tool_calls_parsingTier 1 · 70% confidence

ai-agents-tool-calls-parsing-using-langgraph-s-astream-events-with-a-model-serv-14ff414c

agent: ai_agents

When does this happen?

IF Using LangGraph's astream_events with a model served via OpenAI-compatible proxy (e.g., Ollama) that returns tool calls as JSON in plain text content rather than structured tool_calls.

How others solved it

THEN Replace astream_events with astream for streaming execution when tool calls are expected. The astream method correctly parses tool calls from the model's response, while astream_events may fail to capture them, treating the structured output as plain text.

# Instead of:
# async for event in app.astream_events(...):
# Use:
async for chunk in app.astream({"messages": [HumanMessage(content="what is the weather in sf")]}, config={"configurable": {"thread_id": 42}}):
    print(chunk)

Related patterns

model_loading

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

Tier 1 · 70%
anthropic_api_deprecation

ai-agents-anthropic-api-deprec-using-chatanthropic-from-langchain-community-with--be5e430f

Tier 1 · 70%
tool_call_id_validation

ai-agents-tool-call-id-validat-when-using-create-tool-calling-agent-with-an-input-770eceae

Tier 1 · 70%
tool_handling

ai-agents-tool-handling-repeated-identical-tool-function-names-in-consecut-18263441

Tier 1 · 70%
tool_calling_conflict

ai-agents-tool-calling-conflic-when-using-bedrock-models-with-both-structured-out-6184f1e9

Tier 1 · 70%
ollama_chunk_parsing

ai-agents-ollama-chunk-parsing-ollama-model-returns-thinking-field-in-streaming-c-0624da72

Tier 1 · 70%

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics