github nesquena/hermes-webui v0.51.540
v0.51.540 — Release SY (cross-provider model selection sticks + gateway reasoning effort)

latest releases: v0.51.554, v0.51.553, v0.51.552...
14 hours ago

Release v0.51.540 — Release SY (cross-provider model selection sticks + gateway reasoning effort)

Batch of two independent, gated fix-class PRs. Cherry-picked onto current master with original author attribution preserved.

Fixed

  • A cross-provider relay model no longer silently reverts to the profile default after the first message (#3737). When you selected a cross-provider relay model (e.g. custom:glm-free-relay), the explicit-pick marker was consumed after the first send, so subsequent turns lost the explicit pick and the server "repaired" the model back to the profile default. The composer now treats a non-default model from a different provider than the profile's active provider as an explicit pick on every send, and _catalog_has_provider() correctly recognizes compound provider IDs. Thanks @jja881 (#4554).
  • The gateway chat path now forwards the reasoning-effort control (#4550). The browser's reasoning-effort setting was silently ignored in remote/gateway mode while the local path already honored it. The gateway request now reads and coerces agent.reasoning_effort with the same logic as the local path and forwards it on both the runs-API and legacy chat-completions branches. Thanks @rodboev (#4552).

Gate

  • Full pytest suite: 9741 passed, 0 failed
  • Codex regression gate: SAFE TO SHIP
  • Opus advisor: SAFE — SHIP (one optional non-blocking parity note, no action needed)

Closes #3737, #4550.

Don't miss a new hermes-webui release

NewReleases is sending notifications on new releases.