perf: use SQL aggregation for feedback stats and thread token usage

Replace Python-side counting in FeedbackRepository.aggregate_by_run with
a single SELECT COUNT/SUM query. Add RunStore.aggregate_tokens_by_thread
abstract method with SQL GROUP BY implementation in RunRepository and
Python fallback in MemoryRunStore. Simplify the thread_token_usage
endpoint to delegate to the new method, eliminating the limit=10000
truncation risk.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

backend/packages/harness/deerflow/runtime/runs/store/base.py

@@ -84,3 +84,13 @@ class RunStore(abc.ABC):
     @abc.abstractmethod
     async def list_pending(self, *, before: str | None = None) -> list[dict[str, Any]]:
         pass
+
+    @abc.abstractmethod
+    async def aggregate_tokens_by_thread(self, thread_id: str) -> dict[str, Any]:
+        """Aggregate token usage for completed runs in a thread.
+
+        Returns a dict with keys: total_tokens, total_input_tokens,
+        total_output_tokens, total_runs, by_model (model_name → {tokens, runs}),
+        by_caller ({lead_agent, subagent, middleware}).
+        """
+        pass

backend/packages/harness/deerflow/runtime/runs/store/memory.py

@@ -77,3 +77,24 @@ class MemoryRunStore(RunStore):
         results = [r for r in self._runs.values() if r["status"] == "pending" and r["created_at"] <= now]
         results.sort(key=lambda r: r["created_at"])
         return results
+
+    async def aggregate_tokens_by_thread(self, thread_id: str) -> dict[str, Any]:
+        completed = [r for r in self._runs.values() if r["thread_id"] == thread_id and r.get("status") in ("success", "error")]
+        by_model: dict[str, dict] = {}
+        for r in completed:
+            model = r.get("model_name") or "unknown"
+            entry = by_model.setdefault(model, {"tokens": 0, "runs": 0})
+            entry["tokens"] += r.get("total_tokens", 0)
+            entry["runs"] += 1
+        return {
+            "total_tokens": sum(r.get("total_tokens", 0) for r in completed),
+            "total_input_tokens": sum(r.get("total_input_tokens", 0) for r in completed),
+            "total_output_tokens": sum(r.get("total_output_tokens", 0) for r in completed),
+            "total_runs": len(completed),
+            "by_model": by_model,
+            "by_caller": {
+                "lead_agent": sum(r.get("lead_agent_tokens", 0) for r in completed),
+                "subagent": sum(r.get("subagent_tokens", 0) for r in completed),
+                "middleware": sum(r.get("middleware_tokens", 0) for r in completed),
+            },
+        }