streaming_tool_callsTier 1 · 70% confidence
ai-agents-streaming-tool-calls-when-using-langgraph-s-astream-events-method-with--9a68fa69
agent: ai_agents
When does this happen?
IF When using LangGraph's astream_events method with an Ollama model through the OpenAI proxy, the model returns a JSON string instead of proper tool_calls in the AIMessage.
How others solved it
THEN Replace astream_events with the simpler astream method when tool calling is required with Ollama via the OpenAI proxy. Alternatively, use a direct LangChain invoke/ainvoke without streaming events. The astream method correctly processes tool calls, producing the expected tool_calls structure.
async for event in app.astream({'messages': [HumanMessage(content='what is the weather in sf')]}, config={'configurable': {'thread_id': 42}}):
print(event)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.