Commit Graph
3 Commits
Author SHA1 Message Date
Ettore Di Giacinto 8db6c15fe0 refactor: name the proxy backends with constants
Review asked for constants instead of the "cloud-proxy" and
"localai-proxy" literals. Add CloudProxyBackend and LocalAIProxyBackend next
to the other backend-name constants in pkg/model (WhisperBackend,
TransformersBackend, ...), which core/config already imports, and use them
in every production check: the proxy options builder, IsRemoteProxy,
IsCloudProxyBackendPassthrough, the PII defaults, the localai-proxy backend
hook and loader warning, and the PII middleware metadata in the routes and
the in-process MCP client.

The proxy options builder now calls IsRemoteProxy() instead of repeating
the two-backend check, so the set of proxy backends is defined once.

Assisted-by: Claude:claude-opus-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2026-09-27 07:42:21 +00:00
Ettore Di Giacinto f7f12f8203 fix(failover): warn about warm on a remote target, align the spec
The spec promised a load-time warning when a chain marks a remote
target warm, where the flag does nothing; the loader now logs it. The
remote-backend test moves into ModelConfig.IsRemoteProxy so the loader
and the failover manager agree on what is remote.

The spec now says what ships: a load blocked by pinned warm targets
proceeds over the limit after eviction retries, without an error that
names them.

Assisted-by: Claude:claude-opus-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2026-09-27 07:42:20 +00:00
Ettore Di Giacinto 63221ee779 feat(config): add failover chain block to model configs
A chain is a model config with an ordered list of target models, probe,
trip and recovery settings. Like an alias it has no backend.

Assisted-by: Claude:claude-opus-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2026-09-27 07:42:20 +00:00