test: add comprehensive test coverage across multiple packages

- [x] Add 298 tests for Python chunker functionality
- [x] Add 213 tests for chunking types and constants
- [x] Add 398 tests for TypeScript/JavaScript chunker
- [x] Add 954 tests for MCP server handlers and validation
- [x] Add 563 tests for pattern detector and analysis
- [x] Add 1149 tests for vector client cache and operations
- [x] Add 663 tests for SDK processor, circuit breaker, and deduplication
- [x] Add 731 tests for session manager lifecycle and concurrency
- [x] Add 331 tests for similarity clustering and term extraction

internal/chunking/python/chunker_test.go

@@ -0,0 +1,298 @@
+package python
+
+import (
+	"context"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/lukaszraczylo/claude-mnemonic/internal/chunking"
+)
+
+// =============================================================================
+// TEST HELPERS
+// =============================================================================
+
+func createTempPythonFile(t *testing.T, content string) string {
+	t.Helper()
+
+	tmpDir := t.TempDir()
+	filePath := filepath.Join(tmpDir, "test.py")
+
+	err := os.WriteFile(filePath, []byte(content), 0600)
+	require.NoError(t, err)
+
+	return filePath
+}
+
+// =============================================================================
+// TESTS FOR Chunker
+// =============================================================================
+
+func TestNewChunker(t *testing.T) {
+	t.Parallel()
+
+	opts := chunking.DefaultChunkOptions()
+	c := NewChunker(opts)
+
+	assert.NotNil(t, c)
+	assert.NotNil(t, c.parser)
+}
+
+func TestChunker_Language(t *testing.T) {
+	t.Parallel()
+
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	assert.Equal(t, chunking.LanguagePython, c.Language())
+}
+
+func TestChunker_SupportedExtensions(t *testing.T) {
+	t.Parallel()
+
+	c := NewChunker(chunking.DefaultChunkOptions())
+	exts := c.SupportedExtensions()
+
+	assert.Contains(t, exts, ".py")
+}
+
+func TestChunker_Chunk_SimpleFunction(t *testing.T) {
+	t.Parallel()
+
+	code := `def greet(name):
+    """Greets a person by name."""
+    return f"Hello, {name}!"
+`
+
+	filePath := createTempPythonFile(t, code)
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	chunks, err := c.Chunk(context.Background(), filePath)
+	require.NoError(t, err)
+	require.NotEmpty(t, chunks)
+
+	// Should find the greet function
+	var foundGreet bool
+	for _, chunk := range chunks {
+		if chunk.Name == "greet" {
+			foundGreet = true
+			assert.Equal(t, chunking.ChunkTypeFunction, chunk.Type)
+			assert.Equal(t, chunking.LanguagePython, chunk.Language)
+			assert.Contains(t, chunk.Content, "def greet")
+		}
+	}
+	assert.True(t, foundGreet, "Should find 'greet' function")
+}
+
+func TestChunker_Chunk_ClassWithMethods(t *testing.T) {
+	t.Parallel()
+
+	code := `class Calculator:
+    """A simple calculator class."""
+
+    def add(self, a, b):
+        """Adds two numbers."""
+        return a + b
+
+    def multiply(self, a, b):
+        """Multiplies two numbers."""
+        return a * b
+`
+
+	filePath := createTempPythonFile(t, code)
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	chunks, err := c.Chunk(context.Background(), filePath)
+	require.NoError(t, err)
+	require.NotEmpty(t, chunks)
+
+	// Should find the Calculator class and its methods
+	var foundClass, foundAdd, foundMultiply bool
+	for _, chunk := range chunks {
+		switch chunk.Name {
+		case "Calculator":
+			foundClass = true
+			assert.Equal(t, chunking.ChunkTypeClass, chunk.Type)
+		case "add":
+			foundAdd = true
+			assert.Equal(t, chunking.ChunkTypeMethod, chunk.Type)
+			assert.Equal(t, "Calculator", chunk.ParentName)
+		case "multiply":
+			foundMultiply = true
+			assert.Equal(t, chunking.ChunkTypeMethod, chunk.Type)
+			assert.Equal(t, "Calculator", chunk.ParentName)
+		}
+	}
+
+	assert.True(t, foundClass, "Should find 'Calculator' class")
+	assert.True(t, foundAdd, "Should find 'add' method")
+	assert.True(t, foundMultiply, "Should find 'multiply' method")
+}
+
+func TestChunker_Chunk_MultipleFunctions(t *testing.T) {
+	t.Parallel()
+
+	code := `def first_function():
+    pass
+
+def second_function(x, y):
+    return x + y
+
+def third_function():
+    """Has a docstring."""
+    return 42
+`
+
+	filePath := createTempPythonFile(t, code)
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	chunks, err := c.Chunk(context.Background(), filePath)
+	require.NoError(t, err)
+
+	// Should find all three functions
+	functionNames := make(map[string]bool)
+	for _, chunk := range chunks {
+		if chunk.Type == chunking.ChunkTypeFunction {
+			functionNames[chunk.Name] = true
+		}
+	}
+
+	assert.True(t, functionNames["first_function"])
+	assert.True(t, functionNames["second_function"])
+	assert.True(t, functionNames["third_function"])
+}
+
+func TestChunker_Chunk_FileNotFound(t *testing.T) {
+	t.Parallel()
+
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	_, err := c.Chunk(context.Background(), "/nonexistent/path/file.py")
+	require.Error(t, err)
+	assert.Contains(t, err.Error(), "read file")
+}
+
+func TestChunker_Chunk_EmptyFile(t *testing.T) {
+	t.Parallel()
+
+	filePath := createTempPythonFile(t, "")
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	chunks, err := c.Chunk(context.Background(), filePath)
+	require.NoError(t, err)
+	assert.Empty(t, chunks)
+}
+
+func TestChunker_Chunk_OnlyComments(t *testing.T) {
+	t.Parallel()
+
+	code := `# This is a comment
+# Another comment
+"""
+This is a module docstring
+"""
+`
+
+	filePath := createTempPythonFile(t, code)
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	chunks, err := c.Chunk(context.Background(), filePath)
+	require.NoError(t, err)
+	// Comments and docstrings without code should not produce chunks
+	assert.Empty(t, chunks)
+}
+
+func TestChunker_Chunk_NestedClass(t *testing.T) {
+	t.Parallel()
+
+	code := `class Outer:
+    class Inner:
+        def inner_method(self):
+            pass
+
+    def outer_method(self):
+        pass
+`
+
+	filePath := createTempPythonFile(t, code)
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	chunks, err := c.Chunk(context.Background(), filePath)
+	require.NoError(t, err)
+	require.NotEmpty(t, chunks)
+
+	// Should find the Outer class at minimum
+	var foundOuter bool
+	for _, chunk := range chunks {
+		if chunk.Name == "Outer" {
+			foundOuter = true
+		}
+	}
+	assert.True(t, foundOuter, "Should find 'Outer' class")
+}
+
+func TestChunker_Chunk_Decorators(t *testing.T) {
+	t.Parallel()
+
+	code := `@staticmethod
+def static_func():
+    pass
+
+@classmethod
+def class_func(cls):
+    pass
+
+@property
+def my_property(self):
+    return self._value
+`
+
+	filePath := createTempPythonFile(t, code)
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	chunks, err := c.Chunk(context.Background(), filePath)
+	require.NoError(t, err)
+	require.NotEmpty(t, chunks)
+
+	// Should find decorated functions
+	functionNames := make(map[string]bool)
+	for _, chunk := range chunks {
+		functionNames[chunk.Name] = true
+	}
+
+	assert.True(t, functionNames["static_func"])
+	assert.True(t, functionNames["class_func"])
+	assert.True(t, functionNames["my_property"])
+}
+
+func TestChunker_Chunk_AsyncFunction(t *testing.T) {
+	t.Parallel()
+
+	code := `async def fetch_data(url):
+    """Fetches data from URL asynchronously."""
+    pass
+
+async def process_items(items):
+    for item in items:
+        await process(item)
+`
+
+	filePath := createTempPythonFile(t, code)
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	chunks, err := c.Chunk(context.Background(), filePath)
+	require.NoError(t, err)
+	require.NotEmpty(t, chunks)
+
+	// Should find async functions
+	functionNames := make(map[string]bool)
+	for _, chunk := range chunks {
+		functionNames[chunk.Name] = true
+	}
+
+	assert.True(t, functionNames["fetch_data"])
+	assert.True(t, functionNames["process_items"])
+}

internal/chunking/types_test.go

@@ -0,0 +1,213 @@
+package chunking
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+// =============================================================================
+// TESTS FOR Chunk METHODS
+// =============================================================================
+
+func TestChunk_Identifier(t *testing.T) {
+	tests := []struct {
+		name     string
+		expected string
+		chunk    Chunk
+	}{
+		// ===== GOOD CASES =====
+		{
+			name: "top-level function",
+			chunk: Chunk{
+				Name:       "MyFunction",
+				ParentName: "",
+			},
+			expected: "MyFunction",
+		},
+		{
+			name: "method with parent",
+			chunk: Chunk{
+				Name:       "Process",
+				ParentName: "Handler",
+			},
+			expected: "Handler.Process",
+		},
+		{
+			name: "nested method",
+			chunk: Chunk{
+				Name:       "Validate",
+				ParentName: "UserService",
+			},
+			expected: "UserService.Validate",
+		},
+
+		// ===== EDGE CASES =====
+		{
+			name: "empty name",
+			chunk: Chunk{
+				Name:       "",
+				ParentName: "",
+			},
+			expected: "",
+		},
+		{
+			name: "parent but no name",
+			chunk: Chunk{
+				Name:       "",
+				ParentName: "Parent",
+			},
+			expected: "Parent.",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := tt.chunk.Identifier()
+			assert.Equal(t, tt.expected, result)
+		})
+	}
+}
+
+func TestChunk_LineRange(t *testing.T) {
+	tests := []struct {
+		name     string
+		expected string
+		chunk    Chunk
+	}{
+		// ===== GOOD CASES =====
+		{
+			name: "single line",
+			chunk: Chunk{
+				StartLine: 10,
+				EndLine:   10,
+			},
+			expected: "L10-L10",
+		},
+		{
+			name: "multi-line",
+			chunk: Chunk{
+				StartLine: 25,
+				EndLine:   50,
+			},
+			expected: "L25-L50",
+		},
+
+		// ===== EDGE CASES =====
+		{
+			name: "line 1",
+			chunk: Chunk{
+				StartLine: 1,
+				EndLine:   5,
+			},
+			expected: "L1-L5",
+		},
+		{
+			name: "large line numbers",
+			chunk: Chunk{
+				StartLine: 1000,
+				EndLine:   2500,
+			},
+			expected: "L1000-L2500",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := tt.chunk.LineRange()
+			assert.Equal(t, tt.expected, result)
+		})
+	}
+}
+
+func TestChunk_SearchableContent(t *testing.T) {
+	tests := []struct {
+		name     string
+		contains []string
+		chunk    Chunk
+	}{
+		// ===== GOOD CASES =====
+		{
+			name: "full chunk with all fields",
+			chunk: Chunk{
+				Signature:  "func ProcessData(input []byte) error",
+				DocComment: "// ProcessData handles incoming data",
+				Content:    "func ProcessData(input []byte) error {\n\treturn nil\n}",
+			},
+			contains: []string{
+				"func ProcessData(input []byte) error",
+				"ProcessData handles incoming data",
+				"return nil",
+			},
+		},
+		{
+			name: "only signature",
+			chunk: Chunk{
+				Signature: "func Hello()",
+			},
+			contains: []string{"func Hello()"},
+		},
+		{
+			name: "only content",
+			chunk: Chunk{
+				Content: "some code here",
+			},
+			contains: []string{"some code here"},
+		},
+
+		// ===== EDGE CASES =====
+		{
+			name:     "empty chunk",
+			chunk:    Chunk{},
+			contains: []string{},
+		},
+		{
+			name: "only doc comment",
+			chunk: Chunk{
+				DocComment: "// Important documentation",
+			},
+			contains: []string{"Important documentation"},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := tt.chunk.SearchableContent()
+			for _, expected := range tt.contains {
+				assert.Contains(t, result, expected)
+			}
+		})
+	}
+}
+
+func TestDefaultChunkOptions(t *testing.T) {
+	opts := DefaultChunkOptions()
+
+	assert.Greater(t, opts.MaxChunkSize, 0, "MaxChunkSize should be positive")
+	assert.True(t, opts.IncludeDocComments, "IncludeDocComments should be true by default")
+	assert.True(t, opts.IncludePrivate, "IncludePrivate should be true by default")
+	assert.Equal(t, 0, opts.MinLines, "MinLines should be 0 by default")
+}
+
+// =============================================================================
+// TESTS FOR ChunkType AND Language CONSTANTS
+// =============================================================================
+
+func TestChunkType_Values(t *testing.T) {
+	// Ensure all chunk types have expected values
+	assert.Equal(t, ChunkType("function"), ChunkTypeFunction)
+	assert.Equal(t, ChunkType("method"), ChunkTypeMethod)
+	assert.Equal(t, ChunkType("class"), ChunkTypeClass)
+	assert.Equal(t, ChunkType("interface"), ChunkTypeInterface)
+	assert.Equal(t, ChunkType("type"), ChunkTypeType)
+	assert.Equal(t, ChunkType("const"), ChunkTypeConst)
+	assert.Equal(t, ChunkType("var"), ChunkTypeVar)
+}
+
+func TestLanguage_Values(t *testing.T) {
+	// Ensure all language types have expected values
+	assert.Equal(t, Language("go"), LanguageGo)
+	assert.Equal(t, Language("python"), LanguagePython)
+	assert.Equal(t, Language("typescript"), LanguageTypeScript)
+	assert.Equal(t, Language("javascript"), LanguageJavaScript)
+}

internal/chunking/typescript/chunker_test.go

@@ -0,0 +1,398 @@
+package typescript
+
+import (
+	"context"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/lukaszraczylo/claude-mnemonic/internal/chunking"
+)
+
+// =============================================================================
+// TEST HELPERS
+// =============================================================================
+
+func createTempTSFile(t *testing.T, content string, ext string) string {
+	t.Helper()
+
+	tmpDir := t.TempDir()
+	filePath := filepath.Join(tmpDir, "test"+ext)
+
+	err := os.WriteFile(filePath, []byte(content), 0600)
+	require.NoError(t, err)
+
+	return filePath
+}
+
+// =============================================================================
+// TESTS FOR Chunker
+// =============================================================================
+
+func TestNewChunker(t *testing.T) {
+	t.Parallel()
+
+	opts := chunking.DefaultChunkOptions()
+	c := NewChunker(opts)
+
+	assert.NotNil(t, c)
+	assert.NotNil(t, c.parser)
+}
+
+func TestChunker_Language(t *testing.T) {
+	t.Parallel()
+
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	assert.Equal(t, chunking.LanguageTypeScript, c.Language())
+}
+
+func TestChunker_SupportedExtensions(t *testing.T) {
+	t.Parallel()
+
+	c := NewChunker(chunking.DefaultChunkOptions())
+	exts := c.SupportedExtensions()
+
+	assert.Contains(t, exts, ".ts")
+	assert.Contains(t, exts, ".tsx")
+	assert.Contains(t, exts, ".js")
+	assert.Contains(t, exts, ".jsx")
+}
+
+func TestChunker_Chunk_SimpleFunction(t *testing.T) {
+	t.Parallel()
+
+	code := `function greet(name: string): string {
+    return "Hello, " + name + "!";
+}
+`
+
+	filePath := createTempTSFile(t, code, ".ts")
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	chunks, err := c.Chunk(context.Background(), filePath)
+	require.NoError(t, err)
+	require.NotEmpty(t, chunks)
+
+	// Should find the greet function
+	var foundGreet bool
+	for _, chunk := range chunks {
+		if chunk.Name == "greet" {
+			foundGreet = true
+			assert.Equal(t, chunking.ChunkTypeFunction, chunk.Type)
+			assert.Equal(t, chunking.LanguageTypeScript, chunk.Language)
+			assert.Contains(t, chunk.Content, "function greet")
+		}
+	}
+	assert.True(t, foundGreet, "Should find 'greet' function")
+}
+
+func TestChunker_Chunk_ClassWithMethods(t *testing.T) {
+	t.Parallel()
+
+	code := `class Calculator {
+    add(a: number, b: number): number {
+        return a + b;
+    }
+
+    multiply(a: number, b: number): number {
+        return a * b;
+    }
+}
+`
+
+	filePath := createTempTSFile(t, code, ".ts")
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	chunks, err := c.Chunk(context.Background(), filePath)
+	require.NoError(t, err)
+	require.NotEmpty(t, chunks)
+
+	// Should find the Calculator class and its methods
+	var foundClass, foundAdd, foundMultiply bool
+	for _, chunk := range chunks {
+		switch chunk.Name {
+		case "Calculator":
+			foundClass = true
+			assert.Equal(t, chunking.ChunkTypeClass, chunk.Type)
+		case "add":
+			foundAdd = true
+			assert.Equal(t, chunking.ChunkTypeMethod, chunk.Type)
+			assert.Equal(t, "Calculator", chunk.ParentName)
+		case "multiply":
+			foundMultiply = true
+			assert.Equal(t, chunking.ChunkTypeMethod, chunk.Type)
+			assert.Equal(t, "Calculator", chunk.ParentName)
+		}
+	}
+
+	assert.True(t, foundClass, "Should find 'Calculator' class")
+	assert.True(t, foundAdd, "Should find 'add' method")
+	assert.True(t, foundMultiply, "Should find 'multiply' method")
+}
+
+func TestChunker_Chunk_Interface(t *testing.T) {
+	t.Parallel()
+
+	code := `interface User {
+    id: number;
+    name: string;
+    email: string;
+}
+
+interface Authenticator {
+    login(username: string, password: string): boolean;
+    logout(): void;
+}
+`
+
+	filePath := createTempTSFile(t, code, ".ts")
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	chunks, err := c.Chunk(context.Background(), filePath)
+	require.NoError(t, err)
+	require.NotEmpty(t, chunks)
+
+	// Should find interfaces
+	interfaceNames := make(map[string]bool)
+	for _, chunk := range chunks {
+		if chunk.Type == chunking.ChunkTypeInterface {
+			interfaceNames[chunk.Name] = true
+		}
+	}
+
+	assert.True(t, interfaceNames["User"])
+	assert.True(t, interfaceNames["Authenticator"])
+}
+
+func TestChunker_Chunk_TypeAlias(t *testing.T) {
+	t.Parallel()
+
+	code := `type UserID = string;
+
+type Handler = (event: Event) => void;
+
+type Result<T> = { success: true; data: T } | { success: false; error: Error };
+`
+
+	filePath := createTempTSFile(t, code, ".ts")
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	chunks, err := c.Chunk(context.Background(), filePath)
+	require.NoError(t, err)
+	require.NotEmpty(t, chunks)
+
+	// Should find type aliases
+	typeNames := make(map[string]bool)
+	for _, chunk := range chunks {
+		if chunk.Type == chunking.ChunkTypeType {
+			typeNames[chunk.Name] = true
+		}
+	}
+
+	assert.True(t, typeNames["UserID"])
+	assert.True(t, typeNames["Handler"])
+	assert.True(t, typeNames["Result"])
+}
+
+func TestChunker_Chunk_ArrowFunction(t *testing.T) {
+	t.Parallel()
+
+	code := `const add = (a: number, b: number): number => a + b;
+
+const greet = (name: string): string => {
+    return "Hello, " + name;
+};
+`
+
+	filePath := createTempTSFile(t, code, ".ts")
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	_, err := c.Chunk(context.Background(), filePath)
+	require.NoError(t, err)
+	// Arrow functions may or may not be captured depending on AST structure
+	// At minimum, no error should occur
+}
+
+func TestChunker_Chunk_FileNotFound(t *testing.T) {
+	t.Parallel()
+
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	_, err := c.Chunk(context.Background(), "/nonexistent/path/file.ts")
+	require.Error(t, err)
+	assert.Contains(t, err.Error(), "read file")
+}
+
+func TestChunker_Chunk_EmptyFile(t *testing.T) {
+	t.Parallel()
+
+	filePath := createTempTSFile(t, "", ".ts")
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	chunks, err := c.Chunk(context.Background(), filePath)
+	require.NoError(t, err)
+	assert.Empty(t, chunks)
+}
+
+func TestChunker_Chunk_OnlyComments(t *testing.T) {
+	t.Parallel()
+
+	code := `// This is a comment
+/* Another comment */
+/**
+ * JSDoc comment
+ */
+`
+
+	filePath := createTempTSFile(t, code, ".ts")
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	chunks, err := c.Chunk(context.Background(), filePath)
+	require.NoError(t, err)
+	// Comments without code should not produce chunks
+	assert.Empty(t, chunks)
+}
+
+func TestChunker_Chunk_AsyncFunction(t *testing.T) {
+	t.Parallel()
+
+	code := `async function fetchData(url: string): Promise<any> {
+    const response = await fetch(url);
+    return response.json();
+}
+
+async function processItems(items: string[]): Promise<void> {
+    for (const item of items) {
+        await process(item);
+    }
+}
+`
+
+	filePath := createTempTSFile(t, code, ".ts")
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	chunks, err := c.Chunk(context.Background(), filePath)
+	require.NoError(t, err)
+	require.NotEmpty(t, chunks)
+
+	// Should find async functions
+	functionNames := make(map[string]bool)
+	for _, chunk := range chunks {
+		if chunk.Type == chunking.ChunkTypeFunction {
+			functionNames[chunk.Name] = true
+		}
+	}
+
+	assert.True(t, functionNames["fetchData"])
+	assert.True(t, functionNames["processItems"])
+}
+
+func TestChunker_Chunk_ExportedFunction(t *testing.T) {
+	t.Parallel()
+
+	code := `export function publicFunction(): void {
+    console.log("public");
+}
+
+export default function defaultExport(): void {
+    console.log("default");
+}
+`
+
+	filePath := createTempTSFile(t, code, ".ts")
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	chunks, err := c.Chunk(context.Background(), filePath)
+	require.NoError(t, err)
+	require.NotEmpty(t, chunks)
+
+	// Should find exported functions
+	functionNames := make(map[string]bool)
+	for _, chunk := range chunks {
+		if chunk.Type == chunking.ChunkTypeFunction {
+			functionNames[chunk.Name] = true
+		}
+	}
+
+	assert.True(t, functionNames["publicFunction"])
+	assert.True(t, functionNames["defaultExport"])
+}
+
+func TestChunker_Chunk_JSXFile(t *testing.T) {
+	t.Parallel()
+
+	code := `function Button({ label }: { label: string }) {
+    return <button>{label}</button>;
+}
+
+function App() {
+    return (
+        <div>
+            <Button label="Click me" />
+        </div>
+    );
+}
+`
+
+	filePath := createTempTSFile(t, code, ".tsx")
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	chunks, err := c.Chunk(context.Background(), filePath)
+	require.NoError(t, err)
+	require.NotEmpty(t, chunks)
+
+	// Should find JSX components as functions
+	functionNames := make(map[string]bool)
+	for _, chunk := range chunks {
+		if chunk.Type == chunking.ChunkTypeFunction {
+			functionNames[chunk.Name] = true
+		}
+	}
+
+	assert.True(t, functionNames["Button"])
+	assert.True(t, functionNames["App"])
+}
+
+func TestChunker_Chunk_JavaScript(t *testing.T) {
+	t.Parallel()
+
+	code := `function simpleFunc() {
+    return 42;
+}
+
+class MyClass {
+    constructor() {
+        this.value = 0;
+    }
+
+    getValue() {
+        return this.value;
+    }
+}
+`
+
+	filePath := createTempTSFile(t, code, ".js")
+	c := NewChunker(chunking.DefaultChunkOptions())
+
+	chunks, err := c.Chunk(context.Background(), filePath)
+	require.NoError(t, err)
+	require.NotEmpty(t, chunks)
+
+	// Should find JavaScript functions and classes
+	var foundFunc, foundClass bool
+	for _, chunk := range chunks {
+		if chunk.Name == "simpleFunc" {
+			foundFunc = true
+		}
+		if chunk.Name == "MyClass" {
+			foundClass = true
+		}
+	}
+
+	assert.True(t, foundFunc, "Should find 'simpleFunc' function")
+	assert.True(t, foundClass, "Should find 'MyClass' class")
+}

internal/pattern/detector_test.go

@@ -328,6 +328,26 @@ func TestDefaultConfig(t *testing.T) {
 	}
 }
 
+func TestDefaultConfig_AllFieldsValid(t *testing.T) {
+	config := DefaultConfig()
+
+	if config.MinMatchScore != 0.3 {
+		t.Errorf("MinMatchScore = %f, want 0.3", config.MinMatchScore)
+	}
+	if config.MinFrequencyForPattern != 2 {
+		t.Errorf("MinFrequencyForPattern = %d, want 2", config.MinFrequencyForPattern)
+	}
+	if config.AnalysisInterval != 5*time.Minute {
+		t.Errorf("AnalysisInterval = %v, want 5m", config.AnalysisInterval)
+	}
+	if config.MaxPatternsToTrack != 1000 {
+		t.Errorf("MaxPatternsToTrack = %d, want 1000", config.MaxPatternsToTrack)
+	}
+	if config.MaxCandidates != 500 {
+		t.Errorf("MaxCandidates = %d, want 500", config.MaxCandidates)
+	}
+}
+
 func TestGeneratePatternName(t *testing.T) {
 	tests := []struct {
 		patternType models.PatternType
@@ -352,6 +372,85 @@ func TestGeneratePatternName(t *testing.T) {
 	}
 }
 
+func TestGeneratePatternName_EdgeCases(t *testing.T) {
+	tests := []struct {
+		name      string
+		ptype     models.PatternType
+		title     string
+		want      string
+		signature []string
+	}{
+		{
+			name:      "with title uses title directly",
+			ptype:     models.PatternTypeBug,
+			signature: []string{"ignored"},
+			title:     "Custom Title",
+			want:      "Custom Title",
+		},
+		{
+			name:      "long title generates from signature",
+			ptype:     models.PatternTypeBug,
+			signature: []string{"sig1", "sig2"},
+			title:     "This is a very long title that exceeds sixty characters and should be ignored",
+			want:      "Bug Pattern: sig1, sig2",
+		},
+		{
+			name:      "empty signature returns Unnamed",
+			ptype:     models.PatternTypeBug,
+			signature: []string{},
+			title:     "",
+			want:      "Bug Pattern: Unnamed",
+		},
+		{
+			name:      "single signature element",
+			ptype:     models.PatternTypeRefactor,
+			signature: []string{"single"},
+			title:     "",
+			want:      "Refactor Pattern: single",
+		},
+		{
+			name:      "more than 3 signature elements truncates",
+			ptype:     models.PatternTypeBestPractice,
+			signature: []string{"a", "b", "c", "d", "e"},
+			title:     "",
+			want:      "Best Practice: a, b, c",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := generatePatternName(tt.ptype, tt.signature, tt.title)
+			if got != tt.want {
+				t.Errorf("generatePatternName() = %q, want %q", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestGeneratePatternName_AllTypes(t *testing.T) {
+	tests := []struct {
+		ptype      models.PatternType
+		wantPrefix string
+	}{
+		{models.PatternTypeBug, "Bug Pattern:"},
+		{models.PatternTypeRefactor, "Refactor Pattern:"},
+		{models.PatternTypeArchitecture, "Architecture Pattern:"},
+		{models.PatternTypeAntiPattern, "Anti-Pattern:"},
+		{models.PatternTypeBestPractice, "Best Practice:"},
+		{models.PatternType("unknown"), "test"}, // Unknown type has empty prefix, starts with first signature element
+	}
+
+	for _, tt := range tests {
+		t.Run(string(tt.ptype), func(t *testing.T) {
+			name := generatePatternName(tt.ptype, []string{"test", "sig"}, "")
+			if !hasPrefix(name, tt.wantPrefix) {
+				t.Errorf("Expected prefix %q for type %s, got: %s",
+					tt.wantPrefix, tt.ptype, name)
+			}
+		})
+	}
+}
+
 func TestFormatPatternInsight(t *testing.T) {
 	// Pattern without recommendation
 	pattern1 := &models.Pattern{
@@ -386,6 +485,470 @@ func TestFormatPatternInsight(t *testing.T) {
 	}
 }
 
+func TestFormatPatternInsight_AllTypes(t *testing.T) {
+	types := []struct {
+		ptype    models.PatternType
+		contains string
+	}{
+		{models.PatternTypeBug, "bug pattern"},
+		{models.PatternTypeRefactor, "recognized pattern"},     // Falls to default case
+		{models.PatternTypeArchitecture, "recognized pattern"}, // Falls to default case
+		{models.PatternTypeAntiPattern, "anti-pattern"},
+		{models.PatternTypeBestPractice, "best practice"},
+		{models.PatternType("unknown"), "recognized pattern"}, // Falls to default case
+	}
+
+	for _, tt := range types {
+		t.Run(string(tt.ptype), func(t *testing.T) {
+			pattern := &models.Pattern{
+				Type:      tt.ptype,
+				Frequency: 3,
+				Projects:  []string{"proj1"},
+			}
+			insight := formatPatternInsight(pattern)
+			if !containsString(insight, tt.contains) {
+				t.Errorf("Expected insight to contain %q for type %s, got: %s",
+					tt.contains, tt.ptype, insight)
+			}
+		})
+	}
+}
+
+func TestFormatPatternInsight_MultiProject(t *testing.T) {
+	pattern := &models.Pattern{
+		Type:      models.PatternTypeBug,
+		Frequency: 10,
+		Projects:  []string{"proj1", "proj2", "proj3"},
+	}
+
+	insight := formatPatternInsight(pattern)
+
+	if !containsString(insight, "10 times") {
+		t.Error("Expected frequency in insight")
+	}
+	if !containsString(insight, "3 projects") {
+		t.Error("Expected project count in insight")
+	}
+}
+
+func TestFormatPatternInsight_SingleProject(t *testing.T) {
+	pattern := &models.Pattern{
+		Type:      models.PatternTypeBestPractice,
+		Frequency: 5,
+		Projects:  []string{"only-one"},
+	}
+
+	insight := formatPatternInsight(pattern)
+
+	if !containsString(insight, "5 times") {
+		t.Error("Expected frequency in insight")
+	}
+	// Single project should NOT mention "projects"
+	if containsString(insight, "projects") {
+		t.Error("Single project should not mention 'projects'")
+	}
+}
+
+func TestDetector_SetSyncFunc(t *testing.T) {
+	store := setupTestStore(t)
+	defer store.Close()
+
+	patternStore := gorm.NewPatternStore(store)
+	observationStore := gorm.NewObservationStore(store, nil, nil, nil)
+	config := DefaultConfig()
+
+	detector := NewDetector(patternStore, observationStore, config)
+
+	// Initially nil
+	if detector.syncFunc != nil {
+		t.Error("Expected syncFunc to be nil initially")
+	}
+
+	// Set sync func
+	var syncCalled bool
+	detector.SetSyncFunc(func(p *models.Pattern) {
+		syncCalled = true
+	})
+
+	if detector.syncFunc == nil {
+		t.Error("Expected syncFunc to be set")
+	}
+
+	// Verify it can be called
+	detector.syncFunc(&models.Pattern{})
+	if !syncCalled {
+		t.Error("Expected sync function to be called")
+	}
+}
+
+func TestDetector_CandidateCount(t *testing.T) {
+	store := setupTestStore(t)
+	defer store.Close()
+
+	patternStore := gorm.NewPatternStore(store)
+	observationStore := gorm.NewObservationStore(store, nil, nil, nil)
+	config := DefaultConfig()
+
+	detector := NewDetector(patternStore, observationStore, config)
+
+	// Initially zero
+	if count := detector.CandidateCount(); count != 0 {
+		t.Errorf("Expected 0 candidates, got %d", count)
+	}
+
+	// Add some candidates
+	detector.candidates["key1"] = &candidatePattern{}
+	detector.candidates["key2"] = &candidatePattern{}
+
+	if count := detector.CandidateCount(); count != 2 {
+		t.Errorf("Expected 2 candidates, got %d", count)
+	}
+}
+
+func TestDetector_AnalyzeRecentObservations(t *testing.T) {
+	store := setupTestStore(t)
+	defer store.Close()
+
+	patternStore := gorm.NewPatternStore(store)
+	observationStore := gorm.NewObservationStore(store, nil, nil, nil)
+	config := DefaultConfig()
+
+	detector := NewDetector(patternStore, observationStore, config)
+	ctx := context.Background()
+
+	// Should not error even with no observations
+	err := detector.AnalyzeRecentObservations(ctx)
+	if err != nil {
+		t.Fatalf("AnalyzeRecentObservations() error = %v", err)
+	}
+}
+
+func TestGenerateCandidateKey(t *testing.T) {
+	tests := []struct {
+		name      string
+		want      string
+		signature []string
+	}{
+		{
+			name:      "single element",
+			signature: []string{"error"},
+			want:      "error|",
+		},
+		{
+			name:      "multiple elements",
+			signature: []string{"error", "handling", "nil"},
+			want:      "error|handling|nil|",
+		},
+		{
+			name:      "empty signature",
+			signature: []string{},
+			want:      "",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := generateCandidateKey(tt.signature)
+			if got != tt.want {
+				t.Errorf("generateCandidateKey() = %q, want %q", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestGenerateCandidateKey_EdgeCases(t *testing.T) {
+	tests := []struct {
+		name      string
+		want      string
+		signature []string
+	}{
+		{
+			name:      "nil signature",
+			signature: nil,
+			want:      "",
+		},
+		{
+			name:      "empty strings in signature",
+			signature: []string{"", ""},
+			want:      "||",
+		},
+		{
+			name:      "special characters",
+			signature: []string{"error|handling", "nil"},
+			want:      "error|handling|nil|",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := generateCandidateKey(tt.signature)
+			if got != tt.want {
+				t.Errorf("generateCandidateKey() = %q, want %q", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestItoa(t *testing.T) {
+	tests := []struct {
+		want  string
+		input int
+	}{
+		{"0", 0},
+		{"1", 1},
+		{"10", 10},
+		{"123", 123},
+		{"-1", -1},
+		{"-123", -123},
+		{"1000000", 1000000},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.want, func(t *testing.T) {
+			got := itoa(tt.input)
+			if got != tt.want {
+				t.Errorf("itoa(%d) = %q, want %q", tt.input, got, tt.want)
+			}
+		})
+	}
+}
+
+func TestItoa_EdgeCases(t *testing.T) {
+	tests := []struct {
+		want  string
+		input int
+	}{
+		{"0", 0},
+		{"0", -0},
+		{"1", 1},
+		{"-1", -1},
+		{"9", 9},
+		{"10", 10},
+		{"99", 99},
+		{"100", 100},
+		{"999", 999},
+		{"1000", 1000},
+		{"-999", -999},
+		{"-1000", -1000},
+		{"2147483647", 2147483647},   // Max int32
+		{"-2147483647", -2147483647}, // Min int32 + 1
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.want, func(t *testing.T) {
+			got := itoa(tt.input)
+			if got != tt.want {
+				t.Errorf("itoa(%d) = %q, want %q", tt.input, got, tt.want)
+			}
+		})
+	}
+}
+
+func TestDetectionResult_ZeroValue(t *testing.T) {
+	result := &DetectionResult{}
+
+	if result.MatchedPattern != nil {
+		t.Error("Zero value should have nil MatchedPattern")
+	}
+	if result.MatchScore != 0 {
+		t.Error("Zero value should have 0 MatchScore")
+	}
+	if result.IsNewPattern {
+		t.Error("Zero value should have false IsNewPattern")
+	}
+}
+
+func TestCandidatePattern_Fields(t *testing.T) {
+	candidate := &candidatePattern{
+		patternType:    models.PatternTypeBug,
+		title:          "Test Title",
+		signature:      []string{"sig1", "sig2"},
+		observationIDs: []int64{1, 2, 3},
+		projects:       []string{"proj1", "proj2"},
+		lastSeenEpoch:  time.Now().UnixMilli(),
+	}
+
+	if candidate.patternType != models.PatternTypeBug {
+		t.Error("Wrong pattern type")
+	}
+	if candidate.title != "Test Title" {
+		t.Error("Wrong title")
+	}
+	if len(candidate.signature) != 2 {
+		t.Error("Wrong signature length")
+	}
+	if len(candidate.observationIDs) != 3 {
+		t.Error("Wrong observationIDs length")
+	}
+	if len(candidate.projects) != 2 {
+		t.Error("Wrong projects length")
+	}
+}
+
+func TestDetector_AnalyzeObservation_EmptySignature(t *testing.T) {
+	store := setupTestStore(t)
+	defer store.Close()
+
+	patternStore := gorm.NewPatternStore(store)
+	observationStore := gorm.NewObservationStore(store, nil, nil, nil)
+	config := DefaultConfig()
+
+	detector := NewDetector(patternStore, observationStore, config)
+	ctx := context.Background()
+
+	// Create observation with empty concepts/title/narrative
+	obs := &models.Observation{
+		ID:           1,
+		SDKSessionID: "test-session",
+		Project:      "test-project",
+		Scope:        models.ScopeProject,
+		Type:         models.ObsTypeBugfix,
+		// All fields that would create signature are empty
+	}
+
+	result, err := detector.AnalyzeObservation(ctx, obs)
+	if err != nil {
+		t.Fatalf("AnalyzeObservation() error = %v", err)
+	}
+
+	// Should return empty result for empty signature
+	if result.MatchedPattern != nil {
+		t.Error("Expected nil pattern for empty signature")
+	}
+}
+
+func TestDetector_AnalyzeObservation_CandidateEviction(t *testing.T) {
+	store := setupTestStore(t)
+	defer store.Close()
+
+	patternStore := gorm.NewPatternStore(store)
+	observationStore := gorm.NewObservationStore(store, nil, nil, nil)
+	config := DefaultConfig()
+	config.MaxCandidates = 2           // Very small for testing
+	config.MinFrequencyForPattern = 10 // High so nothing gets promoted
+
+	detector := NewDetector(patternStore, observationStore, config)
+	ctx := context.Background()
+
+	// Add observations with different signatures until we exceed MaxCandidates
+	obs1 := createTestObservation(1, "First", []string{"first", "unique"})
+	obs2 := createTestObservation(2, "Second", []string{"second", "unique"})
+	obs3 := createTestObservation(3, "Third", []string{"third", "unique"})
+
+	// Analyze all observations
+	_, _ = detector.AnalyzeObservation(ctx, obs1)
+	time.Sleep(10 * time.Millisecond) // Small delay so timestamps differ
+	_, _ = detector.AnalyzeObservation(ctx, obs2)
+	time.Sleep(10 * time.Millisecond)
+	_, _ = detector.AnalyzeObservation(ctx, obs3)
+
+	// Should have at most MaxCandidates
+	if count := detector.CandidateCount(); count > config.MaxCandidates {
+		t.Errorf("Expected at most %d candidates, got %d", config.MaxCandidates, count)
+	}
+}
+
+func TestDetector_PromoteCandidateWithSyncFunc(t *testing.T) {
+	store := setupTestStore(t)
+	defer store.Close()
+
+	patternStore := gorm.NewPatternStore(store)
+	observationStore := gorm.NewObservationStore(store, nil, nil, nil)
+	config := DefaultConfig()
+	config.MinFrequencyForPattern = 2
+
+	detector := NewDetector(patternStore, observationStore, config)
+	ctx := context.Background()
+
+	// Set up sync function to track calls
+	var syncedPattern *models.Pattern
+	detector.SetSyncFunc(func(p *models.Pattern) {
+		syncedPattern = p
+	})
+
+	// Create two similar observations to trigger pattern promotion
+	obs1 := createTestObservation(1, "Sync Test", []string{"sync", "test"})
+	obs2 := createTestObservation(2, "Sync Test", []string{"sync", "test"})
+
+	_, _ = detector.AnalyzeObservation(ctx, obs1)
+	result, _ := detector.AnalyzeObservation(ctx, obs2)
+
+	if result.MatchedPattern == nil {
+		t.Fatal("Expected pattern to be created")
+	}
+
+	if syncedPattern == nil {
+		t.Error("Expected sync function to be called")
+	}
+
+	if syncedPattern != nil && syncedPattern.Name != result.MatchedPattern.Name {
+		t.Errorf("Synced pattern name mismatch: got %s, want %s",
+			syncedPattern.Name, result.MatchedPattern.Name)
+	}
+}
+
+func TestDetector_AnalyzeObservation_UpdateExistingCandidate(t *testing.T) {
+	store := setupTestStore(t)
+	defer store.Close()
+
+	patternStore := gorm.NewPatternStore(store)
+	observationStore := gorm.NewObservationStore(store, nil, nil, nil)
+	config := DefaultConfig()
+	config.MinFrequencyForPattern = 5 // High enough that we don't promote
+
+	detector := NewDetector(patternStore, observationStore, config)
+	ctx := context.Background()
+
+	// Create observations with same signature
+	obs1 := createTestObservation(1, "Update Test", []string{"update", "test"})
+	obs2 := createTestObservation(2, "Update Test", []string{"update", "test"})
+	obs2.Project = "different-project"
+
+	// Analyze first observation
+	_, _ = detector.AnalyzeObservation(ctx, obs1)
+
+	// Check candidate count
+	if count := detector.CandidateCount(); count != 1 {
+		t.Errorf("Expected 1 candidate after first obs, got %d", count)
+	}
+
+	// Analyze second observation
+	_, _ = detector.AnalyzeObservation(ctx, obs2)
+
+	// Still 1 candidate (same signature)
+	if count := detector.CandidateCount(); count != 1 {
+		t.Errorf("Expected 1 candidate after second obs, got %d", count)
+	}
+
+	// Check that candidate has both projects
+	key := generateCandidateKey([]string{"update", "test"})
+	candidate := detector.candidates[key]
+	if candidate == nil {
+		t.Fatal("Expected candidate to exist")
+	}
+	if len(candidate.projects) != 2 {
+		t.Errorf("Expected 2 projects, got %d", len(candidate.projects))
+	}
+}
+
+func TestDetector_GetPatternInsight_NotFound(t *testing.T) {
+	store := setupTestStore(t)
+	defer store.Close()
+
+	patternStore := gorm.NewPatternStore(store)
+	observationStore := gorm.NewObservationStore(store, nil, nil, nil)
+	config := DefaultConfig()
+
+	detector := NewDetector(patternStore, observationStore, config)
+	ctx := context.Background()
+
+	// Try to get insight for non-existent pattern
+	_, err := detector.GetPatternInsight(ctx, 99999)
+	if err == nil {
+		t.Error("Expected error for non-existent pattern")
+	}
+}
+
 // Helper functions
 
 func setupTestStore(t *testing.T) *gorm.Store {

internal/worker/sdk/processor_test.go

@@ -1,9 +1,12 @@
 package sdk
 
 import (
+	"context"
 	"os"
 	"path/filepath"
+	"sync"
 	"testing"
+	"time"
 
 	"github.com/lukaszraczylo/claude-mnemonic/pkg/models"
 	"github.com/stretchr/testify/assert"
@@ -1178,3 +1181,663 @@ func TestSafeResolvePath(t *testing.T) {
 		})
 	}
 }
+
+// =============================================================================
+// TESTS FOR CircuitBreaker
+// =============================================================================
+
+func TestNewCircuitBreaker(t *testing.T) {
+	cb := NewCircuitBreaker(5, 60)
+
+	assert.NotNil(t, cb)
+	assert.Equal(t, int64(5), cb.threshold)
+	assert.Equal(t, int64(60), cb.resetTimeout)
+	assert.Equal(t, "closed", cb.State())
+}
+
+func TestCircuitBreaker_Allow_Closed(t *testing.T) {
+	cb := NewCircuitBreaker(5, 60)
+
+	// Closed state should allow requests
+	assert.True(t, cb.Allow())
+	assert.True(t, cb.Allow())
+}
+
+func TestCircuitBreaker_Allow_Open(t *testing.T) {
+	cb := NewCircuitBreaker(2, 60) // Low threshold for testing
+
+	// Record enough failures to open the circuit
+	cb.RecordFailure()
+	cb.RecordFailure()
+
+	// Open state should block requests
+	assert.False(t, cb.Allow())
+	assert.Equal(t, "open", cb.State())
+}
+
+func TestCircuitBreaker_RecordSuccess(t *testing.T) {
+	cb := NewCircuitBreaker(2, 60)
+
+	// Record a failure
+	cb.RecordFailure()
+	assert.Equal(t, int64(1), cb.Metrics().Failures)
+
+	// Record success resets failures
+	cb.RecordSuccess()
+	assert.Equal(t, int64(0), cb.Metrics().Failures)
+	assert.Equal(t, "closed", cb.State())
+}
+
+func TestCircuitBreaker_RecordFailure_OpensCircuit(t *testing.T) {
+	cb := NewCircuitBreaker(3, 60)
+
+	// Record failures below threshold
+	cb.RecordFailure()
+	assert.Equal(t, "closed", cb.State())
+
+	cb.RecordFailure()
+	assert.Equal(t, "closed", cb.State())
+
+	// Third failure should open circuit
+	cb.RecordFailure()
+	assert.Equal(t, "open", cb.State())
+}
+
+func TestCircuitBreaker_State(t *testing.T) {
+	cb := NewCircuitBreaker(1, 60)
+
+	// Initially closed
+	assert.Equal(t, "closed", cb.State())
+
+	// After failure, open
+	cb.RecordFailure()
+	assert.Equal(t, "open", cb.State())
+
+	// After success, closed
+	cb.RecordSuccess()
+	assert.Equal(t, "closed", cb.State())
+}
+
+func TestCircuitBreaker_Metrics(t *testing.T) {
+	cb := NewCircuitBreaker(5, 120)
+
+	metrics := cb.Metrics()
+	assert.Equal(t, "closed", metrics.State)
+	assert.Equal(t, int64(0), metrics.Failures)
+	assert.Equal(t, int64(5), metrics.Threshold)
+	assert.Equal(t, int64(120), metrics.ResetTimeoutSecs)
+	assert.Equal(t, int64(0), metrics.LastFailureUnix)
+
+	// After failure
+	cb.RecordFailure()
+	metrics = cb.Metrics()
+	assert.Equal(t, int64(1), metrics.Failures)
+	assert.Greater(t, metrics.LastFailureUnix, int64(0))
+}
+
+func TestCircuitBreaker_Metrics_OpenWithReset(t *testing.T) {
+	cb := NewCircuitBreaker(1, 60)
+
+	cb.RecordFailure()
+	assert.Equal(t, "open", cb.State())
+
+	metrics := cb.Metrics()
+	assert.Equal(t, "open", metrics.State)
+	assert.Greater(t, metrics.SecondsUntilReset, int64(0))
+	assert.LessOrEqual(t, metrics.SecondsUntilReset, int64(60))
+}
+
+// =============================================================================
+// TESTS FOR RequestDeduplicator
+// =============================================================================
+
+func TestNewRequestDeduplicator(t *testing.T) {
+	d := NewRequestDeduplicator(300, 1000)
+
+	assert.NotNil(t, d)
+	assert.NotNil(t, d.seen)
+	assert.Equal(t, int64(300), d.ttlSecs)
+	assert.Equal(t, 1000, d.maxSize)
+}
+
+func TestRequestDeduplicator_IsDuplicate_NotSeen(t *testing.T) {
+	d := NewRequestDeduplicator(300, 1000)
+
+	// New hash is not a duplicate
+	assert.False(t, d.IsDuplicate("newhash"))
+}
+
+func TestRequestDeduplicator_IsDuplicate_AfterRecord(t *testing.T) {
+	d := NewRequestDeduplicator(300, 1000)
+
+	hash := "testhash"
+
+	// Record the hash
+	d.Record(hash)
+
+	// Now it should be a duplicate
+	assert.True(t, d.IsDuplicate(hash))
+}
+
+func TestRequestDeduplicator_Record(t *testing.T) {
+	d := NewRequestDeduplicator(300, 1000)
+
+	hash := "recordtest"
+	d.Record(hash)
+
+	// Check it was recorded
+	d.mu.RLock()
+	_, exists := d.seen[hash]
+	d.mu.RUnlock()
+
+	assert.True(t, exists)
+}
+
+func TestRequestDeduplicator_Record_Eviction(t *testing.T) {
+	// Small maxSize for testing eviction
+	d := NewRequestDeduplicator(0, 2) // TTL of 0 means everything is "old"
+
+	// Record until capacity
+	d.Record("hash1")
+	d.Record("hash2")
+
+	// Recording a third should trigger eviction (since TTL is 0)
+	d.Record("hash3")
+
+	// Should have cleaned up old entries
+	d.mu.RLock()
+	size := len(d.seen)
+	d.mu.RUnlock()
+
+	// Size should be limited (eviction occurred)
+	assert.LessOrEqual(t, size, 3)
+}
+
+func TestHashRequest(t *testing.T) {
+	tests := []struct {
+		name        string
+		toolName    string
+		input       string
+		output      string
+		compareWith []string
+		wantLen     int
+		wantSame    bool
+	}{
+		{
+			name:     "basic hash",
+			toolName: "Read",
+			input:    "file.txt",
+			output:   "content",
+			wantLen:  16,
+		},
+		{
+			name:     "consistent hashing",
+			toolName: "Edit",
+			input:    "same input",
+			output:   "same output",
+			wantLen:  16,
+		},
+		{
+			name:     "long output truncation",
+			toolName: "Bash",
+			input:    "command",
+			output:   string(make([]byte, 5000)), // Very long output
+			wantLen:  16,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			hash := hashRequest(tt.toolName, tt.input, tt.output)
+			assert.Len(t, hash, tt.wantLen)
+
+			// Same inputs should produce same hash
+			hash2 := hashRequest(tt.toolName, tt.input, tt.output)
+			assert.Equal(t, hash, hash2)
+		})
+	}
+}
+
+func TestHashRequest_DifferentInputs(t *testing.T) {
+	// Different inputs should produce different hashes
+	hash1 := hashRequest("Read", "file1.txt", "content1")
+	hash2 := hashRequest("Read", "file2.txt", "content2")
+
+	assert.NotEqual(t, hash1, hash2)
+}
+
+func TestHashRequest_OutputTruncation(t *testing.T) {
+	// Hash should be the same for outputs that differ only after 1000 chars
+	longOutput1 := string(make([]byte, 1500))
+	longOutput2 := longOutput1[:1000] + "different suffix here"
+
+	hash1 := hashRequest("Read", "input", longOutput1)
+	hash2 := hashRequest("Read", "input", longOutput2)
+
+	// Since we only hash first 1000 chars, these should be the same
+	assert.Equal(t, hash1, hash2)
+}
+
+// =============================================================================
+// TESTS FOR Processor methods
+// =============================================================================
+
+func TestProcessor_CircuitBreakerState(t *testing.T) {
+	p := &Processor{
+		circuitBreaker: NewCircuitBreaker(2, 60),
+	}
+
+	// Initially closed
+	assert.Equal(t, "closed", p.CircuitBreakerState())
+
+	// After enough failures, open
+	p.circuitBreaker.RecordFailure()
+	p.circuitBreaker.RecordFailure()
+	assert.Equal(t, "open", p.CircuitBreakerState())
+
+	// After success, closed
+	p.circuitBreaker.RecordSuccess()
+	assert.Equal(t, "closed", p.CircuitBreakerState())
+}
+
+func TestProcessor_CircuitBreakerMetrics(t *testing.T) {
+	p := &Processor{
+		circuitBreaker: NewCircuitBreaker(5, 120),
+	}
+
+	metrics := p.CircuitBreakerMetrics()
+	assert.Equal(t, "closed", metrics.State)
+	assert.Equal(t, int64(0), metrics.Failures)
+	assert.Equal(t, int64(5), metrics.Threshold)
+	assert.Equal(t, int64(120), metrics.ResetTimeoutSecs)
+
+	// Record a failure and check metrics update
+	p.circuitBreaker.RecordFailure()
+	metrics = p.CircuitBreakerMetrics()
+	assert.Equal(t, int64(1), metrics.Failures)
+	assert.Greater(t, metrics.LastFailureUnix, int64(0))
+}
+
+// =============================================================================
+// TESTS FOR Vector Sync Workers
+// =============================================================================
+
+func TestProcessor_StartAndStopVectorSyncWorkers(t *testing.T) {
+	var syncedObservations []*models.Observation
+	var mu sync.Mutex
+
+	p := &Processor{
+		vectorSyncChan: make(chan *models.Observation, MaxVectorSyncWorkers*2),
+		vectorSyncDone: make(chan struct{}),
+		syncObservationFunc: func(obs *models.Observation) {
+			mu.Lock()
+			syncedObservations = append(syncedObservations, obs)
+			mu.Unlock()
+		},
+	}
+
+	// Start workers
+	p.StartVectorSyncWorkers()
+
+	// Send some observations
+	obs1 := &models.Observation{SDKSessionID: "test1"}
+	obs2 := &models.Observation{SDKSessionID: "test2"}
+	p.vectorSyncChan <- obs1
+	p.vectorSyncChan <- obs2
+
+	// Give workers time to process
+	time.Sleep(50 * time.Millisecond)
+
+	// Stop workers
+	p.StopVectorSyncWorkers()
+
+	// Verify observations were synced
+	mu.Lock()
+	assert.Len(t, syncedObservations, 2)
+	mu.Unlock()
+}
+
+func TestProcessor_VectorSyncWorker_DrainOnShutdown(t *testing.T) {
+	var syncedCount int
+	var mu sync.Mutex
+
+	p := &Processor{
+		vectorSyncChan: make(chan *models.Observation, 10),
+		vectorSyncDone: make(chan struct{}),
+		syncObservationFunc: func(obs *models.Observation) {
+			mu.Lock()
+			syncedCount++
+			mu.Unlock()
+		},
+	}
+
+	// Queue observations before starting workers
+	for i := 0; i < 5; i++ {
+		p.vectorSyncChan <- &models.Observation{SDKSessionID: "pre-queued"}
+	}
+
+	// Start workers
+	p.StartVectorSyncWorkers()
+
+	// Stop immediately - workers should drain the queue
+	p.StopVectorSyncWorkers()
+
+	// All pre-queued items should have been processed
+	mu.Lock()
+	assert.Equal(t, 5, syncedCount)
+	mu.Unlock()
+}
+
+func TestProcessor_VectorSyncWorker_NilSyncFunc(t *testing.T) {
+	p := &Processor{
+		vectorSyncChan:      make(chan *models.Observation, 10),
+		vectorSyncDone:      make(chan struct{}),
+		syncObservationFunc: nil, // No sync function set
+	}
+
+	// Start workers
+	p.StartVectorSyncWorkers()
+
+	// Send observation - should not panic even with nil sync func
+	p.vectorSyncChan <- &models.Observation{SDKSessionID: "test"}
+
+	// Give it time to process
+	time.Sleep(50 * time.Millisecond)
+
+	// Stop workers - should not panic
+	p.StopVectorSyncWorkers()
+}
+
+// =============================================================================
+// TESTS FOR CircuitBreaker Additional Behaviors
+// =============================================================================
+
+func TestCircuitBreaker_Allow_OpenBlocksRequests(t *testing.T) {
+	cb := NewCircuitBreaker(1, 60)
+
+	// Open the circuit
+	cb.RecordFailure()
+	assert.Equal(t, "open", cb.State())
+
+	// All requests should be blocked
+	assert.False(t, cb.Allow())
+	assert.False(t, cb.Allow())
+	assert.False(t, cb.Allow())
+}
+
+func TestCircuitBreaker_MultipleFailures(t *testing.T) {
+	cb := NewCircuitBreaker(3, 60) // Higher threshold
+
+	// Record failures below threshold
+	cb.RecordFailure()
+	assert.Equal(t, "closed", cb.State())
+	assert.Equal(t, int64(1), cb.Metrics().Failures)
+
+	cb.RecordFailure()
+	assert.Equal(t, "closed", cb.State())
+	assert.Equal(t, int64(2), cb.Metrics().Failures)
+
+	// Third failure opens circuit
+	cb.RecordFailure()
+	assert.Equal(t, "open", cb.State())
+	assert.Equal(t, int64(3), cb.Metrics().Failures)
+}
+
+func TestCircuitBreaker_SuccessResetsFailures(t *testing.T) {
+	cb := NewCircuitBreaker(5, 60)
+
+	// Record some failures
+	cb.RecordFailure()
+	cb.RecordFailure()
+	assert.Equal(t, int64(2), cb.Metrics().Failures)
+
+	// Success resets failures
+	cb.RecordSuccess()
+	assert.Equal(t, int64(0), cb.Metrics().Failures)
+	assert.Equal(t, "closed", cb.State())
+}
+
+func TestCircuitBreaker_Metrics_Comprehensive(t *testing.T) {
+	cb := NewCircuitBreaker(5, 120)
+
+	// Initial state
+	metrics := cb.Metrics()
+	assert.Equal(t, "closed", metrics.State)
+	assert.Equal(t, int64(0), metrics.Failures)
+	assert.Equal(t, int64(5), metrics.Threshold)
+	assert.Equal(t, int64(120), metrics.ResetTimeoutSecs)
+	assert.Equal(t, int64(0), metrics.LastFailureUnix)
+	assert.Equal(t, int64(0), metrics.SecondsUntilReset)
+
+	// After failures that open circuit
+	for i := 0; i < 5; i++ {
+		cb.RecordFailure()
+	}
+	metrics = cb.Metrics()
+	assert.Equal(t, "open", metrics.State)
+	assert.Equal(t, int64(5), metrics.Failures)
+	assert.Greater(t, metrics.LastFailureUnix, int64(0))
+	assert.Greater(t, metrics.SecondsUntilReset, int64(0))
+}
+
+// =============================================================================
+// TESTS FOR MaxVectorSyncWorkers constant
+// =============================================================================
+
+func TestMaxVectorSyncWorkers(t *testing.T) {
+	assert.Equal(t, 8, MaxVectorSyncWorkers)
+}
+
+// =============================================================================
+// ADDITIONAL EDGE CASE TESTS
+// =============================================================================
+
+func TestRequestDeduplicator_IsDuplicate_ExpiredEntry(t *testing.T) {
+	if testing.Short() {
+		t.Skip("Skipping time-dependent test in short mode")
+	}
+	// Use a 1-second TTL with enough margin
+	d := NewRequestDeduplicator(1, 100)
+
+	hash := "expiretest"
+	d.Record(hash)
+
+	// Initially duplicate
+	assert.True(t, d.IsDuplicate(hash))
+
+	// Wait for TTL to expire (2.5 seconds to ensure crossing second boundaries)
+	time.Sleep(2500 * time.Millisecond)
+
+	// Should no longer be considered duplicate
+	assert.False(t, d.IsDuplicate(hash))
+}
+
+// =============================================================================
+// TESTS FOR ProcessObservation Early Returns
+// =============================================================================
+
+func TestProcessObservation_SkipTool(t *testing.T) {
+	p := &Processor{
+		circuitBreaker: NewCircuitBreaker(5, 60),
+		deduplicator:   NewRequestDeduplicator(300, 1000),
+	}
+
+	ctx := context.Background()
+
+	// TodoWrite should be skipped
+	err := p.ProcessObservation(ctx, "session-1", "project-1", "TodoWrite",
+		map[string]string{"content": "test"}, "success", 1, "/test/cwd")
+	assert.NoError(t, err)
+
+	// Glob should be skipped
+	err = p.ProcessObservation(ctx, "session-1", "project-1", "Glob",
+		map[string]string{"pattern": "*.go"}, []string{"main.go", "test.go"}, 1, "/test/cwd")
+	assert.NoError(t, err)
+
+	// AskUserQuestion should be skipped
+	err = p.ProcessObservation(ctx, "session-1", "project-1", "AskUserQuestion",
+		"question", "answer", 1, "/test/cwd")
+	assert.NoError(t, err)
+}
+
+func TestProcessObservation_SkipTrivial(t *testing.T) {
+	p := &Processor{
+		circuitBreaker: NewCircuitBreaker(5, 60),
+		deduplicator:   NewRequestDeduplicator(300, 1000),
+	}
+
+	ctx := context.Background()
+
+	// Short output should be skipped
+	err := p.ProcessObservation(ctx, "session-1", "project-1", "Read",
+		map[string]string{"file_path": "/test.go"}, "short", 1, "/test/cwd")
+	assert.NoError(t, err)
+
+	// "No matches found" should be skipped
+	err = p.ProcessObservation(ctx, "session-1", "project-1", "Grep",
+		map[string]string{"pattern": "test"}, "No matches found in the repository", 1, "/test/cwd")
+	assert.NoError(t, err)
+}
+
+func TestProcessObservation_SkipDuplicate(t *testing.T) {
+	p := &Processor{
+		circuitBreaker: NewCircuitBreaker(5, 60),
+		deduplicator:   NewRequestDeduplicator(300, 1000),
+		sem:            make(chan struct{}, 4),
+		claudePath:     "/nonexistent/path", // Will fail at CLI call stage
+	}
+
+	ctx := context.Background()
+
+	// Valid input that would be processed
+	input := map[string]string{"file_path": "/project/main.go"}
+	output := "package main\n\nimport \"fmt\"\n\nfunc main() {\n\tfmt.Println(\"Hello World\")\n}"
+
+	// First call should try to process (will fail because claudePath doesn't exist)
+	err := p.ProcessObservation(ctx, "session-1", "project-1", "Read", input, output, 1, "/test/cwd")
+	// Expect error because claudePath doesn't exist
+	assert.Error(t, err)
+
+	// Second call with same input should be skipped as duplicate
+	err = p.ProcessObservation(ctx, "session-1", "project-1", "Read", input, output, 1, "/test/cwd")
+	assert.NoError(t, err) // No error because it was skipped as duplicate
+}
+
+func TestProcessObservation_CircuitBreakerOpen(t *testing.T) {
+	cb := NewCircuitBreaker(1, 60) // Threshold of 1
+	cb.RecordFailure()             // Open the circuit breaker
+
+	p := &Processor{
+		circuitBreaker: cb,
+		deduplicator:   NewRequestDeduplicator(300, 1000),
+	}
+
+	ctx := context.Background()
+
+	// Valid input that would be processed
+	input := map[string]string{"file_path": "/project/main.go"}
+	output := "package main\n\nimport \"fmt\"\n\nfunc main() {\n\tfmt.Println(\"Hello World\")\n}"
+
+	err := p.ProcessObservation(ctx, "session-1", "project-1", "Read", input, output, 1, "/test/cwd")
+	assert.Error(t, err)
+	assert.Contains(t, err.Error(), "circuit breaker open")
+}
+
+func TestProcessObservation_ContextCancel(t *testing.T) {
+	p := &Processor{
+		circuitBreaker: NewCircuitBreaker(5, 60),
+		deduplicator:   NewRequestDeduplicator(300, 1000),
+		sem:            make(chan struct{}, 1), // Small semaphore
+		claudePath:     "/fake/claude",
+	}
+
+	// Fill the semaphore
+	p.sem <- struct{}{}
+
+	// Create a cancelled context
+	ctx, cancel := context.WithCancel(context.Background())
+	cancel() // Cancel immediately
+
+	// Valid input that would be processed
+	input := map[string]string{"file_path": "/project/main.go"}
+	output := "package main\n\nimport \"fmt\"\n\nfunc main() {\n\tfmt.Println(\"Hello World\")\n}"
+
+	err := p.ProcessObservation(ctx, "session-1", "project-1", "Read", input, output, 1, "/test/cwd")
+	assert.Error(t, err)
+	assert.ErrorIs(t, err, context.Canceled)
+}
+
+// =============================================================================
+// TESTS FOR ProcessSummary Early Returns
+// =============================================================================
+
+func TestProcessSummary_SkipEmptyRequest(t *testing.T) {
+	p := &Processor{
+		circuitBreaker: NewCircuitBreaker(5, 60),
+		deduplicator:   NewRequestDeduplicator(300, 1000),
+	}
+
+	ctx := context.Background()
+
+	// Empty request should be skipped (sessionDBID, sdkSessionID, project, userPrompt, lastUserMsg, lastAssistantMsg)
+	err := p.ProcessSummary(ctx, 1, "session-1", "project-1", "", "", "")
+	assert.NoError(t, err)
+}
+
+func TestProcessSummary_CircuitBreakerOpen(t *testing.T) {
+	cb := NewCircuitBreaker(1, 60)
+	cb.RecordFailure() // Open the circuit breaker
+
+	p := &Processor{
+		circuitBreaker: cb,
+		deduplicator:   NewRequestDeduplicator(300, 1000),
+		sem:            make(chan struct{}, 4),
+		claudePath:     "/nonexistent/path",
+	}
+
+	ctx := context.Background()
+
+	// Meaningful assistant message (> 200 chars, contains code discussion)
+	assistantMsg := `I've updated the handler.go file to fix the authentication bug.
+The function validateToken() was not checking token expiry correctly.
+I've added a check for the exp claim and implemented proper error handling.
+The changes have been tested and the build passes successfully.
+Here's the implementation details and code review.`
+
+	// Valid request but circuit breaker is open
+	err := p.ProcessSummary(ctx, 1, "session-1", "project-1",
+		"Implement authentication", "User message", assistantMsg)
+	assert.Error(t, err)
+	assert.Contains(t, err.Error(), "claude CLI failed")
+}
+
+// =============================================================================
+// TESTS FOR callClaudeCLI Error Paths
+// =============================================================================
+
+func TestCallClaudeCLI_PromptTooLarge(t *testing.T) {
+	p := &Processor{
+		claudePath: "/fake/claude",
+	}
+
+	ctx := context.Background()
+
+	// Create a prompt that exceeds MaxPromptSize
+	largePrompt := string(make([]byte, MaxPromptSize+1))
+
+	_, err := p.callClaudeCLI(ctx, largePrompt)
+	assert.Error(t, err)
+	assert.Contains(t, err.Error(), "prompt exceeds maximum size")
+}
+
+func TestCallClaudeCLI_BinaryNotFound(t *testing.T) {
+	p := &Processor{
+		claudePath: "/nonexistent/path/to/claude",
+	}
+
+	ctx := context.Background()
+
+	_, err := p.callClaudeCLI(ctx, "test prompt")
+	assert.Error(t, err)
+	assert.Contains(t, err.Error(), "claude CLI failed")
+}

internal/worker/session/manager_test.go

@@ -693,3 +693,734 @@ func TestToolInputResponse(t *testing.T) {
 		})
 	}
 }
+
+// =============================================================================
+// TESTS FOR NewManager AND CLEANUP
+// =============================================================================
+
+// TestNewManager tests the NewManager function.
+func TestNewManager(t *testing.T) {
+	t.Parallel()
+
+	// Test with nil session store (valid for testing)
+	manager := NewManager(nil)
+
+	assert.NotNil(t, manager)
+	assert.NotNil(t, manager.sessions)
+	assert.NotNil(t, manager.ProcessNotify)
+	assert.NotNil(t, manager.ctx)
+	assert.NotNil(t, manager.cancel)
+	assert.Equal(t, 0, manager.GetActiveSessionCount())
+
+	// Clean up - cancel context to stop cleanup goroutine
+	manager.cancel()
+}
+
+// TestNewManager_CleanupGoroutineStops tests that cleanup goroutine stops on cancel.
+func TestNewManager_CleanupGoroutineStops(t *testing.T) {
+	t.Parallel()
+
+	manager := NewManager(nil)
+
+	// Give goroutine time to start
+	time.Sleep(10 * time.Millisecond)
+
+	// Cancel should stop the cleanup goroutine
+	manager.cancel()
+
+	// Context should be done
+	select {
+	case <-manager.ctx.Done():
+		// Expected
+	case <-time.After(100 * time.Millisecond):
+		t.Error("Context should be done after cancel")
+	}
+}
+
+// TestCleanupStaleSessions_NoSessions tests cleanup with no sessions.
+func TestCleanupStaleSessions_NoSessions(t *testing.T) {
+	t.Parallel()
+
+	manager := &Manager{
+		sessions:      make(map[int64]*ActiveSession),
+		ProcessNotify: make(chan struct{}, 1),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	manager.ctx = ctx
+	manager.cancel = cancel
+
+	// Should not panic with empty sessions
+	manager.cleanupStaleSessions()
+	assert.Equal(t, 0, manager.GetActiveSessionCount())
+}
+
+// TestCleanupStaleSessions_FreshSession tests that fresh sessions are not cleaned.
+func TestCleanupStaleSessions_FreshSession(t *testing.T) {
+	t.Parallel()
+
+	manager := &Manager{
+		sessions:      make(map[int64]*ActiveSession),
+		ProcessNotify: make(chan struct{}, 1),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	manager.ctx = ctx
+	manager.cancel = cancel
+
+	// Add a fresh session
+	sessionCtx, sessionCancel := context.WithCancel(context.Background())
+	manager.sessions[1] = &ActiveSession{
+		SessionDBID:     1,
+		StartTime:       time.Now(), // Fresh
+		pendingMessages: []PendingMessage{},
+		ctx:             sessionCtx,
+		cancel:          sessionCancel,
+	}
+
+	manager.cleanupStaleSessions()
+
+	// Session should still exist (not stale)
+	assert.Equal(t, 1, manager.GetActiveSessionCount())
+	sessionCancel()
+}
+
+// TestCleanupStaleSessions_StaleSession tests that stale sessions are cleaned.
+func TestCleanupStaleSessions_StaleSession(t *testing.T) {
+	t.Parallel()
+
+	manager := &Manager{
+		sessions:      make(map[int64]*ActiveSession),
+		ProcessNotify: make(chan struct{}, 1),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	manager.ctx = ctx
+	manager.cancel = cancel
+
+	// Add a stale session
+	sessionCtx, sessionCancel := context.WithCancel(context.Background())
+	manager.sessions[1] = &ActiveSession{
+		SessionDBID:     1,
+		StartTime:       time.Now().Add(-SessionTimeout - time.Minute), // Stale
+		pendingMessages: []PendingMessage{},
+		ctx:             sessionCtx,
+		cancel:          sessionCancel,
+	}
+
+	manager.cleanupStaleSessions()
+
+	// Session should be deleted
+	assert.Equal(t, 0, manager.GetActiveSessionCount())
+}
+
+// TestCleanupStaleSessions_StaleWithPending tests stale sessions with pending messages are not cleaned.
+func TestCleanupStaleSessions_StaleWithPending(t *testing.T) {
+	t.Parallel()
+
+	manager := &Manager{
+		sessions:      make(map[int64]*ActiveSession),
+		ProcessNotify: make(chan struct{}, 1),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	manager.ctx = ctx
+	manager.cancel = cancel
+
+	// Add a stale session with pending messages
+	sessionCtx, sessionCancel := context.WithCancel(context.Background())
+	defer sessionCancel()
+	manager.sessions[1] = &ActiveSession{
+		SessionDBID:     1,
+		StartTime:       time.Now().Add(-SessionTimeout - time.Minute), // Stale
+		pendingMessages: []PendingMessage{{Type: MessageTypeObservation}},
+		ctx:             sessionCtx,
+		cancel:          sessionCancel,
+	}
+
+	manager.cleanupStaleSessions()
+
+	// Session should NOT be deleted (has pending messages)
+	assert.Equal(t, 1, manager.GetActiveSessionCount())
+}
+
+// TestCleanupStaleSessions_StaleWithActiveGenerator tests stale sessions with active generator are not cleaned.
+func TestCleanupStaleSessions_StaleWithActiveGenerator(t *testing.T) {
+	t.Parallel()
+
+	manager := &Manager{
+		sessions:      make(map[int64]*ActiveSession),
+		ProcessNotify: make(chan struct{}, 1),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	manager.ctx = ctx
+	manager.cancel = cancel
+
+	// Add a stale session with active generator
+	sessionCtx, sessionCancel := context.WithCancel(context.Background())
+	defer sessionCancel()
+	session := &ActiveSession{
+		SessionDBID:     1,
+		StartTime:       time.Now().Add(-SessionTimeout - time.Minute), // Stale
+		pendingMessages: []PendingMessage{},
+		ctx:             sessionCtx,
+		cancel:          sessionCancel,
+	}
+	session.generatorActive.Store(true)
+	manager.sessions[1] = session
+
+	manager.cleanupStaleSessions()
+
+	// Session should NOT be deleted (generator is active)
+	assert.Equal(t, 1, manager.GetActiveSessionCount())
+}
+
+// TestCleanupStaleSessions_MixedSessions tests cleanup with mixed fresh and stale sessions.
+func TestCleanupStaleSessions_MixedSessions(t *testing.T) {
+	t.Parallel()
+
+	manager := &Manager{
+		sessions:      make(map[int64]*ActiveSession),
+		ProcessNotify: make(chan struct{}, 1),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	manager.ctx = ctx
+	manager.cancel = cancel
+
+	// Fresh session
+	ctx1, cancel1 := context.WithCancel(context.Background())
+	defer cancel1()
+	manager.sessions[1] = &ActiveSession{
+		SessionDBID:     1,
+		StartTime:       time.Now(),
+		pendingMessages: []PendingMessage{},
+		ctx:             ctx1,
+		cancel:          cancel1,
+	}
+
+	// Stale session (should be deleted)
+	ctx2, cancel2 := context.WithCancel(context.Background())
+	manager.sessions[2] = &ActiveSession{
+		SessionDBID:     2,
+		StartTime:       time.Now().Add(-SessionTimeout - time.Minute),
+		pendingMessages: []PendingMessage{},
+		ctx:             ctx2,
+		cancel:          cancel2,
+	}
+
+	// Stale session with pending (should NOT be deleted)
+	ctx3, cancel3 := context.WithCancel(context.Background())
+	defer cancel3()
+	manager.sessions[3] = &ActiveSession{
+		SessionDBID:     3,
+		StartTime:       time.Now().Add(-SessionTimeout - time.Minute),
+		pendingMessages: []PendingMessage{{Type: MessageTypeObservation}},
+		ctx:             ctx3,
+		cancel:          cancel3,
+	}
+
+	manager.cleanupStaleSessions()
+
+	// Should have 2 sessions left (1 fresh, 1 stale with pending)
+	assert.Equal(t, 2, manager.GetActiveSessionCount())
+
+	// Verify which sessions remain
+	manager.mu.RLock()
+	_, has1 := manager.sessions[1]
+	_, has2 := manager.sessions[2]
+	_, has3 := manager.sessions[3]
+	manager.mu.RUnlock()
+
+	assert.True(t, has1, "Fresh session should remain")
+	assert.False(t, has2, "Stale session should be deleted")
+	assert.True(t, has3, "Stale session with pending should remain")
+}
+
+// TestCleanupLoop_ExitsOnCancel tests that cleanup loop exits when context is cancelled.
+func TestCleanupLoop_ExitsOnCancel(t *testing.T) {
+	t.Parallel()
+
+	manager := &Manager{
+		sessions:      make(map[int64]*ActiveSession),
+		ProcessNotify: make(chan struct{}, 1),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	manager.ctx = ctx
+	manager.cancel = cancel
+
+	// Start cleanup loop in goroutine
+	done := make(chan struct{})
+	go func() {
+		manager.cleanupLoop()
+		close(done)
+	}()
+
+	// Cancel immediately
+	cancel()
+
+	// Should exit quickly
+	select {
+	case <-done:
+		// Success - loop exited
+	case <-time.After(100 * time.Millisecond):
+		t.Error("Cleanup loop should exit when context is cancelled")
+	}
+}
+
+// =============================================================================
+// TESTS FOR InitializeSession (without DB)
+// =============================================================================
+
+// TestInitializeSession_AlreadyActive tests reusing an already active session.
+func TestInitializeSession_AlreadyActive(t *testing.T) {
+	t.Parallel()
+
+	manager := &Manager{
+		sessions:      make(map[int64]*ActiveSession),
+		ProcessNotify: make(chan struct{}, 1),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	manager.ctx = ctx
+	manager.cancel = cancel
+
+	// Pre-add an active session
+	existingSession := &ActiveSession{
+		SessionDBID:      42,
+		ClaudeSessionID:  "claude-existing",
+		Project:          "test-project",
+		UserPrompt:       "original prompt",
+		LastPromptNumber: 1,
+		StartTime:        time.Now(),
+		pendingMessages:  make([]PendingMessage, 0),
+	}
+	manager.sessions[42] = existingSession
+
+	// Initialize same session - should reuse
+	session, err := manager.InitializeSession(context.Background(), 42, "new prompt", 5)
+
+	assert.NoError(t, err)
+	assert.NotNil(t, session)
+	assert.Same(t, existingSession, session)
+	assert.Equal(t, "new prompt", session.UserPrompt)
+	assert.Equal(t, 5, session.LastPromptNumber)
+}
+
+// TestInitializeSession_AlreadyActive_EmptyPrompt tests reusing session with empty prompt.
+func TestInitializeSession_AlreadyActive_EmptyPrompt(t *testing.T) {
+	t.Parallel()
+
+	manager := &Manager{
+		sessions:      make(map[int64]*ActiveSession),
+		ProcessNotify: make(chan struct{}, 1),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	manager.ctx = ctx
+	manager.cancel = cancel
+
+	// Pre-add an active session
+	existingSession := &ActiveSession{
+		SessionDBID:      42,
+		UserPrompt:       "original prompt",
+		LastPromptNumber: 1,
+	}
+	manager.sessions[42] = existingSession
+
+	// Initialize with empty prompt - should NOT update
+	session, err := manager.InitializeSession(context.Background(), 42, "", 0)
+
+	assert.NoError(t, err)
+	assert.NotNil(t, session)
+	assert.Equal(t, "original prompt", session.UserPrompt) // Unchanged
+	assert.Equal(t, 1, session.LastPromptNumber)           // Unchanged
+}
+
+// TestInitializeSession_NoStore tests initialization without session store.
+func TestInitializeSession_NoStore(t *testing.T) {
+	t.Parallel()
+
+	manager := &Manager{
+		sessionStore:  nil, // No store
+		sessions:      make(map[int64]*ActiveSession),
+		ProcessNotify: make(chan struct{}, 1),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	manager.ctx = ctx
+	manager.cancel = cancel
+
+	// Should fail gracefully with nil store (panic recovery not expected)
+	// This tests the guard against nil sessionStore
+	defer func() {
+		if r := recover(); r != nil {
+			_ = r // Expected panic when calling nil store - intentionally ignored
+		}
+	}()
+
+	_, _ = manager.InitializeSession(context.Background(), 999, "prompt", 1)
+}
+
+// TestInitializeSession_CallbackTriggered tests that created callback is triggered.
+func TestInitializeSession_CallbackTriggered(t *testing.T) {
+	t.Parallel()
+
+	manager := &Manager{
+		sessions:      make(map[int64]*ActiveSession),
+		ProcessNotify: make(chan struct{}, 1),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	manager.ctx = ctx
+	manager.cancel = cancel
+
+	var calledWithID int64
+	manager.SetOnSessionCreated(func(id int64) {
+		calledWithID = id
+	})
+
+	// Add session directly (simulating what would happen after DB fetch)
+	sessionCtx, sessionCancel := context.WithCancel(context.Background())
+	defer sessionCancel()
+	session := &ActiveSession{
+		SessionDBID:     100,
+		ClaudeSessionID: "test",
+		Project:         "project",
+		StartTime:       time.Now(),
+		pendingMessages: make([]PendingMessage, 0),
+		notify:          make(chan struct{}, 1),
+		ctx:             sessionCtx,
+		cancel:          sessionCancel,
+	}
+
+	manager.mu.Lock()
+	manager.sessions[100] = session
+	onCreated := manager.onCreated
+	manager.mu.Unlock()
+
+	// Trigger callback
+	if onCreated != nil {
+		onCreated(100)
+	}
+
+	assert.Equal(t, int64(100), calledWithID)
+}
+
+// =============================================================================
+// TESTS FOR QueueObservation AND QueueSummarize (without DB)
+// =============================================================================
+
+// TestQueueObservation_ToExistingSession tests queuing to an existing session.
+func TestQueueObservation_ToExistingSession(t *testing.T) {
+	t.Parallel()
+
+	manager := &Manager{
+		sessions:      make(map[int64]*ActiveSession),
+		ProcessNotify: make(chan struct{}, 1),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	manager.ctx = ctx
+	manager.cancel = cancel
+
+	// Pre-add session
+	session := &ActiveSession{
+		SessionDBID:     1,
+		pendingMessages: make([]PendingMessage, 0),
+		notify:          make(chan struct{}, 1),
+	}
+	manager.sessions[1] = session
+
+	// Queue observation
+	err := manager.QueueObservation(context.Background(), 1, ObservationData{
+		ToolName:     "Read",
+		ToolInput:    map[string]string{"path": "/test"},
+		ToolResponse: "content",
+		PromptNumber: 1,
+		CWD:          "/project",
+	})
+
+	assert.NoError(t, err)
+	assert.Equal(t, 1, manager.GetTotalQueueDepth())
+
+	// Verify message
+	messages := manager.DrainMessages(1)
+	assert.Len(t, messages, 1)
+	assert.Equal(t, MessageTypeObservation, messages[0].Type)
+	assert.Equal(t, "Read", messages[0].Observation.ToolName)
+	assert.Equal(t, "/project", messages[0].Observation.CWD)
+}
+
+// TestQueueObservation_NotifiesSession tests that notification is sent to session.
+func TestQueueObservation_NotifiesSession(t *testing.T) {
+	t.Parallel()
+
+	manager := &Manager{
+		sessions:      make(map[int64]*ActiveSession),
+		ProcessNotify: make(chan struct{}, 1),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	manager.ctx = ctx
+	manager.cancel = cancel
+
+	// Pre-add session with notify channel
+	session := &ActiveSession{
+		SessionDBID:     1,
+		pendingMessages: make([]PendingMessage, 0),
+		notify:          make(chan struct{}, 1),
+	}
+	manager.sessions[1] = session
+
+	// Queue observation
+	err := manager.QueueObservation(context.Background(), 1, ObservationData{ToolName: "Test"})
+	assert.NoError(t, err)
+
+	// Should receive notification on session channel
+	select {
+	case <-session.notify:
+		// Success
+	default:
+		t.Error("Session should receive notification")
+	}
+
+	// Should receive notification on process channel
+	select {
+	case <-manager.ProcessNotify:
+		// Success
+	default:
+		t.Error("Manager ProcessNotify should receive notification")
+	}
+}
+
+// TestQueueSummarize_ToExistingSession tests queuing summarize to an existing session.
+func TestQueueSummarize_ToExistingSession(t *testing.T) {
+	t.Parallel()
+
+	manager := &Manager{
+		sessions:      make(map[int64]*ActiveSession),
+		ProcessNotify: make(chan struct{}, 1),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	manager.ctx = ctx
+	manager.cancel = cancel
+
+	// Pre-add session
+	session := &ActiveSession{
+		SessionDBID:     1,
+		pendingMessages: make([]PendingMessage, 0),
+		notify:          make(chan struct{}, 1),
+	}
+	manager.sessions[1] = session
+
+	// Queue summarize
+	err := manager.QueueSummarize(context.Background(), 1, "User asked question", "Assistant answered")
+	assert.NoError(t, err)
+	assert.Equal(t, 1, manager.GetTotalQueueDepth())
+
+	// Verify message
+	messages := manager.DrainMessages(1)
+	assert.Len(t, messages, 1)
+	assert.Equal(t, MessageTypeSummarize, messages[0].Type)
+	assert.Equal(t, "User asked question", messages[0].Summarize.LastUserMessage)
+	assert.Equal(t, "Assistant answered", messages[0].Summarize.LastAssistantMessage)
+}
+
+// TestQueueSummarize_NotifiesSession tests that notification is sent to session.
+func TestQueueSummarize_NotifiesSession(t *testing.T) {
+	t.Parallel()
+
+	manager := &Manager{
+		sessions:      make(map[int64]*ActiveSession),
+		ProcessNotify: make(chan struct{}, 1),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	manager.ctx = ctx
+	manager.cancel = cancel
+
+	// Pre-add session with notify channel
+	session := &ActiveSession{
+		SessionDBID:     1,
+		pendingMessages: make([]PendingMessage, 0),
+		notify:          make(chan struct{}, 1),
+	}
+	manager.sessions[1] = session
+
+	// Queue summarize
+	err := manager.QueueSummarize(context.Background(), 1, "user", "assistant")
+	assert.NoError(t, err)
+
+	// Should receive notification on session channel
+	select {
+	case <-session.notify:
+		// Success
+	default:
+		t.Error("Session should receive notification")
+	}
+
+	// Should receive notification on process channel
+	select {
+	case <-manager.ProcessNotify:
+		// Success
+	default:
+		t.Error("Manager ProcessNotify should receive notification")
+	}
+}
+
+// TestQueueOperations_MultipleMessages tests queuing multiple messages.
+func TestQueueOperations_MultipleMessages(t *testing.T) {
+	t.Parallel()
+
+	manager := &Manager{
+		sessions:      make(map[int64]*ActiveSession),
+		ProcessNotify: make(chan struct{}, 1),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	manager.ctx = ctx
+	manager.cancel = cancel
+
+	// Pre-add session
+	session := &ActiveSession{
+		SessionDBID:     1,
+		pendingMessages: make([]PendingMessage, 0),
+		notify:          make(chan struct{}, 1),
+	}
+	manager.sessions[1] = session
+
+	// Queue multiple messages
+	for i := 0; i < 10; i++ {
+		if i%2 == 0 {
+			err := manager.QueueObservation(context.Background(), 1, ObservationData{
+				ToolName: "Tool" + string(rune('A'+i)),
+			})
+			assert.NoError(t, err)
+		} else {
+			err := manager.QueueSummarize(context.Background(), 1, "user", "assistant")
+			assert.NoError(t, err)
+		}
+	}
+
+	assert.Equal(t, 10, manager.GetTotalQueueDepth())
+
+	// Drain and verify
+	messages := manager.DrainMessages(1)
+	assert.Len(t, messages, 10)
+}
+
+// TestQueueOperations_NonBlockingNotification tests non-blocking notification behavior.
+func TestQueueOperations_NonBlockingNotification(t *testing.T) {
+	t.Parallel()
+
+	manager := &Manager{
+		sessions:      make(map[int64]*ActiveSession),
+		ProcessNotify: make(chan struct{}, 1),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	manager.ctx = ctx
+	manager.cancel = cancel
+
+	// Pre-add session with full notify channel
+	session := &ActiveSession{
+		SessionDBID:     1,
+		pendingMessages: make([]PendingMessage, 0),
+		notify:          make(chan struct{}, 1),
+	}
+	// Fill the notify channel
+	session.notify <- struct{}{}
+	manager.sessions[1] = session
+
+	// Fill ProcessNotify channel
+	manager.ProcessNotify <- struct{}{}
+
+	// Queue should NOT block even with full channels
+	done := make(chan bool)
+	go func() {
+		err := manager.QueueObservation(context.Background(), 1, ObservationData{ToolName: "Test"})
+		assert.NoError(t, err)
+		done <- true
+	}()
+
+	select {
+	case <-done:
+		// Success - didn't block
+	case <-time.After(100 * time.Millisecond):
+		t.Error("Queue operation should not block even with full notification channels")
+	}
+}
+
+// TestConcurrentQueueAndCleanup tests concurrent queue operations and cleanup.
+func TestConcurrentQueueAndCleanup(t *testing.T) {
+	t.Parallel()
+
+	manager := &Manager{
+		sessions:      make(map[int64]*ActiveSession),
+		ProcessNotify: make(chan struct{}, 1),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	manager.ctx = ctx
+	manager.cancel = cancel
+
+	// Pre-add multiple sessions
+	for i := int64(1); i <= 5; i++ {
+		sessionCtx, sessionCancel := context.WithCancel(context.Background())
+		manager.sessions[i] = &ActiveSession{
+			SessionDBID:     i,
+			StartTime:       time.Now(),
+			pendingMessages: make([]PendingMessage, 0),
+			notify:          make(chan struct{}, 1),
+			ctx:             sessionCtx,
+			cancel:          sessionCancel,
+		}
+	}
+
+	var wg sync.WaitGroup
+
+	// Concurrent queue operations
+	for i := 0; i < 50; i++ {
+		wg.Add(1)
+		go func(idx int) {
+			defer wg.Done()
+			sessionID := int64((idx % 5) + 1)
+			if idx%2 == 0 {
+				_ = manager.QueueObservation(context.Background(), sessionID, ObservationData{ToolName: "Test"})
+			} else {
+				_ = manager.QueueSummarize(context.Background(), sessionID, "user", "assistant")
+			}
+		}(i)
+	}
+
+	// Concurrent cleanup
+	for i := 0; i < 10; i++ {
+		wg.Add(1)
+		go func() {
+			defer wg.Done()
+			manager.cleanupStaleSessions()
+		}()
+	}
+
+	// Concurrent reads
+	for i := 0; i < 20; i++ {
+		wg.Add(1)
+		go func() {
+			defer wg.Done()
+			_ = manager.GetActiveSessionCount()
+			_ = manager.GetTotalQueueDepth()
+			_ = manager.IsAnySessionProcessing()
+			_ = manager.GetAllSessions()
+		}()
+	}
+
+	wg.Wait()
+
+	// Should have all sessions (none are stale)
+	assert.Equal(t, 5, manager.GetActiveSessionCount())
+	// Should have 50 messages total
+	assert.Equal(t, 50, manager.GetTotalQueueDepth())
+}

pkg/similarity/clustering_test.go

@@ -290,3 +290,334 @@ func TestClusterObservations_PreservesOrder(t *testing.T) {
 	require.NotEmpty(t, clustered)
 	assert.Equal(t, int64(1), clustered[0].ID, "First observation should be kept as first result")
 }
+
+// =============================================================================
+// TESTS FOR OPTIMIZED CLUSTERING (triggered when len(observations) > 50)
+// =============================================================================
+
+func TestClusterObservationsOptimized_LargeSet(t *testing.T) {
+	t.Parallel()
+
+	// Create 60 observations to trigger optimized path (threshold is 50)
+	observations := make([]*models.Observation, 60)
+
+	// Create 30 pairs of similar observations
+	topics := []string{
+		"authentication", "authorization", "database", "caching", "logging",
+		"monitoring", "testing", "deployment", "scaling", "security",
+		"networking", "storage", "messaging", "scheduling", "configuration",
+		"validation", "serialization", "encryption", "compression", "indexing",
+		"backup", "recovery", "migration", "versioning", "documentation",
+		"profiling", "debugging", "tracing", "alerting", "reporting",
+	}
+
+	for i := 0; i < 30; i++ {
+		// First observation of pair
+		observations[i*2] = &models.Observation{
+			ID:        int64(i*2 + 1),
+			Title:     sql.NullString{String: topics[i] + " implementation", Valid: true},
+			Narrative: sql.NullString{String: "Detailed " + topics[i] + " system design", Valid: true},
+		}
+		// Second observation of pair (similar to first)
+		observations[i*2+1] = &models.Observation{
+			ID:        int64(i*2 + 2),
+			Title:     sql.NullString{String: topics[i] + " update", Valid: true},
+			Narrative: sql.NullString{String: "Updated " + topics[i] + " logic", Valid: true},
+		}
+	}
+
+	clustered := ClusterObservations(observations, 0.4)
+
+	// With similar pairs, we should get roughly 30 clusters (one per topic)
+	t.Logf("Clustered %d observations down to %d", len(observations), len(clustered))
+	assert.Less(t, len(clustered), 60, "Similar observations should be clustered together")
+	assert.GreaterOrEqual(t, len(clustered), 1, "Should have at least one cluster")
+}
+
+func TestClusterObservationsOptimized_AllUnique(t *testing.T) {
+	t.Parallel()
+
+	// Create 55 completely unique observations with NO shared terms
+	// Each observation has only its unique term (no common words like "topic" or "content")
+	uniqueTerms := []string{
+		"aardvark", "butterfly", "caterpillar", "dragonfly", "elephant",
+		"flamingo", "giraffe", "hippopotamus", "iguana", "jellyfish",
+		"kangaroo", "leopard", "mongoose", "nightingale", "octopus",
+		"penguin", "quail", "rhinoceros", "salamander", "toucan",
+		"umbrella", "vulture", "walrus", "xylophone", "yakking",
+		"zebra123", "astronomy99", "biology88", "chemistry77", "dynamics66",
+		"economics55", "forensics44", "genetics33", "hydraulics22", "immunology11",
+		"jurisprudence", "kinetics", "linguistics", "metallurgy", "neurology",
+		"oceanography", "pharmacology", "quantumphysics", "robotics", "sociology",
+		"thermodynamics", "ultrasound", "virology", "wavelength", "xenobiology",
+		"yeastculture", "zoology123", "algebra456", "botany789", "calculus012",
+	}
+
+	observations := make([]*models.Observation, 55)
+	for i := 0; i < 55; i++ {
+		// Each observation has ONLY its unique term - no shared words
+		observations[i] = &models.Observation{
+			ID:        int64(i + 1),
+			Title:     sql.NullString{String: uniqueTerms[i], Valid: true},
+			Narrative: sql.NullString{String: uniqueTerms[i], Valid: true},
+		}
+	}
+
+	clustered := ClusterObservations(observations, 0.4)
+
+	// All unique content should remain unclustered
+	assert.Len(t, clustered, 55, "All unique observations should be kept")
+}
+
+func TestClusterObservationsOptimized_SignaturePrefiltering(t *testing.T) {
+	t.Parallel()
+
+	// Test that signature prefiltering works correctly
+	// Create observations where some have very different signatures
+	observations := make([]*models.Observation, 60)
+
+	// First half: all identical (about "authentication") - should cluster to 1
+	for i := 0; i < 30; i++ {
+		observations[i] = &models.Observation{
+			ID:        int64(i + 1),
+			Title:     sql.NullString{String: "authentication security login", Valid: true},
+			Narrative: sql.NullString{String: "JWT tokens OAuth authentication", Valid: true},
+		}
+	}
+
+	// Second half: each completely unique with NO shared terms
+	diffTerms := []string{
+		"quantumphysics", "photosynthesis", "archaeologydig", "linguisticstudy", "astronomystar",
+		"paleontologyfossil", "oceanographywave", "entomologybug", "mycologyfungi", "herpetologysnake",
+		"ornithologybird", "ichthyologyfish", "seismologyquake", "volcanologylava", "meteorologyrain",
+		"cartographymap", "ethnographyculture", "philologyword", "numismaticscoin", "heraldryshield",
+		"genealogytree", "chronologytime", "typographyfont", "calligraphyink", "epigraphystone",
+		"papyrologytext", "codicologybook", "diplomaticseal", "sigillographywax", "sphragisticsring",
+	}
+	for i := 30; i < 60; i++ {
+		term := diffTerms[i-30]
+		// Each has ONLY its unique term - no shared words
+		observations[i] = &models.Observation{
+			ID:        int64(i + 1),
+			Title:     sql.NullString{String: term, Valid: true},
+			Narrative: sql.NullString{String: term, Valid: true},
+		}
+	}
+
+	clustered := ClusterObservations(observations, 0.5)
+
+	// Should have 31 clusters: 1 for all auth topics + 30 unique topics
+	t.Logf("Clustered %d observations down to %d", len(observations), len(clustered))
+	assert.Equal(t, 31, len(clustered), "Should have 31 clusters (1 auth + 30 unique)")
+}
+
+// =============================================================================
+// TESTS FOR HELPER FUNCTIONS
+// =============================================================================
+
+func TestComputeTermSignature(t *testing.T) {
+	tests := []struct {
+		terms      map[string]bool
+		compareTo  map[string]bool
+		name       string
+		expectZero bool
+		expectSame bool
+	}{
+		// ===== GOOD CASES =====
+		{
+			name:       "single term",
+			terms:      map[string]bool{"hello": true},
+			expectZero: false,
+		},
+		{
+			name:       "multiple terms",
+			terms:      map[string]bool{"hello": true, "world": true},
+			expectZero: false,
+		},
+		{
+			name:       "identical terms produce same signature",
+			terms:      map[string]bool{"alpha": true, "beta": true},
+			expectSame: true,
+			compareTo:  map[string]bool{"alpha": true, "beta": true},
+		},
+
+		// ===== EDGE CASES =====
+		{
+			name:       "empty set",
+			terms:      map[string]bool{},
+			expectZero: true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			sig := computeTermSignature(tt.terms)
+
+			if tt.expectZero {
+				assert.Equal(t, uint64(0), sig, "Empty set should produce zero signature")
+			} else {
+				assert.NotEqual(t, uint64(0), sig, "Non-empty set should produce non-zero signature")
+			}
+
+			if tt.expectSame && tt.compareTo != nil {
+				sig2 := computeTermSignature(tt.compareTo)
+				assert.Equal(t, sig, sig2, "Identical term sets should produce identical signatures")
+			}
+		})
+	}
+}
+
+func TestComputeTermSignature_DifferentSets(t *testing.T) {
+	t.Parallel()
+
+	// Different term sets should usually produce different signatures
+	set1 := map[string]bool{"authentication": true, "security": true}
+	set2 := map[string]bool{"database": true, "migration": true}
+
+	sig1 := computeTermSignature(set1)
+	sig2 := computeTermSignature(set2)
+
+	// While hash collisions are possible, they should be rare
+	assert.NotEqual(t, sig1, sig2, "Different term sets should usually produce different signatures")
+}
+
+func TestPopCount64(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    uint64
+		expected int
+	}{
+		// ===== GOOD CASES =====
+		{name: "zero", input: 0, expected: 0},
+		{name: "one", input: 1, expected: 1},
+		{name: "powers of two", input: 8, expected: 1},
+		{name: "all ones in byte", input: 0xFF, expected: 8},
+		{name: "alternating bits", input: 0xAAAAAAAAAAAAAAAA, expected: 32},
+		{name: "max uint64", input: 0xFFFFFFFFFFFFFFFF, expected: 64},
+
+		// ===== EDGE CASES =====
+		{name: "single high bit", input: 1 << 63, expected: 1},
+		{name: "sparse bits", input: 0x8000000000000001, expected: 2},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := popCount64(tt.input)
+			assert.Equal(t, tt.expected, result)
+		})
+	}
+}
+
+func TestIsSimilarToAny_EmptyTerms(t *testing.T) {
+	t.Parallel()
+
+	// Observation with no extractable terms
+	emptyObs := &models.Observation{
+		ID:        1,
+		Title:     sql.NullString{String: "", Valid: false},
+		Narrative: sql.NullString{String: "", Valid: false},
+	}
+
+	existing := []*models.Observation{
+		{
+			ID:        2,
+			Title:     sql.NullString{String: "Some content here", Valid: true},
+			Narrative: sql.NullString{String: "More content", Valid: true},
+		},
+	}
+
+	// Should return false when new observation has no terms
+	assert.False(t, IsSimilarToAny(emptyObs, existing, 0.3))
+}
+
+func TestExtractObservationTerms_FilesModified(t *testing.T) {
+	t.Parallel()
+
+	obs := &models.Observation{
+		ID:            1,
+		Title:         sql.NullString{String: "Code changes", Valid: true},
+		FilesModified: models.JSONStringArray{"/src/handler.go", "/pkg/models/user.go"},
+	}
+
+	terms := ExtractObservationTerms(obs)
+
+	// Should contain filenames from FilesModified
+	assert.Contains(t, terms, "handler.go")
+	assert.Contains(t, terms, "user.go")
+}
+
+func TestAddTerms_ShortWords(t *testing.T) {
+	t.Parallel()
+
+	terms := make(map[string]bool)
+
+	addTerms(terms, "I am a go developer")
+
+	// Short words (< 3 chars) should be excluded
+	assert.NotContains(t, terms, "i")
+	assert.NotContains(t, terms, "am")
+	assert.NotContains(t, terms, "a")
+	assert.NotContains(t, terms, "go") // Only 2 chars
+
+	// "developer" should be included
+	assert.Contains(t, terms, "developer")
+}
+
+func TestAddTerms_SpecialCharacters(t *testing.T) {
+	t.Parallel()
+
+	terms := make(map[string]bool)
+
+	addTerms(terms, "user_id authentication-flow JWT_token")
+
+	// Hyphens split words, but underscores are kept as part of the word
+	// (underscore is included in the tokenization regex)
+	assert.Contains(t, terms, "user_id")
+	assert.Contains(t, terms, "authentication")
+	assert.Contains(t, terms, "flow")
+	assert.Contains(t, terms, "jwt_token")
+}
+
+func TestJaccardSimilarity_SubsetSuperset(t *testing.T) {
+	t.Parallel()
+
+	subset := map[string]bool{"a": true, "b": true}
+	superset := map[string]bool{"a": true, "b": true, "c": true, "d": true}
+
+	// Subset similarity should be intersection/union = 2/4 = 0.5
+	result := JaccardSimilarity(subset, superset)
+	assert.InDelta(t, 0.5, result, 0.001)
+}
+
+func TestClusterObservations_HighThreshold(t *testing.T) {
+	t.Parallel()
+
+	// With a very high threshold, almost nothing should be clustered
+	observations := []*models.Observation{
+		{ID: 1, Title: sql.NullString{String: "authentication implementation", Valid: true}},
+		{ID: 2, Title: sql.NullString{String: "authentication update", Valid: true}},
+		{ID: 3, Title: sql.NullString{String: "authentication refactor", Valid: true}},
+	}
+
+	// With threshold of 0.9, even similar observations shouldn't cluster
+	clustered := ClusterObservations(observations, 0.9)
+
+	assert.Len(t, clustered, 3, "High threshold should prevent clustering")
+}
+
+func TestClusterObservations_LowThreshold(t *testing.T) {
+	t.Parallel()
+
+	// With a very low threshold, more things should be clustered
+	observations := []*models.Observation{
+		{ID: 1, Title: sql.NullString{String: "authentication implementation details", Valid: true}},
+		{ID: 2, Title: sql.NullString{String: "authentication security update", Valid: true}},
+		{ID: 3, Title: sql.NullString{String: "something completely different topic", Valid: true}},
+	}
+
+	// With threshold of 0.1, partial overlap should cluster
+	clustered := ClusterObservations(observations, 0.1)
+
+	// First two share "authentication", should likely cluster
+	assert.LessOrEqual(t, len(clustered), 3)
+}