Commit Graph
3 Commits
Author SHA1 Message Date
Ettore Di Giacinto e183ea11d1 fix(failover): send remote targets their own upstream model
A chain request reached a cloud-proxy target with the client's model,
the chain name, whenever the target set no upstream_model: passthrough
forwards the body's model and translate falls back to it. The upstream
answered 404, which neither retries nor trips, while the liveness
probe, which checks the target's own name, kept passing.

PrepareTarget now sets the upstream model of a remote target to
proxy.upstream_model or the target name, the same name the probe uses.
The request pipeline and realtime chain stages both call it.

Assisted-by: Claude:claude-opus-5-5
2026-09-26 19:26:13 +00:00
Ettore Di Giacinto 6d49e4a829 fix(failover): stop judging cold local targets by their model file
A missing file is not a reliable signal: models download on first use,
some backends need no file, and dotted names like Phi-3.5-mini look like
paths. Marking such a fallback down removed the retry a chain exists
for. Cold targets are now judged only by real requests.

Assisted-by: Claude:claude-opus-5-5
2026-09-26 17:57:17 +00:00
Ettore Di Giacinto 45123ffc1b test(failover): cover retry per endpoint family and remote fail-back
Assisted-by: Claude:claude-opus-5-5
2026-09-26 17:50:54 +00:00