alita-sdk 0.3.449__py3-none-any.whl → 0.3.457__py3-none-any.whl

alita_sdk/runtime/langchain/langraph_agent.py

@@ -475,10 +475,14 @@ def create_graph(
             if toolkit_name:
                 tool_name = f"{clean_string(toolkit_name)}{TOOLKIT_SPLITTER}{tool_name}"
             logger.info(f"Node: {node_id} : {node_type} - {tool_name}")
-            if node_type in ['function', 'tool', 'loop', 'loop_from_tool', 'indexer', 'subgraph', 'pipeline', 'agent']:
+            if node_type in ['function', 'toolkit', 'mcp', 'tool', 'loop', 'loop_from_tool', 'indexer', 'subgraph', 'pipeline', 'agent']:
+                if node_type == 'mcp' and tool_name not in [tool.name for tool in tools]:
+                    # MCP is not connected and node cannot be added
+                    raise ToolException(f"MCP tool '{tool_name}' not found in the provided tools. "
+                                        f"Make sure it is connected properly. Available tools: {[tool.name for tool in tools]}")
                 for tool in tools:
                     if tool.name == tool_name:
-                        if node_type == 'function':
+                        if node_type in ['function', 'toolkit', 'mcp']:
                             lg_builder.add_node(node_id, FunctionTool(
                                 tool=tool, name=node_id, return_type='dict',
                                 output_variables=node.get('output', []),
@@ -643,6 +647,7 @@ def create_graph(
                         default_output=node.get('default_output', 'END')
                     )
                 )
+                continue
             elif node_type == 'state_modifier':
                 lg_builder.add_node(node_id, StateModifierNode(
                     template=node.get('template', ''),
@@ -663,7 +668,7 @@ def create_graph(
                 lg_builder.add_node(reset_node_id, PrinterNode(
                     input_mapping={'printer': {'type': 'fixed', 'value': ''}}
                 ))
-                lg_builder.add_edge(node_id, reset_node_id)
+                lg_builder.add_conditional_edges(node_id, TransitionalEdge(reset_node_id))
                 lg_builder.add_conditional_edges(reset_node_id, TransitionalEdge(clean_string(node['transition'])))
                 continue
             if node.get('transition'):
@@ -814,35 +819,63 @@ class LangGraphAgentRunnable(CompiledStateGraph):
             input['messages'] = [convert_dict_to_message(msg) for msg in chat_history]
 
         # handler for LLM node: if no input (Chat perspective), then take last human message
+        # Track if input came from messages to handle content extraction properly
+        input_from_messages = False
         if not input.get('input'):
             if input.get('messages'):
                 input['input'] = [next((msg for msg in reversed(input['messages']) if isinstance(msg, HumanMessage)),
-                                          None)]
+                                      None)]
+                if input['input'] is not None:
+                    input_from_messages = True
 
         # Append current input to existing messages instead of overwriting
         if input.get('input'):
             if isinstance(input['input'], str):
                 current_message = input['input']
             else:
+                # input can be a list of messages or a single message object
                 current_message = input.get('input')[-1]
 
             # TODO: add handler after we add 2+ inputs (filterByType, etc.)
             if isinstance(current_message, HumanMessage):
                 current_content = current_message.content
                 if isinstance(current_content, list):
-                    text_contents = [
-                        item['text'] if isinstance(item, dict) and item.get('type') == 'text'
-                        else item if isinstance(item, str)
-                        else None
-                        for item in current_content
-                    ]
-                    text_contents = [text for text in text_contents if text is not None]
-                    input['input'] = ". ".join(text_contents)
+                    # Extract text parts and keep non-text parts (images, etc.)
+                    text_contents = []
+                    non_text_parts = []
+                    
+                    for item in current_content:
+                        if isinstance(item, dict) and item.get('type') == 'text':
+                            text_contents.append(item['text'])
+                        elif isinstance(item, str):
+                            text_contents.append(item)
+                        else:
+                            # Keep image_url and other non-text content
+                            non_text_parts.append(item)
+                    
+                    # Set input to the joined text
+                    input['input'] = ". ".join(text_contents) if text_contents else ""
+                    
+                    # If this message came from input['messages'], update or remove it
+                    if input_from_messages:
+                        if non_text_parts:
+                            # Keep the message but only with non-text content (images, etc.)
+                            current_message.content = non_text_parts
+                        else:
+                            # All content was text, remove this message from the list
+                            input['messages'] = [msg for msg in input['messages'] if msg is not current_message]
+                
                 elif isinstance(current_content, str):
                     # on regenerate case
                     input['input'] = current_content
+                    # If from messages and all content is text, remove the message
+                    if input_from_messages:
+                        input['messages'] = [msg for msg in input['messages'] if msg is not current_message]
                 else:
                     input['input'] = str(current_content)
+                    # If from messages, remove since we extracted the content
+                    if input_from_messages:
+                        input['messages'] = [msg for msg in input['messages'] if msg is not current_message]
             elif isinstance(current_message, str):
                 input['input'] = current_message
             else:
@@ -852,9 +885,18 @@ class LangGraphAgentRunnable(CompiledStateGraph):
                 input['messages'] = [convert_dict_to_message(msg) for msg in input['messages']]
                 # Append to existing messages
                 # input['messages'].append(current_message)
-            else:
-                # No existing messages, create new list
-                input['messages'] = [current_message]
+            # else:
+                # NOTE: Commented out to prevent duplicates with input['input']
+                # input['messages'] = [current_message]
+        
+        # Validate that input is not empty after all processing
+        if not input.get('input'):
+            raise RuntimeError(
+                "Empty input after processing. Cannot send empty string to LLM. "
+                "This likely means the message contained only non-text content "
+                "with no accompanying text."
+            )
+        
         logging.info(f"Input: {thread_id} - {input}")
         if self.checkpointer and self.checkpointer.get_tuple(config):
             self.update_state(config, input)

alita_sdk/runtime/langchain/utils.py

@@ -2,7 +2,7 @@ import builtins
 import json
 import logging
 import re
-from pydantic import create_model, Field
+from pydantic import create_model, Field, Json
 from typing import Tuple, TypedDict, Any, Optional, Annotated
 from langchain_core.messages import AnyMessage
 from langgraph.graph import add_messages
@@ -208,5 +208,21 @@ def safe_format(template, mapping):
 def create_pydantic_model(model_name: str, variables: dict[str, dict]):
     fields = {}
     for var_name, var_data in variables.items():
-        fields[var_name] = (parse_type(var_data['type']), Field(description=var_data.get('description', None)))
-    return create_model(model_name, **fields)
+        fields[var_name] = (parse_pydantic_type(var_data['type']), Field(description=var_data.get('description', None)))
+    return create_model(model_name, **fields)
+
+def parse_pydantic_type(type_name: str):
+    """
+    Helper function to parse type names into Python types.
+    Extend this function to handle custom types like 'dict' -> Json[Any].
+    """
+    type_mapping = {
+        'str': str,
+        'int': int,
+        'float': float,
+        'bool': bool,
+        'dict': Json[Any],  # Map 'dict' to Pydantic's Json type
+        'list': list,
+        'any': Any
+    }
+    return type_mapping.get(type_name, Any)

alita_sdk/runtime/toolkits/artifact.py

@@ -23,11 +23,7 @@ class ArtifactToolkit(BaseToolkit):
             # client = (Any, FieldInfo(description="Client object", required=True, autopopulate=True)),
             bucket=(str, FieldInfo(
                 description="Bucket name",
-                pattern=r'^[a-z][a-z0-9-]*$',
-                json_schema_extra={
-                    'toolkit_name': True,
-                    'max_toolkit_length': ArtifactToolkit.toolkit_max_length
-                }
+                pattern=r'^[a-z][a-z0-9-]*$'
             )),
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             # indexer settings
@@ -37,7 +33,10 @@ class ArtifactToolkit(BaseToolkit):
             embedding_model=(Optional[str], Field(default=None, description="Embedding configuration.",
                                                   json_schema_extra={'configuration_model': 'embedding'})),
 
-            __config__=ConfigDict(json_schema_extra={'metadata': {"label": "Artifact", "icon_url": None}})
+            __config__=ConfigDict(json_schema_extra={'metadata': {"label": "Artifact",
+                                                                  "icon_url": None,
+                                                                  "max_length": ArtifactToolkit.toolkit_max_length
+                                                                  }})
         )
     
     @classmethod

alita_sdk/runtime/toolkits/mcp.py

@@ -498,9 +498,12 @@ class McpToolkit(BaseToolkit):
         all_tools = []
         session_id = connection_config.session_id
         
+        # Generate temporary session_id if not provided (for OAuth flow)
+        # The real session_id should come from frontend after OAuth completes
         if not session_id:
-            logger.error(f"[MCP SSE] session_id is required for SSE servers")
-            raise ValueError("session_id is required. Frontend must generate UUID.")
+            import uuid
+            session_id = str(uuid.uuid4())
+            logger.info(f"[MCP SSE] Generated temporary session_id for OAuth: {session_id}")
         
         logger.info(f"[MCP SSE] Discovering from {connection_config.url} with session {session_id}")
         

alita_sdk/runtime/toolkits/tools.py

@@ -110,6 +110,7 @@ def get_tools(tools_list: list, alita_client, llm, memory_store: BaseStore = Non
                     toolkit_name=tool.get('toolkit_name', ''),
                     **tool['settings']).get_tools())
             elif tool['type'] == 'mcp':
+                # remote mcp tool initialization with token injection
                 settings = dict(tool['settings'])
                 url = settings.get('url')
                 headers = settings.get('headers')

alita_sdk/runtime/tools/function.py

@@ -120,7 +120,8 @@ class FunctionTool(BaseTool):
                     messages_dict = {
                         "messages": [{
                             "role": "assistant",
-                            "content": dumps(tool_result) if not isinstance(tool_result, ToolException)
+                            "content": dumps(tool_result)
+                            if not isinstance(tool_result, ToolException) and not isinstance(tool_result, str)
                             else str(tool_result)
                         }]
                     }

alita_sdk/runtime/tools/vectorstore_base.py

@@ -1,9 +1,9 @@
 import json
-import math
 from collections import OrderedDict
 from logging import getLogger
 from typing import Any, Optional, List, Dict, Generator
 
+import math
 from langchain_core.documents import Document
 from langchain_core.messages import HumanMessage
 from langchain_core.tools import ToolException
@@ -12,7 +12,7 @@ from pydantic import BaseModel, model_validator, Field
 
 from alita_sdk.tools.elitea_base import BaseToolApiWrapper
 from alita_sdk.tools.vector_adapters.VectorStoreAdapter import VectorStoreAdapterFactory
-from ..utils.logging import dispatch_custom_event
+from ...runtime.utils.utils import IndexerKeywords
 
 logger = getLogger(__name__)
 
@@ -222,6 +222,21 @@ class VectorStoreWrapperBase(BaseToolApiWrapper):
             raise RuntimeError(f"Multiple index_meta documents found: {index_metas}")
         return index_metas[0] if index_metas else None
 
+    def get_indexed_count(self, index_name: str) -> int:
+        from sqlalchemy.orm import Session
+        from sqlalchemy import func, or_
+
+        with Session(self.vectorstore.session_maker.bind) as session:
+            return session.query(
+                self.vectorstore.EmbeddingStore.id,
+            ).filter(
+                func.jsonb_extract_path_text(self.vectorstore.EmbeddingStore.cmetadata, 'collection') == index_name,
+                or_(
+                    func.jsonb_extract_path_text(self.vectorstore.EmbeddingStore.cmetadata, 'type').is_(None),
+                    func.jsonb_extract_path_text(self.vectorstore.EmbeddingStore.cmetadata, 'type') != IndexerKeywords.INDEX_META_TYPE.value
+                )
+            ).count()
+
     def _clean_collection(self, index_name: str = ''):
         """
         Clean the vectorstore collection by deleting all indexed data.

alita_sdk/runtime/utils/mcp_sse_client.py

@@ -65,6 +65,53 @@ class McpSseClient:
             
             logger.info(f"[MCP SSE Client] Stream opened: status={self._stream_response.status}")
             
+            # Handle 401 Unauthorized - need OAuth
+            if self._stream_response.status == 401:
+                from ..utils.mcp_oauth import (
+                    McpAuthorizationRequired,
+                    canonical_resource,
+                    extract_resource_metadata_url,
+                    fetch_resource_metadata_async,
+                    infer_authorization_servers_from_realm,
+                    fetch_oauth_authorization_server_metadata
+                )
+                
+                auth_header = self._stream_response.headers.get('WWW-Authenticate', '')
+                resource_metadata_url = extract_resource_metadata_url(auth_header, self.url)
+                
+                metadata = None
+                if resource_metadata_url:
+                    metadata = await fetch_resource_metadata_async(
+                        resource_metadata_url,
+                        session=self._stream_session,
+                        timeout=30
+                    )
+                
+                # Infer authorization servers if not in metadata
+                if not metadata or not metadata.get('authorization_servers'):
+                    inferred_servers = infer_authorization_servers_from_realm(auth_header, self.url)
+                    if inferred_servers:
+                        if not metadata:
+                            metadata = {}
+                        metadata['authorization_servers'] = inferred_servers
+                        logger.info(f"[MCP SSE Client] Inferred authorization servers: {inferred_servers}")
+                        
+                        # Fetch OAuth metadata
+                        auth_server_metadata = fetch_oauth_authorization_server_metadata(inferred_servers[0], timeout=30)
+                        if auth_server_metadata:
+                            metadata['oauth_authorization_server'] = auth_server_metadata
+                            logger.info(f"[MCP SSE Client] Fetched OAuth metadata")
+                
+                raise McpAuthorizationRequired(
+                    message=f"MCP server {self.url} requires OAuth authorization",
+                    server_url=canonical_resource(self.url),
+                    resource_metadata_url=resource_metadata_url,
+                    www_authenticate=auth_header,
+                    resource_metadata=metadata,
+                    status=self._stream_response.status,
+                    tool_name=self.url,
+                )
+            
             if self._stream_response.status != 200:
                 error_text = await self._stream_response.text()
                 raise Exception(f"Failed to open SSE stream: HTTP {self._stream_response.status}: {error_text}")
@@ -248,18 +295,29 @@ class McpSseClient:
         """Close the persistent SSE stream."""
         logger.info(f"[MCP SSE Client] Closing connection...")
         
+        # Cancel background stream reader task
         if self._stream_task and not self._stream_task.done():
             self._stream_task.cancel()
             try:
                 await self._stream_task
-            except asyncio.CancelledError:
-                pass
+            except (asyncio.CancelledError, Exception) as e:
+                logger.debug(f"[MCP SSE Client] Stream task cleanup: {e}")
         
-        if self._stream_response:
-            self._stream_response.close()
+        # Close response stream
+        if self._stream_response and not self._stream_response.closed:
+            try:
+                self._stream_response.close()
+            except Exception as e:
+                logger.debug(f"[MCP SSE Client] Response close error: {e}")
         
-        if self._stream_session:
-            await self._stream_session.close()
+        # Close session
+        if self._stream_session and not self._stream_session.closed:
+            try:
+                await self._stream_session.close()
+                # Give aiohttp time to cleanup
+                await asyncio.sleep(0.1)
+            except Exception as e:
+                logger.debug(f"[MCP SSE Client] Session close error: {e}")
         
         logger.info(f"[MCP SSE Client] Connection closed")
     

alita_sdk/tools/ado/repos/__init__.py

@@ -63,6 +63,7 @@ class AzureDevOpsReposToolkit(BaseToolkit):
                     "icon_url": "ado-repos-icon.svg",
                     "categories": ["code repositories"],
                     "extra_categories": ["code", "repository", "version control"],
+                    "max_length": AzureDevOpsReposToolkit.toolkit_max_length
                 }}}
         )
 

alita_sdk/tools/ado/test_plan/__init__.py

@@ -27,7 +27,6 @@ class AzureDevOpsPlansToolkit(BaseToolkit):
         AzureDevOpsPlansToolkit.toolkit_max_length = get_max_toolkit_length(selected_tools)
         m = create_model(
             name_alias,
-            name=(str, Field(description="Toolkit name", json_schema_extra={'toolkit_name': True, 'max_toolkit_length': AzureDevOpsPlansToolkit.toolkit_max_length})),
             ado_configuration=(AdoConfiguration, Field(description="Ado configuration", json_schema_extra={'configuration_types': ['ado']})),
             limit=(Optional[int], Field(description="ADO plans limit used for limitation of the list with results", default=5)),
             # indexer settings
@@ -40,6 +39,7 @@ class AzureDevOpsPlansToolkit(BaseToolkit):
                 {
                     "label": "ADO plans",
                     "icon_url": "ado-plans.svg",
+                    "max_length": AzureDevOpsPlansToolkit.toolkit_max_length,
                     "categories": ["test management"],
                     "extra_categories": ["test case management", "qa"],
                     "sections": {

alita_sdk/tools/ado/wiki/__init__.py

@@ -24,11 +24,6 @@ class AzureDevOpsWikiToolkit(BaseToolkit):
         AzureDevOpsWikiToolkit.toolkit_max_length = get_max_toolkit_length(selected_tools)
         m = create_model(
             name_alias,
-            name=(str, Field(description="Toolkit name",
-                             json_schema_extra={
-                                 'toolkit_name': True,
-                                 'max_toolkit_length': AzureDevOpsWikiToolkit.toolkit_max_length})
-                  ),
             ado_configuration=(AdoConfiguration, Field(description="Ado configuration", json_schema_extra={'configuration_types': ['ado']})),
             # indexer settings
             pgvector_configuration=(Optional[PgVectorConfiguration], Field(default=None,
@@ -42,6 +37,7 @@ class AzureDevOpsWikiToolkit(BaseToolkit):
                     'metadata': {
                         "label": "ADO wiki",
                         "icon_url": "ado-wiki-icon.svg",
+                        "max_length": AzureDevOpsWikiToolkit.toolkit_max_length,
                         "categories": ["documentation"],
                         "extra_categories": ["knowledge base", "documentation management", "wiki"],
                         "sections": {

alita_sdk/tools/ado/work_item/__init__.py

@@ -23,11 +23,6 @@ class AzureDevOpsWorkItemsToolkit(BaseToolkit):
         AzureDevOpsWorkItemsToolkit.toolkit_max_length = get_max_toolkit_length(selected_tools)
         m = create_model(
             name,
-            name=(str, Field(description="Toolkit name",
-                             json_schema_extra={
-                                 'toolkit_name': True,
-                                 'max_toolkit_length': AzureDevOpsWorkItemsToolkit.toolkit_max_length})
-                  ),
             ado_configuration=(AdoConfiguration, Field(description="Ado Work Item configuration", json_schema_extra={'configuration_types': ['ado']})),
             limit=(Optional[int], Field(description="ADO plans limit used for limitation of the list with results", default=5)),
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
@@ -42,6 +37,7 @@ class AzureDevOpsWorkItemsToolkit(BaseToolkit):
                     'metadata': {
                         "label": "ADO boards",
                         "icon_url": "ado-boards-icon.svg",
+                        "max_length": AzureDevOpsWorkItemsToolkit.toolkit_max_length,
                         "categories": ["project management"],
                         "extra_categories": ["work item management", "issue tracking", "agile boards"],
                         "sections": {

alita_sdk/tools/base_indexer_toolkit.py

@@ -15,6 +15,8 @@ from ..runtime.utils.utils import IndexerKeywords
 
 logger = logging.getLogger(__name__)
 
+DEFAULT_CUT_OFF = 0.2
+
 # Base Vector Store Schema Models
 BaseIndexParams = create_model(
     "BaseIndexParams",
@@ -37,7 +39,7 @@ BaseSearchParams = create_model(
         default={},
         examples=["{\"key\": \"value\"}", "{\"status\": \"active\"}"]
     )),
-    cut_off=(Optional[float], Field(description="Cut-off score for search results", default=0.5, ge=0, le=1)),
+    cut_off=(Optional[float], Field(description="Cut-off score for search results", default=DEFAULT_CUT_OFF, ge=0, le=1)),
     search_top=(Optional[int], Field(description="Number of top results to return", default=10)),
     full_text_search=(Optional[Dict[str, Any]], Field(
         description="Full text search parameters. Can be a dictionary with search options.",
@@ -67,7 +69,7 @@ BaseStepbackSearchParams = create_model(
         default={},
         examples=["{\"key\": \"value\"}", "{\"status\": \"active\"}"]
     )),
-    cut_off=(Optional[float], Field(description="Cut-off score for search results", default=0.5, ge=0, le=1)),
+    cut_off=(Optional[float], Field(description="Cut-off score for search results", default=DEFAULT_CUT_OFF, ge=0, le=1)),
     search_top=(Optional[int], Field(description="Number of top results to return", default=10)),
     full_text_search=(Optional[Dict[str, Any]], Field(
         description="Full text search parameters. Can be a dictionary with search options.",
@@ -380,7 +382,7 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
     def search_index(self,
                      query: str,
                      index_name: str = "",
-                     filter: dict | str = {}, cut_off: float = 0.5,
+                     filter: dict | str = {}, cut_off: float = DEFAULT_CUT_OFF,
                      search_top: int = 10, reranker: dict = {},
                      full_text_search: Optional[Dict[str, Any]] = None,
                      reranking_config: Optional[Dict[str, Dict[str, Any]]] = None,
@@ -411,7 +413,7 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
                      query: str,
                      messages: List[Dict[str, Any]] = [],
                      index_name: str = "",
-                     filter: dict | str = {}, cut_off: float = 0.5,
+                     filter: dict | str = {}, cut_off: float = DEFAULT_CUT_OFF,
                      search_top: int = 10, reranker: dict = {},
                      full_text_search: Optional[Dict[str, Any]] = None,
                      reranking_config: Optional[Dict[str, Dict[str, Any]]] = None,
@@ -436,7 +438,7 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
                      query: str,
                      messages: List[Dict[str, Any]] = [],
                      index_name: str = "",
-                     filter: dict | str = {}, cut_off: float = 0.5,
+                     filter: dict | str = {}, cut_off: float = DEFAULT_CUT_OFF,
                      search_top: int = 10, reranker: dict = {},
                      full_text_search: Optional[Dict[str, Any]] = None,
                      reranking_config: Optional[Dict[str, Dict[str, Any]]] = None,
@@ -470,6 +472,7 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
                 "collection": index_name,
                 "type": IndexerKeywords.INDEX_META_TYPE.value,
                 "indexed": 0,
+                "updated": 0,
                 "state": IndexerKeywords.INDEX_META_IN_PROGRESS.value,
                 "index_configuration": index_configuration,
                 "created_on": created_on,
@@ -487,7 +490,8 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
         #
         if index_meta_raw:
             metadata = copy.deepcopy(index_meta_raw.get("metadata", {}))
-            metadata["indexed"] = result
+            metadata["indexed"] = self.get_indexed_count(index_name)
+            metadata["updated"] = result
             metadata["state"] = state
             metadata["updated_on"] = time.time()
             #

alita_sdk/tools/bitbucket/__init__.py

@@ -61,6 +61,7 @@ class AlitaBitbucketToolkit(BaseToolkit):
                 'metadata':
                     {
                         "label": "Bitbucket", "icon_url": "bitbucket-icon.svg",
+                        "max_length": AlitaBitbucketToolkit.toolkit_max_length,
                         "categories": ["code repositories"],
                         "extra_categories": ["bitbucket", "git", "repository", "code", "version control"],
                     }

alita_sdk/tools/code/sonar/__init__.py

@@ -29,7 +29,7 @@ class SonarToolkit(BaseToolkit):
         SonarToolkit.toolkit_max_length = get_max_toolkit_length(selected_tools)
         return create_model(
             name,
-            sonar_project_name=(str, Field(description="Project name of the desired repository", json_schema_extra={'toolkit_name': True, 'max_toolkit_length': SonarToolkit.toolkit_max_length})),
+            sonar_project_name=(str, Field(description="Project name of the desired repository")),
             sonar_configuration=(SonarConfiguration, Field(description="Sonar Configuration", json_schema_extra={'configuration_types': ['sonar']})),
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __config__=ConfigDict(json_schema_extra=

alita_sdk/tools/confluence/__init__.py

@@ -67,8 +67,7 @@ class ConfluenceToolkit(BaseToolkit):
 
         model = create_model(
             name,
-            space=(str, Field(description="Space", json_schema_extra={'toolkit_name': True,
-                                                                                    'max_toolkit_length': ConfluenceToolkit.toolkit_max_length})),
+            space=(str, Field(description="Space")),
             cloud=(bool, Field(description="Hosting Option", json_schema_extra={'configuration': True})),
             limit=(int, Field(description="Pages limit per request", default=5)),
             labels=(Optional[str], Field(
@@ -95,6 +94,7 @@ class ConfluenceToolkit(BaseToolkit):
                 'metadata': {
                     "label": "Confluence",
                     "icon_url": None,
+                    "max_length": ConfluenceToolkit.toolkit_max_length,
                     "categories": ["documentation"],
                     "extra_categories": ["confluence", "wiki", "knowledge base", "documentation", "atlassian"]
                 }

alita_sdk/tools/github/__init__.py

@@ -53,6 +53,7 @@ class AlitaGitHubToolkit(BaseToolkit):
                     'metadata': {
                         "label": "GitHub",
                         "icon_url": None,
+                        "max_length": AlitaGitHubToolkit.toolkit_max_length,
                         "categories": ["code repositories"],
                         "extra_categories": ["github", "git", "repository", "code", "version control"],
                     },
@@ -62,8 +63,7 @@ class AlitaGitHubToolkit(BaseToolkit):
                                                              json_schema_extra={'configuration_types': ['github']})),
             pgvector_configuration=(Optional[PgVectorConfiguration], Field(description="PgVector configuration", default=None,
                                                                      json_schema_extra={'configuration_types': ['pgvector']})),
-            repository=(str, Field(description="Github repository", json_schema_extra={'toolkit_name': True,
-                                                                                       'max_toolkit_length': AlitaGitHubToolkit.toolkit_max_length})),
+            repository=(str, Field(description="Github repository")),
             active_branch=(Optional[str], Field(description="Active branch", default="main")),
             base_branch=(Optional[str], Field(description="Github Base branch", default="main")),
             # embedder settings

alita_sdk/tools/gitlab/__init__.py

@@ -43,7 +43,7 @@ class AlitaGitlabToolkit(BaseToolkit):
         AlitaGitlabToolkit.toolkit_max_length = get_max_toolkit_length(selected_tools)
         return create_model(
             name,
-            repository=(str, Field(description="GitLab repository", json_schema_extra={'toolkit_name': True, 'max_toolkit_length': AlitaGitlabToolkit.toolkit_max_length})),
+            repository=(str, Field(description="GitLab repository")),
             gitlab_configuration=(GitlabConfiguration, Field(description="GitLab configuration", json_schema_extra={'configuration_types': ['gitlab']})),
             branch=(str, Field(description="Main branch", default="main")),
             # indexer settings
@@ -57,6 +57,7 @@ class AlitaGitlabToolkit(BaseToolkit):
                 'metadata': {
                     "label": "GitLab",
                     "icon_url": None,
+                    "max_length": AlitaGitlabToolkit.toolkit_max_length,
                     "categories": ["code repositories"],
                     "extra_categories": ["gitlab", "git", "repository", "code", "version control"],
                 }

alita_sdk/tools/gitlab_org/__init__.py

@@ -30,8 +30,6 @@ class AlitaGitlabSpaceToolkit(BaseToolkit):
         AlitaGitlabSpaceToolkit.toolkit_max_length = get_max_toolkit_length(selected_tools)
         return create_model(
             name,
-            name=(str, Field(description="Toolkit name", json_schema_extra={'toolkit_name': True,
-                                                                            'max_toolkit_length': AlitaGitlabSpaceToolkit.toolkit_max_length})),
             gitlab_configuration=(GitlabConfiguration, Field(description="GitLab configuration",
                                                                        json_schema_extra={
                                                                            'configuration_types': ['gitlab']})),
@@ -46,6 +44,7 @@ class AlitaGitlabSpaceToolkit(BaseToolkit):
                 'metadata': {
                     "label": "GitLab Org",
                     "icon_url": None,
+                    "max_length": AlitaGitlabSpaceToolkit.toolkit_max_length,
                     "categories": ["code repositories"],
                     "extra_categories": ["gitlab", "git", "repository", "code", "version control"],
                 }

alita_sdk/tools/google_places/__init__.py

@@ -30,7 +30,7 @@ class GooglePlacesToolkit(BaseToolkit):
         GooglePlacesToolkit.toolkit_max_length = get_max_toolkit_length(selected_tools)
         return create_model(
             name,
-            results_count=(Optional[int], Field(description="Results number to show", default=None, json_schema_extra={'toolkit_name': True, 'max_toolkit_length': GooglePlacesToolkit.toolkit_max_length})),
+            results_count=(Optional[int], Field(description="Results number to show", default=None)),
             google_places_configuration=(GooglePlacesConfiguration, Field(description="Google Places Configuration", json_schema_extra={'configuration_types': ['google_places']})),
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __config__=ConfigDict(json_schema_extra=
@@ -38,6 +38,7 @@ class GooglePlacesToolkit(BaseToolkit):
                                       'metadata':
                                           {
                                               "label": "Google Places", "icon_url": "gplaces-icon.svg",
+                                              "max_length": GooglePlacesToolkit.toolkit_max_length,
                                               "categories": ["other"],
                                               "extra_categories": ["google", "places", "maps", "location",
                                                                    "geolocation"],

alita_sdk/tools/jira/__init__.py

@@ -89,6 +89,7 @@ class JiraToolkit(BaseToolkit):
                 'metadata': {
                     "label": "Jira",
                     "icon_url": "jira-icon.svg",
+                    "max_length": JiraToolkit.toolkit_max_length,
                     "categories": ["project management"],
                     "extra_categories": ["jira", "atlassian", "issue tracking", "project management", "task management"],
                 }

alita_sdk/tools/memory/__init__.py

@@ -61,7 +61,7 @@ class MemoryToolkit(BaseToolkit):
 
         return create_model(
             'memory',
-            namespace=(str, Field(description="Memory namespace", json_schema_extra={'toolkit_name': True})),
+            namespace=(str, Field(description="Memory namespace")),
             pgvector_configuration=(PgVectorConfiguration, Field(description="PgVector Configuration",
                                                                            json_schema_extra={
                                                                                'configuration_types': ['pgvector']})),

alita_sdk/tools/pandas/__init__.py

@@ -29,7 +29,7 @@ class PandasToolkit(BaseToolkit):
         PandasToolkit.toolkit_max_length = get_max_toolkit_length(selected_tools)
         return create_model(
             name,
-            bucket_name=(str, Field(default=None, title="Bucket name", description="Bucket where the content file is stored", json_schema_extra={'toolkit_name': True, 'max_toolkit_length': PandasToolkit.toolkit_max_length})),
+            bucket_name=(str, Field(default=None, title="Bucket name", description="Bucket where the content file is stored")),
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __config__=ConfigDict(json_schema_extra={'metadata': {"label": "Pandas", "icon_url": "pandas-icon.svg",
                                                                   "categories": ["analysis"],