6d57b06636
Replace single [agent] config with multi-agent [[agent]] roster system. Each agent has name, role, model, allowed_tools, max_turns, max_budget_usd, and system_prompt fields that map to Claude CLI flags at spawn time. - AgentConfig expanded with structured fields, validated at startup (panics on duplicate names, empty names, non-positive budgets/turns) - Backwards-compatible: legacy [agent] format auto-wraps with deprecation warning - AgentPool uses composite "story_id:agent_name" keys for concurrent agents - agent_name added to AgentEvent variants, AgentInfo, start/stop/subscribe APIs - GET /agents/config returns roster, POST /agents/config/reload hot-reloads - POST /agents/start accepts optional agent_name, /agents/stop requires it - SSE route updated to /agents/:story_id/:agent_name/stream - Frontend: roster badges, agent selector dropdown, composite-key state - Project root initialized to cwd at startup so config endpoints work immediately Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Living Spec Standalone (Web Server Binary)
This app runs as a single Rust web server binary that serves the Vite/React frontend and exposes APIs.
The frontend lives in the frontend/ directory.
You can also run the frontend and backend separately in development (Vite dev server + Rust API).
Running it in development
# Build the frontend
cd frontend
pnpm install
pnpm dev
# Run the server (serves embedded frontend/dist/)
cargo run
Production
# Build the release binary (also builds the frontend via build.rs)
cargo build --release
# Run the server (serves embedded frontend/dist/)
./target/release/story-kit-server
Testing
Frontend Tests
The frontend uses Vitest for unit tests and Playwright for end-to-end tests.
cd frontend
# Run unit tests
pnpm test
# Run end-to-end tests
pnpm test:e2e
Backend Tests
This project uses nextest for running tests and cargo-llvm-cov for code coverage.
Install Tools
cargo install cargo-nextest cargo-llvm-cov
Run Tests
# Run all tests
cargo nextest run
# Run specific module
cargo nextest run search_files
# Run with verbose output
cargo nextest run --no-capture
Generate Coverage
# HTML report (opens in browser)
cargo llvm-cov nextest --html --open
# Terminal output
cargo llvm-cov nextest
# LCOV format (for CI)
cargo llvm-cov nextest --lcov --output-path lcov.info
# Clean coverage data
cargo llvm-cov clean
Configuration
- Nextest config:
.config/nextest.toml - Coverage output:
target/llvm-cov/html/index.html
Current Coverage (search_files module)
Module: commands/search.rs
├── Region Coverage: 75.36%
├── Function Coverage: 69.05%
└── Line Coverage: 72.55%
Available Test Profiles
# Development (default)
cargo nextest run
# CI with retries
cargo nextest run --profile ci
# Coverage optimized
cargo nextest run --profile coverage