test: add file utilities tests

- Add tests for file processing constraints and validators
- Add tests for FileProcessor and FileResolver
- Add tests for resolved file types
- Add tests for file store operations
- Add unit tests for multimodal LLM support

lib/crewai/tests/llms/test_multimodal.py

@@ -0,0 +1,474 @@
+"""Unit tests for LLM multimodal functionality across all providers."""
+
+import base64
+import os
+from unittest.mock import patch
+
+import pytest
+
+from crewai.llm import LLM
+from crewai.utilities.files import ImageFile, PDFFile, TextFile
+
+# Check for optional provider dependencies
+try:
+    from crewai.llms.providers.anthropic.completion import AnthropicCompletion
+    HAS_ANTHROPIC = True
+except ImportError:
+    HAS_ANTHROPIC = False
+
+try:
+    from crewai.llms.providers.azure.completion import AzureCompletion
+    HAS_AZURE = True
+except ImportError:
+    HAS_AZURE = False
+
+try:
+    from crewai.llms.providers.bedrock.completion import BedrockCompletion
+    HAS_BEDROCK = True
+except ImportError:
+    HAS_BEDROCK = False
+
+
+# Minimal valid PNG for testing
+MINIMAL_PNG = (
+    b"\x89PNG\r\n\x1a\n"
+    b"\x00\x00\x00\rIHDR"
+    b"\x00\x00\x00\x01\x00\x00\x00\x01\x08\x02\x00\x00\x00"
+    b"\x90wS\xde"
+    b"\x00\x00\x00\x00IEND\xaeB`\x82"
+)
+
+MINIMAL_PDF = b"%PDF-1.4 test content"
+
+
+@pytest.fixture(autouse=True)
+def mock_api_keys():
+    """Mock API keys for all providers."""
+    env_vars = {
+        "ANTHROPIC_API_KEY": "test-key",
+        "OPENAI_API_KEY": "test-key",
+        "GOOGLE_API_KEY": "test-key",
+        "AZURE_API_KEY": "test-key",
+        "AWS_ACCESS_KEY_ID": "test-key",
+        "AWS_SECRET_ACCESS_KEY": "test-key",
+    }
+    with patch.dict(os.environ, env_vars):
+        yield
+
+
+class TestLiteLLMMultimodal:
+    """Tests for LLM class (litellm wrapper) multimodal functionality.
+
+    These tests use `is_litellm=True` to ensure the litellm wrapper is used
+    instead of native providers.
+    """
+
+    def test_supports_multimodal_gpt4o(self) -> None:
+        """Test GPT-4o model supports multimodal."""
+        llm = LLM(model="gpt-4o", is_litellm=True)
+        assert llm.supports_multimodal() is True
+
+    def test_supports_multimodal_gpt4_turbo(self) -> None:
+        """Test GPT-4 Turbo model supports multimodal."""
+        llm = LLM(model="gpt-4-turbo", is_litellm=True)
+        assert llm.supports_multimodal() is True
+
+    def test_supports_multimodal_claude3(self) -> None:
+        """Test Claude 3 model supports multimodal via litellm."""
+        # Use litellm/ prefix to avoid native provider import
+        llm = LLM(model="litellm/claude-3-sonnet-20240229")
+        assert llm.supports_multimodal() is True
+
+    def test_supports_multimodal_gemini(self) -> None:
+        """Test Gemini model supports multimodal."""
+        llm = LLM(model="gemini/gemini-pro", is_litellm=True)
+        assert llm.supports_multimodal() is True
+
+    def test_supports_multimodal_gpt35_does_not(self) -> None:
+        """Test GPT-3.5 model does not support multimodal."""
+        llm = LLM(model="gpt-3.5-turbo", is_litellm=True)
+        assert llm.supports_multimodal() is False
+
+    def test_supported_content_types_openai(self) -> None:
+        """Test OpenAI models support images only."""
+        llm = LLM(model="gpt-4o", is_litellm=True)
+        types = llm.supported_multimodal_content_types()
+        assert "image/" in types
+        assert "application/pdf" not in types
+
+    def test_supported_content_types_claude(self) -> None:
+        """Test Claude models support images and PDFs via litellm."""
+        # Use litellm/ prefix to avoid native provider import
+        llm = LLM(model="litellm/claude-3-sonnet-20240229")
+        types = llm.supported_multimodal_content_types()
+        assert "image/" in types
+        assert "application/pdf" in types
+
+    def test_supported_content_types_gemini(self) -> None:
+        """Test Gemini models support wide range of content."""
+        llm = LLM(model="gemini/gemini-pro", is_litellm=True)
+        types = llm.supported_multimodal_content_types()
+        assert "image/" in types
+        assert "audio/" in types
+        assert "video/" in types
+        assert "application/pdf" in types
+        assert "text/" in types
+
+    def test_supported_content_types_non_multimodal(self) -> None:
+        """Test non-multimodal models return empty list."""
+        llm = LLM(model="gpt-3.5-turbo", is_litellm=True)
+        assert llm.supported_multimodal_content_types() == []
+
+    def test_format_multimodal_content_image(self) -> None:
+        """Test formatting image content."""
+        llm = LLM(model="gpt-4o", is_litellm=True)
+        files = {"chart": ImageFile(source=MINIMAL_PNG)}
+
+        result = llm.format_multimodal_content(files)
+
+        assert len(result) == 1
+        assert result[0]["type"] == "image_url"
+        assert "data:image/png;base64," in result[0]["image_url"]["url"]
+
+    def test_format_multimodal_content_non_multimodal(self) -> None:
+        """Test non-multimodal model returns empty list."""
+        llm = LLM(model="gpt-3.5-turbo", is_litellm=True)
+        files = {"chart": ImageFile(source=MINIMAL_PNG)}
+
+        result = llm.format_multimodal_content(files)
+
+        assert result == []
+
+    def test_format_multimodal_content_unsupported_type(self) -> None:
+        """Test unsupported content type is skipped."""
+        llm = LLM(model="gpt-4o", is_litellm=True)  # OpenAI doesn't support PDF
+        files = {"doc": PDFFile(source=MINIMAL_PDF)}
+
+        result = llm.format_multimodal_content(files)
+
+        assert result == []
+
+
+@pytest.mark.skipif(not HAS_ANTHROPIC, reason="Anthropic SDK not installed")
+class TestAnthropicMultimodal:
+    """Tests for Anthropic provider multimodal functionality."""
+
+    def test_supports_multimodal_claude3(self) -> None:
+        """Test Claude 3 supports multimodal."""
+        llm = LLM(model="anthropic/claude-3-sonnet-20240229")
+        assert llm.supports_multimodal() is True
+
+    def test_supports_multimodal_claude4(self) -> None:
+        """Test Claude 4 supports multimodal."""
+        llm = LLM(model="anthropic/claude-4-opus")
+        assert llm.supports_multimodal() is True
+
+    def test_supported_content_types(self) -> None:
+        """Test Anthropic supports images and PDFs."""
+        llm = LLM(model="anthropic/claude-3-sonnet-20240229")
+        types = llm.supported_multimodal_content_types()
+        assert "image/" in types
+        assert "application/pdf" in types
+
+    def test_format_multimodal_content_image(self) -> None:
+        """Test Anthropic image format uses source-based structure."""
+        llm = LLM(model="anthropic/claude-3-sonnet-20240229")
+        files = {"chart": ImageFile(source=MINIMAL_PNG)}
+
+        result = llm.format_multimodal_content(files)
+
+        assert len(result) == 1
+        assert result[0]["type"] == "image"
+        assert result[0]["source"]["type"] == "base64"
+        assert result[0]["source"]["media_type"] == "image/png"
+        assert "data" in result[0]["source"]
+
+    def test_format_multimodal_content_pdf(self) -> None:
+        """Test Anthropic PDF format uses document structure."""
+        llm = LLM(model="anthropic/claude-3-sonnet-20240229")
+        files = {"doc": PDFFile(source=MINIMAL_PDF)}
+
+        result = llm.format_multimodal_content(files)
+
+        assert len(result) == 1
+        assert result[0]["type"] == "document"
+        assert result[0]["source"]["type"] == "base64"
+        assert result[0]["source"]["media_type"] == "application/pdf"
+
+
+class TestOpenAIMultimodal:
+    """Tests for OpenAI provider multimodal functionality."""
+
+    def test_supports_multimodal_gpt4o(self) -> None:
+        """Test GPT-4o supports multimodal."""
+        llm = LLM(model="openai/gpt-4o")
+        assert llm.supports_multimodal() is True
+
+    def test_supports_multimodal_gpt4_vision(self) -> None:
+        """Test GPT-4 Vision supports multimodal."""
+        llm = LLM(model="openai/gpt-4-vision-preview")
+        assert llm.supports_multimodal() is True
+
+    def test_supports_multimodal_o1(self) -> None:
+        """Test O1 model supports multimodal."""
+        llm = LLM(model="openai/o1-preview")
+        assert llm.supports_multimodal() is True
+
+    def test_does_not_support_gpt35(self) -> None:
+        """Test GPT-3.5 does not support multimodal."""
+        llm = LLM(model="openai/gpt-3.5-turbo")
+        assert llm.supports_multimodal() is False
+
+    def test_supported_content_types(self) -> None:
+        """Test OpenAI supports only images."""
+        llm = LLM(model="openai/gpt-4o")
+        types = llm.supported_multimodal_content_types()
+        assert types == ["image/"]
+
+    def test_format_multimodal_content_image(self) -> None:
+        """Test OpenAI uses image_url format."""
+        llm = LLM(model="openai/gpt-4o")
+        files = {"chart": ImageFile(source=MINIMAL_PNG)}
+
+        result = llm.format_multimodal_content(files)
+
+        assert len(result) == 1
+        assert result[0]["type"] == "image_url"
+        url = result[0]["image_url"]["url"]
+        assert url.startswith("data:image/png;base64,")
+        # Verify base64 content
+        b64_data = url.split(",")[1]
+        assert base64.b64decode(b64_data) == MINIMAL_PNG
+
+
+class TestGeminiMultimodal:
+    """Tests for Gemini provider multimodal functionality."""
+
+    def test_supports_multimodal_always_true(self) -> None:
+        """Test Gemini always supports multimodal."""
+        llm = LLM(model="gemini/gemini-pro")
+        assert llm.supports_multimodal() is True
+
+    def test_supported_content_types(self) -> None:
+        """Test Gemini supports wide range of types."""
+        llm = LLM(model="gemini/gemini-pro")
+        types = llm.supported_multimodal_content_types()
+        assert "image/" in types
+        assert "audio/" in types
+        assert "video/" in types
+        assert "application/pdf" in types
+        assert "text/" in types
+
+    def test_format_multimodal_content_image(self) -> None:
+        """Test Gemini uses inlineData format."""
+        llm = LLM(model="gemini/gemini-pro")
+        files = {"chart": ImageFile(source=MINIMAL_PNG)}
+
+        result = llm.format_multimodal_content(files)
+
+        assert len(result) == 1
+        assert "inlineData" in result[0]
+        assert result[0]["inlineData"]["mimeType"] == "image/png"
+        assert "data" in result[0]["inlineData"]
+
+    def test_format_text_content(self) -> None:
+        """Test Gemini text format uses simple text key."""
+        llm = LLM(model="gemini/gemini-pro")
+
+        result = llm.format_text_content("Hello world")
+
+        assert result == {"text": "Hello world"}
+
+
+@pytest.mark.skipif(not HAS_AZURE, reason="Azure AI Inference SDK not installed")
+class TestAzureMultimodal:
+    """Tests for Azure OpenAI provider multimodal functionality."""
+
+    @pytest.fixture(autouse=True)
+    def mock_azure_env(self):
+        """Mock Azure-specific environment variables."""
+        env_vars = {
+            "AZURE_API_KEY": "test-key",
+            "AZURE_API_BASE": "https://test.openai.azure.com",
+            "AZURE_API_VERSION": "2024-02-01",
+        }
+        with patch.dict(os.environ, env_vars):
+            yield
+
+    def test_supports_multimodal_gpt4o(self) -> None:
+        """Test Azure GPT-4o supports multimodal."""
+        llm = LLM(model="azure/gpt-4o")
+        assert llm.supports_multimodal() is True
+
+    def test_supports_multimodal_gpt4_turbo(self) -> None:
+        """Test Azure GPT-4 Turbo supports multimodal."""
+        llm = LLM(model="azure/gpt-4-turbo")
+        assert llm.supports_multimodal() is True
+
+    def test_does_not_support_gpt35(self) -> None:
+        """Test Azure GPT-3.5 does not support multimodal."""
+        llm = LLM(model="azure/gpt-35-turbo")
+        assert llm.supports_multimodal() is False
+
+    def test_supported_content_types(self) -> None:
+        """Test Azure supports only images."""
+        llm = LLM(model="azure/gpt-4o")
+        types = llm.supported_multimodal_content_types()
+        assert types == ["image/"]
+
+    def test_format_multimodal_content_image(self) -> None:
+        """Test Azure uses same format as OpenAI."""
+        llm = LLM(model="azure/gpt-4o")
+        files = {"chart": ImageFile(source=MINIMAL_PNG)}
+
+        result = llm.format_multimodal_content(files)
+
+        assert len(result) == 1
+        assert result[0]["type"] == "image_url"
+        assert "data:image/png;base64," in result[0]["image_url"]["url"]
+
+
+@pytest.mark.skipif(not HAS_BEDROCK, reason="AWS Bedrock SDK not installed")
+class TestBedrockMultimodal:
+    """Tests for AWS Bedrock provider multimodal functionality."""
+
+    @pytest.fixture(autouse=True)
+    def mock_bedrock_env(self):
+        """Mock AWS-specific environment variables."""
+        env_vars = {
+            "AWS_ACCESS_KEY_ID": "test-key",
+            "AWS_SECRET_ACCESS_KEY": "test-secret",
+            "AWS_DEFAULT_REGION": "us-east-1",
+        }
+        with patch.dict(os.environ, env_vars):
+            yield
+
+    def test_supports_multimodal_claude3(self) -> None:
+        """Test Bedrock Claude 3 supports multimodal."""
+        llm = LLM(model="bedrock/anthropic.claude-3-sonnet")
+        assert llm.supports_multimodal() is True
+
+    def test_does_not_support_claude2(self) -> None:
+        """Test Bedrock Claude 2 does not support multimodal."""
+        llm = LLM(model="bedrock/anthropic.claude-v2")
+        assert llm.supports_multimodal() is False
+
+    def test_supported_content_types(self) -> None:
+        """Test Bedrock supports images and PDFs."""
+        llm = LLM(model="bedrock/anthropic.claude-3-sonnet")
+        types = llm.supported_multimodal_content_types()
+        assert "image/" in types
+        assert "application/pdf" in types
+
+    def test_format_multimodal_content_image(self) -> None:
+        """Test Bedrock uses Converse API image format."""
+        llm = LLM(model="bedrock/anthropic.claude-3-sonnet")
+        files = {"chart": ImageFile(source=MINIMAL_PNG)}
+
+        result = llm.format_multimodal_content(files)
+
+        assert len(result) == 1
+        assert "image" in result[0]
+        assert result[0]["image"]["format"] == "png"
+        assert "source" in result[0]["image"]
+        assert "bytes" in result[0]["image"]["source"]
+
+    def test_format_multimodal_content_pdf(self) -> None:
+        """Test Bedrock uses Converse API document format."""
+        llm = LLM(model="bedrock/anthropic.claude-3-sonnet")
+        files = {"doc": PDFFile(source=MINIMAL_PDF)}
+
+        result = llm.format_multimodal_content(files)
+
+        assert len(result) == 1
+        assert "document" in result[0]
+        assert result[0]["document"]["format"] == "pdf"
+        assert "source" in result[0]["document"]
+
+
+class TestBaseLLMMultimodal:
+    """Tests for BaseLLM default multimodal behavior."""
+
+    def test_base_supports_multimodal_false(self) -> None:
+        """Test base implementation returns False."""
+        from crewai.llms.base_llm import BaseLLM
+
+        class TestLLM(BaseLLM):
+            def call(self, messages, tools=None, callbacks=None):
+                return "test"
+
+        llm = TestLLM(model="test")
+        assert llm.supports_multimodal() is False
+
+    def test_base_supported_content_types_empty(self) -> None:
+        """Test base implementation returns empty list."""
+        from crewai.llms.base_llm import BaseLLM
+
+        class TestLLM(BaseLLM):
+            def call(self, messages, tools=None, callbacks=None):
+                return "test"
+
+        llm = TestLLM(model="test")
+        assert llm.supported_multimodal_content_types() == []
+
+    def test_base_format_multimodal_content_empty(self) -> None:
+        """Test base implementation returns empty list."""
+        from crewai.llms.base_llm import BaseLLM
+
+        class TestLLM(BaseLLM):
+            def call(self, messages, tools=None, callbacks=None):
+                return "test"
+
+        llm = TestLLM(model="test")
+        files = {"chart": ImageFile(source=MINIMAL_PNG)}
+        assert llm.format_multimodal_content(files) == []
+
+    def test_base_format_text_content(self) -> None:
+        """Test base text formatting uses OpenAI/Anthropic style."""
+        from crewai.llms.base_llm import BaseLLM
+
+        class TestLLM(BaseLLM):
+            def call(self, messages, tools=None, callbacks=None):
+                return "test"
+
+        llm = TestLLM(model="test")
+        result = llm.format_text_content("Hello")
+        assert result == {"type": "text", "text": "Hello"}
+
+
+class TestMultipleFilesFormatting:
+    """Tests for formatting multiple files at once."""
+
+    def test_format_multiple_images(self) -> None:
+        """Test formatting multiple images."""
+        llm = LLM(model="gpt-4o")
+        files = {
+            "chart1": ImageFile(source=MINIMAL_PNG),
+            "chart2": ImageFile(source=MINIMAL_PNG),
+        }
+
+        result = llm.format_multimodal_content(files)
+
+        assert len(result) == 2
+
+    def test_format_mixed_supported_and_unsupported(self) -> None:
+        """Test only supported types are formatted."""
+        llm = LLM(model="gpt-4o")  # OpenAI - images only
+        files = {
+            "chart": ImageFile(source=MINIMAL_PNG),
+            "doc": PDFFile(source=MINIMAL_PDF),  # Not supported
+            "text": TextFile(source=b"hello"),  # Not supported
+        }
+
+        result = llm.format_multimodal_content(files)
+
+        assert len(result) == 1
+        assert result[0]["type"] == "image_url"
+
+    def test_format_empty_files_dict(self) -> None:
+        """Test empty files dict returns empty list."""
+        llm = LLM(model="gpt-4o")
+
+        result = llm.format_multimodal_content({})
+
+        assert result == []

lib/crewai/tests/utilities/files/processing/test_constraints.py

@@ -0,0 +1,226 @@
+"""Tests for provider constraints."""
+
+import pytest
+
+from crewai.utilities.files.processing.constraints import (
+    ANTHROPIC_CONSTRAINTS,
+    BEDROCK_CONSTRAINTS,
+    GEMINI_CONSTRAINTS,
+    OPENAI_CONSTRAINTS,
+    AudioConstraints,
+    ImageConstraints,
+    PDFConstraints,
+    ProviderConstraints,
+    VideoConstraints,
+    get_constraints_for_provider,
+)
+
+
+class TestImageConstraints:
+    """Tests for ImageConstraints dataclass."""
+
+    def test_image_constraints_creation(self):
+        """Test creating image constraints with all fields."""
+        constraints = ImageConstraints(
+            max_size_bytes=5 * 1024 * 1024,
+            max_width=8000,
+            max_height=8000,
+            max_images_per_request=10,
+        )
+
+        assert constraints.max_size_bytes == 5 * 1024 * 1024
+        assert constraints.max_width == 8000
+        assert constraints.max_height == 8000
+        assert constraints.max_images_per_request == 10
+
+    def test_image_constraints_defaults(self):
+        """Test image constraints with default values."""
+        constraints = ImageConstraints(max_size_bytes=1000)
+
+        assert constraints.max_size_bytes == 1000
+        assert constraints.max_width is None
+        assert constraints.max_height is None
+        assert constraints.max_images_per_request is None
+        assert "image/png" in constraints.supported_formats
+
+    def test_image_constraints_frozen(self):
+        """Test that image constraints are immutable."""
+        constraints = ImageConstraints(max_size_bytes=1000)
+
+        with pytest.raises(Exception):
+            constraints.max_size_bytes = 2000
+
+
+class TestPDFConstraints:
+    """Tests for PDFConstraints dataclass."""
+
+    def test_pdf_constraints_creation(self):
+        """Test creating PDF constraints."""
+        constraints = PDFConstraints(
+            max_size_bytes=30 * 1024 * 1024,
+            max_pages=100,
+        )
+
+        assert constraints.max_size_bytes == 30 * 1024 * 1024
+        assert constraints.max_pages == 100
+
+    def test_pdf_constraints_defaults(self):
+        """Test PDF constraints with default values."""
+        constraints = PDFConstraints(max_size_bytes=1000)
+
+        assert constraints.max_size_bytes == 1000
+        assert constraints.max_pages is None
+
+
+class TestAudioConstraints:
+    """Tests for AudioConstraints dataclass."""
+
+    def test_audio_constraints_creation(self):
+        """Test creating audio constraints."""
+        constraints = AudioConstraints(
+            max_size_bytes=100 * 1024 * 1024,
+            max_duration_seconds=3600,
+        )
+
+        assert constraints.max_size_bytes == 100 * 1024 * 1024
+        assert constraints.max_duration_seconds == 3600
+        assert "audio/mp3" in constraints.supported_formats
+
+
+class TestVideoConstraints:
+    """Tests for VideoConstraints dataclass."""
+
+    def test_video_constraints_creation(self):
+        """Test creating video constraints."""
+        constraints = VideoConstraints(
+            max_size_bytes=2 * 1024 * 1024 * 1024,
+            max_duration_seconds=7200,
+        )
+
+        assert constraints.max_size_bytes == 2 * 1024 * 1024 * 1024
+        assert constraints.max_duration_seconds == 7200
+        assert "video/mp4" in constraints.supported_formats
+
+
+class TestProviderConstraints:
+    """Tests for ProviderConstraints dataclass."""
+
+    def test_provider_constraints_creation(self):
+        """Test creating full provider constraints."""
+        constraints = ProviderConstraints(
+            name="test-provider",
+            image=ImageConstraints(max_size_bytes=5 * 1024 * 1024),
+            pdf=PDFConstraints(max_size_bytes=30 * 1024 * 1024),
+            supports_file_upload=True,
+            file_upload_threshold_bytes=10 * 1024 * 1024,
+        )
+
+        assert constraints.name == "test-provider"
+        assert constraints.image is not None
+        assert constraints.pdf is not None
+        assert constraints.supports_file_upload is True
+
+    def test_provider_constraints_defaults(self):
+        """Test provider constraints with default values."""
+        constraints = ProviderConstraints(name="test")
+
+        assert constraints.name == "test"
+        assert constraints.image is None
+        assert constraints.pdf is None
+        assert constraints.audio is None
+        assert constraints.video is None
+        assert constraints.supports_file_upload is False
+
+
+class TestPredefinedConstraints:
+    """Tests for predefined provider constraints."""
+
+    def test_anthropic_constraints(self):
+        """Test Anthropic constraints are properly defined."""
+        assert ANTHROPIC_CONSTRAINTS.name == "anthropic"
+        assert ANTHROPIC_CONSTRAINTS.image is not None
+        assert ANTHROPIC_CONSTRAINTS.image.max_size_bytes == 5 * 1024 * 1024
+        assert ANTHROPIC_CONSTRAINTS.image.max_width == 8000
+        assert ANTHROPIC_CONSTRAINTS.pdf is not None
+        assert ANTHROPIC_CONSTRAINTS.pdf.max_pages == 100
+        assert ANTHROPIC_CONSTRAINTS.supports_file_upload is True
+
+    def test_openai_constraints(self):
+        """Test OpenAI constraints are properly defined."""
+        assert OPENAI_CONSTRAINTS.name == "openai"
+        assert OPENAI_CONSTRAINTS.image is not None
+        assert OPENAI_CONSTRAINTS.image.max_size_bytes == 20 * 1024 * 1024
+        assert OPENAI_CONSTRAINTS.pdf is None  # OpenAI doesn't support PDFs
+
+    def test_gemini_constraints(self):
+        """Test Gemini constraints are properly defined."""
+        assert GEMINI_CONSTRAINTS.name == "gemini"
+        assert GEMINI_CONSTRAINTS.image is not None
+        assert GEMINI_CONSTRAINTS.pdf is not None
+        assert GEMINI_CONSTRAINTS.audio is not None
+        assert GEMINI_CONSTRAINTS.video is not None
+        assert GEMINI_CONSTRAINTS.supports_file_upload is True
+
+    def test_bedrock_constraints(self):
+        """Test Bedrock constraints are properly defined."""
+        assert BEDROCK_CONSTRAINTS.name == "bedrock"
+        assert BEDROCK_CONSTRAINTS.image is not None
+        assert BEDROCK_CONSTRAINTS.image.max_size_bytes == 4_608_000
+        assert BEDROCK_CONSTRAINTS.pdf is not None
+        assert BEDROCK_CONSTRAINTS.supports_file_upload is False
+
+
+class TestGetConstraintsForProvider:
+    """Tests for get_constraints_for_provider function."""
+
+    def test_get_by_exact_name(self):
+        """Test getting constraints by exact provider name."""
+        result = get_constraints_for_provider("anthropic")
+        assert result == ANTHROPIC_CONSTRAINTS
+
+        result = get_constraints_for_provider("openai")
+        assert result == OPENAI_CONSTRAINTS
+
+        result = get_constraints_for_provider("gemini")
+        assert result == GEMINI_CONSTRAINTS
+
+    def test_get_by_alias(self):
+        """Test getting constraints by alias name."""
+        result = get_constraints_for_provider("claude")
+        assert result == ANTHROPIC_CONSTRAINTS
+
+        result = get_constraints_for_provider("gpt")
+        assert result == OPENAI_CONSTRAINTS
+
+        result = get_constraints_for_provider("google")
+        assert result == GEMINI_CONSTRAINTS
+
+    def test_get_case_insensitive(self):
+        """Test case-insensitive lookup."""
+        result = get_constraints_for_provider("ANTHROPIC")
+        assert result == ANTHROPIC_CONSTRAINTS
+
+        result = get_constraints_for_provider("OpenAI")
+        assert result == OPENAI_CONSTRAINTS
+
+    def test_get_with_provider_constraints_object(self):
+        """Test passing ProviderConstraints object returns it unchanged."""
+        custom = ProviderConstraints(name="custom")
+        result = get_constraints_for_provider(custom)
+        assert result is custom
+
+    def test_get_unknown_provider(self):
+        """Test unknown provider returns None."""
+        result = get_constraints_for_provider("unknown-provider")
+        assert result is None
+
+    def test_get_by_partial_match(self):
+        """Test partial match in provider string."""
+        result = get_constraints_for_provider("claude-3-sonnet")
+        assert result == ANTHROPIC_CONSTRAINTS
+
+        result = get_constraints_for_provider("gpt-4o")
+        assert result == OPENAI_CONSTRAINTS
+
+        result = get_constraints_for_provider("gemini-pro")
+        assert result == GEMINI_CONSTRAINTS

lib/crewai/tests/utilities/files/processing/test_processor.py

@@ -0,0 +1,220 @@
+"""Tests for FileProcessor class."""
+
+import pytest
+
+from crewai.utilities.files import FileBytes, ImageFile, PDFFile, TextFile
+from crewai.utilities.files.processing.constraints import (
+    ANTHROPIC_CONSTRAINTS,
+    ImageConstraints,
+    PDFConstraints,
+    ProviderConstraints,
+)
+from crewai.utilities.files.processing.enums import FileHandling
+from crewai.utilities.files.processing.exceptions import (
+    FileTooLargeError,
+    FileValidationError,
+)
+from crewai.utilities.files.processing.processor import FileProcessor
+
+
+# Minimal valid PNG: 8x8 pixel RGB image (valid for PIL)
+MINIMAL_PNG = bytes([
+    0x89, 0x50, 0x4e, 0x47, 0x0d, 0x0a, 0x1a, 0x0a, 0x00, 0x00, 0x00, 0x0d,
+    0x49, 0x48, 0x44, 0x52, 0x00, 0x00, 0x00, 0x08, 0x00, 0x00, 0x00, 0x08,
+    0x08, 0x02, 0x00, 0x00, 0x00, 0x4b, 0x6d, 0x29, 0xdc, 0x00, 0x00, 0x00,
+    0x12, 0x49, 0x44, 0x41, 0x54, 0x78, 0x9c, 0x63, 0xfc, 0xcf, 0x80, 0x1d,
+    0x30, 0xe1, 0x10, 0x1f, 0xa4, 0x12, 0x00, 0xcd, 0x41, 0x01, 0x0f, 0xe8,
+    0x41, 0xe2, 0x6f, 0x00, 0x00, 0x00, 0x00, 0x49, 0x45, 0x4e, 0x44, 0xae,
+    0x42, 0x60, 0x82,
+])
+
+# Minimal valid PDF
+MINIMAL_PDF = (
+    b"%PDF-1.4\n1 0 obj<</Type/Catalog/Pages 2 0 R>>endobj "
+    b"2 0 obj<</Type/Pages/Kids[3 0 R]/Count 1>>endobj "
+    b"3 0 obj<</Type/Page/MediaBox[0 0 612 792]/Parent 2 0 R>>endobj "
+    b"xref\n0 4\n0000000000 65535 f \n0000000009 00000 n \n"
+    b"0000000052 00000 n \n0000000101 00000 n \n"
+    b"trailer<</Size 4/Root 1 0 R>>\nstartxref\n178\n%%EOF"
+)
+
+
+class TestFileProcessorInit:
+    """Tests for FileProcessor initialization."""
+
+    def test_init_with_constraints(self):
+        """Test initialization with ProviderConstraints."""
+        processor = FileProcessor(constraints=ANTHROPIC_CONSTRAINTS)
+
+        assert processor.constraints == ANTHROPIC_CONSTRAINTS
+
+    def test_init_with_provider_string(self):
+        """Test initialization with provider name string."""
+        processor = FileProcessor(constraints="anthropic")
+
+        assert processor.constraints == ANTHROPIC_CONSTRAINTS
+
+    def test_init_with_unknown_provider(self):
+        """Test initialization with unknown provider sets constraints to None."""
+        processor = FileProcessor(constraints="unknown")
+
+        assert processor.constraints is None
+
+    def test_init_with_none_constraints(self):
+        """Test initialization with None constraints."""
+        processor = FileProcessor(constraints=None)
+
+        assert processor.constraints is None
+
+
+class TestFileProcessorValidate:
+    """Tests for FileProcessor.validate method."""
+
+    def test_validate_valid_file(self):
+        """Test validating a valid file returns no errors."""
+        processor = FileProcessor(constraints=ANTHROPIC_CONSTRAINTS)
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
+
+        errors = processor.validate(file)
+
+        assert len(errors) == 0
+
+    def test_validate_without_constraints(self):
+        """Test validating without constraints returns empty list."""
+        processor = FileProcessor(constraints=None)
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
+
+        errors = processor.validate(file)
+
+        assert len(errors) == 0
+
+    def test_validate_strict_raises_on_error(self):
+        """Test STRICT mode raises on validation error."""
+        constraints = ProviderConstraints(
+            name="test",
+            image=ImageConstraints(max_size_bytes=10),
+        )
+        processor = FileProcessor(constraints=constraints)
+        # Set mode to strict on the file
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="strict")
+
+        with pytest.raises(FileTooLargeError):
+            processor.validate(file)
+
+
+class TestFileProcessorProcess:
+    """Tests for FileProcessor.process method."""
+
+    def test_process_valid_file(self):
+        """Test processing a valid file returns it unchanged."""
+        processor = FileProcessor(constraints=ANTHROPIC_CONSTRAINTS)
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
+
+        result = processor.process(file)
+
+        assert result == file
+
+    def test_process_without_constraints(self):
+        """Test processing without constraints returns file unchanged."""
+        processor = FileProcessor(constraints=None)
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
+
+        result = processor.process(file)
+
+        assert result == file
+
+    def test_process_strict_raises_on_error(self):
+        """Test STRICT mode raises on processing error."""
+        constraints = ProviderConstraints(
+            name="test",
+            image=ImageConstraints(max_size_bytes=10),
+        )
+        processor = FileProcessor(constraints=constraints)
+        # Set mode to strict on the file
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="strict")
+
+        with pytest.raises(FileTooLargeError):
+            processor.process(file)
+
+    def test_process_warn_returns_file(self):
+        """Test WARN mode returns file with warning."""
+        constraints = ProviderConstraints(
+            name="test",
+            image=ImageConstraints(max_size_bytes=10),
+        )
+        processor = FileProcessor(constraints=constraints)
+        # Set mode to warn on the file
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="warn")
+
+        result = processor.process(file)
+
+        assert result == file
+
+
+class TestFileProcessorProcessFiles:
+    """Tests for FileProcessor.process_files method."""
+
+    def test_process_files_multiple(self):
+        """Test processing multiple files."""
+        processor = FileProcessor(constraints=ANTHROPIC_CONSTRAINTS)
+        files = {
+            "image1": ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test1.png")),
+            "image2": ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test2.png")),
+        }
+
+        result = processor.process_files(files)
+
+        assert len(result) == 2
+        assert "image1" in result
+        assert "image2" in result
+
+    def test_process_files_empty(self):
+        """Test processing empty files dict."""
+        processor = FileProcessor(constraints=ANTHROPIC_CONSTRAINTS)
+
+        result = processor.process_files({})
+
+        assert result == {}
+
+
+class TestFileHandlingEnum:
+    """Tests for FileHandling enum."""
+
+    def test_enum_values(self):
+        """Test all enum values are accessible."""
+        assert FileHandling.STRICT.value == "strict"
+        assert FileHandling.AUTO.value == "auto"
+        assert FileHandling.WARN.value == "warn"
+        assert FileHandling.CHUNK.value == "chunk"
+
+
+class TestFileProcessorPerFileMode:
+    """Tests for per-file mode handling."""
+
+    def test_file_default_mode_is_auto(self):
+        """Test that files default to auto mode."""
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
+        assert file.mode == "auto"
+
+    def test_file_custom_mode(self):
+        """Test setting custom mode on file."""
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="strict")
+        assert file.mode == "strict"
+
+    def test_processor_respects_file_mode(self):
+        """Test processor uses each file's mode setting."""
+        constraints = ProviderConstraints(
+            name="test",
+            image=ImageConstraints(max_size_bytes=10),
+        )
+        processor = FileProcessor(constraints=constraints)
+
+        # File with strict mode should raise
+        strict_file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="strict")
+        with pytest.raises(FileTooLargeError):
+            processor.process(strict_file)
+
+        # File with warn mode should not raise
+        warn_file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="warn")
+        result = processor.process(warn_file)
+        assert result == warn_file

lib/crewai/tests/utilities/files/processing/test_validators.py

@@ -0,0 +1,208 @@
+"""Tests for file validators."""
+
+import pytest
+
+from crewai.utilities.files import FileBytes, ImageFile, PDFFile, TextFile
+from crewai.utilities.files.processing.constraints import (
+    ANTHROPIC_CONSTRAINTS,
+    ImageConstraints,
+    PDFConstraints,
+    ProviderConstraints,
+)
+from crewai.utilities.files.processing.exceptions import (
+    FileTooLargeError,
+    FileValidationError,
+    UnsupportedFileTypeError,
+)
+from crewai.utilities.files.processing.validators import (
+    validate_file,
+    validate_image,
+    validate_pdf,
+    validate_text,
+)
+
+
+# Minimal valid PNG: 8x8 pixel RGB image (valid for PIL)
+MINIMAL_PNG = bytes([
+    0x89, 0x50, 0x4e, 0x47, 0x0d, 0x0a, 0x1a, 0x0a, 0x00, 0x00, 0x00, 0x0d,
+    0x49, 0x48, 0x44, 0x52, 0x00, 0x00, 0x00, 0x08, 0x00, 0x00, 0x00, 0x08,
+    0x08, 0x02, 0x00, 0x00, 0x00, 0x4b, 0x6d, 0x29, 0xdc, 0x00, 0x00, 0x00,
+    0x12, 0x49, 0x44, 0x41, 0x54, 0x78, 0x9c, 0x63, 0xfc, 0xcf, 0x80, 0x1d,
+    0x30, 0xe1, 0x10, 0x1f, 0xa4, 0x12, 0x00, 0xcd, 0x41, 0x01, 0x0f, 0xe8,
+    0x41, 0xe2, 0x6f, 0x00, 0x00, 0x00, 0x00, 0x49, 0x45, 0x4e, 0x44, 0xae,
+    0x42, 0x60, 0x82,
+])
+
+# Minimal valid PDF
+MINIMAL_PDF = (
+    b"%PDF-1.4\n1 0 obj<</Type/Catalog/Pages 2 0 R>>endobj "
+    b"2 0 obj<</Type/Pages/Kids[3 0 R]/Count 1>>endobj "
+    b"3 0 obj<</Type/Page/MediaBox[0 0 612 792]/Parent 2 0 R>>endobj "
+    b"xref\n0 4\n0000000000 65535 f \n0000000009 00000 n \n"
+    b"0000000052 00000 n \n0000000101 00000 n \n"
+    b"trailer<</Size 4/Root 1 0 R>>\nstartxref\n178\n%%EOF"
+)
+
+
+class TestValidateImage:
+    """Tests for validate_image function."""
+
+    def test_validate_valid_image(self):
+        """Test validating a valid image within constraints."""
+        constraints = ImageConstraints(
+            max_size_bytes=10 * 1024 * 1024,
+            supported_formats=("image/png",),
+        )
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
+
+        errors = validate_image(file, constraints, raise_on_error=False)
+
+        assert len(errors) == 0
+
+    def test_validate_image_too_large(self):
+        """Test validating an image that exceeds size limit."""
+        constraints = ImageConstraints(
+            max_size_bytes=10,  # Very small limit
+            supported_formats=("image/png",),
+        )
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
+
+        with pytest.raises(FileTooLargeError) as exc_info:
+            validate_image(file, constraints)
+
+        assert "exceeds" in str(exc_info.value)
+        assert exc_info.value.file_name == "test.png"
+
+    def test_validate_image_unsupported_format(self):
+        """Test validating an image with unsupported format."""
+        constraints = ImageConstraints(
+            max_size_bytes=10 * 1024 * 1024,
+            supported_formats=("image/jpeg",),  # Only JPEG
+        )
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
+
+        with pytest.raises(UnsupportedFileTypeError) as exc_info:
+            validate_image(file, constraints)
+
+        assert "not supported" in str(exc_info.value)
+
+    def test_validate_image_no_raise(self):
+        """Test validating with raise_on_error=False returns errors list."""
+        constraints = ImageConstraints(
+            max_size_bytes=10,
+            supported_formats=("image/jpeg",),
+        )
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
+
+        errors = validate_image(file, constraints, raise_on_error=False)
+
+        assert len(errors) == 2  # Size error and format error
+
+
+class TestValidatePDF:
+    """Tests for validate_pdf function."""
+
+    def test_validate_valid_pdf(self):
+        """Test validating a valid PDF within constraints."""
+        constraints = PDFConstraints(
+            max_size_bytes=10 * 1024 * 1024,
+        )
+        file = PDFFile(source=FileBytes(data=MINIMAL_PDF, filename="test.pdf"))
+
+        errors = validate_pdf(file, constraints, raise_on_error=False)
+
+        assert len(errors) == 0
+
+    def test_validate_pdf_too_large(self):
+        """Test validating a PDF that exceeds size limit."""
+        constraints = PDFConstraints(
+            max_size_bytes=10,  # Very small limit
+        )
+        file = PDFFile(source=FileBytes(data=MINIMAL_PDF, filename="test.pdf"))
+
+        with pytest.raises(FileTooLargeError) as exc_info:
+            validate_pdf(file, constraints)
+
+        assert "exceeds" in str(exc_info.value)
+
+
+class TestValidateText:
+    """Tests for validate_text function."""
+
+    def test_validate_valid_text(self):
+        """Test validating a valid text file."""
+        constraints = ProviderConstraints(
+            name="test",
+            general_max_size_bytes=10 * 1024 * 1024,
+        )
+        file = TextFile(source=FileBytes(data=b"Hello, World!", filename="test.txt"))
+
+        errors = validate_text(file, constraints, raise_on_error=False)
+
+        assert len(errors) == 0
+
+    def test_validate_text_too_large(self):
+        """Test validating text that exceeds size limit."""
+        constraints = ProviderConstraints(
+            name="test",
+            general_max_size_bytes=5,
+        )
+        file = TextFile(source=FileBytes(data=b"Hello, World!", filename="test.txt"))
+
+        with pytest.raises(FileTooLargeError):
+            validate_text(file, constraints)
+
+    def test_validate_text_no_limit(self):
+        """Test validating text with no size limit."""
+        constraints = ProviderConstraints(name="test")
+        file = TextFile(source=FileBytes(data=b"Hello, World!", filename="test.txt"))
+
+        errors = validate_text(file, constraints, raise_on_error=False)
+
+        assert len(errors) == 0
+
+
+class TestValidateFile:
+    """Tests for validate_file function."""
+
+    def test_validate_file_dispatches_to_image(self):
+        """Test validate_file dispatches to image validator."""
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
+
+        errors = validate_file(file, ANTHROPIC_CONSTRAINTS, raise_on_error=False)
+
+        assert len(errors) == 0
+
+    def test_validate_file_dispatches_to_pdf(self):
+        """Test validate_file dispatches to PDF validator."""
+        file = PDFFile(source=FileBytes(data=MINIMAL_PDF, filename="test.pdf"))
+
+        errors = validate_file(file, ANTHROPIC_CONSTRAINTS, raise_on_error=False)
+
+        assert len(errors) == 0
+
+    def test_validate_file_unsupported_type(self):
+        """Test validating a file type not supported by provider."""
+        constraints = ProviderConstraints(
+            name="test",
+            image=None,  # No image support
+        )
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
+
+        with pytest.raises(UnsupportedFileTypeError) as exc_info:
+            validate_file(file, constraints)
+
+        assert "does not support images" in str(exc_info.value)
+
+    def test_validate_file_pdf_not_supported(self):
+        """Test validating PDF when provider doesn't support it."""
+        constraints = ProviderConstraints(
+            name="test",
+            pdf=None,  # No PDF support
+        )
+        file = PDFFile(source=FileBytes(data=MINIMAL_PDF, filename="test.pdf"))
+
+        with pytest.raises(UnsupportedFileTypeError) as exc_info:
+            validate_file(file, constraints)
+
+        assert "does not support PDFs" in str(exc_info.value)

lib/crewai/tests/utilities/files/test_resolved.py

@@ -0,0 +1,135 @@
+"""Tests for resolved file types."""
+
+from datetime import datetime, timezone
+
+import pytest
+
+from crewai.utilities.files.resolved import (
+    FileReference,
+    InlineBase64,
+    InlineBytes,
+    ResolvedFile,
+    UrlReference,
+)
+
+
+class TestInlineBase64:
+    """Tests for InlineBase64 resolved type."""
+
+    def test_create_inline_base64(self):
+        """Test creating InlineBase64 instance."""
+        resolved = InlineBase64(
+            content_type="image/png",
+            data="iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg==",
+        )
+
+        assert resolved.content_type == "image/png"
+        assert len(resolved.data) > 0
+
+    def test_inline_base64_is_resolved_file(self):
+        """Test InlineBase64 is a ResolvedFile."""
+        resolved = InlineBase64(content_type="image/png", data="abc123")
+
+        assert isinstance(resolved, ResolvedFile)
+
+    def test_inline_base64_frozen(self):
+        """Test InlineBase64 is immutable."""
+        resolved = InlineBase64(content_type="image/png", data="abc123")
+
+        with pytest.raises(Exception):
+            resolved.data = "xyz789"
+
+
+class TestInlineBytes:
+    """Tests for InlineBytes resolved type."""
+
+    def test_create_inline_bytes(self):
+        """Test creating InlineBytes instance."""
+        data = b"\x89PNG\r\n\x1a\n"
+        resolved = InlineBytes(
+            content_type="image/png",
+            data=data,
+        )
+
+        assert resolved.content_type == "image/png"
+        assert resolved.data == data
+
+    def test_inline_bytes_is_resolved_file(self):
+        """Test InlineBytes is a ResolvedFile."""
+        resolved = InlineBytes(content_type="image/png", data=b"test")
+
+        assert isinstance(resolved, ResolvedFile)
+
+
+class TestFileReference:
+    """Tests for FileReference resolved type."""
+
+    def test_create_file_reference(self):
+        """Test creating FileReference instance."""
+        resolved = FileReference(
+            content_type="image/png",
+            file_id="file-abc123",
+            provider="gemini",
+        )
+
+        assert resolved.content_type == "image/png"
+        assert resolved.file_id == "file-abc123"
+        assert resolved.provider == "gemini"
+        assert resolved.expires_at is None
+        assert resolved.file_uri is None
+
+    def test_file_reference_with_expiry(self):
+        """Test FileReference with expiry time."""
+        expiry = datetime.now(timezone.utc)
+        resolved = FileReference(
+            content_type="application/pdf",
+            file_id="file-xyz789",
+            provider="gemini",
+            expires_at=expiry,
+        )
+
+        assert resolved.expires_at == expiry
+
+    def test_file_reference_with_uri(self):
+        """Test FileReference with URI."""
+        resolved = FileReference(
+            content_type="video/mp4",
+            file_id="file-video123",
+            provider="gemini",
+            file_uri="https://generativelanguage.googleapis.com/v1/files/file-video123",
+        )
+
+        assert resolved.file_uri is not None
+
+    def test_file_reference_is_resolved_file(self):
+        """Test FileReference is a ResolvedFile."""
+        resolved = FileReference(
+            content_type="image/png",
+            file_id="file-123",
+            provider="anthropic",
+        )
+
+        assert isinstance(resolved, ResolvedFile)
+
+
+class TestUrlReference:
+    """Tests for UrlReference resolved type."""
+
+    def test_create_url_reference(self):
+        """Test creating UrlReference instance."""
+        resolved = UrlReference(
+            content_type="image/png",
+            url="https://storage.googleapis.com/bucket/image.png",
+        )
+
+        assert resolved.content_type == "image/png"
+        assert resolved.url == "https://storage.googleapis.com/bucket/image.png"
+
+    def test_url_reference_is_resolved_file(self):
+        """Test UrlReference is a ResolvedFile."""
+        resolved = UrlReference(
+            content_type="image/jpeg",
+            url="https://example.com/photo.jpg",
+        )
+
+        assert isinstance(resolved, ResolvedFile)

lib/crewai/tests/utilities/files/test_resolver.py

@@ -0,0 +1,174 @@
+"""Tests for FileResolver."""
+
+import pytest
+
+from crewai.utilities.files import FileBytes, ImageFile
+from crewai.utilities.files.resolved import InlineBase64, InlineBytes
+from crewai.utilities.files.resolver import (
+    FileResolver,
+    FileResolverConfig,
+    create_resolver,
+)
+from crewai.utilities.files.upload_cache import UploadCache
+
+
+# Minimal valid PNG
+MINIMAL_PNG = (
+    b"\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x08\x00\x00\x00\x08"
+    b"\x01\x00\x00\x00\x00\xf9Y\xab\xcd\x00\x00\x00\nIDATx\x9cc`\x00\x00"
+    b"\x00\x02\x00\x01\xe2!\xbc3\x00\x00\x00\x00IEND\xaeB`\x82"
+)
+
+
+class TestFileResolverConfig:
+    """Tests for FileResolverConfig."""
+
+    def test_default_config(self):
+        """Test default configuration values."""
+        config = FileResolverConfig()
+
+        assert config.prefer_upload is False
+        assert config.upload_threshold_bytes is None
+        assert config.use_bytes_for_bedrock is True
+
+    def test_custom_config(self):
+        """Test custom configuration values."""
+        config = FileResolverConfig(
+            prefer_upload=True,
+            upload_threshold_bytes=1024 * 1024,
+            use_bytes_for_bedrock=False,
+        )
+
+        assert config.prefer_upload is True
+        assert config.upload_threshold_bytes == 1024 * 1024
+        assert config.use_bytes_for_bedrock is False
+
+
+class TestFileResolver:
+    """Tests for FileResolver class."""
+
+    def test_resolve_inline_base64(self):
+        """Test resolving file as inline base64."""
+        resolver = FileResolver()
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
+
+        resolved = resolver.resolve(file, "openai")
+
+        assert isinstance(resolved, InlineBase64)
+        assert resolved.content_type == "image/png"
+        assert len(resolved.data) > 0
+
+    def test_resolve_inline_bytes_for_bedrock(self):
+        """Test resolving file as inline bytes for Bedrock."""
+        config = FileResolverConfig(use_bytes_for_bedrock=True)
+        resolver = FileResolver(config=config)
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
+
+        resolved = resolver.resolve(file, "bedrock")
+
+        assert isinstance(resolved, InlineBytes)
+        assert resolved.content_type == "image/png"
+        assert resolved.data == MINIMAL_PNG
+
+    def test_resolve_files_multiple(self):
+        """Test resolving multiple files."""
+        resolver = FileResolver()
+        files = {
+            "image1": ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test1.png")),
+            "image2": ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test2.png")),
+        }
+
+        resolved = resolver.resolve_files(files, "openai")
+
+        assert len(resolved) == 2
+        assert "image1" in resolved
+        assert "image2" in resolved
+        assert all(isinstance(r, InlineBase64) for r in resolved.values())
+
+    def test_resolve_with_cache(self):
+        """Test resolver uses cache."""
+        cache = UploadCache()
+        resolver = FileResolver(upload_cache=cache)
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
+
+        # First resolution
+        resolved1 = resolver.resolve(file, "openai")
+        # Second resolution (should use same base64 encoding)
+        resolved2 = resolver.resolve(file, "openai")
+
+        assert isinstance(resolved1, InlineBase64)
+        assert isinstance(resolved2, InlineBase64)
+        # Data should be identical
+        assert resolved1.data == resolved2.data
+
+    def test_clear_cache(self):
+        """Test clearing resolver cache."""
+        cache = UploadCache()
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
+
+        # Add something to cache manually
+        cache.set(file=file, provider="gemini", file_id="test")
+
+        resolver = FileResolver(upload_cache=cache)
+        resolver.clear_cache()
+
+        assert len(cache) == 0
+
+    def test_get_cached_uploads(self):
+        """Test getting cached uploads from resolver."""
+        cache = UploadCache()
+        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
+
+        cache.set(file=file, provider="gemini", file_id="test-1")
+        cache.set(file=file, provider="anthropic", file_id="test-2")
+
+        resolver = FileResolver(upload_cache=cache)
+
+        gemini_uploads = resolver.get_cached_uploads("gemini")
+        anthropic_uploads = resolver.get_cached_uploads("anthropic")
+
+        assert len(gemini_uploads) == 1
+        assert len(anthropic_uploads) == 1
+
+    def test_get_cached_uploads_empty(self):
+        """Test getting cached uploads when no cache."""
+        resolver = FileResolver()  # No cache
+
+        uploads = resolver.get_cached_uploads("gemini")
+
+        assert uploads == []
+
+
+class TestCreateResolver:
+    """Tests for create_resolver factory function."""
+
+    def test_create_default_resolver(self):
+        """Test creating resolver with default settings."""
+        resolver = create_resolver()
+
+        assert resolver.config.prefer_upload is False
+        assert resolver.upload_cache is not None
+
+    def test_create_resolver_with_options(self):
+        """Test creating resolver with custom options."""
+        resolver = create_resolver(
+            prefer_upload=True,
+            upload_threshold_bytes=5 * 1024 * 1024,
+            enable_cache=False,
+        )
+
+        assert resolver.config.prefer_upload is True
+        assert resolver.config.upload_threshold_bytes == 5 * 1024 * 1024
+        assert resolver.upload_cache is None
+
+    def test_create_resolver_cache_enabled(self):
+        """Test resolver has cache when enabled."""
+        resolver = create_resolver(enable_cache=True)
+
+        assert resolver.upload_cache is not None
+
+    def test_create_resolver_cache_disabled(self):
+        """Test resolver has no cache when disabled."""
+        resolver = create_resolver(enable_cache=False)
+
+        assert resolver.upload_cache is None

lib/crewai/tests/utilities/test_file_store.py

@@ -0,0 +1,171 @@
+"""Unit tests for file_store module."""
+
+import uuid
+
+import pytest
+
+from crewai.utilities.file_store import (
+    clear_files,
+    clear_task_files,
+    get_all_files,
+    get_files,
+    get_task_files,
+    store_files,
+    store_task_files,
+)
+from crewai.utilities.files import TextFile
+
+
+class TestFileStore:
+    """Tests for synchronous file store operations."""
+
+    def setup_method(self) -> None:
+        """Set up test fixtures."""
+        self.crew_id = uuid.uuid4()
+        self.task_id = uuid.uuid4()
+        self.test_file = TextFile(source=b"test content")
+
+    def teardown_method(self) -> None:
+        """Clean up after tests."""
+        clear_files(self.crew_id)
+        clear_task_files(self.task_id)
+
+    def test_store_and_get_files(self) -> None:
+        """Test storing and retrieving crew files."""
+        files = {"doc": self.test_file}
+        store_files(self.crew_id, files)
+
+        retrieved = get_files(self.crew_id)
+
+        assert retrieved is not None
+        assert "doc" in retrieved
+        assert retrieved["doc"].read() == b"test content"
+
+    def test_get_files_returns_none_when_empty(self) -> None:
+        """Test that get_files returns None for non-existent keys."""
+        new_id = uuid.uuid4()
+        result = get_files(new_id)
+        assert result is None
+
+    def test_clear_files(self) -> None:
+        """Test clearing crew files."""
+        files = {"doc": self.test_file}
+        store_files(self.crew_id, files)
+
+        clear_files(self.crew_id)
+
+        result = get_files(self.crew_id)
+        assert result is None
+
+    def test_store_and_get_task_files(self) -> None:
+        """Test storing and retrieving task files."""
+        files = {"task_doc": self.test_file}
+        store_task_files(self.task_id, files)
+
+        retrieved = get_task_files(self.task_id)
+
+        assert retrieved is not None
+        assert "task_doc" in retrieved
+
+    def test_clear_task_files(self) -> None:
+        """Test clearing task files."""
+        files = {"task_doc": self.test_file}
+        store_task_files(self.task_id, files)
+
+        clear_task_files(self.task_id)
+
+        result = get_task_files(self.task_id)
+        assert result is None
+
+    def test_get_all_files_merges_crew_and_task(self) -> None:
+        """Test that get_all_files merges crew and task files."""
+        crew_file = TextFile(source=b"crew content")
+        task_file = TextFile(source=b"task content")
+
+        store_files(self.crew_id, {"crew_doc": crew_file})
+        store_task_files(self.task_id, {"task_doc": task_file})
+
+        merged = get_all_files(self.crew_id, self.task_id)
+
+        assert merged is not None
+        assert "crew_doc" in merged
+        assert "task_doc" in merged
+
+    def test_get_all_files_task_overrides_crew(self) -> None:
+        """Test that task files override crew files with same name."""
+        crew_file = TextFile(source=b"crew version")
+        task_file = TextFile(source=b"task version")
+
+        store_files(self.crew_id, {"shared_doc": crew_file})
+        store_task_files(self.task_id, {"shared_doc": task_file})
+
+        merged = get_all_files(self.crew_id, self.task_id)
+
+        assert merged is not None
+        assert merged["shared_doc"].read() == b"task version"
+
+    def test_get_all_files_crew_only(self) -> None:
+        """Test get_all_files with only crew files."""
+        store_files(self.crew_id, {"doc": self.test_file})
+
+        result = get_all_files(self.crew_id)
+
+        assert result is not None
+        assert "doc" in result
+
+    def test_get_all_files_returns_none_when_empty(self) -> None:
+        """Test that get_all_files returns None when no files exist."""
+        new_crew_id = uuid.uuid4()
+        new_task_id = uuid.uuid4()
+
+        result = get_all_files(new_crew_id, new_task_id)
+
+        assert result is None
+
+
+@pytest.mark.asyncio
+class TestAsyncFileStore:
+    """Tests for asynchronous file store operations."""
+
+    async def test_astore_and_aget_files(self) -> None:
+        """Test async storing and retrieving crew files."""
+        from crewai.utilities.file_store import aclear_files, aget_files, astore_files
+
+        crew_id = uuid.uuid4()
+        test_file = TextFile(source=b"async content")
+
+        try:
+            await astore_files(crew_id, {"doc": test_file})
+            retrieved = await aget_files(crew_id)
+
+            assert retrieved is not None
+            assert "doc" in retrieved
+            assert retrieved["doc"].read() == b"async content"
+        finally:
+            await aclear_files(crew_id)
+
+    async def test_aget_all_files(self) -> None:
+        """Test async get_all_files merging."""
+        from crewai.utilities.file_store import (
+            aclear_files,
+            aclear_task_files,
+            aget_all_files,
+            astore_files,
+            astore_task_files,
+        )
+
+        crew_id = uuid.uuid4()
+        task_id = uuid.uuid4()
+
+        try:
+            await astore_files(crew_id, {"crew": TextFile(source=b"crew")})
+            await astore_task_files(task_id, {"task": TextFile(source=b"task")})
+
+            merged = await aget_all_files(crew_id, task_id)
+
+            assert merged is not None
+            assert "crew" in merged
+            assert "task" in merged
+        finally:
+            await aclear_files(crew_id)
+            await aclear_task_files(task_id)