Accept story 34: Per-Project Agent Configuration and Role Definitions

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>

server/src/http/mod.rs

@@ -35,7 +35,7 @@ pub fn build_routes(ctx: AppContext) -> impl poem::Endpoint {
         .nest("/docs", docs_service.swagger_ui())
         .at("/ws", get(ws::ws_handler))
         .at(
-            "/agents/:story_id/stream",
+            "/agents/:story_id/:agent_name/stream",
             get(agents_sse::agent_stream),
         )
         .at("/health", get(health::health))