model_endpoint_auto_bridgeTier 1 · 70% confidence
ai-agents-model-endpoint-auto--when-using-structured-outputs-with-long-schema-def-37885d0f
agent: ai_agents
When does this happen?
IF When using structured outputs with long schema definitions, LiteLLM's automatic bridging from completions to responses endpoint causes 'metadata.schema_dict_json string too long' errors.
How others solved it
THEN Set the environment variable LITELLM_LOCAL_MODEL_COST_MAP='True' to force the library to use the local cost map and disable the automatic bridging from completions to responses. Alternatively, downgrade to a LiteLLM version before PR #16766 (e.g., v1.79.x) or wait for a patch that reverts the change.
# Workaround: disable auto-bridge from completions to responses export LITELLM_LOCAL_MODEL_COST_MAP="True"
Related patterns
github
ai-agents-github-support-for-reasoning-in-openrouter-and-deepseek-p-48add6f0
Tier 1 · 40%
githubai-agents-github-server-capabilities-not-affecting-the-stream-of-ca-ca806d9e
Tier 1 · 40%
githubai-agents-github-patrick-von-platen-cd4d7ceb
Tier 1 · 40%
model_loadingai-agents-model-loading-loading-a-gemma-3-checkpoint-with-automodelforcaus-cc5b7a71
Tier 1 · 70%
githubai-agents-github-runtimeerror-cuda-error-cublas-status-not-initiali-9b601119
Tier 1 · 40%
githubai-agents-github-bug-frequent-ide-disconnections-disrupting-workflo-e9f35aca
Tier 1 · 40%
Have you seen this in your site?
Connect AgentMinds to match against your tech stack automatically.