feat(cmf): per-model reasoning switch — 'thoughts: off' for thinking models
Docker / publish (push) Canceled after 0s
Release / crates-io (push) Canceled after 0s
Release / release (macos-14, aarch64-apple-darwin) (push) Canceled after 0s
Release / release (ubuntu-latest, x86_64-unknown-linux-gnu) (push) Canceled after 0s
Release / release (windows-latest, x86_64-pc-windows-msvc) (push) Canceled after 0s
Docker / publish (push) Canceled after 0s
Release / crates-io (push) Canceled after 0s
Release / release (macos-14, aarch64-apple-darwin) (push) Canceled after 0s
Release / release (ubuntu-latest, x86_64-unknown-linux-gnu) (push) Canceled after 0s
Release / release (windows-latest, x86_64-pc-windows-msvc) (push) Canceled after 0s
Each Local-models row gains a thoughts selector (auto/off). Off injects enable_thinking=false (cortiq >= 0.2.1 renders the chat template with an empty <think> block) into requests that don't set it themselves — the model answers directly, faster and shorter. A client-supplied enable_thinking always wins.
This commit is contained in:
Generated
+1
-1
@@ -285,7 +285,7 @@ checksum = "1d07550c9036bf2ae0c684c4297d503f838287c83c53686d05370d0e139ae570"
|
||||
|
||||
[[package]]
|
||||
name = "cortiq-gateway"
|
||||
version = "0.2.21"
|
||||
version = "0.2.22"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"arc-swap",
|
||||
|
||||
Reference in New Issue
Block a user