rayhpeng 0af0ae7fbb 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>

2026-04-06 11:20:34 +08:00

..

channels

fix(channels): normalize slack allowed user ids (#1802)

2026-04-05 18:04:21 +08:00

gateway

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

2026-04-06 11:20:34 +08:00

__init__.py

refactor: split backend into harness (deerflow.*) and app (app.*) (#1131)

2026-03-14 22:55:52 +08:00