Commit Graph

267 Commits

Author SHA1 Message Date
Víctor Mayoral Vilches 944128583c CLI responding, but only to proprietary models
Need to investigate why self-hosted models via OLLAMA fail API-wise

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
2025-03-28 09:48:16 +01:00
Víctor Mayoral Vilches f0b93aec91 Fix paths in docs
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
2025-03-28 08:35:25 +01:00
Víctor Mayoral Vilches d2d2ce535d Address error while streaming
[Error occurred during streaming: 1 validation error for ResponseUsage
input_tokens_details
  Input should be a valid dictionary or instance of InputTokensDetails [type=model_type, input_value=InputTokensDetails(prompt...ens=17, cached_tokens=0), input_type=InputTokensDetails]
    For further information visit https://errors.pydantic.dev/2.10/v/model_type]
Location: Traceback (most recent call last):
  File /Users/alias/Alias/research/openai-agents-python/src/cai/cli.py, line 209, in process_streamed_response
    async for event in result.stream_events():
  File /Users/alias/Alias/research/openai-agents-python/src/cai/sdk/agents/result.py, line 186, in stream_events
    raise self._stored_exception
  File /Users/alias/Alias/research/openai-agents-python/src/cai/sdk/agents/run.py, line 539, in _run_streamed_impl
    turn_result = await cls._run_single_turn_streamed(
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File /Users/alias/Alias/research/openai-agents-python/src/cai/sdk/agents/run.py, line 641, in _run_single_turn_streamed
    async for event in model.stream_response(
  File /Users/alias/Alias/research/openai-agents-python/src/cai/sdk/agents/models/openai_chatcompletions.py, line 421, in stream_response
    ResponseUsage(
  File /Users/alias/Alias/research/openai-agents-python/env/lib/python3.12/site-packages/pydantic/main.py, line 214, in __init__
    validated_self = self.__pydantic_validator__.validate_python(data, self_instance=self)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
pydantic_core._pydantic_core.ValidationError: 1 validation error for ResponseUsage
input_tokens_details
  Input should be a valid dictionary or instance of InputTokensDetails [type=model_type, input_value=InputTokensDetails(prompt...ens=17, cached_tokens=0), input_type=InputTokensDetails]
    For further information visit https://errors.pydantic.dev/2.10/v/model_type

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
2025-03-28 08:35:11 +01:00
Víctor Mayoral Vilches f18e659ec8 Fix docs
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
2025-03-28 07:55:41 +01:00
Víctor Mayoral Vilches 1a22013bda Advanced aligning agents but various missing bits:
- agents can't translate directly it seems, see current error
- in addition, it appears streaming mode leads to other problems

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
2025-03-27 19:36:58 +01:00
Víctor Mayoral Vilches 326c3274fc Add blue team agent
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
2025-03-27 15:14:35 +01:00
Víctor Mayoral Vilches 887c2fb319 Add tools, prompts and agents
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
2025-03-27 15:06:12 +01:00
Víctor Mayoral Vilches ac4797cec6 Re-structure under sdk/agents, get CLI mockup
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
2025-03-27 14:31:38 +01:00
Víctor Mayoral Vilches 21048444c6 Minor changes for alignment
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
2025-03-26 18:55:21 +01:00
Víctor Mayoral Vilches adb358baae Update docs to integrate CAI, minor refinements
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
2025-03-26 12:41:45 +01:00
Víctor Mayoral Vilches cd6d218933 Adapt litellm example
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
2025-03-24 19:49:51 +01:00
Víctor Mayoral Vilches 147fc8142e Initial re-structuring towards CAI
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
2025-03-24 19:47:41 +01:00
Víctor Mayoral Vilches 1618434aa9 Fix error in example path
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
2025-03-24 19:47:13 +01:00
Víctor Mayoral Vilches 8718a93155 Remove independent and isolated model tests
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
2025-03-24 18:43:46 +01:00
Víctor Mayoral Vilches 0f8c357231 Restore structure and place litellm integraton under model_providers
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
2025-03-24 18:39:17 +01:00
Víctor Mayoral Vilches 8189f331b6 Update openai library version to avoid version-related issue
In particular:
Traceback (most recent call last):
  File /Users/alias/Alias/research/openai-agents-python/examples/agent_patterns/litellm.py, line 4, in <module>
    from agents import OpenAIChatCompletionsModel,Agent,Runner
  File /Users/alias/Alias/research/openai-agents-python/src/agents/__init__.py, line 44, in <module>
    from .models.openai_chatcompletions import OpenAIChatCompletionsModel
  File /Users/alias/Alias/research/openai-agents-python/src/agents/models/openai_chatcompletions.py, line 57, in <module>
    from openai.types.responses.response_usage import InputTokensDetails, OutputTokensDetails
ImportError: cannot import name 'InputTokensDetails' from 'openai.types.responses.response_usage' (/Users/alias/Alias/research/openai-agents-python/env/lib/python3.12/site-packages/openai/types/responses/response_usage.py). Did you mean: 'OutputTokensDetails'?

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
2025-03-24 18:11:38 +01:00
Víctor Mayoral Vilches 09c2beefdc Merge branch 'main' of https://github.com/openai/openai-agents-python 2025-03-24 17:26:49 +01:00
Víctor Mayoral Vilches 7971856c6c Add some additional bits to README.md
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
2025-03-24 17:26:11 +01:00
Rohan Mehta 244b9850a1 chore: ignore PyCharm .idea/ directory (#317)
Uncomment .idea/ directory in .gitignore to ensure PyCharm IDE project
configuration files are excluded from version control.
2025-03-24 10:08:07 -04:00
madroid 41bb33c761 chore: ignore PyCharm .idea/ directory
Uncomment .idea/ directory in .gitignore to ensure PyCharm IDE
project configuration files are excluded from version control.
2025-03-24 18:30:14 +08:00
Rohan Mehta 21a61969d9 Fix Typos (#258)
Noticed a bunch of typos when reading code, fixing.
2025-03-23 20:28:14 -04:00
Rohan Mehta 84b6dd3642 Improve tracing error messages (#311)
1. Make it clear it's non-fatal
2. Make it clear it's a tracing error
2025-03-23 18:19:45 -04:00
Rohan Mehta 49514f2859 Improve tracing error messages 2025-03-23 18:14:10 -04:00
Rohan Mehta 9f5ebd0e18 Update quickstart.md 2025-03-23 17:56:55 -04:00
Rohan Mehta d6330e4651 Update issues.yml 2025-03-23 12:19:07 -04:00
Rohan Mehta 84e3c22645 Fix code examples in voice pipeline quickstart docs (#277) 2025-03-21 21:44:14 -04:00
Raduan77 db2de55dff revert src/ change per request 2025-03-22 01:06:01 +01:00
Rohan Mehta 7af3f82a18 [docs] fix annotation numbering in context management (#293)
Fix inconsistent numbering between code and explanatory annotations in
the context management documentation.
2025-03-21 19:33:30 -04:00
Rohan Mehta 428b76c695 Fix circular dependency in voice streamed example by renaming agents #291 (#292)
Fix circular dependency in voice streamed example by renaming agents.py
to my_workflow.py

Fix circular dependency in voice streamed example by renaming agents
#291
2025-03-21 19:33:12 -04:00
Aviral Garg 8769a3ebf0 Fix circular dependency in voice streamed example with cleaner import pattern 2025-03-21 16:26:19 -07:00
Aviral Garg 75eec0aed6 Fix type-checking for circular dependency in voice streamed example 2025-03-21 16:18:04 -07:00
Rohan Mehta 289d47fda3 Add Weights & Biases to tracing docs (#294) 2025-03-21 17:59:54 -04:00
Rohan Mehta b02d544629 Read tracing API data lazily (#289) 2025-03-21 17:58:10 -04:00
Scott Condron 849aed4f3a Add Weights & Biases to tracing docs 2025-03-21 21:37:54 +00:00
Han Hwang Lim b2e04bef06 fix annotation numbering in context management
Fix inconsistent numbering between code and explanatory annotations in
the context management documentation.
2025-03-21 21:10:30 +00:00
Aviral Garg ee971e73d2 Fix circular dependency in voice streamed example by renaming agents.py to my_workflow.py 2025-03-21 13:25:46 -07:00
Dmitry Pimenov 3d97f0980d fix line in guardrails doc (#290) 2025-03-21 13:00:18 -07:00
James Hills 860eddd749 fix line in guardrails 2025-03-21 15:58:34 -04:00
Rohan Mehta 9e9ad165ab Read tracing API data lazily 2025-03-21 15:32:37 -04:00
Rohan Mehta de407c688c Replace remaining uses of `fetch_ordered_spans` and `fetch_traces` for stronger tests (#288)
Following https://github.com/openai/openai-agents-python/pull/261
2025-03-21 13:25:43 -04:00
Alex Hall e16c38a6e3 More fetch_normalized_spans 2025-03-21 18:31:06 +02:00
Alex Hall b7df4e470e empty assertions 2025-03-21 18:26:04 +02:00
Rohan Mehta 17868e38a8 Create py.typed (#285)
- Ensure library is properly typehinted
2025-03-21 12:19:48 -04:00
Alex Hall 99d6bc5199 More fetch_normalized_spans 2025-03-21 18:15:52 +02:00
Alex Hall 0d0f35787f More fetch_normalized_spans 2025-03-21 18:14:59 +02:00
Alex Hall b1cfcfd18b More fetch_normalized_spans 2025-03-21 18:13:04 +02:00
Alex Hall 5cea0dffc6 More fetch_normalized_spans 2025-03-21 18:09:19 +02:00
Richie Caputo 353d5eab77 Create py.typed
- Ensure library is properly typehinted
2025-03-21 11:16:24 -04:00
Rohan Mehta ecd06140ff Remove redundant weaker tracing assertions (#261)
Following up on https://github.com/openai/openai-agents-python/pull/25,
this removes uses of `fetch_traces` and `fetch_ordered_spans` where
there's already a stronger assertion using `fetch_normalized_spans`.
This is to help move towards the stronger style as much as possible,
since people are still adding weaker assertions such as
[this](7a0ca7930e/tests/test_concurrency.py (L59-L61))
in https://github.com/openai/openai-agents-python/pull/91. The next step
will be to find remaining uses of `fetch_ordered_spans` that can be
replaced.
2025-03-21 10:31:41 -04:00
Rohan Mehta caa3c6c856 docs: add Langfuse to tracing documentation (#284) 2025-03-21 10:31:05 -04:00