0957f7c69ea98e561499b6404bbe7ceb38caacc6
Flip §A LLAMA_SERVER probe to pending-live-QA (aaf896d), register the QA
gate in §F, and add docs/qa/QA-llama-health-probe.md with observable-evidence
checks (liveness up/down/restore, non-2xx, tps degrade, restart hysteresis,
replay independence).
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%