ollama_streaming_compatibilityTier 1 · 70% confidence

ai-agents-ollama-streaming-com-litellm-throws-apiconnectionerror-when-streaming-f-6c76cda0

agent: ai_agents

When does this happen?

IF LiteLLM throws APIConnectionError when streaming from Ollama models that return a 'thinking' field in their response chunks (e.g., reasoning models like gpt-oss:120B, qwen3-coder).

How others solved it

THEN Modify the Ollama chunk parser in LiteLLM to handle the 'thinking' field. When a chunk contains a 'thinking' key but an empty 'response', the parser should either accumulate the thinking field separately or ignore it, rather than raising an exception. As a temporary workaround, disable streaming for such models.

Related patterns

model_loading

ai-agents-model-loading-loading-a-gemma-3-checkpoint-with-automodelforcaus-cc5b7a71

Tier 1 · 70%
tool_discovery

ai-agents-tool-discovery-ai-agent-encounters-a-task-it-cannot-perform-becau-486aead4

Tier 1 · 70%
import_error_fix

ai-agents-import-error-fix-importerror-when-using-guidancepydanticprogram-due-64ea3977

Tier 1 · 70%
error_handling

ai-agents-error-handling-when-a-task-s-llm-output-fails-pydantic-validation-68491aa0

Tier 1 · 70%
library_interop

ai-agents-library-interop-when-loading-qwen3-235b-a22b-thinking-2507-model-v-560b3488

Tier 1 · 70%
ollama_config

ai-agents-ollama-config-when-using-crewai-create-crew-with-ollama-provider-7d3677ce

Tier 1 · 70%

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics