Accept story 30: Worktree-based agent orchestration

Add git worktree isolation for concurrent story agents. Each agent now
runs in its own worktree with setup/teardown commands driven by
.story_kit/project.toml config. Agents stream output via SSE and support
start/stop lifecycle with Pending/Running/Completed/Failed statuses.

Backend: config.rs (TOML parsing), worktree.rs (git worktree lifecycle),
refactored agents.rs (broadcast streaming), agents_sse.rs (SSE endpoint).
Frontend: AgentPanel.tsx with Run/Stop buttons and streaming output log.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

.story_kit/stories/current/30_worktree_agent_orchestration.md

@@ -1,50 +0,0 @@
----
-name: Worktree-Based Agent Orchestration
-test_plan: pending
----
-# Story 30: Worktree-Based Agent Orchestration
-
-## User Story
-As a user, I want to press a button in the frontend to spin up an agent that works on a story in its own git worktree, so that multiple stories can be worked on concurrently without branch conflicts.
-
-## Acceptance Criteria
-- [ ] The Rust binary can create a git worktree for a given story, on a new feature branch.
-- [ ] The Rust binary can remove a git worktree and clean up the feature branch after story completion.
-- [ ] Project-specific setup commands (e.g., dependency install) are configurable per-project, not hardcoded to any language or framework.
-- [ ] The Rust binary can spawn an agent process (e.g., Claude Code CLI) pointed at the worktree directory.
-- [ ] The backend exposes an API endpoint to start an agent for a given story (creates worktree, runs setup, spawns agent).
-- [ ] The backend exposes an API endpoint to stop a running agent and optionally tear down its worktree.
-- [ ] The backend tracks running agents and their status (idle/running/done/error).
-- [ ] The frontend displays a "Run" button on stories that are ready to be worked on.
-- [ ] The frontend shows agent status (running/done/error) for active stories.
-- [ ] Agent stdout/stderr is streamed to the frontend in real time (via WebSocket or SSE).
-
-## Configuration
-Agent and worktree behavior is driven by a project-level config file (e.g., `.story_kit/config.toml`), keeping the Rust binary language-agnostic. Projects can define multiple components, each with their own working directory and setup/teardown commands:
-
-```toml
-[[component]]
-name = "server"
-path = "."                          # relative to worktree root
-setup = ["cargo check"]
-teardown = []
-
-[[component]]
-name = "frontend"
-path = "frontend"
-setup = ["pnpm install"]
-teardown = []
-
-[agent]
-command = "claude"
-args = ["--print", "--directory", "{{worktree_path}}"]
-prompt = "Read .story_kit/README.md, then pick up story {{story_id}}"
-```
-
-Components are set up in order. Each `path` is relative to the worktree root.
-
-## Out of Scope
-- Coordinating merges to master when multiple agents finish simultaneously (see Story 29).
-- Lock file implementation for multi-agent conflict prevention (see Story 29).
-- Port management for dev servers within worktrees.
-- Agent-to-agent communication.