lybic-guiagents 0.2.2__py3-none-any.whl → 0.2.3__py3-none-any.whl

gui_agents/proto/__init__.py

@@ -0,0 +1,3 @@
+from .pb import agent_pb2, agent_pb2_grpc
+
+__all__ = ["agent_pb2", "agent_pb2_grpc"]

gui_agents/proto/pb/__init__.py

@@ -0,0 +1,4 @@
+from . import agent_pb2
+from . import agent_pb2_grpc
+
+__all__ = ["agent_pb2", "agent_pb2_grpc"]

gui_agents/tools/model.md

@@ -0,0 +1,351 @@
+# Supported Model Providers and Model Lists
+
+## LLM Model Providers
+
+### 1. OpenAI
+
+**Provider**
+
+- `openai`
+
+**Supported Models:**
+
+- `gpt-4.1`
+- `gpt-4.1-mini`
+- `gpt-4.1-nano`
+- `gpt-4.5-preview`
+- `gpt-4o`
+- `gpt-4o-realtime-preview`
+- `gpt-4o-mini`
+- `o1`
+- `o1-pro`
+- `o1-mini`
+- `o3`
+- `o3-pro`
+- `o3-mini`
+- `o4-mini`
+
+**Embedding Models:**
+
+- `text-embedding-3-small`
+- `text-embedding-3-large`
+- `text-embedding-ada-002`
+
+📚 **Reference Link:** <https://platform.openai.com/docs/pricing>
+
+---
+
+### 2. Anthropic Claude
+
+**Provider**
+
+- `anthropic`
+
+**Supported Models:**
+
+- `claude-opus-4-20250514`
+- `claude-sonnet-4-20250514`
+- `claude-3-7-sonnet-20250219`
+- `claude-3-5-sonnet-20241022`
+- `claude-3-5-haiku-20241022`
+
+📚 **Reference Link:** <https://www.anthropic.com/api>
+
+---
+
+### 3. AWS Bedrock
+
+**Provider**
+
+- `bedrock`
+
+
+**Supported Claude Models:**
+
+- `Claude-Opus-4`
+- `Claude-Sonnet-4`
+- `Claude-Sonnet-3.7`
+- `Claude-Sonnet-3.5`
+
+📚 **Reference Link:** <https://aws.amazon.com/bedrock/>
+
+---
+
+### 4. Google Gemini
+
+**Provider**
+
+- `gemini`
+
+**Supported Models:**
+
+- `gemini-2.5-pro`
+- `gemini-2.5-flash`
+- `gemini-2.0-flash`
+- `gemini-1.5-pro`
+- `gemini-1.5-flash`
+
+**Embedding Models:**
+
+- `gemini-embedding-001`
+
+📚 **Reference Link:** <https://ai.google.dev/gemini-api/docs/pricing>
+
+---
+
+### 5. Groq
+
+**Provider**
+
+- `groq`
+
+**Supported Models:**
+
+- `Kimi-K2-Instruct`
+- `Llama-4-Scout-17B-16E-Instruct`
+- `Llama-4-Maverick-17B-128E-Instruct`
+- `Llama-Guard-4-12B`
+- `DeepSeek-R1-Distill-Llama-70B`
+- `Qwen3-32B`
+- `Llama-3.3-70B-Instruct`
+
+📚 **Reference Link:** <https://groq.com/pricing>
+
+---
+
+### 6. Monica (Proxy Platform)
+
+**Provider**
+
+- `monica`
+
+**OpenAI Models:**
+
+- `gpt-4.1`
+- `gpt-4.1-mini`
+- `gpt-4.1-nano`
+- `gpt-4o-2024-11-20`
+- `gpt-4o-mini-2024-07-18`
+- `o4-mini`
+- `o3`
+
+**Anthropic Claude Models:**
+
+- `claude-opus-4-20250514`
+- `claude-sonnet-4-20250514`
+- `claude-3-7-sonnet-latest`
+- `claude-3-5-sonnet-20241022`
+- `claude-3-5-sonnet-20240620`
+- `claude-3-5-haiku-20241022`
+- `claude-3-opus-20240229`
+- `claude-3-haiku-20240307`
+
+**Google Gemini Models:**
+
+- `gemini-2.5-pro-preview-03-25`
+- `gemini-2.5-flash-lite`
+- `gemini-2.5-flash-preview-05-20`
+- `gemini-2.0-flash-001`
+- `gemini-1.5-pro-002`
+- `gemini-1.5-flash-002`
+
+**DeepSeek Models:**
+
+- `deepseek-reasoner`
+- `deepseek-chat`
+
+**Meta Llama Models:**
+
+- `llama-3-8b-instruct`
+- `llama-3.1-8b-instruct`
+- `llama-3.3-70b-instruct`
+- `llama-3-70b-instruct`
+- `llama-3.1-405b-instruct`
+
+**xAI Grok Models:**
+
+- `grok-3-beta`
+- `grok-beta`
+
+📚 **Reference Link:** <https://platform.monica.im/docs/en/models-and-pricing>
+
+---
+
+### 7. OpenRouter (Proxy Platform)
+
+**Provider**
+
+- `openrouter`
+
+**OpenAI Models:**
+
+- `gpt-4.1`
+- `gpt-4.1-mini`
+- `o1`
+- `o1-pro`
+- `o1-mini`
+- `o3`
+- `o3-pro`
+- `o3-mini`
+- `o4-mini`
+
+**xAI Grok Models:**
+
+- `grok-4`
+- `grok-3`
+- `grok-3-mini`
+
+**Anthropic Claude Models:**
+
+- `claude-opus-4`
+- `claude-sonnet-4`
+
+**Google Gemini Models:**
+
+- `gemini-2.5-flash`
+- `gemini-2.5-pro`
+
+📚 **Reference Link:** <https://openrouter.ai/models>
+
+---
+
+### 8. Azure OpenAI
+
+**Provider**
+
+- `azure`
+
+
+**Supported Models:**
+
+- `gpt-4.1`
+- `gpt-4.1-mini`
+- `gpt-4.1-nano`
+- `o1`
+- `o3`
+- `o4-mini`
+
+📚 **Reference Link:** <https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/>
+
+---
+
+### 9. DeepSeek
+
+**Provider**
+
+- `deepseek`
+
+**Supported Models:**
+
+- `deepseek-chat`
+- `deepseek-reasoner`
+
+📚 **Reference Link:** <https://platform.deepseek.com/>
+
+---
+
+### 10. Alibaba Cloud Qwen
+
+**Supported Models:**
+
+- `qwen-max-latest`
+- `qwen-plus-latest`
+- `qwen-turbo-latest`
+- `qwen-vl-max-latest` (Grounding)
+- `qwen-vl-plus-latest` (Grounding)
+
+**Embedding Models:**
+
+- `text-embedding-v4`
+- `text-embedding-v3`
+
+📚 **Reference Link:** <https://bailian.console.aliyun.com/?tab=doc#/doc/?type=model&url=https%3A%2F%2Fhelp.aliyun.com%2Fdocument_detail%2F2840914.html&renderType=iframe>
+
+---
+
+### 11. ByteDance Doubao
+
+**Supported Models:**
+
+- `doubao-seed-1-6-flash-250615`
+- `doubao-seed-1-6-thinking-250715`
+- `doubao-seed-1-6-250615`
+- `doubao-1.5-vision-pro-250328` (Grounding)
+- `doubao-1-5-thinking-vision-pro-250428` (Grounding)
+- `doubao-1-5-ui-tars-250428` (Grounding)
+
+**Embedding Models:**
+
+- `doubao-embedding-large-text-250515`
+- `doubao-embedding-text-240715`
+
+📚 **Reference Link:** <https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW>
+
+---
+
+### 12. Zhipu GLM
+
+**Supported Models:**
+
+- `GLM-4-Plus`
+- `GLM-4-Air-250414`
+- `GLM-4-AirX` (Grounding)
+- `GLM-4V-Plus-0111` (Grounding)
+
+**Embedding Models:**
+
+- `Embedding-3`
+- `Embedding-2`
+
+📚 **Reference Link:** <https://open.bigmodel.cn/pricing>
+
+---
+
+### 13. SiliconFlow
+
+**Supported Models:**
+
+- `Kimi-K2-Instruct`
+- `DeepSeek-V3`
+- `DeepSeek-R1`
+- `Qwen3-32B`
+
+📚 **Reference Link:** <https://cloud.siliconflow.cn/sft-d1pi8rbk20jc73c62gm0/models>
+
+---
+
+## 🔤 Dedicated Embedding Providers
+
+### 14. Jina AI
+
+**Embedding Models:**
+
+- `jina-embeddings-v4`
+- `jina-embeddings-v3`
+
+📚 **Reference Link:** <https://jina.ai/embeddings>
+
+---
+
+## 🔍 AI Search Engines
+
+### 15. Bocha AI
+
+**Service Type:** AI Research & Search
+
+📚 **Reference Link:** <https://open.bochaai.com/overview>
+
+---
+
+### 16. Exa
+
+**Service Type:** AI Research & Search
+
+**Pricing Model:**
+
+- $5.00 / 1k agent searches
+- $5.00 / 1k exa-research agent page reads
+- $10.00 / 1k exa-research-pro agent page reads
+- $5.00 / 1M reasoning tokens
+
+📚 **Reference Link:** <https://dashboard.exa.ai/home>

gui_agents/tools/tools.py

@@ -23,6 +23,11 @@ class BaseTool(ABC):
 
     @classmethod
     def _load_prompts_dict(cls):
+        """
+        Lazily load and cache the prompts dictionary on the class using thread-safe double-checked locking.
+        
+        If the prompts module cannot be loaded, sets `_prompts_dict` to an empty dict and logs an error.
+        """
         if cls._prompts_dict is None:
             with cls._prompts_dict_lock:
                 if cls._prompts_dict is None:
@@ -33,13 +38,22 @@ class BaseTool(ABC):
                         logger.error(f"Failed to load prompts from prompts.py: {e}")
                         cls._prompts_dict = {}
 
-    def __init__(self, provider: str, model_name: str, tool_name: str):
+    def __init__(self, provider: str, model_name: str, tool_name: str, **kwargs):
         """
-        Initialize the base tool.
-        Args:
-            provider: API provider name (e.g., "gemini", "openai")
-            model_name: Model name to use (e.g., "gemini-2.5-pro")
-            tool_name: Name of the tool (used as key in prompts.py)
+        Initialize the base tool, populate engine parameters from provided arguments, load the tool prompt, and create the LLMAgent instance used for LLM calls.
+        
+        Parameters:
+            provider (str): API provider identifier (e.g., "gemini", "openai"); used as the engine_type in engine parameters.
+            model_name (str): Model identifier to use (e.g., "gemini-2.5-pro"); stored as the model in engine parameters.
+            tool_name (str): Tool key used to look up the system prompt template.
+        
+        Keyword Arguments:
+            api_key, base_url, endpoint_url, azure_endpoint, api_version: If present, each is copied into engine parameters and logged as set for the tool.
+            Any other kwargs: Forwarded into engine parameters as-is.
+        
+        Notes:
+            - Loads the prompt template for the tool and stores it on the instance.
+            - Constructs self.engine_params and instantiates self.llm_agent with the system prompt.
         """
         self.provider = provider
         self.model_name = model_name
@@ -51,9 +65,26 @@ class BaseTool(ABC):
             "engine_type": provider,
             "model": model_name
         }
+
+        auth_keys = ['api_key', 'base_url', 'endpoint_url', 'azure_endpoint', 'api_version']
+        for key in auth_keys:
+            if key in kwargs:
+                self.engine_params[key] = kwargs[key]
+                logger.info(f"Setting {key} for tool '{tool_name}' with provider '{provider}'")
+
+        for key, value in kwargs.items():
+            if key not in auth_keys:
+                self.engine_params[key] = value
+
         self.llm_agent = LLMAgent(engine_params=self.engine_params, system_prompt=self._prompt_template)
 
     def _get_prompt_template(self) -> str:
+        """
+        Return the prompt template associated with this tool from the class-level prompts cache.
+        
+        Returns:
+        	(prompt_template (str)): The prompt template for this tool's name, or an empty string if the tool has no name or no template is available.
+        """
         if self.tool_name is None:
             return ""
         prompts = self.__class__._prompts_dict
@@ -170,14 +201,16 @@ class ToolFactory:
 class WebSearchTool(BaseTool):
     """Tool for performing web searches."""
     
-    def __init__(self, provider: str, model_name: str, tool_name: str):
+    def __init__(self, provider: str, model_name: str, tool_name: str, base_url='', api_key=''):
         """
-        Initialize the web search tool.
+        Initialize the WebSearchTool and configure its WebSearchAgent.
         
-        Args:
-            provider: API provider name (e.g., "bocha", "exa")
-            model_name: Model name to use (not used for WebSearchAgent)
-            tool_name: Name of the tool (used as key in prompts.json)
+        Parameters:
+            provider (str): Identifier of the search API provider (e.g., "bocha", "exa").
+            model_name (str): Model identifier to include in engine configuration.
+            tool_name (str): Tool name or prompt key associated with this tool.
+            base_url (str, optional): Custom endpoint URL for the search service.
+            api_key (str, optional): API key or credential for authenticating with the search service.
         """
         self.provider = provider
         
@@ -445,18 +478,21 @@ class ActionGeneratorTool(BaseTool):
     
     def __init__(self, provider: str, model_name: str, tool_name: str, **kwargs):
         """
-        Initialize the action generator tool.
+        Create an ActionGeneratorTool and configure optional web search support.
         
-        Args:
-            provider: API provider name
-            model_name: Model name to use
-            tool_name: Name of the tool (used as key in prompts.json)
-            **kwargs: Additional parameters, including:
-                enable_search: Whether to enable web search functionality
-                search_provider: Provider for web search (defaults to "bocha")
-                search_model: Model for web search (defaults to "")
+        Parameters:
+            provider (str): Name of the API provider to use for the tool.
+            model_name (str): Model identifier used by the underlying LLM engine.
+            tool_name (str): Tool key used to select the prompt template.
+            **kwargs: Additional configuration options:
+                enable_search (bool): If True, a WebSearchTool will be created and attached to the tool as `self.search_tool`. Defaults to False.
+                search_provider (str): Provider to use for the optional web search. Defaults to "bocha".
+                search_model (str): Model identifier to use for the optional web search. Defaults to an empty string.
+        
+        Side effects:
+            Sets `self.enable_search` and, when `enable_search` is True, initializes `self.search_tool` with a WebSearchTool instance and logs the enabling of web search.
         """
-        super().__init__(provider, model_name, tool_name)
+        super().__init__(provider, model_name, tool_name, **kwargs)
         
         # Extract search-related parameters
         self.enable_search = kwargs.get("enable_search", False)
@@ -511,18 +547,19 @@ class FastActionGeneratorTool(BaseTool):
     
     def __init__(self, provider: str, model_name: str, tool_name: str, **kwargs):
         """
-        Initialize the fast action generator tool.
+        Initialize the FastActionGeneratorTool and optionally enable web search augmentation.
         
-        Args:
-            provider: API provider name
-            model_name: Model name to use
-            tool_name: Name of the tool (used as key in prompts.json)
-            **kwargs: Additional parameters, including:
-                enable_search: Whether to enable web search functionality
-                search_provider: Provider for web search (defaults to "bocha")
-                search_model: Model for web search (defaults to "")
+        Parameters:
+            provider (str): API provider name used to configure the underlying LLM/engine.
+            model_name (str): Model identifier to use for generation.
+            tool_name (str): Tool key used to select the prompt template.
+            **kwargs: Additional keyword arguments. Recognized keys:
+                enable_search (bool): If true, instantiate a WebSearchTool to augment requests with search results.
+                search_provider (str): Provider name for the optional web search (default "bocha").
+                search_model (str): Model name for the optional web search (default "").
+                Any other kwargs are forwarded to BaseTool for engine/auth configuration.
         """
-        super().__init__(provider, model_name, tool_name)
+        super().__init__(provider, model_name, tool_name, **kwargs)
         
         # Extract search-related parameters
         self.enable_search = kwargs.get("enable_search", False)
@@ -592,14 +629,16 @@ class FastActionGeneratorTool(BaseTool):
 class EmbeddingTool(BaseTool):
     """Tool for generating text embeddings."""
     
-    def __init__(self, provider: str, model_name: str, tool_name: str):
+    def __init__(self, provider: str, model_name: str, tool_name: str, base_url='', api_key=''):
         """
-        Initialize the embedding tool.
+        Create and configure an EmbeddingTool backed by an EmbeddingAgent.
         
-        Args:
-            provider: API provider name (e.g., "openai", "gemini")
-            model_name: Model name to use
-            tool_name: Name of the tool (used as key in prompts.json)
+        Parameters:
+            provider (str): Name of the embedding service provider (e.g., "openai", "gemini").
+            model_name (str): Embedding model identifier to use.
+            tool_name (str): Tool key used to look up prompts or register the tool.
+            base_url (str, optional): Custom endpoint URL for the provider; defaults to ''.
+            api_key (str, optional): API key or credential for authenticating with the provider; defaults to ''.
         """
         self.provider = provider
         self.model_name = model_name
@@ -608,7 +647,9 @@ class EmbeddingTool(BaseTool):
         # Create EmbeddingAgent instance
         self.engine_params = {
             "engine_type": provider,
-            "embedding_model": model_name
+            "embedding_model": model_name,
+            "base_url": base_url,
+            "api_key": api_key
         }
         
         # Initialize EmbeddingAgent

gui_agents/tools/tools_config.json

@@ -0,0 +1,101 @@
+{
+  "tools": [
+    {
+      "tool_name": "websearch",
+      "provider": "bocha",
+      "model_name": ""
+    },
+    {
+      "tool_name": "context_fusion",
+      "provider": "doubao",
+      "model_name": "doubao-seed-1-6-flash-250615"
+    },
+    {
+      "tool_name": "subtask_planner",
+      "provider": "doubao",
+      "model_name": "doubao-seed-1-6-250615"
+    },
+    {
+      "tool_name": "traj_reflector",
+      "provider": "doubao",
+      "model_name": "doubao-seed-1-6-flash-250615"
+    },
+    {
+      "tool_name": "memory_retrival",
+      "provider": "doubao",
+      "model_name": "doubao-seed-1-6-flash-250615"
+    },
+    {
+      "tool_name": "grounding",
+      "provider": "doubao",
+      "model_name": "doubao-1-5-ui-tars-250428"
+    },
+    {
+      "tool_name": "evaluator",
+      "provider": "doubao",
+      "model_name": "doubao-seed-1-6-flash-250615"
+    },
+    {
+      "tool_name": "action_generator",
+      "provider": "doubao",
+      "model_name": "doubao-seed-1-6-250615",
+      "enable_search": false,
+      "search_provider": "bocha",
+      "search_model": ""
+    },
+    {
+      "tool_name": "action_generator_with_takeover",
+      "provider": "doubao",
+      "model_name": "doubao-seed-1-6-250615",
+      "enable_search": false,
+      "search_provider": "bocha",
+      "search_model": ""
+    },
+    {
+      "tool_name": "fast_action_generator",
+      "provider": "doubao",
+      "model_name": "doubao-1-5-ui-tars-250428",
+      "enable_search": false,
+      "search_provider": "bocha",
+      "search_model": ""
+    },
+    {
+      "tool_name": "fast_action_generator_with_takeover",
+      "provider": "doubao",
+      "model_name": "doubao-1-5-ui-tars-250428",
+      "enable_search": false,
+      "search_provider": "bocha",
+      "search_model": ""
+    },
+    {
+      "tool_name": "dag_translator",
+      "provider": "doubao",
+      "model_name": "doubao-seed-1-6-250615"
+    },
+    {
+      "tool_name": "embedding",
+      "provider": "doubao",
+      "model_name": "doubao-embedding-text-240715"
+    },
+    {
+      "tool_name": "query_formulator",
+      "provider": "doubao",
+      "model_name": "doubao-seed-1-6-flash-250615"
+    },
+    {
+      "tool_name": "narrative_summarization",
+      "provider": "doubao",
+      "model_name": "doubao-seed-1-6-flash-250615"
+    },
+    {
+      "tool_name": "text_span",
+      "provider": "doubao",
+      "model_name": "doubao-seed-1-6-flash-250615"
+    },
+    {
+      "tool_name": "episode_summarization",
+      "provider": "doubao",
+      "model_name": "doubao-seed-1-6-flash-250615"
+    }
+  ]
+}