See #528, some folks are having issues because their output types are
not strict-compatible.
My approach was:
1. Create `AgentOutputSchemaBase`, which represents the base methods for
an output type - the json schema + validation
2. Make the existing `AgentOutputSchema` subclass
`AgentOutputSchemaBase`
3. Allow users to pass a `AgentOutputSchemaBase` to
`Agent(output_type=...)`
This pull request introduces the following changes:
1. **Exclude translated pages from search**: I explored ways to make the
search plugin work with the i18n plugin, but it would require extensive
custom JavaScript hacks. So for now, I’m holding off on this work.
2. **Switch from GPT-4.1 to o3 for even better translation quality**:
While 4.1 performs well, o3 shows even greater quality for this task,
and there’s no reason to avoid using it.
litellm is a library that abstracts away details/differences for a lot
of model providers. Adding an extension, so that any provider can easily
be integrated.
---
[//]: # (BEGIN SAPLING FOOTER)
* #532
* __->__ #524
The current ChatCompletion API supports only `parallel_tool_calls=True`
or `parallel_tool_calls=NOT_GIVEN`
This PR is to support setting `parallel_tool_calls=False`, a common
requirement in controlling agent tool use patterns (e.g. ensuring one
tool call at the time, to facilitate desired tool calling sequence).
I followed the merged
[PR#333](https://github.com/openai/openai-agents-python/pull/333) for
consistency.
This pull request enhances the document translation workflow by
switching to the new GPT-4.1 model. The generator script’s prompt now
includes a “workflow” section that guides the model to iterate
self-reviews on its outputs to autonomously achieve the highest quality.
This addition has noticeably improved the naturalness and consistency of
the wording in the translated outputs.
Allows passing in the previous_response_id to reduce sending the same
data again and again.
Test plan:
Examples. Adding tests in next PR shortly.
---
[//]: # (BEGIN SAPLING FOOTER)
* __->__ #509
* #508
I fixed the type annotations errors for pydantic objects in some
examples as noted in #490 .
When running `make lint` the following error occurs "UP007 Use `X | Y`
for type annotations". If you know how to ignore it I will be happy to
edit the pull request, thanks.
Detected typos using typos-cli (https://crates.io/crates/typos-cli). It
detected "occured" in a string constant "handoff_occured" too, but I
didn't change the part this time because it could be a minor breaking
change.
Full outputs:
```
% typos .
error: `Supresses` should be `Suppresses`
--> ./src/agents/function_schema.py:134:7
|
134 | # Supresses warnings about missing annotations for params
| ^^^^^^^^^
|
error: `typ` should be `typo`, `type`
--> ./src/agents/strict_schema.py:51:5
|
51 | typ = json_schema.get("type")
| ^^^
|
error: `typ` should be `typo`, `type`
--> ./src/agents/strict_schema.py:52:8
|
52 | if typ == "object" and "additionalProperties" not in json_schema:
| ^^^
|
error: `typ` should be `typo`, `type`
--> ./src/agents/strict_schema.py:55:9
|
55 | typ == "object"
| ^^^
|
error: `occured` should be `occurred`
--> ./src/agents/stream_events.py:34:18
|
34 | "handoff_occured",
| ^^^^^^^
|
error: `occured` should be `occurred`
--> ./src/agents/_run_impl.py:723:69
|
723 | event = RunItemStreamEvent(item=item, name="handoff_occured")
| ^^^^^^^
|
error: `desitnation` should be `destination`
--> ./src/agents/tracing/span_data.py:171:25
|
171 | Includes source and desitnation agents.
| ^^^^^^^^^^^
|
error: `exmaples` should be `examples`
--> ./docs/scripts/translate_docs.py:71:145
|
71 | "* The term 'examples' must be code examples when the page mentions the code examples in the repo, it can be translated as either 'code exmaples' or 'sample code'.",
| ^^^^^^^^
|
error: `structed` should be `structured`
--> ./tests/test_agent_hooks.py:227:16
|
227 | async def test_structed_output_non_streamed_agent_hooks():
| ^^^^^^^^
|
error: `structed` should be `structured`
--> ./tests/test_agent_hooks.py:298:16
|
298 | async def test_structed_output_streamed_agent_hooks():
| ^^^^^^^^
|
```
Added the possibility to pass `extra_query` and `extra_body` parameters
when sending a request.
In this implementation I added the attributes to `ModelSettings` as
suggested by @rm-openai in #487 .
I'll be happy to add some tests if you have any suggestions.
This is a pretty minor improvement to the docs: `model_settings`
parameter is only mentioned on the agent doc page, but first-time
visitors may want to know it’s also available on the models page.
fix issue https://github.com/openai/openai-agents-python/issues/442
below is an example to overwrite include_usage
```
result = Runner.run_streamed(
agent,
"Write a haiku about recursion in programming.",
run_config=RunConfig(
model_provider=CUSTOM_MODEL_PROVIDER,
model_settings=ModelSettings(include_usage=True)
),
)
```
Thanks to awesome example `research_bot`
Fix andproduce and goodgrammar (and so on)
```python
>>> from examples.research_bot.agents import search_agent
>>> print(search_agent.INSTRUCTIONS)
You are a research assistant. Given a search term, you search the web for that term andproduce a concise summary of the results. The summary must 2-3 paragraphs and less than 300words. Capture the main points. Write succinctly, no need to have complete sentences or goodgrammar. This will be consumed by someone synthesizing a report, so its vital you capture theessence and ignore any fluff. Do not include any additional commentary other than the summaryitself.
```
### Summary
Updated the `computer-use` example to support simultaneous key presses.
The current implementation presses and releases keys one at a time,
which prevents combo inputs like copy (CTRL+C) from working correctly.
### Test plan
N/A
### Issue number
N/A
### Checks
- [ ] I've added new tests (if relevant)
- [ ] I've added/updated the relevant documentation
- [x] I've run `make lint` and `make format`
- [ ] I've made sure tests pass
Summary:
1. Use <2 for MCP version so it doesn't break if the MCP sdk upgrades.
2. Test the func schema extraction logic.
3. Fix the logic to get the version nuber of the framework
Test Plan:
unit tests
## 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
### **Summary**
This pull request fixes docstring in `ToolsToFinalOutputFunction`, where
`ToolToFinalOutputResult` was incorrectly referenced instead of
`ToolsToFinalOutputResult`.
### **Changes Made**
- Updated the docstring of `ToolsToFinalOutputFunction` to correctly
reference `ToolsToFinalOutputResult`.
### **Before**
```python
"""A function that takes a run context and a list of tool results, and returns a
`ToolToFinalOutputResult`.
"""
```
### **After**
```python
"""A function that takes a run context and a list of tool results, and returns a
`ToolsToFinalOutputResult`.
"""
```
### **Why This Change?**
- The incorrect reference could cause confusion for developers reading
the code.
- This aligns the documentation with the actual return type of the
function.
### **Checklist**
- [x] Verify correct reference to `ToolsToFinalOutputResult`
- [x] Ensure no functionality is affected
### **Testing**
This is a documentation-only change and does not affect runtime
behavior.
### **Reviewer Notes**
- Please review for accuracy in documentation.
- No additional tests are needed since this is a non-functional change.
