versionhq 1.2.2.8__tar.gz → 1.2.2.10__tar.gz

{versionhq-1.2.2.8 → versionhq-1.2.2.10}/.gitignore

@@ -1,6 +1,8 @@
 deploy.py
 destinations.py
 
+refine.py
+
 train.py
 
 _memo

{versionhq-1.2.2.8 → versionhq-1.2.2.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: versionhq
-Version: 1.2.2.8
+Version: 1.2.2.10
 Summary: An agentic orchestration framework for building agent networks that handle task automation.
 Author-email: Kuriko Iwai <kuriko@versi0n.io>
 License: MIT License
@@ -100,7 +100,7 @@ Agentic orchestration framework for multi-agent networks and task graphs for com
 **Visit:**
 
 - [Playground](https://versi0n.io/)
-- [Docs](https://docs.versi0n.io)
+- [Documentation](https://docs.versi0n.io)
 - [Github](https://github.com/versionHQ/)
 - [Python SDK](https://pypi.org/project/versionhq/)
 

{versionhq-1.2.2.8 → versionhq-1.2.2.10}/README.md

@@ -13,7 +13,7 @@ Agentic orchestration framework for multi-agent networks and task graphs for com
 **Visit:**
 
 - [Playground](https://versi0n.io/)
-- [Docs](https://docs.versi0n.io)
+- [Documentation](https://docs.versi0n.io)
 - [Github](https://github.com/versionHQ/)
 - [Python SDK](https://pypi.org/project/versionhq/)
 

versionhq-1.2.2.10/docs/core/knowledge.md

@@ -0,0 +1,11 @@
+---
+tags:
+  - Utilities
+---
+
+
+# Knowledge
+
+<class>`class` versionhq.knowledge.model.<bold>Knowledge<bold></class>
+
+A Pydantic class to store `Knowledge` of the agent.

{versionhq-1.2.2.8 → versionhq-1.2.2.10}/docs/core/llm/index.md

@@ -16,9 +16,10 @@ You can specify a model and integration platform from the list. Else, we'll use
 
 ```python
 "openai": [
-    "gpt-4",
+    "gpt-4.5-preview-2025-02-27",
     "gpt-4o",
     "gpt-4o-mini",
+    "gpt-4",
     "o1-mini",
     "o1-preview",
 ],

versionhq-1.2.2.10/docs/core/memory.md

@@ -0,0 +1,11 @@
+---
+tags:
+  - Utilities
+---
+
+
+# Memory
+
+<class>`class` versionhq.memory.model.<bold>Memory<bold></class>
+
+A Pydantic class to store `Memory` of the agent.

versionhq-1.2.2.10/docs/core/rag-tool.md

@@ -0,0 +1,85 @@
+---
+tags:
+  - Utilities
+---
+
+
+# RAG Tool
+
+<class>`class` versionhq.tool.rag_tool.<bold>RagTool<bold></class>
+
+A Pydantic class to store RAG tools that the agent will use when it executes the task.
+
+
+## Quick Start
+
+Similar to the `Tool` class, you can run the RAG tool using `url` and `query` variables.
+
+```python
+import versionhq as vhq
+
+rt = vhq.RagTool(
+    url="https://github.com/chroma-core/chroma/issues/3233",
+    query="What is the next action plan?"
+)
+res = rt.run()
+
+assert rt.text is not None # text source from the url
+assert res is not None
+```
+
+
+<hr>
+
+## Using with Agents
+
+You can call a specific agent when you run a RAG tool.
+
+```python
+import versionhq as vhq
+
+rt = vhq.RagTool(url="https://github.com/chroma-core/chroma/issues/3233", query="What is the next action plan?")
+
+agent = vhq.Agent(role="RAG Tool Tester")
+res = rt.run(agent=agent)
+
+assert agent.knowledge_sources is not None
+assert rt.text is not None
+assert res is not None
+```
+
+
+Agents can own RAG tools.
+
+```python
+import versionhq as vhq
+
+rt = vhq.RagTool(url="https://github.com/chroma-core/chroma/issues/3233", query="What is the next action plan?")
+
+agent = vhq.Agent(role="RAG Tool Tester", tools=[rt]) # adding RAG tool/s
+task = vhq.Task(description="return a simple response", can_use_agent_tools=True, tool_res_as_final=True)
+res = task.execute(agent=agent)
+
+assert res.raw is not None
+assert res.tool_output is not None
+```
+
+
+### Variables
+
+| <div style="width:160px">**Variable**</div> | **Data Type** | **Default** | **Nullable** | **Description** |
+| :---               | :---  | :--- | :--- | :--- |
+| **`api_key_name`** | Optional[str]   | None | True | API key name in .env file. |
+| **`api_endpoint`**       | Optional[str]   | None | True |API endpoint. |
+| **`url`** | Optional[str] | None | True | URLs to extract the text source. |
+| **`headers`** | Optional[Dict[str, Any]]  | dict() | - | Request headers |
+| **`query`** |  Optional[str] | None | True | Query. |
+| **`text`** |  Optional[str] | None | True | Text sources extracted from the URL or API call |
+
+
+### Class Methods
+
+| <div style="width:120px">**Method**</div> |  <div style="width:300px">**Params**</div> | **Returns** | **Description** |
+| :---               | :---  | :--- | :--- |
+| **`store_data`**  | <p>agent: Optional["vhq.Agent"] = Non</p> | None | Stores the retrieved data in the storage. |
+| **`run`**  | *args, **kwargs | Any | Execute the tool. |

versionhq-1.2.2.10/docs/core/task/evaluation.md

@@ -0,0 +1,77 @@
+---
+tags:
+  - Task Graph
+---
+
+# Evaluation
+
+<class>`class` versionhq.task.evaluate.<bold>Evaluation<bold></class>
+
+A Pydantic class to store conditions and results of the evaluation.
+
+
+### Variables
+
+| <div style="width:120px">**Variable**</div> | **Data Type** | **Default** | **Nullable** | **Description** |
+| :---            | :---  | :--- | :--- | :--- |
+| **`items`**     | List[InstanceOf[EvaluationItem]]  | list() | - | Stores evaluation items. |
+| **`eval_by`**   | Any   | None | True | Stores an agent evaluated the output. |
+
+
+### Property
+
+| <div style="width:120px">**Property**</div> | **Returns** | **Description** |
+| :---               | :---  | :--- |
+| **`aggregate_score`**   | float | Calucurates weighted average eval scores of the task output. |
+| **`suggestion_summary`**  | str   | Returns summary of the suggestions. |
+
+
+
+<hr>
+
+## EvaluationItem
+
+<class>`class` versionhq.task.evaluate.<bold>EvaluationItem<bold></class>
+
+### Variables
+
+| <div style="width:120px">**Variable**</div> | **Data Type** | **Default** | **Nullable** | **Description** |
+| :---            | :---  | :--- | :--- | :--- |
+| **`criteria`**     | str  | None | False | Stores evaluation criteria given by the client. |
+| **`suggestion`**   | str   | None | True | Stores suggestion on improvement from the evaluator agent. |
+| **`score`**   | float   | None | True | Stores the score on a 0 to 1 scale. |
+
+
+<hr>
+
+## Usage
+
+Evaluator agents will evaluate the task output based on the given criteria, and store the results in the `TaskOutput` object.
+
+
+```python
+import versionhq as vhq
+from pydantic import BaseModel
+
+class CustomOutput(BaseModel):
+    test1: str
+    test2: list[str]
+
+task = vhq.Task(
+    description="Research a topic to teach a kid aged 6 about math.",
+    pydantic_output=CustomOutput,
+    should_evaluate=True, # triggers evaluation
+    eval_criteria=["uniquness", "audience fit",],
+
+)
+res = task.execute()
+
+assert isinstance(res.evaluation, vhq.Evaluation)
+assert [item for item in res.evaluation.items if item.criteria == "uniquness" or item.criteria == "audience fit"]
+assert res.evaluation.aggregate_score is not None
+assert res.evaluation.suggestion_summary is not None
+```
+
+An `Evaluation` object provides scores for the given criteria.
+
+For example, it might indicate a `uniqueness` score of 0.56, an `audience fit` score of 0.70, and an `aggregate score` of 0.63.

{versionhq-1.2.2.8 → versionhq-1.2.2.10}/docs/core/task/index.md

@@ -7,7 +7,7 @@ tags:
 
 <class>`class` versionhq.task.model.<bold>Task<bold></class>
 
-A class to store and manage information for individual tasks, including their assignment to agents or agent networks, and dependencies via a node-based system that tracks conditions and status.
+A Pydantic class to store and manage information for individual tasks, including their assignment to agents or agent networks, and dependencies via a node-based system that tracks conditions and status.
 
 Ref. Node / Edge / <a href="/core/task-graph">TaskGraph</a> class
 

versionhq-1.2.2.10/docs/core/task/reference.md

@@ -0,0 +1,105 @@
+## `Task`
+
+### Variables
+
+| <div style="width:160px">**Variable**</div> | **Data Type** | **Default** | **Nullable** | **Description** |
+| :---               | :---  | :--- | :--- | :--- |
+| **`id`**   | UUID  | uuid.uuid4() | False | Stores task `id` as an identifier. |
+| **`name`**       | Optional[str]   | None | True | Stores a task name (Inherited as `node` identifier if the task is dependent) |
+| **`description`**       | str   | None | False | Required field to store a concise task description |
+| **`pydantic_output`** | Optional[Type[BaseModel]] | None | True | Stores pydantic custom output class for structured response |
+| **`response_fields`** | Optional[List[ResponseField]]  | list() | True | Stores JSON formats for stuructured response |
+| **`tools`** |  Optional[List[ToolSet | Tool | Any]] | None | True | Stores tools to be called when the agent executes the task. |
+| **`can_use_agent_tools`** |  bool | True | - | Whether to use the agent tools |
+| **`tool_res_as_final`** |  bool | False | - | Whether to make the tool response a final response from the agent |
+| **`execution_type`** | TaskExecutionType  | TaskExecutionType.SYNC | - | Sync or async execution |
+| **`allow_delegation`** | bool  | False | - | Whether to allow the agent to delegate the task to another agent |
+| **`callback`** | Optional[Callable] | None | True | Callback function to be executed after LLM calling |
+| **`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 |
+| **`output`** | Optional[TaskOutput] | None | True | [Ops] Stores `TaskOutput` object after the execution |
+
+
+### Class Methods
+
+| <div style="width:120px">**Method**</div> |  <div style="width:300px">**Params**</div> | **Returns** | **Description** |
+| :---               | :---  | :--- | :--- |
+| **`execute`**  | <p>type: TaskExecutionType = None<br>agent: Optional["vhq.Agent"] = None<br>context: Optional[Any] = None</p> | InstanceOf[`TaskOutput`] or None (error) |  A main method to handle task execution. Auto-build an agent when the agent is not given. |
+
+
+### Properties
+
+| <div style="width:120px">**Property**</div> | **Returns** | **Description** |
+| :---               | :---  | :--- |
+| **`key`**   | str | Returns task key based on its description and output format. |
+| **`summary`**  | str   | Returns a summary of the task based on its id, description and tools. |
+
+<hr>
+
+## `TaskOutput`
+
+### Variables
+
+| <div style="width:120px">**Variable**</div> | **Data Type** | **Default** | **Nullable** | **Description** |
+| :---               | :---  | :--- | :--- | :--- |
+| **`task_id`**   | UUID  | uuid.uuid4() | False | Stores task `id` as an identifier. |
+| **`raw`**       | str   | None | False | Stores response in plane text format. `None` or `""` when the model returned errors.|
+| **`json_dict`** | Dict[str, Any] | None | False | Stores response in JSON serializable dictionary. When the system failed formatting or executing tasks without response_fields, `{ output: <res.raw> }` will be returned. |
+| **`pydantic`** | Type[`BaseModel`]  | None | True | Populates and stores Pydantic class object defined in the `pydantic_output` field. `None` if `pydantic_output` is NOT given. |
+| **`tool_output`** |  Optional[Any] | None | True | Stores results from the tools of the task or agents ONLY when `tool_res_as_final` set as `True`. |
+| **`callback_output`** |  Optional[Any] | None | True | Stores results from callback functions if any. |
+| **`latency`** |  Optional[float] | None | True | Stores job latency in milseconds. |
+| **`evaluation`** |  Optional[InstanceOf[`Evaluation`]] | None | True | Stores overall evaluations and usage of the task output. |
+
+
+### Class Methods
+
+| <div style="width:120px">**Method**</div> | **Params** | **Returns** | **Description** |
+| :---               | :---  | :--- | :--- |
+| **`evaluate`**   | task: InstanceOf[`Task`]  | InstanceOf[`Evaluation`]  | Evaluates task output based on the criteria |
+
+
+### Property
+
+| <div style="width:120px">**Property**</div> | **Returns** | **Description** |
+| :---               | :---  | :--- |
+| **`aggregate_score`**   | float | Calucurates weighted average eval scores of the task output. |
+| **`json_string`**       | str   | Returns `json_dict` in string format. |
+
+
+<hr>
+
+## `Evaluation`
+
+### Variables
+
+| <div style="width:120px">**Variable**</div> | **Data Type** | **Default** | **Nullable** | **Description** |
+| :---            | :---  | :--- | :--- | :--- |
+| **`items`**     | List[InstanceOf[EvaluationItem]]  | list() | - | Stores evaluation items. |
+| **`eval_by`**   | Any   | None | True | Stores an agent evaluated the output. |
+
+
+### Property
+
+| <div style="width:120px">**Property**</div> | **Returns** | **Description** |
+| :---               | :---  | :--- |
+| **`aggregate_score`**   | float | Calucurates weighted average eval scores of the task output. |
+| **`suggestion_summary`**  | str   | Returns summary of the suggestions. |
+
+
+<hr>
+
+## `EvaluationItem`
+
+### Variables
+
+| <div style="width:120px">**Variable**</div> | **Data Type** | **Default** | **Nullable** | **Description** |
+| :---            | :---  | :--- | :--- | :--- |
+| **`criteria`**     | str  | None | False | Stores evaluation criteria given by the client. |
+| **`suggestion`**   | str   | None | True | Stores suggestion on improvement from the evaluator agent. |
+| **`score`**   | float   | None | True | Stores the score on a 0 to 1 scale. |

{versionhq-1.2.2.8 → versionhq-1.2.2.10}/docs/core/task/task-output.md

@@ -7,7 +7,7 @@ tags:
 
 <class>`class` versionhq.task.model.<bold>TaskOutput<bold></class>
 
-A Pydantic class to store and manage response from the `Task` object.
+A Pydantic class to store and manage results of `Task`.
 
 <hr />
 
@@ -18,9 +18,10 @@ A Pydantic class to store and manage response from the `Task` object.
 | **`task_id`**   | UUID  | uuid.uuid4() | False | Stores task `id` as an identifier. |
 | **`raw`**       | str   | None | False | Stores response in plane text format. `None` or `""` when the model returned errors.|
 | **`json_dict`** | Dict[str, Any] | None | False | Stores response in JSON serializable dictionary. When the system failed formatting or executing tasks without response_fields, `{ output: <res.raw> }` will be returned. |
-| **`pydantic`** | Type[`BaseModel`]  | None | True | Populates and stores Pydantic class defined in the `pydantic_output` field. `None` if `pydantic_output` is NOT given. |
+| **`pydantic`** | Type[`BaseModel`]  | None | True | Populates and stores Pydantic class object defined in the `pydantic_output` field. `None` if `pydantic_output` is NOT given. |
 | **`tool_output`** |  Optional[Any] | None | True | Stores results from the tools of the task or agents ONLY when `tool_res_as_final` set as `True`. |
 | **`callback_output`** |  Optional[Any] | None | True | Stores results from callback functions if any. |
+| **`latency`** |  Optional[float] | None | True | Stores job latency in milseconds. |
 | **`evaluation`** |  Optional[InstanceOf[`Evaluation`]] | None | True | Stores overall evaluations and usage of the task output. |
 
 

{versionhq-1.2.2.8 → versionhq-1.2.2.10}/docs/core/task/task-strc-response.md

@@ -12,7 +12,7 @@ But you can choose to generate Pydantic class or specifig JSON object as respons
 
 `[var]`<bold>`pydantic_output: Optional[Type[BaseModel]] = None`</bold>
 
-Create and add a `custom Pydantic class` as a structured response format to the `pydantic_output` field.
+Add a `custom Pydantic class` as a structured response format to the `pydantic_output` field.
 
 The custom class can accept **one layer of a nested child** as you can see in the following code snippet:
 

{versionhq-1.2.2.8 → versionhq-1.2.2.10}/docs/core/tool.md

@@ -7,7 +7,8 @@ tags:
 
 <class>`class` versionhq.tool.model.<bold>Tool<bold></class>
 
-Tool is an unique function that the agent can utilize when they execute the task with or without LLM.
+A Pydantic class to store the tool object.
+
 
 ## Quick Start
 

{versionhq-1.2.2.8 → versionhq-1.2.2.10}/mkdocs.yml

@@ -131,9 +131,12 @@ nav:
       - Executing: 'core/task/task-execution.md'
       - Outputs: 'core/task/task-output.md'
       - Evaluating: 'core/task/evaluation.md'
-      - Reference: 'core/task/task-ref.md'
+      - Reference: 'core/task/reference.md'
   - Components:
     - Tool: 'core/tool.md'
+    - RAG Tool: core/rag-tool.md
+    - Memory: core/memory.md
+    - Knowledge: core/knowledge.md
   - Archive: 'tags.md'
   - Cases:
     - Playground: https://versi0n.io/playground

{versionhq-1.2.2.8 → versionhq-1.2.2.10}/pyproject.toml

@@ -15,7 +15,7 @@ exclude = ["test*", "__pycache__", "*.egg-info"]
 
 [project]
 name = "versionhq"
-version = "1.2.2.8"
+version = "1.2.2.10"
 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-1.2.2.8 → versionhq-1.2.2.10}/src/versionhq/__init__.py

@@ -32,7 +32,7 @@ from versionhq.agent_network.formation import form_agent_network
 from versionhq.task_graph.draft import workflow
 
 
-__version__ = "1.2.2.8"
+__version__ = "1.2.2.10"
 __all__ = [
     "Agent",
 

{versionhq-1.2.2.8 → versionhq-1.2.2.10}/src/versionhq/llm/llm_vars.py

@@ -19,6 +19,7 @@ ENDPOINT_PROVIDERS = [
 
 MODELS = {
     "openai": [
+        "gpt-4.5-preview-2025-02-27",
         "gpt-4",
         "gpt-4o",
         "gpt-4o-mini",
@@ -77,13 +78,15 @@ ENV_VARS = {
 }
 
 
+
 """
 Max input token size by the model.
 """
 LLM_CONTEXT_WINDOW_SIZES = {
-    "gpt-4": 8192,
+    "gpt-4.5-preview-2025-02-27": 128000,
     "gpt-4o": 128000,
     "gpt-4o-mini": 128000,
+    "gpt-4": 8192,
     "o1-preview": 128000,
     "o1-mini": 128000,
 

{versionhq-1.2.2.8 → versionhq-1.2.2.10}/src/versionhq/llm/model.py

@@ -228,6 +228,10 @@ class LLM(BaseModel):
             else:
                 pass
 
+        if "max_tokens" in valid_config:
+            if self.context_window_size and valid_config["max_tokens"] > self.context_window_size:
+                valid_config["max_tokens"] = self.context_window_size
+
         self.llm_config = valid_config
         return valid_config
 

{versionhq-1.2.2.8 → versionhq-1.2.2.10}/src/versionhq/tool/rag_tool.py

@@ -108,5 +108,6 @@ class RagTool(BaseTool):
                     results.append(str(item))
             return results
 
+
     def run(self, *args, **kwargs):
         return self._run(*args, **kwargs)

{versionhq-1.2.2.8 → versionhq-1.2.2.10}/src/versionhq.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: versionhq
-Version: 1.2.2.8
+Version: 1.2.2.10
 Summary: An agentic orchestration framework for building agent networks that handle task automation.
 Author-email: Kuriko Iwai <kuriko@versi0n.io>
 License: MIT License
@@ -100,7 +100,7 @@ Agentic orchestration framework for multi-agent networks and task graphs for com
 **Visit:**
 
 - [Playground](https://versi0n.io/)
-- [Docs](https://docs.versi0n.io)
+- [Documentation](https://docs.versi0n.io)
 - [Github](https://github.com/versionHQ/)
 - [Python SDK](https://pypi.org/project/versionhq/)
 

{versionhq-1.2.2.8 → versionhq-1.2.2.10}/src/versionhq.egg-info/SOURCES.txt

@@ -23,6 +23,9 @@ docs/quickstart.md
 docs/tags.md
 docs/_logos/favicon.ico
 docs/_logos/logo192.png
+docs/core/knowledge.md
+docs/core/memory.md
+docs/core/rag-tool.md
 docs/core/tool.md
 docs/core/agent/config.md
 docs/core/agent/index.md
@@ -34,10 +37,10 @@ docs/core/agent-network/ref.md
 docs/core/llm/index.md
 docs/core/task/evaluation.md
 docs/core/task/index.md
+docs/core/task/reference.md
 docs/core/task/response-field.md
 docs/core/task/task-execution.md
 docs/core/task/task-output.md
-docs/core/task/task-ref.md
 docs/core/task/task-strc-response.md
 docs/core/task-graph/index.md
 docs/stylesheets/main.css
@@ -137,6 +140,7 @@ tests/llm/llm_test.py
 tests/memory/__init__.py
 tests/memory/memory_test.py
 tests/task/__init__.py
+tests/task/doc_eval_test.py
 tests/task/doc_taskoutput_test.py
 tests/task/doc_test.py
 tests/task/eval_test.py

{versionhq-1.2.2.8 → versionhq-1.2.2.10}/tests/llm/llm_connection_test.py

@@ -37,7 +37,7 @@ def res_field_task():
     return Task(description="return random values strictly following the given response format.", response_fields=demo_response_fields)
 
 
-def test_con(simple_task, tool_task, schema_task, res_field_task):
+def test_con_bedrock(simple_task, tool_task, schema_task, res_field_task):
     llms_to_test = [
         "bedrock/converse/us.meta.llama3-3-70b-instruct-v1:0",
         "bedrock/us.meta.llama3-2-11b-instruct-v1:0",
@@ -48,6 +48,34 @@ def test_con(simple_task, tool_task, schema_task, res_field_task):
 
     for agent in agents:
         assert isinstance(agent.llm, LLM)
+        assert agent.llm.provider == "bedrock"
+        assert agent.llm._init_model_name and agent.llm.provider and agent.llm.llm_config["max_tokens"] == agent.llm_config["max_tokens"]
+
+        res_1 = simple_task.execute(agent=agent, context="running a test")
+        assert res_1.raw is not None
+
+        res_2 = tool_task.execute(agent=agent, context="running a test")
+        assert res_2.tool_output is not None
+
+        res_3 = schema_task.execute(agent=agent, context="running a test")
+        assert [
+            getattr(res_3.pydantic, k) and v.annotation == Demo.model_fields[k].annotation
+            for k, v in res_3.pydantic.model_fields.items()
+        ]
+
+        res_4 = res_field_task.execute(agent=agent, context="running a test")
+        assert [v and type(v) == res_field_task.response_fields[i].data_type for i, (k, v) in enumerate(res_4.json_dict.items())]
+
+
+def test_con_gpt(simple_task, tool_task, schema_task, res_field_task):
+    llms_to_test = [
+        "gpt-4.5-preview-2025-02-27",
+    ]
+    agents = [set_agent(llm=llm) for llm in llms_to_test]
+
+    for agent in agents:
+        assert isinstance(agent.llm, LLM)
+        assert agent.llm.provider == "openai"
         assert agent.llm._init_model_name and agent.llm.provider and agent.llm.llm_config["max_tokens"] == agent.llm_config["max_tokens"]
 
         res_1 = simple_task.execute(agent=agent, context="running a test")

versionhq-1.2.2.10/tests/task/doc_eval_test.py

@@ -0,0 +1,23 @@
+def test_eval():
+    import versionhq as vhq
+    from pydantic import BaseModel
+
+    class CustomOutput(BaseModel):
+        test1: str
+        test2: list[str]
+
+    task = vhq.Task(
+        description="Research a topic to teach a kid aged 6 about math.",
+        pydantic_output=CustomOutput,
+        should_evaluate=True, # triggers evaluation
+        eval_criteria=["Uniquness", "Fit to audience",],
+
+    )
+    res = task.execute()
+
+    assert isinstance(res.evaluation, vhq.Evaluation)
+    assert [item for item in res.evaluation.items if item.criteria == "Uniquness" or item.criteria == "Fit to audience"]
+    assert res.evaluation.aggregate_score is not None
+    assert res.evaluation.suggestion_summary is not None
+
+test_eval()

{versionhq-1.2.2.8 → versionhq-1.2.2.10}/tests/task/eval_test.py

@@ -50,4 +50,4 @@ def test_eval_with_fsls():
     assert [isinstance(item, vhq.EvaluationItem) and item.criteria in task.eval_criteria for item in res.evaluation.items]
     assert res.latency and res._tokens
     assert res.evaluation.aggregate_score is not None
-    assert res.evaluation.suggestion_summary
+    assert res.evaluation.suggestion_summary is not None

{versionhq-1.2.2.8 → versionhq-1.2.2.10}/tests/tool/rag_tool_test.py

@@ -10,7 +10,7 @@ def test_rag_tool():
 def test_rag_tool_with_agent():
     import versionhq as vhq
 
-    agent = vhq.Agent(role="test", goal="use rag tools")
+    agent = vhq.Agent(role="RAG Tool Tester")
     rt = vhq.RagTool(url="https://github.com/chroma-core/chroma/issues/3233", query="What is the next action plan?")
     res = rt.run(agent=agent)
 
@@ -23,8 +23,9 @@ def test_use_rag_tool():
     import versionhq as vhq
 
     rt = vhq.RagTool(url="https://github.com/chroma-core/chroma/issues/3233", query="What is the next action plan?")
-    agent = vhq.Agent(role="test", goal="use rag tools", tools=[rt])
+    agent = vhq.Agent(role="RAG Tool Tester", tools=[rt])
     task = vhq.Task(description="return a simple response", can_use_agent_tools=True, tool_res_as_final=True)
     res = task.execute(agent=agent)
 
     assert res.raw is not None
+    assert res.tool_output is not None

{versionhq-1.2.2.8 → versionhq-1.2.2.10}/uv.lock

@@ -4075,7 +4075,7 @@ wheels = [
 
 [[package]]
 name = "versionhq"
-version = "1.2.2.8"
+version = "1.2.2.10"
 source = { editable = "." }
 dependencies = [
     { name = "appdirs" },

versionhq-1.2.2.8/docs/core/task/evaluation.md

@@ -1,6 +0,0 @@
----
-tags:
-  - Task Graph
----
-
-# Evaluation