ParthSareen 359be5b658 x/cmd: handle 500 errors by informing model and retrying ...

When server returns a 500 error (often due to tool parsing failures),
instead of failing, send the error message and the model's response
back to the model so it can learn and retry.

- Includes both error message and model's failed response
- Limits to 3 consecutive retries to prevent infinite loops
- Resets retry counter on successful responses

2026-01-06 16:55:08 -08:00

..

run_test.go

x/cmd: add context-aware tool output truncation for LLM

2026-01-06 15:36:03 -08:00

run.go

x/cmd: handle 500 errors by informing model and retrying

2026-01-06 16:55:08 -08:00