feat(ml): multi-agent context framework + v4 orchestrator prompt

Adds ml/agents/ — five specialised sub-agents (overdue_task, momentum,
time_of_day, recent_patterns, focus_area) each producing a prompt snippet
from user signals. A registry wires them up; the orchestrator prompt in
ml/serving/prompts.py synthesises their outputs into one tip via LiteLLM.

Also wires /api/agents route in the API and updates the Dockerfile to copy
the full ml/ tree with PYTHONPATH=/app so agent imports resolve correctly.

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

services/api/src/index.ts

@@ -17,6 +17,7 @@ import { userRouter } from './routes/user.js';
 import { pushRouter } from './routes/push.js';
 import { adminRouter, adminInternalRouter } from './routes/admin.js';
 import benchRouter from './routes/bench.js';
+import agentOutputsRouter from './routes/agent-outputs.js';
 import { mkdir } from 'fs/promises';
 import { dirname } from 'path';
 import { requireAuth } from './middleware/session.js';
@@ -68,6 +69,7 @@ app.use('/api/push', pushRouter);
 app.use('/api/admin', adminRouter);
 app.use('/api/admin', adminInternalRouter);
 app.use('/api/bench', requireAuth as any, requireAdmin as any, benchRouter);
+app.use('/api/agents', agentOutputsRouter);
 
 app.use('/api/ml', requireAuth as any, requireAdmin as any, async (req: Request, res: Response) => {
   const mlUrl = config.ML_SERVING_URL;