feat(clustering): 1h TTL + skip recompute when tasks unchanged

focus-area now recomputes at most once per hour, and only if the task list
actually changed since the last compute.

- focus-area TTL: 43200s → 3600s; version bumped to 2.1.0
- computeAndStore hashes sorted task contents (MD5) and checks the stored
  _task_hash in the existing snapshot; skips the ml-serving call when the
  hash matches and the output isn't expired
- ml-serving injects _task_hash into the snapshot so the next cycle can compare

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

ml/agents/focus_area.py

@@ -20,7 +20,7 @@ def _infer_preferred_areas(history: UserHistory) -> list[str]:
 
 MANIFEST = AgentManifest(
     id="focus-area",
-    version="2.0.0",  # semantic clustering via nomic-embed-text (#97, #113)
+    version="2.1.0",  # 1h TTL + task-change detection (#129)
     description="Identifies the most congested semantic focus area in the user's task list.",
     pref_schema={
         "type": "object",
@@ -37,7 +37,7 @@ MANIFEST = AgentManifest(
     context_schema=["todoist.tasks"],
     required_consents=["data:core", "data:todoist"],
     output_contract={"type": "snippet", "format": "free_text"},
-    ttl_sec=43_200,
+    ttl_sec=3_600,
     inferred_params=[
         InferredParam(
             key="preferred_areas",
@@ -54,7 +54,7 @@ class FocusAreaAgent(BaseAgent):
     """Identifies the most congested semantic focus area in the user's task list."""
     agent_id: ClassVar[str] = MANIFEST.id
     ttl_seconds: ClassVar[int] = MANIFEST.ttl_sec
-    version: ClassVar[str] = MANIFEST.version
+    version: ClassVar[str] = MANIFEST.version  # 2.1.0
 
     def compute(self, inp: AgentInput) -> AgentOutput:
         preferred: list[str] = inp.agent_prefs.get("preferred_areas", [])

ml/agents/tests/test_per_agent_inference.py

@@ -662,7 +662,7 @@ class TestFocusAreaPreferredAreas:
 
     def test_version_bumped(self):
         from ml.agents.focus_area import MANIFEST as FA_MANIFEST
-        assert FA_MANIFEST.version == "2.0.0"
+        assert FA_MANIFEST.version == "2.1.0"
 
     def test_snapshot_uses_cluster_keys(self):
         tasks = [self._task("T", "work")]

ml/serving/main.py

@@ -199,6 +199,9 @@ class AgentComputeRequest(BaseModel):
     # Pre-fetched enrichment cache: {content_hash -> description}. Avoids re-calling
     # LiteLLM for task titles already expanded in a prior compute cycle.
     enrichment_cache: dict[str, str] = {}
+    # MD5 of sorted task contents; stored in snapshot so the next cycle can skip
+    # recompute when the task list hasn't changed.
+    task_hash: Optional[str] = None
 
 
 class AgentComputeResponse(BaseModel):
@@ -327,6 +330,8 @@ async def compute_agent(agent_id: str, req: AgentComputeRequest) -> AgentCompute
         log.error("agent_compute_failed", agent_id=agent_id, user_id=req.user_id, error=str(exc))
         raise HTTPException(status_code=500, detail=f"Agent compute failed: {exc}")
 
+    if req.task_hash:
+        output.signals_snapshot["_task_hash"] = req.task_hash
     new_enrichments: dict[str, str] = output.signals_snapshot.pop("_new_enrichments", {})
 
     log.info("agent_computed", agent_id=agent_id, user_id=req.user_id, expires_at=output.expires_at)