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/time_of_day.py

@@ -0,0 +1,50 @@
+from __future__ import annotations
+from typing import ClassVar
+from .base import BaseAgent, AgentInput, AgentOutput
+
+_DOW_NAMES = ["Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday", "Sunday"]
+
+
+class TimeOfDayAgent(BaseAgent):
+    """Frames the current moment relative to the user's productive peak."""
+    agent_id: ClassVar[str] = "time-of-day"
+    ttl_seconds: ClassVar[int] = 900  # 15m — must stay current-hour accurate
+    version: ClassVar[str] = "1.0.0"
+
+    def compute(self, inp: AgentInput) -> AgentOutput:
+        hour = inp.now.hour
+        dow = inp.now.weekday()  # 0=Monday … 6=Sunday
+        preferred = inp.profile.get("preferred_hour")
+        is_weekend = dow >= 5
+
+        parts = [f"It is {hour:02d}:00 on {_DOW_NAMES[dow]} ({self._label(hour)})."]
+
+        if is_weekend:
+            parts.append("Weekend context — prefer personal or reflective tips over work tasks.")
+
+        if preferred is not None:
+            ph = int(preferred)
+            delta = min(abs(hour - ph), 24 - abs(hour - ph))  # circular distance
+            if delta == 0:
+                parts.append(
+                    f"This is the user's peak productivity hour ({ph:02d}:00) — "
+                    f"a high-impact tip is appropriate."
+                )
+            elif delta <= 2:
+                parts.append(f"Approaching the user's peak productivity window ({ph:02d}:00).")
+        else:
+            parts.append("No preferred-hour data yet.")
+
+        prompt = " ".join(parts)
+        snapshot = {"hour": hour, "day_of_week": dow, "preferred_hour": preferred}
+        return self._make_output(inp, prompt, snapshot)
+
+    @staticmethod
+    def _label(hour: int) -> str:
+        if 5 <= hour < 12:
+            return "morning"
+        if 12 <= hour < 17:
+            return "afternoon"
+        if 17 <= hour < 21:
+            return "evening"
+        return "night"