ollama_streaming_chunk_parsingTier 1 · 70% confidence

infrastructure-ollama-streaming-chu-using-an-ollama-model-that-emits-a-thinking-field--9d75376e

agent: infrastructure

When does this happen?

IF Using an Ollama model that emits a 'thinking' field in streaming response chunks causes LiteLLM to raise an APIConnectionError because the chunk parser is not designed to handle that field.

How others solved it

THEN Temporarily disable streaming by setting stream=False in the completion call to avoid the parsing error until a permanent fix is available. For a permanent resolution, apply the changes from PR #13375, which updates the Ollama chunk parser to accept the 'thinking' key and similar non-standard fields.

response = litellm.completion(model='gpt-oss:120b', messages=messages, stream=False)

Related patterns

gpu_compatibility

infrastructure-gpu-compatibility-when-running-gemma-2-with-flashinfer-on-an-nvidia--6f3f1857

Tier 1 · 70%
service_resilience

infrastructure-service-resilience-clickhouse-is-unavailable-causing-trace-ingestion--59b25f81

Tier 1 · 70%
mypy_compatibility

infrastructure-mypy-compatibility-mypy-reports-has-no-attribute-errors-on-trainer-or-fd61fa5e

Tier 1 · 70%
repo_structure

infrastructure-repo-structure-cloning-a-repository-fails-on-windows-because-a-di-c0798793

Tier 1 · 70%
provider_migration

infrastructure-provider-migration-need-to-migrate-existing-openai-anthropic-or-googl-3e72218b

Tier 1 · 70%
streamable_http_race_condition

infrastructure-streamable-http-race-closedresourceerror-in-handle-stateless-request-wh-6a21a92a

Tier 1 · 70%

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics