fix: Improve agent input handling and message filtering#10277
Conversation
Enhances agent.py to ensure input text is never empty, providing defaults to prevent Anthropic API errors. Updates utils.py to filter out messages with empty content and log warnings for conversion failures. Also updates starter project to set a default input value.
Introduces unit tests to verify that the AgentComponent correctly filters out empty and whitespace-only messages in chat history, and handles empty or whitespace input values without errors for both OpenAI and Anthropic models. These tests address previous issues with message validation and ensure robust input handling.
|
Important Review skippedAuto incremental reviews are disabled on this repository. Please check the settings in the CodeRabbit UI or the You can disable this status message by setting the WalkthroughUpdates agent input handling to extract and default text from message content, filters out empty messages during conversion, adjusts the Simple Agent starter’s default prompt, and adds unit tests ensuring empty/whitespace inputs are handled without errors across providers. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
actor User
participant UI as ChatInput
participant Agent as AgentComponent
participant Utils as data_to_messages
participant Model as LLM (OpenAI/Anthropic)
User->>UI: Submit message (may be empty/whitespace)
UI->>Agent: Run with input + chat_history
Agent->>Utils: Convert data to BaseMessages
Utils-->>Agent: Filtered messages (non-empty only)
Agent->>Agent: Extract text from message content<br/>(separate text_items vs images)
alt No usable text
Agent->>Agent: Set default prompt ("Process the provided images." or "Continue the conversation.")
end
Agent->>Model: input_dict with input_text + context
Model-->>Agent: Response
Agent-->>UI: Response (text/data)
note over Agent,Model: Tests assert no errors on empty/whitespace input
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Suggested labels
Suggested reviewers
Pre-merge checks and finishing touches❌ Failed checks (1 error, 2 warnings)
✅ Passed checks (4 passed)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
github-actions
Bot
added
bug
github-actions
Bot
added
bug
Codecov Report❌ Patch coverage is
❌ Your patch status has failed because the patch coverage (0.00%) is below the target coverage (40.00%). You can increase the patch coverage or adjust the target coverage. Additional details and impacted files@@ Coverage Diff @@
## main #10277 +/- ##
==========================================
- Coverage 30.22% 30.21% -0.01%
==========================================
Files 1315 1315
Lines 59290 59309 +19
Branches 8876 8882 +6
==========================================
+ Hits 17920 17921 +1
- Misses 40553 40570 +17
- Partials 817 818 +1
Flags with carried forward coverage won't be shown. Click here to find out more.
🚀 New features to boost your workflow:
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 4
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
src/lfx/src/lfx/base/agents/agent.py (1)
152-163: Fix passing a Data object to data_to_messages; wrap in a listWhen chat_history is a Data object, passing it directly to data_to_messages will iterate the object and likely error. Wrap it in a list.
Apply this diff:
- input_dict["chat_history"] = data_to_messages(self.chat_history) + input_dict["chat_history"] = data_to_messages([self.chat_history])
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (4)
src/backend/base/langflow/initial_setup/starter_projects/Simple Agent.json(1 hunks)src/backend/tests/unit/components/agents/test_agent_component.py(2 hunks)src/lfx/src/lfx/base/agents/agent.py(1 hunks)src/lfx/src/lfx/base/agents/utils.py(1 hunks)
🧰 Additional context used
📓 Path-based instructions (8)
src/backend/tests/unit/components/**/*.py
📄 CodeRabbit inference engine (.cursor/rules/backend_development.mdc)
src/backend/tests/unit/components/**/*.py: Mirror the component directory structure for unit tests in src/backend/tests/unit/components/
Use ComponentTestBaseWithClient or ComponentTestBaseWithoutClient as base classes for component unit tests
Provide file_names_mapping for backward compatibility in component tests
Create comprehensive unit tests for all new components
Files:
src/backend/tests/unit/components/agents/test_agent_component.py
{src/backend/**/*.py,tests/**/*.py,Makefile}
📄 CodeRabbit inference engine (.cursor/rules/backend_development.mdc)
{src/backend/**/*.py,tests/**/*.py,Makefile}: Run make format_backend to format Python code before linting or committing changes
Run make lint to perform linting checks on backend Python code
Files:
src/backend/tests/unit/components/agents/test_agent_component.py
src/backend/tests/unit/**/*.py
📄 CodeRabbit inference engine (.cursor/rules/backend_development.mdc)
Test component integration within flows using create_flow, build_flow, and get_build_events utilities
Files:
src/backend/tests/unit/components/agents/test_agent_component.py
src/backend/tests/**/*.py
📄 CodeRabbit inference engine (.cursor/rules/testing.mdc)
src/backend/tests/**/*.py: Unit tests for backend code must be located in the 'src/backend/tests/' directory, with component tests organized by component subdirectory under 'src/backend/tests/unit/components/'.
Test files should use the same filename as the component under test, with an appropriate test prefix or suffix (e.g., 'my_component.py' → 'test_my_component.py').
Use the 'client' fixture (an async httpx.AsyncClient) for API tests in backend Python tests, as defined in 'src/backend/tests/conftest.py'.
When writing component tests, inherit from the appropriate base class in 'src/backend/tests/base.py' (ComponentTestBase, ComponentTestBaseWithClient, or ComponentTestBaseWithoutClient) and provide the required fixtures: 'component_class', 'default_kwargs', and 'file_names_mapping'.
Each test in backend Python test files should have a clear docstring explaining its purpose, and complex setups or mocks should be well-commented.
Test both sync and async code paths in backend Python tests, using '@pytest.mark.asyncio' for async tests.
Mock external dependencies appropriately in backend Python tests to isolate unit tests from external services.
Test error handling and edge cases in backend Python tests, including using 'pytest.raises' and asserting error messages.
Validate input/output behavior and test component initialization and configuration in backend Python tests.
Use the 'no_blockbuster' pytest marker to skip the blockbuster plugin in tests when necessary.
Be aware of ContextVar propagation in async tests; test both direct event loop execution and 'asyncio.to_thread' scenarios to ensure proper context isolation.
Test error handling by mocking internal functions using monkeypatch in backend Python tests.
Test resource cleanup in backend Python tests by using fixtures that ensure proper initialization and cleanup of resources.
Test timeout and performance constraints in backend Python tests using 'asyncio.wait_for' and timing assertions.
Test Langflow's Messag...
Files:
src/backend/tests/unit/components/agents/test_agent_component.py
src/backend/**/*component*.py
📄 CodeRabbit inference engine (.cursor/rules/icons.mdc)
In your Python component class, set the
iconattribute to a string matching the frontend icon mapping exactly (case-sensitive).
Files:
src/backend/tests/unit/components/agents/test_agent_component.py
src/backend/**/components/**/*.py
📄 CodeRabbit inference engine (.cursor/rules/icons.mdc)
In your Python component class, set the
iconattribute to a string matching the frontend icon mapping exactly (case-sensitive).
Files:
src/backend/tests/unit/components/agents/test_agent_component.py
**/@(test_*.py|*.test.@(ts|tsx))
📄 CodeRabbit inference engine (coderabbit-custom-pre-merge-checks-unique-id-file-non-traceable-F7F2B60C-1728-4C9A-8889-4F2235E186CA.txt)
**/@(test_*.py|*.test.@(ts|tsx)): Check if tests have too many mock objects that obscure what's actually being tested
Warn when mocks are used instead of testing real behavior and interactions
Suggest using real objects or test doubles when mocks become excessive
Ensure mocks are used appropriately for external dependencies, not core logic
Recommend integration tests when unit tests become overly mocked
Test files should have descriptive test function names explaining what is tested
Tests should be organized logically with proper setup and teardown
Include edge cases and error conditions for comprehensive coverage
Verify tests cover both positive and negative scenarios where appropriate
Tests should cover the main functionality being implemented
Ensure tests are not just smoke tests but actually validate behavior
For API endpoints, verify both success and error response testing
Files:
src/backend/tests/unit/components/agents/test_agent_component.py
**/test_*.py
📄 CodeRabbit inference engine (coderabbit-custom-pre-merge-checks-unique-id-file-non-traceable-F7F2B60C-1728-4C9A-8889-4F2235E186CA.txt)
**/test_*.py: Check that backend test files follow naming convention: test_.py
Backend tests should be named test_.py and follow proper pytest structure
For async Python code, ensure proper async testing patterns (pytest) are used
Backend tests should follow pytest conventions; frontend tests should use Playwright
Files:
src/backend/tests/unit/components/agents/test_agent_component.py
🧬 Code graph analysis (2)
src/lfx/src/lfx/base/agents/utils.py (1)
src/backend/base/langflow/memory.py (1)
messages(310-314)
src/backend/tests/unit/components/agents/test_agent_component.py (3)
src/lfx/src/lfx/base/agents/utils.py (1)
data_to_messages(43-65)src/lfx/src/lfx/schema/message.py (1)
Message(34-297)src/lfx/src/lfx/components/agents/agent.py (1)
AgentComponent(37-601)
🪛 GitHub Actions: Ruff Style Check
src/backend/tests/unit/components/agents/test_agent_component.py
[error] 367-367: ARG002 Unused method argument: component_class
🪛 GitHub Check: Ruff Style Check (3.13)
src/backend/tests/unit/components/agents/test_agent_component.py
[failure] 367-367: Ruff (ARG002)
src/backend/tests/unit/components/agents/test_agent_component.py:367:85: ARG002 Unused method argument: default_kwargs
[failure] 367-367: Ruff (ARG002)
src/backend/tests/unit/components/agents/test_agent_component.py:367:68: ARG002 Unused method argument: component_class
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (14)
- GitHub Check: Lint Backend / Run Mypy (3.10)
- GitHub Check: Lint Backend / Run Mypy (3.11)
- GitHub Check: Lint Backend / Run Mypy (3.13)
- GitHub Check: Lint Backend / Run Mypy (3.12)
- GitHub Check: Run Frontend Tests / Determine Test Suites and Shard Distribution
- GitHub Check: Run Backend Tests / Unit Tests - Python 3.10 - Group 5
- GitHub Check: Run Backend Tests / Unit Tests - Python 3.10 - Group 4
- GitHub Check: Run Backend Tests / Unit Tests - Python 3.10 - Group 1
- GitHub Check: Run Backend Tests / Unit Tests - Python 3.10 - Group 3
- GitHub Check: Run Backend Tests / Unit Tests - Python 3.10 - Group 2
- GitHub Check: Run Backend Tests / Integration Tests - Python 3.10
- GitHub Check: Test Starter Templates
- GitHub Check: Optimize new Python code in this PR
- GitHub Check: test-starter-projects
🔇 Additional comments (1)
src/backend/base/langflow/initial_setup/starter_projects/Simple Agent.json (1)
478-479: Good default to avoid empty prompts in the starterSetting a non-empty default improves OOTB behavior and avoids provider errors.
| async def test_agent_filters_empty_chat_history_messages(self, component_class, default_kwargs): | ||
| """Test that empty messages in chat history are filtered out.""" | ||
| from lfx.base.agents.utils import data_to_messages | ||
| from lfx.schema.message import Message | ||
|
|
||
| # Create messages with varying content | ||
| empty_message = Message(text="", sender="User", sender_name="User") | ||
| whitespace_message = Message(text=" ", sender="User", sender_name="User") | ||
| valid_message = Message(text="Hello", sender="User", sender_name="User") | ||
|
|
||
| # Convert to LC messages (should filter out empty ones) | ||
| messages = data_to_messages([empty_message, whitespace_message, valid_message]) | ||
|
|
||
| # Should only have the valid message | ||
| assert len(messages) == 1 | ||
| assert messages[0].content == "Hello" | ||
|
|
There was a problem hiding this comment.
Fix Ruff ARG002: mark unused fixtures as used
component_class and default_kwargs are required fixtures but unused here; delete them to satisfy Ruff.
Apply this diff:
async def test_agent_filters_empty_chat_history_messages(self, component_class, default_kwargs):
"""Test that empty messages in chat history are filtered out."""
from lfx.base.agents.utils import data_to_messages
from lfx.schema.message import Message
+ # Mark fixtures as intentionally unused for linting
+ del component_class, default_kwargs
# Create messages with varying content
empty_message = Message(text="", sender="User", sender_name="User")
whitespace_message = Message(text=" ", sender="User", sender_name="User")
valid_message = Message(text="Hello", sender="User", sender_name="User")📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| async def test_agent_filters_empty_chat_history_messages(self, component_class, default_kwargs): | |
| """Test that empty messages in chat history are filtered out.""" | |
| from lfx.base.agents.utils import data_to_messages | |
| from lfx.schema.message import Message | |
| # Create messages with varying content | |
| empty_message = Message(text="", sender="User", sender_name="User") | |
| whitespace_message = Message(text=" ", sender="User", sender_name="User") | |
| valid_message = Message(text="Hello", sender="User", sender_name="User") | |
| # Convert to LC messages (should filter out empty ones) | |
| messages = data_to_messages([empty_message, whitespace_message, valid_message]) | |
| # Should only have the valid message | |
| assert len(messages) == 1 | |
| assert messages[0].content == "Hello" | |
| async def test_agent_filters_empty_chat_history_messages(self, component_class, default_kwargs): | |
| """Test that empty messages in chat history are filtered out.""" | |
| from lfx.base.agents.utils import data_to_messages | |
| from lfx.schema.message import Message | |
| # Mark fixtures as intentionally unused for linting | |
| del component_class, default_kwargs | |
| # Create messages with varying content | |
| empty_message = Message(text="", sender="User", sender_name="User") | |
| whitespace_message = Message(text=" ", sender="User", sender_name="User") | |
| valid_message = Message(text="Hello", sender="User", sender_name="User") | |
| # Convert to LC messages (should filter out empty ones) | |
| messages = data_to_messages([empty_message, whitespace_message, valid_message]) | |
| # Should only have the valid message | |
| assert len(messages) == 1 | |
| assert messages[0].content == "Hello" |
🧰 Tools
🪛 GitHub Actions: Ruff Style Check
[error] 367-367: ARG002 Unused method argument: component_class
🪛 GitHub Check: Ruff Style Check (3.13)
[failure] 367-367: Ruff (ARG002)
src/backend/tests/unit/components/agents/test_agent_component.py:367:85: ARG002 Unused method argument: default_kwargs
[failure] 367-367: Ruff (ARG002)
src/backend/tests/unit/components/agents/test_agent_component.py:367:68: ARG002 Unused method argument: component_class
🤖 Prompt for AI Agents
In src/backend/tests/unit/components/agents/test_agent_component.py around lines
367 to 383, the test function declares unused fixtures component_class and
default_kwargs which triggers Ruff ARG002; remove these parameters from the test
function signature so the test becomes async def
test_agent_filters_empty_chat_history_messages(self): (or if self is not needed
remove that too) and ensure no other references to those fixtures exist inside
the test; run the test suite and Ruff to confirm the warning is resolved.
| image_dicts = [item for item in lc_message.content if item.get("type") == "image"] | ||
| lc_message.content = [item for item in lc_message.content if item.get("type") != "image"] | ||
| text_items = [item for item in lc_message.content if item.get("type") != "image"] | ||
|
|
||
| # Extract text content from remaining items | ||
| if text_items: | ||
| # If there are text items, extract their text content | ||
| input_text = " ".join(item.get("text", "") for item in text_items if item.get("type") == "text").strip() | ||
|
|
||
| # If input_text is still a list or empty, provide a default | ||
| if isinstance(input_text, list) or not input_text: | ||
| input_text = "Process the provided images." |
There was a problem hiding this comment.
Preserve images for all providers and robustly extract text
Only checking type == "image" drops OpenAI-style image blocks ('image_url'). That loses user images. Also, extract text from any blocks that have a text field.
Apply this diff:
- image_dicts = [item for item in lc_message.content if item.get("type") == "image"]
- text_items = [item for item in lc_message.content if item.get("type") != "image"]
+ image_types = {"image", "image_url", "input_image"}
+ image_dicts = [item for item in lc_message.content if isinstance(item, dict) and item.get("type") in image_types]
+ text_items = [item for item in lc_message.content if isinstance(item, dict) and item.get("type") not in image_types]
# Extract text content from remaining items
if text_items:
- # If there are text items, extract their text content
- input_text = " ".join(item.get("text", "") for item in text_items if item.get("type") == "text").strip()
+ # If there are text items, extract their text content (ignore non-text blocks)
+ input_text = " ".join(
+ str(item.get("text", "")).strip()
+ for item in text_items
+ if item.get("type") == "text"
+ ).strip()
# If input_text is still a list or empty, provide a default
if isinstance(input_text, list) or not input_text:
input_text = "Process the provided images."📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| image_dicts = [item for item in lc_message.content if item.get("type") == "image"] | |
| lc_message.content = [item for item in lc_message.content if item.get("type") != "image"] | |
| text_items = [item for item in lc_message.content if item.get("type") != "image"] | |
| # Extract text content from remaining items | |
| if text_items: | |
| # If there are text items, extract their text content | |
| input_text = " ".join(item.get("text", "") for item in text_items if item.get("type") == "text").strip() | |
| # If input_text is still a list or empty, provide a default | |
| if isinstance(input_text, list) or not input_text: | |
| input_text = "Process the provided images." | |
| image_types = {"image", "image_url", "input_image"} | |
| image_dicts = [item for item in lc_message.content if isinstance(item, dict) and item.get("type") in image_types] | |
| text_items = [item for item in lc_message.content if isinstance(item, dict) and item.get("type") not in image_types] | |
| # Extract text content from remaining items | |
| if text_items: | |
| # If there are text items, extract their text content (ignore non-text blocks) | |
| input_text = " ".join( | |
| str(item.get("text", "")).strip() | |
| for item in text_items | |
| if item.get("type") == "text" | |
| ).strip() | |
| # If input_text is still a list or empty, provide a default | |
| if isinstance(input_text, list) or not input_text: | |
| input_text = "Process the provided images." |
| List[BaseMessage]: The data as messages, filtering out any with empty content. | ||
| """ | ||
| return [value.to_lc_message() for value in data] | ||
| messages = [] | ||
| for value in data: | ||
| try: | ||
| lc_message = value.to_lc_message() | ||
| # Only add messages with non-empty content (prevents Anthropic API errors) | ||
| content = lc_message.content | ||
| if content and ((isinstance(content, str) and content.strip()) or (isinstance(content, list) and content)): | ||
| messages.append(lc_message) | ||
| else: | ||
| logger.warning("Skipping message with empty content in chat history") | ||
| except (ValueError, AttributeError) as e: | ||
| logger.warning(f"Failed to convert message to BaseMessage: {e}") | ||
| continue | ||
| return messages |
There was a problem hiding this comment.
Refine list-content emptiness check to avoid whitespace-only blocks slipping through
Non-empty list content like [{"type":"text","text":" "}] currently passes, but is effectively empty and can still trigger Anthropic’s “non-empty content” error. Keep messages only if there is at least one non-empty text block or any non-text block (e.g., image).
Apply this diff:
- messages = []
- for value in data:
+ messages = []
+ for value in data:
try:
lc_message = value.to_lc_message()
- # Only add messages with non-empty content (prevents Anthropic API errors)
- content = lc_message.content
- if content and ((isinstance(content, str) and content.strip()) or (isinstance(content, list) and content)):
- messages.append(lc_message)
- else:
- logger.warning("Skipping message with empty content in chat history")
+ # Only add messages with non-empty content (prevents Anthropic API errors)
+ content = lc_message.content
+ if isinstance(content, str):
+ if content.strip():
+ messages.append(lc_message)
+ else:
+ logger.warning("Skipping message with empty string content in chat history")
+ elif isinstance(content, list):
+ # Keep if there is any non-empty text block OR any non-text block (e.g., image/image_url)
+ has_non_empty_text = any(
+ isinstance(item, dict) and item.get("type") == "text" and str(item.get("text", "")).strip()
+ for item in content
+ )
+ has_non_text_block = any(
+ isinstance(item, dict) and item.get("type") != "text"
+ for item in content
+ )
+ if has_non_empty_text or has_non_text_block:
+ messages.append(lc_message)
+ else:
+ logger.warning("Skipping message with empty list content in chat history")
+ else:
+ logger.warning("Skipping message: unsupported content type in chat history")
except (ValueError, AttributeError) as e:
logger.warning(f"Failed to convert message to BaseMessage: {e}")
continue
return messages📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| List[BaseMessage]: The data as messages, filtering out any with empty content. | |
| """ | |
| return [value.to_lc_message() for value in data] | |
| messages = [] | |
| for value in data: | |
| try: | |
| lc_message = value.to_lc_message() | |
| # Only add messages with non-empty content (prevents Anthropic API errors) | |
| content = lc_message.content | |
| if content and ((isinstance(content, str) and content.strip()) or (isinstance(content, list) and content)): | |
| messages.append(lc_message) | |
| else: | |
| logger.warning("Skipping message with empty content in chat history") | |
| except (ValueError, AttributeError) as e: | |
| logger.warning(f"Failed to convert message to BaseMessage: {e}") | |
| continue | |
| return messages | |
| messages = [] | |
| for value in data: | |
| try: | |
| lc_message = value.to_lc_message() | |
| # Only add messages with non-empty content (prevents Anthropic API errors) | |
| content = lc_message.content | |
| if isinstance(content, str): | |
| if content.strip(): | |
| messages.append(lc_message) | |
| else: | |
| logger.warning("Skipping message with empty string content in chat history") | |
| elif isinstance(content, list): | |
| # Keep if there is any non-empty text block OR any non-text block (e.g., image/image_url) | |
| has_non_empty_text = any( | |
| isinstance(item, dict) | |
| and item.get("type") == "text" | |
| and str(item.get("text", "")).strip() | |
| for item in content | |
| ) | |
| has_non_text_block = any( | |
| isinstance(item, dict) | |
| and item.get("type") != "text" | |
| for item in content | |
| ) | |
| if has_non_empty_text or has_non_text_block: | |
| messages.append(lc_message) | |
| else: | |
| logger.warning("Skipping message with empty list content in chat history") | |
| else: | |
| logger.warning("Skipping message: unsupported content type in chat history") | |
| except (ValueError, AttributeError) as e: | |
| logger.warning(f"Failed to convert message to BaseMessage: {e}") | |
| continue | |
| return messages |
🤖 Prompt for AI Agents
In src/lfx/src/lfx/base/agents/utils.py around lines 50 to 65, the check
allowing list content like [{"type":"text","text":" "}] slips through as
non-empty; change the validation so a list is considered non-empty only if it
contains at least one non-empty text block (text field with .strip() truthy) or
at least one non-text block (any item whose type != "text" or lacks a text
field). Update the condition that tests list content to iterate the list and set
a flag when a valid block is found (non-empty text or non-text), and only append
lc_message when that flag is true; keep the existing logging for skipped or
failed conversions.
…er to send images in the playground with the agent component
github-actions
Bot
added
bug
Frontend Unit Test Coverage ReportCoverage Summary
Unit Test Results
|
github-actions
Bot
added
bug
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
github-actions
Bot
added
bug
github-actions
Bot
added
bug
github-actions
Bot
added
bug
github-actions
Bot
added
bug
github-actions
Bot
added
bug
|
github-actions
Bot
added
bug
github-actions
Bot
added
bug
The parameters 'component_class' and 'default_kwargs' were removed from the 'test_agent_filters_empty_chat_history_messages' test as they were not used. This simplifies the test signature.
github-actions
Bot
added
bug
…10277) * Improve agent input handling and message filtering Enhances agent.py to ensure input text is never empty, providing defaults to prevent Anthropic API errors. Updates utils.py to filter out messages with empty content and log warnings for conversion failures. Also updates starter project to set a default input value. * Add tests for agent handling of empty and whitespace input Introduces unit tests to verify that the AgentComponent correctly filters out empty and whitespace-only messages in chat history, and handles empty or whitespace input values without errors for both OpenAI and Anthropic models. These tests address previous issues with message validation and ensure robust input handling. * [autofix.ci] apply automated fixes * ✨ (general-bugs-agent-anthropic-integration.spec.ts): add test for user to send images in the playground with the agent component * Update src/lfx/src/lfx/base/agents/agent.py Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> * [autofix.ci] apply automated fixes * Remove unused test parameters in agent component tests The parameters 'component_class' and 'default_kwargs' were removed from the 'test_agent_filters_empty_chat_history_messages' test as they were not used. This simplifies the test signature. --------- Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com> Co-authored-by: cristhianzl <cristhian.lousa@gmail.com> Co-authored-by: Carlos Coelho <80289056+carlosrcoelho@users.noreply.github.com> Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
3 participants
Enhances agent.py to ensure input text is never empty, providing defaults to prevent Anthropic API errors. Updates utils.py to filter out messages with empty content and log warnings for conversion failures. Also updates starter project to set a default input value.
Summary by CodeRabbit