refactor(api): split monolithic handlers.go into focused modules

Break down the 627-line handlers.go into specialized modules:
- handlers_chat.go: chat and streaming endpoints
- handlers_config.go: configuration endpoints
- handlers_common.go: shared utilities
- handlers_info.go: info and status endpoints
- handlers_terminal.go: terminal/shell endpoints
- handlers_tools.go: tool-related endpoints

Also includes config improvements, orchestrator enhancements, and
web component updates.

💘 Generated with Crush

Assisted-by: MiniMax-M2.7 via Crush <crush@charm.land>

internal/orchestrator/orchestrator.go

@@ -1,6 +1,7 @@
 package orchestrator
 
 import (
+	"bufio"
 	"bytes"
 	"encoding/json"
 	"fmt"
@@ -34,6 +35,9 @@ type ChatResponse struct {
 		Message struct {
 			Content string `json:"content"`
 		} `json:"message"`
+		Delta struct {
+			Content string `json:"content"`
+		} `json:"delta"`
 	} `json:"choices"`
 	Usage struct {
 		TotalTokens int `json:"total_tokens"`
@@ -161,6 +165,104 @@ func (o *Orchestrator) Send(userMessage string) (string, error) {
 	return content, nil
 }
 
+func (o *Orchestrator) SendStream(userMessage string, onChunk func(string)) (string, error) {
+	o.histMu.Lock()
+	o.history = append(o.history, Message{
+		Role:    "user",
+		Content: userMessage,
+	})
+
+	if len(o.history) > maxHistorySize {
+		o.history = o.history[len(o.history)-maxHistorySize:]
+	}
+
+	messages := make([]Message, 0, len(o.history)+1)
+	if o.systemPrompt != "" {
+		messages = append(messages, Message{Role: "system", Content: o.systemPrompt})
+	}
+	messages = append(messages, o.history...)
+
+	reqBody := ChatRequest{
+		Model:    o.provider.Model,
+		Messages: messages,
+		Stream:   true,
+	}
+	o.histMu.Unlock()
+
+	body, err := json.Marshal(reqBody)
+	if err != nil {
+		return "", fmt.Errorf("marshal request: %w", err)
+	}
+
+	baseURL := o.provider.BaseURL
+	if baseURL == "" {
+		baseURL = getProviderBaseURL(o.provider.Name)
+	}
+
+	url := strings.TrimRight(baseURL, "/") + "/chat/completions"
+
+	req, err := http.NewRequest("POST", url, bytes.NewReader(body))
+	if err != nil {
+		return "", fmt.Errorf("create request: %w", err)
+	}
+
+	req.Header.Set("Content-Type", "application/json")
+	req.Header.Set("Authorization", "Bearer "+o.provider.APIKey)
+
+	resp, err := o.client.Do(req)
+	if err != nil {
+		return "", fmt.Errorf("send request: %w", err)
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode != http.StatusOK {
+		respBody, _ := io.ReadAll(resp.Body)
+		return "", fmt.Errorf("API error (%d): %s", resp.StatusCode, string(respBody))
+	}
+
+	var fullContent strings.Builder
+	scanner := bufio.NewScanner(resp.Body)
+	scanner.Buffer(make([]byte, 0, 64*1024), 1024*1024)
+
+	for scanner.Scan() {
+		line := scanner.Text()
+		if !strings.HasPrefix(line, "data: ") {
+			continue
+		}
+		data := strings.TrimPrefix(line, "data: ")
+		if data == "[DONE]" {
+			break
+		}
+
+		var chatResp ChatResponse
+		if err := json.Unmarshal([]byte(data), &chatResp); err != nil {
+			continue
+		}
+
+		if len(chatResp.Choices) > 0 {
+			chunk := chatResp.Choices[0].Delta.Content
+			if chunk != "" {
+				fullContent.WriteString(chunk)
+				onChunk(chunk)
+			}
+		}
+	}
+
+	if err := scanner.Err(); err != nil {
+		return fullContent.String(), fmt.Errorf("read stream: %w", err)
+	}
+
+	content := cleanAIResponse(fullContent.String())
+	o.histMu.Lock()
+	o.history = append(o.history, Message{
+		Role:    "assistant",
+		Content: content,
+	})
+	o.histMu.Unlock()
+
+	return content, nil
+}
+
 func cleanAIResponse(content string) string {
 	content = thinkRegex.ReplaceAllString(content, "")
 	lines := strings.Split(content, "\n")