fix(providers): keep minimax chat models text-only

CHANGELOG.md

@@ -22,6 +22,7 @@ Docs: https://docs.openclaw.ai
 - Control UI/Codex harness: emit native Codex app-server assistant and lifecycle completion events so live webchat runs stop spinning without needing a transcript reload fallback. (#70815) Thanks @lesaai.
 - Agents/sessions: persist the runtime-resolved context budget from embedded agent runs, so Codex GPT-5.5 sessions keep the catalog/runtime context cap instead of falling back to the generic 200k status value. Fixes #71294. Thanks @tud0r.
 - Agents/tools: fail runs before model submission when explicit tool allowlists resolve to no callable tools, preventing text-only hallucinated tool results for missing tools such as plugin commands that were not registered. Fixes #71292.
+- Providers/MiniMax: keep M2.7 chat model metadata text-only so image tool requests route through `MiniMax-VL-01` instead of the Anthropic-compatible chat endpoint. Fixes #71296. Thanks @ilker-cevikkaya.
 - Discord/replies: run `message_sending` plugin hooks for Discord reply delivery, including DM targets, so plugins can transform or cancel outbound Discord replies consistently with other channels. Fixes #59350. (#71094) Thanks @wei840222.
 - Control UI/commands: carry provider-owned thinking option ids/labels in session rows and defaults so fresh sessions show and accept dynamic modes such as `adaptive`, `xhigh`, and `max`. Fixes #71269. Thanks @Young-Khalil.
 - Image generation: make explicit `model=` overrides exact-only so failed `openai/gpt-image-2` requests no longer fall through to Gemini or other configured providers, and update `image_generate list` to mention OpenAI Codex OAuth as valid auth for `openai/gpt-image-2`. Fixes #71290 and #71231. Thanks @Young-Khalil and @steipete.

docs/concepts/model-providers.md

@@ -266,7 +266,7 @@ Quirks worth knowing:
 
 - **OpenRouter** applies its app-attribution headers and Anthropic `cache_control` markers only on verified `openrouter.ai` routes. As a proxy-style OpenAI-compatible path, it skips native-OpenAI-only shaping (`serviceTier`, Responses `store`, prompt-cache hints, OpenAI reasoning-compat). Gemini-backed refs keep proxy-Gemini thought-signature sanitation only.
 - **Kilo Gateway** Gemini-backed refs follow the same proxy-Gemini sanitation path; `kilocode/kilo/auto` and other proxy-reasoning-unsupported refs skip proxy reasoning injection.
-- **MiniMax** API-key onboarding writes explicit M2.7 model definitions with `input: ["text", "image"]`; the bundled catalog keeps chat refs text-only until that config is materialized.
+- **MiniMax** API-key onboarding writes explicit text-only M2.7 chat model definitions; image understanding stays on the plugin-owned `MiniMax-VL-01` media provider.
 - **xAI** uses the xAI Responses path. `/fast` or `params.fastMode: true` rewrites `grok-3`, `grok-3-mini`, `grok-4`, and `grok-4-0709` to their `*-fast` variants. `tool_stream` defaults on; disable via `agents.defaults.models["xai/<model>"].params.tool_stream=false`.
 - **Cerebras** GLM models use `zai-glm-4.7` / `zai-glm-4.6`; OpenAI-compatible base URL is `https://api.cerebras.ai/v1`.
 

docs/gateway/config-tools.md

@@ -628,7 +628,7 @@ Base URL should omit `/v1` (Anthropic client appends it). Shortcut: `openclaw on
             id: "MiniMax-M2.7",
             name: "MiniMax M2.7",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: { input: 0.3, output: 1.2, cacheRead: 0.06, cacheWrite: 0.375 },
             contextWindow: 204800,
             maxTokens: 131072,

docs/providers/minimax.md

@@ -144,7 +144,7 @@ Choose your preferred auth method and follow the setup steps.
                 id: "MiniMax-M2.7",
                 name: "MiniMax M2.7",
                 reasoning: true,
-                input: ["text", "image"],
+                input: ["text"],
                 cost: { input: 0.3, output: 1.2, cacheRead: 0.06, cacheWrite: 0.375 },
                 contextWindow: 204800,
                 maxTokens: 131072,
@@ -153,7 +153,7 @@ Choose your preferred auth method and follow the setup steps.
                 id: "MiniMax-M2.7-highspeed",
                 name: "MiniMax M2.7 Highspeed",
                 reasoning: true,
-                input: ["text", "image"],
+                input: ["text"],
                 cost: { input: 0.6, output: 2.4, cacheRead: 0.06, cacheWrite: 0.375 },
                 contextWindow: 204800,
                 maxTokens: 131072,
@@ -237,11 +237,8 @@ the bundled `minimax-portal` auth path instead.
 
 When onboarding or API-key setup writes explicit `models.providers.minimax`
 entries, OpenClaw materializes `MiniMax-M2.7` and
-`MiniMax-M2.7-highspeed` with `input: ["text", "image"]`.
-
-The built-in bundled MiniMax text catalog itself stays text-only metadata until
-that explicit provider config exists. Image understanding is exposed separately
-through the plugin-owned `MiniMax-VL-01` media provider.
+`MiniMax-M2.7-highspeed` as text-only chat models. Image understanding is
+exposed separately through the plugin-owned `MiniMax-VL-01` media provider.
 
 <Note>
 See [Image Generation](/tools/image-generation) for shared tool parameters, provider selection, and failover behavior.
@@ -398,8 +395,8 @@ See [MiniMax Search](/tools/minimax-search) for full web search configuration an
   - OAuth setup: `minimax-portal/<model>`
 - Default chat model: `MiniMax-M2.7`
 - Alternate chat model: `MiniMax-M2.7-highspeed`
-- Onboarding and direct API-key setup write explicit model definitions with `input: ["text", "image"]` for both M2.7 variants
-- The bundled provider catalog currently exposes the chat refs as text-only metadata until explicit MiniMax provider config exists
+- Onboarding and direct API-key setup write text-only model definitions for both M2.7 variants
+- Image understanding uses the plugin-owned `MiniMax-VL-01` media provider
 - Update pricing values in `models.json` if you need exact cost tracking
 - Use `openclaw models list` to confirm the current provider id, then switch with `openclaw models set minimax/MiniMax-M2.7` or `openclaw models set minimax-portal/MiniMax-M2.7`
 

extensions/minimax/model-definitions.test.ts

@@ -38,7 +38,7 @@ describe("minimax model definitions", () => {
       id: "MiniMax-M2.7",
       name: "MiniMax M2.7",
       reasoning: true,
-      input: ["text", "image"], // M2.7 supports images
+      input: ["text"],
     });
   });
 
@@ -62,7 +62,7 @@ describe("minimax model definitions", () => {
     expect(model.cost).toEqual(MINIMAX_API_COST);
     expect(model.contextWindow).toBe(DEFAULT_MINIMAX_CONTEXT_WINDOW);
     expect(model.maxTokens).toBe(DEFAULT_MINIMAX_MAX_TOKENS);
-    expect(model.input).toEqual(["text", "image"]);
+    expect(model.input).toEqual(["text"]);
   });
 
   it("falls back to generated name for unknown model id", () => {
@@ -71,14 +71,14 @@ describe("minimax model definitions", () => {
     expect(model.reasoning).toBe(false);
   });
 
-  it("M2.7 model includes image input", () => {
+  it("keeps M2.7 text-only on the Anthropic-compatible chat path", () => {
     const model = buildMinimaxApiModelDefinition("MiniMax-M2.7");
-    expect(model.input).toEqual(["text", "image"]);
+    expect(model.input).toEqual(["text"]);
   });
 
-  it("M2.7-highspeed model includes image input", () => {
+  it("keeps M2.7-highspeed text-only on the Anthropic-compatible chat path", () => {
     const model = buildMinimaxApiModelDefinition("MiniMax-M2.7-highspeed");
-    expect(model.input).toEqual(["text", "image"]);
+    expect(model.input).toEqual(["text"]);
     expect(model.cost).toEqual(MINIMAX_API_HIGHSPEED_COST);
   });
 

extensions/minimax/model-definitions.ts

@@ -70,13 +70,11 @@ export function buildMinimaxModelDefinition(params: {
   maxTokens: number;
 }): ModelDefinitionConfig {
   const catalog = MINIMAX_TEXT_MODEL_CATALOG[params.id as MinimaxCatalogId];
-  // MiniMax-M2.7 supports image input
-  const isImageCapable = params.id === "MiniMax-M2.7" || params.id.startsWith("MiniMax-M2.7-");
   return {
     id: params.id,
     name: params.name ?? catalog?.name ?? `MiniMax ${params.id}`,
     reasoning: params.reasoning ?? catalog?.reasoning ?? false,
-    input: isImageCapable ? ["text", "image"] : ["text"],
+    input: ["text"],
     cost: params.cost,
     contextWindow: params.contextWindow,
     maxTokens: params.maxTokens,

extensions/minimax/onboard.test.ts

@@ -21,6 +21,13 @@ describe("minimax onboard", () => {
     expect(cfg.models?.providers?.minimax?.models[0]?.reasoning).toBe(true);
   });
 
+  it("keeps MiniMax chat models text-only so image tools use MiniMax-VL-01", () => {
+    const cfg = applyMinimaxApiConfig({}, "MiniMax-M2.7-highspeed");
+    expect(cfg.models?.providers?.minimax?.models).toEqual([
+      expect.objectContaining({ id: "MiniMax-M2.7-highspeed", input: ["text"] }),
+    ]);
+  });
+
   it("preserves existing model params when adding alias", () => {
     const cfg = applyMinimaxApiConfig(
       {

src/agents/tools/image-tool.test.ts

@@ -638,6 +638,33 @@ describe("image tool implicit imageModel config", () => {
     });
   });
 
+  it("does not treat configured MiniMax M2.7 chat metadata as the image model", async () => {
+    await withTempAgentDir(async (agentDir) => {
+      vi.stubEnv("MINIMAX_API_KEY", "minimax-test");
+      vi.stubEnv("OPENAI_API_KEY", "openai-test");
+      vi.stubEnv("ANTHROPIC_API_KEY", "anthropic-test");
+      const cfg: OpenClawConfig = {
+        agents: { defaults: { model: { primary: "minimax/MiniMax-M2.7" } } },
+        models: {
+          mode: "merge",
+          providers: {
+            minimax: {
+              baseUrl: "https://api.minimax.io/anthropic",
+              apiKey: "${MINIMAX_API_KEY}",
+              api: "anthropic-messages",
+              models: [makeModelDefinition("MiniMax-M2.7", ["text"])],
+            },
+          },
+        },
+      };
+      expect(resolveImageModelConfigForTool({ cfg, agentDir })).toEqual({
+        ...createDefaultImageFallbackExpectation("minimax/MiniMax-VL-01"),
+        fallbacks: ["openai/gpt-5.4-mini", "anthropic/claude-opus-4-6"],
+      });
+      expect(createImageTool({ config: cfg, agentDir })).not.toBeNull();
+    });
+  });
+
   it("pairs minimax-portal primary with MiniMax-VL-01 (and fallbacks) when auth exists", async () => {
     await withTempAgentDir(async (agentDir) => {
       await writeAuthProfiles(agentDir, {