feat(agents): semantic task clustering + focus-area inferred preferred_areas (#97, #113)

- New ml/agents/clustering.py: embed task content via nomic-embed-text
  (Ollama), greedy cosine clustering (threshold 0.72, max 6 clusters),
  graceful fallback to project-id grouping when Ollama is unreachable
- focus_area v2.0.0: compute() uses semantic clusters as focus areas;
  adds preferred_areas InferredParam inferred from top-2 projects by
  task_completion count
- 135 tests, all passing

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

ml/agents/tests/test_agents.py

@@ -240,11 +240,13 @@ class TestFocusAreaAgent:
 
     def test_default_project_fallback(self):
         out = self.agent.compute(_inp(tasks=[_task("No project task")]))
-        assert "default project" in out.prompt_text
+        # Tasks without project_id fall back to a "Tasks" bucket
+        assert "Tasks" in out.prompt_text
 
     def test_snapshot_keys(self):
         out = self.agent.compute(_inp(tasks=[_task("T1", project_id="A")]))
-        assert {"top_project", "top_task_count", "top_overdue_count", "project_count", "preferred_areas"} == set(out.signals_snapshot)
+        assert {"top_cluster_label", "top_task_count", "top_overdue_count", "cluster_count",
+                "strategy", "preferred_areas"} == set(out.signals_snapshot)
 
 
 # ── Registry ─────────────────────────────────────────────────────────────────