product · inferred from evidence
LLM
A large language model referenced as part of the workflow that fails to be called.
- SmartScraperGraph returns NA or blank for all fields even though the content is on the page
Using SmartScraperGraph with a plain-language JSON-extraction prompt, the LLM consistently returned "NA" (or blank) for every requested field, even against pages where the information was unambiguously present (e.g. a Wikipedia infobox with
- Agno agent.run() slowed by synchronous telemetry (~1s latency per run)
A benchmark against a local llama-server (no network latency) showed `agent.run()` taking roughly a second longer than calling the LLM directly. Investigating the Agno source revealed the cause: telemetry was dispatched synchronously on the
- n8n 1.119.1 breaks MCP tool calls with "toolCallId: Unexpected keyword argument" validation error
I updated n8n to 1.119.1 and now my MCP tool calls fail. The agent returns: "Error calling tool 'my_tool': 1 validation error for call[my_tool] toolCallId Unexpected keyword argument". My previous workflows ran fine before the update. In an