George WealeandCopybara-Service 2e1f730c3b fix: Update LiteLLM system instruction role from "developer" to "system" ...

This change replaces the use of `ChatCompletionDeveloperMessage` with `ChatCompletionSystemMessage` and sets the role to "system" for providing system instructions to LiteLLM models

Close #3657

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 835388738

2025-11-21 15:56:04 -08:00

..

__init__.py

Support async agent and model callbacks

2025-05-06 15:14:10 -07:00

test_anthropic_llm.py

fix: Add experimental feature to use parameters_json_schema and response_json_schema for McpTool

2025-11-16 20:55:16 -08:00

test_apigee_llm.py

chore: Defer import of live, Client and _transformers in google.genai

2025-11-12 10:27:56 -08:00

test_cache_metadata.py

fix: Create context cache only when prefix matches with previous request

2025-10-09 21:19:28 -07:00

test_gemini_llm_connection.py

fix: Fixes DeprecationWarning when using send method

2025-11-09 16:00:43 -08:00

test_gemma_llm.py

feat(models): add support for gemma model via gemini api

2025-10-07 17:38:35 -07:00

test_google_llm.py

chore: Enhance the messaging with possible fixes for RESOURCE_EXHAUSTED errors from Gemini

2025-11-17 16:15:56 -08:00

test_litellm.py

fix: Update LiteLLM system instruction role from "developer" to "system"

2025-11-21 15:56:04 -08:00

test_llm_request.py

feat: Support non-text content in static instruction

2025-09-23 15:36:15 -07:00

test_llm_response.py

chore: Add model tracking to LiteLlm and introduce a LiteLLM with fallbacks demo

2025-11-04 10:10:09 -08:00

test_models.py

chore: Adding regex for claude-4 models to anthropic_llm and updating tests

2025-05-28 13:39:04 -07:00