feat: add screenshot OCR extraction

internal/domain/config.go

@@ -107,6 +107,29 @@ type LLMConfig struct {
 	Providers      map[string]LLMProviderConfig `json:"providers"`
 }
 
+// OCRProviderConfig stores one cloud OCR endpoint that accepts a screenshot
+// image and returns extracted text. Aliyun and Volcengine both authenticate
+// with an AccessKey pair, but their signing schemes use slightly different
+// endpoint metadata; keeping Region/Service/Action/Version configurable lets
+// the presets track official API changes without a schema rewrite.
+type OCRProviderConfig struct {
+	Label           string `json:"label"`
+	Endpoint        string `json:"endpoint"`
+	AccessKeyID     string `json:"accessKeyId"`
+	AccessKeySecret string `json:"accessKeySecret"`
+	Region          string `json:"region"`
+	Service         string `json:"service"`
+	Action          string `json:"action"`
+	Version         string `json:"version"`
+	TimeoutSecs     int    `json:"timeoutSecs"`
+}
+
+// OCRConfig controls screenshot text extraction.
+type OCRConfig struct {
+	ActiveProvider string                       `json:"activeProvider"`
+	Providers      map[string]OCRProviderConfig `json:"providers"`
+}
+
 // SSH authentication method identifiers stored in SSHConfig.AuthMethod.
 const (
 	// SSHAuthBuiltin is the legacy combined method (password → agent → key
@@ -129,6 +152,12 @@ const (
 	LLMProviderOpenAI = "openai"
 )
 
+// Built-in OCR provider identifiers.
+const (
+	OCRProviderAliyun     = "aliyun"
+	OCRProviderVolcengine = "volcengine"
+)
+
 // Theme preference identifiers stored in AppConfig.Theme.
 const (
 	ThemeAuto  = "auto"
@@ -172,6 +201,9 @@ type AppConfig struct {
 
 	// LLM holds provider settings for the "copy summary" screenshot action.
 	LLM LLMConfig `json:"llm"`
+
+	// OCR holds provider settings for the "extract text" screenshot action.
+	OCR OCRConfig `json:"ocr"`
 }
 
 // DefaultAppConfig returns sane zero-value defaults used on first launch.
@@ -190,6 +222,7 @@ func DefaultAppConfig() AppConfig {
 			StrictHostKey:      false,
 		},
 		LLM: DefaultLLMConfig(),
+		OCR: DefaultOCRConfig(),
 	}
 	cfg.Normalize()
 	return cfg
@@ -234,6 +267,33 @@ func DefaultLLMConfig() LLMConfig {
 	}
 }
 
+// DefaultOCRConfig returns the built-in OCR provider presets. Users only need
+// to fill AccessKey credentials for the common regions/actions, while advanced
+// accounts can still override endpoint metadata from the settings UI.
+func DefaultOCRConfig() OCRConfig {
+	return OCRConfig{
+		ActiveProvider: OCRProviderAliyun,
+		Providers: map[string]OCRProviderConfig{
+			OCRProviderAliyun: {
+				Label:       "阿里云文字识别",
+				Endpoint:    "https://ocr-api.cn-hangzhou.aliyuncs.com",
+				Action:      "RecognizeGeneral",
+				Version:     "2021-07-07",
+				TimeoutSecs: 30,
+			},
+			OCRProviderVolcengine: {
+				Label:       "火山引擎文字识别",
+				Endpoint:    "https://visual.volcengineapi.com",
+				Region:      "cn-north-1",
+				Service:     "cv",
+				Action:      "OCRNormal",
+				Version:     "2020-08-26",
+				TimeoutSecs: 30,
+			},
+		},
+	}
+}
+
 // Normalize fills defaults into configs written by older app versions while
 // preserving any user-provided provider fields.
 func (c *AppConfig) Normalize() {
@@ -295,6 +355,43 @@ func (c *AppConfig) Normalize() {
 		}
 		c.LLM.Providers[id] = current
 	}
+
+	defaultOCR := DefaultOCRConfig()
+	if c.OCR.ActiveProvider == "" {
+		c.OCR.ActiveProvider = defaultOCR.ActiveProvider
+	}
+	if c.OCR.Providers == nil {
+		c.OCR.Providers = map[string]OCRProviderConfig{}
+	}
+	for id, def := range defaultOCR.Providers {
+		current, ok := c.OCR.Providers[id]
+		if !ok {
+			c.OCR.Providers[id] = def
+			continue
+		}
+		if current.Label == "" {
+			current.Label = def.Label
+		}
+		if current.Endpoint == "" {
+			current.Endpoint = def.Endpoint
+		}
+		if current.Region == "" {
+			current.Region = def.Region
+		}
+		if current.Service == "" {
+			current.Service = def.Service
+		}
+		if current.Action == "" {
+			current.Action = def.Action
+		}
+		if current.Version == "" {
+			current.Version = def.Version
+		}
+		if current.TimeoutSecs == 0 {
+			current.TimeoutSecs = def.TimeoutSecs
+		}
+		c.OCR.Providers[id] = current
+	}
 }
 
 // IsS3Configured reports whether the user has filled the mandatory S3 fields.
@@ -329,3 +426,32 @@ func (c AppConfig) IsLLMConfigured() bool {
 	_, provider, ok := c.ActiveLLMProvider()
 	return ok && provider.BaseURL != "" && provider.APIKey != "" && provider.Model != ""
 }
+
+// ActiveOCRProvider returns the selected OCR provider config plus a boolean
+// indicating whether the selection exists.
+func (c AppConfig) ActiveOCRProvider() (string, OCRProviderConfig, bool) {
+	id := c.OCR.ActiveProvider
+	if id == "" {
+		id = OCRProviderAliyun
+	}
+	provider, ok := c.OCR.Providers[id]
+	return id, provider, ok
+}
+
+// IsOCRConfigured reports whether the selected OCR provider has the fields
+// required to sign and send a request.
+func (c AppConfig) IsOCRConfigured() bool {
+	id, provider, ok := c.ActiveOCRProvider()
+	if !ok ||
+		provider.Endpoint == "" ||
+		provider.AccessKeyID == "" ||
+		provider.AccessKeySecret == "" ||
+		provider.Action == "" ||
+		provider.Version == "" {
+		return false
+	}
+	if id == OCRProviderVolcengine && (provider.Region == "" || provider.Service == "") {
+		return false
+	}
+	return true
+}