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>
This commit is contained in:
@@ -5,16 +5,16 @@ use poem::web::{Data, Path};
|
||||
use poem::{Body, IntoResponse, Response};
|
||||
use std::sync::Arc;
|
||||
|
||||
/// SSE endpoint: `GET /agents/:story_id/stream`
|
||||
/// SSE endpoint: `GET /agents/:story_id/:agent_name/stream`
|
||||
///
|
||||
/// Streams `AgentEvent`s as Server-Sent Events. Each event is JSON-encoded
|
||||
/// with `data:` prefix and double newline terminator per the SSE spec.
|
||||
#[handler]
|
||||
pub async fn agent_stream(
|
||||
Path(story_id): Path<String>,
|
||||
Path((story_id, agent_name)): Path<(String, String)>,
|
||||
ctx: Data<&Arc<AppContext>>,
|
||||
) -> impl IntoResponse {
|
||||
let mut rx = match ctx.agents.subscribe(&story_id) {
|
||||
let mut rx = match ctx.agents.subscribe(&story_id, &agent_name) {
|
||||
Ok(rx) => rx,
|
||||
Err(e) => {
|
||||
return Response::builder()
|
||||
|
||||
Reference in New Issue
Block a user