fix(vision): detect umans kimi + qwen models as vision-capable (not just kimi)

4 files changed, 68 insertions, 59 deletions

diff --git a/packages/openai-stream/src/listModels.test.ts b/packages/openai-stream/src/listModels.test.ts
index 3acf46e..2e3b1a3 100644
--- a/packages/openai-stream/src/listModels.test.ts
+++ b/packages/openai-stream/src/listModels.test.ts
@@ -53,28 +53,33 @@ describe("listModels — pure mapping (parseModelList)", () => {
 });
 
 describe("listModels — vision capability detection", () => {
-  it("isVisionModelId returns true for kimi-family model ids", () => {
-    expect(isVisionModelId("kimi-k2.7")).toBe(true);
-    expect(isVisionModelId("Kimi-K2.7")).toBe(true); // case-insensitive
-    expect(isVisionModelId("moonshot/kimi-k2-thinking")).toBe(true);
+  it("isVisionModelId returns true for umans kimi and qwen model ids", () => {
+    expect(isVisionModelId("umans-kimi-k2.7")).toBe(true);
+    expect(isVisionModelId("Umans-Kimi-K2.7")).toBe(true); // case-insensitive
+    expect(isVisionModelId("umans-qwen3.6-35b-a3b")).toBe(true);
   });
 
-  it("isVisionModelId returns false for non-kimi model ids", () => {
-    expect(isVisionModelId("glm-5.2")).toBe(false);
-    expect(isVisionModelId("deepseek-v4-flash")).toBe(false);
+  it("isVisionModelId returns false for non-vision model ids", () => {
+    expect(isVisionModelId("umans-glm-5.2")).toBe(false);
     expect(isVisionModelId("umans-coder")).toBe(false);
+    expect(isVisionModelId("umans-flash")).toBe(false);
+    expect(isVisionModelId("kimi-k2.7-code")).toBe(false); // opencode kimi, not umans
+    expect(isVisionModelId("qwen3.7-max")).toBe(false); // opencode qwen, not umans
+    expect(isVisionModelId("deepseek-v4-flash")).toBe(false);
   });
 
-  it("parseModelList sets vision: true on kimi-family models", () => {
+  it("parseModelList sets vision: true on umans kimi and qwen models only", () => {
     const result = parseModelList([
-      { id: "kimi-k2.7", context_length: 200000 },
-      { id: "glm-5.2", context_length: 128000 },
-      { id: "deepseek-v4-flash" },
+      { id: "umans-kimi-k2.7", context_length: 262144 },
+      { id: "umans-qwen3.6-35b-a3b", context_length: 262144 },
+      { id: "umans-glm-5.2", context_length: 405504 },
+      { id: "umans-coder" },
     ]);
     expect(result).toEqual([
-      { id: "kimi-k2.7", contextWindow: 200000, vision: true },
-      { id: "glm-5.2", contextWindow: 128000 },
-      { id: "deepseek-v4-flash" },
+      { id: "umans-kimi-k2.7", contextWindow: 262144, vision: true },
+      { id: "umans-qwen3.6-35b-a3b", contextWindow: 262144, vision: true },
+      { id: "umans-glm-5.2", contextWindow: 405504 },
+      { id: "umans-coder" },
     ]);
   });
 });
diff --git a/packages/openai-stream/src/listModels.ts b/packages/openai-stream/src/listModels.ts
index 273fee3..df116b0 100644
--- a/packages/openai-stream/src/listModels.ts
+++ b/packages/openai-stream/src/listModels.ts
@@ -27,19 +27,19 @@ interface OpenAIModelListResponse {
  * Whether a model id is vision-capable (can natively accept image input).
  *
  * The OpenAI-compatible `/models` endpoint does not reliably report image
- * capabilities, so this is a hardcoded heuristic by model id: a model whose id
- * contains "kimi" (e.g. `kimi-k2.7`, `moonshot/kimi-k2.7`) is vision-capable;
- * all others are treated as non-vision. This is the single source of truth —
- * the orchestrator's vision handoff and the `read_image` tool both consult the
- * `ModelInfo.vision` flag this sets, so adding a model here enables vision
- * everywhere. Pure: id → boolean, no I/O.
+ * capabilities, so this is a hardcoded heuristic by model id: the Umans Kimi
+ * (`umans-kimi-k2.7`) and Umans Qwen (`umans-qwen3.6-35b-a3b`) models are
+ * vision-capable; all others are treated as non-vision. This is the single
+ * source of truth — the orchestrator's vision handoff and the `consult_vision`
+ * tool both consult the `ModelInfo.vision` flag this sets, so adding a model
+ * here enables vision everywhere. Pure: id → boolean, no I/O.
  *
  * (When an endpoint gains reliable vision reporting, this can be replaced with
  * a real capability check without changing callers.)
  */
 export function isVisionModelId(id: string): boolean {
   const lower = id.toLowerCase();
-  return lower.includes("kimi");
+  return lower.includes("umans-kimi") || lower.includes("umans-qwen");
 }
 
 /**
diff --git a/packages/vision-handoff/src/pure.test.ts b/packages/vision-handoff/src/pure.test.ts
index 4198d00..ea28288 100644
--- a/packages/vision-handoff/src/pure.test.ts
+++ b/packages/vision-handoff/src/pure.test.ts
@@ -11,21 +11,21 @@ import {
 
 describe("isVisionCapable", () => {
   it("returns true when ModelInfo.vision is true", () => {
-    expect(isVisionCapable("umans/kimi-k2.7", { id: "kimi-k2.7", vision: true })).toBe(true);
+    expect(isVisionCapable("umans/umans-kimi-k2.7", { id: "umans-kimi-k2.7", vision: true })).toBe(true);
   });
 
   it("returns false when ModelInfo.vision is false (overrides name heuristic)", () => {
-    expect(isVisionCapable("umans/kimi-k2.7", { id: "kimi-k2.7", vision: false })).toBe(false);
+    expect(isVisionCapable("umans/umans-kimi-k2.7", { id: "umans-kimi-k2.7", vision: false })).toBe(false);
   });
 
-  it("falls back to name heuristic when vision is absent (kimi)", () => {
-    expect(isVisionCapable("umans/kimi-k2.7", undefined)).toBe(true);
-    expect(isVisionCapable("umans/Kimi-K2.7", undefined)).toBe(true); // case-insensitive
+  it("falls back to name heuristic when vision is absent (umans kimi + qwen)", () => {
+    expect(isVisionCapable("umans/umans-kimi-k2.7", undefined)).toBe(true);
+    expect(isVisionCapable("umans/umans-qwen3.6-35b-a3b", undefined)).toBe(true);
   });
 
-  it("falls back to name heuristic when vision is absent (non-kimi)", () => {
-    expect(isVisionCapable("umans/glm-5.2", undefined)).toBe(false);
-    expect(isVisionCapable("umans/deepseek-v4-flash", { id: "deepseek-v4-flash" })).toBe(false);
+  it("falls back to name heuristic when vision is absent (non-vision)", () => {
+    expect(isVisionCapable("umans/umans-glm-5.2", undefined)).toBe(false);
+    expect(isVisionCapable("umans/umans-coder", { id: "umans-coder" })).toBe(false);
   });
 
   it("returns false for undefined model name", () => {
@@ -36,37 +36,41 @@ describe("isVisionCapable", () => {
 describe("findVisionModelName", () => {
   const getInfo = async (name: string): Promise<ModelInfo | undefined> => {
     const map: Record<string, ModelInfo> = {
-      "umans/kimi-k2.7": { id: "kimi-k2.7", vision: true },
-      "umans/glm-5.2": { id: "glm-5.2" },
+      "umans/umans-kimi-k2.7": { id: "umans-kimi-k2.7", vision: true },
+      "umans/umans-qwen3.6-35b-a3b": { id: "umans-qwen3.6-35b-a3b", vision: true },
+      "umans/umans-glm-5.2": { id: "umans-glm-5.2" },
       "umans/llama-vision": { id: "llama-vision", vision: true },
     };
     return map[name];
   };
 
-  it("finds the first kimi-family model via name heuristic", async () => {
+  it("finds the first umans kimi model via name heuristic", async () => {
     const name = await findVisionModelName(
-      ["umans/glm-5.2", "umans/kimi-k2.7", "umans/llama-vision"],
+      ["umans/umans-glm-5.2", "umans/umans-kimi-k2.7", "umans/llama-vision"],
       getInfo,
     );
-    expect(name).toBe("umans/kimi-k2.7");
+    expect(name).toBe("umans/umans-kimi-k2.7");
   });
 
   it("finds a vision model via ModelInfo.vision when name heuristic misses", async () => {
-    const name = await findVisionModelName(["umans/glm-5.2", "umans/llama-vision"], getInfo);
+    const name = await findVisionModelName(
+      ["umans/umans-glm-5.2", "umans/llama-vision"],
+      getInfo,
+    );
     expect(name).toBe("umans/llama-vision");
   });
 
-  it("skips the excluded model", async () => {
+  it("skips the excluded model and finds the next vision model", async () => {
     const name = await findVisionModelName(
-      ["umans/kimi-k2.7", "umans/llama-vision"],
+      ["umans/umans-kimi-k2.7", "umans/umans-qwen3.6-35b-a3b"],
       getInfo,
-      "umans/kimi-k2.7",
+      "umans/umans-kimi-k2.7",
     );
-    expect(name).toBe("umans/llama-vision");
+    expect(name).toBe("umans/umans-qwen3.6-35b-a3b");
   });
 
   it("returns undefined when no vision model is available", async () => {
-    const name = await findVisionModelName(["umans/glm-5.2"], getInfo);
+    const name = await findVisionModelName(["umans/umans-glm-5.2"], getInfo);
     expect(name).toBeUndefined();
   });
 
diff --git a/packages/vision-handoff/src/service.test.ts b/packages/vision-handoff/src/service.test.ts
index 73c647b..dc54902 100644
--- a/packages/vision-handoff/src/service.test.ts
+++ b/packages/vision-handoff/src/service.test.ts
@@ -37,23 +37,23 @@ function makeVisionProvider(
 
 function makeDeps(overrides: Partial<VisionHandoffDeps> = {}): VisionHandoffDeps {
   const visionProvider = makeVisionProvider((url) => `DESCRIPTION of ${url}`);
-  const catalog = ["umans/kimi-k2.7", "umans/glm-5.2"];
+  const catalog = ["umans/umans-kimi-k2.7", "umans/umans-glm-5.2"];
   const infoMap: Record<string, ModelInfo> = {
-    "umans/kimi-k2.7": { id: "kimi-k2.7", vision: true },
-    "umans/glm-5.2": { id: "glm-5.2" },
+    "umans/umans-kimi-k2.7": { id: "umans-kimi-k2.7", vision: true },
+    "umans/umans-glm-5.2": { id: "umans-glm-5.2" },
   };
   return {
     credentialStore: {
       listCatalog: vi.fn(async () => catalog),
       getModelInfo: vi.fn(async (name: string) => infoMap[name]),
       resolve: vi.fn((name: string) => {
-        if (name === "umans/kimi-k2.7") return { providerId: "umans", model: "kimi-k2.7" };
-        if (name === "umans/glm-5.2") return { providerId: "umans", model: "glm-5.2" };
+        if (name === "umans/umans-kimi-k2.7") return { providerId: "umans", model: "umans-kimi-k2.7" };
+        if (name === "umans/umans-glm-5.2") return { providerId: "umans", model: "umans-glm-5.2" };
         return undefined;
       }),
     },
     resolveModel: vi.fn((name: string) =>
-      name === "umans/kimi-k2.7" || name === "umans/glm-5.2"
+      name === "umans/umans-kimi-k2.7" || name === "umans/umans-glm-5.2"
         ? { provider: visionProvider, model: name.split("/")[1] }
         : undefined,
     ),
@@ -65,12 +65,12 @@ function makeDeps(overrides: Partial<VisionHandoffDeps> = {}): VisionHandoffDeps
 describe("VisionHandoffService.isVisionCapable", () => {
   it("returns true for kimi (via ModelInfo)", async () => {
     const svc = createVisionHandoffService(makeDeps());
-    expect(await svc.isVisionCapable("umans/kimi-k2.7")).toBe(true);
+    expect(await svc.isVisionCapable("umans/umans-kimi-k2.7")).toBe(true);
   });
 
   it("returns false for glm-5.2", async () => {
     const svc = createVisionHandoffService(makeDeps());
-    expect(await svc.isVisionCapable("umans/glm-5.2")).toBe(false);
+    expect(await svc.isVisionCapable("umans/umans-glm-5.2")).toBe(false);
   });
 
   it("returns false for undefined model name", async () => {
@@ -83,13 +83,13 @@ describe("VisionHandoffService.resolveVisionModel", () => {
   it("resolves the kimi model from the catalog", async () => {
     const svc = createVisionHandoffService(makeDeps());
     const vision = await svc.resolveVisionModel();
-    expect(vision?.modelName).toBe("umans/kimi-k2.7");
-    expect(vision?.model).toBe("kimi-k2.7");
+    expect(vision?.modelName).toBe("umans/umans-kimi-k2.7");
+    expect(vision?.model).toBe("umans-kimi-k2.7");
   });
 
   it("excludes the given model", async () => {
     const svc = createVisionHandoffService(makeDeps());
-    const vision = await svc.resolveVisionModel("umans/kimi-k2.7");
+    const vision = await svc.resolveVisionModel("umans/umans-kimi-k2.7");
     expect(vision).toBeUndefined();
   });
 });
@@ -107,7 +107,7 @@ describe("VisionHandoffService.prepareForProvider", () => {
         ],
       },
     ];
-    const result = await svc.prepareForProvider(messages, "umans/kimi-k2.7");
+    const result = await svc.prepareForProvider(messages, "umans/umans-kimi-k2.7");
     expect(result).toBe(messages); // same reference — no copy, no change
   });
 
@@ -115,7 +115,7 @@ describe("VisionHandoffService.prepareForProvider", () => {
     const deps = makeDeps();
     const svc = createVisionHandoffService(deps);
     const messages: ChatMessage[] = [{ role: "user", chunks: [{ type: "text", text: "hi" }] }];
-    const result = await svc.prepareForProvider(messages, "umans/glm-5.2");
+    const result = await svc.prepareForProvider(messages, "umans/umans-glm-5.2");
     expect(result).toBe(messages);
   });
 
@@ -131,7 +131,7 @@ describe("VisionHandoffService.prepareForProvider", () => {
         ],
       },
     ];
-    const result = await svc.prepareForProvider(messages, "umans/glm-5.2", {
+    const result = await svc.prepareForProvider(messages, "umans/umans-glm-5.2", {
       conversationId: "conv-1",
     });
     expect(result).toHaveLength(1);
@@ -154,7 +154,7 @@ describe("VisionHandoffService.prepareForProvider", () => {
       { role: "assistant", chunks: [{ type: "text", text: "ok" }] },
       { role: "user", chunks: [{ type: "image", url: "data:image/png;base64,b" }] },
     ];
-    const result = await svc.prepareForProvider(messages, "umans/glm-5.2", {
+    const result = await svc.prepareForProvider(messages, "umans/umans-glm-5.2", {
       conversationId: "conv-1",
     });
     // First image → Image 1, second → Image 2.
@@ -173,7 +173,7 @@ describe("VisionHandoffService.prepareForProvider", () => {
         chunks: [{ type: "image", url: "data:image/png;base64,registered" }],
       },
     ];
-    await svc.prepareForProvider(messages, "umans/glm-5.2", { conversationId: "conv-42" });
+    await svc.prepareForProvider(messages, "umans/umans-glm-5.2", { conversationId: "conv-42" });
     const img = svc.getRegisteredImage("conv-42", 1);
     expect(img?.url).toBe("data:image/png;base64,registered");
   });
@@ -185,7 +185,7 @@ describe("VisionHandoffService.prepareForProvider", () => {
     const messages: ChatMessage[] = [
       { role: "user", chunks: [{ type: "image", url: "data:image/png;base64,abc" }] },
     ];
-    const result = await svc.prepareForProvider(messages, "umans/glm-5.2", {
+    const result = await svc.prepareForProvider(messages, "umans/umans-glm-5.2", {
       conversationId: "conv-1",
     });
     const text = (result[0]?.chunks[0] as { text: string }).text;
@@ -234,7 +234,7 @@ describe("VisionHandoffService.consultVision", () => {
     const messages: ChatMessage[] = [
       { role: "user", chunks: [{ type: "image", url: "data:image/png;base64,img1" }] },
     ];
-    await svc.prepareForProvider(messages, "umans/glm-5.2", { conversationId: "conv-1" });
+    await svc.prepareForProvider(messages, "umans/umans-glm-5.2", { conversationId: "conv-1" });
 
     const result = await svc.consultVision("What error is shown?", {
       conversationId: "conv-1",
@@ -251,7 +251,7 @@ describe("VisionHandoffService.consultVision", () => {
     // The orchestrator was called with the vision model + the image.
     expect(handleMessage).toHaveBeenCalledOnce();
     const call = handleMessage.mock.calls[0]?.[0];
-    expect(call.modelName).toBe("umans/kimi-k2.7");
+    expect(call.modelName).toBe("umans/umans-kimi-k2.7");
     expect(call.images).toHaveLength(1);
     expect(call.images?.[0]?.url).toBe("data:image/png;base64,img1");
   });