05d6850da5
feat: add scripted model test utilities ( #4362 )
2026-08-13 11:20:33 +09:00
4720150fde
fix: bind tool approvals to concrete invocations ( #4257 )
2026-08-07 11:59:01 +00:00
107260f992
fix(tracing): mark non-streaming agent span failures ( #4191 )
...
Co-authored-by: Henry Su <henrysu4707@gmail.com >
2026-08-05 10:47:53 +09:00
9f4292e5d8
fix: resolve agent tool name collisions consistently ( #4137 )
2026-08-03 04:54:49 +00:00
813a00324e
fix: redact invalid JSON payload in ModelBehaviorError data ( #3485 )
2026-05-21 23:54:12 +00:00
cdc0ad6b26
fix : #2061 handle invalid tool arguments JSON without crashing ( #2337 )
2026-01-20 10:46:30 +09:00
01f5e86ea5
Convert MCP schemas to strict where possible ( #414 )
...
## Summary:
Towards #404 . I made this configurable because it's not clear this is
always a good thing to do. I also made it default to False because I'm
not sure if this could cause errors.
If it works out well, we can switch the default in the future as a small
breaking changes
## Test Plan:
Unit tests
2025-04-01 16:50:13 -04:00
6d95a3f191
Mark handoff span as errored when multiple handoffs are requested ( #344 )
...
Also includes the set of requested agents in the error data.
<img width="968" alt="image"
src="https://github.com/user-attachments/assets/0c5c2e81-08f7-445c-bbb0-3e169ef744a5 "
/>
2025-03-26 10:44:59 -04:00
7031d4ab87
Remove redundant weaker tracing assertions
2025-03-20 13:49:38 +02:00
c03d314fb8
Stronger tracing tests with inline-snapshot
2025-03-11 22:57:14 +02:00
aaec57a426
Initial commit
2025-03-11 09:42:28 -07:00
Kazuhiro Sera