ly-wang19 9535a4f1c2

perf(subagents): dedup streamed AI messages via a seen-id set (O(n^2) -> O(n)) (#3687) ...

_aexecute collects AI messages from agent.astream(stream_mode="values"),
which re-yields the full state every super-step. The duplicate check rescanned
the append-only ai_messages list on every chunk -- any(m["id"] == message_id) --
so a run with M messages did O(M^2) work, and M reaches max_turns=150 for the
general-purpose / deep-research subagent.

Track an id-keyed set alongside ai_messages: id-bearing messages become O(1)
set lookups, and the id-less full-dict-compare fallback is preserved. Behavior
is unchanged.

Co-authored-by: ly-wang19 <ly-wang19@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-22 14:31:27 +08:00

..

deerflow

perf(subagents): dedup streamed AI messages via a seen-id set (O(n^2) -> O(n)) (#3687)

2026-06-22 14:31:27 +08:00

pyproject.toml

feat(community): add GroundRoute web search + fetch engine (#3675)

2026-06-21 15:55:10 +08:00