admin-valentin/openai-agents-python
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
openai-agents-python/tests
History
Ashok Saravanan 1994f9d4c4
feat: pass extra_body through to LiteLLM acompletion (#638) 
**Purpose**  
Allow arbitrary `extra_body` parameters (e.g. `cached_content`) to be
forwarded into the LiteLLM call. Useful for context caching in Gemini
models
([docs](https://ai.google.dev/gemini-api/docs/caching?lang=python)).

**Example usage**  
```python
import os
from agents import Agent, ModelSettings
from agents.extensions.models.litellm_model import LitellmModel

cache_name = "cachedContents/34jopukfx5di"  # previously stored context

gemini_model = LitellmModel(
    model="gemini/gemini-1.5-flash-002",
    api_key=os.getenv("GOOGLE_API_KEY")
)

agent = Agent(
    name="Cached Gemini Agent",
    model=gemini_model,
    model_settings=ModelSettings(
        extra_body={"cached_content": cache_name}
    )
)
2025-05-14 12:34:27 -04:00
..
fastapi Start and finish streaming trace in impl metod (#540) 2025-04-21 13:08:38 -04:00
mcp Prevent MCP ClientSession hang (#580) 2025-04-24 12:12:46 -04:00
model_settings Create to_json_dict for ModelSettings (#582) 2025-04-23 20:39:07 -04:00
models feat: pass extra_body through to LiteLLM acompletion (#638) 2025-05-14 12:34:27 -04:00
tracing Read tracing API data lazily 2025-03-21 15:32:37 -04:00
voice Create to_json_dict for ModelSettings (#582) 2025-04-23 20:39:07 -04:00
__init__.py Initial commit 2025-03-11 09:42:28 -07:00
conftest.py Initial commit 2025-03-11 09:42:28 -07:00
fake_model.py Add usage to context in streaming (#595) 2025-04-24 18:20:35 -04:00
README.md Pretty print result classes 2025-03-17 11:11:39 -04:00
test_agent_config.py Enable non-strict output types (#539) 2025-04-21 11:58:36 -04:00
test_agent_hooks.py Fix typos and misspellings (#486) 2025-04-14 10:37:13 -04:00
test_agent_runner.py Examples and tests for previous_response_id (#512) 2025-04-15 12:46:31 -04:00
test_agent_runner_streamed.py fix typos in tests 2025-03-20 11:24:15 +01:00
test_agent_tracing.py More fetch_normalized_spans 2025-03-21 18:31:06 +02:00
test_cancel_streaming.py More tests for cancelling streamed run (#590) 2025-04-24 14:45:03 -04:00
test_computer_action.py Initial commit 2025-03-11 09:42:28 -07:00
test_config.py make format 2025-03-11 14:54:10 -07:00
test_doc_parsing.py Initial commit 2025-03-11 09:42:28 -07:00
test_extension_filters.py Initial commit 2025-03-11 09:42:28 -07:00
test_extra_headers.py Adding extra_headers parameters to ModelSettings (#550) 2025-04-22 22:26:47 -04:00
test_function_schema.py Litellm integration (#524) 2025-04-16 18:48:41 -04:00
test_function_tool.py Introduce tool_use_behavior on agents 2025-03-18 21:55:12 -04:00
test_function_tool_decorator.py Misc small fixes - mcp version, test for function_schema, version gen (#429) 2025-04-03 12:08:01 -04:00
test_global_hooks.py fix typos in tests 2025-03-20 11:24:15 +01:00
test_guardrails.py Initial commit 2025-03-11 09:42:28 -07:00
test_handoff_tool.py Initial commit 2025-03-11 09:42:28 -07:00
test_items_helpers.py Replace referencable_id with response_id (#508) 2025-04-14 21:37:18 -04:00
test_max_turns.py Initial commit 2025-03-11 09:42:28 -07:00
test_openai_chatcompletions.py Litellm integration (#524) 2025-04-16 18:48:41 -04:00
test_openai_chatcompletions_converter.py Enable non-strict output types (#539) 2025-04-21 11:58:36 -04:00
test_openai_chatcompletions_stream.py Previous response id (#509) 2025-04-14 22:02:47 -04:00
test_openai_responses_converter.py Enable non-strict output types (#539) 2025-04-21 11:58:36 -04:00
test_output_tool.py Enable non-strict output types (#539) 2025-04-21 11:58:36 -04:00
test_pretty_print.py Pretty print result classes 2025-03-17 11:11:39 -04:00
test_responses.py Initial commit 2025-03-11 09:42:28 -07:00
test_responses_tracing.py Previous response id (#509) 2025-04-14 22:02:47 -04:00
test_result_cast.py Add usage to context in streaming (#595) 2025-04-24 18:20:35 -04:00
test_run_config.py Initial commit 2025-03-11 09:42:28 -07:00
test_run_step_execution.py Replace referencable_id with response_id (#508) 2025-04-14 21:37:18 -04:00
test_run_step_processing.py Replace referencable_id with response_id (#508) 2025-04-14 21:37:18 -04:00
test_strict_schema.py Initial commit 2025-03-11 09:42:28 -07:00
test_tool_choice_reset.py Make the reset behavior on tool use configurable 2025-03-25 13:29:32 -04:00
test_tool_converter.py Extract chat completions conversion code into helper (#522) 2025-04-15 18:31:17 -04:00
test_tool_use_behavior.py Introduce tool_use_behavior on agents 2025-03-18 21:55:12 -04:00
test_trace_processor.py Initial commit 2025-03-11 09:42:28 -07:00
test_tracing.py More fetch_normalized_spans 2025-03-21 18:31:06 +02:00
test_tracing_errors.py Convert MCP schemas to strict where possible (#414) 2025-04-01 16:50:13 -04:00
test_tracing_errors_streamed.py Mark handoff span as errored when multiple handoffs are requested (#344) 2025-03-26 10:44:59 -04:00
test_visualization.py Refactor visualization functions to improve formatting and streamline edge generation 2025-03-25 19:12:40 +01:00
testing_processor.py More fetch_normalized_spans 2025-03-21 18:31:06 +02:00

README.md

Tests

Before running any tests, make sure you have uv installed (and ideally run make sync after).

Running tests

make tests

Snapshots

We use inline-snapshots for some tests. If your code adds new snapshot tests or breaks existing ones, you can fix/create them. After fixing/creating snapshots, run make tests again to verify the tests pass.

Fixing snapshots

make snapshots-fix

Creating snapshots

make snapshots-update