versionhq 1.2.1.1__tar.gz → 1.2.1.2__tar.gz

{versionhq-1.2.1.1 → versionhq-1.2.1.2}/.gitignore

@@ -24,6 +24,7 @@ temp/*
 assets/*
 memo.txt
 site/
+_logs/
 
 __pycache__
 .ruff_cache/

{versionhq-1.2.1.1 → versionhq-1.2.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: versionhq
-Version: 1.2.1.1
+Version: 1.2.1.2
 Summary: An agentic orchestration framework for building agent networks that handle task automation.
 Author-email: Kuriko Iwai <kuriko@versi0n.io>
 License: MIT License
@@ -115,13 +115,12 @@ A Python framework for agentic orchestration that handles complex task automatio
   - [Forming a agent network](#forming-a-agent-network)
   - [Executing tasks](#executing-tasks)
   - [Supervising](#supervising)
-- [Supervising](#supervising-1)
 - [Technologies Used](#technologies-used)
 - [Project Structure](#project-structure)
-- [Setting Up a Project](#setting-up-a-project)
-  - [1. Installing package manager](#1-installing-package-manager)
-  - [2. Installing dependencies](#2-installing-dependencies)
-  - [3. Adding env secrets to .env file](#3-adding-env-secrets-to-env-file)
+- [Setting Up Your Project](#setting-up-your-project)
+  - [Installing package manager](#installing-package-manager)
+  - [Installing dependencies](#installing-dependencies)
+  - [Adding env secrets to .env file](#adding-env-secrets-to-env-file)
 - [Contributing](#contributing)
   - [Steps](#steps)
   - [Package Management with uv](#package-management-with-uv)
@@ -257,7 +256,7 @@ agent.update(
    res = network.launch()
    ```
 
-   This will form a network with multiple agents on `Formation` and return `TaskOutput` object with output in JSON, plane text, Pydantic model format with evaluation.
+This will form a network with multiple agents on `Formation` and return `TaskOutput` object with output in JSON, plane text, Pydantic model format with evaluation.
 
 
 ### Executing tasks
@@ -267,47 +266,45 @@ You can simply build an agent using `Agent` model and execute the task using `Ta
 By default, agents prioritize JSON over plane text outputs.
 
 
-   ```python
-   import versionhq as vhq
-   from pydantic import BaseModel
+```python
+import versionhq as vhq
+from pydantic import BaseModel
 
-   class CustomOutput(BaseModel):
-      test1: str
-      test2: list[str]
+class CustomOutput(BaseModel):
+   test1: str
+   test2: list[str]
 
-   def dummy_func(message: str, test1: str, test2: list[str]) -> str:
-      return f"""{message}: {test1}, {", ".join(test2)}"""
+def dummy_func(message: str, test1: str, test2: list[str]) -> str:
+   return f"""{message}: {test1}, {", ".join(test2)}"""
 
-   task = vhq.Task(
-      description="Amazing task",
-      pydantic_output=CustomOutput,
-      callback=dummy_func,
-      callback_kwargs=dict(message="Hi! Here is the result: ")
-   )
+task = vhq.Task(
+   description="Amazing task",
+   pydantic_output=CustomOutput,
+   callback=dummy_func,
+   callback_kwargs=dict(message="Hi! Here is the result: ")
+)
 
-   res = task.execute(context="amazing context to consider.")
-   print(res)
-   ```
+res = task.execute(context="amazing context to consider.")
+print(res)
+```
 
 
 This will return a `TaskOutput` object that stores response in plane text, JSON, and Pydantic model: `CustomOutput` formats with a callback result, tool output (if given), and evaluation results (if given).
 
-   ```python
-   res == TaskOutput(
-      task_id=UUID('<TASK UUID>'),
-      raw='{\"test1\":\"random str\", \"test2\":[\"str item 1\", \"str item 2\", \"str item 3\"]}',
-      json_dict={'test1': 'random str', 'test2': ['str item 1', 'str item 2', 'str item 3']},
-      pydantic=<class '__main__.CustomOutput'>,
-      tool_output=None,
-      callback_output='Hi! Here is the result: random str, str item 1, str item 2, str item 3', # returned a plain text summary
-      evaluation=None
-   )
-   ```
+```python
+res == TaskOutput(
+   task_id=UUID('<TASK UUID>'),
+   raw='{\"test1\":\"random str\", \"test2\":[\"str item 1\", \"str item 2\", \"str item 3\"]}',
+   json_dict={'test1': 'random str', 'test2': ['str item 1', 'str item 2', 'str item 3']},
+   pydantic=<class '__main__.CustomOutput'>,
+   tool_output=None,
+   callback_output='Hi! Here is the result: random str, str item 1, str item 2, str item 3', # returned a plain text summary
+   evaluation=None
+)
+```
 
 ### Supervising
 
-## Supervising
-
 To create an agent network with one or more manager agents, designate members using the `is_manager` tag.
 
 ```python
@@ -410,16 +407,19 @@ src/
 │     └── ...
 │
 └── uploads/  [.gitignore]    # Local directory to store uploaded files such as graphviz diagrams generatd by `Network` class
-|
+│
+└── _logs/    [.gitignore]    # Local directory to store error/warning logs for debugging
+│
+│
 pyproject.toml                # Project config
 
 ```
 
 <hr />
 
-## Setting Up a Project
+## Setting Up Your Project
 
-### 1. Installing package manager
+### Installing package manager
 
    For MacOS:
 
@@ -433,7 +433,7 @@ pyproject.toml                # Project config
    ```
 
 
-### 2. Installing dependencies
+### Installing dependencies
 
    ```
    uv venv
@@ -466,7 +466,7 @@ pyproject.toml                # Project config
 
    - `torch`/`Docling` related errors: Set up default Python version either `3.11.x` or `3.12.x` (same as AssertionError)
 
-### 3. Adding env secrets to .env file
+### Adding env secrets to .env file
 
 Create `.env` file in the project root and add following:
 
@@ -479,6 +479,7 @@ Create `.env` file in the project root and add following:
    [OTHER_LLM_INTERFACE_PROVIDER_OF_YOUR_CHOICE]_API_KEY=your-api-key
    ```
 
+
 <hr />
 
 ## Contributing
@@ -583,7 +584,7 @@ Common issues and solutions:
 
 * Issues related to dependencies: `rm -rf uv.lock`, `uv cache clean`, `uv venv`, and run `uv pip install -r requirements.txt -v`.
 
-* Issues related to the AI agents or RAG system: Check the `output.log` file for detailed error messages and stack traces.
+* Issues related to agents and other systems: Check `_logs` directory for detailed error messages and stack traces.
 
 * Issues related to `Python quit unexpectedly`: Check [this stackoverflow article](https://stackoverflow.com/questions/59888499/macos-catalina-python-quit-unexpectedly-error).
 

{versionhq-1.2.1.1 → versionhq-1.2.1.2}/README.md

@@ -34,13 +34,12 @@ A Python framework for agentic orchestration that handles complex task automatio
   - [Forming a agent network](#forming-a-agent-network)
   - [Executing tasks](#executing-tasks)
   - [Supervising](#supervising)
-- [Supervising](#supervising-1)
 - [Technologies Used](#technologies-used)
 - [Project Structure](#project-structure)
-- [Setting Up a Project](#setting-up-a-project)
-  - [1. Installing package manager](#1-installing-package-manager)
-  - [2. Installing dependencies](#2-installing-dependencies)
-  - [3. Adding env secrets to .env file](#3-adding-env-secrets-to-env-file)
+- [Setting Up Your Project](#setting-up-your-project)
+  - [Installing package manager](#installing-package-manager)
+  - [Installing dependencies](#installing-dependencies)
+  - [Adding env secrets to .env file](#adding-env-secrets-to-env-file)
 - [Contributing](#contributing)
   - [Steps](#steps)
   - [Package Management with uv](#package-management-with-uv)
@@ -176,7 +175,7 @@ agent.update(
    res = network.launch()
    ```
 
-   This will form a network with multiple agents on `Formation` and return `TaskOutput` object with output in JSON, plane text, Pydantic model format with evaluation.
+This will form a network with multiple agents on `Formation` and return `TaskOutput` object with output in JSON, plane text, Pydantic model format with evaluation.
 
 
 ### Executing tasks
@@ -186,47 +185,45 @@ You can simply build an agent using `Agent` model and execute the task using `Ta
 By default, agents prioritize JSON over plane text outputs.
 
 
-   ```python
-   import versionhq as vhq
-   from pydantic import BaseModel
+```python
+import versionhq as vhq
+from pydantic import BaseModel
 
-   class CustomOutput(BaseModel):
-      test1: str
-      test2: list[str]
+class CustomOutput(BaseModel):
+   test1: str
+   test2: list[str]
 
-   def dummy_func(message: str, test1: str, test2: list[str]) -> str:
-      return f"""{message}: {test1}, {", ".join(test2)}"""
+def dummy_func(message: str, test1: str, test2: list[str]) -> str:
+   return f"""{message}: {test1}, {", ".join(test2)}"""
 
-   task = vhq.Task(
-      description="Amazing task",
-      pydantic_output=CustomOutput,
-      callback=dummy_func,
-      callback_kwargs=dict(message="Hi! Here is the result: ")
-   )
+task = vhq.Task(
+   description="Amazing task",
+   pydantic_output=CustomOutput,
+   callback=dummy_func,
+   callback_kwargs=dict(message="Hi! Here is the result: ")
+)
 
-   res = task.execute(context="amazing context to consider.")
-   print(res)
-   ```
+res = task.execute(context="amazing context to consider.")
+print(res)
+```
 
 
 This will return a `TaskOutput` object that stores response in plane text, JSON, and Pydantic model: `CustomOutput` formats with a callback result, tool output (if given), and evaluation results (if given).
 
-   ```python
-   res == TaskOutput(
-      task_id=UUID('<TASK UUID>'),
-      raw='{\"test1\":\"random str\", \"test2\":[\"str item 1\", \"str item 2\", \"str item 3\"]}',
-      json_dict={'test1': 'random str', 'test2': ['str item 1', 'str item 2', 'str item 3']},
-      pydantic=<class '__main__.CustomOutput'>,
-      tool_output=None,
-      callback_output='Hi! Here is the result: random str, str item 1, str item 2, str item 3', # returned a plain text summary
-      evaluation=None
-   )
-   ```
+```python
+res == TaskOutput(
+   task_id=UUID('<TASK UUID>'),
+   raw='{\"test1\":\"random str\", \"test2\":[\"str item 1\", \"str item 2\", \"str item 3\"]}',
+   json_dict={'test1': 'random str', 'test2': ['str item 1', 'str item 2', 'str item 3']},
+   pydantic=<class '__main__.CustomOutput'>,
+   tool_output=None,
+   callback_output='Hi! Here is the result: random str, str item 1, str item 2, str item 3', # returned a plain text summary
+   evaluation=None
+)
+```
 
 ### Supervising
 
-## Supervising
-
 To create an agent network with one or more manager agents, designate members using the `is_manager` tag.
 
 ```python
@@ -329,16 +326,19 @@ src/
 │     └── ...
 │
 └── uploads/  [.gitignore]    # Local directory to store uploaded files such as graphviz diagrams generatd by `Network` class
-|
+│
+└── _logs/    [.gitignore]    # Local directory to store error/warning logs for debugging
+│
+│
 pyproject.toml                # Project config
 
 ```
 
 <hr />
 
-## Setting Up a Project
+## Setting Up Your Project
 
-### 1. Installing package manager
+### Installing package manager
 
    For MacOS:
 
@@ -352,7 +352,7 @@ pyproject.toml                # Project config
    ```
 
 
-### 2. Installing dependencies
+### Installing dependencies
 
    ```
    uv venv
@@ -385,7 +385,7 @@ pyproject.toml                # Project config
 
    - `torch`/`Docling` related errors: Set up default Python version either `3.11.x` or `3.12.x` (same as AssertionError)
 
-### 3. Adding env secrets to .env file
+### Adding env secrets to .env file
 
 Create `.env` file in the project root and add following:
 
@@ -398,6 +398,7 @@ Create `.env` file in the project root and add following:
    [OTHER_LLM_INTERFACE_PROVIDER_OF_YOUR_CHOICE]_API_KEY=your-api-key
    ```
 
+
 <hr />
 
 ## Contributing
@@ -502,7 +503,7 @@ Common issues and solutions:
 
 * Issues related to dependencies: `rm -rf uv.lock`, `uv cache clean`, `uv venv`, and run `uv pip install -r requirements.txt -v`.
 
-* Issues related to the AI agents or RAG system: Check the `output.log` file for detailed error messages and stack traces.
+* Issues related to agents and other systems: Check `_logs` directory for detailed error messages and stack traces.
 
 * Issues related to `Python quit unexpectedly`: Check [this stackoverflow article](https://stackoverflow.com/questions/59888499/macos-catalina-python-quit-unexpectedly-error).
 

{versionhq-1.2.1.1 → versionhq-1.2.1.2}/docs/index.md

@@ -216,7 +216,7 @@ Common issues and solutions:
 
 * Issues related to dependencies: `rm -rf uv.lock`, `uv cache clean`, `uv venv`, and run `uv pip install -r requirements.txt -v`.
 
-* Issues related to the AI agents or RAG system: Check the `output.log` file for detailed error messages and stack traces.
+* Issues related to agents and other systems: Check `_logs` directory for detailed error messages and stack traces.
 
 * Issues related to `Python quit unexpectedly`: Check [this stackoverflow article](https://stackoverflow.com/questions/59888499/macos-catalina-python-quit-unexpectedly-error).
 

{versionhq-1.2.1.1 → versionhq-1.2.1.2}/pyproject.toml

@@ -15,7 +15,7 @@ exclude = ["test*", "__pycache__", "*.egg-info"]
 
 [project]
 name = "versionhq"
-version = "1.2.1.1"
+version = "1.2.1.2"
 authors = [{ name = "Kuriko Iwai", email = "kuriko@versi0n.io" }]
 description = "An agentic orchestration framework for building agent networks that handle task automation."
 readme = "README.md"

{versionhq-1.2.1.1 → versionhq-1.2.1.2}/requirements.txt

@@ -19,3 +19,5 @@ chromadb>=0.6.3
 wheel>=0.45.1
 envoy>=0.0.3
 composio-core==0.7.0
+networkx>=3.4.2
+matplotlib>=3.10.0

{versionhq-1.2.1.1 → versionhq-1.2.1.2}/src/versionhq/__init__.py

@@ -30,7 +30,7 @@ from versionhq.memory.model import ShortTermMemory,LongTermMemory, UserMemory, M
 from versionhq.task.formation import form_agent_network
 
 
-__version__ = "1.2.1.1"
+__version__ = "1.2.1.2"
 __all__ = [
     "Agent",
 

versionhq-1.2.1.2/src/versionhq/_utils/logger.py

@@ -0,0 +1,97 @@
+import logging
+from datetime import datetime
+from typing import Optional
+
+from pydantic import BaseModel, Field, PrivateAttr
+
+
+class Printer:
+    def print(self, content: str, color: Optional[str] = None):
+        if color == "purple":
+            self._print_purple(content)
+        elif color == "red":
+            self._print_red(content)
+        elif color == "green":
+            self._print_green(content)
+        elif color == "blue":
+            self._print_blue(content)
+        elif color == "yellow":
+            self._print_yellow(content)
+        else:
+            print(content)
+
+    def _print_purple(self, content):
+        print("\033[1m\033[95m {}\033[00m".format(content))
+
+    def _print_green(self, content):
+        print("\033[1m\033[92m {}\033[00m".format(content))
+
+    def _print_red(self, content):
+        print("\033[91m {}\033[00m".format(content))
+
+    def _print_blue(self, content):
+        print("\033[1m\033[94m {}\033[00m".format(content))
+
+    def _print_yellow(self, content):
+        print("\033[1m\033[93m {}\033[00m".format(content))
+
+
+class Logger(BaseModel):
+    """
+    Control CLI messages.
+    Color: red = error, yellow = warning, blue = info (from vhq), green = info (from third parties)
+    """
+
+    verbose: bool = Field(default=True)
+    info_file_save: bool = Field(default=False, description="whether to save INFO logs")
+    _printer: Printer = PrivateAttr(default_factory=Printer)
+
+
+    def log(self, level: str, message: str, color="yellow"):
+        if self.verbose:
+            timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+            self._printer.print(f"\n{timestamp} - versionHQ [{level.upper()}]: {message}", color=color)
+
+        self._save(level=level, message=message)
+
+
+    def _save(self, level: str, message: str, filename: str = None):
+        import os
+        from pathlib import Path
+
+        if level.lower() == "info" and self.info_file_save == False:
+            return
+
+        logging_level = logging.INFO
+        match level:
+            case "warning":
+                logging_level = logging.WARNING
+            case "error":
+                logging_level = logging.ERROR
+            case _:
+                pass
+
+        cwd = Path.cwd()
+        log_file_dir = f"{cwd}/_logs"
+        os.makedirs(log_file_dir, exist_ok=True)
+        filename = filename if filename else datetime.now().strftime('%H_%M_%S_%d_%m_%Y')
+        abs_dir = f"{log_file_dir}/{filename}.log"
+
+        logging.basicConfig(filename=abs_dir, filemode='w', level=logging_level)
+        logger = logging.getLogger(__name__)
+        file_handler = logging.FileHandler(filename=abs_dir)
+        formatter = logging.Formatter('%(asctime)s : %(levelname)s : %(name)s : %(message)s')
+        file_handler.setFormatter(formatter)
+
+        for handler in logging.root.handlers[:]:
+            logging.root.removeHandler(handler)
+
+        logger.addHandler(file_handler)
+
+        match logging_level:
+            case logging.WARNING:
+                logger.warning(message)
+            case logging.ERROR:
+                logger.error(message)
+            case _:
+               logger.info(message)

{versionhq-1.2.1.1 → versionhq-1.2.1.2}/src/versionhq/task/model.py

@@ -617,6 +617,7 @@ Ref. Output image: {output_formats_to_follow}
 
         self.prompt_context = context
         task_output: InstanceOf[TaskOutput] = None
+        raw_output: str = None
         tool_output: str | list = None
         task_tools: List[List[InstanceOf[Tool]| InstanceOf[ToolSet] | Type[Tool]]] = []
         started_at, ended_at = datetime.datetime.now(), datetime.datetime.now()
@@ -673,7 +674,7 @@ Ref. Output image: {output_formats_to_follow}
         self.output = task_output
         self.processed_agents.add(agent.role)
 
-        if self.should_evaluate:
+        if self.should_evaluate and raw_output: # eval only when raw output exsits
             task_output.evaluate(task=self)
 
         self._create_short_and_long_term_memories(agent=agent, task_output=task_output)

{versionhq-1.2.1.1 → versionhq-1.2.1.2}/src/versionhq.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: versionhq
-Version: 1.2.1.1
+Version: 1.2.1.2
 Summary: An agentic orchestration framework for building agent networks that handle task automation.
 Author-email: Kuriko Iwai <kuriko@versi0n.io>
 License: MIT License
@@ -115,13 +115,12 @@ A Python framework for agentic orchestration that handles complex task automatio
   - [Forming a agent network](#forming-a-agent-network)
   - [Executing tasks](#executing-tasks)
   - [Supervising](#supervising)
-- [Supervising](#supervising-1)
 - [Technologies Used](#technologies-used)
 - [Project Structure](#project-structure)
-- [Setting Up a Project](#setting-up-a-project)
-  - [1. Installing package manager](#1-installing-package-manager)
-  - [2. Installing dependencies](#2-installing-dependencies)
-  - [3. Adding env secrets to .env file](#3-adding-env-secrets-to-env-file)
+- [Setting Up Your Project](#setting-up-your-project)
+  - [Installing package manager](#installing-package-manager)
+  - [Installing dependencies](#installing-dependencies)
+  - [Adding env secrets to .env file](#adding-env-secrets-to-env-file)
 - [Contributing](#contributing)
   - [Steps](#steps)
   - [Package Management with uv](#package-management-with-uv)
@@ -257,7 +256,7 @@ agent.update(
    res = network.launch()
    ```
 
-   This will form a network with multiple agents on `Formation` and return `TaskOutput` object with output in JSON, plane text, Pydantic model format with evaluation.
+This will form a network with multiple agents on `Formation` and return `TaskOutput` object with output in JSON, plane text, Pydantic model format with evaluation.
 
 
 ### Executing tasks
@@ -267,47 +266,45 @@ You can simply build an agent using `Agent` model and execute the task using `Ta
 By default, agents prioritize JSON over plane text outputs.
 
 
-   ```python
-   import versionhq as vhq
-   from pydantic import BaseModel
+```python
+import versionhq as vhq
+from pydantic import BaseModel
 
-   class CustomOutput(BaseModel):
-      test1: str
-      test2: list[str]
+class CustomOutput(BaseModel):
+   test1: str
+   test2: list[str]
 
-   def dummy_func(message: str, test1: str, test2: list[str]) -> str:
-      return f"""{message}: {test1}, {", ".join(test2)}"""
+def dummy_func(message: str, test1: str, test2: list[str]) -> str:
+   return f"""{message}: {test1}, {", ".join(test2)}"""
 
-   task = vhq.Task(
-      description="Amazing task",
-      pydantic_output=CustomOutput,
-      callback=dummy_func,
-      callback_kwargs=dict(message="Hi! Here is the result: ")
-   )
+task = vhq.Task(
+   description="Amazing task",
+   pydantic_output=CustomOutput,
+   callback=dummy_func,
+   callback_kwargs=dict(message="Hi! Here is the result: ")
+)
 
-   res = task.execute(context="amazing context to consider.")
-   print(res)
-   ```
+res = task.execute(context="amazing context to consider.")
+print(res)
+```
 
 
 This will return a `TaskOutput` object that stores response in plane text, JSON, and Pydantic model: `CustomOutput` formats with a callback result, tool output (if given), and evaluation results (if given).
 
-   ```python
-   res == TaskOutput(
-      task_id=UUID('<TASK UUID>'),
-      raw='{\"test1\":\"random str\", \"test2\":[\"str item 1\", \"str item 2\", \"str item 3\"]}',
-      json_dict={'test1': 'random str', 'test2': ['str item 1', 'str item 2', 'str item 3']},
-      pydantic=<class '__main__.CustomOutput'>,
-      tool_output=None,
-      callback_output='Hi! Here is the result: random str, str item 1, str item 2, str item 3', # returned a plain text summary
-      evaluation=None
-   )
-   ```
+```python
+res == TaskOutput(
+   task_id=UUID('<TASK UUID>'),
+   raw='{\"test1\":\"random str\", \"test2\":[\"str item 1\", \"str item 2\", \"str item 3\"]}',
+   json_dict={'test1': 'random str', 'test2': ['str item 1', 'str item 2', 'str item 3']},
+   pydantic=<class '__main__.CustomOutput'>,
+   tool_output=None,
+   callback_output='Hi! Here is the result: random str, str item 1, str item 2, str item 3', # returned a plain text summary
+   evaluation=None
+)
+```
 
 ### Supervising
 
-## Supervising
-
 To create an agent network with one or more manager agents, designate members using the `is_manager` tag.
 
 ```python
@@ -410,16 +407,19 @@ src/
 │     └── ...
 │
 └── uploads/  [.gitignore]    # Local directory to store uploaded files such as graphviz diagrams generatd by `Network` class
-|
+│
+└── _logs/    [.gitignore]    # Local directory to store error/warning logs for debugging
+│
+│
 pyproject.toml                # Project config
 
 ```
 
 <hr />
 
-## Setting Up a Project
+## Setting Up Your Project
 
-### 1. Installing package manager
+### Installing package manager
 
    For MacOS:
 
@@ -433,7 +433,7 @@ pyproject.toml                # Project config
    ```
 
 
-### 2. Installing dependencies
+### Installing dependencies
 
    ```
    uv venv
@@ -466,7 +466,7 @@ pyproject.toml                # Project config
 
    - `torch`/`Docling` related errors: Set up default Python version either `3.11.x` or `3.12.x` (same as AssertionError)
 
-### 3. Adding env secrets to .env file
+### Adding env secrets to .env file
 
 Create `.env` file in the project root and add following:
 
@@ -479,6 +479,7 @@ Create `.env` file in the project root and add following:
    [OTHER_LLM_INTERFACE_PROVIDER_OF_YOUR_CHOICE]_API_KEY=your-api-key
    ```
 
+
 <hr />
 
 ## Contributing
@@ -583,7 +584,7 @@ Common issues and solutions:
 
 * Issues related to dependencies: `rm -rf uv.lock`, `uv cache clean`, `uv venv`, and run `uv pip install -r requirements.txt -v`.
 
-* Issues related to the AI agents or RAG system: Check the `output.log` file for detailed error messages and stack traces.
+* Issues related to agents and other systems: Check `_logs` directory for detailed error messages and stack traces.
 
 * Issues related to `Python quit unexpectedly`: Check [this stackoverflow article](https://stackoverflow.com/questions/59888499/macos-catalina-python-quit-unexpectedly-error).
 

{versionhq-1.2.1.1 → versionhq-1.2.1.2}/tests/agent/agent_test.py

@@ -262,7 +262,6 @@ def test_agent_with_knowledge_sources():
         assert "gold" in res.raw.lower()
 
 
-
 def test_using_contextual_memory():
     from versionhq.task.model import Task
     from versionhq.task.evaluate import Evaluation