Skip to content

Conversation

@vcshih
Copy link

@vcshih vcshih commented Jul 21, 2025

No description provided.

MurtazaAliCode and others added 30 commits August 14, 2025 08:07
Automated update of translated documentation

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
This pull request migrates the translation script from o3 to gpt-5
model.
Automated update of translated documentation

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
There was a problem with the current implementation, where for a single
repsonse, we might have many different guardrails fire. We should have
at most one per response.
Automated update of translated documentation

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Some customers have reported that the agent loop can go on for a long
time and use up the entire context window. This PR allows modifying the
data sent to the model.
We were making deep copies, which is (1) inefficient and (2) causes some
pickling errors.

Instead, this PR just makes shallow copies, calling list.copy(). We do
want a shallow copy so that mutations don't affect the original past-end
list.
@rzhao-openai was seeing errors about incoming messages being too large.
Turns out there's a default limit of 2**20 = 1,048,576 bytes.
### Summary

Adds `is_enabled` parameter to `Agent.as_tool()` method for
conditionally enabling/disabling agent tools at runtime. Supports
boolean values and callable functions for dynamic tool filtering
  in multi-agent orchestration.

  ### Test plan

  - Added unit tests in `tests/test_agent_as_tool.py`
- Added example in
`examples/agent_patterns/agents_as_tools_conditional.py`
  - Updated documentation in `docs/tools.md`
  - All tests pass

  ### Issue number

  Closes #1097

  ### Checks

  - [x] I've added new tests (if relevant)
  - [x] I've added/updated the relevant documentation
  - [x] I've run `make lint` and `make format`
  - [x] I've made sure tests pass

---------

Co-authored-by: thein <[email protected]>
Automated update of translated documentation

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
ihower and others added 30 commits November 4, 2025 12:16
## Summary
- add a `nest_handoff_history` flag to `RunConfig` and call a new helper
that condenses the prior transcript into a developer-role summary when
handing off
- update the default handoff path, docs, and helper library so that the
developer summary is produced automatically unless a custom filter
overrides it
- expand the handoff-focused tests to cover the new behavior (including
helper unit tests) and update existing expectations

## Testing
- `uv run pytest tests/test_extension_filters.py`
- `uv run pytest tests/test_agent_runner.py -k handoff`
- `uv run pytest tests/test_agent_runner_streamed.py -k handoff`


------
https://chatgpt.com/codex/tasks/task_i_68ff73bda0f4832496f3d1fa9103905f
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.