Skip to content

Building AI agents, atomically

Fix typo in atomic-agents (#264)

bglglzd728f93bd0098
diff --git a/UPGRADE_DOC.md b/UPGRADE_DOC.md
index 5fc0821..a3fcd9e 100644
--- a/UPGRADE_DOC.md
+++ b/UPGRADE_DOC.md
@@ -118,7 +118,7 @@ from atomic_agents.lib.base.base_io_schema import BaseIOSchema
class MyTool(BaseTool):
input_schema = MyInputSchema
output_schema = MyOutputSchema
-
+
def run(self, params: MyInputSchema) -> MyOutputSchema:
# Tool logic
pass
@@ -141,7 +141,7 @@ class MyTool(BaseTool[MyInputSchema, MyOutputSchema]):
class CalculatorTool(BaseTool):
input_schema = CalculatorInputSchema
output_schema = CalculatorOutputSchema
-
+
# NEW
class CalculatorTool(BaseTool[CalculatorInputSchema, CalculatorOutputSchema]):
# No need for input_schema and output_schema attributes
@@ -249,15 +249,15 @@ agent = AtomicAgent[CustomInputSchema, CustomOutputSchema](
# Example with custom schemas:
from atomic_agents import BaseIOSchema
from pydantic import Field
-
+
class TranslationInput(BaseIOSchema):
text: str = Field(..., description="Text to translate")
target_language: str = Field(..., description="Target language code")
-
+
class TranslationOutput(BaseIOSchema):
translated_text: str = Field(..., description="The translated text")
confidence: float = Field(..., description="Translation confidence score")
-
+
# OLD - Schemas passed in config
agent = BaseAgent(
BaseAgentConfig(
@@ -268,7 +268,7 @@ agent = AtomicAgent[CustomInputSchema, CustomOutputSchema](
output_schema=TranslationOutput # Was here
)
)
-
+
# NEW - Schemas as type parameters
agent = AtomicAgent[TranslationInput, TranslationOutput](
AgentConfig(
@@ -290,7 +290,7 @@ agent = AtomicAgent[CustomInputSchema, CustomOutputSchema](
temperature=0.7, # Direct parameter
max_tokens=1000 # Direct parameter
)
-
+
# NEW - Grouped parameters
config = AgentConfig(
client=client,
@@ -320,7 +320,7 @@ The v2.0 upgrade brings several key benefits:
1. **Shorter imports**: Eliminated `.lib` from import paths
2. **Consistent API**: All base classes from main package
3. **Cleaner code**: More readable import statements
-4. **Better organization**:
+4. **Better organization**:
- `components` → `context` (better reflects purpose)
- `factories` → `connectors` with MCP-specific functionality grouped under `connectors.mcp`
- `connectors` structure allows future extension for agent-to-agent communications and other connectivity modules
@@ -501,14 +501,14 @@ class WeatherToolOutputSchema(BaseIOSchema):
class WeatherTool(BaseTool):
"""Tool for fetching weather information"""
-
+
input_schema = WeatherToolInputSchema
output_schema = WeatherToolOutputSchema
-
+
def __init__(self, api_key: str, config: BaseToolConfig = BaseToolConfig()):
super().__init__(config)
self.api_key = api_key
-
+
def run(self, params: WeatherToolInputSchema) -> WeatherToolOutputSchema:
# Tool implementation
response = requests.get(
@@ -543,11 +543,11 @@ class WeatherToolOutputSchema(BaseIOSchema):
class WeatherTool(BaseTool[WeatherToolInputSchema, WeatherToolOutputSchema]):
"""Tool for fetching weather information"""
-
+
def __init__(self, api_key: str, config: BaseToolConfig = BaseToolConfig()):
super().__init__(config)
self.api_key = api_key
-
+
def run(self, params: WeatherToolInputSchema) -> WeatherToolOutputSchema:
# Tool implementation (unchanged)
response = requests.get(
@@ -721,7 +721,7 @@ If you encounter import errors after upgrading:
1. Ensure all old `.lib` imports are updated
2. Check that class renames are applied:
- `BaseAgent` → `AtomicAgent`
- - `BaseAgentConfig` → `AgentConfig`
+ - `BaseAgentConfig` → `AgentConfig`
- `BaseAgentInputSchema` → `BasicChatInputSchema`
- `BaseAgentOutputSchema` → `BasicChatOutputSchema`
- `AgentMemory` → `ChatHistory`
diff --git a/agents.md b/agents.md
index 8417247..e925db1 100644
--- a/agents.md
+++ b/agents.md
@@ -391,4 +391,4 @@ criteria, and cross-reference related skills both ways.
- Shared surfaces to compose: core framework `atomic-agents/atomic_agents/` (AtomicAgent, BaseIOSchema, BaseTool, context providers, MCP connectors); CLI `atomic` (atomic-assembler); downloadable tools `atomic-forge/tools/*`; runnable examples `atomic-examples/*`
- Skill convention: frontmatter `name` + `description` (optional `allowed-tools`); one skill per dir at `.claude/skills/<name>/SKILL.md`
- Current skills: `release` (project-local); `skill-forge` + `skill-forge-setup` (installed via plugin `claude-dev-kitchen`)
-<!-- skill-forge:end -->
\ No newline at end of file
+<!-- skill-forge:end -->
diff --git a/atomic-assembler/README.md b/atomic-assembler/README.md
index e69de29..8b13789 100644
--- a/atomic-assembler/README.md
+++ b/atomic-assembler/README.md
@@ -0,0 +1 @@
+
diff --git a/atomic-examples/hooks-example/README.md b/atomic-examples/hooks-example/README.md
index 5c64fd3..e39b8f3 100644
--- a/atomic-examples/hooks-example/README.md
+++ b/atomic-examples/hooks-example/README.md
@@ -5,7 +5,7 @@ This example demonstrates the powerful hook system integration in AtomicAgent, w
## Features Demonstrated
- **🔍 Comprehensive Monitoring**: Track all aspects of agent execution
-- **🛡️ Robust Error Handling**: Graceful handling of validation and completion errors
+- **🛡️ Robust Error Handling**: Graceful handling of validation and completion errors
- **🔄 Intelligent Retry Patterns**: Implement smart retry logic based on error context
- **📊 Performance Metrics**: Monitor response times, success rates, and error patterns
- **🔧 Easy Debugging**: Detailed error information and execution flow visibility
@@ -47,7 +47,7 @@ The example demonstrates several key hook system patterns:
- Completion monitoring and metrics collection
### Advanced Error Handling
-- Comprehensive validation error analysis
+- Comprehensive validation error analysis
- Intelligent retry mechanisms with backoff strategies
- Error isolation to prevent hook failures from disrupting execution
@@ -83,7 +83,7 @@ This hook system implementation provides:
This example demonstrates the complete resolution of GitHub issue #173, showing how the AtomicAgent hook system enables:
- ✅ Parse error hooks triggering on validation failures
-- ✅ Comprehensive error context for retry mechanisms
+- ✅ Comprehensive error context for retry mechanisms
- ✅ Full Instructor hook event support
- ✅ 100% backward compatibility
- ✅ Robust error isolation
@@ -95,4 +95,4 @@ After running this example, you can:
1. Experiment with different hook combinations
2. Implement custom retry strategies
3. Add your own monitoring and alerting logic
-4. Explore integration with observability platforms
\ No newline at end of file
+4. Explore integration with observability platforms
diff --git a/atomic-examples/web-search-agent/README.md b/atomic-examples/web-search-agent/README.md
index 27580f4..57792ef 100644
--- a/atomic-examples/web-search-agent/README.md
+++ b/atomic-examples/web-search-agent/README.md
@@ -59,7 +59,7 @@ Make sure to add these lines to `settings.tml`:
SEARXNG_BASE_URL=your_searxng_instance_url
```
- Replace `your_openai_api_key` with your actual OpenAI API key and `your_searxng_instance_url` with the URL of your SearXNG instance.
+ Replace `your_openai_api_key` with your actual OpenAI API key and `your_searxng_instance_url` with the URL of your SearXNG instance.
If you do not have a SearxNG instance, see the instructions below to set up one locally with docker.
2. Run the Web Search Agent:
diff --git a/pytest.ini b/pytest.ini
index 24cac01..13c41d7 100644
--- a/pytest.ini
+++ b/pytest.ini
@@ -6,4 +6,4 @@ asyncio_default_fixture_loop_scope = function
testpaths = atomic-agents/tests
python_files = test_*.py
python_classes = Test*
-python_functions = test_*
\ No newline at end of file
+python_functions = test_*