fixup! chore: update marketplace for v0.11.37

march-improvements

cmd/hooks/post-tool-use/main.go

@@ -2,8 +2,10 @@
 package main
 
 import (
+	"context"
 	"fmt"
 	"os"
+	"time"
 
 	"github.com/lukaszraczylo/claude-mnemonic/pkg/hooks"
 )
@@ -51,6 +53,10 @@ var skipTools = map[string]bool{
 }
 
 func main() {
+	if !hooks.IsWorkerAvailable() {
+		hooks.WriteResponse("PostToolUse", true)
+		return
+	}
 	hooks.RunHook("PostToolUse", handlePostToolUse)
 }
 
@@ -63,15 +69,31 @@ func handlePostToolUse(ctx *hooks.HookContext, input *Input) (string, error) {
 
 	fmt.Fprintf(os.Stderr, "[post-tool-use] %s\n", input.ToolName)
 
-	// Send observation to worker
-	_, err := hooks.POST(ctx.Port, "/api/sessions/observations", map[string]interface{}{
-		"claudeSessionId": ctx.SessionID,
-		"project":         ctx.Project,
-		"tool_name":       input.ToolName,
-		"tool_input":      input.ToolInput,
-		"tool_response":   input.ToolResponse,
-		"cwd":             ctx.CWD,
-	})
+	// Fire-and-forget: send the observation without waiting for the response.
+	// The worker just queues it -- we don't need the response data.
+	// Use a short-lived context to ensure the request body is at least sent
+	// before this process exits.
+	done := make(chan struct{})
+	go func() {
+		defer close(done)
+		sendCtx, cancel := context.WithTimeout(context.Background(), 500*time.Millisecond)
+		defer cancel()
+		_ = hooks.POSTWithContext(sendCtx, ctx.Port, "/api/sessions/observations", map[string]interface{}{
+			"claudeSessionId": ctx.SessionID,
+			"project":         ctx.Project,
+			"tool_name":       input.ToolName,
+			"tool_input":      input.ToolInput,
+			"tool_response":   input.ToolResponse,
+			"cwd":             ctx.CWD,
+		})
+	}()
 
-	return "", err
+	// Wait briefly for the TCP connection to be established and request sent,
+	// but don't block the hook for the full response.
+	select {
+	case <-done:
+	case <-time.After(100 * time.Millisecond):
+	}
+
+	return "", nil
 }

cmd/hooks/session-start/main.go

@@ -6,6 +6,7 @@ import (
 	"net/url"
 	"os"
 	"strings"
+	"time"
 
 	"github.com/lukaszraczylo/claude-mnemonic/pkg/hooks"
 )
@@ -27,10 +28,17 @@ type Observation struct {
 }
 
 func main() {
+	if !hooks.IsWorkerAvailable() {
+		hooks.WriteResponse("SessionStart", true)
+		return
+	}
 	hooks.RunHook("SessionStart", handleSessionStart)
 }
 
 func handleSessionStart(ctx *hooks.HookContext, input *Input) (string, error) {
+	deadline, cancel := hooks.HookDeadline(30 * time.Second)
+	defer cancel()
+
 	// Fetch observations for context injection
 	endpoint := fmt.Sprintf("/api/context/inject?project=%s&cwd=%s",
 		url.QueryEscape(ctx.Project),
@@ -59,12 +67,21 @@ func handleSessionStart(ctx *hooks.HookContext, input *Input) (string, error) {
 	fmt.Fprintf(os.Stderr, "[claude-mnemonic] Injecting %d observations from project memory (%d detailed, %d condensed)\n",
 		len(obsData), min(fullCount, len(obsData)), max(0, len(obsData)-fullCount))
 
+	// Token budget for context injection
+	maxTokens := 16000 // default; could be made configurable via worker config endpoint
+	currentTokens := 0
+
 	// Build context string
-	contextBuilder := "<claude-mnemonic-context>\n"
-	contextBuilder += fmt.Sprintf("# Project Memory (%d observations)\n", len(obsData))
-	contextBuilder += "Use this knowledge to answer questions without re-exploring the codebase.\n\n"
+	header := fmt.Sprintf("<claude-mnemonic-context>\n# Project Memory (%d observations)\nUse this knowledge to answer questions without re-exploring the codebase.\n\n", len(obsData))
+	currentTokens += estimateTokens(header)
+	contextBuilder := header
 
 	for i, o := range obsData {
+		if deadline.Err() != nil {
+			contextBuilder += "\n... (returning early due to time limit)\n"
+			break
+		}
+
 		obs, ok := o.(map[string]interface{})
 		if !ok {
 			continue
@@ -73,40 +90,94 @@ func handleSessionStart(ctx *hooks.HookContext, input *Input) (string, error) {
 		title := getString(obs, "title")
 		obsType := getString(obs, "type")
 
+		var obsText string
+
 		// First `fullCount` observations get full detail, rest are condensed
 		if i < fullCount {
 			// Full detail: include narrative and facts
 			narrative := getString(obs, "narrative")
 
-			contextBuilder += fmt.Sprintf("## %d. [%s] %s\n", i+1, strings.ToUpper(obsType), title)
+			obsText = fmt.Sprintf("## %d. [%s] %s\n", i+1, strings.ToUpper(obsType), title)
 			if narrative != "" {
-				contextBuilder += narrative + "\n"
+				obsText += narrative + "\n"
 			}
 
 			if facts, ok := obs["facts"].([]interface{}); ok && len(facts) > 0 {
-				contextBuilder += "Key facts:\n"
+				obsText += "Key facts:\n"
 				for _, f := range facts {
 					if fact, ok := f.(string); ok && fact != "" {
-						contextBuilder += fmt.Sprintf("- %s\n", fact)
+						obsText += fmt.Sprintf("- %s\n", fact)
 					}
 				}
 			}
-			contextBuilder += "\n"
+			obsText += "\n"
 		} else {
 			// Condensed: just title and subtitle (one line)
 			subtitle := getString(obs, "subtitle")
 			if subtitle != "" {
-				contextBuilder += fmt.Sprintf("- [%s] %s: %s\n", strings.ToUpper(obsType), title, subtitle)
+				obsText = fmt.Sprintf("- [%s] %s: %s\n", strings.ToUpper(obsType), title, subtitle)
 			} else {
-				contextBuilder += fmt.Sprintf("- [%s] %s\n", strings.ToUpper(obsType), title)
+				obsText = fmt.Sprintf("- [%s] %s\n", strings.ToUpper(obsType), title)
 			}
 		}
+
+		obsTokens := estimateTokens(obsText)
+		if currentTokens+obsTokens > maxTokens {
+			contextBuilder += fmt.Sprintf("\n... (%d more observations omitted due to token budget)\n", len(obsData)-i)
+			break
+		}
+
+		contextBuilder += obsText
+		currentTokens += obsTokens
 	}
 
 	contextBuilder += "</claude-mnemonic-context>\n"
 	return contextBuilder, nil
 }
 
+// estimateTokens provides a more accurate token count estimate.
+// Uses word count * 1.3 as base, with adjustments for code and non-ASCII.
+func estimateTokens(s string) int {
+	if len(s) == 0 {
+		return 0
+	}
+
+	// Count words (split on whitespace)
+	words := len(strings.Fields(s))
+	if words == 0 {
+		// No whitespace = probably a single token or code blob
+		return (len(s) + 3) / 4
+	}
+
+	// Base estimate: ~1.3 tokens per word for English text
+	estimate := int(float64(words) * 1.3)
+
+	// Detect code-heavy content (high non-alpha ratio)
+	nonAlpha := 0
+	nonASCII := 0
+	for _, r := range s {
+		if r > 127 {
+			nonASCII++
+		} else if !('a' <= r && r <= 'z') && !('A' <= r && r <= 'Z') && !('0' <= r && r <= '9') && r != ' ' {
+			nonAlpha++
+		}
+	}
+
+	totalChars := len(s)
+
+	// Code adjustment: more special chars = more tokens per word
+	if totalChars > 0 && float64(nonAlpha)/float64(totalChars) > 0.15 {
+		estimate = int(float64(estimate) * 1.3)
+	}
+
+	// Non-ASCII adjustment: CJK and other scripts use more tokens
+	if totalChars > 0 && float64(nonASCII)/float64(totalChars) > 0.1 {
+		estimate += nonASCII // Roughly 1 extra token per non-ASCII char
+	}
+
+	return estimate
+}
+
 func getString(m map[string]interface{}, key string) string {
 	if v, ok := m[key].(string); ok {
 		return v

cmd/hooks/statusline/main.go

@@ -117,7 +117,7 @@ func getWorkerStats(port int, project string) *WorkerStats {
 	if err != nil {
 		return nil
 	}
-	defer resp.Body.Close()
+	defer func() { _ = resp.Body.Close() }()
 
 	if resp.StatusCode != http.StatusOK {
 		return nil

cmd/hooks/stop/main.go

@@ -5,12 +5,16 @@ import (
 	"bufio"
 	"encoding/json"
 	"fmt"
+	"io"
 	"os"
 	"strings"
+	"time"
 
 	"github.com/lukaszraczylo/claude-mnemonic/pkg/hooks"
 )
 
+var debug = os.Getenv("CLAUDE_MNEMONIC_DEBUG") != ""
+
 // Input is the hook input from Claude Code.
 type Input struct {
 	hooks.BaseInput
@@ -62,7 +66,19 @@ func parseTranscript(path string) (lastUser, lastAssistant string) {
 	if err != nil {
 		return "", ""
 	}
-	defer file.Close()
+	defer func() { _ = file.Close() }()
+
+	// For large transcripts, seek to the last 256KB for efficiency.
+	// We only need the last user/assistant messages, not the entire history.
+	const tailSize = 256 * 1024
+	info, err := file.Stat()
+	if err == nil && info.Size() > tailSize {
+		if _, seekErr := file.Seek(-tailSize, io.SeekEnd); seekErr == nil {
+			// Discard partial first line after seek
+			discardScanner := bufio.NewScanner(file)
+			discardScanner.Scan()
+		}
+	}
 
 	scanner := bufio.NewScanner(file)
 	// Increase buffer size for large messages
@@ -97,12 +113,20 @@ func parseTranscript(path string) (lastUser, lastAssistant string) {
 }
 
 func main() {
+	if !hooks.IsWorkerAvailable() {
+		hooks.WriteResponse("Stop", true)
+		return
+	}
 	hooks.RunHook("Stop", handleStop)
 }
 
 func handleStop(ctx *hooks.HookContext, input *Input) (string, error) {
-	// Debug: dump raw input
-	fmt.Fprintf(os.Stderr, "[stop] Raw input: %s\n", string(ctx.RawInput))
+	deadline, cancel := hooks.HookDeadline(30 * time.Second)
+	defer cancel()
+
+	if debug {
+		fmt.Fprintf(os.Stderr, "[stop] Raw input: %s\n", string(ctx.RawInput))
+	}
 
 	// Find session
 	result, err := hooks.GET(ctx.Port, fmt.Sprintf("/api/sessions?claudeSessionId=%s", ctx.SessionID))
@@ -122,18 +146,33 @@ func handleStop(ctx *hooks.HookContext, input *Input) (string, error) {
 		lastUser, lastAssistant = parseTranscript(input.TranscriptPath)
 	}
 
-	// Debug: log what we extracted
-	fmt.Fprintf(os.Stderr, "[stop] Transcript path: %s\n", input.TranscriptPath)
-	fmt.Fprintf(os.Stderr, "[stop] Last user message length: %d\n", len(lastUser))
-	fmt.Fprintf(os.Stderr, "[stop] Last assistant message length: %d\n", len(lastAssistant))
-	if len(lastAssistant) > 0 {
-		preview := lastAssistant
-		if len(preview) > 300 {
-			preview = preview[:300] + "..."
-		}
-		fmt.Fprintf(os.Stderr, "[stop] Last assistant preview: %s\n", preview)
+	// Truncate messages to avoid sending excessive data to the worker
+	if len(lastAssistant) > 10000 {
+		lastAssistant = lastAssistant[:10000]
+	}
+	if len(lastUser) > 5000 {
+		lastUser = lastUser[:5000]
+	}
+
+	if debug {
+		fmt.Fprintf(os.Stderr, "[stop] Transcript path: %s\n", input.TranscriptPath)
+		fmt.Fprintf(os.Stderr, "[stop] Last user message length: %d\n", len(lastUser))
+		fmt.Fprintf(os.Stderr, "[stop] Last assistant message length: %d\n", len(lastAssistant))
+		if len(lastAssistant) > 0 {
+			preview := lastAssistant
+			if len(preview) > 300 {
+				preview = preview[:300] + "..."
+			}
+			fmt.Fprintf(os.Stderr, "[stop] Last assistant preview: %s\n", preview)
+		}
+		fmt.Fprintf(os.Stderr, "[stop] Requesting summary for session %d (transcript: %v)\n", int64(sessionID), input.TranscriptPath != "")
+	}
+
+	// Check deadline before expensive summary request
+	if deadline.Err() != nil {
+		fmt.Fprintf(os.Stderr, "[stop] Returning early due to time limit\n")
+		return "", nil
 	}
-	fmt.Fprintf(os.Stderr, "[stop] Requesting summary for session %d (transcript: %v)\n", int64(sessionID), input.TranscriptPath != "")
 
 	// Request summary with message context from transcript
 	_, err = hooks.POST(ctx.Port, fmt.Sprintf("/sessions/%d/summarize", int64(sessionID)), map[string]interface{}{

cmd/hooks/subagent-stop/main.go

@@ -16,6 +16,10 @@ type Input struct {
 }
 
 func main() {
+	if !hooks.IsWorkerAvailable() {
+		hooks.WriteResponse("SubagentStop", true)
+		return
+	}
 	hooks.RunHook("SubagentStop", handleSubagentStop)
 }
 

cmd/hooks/user-prompt/main.go

@@ -5,6 +5,9 @@ import (
 	"fmt"
 	"net/url"
 	"os"
+	"strings"
+	"sync"
+	"time"
 
 	"github.com/lukaszraczylo/claude-mnemonic/pkg/hooks"
 )
@@ -15,31 +18,117 @@ type Input struct {
 	Prompt string `json:"prompt"`
 }
 
+// estimateTokens provides a more accurate token count estimate.
+// Uses word count * 1.3 as base, with adjustments for code and non-ASCII.
+func estimateTokens(s string) int {
+	if len(s) == 0 {
+		return 0
+	}
+
+	// Count words (split on whitespace)
+	words := len(strings.Fields(s))
+	if words == 0 {
+		// No whitespace = probably a single token or code blob
+		return (len(s) + 3) / 4
+	}
+
+	// Base estimate: ~1.3 tokens per word for English text
+	estimate := int(float64(words) * 1.3)
+
+	// Detect code-heavy content (high non-alpha ratio)
+	nonAlpha := 0
+	nonASCII := 0
+	for _, r := range s {
+		if r > 127 {
+			nonASCII++
+		} else if !('a' <= r && r <= 'z') && !('A' <= r && r <= 'Z') && !('0' <= r && r <= '9') && r != ' ' {
+			nonAlpha++
+		}
+	}
+
+	totalChars := len(s)
+
+	// Code adjustment: more special chars = more tokens per word
+	if totalChars > 0 && float64(nonAlpha)/float64(totalChars) > 0.15 {
+		estimate = int(float64(estimate) * 1.3)
+	}
+
+	// Non-ASCII adjustment: CJK and other scripts use more tokens
+	if totalChars > 0 && float64(nonASCII)/float64(totalChars) > 0.1 {
+		estimate += nonASCII // Roughly 1 extra token per non-ASCII char
+	}
+
+	return estimate
+}
+
 func main() {
+	if !hooks.IsWorkerAvailable() {
+		hooks.WriteResponse("UserPromptSubmit", true)
+		return
+	}
 	hooks.RunHook("UserPromptSubmit", handleUserPrompt)
 }
 
 func handleUserPrompt(ctx *hooks.HookContext, input *Input) (string, error) {
-	// Search for relevant observations based on the prompt
+	deadline, cancel := hooks.HookDeadline(10 * time.Second)
+	defer cancel()
+
 	searchURL := fmt.Sprintf("/api/context/search?project=%s&query=%s&cwd=%s",
 		url.QueryEscape(ctx.Project),
 		url.QueryEscape(input.Prompt),
 		url.QueryEscape(ctx.CWD))
 
-	var contextToInject string
-	var observationCount int
+	// Run search and session init concurrently.
+	// Session init doesn't strictly depend on search results -- the observation
+	// count passed is approximate (0) and acceptable.
+	var (
+		wg               sync.WaitGroup
+		searchResult     map[string]interface{}
+		initResult       map[string]interface{}
+		initErr          error
+		contextToInject  string
+		observationCount int
+	)
 
-	searchResult, _ := hooks.GET(ctx.Port, searchURL)
+	// Start search in background
+	wg.Add(1)
+	go func() {
+		defer wg.Done()
+		searchResult, _ = hooks.GET(ctx.Port, searchURL)
+	}()
+
+	// Start session init in parallel (with observationCount=0; approximate is fine)
+	wg.Add(1)
+	go func() {
+		defer wg.Done()
+		initResult, initErr = hooks.POST(ctx.Port, "/api/sessions/init", map[string]interface{}{
+			"claudeSessionId":     ctx.SessionID,
+			"project":             ctx.Project,
+			"prompt":              input.Prompt,
+			"matchedObservations": 0,
+		})
+	}()
+
+	// Wait for both to complete
+	wg.Wait()
+
+	// Check deadline after network calls
+	if deadline.Err() != nil {
+		return "", nil
+	}
+
+	// Process search results
 	if observations, ok := searchResult["observations"].([]interface{}); ok && len(observations) > 0 {
-		// Results are already filtered by relevance threshold and capped by max_results
-		// from the server-side config (ContextRelevanceThreshold, ContextMaxPromptResults)
 		observationCount = len(observations)
 
-		// Build context from search results
+		// Token budget for prompt context injection
+		maxTokens := 8000
+		currentTokens := 0
+
+		header := "<relevant-memory>\n# Relevant Knowledge From Previous Sessions\nIMPORTANT: Use this information to answer the question directly. Do NOT explore the codebase if the answer is here.\n\n"
+		currentTokens += estimateTokens(header)
 		var contextBuilder string
-		contextBuilder = "<relevant-memory>\n"
-		contextBuilder += "# Relevant Knowledge From Previous Sessions\n"
-		contextBuilder += "IMPORTANT: Use this information to answer the question directly. Do NOT explore the codebase if the answer is here.\n\n"
+		contextBuilder = header
 
 		for i, obs := range observations {
 			if obsMap, ok := obs.(map[string]interface{}); ok {
@@ -52,24 +141,30 @@ func handleUserPrompt(ctx *hooks.HookContext, input *Input) (string, error) {
 					obsType = t
 				}
 
-				// Start observation block
-				contextBuilder += fmt.Sprintf("## %d. [%s] %s\n", i+1, obsType, title)
+				var obsText string
+				obsText = fmt.Sprintf("## %d. [%s] %s\n", i+1, obsType, title)
 
-				// Add facts first (most concise answers)
 				if facts, ok := obsMap["facts"].([]interface{}); ok && len(facts) > 0 {
-					contextBuilder += "Key facts:\n"
+					obsText += "Key facts:\n"
 					for _, fact := range facts {
 						if factStr, ok := fact.(string); ok {
-							contextBuilder += fmt.Sprintf("- %s\n", factStr)
+							obsText += fmt.Sprintf("- %s\n", factStr)
 						}
 					}
-					contextBuilder += "\n"
+					obsText += "\n"
 				}
 
-				// Add narrative if present
 				if narrative, ok := obsMap["narrative"].(string); ok && narrative != "" {
-					contextBuilder += narrative + "\n\n"
+					obsText += narrative + "\n\n"
 				}
+
+				obsTokens := estimateTokens(obsText)
+				if currentTokens+obsTokens > maxTokens {
+					break
+				}
+
+				contextBuilder += obsText
+				currentTokens += obsTokens
 			}
 		}
 
@@ -77,40 +172,24 @@ func handleUserPrompt(ctx *hooks.HookContext, input *Input) (string, error) {
 		contextToInject = contextBuilder
 	}
 
-	// Initialize session with matched observations count
-	result, err := hooks.POST(ctx.Port, "/api/sessions/init", map[string]interface{}{
-		"claudeSessionId":     ctx.SessionID,
-		"project":             ctx.Project,
-		"prompt":              input.Prompt,
-		"matchedObservations": observationCount,
-	})
-	if err != nil {
-		return "", err
+	// Check session init result
+	if initErr != nil {
+		return "", initErr
 	}
 
 	// Check if skipped due to privacy
-	if skipped, ok := result["skipped"].(bool); ok && skipped {
+	if skipped, ok := initResult["skipped"].(bool); ok && skipped {
 		fmt.Fprintf(os.Stderr, "[user-prompt] Session skipped (private)\n")
 		return "", nil
 	}
 
-	// Safely extract session ID and prompt number with type checking
-	sessionDbIdRaw, ok := result["sessionDbId"].(float64)
-	if !ok {
-		return "", fmt.Errorf("invalid or missing sessionDbId in response")
-	}
-	sessionID := int64(sessionDbIdRaw)
-
-	promptNumberRaw, ok := result["promptNumber"].(float64)
-	if !ok {
-		return "", fmt.Errorf("invalid or missing promptNumber in response")
-	}
-	promptNumber := int(promptNumberRaw)
+	sessionID := int64(initResult["sessionDbId"].(float64))
+	promptNumber := int(initResult["promptNumber"].(float64))
 
 	fmt.Fprintf(os.Stderr, "[user-prompt] Session %d, prompt #%d\n", sessionID, promptNumber)
 
-	// Start SDK agent
-	_, err = hooks.POST(ctx.Port, fmt.Sprintf("/sessions/%d/init", sessionID), map[string]interface{}{
+	// Start SDK agent (depends on session init result, so kept sequential)
+	_, err := hooks.POST(ctx.Port, fmt.Sprintf("/sessions/%d/init", sessionID), map[string]interface{}{
 		"userPrompt":   input.Prompt,
 		"promptNumber": promptNumber,
 	})
@@ -120,7 +199,6 @@ func handleUserPrompt(ctx *hooks.HookContext, input *Input) (string, error) {
 
 	// Return context if we found relevant observations
 	if observationCount > 0 {
-		// Show match count to user via stderr
 		fmt.Fprintf(os.Stderr, "[claude-mnemonic] Found %d relevant memories for this prompt\n", observationCount)
 		return contextToInject, nil
 	}

cmd/mcp/main.go

@@ -4,20 +4,16 @@ package main
 import (
 	"context"
 	"flag"
+	"fmt"
+	"net/http"
 	"os"
 	"os/signal"
 	"syscall"
 	"time"
 
 	"github.com/lukaszraczylo/claude-mnemonic/internal/config"
-	"github.com/lukaszraczylo/claude-mnemonic/internal/db/gorm"
-	"github.com/lukaszraczylo/claude-mnemonic/internal/embedding"
 	"github.com/lukaszraczylo/claude-mnemonic/internal/mcp"
-	"github.com/lukaszraczylo/claude-mnemonic/internal/scoring"
-	"github.com/lukaszraczylo/claude-mnemonic/internal/search"
-	"github.com/lukaszraczylo/claude-mnemonic/internal/vector/sqlitevec"
 	"github.com/lukaszraczylo/claude-mnemonic/internal/watcher"
-	"github.com/lukaszraczylo/claude-mnemonic/pkg/models"
 	"github.com/rs/zerolog"
 	"github.com/rs/zerolog/log"
 )
@@ -28,7 +24,6 @@ var Version = "dev"
 func main() {
 	// Parse flags
 	project := flag.String("project", "", "Project name (required)")
-	dataDir := flag.String("data-dir", "", "Data directory (default: ~/.claude-mnemonic)")
 	debug := flag.Bool("debug", false, "Enable debug logging")
 	flag.Parse()
 
@@ -43,23 +38,12 @@ func main() {
 		log.Fatal().Msg("--project is required")
 	}
 
-	// Ensure data directory and settings exist
-	if err := config.EnsureAll(); err != nil {
-		log.Fatal().Err(err).Msg("Failed to ensure data directories")
-	}
+	// Get worker port from config
+	port := config.GetWorkerPort()
+	workerURL := fmt.Sprintf("http://localhost:%d", port)
 
-	// Load config
-	cfg, err := config.Load()
-	if err != nil {
-		log.Warn().Err(err).Msg("Failed to load config, using defaults")
-		cfg = config.Default()
-	}
-
-	// Override data directory if specified
-	dbPath := cfg.DBPath
-	if *dataDir != "" {
-		dbPath = *dataDir + "/claude-mnemonic.db"
-	}
+	// Create HTTP client for worker
+	client := &http.Client{Timeout: 30 * time.Second}
 
 	ctx, cancel := context.WithCancel(context.Background())
 	defer cancel()
@@ -73,69 +57,12 @@ func main() {
 		cancel()
 	}()
 
-	// Initialize database store (migrations run automatically)
-	storeCfg := gorm.Config{
-		Path:     dbPath,
-		MaxConns: cfg.MaxConns,
-		// WALMode is enabled automatically by GORM
-	}
-	store, err := gorm.NewStore(storeCfg)
-	if err != nil {
-		log.Fatal().Err(err).Msg("Failed to initialize database store")
-	}
-	defer store.Close()
+	// Start file watchers for config changes
+	startWatchers()
 
-	// Initialize stores
-	observationStore := gorm.NewObservationStore(store, nil, nil, nil)
-	summaryStore := gorm.NewSummaryStore(store)
-	promptStore := gorm.NewPromptStore(store, nil)
-	patternStore := gorm.NewPatternStore(store)
-	relationStore := gorm.NewRelationStore(store)
-	sessionStore := gorm.NewSessionStore(store)
-
-	// Initialize embedding service and vector client
-	var vectorClient *sqlitevec.Client
-	embedSvc, err := embedding.NewService()
-	if err != nil {
-		log.Warn().Err(err).Msg("Embedding service unavailable, vector search disabled")
-	} else {
-		defer embedSvc.Close()
-		vectorClient, err = sqlitevec.NewClient(sqlitevec.Config{DB: store.GetRawDB()}, embedSvc)
-		if err != nil {
-			log.Warn().Err(err).Msg("Vector client unavailable, vector search disabled")
-		} else {
-			log.Info().Msg("Vector search enabled via sqlite-vec")
-		}
-	}
-
-	// Initialize scoring components
-	scoreConfig := models.DefaultScoringConfig()
-	scoreCalculator := scoring.NewCalculator(scoreConfig)
-	recalculator := scoring.NewRecalculator(observationStore, scoreCalculator, log.Logger)
-	go recalculator.Start(ctx)
-	defer recalculator.Stop()
-
-	// Initialize search manager
-	searchMgr := search.NewManager(observationStore, summaryStore, promptStore, vectorClient)
-
-	// Start file watchers
-	startWatchers(ctx, dbPath)
-
-	// Create and run MCP server with all dependencies
-	// Note: maintenanceService is nil because it runs in the worker process
-	server := mcp.NewServer(
-		searchMgr,
-		Version,
-		observationStore,
-		patternStore,
-		relationStore,
-		sessionStore,
-		vectorClient,
-		scoreCalculator,
-		recalculator,
-		nil, // maintenanceService - handled by worker
-	)
-	log.Info().Str("project", *project).Str("version", Version).Msg("Starting MCP server")
+	// Create and run MCP server
+	server := mcp.NewServer(client, workerURL, *project, Version)
+	log.Info().Str("project", *project).Str("version", Version).Str("worker", workerURL).Msg("Starting MCP server")
 
 	if err := server.Run(ctx); err != nil {
 		log.Fatal().Err(err).Msg("MCP server error")
@@ -143,7 +70,7 @@ func main() {
 }
 
 // startWatchers initializes file watchers for config.
-func startWatchers(ctx context.Context, dbPath string) {
+func startWatchers() {
 	// Watch config file for changes (triggers process exit for restart)
 	configPath := config.SettingsPath()
 	configWatcher, err := watcher.New(configPath, func() {