Files
flynn/CLAUDE.md
T
William Valentin 9be8f76bc7 feat: implement Tier 3 features — lane queue, credential redaction, token dashboard, xAI, Voyage AI
- Lane Queue: per-session FIFO queue in gateway replacing reject-when-busy (9 tests)
- Credential Redaction: redactConfig() expanded to cover 18+ secret fields (16 tests)
- Web UI Token Dashboard: system.tokenUsage endpoint + Usage page with summary cards
- xAI (Grok) Provider: OpenAI-compatible client with model pricing
- Voyage AI Embeddings: new embedding provider with configurable dimensions (5 tests)
- Update gap analysis: 90→95 match (70%→74%), Tier 3 section marked DONE
- Update state.json: test count 1001→1034, add tier3_completion entry

Total: 1034 tests passing across 85 files, typecheck clean
2026-02-09 10:32:57 -08:00

3.9 KiB

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

pnpm build          # Compile TypeScript to dist/
pnpm dev            # Run daemon with watch mode (tsx watch)
pnpm start          # Start production build
pnpm tui            # Minimal TUI (readline)
pnpm tui:fs         # Fullscreen TUI (React/Ink)
pnpm test           # Run vitest in watch mode
pnpm test:run       # Run tests once (CI)
pnpm lint           # ESLint
pnpm typecheck      # TypeScript check (no emit)

Run a single test file: pnpm test:run src/path/to/file.test.ts

Architecture

Flynn is a multi-channel AI assistant daemon. Messages flow: Channel Adapter → AgentOrchestrator → NativeAgent → ModelClient, with tools executed in the agent loop.

Core Abstractions

ModelClient (src/models/types.ts): chat(request): Promise<ChatResponse>. Providers: Anthropic, OpenAI, Gemini, Bedrock, Ollama, llama.cpp, GitHub Models, OpenRouter, Zhipu. Factory in src/daemon/index.ts (createClientFromConfig()). ModelRouter (src/models/router.ts) manages tiers (default/fast/complex/local) with fallback chains.

ChannelAdapter (src/channels/types.ts): connect(), disconnect(), send(), onMessage(). Adapters: Telegram, Discord, Slack, WhatsApp, WebChat. Registered in ChannelRegistry, each channel+sender pair gets its own session.

Tool (src/tools/types.ts): { name, description, inputSchema, execute(args): Promise<ToolResult> }. Three patterns:

  • Static: export const fooTool: Tool = { ... } (no deps)
  • Factory: export function createFooTool(dep): Tool (single tool needing deps)
  • Multi-factory: export function createFooTools(dep): Tool[] (related tool set)

Registration chain: tool file → src/tools/builtin/index.tssrc/tools/index.ts → registered in src/daemon/index.ts.

Tool Policy (src/tools/policy.ts): Profiles (minimal/messaging/coding/full), groups (group:fs/runtime/web/memory), allow/deny with glob patterns.

NativeAgent (src/backends/native/agent.ts): Core agent loop with tool execution. AgentOrchestrator (src/backends/native/orchestrator.ts) wraps it with session management, compaction, memory extraction, and delegation to different model tiers.

Other Key Systems

  • Config: YAML + Zod validation (src/config/schema.ts). Supports ${ENV_VAR} expansion.
  • Sessions: SQLite via SessionStore (src/session/store.ts). TTL-based pruning.
  • Memory: Namespace-based files + hybrid search (keyword + vector). Embedding providers configurable.
  • Hooks: Pattern-based confirmation engine (src/hooks/). Actions: confirm/log/silent.
  • Sandbox: Docker per-session containers (src/sandbox/manager.ts).
  • Automation: Cron scheduler, webhooks (HMAC), heartbeat monitor, Gmail watcher (src/automation/).
  • Gateway: WebSocket JSON-RPC + HTTP server + vanilla JS dashboard (src/gateway/).
  • System Prompt: Template search for SOUL.md/AGENTS.md/IDENTITY.md/USER.md/TOOLS.md (src/prompt/template.ts).

Code Conventions

  • ES Modules with .js extensions in all imports (e.g., import { foo } from './bar.js')
  • type keyword for type-only imports: import type { Config } from './schema.js'
  • Import order: stdlib → third-party → local
  • Naming: PascalCase for types/classes, camelCase for functions/variables, _prefix for private fields
  • Files: camelCase for .ts, PascalCase for .tsx
  • Tests: co-located as *.test.ts next to source. Vitest with describe/it/expect.
  • Target: ES2022, NodeNext modules, strict mode. Requires Node.js >=22.
  • Error pattern: instanceof Error checks, descriptive messages, try-catch in stream handlers

State Tracking

After implementing features, update docs/plans/state.json (test counts, progress, feature gap scorecard). Commit alongside the feature change.