axelray-dev 28011413bc fix(copilot): guard token refresh with asyncio.Lock to prevent race condition ...

_get_copilot_access_token had a check-then-act race: concurrent chat()
calls after token expiry both fetched new tokens and clobbered each other.
Add asyncio.Lock with double-checked locking so only one fetch happens
per expiry window.

Closes #4677

2026-07-04 21:19:12 +08:00

..

openai_responses

Improve tool call validation strictness (#4190)

2026-06-09 14:50:40 +08:00

__init__.py

chore(release): prepare v0.2.2

2026-06-22 20:53:28 +08:00

anthropic_provider.py

fix(providers): omit temperature for sonnet 5

2026-07-03 15:48:46 +08:00

azure_openai_provider.py

Add optional Nanobot plugin controls (#4396)

2026-07-03 18:17:52 +08:00

base.py

fix(agent): harden tool-call handling against malformed upstream relays

2026-06-28 19:46:59 +08:00

bedrock_provider.py

Add optional Nanobot plugin controls (#4396)

2026-07-03 18:17:52 +08:00

factory.py

feat(providers): support provider-scoped proxy config

2026-06-30 17:33:36 +08:00

fallback_provider.py

fix(fallback): treat empty API choices as fallbackable error

2026-06-19 14:59:44 +08:00

github_copilot_provider.py

fix(copilot): guard token refresh with asyncio.Lock to prevent race condition

2026-07-04 21:19:12 +08:00

image_generation.py

fix openai image reference home paths

2026-06-19 17:16:09 +08:00

openai_codex_provider.py

feat(providers): support provider-scoped proxy config

2026-06-30 17:33:36 +08:00

openai_compat_provider.py

feat(providers): support provider-scoped proxy config

2026-06-30 17:33:36 +08:00

registry.py

refactor(webui): derive provider model catalog kind

2026-07-01 12:59:06 +08:00

transcription.py

fix(asr): normalize StepFun transcription endpoint

2026-06-10 15:50:38 +08:00