versionhq 1.2.1.22__tar.gz → 1.2.2.1__tar.gz

{versionhq-1.2.1.22 → versionhq-1.2.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: versionhq
-Version: 1.2.1.22
+Version: 1.2.2.1
 Summary: An agentic orchestration framework for building agent networks that handle task automation.
 Author-email: Kuriko Iwai <kuriko@versi0n.io>
 License: MIT License
@@ -84,7 +84,7 @@ Requires-Dist: pygraphviz>=1.14; extra == "pygraphviz"
 [![DL](https://img.shields.io/badge/Download-20K+-red)](https://clickpy.clickhouse.com/dashboard/versionhq)
 ![MIT license](https://img.shields.io/badge/License-MIT-green)
 [![Publisher](https://github.com/versionHQ/multi-agent-system/actions/workflows/publish.yml/badge.svg)](https://github.com/versionHQ/multi-agent-system/actions/workflows/publish.yml)
-![PyPI](https://img.shields.io/badge/PyPI-v1.2.1+-blue)
+![PyPI](https://img.shields.io/badge/PyPI-v1.2.2+-blue)
 ![python ver](https://img.shields.io/badge/Python-3.11/3.12-purple)
 ![pyenv ver](https://img.shields.io/badge/pyenv-2.5.0-orange)
 
@@ -255,14 +255,14 @@ agent.update(
    ```python
    import versionhq as vhq
 
-   network = vhq.form_agent_network(
+   network = work(
       task="YOUR AMAZING TASK OVERVIEW",
       expected_outcome="YOUR OUTCOME EXPECTATION",
    )
-   res = network.launch()
+   res, tg = 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 agent network with multiple agents on `Formation` and return response in `TaskOutput` object and `TaskGraph` that connects multiple tasks as nodes.
 
 
 ### Executing tasks
@@ -290,15 +290,15 @@ task = vhq.Task(
    callback_kwargs=dict(message="Hi! Here is the result: ")
 )
 
-res = task.execute(context="amazing context to consider.")
-print(res)
-```
+res = task.execute(context="context to consider")
 
+assert isinstance(res, vhq.TaskOutput)
+```
 
 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(
+res == vhq.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']},
@@ -337,11 +337,13 @@ network =vhq.AgentNetwork(
       vhq.Member(agent=agent_b, is_manager=True, tasks=[task_2]), # Agent B as a manager
    ],
 )
-res = network.launch()
+res, tg = network.launch()
+
+assert isinstance(res, vhq.TaskOutput)
+assert agent_b.key in task_1.processed_agents
+assert agent_b.key in task_2.processed_agents
 
-assert isinstance(res, vhq.NetworkOutput)
-assert not [item for item in task_1.processed_agents if "vhq-Delegated-Agent" == item]
-assert [item for item in task_1.processed_agents if "agent b" == item]
+assert isinstance(tg, vhq.TaskGraph)
 ```
 
 This will return a list with dictionaries with keys defined in the `ResponseField` of each task.

{versionhq-1.2.1.22 → versionhq-1.2.2.1}/README.md

@@ -3,7 +3,7 @@
 [![DL](https://img.shields.io/badge/Download-20K+-red)](https://clickpy.clickhouse.com/dashboard/versionhq)
 ![MIT license](https://img.shields.io/badge/License-MIT-green)
 [![Publisher](https://github.com/versionHQ/multi-agent-system/actions/workflows/publish.yml/badge.svg)](https://github.com/versionHQ/multi-agent-system/actions/workflows/publish.yml)
-![PyPI](https://img.shields.io/badge/PyPI-v1.2.1+-blue)
+![PyPI](https://img.shields.io/badge/PyPI-v1.2.2+-blue)
 ![python ver](https://img.shields.io/badge/Python-3.11/3.12-purple)
 ![pyenv ver](https://img.shields.io/badge/pyenv-2.5.0-orange)
 
@@ -174,14 +174,14 @@ agent.update(
    ```python
    import versionhq as vhq
 
-   network = vhq.form_agent_network(
+   network = work(
       task="YOUR AMAZING TASK OVERVIEW",
       expected_outcome="YOUR OUTCOME EXPECTATION",
    )
-   res = network.launch()
+   res, tg = 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 agent network with multiple agents on `Formation` and return response in `TaskOutput` object and `TaskGraph` that connects multiple tasks as nodes.
 
 
 ### Executing tasks
@@ -209,15 +209,15 @@ task = vhq.Task(
    callback_kwargs=dict(message="Hi! Here is the result: ")
 )
 
-res = task.execute(context="amazing context to consider.")
-print(res)
-```
+res = task.execute(context="context to consider")
 
+assert isinstance(res, vhq.TaskOutput)
+```
 
 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(
+res == vhq.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']},
@@ -256,11 +256,13 @@ network =vhq.AgentNetwork(
       vhq.Member(agent=agent_b, is_manager=True, tasks=[task_2]), # Agent B as a manager
    ],
 )
-res = network.launch()
+res, tg = network.launch()
+
+assert isinstance(res, vhq.TaskOutput)
+assert agent_b.key in task_1.processed_agents
+assert agent_b.key in task_2.processed_agents
 
-assert isinstance(res, vhq.NetworkOutput)
-assert not [item for item in task_1.processed_agents if "vhq-Delegated-Agent" == item]
-assert [item for item in task_1.processed_agents if "agent b" == item]
+assert isinstance(tg, vhq.TaskGraph)
 ```
 
 This will return a list with dictionaries with keys defined in the `ResponseField` of each task.

{versionhq-1.2.1.22 → versionhq-1.2.2.1}/docs/core/agent/config.md

@@ -1,6 +1,3 @@
-
-<hr />
-
 ## Optimizing Model
 
 **Model Optimization**

{versionhq-1.2.1.22 → versionhq-1.2.2.1}/docs/core/agent/task-handling.md

@@ -1,7 +1,7 @@
 
-## Prompting
+## Prompt Engineering
 
-**Developer Prompt (System Prompt)**
+**Developer Prompt**
 
 `[var]`<bold>`backstory: Optional[str] = TEMPLATE_BACKSTORY`<bold>
 
@@ -25,9 +25,7 @@ agent = vhq.Agent(
 	goal="Coping with price competition in saturated markets"
 )
 
-print(agent.backstory)
-
-# You are an expert marketing analyst with relevant skillsets and abilities to query relevant information from the given knowledge sources. Leveraging these, you will identify competitive solutions to achieve the following goal: coping with price competition in saturated markets.
+assert agent.backstory == "You are an expert marketing analyst with relevant skillsets and abilities to query relevant information from the given knowledge sources. Leveraging these, you will identify competitive solutions to achieve the following goal: coping with price competition in saturated markets."
 ```
 
 You can also specify your own backstory by simply adding the value to the backstory field of the Agent model:
@@ -41,9 +39,7 @@ agent = vhq.Agent(
     backstory="You are a marketing analyst for a company in a saturated market. The market is becoming increasingly price-competitive, and your company's profit margins are shrinking. Your primary goal is to develop and implement strategies to help your company maintain its market share and profitability in this challenging environment."
 )
 
-print(agent.backstory)
-
-# You are a marketing analyst for a company in a saturated market. The market is becoming increasingly price-competitive, and your company's profit margins are shrinking. Your primary goal is to develop and implement strategies to help your company maintain its market share and profitability in this challenging environment.
+assert agent.backstory == "You are a marketing analyst for a company in a saturated market. The market is becoming increasingly price-competitive, and your company's profit margins are shrinking. Your primary goal is to develop and implement strategies to help your company maintain its market share and profitability in this challenging environment."
 ```
 <hr />
 

versionhq-1.2.2.1/docs/core/agent-network/config.md

@@ -0,0 +1,102 @@
+---
+tags:
+  - Agent Network
+---
+
+
+## Adding Members
+
+<class>`class` versionhq.agent_network.model.<bold>Member<bold></class>
+
+You can simply add an agent as a member using `members` field.
+
+```python
+import versionhq as vhq
+
+network = vhq.AgentNetwork(
+    members=[
+        vhq.Member(
+            agent=vhq.Agent(role="new member", goal="work in the network"),
+            is_manager=False  # explicitly mentioned. Setting `True` makes this member a manager of the network.
+        ),
+    ]
+)
+assert isinstance(network.members[0].agent, vhq.Agent)
+```
+
+Ref. <a href="/core/agent-network/ref/#member">`Member`</a> class.
+
+<hr />
+
+## Changing Formation
+
+The formation of network members will be automatically assigned based on the task goals, but you can explicitly define it by using `formation` field.
+
+
+```python
+import versionhq as vhq
+
+network = vhq.AgentNetwork(
+  members=[
+    vhq.Member(agent=vhq.Agent(role="member 1", goal="work in the network")),
+    vhq.Member(agent=vhq.Agent(role="member 2", goal="work in the network")),
+    vhq.Member(agent=vhq.Agent(role="member 3", goal="work in the network")),
+  ],
+  formation=vhq.Formation.SQUAD,
+)
+
+assert network.formation == vhq.Formation.SQUAD
+```
+
+Ref. Enum <a href="/core/agent-network/ref/#enum-formation">`Formation`</a>
+
+
+<hr >
+
+## Task Handling
+
+The class method `.launch()` will automatically decide the best task handling process and execute the tasks accordingly.
+
+
+```python
+import versionhq as vhq
+
+network = vhq.AgentNetwork(
+  members=[
+      vhq.Member(agent=vhq.Agent(role="member 1", goal="work in the network"), tasks=[vhq.Task(description="Run a demo 1")]),
+      vhq.Member(agent=vhq.Agent(role="member 2", goal="work in the network"), tasks=[vhq.Task(description="Run a demo")]),
+      vhq.Member(agent=vhq.Agent(role="member 3", goal="work in the network")),
+  ],
+)
+
+res, tg = network.launch()
+
+assert isinstance(res, vhq.TaskOutput)
+assert isinstance(tg, vhq.TaskGraph)
+
+```
+
+<hr >
+
+You can also specify the process using `process` field.
+
+```python
+import versionhq as vhq
+
+network = vhq.AgentNetwork(
+  members=[
+      vhq.Member(agent=vhq.Agent(role="member 1", goal="work in the network"), tasks=[vhq.Task(description="Run a demo 1")]),
+      vhq.Member(agent=vhq.Agent(role="member 2", goal="work in the network"), tasks=[vhq.Task(description="Run a demo 2")]),
+      vhq.Member(agent=vhq.Agent(role="member 3", goal="work in the network")),
+  ],
+  process=vhq.TaskHandlingProcess.CONSENSUAL,
+  consent_trigger=lambda x: True, # consent trigger event is a MUST for TaskHandlingProcess.CONSENSUAL
+)
+
+res, tg = network.launch()
+
+assert isinstance(res, vhq.TaskOutput)
+assert isinstance(tg, vhq.TaskGraph)
+```
+
+Ref. Enum <a href="/core/agent-network/ref/#enum-taskhandlingprocess">`TaskHandlingProcess`</a>

versionhq-1.2.2.1/docs/core/agent-network/form.md

@@ -0,0 +1,117 @@
+---
+tags:
+  - Agent Network
+---
+
+
+You can generate an `AgentNetwork` by using `form_agent_network` method with a concise `task` description and `expected_outcome` args.
+
+```python
+import versionhq as vhq
+
+network = vhq.form_agent_network(
+    task="Find the best trip destination this summer.",
+    expected_outcome="a list of destinations and why it's suitable",
+    context="planning a suprise trip for my friend", # optional
+)
+
+assert isinstance(network, vhq.AgentNetwork)
+assert network.members # auto-generated agents as network members
+assert network.tasks # auto-defined sub-tasks to achieve the main task goal
+```
+
+
+<hr>
+
+**Strucured Output**
+
+To generate structured output, you can add a JSON dict or Pydantic class as `expected_outcome` args instead of plane text.
+
+```python
+import versionhq as vhq
+from pydantic import BaseModel
+
+class Outcome(BaseModel):
+    destinations: list[str]
+    why_suitable: list[str]
+
+
+network = vhq.form_agent_network(
+    task="Find the best trip destination this summer.",
+    expected_outcome=Outcome,
+    context="planning a suprise trip for my friend", # optional
+)
+
+assert isinstance(network, vhq.AgentNetwork)
+assert network.members
+assert network.tasks
+```
+
+<hr >
+
+**Agents**
+
+You can use `agents` args to add existing agents to the network.
+
+```python
+import versionhq as vhq
+from pydantic import BaseModel
+
+my_agent = vhq.Agent(
+    role="Travel Agent",
+    goal="select best trip destination",
+    knowledge_sources=[".....","url1",]
+)
+
+class Outcome(BaseModel):
+    destinations: list[str]
+    why_suitable: list[str]
+
+network = vhq.form_agent_network(
+    task="Find the best trip destination this summer.",
+    expected_outcome=Outcome,
+    context="planning a suprise trip for my friend",
+    agents=[my_agent,]
+)
+
+assert isinstance(network, vhq.AgentNetwork)
+assert [member for member in network.members if member.agent == my_agent]
+assert network.tasks
+```
+
+<hr>
+
+**Formation**
+
+Similar to `agents`, you can define `formation` args to specify the network formation:
+
+
+```python
+import versionhq as vhq
+from pydantic import BaseModel
+
+my_agent = vhq.Agent(
+    role="Travel Agent",
+    goal="select best trip destination",
+    knowledge_sources=[".....","url1",]
+)
+
+class Outcome(BaseModel):
+    destinations: list[str]
+    why_suitable: list[str]
+
+network = vhq.form_agent_network(
+    task="Find the best trip destination this summer.",
+    expected_outcome=Outcome,
+    context="planning a suprise trip for my friend",
+    agents=[my_agent,],
+    formation=vhq.Formation.SUPERVISING
+)
+
+assert isinstance(network, vhq.AgentNetwork)
+assert [member for member in network.members if member.agent == my_agent]
+assert network.tasks
+assert network.formation == vhq.Formation.SUPERVISING
+```
+
+Ref. Enum <a href="core/agent-network/ref/#enum-formation">Formation</a>

{versionhq-1.2.1.22 → versionhq-1.2.2.1}/docs/core/agent-network/index.md

@@ -23,7 +23,7 @@ You can specify a desired formation or allow the agents to determine it autonomo
 
 By default, lead agents will determine the best network formation autonomously based on the given task and its goal.
 
-Calling `.launch()` method can start executing tasks by the network, then generate a response in text and JSON formats stored in the `TaskOutput` object.
+Calling `.launch()` method can start executing tasks and generate a tuple of response as a `TaskOutput` object and `TaskGraph` object.
 
 ```python
 import versionhq as vhq
@@ -33,11 +33,12 @@ network = vhq.form_agent_network(
   expected_outcome='media mix, key messages, and CTA targets.'
 )
 
-res = network.launch()
+res, tg = network.launch()
 
 assert isinstance(res, vhq.TaskOutput)
+assert isinstance(tg, vhq.TaskGraph)
 ```
 
-Ref. <a href="/core/task-output">TaskOutput</a> class
+Ref. <a href="/core/task-output">TaskOutput</a> / <a href="/core/task-graph">TaskGraph </a> class.
 
 Visit <a href="https://versi0n.io">Playground</a>.

versionhq-1.2.2.1/docs/core/agent-network/ref.md

@@ -0,0 +1,141 @@
+---
+tags:
+  - Agent Network
+---
+
+
+## Class `AgentNetwork`
+
+### Variable
+
+| <div style="width:200px">**Variable**</div> | **Data Type** | **Default** | **Nullable** | **Description** |
+| :---               | :---  | :--- | :--- | :--- |
+| **`id`**   | UUID4 | uuid.uuid4() | False | Stores auto-generated ID as identifier. Not editable. |
+| **`name`**   | str | None | True | Stores a name of the network. |
+| **`members`**   | List[`Member`] | list() | False | Stores a list of `Member` objects. |
+| **`formation`**  | `Formation`| None | True | Stores `Formation` enum. |
+| **`should_reform`**  | bool | False | - | Whether to reform the network during the activation. |
+| **`network_tasks`**  | List[`Task`] | list() | - | Stores a list of `Task` objects not assigned to any network members. |
+| **`prompt_file`** | str | None | True | Stores absolute file path to the prompt file with JSON formatted prompt |
+| **`process`** | `TaskHandlingProcess` | TaskHandlingProcess.SEQUENTIAL | - | Enum of the task handling process. |
+| **`consent_trigger`** | Callable[..., Any] | None | True | Stores a trigger event (func) for consentual processing. |
+| **`pre_launch_callbacks`** | List[Callable[..., Any]] | list() | - | Stores callbacks to run before the network launch. |
+| **`post_launch_callbacks`** | List[Callable[..., Any]] | list() | - | Stores callbacks to run after the network launch. |
+| **`step_callbacks`** | Callable[..., Any] | None | True | Stores callbacks to run at every step of each member agent takes during the activation. |
+| **`cache`** | bool | True | - | Whether to store cache. |
+| **`execution_logs`** |  List[Dict[str, Any]] | list() | - | Stores a list of execution logs of all the tasks in the network. |
+
+
+### Class Methods
+
+| <div style="width:120px">**Method**</div> | **Params** | **Returns** | **Description** |
+| :---               | :---  | :--- | :--- |
+| **`launch`** | kwargs_pre: Optional[Dict[str, str]] = None <br> kwargs_post: Optional[Dict[str, Any]] = None <br> start_index: int = None |  Tuple[TaskOutput, TaskGraph]: | Core method to launch the network and execute tasks |
+
+
+### Properties
+
+| <div style="width:120px">**Property**</div> | **Returns** | **Description** |
+| :---               | :---  | :--- |
+| **`key`** | str | Unique identifier of the netowrk. |
+| **`managers`** | List[`Member`] | A list of manager members. |
+| **`manager_tasks`** | List[`Task`] | A list of tasks handled by managers. |
+| **`tasks`** | List[`Task`] | All the tasks in the network.|
+| **`unassigned_member_tasks`** | List[Task] | Unassigned member-level tasks. |
+
+
+<hr>
+
+## Class `Member`
+
+### Variable
+
+| <div style="width:200px">**Variable**</div> | **Data Type** | **Default** | **Nullable** | **Description** |
+| :---               | :---  | :--- | :--- | :--- |
+| **`agent`**   | `Agent` | None | True | Agent as a member |
+| **`is_manager`**   | bool | False | - | Whether the member is a manager. |
+| **`can_share_knowledge`**   | bool | True | - | Whether the member can share its knowledge among the other members in the network. |
+| **`can_share_memory`**   | bool | True | - | Whether the member can share its memories among the other members in the network. |
+| **`tasks`**  | List[`Task`]| list() | - | Assinged tasks. |
+
+
+### Properties
+
+| <div style="width:120px">**Property**</div> | **Returns** | **Description** |
+| :---               | :---  | :--- |
+| **`is_idling`** | bool | Whether it has unprocessed assgined task/s |
+
+
+
+<hr>
+
+## Class `Agent`
+
+### Variables
+
+| <div style="width:200px">**Variable**</div> | **Data Type** | **Default** | **Nullable** | **Description** |
+| :---               | :---  | :--- | :--- | :--- |
+| **`id`**   | UUID4 | uuid.uuid4() | False | Stores auto-generated ID as identifier. Not editable. |
+| **`role`**   | str | None | False | Stores a role of the agent. |
+| **`goal`**   | str | None | False | Stores a goal of the agent. |
+| **`backstory`**  | str | None | True | Stores backstory of the agent. Utilized as system prompt. |
+| **`tools`**  | List[InstanceOf[`Tool` \| `ToolSet`] \| Type[`Tool`]] | None | True | Stores tools to be used when executing a task. |
+| **`knowledge_sources`**  | List[`BaseKnowledgeSource` \| Any] | None | True | Stores knowledge sources in text, file path, or url. |
+| **`embedder_config`** | Dict[str, Any] | None | True | Stores embedding configuration for storing knowledge sources. |
+| **`with_memory`** | bool | False | - | Whether to store tasks and results in memory. |
+| **`memory_config`** |  Dict[str, Any] | None | True | Stores configuration of the memory. |
+| **`short_term_memory`** | InstanceOf[`ShortTermMemory`] | None | True | Stores `ShortTermMemory` object. |
+| **`long_term_memory`** | InstanceOf[`LongTermMemory`] | None | True | Stores `LongTermMemory` object. |
+| **`user_memory`** | InstanceOf[`UserMemory`] | None | True | Stores `UserMemory` object. |
+| **`use_developer_prompt`** |  bool | True | - | Whether to use the system (developer) prompt when calling the model. |
+| **`developer_promt_template`** | str | None | True | File path to the prompt template. |
+| **`user_promt_template`** | str | None | True | File path to the prompt template. |
+| **`networks`** | List[Any] | list() | True | Stores a list of agent networks that the agent belongs to. |
+| **`allow_delegation`** | bool | False | - | Whether the agent can delegate assinged tasks to another agent. |
+| **`max_retry_limit`** | int | 2 | - | Maximum number of retries when the task execution failed. |
+| **`maxit`** | int | 25 | - | Maximum number of total optimization loops conducted when an error occues during the task execution. |
+| **`callbacks`** | List[Callabale] | None | True | Stores a list of callback functions that must be called after every task execution completed.|
+| **`llm`** | str \| InstanceOf[`LLM`] \| Dict[str, Any] | None | False | Stores the main model that the agent runs on. |
+| **`func_calling_llm`** | str \| InstanceOf[`LLM`] \| Dict[str, Any] | None | False | Stores the function calling model that the agent runs on. |
+| **`respect_context_window`** | bool | True | - | Whether to follow the main model's maximum context window size. |
+| **`max_execution_time`** | int | None | True | Stores maximum execution time in seconds. |
+| **`max_rpm`** | int | None | True | Stores maximum number of requests per minute. |
+| **`llm_config`** | Dict[str, Any] | None | True | Stores configuration of `LLM` object. |
+| **`config`** | Dict[str, Any] | None | True | Stores model config. |
+
+
+### Class Methods
+
+| <div style="width:120px">**Method**</div> | **Params** | **Returns** | **Description** |
+| :---               | :---  | :--- | :--- |
+| **`update`** | **kwargs: Any  | Self | Updates agents with given kwargs. Invalid keys will be ignored. |
+| **`start`** | context: Any = None <br> tool_res_as_final: bool = False  | `TaskOutput` \| None  | Starts to operate the agent. |
+| **`execute_task`** | task: [Task] <br> context: Any = None <br> task_tools: Optional[List[Tool \| ToolSet]] = list() | str | Returns response from the model in plane text format. |
+
+
+### Properties
+
+| <div style="width:120px">**Property**</div> | **Returns** | **Description** |
+| :---               | :---  | :--- |
+| **`key`** | str | Unique identifier of the agent using its ID and sanitized role. |
+
+
+## ENUM `Formation`
+
+```python
+class Formation(str, Enum):
+    SOLO = 1
+    SUPERVISING = 2
+    SQUAD = 3
+    RANDOM = 4
+    HYBRID = 10
+```
+
+## ENUM `TaskHandlingProcess`
+
+```python
+class TaskHandlingProcess(str, Enum):
+    HIERARCHY = 1
+    SEQUENTIAL = 2
+    CONSENSUAL = 3
+```

{versionhq-1.2.1.22 → versionhq-1.2.2.1}/docs/core/task/evaluation.md

@@ -4,5 +4,3 @@ tags:
 ---
 
 # Evaluation
-
-Under drafting

{versionhq-1.2.1.22 → versionhq-1.2.2.1}/docs/core/task/index.md

@@ -15,7 +15,7 @@ Ref. Node / Edge / <a href="/core/task-graph">TaskGraph</a> class
 
 ## Quick Start
 
-Create a task by defining its description in one simple sentence. The `description` will be used for task prompting later.
+Create a task by defining its description in one simple sentence. The `description` will be used in the prompt later.
 
 Each task will be assigned a unique ID as an identifier.
 

{versionhq-1.2.1.22 → versionhq-1.2.2.1}/docs/core/task/task-execution.md

@@ -1,9 +1,7 @@
 # Executing Task
 
 
-## Prompting
-
-`[class method]`<bold>`prompt(self, model_provider: str = None, context: Optional[Any] = None) -> str`</bold>
+## Prompt Engineering
 
 Prompts are generated automatically based on the task `description`, response format, context, agent `role`, and `goal`.
 
@@ -40,9 +38,7 @@ In this scenario, `sub_task_2` executes before the main task. Its string output
 
 <hr>
 
-## Executing
-
-**Agent delegation**
+## Delegation
 
 `[var]`<bold>`allow_delegation: bool = False`</bold>
 
@@ -58,13 +54,13 @@ task = vhq.Task(
 task.execute()
 
 assert task.output is not None
-assert "vhq-Delegated-Agent" in task.processed_agents # delegated agent
+assert task.processed_agents is not None # auto assigned
 assert task.delegations ==1
 ```
 
 <hr>
 
-**SYNC - ASYNC**
+## Sync - Async Execution
 
 `[var]`<bold>`type: bool = False`</bold>
 
@@ -87,7 +83,7 @@ with patch.object(vhq.Agent, "execute_task", return_value="test") as execute:
 
 <hr>
 
-**Using tools**
+## Using Tools
 
 `[var]`<bold>`tools: Optional[List[ToolSet | Tool | Any]] = None`</bold>
 
@@ -146,7 +142,7 @@ assert res.tool_output == "simple func"
 
 <hr>
 
-## Callback
+## Callbacks
 
 `[var]`<bold>`callback: Optional[Callable] = None`</bold>
 

{versionhq-1.2.1.22 → versionhq-1.2.2.1}/docs/core/task/task-ref.md

@@ -16,6 +16,7 @@
 | **`callback_kwargs`** | Optional[Dict[str, Any]] | dict() | True | Args for the callback function (if any)|
 | **`should_evaluate`** | bool | False | - | Whether to evaluate the task output using eval criteria |
 | **`eval_criteria`** | Optional[List[str]] | list() | True | Evaluation criteria given by the human client |
+| **`fsls`** | Optional[List[str]] | None | True | Examples of excellent and weak responses |
 | **`processed_agents`** | Set[str] | set() | True | [Ops] Stores roles of the agents executed the task |
 | **`tool_errors`** | int | 0 | True | [Ops] Stores number of tool errors |
 | **`delegation`** | int | 0 | True | [Ops] Stores number of agent delegations |