3ad42ff29e86885113d48f99dede0077ce1b3cec
Long generations (plan/patch stages on larger contexts) exceeded the 1-minute HTTP timeout and surfaced as provider failures mid-pipeline.
fix: workflow inference chain — surface llama-server errors, user-turn-last, bundle-relative prompts
Description
No description provided
Languages
Kotlin
88.4%
Go
11.4%
Python
0.2%