Files
claude-mem/docs/public/platform-integration.mdx
T
Alex Newman 61488042d8 Mem-search enhancements: table output, simplified API, Sonnet default, and removed fake URIs (#317)
* feat: Add batch fetching for observations and update documentation

- Implemented a new endpoint for fetching multiple observations by IDs in a single request.
- Updated the DataRoutes to include a POST /api/observations/batch endpoint.
- Enhanced SKILL.md documentation to reflect changes in the search process and batch fetching capabilities.
- Increased the default limit for search results from 5 to 40 for better usability.

* feat!: Fix timeline parameter passing with SearchManager alignment

BREAKING CHANGE: Timeline MCP tools now use standardized parameter names
- anchor_id → anchor
- before → depth_before
- after → depth_after
- obs_type → type (timeline tool only)

Fixes timeline endpoint failures caused by parameter name mismatch between
MCP layer and SearchManager. Adds new SessionStore methods for fetching
prompts and session summaries by ID.

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

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

* docs: reframe timeline parameter fix as bug fix, not breaking change

The timeline tools were completely broken due to parameter name mismatch.
There's nothing to migrate from since the old parameters never worked.

Co-authored-by: Alex Newman <thedotmack@users.noreply.github.com>

* Refactor mem-search documentation and optimize API tool definitions

- Updated SKILL.md to emphasize batch fetching for observations, clarifying usage and efficiency.
- Removed deprecated tools from mcp-server.ts and streamlined tool definitions for clarity.
- Enhanced formatting in FormattingService.ts for better output readability.
- Adjusted SearchManager.ts to improve result headers and removed unnecessary search tips from combined text.

* Refactor FormattingService and SearchManager for table-based output

- Updated FormattingService to format search results as tables, including methods for formatting observations, sessions, and user prompts.
- Removed JSON format handling from SearchManager and streamlined result formatting to consistently use table format.
- Enhanced readability and consistency in search tips and formatting logic.
- Introduced token estimation for observations and improved time formatting.

* refactor: update documentation and API references for version bump and search functionalities

* Refactor code structure for improved readability and maintainability

* chore: change default model from haiku to sonnet

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

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

* feat: unify timeline formatting across search and context services

Extract shared timeline formatting utilities into reusable module to align
MCP search output format with context-generator's date/file-grouped format.

Changes:
- Create src/shared/timeline-formatting.ts with reusable utilities
  (parseJsonArray, formatDateTime, formatTime, formatDate, toRelativePath,
  extractFirstFile, groupByDate)
- Refactor context-generator.ts to use shared utilities
- Update SearchManager.search() to use date/file grouping
- Add search-specific row formatters to FormattingService
- Fix timeline methods to extract actual file paths from metadata
  instead of hardcoding 'General'
- Remove Work column from search output (kept in context output)

Result: Consistent date/file-grouped markdown formatting across both
systems while maintaining their different column requirements.

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

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

* refactor: remove redundant legend from search output

Remove legend from search/timeline results since it's already shown
in SessionStart context. Saves ~30 tokens per search result.

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

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

* Refactor session summary rendering to remove links

- Removed link generation for session summaries in context generation and search manager.
- Updated output formatting to exclude links while maintaining the session summary structure.
- Adjusted related components in TimelineService to ensure consistency across the application.

* fix: move skillPath declaration outside try block to fix scoping bug

The skillPath variable was declared inside the try block but referenced
in the catch block for error logging. Since const is block-scoped, this
would cause a ReferenceError when the error handler executes.

Moved skillPath declaration before the try block so it's accessible in
both try and catch scopes.

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

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

* fix: address PR #317 code review feedback

**Critical Fixes:**
- Replace happy_path_error__with_fallback debug calls with proper logger methods in mcp-server.ts
- All HTTP API calls now use logger.debug/error for consistent logging

**Code Quality Improvements:**
- Extract 90-day recency window magic numbers to named constants
- Added RECENCY_WINDOW_DAYS and RECENCY_WINDOW_MS constants in SearchManager

**Documentation:**
- Document model cost implications of Haiku → Sonnet upgrade in CHANGELOG
- Provide clear migration path for users who want to revert to Haiku

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

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

* refactor: simplify CHANGELOG - remove cost documentation

Removed model cost comparison documentation per user feedback.
Kept only the technical code quality improvements.

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

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

---------

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Alex Newman <thedotmack@users.noreply.github.com>
2025-12-14 21:58:11 -05:00

1541 lines
36 KiB
Plaintext

---
title: Platform Integration Guide
description: Complete reference for integrating claude-mem worker service into VSCode extensions, IDE plugins, and CLI tools
icon: plug
---
<Note>
**Version:** 7.0.0 (December 2025)
**Target Audience:** Developers building claude-mem integrations (VSCode extensions, IDE plugins, CLI tools)
</Note>
## Quick Reference
### Worker Service Basics
```typescript
const WORKER_BASE_URL = 'http://localhost:37777';
const DEFAULT_PORT = 37777; // Override with CLAUDE_MEM_WORKER_PORT
```
### Most Common Operations
```typescript
// Health check
GET /api/health
// Create/get session and queue observation
POST /api/sessions/observations
Body: { claudeSessionId, tool_name, tool_input, tool_response, cwd }
// Queue summary
POST /api/sessions/summarize
Body: { claudeSessionId, last_user_message, last_assistant_message }
// Complete session
POST /api/sessions/complete
Body: { claudeSessionId }
// Search observations
GET /api/search?query=authentication&type=observations&format=index&limit=20
// Get recent context for project
GET /api/context/recent?project=my-project&limit=3
```
### Environment Variables
```bash
CLAUDE_MEM_MODEL=claude-sonnet-4-5 # Model for observations/summaries
CLAUDE_MEM_CONTEXT_OBSERVATIONS=50 # Observations injected at SessionStart
CLAUDE_MEM_WORKER_PORT=37777 # Worker service port
CLAUDE_MEM_PYTHON_VERSION=3.13 # Python version for chroma-mcp
```
### Build Commands (Local Development)
```bash
npm run build # Compile TypeScript (hooks + worker)
npm run sync-marketplace # Copy to ~/.claude/plugins
npm run worker:restart # Restart worker
npm run worker:logs # View worker logs
npm run worker:status # Check worker status
```
## Worker Architecture
### Request Flow
```plaintext
Platform Hook/Extension
→ HTTP Request to Worker (localhost:37777)
→ Route Handler (SessionRoutes/DataRoutes/SearchRoutes/etc.)
→ Domain Service (SessionManager/SearchManager/DatabaseManager)
→ Database (SQLite3 + Chroma vector DB)
→ SSE Broadcast (real-time UI updates)
```
### Domain Services
<CardGroup cols={2}>
<Card title="DatabaseManager" icon="database">
SQLite connection management, initialization
</Card>
<Card title="SessionManager" icon="timeline">
Event-driven session lifecycle, message queues
</Card>
<Card title="SearchManager" icon="magnifying-glass">
Search orchestration (FTS5 + Chroma)
</Card>
<Card title="SSEBroadcaster" icon="broadcast-tower">
Server-Sent Events for real-time updates
</Card>
<Card title="SDKAgent" icon="robot">
Claude Agent SDK for generating observations/summaries
</Card>
<Card title="PaginationHelper" icon="list">
Query pagination utilities
</Card>
<Card title="SettingsManager" icon="gear">
User settings CRUD
</Card>
<Card title="FormattingService" icon="code">
Result formatting (index vs full)
</Card>
<Card title="TimelineService" icon="clock">
Unified timeline generation
</Card>
</CardGroup>
### Route Organization
<AccordionGroup>
<Accordion title="ViewerRoutes" icon="eye">
- Health check endpoint
- Viewer UI (React app)
- SSE stream for real-time updates
</Accordion>
<Accordion title="SessionRoutes" icon="timeline">
- Session lifecycle (init, observations, summarize, complete)
- Privacy checks and tag stripping
- Auto-start SDK agent generators
</Accordion>
<Accordion title="DataRoutes" icon="database">
- Data retrieval (observations, summaries, prompts, stats)
- Pagination support
- Processing status
</Accordion>
<Accordion title="SearchRoutes" icon="magnifying-glass">
- All search operations
- Unified search API
- Timeline context
- Semantic shortcuts
</Accordion>
<Accordion title="SettingsRoutes" icon="gear">
- User settings
- MCP toggle
- Git branch switching
</Accordion>
</AccordionGroup>
## API Reference
### Session Lifecycle (SessionRoutes)
#### Create/Get Session + Queue Observation (New API)
<CodeGroup>
```http POST /api/sessions/observations
POST /api/sessions/observations
Content-Type: application/json
{
"claudeSessionId": "abc123", // Claude session identifier (string)
"tool_name": "Bash",
"tool_input": { "command": "ls" },
"tool_response": { "stdout": "..." },
"cwd": "/path/to/project"
}
```
```json Response
{ "status": "queued" }
// or
{ "status": "skipped", "reason": "private" }
```
</CodeGroup>
<Info>
**Privacy Check:** Skips if user prompt was entirely wrapped in `<private>` tags.
**Tag Stripping:** Removes `<private>` and `<claude-mem-context>` tags before storage.
**Auto-Start:** Ensures SDK agent generator is running to process the queue.
</Info>
#### Queue Summary (New API)
<CodeGroup>
```http POST /api/sessions/summarize
POST /api/sessions/summarize
Content-Type: application/json
{
"claudeSessionId": "abc123",
"last_user_message": "User's message",
"last_assistant_message": "Assistant's response"
}
```
```json Response
{ "status": "queued" }
// or
{ "status": "skipped", "reason": "private" }
```
</CodeGroup>
#### Complete Session (New API)
<CodeGroup>
```http POST /api/sessions/complete
POST /api/sessions/complete
Content-Type: application/json
{
"claudeSessionId": "abc123"
}
```
```json Response
{ "success": true }
// or
{ "success": true, "message": "No active session found" }
```
</CodeGroup>
<Warning>
**Effect:** Stops SDK agent, marks session complete, broadcasts status change.
</Warning>
#### Legacy Endpoints (Still Supported)
<Tabs>
<Tab title="Initialize Session">
```http
POST /sessions/:sessionDbId/init
Body: { userPrompt, promptNumber }
```
</Tab>
<Tab title="Queue Observations">
```http
POST /sessions/:sessionDbId/observations
Body: { tool_name, tool_input, tool_response, prompt_number, cwd }
```
</Tab>
<Tab title="Queue Summary">
```http
POST /sessions/:sessionDbId/summarize
Body: { last_user_message, last_assistant_message }
```
</Tab>
<Tab title="Complete Session">
```http
POST /sessions/:sessionDbId/complete
```
</Tab>
</Tabs>
<Note>
New integrations should use `/api/sessions/*` endpoints with `claudeSessionId`.
</Note>
### Data Retrieval (DataRoutes)
#### Get Paginated Data
<Tabs>
<Tab title="Observations">
```http
GET /api/observations?offset=0&limit=20&project=my-project
```
</Tab>
<Tab title="Summaries">
```http
GET /api/summaries?offset=0&limit=20&project=my-project
```
</Tab>
<Tab title="User Prompts">
```http
GET /api/prompts?offset=0&limit=20&project=my-project
```
</Tab>
</Tabs>
```json Response Format
{
"items": [...],
"hasMore": boolean,
"offset": number,
"limit": number
}
```
#### Get by ID
<Tabs>
<Tab title="Observation">
```http
GET /api/observation/:id
```
</Tab>
<Tab title="Session">
```http
GET /api/session/:id
```
</Tab>
<Tab title="Prompt">
```http
GET /api/prompt/:id
```
</Tab>
</Tabs>
#### Get Database Stats
```http
GET /api/stats
```
```json Response
{
"worker": {
"version": "7.0.0",
"uptime": 12345,
"activeSessions": 2,
"sseClients": 1,
"port": 37777
},
"database": {
"path": "~/.claude-mem/claude-mem.db",
"size": 1048576,
"observations": 500,
"sessions": 50,
"summaries": 25
}
}
```
#### Get Projects List
```http
GET /api/projects
```
```json Response
{
"projects": ["claude-mem", "other-project", ...]
}
```
#### Get Processing Status
```http
GET /api/processing-status
```
```json Response
{
"isProcessing": boolean,
"queueDepth": number
}
```
### Search Operations (SearchRoutes)
#### Unified Search
```http
GET /api/search?query=authentication&type=observations&format=index&limit=20
```
<ParamField query="query" type="string">
Search query text (optional, omit for filter-only)
</ParamField>
<ParamField query="type" type="string" default="all">
"observations" | "sessions" | "prompts"
</ParamField>
<ParamField query="format" type="string" default="index">
"index" | "full"
</ParamField>
<ParamField query="limit" type="number" default={20}>
Number of results
</ParamField>
<ParamField query="project" type="string">
Filter by project name
</ParamField>
<ParamField query="obs_type" type="string">
Filter by observation type (discovery, decision, bugfix, feature, refactor)
</ParamField>
<ParamField query="concepts" type="string">
Filter by concepts (comma-separated)
</ParamField>
<ParamField query="files" type="string">
Filter by file paths (comma-separated)
</ParamField>
<ParamField query="dateStart" type="string">
ISO timestamp (filter start)
</ParamField>
<ParamField query="dateEnd" type="string">
ISO timestamp (filter end)
</ParamField>
```json Response
{
"observations": [...],
"sessions": [...],
"prompts": [...]
}
```
<Info>
**Format Options:**
- `index`: Minimal fields for list display (id, title, preview)
- `full`: Complete entity with all fields
</Info>
#### Unified Timeline
```http
GET /api/timeline?anchor=123&depth_before=10&depth_after=10&project=my-project
```
<ParamField query="anchor" type="string" required>
Anchor point (observation ID, "S123" for session, or ISO timestamp)
</ParamField>
<ParamField query="depth_before" type="number" default={10}>
Records before anchor
</ParamField>
<ParamField query="depth_after" type="number" default={10}>
Records after anchor
</ParamField>
<ParamField query="project" type="string">
Filter by project
</ParamField>
```json Response
[
{ "type": "observation", "id": 120, "created_at_epoch": ..., ... },
{ "type": "session", "id": 5, "created_at_epoch": ..., ... },
{ "type": "observation", "id": 123, "created_at_epoch": ..., ... }
]
```
#### Semantic Shortcuts
<CardGroup cols={3}>
<Card title="Decisions" icon="check-circle">
```http
GET /api/decisions?format=index&limit=20
```
</Card>
<Card title="Changes" icon="code-commit">
```http
GET /api/changes?format=index&limit=20
```
</Card>
<Card title="How It Works" icon="lightbulb">
```http
GET /api/how-it-works?format=index&limit=20
```
</Card>
</CardGroup>
#### Search by Concept
```http
GET /api/search/by-concept?concept=discovery&format=index&limit=10&project=my-project
```
#### Search by File Path
```http
GET /api/search/by-file?filePath=src/services/worker-service.ts&format=index&limit=10
```
#### Search by Type
```http
GET /api/search/by-type?type=bugfix&format=index&limit=10
```
#### Get Recent Context
```http
GET /api/context/recent?project=my-project&limit=3
```
```json Response
{
"summaries": [...],
"observations": [...]
}
```
#### Context Preview (for Settings UI)
```http
GET /api/context/preview?project=my-project
```
<Note>
Returns plain text with ANSI colors for terminal display
</Note>
#### Context Injection (for Hooks)
```http
GET /api/context/inject?project=my-project&colors=true
```
<Note>
Returns pre-formatted context string ready for display
</Note>
### Settings & Configuration (SettingsRoutes)
#### Get/Update User Settings
<CodeGroup>
```http GET
GET /api/settings
```
```json GET Response
{
"sidebarOpen": boolean,
"selectedProject": string | null
}
```
```http POST
POST /api/settings
Body: { "sidebarOpen": true, "selectedProject": "my-project" }
```
```json POST Response
{ "success": true }
```
</CodeGroup>
#### MCP Server Status/Toggle
<CodeGroup>
```http GET Status
GET /api/mcp/status
```
```json GET Response
{ "enabled": boolean }
```
```http POST Toggle
POST /api/mcp/toggle
Body: { "enabled": true }
```
```json POST Response
{ "success": true, "enabled": boolean }
```
</CodeGroup>
#### Git Branch Operations
<Tabs>
<Tab title="Get Status">
```http
GET /api/branch/status
```
```json
{
"current": "main",
"remote": "origin/main",
"ahead": 0,
"behind": 0
}
```
</Tab>
<Tab title="Switch Branch">
```http
POST /api/branch/switch
Body: { "branch": "feature/new-feature" }
```
```json
{ "success": true }
```
</Tab>
<Tab title="Update Branch">
```http
POST /api/branch/update
```
```json
{ "success": true, "updated": boolean }
```
</Tab>
</Tabs>
### Viewer & Real-Time Updates (ViewerRoutes)
#### Health Check
```http
GET /api/health
```
```json Response
{ "status": "ok" }
```
#### Viewer UI
```http
GET /
```
<Note>
Returns HTML for React app
</Note>
#### SSE Stream
```http
GET /stream
```
<Info>
**Server-Sent Events stream**
Event Types:
- `processing_status`: { type, isProcessing, queueDepth }
- `session_started`: { type, sessionDbId, project }
- `observation_queued`: { type, sessionDbId }
- `summarize_queued`: { type }
- `observation_created`: { type, observation }
- `summary_created`: { type, summary }
- `new_prompt`: { type, id, claude_session_id, project, prompt_number, prompt_text, created_at_epoch }
</Info>
## Data Models
### Active Session (In-Memory)
```typescript
interface ActiveSession {
sessionDbId: number; // Database ID (numeric)
claudeSessionId: string; // Claude session identifier (string)
sdkSessionId: string | null; // SDK session ID
project: string; // Project name
userPrompt: string; // Current user prompt text
pendingMessages: PendingMessage[]; // Queue of pending operations
abortController: AbortController; // For cancellation
generatorPromise: Promise<void> | null; // SDK agent promise
lastPromptNumber: number; // Last processed prompt number
startTime: number; // Session start timestamp
cumulativeInputTokens: number; // Total input tokens
cumulativeOutputTokens: number; // Total output tokens
}
interface PendingMessage {
type: 'observation' | 'summarize';
tool_name?: string;
tool_input?: any;
tool_response?: any;
prompt_number?: number;
cwd?: string;
last_user_message?: string;
last_assistant_message?: string;
}
```
### Database Entities
<Tabs>
<Tab title="SDK Session">
```typescript
interface SDKSessionRow {
id: number;
claude_session_id: string;
sdk_session_id: string;
project: string;
user_prompt: string;
created_at_epoch: number;
completed_at_epoch?: number;
}
```
</Tab>
<Tab title="Observation">
```typescript
interface ObservationRow {
id: number;
sdk_session_id: string;
title: string;
subtitle?: string;
summary: string;
facts: string; // JSON array of fact strings
concepts: string; // JSON array of concept strings
files_touched: string; // JSON array of file paths
obs_type: string; // discovery, decision, bugfix, feature, refactor
project: string;
created_at_epoch: number;
prompt_number: number;
}
```
</Tab>
<Tab title="Session Summary">
```typescript
interface SessionSummaryRow {
id: number;
sdk_session_id: string;
summary_text: string;
facts: string; // JSON array
concepts: string; // JSON array
files_touched: string; // JSON array
project: string;
created_at_epoch: number;
}
```
</Tab>
<Tab title="User Prompt">
```typescript
interface UserPromptRow {
id: number;
claude_session_id: string;
sdk_session_id: string;
project: string;
prompt_number: number;
prompt_text: string;
created_at_epoch: number;
}
```
</Tab>
</Tabs>
### Search Results
```typescript
interface ObservationSearchResult {
id: number;
title: string;
subtitle?: string;
summary: string;
facts: string[]; // Parsed from JSON
concepts: string[]; // Parsed from JSON
files_touched: string[]; // Parsed from JSON
obs_type: string;
project: string;
created_at_epoch: number;
prompt_number: number;
rank?: number; // FTS5 rank score
}
interface SessionSummarySearchResult {
id: number;
summary_text: string;
facts: string[];
concepts: string[];
files_touched: string[];
project: string;
created_at_epoch: number;
rank?: number;
}
interface UserPromptSearchResult {
id: number;
claude_session_id: string;
project: string;
prompt_number: number;
prompt_text: string;
created_at_epoch: number;
rank?: number;
}
```
### Timeline Item
```typescript
interface TimelineItem {
type: 'observation' | 'session' | 'prompt';
id: number;
created_at_epoch: number;
// Entity-specific fields based on type
}
```
## Integration Patterns
### Mapping Claude Code Hooks to Worker API
<Steps>
<Step title="SessionStart Hook">
Not needed for new API - sessions are auto-created on first observation
</Step>
<Step title="UserPromptSubmit Hook">
No API call needed - user_prompt is captured by first observation in the prompt
</Step>
<Step title="PostToolUse Hook">
```typescript
async function onPostToolUse(context: HookContext) {
const { session_id, tool_name, tool_input, tool_result, cwd } = context;
const response = await fetch('http://localhost:37777/api/sessions/observations', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
claudeSessionId: session_id,
tool_name,
tool_input,
tool_response: tool_result,
cwd
})
});
const result = await response.json();
// result.status === 'queued' | 'skipped'
}
```
</Step>
<Step title="Summary Hook">
```typescript
async function onSummary(context: HookContext) {
const { session_id, last_user_message, last_assistant_message } = context;
await fetch('http://localhost:37777/api/sessions/summarize', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
claudeSessionId: session_id,
last_user_message,
last_assistant_message
})
});
}
```
</Step>
<Step title="SessionEnd Hook">
```typescript
async function onSessionEnd(context: HookContext) {
const { session_id } = context;
await fetch('http://localhost:37777/api/sessions/complete', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
claudeSessionId: session_id
})
});
}
```
</Step>
</Steps>
### VSCode Extension Integration
#### Language Model Tool Registration
```typescript
import * as vscode from 'vscode';
interface SearchTool extends vscode.LanguageModelChatTool {
invoke(
options: vscode.LanguageModelToolInvocationOptions<{ query: string }>,
token: vscode.CancellationToken
): vscode.ProviderResult<vscode.LanguageModelToolResult>;
}
const searchTool: SearchTool = {
invoke: async (options, token) => {
const { query } = options.input;
try {
const response = await fetch(
`http://localhost:37777/api/search?query=${encodeURIComponent(query)}&format=index&limit=10`
);
if (!response.ok) {
throw new Error(`Search failed: ${response.statusText}`);
}
const results = await response.json();
// Format results for language model
return new vscode.LanguageModelToolResult([
new vscode.LanguageModelTextPart(JSON.stringify(results, null, 2))
]);
} catch (error) {
return new vscode.LanguageModelToolResult([
new vscode.LanguageModelTextPart(`Error: ${error.message}`)
]);
}
}
};
// Register tool
vscode.lm.registerTool('claude-mem-search', searchTool);
```
#### Chat Participant Implementation
```typescript
const participant = vscode.chat.createChatParticipant('claude-mem', async (request, context, stream, token) => {
const claudeSessionId = context.session.id;
// First message in conversation - no initialization needed
// Session is auto-created on first observation
// Process user message
stream.markdown(`Searching memory for: ${request.prompt}\n\n`);
const response = await fetch(
`http://localhost:37777/api/search?query=${encodeURIComponent(request.prompt)}&format=index&limit=5`
);
const results = await response.json();
if (results.observations?.length > 0) {
stream.markdown('**Found observations:**\n');
for (const obs of results.observations) {
stream.markdown(`- ${obs.title} (${obs.project})\n`);
}
}
return { metadata: { command: 'search' } };
});
```
## Error Handling & Resilience
### Connection Failures
```typescript
async function callWorkerWithFallback<T>(
endpoint: string,
options?: RequestInit
): Promise<T | null> {
try {
const response = await fetch(`http://localhost:37777${endpoint}`, {
...options,
signal: AbortSignal.timeout(5000) // 5s timeout
});
if (!response.ok) {
throw new Error(`HTTP ${response.status}: ${response.statusText}`);
}
return await response.json();
} catch (error) {
console.error(`Worker unavailable (${endpoint}):`, error);
return null; // Graceful degradation
}
}
```
### Retry Logic with Exponential Backoff
```typescript
async function retryWithBackoff<T>(
fn: () => Promise<T>,
maxRetries = 3,
baseDelay = 100
): Promise<T> {
for (let attempt = 0; attempt < maxRetries; attempt++) {
try {
return await fn();
} catch (error) {
if (attempt === maxRetries - 1) throw error;
const delay = baseDelay * Math.pow(2, attempt);
await new Promise(resolve => setTimeout(resolve, delay));
}
}
throw new Error('Max retries exceeded');
}
```
### Worker Health Check
```typescript
async function isWorkerHealthy(): Promise<boolean> {
try {
const response = await fetch('http://localhost:37777/api/health', {
signal: AbortSignal.timeout(2000)
});
return response.ok;
} catch {
return false;
}
}
```
### Privacy Tag Handling
<Info>
The worker automatically strips privacy tags before storage:
- `<private>content</private>` - User-level privacy control
- `<claude-mem-context>content</claude-mem-context>` - System-level tag (prevents recursive storage)
**Privacy Check:** Observations/summaries are skipped if the entire user prompt was wrapped in `<private>` tags.
</Info>
### Custom Error Classes
```typescript
class WorkerUnavailableError extends Error {
constructor() {
super('Claude-mem worker is not running or unreachable');
this.name = 'WorkerUnavailableError';
}
}
class WorkerTimeoutError extends Error {
constructor(endpoint: string) {
super(`Worker request timed out: ${endpoint}`);
this.name = 'WorkerTimeoutError';
}
}
```
### SSE Stream Error Handling
```typescript
function connectToSSE(onEvent: (event: any) => void) {
const eventSource = new EventSource('http://localhost:37777/stream');
eventSource.onmessage = (event) => {
try {
const data = JSON.parse(event.data);
onEvent(data);
} catch (error) {
console.error('SSE parse error:', error);
}
};
eventSource.onerror = (error) => {
console.error('SSE connection error:', error);
eventSource.close();
// Reconnect after 5 seconds
setTimeout(() => connectToSSE(onEvent), 5000);
};
return eventSource;
}
```
## Development Workflow
### Project Structure (Recommended)
```plaintext
vscode-extension/
├── src/
│ ├── extension.ts # Extension entry point
│ ├── services/
│ │ ├── WorkerClient.ts # HTTP client for worker
│ │ └── MemoryManager.ts # High-level memory operations
│ ├── chat/
│ │ └── participant.ts # Chat participant implementation
│ └── tools/
│ ├── search.ts # Search language model tool
│ └── context.ts # Context injection tool
├── package.json
├── tsconfig.json
└── README.md
```
### Build Configuration (esbuild)
```javascript
// build.js
const esbuild = require('esbuild');
esbuild.build({
entryPoints: ['src/extension.ts'],
bundle: true,
outfile: 'dist/extension.js',
external: ['vscode'],
format: 'cjs',
platform: 'node',
target: 'node18',
sourcemap: true
}).catch(() => process.exit(1));
```
### package.json (VSCode Extension)
```json
{
"name": "claude-mem-vscode",
"displayName": "Claude-Mem",
"version": "1.0.0",
"engines": {
"vscode": "^1.95.0"
},
"activationEvents": [
"onStartupFinished"
],
"main": "./dist/extension.js",
"contributes": {
"chatParticipants": [
{
"id": "claude-mem",
"name": "memory",
"description": "Search your persistent memory"
}
],
"languageModelTools": [
{
"name": "claude-mem-search",
"displayName": "Search Memory",
"description": "Search persistent memory for observations, sessions, and prompts"
}
]
},
"scripts": {
"build": "node build.js",
"watch": "node build.js --watch",
"package": "vsce package"
},
"devDependencies": {
"@types/vscode": "^1.95.0",
"esbuild": "^0.19.0",
"typescript": "^5.3.0"
}
}
```
### Local Testing Loop
<Steps>
<Step title="Terminal 1: Watch build">
```bash
npm run watch
```
</Step>
<Step title="Terminal 2: Check worker status">
```bash
npm run worker:status
npm run worker:logs
```
</Step>
<Step title="Terminal 3: Test API manually">
```bash
curl http://localhost:37777/api/health
curl "http://localhost:37777/api/search?query=test&limit=5"
```
</Step>
<Step title="VSCode: Launch extension host">
Press F5 to launch extension host
</Step>
</Steps>
### Debug Configuration (.vscode/launch.json)
```json
{
"version": "0.2.0",
"configurations": [
{
"name": "Run Extension",
"type": "extensionHost",
"request": "launch",
"args": [
"--extensionDevelopmentPath=${workspaceFolder}"
],
"outFiles": [
"${workspaceFolder}/dist/**/*.js"
],
"preLaunchTask": "npm: build"
}
]
}
```
## Testing Strategy
### Unit Tests (Worker Client)
```typescript
import { describe, it, expect } from 'vitest';
import { WorkerClient } from '../src/services/WorkerClient';
describe('WorkerClient', () => {
it('should check worker health', async () => {
const client = new WorkerClient();
const healthy = await client.isHealthy();
expect(healthy).toBe(true);
});
it('should queue observation', async () => {
const client = new WorkerClient();
const result = await client.queueObservation({
claudeSessionId: 'test-123',
tool_name: 'Bash',
tool_input: { command: 'ls' },
tool_response: { stdout: 'file1.txt' },
cwd: '/tmp'
});
expect(result.status).toBe('queued');
});
it('should search observations', async () => {
const client = new WorkerClient();
const results = await client.search({ query: 'test', limit: 5 });
expect(results).toHaveProperty('observations');
});
});
```
### Integration Tests (With Worker Spawning)
```typescript
import { spawn } from 'child_process';
import { describe, it, expect, beforeAll, afterAll } from 'vitest';
describe('Worker Integration', () => {
let workerProcess: ReturnType<typeof spawn>;
beforeAll(async () => {
// Start worker process
workerProcess = spawn('node', ['dist/worker-service.js'], {
env: { ...process.env, CLAUDE_MEM_WORKER_PORT: '37778' }
});
// Wait for worker to be ready
await new Promise(resolve => setTimeout(resolve, 2000));
});
afterAll(() => {
workerProcess.kill();
});
it('should respond to health check', async () => {
const response = await fetch('http://localhost:37778/api/health');
expect(response.ok).toBe(true);
});
});
```
### Manual Testing Checklist
<AccordionGroup>
<Accordion title="Phase 1: Connection & Health">
- [ ] Worker starts successfully (`npm run worker:status`)
- [ ] Health endpoint responds (`curl http://localhost:37777/api/health`)
- [ ] SSE stream connects (`curl http://localhost:37777/stream`)
</Accordion>
<Accordion title="Phase 2: Session Lifecycle">
- [ ] Queue observation creates session
- [ ] Observation appears in database
- [ ] Privacy tags are stripped
- [ ] Private prompts are skipped
- [ ] Queue summary creates summary
- [ ] Complete session stops processing
</Accordion>
<Accordion title="Phase 3: Search & Retrieval">
- [ ] Search observations by query
- [ ] Search sessions by query
- [ ] Search prompts by query
- [ ] Get recent context for project
- [ ] Get timeline around observation
- [ ] Semantic shortcuts (decisions, changes, how-it-works)
</Accordion>
<Accordion title="Phase 4: Real-Time Updates">
- [ ] SSE broadcasts processing status
- [ ] SSE broadcasts new observations
- [ ] SSE broadcasts new summaries
- [ ] SSE broadcasts new prompts
</Accordion>
<Accordion title="Phase 5: Error Handling">
- [ ] Graceful degradation when worker unavailable
- [ ] Timeout handling for slow requests
- [ ] Retry logic for transient failures
</Accordion>
</AccordionGroup>
## Code Examples
### Complete WorkerClient Implementation
<CodeGroup>
```typescript WorkerClient.ts
export class WorkerClient {
private baseUrl: string;
constructor(port: number = 37777) {
this.baseUrl = `http://localhost:${port}`;
}
async isHealthy(): Promise<boolean> {
try {
const response = await fetch(`${this.baseUrl}/api/health`, {
signal: AbortSignal.timeout(2000)
});
return response.ok;
} catch {
return false;
}
}
async queueObservation(data: {
claudeSessionId: string;
tool_name: string;
tool_input: any;
tool_response: any;
cwd?: string;
}): Promise<{ status: string; reason?: string }> {
const response = await fetch(`${this.baseUrl}/api/sessions/observations`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify(data),
signal: AbortSignal.timeout(5000)
});
if (!response.ok) {
throw new Error(`Failed to queue observation: ${response.statusText}`);
}
return await response.json();
}
async queueSummarize(data: {
claudeSessionId: string;
last_user_message?: string;
last_assistant_message?: string;
}): Promise<{ status: string; reason?: string }> {
const response = await fetch(`${this.baseUrl}/api/sessions/summarize`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify(data),
signal: AbortSignal.timeout(5000)
});
if (!response.ok) {
throw new Error(`Failed to queue summary: ${response.statusText}`);
}
return await response.json();
}
async completeSession(claudeSessionId: string): Promise<void> {
const response = await fetch(`${this.baseUrl}/api/sessions/complete`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ claudeSessionId }),
signal: AbortSignal.timeout(5000)
});
if (!response.ok) {
throw new Error(`Failed to complete session: ${response.statusText}`);
}
}
async search(params: {
query?: string;
type?: 'observations' | 'sessions' | 'prompts';
format?: 'index' | 'full';
limit?: number;
project?: string;
}): Promise<any> {
const queryString = new URLSearchParams(
Object.entries(params)
.filter(([_, v]) => v !== undefined)
.map(([k, v]) => [k, String(v)])
).toString();
const response = await fetch(
`${this.baseUrl}/api/search?${queryString}`,
{ signal: AbortSignal.timeout(10000) }
);
if (!response.ok) {
throw new Error(`Search failed: ${response.statusText}`);
}
return await response.json();
}
connectSSE(onEvent: (event: any) => void): EventSource {
const eventSource = new EventSource(`${this.baseUrl}/stream`);
eventSource.onmessage = (event) => {
try {
const data = JSON.parse(event.data);
onEvent(data);
} catch (error) {
console.error('SSE parse error:', error);
}
};
eventSource.onerror = (error) => {
console.error('SSE connection error:', error);
};
return eventSource;
}
}
```
</CodeGroup>
### Search Language Model Tool
```typescript
import * as vscode from 'vscode';
import { WorkerClient } from './WorkerClient';
export function registerSearchTool(context: vscode.ExtensionContext) {
const client = new WorkerClient();
const searchTool = vscode.lm.registerTool('claude-mem-search', {
description: 'Search persistent memory for observations, sessions, and prompts',
inputSchema: {
type: 'object',
properties: {
query: {
type: 'string',
description: 'Search query text'
},
type: {
type: 'string',
enum: ['observations', 'sessions', 'prompts'],
description: 'Type of results to return'
},
limit: {
type: 'number',
description: 'Maximum number of results',
default: 10
}
},
required: ['query']
},
invoke: async (options, token) => {
const { query, type, limit = 10 } = options.input;
try {
const results = await client.search({
query,
type,
format: 'index',
limit
});
// Format results for language model
let formatted = '';
if (results.observations?.length > 0) {
formatted += '## Observations\n\n';
for (const obs of results.observations) {
formatted += `- **${obs.title}** (${obs.project})\n`;
formatted += ` ${obs.summary}\n`;
if (obs.concepts?.length > 0) {
formatted += ` Concepts: ${obs.concepts.join(', ')}\n`;
}
formatted += '\n';
}
}
return new vscode.LanguageModelToolResult([
new vscode.LanguageModelTextPart(formatted)
]);
} catch (error) {
return new vscode.LanguageModelToolResult([
new vscode.LanguageModelTextPart(`Error: ${error.message}`)
]);
}
}
});
context.subscriptions.push(searchTool);
}
```
## Critical Implementation Notes
<Warning>
### sessionDbId vs claudeSessionId
**IMPORTANT:** Use `claudeSessionId` (string) for new API endpoints, not `sessionDbId` (number).
- `sessionDbId` - Numeric database ID (legacy endpoints only)
- `claudeSessionId` - String identifier from Claude platform (new endpoints)
</Warning>
<Warning>
### JSON String Fields
Fields like `facts`, `concepts`, and `files_touched` are stored as JSON strings and require parsing:
```typescript
const observation = await client.getObservationById(123);
const facts = JSON.parse(observation.facts); // string[] array
const concepts = JSON.parse(observation.concepts); // string[] array
```
</Warning>
<Warning>
### Timestamps
All `created_at_epoch` fields are in **milliseconds**, not seconds:
```typescript
const date = new Date(observation.created_at_epoch); // ✅ Correct
const date = new Date(observation.created_at_epoch * 1000); // ❌ Wrong (already in ms)
```
</Warning>
<Info>
### Asynchronous Processing
Workers process observations/summaries asynchronously. Results appear in the database 1-2 seconds after queuing. Use SSE events for real-time notifications.
</Info>
<Info>
### Privacy Tags
Always wrap sensitive content in `<private>` tags to prevent storage:
```typescript
const userMessage = '<private>API key: sk-1234567890</private>';
// This observation will be skipped (entire prompt is private)
```
</Info>
## Additional Resources
<CardGroup cols={2}>
<Card title="Documentation" icon="book" href="https://claude-mem.ai">
Complete claude-mem documentation
</Card>
<Card title="GitHub" icon="github" href="https://github.com/thedotmack/claude-mem">
Source code and issue tracker
</Card>
<Card title="Worker Service" icon="server" href="/architecture/worker-service">
Worker architecture details
</Card>
<Card title="Database Schema" icon="database" href="/architecture/database">
Database structure and queries
</Card>
</CardGroup>