feat(stream-check): refresh default models and detect model-not-found errors (#2099)

* chore(stream-check): update default health check models to latest

Replaces deprecated gpt-5.1-codex@low with gpt-5.4@low and switches
the Gemini default from gemini-3-pro-preview to gemini-3-flash-preview
to pick the lightest variant of the latest series for fast, low-cost
health checks.

https://claude.ai/code/session_01NGWLchcTP76rJHjiP5Ehte

* feat(stream-check): detect model-not-found errors with dedicated toast

Health check previously classified failures purely by HTTP status code,
which meant deprecated/invalid models showed up as a generic "Not found
(404)" error pointing users to check the Base URL — misleading when the
URL is fine and only the test model is wrong (e.g. gpt-5.1-codex after
it was retired).

Backend: add detect_error_category() that inspects 4xx response bodies
for model-not-found indicators (model_not_found, does not exist,
invalid model, not_found_error, etc.) and returns a "modelNotFound"
category. Thread the resolved test model through build_stream_check_result
so the failed result carries it in model_used. Add StreamCheckResult
.error_category field (serde-skipped when None).

Frontend: useStreamCheck branches on errorCategory === "modelNotFound"
before the HTTP-status fallback and renders a toast.error with the model
name and a description pointing to Model Test Config. Add i18n keys
(modelNotFound / modelNotFoundHint) for zh/en/ja.

Tests: unit-test detect_error_category against real OpenAI/Anthropic
error shapes, 5xx false-positive avoidance, and plain 401 auth errors.

https://claude.ai/code/session_01NGWLchcTP76rJHjiP5Ehte

* fix(stream-check): add missing error_category field in fallback

The error_category field was added to StreamCheckResult in this branch
but the fallback constructor in stream_check_all_providers was not
updated, which broke cargo build.

---------

Co-authored-by: Claude <noreply@anthropic.com>

src-tauri/src/commands/stream_check.rs

@@ -133,6 +133,7 @@ pub async fn stream_check_all_providers(
                 model_used: String::new(),
                 tested_at: chrono::Utc::now().timestamp(),
                 retry_count: 0,
+                error_category: None,
             }
         });
 

src-tauri/src/services/stream_check.rs

@@ -55,8 +55,8 @@ impl Default for StreamCheckConfig {
             max_retries: 2,
             degraded_threshold_ms: 6000,
             claude_model: "claude-haiku-4-5-20251001".to_string(),
-            codex_model: "gpt-5.1-codex@low".to_string(),
-            gemini_model: "gemini-3-pro-preview".to_string(),
+            codex_model: "gpt-5.4@low".to_string(),
+            gemini_model: "gemini-3-flash-preview".to_string(),
             test_prompt: default_test_prompt(),
         }
     }
@@ -74,6 +74,9 @@ pub struct StreamCheckResult {
     pub model_used: String,
     pub tested_at: i64,
     pub retry_count: u32,
+    /// 细粒度错误分类（如 "modelNotFound"），前端据此渲染专门的文案
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub error_category: Option<String>,
 }
 
 /// 流式健康检查服务
@@ -143,6 +146,7 @@ impl StreamCheckService {
             model_used: String::new(),
             tested_at: chrono::Utc::now().timestamp(),
             retry_count: effective_config.max_retries,
+            error_category: None,
         }))
     }
 
@@ -275,6 +279,7 @@ impl StreamCheckService {
             result,
             response_time,
             config.degraded_threshold_ms,
+            &model_to_test,
         ))
     }
 
@@ -670,16 +675,21 @@ impl StreamCheckService {
             result,
             response_time,
             config.degraded_threshold_ms,
+            &model_to_test,
         ))
     }
 
     /// 将 check_*_stream 的原始结果包装成 StreamCheckResult
     ///
     /// 抽取自 check_once 的末尾逻辑，以便 OpenCode/OpenClaw 的独立分支复用。
+    ///
+    /// `model_tested` 是本次探测使用的模型名，用于在失败场景下仍能把模型信息透传给前端，
+    /// 方便针对"模型不存在 / 已下架"这类错误渲染专门的提示。
     fn build_stream_check_result(
         result: Result<(u16, String), AppError>,
         response_time: u64,
         degraded_threshold_ms: u64,
+        model_tested: &str,
     ) -> StreamCheckResult {
         let tested_at = chrono::Utc::now().timestamp();
         match result {
@@ -692,14 +702,19 @@ impl StreamCheckService {
                 model_used: model,
                 tested_at,
                 retry_count: 0,
+                error_category: None,
             },
             Err(e) => {
-                let (http_status, message) = match &e {
-                    AppError::HttpStatus { status, .. } => (
-                        Some(*status),
-                        Self::classify_http_status(*status).to_string(),
-                    ),
-                    _ => (None, e.to_string()),
+                let (http_status, message, error_category) = match &e {
+                    AppError::HttpStatus { status, body } => {
+                        let category = Self::detect_error_category(*status, body);
+                        (
+                            Some(*status),
+                            Self::classify_http_status(*status).to_string(),
+                            category.map(|s| s.to_string()),
+                        )
+                    }
+                    _ => (None, e.to_string(), None),
                 };
                 StreamCheckResult {
                     status: HealthStatus::Failed,
@@ -707,14 +722,47 @@ impl StreamCheckService {
                     message,
                     response_time_ms: Some(response_time),
                     http_status,
-                    model_used: String::new(),
+                    model_used: model_tested.to_string(),
                     tested_at,
                     retry_count: 0,
+                    error_category,
                 }
             }
         }
     }
 
+    /// 基于 HTTP 状态码和响应体识别细粒度错误分类。
+    ///
+    /// 目前仅识别"模型不存在 / 已下架"：各厂商该类错误通常返回 4xx，body 中会包含
+    /// 如 `model_not_found`（OpenAI）、`does not exist`、`invalid model`、`not_found_error`
+    /// + `model` 字样（Anthropic）等标记。
+    pub(crate) fn detect_error_category(status: u16, body: &str) -> Option<&'static str> {
+        // 只检查 4xx；5xx 的错误信息里可能巧合出现"model"之类的词，容易误判
+        if !(400..500).contains(&status) {
+            return None;
+        }
+        let lower = body.to_lowercase();
+        // 必须提到 "model"，避免通用 404 / 400 被误判
+        if !lower.contains("model") {
+            return None;
+        }
+        let indicators = [
+            "model_not_found",
+            "model not found",
+            "does not exist",
+            "invalid_model",
+            "invalid model",
+            "unknown_model",
+            "unknown model",
+            "is not a valid model",
+            "not_found_error", // Anthropic 的 type 字段
+        ];
+        if indicators.iter().any(|s| lower.contains(s)) {
+            return Some("modelNotFound");
+        }
+        None
+    }
+
     /// OpenClaw 流式检查分发器
     ///
     /// 根据 `settings_config.api` 字段分发到对应协议的检查器。
@@ -1474,6 +1522,51 @@ mod tests {
         assert_eq!(effort, None);
     }
 
+    #[test]
+    fn test_detect_model_not_found() {
+        // OpenAI 典型响应：404 + model_not_found 错误码
+        let openai_404 = r#"{"error":{"message":"The model `gpt-5.1-codex` does not exist or you do not have access to it","type":"invalid_request_error","param":null,"code":"model_not_found"}}"#;
+        assert_eq!(
+            StreamCheckService::detect_error_category(404, openai_404),
+            Some("modelNotFound")
+        );
+
+        // Anthropic 典型响应：404 + not_found_error + 提到 model
+        let anthropic_404 = r#"{"type":"error","error":{"type":"not_found_error","message":"model: claude-deprecated"}}"#;
+        assert_eq!(
+            StreamCheckService::detect_error_category(404, anthropic_404),
+            Some("modelNotFound")
+        );
+
+        // 400 + invalid model 也算
+        let bad_req = r#"{"error":{"message":"invalid model specified"}}"#;
+        assert_eq!(
+            StreamCheckService::detect_error_category(400, bad_req),
+            Some("modelNotFound")
+        );
+
+        // 通用 404（比如 Base URL 错误），body 里没有 model 字样 → 不应误判
+        let generic_404 = r#"{"error":"Not Found"}"#;
+        assert_eq!(
+            StreamCheckService::detect_error_category(404, generic_404),
+            None
+        );
+
+        // 5xx 就算 body 里有 "model does not exist" 也不分类（避免误判）
+        let server_error = r#"{"error":"model does not exist"}"#;
+        assert_eq!(
+            StreamCheckService::detect_error_category(500, server_error),
+            None
+        );
+
+        // 401 鉴权错误（body 里没有 model 字样）
+        let auth_err = r#"{"error":"Invalid API key"}"#;
+        assert_eq!(
+            StreamCheckService::detect_error_category(401, auth_err),
+            None
+        );
+    }
+
     #[test]
     fn test_get_os_name() {
         let os_name = StreamCheckService::get_os_name();

src/components/usage/ModelTestConfigPanel.tsx

@@ -25,7 +25,7 @@ export function ModelTestConfigPanel() {
     degradedThresholdMs: "6000",
     claudeModel: "claude-haiku-4-5-20251001",
     codexModel: "gpt-5.4@low",
-    geminiModel: "gemini-3-pro-preview",
+    geminiModel: "gemini-3-flash-preview",
     testPrompt: "Who are you?",
   });
 

src/hooks/useStreamCheck.ts

@@ -46,6 +46,22 @@ export function useStreamCheck(appId: AppId) {
 
           // 降级状态也重置熔断器，因为至少能通信
           resetCircuitBreaker.mutate({ providerId, appType: appId });
+        } else if (result.errorCategory === "modelNotFound") {
+          // 专门处理"模型不存在/已下架"：指向配置入口，比通用 404 文案更有指导性
+          toast.error(
+            t("streamCheck.modelNotFound", {
+              providerName: providerName,
+              model: result.modelUsed,
+              defaultValue: `${providerName} 测试模型 ${result.modelUsed} 不存在或已下架`,
+            }),
+            {
+              description: t("streamCheck.modelNotFoundHint", {
+                defaultValue: "",
+              }),
+              duration: 10000,
+              closeButton: true,
+            },
+          );
         } else {
           const httpStatus = result.httpStatus;
           const hintKey = httpStatus

src/i18n/locales/en.json

@@ -2131,6 +2131,8 @@
     "failed": "{{providerName}} check failed: {{message}}",
     "rejected": "{{providerName}} check rejected: {{message}}",
     "error": "{{providerName}} check error: {{error}}",
+    "modelNotFound": "{{providerName}} test model {{model}} does not exist or has been deprecated",
+    "modelNotFoundHint": "This model may have been retired by the provider. Update the default test model in \"Model Test Config\".",
     "httpHint": {
       "400": "Provider rejected request format. Health check probe may differ from actual usage.",
       "401": "API key may be invalid, or provider uses OAuth auth. Check failure doesn't mean it's unusable.",

src/i18n/locales/ja.json

@@ -2131,6 +2131,8 @@
     "failed": "{{providerName}} のチェックに失敗しました: {{message}}",
     "rejected": "{{providerName}} のチェックが拒否されました: {{message}}",
     "error": "{{providerName}} のチェックでエラーが発生しました: {{error}}",
+    "modelNotFound": "{{providerName}} のテストモデル {{model}} は存在しないか廃止されています",
+    "modelNotFoundHint": "このモデルはプロバイダーにより廃止された可能性があります。「モデルテスト設定」でデフォルトのテストモデルを更新してください。",
     "httpHint": {
       "400": "リクエスト形式が拒否されました。ヘルスチェックの形式は実際の使用と異なる場合があります。",
       "401": "APIキーが無効か、OAuthなどの認証方式を使用しています。チェック失敗は実際に使えないことを意味しません。",

src/i18n/locales/zh.json

@@ -2132,6 +2132,8 @@
     "failed": "{{providerName}} 检查失败: {{message}}",
     "rejected": "{{providerName}} 检查被拒: {{message}}",
     "error": "{{providerName}} 检查出错: {{error}}",
+    "modelNotFound": "{{providerName}} 测试模型 {{model}} 不存在或已下架",
+    "modelNotFoundHint": "该模型可能已被供应商弃用。请在\"模型测试配置\"中更新默认测试模型。",
     "httpHint": {
       "400": "供应商拒绝了请求格式。健康检查的探测格式可能与实际使用不同。",
       "401": "API Key 可能无效，或供应商使用 OAuth 等认证方式。检查失败不代表实际不可用。",

src/lib/api/model-test.ts

@@ -24,6 +24,8 @@ export interface StreamCheckResult {
   modelUsed: string;
   testedAt: number;
   retryCount: number;
+  /** 细粒度错误分类，如 "modelNotFound" */
+  errorCategory?: string;
 }
 
 // ===== 流式健康检查 API =====