feat(webui): accept temperature/top_p in thread model selection

src/app/hooks/useChat.ts

@@ -174,6 +174,8 @@ function readSelectionFromMetadata(metadata: Record<string, unknown> | undefined
     const candidate = raw as {
       primary?: unknown;
       reasoning_effort?: unknown;
+      temperature?: unknown;
+      top_p?: unknown;
     };
     if (isModelRefShape(candidate.primary)) {
       const effort = candidate.reasoning_effort;
@@ -184,6 +186,16 @@ function readSelectionFromMetadata(metadata: Record<string, unknown> | undefined
             effort === "low" || effort === "medium" || effort === "high"
               ? effort
               : null,
+          temperature:
+            typeof candidate.temperature === "number" &&
+            Number.isFinite(candidate.temperature)
+              ? candidate.temperature
+              : null,
+          top_p:
+            typeof candidate.top_p === "number" &&
+            Number.isFinite(candidate.top_p)
+              ? candidate.top_p
+              : null,
         },
         revision,
       };

src/lib/modelRegistry.ts

@@ -192,13 +192,16 @@ export interface GetSelectableModelsResponse {
   defaults?: RegistryDefaults;
 }
 
-/** ThreadModelSelection (design doc 7.2). The optional reasoning_effort is a
- * per-thread override frozen into the run snapshot for the primary role. */
+/** ThreadModelSelection (design doc 7.2). The optional reasoning_effort,
+ * temperature, and top_p are per-thread overrides frozen into the run
+ * snapshot for the primary role; null means the registry default. */
 export type ThreadModelSelection =
   | "inherit"
   | {
       primary: ModelRef;
       reasoning_effort?: ReasoningEffort | null;
+      temperature?: number | null;
+      top_p?: number | null;
     };
 
 export interface RegistryApiError {

src/lib/server/threadModelSelection.test.ts

@@ -14,7 +14,12 @@ describe("parseThreadModelSelection", () => {
         primary: REF,
         reasoning_effort: "high",
       })
-    ).toEqual({ primary: REF, reasoning_effort: "high" });
+    ).toEqual({
+      primary: REF,
+      reasoning_effort: "high",
+      temperature: null,
+      top_p: null,
+    });
   });
 
   it("normalizes auto and missing effort to null", () => {
@@ -23,10 +28,17 @@ describe("parseThreadModelSelection", () => {
         primary: REF,
         reasoning_effort: "auto",
       })
-    ).toEqual({ primary: REF, reasoning_effort: null });
+    ).toEqual({
+      primary: REF,
+      reasoning_effort: null,
+      temperature: null,
+      top_p: null,
+    });
     expect(parseThreadModelSelection({ primary: REF })).toEqual({
       primary: REF,
       reasoning_effort: null,
+      temperature: null,
+      top_p: null,
     });
   });
 
@@ -37,7 +49,47 @@ describe("parseThreadModelSelection", () => {
         auxiliary: { provider_id: "ollama", model_key: "qwen3" },
         reasoning_effort: "low",
       })
-    ).toEqual({ primary: REF, reasoning_effort: "low" });
+    ).toEqual({
+      primary: REF,
+      reasoning_effort: "low",
+      temperature: null,
+      top_p: null,
+    });
+  });
+
+  it("keeps explicit temperature/top_p overrides", () => {
+    expect(
+      parseThreadModelSelection({ primary: REF, temperature: 1.2, top_p: 0.5 })
+    ).toEqual({
+      primary: REF,
+      reasoning_effort: null,
+      temperature: 1.2,
+      top_p: 0.5,
+    });
+  });
+
+  it("normalizes missing generation overrides to null", () => {
+    expect(parseThreadModelSelection({ primary: REF })).toEqual({
+      primary: REF,
+      reasoning_effort: null,
+      temperature: null,
+      top_p: null,
+    });
+  });
+
+  it("rejects out-of-range or non-finite generation overrides", () => {
+    for (const bad of [
+      { primary: REF, temperature: -0.1 },
+      { primary: REF, temperature: 2.1 },
+      { primary: REF, temperature: Number.NaN },
+      { primary: REF, top_p: 0 },
+      { primary: REF, top_p: 1.01 },
+      { primary: REF, top_p: "high" },
+    ]) {
+      expect(() => parseThreadModelSelection(bad)).toThrowError(
+        /model_selection must be/
+      );
+    }
   });
 
   it("rejects an unknown effort value", () => {

src/lib/server/threadModelSelection.ts

@@ -29,10 +29,25 @@ function isModelRef(value: unknown): value is ModelRef {
   );
 }
 
+function isTemperature(value: unknown): boolean {
+  return (
+    typeof value === "number" && Number.isFinite(value) && value >= 0 && value <= 2
+  );
+}
+
+function isTopP(value: unknown): boolean {
+  return (
+    typeof value === "number" && Number.isFinite(value) && value > 0 && value <= 1
+  );
+}
+
 /** Validates a browser-supplied `model_selection` payload (design doc 7.2).
  * `reasoning_effort` is optional; "auto" is normalized away so toggling the
- * picker back to Auto keeps the selection (and its snapshot hash) stable. A
- * legacy `auxiliary` key from pre-6.1 metadata is tolerated and dropped. */
+ * picker back to Auto keeps the selection (and its snapshot hash) stable.
+ * `temperature`/`top_p` are optional per-thread overrides, shape-checked
+ * here (0–2 / (0,1]); model-level contracts are enforced server-side when
+ * the run snapshot is created. A legacy `auxiliary` key from pre-6.1
+ * metadata is tolerated and dropped. */
 export function parseThreadModelSelection(value: unknown): ThreadModelSelection {
   if (value === "inherit") return "inherit";
   if (
@@ -41,7 +56,11 @@ export function parseThreadModelSelection(value: unknown): ThreadModelSelection
     (value.reasoning_effort === undefined ||
       value.reasoning_effort === null ||
       (typeof value.reasoning_effort === "string" &&
-        EFFORTS.has(value.reasoning_effort as ReasoningEffort)))
+        EFFORTS.has(value.reasoning_effort as ReasoningEffort))) &&
+    (value.temperature === undefined ||
+      value.temperature === null ||
+      isTemperature(value.temperature)) &&
+    (value.top_p === undefined || value.top_p === null || isTopP(value.top_p))
   ) {
     const effort = value.reasoning_effort;
     return {
@@ -50,11 +69,14 @@ export function parseThreadModelSelection(value: unknown): ThreadModelSelection
         typeof effort === "string" && effort !== "auto"
           ? (effort as ReasoningEffort)
           : null,
+      temperature:
+        typeof value.temperature === "number" ? value.temperature : null,
+      top_p: typeof value.top_p === "number" ? value.top_p : null,
     };
   }
   throw new ThreadModelSelectionError(
     "INVALID_REQUEST",
-    "model_selection must be \"inherit\" or { primary: ModelRef, reasoning_effort?: \"low\" | \"medium\" | \"high\" | null }."
+    "model_selection must be \"inherit\" or { primary: ModelRef, reasoning_effort?: \"low\" | \"medium\" | \"high\" | null, temperature?: number | null, top_p?: number | null }."
   );
 }