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/serving/prompts.py

@@ -108,6 +108,52 @@ PROMPTS: dict[str, Prompt] = {
 }
 
 
+# ── v4-orchestrator ────────────────────────────────────────────────────────
+# Not a Prompt entry — takes pre-computed agent snippets, not a _Ctx.
+
+_SYS_V4_ORCHESTRATOR = (
+    "You are a personal advisor generating a single, perfectly-timed tip. "
+    "Multiple specialized agents have analyzed the user's current context and provided "
+    "their insights below. Synthesize their combined perspective to generate exactly ONE "
+    "tip that is specific, actionable, and relevant right now. "
+    "Respond ONLY with a JSON object with keys: "
+    '"id" (short slug), "content" (the tip, ≤2 sentences), '
+    '"rationale" (why now, ≤1 sentence). '
+    "No markdown, no prose outside the JSON object."
+)
+
+
+def build_orchestrator_messages(
+    agent_outputs: list[dict],
+    tasks: list[dict],
+    hour_of_day: int,
+    day_of_week: int,
+) -> list[dict]:
+    """Build the [system, user] message list for the orchestrator LLM call.
+
+    agent_outputs: list of {agent_id, prompt_text} dicts.
+    Falls back to raw task summary when agent_outputs is empty.
+    """
+    lines = [f"Current time: {hour_of_day:02d}:00, day_of_week={day_of_week}", ""]
+    if agent_outputs:
+        lines.append("Context from analysis agents:")
+        for s in agent_outputs:
+            lines.append(f"[{s['agent_id']}] {s['prompt_text']}")
+    else:
+        overdue = [t for t in tasks if t.get("is_overdue")]
+        lines.append(
+            f"No pre-computed agent context available. "
+            f"Tasks: {len(tasks)} total, {len(overdue)} overdue."
+        )
+        for t in tasks[:3]:
+            lines.append(f"  - {t.get('content', '?')}")
+    lines.append("\nGenerate one tip as a JSON object.")
+    return [
+        {"role": "system", "content": _SYS_V4_ORCHESTRATOR},
+        {"role": "user", "content": "\n".join(lines)},
+    ]
+
+
 def default_version() -> str:
     return os.getenv("DEFAULT_PROMPT_VERSION", "v1")