings.json && \
 cd ~/.claude/plugins/marketplaces/thedotmack/ && \
-claude-mem restart && \
+npm run worker:restart && \
 sleep 2 && \
 curl -s http://127.0.0.1:37778/health
 ```
@@ -86,7 +86,7 @@ curl -s http://127.0.0.1:37778/health
 cp ~/.claude-mem/claude-mem.db ~/.claude-mem/claude-mem.db.backup && \
 sqlite3 ~/.claude-mem/claude-mem.db "PRAGMA integrity_check;" && \
 cd ~/.claude/plugins/marketplaces/thedotmack/ && \
-claude-mem restart
+npm run worker:restart
 ```
 
 **If integrity check fails, recreate database:**
@@ -94,7 +94,7 @@ claude-mem restart
 # WARNING: This deletes all memory data
 mv ~/.claude-mem/claude-mem.db ~/.claude-mem/claude-mem.db.old && \
 cd ~/.claude/plugins/marketplaces/thedotmack/ && \
-claude-mem restart
+npm run worker:restart
 ```
 
 ## Fix: Clean Reinstall
@@ -135,7 +135,7 @@ find ~/.claude-mem/logs/ -name "worker-*.log" -mtime +7 -delete
 
 # Restart worker for fresh log
 cd ~/.claude/plugins/marketplaces/thedotmack/
-claude-mem restart
+npm run worker:restart
 ```
 
 **Note:** Logs auto-rotate daily, manual cleanup rarely needed.

plugin/skills/troubleshoot/operations/common-issues.md

@@ -29,7 +29,7 @@ Quick fixes for frequently encountered claude-mem problems.
 3. Restart worker and start new session:
    ```bash
    cd ~/.claude/plugins/marketplaces/thedotmack/
-   claude-mem restart
+   npm run worker:restart
    ```
 
 4. Create a test observation: `/skill version-bump` then cancel
@@ -173,7 +173,7 @@ Quick fixes for frequently encountered claude-mem problems.
 4. If FTS5 out of sync, restart worker (triggers reindex):
    ```bash
    cd ~/.claude/plugins/marketplaces/thedotmack/
-   claude-mem restart
+   npm run worker:restart
    ```
 
 ## Issue: Port Conflicts
@@ -194,7 +194,7 @@ Quick fixes for frequently encountered claude-mem problems.
    mkdir -p ~/.claude-mem
    echo '{"CLAUDE_MEM_WORKER_PORT":"37778"}' > ~/.claude-mem/settings.json
    cd ~/.claude/plugins/marketplaces/thedotmack/
-   claude-mem restart
+   npm run worker:restart
    ```
 
 ## Issue: Database Corrupted
@@ -219,7 +219,7 @@ Quick fixes for frequently encountered claude-mem problems.
    ```bash
    rm ~/.claude-mem/claude-mem.db
    cd ~/.claude/plugins/marketplaces/thedotmack/
-   claude-mem restart
+   npm run worker:restart
    # Worker will create new database
    ```
 

plugin/skills/troubleshoot/operations/database.md

@@ -173,7 +173,7 @@ If FTS5 counts don't match, triggers may have failed. Restart worker to rebuild:
 
 ```bash
 cd ~/.claude/plugins/marketplaces/thedotmack/
-claude-mem restart
+npm run worker:restart
 ```
 
 The worker will rebuild FTS5 indexes on startup if they're out of sync.
@@ -263,7 +263,7 @@ sqlite3 ~/.claude-mem/claude-mem.db "SELECT COUNT(*) FROM observations;"
    ```bash
    mv ~/.claude-mem/claude-mem.db ~/.claude-mem/claude-mem.db.archive
    cd ~/.claude/plugins/marketplaces/thedotmack/
-   claude-mem restart
+   npm run worker:restart
    ```
 
 ## Database Recovery

plugin/skills/troubleshoot/operations/reference.md

@@ -13,7 +13,7 @@ npm run worker:status
 npm run worker:start
 
 # Restart worker
-claude-mem restart
+npm run worker:restart
 
 # Stop worker
 npm run worker:stop

plugin/skills/troubleshoot/operations/worker.md

@@ -152,7 +152,7 @@ npm run worker:start
 ```bash
 # Restart worker (stops and starts)
 cd ~/.claude/plugins/marketplaces/thedotmack/
-claude-mem restart
+npm run worker:restart
 
 # Or manually stop and start
 npm run worker:stop
@@ -219,7 +219,7 @@ npm run worker:start
 **Port conflict:**
 ```bash
 echo '{"CLAUDE_MEM_WORKER_PORT":"37778"}' > ~/.claude-mem/settings.json
-claude-mem restart
+npm run worker:restart
 ```
 
 **Stale PID file:**
@@ -261,14 +261,14 @@ If fails, backup and recreate database.
 **Out of memory:**
 Check if database is too large or memory leak. Restart:
 ```bash
-claude-mem restart
+npm run worker:restart
 ```
 
 **Port conflict race condition:**
 Another process grabbing port intermittently. Change port:
 ```bash
 echo '{"CLAUDE_MEM_WORKER_PORT":"37778"}' > ~/.claude-mem/settings.json
-claude-mem restart
+npm run worker:restart
 ```
 
 ## Worker Management Commands
@@ -284,7 +284,7 @@ npm run worker:start
 npm run worker:stop
 
 # Restart worker
-claude-mem restart
+npm run worker:restart
 
 # View logs
 npm run worker:logs
@@ -355,7 +355,7 @@ All should return appropriate responses (HTML for viewer, JSON for APIs).
 |---------|---------|----------------|
 | Check if running | `npm run worker:status` | Shows PID and uptime |
 | Worker not running | `npm run worker:start` | Worker starts successfully |
-| Worker crashed | `claude-mem restart` | Worker restarts |
+| Worker crashed | `npm run worker:restart` | Worker restarts |
 | View recent errors | `grep -i error ~/.claude-mem/logs/worker-$(date +%Y-%m-%d).log \| tail -20` | Shows recent errors |
 | Port in use | `lsof -i :37777` | Shows process using port |
 | Stale PID | `rm ~/.claude-mem/worker.pid && npm run worker:start` | Removes stale PID and starts |

plugin/ui/viewer.html

@@ -1817,6 +1817,49 @@
       min-height: 0;
     }
 
+    .modal-footer {
+      display: flex;
+      justify-content: flex-end;
+      align-items: center;
+      gap: 16px;
+      padding: 16px 24px;
+      border-top: 1px solid var(--modal-border);
+      background: var(--modal-header-bg);
+    }
+
+    .modal-footer .save-status {
+      font-size: 13px;
+    }
+
+    .modal-footer .save-status .success {
+      color: var(--success-color, #22c55e);
+    }
+
+    .modal-footer .save-status .error {
+      color: var(--error-color, #ef4444);
+    }
+
+    .modal-footer .save-btn {
+      padding: 8px 24px;
+      background: var(--accent-color, #3b82f6);
+      color: white;
+      border: none;
+      border-radius: 6px;
+      font-size: 14px;
+      font-weight: 500;
+      cursor: pointer;
+      transition: background 0.15s ease;
+    }
+
+    .modal-footer .save-btn:hover:not(:disabled) {
+      background: var(--accent-hover, #2563eb);
+    }
+
+    .modal-footer .save-btn:disabled {
+      opacity: 0.6;
+      cursor: not-allowed;
+    }
+
     /* Preview Column - Terminal Style */
     .preview-column {
       padding: 20px;

scripts/build-hooks.js

@@ -25,11 +25,6 @@ const WORKER_SERVICE = {
   source: 'src/services/worker-service.ts'
 };
 
-const WORKER_WRAPPER = {
-  name: 'worker-wrapper',
-  source: 'src/services/worker-wrapper.ts'
-};
-
 const MCP_SERVER = {
   name: 'mcp-server',
   source: 'src/servers/mcp-server.ts'
@@ -40,11 +35,6 @@ const CONTEXT_GENERATOR = {
   source: 'src/services/context-generator.ts'
 };
 
-const WORKER_CLI = {
-  name: 'worker-cli',
-  source: 'src/cli/worker-cli.ts'
-};
-
 async function buildHooks() {
   console.log('🔨 Building claude-mem hooks and worker service...\n');
 
@@ -124,31 +114,6 @@ async function buildHooks() {
     const workerStats = fs.statSync(`${hooksDir}/${WORKER_SERVICE.name}.cjs`);
     console.log(`✓ worker-service built (${(workerStats.size / 1024).toFixed(2)} KB)`);
 
-    // Build worker wrapper (Windows zombie port fix)
-    console.log(`\n🔧 Building worker wrapper...`);
-    await build({
-      entryPoints: [WORKER_WRAPPER.source],
-      bundle: true,
-      platform: 'node',
-      target: 'node18',
-      format: 'cjs',
-      outfile: `${hooksDir}/${WORKER_WRAPPER.name}.cjs`,
-      minify: true,
-      logLevel: 'error',
-      external: ['bun:sqlite'],
-      define: {
-        '__DEFAULT_PACKAGE_VERSION__': `"${version}"`
-      },
-      banner: {
-        js: '#!/usr/bin/env bun'
-      }
-    });
-
-    // Make worker wrapper executable
-    fs.chmodSync(`${hooksDir}/${WORKER_WRAPPER.name}.cjs`, 0o755);
-    const wrapperStats = fs.statSync(`${hooksDir}/${WORKER_WRAPPER.name}.cjs`);
-    console.log(`✓ worker-wrapper built (${(wrapperStats.size / 1024).toFixed(2)} KB)`);
-
     // Build MCP server
     console.log(`\n🔧 Building MCP server...`);
     await build({
@@ -194,31 +159,6 @@ async function buildHooks() {
     const contextGenStats = fs.statSync(`${hooksDir}/${CONTEXT_GENERATOR.name}.cjs`);
     console.log(`✓ context-generator built (${(contextGenStats.size / 1024).toFixed(2)} KB)`);
 
-    // Build worker CLI
-    console.log(`\n🔧 Building worker CLI...`);
-    await build({
-      entryPoints: [WORKER_CLI.source],
-      bundle: true,
-      platform: 'node',
-      target: 'node18',
-      format: 'esm',
-      outfile: `${hooksDir}/${WORKER_CLI.name}.js`,
-      minify: true,
-      logLevel: 'error',
-      external: ['bun:sqlite'],
-      define: {
-        '__DEFAULT_PACKAGE_VERSION__': `"${version}"`
-      },
-      banner: {
-        js: '#!/usr/bin/env bun'
-      }
-    });
-
-    // Make worker CLI executable
-    fs.chmodSync(`${hooksDir}/${WORKER_CLI.name}.js`, 0o755);
-    const workerCliStats = fs.statSync(`${hooksDir}/${WORKER_CLI.name}.js`);
-    console.log(`✓ worker-cli built (${(workerCliStats.size / 1024).toFixed(2)} KB)`);
-
     // Build each hook
     for (const hook of HOOKS) {
       console.log(`\n🔧 Building ${hook.name}...`);

src/cli/worker-cli.ts

@@ -1,81 +0,0 @@
-import { ProcessManager } from '../services/process/ProcessManager.js';
-import { getWorkerPort } from '../shared/worker-utils.js';
-import { stdin } from 'process';
-
-const command = process.argv[2];
-const port = getWorkerPort();
-
-const HOOK_STANDARD_RESPONSE = '{"continue": true, "suppressOutput": true}';
-const isManualRun = stdin.isTTY;
-
-async function main() {
-  switch (command) {
-    case 'start': {
-      const result = await ProcessManager.start(port);
-      if (result.success) {
-        if (isManualRun) {
-          console.log(`Worker started (PID: ${result.pid})`);
-          const date = new Date().toISOString().slice(0, 10);
-          console.log(`Logs: ~/.claude-mem/logs/worker-${date}.log`);
-        } else {
-          console.log(HOOK_STANDARD_RESPONSE);
-        }
-        process.exit(0);
-      } else {
-        console.error(`Failed to start: ${result.error}`);
-        process.exit(1);
-      }
-    }
-
-    case 'stop': {
-      await ProcessManager.stop();
-      if (isManualRun) {
-        console.log('Worker stopped');
-      } else {
-        console.log(HOOK_STANDARD_RESPONSE);
-      }
-      process.exit(0);
-    }
-
-    case 'restart': {
-      const result = await ProcessManager.restart(port);
-      if (result.success) {
-        if (isManualRun) {
-          console.log(`Worker restarted (PID: ${result.pid})`);
-        } else {
-          console.log(HOOK_STANDARD_RESPONSE);
-        }
-        process.exit(0);
-      } else {
-        console.error(`Failed to restart: ${result.error}`);
-        process.exit(1);
-      }
-    }
-
-    case 'status': {
-      const status = await ProcessManager.status();
-      if (isManualRun) {
-        if (status.running) {
-          console.log('Worker is running');
-          console.log(`  PID: ${status.pid}`);
-          console.log(`  Port: ${status.port}`);
-          console.log(`  Uptime: ${status.uptime}`);
-        } else {
-          console.log('Worker is not running');
-        }
-      } else {
-        console.log(HOOK_STANDARD_RESPONSE);
-      }
-      process.exit(0);
-    }
-
-    default:
-      console.log('Usage: worker-cli.js <start|stop|restart|status>');
-      process.exit(1);
-  }
-}
-
-main().catch(error => {
-  console.error(error);
-  process.exit(1);
-});

src/servers/mcp-server.ts

@@ -496,7 +496,7 @@ async function main() {
     if (!workerAvailable) {
       logger.warn('SYSTEM', 'Worker not available', undefined, { workerUrl: WORKER_BASE_URL });
       logger.warn('SYSTEM', 'Tools will fail until Worker is started');
-      logger.warn('SYSTEM', 'Start Worker with: claude-mem restart');
+      logger.warn('SYSTEM', 'Start Worker with: npm run worker:restart');
     } else {
       logger.info('SYSTEM', 'Worker available', undefined, { workerUrl: WORKER_BASE_URL });
     }

src/services/process/ProcessManager.ts

@@ -1,433 +0,0 @@
-import { existsSync, readFileSync, writeFileSync, unlinkSync, mkdirSync } from 'fs';
-import { createWriteStream } from 'fs';
-import { join } from 'path';
-import { spawn, spawnSync } from 'child_process';
-import { homedir } from 'os';
-import { DATA_DIR } from '../../shared/paths.js';
-import { getBunPath, isBunAvailable } from '../../utils/bun-path.js';
-import { SettingsDefaultsManager } from '../../shared/SettingsDefaultsManager.js';
-
-const PID_FILE = join(DATA_DIR, 'worker.pid');
-const LOG_DIR = join(DATA_DIR, 'logs');
-const MARKETPLACE_ROOT = join(homedir(), '.claude', 'plugins', 'marketplaces', 'thedotmack');
-
-interface PidInfo {
-  pid: number;
-  port: number;
-  startedAt: string;
-  version: string;
-}
-
-export class ProcessManager {
-  static async start(port: number): Promise<{ success: boolean; pid?: number; error?: string }> {
-    // Validate port range
-    if (isNaN(port) || port < 1024 || port > 65535) {
-      return {
-        success: false,
-        error: `Invalid port ${port}. Must be between 1024 and 65535`
-      };
-    }
-
-    // Check if already running
-    if (await this.isRunning()) {
-      const info = this.getPidInfo();
-      return { success: true, pid: info?.pid };
-    }
-
-    // Ensure log directory exists
-    mkdirSync(LOG_DIR, { recursive: true });
-
-    // On Windows, use the wrapper script to solve zombie port problem
-    // On Unix, use the worker directly
-    const scriptName = process.platform === 'win32' ? 'worker-wrapper.cjs' : 'worker-service.cjs';
-    const workerScript = join(MARKETPLACE_ROOT, 'plugin', 'scripts', scriptName);
-
-    if (!existsSync(workerScript)) {
-      return { success: false, error: `Worker script not found at ${workerScript}` };
-    }
-
-    const logFile = this.getLogFilePath();
-
-    // Use Bun on all platforms with PowerShell workaround for Windows console popups
-    return this.startWithBun(workerScript, logFile, port);
-  }
-
-  private static isBunAvailable(): boolean {
-    return isBunAvailable();
-  }
-
-  /**
-   * Escapes a string for safe use in PowerShell single-quoted strings.
-   * In PowerShell single quotes, the only special character is the single quote itself,
-   * which must be doubled to escape it.
-   */
-  private static escapePowerShellString(str: string): string {
-    return str.replace(/'/g, "''");
-  }
-
-  private static async startWithBun(script: string, logFile: string, port: number): Promise<{ success: boolean; pid?: number; error?: string }> {
-    const bunPath = getBunPath();
-    if (!bunPath) {
-      return {
-        success: false,
-        error: 'Bun is required but not found in PATH or common installation paths. Install from https://bun.sh'
-      };
-    }
-    try {
-      const isWindows = process.platform === 'win32';
-
-      if (isWindows) {
-        // Windows: Use PowerShell Start-Process with -WindowStyle Hidden
-        // This properly hides the console window (affects both Bun and Node.js)
-        // Note: windowsHide: true doesn't work with detached: true (Bun inherits Node.js process spawning semantics)
-        // See: https://github.com/nodejs/node/issues/21825 and PR #315 for detailed testing
-        //
-        // On Windows, we start worker-wrapper.cjs which manages the actual worker-service.cjs.
-        // This solves the zombie port problem: the wrapper has no sockets, so when it kills
-        // and respawns the inner worker, the socket is properly released.
-        //
-        // Security: All paths (bunPath, script, MARKETPLACE_ROOT) are application-controlled system paths,
-        // not user input. If an attacker could modify these paths, they would already have full filesystem
-        // access including direct access to ~/.claude-mem/claude-mem.db. Nevertheless, we properly escape
-        // all values for PowerShell to follow security best practices.
-        const escapedBunPath = this.escapePowerShellString(bunPath);
-        const escapedScript = this.escapePowerShellString(script);
-        const escapedWorkDir = this.escapePowerShellString(MARKETPLACE_ROOT);
-        const escapedLogFile = this.escapePowerShellString(logFile);
-        const envVars = `$env:CLAUDE_MEM_WORKER_PORT='${port}'`;
-        const psCommand = `${envVars}; Start-Process -FilePath '${escapedBunPath}' -ArgumentList '${escapedScript}' -WorkingDirectory '${escapedWorkDir}' -WindowStyle Hidden -RedirectStandardOutput '${escapedLogFile}' -RedirectStandardError '${escapedLogFile}.err' -PassThru | Select-Object -ExpandProperty Id`;
-
-        const result = spawnSync('powershell', ['-Command', psCommand], {
-          stdio: 'pipe',
-          timeout: 10000,
-          windowsHide: true
-        });
-
-        if (result.status !== 0) {
-          return {
-            success: false,
-            error: `PowerShell spawn failed: ${result.stderr?.toString() || 'unknown error'}`
-          };
-        }
-
-        const pid = parseInt(result.stdout.toString().trim(), 10);
-        if (isNaN(pid)) {
-          return { success: false, error: 'Failed to get PID from PowerShell' };
-        }
-
-        // Write PID file
-        this.writePidFile({
-          pid,
-          port,
-          startedAt: new Date().toISOString(),
-          version: process.env.npm_package_version || 'unknown'
-        });
-
-        // Wait for health
-        return this.waitForHealth(pid, port);
-      } else {
-        // Unix: Use standard spawn with detached
-        const child = spawn(bunPath, [script], {
-          detached: true,
-          stdio: ['ignore', 'pipe', 'pipe'],
-          env: { ...process.env, CLAUDE_MEM_WORKER_PORT: String(port) },
-          cwd: MARKETPLACE_ROOT
-        });
-
-        // Write logs
-        const logStream = createWriteStream(logFile, { flags: 'a' });
-        child.stdout?.pipe(logStream);
-        child.stderr?.pipe(logStream);
-
-        child.unref();
-
-        if (!child.pid) {
-          return { success: false, error: 'Failed to get PID from spawned process' };
-        }
-
-        // Write PID file
-        this.writePidFile({
-          pid: child.pid,
-          port,
-          startedAt: new Date().toISOString(),
-          version: process.env.npm_package_version || 'unknown'
-        });
-
-        // Wait for health
-        return this.waitForHealth(child.pid, port);
-      }
-    } catch (error) {
-      return {
-        success: false,
-        error: error instanceof Error ? error.message : String(error)
-      };
-    }
-  }
-
-  static async stop(timeout: number = 5000): Promise<boolean> {
-    const info = this.getPidInfo();
-
-    if (process.platform === 'win32') {
-      // Windows: Try graceful HTTP shutdown first - this works regardless of PID file state
-      // because the worker shuts itself down from the inside (via wrapper IPC)
-      const port = info?.port ?? this.getPortFromSettings();
-      const httpShutdownSucceeded = await this.tryHttpShutdown(port);
-
-      if (httpShutdownSucceeded) {
-        // HTTP shutdown succeeded - worker confirmed down, safe to remove PID file
-        this.removePidFile();
-        return true;
-      }
-
-      // HTTP shutdown failed (worker not responding), fall back to taskkill
-      if (!info) {
-        // No PID file and HTTP failed - nothing more we can do
-        return true;
-      }
-
-      const { execSync } = await import('child_process');
-      try {
-        // Use taskkill /T /F to kill entire process tree
-        // This ensures the wrapper AND all its children (inner worker, MCP, ChromaSync) are killed
-        // which is necessary to properly release the socket and avoid zombie ports
-        execSync(`taskkill /PID ${info.pid} /T /F`, { timeout: 10000, stdio: 'ignore' });
-      } catch {
-        // Process may already be dead
-      }
-
-      // Wait for process to actually exit before removing PID file
-      try {
-        await this.waitForExit(info.pid, timeout);
-      } catch {
-        // Timeout waiting - process may still be alive
-      }
-
-      // Only remove PID file if process is confirmed dead
-      if (!this.isProcessAlive(info.pid)) {
-        this.removePidFile();
-      }
-      return true;
-    } else {
-      // Unix: Use signals (unchanged behavior)
-      if (!info) return true;
-
-      try {
-        process.kill(info.pid, 'SIGTERM');
-        await this.waitForExit(info.pid, timeout);
-      } catch {
-        try {
-          process.kill(info.pid, 'SIGKILL');
-        } catch {
-          // Process already dead
-        }
-      }
-
-      this.removePidFile();
-      return true;
-    }
-  }
-
-  static async restart(port: number): Promise<{ success: boolean; pid?: number; error?: string }> {
-    await this.stop();
-    return this.start(port);
-  }
-
-  static async status(): Promise<{ running: boolean; pid?: number; port?: number; uptime?: string }> {
-    const info = this.getPidInfo();
-    if (!info) return { running: false };
-
-    const running = this.isProcessAlive(info.pid);
-    return {
-      running,
-      pid: running ? info.pid : undefined,
-      port: running ? info.port : undefined,
-      uptime: running ? this.formatUptime(info.startedAt) : undefined
-    };
-  }
-
-  static async isRunning(): Promise<boolean> {
-    const info = this.getPidInfo();
-    if (!info) return false;
-    const alive = this.isProcessAlive(info.pid);
-    if (!alive) {
-      this.removePidFile(); // Clean up stale PID file
-    }
-    return alive;
-  }
-
-  /**
-   * Get worker port from settings file
-   */
-  private static getPortFromSettings(): number {
-    try {
-      const settingsPath = join(DATA_DIR, 'settings.json');
-      const settings = SettingsDefaultsManager.loadFromFile(settingsPath);
-      return parseInt(settings.CLAUDE_MEM_WORKER_PORT, 10);
-    } catch {
-      return parseInt(SettingsDefaultsManager.get('CLAUDE_MEM_WORKER_PORT'), 10);
-    }
-  }
-
-  /**
-   * Try to shut down the worker via HTTP endpoint
-   * Returns true if shutdown succeeded, false if worker not responding
-   */
-  private static async tryHttpShutdown(port: number): Promise<boolean> {
-    try {
-      // Send shutdown request
-      const response = await fetch(`http://127.0.0.1:${port}/api/admin/shutdown`, {
-        method: 'POST',
-        signal: AbortSignal.timeout(2000)
-      });
-
-      if (!response.ok) {
-        return false;
-      }
-
-      // Wait for worker to actually stop responding
-      return await this.waitForWorkerDown(port, 5000);
-    } catch {
-      // Worker not responding to HTTP - it may be dead or hung
-      return false;
-    }
-  }
-
-  /**
-   * Wait for worker to stop responding on the given port
-   */
-  private static async waitForWorkerDown(port: number, timeout: number): Promise<boolean> {
-    const startTime = Date.now();
-
-    while (Date.now() - startTime < timeout) {
-      try {
-        await fetch(`http://127.0.0.1:${port}/api/health`, {
-          signal: AbortSignal.timeout(500)
-        });
-        // Still responding, wait and retry
-        await new Promise(resolve => setTimeout(resolve, 100));
-      } catch {
-        // Worker stopped responding - success
-        return true;
-      }
-    }
-
-    // Timeout - worker still responding
-    return false;
-  }
-
-  // Helper methods
-  private static getPidInfo(): PidInfo | null {
-    try {
-      if (!existsSync(PID_FILE)) return null;
-      const content = readFileSync(PID_FILE, 'utf-8');
-      const parsed = JSON.parse(content);
-      // Validate required fields have correct types
-      if (typeof parsed.pid !== 'number' || typeof parsed.port !== 'number') {
-        logger.warn('PROCESS', 'Malformed PID file: missing or invalid pid/port fields', {}, { parsed });
-        return null;
-      }
-      return parsed as PidInfo;
-    } catch (error) {
-      logger.warn('PROCESS', 'Failed to read PID file', {}, {
-        error: error instanceof Error ? error.message : String(error),
-        path: PID_FILE
-      });
-      return null;
-    }
-  }
-
-  private static writePidFile(info: PidInfo): void {
-    mkdirSync(DATA_DIR, { recursive: true });
-    writeFileSync(PID_FILE, JSON.stringify(info, null, 2));
-  }
-
-  private static removePidFile(): void {
-    try {
-      if (existsSync(PID_FILE)) {
-        unlinkSync(PID_FILE);
-      }
-    } catch {
-      // Ignore errors
-    }
-  }
-
-  private static isProcessAlive(pid: number): boolean {
-    try {
-      process.kill(pid, 0);
-      return true;
-    } catch {
-      return false;
-    }
-  }
-
-  private static async waitForHealth(pid: number, port: number, timeoutMs: number = 10000): Promise<{ success: boolean; pid?: number; error?: string }> {
-    const startTime = Date.now();
-    const isWindows = process.platform === 'win32';
-    // Increase timeout on Windows to account for slower process startup
-    const adjustedTimeout = isWindows ? timeoutMs * 2 : timeoutMs;
-
-    while (Date.now() - startTime < adjustedTimeout) {
-      // Check if process is still alive
-      if (!this.isProcessAlive(pid)) {
-        const errorMsg = isWindows
-          ? `Process died during startup\n\nTroubleshooting:\n1. Check Task Manager for zombie 'bun.exe' or 'node.exe' processes\n2. Verify port ${port} is not in use: netstat -ano | findstr ${port}\n3. Check worker logs in ~/.claude-mem/logs/\n4. See GitHub issues: #363, #367, #371, #373\n5. Docs: https://docs.claude-mem.ai/troubleshooting/windows-issues`
-          : 'Process died during startup';
-        return { success: false, error: errorMsg };
-      }
-
-      // Try readiness check (changed from /health to /api/readiness)
-      try {
-        const response = await fetch(`http://127.0.0.1:${port}/api/readiness`, {
-          signal: AbortSignal.timeout(1000)
-        });
-        if (response.ok) {
-          return { success: true, pid };
-        }
-      } catch {
-        // Not ready yet, continue polling
-      }
-
-      await new Promise(resolve => setTimeout(resolve, 200));
-    }
-
-    const timeoutMsg = isWindows
-      ? `Worker failed to start on Windows (readiness check timed out after ${adjustedTimeout}ms)\n\nTroubleshooting:\n1. Check Task Manager for zombie 'bun.exe' or 'node.exe' processes\n2. Verify port ${port} is not in use: netstat -ano | findstr ${port}\n3. Check worker logs in ~/.claude-mem/logs/\n4. See GitHub issues: #363, #367, #371, #373\n5. Docs: https://docs.claude-mem.ai/troubleshooting/windows-issues`
-      : `Readiness check timed out after ${adjustedTimeout}ms`;
-
-    return { success: false, error: timeoutMsg };
-  }
-
-  private static async waitForExit(pid: number, timeout: number): Promise<void> {
-    const startTime = Date.now();
-
-    while (Date.now() - startTime < timeout) {
-      if (!this.isProcessAlive(pid)) {
-        return;
-      }
-      await new Promise(resolve => setTimeout(resolve, 100));
-    }
-
-    throw new Error('Process did not exit within timeout');
-  }
-
-  private static getLogFilePath(): string {
-    const date = new Date().toISOString().slice(0, 10);
-    return join(LOG_DIR, `worker-${date}.log`);
-  }
-
-  private static formatUptime(startedAt: string): string {
-    const startTime = new Date(startedAt).getTime();
-    const now = Date.now();
-    const diffMs = now - startTime;
-
-    const seconds = Math.floor(diffMs / 1000);
-    const minutes = Math.floor(seconds / 60);
-    const hours = Math.floor(minutes / 60);
-    const days = Math.floor(hours / 24);
-
-    if (days > 0) return `${days}d ${hours % 24}h`;
-    if (hours > 0) return `${hours}h ${minutes % 60}m`;
-    if (minutes > 0) return `${minutes}m ${seconds % 60}s`;
-    return `${seconds}s`;
-  }
-}

src/services/worker-service.ts

@@ -14,16 +14,203 @@ import { Client } from '@modelcontextprotocol/sdk/client/index.js';
 import { StdioClientTransport } from '@modelcontextprotocol/sdk/client/stdio.js';
 import { getWorkerPort, getWorkerHost } from '../shared/worker-utils.js';
 import { logger } from '../utils/logger.js';
-import { exec, execSync } from 'child_process';
+import { exec, execSync, spawn } from 'child_process';
+import { homedir } from 'os';
+import { existsSync, writeFileSync, readFileSync, unlinkSync, mkdirSync } from 'fs';
 import { promisify } from 'util';
 
 const execAsync = promisify(exec);
 
+// PID file management for self-spawn pattern
+const DATA_DIR = path.join(homedir(), '.claude-mem');
+const PID_FILE = path.join(DATA_DIR, 'worker.pid');
+const HOOK_RESPONSE = '{"continue": true, "suppressOutput": true}';
+
+interface PidInfo {
+  pid: number;
+  port: number;
+  startedAt: string;
+}
+
+// PID file utility functions
+function writePidFile(info: PidInfo): void {
+  mkdirSync(DATA_DIR, { recursive: true });
+  writeFileSync(PID_FILE, JSON.stringify(info, null, 2));
+}
+
+function readPidFile(): PidInfo | null {
+  try {
+    if (!existsSync(PID_FILE)) return null;
+    return JSON.parse(readFileSync(PID_FILE, 'utf-8'));
+  } catch (error) {
+    logger.warn('SYSTEM', 'Failed to read PID file', { path: PID_FILE, error: (error as Error).message });
+    return null;
+  }
+}
+
+function removePidFile(): void {
+  try {
+    if (existsSync(PID_FILE)) unlinkSync(PID_FILE);
+  } catch (error) {
+    logger.warn('SYSTEM', 'Failed to remove PID file', { path: PID_FILE, error: (error as Error).message });
+  }
+}
+
+// Lockfile for CLI command mutual exclusion (prevents race conditions on Windows)
+const LOCK_FILE = path.join(DATA_DIR, 'worker.lock');
+const LOCK_STALE_MS = 120000; // Lock considered stale after 2 minutes
+
+interface LockInfo {
+  pid: number;
+  command: string;
+  startedAt: string;
+}
+
+/**
+ * Clean up stale lock from crashed processes
+ */
+function cleanupStaleLock(): void {
+  try {
+    if (!existsSync(LOCK_FILE)) return;
+    const lockData = readFileSync(LOCK_FILE, 'utf-8');
+    const lockInfo: LockInfo = JSON.parse(lockData);
+    const lockAge = Date.now() - new Date(lockInfo.startedAt).getTime();
+    if (lockAge > LOCK_STALE_MS) {
+      logger.warn('SYSTEM', 'Removing stale lock', {
+        lockAge: Math.round(lockAge / 1000) + 's',
+        originalPid: lockInfo.pid,
+        originalCommand: lockInfo.command
+      });
+      unlinkSync(LOCK_FILE);
+    }
+  } catch {
+    // If we can't read the lock, it's likely corrupted - remove it
+    try { unlinkSync(LOCK_FILE); } catch {}
+  }
+}
+
+/**
+ * Acquire exclusive lock for worker operations
+ * Uses atomic file creation (O_EXCL) for cross-process safety
+ */
+function acquireLock(command: string): boolean {
+  mkdirSync(DATA_DIR, { recursive: true });
+  cleanupStaleLock();
+
+  const lockInfo: LockInfo = {
+    pid: process.pid,
+    command,
+    startedAt: new Date().toISOString()
+  };
+
+  try {
+    // O_EXCL ensures atomic creation - fails if file exists
+    const fd = fs.openSync(LOCK_FILE, fs.constants.O_CREAT | fs.constants.O_EXCL | fs.constants.O_WRONLY);
+    fs.writeSync(fd, JSON.stringify(lockInfo, null, 2));
+    fs.closeSync(fd);
+    return true;
+  } catch (error: unknown) {
+    if ((error as NodeJS.ErrnoException).code === 'EEXIST') {
+      return false;
+    }
+    logger.warn('SYSTEM', 'Lock acquisition error', { error: (error as Error).message });
+    return false;
+  }
+}
+
+/**
+ * Release lock file
+ */
+function releaseLock(): void {
+  try {
+    if (existsSync(LOCK_FILE)) unlinkSync(LOCK_FILE);
+  } catch (error) {
+    logger.warn('SYSTEM', 'Lock release error', { error: (error as Error).message });
+  }
+}
+
+/**
+ * Wait for lock with timeout
+ */
+async function waitForLock(command: string, timeoutMs: number): Promise<boolean> {
+  const start = Date.now();
+  while (Date.now() - start < timeoutMs) {
+    if (acquireLock(command)) return true;
+    await new Promise(r => setTimeout(r, 200));
+  }
+  return false;
+}
+
+/**
+ * Get platform-adjusted timeout (Windows socket cleanup is slower)
+ */
+function getPlatformTimeout(baseMs: number): number {
+  const WINDOWS_MULTIPLIER = 2.0;
+  return process.platform === 'win32' ? Math.round(baseMs * WINDOWS_MULTIPLIER) : baseMs;
+}
+
+async function isPortInUse(port: number): Promise<boolean> {
+  try {
+    const response = await fetch(`http://127.0.0.1:${port}/api/health`, {
+      signal: AbortSignal.timeout(2000)
+    });
+    return response.ok;
+  } catch { return false; }
+}
+
+async function waitForHealth(port: number, timeoutMs: number = 30000): Promise<boolean> {
+  const start = Date.now();
+  while (Date.now() - start < timeoutMs) {
+    try {
+      const response = await fetch(`http://127.0.0.1:${port}/api/readiness`, {
+        signal: AbortSignal.timeout(2000)
+      });
+      if (response.ok) return true;
+    } catch {
+      // Not ready yet
+    }
+    await new Promise(r => setTimeout(r, 500));
+  }
+  return false;
+}
+
+async function httpShutdown(port: number): Promise<boolean> {
+  try {
+    const response = await fetch(`http://127.0.0.1:${port}/api/admin/shutdown`, {
+      method: 'POST',
+      signal: AbortSignal.timeout(5000)
+    });
+    if (!response.ok) {
+      logger.warn('SYSTEM', 'Shutdown request returned error', { port, status: response.status });
+      return false;
+    }
+    return true;
+  } catch (error) {
+    // Connection refused is expected if worker already stopped
+    const isConnectionRefused = (error as Error).message?.includes('ECONNREFUSED');
+    if (!isConnectionRefused) {
+      logger.warn('SYSTEM', 'Shutdown request failed', { port, error: (error as Error).message });
+    }
+    return false;
+  }
+}
+
+async function waitForPortFree(port: number, timeoutMs: number = 10000): Promise<boolean> {
+  const start = Date.now();
+  while (Date.now() - start < timeoutMs) {
+    if (!(await isPortInUse(port))) return true;
+    await new Promise(r => setTimeout(r, 500));
+  }
+  return false;
+}
+
 // Import composed service layer
 import { DatabaseManager } from './worker/DatabaseManager.js';
 import { SessionManager } from './worker/SessionManager.js';
 import { SSEBroadcaster } from './worker/SSEBroadcaster.js';
 import { SDKAgent } from './worker/SDKAgent.js';
+import { GeminiAgent } from './worker/GeminiAgent.js';
+import { OpenRouterAgent } from './worker/OpenRouterAgent.js';
 import { PaginationHelper } from './worker/PaginationHelper.js';
 import { SettingsManager } from './worker/SettingsManager.js';
 import { SearchManager } from './worker/SearchManager.js';
@@ -54,6 +241,8 @@ export class WorkerService {
   private sessionManager: SessionManager;
   private sseBroadcaster: SSEBroadcaster;
   private sdkAgent: SDKAgent;
+  private geminiAgent: GeminiAgent;
+  private openRouterAgent: OpenRouterAgent;
   private paginationHelper: PaginationHelper;
   private settingsManager: SettingsManager;
   private sessionEventBroadcaster: SessionEventBroadcaster;
@@ -82,6 +271,10 @@ export class WorkerService {
     this.sessionManager = new SessionManager(this.dbManager);
     this.sseBroadcaster = new SSEBroadcaster();
     this.sdkAgent = new SDKAgent(this.dbManager, this.sessionManager);
+    this.geminiAgent = new GeminiAgent(this.dbManager, this.sessionManager);
+    this.geminiAgent.setFallbackAgent(this.sdkAgent);  // Enable fallback to Claude on Gemini API failure
+    this.openRouterAgent = new OpenRouterAgent(this.dbManager, this.sessionManager);
+    this.openRouterAgent.setFallbackAgent(this.sdkAgent);  // Enable fallback to Claude on OpenRouter API failure
     this.paginationHelper = new PaginationHelper(this.dbManager);
     this.settingsManager = new SettingsManager(this.dbManager);
     this.sessionEventBroadcaster = new SessionEventBroadcaster(this.sseBroadcaster, this);
@@ -99,7 +292,7 @@ export class WorkerService {
 
     // Initialize route handlers (SearchRoutes will use MCP client initially, then switch to SearchManager after DB init)
     this.viewerRoutes = new ViewerRoutes(this.sseBroadcaster, this.dbManager, this.sessionManager);
-    this.sessionRoutes = new SessionRoutes(this.sessionManager, this.dbManager, this.sdkAgent, this.sessionEventBroadcaster, this);
+    this.sessionRoutes = new SessionRoutes(this.sessionManager, this.dbManager, this.sdkAgent, this.geminiAgent, this.openRouterAgent, this.sessionEventBroadcaster, this);
     this.dataRoutes = new DataRoutes(this.paginationHelper, this.dbManager, this.sessionManager, this.sseBroadcaster, this, this.startTime);
     // SearchRoutes needs SearchManager which requires initialized DB - will be created in initializeBackground()
     this.searchRoutes = null;
@@ -262,7 +455,7 @@ export class WorkerService {
     this.app.get('/api/context/inject', async (req, res, next) => {
       try {
         // Wait for initialization to complete (with timeout)
-        const timeoutMs = 30000; // 30 second timeout
+        const timeoutMs = 300000; // 5 minute timeout for slow systems
         const timeoutPromise = new Promise((_, reject) => 
           setTimeout(() => reject(new Error('Initialization timeout')), timeoutMs)
         );
@@ -322,7 +515,7 @@ export class WorkerService {
     if (isWindows) {
       // Windows: Use PowerShell Get-CimInstance to find chroma-mcp processes
       const cmd = `powershell -Command "Get-CimInstance Win32_Process | Where-Object { $_.Name -like '*python*' -and $_.CommandLine -like '*chroma-mcp*' } | Select-Object -ExpandProperty ProcessId"`;
-      const { stdout } = await execAsync(cmd, { timeout: 5000 });
+      const { stdout } = await execAsync(cmd, { timeout: 60000 });
 
       if (!stdout.trim()) {
         logger.debug('SYSTEM', 'No orphaned chroma-mcp processes found (Windows)');
@@ -377,10 +570,20 @@ export class WorkerService {
           logger.warn('SYSTEM', 'Skipping invalid PID', { pid });
           continue;
         }
-        execSync(`taskkill /PID ${pid} /T /F`, { timeout: 5000, stdio: 'ignore' });
+        try {
+          execSync(`taskkill /PID ${pid} /T /F`, { timeout: 60000, stdio: 'ignore' });
+        } catch {
+          // Process may have already exited - continue cleanup
+        }
       }
     } else {
-      await execAsync(`kill ${pids.join(' ')}`);
+      for (const pid of pids) {
+        try {
+          process.kill(pid, 'SIGKILL');
+        } catch {
+          // Process already exited - that's fine
+        }
+      }
     }
 
     logger.info('SYSTEM', 'Orphaned processes cleaned up', { count: pids.length });
@@ -459,11 +662,11 @@ export class WorkerService {
         env: process.env
       });
 
-      // Add timeout guard to prevent hanging on MCP connection (15 seconds)
-      const MCP_INIT_TIMEOUT_MS = 15000;
+      // Add timeout guard to prevent hanging on MCP connection (5 minutes for slow systems)
+      const MCP_INIT_TIMEOUT_MS = 300000;
       const mcpConnectionPromise = this.mcpClient.connect(transport);
       const timeoutPromise = new Promise<never>((_, reject) =>
-        setTimeout(() => reject(new Error('MCP connection timeout after 15s')), MCP_INIT_TIMEOUT_MS)
+        setTimeout(() => reject(new Error('MCP connection timeout after 5 minutes')), MCP_INIT_TIMEOUT_MS)
       );
 
       await Promise.race([mcpConnectionPromise, timeoutPromise]);
@@ -647,13 +850,18 @@ export class WorkerService {
       return [];
     }
 
-    const cmd = `powershell -Command "Get-CimInstance Win32_Process | Where-Object { $_.ParentProcessId -eq ${parentPid} } | Select-Object -ExpandProperty ProcessId"`;
-    const { stdout } = await execAsync(cmd, { timeout: 5000 });
-    return stdout
-      .trim()
-      .split('\n')
-      .map(s => parseInt(s.trim(), 10))
-      .filter(n => !isNaN(n) && Number.isInteger(n) && n > 0); // SECURITY: Validate each PID
+    try {
+      const cmd = `powershell -Command "Get-CimInstance Win32_Process | Where-Object { $_.ParentProcessId -eq ${parentPid} } | Select-Object -ExpandProperty ProcessId"`;
+      const { stdout } = await execAsync(cmd, { timeout: 60000 });
+      return stdout
+        .trim()
+        .split('\n')
+        .map(s => parseInt(s.trim(), 10))
+        .filter(n => !isNaN(n) && Number.isInteger(n) && n > 0); // SECURITY: Validate each PID
+    } catch (error) {
+      logger.warn('SYSTEM', 'Failed to enumerate child processes', { parentPid, error: (error as Error).message });
+      return []; // Fail safely - continue shutdown without child process cleanup
+    }
   }
 
   /**
@@ -666,12 +874,17 @@ export class WorkerService {
       return;
     }
 
-    if (process.platform === 'win32') {
-      // /T kills entire process tree, /F forces termination
-      await execAsync(`taskkill /PID ${pid} /T /F`, { timeout: 5000 });
+    try {
+      if (process.platform === 'win32') {
+        // /T kills entire process tree, /F forces termination
+        await execAsync(`taskkill /PID ${pid} /T /F`, { timeout: 60000 });
+      } else {
+        process.kill(pid, 'SIGKILL');
+      }
       logger.info('SYSTEM', 'Killed process', { pid });
-    } else {
-      process.kill(pid, 'SIGKILL');
+    } catch {
+      // Process may have already exited - continue shutdown
+      logger.debug('SYSTEM', 'Process already exited during force kill', { pid });
     }
   }
 
@@ -683,8 +896,12 @@ export class WorkerService {
 
     while (Date.now() - start < timeoutMs) {
       const stillAlive = pids.filter(pid => {
-        process.kill(pid, 0); // Signal 0 checks if process exists - throws if dead
-        return true;
+        try {
+          process.kill(pid, 0);
+          return true;
+        } catch {
+          return false;
+        }
       });
 
       if (stillAlive.length === 0) {
@@ -733,31 +950,187 @@ export class WorkerService {
 }
 
 // ============================================================================
-// Main Entry Point
+// CLI Entry Point
 // ============================================================================
 
-/**
- * Start the worker service (if running as main module)
- * Note: Using require.main check for CJS compatibility (build outputs CJS)
- */
-if (require.main === module || !module.parent) {
-  const worker = new WorkerService();
+async function main() {
+  const command = process.argv[2];
+  const port = getWorkerPort();
 
-  // Graceful shutdown
-  process.on('SIGTERM', async () => {
-    logger.info('SYSTEM', 'Received SIGTERM, shutting down gracefully');
-    await worker.shutdown();
-    process.exit(0);
-  });
+  switch (command) {
+    case 'start': {
+      // Acquire lock BEFORE checking port to prevent race condition
+      // If we can't get lock, another session is spawning - wait for health instead
+      if (!acquireLock('start')) {
+        logger.info('SYSTEM', 'Another session is spawning worker, waiting for health');
+        const healthy = await waitForHealth(port, getPlatformTimeout(30000));
+        if (healthy) {
+          console.log(HOOK_RESPONSE);
+          process.exit(0);
+        }
+        // Still not healthy after wait - try to acquire lock and spawn
+        const gotLock = await waitForLock('start', 5000);
+        if (!gotLock) {
+          console.error('Failed to acquire lock after timeout');
+          process.exit(1);
+        }
+      }
 
-  process.on('SIGINT', async () => {
-    logger.info('SYSTEM', 'Received SIGINT, shutting down gracefully');
-    await worker.shutdown();
-    process.exit(0);
-  });
+      try {
+        // Re-check port AFTER acquiring lock
+        if (await isPortInUse(port)) {
+          releaseLock();
+          console.log(HOOK_RESPONSE);
+          process.exit(0);
+        }
 
-  worker.start().catch((error) => {
-    logger.failure('SYSTEM', 'Worker failed to start', {}, error as Error);
-    process.exit(1);
-  });
+        // Spawn self as daemon
+        const child = spawn(process.execPath, [__filename, '--daemon'], {
+          detached: true,
+          stdio: 'ignore',
+          windowsHide: true,
+          env: { ...process.env, CLAUDE_MEM_WORKER_PORT: String(port) }
+        });
+
+        if (child.pid === undefined) {
+          releaseLock();
+          console.error('Failed to spawn worker daemon');
+          process.exit(1);
+        }
+
+        child.unref();
+
+        // Write PID file
+        writePidFile({ pid: child.pid, port, startedAt: new Date().toISOString() });
+
+        // Wait for health with platform-adjusted timeout
+        const healthy = await waitForHealth(port, getPlatformTimeout(30000));
+        releaseLock();
+
+        if (!healthy) {
+          removePidFile();
+          console.error('Worker failed to start');
+          process.exit(1);
+        }
+
+        console.log(HOOK_RESPONSE);
+        process.exit(0);
+      } catch (error) {
+        releaseLock();
+        throw error;
+      }
+    }
+
+    case 'stop': {
+      // Acquire lock for stop operation
+      if (!acquireLock('stop')) {
+        // Wait briefly for concurrent operation to complete
+        await new Promise(r => setTimeout(r, 2000));
+      }
+
+      try {
+        await httpShutdown(port);
+        await waitForPortFree(port, getPlatformTimeout(15000));
+        removePidFile();
+        releaseLock();
+        console.log(HOOK_RESPONSE);
+        process.exit(0);
+      } catch (error) {
+        releaseLock();
+        throw error;
+      }
+    }
+
+    case 'restart': {
+      // Acquire lock for restart operation
+      if (!acquireLock('restart')) {
+        // Another session is already restarting - wait for health
+        logger.info('SYSTEM', 'Another session is restarting worker, waiting');
+        const healthy = await waitForHealth(port, getPlatformTimeout(45000));
+        if (healthy) {
+          console.log(HOOK_RESPONSE);
+          process.exit(0);
+        }
+        console.error('Worker failed to restart (concurrent operation)');
+        process.exit(1);
+      }
+
+      try {
+        await httpShutdown(port);
+        await waitForPortFree(port, getPlatformTimeout(15000));
+        removePidFile();
+
+        const child = spawn(process.execPath, [__filename, '--daemon'], {
+          detached: true,
+          stdio: 'ignore',
+          windowsHide: true,
+          env: { ...process.env, CLAUDE_MEM_WORKER_PORT: String(port) }
+        });
+
+        if (child.pid === undefined) {
+          releaseLock();
+          console.error('Failed to spawn worker daemon during restart');
+          process.exit(1);
+        }
+
+        child.unref();
+        writePidFile({ pid: child.pid, port, startedAt: new Date().toISOString() });
+
+        const healthy = await waitForHealth(port, getPlatformTimeout(30000));
+        releaseLock();
+
+        if (!healthy) {
+          removePidFile();
+          console.error('Worker failed to restart');
+          process.exit(1);
+        }
+        console.log(HOOK_RESPONSE);
+        process.exit(0);
+      } catch (error) {
+        releaseLock();
+        throw error;
+      }
+    }
+
+    case 'status': {
+      const running = await isPortInUse(port);
+      const pidInfo = readPidFile();
+      if (running && pidInfo) {
+        console.log(`Worker running (PID: ${pidInfo.pid}, Port: ${pidInfo.port})`);
+      } else {
+        console.log('Worker not running');
+      }
+      process.exit(0);
+    }
+
+    case '--daemon':
+    default: {
+      // Run server directly
+      const worker = new WorkerService();
+
+      process.on('SIGTERM', async () => {
+        logger.info('SYSTEM', 'Received SIGTERM');
+        await worker.shutdown();
+        removePidFile();
+        process.exit(0);
+      });
+
+      process.on('SIGINT', async () => {
+        logger.info('SYSTEM', 'Received SIGINT');
+        await worker.shutdown();
+        removePidFile();
+        process.exit(0);
+      });
+
+      worker.start().catch((error) => {
+        logger.failure('SYSTEM', 'Worker failed to start', {}, error as Error);
+        removePidFile();
+        process.exit(1);
+      });
+    }
+  }
+}
+
+if (require.main === module || !module.parent) {
+  main();
 }

src/services/worker-types.ts

@@ -8,6 +8,15 @@ import type { Response } from 'express';
 // Active Session Types
 // ============================================================================
 
+/**
+ * Provider-agnostic conversation message for shared history
+ * Used to maintain context across Claude↔Gemini provider switches
+ */
+export interface ConversationMessage {
+  role: 'user' | 'assistant';
+  content: string;
+}
+
 export interface ActiveSession {
   sessionDbId: number;
   claudeSessionId: string;
@@ -23,6 +32,8 @@ export interface ActiveSession {
   cumulativeOutputTokens: number;  // Track output tokens for discovery cost
   pendingProcessingIds: Set<number>;  // Track ALL message IDs yielded but not yet processed
   earliestPendingTimestamp: number | null;  // Original timestamp of earliest pending message (for accurate observation timestamps)
+  conversationHistory: ConversationMessage[];  // Shared conversation history for provider switching
+  currentProvider: 'claude' | 'gemini' | 'openrouter' | null;  // Track which provider is currently running
 }
 
 export interface PendingMessage {

src/services/worker-wrapper.ts

@@ -1,157 +0,0 @@
-/**
- * Worker Wrapper - Manages worker process lifecycle
- *
- * This wrapper exists to solve the Windows zombie port problem.
- * The wrapper spawns the actual worker as a child process.
- * When shutdown is requested, the wrapper kills the child and exits.
- * The hooks will start a fresh wrapper+worker if needed.
- *
- * The wrapper itself has no sockets, so Bun's socket cleanup bug
- * doesn't affect it.
- *
- * NOTE: The wrapper does NOT auto-restart the worker on crash.
- * This is intentional - the hooks handle startup via ensureWorkerRunning().
- * Auto-restart would cause PID file mismatches and potential infinite loops.
- */
-
-import { spawn, ChildProcess, execSync } from 'child_process';
-import path from 'path';
-
-const isWindows = process.platform === 'win32';
-
-const SCRIPT_DIR = __dirname;
-const INNER_SCRIPT = path.join(SCRIPT_DIR, 'worker-service.cjs');
-
-let inner: ChildProcess | null = null;
-let isShuttingDown = false;
-
-function log(msg: string) {
-  const timestamp = new Date().toISOString();
-  console.log(`[${timestamp}] [wrapper] ${msg}`);
-}
-
-function spawnInner() {
-  log(`Spawning inner worker: ${INNER_SCRIPT}`);
-
-  inner = spawn(process.execPath, [INNER_SCRIPT], {
-    stdio: ['inherit', 'inherit', 'inherit', 'ipc'],
-    env: { ...process.env, CLAUDE_MEM_MANAGED: 'true' },
-    cwd: path.dirname(INNER_SCRIPT),
-  });
-
-  inner.on('message', async (msg: { type: string }) => {
-    if (msg.type === 'restart' || msg.type === 'shutdown') {
-      // Both restart and shutdown: kill inner and exit wrapper
-      // The hooks will start a fresh wrapper+inner if needed
-      log(`${msg.type} requested by inner`);
-      isShuttingDown = true;
-      await killInner();
-      log('Exiting wrapper');
-      process.exit(0);
-    }
-  });
-
-  inner.on('exit', (code, signal) => {
-    log(`Inner exited with code=${code}, signal=${signal}`);
-    inner = null;
-
-    // Don't auto-restart - let hooks handle it via ensureWorkerRunning()
-    // Auto-restart causes PID file mismatches and potential infinite loops
-    if (!isShuttingDown) {
-      log('Inner exited unexpectedly, wrapper exiting (hooks will restart if needed)');
-      process.exit(code ?? 1);
-    }
-  });
-
-  inner.on('error', (err) => {
-    log(`Inner error: ${err.message}`);
-  });
-}
-
-async function killInner(): Promise<void> {
-  if (!inner || !inner.pid) {
-    log('No inner process to kill');
-    return;
-  }
-
-  const pid = inner.pid;
-  log(`Killing inner process tree (pid=${pid})`);
-
-  if (isWindows) {
-    // On Windows, use taskkill /T /F to kill entire process tree
-    // This ensures all children (MCP server, ChromaSync, etc.) are killed
-    // which is necessary to properly release the socket
-    try {
-      execSync(`taskkill /PID ${pid} /T /F`, { timeout: 10000, stdio: 'ignore' });
-      log(`taskkill completed for pid=${pid}`);
-    } catch (error) {
-      // Process may already be dead
-      log(`taskkill failed (process may be dead): ${error}`);
-    }
-  } else {
-    // On Unix, SIGTERM then SIGKILL
-    inner.kill('SIGTERM');
-
-    // Wait for exit with timeout
-    const exitPromise = new Promise<void>(resolve => {
-      if (!inner) {
-        resolve();
-        return;
-      }
-      inner.on('exit', () => resolve());
-    });
-
-    const timeoutPromise = new Promise<void>(resolve =>
-      setTimeout(() => resolve(), 5000)
-    );
-
-    await Promise.race([exitPromise, timeoutPromise]);
-
-    // Force kill if still alive
-    if (inner && !inner.killed) {
-      log('Inner did not exit gracefully, force killing');
-      inner.kill('SIGKILL');
-    }
-  }
-
-  // Wait for the process to fully exit
-  await waitForProcessExit(pid, 5000);
-
-  inner = null;
-  log('Inner process terminated');
-}
-
-async function waitForProcessExit(pid: number, timeoutMs: number): Promise<void> {
-  const start = Date.now();
-
-  while (Date.now() - start < timeoutMs) {
-    try {
-      process.kill(pid, 0); // Check if process exists
-      await new Promise(r => setTimeout(r, 100));
-    } catch {
-      // Process is dead
-      return;
-    }
-  }
-
-  log(`Timeout waiting for process ${pid} to exit`);
-}
-
-// Handle wrapper signals
-process.on('SIGTERM', async () => {
-  log('Wrapper received SIGTERM');
-  isShuttingDown = true;
-  await killInner();
-  process.exit(0);
-});
-
-process.on('SIGINT', async () => {
-  log('Wrapper received SIGINT');
-  isShuttingDown = true;
-  await killInner();
-  process.exit(0);
-});
-
-// Start the inner worker
-log('Wrapper starting');
-spawnInner();

src/services/worker/BranchManager.ts

@@ -28,9 +28,9 @@ function isValidBranchName(branchName: string): boolean {
   return validBranchRegex.test(branchName) && !branchName.includes('..');
 }
 
-// Timeout constants
-const GIT_COMMAND_TIMEOUT_MS = 30_000;
-const NPM_INSTALL_TIMEOUT_MS = 120_000;
+// Timeout constants (increased for slow systems)
+const GIT_COMMAND_TIMEOUT_MS = 300_000;
+const NPM_INSTALL_TIMEOUT_MS = 600_000;
 const DEFAULT_SHELL_TIMEOUT_MS = 60_000;
 
 export interface BranchInfo {

src/services/worker/GeminiAgent.ts

@@ -0,0 +1,583 @@
+/**
+ * GeminiAgent: Gemini-based observation extraction
+ *
+ * Alternative to SDKAgent that uses Google's Gemini API directly
+ * for extracting observations from tool usage.
+ *
+ * Responsibility:
+ * - Call Gemini REST API for observation extraction
+ * - Parse XML responses (same format as Claude)
+ * - Sync to database and Chroma
+ */
+
+import path from 'path';
+import { homedir } from 'os';
+import { DatabaseManager } from './DatabaseManager.js';
+import { SessionManager } from './SessionManager.js';
+import { logger } from '../../utils/logger.js';
+import { parseObservations, parseSummary } from '../../sdk/parser.js';
+import { buildInitPrompt, buildObservationPrompt, buildSummaryPrompt, buildContinuationPrompt } from '../../sdk/prompts.js';
+import { SettingsDefaultsManager } from '../../shared/SettingsDefaultsManager.js';
+import type { ActiveSession, ConversationMessage } from '../worker-types.js';
+import { ModeManager } from '../domain/ModeManager.js';
+
+// Gemini API endpoint
+const GEMINI_API_URL = 'https://generativelanguage.googleapis.com/v1beta/models';
+
+// Gemini model types (available via API)
+export type GeminiModel =
+  | 'gemini-2.5-flash-lite'
+  | 'gemini-2.5-flash'
+  | 'gemini-2.5-pro'
+  | 'gemini-2.0-flash'
+  | 'gemini-2.0-flash-lite';
+
+// Free tier RPM limits by model (requests per minute)
+const GEMINI_RPM_LIMITS: Record<GeminiModel, number> = {
+  'gemini-2.5-flash-lite': 10,
+  'gemini-2.5-flash': 10,
+  'gemini-2.5-pro': 5,
+  'gemini-2.0-flash': 15,
+  'gemini-2.0-flash-lite': 30,
+};
+
+// Track last request time for rate limiting
+let lastRequestTime = 0;
+
+/**
+ * Enforce RPM rate limit for Gemini free tier.
+ * Waits the required time between requests based on model's RPM limit + 100ms safety buffer.
+ * Skipped entirely if rate limiting is disabled (billing users with 1000+ RPM available).
+ */
+async function enforceRateLimitForModel(model: GeminiModel, rateLimitingEnabled: boolean): Promise<void> {
+  // Skip rate limiting if disabled (billing users with 1000+ RPM)
+  if (!rateLimitingEnabled) {
+    return;
+  }
+
+  const rpm = GEMINI_RPM_LIMITS[model] || 5;
+  const minimumDelayMs = Math.ceil(60000 / rpm) + 100; // (60s / RPM) + 100ms safety buffer
+
+  const now = Date.now();
+  const timeSinceLastRequest = now - lastRequestTime;
+
+  if (timeSinceLastRequest < minimumDelayMs) {
+    const waitTime = minimumDelayMs - timeSinceLastRequest;
+    logger.debug('SDK', `Rate limiting: waiting ${waitTime}ms before Gemini request`, { model, rpm });
+    await new Promise(resolve => setTimeout(resolve, waitTime));
+  }
+
+  lastRequestTime = Date.now();
+}
+
+interface GeminiResponse {
+  candidates?: Array<{
+    content?: {
+      parts?: Array<{
+        text?: string;
+      }>;
+    };
+  }>;
+  usageMetadata?: {
+    promptTokenCount?: number;
+    candidatesTokenCount?: number;
+    totalTokenCount?: number;
+  };
+}
+
+/**
+ * Gemini content message format
+ * role: "user" or "model" (Gemini uses "model" not "assistant")
+ */
+interface GeminiContent {
+  role: 'user' | 'model';
+  parts: Array<{ text: string }>;
+}
+
+// Forward declaration for fallback agent type
+type FallbackAgent = {
+  startSession(session: ActiveSession, worker?: any): Promise<void>;
+};
+
+export class GeminiAgent {
+  private dbManager: DatabaseManager;
+  private sessionManager: SessionManager;
+  private fallbackAgent: FallbackAgent | null = null;
+
+  constructor(dbManager: DatabaseManager, sessionManager: SessionManager) {
+    this.dbManager = dbManager;
+    this.sessionManager = sessionManager;
+  }
+
+  /**
+   * Set the fallback agent (Claude SDK) for when Gemini API fails
+   * Must be set after construction to avoid circular dependency
+   */
+  setFallbackAgent(agent: FallbackAgent): void {
+    this.fallbackAgent = agent;
+  }
+
+  /**
+   * Check if an error should trigger fallback to Claude
+   */
+  private shouldFallbackToClaude(error: any): boolean {
+    const message = error?.message || '';
+    // Fall back on rate limit (429), server errors (5xx), or network issues
+    return (
+      message.includes('429') ||
+      message.includes('500') ||
+      message.includes('502') ||
+      message.includes('503') ||
+      message.includes('ECONNREFUSED') ||
+      message.includes('ETIMEDOUT') ||
+      message.includes('fetch failed')
+    );
+  }
+
+  /**
+   * Start Gemini agent for a session
+   * Uses multi-turn conversation to maintain context across messages
+   */
+  async startSession(session: ActiveSession, worker?: any): Promise<void> {
+    try {
+      // Get Gemini configuration
+      const { apiKey, model, rateLimitingEnabled } = this.getGeminiConfig();
+
+      if (!apiKey) {
+        throw new Error('Gemini API key not configured. Set CLAUDE_MEM_GEMINI_API_KEY in settings or GEMINI_API_KEY environment variable.');
+      }
+
+      // Load active mode
+      const mode = ModeManager.getInstance().getActiveMode();
+
+      // Build initial prompt
+      const initPrompt = session.lastPromptNumber === 1
+        ? buildInitPrompt(session.project, session.claudeSessionId, session.userPrompt, mode)
+        : buildContinuationPrompt(session.userPrompt, session.lastPromptNumber, session.claudeSessionId, mode);
+
+      // Add to conversation history and query Gemini with full context
+      session.conversationHistory.push({ role: 'user', content: initPrompt });
+      const initResponse = await this.queryGeminiMultiTurn(session.conversationHistory, apiKey, model, rateLimitingEnabled);
+
+      if (initResponse.content) {
+        // Add response to conversation history
+        session.conversationHistory.push({ role: 'assistant', content: initResponse.content });
+
+        // Track token usage
+        const tokensUsed = initResponse.tokensUsed || 0;
+        session.cumulativeInputTokens += Math.floor(tokensUsed * 0.7);  // Rough estimate
+        session.cumulativeOutputTokens += Math.floor(tokensUsed * 0.3);
+
+        // Process response (no original timestamp for init - not from queue)
+        await this.processGeminiResponse(session, initResponse.content, worker, tokensUsed, null);
+      } else {
+        logger.warn('SDK', 'Empty Gemini init response - session may lack context', {
+          sessionId: session.sessionDbId,
+          model
+        });
+      }
+
+      // Process pending messages
+      for await (const message of this.sessionManager.getMessageIterator(session.sessionDbId)) {
+        // Capture earliest timestamp BEFORE processing (will be cleared after)
+        // This ensures backlog messages get their original timestamps, not current time
+        const originalTimestamp = session.earliestPendingTimestamp;
+
+        if (message.type === 'observation') {
+          // Update last prompt number
+          if (message.prompt_number !== undefined) {
+            session.lastPromptNumber = message.prompt_number;
+          }
+
+          // Build observation prompt
+          const obsPrompt = buildObservationPrompt({
+            id: 0,
+            tool_name: message.tool_name!,
+            tool_input: JSON.stringify(message.tool_input),
+            tool_output: JSON.stringify(message.tool_response),
+            created_at_epoch: originalTimestamp ?? Date.now(),
+            cwd: message.cwd
+          });
+
+          // Add to conversation history and query Gemini with full context
+          session.conversationHistory.push({ role: 'user', content: obsPrompt });
+          const obsResponse = await this.queryGeminiMultiTurn(session.conversationHistory, apiKey, model, rateLimitingEnabled);
+
+          if (obsResponse.content) {
+            // Add response to conversation history
+            session.conversationHistory.push({ role: 'assistant', content: obsResponse.content });
+
+            const tokensUsed = obsResponse.tokensUsed || 0;
+            session.cumulativeInputTokens += Math.floor(tokensUsed * 0.7);
+            session.cumulativeOutputTokens += Math.floor(tokensUsed * 0.3);
+            await this.processGeminiResponse(session, obsResponse.content, worker, tokensUsed, originalTimestamp);
+          } else {
+            // Empty response - still mark messages as processed to avoid stuck state
+            logger.warn('SDK', 'Empty Gemini response for observation, marking as processed', {
+              sessionId: session.sessionDbId,
+              toolName: message.tool_name
+            });
+            await this.markMessagesProcessed(session, worker);
+          }
+
+        } else if (message.type === 'summarize') {
+          // Build summary prompt
+          const summaryPrompt = buildSummaryPrompt({
+            id: session.sessionDbId,
+            sdk_session_id: session.sdkSessionId,
+            project: session.project,
+            user_prompt: session.userPrompt,
+            last_user_message: message.last_user_message || '',
+            last_assistant_message: message.last_assistant_message || ''
+          }, mode);
+
+          // Add to conversation history and query Gemini with full context
+          session.conversationHistory.push({ role: 'user', content: summaryPrompt });
+          const summaryResponse = await this.queryGeminiMultiTurn(session.conversationHistory, apiKey, model, rateLimitingEnabled);
+
+          if (summaryResponse.content) {
+            // Add response to conversation history
+            session.conversationHistory.push({ role: 'assistant', content: summaryResponse.content });
+
+            const tokensUsed = summaryResponse.tokensUsed || 0;
+            session.cumulativeInputTokens += Math.floor(tokensUsed * 0.7);
+            session.cumulativeOutputTokens += Math.floor(tokensUsed * 0.3);
+            await this.processGeminiResponse(session, summaryResponse.content, worker, tokensUsed, originalTimestamp);
+          } else {
+            // Empty response - still mark messages as processed to avoid stuck state
+            logger.warn('SDK', 'Empty Gemini response for summary, marking as processed', {
+              sessionId: session.sessionDbId
+            });
+            await this.markMessagesProcessed(session, worker);
+          }
+        }
+      }
+
+      // Mark session complete
+      const sessionDuration = Date.now() - session.startTime;
+      logger.success('SDK', 'Gemini agent completed', {
+        sessionId: session.sessionDbId,
+        duration: `${(sessionDuration / 1000).toFixed(1)}s`,
+        historyLength: session.conversationHistory.length
+      });
+
+    } catch (error: any) {
+      if (error.name === 'AbortError') {
+        logger.warn('SDK', 'Gemini agent aborted', { sessionId: session.sessionDbId });
+        throw error;
+      }
+
+      // Check if we should fall back to Claude
+      if (this.shouldFallbackToClaude(error) && this.fallbackAgent) {
+        logger.warn('SDK', 'Gemini API failed, falling back to Claude SDK', {
+          sessionDbId: session.sessionDbId,
+          error: error.message,
+          historyLength: session.conversationHistory.length
+        });
+
+        // Reset any 'processing' messages back to 'pending' so Claude can retry them
+        // This handles the case where Gemini failed mid-processing a message
+        const pendingStore = this.sessionManager.getPendingMessageStore();
+        const resetCount = pendingStore.resetStuckMessages(0);  // 0 = reset ALL processing messages
+        if (resetCount > 0) {
+          logger.info('SDK', 'Reset processing messages for fallback', {
+            sessionDbId: session.sessionDbId,
+            resetCount
+          });
+        }
+
+        // Fall back to Claude - it will use the same session with shared conversationHistory
+        // Note: Claude SDK will continue processing from current state
+        return this.fallbackAgent.startSession(session, worker);
+      }
+
+      logger.failure('SDK', 'Gemini agent error', { sessionDbId: session.sessionDbId }, error);
+      throw error;
+    }
+  }
+
+  /**
+   * Convert shared ConversationMessage array to Gemini's contents format
+   * Maps 'assistant' role to 'model' for Gemini API compatibility
+   */
+  private conversationToGeminiContents(history: ConversationMessage[]): GeminiContent[] {
+    return history.map(msg => ({
+      role: msg.role === 'assistant' ? 'model' : 'user',
+      parts: [{ text: msg.content }]
+    }));
+  }
+
+  /**
+   * Query Gemini via REST API with full conversation history (multi-turn)
+   * Sends the entire conversation context for coherent responses
+   */
+  private async queryGeminiMultiTurn(
+    history: ConversationMessage[],
+    apiKey: string,
+    model: GeminiModel,
+    rateLimitingEnabled: boolean
+  ): Promise<{ content: string; tokensUsed?: number }> {
+    const contents = this.conversationToGeminiContents(history);
+    const totalChars = history.reduce((sum, m) => sum + m.content.length, 0);
+
+    logger.debug('SDK', `Querying Gemini multi-turn (${model})`, {
+      turns: history.length,
+      totalChars
+    });
+
+    const url = `${GEMINI_API_URL}/${model}:generateContent?key=${apiKey}`;
+
+    // Enforce RPM rate limit for free tier (skipped if rate limiting disabled)
+    await enforceRateLimitForModel(model, rateLimitingEnabled);
+
+    const response = await fetch(url, {
+      method: 'POST',
+      headers: {
+        'Content-Type': 'application/json',
+      },
+      body: JSON.stringify({
+        contents,
+        generationConfig: {
+          temperature: 0.3,  // Lower temperature for structured extraction
+          maxOutputTokens: 4096,
+        },
+      }),
+    });
+
+    if (!response.ok) {
+      const error = await response.text();
+      throw new Error(`Gemini API error: ${response.status} - ${error}`);
+    }
+
+    const data = await response.json() as GeminiResponse;
+
+    if (!data.candidates?.[0]?.content?.parts?.[0]?.text) {
+      logger.warn('SDK', 'Empty response from Gemini');
+      return { content: '' };
+    }
+
+    const content = data.candidates[0].content.parts[0].text;
+    const tokensUsed = data.usageMetadata?.totalTokenCount;
+
+    return { content, tokensUsed };
+  }
+
+  /**
+   * Process Gemini response (same format as Claude)
+   * @param originalTimestamp - Original epoch when message was queued (for backlog processing accuracy)
+   */
+  private async processGeminiResponse(
+    session: ActiveSession,
+    text: string,
+    worker: any | undefined,
+    discoveryTokens: number,
+    originalTimestamp: number | null
+  ): Promise<void> {
+    // Parse observations (same XML format)
+    const observations = parseObservations(text, session.claudeSessionId);
+
+    // Store observations with original timestamp (if processing backlog) or current time
+    for (const obs of observations) {
+      const { id: obsId, createdAtEpoch } = this.dbManager.getSessionStore().storeObservation(
+        session.claudeSessionId,
+        session.project,
+        obs,
+        session.lastPromptNumber,
+        discoveryTokens,
+        originalTimestamp ?? undefined
+      );
+
+      logger.info('SDK', 'Gemini observation saved', {
+        sessionId: session.sessionDbId,
+        obsId,
+        type: obs.type,
+        title: obs.title || '(untitled)'
+      });
+
+      // Sync to Chroma
+      this.dbManager.getChromaSync().syncObservation(
+        obsId,
+        session.claudeSessionId,
+        session.project,
+        obs,
+        session.lastPromptNumber,
+        createdAtEpoch,
+        discoveryTokens
+      ).catch(err => {
+        logger.warn('SDK', 'Gemini chroma sync failed', { obsId }, err);
+      });
+
+      // Broadcast to SSE clients
+      if (worker && worker.sseBroadcaster) {
+        worker.sseBroadcaster.broadcast({
+          type: 'new_observation',
+          observation: {
+            id: obsId,
+            sdk_session_id: session.sdkSessionId,
+            session_id: session.claudeSessionId,
+            type: obs.type,
+            title: obs.title,
+            subtitle: obs.subtitle,
+            text: null,
+            narrative: obs.narrative || null,
+            facts: JSON.stringify(obs.facts || []),
+            concepts: JSON.stringify(obs.concepts || []),
+            files_read: JSON.stringify(obs.files_read || []),
+            files_modified: JSON.stringify(obs.files_modified || []),
+            project: session.project,
+            prompt_number: session.lastPromptNumber,
+            created_at_epoch: createdAtEpoch
+          }
+        });
+      }
+    }
+
+    // Parse summary
+    const summary = parseSummary(text, session.sessionDbId);
+
+    if (summary) {
+      // Convert nullable fields to empty strings for storeSummary
+      const summaryForStore = {
+        request: summary.request || '',
+        investigated: summary.investigated || '',
+        learned: summary.learned || '',
+        completed: summary.completed || '',
+        next_steps: summary.next_steps || '',
+        notes: summary.notes
+      };
+
+      const { id: summaryId, createdAtEpoch } = this.dbManager.getSessionStore().storeSummary(
+        session.claudeSessionId,
+        session.project,
+        summaryForStore,
+        session.lastPromptNumber,
+        discoveryTokens,
+        originalTimestamp ?? undefined
+      );
+
+      logger.info('SDK', 'Gemini summary saved', {
+        sessionId: session.sessionDbId,
+        summaryId,
+        request: summary.request || '(no request)'
+      });
+
+      // Sync to Chroma
+      this.dbManager.getChromaSync().syncSummary(
+        summaryId,
+        session.claudeSessionId,
+        session.project,
+        summaryForStore,
+        session.lastPromptNumber,
+        createdAtEpoch,
+        discoveryTokens
+      ).catch(err => {
+        logger.warn('SDK', 'Gemini chroma sync failed', { summaryId }, err);
+      });
+
+      // Broadcast to SSE clients
+      if (worker && worker.sseBroadcaster) {
+        worker.sseBroadcaster.broadcast({
+          type: 'new_summary',
+          summary: {
+            id: summaryId,
+            session_id: session.claudeSessionId,
+            request: summary.request,
+            investigated: summary.investigated,
+            learned: summary.learned,
+            completed: summary.completed,
+            next_steps: summary.next_steps,
+            notes: summary.notes,
+            project: session.project,
+            prompt_number: session.lastPromptNumber,
+            created_at_epoch: createdAtEpoch
+          }
+        });
+      }
+    }
+
+    // Mark messages as processed
+    await this.markMessagesProcessed(session, worker);
+  }
+
+  /**
+   * Mark pending messages as processed
+   */
+  private async markMessagesProcessed(session: ActiveSession, worker: any | undefined): Promise<void> {
+    const pendingMessageStore = this.sessionManager.getPendingMessageStore();
+    if (session.pendingProcessingIds.size > 0) {
+      for (const messageId of session.pendingProcessingIds) {
+        pendingMessageStore.markProcessed(messageId);
+      }
+      logger.debug('SDK', 'Gemini messages marked as processed', {
+        sessionId: session.sessionDbId,
+        count: session.pendingProcessingIds.size
+      });
+      session.pendingProcessingIds.clear();
+
+      const deletedCount = pendingMessageStore.cleanupProcessed(100);
+      if (deletedCount > 0) {
+        logger.debug('SDK', 'Gemini cleaned up old processed messages', { deletedCount });
+      }
+    }
+
+    if (worker && typeof worker.broadcastProcessingStatus === 'function') {
+      worker.broadcastProcessingStatus();
+    }
+  }
+
+  /**
+   * Get Gemini configuration from settings or environment
+   */
+  private getGeminiConfig(): { apiKey: string; model: GeminiModel; rateLimitingEnabled: boolean } {
+    const settingsPath = path.join(homedir(), '.claude-mem', 'settings.json');
+    const settings = SettingsDefaultsManager.loadFromFile(settingsPath);
+
+    // API key: check settings first, then environment variable
+    const apiKey = settings.CLAUDE_MEM_GEMINI_API_KEY || process.env.GEMINI_API_KEY || '';
+
+    // Model: from settings or default, with validation
+    const defaultModel: GeminiModel = 'gemini-2.5-flash';
+    const configuredModel = settings.CLAUDE_MEM_GEMINI_MODEL || defaultModel;
+    const validModels: GeminiModel[] = [
+      'gemini-2.5-flash-lite',
+      'gemini-2.5-flash',
+      'gemini-2.5-pro',
+      'gemini-2.0-flash',
+      'gemini-2.0-flash-lite',
+    ];
+
+    let model: GeminiModel;
+    if (validModels.includes(configuredModel as GeminiModel)) {
+      model = configuredModel as GeminiModel;
+    } else {
+      logger.warn('SDK', `Invalid Gemini model "${configuredModel}", falling back to ${defaultModel}`, {
+        configured: configuredModel,
+        validModels,
+      });
+      model = defaultModel;
+    }
+
+    // Rate limiting: enabled by default for free tier users
+    const rateLimitingEnabled = settings.CLAUDE_MEM_GEMINI_RATE_LIMITING_ENABLED !== 'false';
+
+    return { apiKey, model, rateLimitingEnabled };
+  }
+}
+
+/**
+ * Check if Gemini is available (has API key configured)
+ */
+export function isGeminiAvailable(): boolean {
+  const settingsPath = path.join(homedir(), '.claude-mem', 'settings.json');
+  const settings = SettingsDefaultsManager.loadFromFile(settingsPath);
+  return !!(settings.CLAUDE_MEM_GEMINI_API_KEY || process.env.GEMINI_API_KEY);
+}
+
+/**
+ * Check if Gemini is the selected provider
+ */
+export function isGeminiSelected(): boolean {
+  const settingsPath = path.join(homedir(), '.claude-mem', 'settings.json');
+  const settings = SettingsDefaultsManager.loadFromFile(settingsPath);
+  return settings.CLAUDE_MEM_PROVIDER === 'gemini';
+}

src/services/worker/OpenRouterAgent.ts

@@ -0,0 +1,608 @@
+/**
+ * OpenRouterAgent: OpenRouter-based observation extraction
+ *
+ * Alternative to SDKAgent that uses OpenRouter's unified API
+ * for accessing 100+ models from different providers.
+ *
+ * Responsibility:
+ * - Call OpenRouter REST API for observation extraction
+ * - Parse XML responses (same format as Claude/Gemini)
+ * - Sync to database and Chroma
+ * - Support dynamic model selection across providers
+ */
+
+import { DatabaseManager } from './DatabaseManager.js';
+import { SessionManager } from './SessionManager.js';
+import { logger } from '../../utils/logger.js';
+import { parseObservations, parseSummary } from '../../sdk/parser.js';
+import { buildInitPrompt, buildObservationPrompt, buildSummaryPrompt, buildContinuationPrompt } from '../../sdk/prompts.js';
+import { SettingsDefaultsManager } from '../../shared/SettingsDefaultsManager.js';
+import { USER_SETTINGS_PATH } from '../../shared/paths.js';
+import type { ActiveSession, ConversationMessage } from '../worker-types.js';
+import { ModeManager } from '../domain/ModeManager.js';
+
+// OpenRouter API endpoint
+const OPENROUTER_API_URL = 'https://openrouter.ai/api/v1/chat/completions';
+
+// Context window management constants (defaults, overridable via settings)
+const DEFAULT_MAX_CONTEXT_MESSAGES = 20;  // Maximum messages to keep in conversation history
+const DEFAULT_MAX_ESTIMATED_TOKENS = 100000;  // ~100k tokens max context (safety limit)
+const CHARS_PER_TOKEN_ESTIMATE = 4;  // Conservative estimate: 1 token ≈ 4 chars
+
+// OpenAI-compatible message format
+interface OpenAIMessage {
+  role: 'user' | 'assistant' | 'system';
+  content: string;
+}
+
+interface OpenRouterResponse {
+  choices?: Array<{
+    message?: {
+      role?: string;
+      content?: string;
+    };
+    finish_reason?: string;
+  }>;
+  usage?: {
+    prompt_tokens?: number;
+    completion_tokens?: number;
+    total_tokens?: number;
+  };
+  error?: {
+    message?: string;
+    code?: string;
+  };
+}
+
+// Forward declaration for fallback agent type
+type FallbackAgent = {
+  startSession(session: ActiveSession, worker?: any): Promise<void>;
+};
+
+export class OpenRouterAgent {
+  private dbManager: DatabaseManager;
+  private sessionManager: SessionManager;
+  private fallbackAgent: FallbackAgent | null = null;
+
+  constructor(dbManager: DatabaseManager, sessionManager: SessionManager) {
+    this.dbManager = dbManager;
+    this.sessionManager = sessionManager;
+  }
+
+  /**
+   * Set the fallback agent (Claude SDK) for when OpenRouter API fails
+   * Must be set after construction to avoid circular dependency
+   */
+  setFallbackAgent(agent: FallbackAgent): void {
+    this.fallbackAgent = agent;
+  }
+
+  /**
+   * Check if an error should trigger fallback to Claude
+   */
+  private shouldFallbackToClaude(error: any): boolean {
+    const message = error?.message || '';
+    // Fall back on rate limit (429), server errors (5xx), or network issues
+    return (
+      message.includes('429') ||
+      message.includes('500') ||
+      message.includes('502') ||
+      message.includes('503') ||
+      message.includes('ECONNREFUSED') ||
+      message.includes('ETIMEDOUT') ||
+      message.includes('fetch failed')
+    );
+  }
+
+  /**
+   * Start OpenRouter agent for a session
+   * Uses multi-turn conversation to maintain context across messages
+   */
+  async startSession(session: ActiveSession, worker?: any): Promise<void> {
+    try {
+      // Get OpenRouter configuration
+      const { apiKey, model, siteUrl, appName } = this.getOpenRouterConfig();
+
+      if (!apiKey) {
+        throw new Error('OpenRouter API key not configured. Set CLAUDE_MEM_OPENROUTER_API_KEY in settings or OPENROUTER_API_KEY environment variable.');
+      }
+
+      // Load active mode
+      const mode = ModeManager.getInstance().getActiveMode();
+
+      // Build initial prompt
+      const initPrompt = session.lastPromptNumber === 1
+        ? buildInitPrompt(session.project, session.claudeSessionId, session.userPrompt, mode)
+        : buildContinuationPrompt(session.userPrompt, session.lastPromptNumber, session.claudeSessionId, mode);
+
+      // Add to conversation history and query OpenRouter with full context
+      session.conversationHistory.push({ role: 'user', content: initPrompt });
+      const initResponse = await this.queryOpenRouterMultiTurn(session.conversationHistory, apiKey, model, siteUrl, appName);
+
+      if (initResponse.content) {
+        // Add response to conversation history
+        session.conversationHistory.push({ role: 'assistant', content: initResponse.content });
+
+        // Track token usage
+        const tokensUsed = initResponse.tokensUsed || 0;
+        session.cumulativeInputTokens += Math.floor(tokensUsed * 0.7);  // Rough estimate
+        session.cumulativeOutputTokens += Math.floor(tokensUsed * 0.3);
+
+        // Process response (no original timestamp for init - not from queue)
+        await this.processOpenRouterResponse(session, initResponse.content, worker, tokensUsed, null);
+      } else {
+        logger.warn('SDK', 'Empty OpenRouter init response - session may lack context', {
+          sessionId: session.sessionDbId,
+          model
+        });
+      }
+
+      // Process pending messages
+      for await (const message of this.sessionManager.getMessageIterator(session.sessionDbId)) {
+        // Capture earliest timestamp BEFORE processing (will be cleared after)
+        const originalTimestamp = session.earliestPendingTimestamp;
+
+        if (message.type === 'observation') {
+          // Update last prompt number
+          if (message.prompt_number !== undefined) {
+            session.lastPromptNumber = message.prompt_number;
+          }
+
+          // Build observation prompt
+          const obsPrompt = buildObservationPrompt({
+            id: 0,
+            tool_name: message.tool_name!,
+            tool_input: JSON.stringify(message.tool_input),
+            tool_output: JSON.stringify(message.tool_response),
+            created_at_epoch: originalTimestamp ?? Date.now(),
+            cwd: message.cwd
+          });
+
+          // Add to conversation history and query OpenRouter with full context
+          session.conversationHistory.push({ role: 'user', content: obsPrompt });
+          const obsResponse = await this.queryOpenRouterMultiTurn(session.conversationHistory, apiKey, model, siteUrl, appName);
+
+          if (obsResponse.content) {
+            // Add response to conversation history
+            session.conversationHistory.push({ role: 'assistant', content: obsResponse.content });
+
+            const tokensUsed = obsResponse.tokensUsed || 0;
+            session.cumulativeInputTokens += Math.floor(tokensUsed * 0.7);
+            session.cumulativeOutputTokens += Math.floor(tokensUsed * 0.3);
+            await this.processOpenRouterResponse(session, obsResponse.content, worker, tokensUsed, originalTimestamp);
+          } else {
+            // Empty response - still mark messages as processed to avoid stuck state
+            logger.warn('SDK', 'Empty OpenRouter response for observation, marking as processed', {
+              sessionId: session.sessionDbId,
+              toolName: message.tool_name
+            });
+            await this.markMessagesProcessed(session, worker);
+          }
+
+        } else if (message.type === 'summarize') {
+          // Build summary prompt
+          const summaryPrompt = buildSummaryPrompt({
+            id: session.sessionDbId,
+            sdk_session_id: session.sdkSessionId,
+            project: session.project,
+            user_prompt: session.userPrompt,
+            last_user_message: message.last_user_message || '',
+            last_assistant_message: message.last_assistant_message || ''
+          }, mode);
+
+          // Add to conversation history and query OpenRouter with full context
+          session.conversationHistory.push({ role: 'user', content: summaryPrompt });
+          const summaryResponse = await this.queryOpenRouterMultiTurn(session.conversationHistory, apiKey, model, siteUrl, appName);
+
+          if (summaryResponse.content) {
+            // Add response to conversation history
+            session.conversationHistory.push({ role: 'assistant', content: summaryResponse.content });
+
+            const tokensUsed = summaryResponse.tokensUsed || 0;
+            session.cumulativeInputTokens += Math.floor(tokensUsed * 0.7);
+            session.cumulativeOutputTokens += Math.floor(tokensUsed * 0.3);
+            await this.processOpenRouterResponse(session, summaryResponse.content, worker, tokensUsed, originalTimestamp);
+          } else {
+            // Empty response - still mark messages as processed to avoid stuck state
+            logger.warn('SDK', 'Empty OpenRouter response for summary, marking as processed', {
+              sessionId: session.sessionDbId
+            });
+            await this.markMessagesProcessed(session, worker);
+          }
+        }
+      }
+
+      // Mark session complete
+      const sessionDuration = Date.now() - session.startTime;
+      logger.success('SDK', 'OpenRouter agent completed', {
+        sessionId: session.sessionDbId,
+        duration: `${(sessionDuration / 1000).toFixed(1)}s`,
+        historyLength: session.conversationHistory.length,
+        model
+      });
+
+    } catch (error: any) {
+      if (error.name === 'AbortError') {
+        logger.warn('SDK', 'OpenRouter agent aborted', { sessionId: session.sessionDbId });
+        throw error;
+      }
+
+      // Check if we should fall back to Claude
+      if (this.shouldFallbackToClaude(error) && this.fallbackAgent) {
+        logger.warn('SDK', 'OpenRouter API failed, falling back to Claude SDK', {
+          sessionDbId: session.sessionDbId,
+          error: error.message,
+          historyLength: session.conversationHistory.length
+        });
+
+        // Reset any 'processing' messages back to 'pending' so Claude can retry them
+        const pendingStore = this.sessionManager.getPendingMessageStore();
+        const resetCount = pendingStore.resetStuckMessages(0);  // 0 = reset ALL processing messages
+        if (resetCount > 0) {
+          logger.info('SDK', 'Reset processing messages for fallback', {
+            sessionDbId: session.sessionDbId,
+            resetCount
+          });
+        }
+
+        // Fall back to Claude - it will use the same session with shared conversationHistory
+        return this.fallbackAgent.startSession(session, worker);
+      }
+
+      logger.failure('SDK', 'OpenRouter agent error', { sessionDbId: session.sessionDbId }, error);
+      throw error;
+    }
+  }
+
+  /**
+   * Estimate token count from text (conservative estimate)
+   */
+  private estimateTokens(text: string): number {
+    return Math.ceil(text.length / CHARS_PER_TOKEN_ESTIMATE);
+  }
+
+  /**
+   * Truncate conversation history to prevent runaway context costs
+   * Keeps most recent messages within token budget
+   */
+  private truncateHistory(history: ConversationMessage[]): ConversationMessage[] {
+    const settings = SettingsDefaultsManager.loadFromFile(
+      USER_SETTINGS_PATH
+    );
+
+    const MAX_CONTEXT_MESSAGES = parseInt(settings.CLAUDE_MEM_OPENROUTER_MAX_CONTEXT_MESSAGES) || DEFAULT_MAX_CONTEXT_MESSAGES;
+    const MAX_ESTIMATED_TOKENS = parseInt(settings.CLAUDE_MEM_OPENROUTER_MAX_TOKENS) || DEFAULT_MAX_ESTIMATED_TOKENS;
+
+    if (history.length <= MAX_CONTEXT_MESSAGES) {
+      // Check token count even if message count is ok
+      const totalTokens = history.reduce((sum, m) => sum + this.estimateTokens(m.content), 0);
+      if (totalTokens <= MAX_ESTIMATED_TOKENS) {
+        return history;
+      }
+    }
+
+    // Sliding window: keep most recent messages within limits
+    const truncated: ConversationMessage[] = [];
+    let tokenCount = 0;
+
+    // Process messages in reverse (most recent first)
+    for (let i = history.length - 1; i >= 0; i--) {
+      const msg = history[i];
+      const msgTokens = this.estimateTokens(msg.content);
+
+      if (truncated.length >= MAX_CONTEXT_MESSAGES || tokenCount + msgTokens > MAX_ESTIMATED_TOKENS) {
+        logger.warn('SDK', 'Context window truncated to prevent runaway costs', {
+          originalMessages: history.length,
+          keptMessages: truncated.length,
+          droppedMessages: i + 1,
+          estimatedTokens: tokenCount,
+          tokenLimit: MAX_ESTIMATED_TOKENS
+        });
+        break;
+      }
+
+      truncated.unshift(msg);  // Add to beginning
+      tokenCount += msgTokens;
+    }
+
+    return truncated;
+  }
+
+  /**
+   * Convert shared ConversationMessage array to OpenAI-compatible message format
+   */
+  private conversationToOpenAIMessages(history: ConversationMessage[]): OpenAIMessage[] {
+    return history.map(msg => ({
+      role: msg.role === 'assistant' ? 'assistant' : 'user',
+      content: msg.content
+    }));
+  }
+
+  /**
+   * Query OpenRouter via REST API with full conversation history (multi-turn)
+   * Sends the entire conversation context for coherent responses
+   */
+  private async queryOpenRouterMultiTurn(
+    history: ConversationMessage[],
+    apiKey: string,
+    model: string,
+    siteUrl?: string,
+    appName?: string
+  ): Promise<{ content: string; tokensUsed?: number }> {
+    // Truncate history to prevent runaway costs
+    const truncatedHistory = this.truncateHistory(history);
+    const messages = this.conversationToOpenAIMessages(truncatedHistory);
+    const totalChars = truncatedHistory.reduce((sum, m) => sum + m.content.length, 0);
+    const estimatedTokens = this.estimateTokens(truncatedHistory.map(m => m.content).join(''));
+
+    logger.debug('SDK', `Querying OpenRouter multi-turn (${model})`, {
+      turns: truncatedHistory.length,
+      totalChars,
+      estimatedTokens
+    });
+
+    const response = await fetch(OPENROUTER_API_URL, {
+      method: 'POST',
+      headers: {
+        'Authorization': `Bearer ${apiKey}`,
+        'HTTP-Referer': siteUrl || 'https://github.com/thedotmack/claude-mem',
+        'X-Title': appName || 'claude-mem',
+        'Content-Type': 'application/json',
+      },
+      body: JSON.stringify({
+        model,
+        messages,
+        temperature: 0.3,  // Lower temperature for structured extraction
+        max_tokens: 4096,
+      }),
+    });
+
+    if (!response.ok) {
+      const errorText = await response.text();
+      throw new Error(`OpenRouter API error: ${response.status} - ${errorText}`);
+    }
+
+    const data = await response.json() as OpenRouterResponse;
+
+    // Check for API error in response body
+    if (data.error) {
+      throw new Error(`OpenRouter API error: ${data.error.code} - ${data.error.message}`);
+    }
+
+    if (!data.choices?.[0]?.message?.content) {
+      logger.warn('SDK', 'Empty response from OpenRouter');
+      return { content: '' };
+    }
+
+    const content = data.choices[0].message.content;
+    const tokensUsed = data.usage?.total_tokens;
+
+    // Log actual token usage for cost tracking
+    if (tokensUsed) {
+      const inputTokens = data.usage?.prompt_tokens || 0;
+      const outputTokens = data.usage?.completion_tokens || 0;
+      // Token usage (cost varies by model - many OpenRouter models are free)
+      const estimatedCost = (inputTokens / 1000000 * 3) + (outputTokens / 1000000 * 15);
+
+      logger.info('SDK', 'OpenRouter API usage', {
+        model,
+        inputTokens,
+        outputTokens,
+        totalTokens: tokensUsed,
+        estimatedCostUSD: estimatedCost.toFixed(4),
+        messagesInContext: truncatedHistory.length
+      });
+
+      // Warn if costs are getting high
+      if (tokensUsed > 50000) {
+        logger.warn('SDK', 'High token usage detected - consider reducing context', {
+          totalTokens: tokensUsed,
+          estimatedCost: estimatedCost.toFixed(4)
+        });
+      }
+    }
+
+    return { content, tokensUsed };
+  }
+
+  /**
+   * Process OpenRouter response (same format as Claude/Gemini)
+   * @param originalTimestamp - Original epoch when message was queued (for backlog processing accuracy)
+   */
+  private async processOpenRouterResponse(
+    session: ActiveSession,
+    text: string,
+    worker: any | undefined,
+    discoveryTokens: number,
+    originalTimestamp: number | null
+  ): Promise<void> {
+    // Parse observations (same XML format)
+    const observations = parseObservations(text, session.claudeSessionId);
+
+    // Store observations with original timestamp (if processing backlog) or current time
+    for (const obs of observations) {
+      const { id: obsId, createdAtEpoch } = this.dbManager.getSessionStore().storeObservation(
+        session.claudeSessionId,
+        session.project,
+        obs,
+        session.lastPromptNumber,
+        discoveryTokens,
+        originalTimestamp ?? undefined
+      );
+
+      logger.info('SDK', 'OpenRouter observation saved', {
+        sessionId: session.sessionDbId,
+        obsId,
+        type: obs.type,
+        title: obs.title || '(untitled)'
+      });
+
+      // Sync to Chroma
+      this.dbManager.getChromaSync().syncObservation(
+        obsId,
+        session.claudeSessionId,
+        session.project,
+        obs,
+        session.lastPromptNumber,
+        createdAtEpoch,
+        discoveryTokens
+      ).catch(err => {
+        logger.warn('SDK', 'OpenRouter chroma sync failed', { obsId }, err);
+      });
+
+      // Broadcast to SSE clients
+      if (worker && worker.sseBroadcaster) {
+        worker.sseBroadcaster.broadcast({
+          type: 'new_observation',
+          observation: {
+            id: obsId,
+            sdk_session_id: session.sdkSessionId,
+            session_id: session.claudeSessionId,
+            type: obs.type,
+            title: obs.title,
+            subtitle: obs.subtitle,
+            text: null,
+            narrative: obs.narrative || null,
+            facts: JSON.stringify(obs.facts || []),
+            concepts: JSON.stringify(obs.concepts || []),
+            files_read: JSON.stringify(obs.files_read || []),
+            files_modified: JSON.stringify(obs.files_modified || []),
+            project: session.project,
+            prompt_number: session.lastPromptNumber,
+            created_at_epoch: createdAtEpoch
+          }
+        });
+      }
+    }
+
+    // Parse summary
+    const summary = parseSummary(text, session.sessionDbId);
+
+    if (summary) {
+      // Convert nullable fields to empty strings for storeSummary
+      const summaryForStore = {
+        request: summary.request || '',
+        investigated: summary.investigated || '',
+        learned: summary.learned || '',
+        completed: summary.completed || '',
+        next_steps: summary.next_steps || '',
+        notes: summary.notes
+      };
+
+      const { id: summaryId, createdAtEpoch } = this.dbManager.getSessionStore().storeSummary(
+        session.claudeSessionId,
+        session.project,
+        summaryForStore,
+        session.lastPromptNumber,
+        discoveryTokens,
+        originalTimestamp ?? undefined
+      );
+
+      logger.info('SDK', 'OpenRouter summary saved', {
+        sessionId: session.sessionDbId,
+        summaryId,
+        request: summary.request || '(no request)'
+      });
+
+      // Sync to Chroma
+      this.dbManager.getChromaSync().syncSummary(
+        summaryId,
+        session.claudeSessionId,
+        session.project,
+        summaryForStore,
+        session.lastPromptNumber,
+        createdAtEpoch,
+        discoveryTokens
+      ).catch(err => {
+        logger.warn('SDK', 'OpenRouter chroma sync failed', { summaryId }, err);
+      });
+
+      // Broadcast to SSE clients
+      if (worker && worker.sseBroadcaster) {
+        worker.sseBroadcaster.broadcast({
+          type: 'new_summary',
+          summary: {
+            id: summaryId,
+            session_id: session.claudeSessionId,
+            request: summary.request,
+            investigated: summary.investigated,
+            learned: summary.learned,
+            completed: summary.completed,
+            next_steps: summary.next_steps,
+            notes: summary.notes,
+            project: session.project,
+            prompt_number: session.lastPromptNumber,
+            created_at_epoch: createdAtEpoch
+          }
+        });
+      }
+    }
+
+    // Mark messages as processed
+    await this.markMessagesProcessed(session, worker);
+  }
+
+  /**
+   * Mark pending messages as processed
+   */
+  private async markMessagesProcessed(session: ActiveSession, worker: any | undefined): Promise<void> {
+    const pendingMessageStore = this.sessionManager.getPendingMessageStore();
+    if (session.pendingProcessingIds.size > 0) {
+      for (const messageId of session.pendingProcessingIds) {
+        pendingMessageStore.markProcessed(messageId);
+      }
+      logger.debug('SDK', 'OpenRouter messages marked as processed', {
+        sessionId: session.sessionDbId,
+        count: session.pendingProcessingIds.size
+      });
+      session.pendingProcessingIds.clear();
+
+      const deletedCount = pendingMessageStore.cleanupProcessed(100);
+      if (deletedCount > 0) {
+        logger.debug('SDK', 'OpenRouter cleaned up old processed messages', { deletedCount });
+      }
+    }
+
+    if (worker && typeof worker.broadcastProcessingStatus === 'function') {
+      worker.broadcastProcessingStatus();
+    }
+  }
+
+  /**
+   * Get OpenRouter configuration from settings or environment
+   */
+  private getOpenRouterConfig(): { apiKey: string; model: string; siteUrl?: string; appName?: string } {
+    const settingsPath = USER_SETTINGS_PATH;
+    const settings = SettingsDefaultsManager.loadFromFile(settingsPath);
+
+    // API key: check settings first, then environment variable
+    const apiKey = settings.CLAUDE_MEM_OPENROUTER_API_KEY || process.env.OPENROUTER_API_KEY || '';
+
+    // Model: from settings or default
+    const model = settings.CLAUDE_MEM_OPENROUTER_MODEL || 'xiaomi/mimo-v2-flash:free';
+
+    // Optional analytics headers
+    const siteUrl = settings.CLAUDE_MEM_OPENROUTER_SITE_URL || '';
+    const appName = settings.CLAUDE_MEM_OPENROUTER_APP_NAME || 'claude-mem';
+
+    return { apiKey, model, siteUrl, appName };
+  }
+}
+
+/**
+ * Check if OpenRouter is available (has API key configured)
+ */
+export function isOpenRouterAvailable(): boolean {
+  const settingsPath = USER_SETTINGS_PATH;
+  const settings = SettingsDefaultsManager.loadFromFile(settingsPath);
+  return !!(settings.CLAUDE_MEM_OPENROUTER_API_KEY || process.env.OPENROUTER_API_KEY);
+}
+
+/**
+ * Check if OpenRouter is the selected provider
+ */
+export function isOpenRouterSelected(): boolean {
+  const settingsPath = USER_SETTINGS_PATH;
+  const settings = SettingsDefaultsManager.loadFromFile(settingsPath);
+  return settings.CLAUDE_MEM_PROVIDER === 'openrouter';
+}

src/services/worker/SDKAgent.ts

@@ -185,20 +185,31 @@ export class SDKAgent {
    * - SessionManager.initializeSession already fetched this from database
    * - Database row was created by new-hook's createSDKSession call
    * - We just use the session_id we're given - simple and reliable
+   *
+   * SHARED CONVERSATION HISTORY:
+   * - Each user message is added to session.conversationHistory
+   * - This allows provider switching (Claude→Gemini) with full context
+   * - SDK manages its own internal state, but we mirror it for interop
    */
   private async *createMessageGenerator(session: ActiveSession): AsyncIterableIterator<SDKUserMessage> {
     // Load active mode
     const mode = ModeManager.getInstance().getActiveMode();
 
+    // Build initial prompt
+    const initPrompt = session.lastPromptNumber === 1
+      ? buildInitPrompt(session.project, session.claudeSessionId, session.userPrompt, mode)
+      : buildContinuationPrompt(session.userPrompt, session.lastPromptNumber, session.claudeSessionId, mode);
+
+    // Add to shared conversation history for provider interop
+    session.conversationHistory.push({ role: 'user', content: initPrompt });
+
     // Yield initial user prompt with context (or continuation if prompt #2+)
     // CRITICAL: Both paths use session.claudeSessionId from the hook
     yield {
       type: 'user',
       message: {
         role: 'user',
-        content: session.lastPromptNumber === 1
-          ? buildInitPrompt(session.project, session.claudeSessionId, session.userPrompt, mode)
-          : buildContinuationPrompt(session.userPrompt, session.lastPromptNumber, session.claudeSessionId, mode)
+        content: initPrompt
       },
       session_id: session.claudeSessionId,
       parent_tool_use_id: null,
@@ -213,36 +224,46 @@ export class SDKAgent {
           session.lastPromptNumber = message.prompt_number;
         }
 
+        const obsPrompt = buildObservationPrompt({
+          id: 0, // Not used in prompt
+          tool_name: message.tool_name!,
+          tool_input: JSON.stringify(message.tool_input),
+          tool_output: JSON.stringify(message.tool_response),
+          created_at_epoch: Date.now(),
+          cwd: message.cwd
+        });
+
+        // Add to shared conversation history for provider interop
+        session.conversationHistory.push({ role: 'user', content: obsPrompt });
+
         yield {
           type: 'user',
           message: {
             role: 'user',
-            content: buildObservationPrompt({
-              id: 0, // Not used in prompt
-              tool_name: message.tool_name!,
-              tool_input: JSON.stringify(message.tool_input),
-              tool_output: JSON.stringify(message.tool_response),
-              created_at_epoch: Date.now(),
-              cwd: message.cwd
-            })
+            content: obsPrompt
           },
           session_id: session.claudeSessionId,
           parent_tool_use_id: null,
           isSynthetic: true
         };
       } else if (message.type === 'summarize') {
+        const summaryPrompt = buildSummaryPrompt({
+          id: session.sessionDbId,
+          sdk_session_id: session.sdkSessionId,
+          project: session.project,
+          user_prompt: session.userPrompt,
+          last_user_message: message.last_user_message || '',
+          last_assistant_message: message.last_assistant_message || ''
+        }, mode);
+
+        // Add to shared conversation history for provider interop
+        session.conversationHistory.push({ role: 'user', content: summaryPrompt });
+
         yield {
           type: 'user',
           message: {
             role: 'user',
-            content: buildSummaryPrompt({
-              id: session.sessionDbId,
-              sdk_session_id: session.sdkSessionId,
-              project: session.project,
-              user_prompt: session.userPrompt,
-              last_user_message: message.last_user_message || '',
-              last_assistant_message: message.last_assistant_message || ''
-            }, mode)
+            content: summaryPrompt
           },
           session_id: session.claudeSessionId,
           parent_tool_use_id: null,
@@ -256,8 +277,16 @@ export class SDKAgent {
    * Process SDK response text (parse XML, save to database, sync to Chroma)
    * @param discoveryTokens - Token cost for discovering this response (delta, not cumulative)
    * @param originalTimestamp - Original epoch when message was queued (for backlog processing accuracy)
+   *
+   * Also captures assistant responses to shared conversation history for provider interop.
+   * This allows Gemini to see full context if provider is switched mid-session.
    */
   private async processSDKResponse(session: ActiveSession, text: string, worker: any | undefined, discoveryTokens: number, originalTimestamp: number | null): Promise<void> {
+    // Add assistant response to shared conversation history for provider interop
+    if (text) {
+      session.conversationHistory.push({ role: 'assistant', content: text });
+    }
+
     // Parse observations
     const observations = parseObservations(text, session.claudeSessionId);
 

src/services/worker/SessionManager.ts

@@ -118,7 +118,9 @@ export class SessionManager {
       cumulativeInputTokens: 0,
       cumulativeOutputTokens: 0,
       pendingProcessingIds: new Set(),
-      earliestPendingTimestamp: null
+      earliestPendingTimestamp: null,
+      conversationHistory: [],  // Initialize empty - will be populated by agents
+      currentProvider: null  // Will be set when generator starts
     };
 
     this.sessions.set(sessionDbId, session);

src/services/worker/http/routes/SessionRoutes.ts

@@ -12,6 +12,8 @@ import { stripMemoryTagsFromJson, stripMemoryTagsFromPrompt } from '../../../../
 import { SessionManager } from '../../SessionManager.js';
 import { DatabaseManager } from '../../DatabaseManager.js';
 import { SDKAgent } from '../../SDKAgent.js';
+import { GeminiAgent, isGeminiSelected, isGeminiAvailable } from '../../GeminiAgent.js';
+import { OpenRouterAgent, isOpenRouterSelected, isOpenRouterAvailable } from '../../OpenRouterAgent.js';
 import type { WorkerService } from '../../../worker-service.js';
 import { BaseRouteHandler } from '../BaseRouteHandler.js';
 import { SessionEventBroadcaster } from '../../events/SessionEventBroadcaster.js';
@@ -27,6 +29,8 @@ export class SessionRoutes extends BaseRouteHandler {
     private sessionManager: SessionManager,
     private dbManager: DatabaseManager,
     private sdkAgent: SDKAgent,
+    private geminiAgent: GeminiAgent,
+    private openRouterAgent: OpenRouterAgent,
     private eventBroadcaster: SessionEventBroadcaster,
     private workerService: WorkerService
   ) {
@@ -38,24 +42,112 @@ export class SessionRoutes extends BaseRouteHandler {
   }
 
   /**
-   * Ensures SDK agent generator is running for a session
+   * Get the appropriate agent based on settings
+   * Throws error if provider is selected but not configured (no silent fallback)
+   *
+   * Note: Session linking via claudeSessionId allows provider switching mid-session.
+   * The conversationHistory on ActiveSession maintains context across providers.
+   */
+  private getActiveAgent(): SDKAgent | GeminiAgent | OpenRouterAgent {
+    if (isOpenRouterSelected()) {
+      if (isOpenRouterAvailable()) {
+        logger.debug('SESSION', 'Using OpenRouter agent');
+        return this.openRouterAgent;
+      } else {
+        throw new Error('OpenRouter provider selected but no API key configured. Set CLAUDE_MEM_OPENROUTER_API_KEY in settings or OPENROUTER_API_KEY environment variable.');
+      }
+    }
+    if (isGeminiSelected()) {
+      if (isGeminiAvailable()) {
+        logger.debug('SESSION', 'Using Gemini agent');
+        return this.geminiAgent;
+      } else {
+        throw new Error('Gemini provider selected but no API key configured. Set CLAUDE_MEM_GEMINI_API_KEY in settings or GEMINI_API_KEY environment variable.');
+      }
+    }
+    return this.sdkAgent;
+  }
+
+  /**
+   * Get the currently selected provider name
+   */
+  private getSelectedProvider(): 'claude' | 'gemini' | 'openrouter' {
+    if (isOpenRouterSelected() && isOpenRouterAvailable()) {
+      return 'openrouter';
+    }
+    return (isGeminiSelected() && isGeminiAvailable()) ? 'gemini' : 'claude';
+  }
+
+  /**
+   * Ensures agent generator is running for a session
    * Auto-starts if not already running to process pending queue
+   * Uses either Claude SDK or Gemini based on settings
+   *
+   * Provider switching: If provider setting changed while generator is running,
+   * we let the current generator finish naturally (max 5s linger timeout).
+   * The next generator will use the new provider with shared conversationHistory.
    */
   private ensureGeneratorRunning(sessionDbId: number, source: string): void {
     const session = this.sessionManager.getSession(sessionDbId);
-    if (session && !session.generatorPromise) {
-      logger.info('SESSION', `Generator auto-starting (${source})`, {
-        sessionId: sessionDbId,
-        queueDepth: session.pendingMessages.length
-      });
+    if (!session) return;
 
-      session.generatorPromise = this.sdkAgent.startSession(session, this.workerService)
-        .finally(() => {
-          logger.info('SESSION', `Generator finished`, { sessionId: sessionDbId });
-          session.generatorPromise = null;
-          this.workerService.broadcastProcessingStatus();
-        });
+    const selectedProvider = this.getSelectedProvider();
+
+    // Start generator if not running
+    if (!session.generatorPromise) {
+      this.startGeneratorWithProvider(session, selectedProvider, source);
+      return;
     }
+
+    // Generator is running - check if provider changed
+    if (session.currentProvider && session.currentProvider !== selectedProvider) {
+      logger.info('SESSION', `Provider changed, will switch after current generator finishes`, {
+        sessionId: sessionDbId,
+        currentProvider: session.currentProvider,
+        selectedProvider,
+        historyLength: session.conversationHistory.length
+      });
+      // Let current generator finish naturally, next one will use new provider
+      // The shared conversationHistory ensures context is preserved
+    }
+  }
+
+  /**
+   * Start a generator with the specified provider
+   */
+  private startGeneratorWithProvider(
+    session: ReturnType<typeof this.sessionManager.getSession>,
+    provider: 'claude' | 'gemini' | 'openrouter',
+    source: string
+  ): void {
+    if (!session) return;
+
+    const agent = provider === 'openrouter' ? this.openRouterAgent : (provider === 'gemini' ? this.geminiAgent : this.sdkAgent);
+    const agentName = provider === 'openrouter' ? 'OpenRouter' : (provider === 'gemini' ? 'Gemini' : 'Claude SDK');
+
+    logger.info('SESSION', `Generator auto-starting (${source}) using ${agentName}`, {
+      sessionId: session.sessionDbId,
+      queueDepth: session.pendingMessages.length,
+      historyLength: session.conversationHistory.length
+    });
+
+    // Track which provider is running
+    session.currentProvider = provider;
+
+    session.generatorPromise = agent.startSession(session, this.workerService)
+      .catch(error => {
+        logger.error('SESSION', `Generator failed`, {
+          sessionId: session.sessionDbId,
+          provider: provider,
+          error: error.message
+        }, error);
+      })
+      .finally(() => {
+        logger.info('SESSION', `Generator finished`, { sessionId: session.sessionDbId });
+        session.generatorPromise = null;
+        session.currentProvider = null;
+        this.workerService.broadcastProcessingStatus();
+      });
   }
 
   setupRoutes(app: express.Application): void {
@@ -125,21 +217,8 @@ export class SessionRoutes extends BaseRouteHandler {
       });
     }
 
-    // Start SDK agent in background (pass worker ref for spinner control)
-    logger.info('SESSION', 'Generator starting', {
-      sessionId: sessionDbId,
-      project: session.project,
-      promptNum: session.lastPromptNumber
-    });
-
-    session.generatorPromise = this.sdkAgent.startSession(session, this.workerService)
-      .finally(() => {
-        // Clear generator reference when completed
-        logger.info('SESSION', `Generator finished`, { sessionId: sessionDbId });
-        session.generatorPromise = null;
-        // Broadcast status change (generator finished, may stop spinner)
-        this.workerService.broadcastProcessingStatus();
-      });
+    // Start agent in background using the helper method
+    this.startGeneratorWithProvider(session, this.getSelectedProvider(), 'init');
 
     // Broadcast session started event
     this.eventBroadcaster.broadcastSessionStarted(sessionDbId, session.project);

src/services/worker/http/routes/SettingsRoutes.ts

@@ -71,7 +71,16 @@ export class SettingsRoutes extends BaseRouteHandler {
 
     if (existsSync(settingsPath)) {
       const settingsData = readFileSync(settingsPath, 'utf-8');
-      settings = JSON.parse(settingsData);
+      try {
+        settings = JSON.parse(settingsData);
+      } catch (parseError) {
+        logger.error('SETTINGS', 'Failed to parse settings file', { settingsPath }, parseError as Error);
+        res.status(500).json({
+          success: false,
+          error: 'Settings file is corrupted. Delete ~/.claude-mem/settings.json to reset.'
+        });
+        return;
+      }
     }
 
     // Update all settings from request body
@@ -80,6 +89,18 @@ export class SettingsRoutes extends BaseRouteHandler {
       'CLAUDE_MEM_CONTEXT_OBSERVATIONS',
       'CLAUDE_MEM_WORKER_PORT',
       'CLAUDE_MEM_WORKER_HOST',
+      // AI Provider Configuration
+      'CLAUDE_MEM_PROVIDER',
+      'CLAUDE_MEM_GEMINI_API_KEY',
+      'CLAUDE_MEM_GEMINI_MODEL',
+      'CLAUDE_MEM_GEMINI_RATE_LIMITING_ENABLED',
+      // OpenRouter Configuration
+      'CLAUDE_MEM_OPENROUTER_API_KEY',
+      'CLAUDE_MEM_OPENROUTER_MODEL',
+      'CLAUDE_MEM_OPENROUTER_SITE_URL',
+      'CLAUDE_MEM_OPENROUTER_APP_NAME',
+      'CLAUDE_MEM_OPENROUTER_MAX_CONTEXT_MESSAGES',
+      'CLAUDE_MEM_OPENROUTER_MAX_TOKENS',
       // System Configuration
       'CLAUDE_MEM_DATA_DIR',
       'CLAUDE_MEM_LOG_LEVEL',
@@ -210,6 +231,22 @@ export class SettingsRoutes extends BaseRouteHandler {
    * Validate all settings from request body (single source of truth)
    */
   private validateSettings(settings: any): { valid: boolean; error?: string } {
+    // Validate CLAUDE_MEM_PROVIDER
+    if (settings.CLAUDE_MEM_PROVIDER) {
+    const validProviders = ['claude', 'gemini', 'openrouter'];
+    if (!validProviders.includes(settings.CLAUDE_MEM_PROVIDER)) {
+      return { valid: false, error: 'CLAUDE_MEM_PROVIDER must be "claude", "gemini", or "openrouter"' };
+      }
+    }
+
+    // Validate CLAUDE_MEM_GEMINI_MODEL
+    if (settings.CLAUDE_MEM_GEMINI_MODEL) {
+      const validGeminiModels = ['gemini-2.5-flash-lite', 'gemini-2.5-flash', 'gemini-3-flash'];
+      if (!validGeminiModels.includes(settings.CLAUDE_MEM_GEMINI_MODEL)) {
+        return { valid: false, error: 'CLAUDE_MEM_GEMINI_MODEL must be one of: gemini-2.5-flash-lite, gemini-2.5-flash, gemini-3-flash' };
+      }
+    }
+
     // Validate CLAUDE_MEM_CONTEXT_OBSERVATIONS
     if (settings.CLAUDE_MEM_CONTEXT_OBSERVATIONS) {
       const obsCount = parseInt(settings.CLAUDE_MEM_CONTEXT_OBSERVATIONS, 10);
@@ -291,6 +328,31 @@ export class SettingsRoutes extends BaseRouteHandler {
       }
     }
 
+    // Validate CLAUDE_MEM_OPENROUTER_MAX_CONTEXT_MESSAGES
+    if (settings.CLAUDE_MEM_OPENROUTER_MAX_CONTEXT_MESSAGES) {
+      const count = parseInt(settings.CLAUDE_MEM_OPENROUTER_MAX_CONTEXT_MESSAGES, 10);
+      if (isNaN(count) || count < 1 || count > 100) {
+        return { valid: false, error: 'CLAUDE_MEM_OPENROUTER_MAX_CONTEXT_MESSAGES must be between 1 and 100' };
+      }
+    }
+
+    // Validate CLAUDE_MEM_OPENROUTER_MAX_TOKENS
+    if (settings.CLAUDE_MEM_OPENROUTER_MAX_TOKENS) {
+      const tokens = parseInt(settings.CLAUDE_MEM_OPENROUTER_MAX_TOKENS, 10);
+      if (isNaN(tokens) || tokens < 1000 || tokens > 1000000) {
+        return { valid: false, error: 'CLAUDE_MEM_OPENROUTER_MAX_TOKENS must be between 1000 and 1000000' };
+      }
+    }
+
+    // Validate CLAUDE_MEM_OPENROUTER_SITE_URL if provided
+    if (settings.CLAUDE_MEM_OPENROUTER_SITE_URL) {
+      try {
+        new URL(settings.CLAUDE_MEM_OPENROUTER_SITE_URL);
+      } catch {
+        return { valid: false, error: 'CLAUDE_MEM_OPENROUTER_SITE_URL must be a valid URL' };
+      }
+    }
+
     // Skip observation types validation - any type string is valid since modes define their own types
     // The database accepts any TEXT value, and mode-specific validation happens at parse time
 

src/shared/SettingsDefaultsManager.ts

@@ -17,6 +17,17 @@ export interface SettingsDefaults {
   CLAUDE_MEM_WORKER_PORT: string;
   CLAUDE_MEM_WORKER_HOST: string;
   CLAUDE_MEM_SKIP_TOOLS: string;
+  // AI Provider Configuration
+  CLAUDE_MEM_PROVIDER: string;  // 'claude' | 'gemini' | 'openrouter'
+  CLAUDE_MEM_GEMINI_API_KEY: string;
+  CLAUDE_MEM_GEMINI_MODEL: string;  // 'gemini-2.5-flash-lite' | 'gemini-2.5-flash' | 'gemini-3-flash'
+  CLAUDE_MEM_GEMINI_RATE_LIMITING_ENABLED: string;  // 'true' | 'false' - enable rate limiting for free tier
+  CLAUDE_MEM_OPENROUTER_API_KEY: string;
+  CLAUDE_MEM_OPENROUTER_MODEL: string;
+  CLAUDE_MEM_OPENROUTER_SITE_URL: string;
+  CLAUDE_MEM_OPENROUTER_APP_NAME: string;
+  CLAUDE_MEM_OPENROUTER_MAX_CONTEXT_MESSAGES: string;
+  CLAUDE_MEM_OPENROUTER_MAX_TOKENS: string;
   // System Configuration
   CLAUDE_MEM_DATA_DIR: string;
   CLAUDE_MEM_LOG_LEVEL: string;
@@ -50,6 +61,17 @@ export class SettingsDefaultsManager {
     CLAUDE_MEM_WORKER_PORT: '37777',
     CLAUDE_MEM_WORKER_HOST: '127.0.0.1',
     CLAUDE_MEM_SKIP_TOOLS: 'ListMcpResourcesTool,SlashCommand,Skill,TodoWrite,AskUserQuestion',
+    // AI Provider Configuration
+    CLAUDE_MEM_PROVIDER: 'claude',  // Default to Claude
+    CLAUDE_MEM_GEMINI_API_KEY: '',  // Empty by default, can be set via UI or env
+    CLAUDE_MEM_GEMINI_MODEL: 'gemini-2.5-flash-lite',  // Default Gemini model (highest free tier RPM)
+    CLAUDE_MEM_GEMINI_RATE_LIMITING_ENABLED: 'true',  // Rate limiting ON by default for free tier users
+    CLAUDE_MEM_OPENROUTER_API_KEY: '',  // Empty by default, can be set via UI or env
+    CLAUDE_MEM_OPENROUTER_MODEL: 'xiaomi/mimo-v2-flash:free',  // Default OpenRouter model (free tier)
+    CLAUDE_MEM_OPENROUTER_SITE_URL: '',  // Optional: for OpenRouter analytics
+    CLAUDE_MEM_OPENROUTER_APP_NAME: 'claude-mem',  // App name for OpenRouter analytics
+    CLAUDE_MEM_OPENROUTER_MAX_CONTEXT_MESSAGES: '20',  // Max messages in context window
+    CLAUDE_MEM_OPENROUTER_MAX_TOKENS: '100000',  // Max estimated tokens (~100k safety limit)
     // System Configuration
     CLAUDE_MEM_DATA_DIR: join(homedir(), '.claude-mem'),
     CLAUDE_MEM_LOG_LEVEL: 'INFO',

src/shared/hook-constants.ts

@@ -1,8 +1,8 @@
 export const HOOK_TIMEOUTS = {
-  DEFAULT: 120000,            // Standard HTTP timeout (up from 2000ms)
-  HEALTH_CHECK: 1000,         // Worker health check (up from 500ms)
+  DEFAULT: 300000,            // Standard HTTP timeout (5 min for slow systems)
+  HEALTH_CHECK: 30000,        // Worker health check (30s for slow systems)
   WORKER_STARTUP_WAIT: 1000,
-  WORKER_STARTUP_RETRIES: 15,
+  WORKER_STARTUP_RETRIES: 300,
   PRE_RESTART_SETTLE_DELAY: 2000,  // Give files time to sync before restart
   WINDOWS_MULTIPLIER: 1.5     // Platform-specific adjustment
 } as const;

src/ui/viewer-template.html

@@ -1817,6 +1817,49 @@
       min-height: 0;
     }
 
+    .modal-footer {
+      display: flex;
+      justify-content: flex-end;
+      align-items: center;
+      gap: 16px;
+      padding: 16px 24px;
+      border-top: 1px solid var(--modal-border);
+      background: var(--modal-header-bg);
+    }
+
+    .modal-footer .save-status {
+      font-size: 13px;
+    }
+
+    .modal-footer .save-status .success {
+      color: var(--success-color, #22c55e);
+    }
+
+    .modal-footer .save-status .error {
+      color: var(--error-color, #ef4444);
+    }
+
+    .modal-footer .save-btn {
+      padding: 8px 24px;
+      background: var(--accent-color, #3b82f6);
+      color: white;
+      border: none;
+      border-radius: 6px;
+      font-size: 14px;
+      font-weight: 500;
+      cursor: pointer;
+      transition: background 0.15s ease;
+    }
+
+    .modal-footer .save-btn:hover:not(:disabled) {
+      background: var(--accent-hover, #2563eb);
+    }
+
+    .modal-footer .save-btn:disabled {
+      opacity: 0.6;
+      cursor: not-allowed;
+    }
+
     /* Preview Column - Terminal Style */
     .preview-column {
       padding: 20px;

src/ui/viewer/components/ContextSettingsModal.tsx

@@ -12,15 +12,6 @@ interface ContextSettingsModalProps {
   saveStatus: string;
 }
 
-// Simple debounce helper
-function debounce<T extends (...args: any[]) => any>(fn: T, ms: number): T {
-  let timeoutId: NodeJS.Timeout;
-  return ((...args: any[]) => {
-    clearTimeout(timeoutId);
-    timeoutId = setTimeout(() => fn(...args), ms);
-  }) as T;
-}
-
 // Collapsible section component
 function CollapsibleSection({
   title,
@@ -195,14 +186,6 @@ export function ContextSettingsModal({
 }: ContextSettingsModalProps) {
   const [formState, setFormState] = useState<Settings>(settings);
 
-  // Create debounced save function
-  const debouncedSave = useCallback(
-    debounce((newSettings: Settings) => {
-      onSave(newSettings);
-    }, 300),
-    [onSave]
-  );
-
   // Update form state when settings prop changes
   useEffect(() => {
     setFormState(settings);
@@ -214,8 +197,11 @@ export function ContextSettingsModal({
   const updateSetting = useCallback((key: keyof Settings, value: string) => {
     const newState = { ...formState, [key]: value };
     setFormState(newState);
-    debouncedSave(newState);
-  }, [formState, debouncedSave]);
+  }, [formState]);
+
+  const handleSave = useCallback(() => {
+    onSave(formState);
+  }, [formState, onSave]);
 
   const toggleBoolean = useCallback((key: keyof Settings) => {
     const currentValue = formState[key];
@@ -423,24 +409,126 @@ export function ContextSettingsModal({
             {/* Section 4: Advanced */}
             <CollapsibleSection
               title="Advanced"
-              description="Model selection and integrations"
+              description="AI provider and model selection"
               defaultOpen={false}
             >
               <FormField
-                label="Model"
-                tooltip="AI model used for generating observations"
+                label="AI Provider"
+                tooltip="Choose between Claude (via Agent SDK) or Gemini (via REST API)"
               >
                 <select
-                  value={formState.CLAUDE_MEM_MODEL || 'haiku'}
-                  onChange={(e) => updateSetting('CLAUDE_MEM_MODEL', e.target.value)}
+                  value={formState.CLAUDE_MEM_PROVIDER || 'claude'}
+                  onChange={(e) => updateSetting('CLAUDE_MEM_PROVIDER', e.target.value)}
                 >
-                  {/* Shorthand names forward to latest model version */}
-                  <option value="haiku">haiku (fastest)</option>
-                  <option value="sonnet">sonnet (balanced)</option>
-                  <option value="opus">opus (highest quality)</option>
+                  <option value="claude">Claude (uses your Claude account)</option>
+                  <option value="gemini">Gemini (uses API key)</option>
+                  <option value="openrouter">OpenRouter (multi-model)</option>
                 </select>
               </FormField>
 
+              {formState.CLAUDE_MEM_PROVIDER === 'claude' && (
+                <FormField
+                  label="Claude Model"
+                  tooltip="Claude model used for generating observations"
+                >
+                  <select
+                    value={formState.CLAUDE_MEM_MODEL || 'haiku'}
+                    onChange={(e) => updateSetting('CLAUDE_MEM_MODEL', e.target.value)}
+                  >
+                    <option value="haiku">haiku (fastest)</option>
+                    <option value="sonnet">sonnet (balanced)</option>
+                    <option value="opus">opus (highest quality)</option>
+                  </select>
+                </FormField>
+              )}
+
+              {formState.CLAUDE_MEM_PROVIDER === 'gemini' && (
+                <>
+                  <FormField
+                    label="Gemini API Key"
+                    tooltip="Your Google AI Studio API key (or set GEMINI_API_KEY env var)"
+                  >
+                    <input
+                      type="password"
+                      value={formState.CLAUDE_MEM_GEMINI_API_KEY || ''}
+                      onChange={(e) => updateSetting('CLAUDE_MEM_GEMINI_API_KEY', e.target.value)}
+                      placeholder="Enter Gemini API key..."
+                    />
+                  </FormField>
+                  <FormField
+                    label="Gemini Model"
+                    tooltip="Gemini model used for generating observations"
+                  >
+                    <select
+                      value={formState.CLAUDE_MEM_GEMINI_MODEL || 'gemini-2.5-flash-lite'}
+                      onChange={(e) => updateSetting('CLAUDE_MEM_GEMINI_MODEL', e.target.value)}
+                    >
+                      <option value="gemini-2.5-flash-lite">gemini-2.5-flash-lite (10 RPM free)</option>
+                      <option value="gemini-2.5-flash">gemini-2.5-flash (5 RPM free)</option>
+                      <option value="gemini-3-flash">gemini-3-flash (5 RPM free)</option>
+                    </select>
+                  </FormField>
+                  <div className="toggle-group" style={{ marginTop: '8px' }}>
+                    <ToggleSwitch
+                      id="gemini-rate-limiting"
+                      label="Rate Limiting"
+                      description="Enable for free tier (10-30 RPM). Disable if you have billing set up (1000+ RPM)."
+                      checked={formState.CLAUDE_MEM_GEMINI_RATE_LIMITING_ENABLED === 'true'}
+                      onChange={(checked) => updateSetting('CLAUDE_MEM_GEMINI_RATE_LIMITING_ENABLED', checked ? 'true' : 'false')}
+                    />
+                  </div>
+                </>
+              )}
+
+              {formState.CLAUDE_MEM_PROVIDER === 'openrouter' && (
+                <>
+                  <FormField
+                    label="OpenRouter API Key"
+                    tooltip="Your OpenRouter API key from openrouter.ai (or set OPENROUTER_API_KEY env var)"
+                  >
+                    <input
+                      type="password"
+                      value={formState.CLAUDE_MEM_OPENROUTER_API_KEY || ''}
+                      onChange={(e) => updateSetting('CLAUDE_MEM_OPENROUTER_API_KEY', e.target.value)}
+                      placeholder="Enter OpenRouter API key..."
+                    />
+                  </FormField>
+                  <FormField
+                    label="OpenRouter Model"
+                    tooltip="Model identifier from OpenRouter (e.g., anthropic/claude-3.5-sonnet, google/gemini-2.0-flash-thinking-exp)"
+                  >
+                    <input
+                      type="text"
+                      value={formState.CLAUDE_MEM_OPENROUTER_MODEL || 'xiaomi/mimo-v2-flash:free'}
+                      onChange={(e) => updateSetting('CLAUDE_MEM_OPENROUTER_MODEL', e.target.value)}
+                      placeholder="e.g., xiaomi/mimo-v2-flash:free"
+                    />
+                  </FormField>
+                  <FormField
+                    label="Site URL (Optional)"
+                    tooltip="Your site URL for OpenRouter analytics (optional)"
+                  >
+                    <input
+                      type="text"
+                      value={formState.CLAUDE_MEM_OPENROUTER_SITE_URL || ''}
+                      onChange={(e) => updateSetting('CLAUDE_MEM_OPENROUTER_SITE_URL', e.target.value)}
+                      placeholder="https://yoursite.com"
+                    />
+                  </FormField>
+                  <FormField
+                    label="App Name (Optional)"
+                    tooltip="Your app name for OpenRouter analytics (optional)"
+                  >
+                    <input
+                      type="text"
+                      value={formState.CLAUDE_MEM_OPENROUTER_APP_NAME || 'claude-mem'}
+                      onChange={(e) => updateSetting('CLAUDE_MEM_OPENROUTER_APP_NAME', e.target.value)}
+                      placeholder="claude-mem"
+                    />
+                  </FormField>
+                </>
+              )}
+
               <FormField
                 label="Worker Port"
                 tooltip="Port for the background worker service"
@@ -473,6 +561,20 @@ export function ContextSettingsModal({
             </CollapsibleSection>
           </div>
         </div>
+
+        {/* Footer with Save button */}
+        <div className="modal-footer">
+          <div className="save-status">
+            {saveStatus && <span className={saveStatus.includes('✓') ? 'success' : saveStatus.includes('✗') ? 'error' : ''}>{saveStatus}</span>}
+          </div>
+          <button
+            className="save-btn"
+            onClick={handleSave}
+            disabled={isSaving}
+          >
+            {isSaving ? 'Saving...' : 'Save'}
+          </button>
+        </div>
       </div>
     </div>
   );

src/ui/viewer/components/Header.tsx

@@ -2,6 +2,7 @@ import React from 'react';
 import { ThemeToggle } from './ThemeToggle';
 import { ThemePreference } from '../hooks/useTheme';
 import { GitHubStarsButton } from './GitHubStarsButton';
+import { useSpinningFavicon } from '../hooks/useSpinningFavicon';
 
 interface HeaderProps {
   isConnected: boolean;
@@ -26,6 +27,8 @@ export function Header({
   onThemeChange,
   onContextPreviewToggle
 }: HeaderProps) {
+  useSpinningFavicon(isProcessing);
+
   return (
     <div className="header">
       <h1>

src/ui/viewer/constants/settings.ts

@@ -8,6 +8,16 @@ export const DEFAULT_SETTINGS = {
   CLAUDE_MEM_WORKER_PORT: '37777',
   CLAUDE_MEM_WORKER_HOST: '127.0.0.1',
 
+  // AI Provider Configuration
+  CLAUDE_MEM_PROVIDER: 'claude',
+  CLAUDE_MEM_GEMINI_API_KEY: '',
+  CLAUDE_MEM_GEMINI_MODEL: 'gemini-2.5-flash-lite',
+  CLAUDE_MEM_OPENROUTER_API_KEY: '',
+  CLAUDE_MEM_OPENROUTER_MODEL: 'xiaomi/mimo-v2-flash:free',
+  CLAUDE_MEM_OPENROUTER_SITE_URL: '',
+  CLAUDE_MEM_OPENROUTER_APP_NAME: 'claude-mem',
+  CLAUDE_MEM_GEMINI_RATE_LIMITING_ENABLED: 'true',
+
   // Token Economics (all true for backwards compatibility)
   CLAUDE_MEM_CONTEXT_SHOW_READ_TOKENS: 'true',
   CLAUDE_MEM_CONTEXT_SHOW_WORK_TOKENS: 'true',

src/ui/viewer/hooks/useSettings.ts

@@ -20,6 +20,18 @@ export function useSettings() {
           CLAUDE_MEM_WORKER_PORT: data.CLAUDE_MEM_WORKER_PORT || DEFAULT_SETTINGS.CLAUDE_MEM_WORKER_PORT,
           CLAUDE_MEM_WORKER_HOST: data.CLAUDE_MEM_WORKER_HOST || DEFAULT_SETTINGS.CLAUDE_MEM_WORKER_HOST,
 
+          // AI Provider Configuration
+          CLAUDE_MEM_PROVIDER: data.CLAUDE_MEM_PROVIDER || DEFAULT_SETTINGS.CLAUDE_MEM_PROVIDER,
+          CLAUDE_MEM_GEMINI_API_KEY: data.CLAUDE_MEM_GEMINI_API_KEY || DEFAULT_SETTINGS.CLAUDE_MEM_GEMINI_API_KEY,
+          CLAUDE_MEM_GEMINI_MODEL: data.CLAUDE_MEM_GEMINI_MODEL || DEFAULT_SETTINGS.CLAUDE_MEM_GEMINI_MODEL,
+          CLAUDE_MEM_GEMINI_RATE_LIMITING_ENABLED: data.CLAUDE_MEM_GEMINI_RATE_LIMITING_ENABLED || DEFAULT_SETTINGS.CLAUDE_MEM_GEMINI_RATE_LIMITING_ENABLED,
+
+          // OpenRouter Configuration
+          CLAUDE_MEM_OPENROUTER_API_KEY: data.CLAUDE_MEM_OPENROUTER_API_KEY || DEFAULT_SETTINGS.CLAUDE_MEM_OPENROUTER_API_KEY,
+          CLAUDE_MEM_OPENROUTER_MODEL: data.CLAUDE_MEM_OPENROUTER_MODEL || DEFAULT_SETTINGS.CLAUDE_MEM_OPENROUTER_MODEL,
+          CLAUDE_MEM_OPENROUTER_SITE_URL: data.CLAUDE_MEM_OPENROUTER_SITE_URL || DEFAULT_SETTINGS.CLAUDE_MEM_OPENROUTER_SITE_URL,
+          CLAUDE_MEM_OPENROUTER_APP_NAME: data.CLAUDE_MEM_OPENROUTER_APP_NAME || DEFAULT_SETTINGS.CLAUDE_MEM_OPENROUTER_APP_NAME,
+
           // Token Economics Display
           CLAUDE_MEM_CONTEXT_SHOW_READ_TOKENS: data.CLAUDE_MEM_CONTEXT_SHOW_READ_TOKENS || DEFAULT_SETTINGS.CLAUDE_MEM_CONTEXT_SHOW_READ_TOKENS,
           CLAUDE_MEM_CONTEXT_SHOW_WORK_TOKENS: data.CLAUDE_MEM_CONTEXT_SHOW_WORK_TOKENS || DEFAULT_SETTINGS.CLAUDE_MEM_CONTEXT_SHOW_WORK_TOKENS,

src/ui/viewer/hooks/useSpinningFavicon.ts

@@ -0,0 +1,93 @@
+import { useEffect, useRef } from 'react';
+
+/**
+ * Hook that makes the browser tab favicon spin when isProcessing is true.
+ * Uses canvas to rotate the logo image and dynamically update the favicon.
+ */
+export function useSpinningFavicon(isProcessing: boolean) {
+  const animationRef = useRef<number | null>(null);
+  const canvasRef = useRef<HTMLCanvasElement | null>(null);
+  const imageRef = useRef<HTMLImageElement | null>(null);
+  const rotationRef = useRef(0);
+  const originalFaviconRef = useRef<string | null>(null);
+
+  useEffect(() => {
+    // Create canvas once
+    if (!canvasRef.current) {
+      canvasRef.current = document.createElement('canvas');
+      canvasRef.current.width = 32;
+      canvasRef.current.height = 32;
+    }
+
+    // Load image once
+    if (!imageRef.current) {
+      imageRef.current = new Image();
+      imageRef.current.src = 'claude-mem-logomark.webp';
+    }
+
+    // Store original favicon
+    if (!originalFaviconRef.current) {
+      const link = document.querySelector<HTMLLinkElement>('link[rel="icon"]');
+      if (link) {
+        originalFaviconRef.current = link.href;
+      }
+    }
+
+    const canvas = canvasRef.current;
+    const ctx = canvas.getContext('2d');
+    const image = imageRef.current;
+
+    if (!ctx) return;
+
+    const updateFavicon = (dataUrl: string) => {
+      let link = document.querySelector<HTMLLinkElement>('link[rel="icon"]');
+      if (!link) {
+        link = document.createElement('link');
+        link.rel = 'icon';
+        document.head.appendChild(link);
+      }
+      link.href = dataUrl;
+    };
+
+    const animate = () => {
+      if (!image.complete) {
+        animationRef.current = requestAnimationFrame(animate);
+        return;
+      }
+
+      // Rotate by ~4 degrees per frame (matches 1.5s for full rotation at 60fps)
+      rotationRef.current += (2 * Math.PI) / 90;
+
+      ctx.clearRect(0, 0, 32, 32);
+      ctx.save();
+      ctx.translate(16, 16);
+      ctx.rotate(rotationRef.current);
+      ctx.drawImage(image, -16, -16, 32, 32);
+      ctx.restore();
+
+      updateFavicon(canvas.toDataURL('image/png'));
+      animationRef.current = requestAnimationFrame(animate);
+    };
+
+    if (isProcessing) {
+      rotationRef.current = 0;
+      animate();
+    } else {
+      // Stop animation and restore original favicon
+      if (animationRef.current) {
+        cancelAnimationFrame(animationRef.current);
+        animationRef.current = null;
+      }
+      if (originalFaviconRef.current) {
+        updateFavicon(originalFaviconRef.current);
+      }
+    }
+
+    return () => {
+      if (animationRef.current) {
+        cancelAnimationFrame(animationRef.current);
+        animationRef.current = null;
+      }
+    };
+  }, [isProcessing]);
+}

src/ui/viewer/types.ts

@@ -60,6 +60,16 @@ export interface Settings {
   CLAUDE_MEM_WORKER_PORT: string;
   CLAUDE_MEM_WORKER_HOST: string;
 
+  // AI Provider Configuration
+  CLAUDE_MEM_PROVIDER?: string;  // 'claude' | 'gemini' | 'openrouter'
+  CLAUDE_MEM_GEMINI_API_KEY?: string;
+  CLAUDE_MEM_GEMINI_MODEL?: string;  // 'gemini-2.5-flash-lite' | 'gemini-2.5-flash' | 'gemini-3-flash'
+  CLAUDE_MEM_GEMINI_RATE_LIMITING_ENABLED?: string;  // 'true' | 'false'
+  CLAUDE_MEM_OPENROUTER_API_KEY?: string;
+  CLAUDE_MEM_OPENROUTER_MODEL?: string;
+  CLAUDE_MEM_OPENROUTER_SITE_URL?: string;
+  CLAUDE_MEM_OPENROUTER_APP_NAME?: string;
+
   // Token Economics Display
   CLAUDE_MEM_CONTEXT_SHOW_READ_TOKENS?: string;
   CLAUDE_MEM_CONTEXT_SHOW_WORK_TOKENS?: string;

src/utils/error-messages.ts

@@ -31,7 +31,7 @@ export function getWorkerRestartInstructions(
   let message = `${prefix}${portInfo}\n\n`;
   message += `To restart the worker:\n`;
   message += `1. Exit Claude Code completely\n`;
-  message += `2. Run: claude-mem restart\n`;
+  message += `2. Run: npm run worker:restart\n`;
   message += `3. Restart Claude Code`;
 
   if (includeSkillFallback) {

tests/gemini_agent.test.ts

@@ -0,0 +1,298 @@
+import { describe, it, expect, beforeEach, afterEach, spyOn, mock } from 'bun:test';
+import { GeminiAgent } from '../src/services/worker/GeminiAgent';
+import { DatabaseManager } from '../src/services/worker/DatabaseManager';
+import { SessionManager } from '../src/services/worker/SessionManager';
+import { ModeManager } from '../src/services/worker/domain/ModeManager';
+import { SettingsDefaultsManager } from '../src/shared/SettingsDefaultsManager';
+
+let billingEnabled = 'true';
+
+// Mock SettingsDefaultsManager
+mock.module('../src/shared/SettingsDefaultsManager', () => ({
+  SettingsDefaultsManager: {
+    loadFromFile: () => ({
+      CLAUDE_MEM_GEMINI_API_KEY: 'test-api-key',
+      CLAUDE_MEM_GEMINI_MODEL: 'gemini-2.5-flash-lite',
+      CLAUDE_MEM_GEMINI_BILLING_ENABLED: billingEnabled
+    }),
+    get: (key: string) => {
+      if (key === 'CLAUDE_MEM_LOG_LEVEL') return 'INFO';
+      return '';
+    }
+  }
+}));
+
+// Mock ModeManager
+const mockMode = {
+  name: 'code',
+  prompts: {
+    init: 'init prompt',
+    observation: 'obs prompt',
+    summary: 'summary prompt'
+  },
+  observation_types: [{ id: 'discovery' }, { id: 'bugfix' }],
+  observation_concepts: []
+};
+
+mock.module('../src/services/domain/ModeManager', () => ({
+  ModeManager: {
+    getInstance: () => ({
+      getActiveMode: () => mockMode
+    })
+  }
+}));
+
+describe('GeminiAgent', () => {
+  let agent: GeminiAgent;
+  let originalFetch: typeof global.fetch;
+
+  // Mocks
+  let mockStoreObservation: any;
+  let mockStoreSummary: any;
+  let mockMarkSessionCompleted: any;
+  let mockSyncObservation: any;
+  let mockSyncSummary: any;
+  let mockMarkProcessed: any;
+  let mockCleanupProcessed: any;
+  let mockResetStuckMessages: any;
+  let mockDbManager: DatabaseManager;
+  let mockSessionManager: SessionManager;
+
+  beforeEach(() => {
+    // Reset billing for each test default
+    billingEnabled = 'true';
+
+    // Initialize mocks
+    mockStoreObservation = mock(() => ({ id: 1, createdAtEpoch: Date.now() }));
+    mockStoreSummary = mock(() => ({ id: 1, createdAtEpoch: Date.now() }));
+    mockMarkSessionCompleted = mock(() => {});
+    mockSyncObservation = mock(() => Promise.resolve());
+    mockSyncSummary = mock(() => Promise.resolve());
+    mockMarkProcessed = mock(() => {});
+    mockCleanupProcessed = mock(() => 0);
+    mockResetStuckMessages = mock(() => 0);
+
+    const mockSessionStore = {
+      storeObservation: mockStoreObservation,
+      storeSummary: mockStoreSummary,
+      markSessionCompleted: mockMarkSessionCompleted
+    };
+
+    const mockChromaSync = {
+      syncObservation: mockSyncObservation,
+      syncSummary: mockSyncSummary
+    };
+
+    mockDbManager = {
+      getSessionStore: () => mockSessionStore,
+      getChromaSync: () => mockChromaSync
+    } as unknown as DatabaseManager;
+
+    const mockPendingMessageStore = {
+      markProcessed: mockMarkProcessed,
+      cleanupProcessed: mockCleanupProcessed,
+      resetStuckMessages: mockResetStuckMessages
+    };
+
+    mockSessionManager = {
+      getMessageIterator: async function* () { yield* []; },
+      getPendingMessageStore: () => mockPendingMessageStore
+    } as unknown as SessionManager;
+
+    agent = new GeminiAgent(mockDbManager, mockSessionManager);
+    originalFetch = global.fetch;
+  });
+
+  afterEach(() => {
+    global.fetch = originalFetch;
+    mock.restore();
+  });
+
+  it('should initialize with correct config', async () => {
+    const session = {
+      sessionDbId: 1,
+      claudeSessionId: 'test-session',
+      sdkSessionId: 'test-sdk',
+      project: 'test-project',
+      userPrompt: 'test prompt',
+      conversationHistory: [],
+      lastPromptNumber: 1,
+      cumulativeInputTokens: 0,
+      cumulativeOutputTokens: 0,
+      pendingProcessingIds: new Set(),
+      startTime: Date.now()
+    } as any;
+
+    global.fetch = mock(() => Promise.resolve(new Response(JSON.stringify({
+      candidates: [{
+        content: {
+          parts: [{ text: '<observation><type>discovery</type><title>Test</title></observation>' }]
+        }
+      }],
+      usageMetadata: { totalTokenCount: 100 }
+    }))));
+
+    await agent.startSession(session);
+
+    expect(global.fetch).toHaveBeenCalledTimes(1);
+    const url = (global.fetch as any).mock.calls[0][0];
+    expect(url).toContain('https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-lite:generateContent');
+    expect(url).toContain('key=test-api-key');
+  });
+
+  it('should handle multi-turn conversation', async () => {
+    const session = {
+      sessionDbId: 1,
+      claudeSessionId: 'test-session',
+      sdkSessionId: 'test-sdk',
+      project: 'test-project',
+      userPrompt: 'test prompt',
+      conversationHistory: [{ role: 'user', content: 'prev context' }, { role: 'assistant', content: 'prev response' }],
+      lastPromptNumber: 2,
+      cumulativeInputTokens: 0,
+      cumulativeOutputTokens: 0,
+      pendingProcessingIds: new Set(),
+      startTime: Date.now()
+    } as any;
+
+    global.fetch = mock(() => Promise.resolve(new Response(JSON.stringify({
+      candidates: [{ content: { parts: [{ text: 'response' }] } }]
+    }))));
+
+    await agent.startSession(session);
+
+    const body = JSON.parse((global.fetch as any).mock.calls[0][1].body);
+    expect(body.contents).toHaveLength(3);
+    expect(body.contents[0].role).toBe('user');
+    expect(body.contents[1].role).toBe('model');
+    expect(body.contents[2].role).toBe('user');
+  });
+
+  it('should process observations and store them', async () => {
+    const session = {
+      sessionDbId: 1,
+      claudeSessionId: 'test-session',
+      sdkSessionId: 'test-sdk',
+      project: 'test-project',
+      userPrompt: 'test prompt',
+      conversationHistory: [],
+      lastPromptNumber: 1,
+      cumulativeInputTokens: 0,
+      cumulativeOutputTokens: 0,
+      pendingProcessingIds: new Set(),
+      startTime: Date.now()
+    } as any;
+
+    const observationXml = `
+      <observation>
+        <type>discovery</type>
+        <title>Found bug</title>
+        <subtitle>Null pointer</subtitle>
+        <narrative>Found a null pointer in the code</narrative>
+        <facts><fact>Null check missing</fact></facts>
+        <concepts><concept>bug</concept></concepts>
+        <files_read><file>src/main.ts</file></files_read>
+        <files_modified></files_modified>
+      </observation>
+    `;
+
+    global.fetch = mock(() => Promise.resolve(new Response(JSON.stringify({
+      candidates: [{ content: { parts: [{ text: observationXml }] } }],
+      usageMetadata: { totalTokenCount: 50 }
+    }))));
+
+    await agent.startSession(session);
+
+    expect(mockStoreObservation).toHaveBeenCalled();
+    expect(mockSyncObservation).toHaveBeenCalled();
+    expect(session.cumulativeInputTokens).toBeGreaterThan(0);
+  });
+
+  it('should fallback to Claude on rate limit error', async () => {
+    const session = {
+      sessionDbId: 1,
+      claudeSessionId: 'test-session',
+      sdkSessionId: 'test-sdk',
+      project: 'test-project',
+      userPrompt: 'test prompt',
+      conversationHistory: [],
+      lastPromptNumber: 1,
+      cumulativeInputTokens: 0,
+      cumulativeOutputTokens: 0,
+      pendingProcessingIds: new Set(),
+      startTime: Date.now()
+    } as any;
+
+    global.fetch = mock(() => Promise.resolve(new Response('Resource has been exhausted (e.g. check quota).', { status: 429 })));
+
+    const fallbackAgent = {
+      startSession: mock(() => Promise.resolve())
+    };
+    agent.setFallbackAgent(fallbackAgent);
+
+    await agent.startSession(session);
+
+    expect(fallbackAgent.startSession).toHaveBeenCalledWith(session, undefined);
+    expect(mockResetStuckMessages).toHaveBeenCalled();
+  });
+
+  it('should NOT fallback on other errors', async () => {
+    const session = {
+      sessionDbId: 1,
+      claudeSessionId: 'test-session',
+      sdkSessionId: 'test-sdk',
+      project: 'test-project',
+      userPrompt: 'test prompt',
+      conversationHistory: [],
+      lastPromptNumber: 1,
+      cumulativeInputTokens: 0,
+      cumulativeOutputTokens: 0,
+      pendingProcessingIds: new Set(),
+      startTime: Date.now()
+    } as any;
+
+    global.fetch = mock(() => Promise.resolve(new Response('Invalid argument', { status: 400 })));
+
+    const fallbackAgent = {
+      startSession: mock(() => Promise.resolve())
+    };
+    agent.setFallbackAgent(fallbackAgent);
+
+    expect(agent.startSession(session)).rejects.toThrow('Gemini API error: 400 - Invalid argument');
+    expect(fallbackAgent.startSession).not.toHaveBeenCalled();
+  });
+
+  it('should respect rate limits when billing disabled', async () => {
+    billingEnabled = 'false';
+    const originalSetTimeout = global.setTimeout;
+    const mockSetTimeout = mock((cb: any) => cb());
+    global.setTimeout = mockSetTimeout as any;
+
+    try {
+      const session = {
+        sessionDbId: 1,
+        claudeSessionId: 'test-session',
+        sdkSessionId: 'test-sdk',
+        project: 'test-project',
+        userPrompt: 'test prompt',
+        conversationHistory: [],
+        lastPromptNumber: 1,
+        cumulativeInputTokens: 0,
+        cumulativeOutputTokens: 0,
+        pendingProcessingIds: new Set(),
+        startTime: Date.now()
+      } as any;
+
+      global.fetch = mock(() => Promise.resolve(new Response(JSON.stringify({
+        candidates: [{ content: { parts: [{ text: 'ok' }] } }]
+      }))));
+
+      await agent.startSession(session);
+      await agent.startSession(session);
+
+      expect(mockSetTimeout).toHaveBeenCalled();
+    } finally {
+      global.setTimeout = originalSetTimeout;
+    }
+  });
+});

tests/hook-constants.test.ts

@@ -0,0 +1,100 @@
+import { describe, it, expect, beforeEach, afterEach } from 'bun:test';
+import { HOOK_TIMEOUTS, HOOK_EXIT_CODES, getTimeout } from '../src/shared/hook-constants.js';
+
+describe('hook-constants', () => {
+  const originalPlatform = process.platform;
+
+  afterEach(() => {
+    // Restore original platform after each test
+    Object.defineProperty(process, 'platform', {
+      value: originalPlatform,
+      writable: true,
+      configurable: true
+    });
+  });
+
+  describe('HOOK_TIMEOUTS', () => {
+    it('should define DEFAULT timeout', () => {
+      expect(HOOK_TIMEOUTS.DEFAULT).toBe(300000);
+    });
+
+    it('should define HEALTH_CHECK timeout', () => {
+      expect(HOOK_TIMEOUTS.HEALTH_CHECK).toBe(30000);
+    });
+
+    it('should define WORKER_STARTUP_WAIT', () => {
+      expect(HOOK_TIMEOUTS.WORKER_STARTUP_WAIT).toBe(1000);
+    });
+
+    it('should define WORKER_STARTUP_RETRIES', () => {
+      expect(HOOK_TIMEOUTS.WORKER_STARTUP_RETRIES).toBe(300);
+    });
+
+    it('should define PRE_RESTART_SETTLE_DELAY', () => {
+      expect(HOOK_TIMEOUTS.PRE_RESTART_SETTLE_DELAY).toBe(2000);
+    });
+
+    it('should define WINDOWS_MULTIPLIER', () => {
+      expect(HOOK_TIMEOUTS.WINDOWS_MULTIPLIER).toBe(1.5);
+    });
+  });
+
+  describe('HOOK_EXIT_CODES', () => {
+    it('should define SUCCESS exit code', () => {
+      expect(HOOK_EXIT_CODES.SUCCESS).toBe(0);
+    });
+
+    it('should define FAILURE exit code', () => {
+      expect(HOOK_EXIT_CODES.FAILURE).toBe(1);
+    });
+
+    it('should define USER_MESSAGE_ONLY exit code', () => {
+      expect(HOOK_EXIT_CODES.USER_MESSAGE_ONLY).toBe(3);
+    });
+  });
+
+  describe('getTimeout', () => {
+    it('should return base timeout on non-Windows platforms', () => {
+      Object.defineProperty(process, 'platform', {
+        value: 'darwin',
+        writable: true,
+        configurable: true
+      });
+
+      expect(getTimeout(1000)).toBe(1000);
+      expect(getTimeout(5000)).toBe(5000);
+    });
+
+    it('should apply Windows multiplier on Windows platform', () => {
+      Object.defineProperty(process, 'platform', {
+        value: 'win32',
+        writable: true,
+        configurable: true
+      });
+
+      expect(getTimeout(1000)).toBe(1500);
+      expect(getTimeout(2000)).toBe(3000);
+    });
+
+    it('should round Windows timeout to nearest integer', () => {
+      Object.defineProperty(process, 'platform', {
+        value: 'win32',
+        writable: true,
+        configurable: true
+      });
+
+      // 333 * 1.5 = 499.5, should round to 500
+      expect(getTimeout(333)).toBe(500);
+    });
+
+    it('should return base timeout on Linux', () => {
+      Object.defineProperty(process, 'platform', {
+        value: 'linux',
+        writable: true,
+        configurable: true
+      });
+
+      expect(getTimeout(1000)).toBe(1000);
+    });
+  });
+});

tests/worker-spawn.test.ts

@@ -0,0 +1,349 @@
+import { describe, it, expect, beforeEach, afterEach, beforeAll, afterAll } from 'bun:test';
+import { spawn, execSync, ChildProcess } from 'child_process';
+import { existsSync, readFileSync, writeFileSync, unlinkSync, mkdirSync, rmSync } from 'fs';
+import { homedir } from 'os';
+import path from 'path';
+
+// Test configuration
+const TEST_PORT = 37877; // Use different port than default to avoid conflicts
+const TEST_DATA_DIR = path.join(homedir(), '.claude-mem-test');
+const TEST_PID_FILE = path.join(TEST_DATA_DIR, 'worker.pid');
+const WORKER_SCRIPT = path.join(__dirname, '../plugin/scripts/worker-service.cjs');
+
+// Timeout for health checks
+const HEALTH_TIMEOUT_MS = 5000;
+
+interface PidInfo {
+  pid: number;
+  port: number;
+  startedAt: string;
+}
+
+/**
+ * Helper to check if port is in use by attempting a health check
+ */
+async function isPortInUse(port: number): Promise<boolean> {
+  try {
+    const response = await fetch(`http://127.0.0.1:${port}/api/health`, {
+      signal: AbortSignal.timeout(2000)
+    });
+    return response.ok;
+  } catch {
+    return false;
+  }
+}
+
+/**
+ * Helper to wait for port to be healthy
+ */
+async function waitForHealth(port: number, timeoutMs: number = 30000): Promise<boolean> {
+  const start = Date.now();
+  while (Date.now() - start < timeoutMs) {
+    if (await isPortInUse(port)) return true;
+    await new Promise(r => setTimeout(r, 500));
+  }
+  return false;
+}
+
+/**
+ * Helper to wait for port to be free
+ */
+async function waitForPortFree(port: number, timeoutMs: number = 10000): Promise<boolean> {
+  const start = Date.now();
+  while (Date.now() - start < timeoutMs) {
+    if (!(await isPortInUse(port))) return true;
+    await new Promise(r => setTimeout(r, 500));
+  }
+  return false;
+}
+
+/**
+ * Helper to shut down worker via HTTP
+ */
+async function httpShutdown(port: number): Promise<boolean> {
+  try {
+    await fetch(`http://127.0.0.1:${port}/api/admin/shutdown`, {
+      method: 'POST',
+      signal: AbortSignal.timeout(5000)
+    });
+    return true;
+  } catch {
+    return false;
+  }
+}
+
+/**
+ * Run worker CLI command and return stdout
+ */
+function runWorkerCommand(command: string, env: Record<string, string> = {}): string {
+  const result = execSync(`bun "${WORKER_SCRIPT}" ${command}`, {
+    env: { ...process.env, ...env },
+    encoding: 'utf-8',
+    timeout: 60000
+  });
+  return result.trim();
+}
+
+describe('Worker Self-Spawn CLI', () => {
+  beforeAll(async () => {
+    // Clean up test data directory
+    if (existsSync(TEST_DATA_DIR)) {
+      rmSync(TEST_DATA_DIR, { recursive: true });
+    }
+  });
+
+  afterAll(async () => {
+    // Clean up test data directory
+    if (existsSync(TEST_DATA_DIR)) {
+      rmSync(TEST_DATA_DIR, { recursive: true });
+    }
+  });
+
+  describe('status command', () => {
+    it('should report worker status in expected format', async () => {
+      // The status command reads from settings file, not env vars
+      // Just verify the output format is correct (running or not running)
+      const output = runWorkerCommand('status');
+
+      // Should contain either "running" or "not running"
+      const hasValidStatus = output.includes('running');
+      expect(hasValidStatus).toBe(true);
+    });
+
+    it('should include PID and port when running', async () => {
+      const output = runWorkerCommand('status');
+
+      // If running, should include PID and port
+      if (output.includes('Worker running')) {
+        expect(output).toMatch(/PID: \d+/);
+        expect(output).toMatch(/Port: \d+/);
+      }
+    });
+  });
+
+  describe('PID file management', () => {
+    it('should create PID file with correct structure', () => {
+      // Create test directory
+      mkdirSync(TEST_DATA_DIR, { recursive: true });
+
+      const testPidInfo: PidInfo = {
+        pid: 12345,
+        port: TEST_PORT,
+        startedAt: new Date().toISOString()
+      };
+
+      writeFileSync(TEST_PID_FILE, JSON.stringify(testPidInfo, null, 2));
+
+      expect(existsSync(TEST_PID_FILE)).toBe(true);
+
+      const readInfo = JSON.parse(readFileSync(TEST_PID_FILE, 'utf-8')) as PidInfo;
+      expect(readInfo.pid).toBe(12345);
+      expect(readInfo.port).toBe(TEST_PORT);
+      expect(readInfo.startedAt).toBe(testPidInfo.startedAt);
+    });
+
+    it('should handle missing PID file gracefully', () => {
+      const missingPath = path.join(TEST_DATA_DIR, 'nonexistent.pid');
+      expect(existsSync(missingPath)).toBe(false);
+    });
+
+    it('should remove PID file correctly', () => {
+      mkdirSync(TEST_DATA_DIR, { recursive: true });
+      writeFileSync(TEST_PID_FILE, JSON.stringify({ pid: 1, port: 1, startedAt: '' }));
+
+      expect(existsSync(TEST_PID_FILE)).toBe(true);
+
+      unlinkSync(TEST_PID_FILE);
+
+      expect(existsSync(TEST_PID_FILE)).toBe(false);
+    });
+  });
+
+  describe('health check utilities', () => {
+    it('should return false for non-existent server', async () => {
+      const unusedPort = 39999;
+      const result = await isPortInUse(unusedPort);
+      expect(result).toBe(false);
+    });
+
+    it('should timeout appropriately for unreachable server', async () => {
+      const start = Date.now();
+      const result = await isPortInUse(39998);
+      const elapsed = Date.now() - start;
+
+      expect(result).toBe(false);
+      // Should not wait longer than the timeout (2s) + small buffer
+      expect(elapsed).toBeLessThan(3000);
+    });
+  });
+
+  describe('hook response format', () => {
+    it('should return valid JSON hook response', () => {
+      const hookResponse = '{"continue": true, "suppressOutput": true}';
+      const parsed = JSON.parse(hookResponse);
+
+      expect(parsed.continue).toBe(true);
+      expect(parsed.suppressOutput).toBe(true);
+    });
+  });
+});
+
+describe('Worker Health Endpoints', () => {
+  let workerProcess: ChildProcess | null = null;
+
+  beforeAll(async () => {
+    // Skip if worker script doesn't exist (not built)
+    if (!existsSync(WORKER_SCRIPT)) {
+      console.log('Skipping worker health tests - worker script not built');
+      return;
+    }
+
+    // Start worker for health endpoint tests using default port
+    // Note: These tests use the real worker, so they may be affected by existing worker state
+  });
+
+  afterAll(async () => {
+    if (workerProcess) {
+      workerProcess.kill('SIGTERM');
+      workerProcess = null;
+    }
+  });
+
+  describe('health endpoint contract', () => {
+    it('should expect /api/health to return status ok', async () => {
+      // This is a contract test - validates expected format
+      const expectedHealthResponse = {
+        status: 'ok',
+        build: expect.any(String),
+        managed: expect.any(Boolean),
+        hasIpc: expect.any(Boolean),
+        platform: expect.any(String),
+        pid: expect.any(Number),
+        initialized: expect.any(Boolean),
+        mcpReady: expect.any(Boolean)
+      };
+
+      // Verify the contract structure matches what the code returns
+      const mockResponse = {
+        status: 'ok',
+        build: 'TEST-008-wrapper-ipc',
+        managed: false,
+        hasIpc: false,
+        platform: 'darwin',
+        pid: 12345,
+        initialized: true,
+        mcpReady: true
+      };
+
+      expect(mockResponse.status).toBe('ok');
+      expect(typeof mockResponse.build).toBe('string');
+      expect(typeof mockResponse.pid).toBe('number');
+    });
+
+    it('should expect /api/readiness to return status when ready', async () => {
+      const expectedReadyResponse = {
+        status: 'ready',
+        mcpReady: true
+      };
+
+      expect(expectedReadyResponse.status).toBe('ready');
+      expect(expectedReadyResponse.mcpReady).toBe(true);
+    });
+
+    it('should expect /api/readiness to return 503 when initializing', async () => {
+      const expectedInitializingResponse = {
+        status: 'initializing',
+        message: 'Worker is still initializing, please retry'
+      };
+
+      expect(expectedInitializingResponse.status).toBe('initializing');
+    });
+  });
+});
+
+describe('Windows-specific behavior', () => {
+  const originalPlatform = process.platform;
+
+  afterEach(() => {
+    Object.defineProperty(process, 'platform', {
+      value: originalPlatform,
+      writable: true,
+      configurable: true
+    });
+  });
+
+  it('should use different shutdown behavior on Windows', () => {
+    Object.defineProperty(process, 'platform', {
+      value: 'win32',
+      writable: true,
+      configurable: true
+    });
+
+    // Windows uses IPC messages for managed workers
+    const isWindowsManaged = process.platform === 'win32' &&
+      process.env.CLAUDE_MEM_MANAGED === 'true' &&
+      typeof process.send === 'function';
+
+    // In non-managed mode, this should be false
+    expect(isWindowsManaged).toBe(false);
+  });
+
+  it('should identify managed Windows worker correctly', () => {
+    Object.defineProperty(process, 'platform', {
+      value: 'win32',
+      writable: true,
+      configurable: true
+    });
+
+    // Set managed environment
+    process.env.CLAUDE_MEM_MANAGED = 'true';
+
+    const isWindows = process.platform === 'win32';
+    const isManaged = process.env.CLAUDE_MEM_MANAGED === 'true';
+
+    expect(isWindows).toBe(true);
+    expect(isManaged).toBe(true);
+
+    // Cleanup
+    delete process.env.CLAUDE_MEM_MANAGED;
+  });
+});
+
+describe('CLI command parsing', () => {
+  it('should recognize start command', () => {
+    const args = ['node', 'worker-service.cjs', 'start'];
+    const command = args[2];
+    expect(command).toBe('start');
+  });
+
+  it('should recognize stop command', () => {
+    const args = ['node', 'worker-service.cjs', 'stop'];
+    const command = args[2];
+    expect(command).toBe('stop');
+  });
+
+  it('should recognize restart command', () => {
+    const args = ['node', 'worker-service.cjs', 'restart'];
+    const command = args[2];
+    expect(command).toBe('restart');
+  });
+
+  it('should recognize status command', () => {
+    const args = ['node', 'worker-service.cjs', 'status'];
+    const command = args[2];
+    expect(command).toBe('status');
+  });
+
+  it('should recognize --daemon flag', () => {
+    const args = ['node', 'worker-service.cjs', '--daemon'];
+    const command = args[2];
+    expect(command).toBe('--daemon');
+  });
+
+  it('should default to daemon mode without command', () => {
+    const args = ['node', 'worker-service.cjs'];
+    const command = args[2]; // undefined
+    // Default case in switch handles undefined by running as daemon
+    expect(command).toBeUndefined();
+  });
+});