Commit Graph

662 Commits

Author SHA1 Message Date
xianghuijin 5f430076a3 Update documentation for tool_choice auto-reset feature 2025-03-20 21:49:38 +08:00
xianghuijin eaafad41ca Revert test file name to match project naming style 2025-03-20 21:28:24 +08:00
xianghuijin 29f39313a3 Rename test file for better clarity 2025-03-20 21:26:59 +08:00
xianghuijin 20271a3591 Fix potential infinite tool call loop by resetting tool_choice after tool execution 2025-03-20 21:22:27 +08:00
Alex Hall da4122975c lint 2025-03-20 13:56:11 +02:00
Alex Hall 8ff2f3a72c Remove redundant weaker tracing assertions 2025-03-20 13:49:38 +02:00
Raduan77 5ee8c79c51 fix typos in tests 2025-03-20 11:24:15 +01:00
Raduan77 e172dd8891 fix typos in src/ 2025-03-20 11:24:08 +01:00
Raduan77 a49fb03c41 fix typos in /examples 2025-03-20 11:23:57 +01:00
Shyamal H Anadkat ec5211c38f Adds example for financial agent 2025-03-19 22:33:13 -07:00
Rohan Mehta d300729e4f formatting updates to examples doc (#249) 2025-03-19 17:26:24 -04:00
James Hills 3de6c69f25 formatting updates to examples doc 2025-03-19 14:23:28 -07:00
Rohan Mehta b0604f6d8c add examples section to docs (#242)
Have gotten feedback that Examples are somewhat buried in the Github
docs. Adding new page after quickstart.
2025-03-19 15:42:41 -04:00
jhills20 266359977d add examples section to docs 2025-03-19 11:43:09 -07:00
Rohan Mehta b2a7d1f376 v0.0.5 (#241) 2025-03-19 12:35:15 -04:00
Rohan Mehta a4cfa67160 v0.0.5 2025-03-19 12:32:36 -04:00
Rohan Mehta 66e6cd16e2 Fix breaking changes from openai 1.66.2 (#232)
Breaking change in 1.66.2
2025-03-19 12:31:59 -04:00
Rohan Mehta 4d6edb9eb9 chore(docs): Added comet opik to tracing AND formatted into a list (#73)
Comet Opik added support for Agent SDK tracing and should be included.
2025-03-19 12:31:02 -04:00
Rohan Mehta e7caa14c30 Fix breaking changes from openai 1.66.2 2025-03-19 12:30:45 -04:00
Rohan Mehta de5710f229 Introduce tool_use_behavior on agents (#203)
## Context
By default, the outputs of tools are sent to the LLM again. The LLM gets
to read the outputs, and produce a new response. There are cases where
this is not desired:
1. Every tool results in another round trip, and sometimes the output of
the tool is enough.
2. If you force tool use (via model settings `tool_choice=required`),
then the agent will just infinite loop.

This enables you to have different behavior, e.g. use the first tool
output as the final output, or write a custom function to process tool
results and potentially produce an output.

## Test plan
Added new tests and ran existing tests
Also added examples.


Closes #117
2025-03-19 12:27:02 -04:00
Vincent Koc ef3f1d73b5 Merge branch 'main' into patch-1 2025-03-20 02:57:34 +11:00
Rohan Mehta 435f77cc49 fix reasoning order in guardrails.md (#234) 2025-03-18 23:27:33 -04:00
CCM b642cd4506 fix reasoning order in guardrails.md 2025-03-19 11:10:58 +08:00
Rohan Mehta c91db09d3c Introduce tool_use_behavior on agents 2025-03-18 21:55:12 -04:00
Rohan Mehta 8b643537a0 Update tests and docs for strict mode decorator (#205)
As titled. Test plan: unit tests/docs.
2025-03-18 21:35:00 -04:00
Rohan Mehta 9291c1743c Add min 95% code coverage (#229)
Run the tests with `coverage`, and make sure the min coverage is 95%.
2025-03-18 16:50:00 -04:00
Rohan Mehta d743b4ac4c Add min 95% code coverage 2025-03-18 16:48:43 -04:00
Dmitry Pimenov 11ce7c9995 chore: adds Maxim AI to tracing processors (#210) 2025-03-18 09:10:52 -07:00
Rohan Mehta 9b7cc2436f [doc] add mlflow tracing integration (#171)
Hi team! Congrats on the new Agents SDK launch!

This PR adds MLflow to the tracing documentation, as it supports
automatic tracing for OpenAI Agents SDK. It has also been supporting
tracing for
[Swarm](https://mlflow.org/docs/latest/tracing/integrations/swarm) as
well, so it is fantastic that the new SDK offers built-in mechanism for
3P trace providers🙂


![image](https://github.com/user-attachments/assets/d36382da-dca1-4335-a915-ca94a994e26a)
2025-03-18 10:21:54 -04:00
Martín Bravo a59728db1f style: improve string formatting in visualization functions 2025-03-18 10:15:41 +01:00
Martín Bravo b97e5dcbe6 style: improve string formatting 2025-03-18 10:14:52 +01:00
Martín Bravo 4a477780a1 style: improve code formatting and readability in visualization functions 2025-03-18 10:09:44 +01:00
Martín Bravo 4012155926 rename: test_visualization.py 2025-03-18 09:59:47 +01:00
Martín Bravo dc92970eca feat: add visualization module for agent graphs using Graphviz 2025-03-18 09:55:30 +01:00
Martín Bravo 3521ab0e48 feat: add documentation for agent visualization using Graphviz 2025-03-18 09:55:23 +01:00
Martín Bravo cd96e745df refactor: move graphviz dependency to visualization section 2025-03-18 09:53:53 +01:00
Martín Bravo c7805669bc feat: add visualization functions for agent graphs 2025-03-18 09:53:48 +01:00
B-Step62 aeb6917e17 [doc] add mlflow tracing integration
Signed-off-by: B-Step62 <yuki.watanabe@databricks.com>
2025-03-18 11:29:21 +09:00
Akshay Deo 5b86a4eadc chore: adds Maxim AI to tracing processors 2025-03-18 07:49:33 +05:30
Martín Bravo dba2d4bd23 Merge branch 'main' of https://github.com/openai/openai-agents-python into feat/draw_graph 2025-03-17 23:50:52 +01:00
Dmitry Pimenov 87fb4ee6bc Docs: update readme text to clarify handoffs (#208)
Clarifying that the handoff abstraction is implemented via Responses
tool calling
2025-03-17 15:15:13 -07:00
Dmitry Pimenov e2be8cc604 clarifying that handoffs are a type of tool call under the hood 2025-03-17 15:05:15 -07:00
Rohan Mehta 801cddc28a Stronger tracing tests with `inline-snapshot` (#25)
`assert len(spans) == 12` is a very weak assertion. This PR asserts the
exported traces and spans more precisely in a readable tree format. And
when the format of an exported trace/span changes (e.g. a new key is
added to every span), you can use `pytest --inline-snapshot=fix` to
update all relevant tests automatically. See
https://15r10nk.github.io/inline-snapshot/latest/ for more info.
2025-03-17 17:59:04 -04:00
Alex Hall 09279d164e mypy 2025-03-17 23:56:42 +02:00
Alex Hall 3ff9238dae Merge branch 'main' of github.com:openai/openai-agents-python into alex/inline-snapshot 2025-03-17 23:55:56 +02:00
Rohan Mehta 7253030b0c Fix typo on Agent documentation (#151)
Argument name is not description but handoff_description
2025-03-17 16:51:47 -04:00
Carlos Souza 268ea2f80d Fix lint 2025-03-17 16:14:28 -04:00
Rohan Mehta 7f1b04e4f3 Fix handoffs example use cases (#156)
## Changes
- In this handoff example, we need to use `first_agent` with
`random_number_tool`, instead of `second_agent` without that tool, since
the user is asking to generate a random number.
- fixed typo in comments
2025-03-17 15:59:18 -04:00
Rohan Mehta d5fbf42a9d fix typo in agent_lifecycle_example.py (#161) 2025-03-17 15:59:00 -04:00
Rohan Mehta 2cccc61118 docs: add arize-phoenix to tracing documentation (#169) 2025-03-17 15:58:28 -04:00