Merge branch 'main' into patch-1
This commit is contained in:
64
README.md
64
README.md
@@ -66,11 +66,11 @@
|
||||
🤖 **AI-Bootstrapped**: Autonomous Go-native implementation — 95% Agent-generated core with human-in-the-loop refinement.
|
||||
|
||||
| | OpenClaw | NanoBot | **PicoClaw** |
|
||||
| --- | --- | --- |--- |
|
||||
| ----------------------------- | ------------- | ------------------------ | ----------------------------------------- |
|
||||
| **Language** | TypeScript | Python | **Go** |
|
||||
| **RAM** | >1GB |>100MB| **< 10MB** |
|
||||
| **RAM** | >1GB | >100MB | **< 10MB** |
|
||||
| **Startup**</br>(0.8GHz core) | >500s | >30s | **<1s** |
|
||||
| **Cost** | Mac Mini 599$ | Most Linux SBC </br>~50$ |**Any Linux Board**</br>**As low as 10$** |
|
||||
| **Cost** | Mac Mini 599$ | Most Linux SBC </br>~50$ | **Any Linux Board**</br>**As low as 10$** |
|
||||
|
||||
<img src="assets/compare.jpg" alt="PicoClaw" width="512">
|
||||
|
||||
@@ -100,9 +100,9 @@
|
||||
|
||||
PicoClaw can be deployed on almost any Linux device!
|
||||
|
||||
* $9.9 [LicheeRV-Nano](https://www.aliexpress.com/item/1005006519668532.html) E(Ethernet) or W(WiFi6) version, for Minimal Home Assistant
|
||||
* $30~50 [NanoKVM](https://www.aliexpress.com/item/1005007369816019.html), or $100 [NanoKVM-Pro](https://www.aliexpress.com/item/1005010048471263.html) for Automated Server Maintenance
|
||||
* $50 [MaixCAM](https://www.aliexpress.com/item/1005008053333693.html) or $100 [MaixCAM2](https://www.kickstarter.com/projects/zepan/maixcam2-build-your-next-gen-4k-ai-camera) for Smart Monitoring
|
||||
- $9.9 [LicheeRV-Nano](https://www.aliexpress.com/item/1005006519668532.html) E(Ethernet) or W(WiFi6) version, for Minimal Home Assistant
|
||||
- $30~50 [NanoKVM](https://www.aliexpress.com/item/1005007369816019.html), or $100 [NanoKVM-Pro](https://www.aliexpress.com/item/1005010048471263.html) for Automated Server Maintenance
|
||||
- $50 [MaixCAM](https://www.aliexpress.com/item/1005008053333693.html) or $100 [MaixCAM2](https://www.kickstarter.com/projects/zepan/maixcam2-build-your-next-gen-4k-ai-camera) for Smart Monitoring
|
||||
|
||||
<https://private-user-images.githubusercontent.com/83055338/547056448-e7b031ff-d6f5-4468-bcca-5726b6fecb5c.mp4>
|
||||
|
||||
@@ -177,7 +177,7 @@ docker compose --profile gateway up -d
|
||||
> [!TIP]
|
||||
> Set your API key in `~/.picoclaw/config.json`.
|
||||
> Get API keys: [OpenRouter](https://openrouter.ai/keys) (LLM) · [Zhipu](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) (LLM)
|
||||
> Web search is **optional** - get free [Brave Search API](https://brave.com/search/api) (2000 free queries/month)
|
||||
> Web search is **optional** - get free [Brave Search API](https://brave.com/search/api) (2000 free queries/month) or use built-in auto fallback.
|
||||
|
||||
**1. Initialize**
|
||||
|
||||
@@ -206,9 +206,14 @@ picoclaw onboard
|
||||
},
|
||||
"tools": {
|
||||
"web": {
|
||||
"search": {
|
||||
"brave": {
|
||||
"enabled": false,
|
||||
"api_key": "YOUR_BRAVE_API_KEY",
|
||||
"max_results": 5
|
||||
},
|
||||
"duckduckgo": {
|
||||
"enabled": true,
|
||||
"max_results": 5
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -237,7 +242,7 @@ That's it! You have a working AI assistant in 2 minutes.
|
||||
Talk to your picoclaw through Telegram, Discord, or DingTalk
|
||||
|
||||
| Channel | Setup |
|
||||
|---------|-------|
|
||||
| ------------ | -------------------------- |
|
||||
| **Telegram** | Easy (just a token) |
|
||||
| **Discord** | Easy (bot token + intents) |
|
||||
| **QQ** | Easy (AppID + AppSecret) |
|
||||
@@ -597,7 +602,7 @@ The subagent has access to tools (message, web_search, etc.) and can communicate
|
||||
> Groq provides free voice transcription via Whisper. If configured, Telegram voice messages will be automatically transcribed.
|
||||
|
||||
| Provider | Purpose | Get API Key |
|
||||
|----------|---------|-------------|
|
||||
| -------------------------- | --------------------------------------- | ------------------------------------------------------ |
|
||||
| `gemini` | LLM (Gemini direct) | [aistudio.google.com](https://aistudio.google.com) |
|
||||
| `zhipu` | LLM (Zhipu direct) | [bigmodel.cn](bigmodel.cn) |
|
||||
| `openrouter(To be tested)` | LLM (recommended, access to all models) | [openrouter.ai](https://openrouter.ai) |
|
||||
@@ -630,8 +635,8 @@ The subagent has access to tools (message, web_search, etc.) and can communicate
|
||||
"zhipu": {
|
||||
"api_key": "Your API Key",
|
||||
"api_base": "https://open.bigmodel.cn/api/paas/v4"
|
||||
},
|
||||
},
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
@@ -692,8 +697,14 @@ picoclaw agent -m "Hello"
|
||||
},
|
||||
"tools": {
|
||||
"web": {
|
||||
"search": {
|
||||
"api_key": "BSA..."
|
||||
"brave": {
|
||||
"enabled": false,
|
||||
"api_key": "BSA...",
|
||||
"max_results": 5
|
||||
},
|
||||
"duckduckgo": {
|
||||
"enabled": true,
|
||||
"max_results": 5
|
||||
}
|
||||
}
|
||||
},
|
||||
@@ -709,7 +720,7 @@ picoclaw agent -m "Hello"
|
||||
## CLI Reference
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| ------------------------- | ----------------------------- |
|
||||
| `picoclaw onboard` | Initialize config & workspace |
|
||||
| `picoclaw agent -m "..."` | Chat with the agent |
|
||||
| `picoclaw agent` | Interactive chat mode |
|
||||
@@ -750,21 +761,28 @@ This is normal if you haven't configured a search API key yet. PicoClaw will pro
|
||||
|
||||
To enable web search:
|
||||
|
||||
1. Get a free API key at [https://brave.com/search/api](https://brave.com/search/api) (2000 free queries/month)
|
||||
2. Add to `~/.picoclaw/config.json`:
|
||||
1. **Option 1 (Recommended)**: Get a free API key at [https://brave.com/search/api](https://brave.com/search/api) (2000 free queries/month) for the best results.
|
||||
2. **Option 2 (No Credit Card)**: If you don't have a key, we automatically fall back to **DuckDuckGo** (no key required).
|
||||
|
||||
```json
|
||||
{
|
||||
Add the key to `~/.picoclaw/config.json` if using Brave:
|
||||
|
||||
```json
|
||||
{
|
||||
"tools": {
|
||||
"web": {
|
||||
"search": {
|
||||
"brave": {
|
||||
"enabled": false,
|
||||
"api_key": "YOUR_BRAVE_API_KEY",
|
||||
"max_results": 5
|
||||
},
|
||||
"duckduckgo": {
|
||||
"enabled": true,
|
||||
"max_results": 5
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
}
|
||||
```
|
||||
|
||||
### Getting content filtering errors
|
||||
|
||||
@@ -779,7 +797,7 @@ This happens when another instance of the bot is running. Make sure only one `pi
|
||||
## 📝 API Key Comparison
|
||||
|
||||
| Service | Free Tier | Use Case |
|
||||
|---------|-----------|-----------|
|
||||
| ---------------- | ------------------- | ------------------------------------- |
|
||||
| **OpenRouter** | 200K tokens/month | Multiple models (Claude, GPT-4, etc.) |
|
||||
| **Zhipu** | 200K tokens/month | Best for Chinese users |
|
||||
| **Brave Search** | 2000 queries/month | Web search functionality |
|
||||
|
||||
@@ -70,9 +70,15 @@ func createToolRegistry(workspace string, restrict bool, cfg *config.Config, msg
|
||||
// Shell execution
|
||||
registry.Register(tools.NewExecTool(workspace, restrict))
|
||||
|
||||
// Web tools
|
||||
braveAPIKey := cfg.Tools.Web.Search.APIKey
|
||||
registry.Register(tools.NewWebSearchTool(braveAPIKey, cfg.Tools.Web.Search.MaxResults))
|
||||
if searchTool := tools.NewWebSearchTool(tools.WebSearchToolOptions{
|
||||
BraveAPIKey: cfg.Tools.Web.Brave.APIKey,
|
||||
BraveMaxResults: cfg.Tools.Web.Brave.MaxResults,
|
||||
BraveEnabled: cfg.Tools.Web.Brave.Enabled,
|
||||
DuckDuckGoMaxResults: cfg.Tools.Web.DuckDuckGo.MaxResults,
|
||||
DuckDuckGoEnabled: cfg.Tools.Web.DuckDuckGo.Enabled,
|
||||
}); searchTool != nil {
|
||||
registry.Register(searchTool)
|
||||
}
|
||||
registry.Register(tools.NewWebFetchTool(50000))
|
||||
|
||||
// Message tool - available to both agent and subagent
|
||||
|
||||
@@ -59,7 +59,22 @@ func (c *BaseChannel) IsAllowed(senderID string) bool {
|
||||
for _, allowed := range c.allowList {
|
||||
// Strip leading "@" from allowed value for username matching
|
||||
trimmed := strings.TrimPrefix(allowed, "@")
|
||||
if senderID == allowed || idPart == allowed || senderID == trimmed || idPart == trimmed || (userPart != "" && (userPart == allowed || userPart == trimmed)) {
|
||||
allowedID := trimmed
|
||||
allowedUser := ""
|
||||
if idx := strings.Index(trimmed, "|"); idx > 0 {
|
||||
allowedID = trimmed[:idx]
|
||||
allowedUser = trimmed[idx+1:]
|
||||
}
|
||||
|
||||
// Support either side using "id|username" compound form.
|
||||
// This keeps backward compatibility with legacy Telegram allowlist entries.
|
||||
if senderID == allowed ||
|
||||
idPart == allowed ||
|
||||
senderID == trimmed ||
|
||||
idPart == trimmed ||
|
||||
idPart == allowedID ||
|
||||
(allowedUser != "" && senderID == allowedUser) ||
|
||||
(userPart != "" && (userPart == allowed || userPart == trimmed || userPart == allowedUser)) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
53
pkg/channels/base_test.go
Normal file
53
pkg/channels/base_test.go
Normal file
@@ -0,0 +1,53 @@
|
||||
package channels
|
||||
|
||||
import "testing"
|
||||
|
||||
func TestBaseChannelIsAllowed(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
allowList []string
|
||||
senderID string
|
||||
want bool
|
||||
}{
|
||||
{
|
||||
name: "empty allowlist allows all",
|
||||
allowList: nil,
|
||||
senderID: "anyone",
|
||||
want: true,
|
||||
},
|
||||
{
|
||||
name: "compound sender matches numeric allowlist",
|
||||
allowList: []string{"123456"},
|
||||
senderID: "123456|alice",
|
||||
want: true,
|
||||
},
|
||||
{
|
||||
name: "compound sender matches username allowlist",
|
||||
allowList: []string{"@alice"},
|
||||
senderID: "123456|alice",
|
||||
want: true,
|
||||
},
|
||||
{
|
||||
name: "numeric sender matches legacy compound allowlist",
|
||||
allowList: []string{"123456|alice"},
|
||||
senderID: "123456",
|
||||
want: true,
|
||||
},
|
||||
{
|
||||
name: "non matching sender is denied",
|
||||
allowList: []string{"123456"},
|
||||
senderID: "654321|bob",
|
||||
want: false,
|
||||
},
|
||||
}
|
||||
|
||||
for _, tt := range tests {
|
||||
t.Run(tt.name, func(t *testing.T) {
|
||||
ch := NewBaseChannel("test", nil, nil, tt.allowList)
|
||||
if got := ch.IsAllowed(tt.senderID); got != tt.want {
|
||||
t.Fatalf("IsAllowed(%q) = %v, want %v", tt.senderID, got, tt.want)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
@@ -177,15 +177,17 @@ func (c *TelegramChannel) handleMessage(ctx context.Context, update telego.Updat
|
||||
return
|
||||
}
|
||||
|
||||
senderID := fmt.Sprintf("%d", user.ID)
|
||||
userID := fmt.Sprintf("%d", user.ID)
|
||||
senderID := userID
|
||||
if user.Username != "" {
|
||||
senderID = fmt.Sprintf("%d|%s", user.ID, user.Username)
|
||||
senderID = fmt.Sprintf("%s|%s", userID, user.Username)
|
||||
}
|
||||
|
||||
// 检查白名单,避免为被拒绝的用户下载附件
|
||||
if !c.IsAllowed(senderID) {
|
||||
if !c.IsAllowed(userID) && !c.IsAllowed(senderID) {
|
||||
logger.DebugCF("telegram", "Message rejected by allowlist", map[string]interface{}{
|
||||
"user_id": senderID,
|
||||
"user_id": userID,
|
||||
"username": user.Username,
|
||||
})
|
||||
return
|
||||
}
|
||||
@@ -359,7 +361,7 @@ func (c *TelegramChannel) handleMessage(ctx context.Context, update telego.Updat
|
||||
"is_group": fmt.Sprintf("%t", message.Chat.Type != "private"),
|
||||
}
|
||||
|
||||
c.HandleMessage(fmt.Sprintf("%d", user.ID), fmt.Sprintf("%d", chatID), content, mediaPaths, metadata)
|
||||
c.HandleMessage(senderID, fmt.Sprintf("%d", chatID), content, mediaPaths, metadata)
|
||||
}
|
||||
|
||||
func (c *TelegramChannel) downloadPhoto(ctx context.Context, fileID string) string {
|
||||
|
||||
@@ -164,13 +164,20 @@ type GatewayConfig struct {
|
||||
Port int `json:"port" env:"PICOCLAW_GATEWAY_PORT"`
|
||||
}
|
||||
|
||||
type WebSearchConfig struct {
|
||||
APIKey string `json:"api_key" env:"PICOCLAW_TOOLS_WEB_SEARCH_API_KEY"`
|
||||
MaxResults int `json:"max_results" env:"PICOCLAW_TOOLS_WEB_SEARCH_MAX_RESULTS"`
|
||||
type BraveConfig struct {
|
||||
Enabled bool `json:"enabled" env:"PICOCLAW_TOOLS_WEB_BRAVE_ENABLED"`
|
||||
APIKey string `json:"api_key" env:"PICOCLAW_TOOLS_WEB_BRAVE_API_KEY"`
|
||||
MaxResults int `json:"max_results" env:"PICOCLAW_TOOLS_WEB_BRAVE_MAX_RESULTS"`
|
||||
}
|
||||
|
||||
type DuckDuckGoConfig struct {
|
||||
Enabled bool `json:"enabled" env:"PICOCLAW_TOOLS_WEB_DUCKDUCKGO_ENABLED"`
|
||||
MaxResults int `json:"max_results" env:"PICOCLAW_TOOLS_WEB_DUCKDUCKGO_MAX_RESULTS"`
|
||||
}
|
||||
|
||||
type WebToolsConfig struct {
|
||||
Search WebSearchConfig `json:"search"`
|
||||
Brave BraveConfig `json:"brave"`
|
||||
DuckDuckGo DuckDuckGoConfig `json:"duckduckgo"`
|
||||
}
|
||||
|
||||
type ToolsConfig struct {
|
||||
@@ -257,10 +264,15 @@ func DefaultConfig() *Config {
|
||||
},
|
||||
Tools: ToolsConfig{
|
||||
Web: WebToolsConfig{
|
||||
Search: WebSearchConfig{
|
||||
Brave: BraveConfig{
|
||||
Enabled: false,
|
||||
APIKey: "",
|
||||
MaxResults: 5,
|
||||
},
|
||||
DuckDuckGo: DuckDuckGoConfig{
|
||||
Enabled: true,
|
||||
MaxResults: 5,
|
||||
},
|
||||
},
|
||||
},
|
||||
Heartbeat: HeartbeatConfig{
|
||||
|
||||
@@ -212,12 +212,17 @@ func ConvertConfig(data map[string]interface{}) (*config.Config, []string, error
|
||||
|
||||
if tools, ok := getMap(data, "tools"); ok {
|
||||
if web, ok := getMap(tools, "web"); ok {
|
||||
// Migrate old "search" config to "brave" if api_key is present
|
||||
if search, ok := getMap(web, "search"); ok {
|
||||
if v, ok := getString(search, "api_key"); ok {
|
||||
cfg.Tools.Web.Search.APIKey = v
|
||||
cfg.Tools.Web.Brave.APIKey = v
|
||||
if v != "" {
|
||||
cfg.Tools.Web.Brave.Enabled = true
|
||||
}
|
||||
}
|
||||
if v, ok := getFloat(search, "max_results"); ok {
|
||||
cfg.Tools.Web.Search.MaxResults = int(v)
|
||||
cfg.Tools.Web.Brave.MaxResults = int(v)
|
||||
cfg.Tools.Web.DuckDuckGo.MaxResults = int(v)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -271,8 +276,8 @@ func MergeConfig(existing, incoming *config.Config) *config.Config {
|
||||
existing.Channels.MaixCam = incoming.Channels.MaixCam
|
||||
}
|
||||
|
||||
if existing.Tools.Web.Search.APIKey == "" {
|
||||
existing.Tools.Web.Search = incoming.Tools.Web.Search
|
||||
if existing.Tools.Web.Brave.APIKey == "" {
|
||||
existing.Tools.Web.Brave = incoming.Tools.Web.Brave
|
||||
}
|
||||
|
||||
return existing
|
||||
|
||||
@@ -42,7 +42,7 @@ func NewHTTPProvider(apiKey, apiBase, proxy string) *HTTPProvider {
|
||||
|
||||
return &HTTPProvider{
|
||||
apiKey: apiKey,
|
||||
apiBase: apiBase,
|
||||
apiBase: strings.TrimRight(apiBase, "/"),
|
||||
httpClient: client,
|
||||
}
|
||||
}
|
||||
@@ -116,7 +116,7 @@ func (p *HTTPProvider) Chat(ctx context.Context, messages []Message, tools []Too
|
||||
}
|
||||
|
||||
if resp.StatusCode != http.StatusOK {
|
||||
return nil, fmt.Errorf("API error: %s", string(body))
|
||||
return nil, fmt.Errorf("API request failed:\n Status: %d\n Body: %s", resp.StatusCode, string(body))
|
||||
}
|
||||
|
||||
return p.parseResponse(body)
|
||||
|
||||
268
pkg/tools/web.go
268
pkg/tools/web.go
@@ -13,20 +13,210 @@ import (
|
||||
)
|
||||
|
||||
const (
|
||||
userAgent = "Mozilla/5.0 (compatible; picoclaw/1.0)"
|
||||
userAgent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
|
||||
)
|
||||
|
||||
type WebSearchTool struct {
|
||||
type SearchProvider interface {
|
||||
Search(ctx context.Context, query string, count int) (string, error)
|
||||
}
|
||||
|
||||
type BraveSearchProvider struct {
|
||||
apiKey string
|
||||
}
|
||||
|
||||
func (p *BraveSearchProvider) Search(ctx context.Context, query string, count int) (string, error) {
|
||||
searchURL := fmt.Sprintf("https://api.search.brave.com/res/v1/web/search?q=%s&count=%d",
|
||||
url.QueryEscape(query), count)
|
||||
|
||||
req, err := http.NewRequestWithContext(ctx, "GET", searchURL, nil)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("failed to create request: %w", err)
|
||||
}
|
||||
|
||||
req.Header.Set("Accept", "application/json")
|
||||
req.Header.Set("X-Subscription-Token", p.apiKey)
|
||||
|
||||
client := &http.Client{Timeout: 10 * time.Second}
|
||||
resp, err := client.Do(req)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("request failed: %w", err)
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
|
||||
body, err := io.ReadAll(resp.Body)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("failed to read response: %w", err)
|
||||
}
|
||||
|
||||
var searchResp struct {
|
||||
Web struct {
|
||||
Results []struct {
|
||||
Title string `json:"title"`
|
||||
URL string `json:"url"`
|
||||
Description string `json:"description"`
|
||||
} `json:"results"`
|
||||
} `json:"web"`
|
||||
}
|
||||
|
||||
if err := json.Unmarshal(body, &searchResp); err != nil {
|
||||
// Log error body for debugging
|
||||
fmt.Printf("Brave API Error Body: %s\n", string(body))
|
||||
return "", fmt.Errorf("failed to parse response: %w", err)
|
||||
}
|
||||
|
||||
results := searchResp.Web.Results
|
||||
if len(results) == 0 {
|
||||
return fmt.Sprintf("No results for: %s", query), nil
|
||||
}
|
||||
|
||||
var lines []string
|
||||
lines = append(lines, fmt.Sprintf("Results for: %s", query))
|
||||
for i, item := range results {
|
||||
if i >= count {
|
||||
break
|
||||
}
|
||||
lines = append(lines, fmt.Sprintf("%d. %s\n %s", i+1, item.Title, item.URL))
|
||||
if item.Description != "" {
|
||||
lines = append(lines, fmt.Sprintf(" %s", item.Description))
|
||||
}
|
||||
}
|
||||
|
||||
return strings.Join(lines, "\n"), nil
|
||||
}
|
||||
|
||||
type DuckDuckGoSearchProvider struct{}
|
||||
|
||||
func (p *DuckDuckGoSearchProvider) Search(ctx context.Context, query string, count int) (string, error) {
|
||||
searchURL := fmt.Sprintf("https://html.duckduckgo.com/html/?q=%s", url.QueryEscape(query))
|
||||
|
||||
req, err := http.NewRequestWithContext(ctx, "GET", searchURL, nil)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("failed to create request: %w", err)
|
||||
}
|
||||
|
||||
req.Header.Set("User-Agent", userAgent)
|
||||
|
||||
client := &http.Client{Timeout: 10 * time.Second}
|
||||
resp, err := client.Do(req)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("request failed: %w", err)
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
|
||||
body, err := io.ReadAll(resp.Body)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("failed to read response: %w", err)
|
||||
}
|
||||
|
||||
return p.extractResults(string(body), count, query)
|
||||
}
|
||||
|
||||
func (p *DuckDuckGoSearchProvider) extractResults(html string, count int, query string) (string, error) {
|
||||
// Simple regex based extraction for DDG HTML
|
||||
// Strategy: Find all result containers or key anchors directly
|
||||
|
||||
// Try finding the result links directly first, as they are the most critical
|
||||
// Pattern: <a class="result__a" href="...">Title</a>
|
||||
// The previous regex was a bit strict. Let's make it more flexible for attributes order/content
|
||||
reLink := regexp.MustCompile(`<a[^>]*class="[^"]*result__a[^"]*"[^>]*href="([^"]+)"[^>]*>([\s\S]*?)</a>`)
|
||||
matches := reLink.FindAllStringSubmatch(html, count+5)
|
||||
|
||||
if len(matches) == 0 {
|
||||
return fmt.Sprintf("No results found or extraction failed. Query: %s", query), nil
|
||||
}
|
||||
|
||||
var lines []string
|
||||
lines = append(lines, fmt.Sprintf("Results for: %s (via DuckDuckGo)", query))
|
||||
|
||||
// Pre-compile snippet regex to run inside the loop
|
||||
// We'll search for snippets relative to the link position or just globally if needed
|
||||
// But simple global search for snippets might mismatch order.
|
||||
// Since we only have the raw HTML string, let's just extract snippets globally and assume order matches (risky but simple for regex)
|
||||
// Or better: Let's assume the snippet follows the link in the HTML
|
||||
|
||||
// A better regex approach: iterate through text and find matches in order
|
||||
// But for now, let's grab all snippets too
|
||||
reSnippet := regexp.MustCompile(`<a class="result__snippet[^"]*".*?>([\s\S]*?)</a>`)
|
||||
snippetMatches := reSnippet.FindAllStringSubmatch(html, count+5)
|
||||
|
||||
maxItems := min(len(matches), count)
|
||||
|
||||
for i := 0; i < maxItems; i++ {
|
||||
urlStr := matches[i][1]
|
||||
title := stripTags(matches[i][2])
|
||||
title = strings.TrimSpace(title)
|
||||
|
||||
// URL decoding if needed
|
||||
if strings.Contains(urlStr, "uddg=") {
|
||||
if u, err := url.QueryUnescape(urlStr); err == nil {
|
||||
idx := strings.Index(u, "uddg=")
|
||||
if idx != -1 {
|
||||
urlStr = u[idx+5:]
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
lines = append(lines, fmt.Sprintf("%d. %s\n %s", i+1, title, urlStr))
|
||||
|
||||
// Attempt to attach snippet if available and index aligns
|
||||
if i < len(snippetMatches) {
|
||||
snippet := stripTags(snippetMatches[i][1])
|
||||
snippet = strings.TrimSpace(snippet)
|
||||
if snippet != "" {
|
||||
lines = append(lines, fmt.Sprintf(" %s", snippet))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return strings.Join(lines, "\n"), nil
|
||||
}
|
||||
|
||||
func min(a, b int) int {
|
||||
if a < b {
|
||||
return a
|
||||
}
|
||||
return b
|
||||
}
|
||||
|
||||
func stripTags(content string) string {
|
||||
re := regexp.MustCompile(`<[^>]+>`)
|
||||
return re.ReplaceAllString(content, "")
|
||||
}
|
||||
|
||||
type WebSearchTool struct {
|
||||
provider SearchProvider
|
||||
maxResults int
|
||||
}
|
||||
|
||||
func NewWebSearchTool(apiKey string, maxResults int) *WebSearchTool {
|
||||
if maxResults <= 0 || maxResults > 10 {
|
||||
maxResults = 5
|
||||
type WebSearchToolOptions struct {
|
||||
BraveAPIKey string
|
||||
BraveMaxResults int
|
||||
BraveEnabled bool
|
||||
DuckDuckGoMaxResults int
|
||||
DuckDuckGoEnabled bool
|
||||
}
|
||||
|
||||
func NewWebSearchTool(opts WebSearchToolOptions) *WebSearchTool {
|
||||
var provider SearchProvider
|
||||
maxResults := 5
|
||||
|
||||
// Priority: Brave > DuckDuckGo
|
||||
if opts.BraveEnabled && opts.BraveAPIKey != "" {
|
||||
provider = &BraveSearchProvider{apiKey: opts.BraveAPIKey}
|
||||
if opts.BraveMaxResults > 0 {
|
||||
maxResults = opts.BraveMaxResults
|
||||
}
|
||||
} else if opts.DuckDuckGoEnabled {
|
||||
provider = &DuckDuckGoSearchProvider{}
|
||||
if opts.DuckDuckGoMaxResults > 0 {
|
||||
maxResults = opts.DuckDuckGoMaxResults
|
||||
}
|
||||
} else {
|
||||
return nil
|
||||
}
|
||||
|
||||
return &WebSearchTool{
|
||||
apiKey: apiKey,
|
||||
provider: provider,
|
||||
maxResults: maxResults,
|
||||
}
|
||||
}
|
||||
@@ -59,10 +249,6 @@ func (t *WebSearchTool) Parameters() map[string]interface{} {
|
||||
}
|
||||
|
||||
func (t *WebSearchTool) Execute(ctx context.Context, args map[string]interface{}) *ToolResult {
|
||||
if t.apiKey == "" {
|
||||
return ErrorResult("BRAVE_API_KEY not configured")
|
||||
}
|
||||
|
||||
query, ok := args["query"].(string)
|
||||
if !ok {
|
||||
return ErrorResult("query is required")
|
||||
@@ -75,68 +261,14 @@ func (t *WebSearchTool) Execute(ctx context.Context, args map[string]interface{}
|
||||
}
|
||||
}
|
||||
|
||||
searchURL := fmt.Sprintf("https://api.search.brave.com/res/v1/web/search?q=%s&count=%d",
|
||||
url.QueryEscape(query), count)
|
||||
|
||||
req, err := http.NewRequestWithContext(ctx, "GET", searchURL, nil)
|
||||
result, err := t.provider.Search(ctx, query, count)
|
||||
if err != nil {
|
||||
return ErrorResult(fmt.Sprintf("failed to create request: %v", err))
|
||||
return ErrorResult(fmt.Sprintf("search failed: %v", err))
|
||||
}
|
||||
|
||||
req.Header.Set("Accept", "application/json")
|
||||
req.Header.Set("X-Subscription-Token", t.apiKey)
|
||||
|
||||
client := &http.Client{Timeout: 10 * time.Second}
|
||||
resp, err := client.Do(req)
|
||||
if err != nil {
|
||||
return ErrorResult(fmt.Sprintf("request failed: %v", err))
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
|
||||
body, err := io.ReadAll(resp.Body)
|
||||
if err != nil {
|
||||
return ErrorResult(fmt.Sprintf("failed to read response: %v", err))
|
||||
}
|
||||
|
||||
var searchResp struct {
|
||||
Web struct {
|
||||
Results []struct {
|
||||
Title string `json:"title"`
|
||||
URL string `json:"url"`
|
||||
Description string `json:"description"`
|
||||
} `json:"results"`
|
||||
} `json:"web"`
|
||||
}
|
||||
|
||||
if err := json.Unmarshal(body, &searchResp); err != nil {
|
||||
return ErrorResult(fmt.Sprintf("failed to parse response: %v", err))
|
||||
}
|
||||
|
||||
results := searchResp.Web.Results
|
||||
if len(results) == 0 {
|
||||
msg := fmt.Sprintf("No results for: %s", query)
|
||||
return &ToolResult{
|
||||
ForLLM: msg,
|
||||
ForUser: msg,
|
||||
}
|
||||
}
|
||||
|
||||
var lines []string
|
||||
lines = append(lines, fmt.Sprintf("Results for: %s", query))
|
||||
for i, item := range results {
|
||||
if i >= count {
|
||||
break
|
||||
}
|
||||
lines = append(lines, fmt.Sprintf("%d. %s\n %s", i+1, item.Title, item.URL))
|
||||
if item.Description != "" {
|
||||
lines = append(lines, fmt.Sprintf(" %s", item.Description))
|
||||
}
|
||||
}
|
||||
|
||||
output := strings.Join(lines, "\n")
|
||||
return &ToolResult{
|
||||
ForLLM: fmt.Sprintf("Found %d results for: %s", len(results), query),
|
||||
ForUser: output,
|
||||
ForLLM: result,
|
||||
ForUser: result,
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user