Reorganize repo: backend/, deploy/, docs/ layout + AGENTS.md

Restructure the monorepo into clear top-level directories:
- backend/: Go module root (cmd, internal, pkg, configs, migrations,
  docs/swagger, scripts, tests, go.mod, Makefile, .air.toml)
- deploy/: Docker (Dockerfile, docker-compose*), quickstart, fluentd
- docs/: project documentation + reports/ (moved from repo root)
- AGENTS.md: new AI coding-agent guide at repo root

Update all references to the new layout:
- Dockerfile: COPY backend/go.mod, COPY backend/ (context = repo root)
- docker-compose files: context ../.., dockerfile deploy/docker/Dockerfile,
  env_file ../../.env, volume mounts ../../backend:/app
- deploy/quickstart/compose.yaml: dockerfile deploy/docker/Dockerfile
- CI: working-directory: backend for go commands, file deploy/docker/Dockerfile,
  coverage path backend/coverage.out, health_check backend/scripts/
- backend/Makefile: docker target uses -f ../deploy/docker/Dockerfile ../
- README: architecture tree, quickstart, config paths updated

Move root stray scripts (rename_models.*, run_m11_tests.sh, verify_build.sh,
gorm_bool_main.go) to backend/scripts/legacy/. All moves via git mv to
preserve history. Build, vet, SQLite tests, and docker compose config verified.

backend/internal/handler/api/v1/sse_stream_handler_test.go

@@ -0,0 +1,133 @@
+package v1
+
+import (
+	"encoding/json"
+	"fmt"
+	"context"
+	"net/http/httptest"
+	"testing"
+
+	"github.com/gin-gonic/gin"
+	"github.com/stretchr/testify/assert"
+
+	"github.com/gochat/gochat/internal/llm"
+	"github.com/gochat/gochat/internal/model"
+)
+
+// ========== Mock LLM Provider for SSE tests ==========
+
+type mockSSELLMProvider struct {
+	streamChunks []llm.StreamChunk
+	streamError  error
+	lastStreamReq *llm.ChatRequest
+}
+
+func (m *mockSSELLMProvider) ChatCompletion(ctx context.Context, req llm.ChatRequest) (*llm.ChatResponse, error) {
+	return nil, fmt.Errorf("not implemented")
+}
+
+func (m *mockSSELLMProvider) CreateEmbedding(ctx context.Context, req llm.EmbeddingRequest) (*llm.EmbeddingResponse, error) {
+	return nil, fmt.Errorf("not implemented")
+}
+
+func (m *mockSSELLMProvider) ChatCompletionStream(ctx context.Context, req llm.ChatRequest, onChunk func(llm.StreamChunk) error) error {
+	m.lastStreamReq = &req
+	if m.streamError != nil {
+		return m.streamError
+	}
+	for _, chunk := range m.streamChunks {
+		if err := onChunk(chunk); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+// ========== escapeJSONString Tests ==========
+
+func TestEscapeJSONString_双引号(t *testing.T) {
+	result := escapeJSONString(`he said "hello"`)
+	assert.Equal(t, `he said \"hello\"`, result)
+}
+
+func TestEscapeJSONString_反斜杠(t *testing.T) {
+	result := escapeJSONString(`path\to\file`)
+	assert.Equal(t, `path\\to\\file`, result)
+}
+
+func TestEscapeJSONString_换行(t *testing.T) {
+	result := escapeJSONString("line1\nline2")
+	assert.Equal(t, "line1\\nline2", result)
+}
+
+func TestEscapeJSONString_制表符(t *testing.T) {
+	result := escapeJSONString("col1\tcol2")
+	assert.Equal(t, "col1\\tcol2", result)
+}
+
+func TestEscapeJSONString_无特殊字符(t *testing.T) {
+	result := escapeJSONString("plain text")
+	assert.Equal(t, "plain text", result)
+}
+
+// ========== buildStreamChatMessages Tests ==========
+
+func TestBuildStreamChatMessages_空历史(t *testing.T) {
+	thread := &model.CopilotThread{
+		Title: "Test Thread",
+	}
+	_ = thread // used indirectly via buildStreamChatMessages
+
+	result := buildStreamChatMessages(thread, "user question")
+
+	assert.Len(t, result, 2) // system + user
+	assert.Equal(t, "system", result[0].Role)
+	assert.Equal(t, "user", result[1].Role)
+	assert.Equal(t, "user question", result[1].Content)
+}
+
+func TestBuildStreamChatMessages_有历史(t *testing.T) {
+	thread := &model.CopilotThread{
+		Title: "Test Thread",
+	}
+	messages := []model.CopilotMessage{
+		{MessageType: model.CopilotMessageTypeUser, Message: json.RawMessage(`"previous user msg"`)},
+		{MessageType: model.CopilotMessageTypeAssistant, Message: json.RawMessage(`"previous assistant msg"`)},
+	}
+	thread.Messages = messages
+
+	result := buildStreamChatMessages(thread, "new question")
+
+	// system + 2 history + new user = 4
+	assert.Len(t, result, 4)
+	assert.Equal(t, "system", result[0].Role)
+	assert.Equal(t, "new question", result[len(result)-1].Content)
+}
+
+// ========== writeSSEMessage Tests ==========
+
+func TestWriteSSEMessage_格式(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+	w := httptest.NewRecorder()
+	c, _ := gin.CreateTestContext(w)
+
+	writeSSEMessage(c, "message", `{"content": "hello"}`)
+
+	body := w.Body.String()
+	assert.Contains(t, body, "event: message")
+assert.Contains(t, body, `data: {"content": "hello"}`)
+	// SSE format requires double newline
+	assert.Contains(t, body, "\n\n")
+}
+
+func TestWriteSSEMessage_Done事件(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+	w := httptest.NewRecorder()
+	c, _ := gin.CreateTestContext(w)
+
+	writeSSEMessage(c, "done", `{"done": true}`)
+
+	body := w.Body.String()
+	assert.Contains(t, body, "event: done")
+	assert.Contains(t, body, `data: {"done": true}`)
+}