feat: durable token usage tracking (SQLite + usage_get_summary action)

.claude/skills/add-compact/SKILL.md

@@ -31,6 +31,7 @@ git merge upstream/skill/compact
 > **Note:** `upstream` is the remote pointing to `qwibitai/agentlite`. If using a different remote name, substitute accordingly.
 
 This adds:
+
 - `src/session-commands.ts` (extract and authorize session commands)
 - `src/session-commands.test.ts` (unit tests for command parsing and auth)
 - Session command interception in `src/orchestrator.ts` (both `processGroupMessages` and `startMessageLoop`)

.claude/skills/add-discord/SKILL.md

@@ -47,6 +47,7 @@ git merge discord/main || {
 ```
 
 This merges in:
+
 - `src/channels/discord.ts` (DiscordChannel class with self-registration via `registerChannel`)
 - `src/channels/discord.test.ts` (unit tests with discord.js mock)
 - `import './discord.js'` appended to the channel barrel file `src/channels/index.ts`
@@ -151,6 +152,7 @@ npx tsx setup/index.ts --step register -- --jid "dc:<channel-id>" --name "<serve
 Tell the user:
 
 > Send a message in your registered Discord channel:
+>
 > - For main channel: Any message works
 > - For non-main: @mention the bot in Discord
 >
@@ -175,12 +177,14 @@ tail -f logs/agentlite.log
 ### Bot only responds to @mentions
 
 This is the default behavior for non-main channels (`requiresTrigger: true`). To change:
+
 - Update the registered group's `requiresTrigger` to `false`
 - Or register the channel as the main channel
 
 ### Message Content Intent not enabled
 
 If the bot connects but can't read messages, ensure:
+
 1. Go to [Discord Developer Portal](https://discord.com/developers/applications)
 2. Select your application > **Bot** tab
 3. Under **Privileged Gateway Intents**, enable **Message Content Intent**
@@ -189,12 +193,14 @@ If the bot connects but can't read messages, ensure:
 ### Getting Channel ID
 
 If you can't copy the channel ID:
+
 - Ensure **Developer Mode** is enabled: User Settings > Advanced > Developer Mode
 - Right-click the channel name in the server sidebar > Copy Channel ID
 
 ## After Setup
 
 The Discord bot supports:
+
 - Text messages in registered channels
 - Attachment descriptions (images, videos, files shown as placeholders)
 - Reply context (shows who the user is replying to)

.claude/skills/add-gmail/SKILL.md

@@ -48,6 +48,7 @@ git merge gmail/main || {
 ```
 
 This merges in:
+
 - `src/channels/gmail.ts` (GmailChannel class with self-registration via `registerChannel`)
 - `src/channels/gmail.test.ts` (unit tests)
 - `import './gmail.js'` appended to the channel barrel file `src/channels/index.ts`

.claude/skills/add-image-vision/SKILL.md

@@ -40,6 +40,7 @@ git merge whatsapp/skill/image-vision || {
 ```
 
 This merges in:
+
 - `src/image.ts` (image download, resize via sharp, base64 encoding)
 - `src/image.test.ts` (8 unit tests)
 - Image attachment handling in `src/channels/whatsapp.ts`
@@ -62,11 +63,13 @@ All tests must pass and build must be clean before proceeding.
 ## Phase 3: Configure
 
 1. Rebuild the container (agent-runner changes need a rebuild):
+
    ```bash
    ./container/build.sh
    ```
 
 2. Sync agent-runner source to group caches:
+
    ```bash
    for dir in data/sessions/*/agent-runner-src/; do
      cp container/agent-runner/src/*.ts "$dir"

.claude/skills/add-ollama-tool/SKILL.md

@@ -8,6 +8,7 @@ description: Add Ollama MCP server so the container agent can call local models
 This skill adds a stdio-based MCP server that exposes local Ollama models as tools for the container agent. Claude remains the orchestrator but can offload work to local models.
 
 Tools added:
+
 - `ollama_list_models` — lists installed Ollama models
 - `ollama_generate` — sends a prompt to a specified model and returns the response
 
@@ -59,6 +60,7 @@ git merge upstream/skill/ollama-tool
 ```
 
 This merges in:
+
 - `container/agent-runner/src/ollama-mcp-stdio.ts` (Ollama MCP server)
 - `scripts/ollama-watch.sh` (macOS notification watcher)
 - Ollama MCP config in `container/agent-runner/src/index.ts` (allowedTools + mcpServers)
@@ -129,6 +131,7 @@ tail -f logs/agentlite.log | grep -i ollama
 ```
 
 Look for:
+
 - `Agent output: ... Ollama ...` — agent used Ollama successfully
 - `[OLLAMA] >>> Generating` — generation started (if log surfacing works)
 - `[OLLAMA] <<< Done` — generation completed
@@ -138,6 +141,7 @@ Look for:
 ### Agent says "Ollama is not installed"
 
 The agent is trying to run `ollama` CLI inside the container instead of using the MCP tools. This means:
+
 1. The MCP server wasn't registered — check `container/agent-runner/src/index.ts` has the `ollama` entry in `mcpServers`
 2. The per-group source wasn't updated — re-copy files (see Phase 2)
 3. The container wasn't rebuilt — run `./container/build.sh`

.claude/skills/add-parallel/SKILL.md

@@ -11,6 +11,7 @@ Adds Parallel AI MCP integration to AgentLite for advanced web research capabili
 ## Prerequisites
 
 User must have:
+
 1. Parallel AI API key from https://platform.parallel.ai
 2. AgentLite already set up and running
 3. Docker installed and running
@@ -28,6 +29,7 @@ Collect it now.
 
 **If they need one:**
 Tell them:
+
 > 1. Go to https://platform.parallel.ai
 > 2. Sign up or log in
 > 3. Navigate to API Keys section
@@ -58,6 +60,7 @@ fi
 ```
 
 Verify:
+
 ```bash
 grep "PARALLEL_API_KEY" .env | head -c 50
 ```
@@ -67,48 +70,56 @@ grep "PARALLEL_API_KEY" .env | head -c 50
 Add `PARALLEL_API_KEY` to allowed environment variables in `src/container-runner.ts`:
 
 Find the line:
+
 ```typescript
 const allowedVars = ['CLAUDE_CODE_OAUTH_TOKEN', 'ANTHROPIC_API_KEY'];
 ```
 
 Replace with:
+
 ```typescript
-const allowedVars = ['CLAUDE_CODE_OAUTH_TOKEN', 'ANTHROPIC_API_KEY', 'PARALLEL_API_KEY'];
+const allowedVars = [
+  'CLAUDE_CODE_OAUTH_TOKEN',
+  'ANTHROPIC_API_KEY',
+  'PARALLEL_API_KEY',
+];
 ```
 
 ### 4. Configure MCP Servers in Agent Runner
 
 Update `container/agent-runner/src/index.ts`:
 
 Find the section where `mcpServers` is configured (around line 237-252):
+
 ```typescript
 const mcpServers: Record<string, any> = {
-  agentlite: ipcMcp
+  agentlite: ipcMcp,
 };
 ```
 
 Add Parallel AI MCP servers after the agentlite server:
+
 ```typescript
 const mcpServers: Record<string, any> = {
-  agentlite: ipcMcp
+  agentlite: ipcMcp,
 };
 
 // Add Parallel AI MCP servers if API key is available
 const parallelApiKey = process.env.PARALLEL_API_KEY;
 if (parallelApiKey) {
   mcpServers['parallel-search'] = {
-    type: 'http',  // REQUIRED: Must specify type for HTTP MCP servers
+    type: 'http', // REQUIRED: Must specify type for HTTP MCP servers
     url: 'https://search-mcp.parallel.ai/mcp',
     headers: {
-      'Authorization': `Bearer ${parallelApiKey}`
-    }
+      Authorization: `Bearer ${parallelApiKey}`,
+    },
   };
   mcpServers['parallel-task'] = {
-    type: 'http',  // REQUIRED: Must specify type for HTTP MCP servers  
+    type: 'http', // REQUIRED: Must specify type for HTTP MCP servers
     url: 'https://task-mcp.parallel.ai/mcp',
     headers: {
-      'Authorization': `Bearer ${parallelApiKey}`
-    }
+      Authorization: `Bearer ${parallelApiKey}`,
+    },
   };
   log('Parallel AI MCP servers configured');
 } else {
@@ -117,6 +128,7 @@ if (parallelApiKey) {
 ```
 
 Also update the `allowedTools` array to include Parallel MCP tools (around line 242-248):
+
 ```typescript
 allowedTools: [
   'Bash',
@@ -133,20 +145,24 @@ allowedTools: [
 Add Parallel AI usage instructions to `groups/main/CLAUDE.md`:
 
 Find the "## What You Can Do" section and add after the existing bullet points:
+
 ```markdown
 - Use Parallel AI for web research and deep learning tasks
 ```
 
 Then add a new section after "## What You Can Do":
+
 ```markdown
 ## Web Research Tools
 
 You have access to two Parallel AI research tools:
 
 ### Quick Web Search (`mcp__parallel-search__search`)
+
 **When to use:** Freely use for factual lookups, current events, definitions, recent information, or verifying facts.
 
 **Examples:**
+
 - "Who invented the transistor?"
 - "What's the latest news about quantum computing?"
 - "When was the UN founded?"
@@ -157,9 +173,11 @@ You have access to two Parallel AI research tools:
 **Permission:** Not needed - use whenever it helps answer the question
 
 ### Deep Research (`mcp__parallel-task__create_task_run`)
+
 **When to use:** Comprehensive analysis, learning about complex topics, comparing concepts, historical overviews, or structured research.
 
 **Examples:**
+
 - "Explain the development of quantum mechanics from 1900-1930"
 - "Compare the literary styles of Hemingway and Faulkner"
 - "Research the evolution of jazz from bebop to fusion"
@@ -171,28 +189,32 @@ You have access to two Parallel AI research tools:
 
 **How to ask permission:**
 ```
+
 AskUserQuestion: I can do deep research on [topic] using Parallel's Task API. This will take 2-5 minutes and provide comprehensive analysis with citations. Should I proceed?
+
 ```
 
 **After permission - DO NOT BLOCK! Use scheduler instead:**
 
 1. Create the task using `mcp__parallel-task__create_task_run`
 2. Get the `run_id` from the response
 3. Create a polling scheduled task using `mcp__agentlite__schedule_task`:
-   ```
-   Prompt: "Check Parallel AI task run [run_id] and send results when ready.
+```
+
+Prompt: "Check Parallel AI task run [run_id] and send results when ready.
 
-   1. Use the Parallel Task MCP to check the task status
-   2. If status is 'completed', extract the results
-   3. Send results to user with mcp__agentlite__send_message
-   4. Use mcp__agentlite__complete_scheduled_task to mark this task as done
+1.  Use the Parallel Task MCP to check the task status
+2.  If status is 'completed', extract the results
+3.  Send results to user with mcp**agentlite**send_message
+4.  Use mcp**agentlite**complete_scheduled_task to mark this task as done
 
-   If status is still 'running' or 'pending', do nothing (task will run again in 30s).
-   If status is 'failed', send error message and complete the task."
+If status is still 'running' or 'pending', do nothing (task will run again in 30s).
+If status is 'failed', send error message and complete the task."
 
-   Schedule: interval every 30 seconds
-   Context mode: isolated
-   ```
+Schedule: interval every 30 seconds
+Context mode: isolated
+
+```
 4. Send acknowledgment with tracking link
 5. Exit immediately - scheduler handles the rest
 
@@ -223,6 +245,7 @@ Build the container with updated agent runner:
 ```
 
 Verify the build:
+
 ```bash
 echo '{}' | docker run -i --entrypoint /bin/echo agentlite-agent:latest "Container OK"
 ```
@@ -238,6 +261,7 @@ launchctl kickstart -k gui/$(id -u)/com.agentlite  # macOS
 ```
 
 Wait 3 seconds for service to start, then verify:
+
 ```bash
 sleep 3
 launchctl list | grep agentlite  # macOS
@@ -247,6 +271,7 @@ launchctl list | grep agentlite  # macOS
 ### 8. Test Integration
 
 Tell the user to test:
+
 > Send a message to your assistant: `@[YourAssistantName] what's the latest news about AI?`
 >
 > The assistant should use Parallel Search API to find current information.
@@ -256,6 +281,7 @@ Tell the user to test:
 > The assistant should ask for permission before using the Task API.
 
 Check logs to verify MCP servers loaded:
+
 ```bash
 tail -20 logs/agentlite.log
 ```
@@ -265,16 +291,19 @@ Look for: `Parallel AI MCP servers configured`
 ## Troubleshooting
 
 **Container hangs or times out:**
+
 - Check that `type: 'http'` is specified in MCP server config
 - Verify API key is correct in .env
 - Check container logs: `cat groups/main/logs/container-*.log | tail -50`
 
 **MCP servers not loading:**
+
 - Ensure PARALLEL_API_KEY is in .env
 - Verify container-runner.ts includes PARALLEL_API_KEY in allowedVars
 - Check agent-runner logs for "Parallel AI MCP servers configured" message
 
 **Task polling not working:**
+
 - Verify scheduled task was created: `sqlite3 store/messages.db "SELECT * FROM scheduled_tasks"`
 - Check task runs: `tail -f logs/agentlite.log | grep "scheduled task"`
 - Ensure task prompt includes proper Parallel MCP tool names

.claude/skills/add-pdf-reader/SKILL.md

@@ -38,6 +38,7 @@ git merge whatsapp/skill/pdf-reader || {
 ```
 
 This merges in:
+
 - `container/skills/pdf-reader/SKILL.md` (agent-facing documentation)
 - `container/skills/pdf-reader/pdf-reader` (CLI script)
 - `poppler-utils` in `container/Dockerfile`
@@ -71,6 +72,7 @@ launchctl kickstart -k gui/$(id -u)/com.agentlite  # macOS
 ### Test PDF extraction
 
 Send a PDF file in any registered WhatsApp chat. The agent should:
+
 1. Download the PDF to `attachments/`
 2. Respond acknowledging the PDF
 3. Be able to extract text when asked
@@ -86,6 +88,7 @@ tail -f logs/agentlite.log | grep -i pdf
 ```
 
 Look for:
+
 - `Downloaded PDF attachment` — successful download
 - `Failed to download PDF attachment` — media download issue
 

.claude/skills/add-reactions/SKILL.md

@@ -45,6 +45,7 @@ git merge whatsapp/skill/reactions || {
 ```
 
 This adds:
+
 - `scripts/migrate-reactions.ts` (database migration for `reactions` table with composite PK and indexes)
 - `src/status-tracker.ts` (forward-only emoji state machine for message lifecycle signaling, with persistence and retry)
 - `src/status-tracker.test.ts` (unit tests for StatusTracker)
@@ -75,11 +76,13 @@ npm run build
 ```
 
 Linux:
+
 ```bash
 systemctl --user restart agentlite
 ```
 
 macOS:
+
 ```bash
 launchctl kickstart -k gui/$(id -u)/com.agentlite
 ```