fix(open-sse): declare Ollama Cloud reasoning models' supportedThinkingEfforts (#10788)

glm-5.1, glm-5.2, deepseek-v4-pro and deepseek-v4-flash declared supportsReasoning:true but no supportedThinkingEfforts, so the catalog's appendSyncedEffortVariants() pass (which only synthesizes -low/-high/-max ids from an already-populated capabilities.effort_tiers) never exposed a selectable effort tier for them, unlike gpt-oss:20b/120b. Add the documented low/medium/high/max vocabulary (see supportsMaxEffortForProvider's isOllamaCloud comment in reasoningEffort.ts).

changelog.d/fixes/10788-ollama-cloud-effort-tiers.md

@@ -0,0 +1 @@
+- **fix(open-sse):** declare `supportedThinkingEfforts` (`low`/`medium`/`high`/`max`) on Ollama Cloud's `glm-5.1`, `glm-5.2`, `deepseek-v4-pro` and `deepseek-v4-flash` registry entries so the catalog's `appendSyncedEffortVariants()` pass — which only synthesizes selectable `-low`/`-high`/`-max` model ids from an already-populated `capabilities.effort_tiers` — can expose an effort selector for these reasoning-capable models, matching what `gpt-oss:20b`/`gpt-oss:120b` already had (#10788)

open-sse/config/providers/registry/ollama-cloud/index.ts

@@ -24,8 +24,24 @@ export const ollama_cloudProvider: RegistryEntry = {
       supportsReasoning: true,
       supportedThinkingEfforts: ["low", "medium", "high"],
     },
-    { id: "deepseek-v4-pro", name: "DeepSeek V4 Pro", supportsReasoning: true },
-    { id: "deepseek-v4-flash", name: "DeepSeek V4 Flash", supportsReasoning: true },
+    // #10788: Ollama Cloud accepts low|medium|high|max|none uniformly across
+    // its reasoning-capable models (see supportsMaxEffortForProvider's
+    // isOllamaCloud comment in open-sse/executors/base/reasoningEffort.ts) —
+    // declare supportedThinkingEfforts so appendSyncedEffortVariants() (which
+    // runs before static-model capability enrichment) can synthesize the
+    // catalog's selectable -low/-high/-max variant ids for these models.
+    {
+      id: "deepseek-v4-pro",
+      name: "DeepSeek V4 Pro",
+      supportsReasoning: true,
+      supportedThinkingEfforts: ["low", "medium", "high", "max"],
+    },
+    {
+      id: "deepseek-v4-flash",
+      name: "DeepSeek V4 Flash",
+      supportsReasoning: true,
+      supportedThinkingEfforts: ["low", "medium", "high", "max"],
+    },
     { id: "kimi-k2.6", name: "Kimi K2.6" },
     // Ollama Cloud accepts low|medium|high|max|none and rejects xhigh, so the
     // explicit supportsXHighEffort:false makes the sanitizer map xhigh → max.
@@ -34,12 +50,14 @@ export const ollama_cloudProvider: RegistryEntry = {
       name: "GLM 5.1",
       supportsReasoning: true,
       supportsXHighEffort: false,
+      supportedThinkingEfforts: ["low", "medium", "high", "max"],
     },
     {
       id: "glm-5.2",
       name: "GLM 5.2",
       supportsReasoning: true,
       supportsXHighEffort: false,
+      supportedThinkingEfforts: ["low", "medium", "high", "max"],
     },
     // #3110: MiniMax M3 via Ollama
     { id: "minimax-m3", name: "MiniMax M3", contextLength: 1048576, supportsVision: true },

tests/unit/ollama-cloud-reasoning-effort-tiers-10788.test.ts

@@ -0,0 +1,40 @@
+import { test } from "node:test";
+import assert from "node:assert/strict";
+import { ollama_cloudProvider } from "../../open-sse/config/providers/registry/ollama-cloud/index.ts";
+
+// #10788: ollama-cloud declared supportsReasoning:true on several models
+// (glm-5.1/5.2, deepseek-v4-pro/flash) but never declared
+// supportedThinkingEfforts. appendSyncedEffortVariants() (open-sse/utils/
+// syncedEffortVariants.ts) only synthesizes catalog `<model>-<tier>` ids from
+// an already-populated capabilities.effort_tiers, and for static registry
+// models that population only happens from a non-empty
+// supportedThinkingEfforts — so these models never got a selectable
+// -low/-high/-max catalog id. gpt-oss:20b/120b already declared it as the
+// control case.
+test("#10788: ollama-cloud reasoning-capable models declare supportedThinkingEfforts", () => {
+  const byId = new Map(ollama_cloudProvider.models.map((m) => [m.id, m]));
+
+  const control = byId.get("gpt-oss:20b");
+  assert.ok(
+    Array.isArray(control?.supportedThinkingEfforts) && control.supportedThinkingEfforts.length > 0,
+    "control: gpt-oss:20b should already declare supportedThinkingEfforts"
+  );
+
+  const reasoningModelIds = ["glm-5.1", "glm-5.2", "deepseek-v4-pro", "deepseek-v4-flash"];
+  for (const id of reasoningModelIds) {
+    const model = byId.get(id);
+    assert.ok(model?.supportsReasoning, `${id} should be flagged as a reasoning model`);
+    assert.ok(
+      Array.isArray(model?.supportedThinkingEfforts) && model.supportedThinkingEfforts.length > 0,
+      `${id} supports reasoning but declares no supportedThinkingEfforts`
+    );
+    // Ollama Cloud's documented vocabulary (see supportsMaxEffortForProvider's
+    // isOllamaCloud comment in open-sse/executors/base/reasoningEffort.ts):
+    // low|medium|high|max|none — xhigh is rejected and mapped to max.
+    assert.deepEqual(
+      [...(model?.supportedThinkingEfforts ?? [])],
+      ["low", "medium", "high", "max"],
+      `${id} should declare Ollama Cloud's documented low/medium/high/max vocabulary`
+    );
+  }
+});