feat: add glm vision model check (#741)

* Implement GLM model identification logic

Add checks for GLM text and visual model naming conventions.

* fix: simplify GLM vision detection and add tests

- Remove redundant includes("v-") check that could cause false positives
  on model names containing "dev-", "csv-", etc.
- Remove unnecessary includes("v") pre-check
- Update comments with real GLM model names
- Add unit tests for GLM text and vision models

* feat: add vision detection for MiniMax, Moonshot, and fix Qwen

- Add MiniMax text model detection (M2.x series are text-only)
- Add Moonshot v1 text model detection (moonshot-v1-* are text-only)
- Add qwen3.5-flash to Qwen vision model exceptions
- Add unit tests for all new model checks

---------

Co-authored-by: dayuan.jiang <jdy.toh@gmail.com>

lib/ai-providers.ts

@@ -1335,6 +1335,16 @@ export function supportsImageInput(modelId: string): boolean {
         return false
     }
 
+    // Moonshot text models (moonshot-v1 series are text-only)
+    if (lowerModelId.includes("moonshot-v1") && !hasVisionIndicator) {
+        return false
+    }
+
+    // MiniMax text models (MiniMax-M2.x series are text-only)
+    if (lowerModelId.includes("minimax") && !hasVisionIndicator) {
+        return false
+    }
+
     // DeepSeek text models (not vision variants)
     if (lowerModelId.includes("deepseek") && !hasVisionIndicator) {
         return false
@@ -1345,11 +1355,20 @@ export function supportsImageInput(modelId: string): boolean {
     if (
         lowerModelId.includes("qwen") &&
         !hasVisionIndicator &&
-        !lowerModelId.includes("qwen3.5-plus")
+        !lowerModelId.includes("qwen3.5-plus") &&
+        !lowerModelId.includes("qwen3.5-flash")
     ) {
         return false
     }
 
+    // GLM text models (not vision variants)
+    // GLM vision models: glm-4v, glm-4v-9b, glm-4.1v-9b-thinking
+    if (lowerModelId.includes("glm") && !hasVisionIndicator) {
+        if (!/[\d.]v/.test(lowerModelId)) {
+            return false
+        }
+    }
+
     // Default: assume model supports images
     return true
 }

tests/unit/ai-providers.test.ts

@@ -174,6 +174,19 @@ describe("supportsImageInput", () => {
         expect(supportsImageInput("moonshotai/kimi-k2.5")).toBe(true)
     })
 
+    it("returns false for Moonshot v1 text models", () => {
+        expect(supportsImageInput("moonshot-v1-8k")).toBe(false)
+        expect(supportsImageInput("moonshot-v1-32k")).toBe(false)
+        expect(supportsImageInput("moonshot-v1-128k")).toBe(false)
+    })
+
+    it("returns false for MiniMax text models", () => {
+        expect(supportsImageInput("MiniMax-M2.7")).toBe(false)
+        expect(supportsImageInput("MiniMax-M2.5")).toBe(false)
+        expect(supportsImageInput("MiniMax-M2")).toBe(false)
+        expect(supportsImageInput("MiniMax-M2.5-highspeed")).toBe(false)
+    })
+
     it("returns false for DeepSeek text models", () => {
         expect(supportsImageInput("deepseek-chat")).toBe(false)
         expect(supportsImageInput("deepseek-coder")).toBe(false)
@@ -182,6 +195,30 @@ describe("supportsImageInput", () => {
     it("returns false for Qwen text models", () => {
         expect(supportsImageInput("qwen-turbo")).toBe(false)
         expect(supportsImageInput("qwen-plus")).toBe(false)
+        expect(supportsImageInput("qwen3-max")).toBe(false)
+    })
+
+    it("returns true for Qwen vision models", () => {
+        expect(supportsImageInput("qwen-vl")).toBe(true)
+        expect(supportsImageInput("qwen3.5-plus")).toBe(true)
+        expect(supportsImageInput("qwen3.5-flash")).toBe(true)
+        expect(supportsImageInput("qwen3-vl-plus")).toBe(true)
+        expect(supportsImageInput("qwen3-vl-flash")).toBe(true)
+    })
+
+    it("returns false for GLM text models", () => {
+        expect(supportsImageInput("glm-4")).toBe(false)
+        expect(supportsImageInput("glm-4-plus")).toBe(false)
+        expect(supportsImageInput("glm-4-flash")).toBe(false)
+        expect(supportsImageInput("glm-4-long")).toBe(false)
+        expect(supportsImageInput("glm-4.7")).toBe(false)
+        expect(supportsImageInput("glm-5")).toBe(false)
+    })
+
+    it("returns true for GLM vision models", () => {
+        expect(supportsImageInput("glm-4v")).toBe(true)
+        expect(supportsImageInput("glm-4v-9b")).toBe(true)
+        expect(supportsImageInput("glm-4.1v-9b-thinking")).toBe(true)
     })
 
     it("returns true for Claude and GPT models by default", () => {