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>

ml/agents/registry.py

@@ -0,0 +1,28 @@
+from __future__ import annotations
+from .base import BaseAgent
+from .overdue_task import OverdueTaskAgent
+from .momentum import MomentumAgent
+from .time_of_day import TimeOfDayAgent
+from .recent_patterns import RecentPatternsAgent
+from .focus_area import FocusAreaAgent
+
+_AGENTS: dict[str, BaseAgent] = {
+    a.agent_id: a
+    for a in [
+        OverdueTaskAgent(),
+        MomentumAgent(),
+        TimeOfDayAgent(),
+        RecentPatternsAgent(),
+        FocusAreaAgent(),
+    ]
+}
+
+
+def get_agent(agent_id: str) -> BaseAgent:
+    if agent_id not in _AGENTS:
+        raise KeyError(f"Unknown agent: {agent_id!r}. Known: {sorted(_AGENTS)}")
+    return _AGENTS[agent_id]
+
+
+def all_agents() -> list[BaseAgent]:
+    return list(_AGENTS.values())