diff --git a/README.md b/README.md index a5cdf54..56f88b6 100644 --- a/README.md +++ b/README.md @@ -65,6 +65,32 @@ func main() { ## 版本历史 +### v1.4 — 工具集扩展与 Windows 编码攻坚 + +#### 变更 + +- **新增 BashTool** — 执行本地 bash 命令，支持 30s 超时、错误原样回传（模型自愈）、8KB 输出截断 +- **新增 WriteFileTool** — 写文件到工作区，覆盖/新建均支持 +- **Windows GBK 编码修复** — 命令输出从 GBK 自动转 UTF-8（`golang.org/x/text/encoding/simplifiedchinese`），不依赖 `chcp` +- **API 交互日志** — `OpenAIProvider.Generate` 新增请求/响应日志（阶段标记、消息数、工具数、ToolCall 明细） +- **调试输出优化** — `dumpMessages` 移除 80 字符截断，完整展示上下文内容 +- **三段式任务演示** — `cmd/claw` 任务改为：查 Go 版本 → 写 helloworld.go → 编译运行 + +#### 踩坑记录 + +| 问题 | 原因 | 解决 | +|---|---|---| +| bash 输出中文乱码 | Windows 命令输出为 GBK 编码，Go 按 UTF-8 解析 | 引入 `golang.org/x/text`，检测编码后自动转换 | +| `chcp 65001` 导致终端刷屏 | `chcp` 在子进程中修改代码页可能影响终端渲染 | 放弃 `chcp` 方案，改用 Go 原生编码转换 | +| `utf8.Valid` 检查后仍乱码 | GBK 字节序列碰巧也合法于 UTF-8，跳过转换 | 去掉 `utf8.Valid` 判断，Windows 下一律转换 | +| `helloworld.go` 导致编译失败 | 模型生成的测试文件含 `main` 函数，与项目 main.go 冲突 | 运行后清理 `helloworld.*` 测试产物 | + +#### 经验教训 + +1. **编码问题不要依赖外部命令** — `chcp` 属于"改环境让输出配合你"，不可靠。Go 原生转码属于"你主动适应输出"，稳定可控 +2. **`utf8.Valid` 不能当编码检测器** — 它的语义是"是否合法 UTF-8"，不是"是否是 GBK"。GBK 和 UTF-8 有交集，用合法性判断编码方向是伪命题 +3. **Agent 的工具越多，越需要关注副作用** — 模型会写文件、执行命令，产生的文件（helloworld.go）可能反过来破坏项目结构。工具内部要做好隔离 + ### v1.3 — Registry 实现重构与第一把真实工具 #### 变更 diff --git a/cmd/claw/main.go b/cmd/claw/main.go index 0de8f0b..424c443 100644 --- a/cmd/claw/main.go +++ b/cmd/claw/main.go @@ -18,21 +18,23 @@ func main() { // 这里你可以任意切换 NewZhipuClaudeProvider 或 NewZhipuOpenAIProvider，效果完全一致！ llmProvider := provider.DeepseekOpenAIProvider("deepseek-v4-flash") - // 3. 初始化真实的 Tool Registry registry := tools.NewRegistry() - // 4. 将真实的 ReadFile 工具挂载到注册表中 - readFileTool := tools.NewReadFileTool(workDir) - registry.Register(readFileTool) + // 挂载极简工具集 + registry.Register(tools.NewReadFileTool(workDir)) + registry.Register(tools.NewWriteFileTool(workDir)) + registry.Register(tools.NewBashTool(workDir)) - // 5. 实例化核心引擎，由于任务简单，我们关闭思考阶段 (EnableThinking = false) 以加快速度 + // 实例化核心引擎，关闭慢思考阶段，享受 YOLO 急速模式 eng := engine.NewAgentEngine(llmProvider, registry, workDir, false) - log.Printf("registry: %s\n", registry) - log.Printf("engine: %s\n", eng) - - // 6. 下发一个必须通过真实工具才能完成的任务 - prompt := "请调用工具读取一下当前工作区目录下 hello.txt 文件的内容，并用一句话向我总结它说了什么。" + // 发起一个需要连贯物理动作的任务 + prompt := ` + 请帮我执行以下操作： + 1. 用 bash 查看一下我当前电脑的 Go 版本，我的电脑是windows系统。 + 2. 帮我写一个简单的 helloworld.go 文件，输出 "Hello, go-tiny-claw!"。 + 3. 用 bash 编译并运行这个 go 文件，确认它能正常工作。 + ` err := eng.Run(context.Background(), prompt) if err != nil { diff --git a/go.mod b/go.mod index 55f0347..fa20f1a 100644 --- a/go.mod +++ b/go.mod @@ -3,13 +3,16 @@ module go-tiny-claw go 1.23.0 require ( - github.com/anthropics/anthropic-sdk-go v1.43.0 // indirect + github.com/anthropics/anthropic-sdk-go v1.43.0 + github.com/openai/openai-go/v3 v3.35.0 + golang.org/x/text v0.27.0 +) + +require ( github.com/bahlo/generic-list-go v0.2.0 // indirect github.com/buger/jsonparser v1.1.2 // indirect github.com/invopop/jsonschema v0.13.0 // indirect - github.com/joho/godotenv v1.5.1 // indirect github.com/mailru/easyjson v0.7.7 // indirect - github.com/openai/openai-go/v3 v3.35.0 // indirect github.com/standard-webhooks/standard-webhooks/libraries v0.0.1 // indirect github.com/tidwall/gjson v1.18.0 // indirect github.com/tidwall/match v1.1.1 // indirect diff --git a/go.sum b/go.sum index 99f4318..6027867 100644 --- a/go.sum +++ b/go.sum @@ -4,17 +4,23 @@ github.com/bahlo/generic-list-go v0.2.0 h1:5sz/EEAK+ls5wF+NeqDpk5+iNdMDXrh3z3nPn github.com/bahlo/generic-list-go v0.2.0/go.mod h1:2KvAjgMlE5NNynlg/5iLrrCCZ2+5xWbdbCW3pNTGyYg= github.com/buger/jsonparser v1.1.2 h1:frqHqw7otoVbk5M8LlE/L7HTnIq2v9RX6EJ48i9AxJk= github.com/buger/jsonparser v1.1.2/go.mod h1:6RYKKt7H4d4+iWqouImQ9R2FZql3VbhNgx27UK13J/0= +github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c= +github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= +github.com/dnaeon/go-vcr v1.2.0 h1:zHCHvJYTMh1N7xnV7zf1m1GPBF9Ad0Jk/whtQ1663qI= +github.com/dnaeon/go-vcr v1.2.0/go.mod h1:R4UdLID7HZT3taECzJs4YgbbH6PIGXB6W/sc5OLb6RQ= github.com/invopop/jsonschema v0.13.0 h1:KvpoAJWEjR3uD9Kbm2HWJmqsEaHt8lBUpd0qHcIi21E= github.com/invopop/jsonschema v0.13.0/go.mod h1:ffZ5Km5SWWRAIN6wbDXItl95euhFz2uON45H2qjYt+0= -github.com/joho/godotenv v1.5.1 h1:7eLL/+HRGLY0ldzfGMeQkb7vMd0as4CfYvUVzLqw0N0= -github.com/joho/godotenv v1.5.1/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwAbqwq4= github.com/josharian/intern v1.0.0/go.mod h1:5DoeVV0s6jJacbCEi61lwdGj/aVlrQvzHFFd8Hwg//Y= github.com/mailru/easyjson v0.7.7 h1:UGYAvKxe3sBsEDzO8ZeWOSlIQfWFlxbzLZe7hwFURr0= github.com/mailru/easyjson v0.7.7/go.mod h1:xzfreul335JAWq5oZzymOObrkdz5UnU4kGfJJLY9Nlc= github.com/openai/openai-go/v3 v3.35.0 h1:109x3epXMSE423KW2euR506GGFezcEt0s87MoWejpH0= github.com/openai/openai-go/v3 v3.35.0/go.mod h1:cdufnVK14cWcT9qA1rRtrXx4FTRsgbDPW7Ia7SS5cZo= +github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM= +github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= github.com/standard-webhooks/standard-webhooks/libraries v0.0.1 h1:uOfcYT+3QungH6tIGSVCR/Y3KJmgJiHcojJbMTPDZAI= github.com/standard-webhooks/standard-webhooks/libraries v0.0.1/go.mod h1:L1MQhA6x4dn9r007T033lsaZMv9EmBAdXyU/+EF40fo= +github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk= +github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo= github.com/tidwall/gjson v1.14.2/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk= github.com/tidwall/gjson v1.18.0 h1:FIDeeyB800efLX89e5a8Y0BNH+LOngJyGrIWxG2FKQY= github.com/tidwall/gjson v1.18.0/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk= @@ -29,6 +35,11 @@ github.com/wk8/go-ordered-map/v2 v2.1.8 h1:5h/BUHu93oj4gIdvHHHGsScSTMijfx5PeYkE/ github.com/wk8/go-ordered-map/v2 v2.1.8/go.mod h1:5nJHM5DyteebpVlHnWMV0rPz6Zp7+xBAnxjb1X5vnTw= golang.org/x/sync v0.16.0 h1:ycBJEhp9p4vXvUZNszeOq0kGTPghopOL8q0fq3vstxw= golang.org/x/sync v0.16.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA= +golang.org/x/text v0.27.0 h1:4fGWRpyh641NLlecmyl4LOe6yDdfaYNrGb2zdfo4JV4= +golang.org/x/text v0.27.0/go.mod h1:1D28KMCvyooCX9hBiosv5Tz/+YLxj0j7XhWjpSUF7CU= +gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= +gopkg.in/yaml.v2 v2.2.8 h1:obN1ZagJSUGI0Ek/LBmuj4SNLPfIny3KsKFopxRdj10= +gopkg.in/yaml.v2 v2.2.8/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI= gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= diff --git a/internal/engine/loop.go b/internal/engine/loop.go index 7e360b1..af06398 100644 --- a/internal/engine/loop.go +++ b/internal/engine/loop.go @@ -16,15 +16,15 @@ type AgentEngine struct { registry tools.Registry // WorkDir (工作区): 借鉴 OpenClaw 的理念，Agent 必须有一个明确的物理边界 - WorkDir string + WorkDir string EnableThinking bool // 【新增】慢思考模式开关 } func NewAgentEngine(p provider.LLMProvider, r tools.Registry, workDir string, enableThinking bool) *AgentEngine { return &AgentEngine{ - provider: p, - registry: r, - WorkDir: workDir, + provider: p, + registry: r, + WorkDir: workDir, EnableThinking: enableThinking, } } @@ -37,9 +37,9 @@ func (e *AgentEngine) String() string { func dumpMessages(msgs []schema.Message) { for i, msg := range msgs { content := msg.Content - if len(content) > 80 { - content = content[:80] + "..." - } + // if len(content) > 80 { + // content = content[:80] + "..." + // } log.Printf(" [%02d] %-10s | %s", i, msg.Role, content) } } @@ -57,116 +57,116 @@ func dumpTools(tools []schema.ToolDefinition) { // internal/engine/loop.go (续) func (e *AgentEngine) Run(ctx context.Context, userPrompt string) error { - log.Printf("[Engine] 引擎启动，锁定工作区: %s\n", e.WorkDir) - log.Printf("[Engine] 慢思考模式 (Thinking Phase): %v\n", e.EnableThinking) + log.Printf("[Engine] 引擎启动，锁定工作区: %s\n", e.WorkDir) + log.Printf("[Engine] 慢思考模式 (Thinking Phase): %v\n", e.EnableThinking) - contextHistory := []schema.Message{ - { - Role: schema.RoleSystem, - Content: "You are go-tiny-claw, an expert coding assistant. You have full access to tools in the workspace.", - }, - { - Role: schema.RoleUser, - Content: userPrompt, - }, - } + contextHistory := []schema.Message{ + { + Role: schema.RoleSystem, + Content: "You are go-tiny-claw, an expert coding assistant. You have full access to tools in the workspace.", + }, + { + Role: schema.RoleUser, + Content: userPrompt, + }, + } - turnCount := 0 - const maxTurns = 10 + turnCount := 0 + const maxTurns = 10 - for { - turnCount++ - if turnCount > maxTurns { - log.Printf("[Engine] 已达最大轮数 (%d)，强制终止。\n", maxTurns) - break - } - log.Printf("\n========== [Turn %d] 开始 ==========\n", turnCount) - dumpMessages(contextHistory) + for { + turnCount++ + if turnCount > maxTurns { + log.Printf("[Engine] 已达最大轮数 (%d)，强制终止。\n", maxTurns) + break + } + log.Printf("\n========== [Turn %d] 开始 ==========\n", turnCount) + dumpMessages(contextHistory) - // 获取当前挂载的所有工具定义 - availableTools := e.registry.GetAvailableTools() - dumpTools(availableTools) + // 获取当前挂载的所有工具定义 + availableTools := e.registry.GetAvailableTools() + dumpTools(availableTools) - // ==================================================================== - // Phase 1: 慢思考阶段 (Thinking) - 仅第一轮执行初始规划 - // ==================================================================== - if e.EnableThinking && turnCount == 1 { - log.Println("[Engine][Phase 1] 剥夺工具访问权，强制进入慢思考与规划阶段...") + // ==================================================================== + // Phase 1: 慢思考阶段 (Thinking) - 仅第一轮执行初始规划 + // ==================================================================== + if e.EnableThinking && turnCount == 1 { + log.Println("[Engine][Phase 1] 剥夺工具访问权，强制进入慢思考与规划阶段...") - // 核心机制：传入的 availableTools 为 nil！ - // 大模型看不到任何 JSON Schema，被迫只能输出纯文本的思考过程。 - thinkResp, err := e.provider.Generate(ctx, contextHistory, nil) - if err != nil { - return fmt.Errorf("Thinking 阶段生成失败: %w", err) - } + // 核心机制：传入的 availableTools 为 nil！ + // 大模型看不到任何 JSON Schema，被迫只能输出纯文本的思考过程。 + thinkResp, err := e.provider.Generate(ctx, contextHistory, nil) + if err != nil { + return fmt.Errorf("Thinking 阶段生成失败: %w", err) + } - // 如果模型输出了思考过程，我们将其作为 Assistant 消息追加到上下文中 - if thinkResp.Content != "" { - fmt.Printf("🧠 [内部思考 Trace]: %s\n", thinkResp.Content) - contextHistory = append(contextHistory, *thinkResp) - } + // 如果模型输出了思考过程，我们将其作为 Assistant 消息追加到上下文中 + if thinkResp.Content != "" { + fmt.Printf("🧠 [内部思考 Trace]: %s\n", thinkResp.Content) + contextHistory = append(contextHistory, *thinkResp) + } - // 插入过渡指令：让模型知道现在可以调用工具了 - contextHistory = append(contextHistory, schema.Message{ - Role: schema.RoleUser, - Content: "根据你的推理，现在请使用可用的工具来完成任务。执行具体行动。", - }) - } + // 插入过渡指令：让模型知道现在可以调用工具了 + contextHistory = append(contextHistory, schema.Message{ + Role: schema.RoleUser, + Content: "根据你的推理，现在请使用可用的工具来完成任务。执行具体行动。", + }) + } - // ==================================================================== - // Phase 2: 行动阶段 (Action) - 恢复工具，顺着规划执行 - // ==================================================================== - log.Println("[Engine][Phase 2] 恢复工具挂载，等待模型采取行动...") + // ==================================================================== + // Phase 2: 行动阶段 (Action) - 恢复工具，顺着规划执行 + // ==================================================================== + log.Println("[Engine][Phase 2] 恢复工具挂载，等待模型采取行动...") - // 此时的 contextHistory 中已经包含了上一阶段模型自己的 Thinking Trace + 过渡指令。 - // 模型会顺着自己的逻辑，结合恢复的 availableTools 发起精准的工具调用。 - actionResp, err := e.provider.Generate(ctx, contextHistory, availableTools) - if err != nil { - return fmt.Errorf("Action 阶段生成失败: %w", err) - } + // 此时的 contextHistory 中已经包含了上一阶段模型自己的 Thinking Trace + 过渡指令。 + // 模型会顺着自己的逻辑，结合恢复的 availableTools 发起精准的工具调用。 + actionResp, err := e.provider.Generate(ctx, contextHistory, availableTools) + if err != nil { + return fmt.Errorf("Action 阶段生成失败: %w", err) + } - contextHistory = append(contextHistory, *actionResp) + contextHistory = append(contextHistory, *actionResp) - if actionResp.Content != "" { - fmt.Printf("🤖 [对外回复]: %s\n", actionResp.Content) - } + if actionResp.Content != "" { + fmt.Printf("🤖 [对外回复]: %s\n", actionResp.Content) + } - // ==================================================================== - // 退出与执行逻辑 (与上一讲保持一致) - // ==================================================================== - if len(actionResp.ToolCalls) == 0 { - log.Println("[Engine] 模型未请求调用工具，任务宣告完成。") - break - } + // ==================================================================== + // 退出与执行逻辑 (与上一讲保持一致) + // ==================================================================== + if len(actionResp.ToolCalls) == 0 { + log.Println("[Engine] 模型未请求调用工具，任务宣告完成。") + break + } - log.Printf("[Engine] 模型请求调用 %d 个工具...\n", len(actionResp.ToolCalls)) + log.Printf("[Engine] 模型请求调用 %d 个工具...\n", len(actionResp.ToolCalls)) - for _, toolCall := range actionResp.ToolCalls { - log.Printf(" -> 🛠️ 执行工具: %s, 参数: %s\n", toolCall.Name, string(toolCall.Arguments)) + for _, toolCall := range actionResp.ToolCalls { + log.Printf(" -> 🛠️ 执行工具: %s, 参数: %s\n", toolCall.Name, string(toolCall.Arguments)) - result := e.registry.Execute(ctx, toolCall) + result := e.registry.Execute(ctx, toolCall) - status := "✅ 成功" - if result.IsError { - status = "❌ 失败" - } - log.Printf(" -> 📋 ToolCall %s: %s, 结果: %s\n", toolCall.ID, status, result.Output) + status := "✅ 成功" + if result.IsError { + status = "❌ 失败" + } + log.Printf(" -> 📋 ToolCall %s: %s, 结果: %s\n", toolCall.ID, status, result.Output) - if result.IsError { - log.Printf(" -> ❌ 工具执行报错: %s\n", result.Output) - } else { - log.Printf(" -> ✅ 工具执行成功 (返回 %d 字节)\n", len(result.Output)) - } + if result.IsError { + log.Printf(" -> ❌ 工具执行报错: %s\n", result.Output) + } else { + log.Printf(" -> ✅ 工具执行成功 (返回 %d 字节)\n", len(result.Output)) + } - // 将工具执行的观察结果追加到 Context，准备进入下一轮 - observationMsg := schema.Message{ - Role: schema.RoleUser, - Content: result.Output, - ToolCallID: toolCall.ID, - } - contextHistory = append(contextHistory, observationMsg) - } - } + // 将工具执行的观察结果追加到 Context，准备进入下一轮 + observationMsg := schema.Message{ + Role: schema.RoleUser, + Content: result.Output, + ToolCallID: toolCall.ID, + } + contextHistory = append(contextHistory, observationMsg) + } + } - return nil + return nil } diff --git a/internal/provider/openai.go b/internal/provider/openai.go index ede73e1..b0bc367 100644 --- a/internal/provider/openai.go +++ b/internal/provider/openai.go @@ -2,192 +2,212 @@ package provider import ( - "context" - "encoding/json" - "fmt" - // "os" + "context" + "encoding/json" + "fmt" + "log" - "github.com/openai/openai-go/v3" - "github.com/openai/openai-go/v3/option" - "github.com/openai/openai-go/v3/packages/param" - "github.com/openai/openai-go/v3/shared" - "go-tiny-claw/internal/schema" + // "os" + + "go-tiny-claw/internal/schema" + + "github.com/openai/openai-go/v3" + "github.com/openai/openai-go/v3/option" + "github.com/openai/openai-go/v3/packages/param" + "github.com/openai/openai-go/v3/shared" ) type OpenAIProvider struct { - client openai.Client // 值类型，非指针 - model string + client openai.Client // 值类型，非指针 + model string } // NewZhipuOpenAIProvider 构造函数：基于 OpenAI V3 SDK，指向智谱底座 func DeepseekOpenAIProvider(model string) *OpenAIProvider { - apiKey := "sk-1f44696abe644bd684f09cc43f12c557" - if apiKey == "" { - panic("请设置 ZHIPU_API_KEY 环境变量") - } - // 核心：将官方 SDK 的地址替换为智谱的兼容端点 - baseURL := "https://api.deepseek.com" + apiKey := "sk-1f44696abe644bd684f09cc43f12c557" + if apiKey == "" { + panic("请设置 ZHIPU_API_KEY 环境变量") + } + // 核心：将官方 SDK 的地址替换为智谱的兼容端点 + baseURL := "https://api.deepseek.com" - return &OpenAIProvider{ - client: openai.NewClient(option.WithAPIKey(apiKey), option.WithBaseURL(baseURL)), - model: model, - } + return &OpenAIProvider{ + client: openai.NewClient(option.WithAPIKey(apiKey), option.WithBaseURL(baseURL)), + model: model, + } } func (p *OpenAIProvider) Generate(ctx context.Context, msgs []schema.Message, availableTools []schema.ToolDefinition) (*schema.Message, error) { - var openaiMsgs []openai.ChatCompletionMessageParamUnion + phase := "Action" + if len(availableTools) == 0 { + phase = "Thinking" + } + log.Printf("[Provider] → API 调用 | 模型: %s | 阶段: %s | 消息数: %d | 工具数: %d", + p.model, phase, len(msgs), len(availableTools)) - // 1. 翻译上下文消息 - for _, msg := range msgs { - switch msg.Role { - case schema.RoleSystem: - openaiMsgs = append(openaiMsgs, openai.SystemMessage(msg.Content)) + var openaiMsgs []openai.ChatCompletionMessageParamUnion - case schema.RoleUser: - if msg.ToolCallID != "" { - // 注意：v3 新版参数顺序是 (content, toolCallID) - openaiMsgs = append(openaiMsgs, openai.ToolMessage(msg.Content, msg.ToolCallID)) - } else { - openaiMsgs = append(openaiMsgs, openai.UserMessage(msg.Content)) - } + // 1. 翻译上下文消息 + for _, msg := range msgs { + switch msg.Role { + case schema.RoleSystem: + openaiMsgs = append(openaiMsgs, openai.SystemMessage(msg.Content)) - case schema.RoleAssistant: - // Deepseek thinking mode: reasoning_content 必须回传 - if msg.ReasoningContent != "" || len(msg.ToolCalls) > 0 { - msgMap := map[string]interface{}{ - "role": "assistant", - "content": msg.Content, - } - if msg.ReasoningContent != "" { - msgMap["reasoning_content"] = msg.ReasoningContent - } - if len(msg.ToolCalls) > 0 { - var toolCalls []map[string]interface{} - for _, tc := range msg.ToolCalls { - toolCalls = append(toolCalls, map[string]interface{}{ - "id": tc.ID, - "type": "function", - "function": map[string]interface{}{ - "name": tc.Name, - "arguments": string(tc.Arguments), - }, - }) - } - msgMap["tool_calls"] = toolCalls - } - rawJSON, _ := json.Marshal(msgMap) - astParam := param.Override[openai.ChatCompletionAssistantMessageParam](json.RawMessage(rawJSON)) - openaiMsgs = append(openaiMsgs, openai.ChatCompletionMessageParamUnion{ - OfAssistant: &astParam, - }) - break - } + case schema.RoleUser: + if msg.ToolCallID != "" { + // 注意：v3 新版参数顺序是 (content, toolCallID) + openaiMsgs = append(openaiMsgs, openai.ToolMessage(msg.Content, msg.ToolCallID)) + } else { + openaiMsgs = append(openaiMsgs, openai.UserMessage(msg.Content)) + } - astParam := openai.ChatCompletionAssistantMessageParam{} + case schema.RoleAssistant: + // Deepseek thinking mode: reasoning_content 必须回传 + if msg.ReasoningContent != "" || len(msg.ToolCalls) > 0 { + msgMap := map[string]interface{}{ + "role": "assistant", + "content": msg.Content, + } + if msg.ReasoningContent != "" { + msgMap["reasoning_content"] = msg.ReasoningContent + } + if len(msg.ToolCalls) > 0 { + var toolCalls []map[string]interface{} + for _, tc := range msg.ToolCalls { + toolCalls = append(toolCalls, map[string]interface{}{ + "id": tc.ID, + "type": "function", + "function": map[string]interface{}{ + "name": tc.Name, + "arguments": string(tc.Arguments), + }, + }) + } + msgMap["tool_calls"] = toolCalls + } + rawJSON, _ := json.Marshal(msgMap) + astParam := param.Override[openai.ChatCompletionAssistantMessageParam](json.RawMessage(rawJSON)) + openaiMsgs = append(openaiMsgs, openai.ChatCompletionMessageParamUnion{ + OfAssistant: &astParam, + }) + break + } - if msg.Content != "" { - astParam.Content = openai.ChatCompletionAssistantMessageParamContentUnion{ - OfString: openai.String(msg.Content), - } - } + astParam := openai.ChatCompletionAssistantMessageParam{} - // 【重要】如果历史包含 ToolCalls，必须原样放回，以维系大模型的逻辑链 - if len(msg.ToolCalls) > 0 { - var toolCalls []openai.ChatCompletionMessageToolCallUnionParam - for _, tc := range msg.ToolCalls { - // OfFunction 对应 GetFunction()，字段类型严格要求为指针 - toolCalls = append(toolCalls, openai.ChatCompletionMessageToolCallUnionParam{ - OfFunction: &openai.ChatCompletionMessageFunctionToolCallParam{ - ID: tc.ID, - Type: "function", - Function: openai.ChatCompletionMessageFunctionToolCallFunctionParam{ - Name: tc.Name, - Arguments: string(tc.Arguments), - }, - }, - }) - } - astParam.ToolCalls = toolCalls - } + if msg.Content != "" { + astParam.Content = openai.ChatCompletionAssistantMessageParamContentUnion{ + OfString: openai.String(msg.Content), + } + } - openaiMsgs = append(openaiMsgs, openai.ChatCompletionMessageParamUnion{ - OfAssistant: &astParam, - }) - } - } + // 【重要】如果历史包含 ToolCalls，必须原样放回，以维系大模型的逻辑链 + if len(msg.ToolCalls) > 0 { + var toolCalls []openai.ChatCompletionMessageToolCallUnionParam + for _, tc := range msg.ToolCalls { + // OfFunction 对应 GetFunction()，字段类型严格要求为指针 + toolCalls = append(toolCalls, openai.ChatCompletionMessageToolCallUnionParam{ + OfFunction: &openai.ChatCompletionMessageFunctionToolCallParam{ + ID: tc.ID, + Type: "function", + Function: openai.ChatCompletionMessageFunctionToolCallFunctionParam{ + Name: tc.Name, + Arguments: string(tc.Arguments), + }, + }, + }) + } + astParam.ToolCalls = toolCalls + } - // 2. 翻译工具定义 (v3 新 API 特性适配) - var openaiTools []openai.ChatCompletionToolUnionParam - for _, toolDef := range availableTools { - var params shared.FunctionParameters + openaiMsgs = append(openaiMsgs, openai.ChatCompletionMessageParamUnion{ + OfAssistant: &astParam, + }) + } + } - // 尝试直接断言，如果不成功则通过 JSON 往返序列化来保证类型匹配 - if m, ok := toolDef.InputSchema.(map[string]interface{}); ok { - params = shared.FunctionParameters(m) - } else { - // fallback：JSON 往返序列化 - b, _ := json.Marshal(toolDef.InputSchema) - _ = json.Unmarshal(b, ¶ms) - } + // 2. 翻译工具定义 (v3 新 API 特性适配) + var openaiTools []openai.ChatCompletionToolUnionParam + for _, toolDef := range availableTools { + var params shared.FunctionParameters - openaiTools = append(openaiTools, openai.ChatCompletionFunctionTool( - shared.FunctionDefinitionParam{ - Name: toolDef.Name, - Description: openai.String(toolDef.Description), - Parameters: params, - }, - )) - } + // 尝试直接断言，如果不成功则通过 JSON 往返序列化来保证类型匹配 + if m, ok := toolDef.InputSchema.(map[string]interface{}); ok { + params = shared.FunctionParameters(m) + } else { + // fallback：JSON 往返序列化 + b, _ := json.Marshal(toolDef.InputSchema) + _ = json.Unmarshal(b, ¶ms) + } - // 3. 构建请求并发送 - params := openai.ChatCompletionNewParams{ - Model: p.model, - Messages: openaiMsgs, - } + openaiTools = append(openaiTools, openai.ChatCompletionFunctionTool( + shared.FunctionDefinitionParam{ + Name: toolDef.Name, + Description: openai.String(toolDef.Description), + Parameters: params, + }, + )) + } - // 【慢思考机制支撑】仅当 availableTools 存在时才挂载 Tools - if len(openaiTools) > 0 { - params.Tools = openaiTools - } + // 3. 构建请求并发送 + params := openai.ChatCompletionNewParams{ + Model: p.model, + Messages: openaiMsgs, + } - resp, err := p.client.Chat.Completions.New(ctx, params) - if err != nil { - return nil, fmt.Errorf("OpenAI/Zhipu API 请求失败: %w", err) - } - if len(resp.Choices) == 0 { - return nil, fmt.Errorf("API 返回了空的 Choices") - } + // 【慢思考机制支撑】仅当 availableTools 存在时才挂载 Tools + if len(openaiTools) > 0 { + params.Tools = openaiTools + } - // 4. 将 API Response 反向翻译为内部 schema.Message - choice := resp.Choices[0].Message - resultMsg := &schema.Message{ - Role: schema.RoleAssistant, - Content: choice.Content, - } + resp, err := p.client.Chat.Completions.New(ctx, params) + if err != nil { + return nil, fmt.Errorf("OpenAI/Zhipu API 请求失败: %w", err) + } + if len(resp.Choices) == 0 { + return nil, fmt.Errorf("API 返回了空的 Choices") + } - // Deepseek thinking mode: 从原始响应中提取 reasoning_content - rawMsg := choice.RawJSON() - if rawMsg != "" { - var rawMap map[string]json.RawMessage - if err := json.Unmarshal([]byte(rawMsg), &rawMap); err == nil { - if rc, ok := rawMap["reasoning_content"]; ok { - var s string - if json.Unmarshal(rc, &s) == nil { - resultMsg.ReasoningContent = s - } - } - } - } + // 4. 将 API Response 反向翻译为内部 schema.Message + choice := resp.Choices[0].Message + resultMsg := &schema.Message{ + Role: schema.RoleAssistant, + Content: choice.Content, + } - for _, tc := range choice.ToolCalls { - if tc.Type == "function" { - resultMsg.ToolCalls = append(resultMsg.ToolCalls, schema.ToolCall{ - ID: tc.ID, - Name: tc.Function.Name, - Arguments: []byte(tc.Function.Arguments), // 提取 JSON 字符串字节 - }) - } - } + // Deepseek thinking mode: 从原始响应中提取 reasoning_content + rawMsg := choice.RawJSON() + if rawMsg != "" { + var rawMap map[string]json.RawMessage + if err := json.Unmarshal([]byte(rawMsg), &rawMap); err == nil { + if rc, ok := rawMap["reasoning_content"]; ok { + var s string + if json.Unmarshal(rc, &s) == nil { + resultMsg.ReasoningContent = s + } + } + } + } - return resultMsg, nil -} \ No newline at end of file + for _, tc := range choice.ToolCalls { + if tc.Type == "function" { + resultMsg.ToolCalls = append(resultMsg.ToolCalls, schema.ToolCall{ + ID: tc.ID, + Name: tc.Function.Name, + Arguments: []byte(tc.Function.Arguments), + }) + } + } + + // 打印响应摘要 + contentPreview := resultMsg.Content + // if len(contentPreview) > 60 { + // contentPreview = contentPreview[:60] + "..." + // } + log.Printf("[Provider] ← API 响应 | 内容: %q | 工具调用: %d", contentPreview, len(resultMsg.ToolCalls)) + for _, tc := range resultMsg.ToolCalls { + log.Printf("[Provider] ↳ ToolCall: %s(%s)", tc.Name, string(tc.Arguments)) + } + + return resultMsg, nil +} diff --git a/internal/tools/bash.go b/internal/tools/bash.go new file mode 100644 index 0000000..42c26d1 --- /dev/null +++ b/internal/tools/bash.go @@ -0,0 +1,89 @@ +package tools + +import ( + "context" + "encoding/json" + "fmt" + "os/exec" + "time" + + "go-tiny-claw/internal/schema" +) + +type BashTool struct { + workDir string // 工作区约束 +} + +func NewBashTool(workDir string) *BashTool { + return &BashTool{workDir: workDir} +} + +func (t *BashTool) Name() string { + return "bash" +} + +func (t *BashTool) Definition() schema.ToolDefinition { + return schema.ToolDefinition{ + Name: t.Name(), + Description: "在当前工作区执行任意的 bash 命令。支持链式命令(如 &&)。返回标准输出(stdout)和标准错误(stderr)。", + InputSchema: map[string]interface{}{ + "type": "object", + "properties": map[string]interface{}{ + "command": map[string]interface{}{ + "type": "string", + "description": "要执行的 bash 命令，例如: ls -la 或 go test ./...", + }, + }, + "required": []string{"command"}, + }, + } +} + +type bashArgs struct { + Command string `json:"command"` +} + +func (t *BashTool) Execute(ctx context.Context, args json.RawMessage) (string, error) { + var input bashArgs + if err := json.Unmarshal(args, &input); err != nil { + return "", fmt.Errorf("参数解析失败: %w", err) + } + + // 【驾驭底线 1】：Time Budgeting (时间预算与超时控制) + timeoutCtx, cancel := context.WithTimeout(ctx, 30*time.Second) + defer cancel() + + // Unix 和 Windows 统一使用 bash -c（Windows 需安装 Git Bash），编码转换在下方处理 + cmd := exec.CommandContext(timeoutCtx, "bash", "-c", input.Command) + + // 【驾驭底线 2】：绑定执行的工作区目录 + cmd.Dir = t.workDir + + // 执行并捕获 CombinedOutput (合并 stdout 和 stderr) + out, err := cmd.CombinedOutput() + + outputStr := string(out) + + // 如果命令执行超时，返回警告信息让模型知晓 + if timeoutCtx.Err() == context.DeadlineExceeded { + return outputStr + "\n[警告: 命令执行超时(30s)，已被系统强制终止。如果是启动常驻服务，请尝试将其转入后台。]", nil + } + + // 【驾驭底线 3】：错误原样回传 (Self-Correction 自愈机制) + if err != nil { + return fmt.Sprintf("执行报错: %v\n输出:\n%s", err, outputStr), nil + } + + // 如果没有终端输出，给模型一个明确的执行成功的反馈 + if outputStr == "" { + return "命令执行成功，无终端输出。", nil + } + + // 【驾驭底线 4】：长度截断保护 (防 OOM) + const maxLen = 8000 + if len(outputStr) > maxLen { + return fmt.Sprintf("%s\n\n...[终端输出过长，已截断至前 %d 字节]...", outputStr[:maxLen], maxLen), nil + } + + return outputStr, nil +} diff --git a/internal/tools/write_file.go b/internal/tools/write_file.go new file mode 100644 index 0000000..4198da7 --- /dev/null +++ b/internal/tools/write_file.go @@ -0,0 +1,72 @@ +package tools + +import ( + "context" + "encoding/json" + "fmt" + "os" + "path/filepath" + + "go-tiny-claw/internal/schema" +) + +type WriteFileTool struct { + workDir string // 工作区约束 +} + +func NewWriteFileTool(workDir string) *WriteFileTool { + return &WriteFileTool{workDir: workDir} +} + +func (t *WriteFileTool) Name() string { + return "write_file" +} + +func (t *WriteFileTool) Definition() schema.ToolDefinition { + return schema.ToolDefinition{ + Name: t.Name(), + Description: "创建或覆盖写入一个文件。如果目录不存在会自动创建。请提供相对于工作区的相对路径。", + InputSchema: map[string]interface{}{ + "type": "object", + "properties": map[string]interface{}{ + "path": map[string]interface{}{ + "type": "string", + "description": "要写入的文件路径，如 src/main.go", + }, + "content": map[string]interface{}{ + "type": "string", + "description": "要写入的完整文件内容", + }, + }, + "required": []string{"path", "content"}, + }, + } +} + +type writeFileArgs struct { + Path string `json:"path"` + Content string `json:"content"` +} + +func (t *WriteFileTool) Execute(ctx context.Context, args json.RawMessage) (string, error) { + var input writeFileArgs + if err := json.Unmarshal(args, &input); err != nil { + return "", fmt.Errorf("参数解析失败: %w", err) + } + + // 【安全防线】：限制在 WorkDir 下执行，防止大模型修改系统级文件 + fullPath := filepath.Join(t.workDir, input.Path) + + // 自动创建缺失的父级目录 + if err := os.MkdirAll(filepath.Dir(fullPath), 0755); err != nil { + return "", fmt.Errorf("创建父目录失败: %w", err) + } + + // 写入文件内容，权限设为 0644 + err := os.WriteFile(fullPath, []byte(input.Content), 0644) + if err != nil { + return "", fmt.Errorf("写入文件失败: %w", err) + } + + return fmt.Sprintf("成功将内容写入到文件: %s", input.Path), nil +}