alita-sdk 0.3.379__py3-none-any.whl → 0.3.462__py3-none-any.whl

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/ado/work_item/ado_wrapper.py

@@ -329,11 +329,14 @@ class AzureDevOpsApiWrapper(NonCodeIndexerToolkit):
                 parsed_item.update(fields_data)
 
             # extract relations if any
-            relations_data = work_item.relations
+            relations_data = None
+            if expand and str(expand).lower() in ("relations", "all"):
+                try:
+                    relations_data = getattr(work_item, 'relations', None)
+                except KeyError:
+                    relations_data = None
             if relations_data:
-                parsed_item['relations'] = []
-                for relation in relations_data:
-                    parsed_item['relations'].append(relation.as_dict())
+                parsed_item['relations'] = [relation.as_dict() for relation in relations_data]
 
             if parse_attachments:
                 # describe images in work item fields if present
@@ -344,13 +347,19 @@ class AzureDevOpsApiWrapper(NonCodeIndexerToolkit):
                         for img in images:
                             src = img.get('src')
                             if src:
-                                description = self.parse_attachment_by_url(src, image_description_prompt)
+                                description = self.parse_attachment_by_url(src, image_description_prompt=image_description_prompt)
                                 img['image-description'] = description
                         parsed_item[field_name] = str(soup)
                 # parse attached documents if present
-                if parsed_item['relations']:
-                    for attachment in parsed_item['relations']:
-                        attachment['content'] = self.parse_attachment_by_url(attachment['url'], attachment['attributes']['name'], image_description_prompt)
+                for relation in parsed_item.get('relations', []):
+                    # Only process actual file attachments
+                    if relation.get('rel') == 'AttachedFile':
+                        file_name = relation.get('attributes', {}).get('name')
+                        if file_name:
+                            try:
+                                relation['content'] = self.parse_attachment_by_url(relation['url'], file_name, image_description_prompt=image_description_prompt)
+                            except Exception as att_e:
+                                logger.warning(f"Failed to parse attachment {file_name}: {att_e}")
 
 
             return parsed_item

alita_sdk/tools/base_indexer_toolkit.py

@@ -4,10 +4,10 @@ import logging
 import time
 from typing import Any, Optional, List, Dict, Generator
 
+from langchain_core.callbacks import dispatch_custom_event
 from langchain_core.documents import Document
 from pydantic import create_model, Field, SecretStr
 
-from .utils import make_json_serializable
 from .utils.content_parser import file_extension_by_chunker, process_document_by_type
 from .vector_adapters.VectorStoreAdapter import VectorStoreAdapterFactory
 from ..runtime.langchain.document_loaders.constants import loaders_allowed_to_override
@@ -16,6 +16,8 @@ from ..runtime.utils.utils import IndexerKeywords
 
 logger = logging.getLogger(__name__)
 
+DEFAULT_CUT_OFF = 0.2
+
 # Base Vector Store Schema Models
 BaseIndexParams = create_model(
     "BaseIndexParams",
@@ -38,7 +40,7 @@ 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.",
@@ -68,7 +70,7 @@ 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.",
@@ -111,7 +113,7 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
     def __init__(self, **kwargs):
         conn = kwargs.get('connection_string', None)
         connection_string = conn.get_secret_value() if isinstance(conn, SecretStr) else conn
-        collection_name = kwargs.get('collection_name')
+        collection_name = kwargs.get('collection_schema')
         
         if 'vectorstore_type' not in kwargs:
             kwargs['vectorstore_type'] = 'PGVector'
@@ -176,11 +178,15 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
                                  f"Processing documents to collect dependencies and prepare them for indexing...")
             self._save_index_generator(documents, documents_count, chunking_tool, chunking_config, index_name=index_name, result=result)
             #
-            self.index_meta_update(index_name, IndexerKeywords.INDEX_META_COMPLETED.value, result["count"])
+            results_count = result["count"]
+            self.index_meta_update(index_name, IndexerKeywords.INDEX_META_COMPLETED.value, results_count)
+            self._emit_index_event(index_name)
             #
-            return {"status": "ok", "message": f"successfully indexed {result["count"]} documents"}
+            return {"status": "ok", "message": f"successfully indexed {results_count} documents" if results_count > 0
+            else "no new documents to index"}
         except Exception as e:
             self.index_meta_update(index_name, IndexerKeywords.INDEX_META_FAILED.value, result["count"])
+            self._emit_index_event(index_name, error=str(e))
             raise e
             
 
@@ -379,7 +385,7 @@ 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,
@@ -410,7 +416,7 @@ 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,
@@ -435,7 +441,7 @@ 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,
@@ -457,37 +463,29 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
         )
     
     def index_meta_init(self, index_name: str, index_configuration: dict[str, Any]):
-        index_meta_raw = super().get_index_meta(index_name)
-        from ..runtime.langchain.interfaces.llm_processor import add_documents
-        created_on = time.time()
-        metadata = {
-            "collection": index_name,
-            "type": IndexerKeywords.INDEX_META_TYPE.value,
-            "indexed": 0,
-            "state": IndexerKeywords.INDEX_META_IN_PROGRESS.value,
-            "index_configuration": index_configuration,
-            "created_on": created_on,
-            "updated_on": created_on,
-            "history": "[]",
-        }
-        index_meta_ids = None
-        #
-        if index_meta_raw:
-            history_raw = index_meta_raw.get("metadata", {}).get("history", "[]")
-            if isinstance(history_raw, str) and history_raw.strip():
-                try:
-                    history = json.loads(history_raw)
-                except (json.JSONDecodeError, TypeError):
-                    history = []
-            else:
-                history = []
-            new_history_item = {k: v for k, v in index_meta_raw.get("metadata", {}).items() if k != "history"}
-            history.append(new_history_item)
-            metadata["history"] = json.dumps(history)
-            index_meta_ids = [index_meta_raw.get("id")]
-        #
-        index_meta_doc = Document(page_content=f"{IndexerKeywords.INDEX_META_TYPE.value}_{index_name}", metadata=metadata)
-        add_documents(vectorstore=self.vectorstore, documents=[index_meta_doc], ids=index_meta_ids)
+        index_meta = super().get_index_meta(index_name)
+        if not index_meta:
+            self._log_tool_event(
+                f"There is no existing index_meta for collection '{index_name}'. Initializing it.",
+                tool_name="index_data"
+            )
+            from ..runtime.langchain.interfaces.llm_processor import add_documents
+            created_on = time.time()
+            metadata = {
+                "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,
+                "updated_on": created_on,
+                "task_id": None,
+                "conversation_id": None,
+            }
+            metadata["history"] = json.dumps([metadata])
+            index_meta_doc = Document(page_content=f"{IndexerKeywords.INDEX_META_TYPE.value}_{index_name}", metadata=metadata)
+            add_documents(vectorstore=self.vectorstore, documents=[index_meta_doc])
 
     def index_meta_update(self, index_name: str, state: str, result: int):
         index_meta_raw = super().get_index_meta(index_name)
@@ -495,12 +493,75 @@ 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()
+            #
+            history_raw = metadata.pop("history", "[]")
+            try:
+                history = json.loads(history_raw) if history_raw.strip() else []
+                # replace the last history item with updated metadata
+                if history and isinstance(history, list):
+                    history[-1] = metadata
+                else:
+                    history = [metadata]
+            except (json.JSONDecodeError, TypeError):
+                logger.warning(f"Failed to load index history: {history_raw}. Create new with only current item.")
+                history = [metadata]
+            #
+            metadata["history"] = json.dumps(history)
             index_meta_doc = Document(page_content=index_meta_raw.get("content", ""), metadata=metadata)
             add_documents(vectorstore=self.vectorstore, documents=[index_meta_doc], ids=[index_meta_raw.get("id")])
 
+    def _emit_index_event(self, index_name: str, error: Optional[str] = None):
+        """
+        Emit custom event for index data operation.
+        
+        Args:
+            index_name: The name of the index
+            error: Error message if the operation failed, None otherwise
+        """
+        index_meta = super().get_index_meta(index_name)
+        
+        if not index_meta:
+            logger.warning(
+                f"No index_meta found for index '{index_name}'. "
+                "Cannot emit index event."
+            )
+            return
+        
+        metadata = index_meta.get("metadata", {})
+        
+        # Determine if this is a reindex operation
+        history_raw = metadata.get("history", "[]")
+        try:
+            history = json.loads(history_raw) if history_raw.strip() else []
+            is_reindex = len(history) > 1
+        except (json.JSONDecodeError, TypeError):
+            is_reindex = False
+        
+        # Build event message
+        event_data = {
+            "id": index_meta.get("id"),
+            "index_name": index_name,
+            "state": metadata.get("state"),
+            "error": error,
+            "reindex": is_reindex,
+            "indexed": metadata.get("indexed", 0),
+            "updated": metadata.get("updated", 0),
+        }
+        
+        # Emit the event
+        try:
+            dispatch_custom_event("index_data_status", event_data)
+            logger.debug(
+                f"Emitted index_data_status event for index "
+                f"'{index_name}': {event_data}"
+            )
+        except Exception as e:
+            logger.warning(f"Failed to emit index_data_status event: {e}")
+
     def get_available_tools(self):
         """
         Returns the standardized vector search tools (search operations only).
@@ -554,6 +615,7 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
                 "mode": "list_collections",
                 "ref": self.list_collections,
                 "description": self.list_collections.__doc__,
-                "args_schema": create_model("ListCollectionsParams")  # No parameters
+                # No parameters
+                "args_schema": create_model("ListCollectionsParams")
             },
-        ]
+        ]

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/chunkers/sematic/proposal_chunker.py

@@ -6,7 +6,7 @@ from langchain_core.prompts import ChatPromptTemplate
 from langchain.text_splitter import TokenTextSplitter
 
 from typing import Optional, List
-from langchain_core.pydantic_v1 import BaseModel
+from pydantic import BaseModel
 from ..utils import tiktoken_length
 
 logger = getLogger(__name__)

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/code_indexer_toolkit.py

@@ -1,5 +1,6 @@
 import ast
 import fnmatch
+import json
 import logging
 from typing import Optional, List, Generator
 
@@ -21,7 +22,7 @@ class CodeIndexerToolkit(BaseIndexerToolkit):
         return self.vector_adapter.get_code_indexed_data(self, index_name)
 
     def key_fn(self, document: Document):
-        return document.metadata.get('id')
+        return document.metadata.get("filename")
 
     def compare_fn(self, document: Document, idx_data):
         return (document.metadata.get('commit_hash') and
@@ -46,7 +47,7 @@ class CodeIndexerToolkit(BaseIndexerToolkit):
         )
 
     def _extend_data(self, documents: Generator[Document, None, None]):
-        yield from parse_code_files_for_db(documents)
+        yield from documents
 
     def _index_tool_params(self):
         """Return the parameters for indexing data."""
@@ -117,6 +118,15 @@ class CodeIndexerToolkit(BaseIndexerToolkit):
                     if not file_content:
                         # empty file, skip
                         continue
+                    #
+                    # ensure file content is a string
+                    if isinstance(file_content, bytes):
+                        file_content = file_content.decode("utf-8", errors="ignore")
+                    elif isinstance(file_content, dict) and file.endswith('.json'):
+                        file_content = json.dumps(file_content)
+                    elif not isinstance(file_content, str):
+                        file_content = str(file_content)
+                    #
                     # hash the file content to ensure uniqueness
                     import hashlib
                     file_hash = hashlib.sha256(file_content.encode("utf-8")).hexdigest()
@@ -127,7 +137,7 @@ class CodeIndexerToolkit(BaseIndexerToolkit):
                     self._log_tool_event(message=f"{idx} out of {total_files} files have been read", tool_name="loader")
             self._log_tool_event(message=f"{len(_files)} have been read", tool_name="loader")
     
-        return file_content_generator()
+        return parse_code_files_for_db(file_content_generator())
 
     def __handle_get_files(self, path: str, branch: str):
         """

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/confluence/api_wrapper.py

@@ -7,12 +7,14 @@ from json import JSONDecodeError
 from typing import Optional, List, Any, Dict, Callable, Generator, Literal
 
 import requests
+from atlassian.errors import ApiError
 from langchain_community.document_loaders.confluence import ContentFormat
 from langchain_core.documents import Document
 from langchain_core.messages import HumanMessage
 from langchain_core.tools import ToolException
 from markdownify import markdownify
 from pydantic import Field, PrivateAttr, model_validator, create_model, SecretStr
+from requests import HTTPError
 from tenacity import retry, stop_after_attempt, wait_exponential, before_sleep_log
 
 from alita_sdk.tools.non_code_indexer_toolkit import NonCodeIndexerToolkit
@@ -194,6 +196,7 @@ class ConfluenceAPIWrapper(NonCodeIndexerToolkit):
     keep_markdown_format: Optional[bool] = True
     ocr_languages: Optional[str] = None
     keep_newlines: Optional[bool] = True
+    _errors: Optional[list[str]] = None
     _image_cache: ImageDescriptionCache = PrivateAttr(default_factory=ImageDescriptionCache)
 
     @model_validator(mode='before')
@@ -498,7 +501,9 @@ class ConfluenceAPIWrapper(NonCodeIndexerToolkit):
         restrictions = self.client.get_all_restrictions_for_content(page["id"])
 
         return (
-                page["status"] == "current"
+                (page["status"] == "current"
+                # allow user to see archived content if needed
+                 or page["status"] == "archived")
                 and not restrictions["read"]["restrictions"]["user"]["results"]
                 and not restrictions["read"]["restrictions"]["group"]["results"]
         )
@@ -518,18 +523,35 @@ class ConfluenceAPIWrapper(NonCodeIndexerToolkit):
                 ),
                 before_sleep=before_sleep_log(logger, logging.WARNING),
             )(self.client.get_page_by_id)
-            page = get_page(
-                page_id=page_id, expand=f"{self.content_format.value},version"
-            )
-            if not self.include_restricted_content and not self.is_public_page(page):
-                continue
+            try:
+                page = get_page(
+                    page_id=page_id, expand=f"{self.content_format.value},version"
+                )
+            except (ApiError, HTTPError) as e:
+                logger.error(f"Error fetching page with ID {page_id}: {e}")
+                page_content_temp = f"Confluence API Error: cannot fetch the page with ID {page_id}: {e}"
+                # store errors
+                if self._errors is None:
+                    self._errors = []
+                self._errors.append(page_content_temp)
+                return Document(page_content=page_content_temp,
+                                metadata={})
+            # TODO: update on toolkit advanced settings level as a separate feature
+            # if not self.include_restricted_content and not self.is_public_page(page):
+            #     continue
             yield self.process_page(page, skip_images)
 
+    def _log_errors(self):
+        """ Log errors encountered during toolkit execution. """
+        if self._errors:
+            logger.info(f"Errors encountered during toolkit execution: {self._errors}")
+
     def read_page_by_id(self, page_id: str, skip_images: bool = False):
         """Reads a page by its id in the Confluence space. If id is not available, but there is a title - use get_page_id first."""
         result = list(self.get_pages_by_id([page_id], skip_images))
         if not result:
-            "Page not found"
+            return f"Pages not found. Errors: {self._errors}" if self._errors \
+                else "Pages not found or you do not have access to them."
         return result[0].page_content
         # return self._strip_base64_images(result[0].page_content) if skip_images else result[0].page_content
 

alita_sdk/tools/confluence/loader.py

@@ -3,6 +3,7 @@ from typing import Optional, List
 from logging import getLogger
 
 import requests
+from langchain_core.documents import Document
 
 logger = getLogger(__name__)
 from PIL import Image
@@ -193,6 +194,15 @@ class AlitaConfluenceLoader(ConfluenceLoader):
         else:
             return super().process_image(link, ocr_languages)
 
+    def process_page(self, page: dict, include_attachments: bool, include_comments: bool, include_labels: bool,
+                     content_format: ContentFormat, ocr_languages: Optional[str] = None,
+                     keep_markdown_format: Optional[bool] = False, keep_newlines: bool = False) -> Document:
+        if not page.get("title"):
+            # if 'include_restricted_content' set to True, draft pages are loaded and can have no title
+            page["title"] = "Untitled"
+        return super().process_page(page, include_attachments, include_comments, include_labels, content_format,
+                                    ocr_languages, keep_markdown_format, keep_newlines)
+
     # TODO review usage
     # def process_svg(
     #         self,

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/api_wrapper.py

@@ -117,7 +117,11 @@ class GitLabAPIWrapper(CodeIndexerToolkit):
 
     @model_validator(mode='before')
     @classmethod
-    def validate_toolkit(cls, values: Dict) -> Dict:
+    def validate_toolkit_before(cls, values: Dict) -> Dict:
+        return super().validate_toolkit(values)
+
+    @model_validator(mode='after')
+    def validate_toolkit(self):
         try:
            import gitlab
         except ImportError:
@@ -125,17 +129,17 @@ class GitLabAPIWrapper(CodeIndexerToolkit):
                 "python-gitlab is not installed. "
                 "Please install it with `pip install python-gitlab`"
             )
-        values['repository'] = cls._sanitize_url(values['repository'])
+        self.repository = self._sanitize_url(self.repository)
         g = gitlab.Gitlab(
-            url=cls._sanitize_url(values['url']),
-            private_token=values['private_token'],
+            url=self._sanitize_url(self.url),
+            private_token=self.private_token.get_secret_value(),
             keep_base_url=True,
         )
 
         g.auth()
-        cls._git = g
-        cls._active_branch = values.get('branch')
-        return super().validate_toolkit(values)
+        self._git = g
+        self._active_branch = self.branch
+        return self
 
     @property
     def repo_instance(self):

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/jira/api_wrapper.py

@@ -563,7 +563,7 @@ class JiraApiWrapper(NonCodeIndexerToolkit):
         Use the appropriate issue link type (e.g., "Test", "Relates", "Blocks").
         If we use "Test" linktype, the test is inward issue, the story/other issue is outward issue.."""
 
-        comment = "This test is linked to the story."
+        comment = f"Issue {inward_issue_key} was linked to {outward_issue_key}."
         comment_body = {"content": [{"content": [{"text": comment,"type": "text"}],"type": "paragraph"}],"type": "doc","version": 1} if self.api_version == "3" else comment
         link_data = {
             "type": {"name": f"{linktype}"},

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']})),