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/focus_area.py

@@ -0,0 +1,46 @@
+from __future__ import annotations
+from collections import defaultdict
+from typing import ClassVar
+from .base import BaseAgent, AgentInput, AgentOutput
+
+
+class FocusAreaAgent(BaseAgent):
+    """Identifies the most congested project/area in the user's task list."""
+    agent_id: ClassVar[str] = "focus-area"
+    ttl_seconds: ClassVar[int] = 43_200  # 12h
+    version: ClassVar[str] = "1.0.0"
+
+    def compute(self, inp: AgentInput) -> AgentOutput:
+        by_project: dict[str, list[dict]] = defaultdict(list)
+        for task in inp.tasks:
+            project = task.get("project_id") or task.get("project") or "default"
+            by_project[project].append(task)
+
+        if not by_project:
+            prompt = "No tasks available to identify a focus area."
+            return self._make_output(inp, prompt, {"project_count": 0})
+
+        # Score each project: overdue tasks count double
+        def score(tasks: list[dict]) -> float:
+            return sum(2.0 if t.get("is_overdue") else 1.0 for t in tasks)
+
+        top_project, top_tasks = max(by_project.items(), key=lambda kv: score(kv[1]))
+        overdue_in_top = sum(1 for t in top_tasks if t.get("is_overdue"))
+        label = "the default project" if top_project == "default" else f'"{top_project}"'
+        n = len(top_tasks)
+
+        parts = [
+            f"The user's most congested area is {label} "
+            f"({n} task{'s' if n != 1 else ''}, {overdue_in_top} overdue)."
+        ]
+        if overdue_in_top >= 3:
+            parts.append("Consider surfacing an action from this area.")
+
+        prompt = " ".join(parts)
+        snapshot = {
+            "top_project": top_project,
+            "top_task_count": n,
+            "top_overdue_count": overdue_in_top,
+            "project_count": len(by_project),
+        }
+        return self._make_output(inp, prompt, snapshot)