fix: update OVHcloud default model to Qwen3.5-397B-A17B

Qwen3-235B-A22B is not in the current OVHcloud AI Endpoints catalogue.
Replace it with Qwen3.5-397B-A17B (confirmed present) everywhere:
DefaultModels, examples/ovhcloud.yaml, and all doc snippets.

Also refresh the model table in docs/providers/ovhcloud/index.md:
drop the three stale rows (Qwen3-235B-A22B, Mixtral-8x7B-Instruct-v0.1,
DeepSeek-R1-Distill-Llama-70B) and add current catalogue IDs
(Qwen3.5-397B-A17B, Qwen3.6-27B, Qwen3.5-9B, Qwen3-Coder-30B-A3B-Instruct).

Addresses review feedback on PR #3343.

docs/providers/ovhcloud/index.md

@@ -31,7 +31,7 @@ built-in support for OVHcloud as an alias provider.
 ```yaml
 agents:
   root:
-    model: ovhcloud/Qwen3-235B-A22B
+    model: ovhcloud/Qwen3.5-397B-A17B
     description: Assistant using OVHcloud
     instruction: You are a helpful assistant.
 ```
@@ -42,7 +42,7 @@ agents:
 models:
   ovhcloud_model:
     provider: ovhcloud
-    model: Qwen3-235B-A22B
+    model: Qwen3.5-397B-A17B
     temperature: 0.7
     max_tokens: 8192
 
@@ -61,12 +61,13 @@ IDs, context limits, and free-tier availability.
 
 | Model | Description |
 | --- | --- |
-| `Qwen3-235B-A22B` | Large Qwen3 MoE — strong general, coding, and reasoning |
+| `Qwen3.5-397B-A17B` | Large Qwen3.5 MoE — strong general, coding, and reasoning |
 | `Qwen3-32B` | Mid-size Qwen3 — fast, tool-calling, reasoning |
+| `Qwen3.6-27B` | Compact Qwen3.6 — fast and efficient |
+| `Qwen3.5-9B` | Small Qwen3.5 — lightweight, free-tier friendly |
+| `Qwen3-Coder-30B-A3B-Instruct` | Qwen3 Coder MoE — optimised for code generation |
 | `Meta-Llama-3_3-70B-Instruct` | Llama 3.3 70B — reliable general-purpose chat |
 | `Mistral-Small-3.2-24B-Instruct-2506` | Compact, fast, tool-calling |
-| `Mixtral-8x7B-Instruct-v0.1` | Mixtral MoE — cost-efficient |
-| `DeepSeek-R1-Distill-Llama-70B` | Distilled reasoning model |
 
 > Model IDs are case-sensitive and must be passed exactly as the catalogue lists
 > them.
@@ -95,8 +96,8 @@ paid plan avoids the free-tier request-rate cap.
 ```yaml
 agents:
   coder:
-    model: ovhcloud/Qwen3-235B-A22B
-    description: Code assistant using Qwen3
+    model: ovhcloud/Qwen3.5-397B-A17B
+    description: Code assistant using Qwen3.5
     instruction: |
       You are an expert programmer.
       Write clean, well-documented code and follow language best practices.

examples/ovhcloud.yaml

@@ -3,7 +3,7 @@
 models:
   ovhcloud_model:
     provider: ovhcloud
-    model: Qwen3-235B-A22B
+    model: Qwen3.5-397B-A17B
 
 agents:
   root:

pkg/config/auto.go

@@ -110,7 +110,7 @@ var DefaultModels = map[string]string{
 	"mistral":        "mistral-small-latest",
 	"openrouter":     "meta-llama/llama-3.3-70b-instruct",
 	"baseten":        "deepseek-ai/DeepSeek-V3.1",
-	"ovhcloud":       "Qwen3-235B-A22B",
+	"ovhcloud":       "Qwen3.5-397B-A17B",
 	"amazon-bedrock": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
 	"opencode-go":    "deepseek-v4-flash",
 	"opencode-zen":   "deepseek-v4-flash-free",

pkg/config/auto_test.go

@@ -246,7 +246,7 @@ func TestAutoModelConfig(t *testing.T) {
 				"OVH_AI_ENDPOINTS_ACCESS_TOKEN": "test-token",
 			},
 			expectedProvider:  "ovhcloud",
-			expectedModel:     "Qwen3-235B-A22B",
+			expectedModel:     "Qwen3.5-397B-A17B",
 			expectedMaxTokens: 32000,
 		},
 		{
@@ -349,7 +349,7 @@ func TestDefaultModels(t *testing.T) {
 	assert.Equal(t, "mistral-small-latest", DefaultModels["mistral"])
 	assert.Equal(t, "meta-llama/llama-3.3-70b-instruct", DefaultModels["openrouter"])
 	assert.Equal(t, "deepseek-ai/DeepSeek-V3.1", DefaultModels["baseten"])
-	assert.Equal(t, "Qwen3-235B-A22B", DefaultModels["ovhcloud"])
+	assert.Equal(t, "Qwen3.5-397B-A17B", DefaultModels["ovhcloud"])
 	assert.Equal(t, "global.anthropic.claude-sonnet-4-5-20250929-v1:0", DefaultModels["amazon-bedrock"])
 	assert.Equal(t, "deepseek-v4-flash", DefaultModels["opencode-go"])
 	assert.Equal(t, "deepseek-v4-flash-free", DefaultModels["opencode-zen"])

pkg/model/provider/openai/system_message_merge_test.go

@@ -50,7 +50,7 @@ func TestOVHcloud_MergesConsecutiveSystemMessages(t *testing.T) {
 
 	assertMergesConsecutiveMessages(t, &latest.ModelConfig{
 		Provider: "ovhcloud",
-		Model:    "Qwen3-235B-A22B",
+		Model:    "Qwen3.5-397B-A17B",
 		TokenKey: "MY_TOKEN",
 	})
 }