mojentic 0.9.0__py3-none-any.whl → 1.0.1__py3-none-any.whl

_examples/async_dispatcher_example.py

@@ -62,7 +62,11 @@ class TextAnalyzerAgent(BaseAsyncLLMAgent):
     def __init__(self, llm: LLMBroker):
         super().__init__(
             llm=llm,
-            behaviour="You are a text analysis assistant. Your job is to provide a detailed analysis of the given text, including key themes, structure, and notable elements.",
+            behaviour=(
+                "You are a text analysis assistant. "
+                "Your job is to provide a detailed analysis of the given text, "
+                "including key themes, structure, and notable elements."
+            ),
             response_model=AnalysisResponse
         )
 
@@ -93,7 +97,11 @@ class TextSummarizerAgent(BaseAsyncLLMAgent):
     def __init__(self, llm: LLMBroker):
         super().__init__(
             llm=llm,
-            behaviour="You are a text summarization assistant. Your job is to provide concise, accurate summaries of texts while preserving the key information and main points.",
+            behaviour=(
+                "You are a text summarization assistant. "
+                "Your job is to provide concise, accurate summaries of texts "
+                "while preserving the key information and main points."
+            ),
             response_model=SummaryResponse
         )
 
@@ -143,8 +151,8 @@ Analysis: {analysis_event.analysis}
 
 Summary: {summary_event.summary}
 
-Please create a well-structured, insightful report that integrates the analysis and summary, 
-highlighting the most important aspects of the text. The report should provide a comprehensive 
+Please create a well-structured, insightful report that integrates the analysis and summary,
+highlighting the most important aspects of the text. The report should provide a comprehensive
 understanding of the text's content, structure, and significance.
 """
             # Create a temporary LLM agent to generate the response

_examples/async_llm_example.py

@@ -5,14 +5,13 @@ This script shows how to create and use asynchronous LLM agents with the AsyncDi
 """
 
 import asyncio
-from typing import List, Optional
+from typing import List
 
 from pydantic import BaseModel, Field
 
 from mojentic.agents.async_aggregator_agent import AsyncAggregatorAgent
 from mojentic.agents.async_llm_agent import BaseAsyncLLMAgent
 from mojentic.async_dispatcher import AsyncDispatcher
-from mojentic.context.shared_working_memory import SharedWorkingMemory
 from mojentic.event import Event
 from mojentic.llm import LLMBroker
 from mojentic.router import Router

_examples/broker_as_tool.py

@@ -2,7 +2,7 @@ import os
 from mojentic.agents.base_llm_agent import BaseLLMAgent
 from mojentic.llm.llm_broker import LLMBroker
 from mojentic.llm.tools.date_resolver import ResolveDateTool
-from mojentic.llm.tools.file_manager import FileManager, ListFilesTool, ReadFileTool, WriteFileTool, FilesystemGateway
+from mojentic.llm.tools.file_manager import ListFilesTool, ReadFileTool, WriteFileTool, FilesystemGateway
 from mojentic.llm.tools.tool_wrapper import ToolWrapper
 
 #
@@ -12,7 +12,10 @@ from mojentic.llm.tools.tool_wrapper import ToolWrapper
 temporal_specialist = BaseLLMAgent(
     llm=LLMBroker(model="qwen3:7b"),
     tools=[ResolveDateTool()],
-    behaviour="You are a historian and sociologist who focuses on sorting out temporal events, determining what happened or will happen when."
+    behaviour=(
+        "You are a historian and sociologist who focuses on sorting out temporal events, "
+        "determining what happened or will happen when."
+    )
 )
 
 if not os.path.exists("local"):
@@ -28,31 +31,53 @@ knowledge_specialist = BaseLLMAgent(
         ReadFileTool(fs),
         WriteFileTool(fs),
     ],
-    behaviour="You are a knowledge management agent who focuses on sorting out facts and information, able to organize elemental ideas and make connections between them. You can list files to find out where you stored information, read files to review that information, and write files to store that information for later retrieval."
+    behaviour=(
+        "You are a knowledge management agent who focuses on sorting out facts and information, "
+        "able to organize elemental ideas and make connections between them. You can list files "
+        "to find out where you stored information, read files to review that information, and "
+        "write files to store that information for later retrieval."
+    )
 )
 
 
-
 coordinator = BaseLLMAgent(
     llm=LLMBroker(model="qwen3:32b"),
     behaviour="You are a coordinator who can manage multiple agents and delegate tasks to them to solve problems.",
     tools=[
-        ToolWrapper(temporal_specialist, "temporal_specialist", "A historian and sociologist who focuses on sorting out temporal events, figuring out dates, determining what happened or will happen when."),
-        ToolWrapper(knowledge_specialist, "knowledge_specialist", "A knowledge management specialist who focuses on sorting out facts and information, able to organize elemental ideas and make connections between them. Can list files to find out where you stored information, read files to review that information, and write files to store that information for later retrieval."),
+        ToolWrapper(
+            temporal_specialist,
+            "temporal_specialist",
+            "A historian and sociologist who focuses on sorting out temporal events, figuring out "
+            "dates, determining what happened or will happen when."
+        ),
+        ToolWrapper(
+            knowledge_specialist,
+            "knowledge_specialist",
+            "A knowledge management specialist who focuses on sorting out facts and information, "
+            "able to organize elemental ideas and make connections between them. Can list files to "
+            "find out where you stored information, read files to review that information, and "
+            "write files to store that information for later retrieval."
+        ),
     ]
 )
 
-result = coordinator.generate_response("""
-
+result = coordinator.generate_response(
+    """
 I have several things I need to do this week:
 
-- On Monday, I need to ensure that I have called Scotiabank and ordered replacement cards for my current, credit, and line of credit accounts.
-- On Wednesday, I need to drive into Toronto for work. While in Toronto I need to pick up razors. I need to make sure I see Gregg, Britney and Vikram.
+- On Monday, I need to ensure that I have called Scotiabank and ordered replacement cards for "
+  "my current, credit, and line of credit accounts.
+- On Wednesday, I need to drive into Toronto for work. While in Toronto I need to pick up "
+  "razors. I need to make sure I see Gregg, Britney and Vikram.
 - On Thursday, I need to ensure I'm up by 7am so that I can be showered and ready for work by 9.
-- On Friday, I need to ensure that I have my laundry done and my bags packed for my trip to Ottawa.
+- On Friday, I need to ensure that I have my laundry done and my bags packed for my trip to "
+  "Ottawa.
 
-Create me a markdown file for each day of the week, named "YYYY-MM-DD-ToDo.md" where the date is the date of that day.
-Make a list of to-do items in the markdown file, and add a section for the day's daily notes that I can fill out each day.
-""")
+Create me a markdown file for each day of the week, named "YYYY-MM-DD-ToDo.md" where the date "
+"is the date of that day.
+Make a list of to-do items in the markdown file, and add a section for the day's daily notes that "
+"I can fill out each day.
+"""
+)
 
 print(result)

_examples/broker_examples.py

@@ -1,18 +1,16 @@
 import logging
 import os
-
-from mojentic.llm import LLMBroker
-from mojentic.llm.gateways import OpenAIGateway
-
-logging.basicConfig(level=logging.WARN)
-
 from pathlib import Path
 
 from pydantic import BaseModel, Field
 
+from mojentic.llm import LLMBroker
+from mojentic.llm.gateways import OpenAIGateway
 from mojentic.llm.gateways.models import LLMMessage
 from mojentic.llm.tools.date_resolver import ResolveDateTool
 
+logging.basicConfig(level=logging.WARN)
+
 
 def openai_llm(model="gpt-5"):
     api_key = os.getenv("OPENAI_API_KEY")

_examples/characterize_ollama.py

@@ -1,7 +1,7 @@
 from ollama import chat
 from pydantic import BaseModel, Field
 
-from mojentic.llm.gateways.models import LLMMessage, MessageRole
+from mojentic.llm.gateways.models import LLMMessage
 from mojentic.llm.gateways.ollama import OllamaGateway
 from mojentic.llm.tools.date_resolver import ResolveDateTool
 

_examples/characterize_openai.py

@@ -2,7 +2,7 @@ import os
 
 from pydantic import BaseModel, Field
 
-from mojentic.llm.gateways.models import LLMMessage, MessageRole
+from mojentic.llm.gateways.models import LLMMessage
 from mojentic.llm.gateways.openai import OpenAIGateway
 
 api_key = os.getenv("OPENAI_API_KEY")

_examples/chat_session.py

@@ -9,4 +9,4 @@ while True:
         break
     else:
         response = chat_session.send(query)
-        print(response)
+        print(response)

_examples/chat_session_with_tool.py

@@ -10,4 +10,4 @@ while True:
         break
     else:
         response = chat_session.send(query)
-        print(response)
+        print(response)

_examples/coding_file_tool.py

@@ -30,7 +30,7 @@ from mojentic.llm.tools.file_manager import (
     EditFileWithDiffTool, CreateDirectoryTool, FilesystemGateway
 )
 
-base_dir = Path(__file__).parent.parent.parent.parent / "code-playground2"
+base_dir = Path(__file__).parent.parent.parent.parent / "code-playground3"
 
 # Initialize the LLM broker
 
@@ -38,9 +38,7 @@ api_key = os.getenv("OPENAI_API_KEY")
 gateway = OpenAIGateway(api_key)
 llm = LLMBroker(model="o4-mini", gateway=gateway)
 
-# llm = LLMBroker("qwen3-coder:30b")
 llm = LLMBroker("qwen3-coder:30b")
-# llm = LLMBroker(model="qwen3-128k:32b")
 
 # Create a filesystem gateway for the sandbox
 fs = FilesystemGateway(base_path=str(base_dir))

_examples/current_datetime_tool_example.py

@@ -25,4 +25,4 @@ result = llm.generate(
 )
 
 print("\nLLM Response with custom format:")
-print(result)
+print(result)

_examples/embeddings.py

@@ -6,4 +6,4 @@ ollama = OllamaGateway()
 print(len(ollama.calculate_embeddings("Hello, world!")))
 
 openai = OpenAIGateway(os.environ["OPENAI_API_KEY"])
-print(len(openai.calculate_embeddings("Hello, world!")))
+print(len(openai.calculate_embeddings("Hello, world!")))

_examples/ephemeral_task_manager_example.py

@@ -2,13 +2,6 @@
 Example script demonstrating the usage of the ephemeral task manager tools.
 """
 import logging
-import os
-
-from mojentic.llm.gateways import OpenAIGateway
-
-logging.basicConfig(
-    level=logging.WARN
-)
 
 from mojentic.llm import LLMBroker
 from mojentic.llm.gateways.models import LLMMessage
@@ -24,13 +17,24 @@ from mojentic.llm.tools.ephemeral_task_manager import (
 )
 from mojentic.llm.tools.tell_user_tool import TellUserTool
 
+logging.basicConfig(
+    level=logging.WARN
+)
+
 # llm = LLMBroker(model="qwen3:30b-a3b-q4_K_M")
 # llm = LLMBroker(model="qwen3:32b")
 llm = LLMBroker(model="qwen3:7b")
 # llm = LLMBroker(model="qwen3:72b")
 # llm = LLMBroker(model="o4-mini", gateway=OpenAIGateway(os.environ["OPENAI_API_KEY"]))
 message = LLMMessage(
-    content="I want you to count from 1 to 10. Break that request down into individual tasks, track them using available tools, and perform them one by one until you're finished. Interrupt me to tell the user as you complete every task.")
+    content=(
+        "I want you to count from 1 to 10. "
+        "Break that request down into individual tasks, "
+        "track them using available tools, "
+        "and perform them one by one until you're finished. "
+        "Interrupt me to tell the user as you complete every task."
+    )
+)
 task_list = EphemeralTaskList()
 tools = [
     AppendTaskTool(task_list),
@@ -45,4 +49,4 @@ tools = [
 
 result = llm.generate(messages=[message], tools=tools, temperature=0.0)
 print(result)
-print(task_list.list_tasks())
+print(task_list.list_tasks())

_examples/fetch_openai_models.py

@@ -5,6 +5,7 @@ Script to fetch current OpenAI models and update the registry with up-to-date mo
 import os
 from mojentic.llm.gateways.openai import OpenAIGateway
 
+
 def fetch_current_openai_models():
     """Fetch the current list of OpenAI models."""
     api_key = os.getenv("OPENAI_API_KEY")
@@ -20,6 +21,7 @@ def fetch_current_openai_models():
         print(f"ERROR: Failed to fetch models from OpenAI API: {e}")
         return None
 
+
 def categorize_models(models):
     """Categorize models by type based on naming patterns."""
     reasoning_models = []
@@ -32,7 +34,7 @@ def categorize_models(models):
 
         # Reasoning models: o1, o3, o4, and gpt-5 series
         if (any(pattern in model_lower for pattern in ['o1-', 'o3-', 'o4-', 'gpt-5']) or
-            model_lower in ['o1', 'o3', 'o4', 'gpt-5']):
+                model_lower in ['o1', 'o3', 'o4', 'gpt-5']):
             reasoning_models.append(model)
         elif 'embedding' in model_lower:
             embedding_models.append(model)
@@ -48,6 +50,7 @@ def categorize_models(models):
         'other': sorted(other_models)
     }
 
+
 def print_model_lists(categorized_models):
     """Print the categorized models in a format ready for the registry."""
     print("=== Current OpenAI Models ===\n")
@@ -84,6 +87,7 @@ def print_model_lists(categorized_models):
         print(f'#     "{model}",')
     print("# ]\n")
 
+
 if __name__ == "__main__":
     print("Fetching current OpenAI models...")
     models = fetch_current_openai_models()
@@ -99,6 +103,9 @@ if __name__ == "__main__":
         print(f"Embedding models: {len(categorized['embedding'])}")
         print(f"Other models: {len(categorized['other'])}")
 
-        print("\nCopy the model lists above and update the _initialize_default_models() method in openai_model_registry.py")
+        print(
+            "\nCopy the model lists above and update the "
+            "_initialize_default_models() method in openai_model_registry.py"
+        )
     else:
-        print("Failed to fetch models. Please check your API key and try again.")
+        print("Failed to fetch models. Please check your API key and try again.")

_examples/file_deduplication.py

@@ -14,9 +14,9 @@ message_builder.add_images(image_path, image_path)  # Adding the same image twic
 
 # Build the message and check the number of images
 message = message_builder.build()
-print(f"Number of images in message: {len(message.image_paths)}")
-print(f"Expected number of images: 1")
-print(f"De-duplication working: {len(message.image_paths) == 1}")
+print("Number of images in message: {len(message.image_paths)}")
+print("Expected number of images: 1")
+print("De-duplication working: {len(message.image_paths) == 1}")
 
 # Test de-duplication of files
 print("\nTesting file de-duplication:")
@@ -31,8 +31,8 @@ message_builder.add_files(file_path, file_path)  # Adding the same file twice mo
 # Build the message and check the number of files
 message = message_builder.build()
 # Since we're using the file content in the message, we need to check file_paths directly
-print(f"Number of files in message_builder.file_paths: {len(message_builder.file_paths)}")
-print(f"Expected number of files: 1")
-print(f"De-duplication working: {len(message_builder.file_paths) == 1}")
+print("Number of files in message_builder.file_paths: {len(message_builder.file_paths)}")
+print("Expected number of files: 1")
+print("De-duplication working: {len(message_builder.file_paths) == 1}")
 
 print("\nTest completed.")

_examples/image_analysis.py

@@ -1,7 +1,6 @@
-import os
 from pathlib import Path
 
-from mojentic.llm.gateways import OllamaGateway, OpenAIGateway
+from mojentic.llm.gateways import OllamaGateway
 from mojentic.llm.gateways.models import LLMMessage
 
 llmg = OllamaGateway()
@@ -18,4 +17,4 @@ response = llmg.complete(
     ],
 )
 
-print(response)
+print(response)

_examples/image_broker.py

@@ -1,7 +1,7 @@
 from pathlib import Path
 
 from mojentic.llm import LLMBroker
-from mojentic.llm.message_composers import MessagesBuilder, MessageBuilder
+from mojentic.llm.message_composers import MessageBuilder
 
 llm = LLMBroker(model="gemma3:27b")
 

_examples/image_broker_splat.py

@@ -47,4 +47,4 @@ print(f"Example 4: Added {len(message4.image_paths)} image(s)")
 # Generate a response using one of the messages (e.g., message1)
 print("\nGenerating response for Example 1...")
 result = llm.generate(messages=[message1])
-print(result)
+print(result)

_examples/iterative_solver.py

@@ -7,13 +7,13 @@ date-related query using the ResolveDateTool.
 
 import logging
 
-logging.basicConfig(level=logging.WARN)
-
 from mojentic.agents.iterative_problem_solver import IterativeProblemSolver
 from mojentic.llm.tools.date_resolver import ResolveDateTool
 from mojentic.llm.tools.ask_user_tool import AskUserTool
 from mojentic.llm import LLMBroker
 
+logging.basicConfig(level=logging.WARN)
+
 
 def main():
     # Initialize the LLM broker with your preferred model

_examples/model_characterization.py

@@ -2,6 +2,7 @@ import os
 from mojentic.llm.gateways.openai import OpenAIGateway
 from mojentic.llm.gateways.models import LLMMessage, MessageRole
 
+
 def check_model_characterization():
     """
     Test the model characterization functionality with different OpenAI models.
@@ -69,5 +70,6 @@ def check_model_characterization():
     print("\n" + "=" * 60)
     print("Model characterization test completed!")
 
+
 if __name__ == "__main__":
     check_model_characterization()

_examples/openai_gateway_enhanced_demo.py

@@ -6,11 +6,11 @@ for reasoning models vs chat models, provides detailed logging, and offers bette
 error handling.
 """
 
-import os
 from mojentic.llm.gateways.openai import OpenAIGateway
 from mojentic.llm.gateways.openai_model_registry import get_model_registry
 from mojentic.llm.gateways.models import LLMMessage, MessageRole
 
+
 def demonstrate_model_registry():
     """Demonstrate the model registry capabilities."""
     print("=== Model Registry Demonstration ===")
@@ -38,6 +38,7 @@ def demonstrate_model_registry():
     token_param = capabilities.get_token_limit_param()
     print(f"   → Defaulted to: type={capabilities.model_type.value}, token_param={token_param}")
 
+
 def demonstrate_parameter_adaptation():
     """Demonstrate parameter adaptation for different model types."""
     print("\n=== Parameter Adaptation Demonstration ===")
@@ -54,8 +55,14 @@ def demonstrate_parameter_adaptation():
     }
 
     adapted_args = gateway._adapt_parameters_for_model('o1-mini', original_args)
-    print(f"   Original: max_tokens={original_args.get('max_tokens')}, has_tools={'tools' in original_args}")
-    print(f"   Adapted: max_completion_tokens={adapted_args.get('max_completion_tokens')}, has_tools={'tools' in adapted_args}")
+    print(
+        f"   Original: max_tokens={original_args.get('max_tokens')}, "
+        f"has_tools={'tools' in original_args}"
+    )
+    print(
+        f"   Adapted: max_completion_tokens={adapted_args.get('max_completion_tokens')}, "
+        f"has_tools={'tools' in adapted_args}"
+    )
 
     print("\n2. Chat model parameter adaptation (gpt-4o):")
     original_args = {
@@ -69,6 +76,7 @@ def demonstrate_parameter_adaptation():
     print(f"   Original: max_tokens={original_args.get('max_tokens')}, has_tools={'tools' in original_args}")
     print(f"   Adapted: max_tokens={adapted_args.get('max_tokens')}, has_tools={'tools' in adapted_args}")
 
+
 def demonstrate_model_validation():
     """Demonstrate model parameter validation."""
     print("\n=== Model Validation Demonstration ===")
@@ -89,6 +97,7 @@ def demonstrate_model_validation():
     except Exception as e:
         print(f"   Validation error: {e}")
 
+
 def demonstrate_registry_extensibility():
     """Demonstrate how to extend the registry with new models."""
     print("\n=== Registry Extensibility Demonstration ===")
@@ -106,7 +115,7 @@ def demonstrate_registry_extensibility():
     )
 
     registry.register_model("o5-preview", new_capabilities)
-    print(f"   Registered o5-preview as reasoning model")
+    print("   Registered o5-preview as reasoning model")
 
     # Test the new model
     capabilities = registry.get_model_capabilities("o5-preview")
@@ -120,6 +129,7 @@ def demonstrate_registry_extensibility():
     capabilities = registry.get_model_capabilities("claude-3-opus")
     print(f"   claude-3-opus (inferred): type={capabilities.model_type.value}")
 
+
 if __name__ == "__main__":
     print("OpenAI Gateway Enhanced Infrastructure Demo")
     print("=" * 50)
@@ -137,4 +147,4 @@ if __name__ == "__main__":
     print("✓ Enhanced logging for debugging")
     print("✓ Parameter validation with helpful warnings")
     print("✓ Pattern matching for unknown models")
-    print("✓ Comprehensive test coverage")
+    print("✓ Comprehensive test coverage")

_examples/raw.py

@@ -18,4 +18,4 @@ anthropic_args = {
 
 response = client.messages.create(**anthropic_args)
 
-print(response.content[0].text)
+print(response.content[0].text)