Commit graph

6 commits

Author SHA1 Message Date
Rohan Mehta
d4c7a23e1d
Don't cache agent tools during a run (#803)
### Summary:
Towards #767. We were caching the list of tools for an agent, so if you
did `agent.tools.append(...)` from a tool call, the next call to the
model wouldn't include the new tool. THis is a bug.

### Test Plan:
Unit tests. Note that now MCP tools are listed each time the agent runs
(users can still cache the `list_tools` however).
2025-06-02 14:49:16 -04:00
Rohan Mehta
f329eef7e8
Examples and tests for previous_response_id (#512)
Examples + tests
2025-04-15 12:46:31 -04:00
Rohan Mehta
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
Steven Heidel
aad8accc86
Expose the "store" parameter through ModelSettings (#357)
Closes https://github.com/openai/openai-agents-python/issues/173

This will also set stored completions to True by default, encouraging a
best practice.
2025-03-26 19:01:28 -04:00
Rohan Mehta
10aa5555af Introduce tool_use_behavior on agents 2025-03-18 21:55:12 -04:00
Rohan Mehta
aaec57a426 Initial commit 2025-03-11 09:42:28 -07:00