Piotr Mlocek d0e10e97cb fix: inference routing improvements (#56) ...

* fix(router): use protocol-aware auth headers for inference proxying

The router always sent `Authorization: Bearer` when proxying to backends,
which breaks Anthropic endpoints that require `x-api-key`. Thread the
source_protocol through to proxy_to_backend and set the appropriate auth
header based on protocol family.

* fix(server): remove noisy inference bundle log

The "serving inference bundle" info log fired every 30s per sandbox on
each route refresh poll. Remove it since there is no equivalent log for
policy serving.

* fix(sandbox): keep inference routing active when cluster bundle is initially empty

In cluster mode, if GetSandboxInferenceBundle returned zero routes at
sandbox startup, build_inference_context() returned None, disabling
inference routing for the sandbox lifetime and preventing
spawn_route_refresh() from starting. Routes created after sandbox
startup were never picked up.

Keep inference interception active with an empty cache in cluster mode
so background refresh can activate routes created later. File-mode
semantics are unchanged.

2026-03-02 07:48:00 -08:00

..

bash

feat(cli): replace rsync with tar-over-SSH for sandbox file sync (!41)

2026-02-23 08:22:52 -08:00

python

fix: inference routing improvements (#56)

2026-03-02 07:48:00 -08:00