feat: you can summary screen shot directly

2026-07-07 00:59:26 +08:00
parent 39f0aaae02
commit 712a2cbb6a
17 changed files with 1432 additions and 51 deletions
@@ -10,12 +10,12 @@ package domain
 // endpoint, etc.).
 //
 // Field design notes:
-// - PathPrefix supports object name templating so users can group screenshots
-//   by date.
-// - PublicURLBase is optional to support CDN-fronted buckets; otherwise the
-//   adapter falls back to "{Endpoint}/{Bucket}/{Key}" (path-style).
-// - UsePathStyle defaults to true because many self-hosted MinIO / R2
-//   deployments do not support virtual-hosted-style addressing.
+//   - PathPrefix supports object name templating so users can group screenshots
+//     by date.
+//   - PublicURLBase is optional to support CDN-fronted buckets; otherwise the
+//     adapter falls back to "{Endpoint}/{Bucket}/{Key}" (path-style).
+//   - UsePathStyle defaults to true because many self-hosted MinIO / R2
+//     deployments do not support virtual-hosted-style addressing.
 type S3Config struct {
 	Endpoint        string `json:"endpoint"`
 	Region          string `json:"region"`
@@ -34,17 +34,17 @@ type S3Config struct {
 //   - Host / Port form the destination endpoint. Port defaults to 22 when 0.
 //   - User is the SSH login name.
 //   - AuthMethod selects how the connection authenticates:
-//       "password"     → password only, via the in-process Go SSH client.
-//       "key"          → ssh-agent + ~/.ssh/id_* key files (no password),
-//                         via the in-process Go SSH client.
-//       "kerberos"     → delegate to the system /usr/bin/ssh binary so the
-//                         existing Kerberos (GSSAPI) credential cache from
-//                         `kinit` is reused. Native GSSAPI is required here
-//                         because macOS stores tickets in an API: ccache
-//                         that pure-Go SSH libraries cannot read.
-//       "" / "builtin" → legacy combined behaviour (password → agent → key
-//                         files) kept only for backward compatibility with
-//                         configs written before the method was split.
+//     "password"     → password only, via the in-process Go SSH client.
+//     "key"          → ssh-agent + ~/.ssh/id_* key files (no password),
+//     via the in-process Go SSH client.
+//     "kerberos"     → delegate to the system /usr/bin/ssh binary so the
+//     existing Kerberos (GSSAPI) credential cache from
+//     `kinit` is reused. Native GSSAPI is required here
+//     because macOS stores tickets in an API: ccache
+//     that pure-Go SSH libraries cannot read.
+//     "" / "builtin" → legacy combined behaviour (password → agent → key
+//     files) kept only for backward compatibility with
+//     configs written before the method was split.
 //   - Password is optional; when empty the implementation falls back to the
 //     local SSH agent or ~/.ssh/id_* keys (i.e. the user is responsible for
 //     having password-less access already configured on this machine).
@@ -72,6 +72,29 @@ type SSHConfig struct {
 	ConnectTimeoutSecs int    `json:"connectTimeoutSecs"`
 }

+// LLMProviderConfig stores one OpenAI-compatible multimodal chat endpoint.
+//
+// The three built-in providers (Qwen, Doubao/Ark, OpenAI-compatible) all use
+// the same request shape: chat/completions with a user content array that
+// contains text plus an image_url item. Keeping them as provider records lets
+// users switch between credentials/models without retyping every field.
+type LLMProviderConfig struct {
+	Label       string  `json:"label"`
+	BaseURL     string  `json:"baseUrl"`
+	APIKey      string  `json:"apiKey"`
+	Model       string  `json:"model"`
+	MaxTokens   int     `json:"maxTokens"`
+	Temperature float64 `json:"temperature"`
+	TimeoutSecs int     `json:"timeoutSecs"`
+}
+
+// LLMConfig controls screenshot summarisation.
+type LLMConfig struct {
+	ActiveProvider string                       `json:"activeProvider"`
+	Prompt         string                       `json:"prompt"`
+	Providers      map[string]LLMProviderConfig `json:"providers"`
+}
+
 // SSH authentication method identifiers stored in SSHConfig.AuthMethod.
 const (
 	// SSHAuthBuiltin is the legacy combined method (password → agent → key
@@ -87,6 +110,22 @@ const (
 	SSHAuthKerberos = "kerberos"
 )

+// Built-in LLM provider identifiers.
+const (
+	LLMProviderQwen   = "qwen"
+	LLMProviderDoubao = "doubao"
+	LLMProviderOpenAI = "openai"
+)
+
+const DefaultSummaryPrompt = `你是一个截图内容总结助手。请阅读截图，并用中文输出一段适合直接粘贴到聊天、工单、Issue 或 PR 中的说明。
+
+要求：
+- 先说明截图中最重要的信息和用户可能想表达的意图。
+- 如果截图包含报错、异常状态、表格、代码、界面控件或关键数字，请准确提取。
+- 如果截图内容不足以判断，不要编造；直接说明不确定点。
+- 输出尽量简洁，默认 3 到 6 条要点。
+- 不要输出 Markdown 标题，不要寒暄。`
+
 // IsKerberos reports whether this config requests Kerberos/GSSAPI auth.
 func (c SSHConfig) IsKerberos() bool {
 	return c.AuthMethod == SSHAuthKerberos
@@ -108,11 +147,14 @@ type AppConfig struct {
 	// SSH holds the configuration for the optional "save to remote via scp"
 	// destination triggered by the save-remote toolbar button.
 	SSH SSHConfig `json:"ssh"`
+
+	// LLM holds provider settings for the "copy summary" screenshot action.
+	LLM LLMConfig `json:"llm"`
 }

 // DefaultAppConfig returns sane zero-value defaults used on first launch.
 func DefaultAppConfig() AppConfig {
-	return AppConfig{
+	cfg := AppConfig{
 		Hotkey: "cmd+shift+a",
 		S3: S3Config{
 			PathPrefix:   "snapgo/",
@@ -124,6 +166,102 @@ func DefaultAppConfig() AppConfig {
 			ConnectTimeoutSecs: 10,
 			StrictHostKey:      false,
 		},
+		LLM: DefaultLLMConfig(),
+	}
+	cfg.Normalize()
+	return cfg
+}
+
+// DefaultLLMConfig returns the built-in provider presets. API keys and exact
+// models remain user-editable because each provider account may expose
+// different model names / endpoint IDs.
+func DefaultLLMConfig() LLMConfig {
+	return LLMConfig{
+		ActiveProvider: LLMProviderOpenAI,
+		Prompt:         DefaultSummaryPrompt,
+		Providers: map[string]LLMProviderConfig{
+			LLMProviderQwen: {
+				Label:       "阿里千问多模态",
+				BaseURL:     "https://dashscope.aliyuncs.com/compatible-mode/v1",
+				Model:       "qwen-vl-plus",
+				MaxTokens:   600,
+				Temperature: 0.2,
+				TimeoutSecs: 60,
+			},
+			LLMProviderDoubao: {
+				Label:       "火山方舟豆包多模态",
+				BaseURL:     "https://ark.cn-beijing.volces.com/api/v3",
+				Model:       "",
+				MaxTokens:   600,
+				Temperature: 0.2,
+				TimeoutSecs: 60,
+			},
+			LLMProviderOpenAI: {
+				Label:       "ChatGPT / OpenAI-compatible",
+				BaseURL:     "https://api.openai.com/v1",
+				Model:       "gpt-5.5",
+				MaxTokens:   600,
+				Temperature: 0.2,
+				TimeoutSecs: 60,
+			},
+		},
+	}
+}
+
+// Normalize fills defaults into configs written by older app versions while
+// preserving any user-provided provider fields.
+func (c *AppConfig) Normalize() {
+	if c.Hotkey == "" {
+		c.Hotkey = "cmd+shift+a"
+	}
+	if c.S3.PathPrefix == "" {
+		c.S3.PathPrefix = "snapgo/"
+	}
+	if c.SSH.Port == 0 {
+		c.SSH.Port = 22
+	}
+	if c.SSH.PathPrefix == "" {
+		c.SSH.PathPrefix = "snapgo/"
+	}
+	if c.SSH.ConnectTimeoutSecs == 0 {
+		c.SSH.ConnectTimeoutSecs = 10
+	}
+
+	defaultLLM := DefaultLLMConfig()
+	if c.LLM.ActiveProvider == "" {
+		c.LLM.ActiveProvider = defaultLLM.ActiveProvider
+	}
+	if c.LLM.Prompt == "" {
+		c.LLM.Prompt = defaultLLM.Prompt
+	}
+	if c.LLM.Providers == nil {
+		c.LLM.Providers = map[string]LLMProviderConfig{}
+	}
+	for id, def := range defaultLLM.Providers {
+		current, ok := c.LLM.Providers[id]
+		if !ok {
+			c.LLM.Providers[id] = def
+			continue
+		}
+		if current.Label == "" {
+			current.Label = def.Label
+		}
+		if current.BaseURL == "" {
+			current.BaseURL = def.BaseURL
+		}
+		if current.Model == "" && id != LLMProviderDoubao {
+			current.Model = def.Model
+		}
+		if current.MaxTokens == 0 {
+			current.MaxTokens = def.MaxTokens
+		}
+		if current.Temperature < 0 {
+			current.Temperature = def.Temperature
+		}
+		if current.TimeoutSecs == 0 {
+			current.TimeoutSecs = def.TimeoutSecs
+		}
+		c.LLM.Providers[id] = current
 	}
 }

@@ -141,3 +279,21 @@ func (c AppConfig) IsS3Configured() bool {
 func (c AppConfig) IsSSHConfigured() bool {
 	return c.SSH.Host != "" && c.SSH.User != ""
 }
+
+// ActiveLLMProvider returns the selected provider config plus a boolean
+// indicating whether the selection exists.
+func (c AppConfig) ActiveLLMProvider() (string, LLMProviderConfig, bool) {
+	id := c.LLM.ActiveProvider
+	if id == "" {
+		id = LLMProviderOpenAI
+	}
+	provider, ok := c.LLM.Providers[id]
+	return id, provider, ok
+}
+
+// IsLLMConfigured reports whether the selected multimodal provider has the
+// fields required to make a request.
+func (c AppConfig) IsLLMConfigured() bool {
+	_, provider, ok := c.ActiveLLMProvider()
+	return ok && provider.BaseURL != "" && provider.APIKey != "" && provider.Model != ""
+}