versionhq 1.1.12.2__py3-none-any.whl → 1.1.12.4__py3-none-any.whl

versionhq/__init__.py

@@ -21,9 +21,10 @@ from versionhq.tool.composio_tool import ComposioHandler
 from versionhq.memory.contextual_memory import ContextualMemory
 from versionhq.memory.model import ShortTermMemory,LongTermMemory, UserMemory, MemoryItem
 
+from versionhq.task.formation import form_agent_network
 
 
-__version__ = "1.1.12.2"
+__version__ = "1.1.12.4"
 __all__ = [
     "Agent",
 
@@ -67,5 +68,7 @@ __all__ = [
     "ShortTermMemory",
     "LongTermMemory",
     "UserMemory",
-    "MemoryItem"
+    "MemoryItem",
+
+    "form_agent_network"
 ]

versionhq/agent/model.py

@@ -128,7 +128,7 @@ class Agent(BaseModel):
     max_tokens: Optional[int] = Field(default=None, description="max. number of tokens for the agent's execution")
     max_execution_time: Optional[int] = Field(default=None, description="max. execution time for an agent to execute a task")
     max_rpm: Optional[int] = Field(default=None, description="max. number of requests per minute")
-    llm_config: Optional[Dict[str, Any]] = Field(default=None, description="other llm config cascaded to the model")
+    llm_config: Optional[Dict[str, Any]] = Field(default=None, description="other llm config cascaded to the LLM model")
 
     # cache, error, ops handling
     formatting_errors: int = Field(default=0, description="number of formatting errors.")
@@ -164,34 +164,43 @@ class Agent(BaseModel):
         Set up `llm` and `function_calling_llm` as valid LLM objects using the given values.
         """
         self.agent_ops_agent_name = self.role
-        self.llm = self._convert_to_llm_class(llm=self.llm)
+        self.llm = self._convert_to_llm_object(llm=self.llm)
 
         function_calling_llm = self.function_calling_llm if self.function_calling_llm else self.llm if self.llm else None
-        function_calling_llm = self._convert_to_llm_class(llm=function_calling_llm)
+        function_calling_llm = self._convert_to_llm_object(llm=function_calling_llm)
         if function_calling_llm._supports_function_calling():
             self.function_calling_llm = function_calling_llm
+        elif self.llm._supports_function_calling():
+            self.function_calling_llm = self.llm
+        else:
+            self.function_calling_llm = self._convert_to_llm_object(llm=LLM(model=DEFAULT_MODEL_NAME))
         return self
 
 
-    def _convert_to_llm_class(self, llm: Any | None) -> LLM:
+    def _convert_to_llm_object(self, llm: Any | None) -> LLM:
+        """
+        Convert the given value to LLM object.
+        When `llm` is dict or self.llm_config is not None, add these values to the LLM object after validating them.
+        """
         llm = llm if llm is not None else DEFAULT_MODEL_NAME
 
         match llm:
             case LLM():
-                return self._set_llm_params(llm=llm)
+                return self._set_llm_params(llm=llm, config=self.llm_config)
 
             case str():
                 llm_obj = LLM(model=llm)
-                return self._set_llm_params(llm=llm_obj)
+                return self._set_llm_params(llm=llm_obj, config=self.llm_config)
 
             case dict():
                 model_name = llm.pop("model_name", llm.pop("deployment_name", str(llm)))
                 llm_obj = LLM(model=model_name if model_name else DEFAULT_MODEL_NAME)
-                return self._set_llm_params(llm_obj, { k: v for k, v in llm.items() if v is not None })
+                config = llm.update(self.llm_config) if self.llm_config else llm
+                return self._set_llm_params(llm_obj, config=config)
 
             case _:
                 model_name = (getattr(self.llm, "model_name") or getattr(self.llm, "deployment_name") or str(self.llm))
-                llm_obj = LLM(model=model_name)
+                llm_obj = LLM(model=model_name if model_name else DEFAULT_MODEL_NAME)
                 llm_params = {
                     "max_tokens": (getattr(llm, "max_tokens") or self.max_tokens or 3000),
                     "timeout": getattr(llm, "timeout", self.max_execution_time),
@@ -201,15 +210,40 @@ class Agent(BaseModel):
                     "api_key": getattr(llm, "api_key", os.environ.get("LITELLM_API_KEY", None)),
                     "base_url": getattr(llm, "base_url", None),
                 }
-                return self._set_llm_params(llm=llm_obj, config=llm_params)
+                config = llm_params.update(self.llm_config) if self.llm_config else llm_params
+                return self._set_llm_params(llm=llm_obj, config=config)
 
 
     def _set_llm_params(self, llm: LLM, config: Dict[str, Any] = None) -> LLM:
         """
-        After setting up an LLM instance, add params to the instance.
-        Prioritize the agent's settings over the model's base setups.
+        Add valid params to the LLM object.
         """
 
+        import litellm
+        from versionhq.llm.llm_vars import PARAMS
+
+        valid_config = {k: v for k, v in config.items() if v} if config else {}
+
+        if valid_config:
+            valid_keys = list()
+            try:
+                valid_keys = litellm.get_supported_openai_params(model=llm.model, custom_llm_provider=self.endpoint_provider, request_type="chat_completion")
+                if not valid_keys:
+                    valid_keys = PARAMS.get("common")
+            except:
+                valid_keys = PARAMS.get("common")
+
+            valid_keys += PARAMS.get("litellm")
+
+            for key in valid_keys:
+                if key in valid_config and valid_config[key]:
+                    val = valid_config[key]
+                    if [key == k for k, v in LLM.model_fields.items()]:
+                        setattr(llm, key, val)
+                    else:
+                        llm.other_valid_config.update({ key: val})
+
+
         llm.timeout = self.max_execution_time if llm.timeout is None else llm.timeout
         llm.max_tokens = self.max_tokens if self.max_tokens else llm.max_tokens
 
@@ -225,15 +259,6 @@ class Agent(BaseModel):
         if self.respect_context_window == False:
             llm.context_window_size = DEFAULT_CONTEXT_WINDOW_SIZE
 
-        config = self.config.update(config) if self.config else config
-        if config:
-            valid_params = litellm.get_supported_openai_params(model=llm.model)
-            for k, v in config.items():
-                try:
-                    if k in valid_params and v is not None:
-                        setattr(llm, k, v)
-                except:
-                    pass
         return llm
 
 
@@ -407,9 +432,8 @@ class Agent(BaseModel):
             self._logger.log(level="info", message=f"Messages sent to the model: {messages}", color="blue")
 
             if tool_res_as_final:
-                func_llm = self.function_calling_llm if self.function_calling_llm and self.function_calling_llm._supports_function_calling() else self.llm if self.llm and self.llm._supports_function_calling() else LLM(model=DEFAULT_MODEL_NAME)
-                raw_response = func_llm.call(messages=messages, tools=tools, tool_res_as_final=True)
-                task.tokens = func_llm._tokens
+                raw_response = self.function_calling_llm.call(messages=messages, tools=tools, tool_res_as_final=True)
+                task.tokens = self.function_calling_llm._tokens
             else:
                 raw_response = self.llm.call(messages=messages, response_format=response_format, tools=tools)
                 task.tokens = self.llm._tokens

versionhq/llm/llm_vars.py

@@ -53,7 +53,7 @@ MODELS = {
         "claude-3-haiku-20240307",
     ],
     "openrouter": [
-        "openrouter/deepseek/deepseek-r1:free",
+        "openrouter/deepseek/deepseek-r1",
         "openrouter/qwen/qwen-2.5-72b-instruct",
     ],
     "huggingface": [

versionhq/llm/model.py

@@ -95,6 +95,7 @@ class LLM(BaseModel):
     top_logprobs: Optional[int] = Field(default=None)
     tools: Optional[List[Dict[str, Any]]] = Field(default_factory=list, description="store a list of tool properties")
     callbacks: List[Any] = Field(default_factory=list)
+    other_valid_config: Optional[Dict[str, Any]] = Field(default_factory=dict, description="store other valid values in dict to cascade to the model")
 
     # LiteLLM specific fields
     api_base: Optional[str] = Field(default=None, description="litellm specific field - api base of the model provider")
@@ -201,7 +202,6 @@ class LLM(BaseModel):
         if api_key_name:
             self.api_key = os.environ.get(api_key_name, None)
 
-
         base_url_key_name = self.endpoint_provider.upper() + "_API_BASE" if self.endpoint_provider else None
 
         if base_url_key_name:
@@ -229,6 +229,8 @@ class LLM(BaseModel):
         for item in valid_keys:
             if hasattr(self, item) and getattr(self, item):
                 valid_params[item] = getattr(self, item)
+            elif item in self.other_valid_config and self.other_valid_config[item]:
+                valid_params[item] = self.other_valid_config[item]
             elif item in config and config[item]:
                 valid_params[item] = config[item]
 

versionhq/task/formation.py

@@ -11,7 +11,7 @@ from versionhq._utils import Logger
 
 
 def form_agent_network(
-        task_overview: str,
+        task: str,
         expected_outcome: str,
         agents: List[Agent] = None,
         context: str = None,
@@ -21,7 +21,7 @@ def form_agent_network(
     Make a formation of agents from the given task description, agents (optional), context (optional), and expected outcome (optional).
     """
 
-    if not task_overview:
+    if not task:
         Logger(verbose=True).log(level="error", message="Missing task description.", color="red")
         return None
 
@@ -40,7 +40,7 @@ def form_agent_network(
         vhq_task = Task(
             description=f"""
     Create a team of specialized agents designed to automate the following task and deliver the expected outcome. Consider the necessary roles for each agent with a clear task description. If you think we neeed a leader to handle the automation, return a leader_agent role as well, but if not, leave the a leader_agent role blank.
-    Task: {str(task_overview)}
+    Task: {str(task)}
     Expected outcome: {str(expected_outcome)}
             """,
             pydantic_output=Outcome
@@ -112,12 +112,3 @@ def form_agent_network(
     except Exception as e:
         Logger(verbose=True).log(level="error", message=f"Failed to create an agent network - return None. You can try with solo agent. Error: {str(e)}", color="red")
         return None
-
-
-
-if __name__ == "__main__":
-    res = form_agent_network(
-        task_overview="Launch an outbound campaign to attract young audience.",
-        expected_outcome="Best media mix of the campaign.",
-        context="We are selling sports wear.",
-    )

versionhq/task/model.py

@@ -607,7 +607,7 @@ Ref. Output image: {output_formats_to_follow}
                     if len(peers) > 0:
                         agent_to_delegate = peers[0]
             else:
-                agent_to_delegate = Agent(role="delegated_agent", goal=agent.goal, llm=agent.llm)
+                agent_to_delegate = Agent(role="vhq-Delegated-Agent", goal=agent.goal, llm=agent.llm)
 
             agent = agent_to_delegate
             self.delegations += 1

versionhq/team/model.py

@@ -387,9 +387,9 @@ class Team(BaseModel):
         return self._create_team_output(task_outputs, lead_task_output)
 
 
-    def kickoff(self, kwargs_before: Optional[Dict[str, str]] = None, kwargs_after: Optional[Dict[str, Any]] = None) -> TeamOutput:
+    def launch(self, kwargs_before: Optional[Dict[str, str]] = None, kwargs_after: Optional[Dict[str, Any]] = None) -> TeamOutput:
         """
-        Kickoff the team:
+        Confirm and launch the formation - execute tasks and record outputs.
         0. Assign an agent to a task - using conditions (manager prioritizes team_tasks) and planning_llm.
         1. Address `before_kickoff_callbacks` if any.
         2. Handle team members' tasks in accordance with the process.

{versionhq-1.1.12.2.dist-info → versionhq-1.1.12.4.dist-info}/METADATA

@@ -1,7 +1,7 @@
 Metadata-Version: 2.2
 Name: versionhq
-Version: 1.1.12.2
-Summary: Agentic orchestration framework for task automation
+Version: 1.1.12.4
+Summary: An agentic orchestration framework for multi-agent system that shares memory, knowledge base, and RAG tools.
 Author-email: Kuriko Iwai <kuriko@versi0n.io>
 License: MIT License
         
@@ -26,7 +26,7 @@ License: MIT License
         SOFTWARE.
         
 Project-URL: Homepage, https://versi0n.io
-Project-URL: Documentation, https://chief-oxygen-8a2.notion.site/Documentation-17e923685cf98001a5fad5c4b2acd79b?pvs=73
+Project-URL: Documentation, https://docs.versi0n.io
 Project-URL: Repository, https://github.com/versionHQ/multi-agent-system
 Project-URL: Issues, https://github.com/versionHQ/multi-agent-system/issues
 Keywords: orchestration framework,orchestration,ai agent,multi-agent system,RAG,agent,agentic orchestration,llm
@@ -91,7 +91,7 @@ Agentic orchestration framework to deploy agent network and handle complex task
 - [PyPI](https://pypi.org/project/versionhq/)
 - [Github (LLM orchestration framework)](https://github.com/versionHQ/multi-agent-system)
 - [Use case](https://versi0n.io/) / [Quick demo](https://res.cloudinary.com/dfeirxlea/video/upload/v1737732977/pj_m_home/pnsyh5mfvmilwgt0eusa.mov)
-- [Documentation](https://chief-oxygen-8a2.notion.site/Documentation-17e923685cf98001a5fad5c4b2acd79b?pvs=4) *Some components are under review.
+- [Docs](https://docs.versi0n.io)
 
 
 <hr />
@@ -103,13 +103,16 @@ Agentic orchestration framework to deploy agent network and handle complex task
 - [Key Features](#key-features)
   - [Agent formation](#agent-formation)
 - [Quick Start](#quick-start)
-  - [Case 1. Solo Agent:](#case-1-solo-agent)
+  - [Generate agent networks and launch task execution:](#generate-agent-networks-and-launch-task-execution)
+  - [Solo Agent:](#solo-agent)
     - [Return a structured output with a summary in string.](#return-a-structured-output-with-a-summary-in-string)
-  - [Case 2. Supervising:](#case-2-supervising)
+  - [Supervising:](#supervising)
 - [Technologies Used](#technologies-used)
 - [Project Structure](#project-structure)
 - [Setup](#setup)
+- [Set up a project](#set-up-a-project)
 - [Contributing](#contributing)
+  - [Documentation](#documentation)
   - [Customizing AI Agents](#customizing-ai-agents)
   - [Modifying RAG Functionality](#modifying-rag-functionality)
   - [Package Management with uv](#package-management-with-uv)
@@ -123,9 +126,9 @@ Agentic orchestration framework to deploy agent network and handle complex task
 
 ## Key Features
 
-Generate multi-agent systems based on the task complexity, execute tasks, and evaluate output based on the given criteria.
+`versionhq` is a Python framework for agent networks that handle complex task automation without human interaction.
 
-Agents are model-agnostic, and can handle and share RAG tools, knowledge, memory, and callbacks among other agents. (self-learn)
+Agents are model-agnostic, and will improve task output, while oprimizing token cost and job latency, by sharing their memory, knowledge base, and RAG tools with other agents in the network.
 
 
 ###  Agent formation
@@ -137,7 +140,7 @@ You can specify a desired formation or allow the agents to determine it autonomo
 
 |  | **Solo Agent** | **Supervising** | **Network** | **Random** |
 | :--- | :--- | :--- | :--- | :--- |
-| **Formation** | <img src="https://res.cloudinary.com/dfeirxlea/image/upload/v1737893140/pj_m_agents/tglrxoiuv7kk7nzvpe1z.jpg" alt="solo" width="200"> | <img src="https://res.cloudinary.com/dfeirxlea/image/upload/v1737893141/pj_m_agents/hxngdvnn5b5qdxo0ayl5.jpg" alt="solo" width="200"> | <img src="https://res.cloudinary.com/dfeirxlea/image/upload/v1737893142/pj_m_agents/kyc6neg8m6keyizszcpi.jpg" alt="solo" width="200"> | <img src="https://res.cloudinary.com/dfeirxlea/image/upload/v1737893139/pj_m_agents/hzpchlcpnpwxwaapu1hr.jpg" alt="solo" width="200"> |
+| **Formation** | <img src="https://res.cloudinary.com/dfeirxlea/image/upload/v1738818211/pj_m_agents/rbgxttfoeqqis1ettlfz.png" alt="solo" width="200"> | <img src="https://res.cloudinary.com/dfeirxlea/image/upload/v1738818211/pj_m_agents/zhungor3elxzer5dum10.png" alt="solo" width="200"> | <img src="https://res.cloudinary.com/dfeirxlea/image/upload/v1738818211/pj_m_agents/dnusl7iy7kiwkxwlpmg8.png" alt="solo" width="200"> | <img src="https://res.cloudinary.com/dfeirxlea/image/upload/v1738818211/pj_m_agents/sndpczatfzbrosxz9ama.png" alt="solo" width="200"> |
 | **Usage** | <ul><li>A single agent with tools, knowledge, and memory.</li><li>When self-learning mode is on - it will turn into **Random** formation.</li></ul> | <ul><li>Leader agent gives directions, while sharing its knowledge and memory.</li><li>Subordinates can be solo agents or networks.</li></ul> | <ul><li>Share tasks, knowledge, and memory among network members.</li></ul> | <ul><li>A single agent handles tasks, asking help from other agents without sharing its memory or knowledge.</li></ul> |
 | **Use case** | An email agent drafts promo message for the given audience. | The leader agent strategizes an outbound campaign plan and assigns components such as media mix or message creation to subordinate agents. | An email agent and social media agent share the product knowledge and deploy multi-channel outbound campaign. | 1. An email agent drafts promo message for the given audience, asking insights on tones from other email agents which oversee other clusters. 2. An agent calls the external agent to deploy the campaign. |
 
@@ -153,8 +156,22 @@ You can specify a desired formation or allow the agents to determine it autonomo
 
 (Python 3.11 or higher)
 
+### Generate agent networks and launch task execution:
 
-### Case 1. Solo Agent:
+   ```
+   from versionhq import form_agent_network
+
+   network = form_agent_network(
+      task="YOUR AMAZING TASK OVERVIEW",
+      expected_outcome="YOUR OUTCOME EXPECTATION",
+   )
+   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.
+
+
+### Solo Agent:
 
 #### Return a structured output with a summary in string.
 
@@ -197,7 +214,7 @@ This will return `TaskOutput` instance that stores a response in plane text, JSO
    )
    ```
 
-### Case 2. Supervising:
+### Supervising:
 
    ```
    from versionhq import Agent, Task, ResponseField, Team, TeamMember
@@ -291,19 +308,24 @@ src/
 
 ## Setup
 
+
+
+## Set up a project
+
 1. Install `uv` package manager:
 
-   For MacOS:
+      For MacOS:
 
-   ```
-   brew install uv
-   ```
+      ```
+      brew install uv
+      ```
 
-   For Ubuntu/Debian:
+      For Ubuntu/Debian:
+
+      ```
+      sudo apt-get install uv
+      ```
 
-   ```
-   sudo apt-get install uv
-   ```
 
 2. Install dependencies:
    ```
@@ -325,11 +347,11 @@ src/
 3. Set up environment variables:
    Create a `.env` file in the project root and add the following:
    ```
-   OPENAI_API_KEY=your-openai-api-key
    LITELLM_API_KEY=your-litellm-api-key
-   UPSTAGE_API_KEY=your-upstage-api-key
+   OPENAI_API_KEY=your-openai-api-key
    COMPOSIO_API_KEY=your-composio-api-key
    COMPOSIO_CLI_KEY=your-composio-cli-key
+   [LLM_INTERFACE_PROVIDER_OF_YOUR_CHOICE]_API_KEY=your-api-key
    ```
 
 <hr />
@@ -363,16 +385,25 @@ src/
 **Optional**
 * Flag with `#! REFINEME` for any improvements needed and `#! FIXME` for any errors.
 
-* Run a React demo app: [React demo app](https://github.com/versionHQ/test-client-app) to check it on the client endpoint.
+<!-- * Run a React demo app: [React demo app](https://github.com/versionHQ/test-client-app) to check it on the client endpoint.
    ```
    npm i
    npm start
    ```
-   The frontend will be available at `http://localhost:3000`.
+   The frontend will be available at `http://localhost:3000`. -->
 
 * `production` use case is available at `https://versi0n.io`. Currently, we are running alpha test.
 
 
+### Documentation
+* To edit the documentation, see `docs` repository and edit the respective component.
+
+* We use `mkdocs` to update the docs. You can run the doc locally at http://127.0.0.1:8000/:
+
+   ```
+   uv run python3 -m mkdocs serve --clean
+   ```
+
 
 ### Customizing AI Agents
 

{versionhq-1.1.12.2.dist-info → versionhq-1.1.12.4.dist-info}/RECORD

@@ -1,4 +1,4 @@
-versionhq/__init__.py,sha256=1hMfk5eYF9pdzZypJBvtvbqHdhM_2Oi-UWuz7yg5Ikc,2266
+versionhq/__init__.py,sha256=JhEVJI4u5L_5zgmcnPC4erd7T1L_nkgwT49dfI_G6TU,2349
 versionhq/_utils/__init__.py,sha256=dzoZr4cBlh-2QZuPzTdehPUCe9lP1dmRtauD7qTjUaA,158
 versionhq/_utils/i18n.py,sha256=TwA_PnYfDLA6VqlUDPuybdV9lgi3Frh_ASsb_X8jJo8,1483
 versionhq/_utils/logger.py,sha256=j9SlQPIefdVUlwpGfJY83E2BUt1ejWgZ2M2I8aMyQ3c,1579
@@ -7,7 +7,7 @@ versionhq/_utils/usage_metrics.py,sha256=hhq1OCW8Z4V93vwW2O2j528EyjOlF8wlTsX5IL-
 versionhq/_utils/vars.py,sha256=bZ5Dx_bFKlt3hi4-NNGXqdk7B23If_WaTIju2fiTyPQ,57
 versionhq/agent/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 versionhq/agent/inhouse_agents.py,sha256=v8frZjmiqYR8zuuh4CjYJheaHfHT2n_utT8pWCLJFes,2375
-versionhq/agent/model.py,sha256=w58WIwIOI_gBlRHVlkU07ILVRlBSSJnpqWhzx0TU8d0,22416
+versionhq/agent/model.py,sha256=qJCPsPV4SWIJnvbOL8Ntb60YFzWmVrqoNINww6Gbv2Q,23313
 versionhq/agent/parser.py,sha256=riG0dkdQCxH7uJ0AbdVdg7WvL0BXhUgJht0VtQvxJBc,4082
 versionhq/agent/rpm_controller.py,sha256=grezIxyBci_lDlwAlgWFRyR5KOocXeOhYkgN02dNFNE,2360
 versionhq/agent/TEMPLATES/Backstory.py,sha256=IAhGnnt6VUMe3wO6IzeyZPDNu7XE7Uiu3VEXUreOcKs,532
@@ -28,8 +28,8 @@ versionhq/knowledge/source.py,sha256=30VXsl3uHdM0wK0Dik3XfFxpNpEiy539PBNBvg0Y4-g
 versionhq/knowledge/source_docling.py,sha256=hhHn3rS4KVsFKEPWcfllM8VxSL86PckZdAHDZNQNOq8,5411
 versionhq/knowledge/storage.py,sha256=7oxCg3W9mFjYH1YmuH9kFtTbNxquzYFjuUjd_TlsB9E,8170
 versionhq/llm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-versionhq/llm/llm_vars.py,sha256=asJtkKCcD0WWIbyVn7CYOWg-WZ6MSKS9lIRaYIkdib4,6778
-versionhq/llm/model.py,sha256=wSjRGyk9AZtvDqNfcyyeOMoV_hpTaUHCM849hBF0MhU,15145
+versionhq/llm/llm_vars.py,sha256=p4MbhH0eaQ1qWkHfA3QBP1KteJFkatEecvSCwqJ4m-M,6773
+versionhq/llm/model.py,sha256=tbsd6IXwxLwCzni7weSVPDMgBbOcg5dtlzhN_as89gE,15446
 versionhq/memory/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 versionhq/memory/contextual_memory.py,sha256=tCsOOAUnfrOL7YiakqGoi3uShzzS870TmGnlGd3z_A4,3556
 versionhq/memory/model.py,sha256=4wow2O3UuMZ0AbC2NyxddGZac3-_GjNZbK9wsA015NA,8145
@@ -42,14 +42,14 @@ versionhq/storage/task_output_storage.py,sha256=E1t_Fkt78dPYIOl3MP7LfQ8oGtjlzxBu
 versionhq/storage/utils.py,sha256=ByYXPoEIGJYLUqz-DWjbCAnneNrH1otiYbp12SCILpM,747
 versionhq/task/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 versionhq/task/evaluate.py,sha256=f8S-nuEl2xJ2LnLv7iQixH53-gp0pKx1hFp_sUlN464,3977
-versionhq/task/formation.py,sha256=BBB-Fgc9nmoOIuMIPndt-XO2I6uWCBDgFkSMi_72brk,4986
+versionhq/task/formation.py,sha256=bZytru6I5a_CFq2rtmsBb0hVWIqExpzUxXPXYpd6qnI,4706
 versionhq/task/formatter.py,sha256=N8Kmk9vtrMtBdgJ8J7RmlKNMdZWSmV8O1bDexmCWgU0,643
 versionhq/task/log_handler.py,sha256=KJRrcNZgFSKhlNzvtYFnvtp6xukaF1s7ifX9u4zWrN8,1683
-versionhq/task/model.py,sha256=2p3Fc4iphfAjARaClFL3AXDg_203Kx6VAlMgt2-L29U,29444
+versionhq/task/model.py,sha256=iEzNZ2BILmCg6iEhuspNR0mrUh1vxfCZxz4Sjw5Nkto,29448
 versionhq/task/structured_response.py,sha256=uVqgeUxNOACPe2hdc0RELSbtKd1vrwonfjXMOGTT0TI,4818
 versionhq/task/TEMPLATES/Description.py,sha256=V-4kh8xpQTKOcDMi2xnuP-fcNk6kuoz1_5tYBlDLQWQ,420
 versionhq/team/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-versionhq/team/model.py,sha256=NYKYxyebZrbhbDReqP01M4viHJ-48AXlpPMpxUw4SX4,18836
+versionhq/team/model.py,sha256=WDnaJuvnVMmreztR0CMypnKpqFtGzAb7rrZ-HKa010Y,18886
 versionhq/team/team_planner.py,sha256=l1PwyBXK1F3uOcbF1IvJBWKApJhghZnBF_ErkNcE04s,3745
 versionhq/tool/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 versionhq/tool/cache_handler.py,sha256=iL8FH7X0G-cdT0uhJwzuhLDaadTXOdfybZcDy151-es,1085
@@ -58,8 +58,8 @@ versionhq/tool/composio_tool_vars.py,sha256=FvBuEXsOQUYnN7RTFxT20kAkiEYkxWKkiVtg
 versionhq/tool/decorator.py,sha256=C4ZM7Xi2gwtEMaSeRo-geo_g_MAkY77WkSLkAuY0AyI,1205
 versionhq/tool/model.py,sha256=ILfvRviQR1W1w-u3MtOIz0PrWa-brpgfAiyKWol63mk,12227
 versionhq/tool/tool_handler.py,sha256=2m41K8qo5bGCCbwMFferEjT-XZ-mE9F0mDUOBkgivOI,1416
-versionhq-1.1.12.2.dist-info/LICENSE,sha256=cRoGGdM73IiDs6nDWKqPlgSv7aR4n-qBXYnJlCMHCeE,1082
-versionhq-1.1.12.2.dist-info/METADATA,sha256=8DC3AWye0ks-8k7iv5aZtLlJSxCpVLKojjCCy5FGFAQ,18563
-versionhq-1.1.12.2.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-versionhq-1.1.12.2.dist-info/top_level.txt,sha256=DClQwxDWqIUGeRJkA8vBlgeNsYZs4_nJWMonzFt5Wj0,10
-versionhq-1.1.12.2.dist-info/RECORD,,
+versionhq-1.1.12.4.dist-info/LICENSE,sha256=cRoGGdM73IiDs6nDWKqPlgSv7aR4n-qBXYnJlCMHCeE,1082
+versionhq-1.1.12.4.dist-info/METADATA,sha256=rL_c6WuvaaZVs_uX7tMLfT-hbkH3qCT7KT90lO_tuVE,19414
+versionhq-1.1.12.4.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+versionhq-1.1.12.4.dist-info/top_level.txt,sha256=DClQwxDWqIUGeRJkA8vBlgeNsYZs4_nJWMonzFt5Wj0,10
+versionhq-1.1.12.4.dist-info/RECORD,,