Merge branch 'main' into acl-vector-stores

.github/workflows/coverage-badge.yml

@@ -15,6 +15,9 @@ on:
 
 jobs:
   unit-tests:
+    permissions:
+      contents: write  # for peter-evans/create-pull-request to create branch
+      pull-requests: write  # for peter-evans/create-pull-request to create a PR
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository

CONTRIBUTING.md

@@ -10,8 +10,13 @@ If in doubt, please open a [discussion](https://github.com/meta-llama/llama-stac
 
 **I'd like to contribute!**
 
-All issues are actionable (please report if they are not.) Pick one and start working on it. Thank you.
+If you are new to the project, start by looking at the issues tagged with "good first issue". If you're interested
-If you need help or guidance, comment on the issue. Issues that are extra friendly to new contributors are tagged with "contributor friendly".
+leave a comment on the issue and a triager will assign it to you.
+
+Please avoid picking up too many issues at once. This helps you stay focused and ensures that others in the community also have opportunities to contribute.
+- Try to work on only 1–2 issues at a time, especially if you’re still getting familiar with the codebase.
+- Before taking an issue, check if it’s already assigned or being actively discussed.
+- If you’re blocked or can’t continue with an issue, feel free to unassign yourself or leave a comment so others can step in.
 
 **I have a bug!**
 
@@ -41,6 +46,15 @@ If you need help or guidance, comment on the issue. Issues that are extra friend
 4. Make sure your code lints using `pre-commit`.
 5. If you haven't already, complete the Contributor License Agreement ("CLA").
 6. Ensure your pull request follows the [conventional commits format](https://www.conventionalcommits.org/en/v1.0.0/).
+7. Ensure your pull request follows the [coding style](#coding-style).
+
+
+Please keep pull requests (PRs) small and focused. If you have a large set of changes, consider splitting them into logically grouped, smaller PRs to facilitate review and testing.
+
+> [!TIP]
+> As a general guideline:
+> - Experienced contributors should try to keep no more than 5 open PRs at a time.
+> - New contributors are encouraged to have only one open PR at a time until they’re familiar with the codebase and process.
 
 ## Contributor License Agreement ("CLA")
 In order to accept your pull request, we need you to submit a CLA. You only need
@@ -140,7 +154,9 @@ uv sync
 * Don't use unicode characters in the codebase. ASCII-only is preferred for compatibility or
   readability reasons.
 * Providers configuration class should be Pydantic Field class. It should have a `description` field
-  that describes the configuration. These descriptions will be used to generate the provider documentation.
+  that describes the configuration. These descriptions will be used to generate the provider
+  documentation.
+* When possible, use keyword arguments only when calling functions.
 
 ## Common Tasks
 

llama_stack/apis/vector_dbs/vector_dbs.py

@@ -34,6 +34,7 @@ class VectorDBInput(BaseModel):
     vector_db_id: str
     embedding_model: str
     embedding_dimension: int
+    provider_id: str | None = None
     provider_vector_db_id: str | None = None
 
 

llama_stack/providers/inline/agents/meta_reference/agent_instance.py

@@ -10,6 +10,7 @@ import re
 import secrets
 import string
 import uuid
+import warnings
 from collections.abc import AsyncGenerator
 from datetime import UTC, datetime
 
@@ -911,8 +912,16 @@ async def load_data_from_url(url: str) -> str:
 
 
 async def get_raw_document_text(document: Document) -> str:
-    if not document.mime_type.startswith("text/"):
+    # Handle deprecated text/yaml mime type with warning
+    if document.mime_type == "text/yaml":
+        warnings.warn(
+            "The 'text/yaml' MIME type is deprecated. Please use 'application/yaml' instead.",
+            DeprecationWarning,
+            stacklevel=2,
+        )
+    elif not (document.mime_type.startswith("text/") or document.mime_type == "application/yaml"):
         raise ValueError(f"Unexpected document mime type: {document.mime_type}")
+
     if isinstance(document.content, URL):
         return await load_data_from_url(document.content.uri)
     elif isinstance(document.content, str):

tests/unit/providers/agent/test_get_raw_document_text.py

@@ -0,0 +1,187 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+import warnings
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import pytest
+
+from llama_stack.apis.agents import Document
+from llama_stack.apis.common.content_types import URL, TextContentItem
+from llama_stack.providers.inline.agents.meta_reference.agent_instance import get_raw_document_text
+
+
+@pytest.mark.asyncio
+async def test_get_raw_document_text_supports_text_mime_types():
+    """Test that the function accepts text/* mime types."""
+    document = Document(content="Sample text content", mime_type="text/plain")
+
+    result = await get_raw_document_text(document)
+    assert result == "Sample text content"
+
+
+@pytest.mark.asyncio
+async def test_get_raw_document_text_supports_yaml_mime_type():
+    """Test that the function accepts application/yaml mime type."""
+    yaml_content = """
+    name: test
+    version: 1.0
+    items:
+      - item1
+      - item2
+    """
+
+    document = Document(content=yaml_content, mime_type="application/yaml")
+
+    result = await get_raw_document_text(document)
+    assert result == yaml_content
+
+
+@pytest.mark.asyncio
+async def test_get_raw_document_text_supports_deprecated_text_yaml_with_warning():
+    """Test that the function accepts text/yaml but emits a deprecation warning."""
+    yaml_content = """
+    name: test
+    version: 1.0
+    items:
+      - item1
+      - item2
+    """
+
+    document = Document(content=yaml_content, mime_type="text/yaml")
+
+    with warnings.catch_warnings(record=True) as w:
+        warnings.simplefilter("always")
+        result = await get_raw_document_text(document)
+
+        # Check that result is correct
+        assert result == yaml_content
+
+        # Check that exactly one warning was issued
+        assert len(w) == 1
+        assert issubclass(w[0].category, DeprecationWarning)
+        assert "text/yaml" in str(w[0].message)
+        assert "application/yaml" in str(w[0].message)
+        assert "deprecated" in str(w[0].message).lower()
+
+
+@pytest.mark.asyncio
+async def test_get_raw_document_text_deprecated_text_yaml_with_url():
+    """Test that text/yaml works with URL content and emits warning."""
+    yaml_content = "name: test\nversion: 1.0"
+
+    with patch("llama_stack.providers.inline.agents.meta_reference.agent_instance.load_data_from_url") as mock_load:
+        mock_load.return_value = yaml_content
+
+        document = Document(content=URL(uri="https://example.com/config.yaml"), mime_type="text/yaml")
+
+        with warnings.catch_warnings(record=True) as w:
+            warnings.simplefilter("always")
+            result = await get_raw_document_text(document)
+
+            # Check that result is correct
+            assert result == yaml_content
+            mock_load.assert_called_once_with("https://example.com/config.yaml")
+
+            # Check that deprecation warning was issued
+            assert len(w) == 1
+            assert issubclass(w[0].category, DeprecationWarning)
+            assert "text/yaml" in str(w[0].message)
+
+
+@pytest.mark.asyncio
+async def test_get_raw_document_text_deprecated_text_yaml_with_text_content_item():
+    """Test that text/yaml works with TextContentItem and emits warning."""
+    yaml_content = "key: value\nlist:\n  - item1\n  - item2"
+
+    document = Document(content=TextContentItem(text=yaml_content), mime_type="text/yaml")
+
+    with warnings.catch_warnings(record=True) as w:
+        warnings.simplefilter("always")
+        result = await get_raw_document_text(document)
+
+        # Check that result is correct
+        assert result == yaml_content
+
+        # Check that deprecation warning was issued
+        assert len(w) == 1
+        assert issubclass(w[0].category, DeprecationWarning)
+        assert "text/yaml" in str(w[0].message)
+
+
+@pytest.mark.asyncio
+async def test_get_raw_document_text_rejects_unsupported_mime_types():
+    """Test that the function rejects unsupported mime types."""
+    document = Document(
+        content="Some content",
+        mime_type="application/json",  # Not supported
+    )
+
+    with pytest.raises(ValueError, match="Unexpected document mime type: application/json"):
+        await get_raw_document_text(document)
+
+
+@pytest.mark.asyncio
+async def test_get_raw_document_text_with_url_content():
+    """Test that the function handles URL content correctly."""
+    mock_response = AsyncMock()
+    mock_response.text = "Content from URL"
+
+    with patch("llama_stack.providers.inline.agents.meta_reference.agent_instance.load_data_from_url") as mock_load:
+        mock_load.return_value = "Content from URL"
+
+        document = Document(content=URL(uri="https://example.com/test.txt"), mime_type="text/plain")
+
+        result = await get_raw_document_text(document)
+        assert result == "Content from URL"
+        mock_load.assert_called_once_with("https://example.com/test.txt")
+
+
+@pytest.mark.asyncio
+async def test_get_raw_document_text_with_yaml_url():
+    """Test that the function handles YAML URLs correctly."""
+    yaml_content = "name: test\nversion: 1.0"
+
+    with patch("llama_stack.providers.inline.agents.meta_reference.agent_instance.load_data_from_url") as mock_load:
+        mock_load.return_value = yaml_content
+
+        document = Document(content=URL(uri="https://example.com/config.yaml"), mime_type="application/yaml")
+
+        result = await get_raw_document_text(document)
+        assert result == yaml_content
+        mock_load.assert_called_once_with("https://example.com/config.yaml")
+
+
+@pytest.mark.asyncio
+async def test_get_raw_document_text_with_text_content_item():
+    """Test that the function handles TextContentItem correctly."""
+    document = Document(content=TextContentItem(text="Text content item"), mime_type="text/plain")
+
+    result = await get_raw_document_text(document)
+    assert result == "Text content item"
+
+
+@pytest.mark.asyncio
+async def test_get_raw_document_text_with_yaml_text_content_item():
+    """Test that the function handles YAML TextContentItem correctly."""
+    yaml_content = "key: value\nlist:\n  - item1\n  - item2"
+
+    document = Document(content=TextContentItem(text=yaml_content), mime_type="application/yaml")
+
+    result = await get_raw_document_text(document)
+    assert result == yaml_content
+
+
+@pytest.mark.asyncio
+async def test_get_raw_document_text_rejects_unexpected_content_type():
+    """Test that the function rejects unexpected document content types."""
+    # Create a mock document that bypasses Pydantic validation
+    mock_document = MagicMock(spec=Document)
+    mock_document.mime_type = "text/plain"
+    mock_document.content = 123  # Unexpected content type (not str, URL, or TextContentItem)
+
+    with pytest.raises(ValueError, match="Unexpected document content type: <class 'int'>"):
+        await get_raw_document_text(mock_document)