George WealeandCopybara-Service 2dbd1f25bd fix: Add OpenAI strict JSON schema enforcement in LiteLLM ...

This change introduces a recursive function to transform JSON schemas to meet OpenAI's strict mode requirements, including adding "additionalProperties: false" to all object schemas, making all properties required, and stripping sibling keywords from $ref nodes. The schema conversion uses deep copies to not mutating the original input

Close #4573

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 874174994

2026-02-23 11:35:35 -08:00

..

__init__.py

chore: Upgrade to headers to 2026

2026-01-20 14:50:09 -08:00

test_anthropic_llm.py

feat: Mark Vertex calls made from non-gemini models

2026-02-02 02:23:56 -08:00

test_apigee_llm.py

feat: Add /chat/completions integration to ApigeeLlm

2026-02-20 13:27:22 -08:00

test_cache_metadata.py

chore: Upgrade to headers to 2026

2026-01-20 14:50:09 -08:00

test_completions_http_client.py

feat: Add /chat/completions integration to ApigeeLlm

2026-02-20 13:27:22 -08:00

test_gemini_llm_connection.py

chore: Upgrade to headers to 2026

2026-01-20 14:50:09 -08:00

test_gemma_llm.py

feat: Expand LiteLlm supported models and add registry tests

2026-02-13 13:47:13 -08:00

test_google_llm.py

feat: Mark Vertex calls made from non-gemini models

2026-02-02 02:23:56 -08:00

test_interactions_utils.py

fix: Preserve thought_signature in function call conversions for interactions API integration

2026-02-10 15:14:18 -08:00

test_litellm_import.py

fix: Set LITELLM_MODE to PRODUCTION before importing LiteLLM

2026-01-20 13:16:38 -08:00

test_litellm.py

fix: Add OpenAI strict JSON schema enforcement in LiteLLM

2026-02-23 11:35:35 -08:00

test_llm_request.py

chore: Upgrade to headers to 2026

2026-01-20 14:50:09 -08:00

test_llm_response.py

chore: Upgrade to headers to 2026

2026-01-20 14:50:09 -08:00

test_models.py

chore: Upgrade to headers to 2026

2026-01-20 14:50:09 -08:00