diff --git a/tests/unit/test_chunking/__init__.py b/tests/unit/test_chunking/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/tests/unit/test_chunking/conftest.py b/tests/unit/test_chunking/conftest.py
new file mode 100644
index 00000000..c01f73d8
--- /dev/null
+++ b/tests/unit/test_chunking/conftest.py
@@ -0,0 +1,153 @@
+import pytest
+from unittest.mock import AsyncMock, Mock, patch
+from trustgraph.schema import TextDocument, Metadata
+from trustgraph.chunking.recursive.chunker import Processor as RecursiveChunker
+from trustgraph.chunking.token.chunker import Processor as TokenChunker
+from prometheus_client import REGISTRY
+
+
+@pytest.fixture
+def mock_flow():
+    """Mock flow function that returns a mock output producer."""
+    output_mock = AsyncMock()
+    flow_mock = Mock(return_value=output_mock)
+    return flow_mock, output_mock
+
+
+@pytest.fixture
+def mock_consumer():
+    """Mock consumer with test attributes."""
+    consumer = Mock()
+    consumer.id = "test-consumer"
+    consumer.flow = "test-flow"
+    return consumer
+
+
+@pytest.fixture
+def sample_text_document():
+    """Sample document with moderate length text."""
+    metadata = Metadata(
+        id="test-doc-1",
+        metadata=[],
+        user="test-user",
+        collection="test-collection"
+    )
+    text = "The quick brown fox jumps over the lazy dog. " * 20
+    return TextDocument(
+        metadata=metadata,
+        text=text.encode("utf-8")
+    )
+
+
+@pytest.fixture
+def long_text_document():
+    """Long document for testing multiple chunks."""
+    metadata = Metadata(
+        id="test-doc-long",
+        metadata=[],
+        user="test-user",
+        collection="test-collection"
+    )
+    # Create a long text that will definitely be chunked
+    text = " ".join([f"Sentence number {i}. This is part of a long document." for i in range(200)])
+    return TextDocument(
+        metadata=metadata,
+        text=text.encode("utf-8")
+    )
+
+
+@pytest.fixture
+def unicode_text_document():
+    """Document with various unicode characters."""
+    metadata = Metadata(
+        id="test-doc-unicode",
+        metadata=[],
+        user="test-user",
+        collection="test-collection"
+    )
+    text = """
+    English: Hello World!
+    Chinese: 你好世界
+    Japanese: こんにちは世界
+    Korean: 안녕하세요 세계
+    Arabic: مرحبا بالعالم
+    Russian: Привет мир
+    Emoji: 🌍 🌎 🌏 😀 🎉
+    Math: ∑ ∏ ∫ ∞ √ π
+    Symbols: © ® ™ € £ ¥
+    """
+    return TextDocument(
+        metadata=metadata,
+        text=text.encode("utf-8")
+    )
+
+
+@pytest.fixture
+def empty_text_document():
+    """Empty document for edge case testing."""
+    metadata = Metadata(
+        id="test-doc-empty",
+        metadata=[],
+        user="test-user",
+        collection="test-collection"
+    )
+    return TextDocument(
+        metadata=metadata,
+        text=b""
+    )
+
+
+@pytest.fixture
+def mock_message(sample_text_document):
+    """Mock message containing a document."""
+    msg = Mock()
+    msg.value.return_value = sample_text_document
+    return msg
+
+
+@pytest.fixture(autouse=True)
+def clear_metrics():
+    """Clear metrics before each test to avoid duplicates."""
+    # Clear the chunk_metric class attribute if it exists
+    if hasattr(RecursiveChunker, 'chunk_metric'):
+        # Unregister from Prometheus registry first
+        try:
+            REGISTRY.unregister(RecursiveChunker.chunk_metric)
+        except KeyError:
+            pass  # Already unregistered
+        delattr(RecursiveChunker, 'chunk_metric')
+    if hasattr(TokenChunker, 'chunk_metric'):
+        try:
+            REGISTRY.unregister(TokenChunker.chunk_metric)
+        except KeyError:
+            pass  # Already unregistered
+        delattr(TokenChunker, 'chunk_metric')
+    yield
+    # Clean up after test as well
+    if hasattr(RecursiveChunker, 'chunk_metric'):
+        try:
+            REGISTRY.unregister(RecursiveChunker.chunk_metric)
+        except KeyError:
+            pass
+        delattr(RecursiveChunker, 'chunk_metric')
+    if hasattr(TokenChunker, 'chunk_metric'):
+        try:
+            REGISTRY.unregister(TokenChunker.chunk_metric)
+        except KeyError:
+            pass
+        delattr(TokenChunker, 'chunk_metric')
+
+
+@pytest.fixture
+def mock_async_processor_init():
+    """Mock AsyncProcessor.__init__ to avoid taskgroup requirement."""
+    def init_mock(self, **kwargs):
+        # Set attributes that AsyncProcessor would normally set
+        self.config_handlers = []
+        self.specifications = []
+        self.flows = {}
+        self.id = kwargs.get('id', 'test-processor')
+        # Don't call the real __init__
+    
+    with patch('trustgraph.base.async_processor.AsyncProcessor.__init__', init_mock):
+        yield
\ No newline at end of file
diff --git a/tests/unit/test_chunking/test_recursive_chunker.py b/tests/unit/test_chunking/test_recursive_chunker.py
new file mode 100644
index 00000000..045133cd
--- /dev/null
+++ b/tests/unit/test_chunking/test_recursive_chunker.py
@@ -0,0 +1,211 @@
+import pytest
+import asyncio
+from unittest.mock import AsyncMock, Mock, patch, MagicMock
+from trustgraph.schema import TextDocument, Chunk, Metadata
+from trustgraph.chunking.recursive.chunker import Processor as RecursiveChunker
+
+
+@pytest.fixture
+def mock_flow():
+    output_mock = AsyncMock()
+    flow_mock = Mock(return_value=output_mock)
+    return flow_mock, output_mock
+
+
+@pytest.fixture
+def mock_consumer():
+    consumer = Mock()
+    consumer.id = "test-consumer"
+    consumer.flow = "test-flow"
+    return consumer
+
+
+@pytest.fixture
+def sample_document():
+    metadata = Metadata(
+        id="test-doc-1",
+        metadata=[],
+        user="test-user",
+        collection="test-collection"
+    )
+    text = "This is a test document. " * 100  # Create text long enough to be chunked
+    return TextDocument(
+        metadata=metadata,
+        text=text.encode("utf-8")
+    )
+
+
+@pytest.fixture
+def short_document():
+    metadata = Metadata(
+        id="test-doc-2",
+        metadata=[],
+        user="test-user",
+        collection="test-collection"
+    )
+    text = "This is a very short document."
+    return TextDocument(
+        metadata=metadata,
+        text=text.encode("utf-8")
+    )
+
+
+class TestRecursiveChunker:
+    
+    def test_init_default_params(self, mock_async_processor_init):
+        processor = RecursiveChunker()
+        assert processor.text_splitter._chunk_size == 2000
+        assert processor.text_splitter._chunk_overlap == 100
+        
+    def test_init_custom_params(self, mock_async_processor_init):
+        processor = RecursiveChunker(chunk_size=500, chunk_overlap=50)
+        assert processor.text_splitter._chunk_size == 500
+        assert processor.text_splitter._chunk_overlap == 50
+        
+    def test_init_with_id(self, mock_async_processor_init):
+        processor = RecursiveChunker(id="custom-chunker")
+        assert processor.id == "custom-chunker"
+        
+    @pytest.mark.asyncio
+    async def test_on_message_single_chunk(self, mock_async_processor_init, mock_flow, mock_consumer, short_document):
+        flow_mock, output_mock = mock_flow
+        processor = RecursiveChunker(chunk_size=2000, chunk_overlap=100)
+        
+        msg = Mock()
+        msg.value.return_value = short_document
+        
+        await processor.on_message(msg, mock_consumer, flow_mock)
+        
+        # Should produce exactly one chunk for short text
+        assert output_mock.send.call_count == 1
+        
+        # Verify the chunk was created correctly
+        chunk_call = output_mock.send.call_args[0][0]
+        assert isinstance(chunk_call, Chunk)
+        assert chunk_call.metadata == short_document.metadata
+        assert chunk_call.chunk.decode("utf-8") == short_document.text.decode("utf-8")
+        
+    @pytest.mark.asyncio
+    async def test_on_message_multiple_chunks(self, mock_async_processor_init, mock_flow, mock_consumer, sample_document):
+        flow_mock, output_mock = mock_flow
+        processor = RecursiveChunker(chunk_size=100, chunk_overlap=20)
+        
+        msg = Mock()
+        msg.value.return_value = sample_document
+        
+        await processor.on_message(msg, mock_consumer, flow_mock)
+        
+        # Should produce multiple chunks
+        assert output_mock.send.call_count > 1
+        
+        # Verify all chunks have correct metadata
+        for call in output_mock.send.call_args_list:
+            chunk = call[0][0]
+            assert isinstance(chunk, Chunk)
+            assert chunk.metadata == sample_document.metadata
+            assert len(chunk.chunk) > 0
+            
+    @pytest.mark.asyncio
+    async def test_on_message_chunk_overlap(self, mock_async_processor_init, mock_flow, mock_consumer):
+        flow_mock, output_mock = mock_flow
+        processor = RecursiveChunker(chunk_size=50, chunk_overlap=10)
+        
+        # Create a document with predictable content
+        metadata = Metadata(id="test", metadata=[], user="test-user", collection="test-collection")
+        text = "ABCDEFGHIJ" * 10  # 100 characters
+        document = TextDocument(metadata=metadata, text=text.encode("utf-8"))
+        
+        msg = Mock()
+        msg.value.return_value = document
+        
+        await processor.on_message(msg, mock_consumer, flow_mock)
+        
+        # Collect all chunks
+        chunks = []
+        for call in output_mock.send.call_args_list:
+            chunk_text = call[0][0].chunk.decode("utf-8")
+            chunks.append(chunk_text)
+            
+        # Verify chunks have expected overlap
+        for i in range(len(chunks) - 1):
+            # The end of chunk i should overlap with the beginning of chunk i+1
+            # Check if there's some overlap (exact overlap depends on text splitter logic)
+            assert len(chunks[i]) <= 50 + 10  # chunk_size + some tolerance
+            
+    @pytest.mark.asyncio
+    async def test_on_message_empty_document(self, mock_async_processor_init, mock_flow, mock_consumer):
+        flow_mock, output_mock = mock_flow
+        processor = RecursiveChunker()
+        
+        metadata = Metadata(id="empty", metadata=[], user="test-user", collection="test-collection")
+        document = TextDocument(metadata=metadata, text=b"")
+        
+        msg = Mock()
+        msg.value.return_value = document
+        
+        await processor.on_message(msg, mock_consumer, flow_mock)
+        
+        # Empty documents typically don't produce chunks with langchain splitters
+        # This behavior is expected - no chunks should be produced
+        assert output_mock.send.call_count == 0
+        
+    @pytest.mark.asyncio
+    async def test_on_message_unicode_handling(self, mock_async_processor_init, mock_flow, mock_consumer):
+        flow_mock, output_mock = mock_flow
+        processor = RecursiveChunker(chunk_size=500, chunk_overlap=20)  # Fixed overlap < chunk_size
+        
+        metadata = Metadata(id="unicode", metadata=[], user="test-user", collection="test-collection")
+        text = "Hello 世界! 🌍 This is a test with émojis and spëcial characters."
+        document = TextDocument(metadata=metadata, text=text.encode("utf-8"))
+        
+        msg = Mock()
+        msg.value.return_value = document
+        
+        await processor.on_message(msg, mock_consumer, flow_mock)
+        
+        # Verify unicode is preserved correctly
+        all_chunks = []
+        for call in output_mock.send.call_args_list:
+            chunk_text = call[0][0].chunk.decode("utf-8")
+            all_chunks.append(chunk_text)
+            
+        # Reconstruct text (approximately, due to overlap)
+        reconstructed = "".join(all_chunks)
+        assert "世界" in reconstructed
+        assert "🌍" in reconstructed
+        assert "émojis" in reconstructed
+        
+    @pytest.mark.asyncio
+    async def test_metrics_recorded(self, mock_async_processor_init, mock_flow, mock_consumer, sample_document):
+        flow_mock, output_mock = mock_flow
+        processor = RecursiveChunker(chunk_size=100)
+        
+        msg = Mock()
+        msg.value.return_value = sample_document
+        
+        # Mock the metric
+        with patch.object(RecursiveChunker.chunk_metric, 'labels') as mock_labels:
+            mock_observe = Mock()
+            mock_labels.return_value.observe = mock_observe
+            
+            await processor.on_message(msg, mock_consumer, flow_mock)
+            
+            # Verify metrics were recorded
+            mock_labels.assert_called_with(id="test-consumer", flow="test-flow")
+            assert mock_observe.call_count > 0
+            
+            # Verify chunk sizes were observed
+            for call in mock_observe.call_args_list:
+                chunk_size = call[0][0]
+                assert chunk_size > 0
+                
+    def test_add_args(self):
+        parser = Mock()
+        RecursiveChunker.add_args(parser)
+        
+        # Verify arguments were added
+        calls = parser.add_argument.call_args_list
+        arg_names = [call[0][0] for call in calls]
+        
+        assert '-z' in arg_names or '--chunk-size' in arg_names
+        assert '-v' in arg_names or '--chunk-overlap' in arg_names
\ No newline at end of file
diff --git a/tests/unit/test_chunking/test_token_chunker.py b/tests/unit/test_chunking/test_token_chunker.py
new file mode 100644
index 00000000..31dcc0c3
--- /dev/null
+++ b/tests/unit/test_chunking/test_token_chunker.py
@@ -0,0 +1,275 @@
+import pytest
+import asyncio
+from unittest.mock import AsyncMock, Mock, patch
+from trustgraph.schema import TextDocument, Chunk, Metadata
+from trustgraph.chunking.token.chunker import Processor as TokenChunker
+
+
+@pytest.fixture
+def mock_flow():
+    output_mock = AsyncMock()
+    flow_mock = Mock(return_value=output_mock)
+    return flow_mock, output_mock
+
+
+@pytest.fixture
+def mock_consumer():
+    consumer = Mock()
+    consumer.id = "test-consumer"
+    consumer.flow = "test-flow"
+    return consumer
+
+
+@pytest.fixture
+def sample_document():
+    metadata = Metadata(
+        id="test-doc-1",
+        metadata=[],
+        user="test-user",
+        collection="test-collection"
+    )
+    # Create text that will result in multiple token chunks
+    text = "The quick brown fox jumps over the lazy dog. " * 50
+    return TextDocument(
+        metadata=metadata,
+        text=text.encode("utf-8")
+    )
+
+
+@pytest.fixture
+def short_document():
+    metadata = Metadata(
+        id="test-doc-2",
+        metadata=[],
+        user="test-user",
+        collection="test-collection"
+    )
+    text = "Short text."
+    return TextDocument(
+        metadata=metadata,
+        text=text.encode("utf-8")
+    )
+
+
+class TestTokenChunker:
+    
+    def test_init_default_params(self, mock_async_processor_init):
+        processor = TokenChunker()
+        assert processor.text_splitter._chunk_size == 250
+        assert processor.text_splitter._chunk_overlap == 15
+        # Just verify the text splitter was created (encoding verification is complex)
+        assert processor.text_splitter is not None
+        assert hasattr(processor.text_splitter, 'split_text')
+        
+    def test_init_custom_params(self, mock_async_processor_init):
+        processor = TokenChunker(chunk_size=100, chunk_overlap=10)
+        assert processor.text_splitter._chunk_size == 100
+        assert processor.text_splitter._chunk_overlap == 10
+        
+    def test_init_with_id(self, mock_async_processor_init):
+        processor = TokenChunker(id="custom-token-chunker")
+        assert processor.id == "custom-token-chunker"
+        
+    @pytest.mark.asyncio
+    async def test_on_message_single_chunk(self, mock_async_processor_init, mock_flow, mock_consumer, short_document):
+        flow_mock, output_mock = mock_flow
+        processor = TokenChunker(chunk_size=250, chunk_overlap=15)
+        
+        msg = Mock()
+        msg.value.return_value = short_document
+        
+        await processor.on_message(msg, mock_consumer, flow_mock)
+        
+        # Short text should produce exactly one chunk
+        assert output_mock.send.call_count == 1
+        
+        # Verify the chunk was created correctly
+        chunk_call = output_mock.send.call_args[0][0]
+        assert isinstance(chunk_call, Chunk)
+        assert chunk_call.metadata == short_document.metadata
+        assert chunk_call.chunk.decode("utf-8") == short_document.text.decode("utf-8")
+        
+    @pytest.mark.asyncio
+    async def test_on_message_multiple_chunks(self, mock_async_processor_init, mock_flow, mock_consumer, sample_document):
+        flow_mock, output_mock = mock_flow
+        processor = TokenChunker(chunk_size=50, chunk_overlap=5)
+        
+        msg = Mock()
+        msg.value.return_value = sample_document
+        
+        await processor.on_message(msg, mock_consumer, flow_mock)
+        
+        # Should produce multiple chunks
+        assert output_mock.send.call_count > 1
+        
+        # Verify all chunks have correct metadata
+        for call in output_mock.send.call_args_list:
+            chunk = call[0][0]
+            assert isinstance(chunk, Chunk)
+            assert chunk.metadata == sample_document.metadata
+            assert len(chunk.chunk) > 0
+            
+    @pytest.mark.asyncio
+    async def test_on_message_token_overlap(self, mock_async_processor_init, mock_flow, mock_consumer):
+        flow_mock, output_mock = mock_flow
+        processor = TokenChunker(chunk_size=20, chunk_overlap=5)
+        
+        # Create a document with repeated pattern
+        metadata = Metadata(id="test", metadata=[], user="test-user", collection="test-collection")
+        text = "one two three four five six seven eight nine ten " * 5
+        document = TextDocument(metadata=metadata, text=text.encode("utf-8"))
+        
+        msg = Mock()
+        msg.value.return_value = document
+        
+        await processor.on_message(msg, mock_consumer, flow_mock)
+        
+        # Collect all chunks
+        chunks = []
+        for call in output_mock.send.call_args_list:
+            chunk_text = call[0][0].chunk.decode("utf-8")
+            chunks.append(chunk_text)
+            
+        # Should have multiple chunks
+        assert len(chunks) > 1
+        
+        # Verify chunks are not empty
+        for chunk in chunks:
+            assert len(chunk) > 0
+            
+    @pytest.mark.asyncio
+    async def test_on_message_empty_document(self, mock_async_processor_init, mock_flow, mock_consumer):
+        flow_mock, output_mock = mock_flow
+        processor = TokenChunker()
+        
+        metadata = Metadata(id="empty", metadata=[], user="test-user", collection="test-collection")
+        document = TextDocument(metadata=metadata, text=b"")
+        
+        msg = Mock()
+        msg.value.return_value = document
+        
+        await processor.on_message(msg, mock_consumer, flow_mock)
+        
+        # Empty documents typically don't produce chunks with langchain splitters
+        # This behavior is expected - no chunks should be produced
+        assert output_mock.send.call_count == 0
+        
+    @pytest.mark.asyncio
+    async def test_on_message_unicode_handling(self, mock_async_processor_init, mock_flow, mock_consumer):
+        flow_mock, output_mock = mock_flow
+        processor = TokenChunker(chunk_size=50)
+        
+        metadata = Metadata(id="unicode", metadata=[], user="test-user", collection="test-collection")
+        # Test with various unicode characters
+        text = "Hello 世界! 🌍 Test émojis café naïve résumé. Greek: αβγδε Hebrew: אבגדה"
+        document = TextDocument(metadata=metadata, text=text.encode("utf-8"))
+        
+        msg = Mock()
+        msg.value.return_value = document
+        
+        await processor.on_message(msg, mock_consumer, flow_mock)
+        
+        # Verify unicode is preserved correctly
+        all_chunks = []
+        for call in output_mock.send.call_args_list:
+            chunk_text = call[0][0].chunk.decode("utf-8")
+            all_chunks.append(chunk_text)
+            
+        # Reconstruct text
+        reconstructed = "".join(all_chunks)
+        assert "世界" in reconstructed
+        assert "🌍" in reconstructed
+        assert "émojis" in reconstructed
+        assert "αβγδε" in reconstructed
+        assert "אבגדה" in reconstructed
+        
+    @pytest.mark.asyncio
+    async def test_on_message_token_boundary_preservation(self, mock_async_processor_init, mock_flow, mock_consumer):
+        flow_mock, output_mock = mock_flow
+        processor = TokenChunker(chunk_size=10, chunk_overlap=2)
+        
+        metadata = Metadata(id="boundary", metadata=[], user="test-user", collection="test-collection")
+        # Text with clear word boundaries
+        text = "This is a test of token boundaries and proper splitting."
+        document = TextDocument(metadata=metadata, text=text.encode("utf-8"))
+        
+        msg = Mock()
+        msg.value.return_value = document
+        
+        await processor.on_message(msg, mock_consumer, flow_mock)
+        
+        # Collect all chunks
+        chunks = []
+        for call in output_mock.send.call_args_list:
+            chunk_text = call[0][0].chunk.decode("utf-8")
+            chunks.append(chunk_text)
+            
+        # Token chunker should respect token boundaries
+        for chunk in chunks:
+            # Chunks should not start or end with partial words (in most cases)
+            assert len(chunk.strip()) > 0
+            
+    @pytest.mark.asyncio
+    async def test_metrics_recorded(self, mock_async_processor_init, mock_flow, mock_consumer, sample_document):
+        flow_mock, output_mock = mock_flow
+        processor = TokenChunker(chunk_size=50)
+        
+        msg = Mock()
+        msg.value.return_value = sample_document
+        
+        # Mock the metric
+        with patch.object(TokenChunker.chunk_metric, 'labels') as mock_labels:
+            mock_observe = Mock()
+            mock_labels.return_value.observe = mock_observe
+            
+            await processor.on_message(msg, mock_consumer, flow_mock)
+            
+            # Verify metrics were recorded
+            mock_labels.assert_called_with(id="test-consumer", flow="test-flow")
+            assert mock_observe.call_count > 0
+            
+            # Verify chunk sizes were observed
+            for call in mock_observe.call_args_list:
+                chunk_size = call[0][0]
+                assert chunk_size > 0
+                
+    def test_add_args(self):
+        parser = Mock()
+        TokenChunker.add_args(parser)
+        
+        # Verify arguments were added
+        calls = parser.add_argument.call_args_list
+        arg_names = [call[0][0] for call in calls]
+        
+        assert '-z' in arg_names or '--chunk-size' in arg_names
+        assert '-v' in arg_names or '--chunk-overlap' in arg_names
+        
+    @pytest.mark.asyncio
+    async def test_encoding_specific_behavior(self, mock_async_processor_init, mock_flow, mock_consumer):
+        flow_mock, output_mock = mock_flow
+        processor = TokenChunker(chunk_size=10, chunk_overlap=0)
+        
+        metadata = Metadata(id="encoding", metadata=[], user="test-user", collection="test-collection")
+        # Test text that might tokenize differently with cl100k_base encoding
+        text = "GPT-4 is an AI model. It uses tokens."
+        document = TextDocument(metadata=metadata, text=text.encode("utf-8"))
+        
+        msg = Mock()
+        msg.value.return_value = document
+        
+        await processor.on_message(msg, mock_consumer, flow_mock)
+        
+        # Verify chunking happened
+        assert output_mock.send.call_count >= 1
+        
+        # Collect all chunks
+        chunks = []
+        for call in output_mock.send.call_args_list:
+            chunk_text = call[0][0].chunk.decode("utf-8")
+            chunks.append(chunk_text)
+            
+        # Verify all text is preserved (allowing for overlap)
+        all_text = " ".join(chunks)
+        assert "GPT-4" in all_text
+        assert "AI model" in all_text
+        assert "tokens" in all_text
\ No newline at end of file