xzq.xu 6028b4828b perf(loop): parallelize tool execution with asyncio.gather ...

Tool calls from a single LLM response are independent by design —
the model batches them precisely because they can run concurrently.
Replace the serial for-loop with asyncio.gather so N tools complete
in max(time_i) instead of sum(time_i).

Made-with: Cursor

2026-03-22 20:45:31 +08:00

..

agent

perf(loop): parallelize tool execution with asyncio.gather

2026-03-22 20:45:31 +08:00

bus

style: unify code formatting and import order

2026-02-28 20:55:43 +08:00

channels

feat(whatsapp): add group_policy to control bot response behavior in groups

2026-03-22 20:45:31 +08:00

cli

feat(provider): add OpenVINO Model Server provider (#2193)

2026-03-22 20:45:31 +08:00

config

feat(provider): add OpenVINO Model Server provider (#2193)

2026-03-22 20:45:31 +08:00

cron

feat(cron): add run history tracking for cron jobs

2026-03-21 02:28:35 +08:00

heartbeat

fix(heartbeat): inject shared current time context into phase 1

2026-03-16 10:52:26 +08:00

providers

feat(provider): add OpenVINO Model Server provider (#2193)

2026-03-22 20:45:31 +08:00

security

security: add SSRF protection, untrusted content marking, and internal URL blocking

2026-03-16 15:05:26 +08:00

session

fix: keep truncated session history tool-call consistent

2026-03-16 17:25:30 +08:00

skills

cleanup

2026-03-13 14:09:38 +08:00

templates

refactor(cron): remove CLI cron commands and unify scheduling via cron tool

2026-03-03 05:51:24 +00:00

utils

fix(agent): count all message fields in token estimation

2026-03-22 12:19:44 +08:00

__init__.py

bump version to 0.1.4.post5

2026-03-16 15:11:15 +00:00

__main__.py

🐈nanobot: hello world!

2026-02-01 07:36:42 +00:00