Ettore Di Giacinto 881141ab43 fix(distributed): enforce staging admission ...

Propagate multimodal staging failures before inference and claim matching ephemeral HTTP cache entries. Fall back to PUT when an older worker does not support claims.

Assisted-by: Codex:gpt-6

2026-09-08 13:35:31 +00:00

..

addr_test.go

fix(model): make backend shutdown model-scoped (#10865)

2026-07-19 08:43:17 +02:00

auth_required_test.go

feat(distributed): enforce registration token for worker file transfer (#10183)

2026-06-05 14:34:28 +02:00

backend_delete_test.go

fix(worker): reap deleted backends and stop models that live on a worker (#10956)

2026-07-20 01:09:22 +02:00

backend_reinstall_cwd_test.go

fix(worker): never reuse a backend process whose directory a reinstall replaced (#11029)

2026-07-22 17:29:59 +02:00

concurrency_test.go

fix(distributed): split NATS backend.upgrade off install + dedup loads (#9717)

2026-05-08 16:24:54 +02:00

config.go

feat(worker): enforce ephemeral staging bounds

2026-09-08 13:35:31 +00:00

ephemeral_capacity_test.go

fix(worker): retain staged input ownership

2026-09-08 13:35:31 +00:00

ephemeral_capacity.go

fix(worker): claim cached ephemeral inputs

2026-09-08 13:35:31 +00:00

ephemeral_cleanup_test.go

fix(worker): retain staged input ownership

2026-09-08 13:35:31 +00:00

ephemeral_cleanup.go

feat(worker): enforce ephemeral staging bounds

2026-09-08 13:35:31 +00:00

file_staging_release_test.go

fix(distributed): enforce staging admission

2026-09-08 13:35:31 +00:00

file_staging.go

fix(worker): claim cached ephemeral inputs

2026-09-08 13:35:31 +00:00

free_timeout_test.go

Revert "chore(tests): Avoid network, sleep and more during tests" (#11601)

2026-08-19 16:39:39 +02:00

install.go

fix(worker): never reuse a backend process whose directory a reinstall replaced (#11029)

2026-07-22 17:29:59 +02:00

lifecycle.go

fix(distributed): keep model replicas config-consistent (#11664)

2026-08-22 22:44:03 +02:00

loaded_backend_addresses_test.go

fix(distributed): survive a slow control-plane database (#11837)

2026-09-02 12:37:12 +02:00

model_stop_test.go

fix(distributed): keep model replicas config-consistent (#11664)

2026-08-22 22:44:03 +02:00

models_running_test.go

fix(distributed): reaper reaps live backends, ghost model stubs, in_flight leak, sidecar staging runaway (#11142)

2026-07-27 18:36:31 +02:00

models_running.go

fix(distributed): reaper reaps live backends, ghost model stubs, in_flight leak, sidecar staging runaway (#11142)

2026-07-27 18:36:31 +02:00

nats_connect_test.go

feat(distributed): Add NATS JWT authentication and TLS/mTLS options (#10159)

2026-06-03 19:43:56 +02:00

nats_connect.go

feat(distributed): Add NATS JWT authentication and TLS/mTLS options (#10159)

2026-06-03 19:43:56 +02:00

port_allocator_test.go

fix(worker): bound the gRPC port allocator and stop leaking dead backends' ports (#10968)

2026-07-19 23:56:37 +00:00

port_quarantine_test.go

fix(worker): bound the gRPC port allocator and stop leaking dead backends' ports (#10968)

2026-07-19 23:56:37 +00:00

prefetch_test.go

feat(worker): add LOCALAI_PREFETCH_MODELS for boot-time gallery prefetch (#10108)

2026-05-31 12:22:45 +02:00

prefetch.go

feat(worker): add LOCALAI_PREFETCH_MODELS for boot-time gallery prefetch (#10108)

2026-05-31 12:22:45 +02:00

process_helpers.go

fix(distributed): split NATS backend.upgrade off install + dedup loads (#9717)

2026-05-08 16:24:54 +02:00

registration_test.go

fix(worker): report RAM alongside GPU memory (#11167)

2026-07-28 23:55:35 +02:00

registration.go

fix(worker): report RAM alongside GPU memory (#11167)

2026-07-28 23:55:35 +02:00

replica_test.go

fix(distributed): survive a slow control-plane database (#11837)

2026-09-02 12:37:12 +02:00

reply.go

fix(distributed): split NATS backend.upgrade off install + dedup loads (#9717)

2026-05-08 16:24:54 +02:00

supervisor.go

fix(distributed): survive a slow control-plane database (#11837)

2026-09-02 12:37:12 +02:00

worker_suite_test.go

fix(distributed): split NATS backend.upgrade off install + dedup loads (#9717)

2026-05-08 16:24:54 +02:00

worker.go

feat(worker): enforce ephemeral staging bounds

2026-09-08 13:35:31 +00:00