merge

api/configs/packaging/__init__.py

@@ -8,11 +8,6 @@ class PackagingInfo(PyProjectTomlConfig):
     Packaging build information
     """
 
-    CURRENT_VERSION: str = Field(
-        description="Dify version",
-        default="1.5.1",
-    )
-
     COMMIT_SHA: str = Field(
         description="SHA-1 checksum of the git commit used to build the app",
         default="",

api/controllers/console/app/audio.py

@@ -90,23 +90,11 @@ class ChatMessageTextApi(Resource):
 
             message_id = args.get("message_id", None)
             text = args.get("text", None)
-            if (
-                app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}
-                and app_model.workflow
-                and app_model.workflow.features_dict
-            ):
-                text_to_speech = app_model.workflow.features_dict.get("text_to_speech")
-                if text_to_speech is None:
-                    raise ValueError("TTS is not enabled")
-                voice = args.get("voice") or text_to_speech.get("voice")
-            else:
-                try:
-                    if app_model.app_model_config is None:
-                        raise ValueError("AppModelConfig not found")
-                    voice = args.get("voice") or app_model.app_model_config.text_to_speech_dict.get("voice")
-                except Exception:
-                    voice = None
-            response = AudioService.transcript_tts(app_model=app_model, text=text, message_id=message_id, voice=voice)
+            voice = args.get("voice", None)
+
+            response = AudioService.transcript_tts(
+                app_model=app_model, text=text, voice=voice, message_id=message_id, is_draft=True
+            )
             return response
         except services.errors.app_model_config.AppModelConfigBrokenError:
             logging.exception("App model config broken.")

api/controllers/console/explore/audio.py

@@ -18,7 +18,6 @@ from controllers.console.app.error import (
 from controllers.console.explore.wraps import InstalledAppResource
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError
-from models.model import AppMode
 from services.audio_service import AudioService
 from services.errors.audio import (
     AudioTooLargeServiceError,
@@ -79,19 +78,9 @@ class ChatTextApi(InstalledAppResource):
 
             message_id = args.get("message_id", None)
             text = args.get("text", None)
-            if (
-                app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}
-                and app_model.workflow
-                and app_model.workflow.features_dict
-            ):
-                text_to_speech = app_model.workflow.features_dict.get("text_to_speech")
-                voice = args.get("voice") or text_to_speech.get("voice")
-            else:
-                try:
-                    voice = args.get("voice") or app_model.app_model_config.text_to_speech_dict.get("voice")
-                except Exception:
-                    voice = None
-            response = AudioService.transcript_tts(app_model=app_model, message_id=message_id, voice=voice, text=text)
+            voice = args.get("voice", None)
+
+            response = AudioService.transcript_tts(app_model=app_model, text=text, voice=voice, message_id=message_id)
             return response
         except services.errors.app_model_config.AppModelConfigBrokenError:
             logging.exception("App model config broken.")

api/controllers/files/upload.py

@@ -87,7 +87,5 @@ class PluginUploadFileApi(Resource):
         except services.errors.file.UnsupportedFileTypeError:
             raise UnsupportedFileTypeError()
 
-        return tool_file, 201
-
 
 api.add_resource(PluginUploadFileApi, "/files/upload/for-plugin")

api/controllers/service_api/app/audio.py

@@ -20,7 +20,7 @@ from controllers.service_api.app.error import (
 from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError
-from models.model import App, AppMode, EndUser
+from models.model import App, EndUser
 from services.audio_service import AudioService
 from services.errors.audio import (
     AudioTooLargeServiceError,
@@ -78,20 +78,9 @@ class TextApi(Resource):
 
             message_id = args.get("message_id", None)
             text = args.get("text", None)
-            if (
-                app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}
-                and app_model.workflow
-                and app_model.workflow.features_dict
-            ):
-                text_to_speech = app_model.workflow.features_dict.get("text_to_speech", {})
-                voice = args.get("voice") or text_to_speech.get("voice")
-            else:
-                try:
-                    voice = args.get("voice") or app_model.app_model_config.text_to_speech_dict.get("voice")
-                except Exception:
-                    voice = None
+            voice = args.get("voice", None)
             response = AudioService.transcript_tts(
-                app_model=app_model, message_id=message_id, end_user=end_user.external_user_id, voice=voice, text=text
+                app_model=app_model, text=text, voice=voice, end_user=end_user.external_user_id, message_id=message_id
             )
 
             return response

api/controllers/service_api/dataset/document.py

@@ -211,6 +211,9 @@ class DocumentAddByFileApi(DatasetApiResource):
         if not dataset:
             raise ValueError("Dataset does not exist.")
 
+        if dataset.provider == "external":
+            raise ValueError("External datasets are not supported.")
+
         indexing_technique = args.get("indexing_technique") or dataset.indexing_technique
         if not indexing_technique:
             raise ValueError("indexing_technique is required.")
@@ -301,6 +304,9 @@ class DocumentUpdateByFileApi(DatasetApiResource):
         if not dataset:
             raise ValueError("Dataset does not exist.")
 
+        if dataset.provider == "external":
+            raise ValueError("External datasets are not supported.")
+
         # indexing_technique is already set in dataset since this is an update
         args["indexing_technique"] = dataset.indexing_technique
 

api/controllers/web/audio.py

@@ -19,7 +19,7 @@ from controllers.web.error import (
 from controllers.web.wraps import WebApiResource
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError
-from models.model import App, AppMode
+from models.model import App
 from services.audio_service import AudioService
 from services.errors.audio import (
     AudioTooLargeServiceError,
@@ -77,21 +77,9 @@ class TextApi(WebApiResource):
 
             message_id = args.get("message_id", None)
             text = args.get("text", None)
-            if (
-                app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}
-                and app_model.workflow
-                and app_model.workflow.features_dict
-            ):
-                text_to_speech = app_model.workflow.features_dict.get("text_to_speech", {})
-                voice = args.get("voice") or text_to_speech.get("voice")
-            else:
-                try:
-                    voice = args.get("voice") or app_model.app_model_config.text_to_speech_dict.get("voice")
-                except Exception:
-                    voice = None
-
+            voice = args.get("voice", None)
             response = AudioService.transcript_tts(
-                app_model=app_model, message_id=message_id, end_user=end_user.external_user_id, voice=voice, text=text
+                app_model=app_model, text=text, voice=voice, end_user=end_user.external_user_id, message_id=message_id
             )
 
             return response

api/core/app/task_pipeline/based_generate_task_pipeline.py

@@ -19,6 +19,7 @@ from core.app.entities.task_entities import (
 from core.errors.error import QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
 from core.moderation.output_moderation import ModerationRule, OutputModeration
+from models.enums import MessageStatus
 from models.model import Message
 
 logger = logging.getLogger(__name__)
@@ -62,7 +63,7 @@ class BasedGenerateTaskPipeline:
             return err
 
         err_desc = self._error_to_desc(err)
-        message.status = "error"
+        message.status = MessageStatus.ERROR
         message.error = err_desc
         return err
 

api/core/helper/code_executor/template_transformer.py

@@ -28,7 +28,7 @@ class TemplateTransformer(ABC):
     def extract_result_str_from_response(cls, response: str):
         result = re.search(rf"{cls._result_tag}(.*){cls._result_tag}", response, re.DOTALL)
         if not result:
-            raise ValueError("Failed to parse result")
+            raise ValueError(f"Failed to parse result: no result tag found in response. Response: {response[:200]}...")
         return result.group(1)
 
     @classmethod
@@ -38,16 +38,53 @@ class TemplateTransformer(ABC):
         :param response: response
         :return:
         """
+
         try:
-            result = json.loads(cls.extract_result_str_from_response(response))
-        except json.JSONDecodeError:
-            raise ValueError("failed to parse response")
+            result_str = cls.extract_result_str_from_response(response)
+            result = json.loads(result_str)
+        except json.JSONDecodeError as e:
+            raise ValueError(f"Failed to parse JSON response: {str(e)}. Response content: {result_str[:200]}...")
+        except ValueError as e:
+            # Re-raise ValueError from extract_result_str_from_response
+            raise e
+        except Exception as e:
+            raise ValueError(f"Unexpected error during response transformation: {str(e)}")
+
+        # Check if the result contains an error
+        if isinstance(result, dict) and "error" in result:
+            raise ValueError(f"JavaScript execution error: {result['error']}")
+
         if not isinstance(result, dict):
-            raise ValueError("result must be a dict")
+            raise ValueError(f"Result must be a dict, got {type(result).__name__}")
         if not all(isinstance(k, str) for k in result):
-            raise ValueError("result keys must be strings")
+            raise ValueError("Result keys must be strings")
+
+        # Post-process the result to convert scientific notation strings back to numbers
+        result = cls._post_process_result(result)
         return result
 
+    @classmethod
+    def _post_process_result(cls, result: dict[Any, Any]) -> dict[Any, Any]:
+        """
+        Post-process the result to convert scientific notation strings back to numbers
+        """
+
+        def convert_scientific_notation(value):
+            if isinstance(value, str):
+                # Check if the string looks like scientific notation
+                if re.match(r"^-?\d+\.?\d*e[+-]\d+$", value, re.IGNORECASE):
+                    try:
+                        return float(value)
+                    except ValueError:
+                        pass
+            elif isinstance(value, dict):
+                return {k: convert_scientific_notation(v) for k, v in value.items()}
+            elif isinstance(value, list):
+                return [convert_scientific_notation(v) for v in value]
+            return value
+
+        return convert_scientific_notation(result)  # type: ignore[no-any-return]
+
     @classmethod
     @abstractmethod
     def get_runner_script(cls) -> str:

api/core/indexing_runner.py

@@ -317,9 +317,10 @@ class IndexingRunner:
                 image_upload_file_ids = get_image_upload_file_ids(document.page_content)
                 for upload_file_id in image_upload_file_ids:
                     image_file = db.session.query(UploadFile).filter(UploadFile.id == upload_file_id).first()
+                    if image_file is None:
+                        continue
                     try:
-                        if image_file:
-                            storage.delete(image_file.key)
+                        storage.delete(image_file.key)
                     except Exception:
                         logging.exception(
                             "Delete image_files failed while indexing_estimate, \

api/core/llm_generator/output_parser/structured_output.py

@@ -23,6 +23,7 @@ from core.model_runtime.entities.message_entities import (
     PromptMessage,
     PromptMessageTool,
     SystemPromptMessage,
+    TextPromptMessageContent,
 )
 from core.model_runtime.entities.model_entities import AIModelEntity, ParameterRule
 
@@ -170,10 +171,15 @@ def invoke_llm_with_structured_output(
             system_fingerprint: Optional[str] = None
             for event in llm_result:
                 if isinstance(event, LLMResultChunk):
+                    prompt_messages = event.prompt_messages
+                    system_fingerprint = event.system_fingerprint
+
                     if isinstance(event.delta.message.content, str):
                         result_text += event.delta.message.content
-                        prompt_messages = event.prompt_messages
-                        system_fingerprint = event.system_fingerprint
+                    elif isinstance(event.delta.message.content, list):
+                        for item in event.delta.message.content:
+                            if isinstance(item, TextPromptMessageContent):
+                                result_text += item.data
 
                 yield LLMResultChunkWithStructuredOutput(
                     model=model_schema.model,

api/core/model_runtime/entities/llm_entities.py

@@ -53,6 +53,37 @@ class LLMUsage(ModelUsage):
             latency=0.0,
         )
 
+    @classmethod
+    def from_metadata(cls, metadata: dict) -> "LLMUsage":
+        """
+        Create LLMUsage instance from metadata dictionary with default values.
+
+        Args:
+            metadata: Dictionary containing usage metadata
+
+        Returns:
+            LLMUsage instance with values from metadata or defaults
+        """
+        total_tokens = metadata.get("total_tokens", 0)
+        completion_tokens = metadata.get("completion_tokens", 0)
+        if total_tokens > 0 and completion_tokens == 0:
+            completion_tokens = total_tokens
+
+        return cls(
+            prompt_tokens=metadata.get("prompt_tokens", 0),
+            completion_tokens=completion_tokens,
+            total_tokens=total_tokens,
+            prompt_unit_price=Decimal(str(metadata.get("prompt_unit_price", 0))),
+            completion_unit_price=Decimal(str(metadata.get("completion_unit_price", 0))),
+            total_price=Decimal(str(metadata.get("total_price", 0))),
+            currency=metadata.get("currency", "USD"),
+            prompt_price_unit=Decimal(str(metadata.get("prompt_price_unit", 0))),
+            completion_price_unit=Decimal(str(metadata.get("completion_price_unit", 0))),
+            prompt_price=Decimal(str(metadata.get("prompt_price", 0))),
+            completion_price=Decimal(str(metadata.get("completion_price", 0))),
+            latency=metadata.get("latency", 0.0),
+        )
+
     def plus(self, other: "LLMUsage") -> "LLMUsage":
         """
         Add two LLMUsage instances together.

api/core/ops/aliyun_trace/aliyun_trace.py

@@ -0,0 +1,486 @@
+import json
+import logging
+from collections.abc import Sequence
+from typing import Optional
+from urllib.parse import urljoin
+
+from opentelemetry.trace import Status, StatusCode
+from sqlalchemy.orm import Session, sessionmaker
+
+from core.ops.aliyun_trace.data_exporter.traceclient import (
+    TraceClient,
+    convert_datetime_to_nanoseconds,
+    convert_to_span_id,
+    convert_to_trace_id,
+    generate_span_id,
+)
+from core.ops.aliyun_trace.entities.aliyun_trace_entity import SpanData
+from core.ops.aliyun_trace.entities.semconv import (
+    GEN_AI_COMPLETION,
+    GEN_AI_FRAMEWORK,
+    GEN_AI_MODEL_NAME,
+    GEN_AI_PROMPT,
+    GEN_AI_PROMPT_TEMPLATE_TEMPLATE,
+    GEN_AI_PROMPT_TEMPLATE_VARIABLE,
+    GEN_AI_RESPONSE_FINISH_REASON,
+    GEN_AI_SESSION_ID,
+    GEN_AI_SPAN_KIND,
+    GEN_AI_SYSTEM,
+    GEN_AI_USAGE_INPUT_TOKENS,
+    GEN_AI_USAGE_OUTPUT_TOKENS,
+    GEN_AI_USAGE_TOTAL_TOKENS,
+    GEN_AI_USER_ID,
+    INPUT_VALUE,
+    OUTPUT_VALUE,
+    RETRIEVAL_DOCUMENT,
+    RETRIEVAL_QUERY,
+    TOOL_DESCRIPTION,
+    TOOL_NAME,
+    TOOL_PARAMETERS,
+    GenAISpanKind,
+)
+from core.ops.base_trace_instance import BaseTraceInstance
+from core.ops.entities.config_entity import AliyunConfig
+from core.ops.entities.trace_entity import (
+    BaseTraceInfo,
+    DatasetRetrievalTraceInfo,
+    GenerateNameTraceInfo,
+    MessageTraceInfo,
+    ModerationTraceInfo,
+    SuggestedQuestionTraceInfo,
+    ToolTraceInfo,
+    WorkflowTraceInfo,
+)
+from core.rag.models.document import Document
+from core.repositories import SQLAlchemyWorkflowNodeExecutionRepository
+from core.workflow.entities.workflow_node_execution import (
+    WorkflowNodeExecution,
+    WorkflowNodeExecutionMetadataKey,
+    WorkflowNodeExecutionStatus,
+)
+from core.workflow.nodes import NodeType
+from models import Account, App, EndUser, TenantAccountJoin, WorkflowNodeExecutionTriggeredFrom, db
+
+logger = logging.getLogger(__name__)
+
+
+class AliyunDataTrace(BaseTraceInstance):
+    def __init__(
+        self,
+        aliyun_config: AliyunConfig,
+    ):
+        super().__init__(aliyun_config)
+        base_url = aliyun_config.endpoint.rstrip("/")
+        endpoint = urljoin(base_url, f"adapt_{aliyun_config.license_key}/api/otlp/traces")
+        self.trace_client = TraceClient(service_name=aliyun_config.app_name, endpoint=endpoint)
+
+    def trace(self, trace_info: BaseTraceInfo):
+        if isinstance(trace_info, WorkflowTraceInfo):
+            self.workflow_trace(trace_info)
+        if isinstance(trace_info, MessageTraceInfo):
+            self.message_trace(trace_info)
+        if isinstance(trace_info, ModerationTraceInfo):
+            pass
+        if isinstance(trace_info, SuggestedQuestionTraceInfo):
+            self.suggested_question_trace(trace_info)
+        if isinstance(trace_info, DatasetRetrievalTraceInfo):
+            self.dataset_retrieval_trace(trace_info)
+        if isinstance(trace_info, ToolTraceInfo):
+            self.tool_trace(trace_info)
+        if isinstance(trace_info, GenerateNameTraceInfo):
+            pass
+
+    def api_check(self):
+        return self.trace_client.api_check()
+
+    def get_project_url(self):
+        try:
+            return self.trace_client.get_project_url()
+        except Exception as e:
+            logger.info(f"Aliyun get run url failed: {str(e)}", exc_info=True)
+            raise ValueError(f"Aliyun get run url failed: {str(e)}")
+
+    def workflow_trace(self, trace_info: WorkflowTraceInfo):
+        trace_id = convert_to_trace_id(trace_info.workflow_run_id)
+        workflow_span_id = convert_to_span_id(trace_info.workflow_run_id, "workflow")
+        self.add_workflow_span(trace_id, workflow_span_id, trace_info)
+
+        workflow_node_executions = self.get_workflow_node_executions(trace_info)
+        for node_execution in workflow_node_executions:
+            node_span = self.build_workflow_node_span(node_execution, trace_id, trace_info, workflow_span_id)
+            self.trace_client.add_span(node_span)
+
+    def message_trace(self, trace_info: MessageTraceInfo):
+        message_data = trace_info.message_data
+        if message_data is None:
+            return
+        message_id = trace_info.message_id
+
+        user_id = message_data.from_account_id
+        if message_data.from_end_user_id:
+            end_user_data: Optional[EndUser] = (
+                db.session.query(EndUser).filter(EndUser.id == message_data.from_end_user_id).first()
+            )
+            if end_user_data is not None:
+                user_id = end_user_data.session_id
+
+        status: Status = Status(StatusCode.OK)
+        if trace_info.error:
+            status = Status(StatusCode.ERROR, trace_info.error)
+
+        trace_id = convert_to_trace_id(message_id)
+        message_span_id = convert_to_span_id(message_id, "message")
+        message_span = SpanData(
+            trace_id=trace_id,
+            parent_span_id=None,
+            span_id=message_span_id,
+            name="message",
+            start_time=convert_datetime_to_nanoseconds(trace_info.start_time),
+            end_time=convert_datetime_to_nanoseconds(trace_info.end_time),
+            attributes={
+                GEN_AI_SESSION_ID: trace_info.metadata.get("conversation_id", ""),
+                GEN_AI_USER_ID: str(user_id),
+                GEN_AI_SPAN_KIND: GenAISpanKind.CHAIN.value,
+                GEN_AI_FRAMEWORK: "dify",
+                INPUT_VALUE: json.dumps(trace_info.inputs, ensure_ascii=False),
+                OUTPUT_VALUE: str(trace_info.outputs),
+            },
+            status=status,
+        )
+        self.trace_client.add_span(message_span)
+
+        app_model_config = getattr(trace_info.message_data, "app_model_config", {})
+        pre_prompt = getattr(app_model_config, "pre_prompt", "")
+        inputs_data = getattr(trace_info.message_data, "inputs", {})
+        llm_span = SpanData(
+            trace_id=trace_id,
+            parent_span_id=message_span_id,
+            span_id=convert_to_span_id(message_id, "llm"),
+            name="llm",
+            start_time=convert_datetime_to_nanoseconds(trace_info.start_time),
+            end_time=convert_datetime_to_nanoseconds(trace_info.end_time),
+            attributes={
+                GEN_AI_SESSION_ID: trace_info.metadata.get("conversation_id", ""),
+                GEN_AI_USER_ID: str(user_id),
+                GEN_AI_SPAN_KIND: GenAISpanKind.LLM.value,
+                GEN_AI_FRAMEWORK: "dify",
+                GEN_AI_MODEL_NAME: trace_info.metadata.get("ls_model_name", ""),
+                GEN_AI_SYSTEM: trace_info.metadata.get("ls_provider", ""),
+                GEN_AI_USAGE_INPUT_TOKENS: str(trace_info.message_tokens),
+                GEN_AI_USAGE_OUTPUT_TOKENS: str(trace_info.answer_tokens),
+                GEN_AI_USAGE_TOTAL_TOKENS: str(trace_info.total_tokens),
+                GEN_AI_PROMPT_TEMPLATE_VARIABLE: json.dumps(inputs_data, ensure_ascii=False),
+                GEN_AI_PROMPT_TEMPLATE_TEMPLATE: pre_prompt,
+                GEN_AI_PROMPT: json.dumps(trace_info.inputs, ensure_ascii=False),
+                GEN_AI_COMPLETION: str(trace_info.outputs),
+                INPUT_VALUE: json.dumps(trace_info.inputs, ensure_ascii=False),
+                OUTPUT_VALUE: str(trace_info.outputs),
+            },
+            status=status,
+        )
+        self.trace_client.add_span(llm_span)
+
+    def dataset_retrieval_trace(self, trace_info: DatasetRetrievalTraceInfo):
+        if trace_info.message_data is None:
+            return
+        message_id = trace_info.message_id
+
+        documents_data = extract_retrieval_documents(trace_info.documents)
+        dataset_retrieval_span = SpanData(
+            trace_id=convert_to_trace_id(message_id),
+            parent_span_id=convert_to_span_id(message_id, "message"),
+            span_id=generate_span_id(),
+            name="dataset_retrieval",
+            start_time=convert_datetime_to_nanoseconds(trace_info.start_time),
+            end_time=convert_datetime_to_nanoseconds(trace_info.end_time),
+            attributes={
+                GEN_AI_SPAN_KIND: GenAISpanKind.RETRIEVER.value,
+                GEN_AI_FRAMEWORK: "dify",
+                RETRIEVAL_QUERY: str(trace_info.inputs),
+                RETRIEVAL_DOCUMENT: json.dumps(documents_data, ensure_ascii=False),
+                INPUT_VALUE: str(trace_info.inputs),
+                OUTPUT_VALUE: json.dumps(documents_data, ensure_ascii=False),
+            },
+        )
+        self.trace_client.add_span(dataset_retrieval_span)
+
+    def tool_trace(self, trace_info: ToolTraceInfo):
+        if trace_info.message_data is None:
+            return
+        message_id = trace_info.message_id
+
+        status: Status = Status(StatusCode.OK)
+        if trace_info.error:
+            status = Status(StatusCode.ERROR, trace_info.error)
+
+        tool_span = SpanData(
+            trace_id=convert_to_trace_id(message_id),
+            parent_span_id=convert_to_span_id(message_id, "message"),
+            span_id=generate_span_id(),
+            name=trace_info.tool_name,
+            start_time=convert_datetime_to_nanoseconds(trace_info.start_time),
+            end_time=convert_datetime_to_nanoseconds(trace_info.end_time),
+            attributes={
+                GEN_AI_SPAN_KIND: GenAISpanKind.TOOL.value,
+                GEN_AI_FRAMEWORK: "dify",
+                TOOL_NAME: trace_info.tool_name,
+                TOOL_DESCRIPTION: json.dumps(trace_info.tool_config, ensure_ascii=False),
+                TOOL_PARAMETERS: json.dumps(trace_info.tool_inputs, ensure_ascii=False),
+                INPUT_VALUE: json.dumps(trace_info.inputs, ensure_ascii=False),
+                OUTPUT_VALUE: str(trace_info.tool_outputs),
+            },
+            status=status,
+        )
+        self.trace_client.add_span(tool_span)
+
+    def get_workflow_node_executions(self, trace_info: WorkflowTraceInfo) -> Sequence[WorkflowNodeExecution]:
+        # through workflow_run_id get all_nodes_execution using repository
+        session_factory = sessionmaker(bind=db.engine)
+        # Find the app's creator account
+        with Session(db.engine, expire_on_commit=False) as session:
+            # Get the app to find its creator
+            app_id = trace_info.metadata.get("app_id")
+            if not app_id:
+                raise ValueError("No app_id found in trace_info metadata")
+
+            app = session.query(App).filter(App.id == app_id).first()
+            if not app:
+                raise ValueError(f"App with id {app_id} not found")
+
+            if not app.created_by:
+                raise ValueError(f"App with id {app_id} has no creator (created_by is None)")
+
+            service_account = session.query(Account).filter(Account.id == app.created_by).first()
+            if not service_account:
+                raise ValueError(f"Creator account with id {app.created_by} not found for app {app_id}")
+            current_tenant = (
+                session.query(TenantAccountJoin).filter_by(account_id=service_account.id, current=True).first()
+            )
+            if not current_tenant:
+                raise ValueError(f"Current tenant not found for account {service_account.id}")
+            service_account.set_tenant_id(current_tenant.tenant_id)
+        workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
+            session_factory=session_factory,
+            user=service_account,
+            app_id=trace_info.metadata.get("app_id"),
+            triggered_from=WorkflowNodeExecutionTriggeredFrom.WORKFLOW_RUN,
+        )
+        # Get all executions for this workflow run
+        workflow_node_executions = workflow_node_execution_repository.get_by_workflow_run(
+            workflow_run_id=trace_info.workflow_run_id
+        )
+        return workflow_node_executions
+
+    def build_workflow_node_span(
+        self, node_execution: WorkflowNodeExecution, trace_id: int, trace_info: WorkflowTraceInfo, workflow_span_id: int
+    ):
+        try:
+            if node_execution.node_type == NodeType.LLM:
+                node_span = self.build_workflow_llm_span(trace_id, workflow_span_id, trace_info, node_execution)
+            elif node_execution.node_type == NodeType.KNOWLEDGE_RETRIEVAL:
+                node_span = self.build_workflow_retrieval_span(trace_id, workflow_span_id, trace_info, node_execution)
+            elif node_execution.node_type == NodeType.TOOL:
+                node_span = self.build_workflow_tool_span(trace_id, workflow_span_id, trace_info, node_execution)
+            else:
+                node_span = self.build_workflow_task_span(trace_id, workflow_span_id, trace_info, node_execution)
+            return node_span
+        except Exception:
+            return None
+
+    def get_workflow_node_status(self, node_execution: WorkflowNodeExecution) -> Status:
+        span_status: Status = Status(StatusCode.UNSET)
+        if node_execution.status == WorkflowNodeExecutionStatus.SUCCEEDED:
+            span_status = Status(StatusCode.OK)
+        elif node_execution.status in [WorkflowNodeExecutionStatus.FAILED, WorkflowNodeExecutionStatus.EXCEPTION]:
+            span_status = Status(StatusCode.ERROR, str(node_execution.error))
+        return span_status
+
+    def build_workflow_task_span(
+        self, trace_id: int, workflow_span_id: int, trace_info: WorkflowTraceInfo, node_execution: WorkflowNodeExecution
+    ) -> SpanData:
+        return SpanData(
+            trace_id=trace_id,
+            parent_span_id=workflow_span_id,
+            span_id=convert_to_span_id(node_execution.id, "node"),
+            name=node_execution.title,
+            start_time=convert_datetime_to_nanoseconds(node_execution.created_at),
+            end_time=convert_datetime_to_nanoseconds(node_execution.finished_at),
+            attributes={
+                GEN_AI_SESSION_ID: trace_info.metadata.get("conversation_id", ""),
+                GEN_AI_SPAN_KIND: GenAISpanKind.TASK.value,
+                GEN_AI_FRAMEWORK: "dify",
+                INPUT_VALUE: json.dumps(node_execution.inputs, ensure_ascii=False),
+                OUTPUT_VALUE: json.dumps(node_execution.outputs, ensure_ascii=False),
+            },
+            status=self.get_workflow_node_status(node_execution),
+        )
+
+    def build_workflow_tool_span(
+        self, trace_id: int, workflow_span_id: int, trace_info: WorkflowTraceInfo, node_execution: WorkflowNodeExecution
+    ) -> SpanData:
+        tool_des = {}
+        if node_execution.metadata:
+            tool_des = node_execution.metadata.get(WorkflowNodeExecutionMetadataKey.TOOL_INFO, {})
+        return SpanData(
+            trace_id=trace_id,
+            parent_span_id=workflow_span_id,
+            span_id=convert_to_span_id(node_execution.id, "node"),
+            name=node_execution.title,
+            start_time=convert_datetime_to_nanoseconds(node_execution.created_at),
+            end_time=convert_datetime_to_nanoseconds(node_execution.finished_at),
+            attributes={
+                GEN_AI_SPAN_KIND: GenAISpanKind.TOOL.value,
+                GEN_AI_FRAMEWORK: "dify",
+                TOOL_NAME: node_execution.title,
+                TOOL_DESCRIPTION: json.dumps(tool_des, ensure_ascii=False),
+                TOOL_PARAMETERS: json.dumps(node_execution.inputs if node_execution.inputs else {}, ensure_ascii=False),
+                INPUT_VALUE: json.dumps(node_execution.inputs if node_execution.inputs else {}, ensure_ascii=False),
+                OUTPUT_VALUE: json.dumps(node_execution.outputs, ensure_ascii=False),
+            },
+            status=self.get_workflow_node_status(node_execution),
+        )
+
+    def build_workflow_retrieval_span(
+        self, trace_id: int, workflow_span_id: int, trace_info: WorkflowTraceInfo, node_execution: WorkflowNodeExecution
+    ) -> SpanData:
+        input_value = ""
+        if node_execution.inputs:
+            input_value = str(node_execution.inputs.get("query", ""))
+        output_value = ""
+        if node_execution.outputs:
+            output_value = json.dumps(node_execution.outputs.get("result", []), ensure_ascii=False)
+        return SpanData(
+            trace_id=trace_id,
+            parent_span_id=workflow_span_id,
+            span_id=convert_to_span_id(node_execution.id, "node"),
+            name=node_execution.title,
+            start_time=convert_datetime_to_nanoseconds(node_execution.created_at),
+            end_time=convert_datetime_to_nanoseconds(node_execution.finished_at),
+            attributes={
+                GEN_AI_SPAN_KIND: GenAISpanKind.RETRIEVER.value,
+                GEN_AI_FRAMEWORK: "dify",
+                RETRIEVAL_QUERY: input_value,
+                RETRIEVAL_DOCUMENT: output_value,
+                INPUT_VALUE: input_value,
+                OUTPUT_VALUE: output_value,
+            },
+            status=self.get_workflow_node_status(node_execution),
+        )
+
+    def build_workflow_llm_span(
+        self, trace_id: int, workflow_span_id: int, trace_info: WorkflowTraceInfo, node_execution: WorkflowNodeExecution
+    ) -> SpanData:
+        process_data = node_execution.process_data or {}
+        outputs = node_execution.outputs or {}
+        return SpanData(
+            trace_id=trace_id,
+            parent_span_id=workflow_span_id,
+            span_id=convert_to_span_id(node_execution.id, "node"),
+            name=node_execution.title,
+            start_time=convert_datetime_to_nanoseconds(node_execution.created_at),
+            end_time=convert_datetime_to_nanoseconds(node_execution.finished_at),
+            attributes={
+                GEN_AI_SESSION_ID: trace_info.metadata.get("conversation_id", ""),
+                GEN_AI_SPAN_KIND: GenAISpanKind.LLM.value,
+                GEN_AI_FRAMEWORK: "dify",
+                GEN_AI_MODEL_NAME: process_data.get("model_name", ""),
+                GEN_AI_SYSTEM: process_data.get("model_provider", ""),
+                GEN_AI_USAGE_INPUT_TOKENS: str(outputs.get("usage", {}).get("prompt_tokens", 0)),
+                GEN_AI_USAGE_OUTPUT_TOKENS: str(outputs.get("usage", {}).get("completion_tokens", 0)),
+                GEN_AI_USAGE_TOTAL_TOKENS: str(outputs.get("usage", {}).get("total_tokens", 0)),
+                GEN_AI_PROMPT: json.dumps(process_data.get("prompts", []), ensure_ascii=False),
+                GEN_AI_COMPLETION: str(outputs.get("text", "")),
+                GEN_AI_RESPONSE_FINISH_REASON: outputs.get("finish_reason", ""),
+                INPUT_VALUE: json.dumps(process_data.get("prompts", []), ensure_ascii=False),
+                OUTPUT_VALUE: str(outputs.get("text", "")),
+            },
+            status=self.get_workflow_node_status(node_execution),
+        )
+
+    def add_workflow_span(self, trace_id: int, workflow_span_id: int, trace_info: WorkflowTraceInfo):
+        message_span_id = None
+        if trace_info.message_id:
+            message_span_id = convert_to_span_id(trace_info.message_id, "message")
+        user_id = trace_info.metadata.get("user_id")
+        status: Status = Status(StatusCode.OK)
+        if trace_info.error:
+            status = Status(StatusCode.ERROR, trace_info.error)
+        if message_span_id:  # chatflow
+            message_span = SpanData(
+                trace_id=trace_id,
+                parent_span_id=None,
+                span_id=message_span_id,
+                name="message",
+                start_time=convert_datetime_to_nanoseconds(trace_info.start_time),
+                end_time=convert_datetime_to_nanoseconds(trace_info.end_time),
+                attributes={
+                    GEN_AI_SESSION_ID: trace_info.metadata.get("conversation_id", ""),
+                    GEN_AI_USER_ID: str(user_id),
+                    GEN_AI_SPAN_KIND: GenAISpanKind.CHAIN.value,
+                    GEN_AI_FRAMEWORK: "dify",
+                    INPUT_VALUE: trace_info.workflow_run_inputs.get("sys.query", ""),
+                    OUTPUT_VALUE: json.dumps(trace_info.workflow_run_outputs, ensure_ascii=False),
+                },
+                status=status,
+            )
+            self.trace_client.add_span(message_span)
+
+        workflow_span = SpanData(
+            trace_id=trace_id,
+            parent_span_id=message_span_id,
+            span_id=workflow_span_id,
+            name="workflow",
+            start_time=convert_datetime_to_nanoseconds(trace_info.start_time),
+            end_time=convert_datetime_to_nanoseconds(trace_info.end_time),
+            attributes={
+                GEN_AI_USER_ID: str(user_id),
+                GEN_AI_SPAN_KIND: GenAISpanKind.CHAIN.value,
+                GEN_AI_FRAMEWORK: "dify",
+                INPUT_VALUE: json.dumps(trace_info.workflow_run_inputs, ensure_ascii=False),
+                OUTPUT_VALUE: json.dumps(trace_info.workflow_run_outputs, ensure_ascii=False),
+            },
+            status=status,
+        )
+        self.trace_client.add_span(workflow_span)
+
+    def suggested_question_trace(self, trace_info: SuggestedQuestionTraceInfo):
+        message_id = trace_info.message_id
+        status: Status = Status(StatusCode.OK)
+        if trace_info.error:
+            status = Status(StatusCode.ERROR, trace_info.error)
+        suggested_question_span = SpanData(
+            trace_id=convert_to_trace_id(message_id),
+            parent_span_id=convert_to_span_id(message_id, "message"),
+            span_id=convert_to_span_id(message_id, "suggested_question"),
+            name="suggested_question",
+            start_time=convert_datetime_to_nanoseconds(trace_info.start_time),
+            end_time=convert_datetime_to_nanoseconds(trace_info.end_time),
+            attributes={
+                GEN_AI_SPAN_KIND: GenAISpanKind.LLM.value,
+                GEN_AI_FRAMEWORK: "dify",
+                GEN_AI_MODEL_NAME: trace_info.metadata.get("ls_model_name", ""),
+                GEN_AI_SYSTEM: trace_info.metadata.get("ls_provider", ""),
+                GEN_AI_PROMPT: json.dumps(trace_info.inputs, ensure_ascii=False),
+                GEN_AI_COMPLETION: json.dumps(trace_info.suggested_question, ensure_ascii=False),
+                INPUT_VALUE: json.dumps(trace_info.inputs, ensure_ascii=False),
+                OUTPUT_VALUE: json.dumps(trace_info.suggested_question, ensure_ascii=False),
+            },
+            status=status,
+        )
+        self.trace_client.add_span(suggested_question_span)
+
+
+def extract_retrieval_documents(documents: list[Document]):
+    documents_data = []
+    for document in documents:
+        document_data = {
+            "content": document.page_content,
+            "metadata": {
+                "dataset_id": document.metadata.get("dataset_id"),
+                "doc_id": document.metadata.get("doc_id"),
+                "document_id": document.metadata.get("document_id"),
+            },
+            "score": document.metadata.get("score"),
+        }
+        documents_data.append(document_data)
+    return documents_data

api/core/ops/aliyun_trace/data_exporter/traceclient.py

@@ -0,0 +1,200 @@
+import hashlib
+import logging
+import random
+import socket
+import threading
+import uuid
+from collections import deque
+from collections.abc import Sequence
+from datetime import datetime
+from typing import Optional
+
+import requests
+from opentelemetry import trace as trace_api
+from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
+from opentelemetry.sdk.resources import Resource
+from opentelemetry.sdk.trace import ReadableSpan
+from opentelemetry.sdk.util.instrumentation import InstrumentationScope
+from opentelemetry.semconv.resource import ResourceAttributes
+
+from configs import dify_config
+from core.ops.aliyun_trace.entities.aliyun_trace_entity import SpanData
+
+INVALID_SPAN_ID = 0x0000000000000000
+INVALID_TRACE_ID = 0x00000000000000000000000000000000
+
+logger = logging.getLogger(__name__)
+
+
+class TraceClient:
+    def __init__(
+        self,
+        service_name: str,
+        endpoint: str,
+        max_queue_size: int = 1000,
+        schedule_delay_sec: int = 5,
+        max_export_batch_size: int = 50,
+    ):
+        self.endpoint = endpoint
+        self.resource = Resource(
+            attributes={
+                ResourceAttributes.SERVICE_NAME: service_name,
+                ResourceAttributes.SERVICE_VERSION: f"dify-{dify_config.project.version}-{dify_config.COMMIT_SHA}",
+                ResourceAttributes.DEPLOYMENT_ENVIRONMENT: f"{dify_config.DEPLOY_ENV}-{dify_config.EDITION}",
+                ResourceAttributes.HOST_NAME: socket.gethostname(),
+            }
+        )
+        self.span_builder = SpanBuilder(self.resource)
+        self.exporter = OTLPSpanExporter(endpoint=endpoint)
+
+        self.max_queue_size = max_queue_size
+        self.schedule_delay_sec = schedule_delay_sec
+        self.max_export_batch_size = max_export_batch_size
+
+        self.queue: deque = deque(maxlen=max_queue_size)
+        self.condition = threading.Condition(threading.Lock())
+        self.done = False
+
+        self.worker_thread = threading.Thread(target=self._worker, daemon=True)
+        self.worker_thread.start()
+
+        self._spans_dropped = False
+
+    def export(self, spans: Sequence[ReadableSpan]):
+        self.exporter.export(spans)
+
+    def api_check(self):
+        try:
+            response = requests.head(self.endpoint, timeout=5)
+            if response.status_code == 405:
+                return True
+            else:
+                logger.debug(f"AliyunTrace API check failed: Unexpected status code: {response.status_code}")
+                return False
+        except requests.exceptions.RequestException as e:
+            logger.debug(f"AliyunTrace API check failed: {str(e)}")
+            raise ValueError(f"AliyunTrace API check failed: {str(e)}")
+
+    def get_project_url(self):
+        return "https://arms.console.aliyun.com/#/llm"
+
+    def add_span(self, span_data: SpanData):
+        if span_data is None:
+            return
+        span: ReadableSpan = self.span_builder.build_span(span_data)
+        with self.condition:
+            if len(self.queue) == self.max_queue_size:
+                if not self._spans_dropped:
+                    logger.warning("Queue is full, likely spans will be dropped.")
+                    self._spans_dropped = True
+
+            self.queue.appendleft(span)
+            if len(self.queue) >= self.max_export_batch_size:
+                self.condition.notify()
+
+    def _worker(self):
+        while not self.done:
+            with self.condition:
+                if len(self.queue) < self.max_export_batch_size and not self.done:
+                    self.condition.wait(timeout=self.schedule_delay_sec)
+            self._export_batch()
+
+    def _export_batch(self):
+        spans_to_export: list[ReadableSpan] = []
+        with self.condition:
+            while len(spans_to_export) < self.max_export_batch_size and self.queue:
+                spans_to_export.append(self.queue.pop())
+
+        if spans_to_export:
+            try:
+                self.exporter.export(spans_to_export)
+            except Exception as e:
+                logger.debug(f"Error exporting spans: {e}")
+
+    def shutdown(self):
+        with self.condition:
+            self.done = True
+            self.condition.notify_all()
+        self.worker_thread.join()
+        self._export_batch()
+        self.exporter.shutdown()
+
+
+class SpanBuilder:
+    def __init__(self, resource):
+        self.resource = resource
+        self.instrumentation_scope = InstrumentationScope(
+            __name__,
+            "",
+            None,
+            None,
+        )
+
+    def build_span(self, span_data: SpanData) -> ReadableSpan:
+        span_context = trace_api.SpanContext(
+            trace_id=span_data.trace_id,
+            span_id=span_data.span_id,
+            is_remote=False,
+            trace_flags=trace_api.TraceFlags(trace_api.TraceFlags.SAMPLED),
+            trace_state=None,
+        )
+
+        parent_span_context = None
+        if span_data.parent_span_id is not None:
+            parent_span_context = trace_api.SpanContext(
+                trace_id=span_data.trace_id,
+                span_id=span_data.parent_span_id,
+                is_remote=False,
+                trace_flags=trace_api.TraceFlags(trace_api.TraceFlags.SAMPLED),
+                trace_state=None,
+            )
+
+        span = ReadableSpan(
+            name=span_data.name,
+            context=span_context,
+            parent=parent_span_context,
+            resource=self.resource,
+            attributes=span_data.attributes,
+            events=span_data.events,
+            links=span_data.links,
+            kind=trace_api.SpanKind.INTERNAL,
+            status=span_data.status,
+            start_time=span_data.start_time,
+            end_time=span_data.end_time,
+            instrumentation_scope=self.instrumentation_scope,
+        )
+        return span
+
+
+def generate_span_id() -> int:
+    span_id = random.getrandbits(64)
+    while span_id == INVALID_SPAN_ID:
+        span_id = random.getrandbits(64)
+    return span_id
+
+
+def convert_to_trace_id(uuid_v4: Optional[str]) -> int:
+    try:
+        uuid_obj = uuid.UUID(uuid_v4)
+        return uuid_obj.int
+    except Exception as e:
+        raise ValueError(f"Invalid UUID input: {e}")
+
+
+def convert_to_span_id(uuid_v4: Optional[str], span_type: str) -> int:
+    try:
+        uuid_obj = uuid.UUID(uuid_v4)
+    except Exception as e:
+        raise ValueError(f"Invalid UUID input: {e}")
+    combined_key = f"{uuid_obj.hex}-{span_type}"
+    hash_bytes = hashlib.sha256(combined_key.encode("utf-8")).digest()
+    span_id = int.from_bytes(hash_bytes[:8], byteorder="big", signed=False)
+    return span_id
+
+
+def convert_datetime_to_nanoseconds(start_time_a: Optional[datetime]) -> Optional[int]:
+    if start_time_a is None:
+        return None
+    timestamp_in_seconds = start_time_a.timestamp()
+    timestamp_in_nanoseconds = int(timestamp_in_seconds * 1e9)
+    return timestamp_in_nanoseconds

api/core/ops/aliyun_trace/entities/aliyun_trace_entity.py

@@ -0,0 +1,21 @@
+from collections.abc import Sequence
+from typing import Optional
+
+from opentelemetry import trace as trace_api
+from opentelemetry.sdk.trace import Event, Status, StatusCode
+from pydantic import BaseModel, Field
+
+
+class SpanData(BaseModel):
+    model_config = {"arbitrary_types_allowed": True}
+
+    trace_id: int = Field(..., description="The unique identifier for the trace.")
+    parent_span_id: Optional[int] = Field(None, description="The ID of the parent span, if any.")
+    span_id: int = Field(..., description="The unique identifier for this span.")
+    name: str = Field(..., description="The name of the span.")
+    attributes: dict[str, str] = Field(default_factory=dict, description="Attributes associated with the span.")
+    events: Sequence[Event] = Field(default_factory=list, description="Events recorded in the span.")
+    links: Sequence[trace_api.Link] = Field(default_factory=list, description="Links to other spans.")
+    status: Status = Field(default=Status(StatusCode.UNSET), description="The status of the span.")
+    start_time: Optional[int] = Field(..., description="The start time of the span in nanoseconds.")
+    end_time: Optional[int] = Field(..., description="The end time of the span in nanoseconds.")

api/core/ops/aliyun_trace/entities/semconv.py

@@ -0,0 +1,64 @@
+from enum import Enum
+
+# public
+GEN_AI_SESSION_ID = "gen_ai.session.id"
+
+GEN_AI_USER_ID = "gen_ai.user.id"
+
+GEN_AI_USER_NAME = "gen_ai.user.name"
+
+GEN_AI_SPAN_KIND = "gen_ai.span.kind"
+
+GEN_AI_FRAMEWORK = "gen_ai.framework"
+
+
+# Chain
+INPUT_VALUE = "input.value"
+
+OUTPUT_VALUE = "output.value"
+
+
+# Retriever
+RETRIEVAL_QUERY = "retrieval.query"
+
+RETRIEVAL_DOCUMENT = "retrieval.document"
+
+
+# LLM
+GEN_AI_MODEL_NAME = "gen_ai.model_name"
+
+GEN_AI_SYSTEM = "gen_ai.system"
+
+GEN_AI_USAGE_INPUT_TOKENS = "gen_ai.usage.input_tokens"
+
+GEN_AI_USAGE_OUTPUT_TOKENS = "gen_ai.usage.output_tokens"
+
+GEN_AI_USAGE_TOTAL_TOKENS = "gen_ai.usage.total_tokens"
+
+GEN_AI_PROMPT_TEMPLATE_TEMPLATE = "gen_ai.prompt_template.template"
+
+GEN_AI_PROMPT_TEMPLATE_VARIABLE = "gen_ai.prompt_template.variable"
+
+GEN_AI_PROMPT = "gen_ai.prompt"
+
+GEN_AI_COMPLETION = "gen_ai.completion"
+
+GEN_AI_RESPONSE_FINISH_REASON = "gen_ai.response.finish_reason"
+
+# Tool
+TOOL_NAME = "tool.name"
+
+TOOL_DESCRIPTION = "tool.description"
+
+TOOL_PARAMETERS = "tool.parameters"
+
+
+class GenAISpanKind(Enum):
+    CHAIN = "CHAIN"
+    RETRIEVER = "RETRIEVER"
+    RERANKER = "RERANKER"
+    LLM = "LLM"
+    EMBEDDING = "EMBEDDING"
+    TOOL = "TOOL"
+    AGENT = "AGENT"
+    TASK = "TASK"

api/core/ops/arize_phoenix_trace/arize_phoenix_trace.py

@@ -0,0 +1,720 @@
+import hashlib
+import json
+import logging
+import os
+from datetime import datetime, timedelta
+from typing import Optional, Union, cast
+
+from openinference.semconv.trace import OpenInferenceSpanKindValues, SpanAttributes
+from opentelemetry import trace
+from opentelemetry.exporter.otlp.proto.grpc.trace_exporter import OTLPSpanExporter as GrpcOTLPSpanExporter
+from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter as HttpOTLPSpanExporter
+from opentelemetry.sdk import trace as trace_sdk
+from opentelemetry.sdk.resources import Resource
+from opentelemetry.sdk.trace.export import SimpleSpanProcessor
+from opentelemetry.sdk.trace.id_generator import RandomIdGenerator
+from opentelemetry.trace import SpanContext, TraceFlags, TraceState
+
+from core.ops.base_trace_instance import BaseTraceInstance
+from core.ops.entities.config_entity import ArizeConfig, PhoenixConfig
+from core.ops.entities.trace_entity import (
+    BaseTraceInfo,
+    DatasetRetrievalTraceInfo,
+    GenerateNameTraceInfo,
+    MessageTraceInfo,
+    ModerationTraceInfo,
+    SuggestedQuestionTraceInfo,
+    ToolTraceInfo,
+    TraceTaskName,
+    WorkflowTraceInfo,
+)
+from extensions.ext_database import db
+from models.model import EndUser, MessageFile
+from models.workflow import WorkflowNodeExecutionModel
+
+logger = logging.getLogger(__name__)
+
+
+def setup_tracer(arize_phoenix_config: ArizeConfig | PhoenixConfig) -> tuple[trace_sdk.Tracer, SimpleSpanProcessor]:
+    """Configure OpenTelemetry tracer with OTLP exporter for Arize/Phoenix."""
+    try:
+        # Choose the appropriate exporter based on config type
+        exporter: Union[GrpcOTLPSpanExporter, HttpOTLPSpanExporter]
+        if isinstance(arize_phoenix_config, ArizeConfig):
+            arize_endpoint = f"{arize_phoenix_config.endpoint}/v1"
+            arize_headers = {
+                "api_key": arize_phoenix_config.api_key or "",
+                "space_id": arize_phoenix_config.space_id or "",
+                "authorization": f"Bearer {arize_phoenix_config.api_key or ''}",
+            }
+            exporter = GrpcOTLPSpanExporter(
+                endpoint=arize_endpoint,
+                headers=arize_headers,
+                timeout=30,
+            )
+        else:
+            phoenix_endpoint = f"{arize_phoenix_config.endpoint}/v1/traces"
+            phoenix_headers = {
+                "api_key": arize_phoenix_config.api_key or "",
+                "authorization": f"Bearer {arize_phoenix_config.api_key or ''}",
+            }
+            exporter = HttpOTLPSpanExporter(
+                endpoint=phoenix_endpoint,
+                headers=phoenix_headers,
+                timeout=30,
+            )
+
+        attributes = {
+            "openinference.project.name": arize_phoenix_config.project or "",
+            "model_id": arize_phoenix_config.project or "",
+        }
+        resource = Resource(attributes=attributes)
+        provider = trace_sdk.TracerProvider(resource=resource)
+        processor = SimpleSpanProcessor(
+            exporter,
+        )
+        provider.add_span_processor(processor)
+
+        # Create a named tracer instead of setting the global provider
+        tracer_name = f"arize_phoenix_tracer_{arize_phoenix_config.project}"
+        logger.info(f"[Arize/Phoenix] Created tracer with name: {tracer_name}")
+        return cast(trace_sdk.Tracer, provider.get_tracer(tracer_name)), processor
+    except Exception as e:
+        logger.error(f"[Arize/Phoenix] Failed to setup the tracer: {str(e)}", exc_info=True)
+        raise
+
+
+def datetime_to_nanos(dt: Optional[datetime]) -> int:
+    """Convert datetime to nanoseconds since epoch. If None, use current time."""
+    if dt is None:
+        dt = datetime.now()
+    return int(dt.timestamp() * 1_000_000_000)
+
+
+def uuid_to_trace_id(string: Optional[str]) -> int:
+    """Convert UUID string to a valid trace ID (16-byte integer)."""
+    if string is None:
+        string = ""
+    hash_object = hashlib.sha256(string.encode())
+
+    # Take the first 16 bytes (128 bits) of the hash
+    digest = hash_object.digest()[:16]
+
+    # Convert to integer (128 bits)
+    return int.from_bytes(digest, byteorder="big")
+
+
+class ArizePhoenixDataTrace(BaseTraceInstance):
+    def __init__(
+        self,
+        arize_phoenix_config: ArizeConfig | PhoenixConfig,
+    ):
+        super().__init__(arize_phoenix_config)
+        import logging
+
+        logging.basicConfig()
+        logging.getLogger().setLevel(logging.DEBUG)
+        self.arize_phoenix_config = arize_phoenix_config
+        self.tracer, self.processor = setup_tracer(arize_phoenix_config)
+        self.project = arize_phoenix_config.project
+        self.file_base_url = os.getenv("FILES_URL", "http://127.0.0.1:5001")
+
+    def trace(self, trace_info: BaseTraceInfo):
+        logger.info(f"[Arize/Phoenix] Trace: {trace_info}")
+        try:
+            if isinstance(trace_info, WorkflowTraceInfo):
+                self.workflow_trace(trace_info)
+            if isinstance(trace_info, MessageTraceInfo):
+                self.message_trace(trace_info)
+            if isinstance(trace_info, ModerationTraceInfo):
+                self.moderation_trace(trace_info)
+            if isinstance(trace_info, SuggestedQuestionTraceInfo):
+                self.suggested_question_trace(trace_info)
+            if isinstance(trace_info, DatasetRetrievalTraceInfo):
+                self.dataset_retrieval_trace(trace_info)
+            if isinstance(trace_info, ToolTraceInfo):
+                self.tool_trace(trace_info)
+            if isinstance(trace_info, GenerateNameTraceInfo):
+                self.generate_name_trace(trace_info)
+
+        except Exception as e:
+            logger.error(f"[Arize/Phoenix] Error in the trace: {str(e)}", exc_info=True)
+            raise
+
+    def workflow_trace(self, trace_info: WorkflowTraceInfo):
+        if trace_info.message_data is None:
+            return
+
+        workflow_metadata = {
+            "workflow_id": trace_info.workflow_run_id or "",
+            "message_id": trace_info.message_id or "",
+            "workflow_app_log_id": trace_info.workflow_app_log_id or "",
+            "status": trace_info.workflow_run_status or "",
+            "status_message": trace_info.error or "",
+            "level": "ERROR" if trace_info.error else "DEFAULT",
+            "total_tokens": trace_info.total_tokens or 0,
+        }
+        workflow_metadata.update(trace_info.metadata)
+
+        trace_id = uuid_to_trace_id(trace_info.message_id)
+        span_id = RandomIdGenerator().generate_span_id()
+        context = SpanContext(
+            trace_id=trace_id,
+            span_id=span_id,
+            is_remote=False,
+            trace_flags=TraceFlags(TraceFlags.SAMPLED),
+            trace_state=TraceState(),
+        )
+
+        workflow_span = self.tracer.start_span(
+            name=TraceTaskName.WORKFLOW_TRACE.value,
+            attributes={
+                SpanAttributes.INPUT_VALUE: json.dumps(trace_info.workflow_run_inputs, ensure_ascii=False),
+                SpanAttributes.OUTPUT_VALUE: json.dumps(trace_info.workflow_run_outputs, ensure_ascii=False),
+                SpanAttributes.OPENINFERENCE_SPAN_KIND: OpenInferenceSpanKindValues.CHAIN.value,
+                SpanAttributes.METADATA: json.dumps(workflow_metadata, ensure_ascii=False),
+                SpanAttributes.SESSION_ID: trace_info.conversation_id or "",
+            },
+            start_time=datetime_to_nanos(trace_info.start_time),
+            context=trace.set_span_in_context(trace.NonRecordingSpan(context)),
+        )
+
+        try:
+            # Process workflow nodes
+            for node_execution in self._get_workflow_nodes(trace_info.workflow_run_id):
+                created_at = node_execution.created_at or datetime.now()
+                elapsed_time = node_execution.elapsed_time
+                finished_at = created_at + timedelta(seconds=elapsed_time)
+
+                process_data = json.loads(node_execution.process_data) if node_execution.process_data else {}
+
+                node_metadata = {
+                    "node_id": node_execution.id,
+                    "node_type": node_execution.node_type,
+                    "node_status": node_execution.status,
+                    "tenant_id": node_execution.tenant_id,
+                    "app_id": node_execution.app_id,
+                    "app_name": node_execution.title,
+                    "status": node_execution.status,
+                    "level": "ERROR" if node_execution.status != "succeeded" else "DEFAULT",
+                }
+
+                if node_execution.execution_metadata:
+                    node_metadata.update(json.loads(node_execution.execution_metadata))
+
+                # Determine the correct span kind based on node type
+                span_kind = OpenInferenceSpanKindValues.CHAIN.value
+                if node_execution.node_type == "llm":
+                    span_kind = OpenInferenceSpanKindValues.LLM.value
+                    provider = process_data.get("model_provider")
+                    model = process_data.get("model_name")
+                    if provider:
+                        node_metadata["ls_provider"] = provider
+                    if model:
+                        node_metadata["ls_model_name"] = model
+
+                    usage = json.loads(node_execution.outputs).get("usage", {}) if node_execution.outputs else {}
+                    if usage:
+                        node_metadata["total_tokens"] = usage.get("total_tokens", 0)
+                        node_metadata["prompt_tokens"] = usage.get("prompt_tokens", 0)
+                        node_metadata["completion_tokens"] = usage.get("completion_tokens", 0)
+                elif node_execution.node_type == "dataset_retrieval":
+                    span_kind = OpenInferenceSpanKindValues.RETRIEVER.value
+                elif node_execution.node_type == "tool":
+                    span_kind = OpenInferenceSpanKindValues.TOOL.value
+                else:
+                    span_kind = OpenInferenceSpanKindValues.CHAIN.value
+
+                node_span = self.tracer.start_span(
+                    name=node_execution.node_type,
+                    attributes={
+                        SpanAttributes.INPUT_VALUE: node_execution.inputs or "{}",
+                        SpanAttributes.OUTPUT_VALUE: node_execution.outputs or "{}",
+                        SpanAttributes.OPENINFERENCE_SPAN_KIND: span_kind,
+                        SpanAttributes.METADATA: json.dumps(node_metadata, ensure_ascii=False),
+                        SpanAttributes.SESSION_ID: trace_info.conversation_id or "",
+                    },
+                    start_time=datetime_to_nanos(created_at),
+                )
+
+                try:
+                    if node_execution.node_type == "llm":
+                        provider = process_data.get("model_provider")
+                        model = process_data.get("model_name")
+                        if provider:
+                            node_span.set_attribute(SpanAttributes.LLM_PROVIDER, provider)
+                        if model:
+                            node_span.set_attribute(SpanAttributes.LLM_MODEL_NAME, model)
+
+                        usage = json.loads(node_execution.outputs).get("usage", {}) if node_execution.outputs else {}
+                        if usage:
+                            node_span.set_attribute(SpanAttributes.LLM_TOKEN_COUNT_TOTAL, usage.get("total_tokens", 0))
+                            node_span.set_attribute(
+                                SpanAttributes.LLM_TOKEN_COUNT_PROMPT, usage.get("prompt_tokens", 0)
+                            )
+                            node_span.set_attribute(
+                                SpanAttributes.LLM_TOKEN_COUNT_COMPLETION, usage.get("completion_tokens", 0)
+                            )
+                finally:
+                    node_span.end(end_time=datetime_to_nanos(finished_at))
+        finally:
+            workflow_span.end(end_time=datetime_to_nanos(trace_info.end_time))
+
+    def message_trace(self, trace_info: MessageTraceInfo):
+        if trace_info.message_data is None:
+            return
+
+        file_list = cast(list[str], trace_info.file_list) or []
+        message_file_data: Optional[MessageFile] = trace_info.message_file_data
+
+        if message_file_data is not None:
+            file_url = f"{self.file_base_url}/{message_file_data.url}" if message_file_data else ""
+            file_list.append(file_url)
+
+        message_metadata = {
+            "message_id": trace_info.message_id or "",
+            "conversation_mode": str(trace_info.conversation_mode or ""),
+            "user_id": trace_info.message_data.from_account_id or "",
+            "file_list": json.dumps(file_list),
+            "status": trace_info.message_data.status or "",
+            "status_message": trace_info.error or "",
+            "level": "ERROR" if trace_info.error else "DEFAULT",
+            "total_tokens": trace_info.total_tokens or 0,
+            "prompt_tokens": trace_info.message_tokens or 0,
+            "completion_tokens": trace_info.answer_tokens or 0,
+            "ls_provider": trace_info.message_data.model_provider or "",
+            "ls_model_name": trace_info.message_data.model_id or "",
+        }
+        message_metadata.update(trace_info.metadata)
+
+        # Add end user data if available
+        if trace_info.message_data.from_end_user_id:
+            end_user_data: Optional[EndUser] = (
+                db.session.query(EndUser).filter(EndUser.id == trace_info.message_data.from_end_user_id).first()
+            )
+            if end_user_data is not None:
+                message_metadata["end_user_id"] = end_user_data.session_id
+
+        attributes = {
+            SpanAttributes.INPUT_VALUE: trace_info.message_data.query,
+            SpanAttributes.OUTPUT_VALUE: trace_info.message_data.answer,
+            SpanAttributes.OPENINFERENCE_SPAN_KIND: OpenInferenceSpanKindValues.CHAIN.value,
+            SpanAttributes.METADATA: json.dumps(message_metadata, ensure_ascii=False),
+            SpanAttributes.SESSION_ID: trace_info.message_data.conversation_id,
+        }
+
+        trace_id = uuid_to_trace_id(trace_info.message_id)
+        message_span_id = RandomIdGenerator().generate_span_id()
+        span_context = SpanContext(
+            trace_id=trace_id,
+            span_id=message_span_id,
+            is_remote=False,
+            trace_flags=TraceFlags(TraceFlags.SAMPLED),
+            trace_state=TraceState(),
+        )
+
+        message_span = self.tracer.start_span(
+            name=TraceTaskName.MESSAGE_TRACE.value,
+            attributes=attributes,
+            start_time=datetime_to_nanos(trace_info.start_time),
+            context=trace.set_span_in_context(trace.NonRecordingSpan(span_context)),
+        )
+
+        try:
+            if trace_info.error:
+                message_span.add_event(
+                    "exception",
+                    attributes={
+                        "exception.message": trace_info.error,
+                        "exception.type": "Error",
+                        "exception.stacktrace": trace_info.error,
+                    },
+                )
+
+            # Convert outputs to string based on type
+            if isinstance(trace_info.outputs, dict | list):
+                outputs_str = json.dumps(trace_info.outputs, ensure_ascii=False)
+            elif isinstance(trace_info.outputs, str):
+                outputs_str = trace_info.outputs
+            else:
+                outputs_str = str(trace_info.outputs)
+
+            llm_attributes = {
+                SpanAttributes.OPENINFERENCE_SPAN_KIND: OpenInferenceSpanKindValues.LLM.value,
+                SpanAttributes.INPUT_VALUE: json.dumps(trace_info.inputs, ensure_ascii=False),
+                SpanAttributes.OUTPUT_VALUE: outputs_str,
+                SpanAttributes.METADATA: json.dumps(message_metadata, ensure_ascii=False),
+                SpanAttributes.SESSION_ID: trace_info.message_data.conversation_id,
+            }
+
+            if isinstance(trace_info.inputs, list):
+                for i, msg in enumerate(trace_info.inputs):
+                    if isinstance(msg, dict):
+                        llm_attributes[f"{SpanAttributes.LLM_INPUT_MESSAGES}.{i}.message.content"] = msg.get("text", "")
+                        llm_attributes[f"{SpanAttributes.LLM_INPUT_MESSAGES}.{i}.message.role"] = msg.get(
+                            "role", "user"
+                        )
+                        # todo: handle assistant and tool role messages, as they don't always
+                        # have a text field, but may have a tool_calls field instead
+                        # e.g. 'tool_calls': [{'id': '98af3a29-b066-45a5-b4b1-46c74ddafc58',
+                        # 'type': 'function', 'function': {'name': 'current_time', 'arguments': '{}'}}]}
+            elif isinstance(trace_info.inputs, dict):
+                llm_attributes[f"{SpanAttributes.LLM_INPUT_MESSAGES}.0.message.content"] = json.dumps(trace_info.inputs)
+                llm_attributes[f"{SpanAttributes.LLM_INPUT_MESSAGES}.0.message.role"] = "user"
+            elif isinstance(trace_info.inputs, str):
+                llm_attributes[f"{SpanAttributes.LLM_INPUT_MESSAGES}.0.message.content"] = trace_info.inputs
+                llm_attributes[f"{SpanAttributes.LLM_INPUT_MESSAGES}.0.message.role"] = "user"
+
+            if trace_info.total_tokens is not None and trace_info.total_tokens > 0:
+                llm_attributes[SpanAttributes.LLM_TOKEN_COUNT_TOTAL] = trace_info.total_tokens
+            if trace_info.message_tokens is not None and trace_info.message_tokens > 0:
+                llm_attributes[SpanAttributes.LLM_TOKEN_COUNT_PROMPT] = trace_info.message_tokens
+            if trace_info.answer_tokens is not None and trace_info.answer_tokens > 0:
+                llm_attributes[SpanAttributes.LLM_TOKEN_COUNT_COMPLETION] = trace_info.answer_tokens
+
+            if trace_info.message_data.model_id is not None:
+                llm_attributes[SpanAttributes.LLM_MODEL_NAME] = trace_info.message_data.model_id
+            if trace_info.message_data.model_provider is not None:
+                llm_attributes[SpanAttributes.LLM_PROVIDER] = trace_info.message_data.model_provider
+
+            if trace_info.message_data and trace_info.message_data.message_metadata:
+                metadata_dict = json.loads(trace_info.message_data.message_metadata)
+                if model_params := metadata_dict.get("model_parameters"):
+                    llm_attributes[SpanAttributes.LLM_INVOCATION_PARAMETERS] = json.dumps(model_params)
+
+            llm_span = self.tracer.start_span(
+                name="llm",
+                attributes=llm_attributes,
+                start_time=datetime_to_nanos(trace_info.start_time),
+                context=trace.set_span_in_context(trace.NonRecordingSpan(span_context)),
+            )
+
+            try:
+                if trace_info.error:
+                    llm_span.add_event(
+                        "exception",
+                        attributes={
+                            "exception.message": trace_info.error,
+                            "exception.type": "Error",
+                            "exception.stacktrace": trace_info.error,
+                        },
+                    )
+            finally:
+                llm_span.end(end_time=datetime_to_nanos(trace_info.end_time))
+        finally:
+            message_span.end(end_time=datetime_to_nanos(trace_info.end_time))
+
+    def moderation_trace(self, trace_info: ModerationTraceInfo):
+        if trace_info.message_data is None:
+            return
+
+        metadata = {
+            "message_id": trace_info.message_id,
+            "tool_name": "moderation",
+            "status": trace_info.message_data.status,
+            "status_message": trace_info.message_data.error or "",
+            "level": "ERROR" if trace_info.message_data.error else "DEFAULT",
+        }
+        metadata.update(trace_info.metadata)
+
+        trace_id = uuid_to_trace_id(trace_info.message_id)
+        span_id = RandomIdGenerator().generate_span_id()
+        context = SpanContext(
+            trace_id=trace_id,
+            span_id=span_id,
+            is_remote=False,
+            trace_flags=TraceFlags(TraceFlags.SAMPLED),
+            trace_state=TraceState(),
+        )
+
+        span = self.tracer.start_span(
+            name=TraceTaskName.MODERATION_TRACE.value,
+            attributes={
+                SpanAttributes.INPUT_VALUE: json.dumps(trace_info.inputs, ensure_ascii=False),
+                SpanAttributes.OUTPUT_VALUE: json.dumps(
+                    {
+                        "action": trace_info.action,
+                        "flagged": trace_info.flagged,
+                        "preset_response": trace_info.preset_response,
+                        "inputs": trace_info.inputs,
+                    },
+                    ensure_ascii=False,
+                ),
+                SpanAttributes.OPENINFERENCE_SPAN_KIND: OpenInferenceSpanKindValues.CHAIN.value,
+                SpanAttributes.METADATA: json.dumps(metadata, ensure_ascii=False),
+            },
+            start_time=datetime_to_nanos(trace_info.start_time),
+            context=trace.set_span_in_context(trace.NonRecordingSpan(context)),
+        )
+
+        try:
+            if trace_info.message_data.error:
+                span.add_event(
+                    "exception",
+                    attributes={
+                        "exception.message": trace_info.message_data.error,
+                        "exception.type": "Error",
+                        "exception.stacktrace": trace_info.message_data.error,
+                    },
+                )
+        finally:
+            span.end(end_time=datetime_to_nanos(trace_info.end_time))
+
+    def suggested_question_trace(self, trace_info: SuggestedQuestionTraceInfo):
+        if trace_info.message_data is None:
+            return
+
+        start_time = trace_info.start_time or trace_info.message_data.created_at
+        end_time = trace_info.end_time or trace_info.message_data.updated_at
+
+        metadata = {
+            "message_id": trace_info.message_id,
+            "tool_name": "suggested_question",
+            "status": trace_info.status,
+            "status_message": trace_info.error or "",
+            "level": "ERROR" if trace_info.error else "DEFAULT",
+            "total_tokens": trace_info.total_tokens,
+            "ls_provider": trace_info.model_provider or "",
+            "ls_model_name": trace_info.model_id or "",
+        }
+        metadata.update(trace_info.metadata)
+
+        trace_id = uuid_to_trace_id(trace_info.message_id)
+        span_id = RandomIdGenerator().generate_span_id()
+        context = SpanContext(
+            trace_id=trace_id,
+            span_id=span_id,
+            is_remote=False,
+            trace_flags=TraceFlags(TraceFlags.SAMPLED),
+            trace_state=TraceState(),
+        )
+
+        span = self.tracer.start_span(
+            name=TraceTaskName.SUGGESTED_QUESTION_TRACE.value,
+            attributes={
+                SpanAttributes.INPUT_VALUE: json.dumps(trace_info.inputs, ensure_ascii=False),
+                SpanAttributes.OUTPUT_VALUE: json.dumps(trace_info.suggested_question, ensure_ascii=False),
+                SpanAttributes.OPENINFERENCE_SPAN_KIND: OpenInferenceSpanKindValues.CHAIN.value,
+                SpanAttributes.METADATA: json.dumps(metadata, ensure_ascii=False),
+            },
+            start_time=datetime_to_nanos(start_time),
+            context=trace.set_span_in_context(trace.NonRecordingSpan(context)),
+        )
+
+        try:
+            if trace_info.error:
+                span.add_event(
+                    "exception",
+                    attributes={
+                        "exception.message": trace_info.error,
+                        "exception.type": "Error",
+                        "exception.stacktrace": trace_info.error,
+                    },
+                )
+        finally:
+            span.end(end_time=datetime_to_nanos(end_time))
+
+    def dataset_retrieval_trace(self, trace_info: DatasetRetrievalTraceInfo):
+        if trace_info.message_data is None:
+            return
+
+        start_time = trace_info.start_time or trace_info.message_data.created_at
+        end_time = trace_info.end_time or trace_info.message_data.updated_at
+
+        metadata = {
+            "message_id": trace_info.message_id,
+            "tool_name": "dataset_retrieval",
+            "status": trace_info.message_data.status,
+            "status_message": trace_info.message_data.error or "",
+            "level": "ERROR" if trace_info.message_data.error else "DEFAULT",
+            "ls_provider": trace_info.message_data.model_provider or "",
+            "ls_model_name": trace_info.message_data.model_id or "",
+        }
+        metadata.update(trace_info.metadata)
+
+        trace_id = uuid_to_trace_id(trace_info.message_id)
+        span_id = RandomIdGenerator().generate_span_id()
+        context = SpanContext(
+            trace_id=trace_id,
+            span_id=span_id,
+            is_remote=False,
+            trace_flags=TraceFlags(TraceFlags.SAMPLED),
+            trace_state=TraceState(),
+        )
+
+        span = self.tracer.start_span(
+            name=TraceTaskName.DATASET_RETRIEVAL_TRACE.value,
+            attributes={
+                SpanAttributes.INPUT_VALUE: json.dumps(trace_info.inputs, ensure_ascii=False),
+                SpanAttributes.OUTPUT_VALUE: json.dumps({"documents": trace_info.documents}, ensure_ascii=False),
+                SpanAttributes.OPENINFERENCE_SPAN_KIND: OpenInferenceSpanKindValues.RETRIEVER.value,
+                SpanAttributes.METADATA: json.dumps(metadata, ensure_ascii=False),
+                "start_time": start_time.isoformat() if start_time else "",
+                "end_time": end_time.isoformat() if end_time else "",
+            },
+            start_time=datetime_to_nanos(start_time),
+            context=trace.set_span_in_context(trace.NonRecordingSpan(context)),
+        )
+
+        try:
+            if trace_info.message_data.error:
+                span.add_event(
+                    "exception",
+                    attributes={
+                        "exception.message": trace_info.message_data.error,
+                        "exception.type": "Error",
+                        "exception.stacktrace": trace_info.message_data.error,
+                    },
+                )
+        finally:
+            span.end(end_time=datetime_to_nanos(end_time))
+
+    def tool_trace(self, trace_info: ToolTraceInfo):
+        if trace_info.message_data is None:
+            logger.warning("[Arize/Phoenix] Message data is None, skipping tool trace.")
+            return
+
+        metadata = {
+            "message_id": trace_info.message_id,
+            "tool_config": json.dumps(trace_info.tool_config, ensure_ascii=False),
+        }
+
+        trace_id = uuid_to_trace_id(trace_info.message_id)
+        tool_span_id = RandomIdGenerator().generate_span_id()
+        logger.info(f"[Arize/Phoenix] Creating tool trace with trace_id: {trace_id}, span_id: {tool_span_id}")
+
+        # Create span context with the same trace_id as the parent
+        # todo: Create with the appropriate parent span context, so that the tool span is
+        # a child of the appropriate span (e.g. message span)
+        span_context = SpanContext(
+            trace_id=trace_id,
+            span_id=tool_span_id,
+            is_remote=False,
+            trace_flags=TraceFlags(TraceFlags.SAMPLED),
+            trace_state=TraceState(),
+        )
+
+        tool_params_str = (
+            json.dumps(trace_info.tool_parameters, ensure_ascii=False)
+            if isinstance(trace_info.tool_parameters, dict)
+            else str(trace_info.tool_parameters)
+        )
+
+        span = self.tracer.start_span(
+            name=trace_info.tool_name,
+            attributes={
+                SpanAttributes.INPUT_VALUE: json.dumps(trace_info.tool_inputs, ensure_ascii=False),
+                SpanAttributes.OUTPUT_VALUE: trace_info.tool_outputs,
+                SpanAttributes.OPENINFERENCE_SPAN_KIND: OpenInferenceSpanKindValues.TOOL.value,
+                SpanAttributes.METADATA: json.dumps(metadata, ensure_ascii=False),
+                SpanAttributes.TOOL_NAME: trace_info.tool_name,
+                SpanAttributes.TOOL_PARAMETERS: tool_params_str,
+            },
+            start_time=datetime_to_nanos(trace_info.start_time),
+            context=trace.set_span_in_context(trace.NonRecordingSpan(span_context)),
+        )
+
+        try:
+            if trace_info.error:
+                span.add_event(
+                    "exception",
+                    attributes={
+                        "exception.message": trace_info.error,
+                        "exception.type": "Error",
+                        "exception.stacktrace": trace_info.error,
+                    },
+                )
+        finally:
+            span.end(end_time=datetime_to_nanos(trace_info.end_time))
+
+    def generate_name_trace(self, trace_info: GenerateNameTraceInfo):
+        if trace_info.message_data is None:
+            return
+
+        metadata = {
+            "project_name": self.project,
+            "message_id": trace_info.message_id,
+            "status": trace_info.message_data.status,
+            "status_message": trace_info.message_data.error or "",
+            "level": "ERROR" if trace_info.message_data.error else "DEFAULT",
+        }
+        metadata.update(trace_info.metadata)
+
+        trace_id = uuid_to_trace_id(trace_info.message_id)
+        span_id = RandomIdGenerator().generate_span_id()
+        context = SpanContext(
+            trace_id=trace_id,
+            span_id=span_id,
+            is_remote=False,
+            trace_flags=TraceFlags(TraceFlags.SAMPLED),
+            trace_state=TraceState(),
+        )
+
+        span = self.tracer.start_span(
+            name=TraceTaskName.GENERATE_NAME_TRACE.value,
+            attributes={
+                SpanAttributes.INPUT_VALUE: json.dumps(trace_info.inputs, ensure_ascii=False),
+                SpanAttributes.OUTPUT_VALUE: json.dumps(trace_info.outputs, ensure_ascii=False),
+                SpanAttributes.OPENINFERENCE_SPAN_KIND: OpenInferenceSpanKindValues.CHAIN.value,
+                SpanAttributes.METADATA: json.dumps(metadata, ensure_ascii=False),
+                SpanAttributes.SESSION_ID: trace_info.message_data.conversation_id,
+                "start_time": trace_info.start_time.isoformat() if trace_info.start_time else "",
+                "end_time": trace_info.end_time.isoformat() if trace_info.end_time else "",
+            },
+            start_time=datetime_to_nanos(trace_info.start_time),
+            context=trace.set_span_in_context(trace.NonRecordingSpan(context)),
+        )
+
+        try:
+            if trace_info.message_data.error:
+                span.add_event(
+                    "exception",
+                    attributes={
+                        "exception.message": trace_info.message_data.error,
+                        "exception.type": "Error",
+                        "exception.stacktrace": trace_info.message_data.error,
+                    },
+                )
+        finally:
+            span.end(end_time=datetime_to_nanos(trace_info.end_time))
+
+    def api_check(self):
+        try:
+            with self.tracer.start_span("api_check") as span:
+                span.set_attribute("test", "true")
+            return True
+        except Exception as e:
+            logger.info(f"[Arize/Phoenix] API check failed: {str(e)}", exc_info=True)
+            raise ValueError(f"[Arize/Phoenix] API check failed: {str(e)}")
+
+    def get_project_url(self):
+        try:
+            if self.arize_phoenix_config.endpoint == "https://otlp.arize.com":
+                return "https://app.arize.com/"
+            else:
+                return f"{self.arize_phoenix_config.endpoint}/projects/"
+        except Exception as e:
+            logger.info(f"[Arize/Phoenix] Get run url failed: {str(e)}", exc_info=True)
+            raise ValueError(f"[Arize/Phoenix] Get run url failed: {str(e)}")
+
+    def _get_workflow_nodes(self, workflow_run_id: str):
+        """Helper method to get workflow nodes"""
+        workflow_nodes = (
+            db.session.query(
+                WorkflowNodeExecutionModel.id,
+                WorkflowNodeExecutionModel.tenant_id,
+                WorkflowNodeExecutionModel.app_id,
+                WorkflowNodeExecutionModel.title,
+                WorkflowNodeExecutionModel.node_type,
+                WorkflowNodeExecutionModel.status,
+                WorkflowNodeExecutionModel.inputs,
+                WorkflowNodeExecutionModel.outputs,
+                WorkflowNodeExecutionModel.created_at,
+                WorkflowNodeExecutionModel.elapsed_time,
+                WorkflowNodeExecutionModel.process_data,
+                WorkflowNodeExecutionModel.execution_metadata,
+            )
+            .filter(WorkflowNodeExecutionModel.workflow_run_id == workflow_run_id)
+            .all()
+        )
+        return workflow_nodes

api/core/ops/entities/config_entity.py

@@ -2,20 +2,92 @@ from enum import StrEnum
 
 from pydantic import BaseModel, ValidationInfo, field_validator
 
+from core.ops.utils import validate_project_name, validate_url, validate_url_with_path
+
 
 class TracingProviderEnum(StrEnum):
+    ARIZE = "arize"
+    PHOENIX = "phoenix"
     LANGFUSE = "langfuse"
     LANGSMITH = "langsmith"
     OPIK = "opik"
     WEAVE = "weave"
+    ALIYUN = "aliyun"
 
 
 class BaseTracingConfig(BaseModel):
     """
-    Base model class for tracing
+    Base model class for tracing configurations
     """
 
-    ...
+    @classmethod
+    def validate_endpoint_url(cls, v: str, default_url: str) -> str:
+        """
+        Common endpoint URL validation logic
+
+        Args:
+            v: URL value to validate
+            default_url: Default URL to use if input is None or empty
+
+        Returns:
+            Validated and normalized URL
+        """
+        return validate_url(v, default_url)
+
+    @classmethod
+    def validate_project_field(cls, v: str, default_name: str) -> str:
+        """
+        Common project name validation logic
+
+        Args:
+            v: Project name to validate
+            default_name: Default name to use if input is None or empty
+
+        Returns:
+            Validated project name
+        """
+        return validate_project_name(v, default_name)
+
+
+class ArizeConfig(BaseTracingConfig):
+    """
+    Model class for Arize tracing config.
+    """
+
+    api_key: str | None = None
+    space_id: str | None = None
+    project: str | None = None
+    endpoint: str = "https://otlp.arize.com"
+
+    @field_validator("project")
+    @classmethod
+    def project_validator(cls, v, info: ValidationInfo):
+        return cls.validate_project_field(v, "default")
+
+    @field_validator("endpoint")
+    @classmethod
+    def endpoint_validator(cls, v, info: ValidationInfo):
+        return cls.validate_endpoint_url(v, "https://otlp.arize.com")
+
+
+class PhoenixConfig(BaseTracingConfig):
+    """
+    Model class for Phoenix tracing config.
+    """
+
+    api_key: str | None = None
+    project: str | None = None
+    endpoint: str = "https://app.phoenix.arize.com"
+
+    @field_validator("project")
+    @classmethod
+    def project_validator(cls, v, info: ValidationInfo):
+        return cls.validate_project_field(v, "default")
+
+    @field_validator("endpoint")
+    @classmethod
+    def endpoint_validator(cls, v, info: ValidationInfo):
+        return cls.validate_endpoint_url(v, "https://app.phoenix.arize.com")
 
 
 class LangfuseConfig(BaseTracingConfig):
@@ -29,13 +101,8 @@ class LangfuseConfig(BaseTracingConfig):
 
     @field_validator("host")
     @classmethod
-    def set_value(cls, v, info: ValidationInfo):
-        if v is None or v == "":
-            v = "https://api.langfuse.com"
-        if not v.startswith("https://") and not v.startswith("http://"):
-            raise ValueError("host must start with https:// or http://")
-
-        return v
+    def host_validator(cls, v, info: ValidationInfo):
+        return cls.validate_endpoint_url(v, "https://api.langfuse.com")
 
 
 class LangSmithConfig(BaseTracingConfig):
@@ -49,13 +116,9 @@ class LangSmithConfig(BaseTracingConfig):
 
     @field_validator("endpoint")
     @classmethod
-    def set_value(cls, v, info: ValidationInfo):
-        if v is None or v == "":
-            v = "https://api.smith.langchain.com"
-        if not v.startswith("https://"):
-            raise ValueError("endpoint must start with https://")
-
-        return v
+    def endpoint_validator(cls, v, info: ValidationInfo):
+        # LangSmith only allows HTTPS
+        return validate_url(v, "https://api.smith.langchain.com", allowed_schemes=("https",))
 
 
 class OpikConfig(BaseTracingConfig):
@@ -71,22 +134,12 @@ class OpikConfig(BaseTracingConfig):
     @field_validator("project")
     @classmethod
     def project_validator(cls, v, info: ValidationInfo):
-        if v is None or v == "":
-            v = "Default Project"
-
-        return v
+        return cls.validate_project_field(v, "Default Project")
 
     @field_validator("url")
     @classmethod
     def url_validator(cls, v, info: ValidationInfo):
-        if v is None or v == "":
-            v = "https://www.comet.com/opik/api/"
-        if not v.startswith(("https://", "http://")):
-            raise ValueError("url must start with https:// or http://")
-        if not v.endswith("/api/"):
-            raise ValueError("url should ends with /api/")
-
-        return v
+        return validate_url_with_path(v, "https://www.comet.com/opik/api/", required_suffix="/api/")
 
 
 class WeaveConfig(BaseTracingConfig):
@@ -102,22 +155,44 @@ class WeaveConfig(BaseTracingConfig):
 
     @field_validator("endpoint")
     @classmethod
-    def set_value(cls, v, info: ValidationInfo):
-        if v is None or v == "":
-            v = "https://trace.wandb.ai"
-        if not v.startswith("https://"):
-            raise ValueError("endpoint must start with https://")
-
-        return v
+    def endpoint_validator(cls, v, info: ValidationInfo):
+        # Weave only allows HTTPS for endpoint
+        return validate_url(v, "https://trace.wandb.ai", allowed_schemes=("https",))
 
     @field_validator("host")
     @classmethod
-    def validate_host(cls, v, info: ValidationInfo):
-        if v is not None and v != "":
-            if not v.startswith(("https://", "http://")):
-                raise ValueError("host must start with https:// or http://")
+    def host_validator(cls, v, info: ValidationInfo):
+        if v is not None and v.strip() != "":
+            return validate_url(v, v, allowed_schemes=("https", "http"))
         return v
 
 
+class AliyunConfig(BaseTracingConfig):
+    """
+    Model class for Aliyun tracing config.
+    """
+
+    app_name: str = "dify_app"
+    license_key: str
+    endpoint: str
+
+    @field_validator("app_name")
+    @classmethod
+    def app_name_validator(cls, v, info: ValidationInfo):
+        return cls.validate_project_field(v, "dify_app")
+
+    @field_validator("license_key")
+    @classmethod
+    def license_key_validator(cls, v, info: ValidationInfo):
+        if not v or v.strip() == "":
+            raise ValueError("License key cannot be empty")
+        return v
+
+    @field_validator("endpoint")
+    @classmethod
+    def endpoint_validator(cls, v, info: ValidationInfo):
+        return cls.validate_endpoint_url(v, "https://tracing-analysis-dc-hz.aliyuncs.com")
+
+
 OPS_FILE_PATH = "ops_trace/"
 OPS_TRACE_FAILED_KEY = "FAILED_OPS_TRACE"

api/core/ops/langfuse_trace/langfuse_trace.py

@@ -32,6 +32,7 @@ from core.repositories import SQLAlchemyWorkflowNodeExecutionRepository
 from core.workflow.nodes.enums import NodeType
 from extensions.ext_database import db
 from models import EndUser, WorkflowNodeExecutionTriggeredFrom
+from models.enums import MessageStatus
 
 logger = logging.getLogger(__name__)
 
@@ -293,7 +294,7 @@ class LangFuseDataTrace(BaseTraceInstance):
             input=trace_info.inputs,
             output=message_data.answer,
             metadata=metadata,
-            level=(LevelEnum.DEFAULT if message_data.status != "error" else LevelEnum.ERROR),
+            level=(LevelEnum.DEFAULT if message_data.status != MessageStatus.ERROR else LevelEnum.ERROR),
             status_message=message_data.error or "",
             usage=generation_usage,
         )
@@ -339,7 +340,7 @@ class LangFuseDataTrace(BaseTraceInstance):
             start_time=trace_info.start_time,
             end_time=trace_info.end_time,
             metadata=trace_info.metadata,
-            level=(LevelEnum.DEFAULT if message_data.status != "error" else LevelEnum.ERROR),
+            level=(LevelEnum.DEFAULT if message_data.status != MessageStatus.ERROR else LevelEnum.ERROR),
             status_message=message_data.error or "",
             usage=generation_usage,
         )

api/core/ops/ops_trace_manager.py

@@ -84,6 +84,36 @@ class OpsTraceProviderConfigMap(dict[str, dict[str, Any]]):
                     "other_keys": ["project", "entity", "endpoint", "host"],
                     "trace_instance": WeaveDataTrace,
                 }
+            case TracingProviderEnum.ARIZE:
+                from core.ops.arize_phoenix_trace.arize_phoenix_trace import ArizePhoenixDataTrace
+                from core.ops.entities.config_entity import ArizeConfig
+
+                return {
+                    "config_class": ArizeConfig,
+                    "secret_keys": ["api_key", "space_id"],
+                    "other_keys": ["project", "endpoint"],
+                    "trace_instance": ArizePhoenixDataTrace,
+                }
+            case TracingProviderEnum.PHOENIX:
+                from core.ops.arize_phoenix_trace.arize_phoenix_trace import ArizePhoenixDataTrace
+                from core.ops.entities.config_entity import PhoenixConfig
+
+                return {
+                    "config_class": PhoenixConfig,
+                    "secret_keys": ["api_key"],
+                    "other_keys": ["project", "endpoint"],
+                    "trace_instance": ArizePhoenixDataTrace,
+                }
+            case TracingProviderEnum.ALIYUN:
+                from core.ops.aliyun_trace.aliyun_trace import AliyunDataTrace
+                from core.ops.entities.config_entity import AliyunConfig
+
+                return {
+                    "config_class": AliyunConfig,
+                    "secret_keys": ["license_key"],
+                    "other_keys": ["endpoint", "app_name"],
+                    "trace_instance": AliyunDataTrace,
+                }
 
             case _:
                 raise KeyError(f"Unsupported tracing provider: {provider}")

api/core/ops/utils.py

@@ -1,6 +1,7 @@
 from contextlib import contextmanager
 from datetime import datetime
 from typing import Optional, Union
+from urllib.parse import urlparse
 
 from extensions.ext_database import db
 from models.model import Message
@@ -60,3 +61,83 @@ def generate_dotted_order(
         return current_segment
 
     return f"{parent_dotted_order}.{current_segment}"
+
+
+def validate_url(url: str, default_url: str, allowed_schemes: tuple = ("https", "http")) -> str:
+    """
+    Validate and normalize URL with proper error handling
+
+    Args:
+        url: The URL to validate
+        default_url: Default URL to use if input is None or empty
+        allowed_schemes: Tuple of allowed URL schemes (default: https, http)
+
+    Returns:
+        Normalized URL string
+
+    Raises:
+        ValueError: If URL format is invalid or scheme not allowed
+    """
+    if not url or url.strip() == "":
+        return default_url
+
+    # Parse URL to validate format
+    parsed = urlparse(url)
+
+    # Check if scheme is allowed
+    if parsed.scheme not in allowed_schemes:
+        raise ValueError(f"URL scheme must be one of: {', '.join(allowed_schemes)}")
+
+    # Reconstruct URL with only scheme, netloc (removing path, query, fragment)
+    normalized_url = f"{parsed.scheme}://{parsed.netloc}"
+
+    return normalized_url
+
+
+def validate_url_with_path(url: str, default_url: str, required_suffix: str | None = None) -> str:
+    """
+    Validate URL that may include path components
+
+    Args:
+        url: The URL to validate
+        default_url: Default URL to use if input is None or empty
+        required_suffix: Optional suffix that URL must end with
+
+    Returns:
+        Validated URL string
+
+    Raises:
+        ValueError: If URL format is invalid or doesn't match required suffix
+    """
+    if not url or url.strip() == "":
+        return default_url
+
+    # Parse URL to validate format
+    parsed = urlparse(url)
+
+    # Check if scheme is allowed
+    if parsed.scheme not in ("https", "http"):
+        raise ValueError("URL must start with https:// or http://")
+
+    # Check required suffix if specified
+    if required_suffix and not url.endswith(required_suffix):
+        raise ValueError(f"URL should end with {required_suffix}")
+
+    return url
+
+
+def validate_project_name(project: str, default_name: str) -> str:
+    """
+    Validate and normalize project name
+
+    Args:
+        project: Project name to validate
+        default_name: Default name to use if input is None or empty
+
+    Returns:
+        Normalized project name
+    """
+    if not project or project.strip() == "":
+        return default_name
+
+    return project.strip()

api/core/rag/extractor/helpers.py

@@ -1,7 +1,6 @@
 """Document loader helpers."""
 
 import concurrent.futures
-from pathlib import Path
 from typing import NamedTuple, Optional, cast
 
 
@@ -16,7 +15,7 @@ class FileEncoding(NamedTuple):
     """The language of the file."""
 
 
-def detect_file_encodings(file_path: str, timeout: int = 5) -> list[FileEncoding]:
+def detect_file_encodings(file_path: str, timeout: int = 5, sample_size: int = 1024 * 1024) -> list[FileEncoding]:
     """Try to detect the file encoding.
 
     Returns a list of `FileEncoding` tuples with the detected encodings ordered
@@ -25,11 +24,16 @@ def detect_file_encodings(file_path: str, timeout: int = 5) -> list[FileEncoding
     Args:
         file_path: The path to the file to detect the encoding for.
         timeout: The timeout in seconds for the encoding detection.
+        sample_size: The number of bytes to read for encoding detection. Default is 1MB.
+                    For large files, reading only a sample is sufficient and prevents timeout.
     """
     import chardet
 
     def read_and_detect(file_path: str) -> list[dict]:
-        rawdata = Path(file_path).read_bytes()
+        with open(file_path, "rb") as f:
+            # Read only a sample of the file for encoding detection
+            # This prevents timeout on large files while still providing accurate encoding detection
+            rawdata = f.read(sample_size)
         return cast(list[dict], chardet.detect_all(rawdata))
 
     with concurrent.futures.ThreadPoolExecutor() as executor:

api/core/rag/extractor/text_extractor.py

@@ -36,8 +36,12 @@ class TextExtractor(BaseExtractor):
                         break
                     except UnicodeDecodeError:
                         continue
+                else:
+                    raise RuntimeError(
+                        f"Decode failed: {self._file_path}, all detected encodings failed. Original error: {e}"
+                    )
             else:
-                raise RuntimeError(f"Error loading {self._file_path}") from e
+                raise RuntimeError(f"Decode failed: {self._file_path}, specified encoding failed. Original error: {e}")
         except Exception as e:
             raise RuntimeError(f"Error loading {self._file_path}") from e
 

api/core/tools/builtin_tool/providers/audio/tools/tts.py

@@ -31,6 +31,14 @@ class TTSTool(BuiltinTool):
             model_type=ModelType.TTS,
             model=model,
         )
+        if not voice:
+            voices = model_instance.get_tts_voices()
+            if voices:
+                voice = voices[0].get("value")
+                if not voice:
+                    raise ValueError("Sorry, no voice available.")
+            else:
+                raise ValueError("Sorry, no voice available.")
         tts = model_instance.invoke_tts(
             content_text=tool_parameters.get("text"),  # type: ignore
             user=user_id,

api/core/workflow/graph_engine/graph_engine.py

@@ -103,7 +103,7 @@ class GraphEngine:
         call_depth: int,
         graph: Graph,
         graph_config: Mapping[str, Any],
-        variable_pool: VariablePool,
+        graph_runtime_state: GraphRuntimeState,
         max_execution_steps: int,
         max_execution_time: int,
         thread_pool_id: Optional[str] = None,
@@ -140,7 +140,7 @@ class GraphEngine:
             call_depth=call_depth,
         )
 
-        self.graph_runtime_state = GraphRuntimeState(variable_pool=variable_pool, start_at=time.perf_counter())
+        self.graph_runtime_state = graph_runtime_state
 
         self.max_execution_steps = max_execution_steps
         self.max_execution_time = max_execution_time

api/core/workflow/nodes/agent/agent_node.py

@@ -1,4 +1,5 @@
 import json
+import uuid
 from collections.abc import Generator, Mapping, Sequence
 from typing import Any, Optional, cast
 
@@ -15,7 +16,7 @@ from core.model_runtime.entities.model_entities import AIModelEntity, ModelType
 from core.plugin.impl.exc import PluginDaemonClientSideError
 from core.plugin.impl.plugin import PluginInstaller
 from core.provider_manager import ProviderManager
-from core.tools.entities.tool_entities import ToolParameter, ToolProviderType
+from core.tools.entities.tool_entities import ToolInvokeMessage, ToolParameter, ToolProviderType
 from core.tools.tool_manager import ToolManager
 from core.variables.segments import StringSegment
 from core.workflow.entities.node_entities import NodeRunResult
@@ -106,6 +107,32 @@ class AgentNode(ToolNode):
 
         try:
             # convert tool messages
+            agent_thoughts: list = []
+
+            thought_log_message = ToolInvokeMessage(
+                type=ToolInvokeMessage.MessageType.LOG,
+                message=ToolInvokeMessage.LogMessage(
+                    id=str(uuid.uuid4()),
+                    label=f"Agent Strategy: {cast(AgentNodeData, self.node_data).agent_strategy_name}",
+                    parent_id=None,
+                    error=None,
+                    status=ToolInvokeMessage.LogMessage.LogStatus.START,
+                    data={
+                        "strategy": cast(AgentNodeData, self.node_data).agent_strategy_name,
+                        "parameters": parameters_for_log,
+                        "thought_process": "Agent strategy execution started",
+                    },
+                    metadata={
+                        "icon": self.agent_strategy_icon,
+                        "agent_strategy": cast(AgentNodeData, self.node_data).agent_strategy_name,
+                    },
+                ),
+            )
+
+            def enhanced_message_stream():
+                yield thought_log_message
+
+                yield from message_stream
 
             yield from self._transform_message(
                 message_stream,
@@ -114,6 +141,7 @@ class AgentNode(ToolNode):
                     "agent_strategy": cast(AgentNodeData, self.node_data).agent_strategy_name,
                 },
                 parameters_for_log,
+                agent_thoughts,
             )
         except PluginDaemonClientSideError as e:
             yield RunCompletedEvent(

api/core/workflow/nodes/http_request/executor.py

@@ -8,6 +8,7 @@ from typing import Any, Literal
 from urllib.parse import urlencode, urlparse
 
 import httpx
+from json_repair import repair_json
 
 from configs import dify_config
 from core.file import file_manager
@@ -178,7 +179,8 @@ class Executor:
                         raise RequestBodyError("json body type should have exactly one item")
                     json_string = self.variable_pool.convert_template(data[0].value).text
                     try:
-                        json_object = json.loads(json_string, strict=False)
+                        repaired = repair_json(json_string)
+                        json_object = json.loads(repaired, strict=False)
                     except json.JSONDecodeError as e:
                         raise RequestBodyError(f"Failed to parse JSON: {json_string}") from e
                     self.json = json_object

api/core/workflow/nodes/iteration/iteration_node.py

@@ -1,5 +1,6 @@
 import contextvars
 import logging
+import time
 import uuid
 from collections.abc import Generator, Mapping, Sequence
 from concurrent.futures import Future, wait
@@ -133,8 +134,11 @@ class IterationNode(BaseNode[IterationNodeData]):
         variable_pool.add([self.node_id, "item"], iterator_list_value[0])
 
         # init graph engine
+        from core.workflow.graph_engine.entities.graph_runtime_state import GraphRuntimeState
         from core.workflow.graph_engine.graph_engine import GraphEngine, GraphEngineThreadPool
 
+        graph_runtime_state = GraphRuntimeState(variable_pool=variable_pool, start_at=time.perf_counter())
+
         graph_engine = GraphEngine(
             tenant_id=self.tenant_id,
             app_id=self.app_id,
@@ -146,7 +150,7 @@ class IterationNode(BaseNode[IterationNodeData]):
             call_depth=self.workflow_call_depth,
             graph=iteration_graph,
             graph_config=graph_config,
-            variable_pool=variable_pool,
+            graph_runtime_state=graph_runtime_state,
             max_execution_steps=dify_config.WORKFLOW_MAX_EXECUTION_STEPS,
             max_execution_time=dify_config.WORKFLOW_MAX_EXECUTION_TIME,
             thread_pool_id=self.thread_pool_id,

api/core/workflow/nodes/loop/loop_node.py

@@ -1,5 +1,6 @@
 import json
 import logging
+import time
 from collections.abc import Generator, Mapping, Sequence
 from datetime import UTC, datetime
 from typing import TYPE_CHECKING, Any, Literal, cast
@@ -101,8 +102,11 @@ class LoopNode(BaseNode[LoopNodeData]):
                 loop_variable_selectors[loop_variable.label] = variable_selector
                 inputs[loop_variable.label] = processed_segment.value
 
+        from core.workflow.graph_engine.entities.graph_runtime_state import GraphRuntimeState
         from core.workflow.graph_engine.graph_engine import GraphEngine
 
+        graph_runtime_state = GraphRuntimeState(variable_pool=variable_pool, start_at=time.perf_counter())
+
         graph_engine = GraphEngine(
             tenant_id=self.tenant_id,
             app_id=self.app_id,
@@ -114,7 +118,7 @@ class LoopNode(BaseNode[LoopNodeData]):
             call_depth=self.workflow_call_depth,
             graph=loop_graph,
             graph_config=self.graph_config,
-            variable_pool=variable_pool,
+            graph_runtime_state=graph_runtime_state,
             max_execution_steps=dify_config.WORKFLOW_MAX_EXECUTION_STEPS,
             max_execution_time=dify_config.WORKFLOW_MAX_EXECUTION_TIME,
             thread_pool_id=self.thread_pool_id,

api/core/workflow/nodes/tool/tool_node.py

@@ -1,11 +1,12 @@
 from collections.abc import Generator, Mapping, Sequence
-from typing import Any, cast
+from typing import Any, Optional, cast
 
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 
 from core.callback_handler.workflow_tool_callback_handler import DifyWorkflowCallbackHandler
 from core.file import File, FileTransferMethod
+from core.model_runtime.entities.llm_entities import LLMUsage
 from core.plugin.impl.exc import PluginDaemonClientSideError
 from core.plugin.impl.plugin import PluginInstaller
 from core.tools.entities.tool_entities import ToolInvokeMessage, ToolParameter
@@ -190,6 +191,7 @@ class ToolNode(BaseNode[ToolNodeData]):
         messages: Generator[ToolInvokeMessage, None, None],
         tool_info: Mapping[str, Any],
         parameters_for_log: dict[str, Any],
+        agent_thoughts: Optional[list] = None,
     ) -> Generator:
         """
         Convert ToolInvokeMessages into tuple[plain_text, files]
@@ -208,7 +210,7 @@ class ToolNode(BaseNode[ToolNodeData]):
 
         agent_logs: list[AgentLogEvent] = []
         agent_execution_metadata: Mapping[WorkflowNodeExecutionMetadataKey, Any] = {}
-
+        llm_usage: LLMUsage | None = None
         variables: dict[str, Any] = {}
 
         for message in message_stream:
@@ -276,9 +278,10 @@ class ToolNode(BaseNode[ToolNodeData]):
             elif message.type == ToolInvokeMessage.MessageType.JSON:
                 assert isinstance(message.message, ToolInvokeMessage.JsonMessage)
                 if self.node_type == NodeType.AGENT:
-                    msg_metadata = message.message.json_object.pop("execution_metadata", {})
+                    msg_metadata: dict[str, Any] = message.message.json_object.pop("execution_metadata", {})
+                    llm_usage = LLMUsage.from_metadata(msg_metadata)
                     agent_execution_metadata = {
-                        key: value
+                        WorkflowNodeExecutionMetadataKey(key): value
                         for key, value in msg_metadata.items()
                         if key in WorkflowNodeExecutionMetadataKey.__members__.values()
                     }
@@ -366,17 +369,42 @@ class ToolNode(BaseNode[ToolNodeData]):
                     agent_logs.append(agent_log)
 
                 yield agent_log
+        # Add agent_logs to outputs['json'] to ensure frontend can access thinking process
+        json_output: dict[str, Any] = {}
+        if json:
+            if isinstance(json, list) and len(json) == 1:
+                # If json is a list with only one element, convert it to a dictionary
+                json_output = json[0] if isinstance(json[0], dict) else {"data": json[0]}
+            elif isinstance(json, list):
+                # If json is a list with multiple elements, create a dictionary containing all data
+                json_output = {"data": json}
 
+        if agent_logs:
+            # Add agent_logs to json output
+            json_output["agent_logs"] = [
+                {
+                    "id": log.id,
+                    "parent_id": log.parent_id,
+                    "error": log.error,
+                    "status": log.status,
+                    "data": log.data,
+                    "label": log.label,
+                    "metadata": log.metadata,
+                    "node_id": log.node_id,
+                }
+                for log in agent_logs
+            ]
         yield RunCompletedEvent(
             run_result=NodeRunResult(
                 status=WorkflowNodeExecutionStatus.SUCCEEDED,
-                outputs={"text": text, "files": ArrayFileSegment(value=files), "json": json, **variables},
+                outputs={"text": text, "files": ArrayFileSegment(value=files), "json": json_output, **variables},
                 metadata={
                     **agent_execution_metadata,
                     WorkflowNodeExecutionMetadataKey.TOOL_INFO: tool_info,
                     WorkflowNodeExecutionMetadataKey.AGENT_LOG: agent_logs,
                 },
                 inputs=parameters_for_log,
+                llm_usage=llm_usage,
             )
         )
 

api/core/workflow/workflow_entry.py

@@ -69,6 +69,7 @@ class WorkflowEntry:
             raise ValueError("Max workflow call depth {} reached.".format(workflow_call_max_depth))
 
         # init workflow run state
+        graph_runtime_state = GraphRuntimeState(variable_pool=variable_pool, start_at=time.perf_counter())
         self.graph_engine = GraphEngine(
             tenant_id=tenant_id,
             app_id=app_id,
@@ -80,7 +81,7 @@ class WorkflowEntry:
             call_depth=call_depth,
             graph=graph,
             graph_config=graph_config,
-            variable_pool=variable_pool,
+            graph_runtime_state=graph_runtime_state,
             max_execution_steps=dify_config.WORKFLOW_MAX_EXECUTION_STEPS,
             max_execution_time=dify_config.WORKFLOW_MAX_EXECUTION_TIME,
             thread_pool_id=thread_pool_id,

api/models/enums.py

@@ -21,3 +21,12 @@ class DraftVariableType(StrEnum):
     NODE = "node"
     SYS = "sys"
     CONVERSATION = "conversation"
+
+
+class MessageStatus(StrEnum):
+    """
+    Message Status Enum
+    """
+
+    NORMAL = "normal"
+    ERROR = "error"

api/pyproject.toml

@@ -4,6 +4,7 @@ version = "1.5.1"
 requires-python = ">=3.11,<3.13"
 
 dependencies = [
+    "arize-phoenix-otel~=0.9.2",
     "authlib==1.3.1",
     "azure-identity==1.16.1",
     "beautifulsoup4==4.12.2",

api/services/audio_service.py

@@ -1,13 +1,17 @@
 import io
 import logging
 import uuid
+from collections.abc import Generator
 from typing import Optional
 
+from flask import Response, stream_with_context
 from werkzeug.datastructures import FileStorage
 
 from constants import AUDIO_EXTENSIONS
 from core.model_manager import ModelManager
 from core.model_runtime.entities.model_entities import ModelType
+from extensions.ext_database import db
+from models.enums import MessageStatus
 from models.model import App, AppMode, AppModelConfig, Message
 from services.errors.audio import (
     AudioTooLargeServiceError,
@@ -16,6 +20,7 @@ from services.errors.audio import (
     ProviderNotSupportTextToSpeechServiceError,
     UnsupportedAudioTypeServiceError,
 )
+from services.workflow_service import WorkflowService
 
 FILE_SIZE = 30
 FILE_SIZE_LIMIT = FILE_SIZE * 1024 * 1024
@@ -74,35 +79,36 @@ class AudioService:
         voice: Optional[str] = None,
         end_user: Optional[str] = None,
         message_id: Optional[str] = None,
+        is_draft: bool = False,
     ):
-        from collections.abc import Generator
-
-        from flask import Response, stream_with_context
-
         from app import app
-        from extensions.ext_database import db
 
-        def invoke_tts(text_content: str, app_model: App, voice: Optional[str] = None):
+        def invoke_tts(text_content: str, app_model: App, voice: Optional[str] = None, is_draft: bool = False):
             with app.app_context():
-                if app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}:
-                    workflow = app_model.workflow
-                    if workflow is None:
-                        raise ValueError("TTS is not enabled")
+                if voice is None:
+                    if app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}:
+                        if is_draft:
+                            workflow = WorkflowService().get_draft_workflow(app_model=app_model)
+                        else:
+                            workflow = app_model.workflow
+                        if (
+                            workflow is None
+                            or "text_to_speech" not in workflow.features_dict
+                            or not workflow.features_dict["text_to_speech"].get("enabled")
+                        ):
+                            raise ValueError("TTS is not enabled")
 
-                    features_dict = workflow.features_dict
-                    if "text_to_speech" not in features_dict or not features_dict["text_to_speech"].get("enabled"):
-                        raise ValueError("TTS is not enabled")
+                        voice = workflow.features_dict["text_to_speech"].get("voice")
+                    else:
+                        if not is_draft:
+                            if app_model.app_model_config is None:
+                                raise ValueError("AppModelConfig not found")
+                            text_to_speech_dict = app_model.app_model_config.text_to_speech_dict
 
-                    voice = features_dict["text_to_speech"].get("voice") if voice is None else voice
-                else:
-                    if app_model.app_model_config is None:
-                        raise ValueError("AppModelConfig not found")
-                    text_to_speech_dict = app_model.app_model_config.text_to_speech_dict
+                            if not text_to_speech_dict.get("enabled"):
+                                raise ValueError("TTS is not enabled")
 
-                    if not text_to_speech_dict.get("enabled"):
-                        raise ValueError("TTS is not enabled")
-
-                    voice = text_to_speech_dict.get("voice") if voice is None else voice
+                            voice = text_to_speech_dict.get("voice")
 
                 model_manager = ModelManager()
                 model_instance = model_manager.get_default_model_instance(
@@ -132,18 +138,18 @@ class AudioService:
             message = db.session.query(Message).filter(Message.id == message_id).first()
             if message is None:
                 return None
-            if message.answer == "" and message.status == "normal":
+            if message.answer == "" and message.status == MessageStatus.NORMAL:
                 return None
 
             else:
-                response = invoke_tts(message.answer, app_model=app_model, voice=voice)
+                response = invoke_tts(text_content=message.answer, app_model=app_model, voice=voice, is_draft=is_draft)
                 if isinstance(response, Generator):
                     return Response(stream_with_context(response), content_type="audio/mpeg")
                 return response
         else:
             if text is None:
                 raise ValueError("Text is required")
-            response = invoke_tts(text, app_model, voice)
+            response = invoke_tts(text_content=text, app_model=app_model, voice=voice, is_draft=is_draft)
             if isinstance(response, Generator):
                 return Response(stream_with_context(response), content_type="audio/mpeg")
             return response

api/services/ops_service.py

@@ -34,6 +34,24 @@ class OpsService:
         )
         new_decrypt_tracing_config = OpsTraceManager.obfuscated_decrypt_token(tracing_provider, decrypt_tracing_config)
 
+        if tracing_provider == "arize" and (
+            "project_url" not in decrypt_tracing_config or not decrypt_tracing_config.get("project_url")
+        ):
+            try:
+                project_url = OpsTraceManager.get_trace_config_project_url(decrypt_tracing_config, tracing_provider)
+                new_decrypt_tracing_config.update({"project_url": project_url})
+            except Exception:
+                new_decrypt_tracing_config.update({"project_url": "https://app.arize.com/"})
+
+        if tracing_provider == "phoenix" and (
+            "project_url" not in decrypt_tracing_config or not decrypt_tracing_config.get("project_url")
+        ):
+            try:
+                project_url = OpsTraceManager.get_trace_config_project_url(decrypt_tracing_config, tracing_provider)
+                new_decrypt_tracing_config.update({"project_url": project_url})
+            except Exception:
+                new_decrypt_tracing_config.update({"project_url": "https://app.phoenix.arize.com/projects/"})
+
         if tracing_provider == "langfuse" and (
             "project_key" not in decrypt_tracing_config or not decrypt_tracing_config.get("project_key")
         ):
@@ -76,6 +94,16 @@ class OpsService:
                 new_decrypt_tracing_config.update({"project_url": project_url})
             except Exception:
                 new_decrypt_tracing_config.update({"project_url": "https://wandb.ai/"})
+
+        if tracing_provider == "aliyun" and (
+            "project_url" not in decrypt_tracing_config or not decrypt_tracing_config.get("project_url")
+        ):
+            try:
+                project_url = OpsTraceManager.get_trace_config_project_url(decrypt_tracing_config, tracing_provider)
+                new_decrypt_tracing_config.update({"project_url": project_url})
+            except Exception:
+                new_decrypt_tracing_config.update({"project_url": "https://arms.console.aliyun.com/"})
+
         trace_config_data.tracing_config = new_decrypt_tracing_config
         return trace_config_data.to_dict()
 
@@ -107,7 +135,9 @@ class OpsService:
             return {"error": "Invalid Credentials"}
 
         # get project url
-        if tracing_provider == "langfuse":
+        if tracing_provider in ("arize", "phoenix"):
+            project_url = OpsTraceManager.get_trace_config_project_url(tracing_config, tracing_provider)
+        elif tracing_provider == "langfuse":
             project_key = OpsTraceManager.get_trace_config_project_key(tracing_config, tracing_provider)
             project_url = "{host}/project/{key}".format(host=tracing_config.get("host"), key=project_key)
         elif tracing_provider in ("langsmith", "opik"):

api/tests/unit_tests/configs/test_dify_config.py

@@ -1,6 +1,7 @@
 import os
 
 from flask import Flask
+from packaging.version import Version
 from yarl import URL
 
 from configs.app_config import DifyConfig
@@ -40,6 +41,9 @@ def test_dify_config(monkeypatch):
 
     assert config.WORKFLOW_PARALLEL_DEPTH_LIMIT == 3
 
+    # values from pyproject.toml
+    assert Version(config.project.version) >= Version("1.0.0")
+
 
 # NOTE: If there is a `.env` file in your Workspace, this test might not succeed as expected.
 # This is due to `pymilvus` loading all the variables from the `.env` file into `os.environ`.

api/tests/unit_tests/core/ops/__init__.py

@@ -0,0 +1 @@
+# Unit tests for core ops module

api/tests/unit_tests/core/ops/test_config_entity.py

@@ -0,0 +1,385 @@
+import pytest
+from pydantic import ValidationError
+
+from core.ops.entities.config_entity import (
+    AliyunConfig,
+    ArizeConfig,
+    LangfuseConfig,
+    LangSmithConfig,
+    OpikConfig,
+    PhoenixConfig,
+    TracingProviderEnum,
+    WeaveConfig,
+)
+
+
+class TestTracingProviderEnum:
+    """Test cases for TracingProviderEnum"""
+
+    def test_enum_values(self):
+        """Test that all expected enum values are present"""
+        assert TracingProviderEnum.ARIZE == "arize"
+        assert TracingProviderEnum.PHOENIX == "phoenix"
+        assert TracingProviderEnum.LANGFUSE == "langfuse"
+        assert TracingProviderEnum.LANGSMITH == "langsmith"
+        assert TracingProviderEnum.OPIK == "opik"
+        assert TracingProviderEnum.WEAVE == "weave"
+        assert TracingProviderEnum.ALIYUN == "aliyun"
+
+
+class TestArizeConfig:
+    """Test cases for ArizeConfig"""
+
+    def test_valid_config(self):
+        """Test valid Arize configuration"""
+        config = ArizeConfig(
+            api_key="test_key", space_id="test_space", project="test_project", endpoint="https://custom.arize.com"
+        )
+        assert config.api_key == "test_key"
+        assert config.space_id == "test_space"
+        assert config.project == "test_project"
+        assert config.endpoint == "https://custom.arize.com"
+
+    def test_default_values(self):
+        """Test default values are set correctly"""
+        config = ArizeConfig()
+        assert config.api_key is None
+        assert config.space_id is None
+        assert config.project is None
+        assert config.endpoint == "https://otlp.arize.com"
+
+    def test_project_validation_empty(self):
+        """Test project validation with empty value"""
+        config = ArizeConfig(project="")
+        assert config.project == "default"
+
+    def test_project_validation_none(self):
+        """Test project validation with None value"""
+        config = ArizeConfig(project=None)
+        assert config.project == "default"
+
+    def test_endpoint_validation_empty(self):
+        """Test endpoint validation with empty value"""
+        config = ArizeConfig(endpoint="")
+        assert config.endpoint == "https://otlp.arize.com"
+
+    def test_endpoint_validation_with_path(self):
+        """Test endpoint validation normalizes URL by removing path"""
+        config = ArizeConfig(endpoint="https://custom.arize.com/api/v1")
+        assert config.endpoint == "https://custom.arize.com"
+
+    def test_endpoint_validation_invalid_scheme(self):
+        """Test endpoint validation rejects invalid schemes"""
+        with pytest.raises(ValidationError, match="URL scheme must be one of"):
+            ArizeConfig(endpoint="ftp://invalid.com")
+
+    def test_endpoint_validation_no_scheme(self):
+        """Test endpoint validation rejects URLs without scheme"""
+        with pytest.raises(ValidationError, match="URL scheme must be one of"):
+            ArizeConfig(endpoint="invalid.com")
+
+
+class TestPhoenixConfig:
+    """Test cases for PhoenixConfig"""
+
+    def test_valid_config(self):
+        """Test valid Phoenix configuration"""
+        config = PhoenixConfig(api_key="test_key", project="test_project", endpoint="https://custom.phoenix.com")
+        assert config.api_key == "test_key"
+        assert config.project == "test_project"
+        assert config.endpoint == "https://custom.phoenix.com"
+
+    def test_default_values(self):
+        """Test default values are set correctly"""
+        config = PhoenixConfig()
+        assert config.api_key is None
+        assert config.project is None
+        assert config.endpoint == "https://app.phoenix.arize.com"
+
+    def test_project_validation_empty(self):
+        """Test project validation with empty value"""
+        config = PhoenixConfig(project="")
+        assert config.project == "default"
+
+    def test_endpoint_validation_with_path(self):
+        """Test endpoint validation normalizes URL by removing path"""
+        config = PhoenixConfig(endpoint="https://custom.phoenix.com/api/v1")
+        assert config.endpoint == "https://custom.phoenix.com"
+
+
+class TestLangfuseConfig:
+    """Test cases for LangfuseConfig"""
+
+    def test_valid_config(self):
+        """Test valid Langfuse configuration"""
+        config = LangfuseConfig(public_key="public_key", secret_key="secret_key", host="https://custom.langfuse.com")
+        assert config.public_key == "public_key"
+        assert config.secret_key == "secret_key"
+        assert config.host == "https://custom.langfuse.com"
+
+    def test_default_values(self):
+        """Test default values are set correctly"""
+        config = LangfuseConfig(public_key="public", secret_key="secret")
+        assert config.host == "https://api.langfuse.com"
+
+    def test_missing_required_fields(self):
+        """Test that required fields are enforced"""
+        with pytest.raises(ValidationError):
+            LangfuseConfig()
+
+        with pytest.raises(ValidationError):
+            LangfuseConfig(public_key="public")
+
+        with pytest.raises(ValidationError):
+            LangfuseConfig(secret_key="secret")
+
+    def test_host_validation_empty(self):
+        """Test host validation with empty value"""
+        config = LangfuseConfig(public_key="public", secret_key="secret", host="")
+        assert config.host == "https://api.langfuse.com"
+
+
+class TestLangSmithConfig:
+    """Test cases for LangSmithConfig"""
+
+    def test_valid_config(self):
+        """Test valid LangSmith configuration"""
+        config = LangSmithConfig(api_key="test_key", project="test_project", endpoint="https://custom.smith.com")
+        assert config.api_key == "test_key"
+        assert config.project == "test_project"
+        assert config.endpoint == "https://custom.smith.com"
+
+    def test_default_values(self):
+        """Test default values are set correctly"""
+        config = LangSmithConfig(api_key="key", project="project")
+        assert config.endpoint == "https://api.smith.langchain.com"
+
+    def test_missing_required_fields(self):
+        """Test that required fields are enforced"""
+        with pytest.raises(ValidationError):
+            LangSmithConfig()
+
+        with pytest.raises(ValidationError):
+            LangSmithConfig(api_key="key")
+
+        with pytest.raises(ValidationError):
+            LangSmithConfig(project="project")
+
+    def test_endpoint_validation_https_only(self):
+        """Test endpoint validation only allows HTTPS"""
+        with pytest.raises(ValidationError, match="URL scheme must be one of"):
+            LangSmithConfig(api_key="key", project="project", endpoint="http://insecure.com")
+
+
+class TestOpikConfig:
+    """Test cases for OpikConfig"""
+
+    def test_valid_config(self):
+        """Test valid Opik configuration"""
+        config = OpikConfig(
+            api_key="test_key",
+            project="test_project",
+            workspace="test_workspace",
+            url="https://custom.comet.com/opik/api/",
+        )
+        assert config.api_key == "test_key"
+        assert config.project == "test_project"
+        assert config.workspace == "test_workspace"
+        assert config.url == "https://custom.comet.com/opik/api/"
+
+    def test_default_values(self):
+        """Test default values are set correctly"""
+        config = OpikConfig()
+        assert config.api_key is None
+        assert config.project is None
+        assert config.workspace is None
+        assert config.url == "https://www.comet.com/opik/api/"
+
+    def test_project_validation_empty(self):
+        """Test project validation with empty value"""
+        config = OpikConfig(project="")
+        assert config.project == "Default Project"
+
+    def test_url_validation_empty(self):
+        """Test URL validation with empty value"""
+        config = OpikConfig(url="")
+        assert config.url == "https://www.comet.com/opik/api/"
+
+    def test_url_validation_missing_suffix(self):
+        """Test URL validation requires /api/ suffix"""
+        with pytest.raises(ValidationError, match="URL should end with /api/"):
+            OpikConfig(url="https://custom.comet.com/opik/")
+
+    def test_url_validation_invalid_scheme(self):
+        """Test URL validation rejects invalid schemes"""
+        with pytest.raises(ValidationError, match="URL must start with https:// or http://"):
+            OpikConfig(url="ftp://custom.comet.com/opik/api/")
+
+
+class TestWeaveConfig:
+    """Test cases for WeaveConfig"""
+
+    def test_valid_config(self):
+        """Test valid Weave configuration"""
+        config = WeaveConfig(
+            api_key="test_key",
+            entity="test_entity",
+            project="test_project",
+            endpoint="https://custom.wandb.ai",
+            host="https://custom.host.com",
+        )
+        assert config.api_key == "test_key"
+        assert config.entity == "test_entity"
+        assert config.project == "test_project"
+        assert config.endpoint == "https://custom.wandb.ai"
+        assert config.host == "https://custom.host.com"
+
+    def test_default_values(self):
+        """Test default values are set correctly"""
+        config = WeaveConfig(api_key="key", project="project")
+        assert config.entity is None
+        assert config.endpoint == "https://trace.wandb.ai"
+        assert config.host is None
+
+    def test_missing_required_fields(self):
+        """Test that required fields are enforced"""
+        with pytest.raises(ValidationError):
+            WeaveConfig()
+
+        with pytest.raises(ValidationError):
+            WeaveConfig(api_key="key")
+
+        with pytest.raises(ValidationError):
+            WeaveConfig(project="project")
+
+    def test_endpoint_validation_https_only(self):
+        """Test endpoint validation only allows HTTPS"""
+        with pytest.raises(ValidationError, match="URL scheme must be one of"):
+            WeaveConfig(api_key="key", project="project", endpoint="http://insecure.wandb.ai")
+
+    def test_host_validation_optional(self):
+        """Test host validation is optional but validates when provided"""
+        config = WeaveConfig(api_key="key", project="project", host=None)
+        assert config.host is None
+
+        config = WeaveConfig(api_key="key", project="project", host="")
+        assert config.host == ""
+
+        config = WeaveConfig(api_key="key", project="project", host="https://valid.host.com")
+        assert config.host == "https://valid.host.com"
+
+    def test_host_validation_invalid_scheme(self):
+        """Test host validation rejects invalid schemes when provided"""
+        with pytest.raises(ValidationError, match="URL scheme must be one of"):
+            WeaveConfig(api_key="key", project="project", host="ftp://invalid.host.com")
+
+
+class TestAliyunConfig:
+    """Test cases for AliyunConfig"""
+
+    def test_valid_config(self):
+        """Test valid Aliyun configuration"""
+        config = AliyunConfig(
+            app_name="test_app",
+            license_key="test_license_key",
+            endpoint="https://custom.tracing-analysis-dc-hz.aliyuncs.com",
+        )
+        assert config.app_name == "test_app"
+        assert config.license_key == "test_license_key"
+        assert config.endpoint == "https://custom.tracing-analysis-dc-hz.aliyuncs.com"
+
+    def test_default_values(self):
+        """Test default values are set correctly"""
+        config = AliyunConfig(license_key="test_license", endpoint="https://tracing-analysis-dc-hz.aliyuncs.com")
+        assert config.app_name == "dify_app"
+
+    def test_missing_required_fields(self):
+        """Test that required fields are enforced"""
+        with pytest.raises(ValidationError):
+            AliyunConfig()
+
+        with pytest.raises(ValidationError):
+            AliyunConfig(license_key="test_license")
+
+        with pytest.raises(ValidationError):
+            AliyunConfig(endpoint="https://tracing-analysis-dc-hz.aliyuncs.com")
+
+    def test_app_name_validation_empty(self):
+        """Test app_name validation with empty value"""
+        config = AliyunConfig(
+            license_key="test_license", endpoint="https://tracing-analysis-dc-hz.aliyuncs.com", app_name=""
+        )
+        assert config.app_name == "dify_app"
+
+    def test_endpoint_validation_empty(self):
+        """Test endpoint validation with empty value"""
+        config = AliyunConfig(license_key="test_license", endpoint="")
+        assert config.endpoint == "https://tracing-analysis-dc-hz.aliyuncs.com"
+
+    def test_endpoint_validation_with_path(self):
+        """Test endpoint validation normalizes URL by removing path"""
+        config = AliyunConfig(
+            license_key="test_license", endpoint="https://tracing-analysis-dc-hz.aliyuncs.com/api/v1/traces"
+        )
+        assert config.endpoint == "https://tracing-analysis-dc-hz.aliyuncs.com"
+
+    def test_endpoint_validation_invalid_scheme(self):
+        """Test endpoint validation rejects invalid schemes"""
+        with pytest.raises(ValidationError, match="URL scheme must be one of"):
+            AliyunConfig(license_key="test_license", endpoint="ftp://invalid.tracing-analysis-dc-hz.aliyuncs.com")
+
+    def test_endpoint_validation_no_scheme(self):
+        """Test endpoint validation rejects URLs without scheme"""
+        with pytest.raises(ValidationError, match="URL scheme must be one of"):
+            AliyunConfig(license_key="test_license", endpoint="invalid.tracing-analysis-dc-hz.aliyuncs.com")
+
+    def test_license_key_required(self):
+        """Test that license_key is required and cannot be empty"""
+        with pytest.raises(ValidationError):
+            AliyunConfig(license_key="", endpoint="https://tracing-analysis-dc-hz.aliyuncs.com")
+
+
+class TestConfigIntegration:
+    """Integration tests for configuration classes"""
+
+    def test_all_configs_can_be_instantiated(self):
+        """Test that all config classes can be instantiated with valid data"""
+        configs = [
+            ArizeConfig(api_key="key"),
+            PhoenixConfig(api_key="key"),
+            LangfuseConfig(public_key="public", secret_key="secret"),
+            LangSmithConfig(api_key="key", project="project"),
+            OpikConfig(api_key="key"),
+            WeaveConfig(api_key="key", project="project"),
+            AliyunConfig(license_key="test_license", endpoint="https://tracing-analysis-dc-hz.aliyuncs.com"),
+        ]
+
+        for config in configs:
+            assert config is not None
+
+    def test_url_normalization_consistency(self):
+        """Test that URL normalization works consistently across configs"""
+        # Test that paths are removed from endpoints
+        arize_config = ArizeConfig(endpoint="https://arize.com/api/v1/test")
+        phoenix_config = PhoenixConfig(endpoint="https://phoenix.com/api/v2/")
+        aliyun_config = AliyunConfig(
+            license_key="test_license", endpoint="https://tracing-analysis-dc-hz.aliyuncs.com/api/v1/traces"
+        )
+
+        assert arize_config.endpoint == "https://arize.com"
+        assert phoenix_config.endpoint == "https://phoenix.com"
+        assert aliyun_config.endpoint == "https://tracing-analysis-dc-hz.aliyuncs.com"
+
+    def test_project_default_values(self):
+        """Test that project default values are set correctly"""
+        arize_config = ArizeConfig(project="")
+        phoenix_config = PhoenixConfig(project="")
+        opik_config = OpikConfig(project="")
+        aliyun_config = AliyunConfig(
+            license_key="test_license", endpoint="https://tracing-analysis-dc-hz.aliyuncs.com", app_name=""
+        )
+
+        assert arize_config.project == "default"
+        assert phoenix_config.project == "default"
+        assert opik_config.project == "Default Project"
+        assert aliyun_config.app_name == "dify_app"

api/tests/unit_tests/core/ops/test_utils.py

@@ -0,0 +1,138 @@
+import pytest
+
+from core.ops.utils import validate_project_name, validate_url, validate_url_with_path
+
+
+class TestValidateUrl:
+    """Test cases for validate_url function"""
+
+    def test_valid_https_url(self):
+        """Test valid HTTPS URL"""
+        result = validate_url("https://example.com", "https://default.com")
+        assert result == "https://example.com"
+
+    def test_valid_http_url(self):
+        """Test valid HTTP URL"""
+        result = validate_url("http://example.com", "https://default.com")
+        assert result == "http://example.com"
+
+    def test_url_with_path_removed(self):
+        """Test that URL path is removed during normalization"""
+        result = validate_url("https://example.com/api/v1/test", "https://default.com")
+        assert result == "https://example.com"
+
+    def test_url_with_query_removed(self):
+        """Test that URL query parameters are removed"""
+        result = validate_url("https://example.com?param=value", "https://default.com")
+        assert result == "https://example.com"
+
+    def test_url_with_fragment_removed(self):
+        """Test that URL fragments are removed"""
+        result = validate_url("https://example.com#section", "https://default.com")
+        assert result == "https://example.com"
+
+    def test_empty_url_returns_default(self):
+        """Test empty URL returns default"""
+        result = validate_url("", "https://default.com")
+        assert result == "https://default.com"
+
+    def test_none_url_returns_default(self):
+        """Test None URL returns default"""
+        result = validate_url(None, "https://default.com")
+        assert result == "https://default.com"
+
+    def test_whitespace_url_returns_default(self):
+        """Test whitespace URL returns default"""
+        result = validate_url("   ", "https://default.com")
+        assert result == "https://default.com"
+
+    def test_invalid_scheme_raises_error(self):
+        """Test invalid scheme raises ValueError"""
+        with pytest.raises(ValueError, match="URL scheme must be one of"):
+            validate_url("ftp://example.com", "https://default.com")
+
+    def test_no_scheme_raises_error(self):
+        """Test URL without scheme raises ValueError"""
+        with pytest.raises(ValueError, match="URL scheme must be one of"):
+            validate_url("example.com", "https://default.com")
+
+    def test_custom_allowed_schemes(self):
+        """Test custom allowed schemes"""
+        result = validate_url("https://example.com", "https://default.com", allowed_schemes=("https",))
+        assert result == "https://example.com"
+
+        with pytest.raises(ValueError, match="URL scheme must be one of"):
+            validate_url("http://example.com", "https://default.com", allowed_schemes=("https",))
+
+
+class TestValidateUrlWithPath:
+    """Test cases for validate_url_with_path function"""
+
+    def test_valid_url_with_path(self):
+        """Test valid URL with path"""
+        result = validate_url_with_path("https://example.com/api/v1", "https://default.com")
+        assert result == "https://example.com/api/v1"
+
+    def test_valid_url_with_required_suffix(self):
+        """Test valid URL with required suffix"""
+        result = validate_url_with_path("https://example.com/api/", "https://default.com", required_suffix="/api/")
+        assert result == "https://example.com/api/"
+
+    def test_url_without_required_suffix_raises_error(self):
+        """Test URL without required suffix raises error"""
+        with pytest.raises(ValueError, match="URL should end with /api/"):
+            validate_url_with_path("https://example.com/api", "https://default.com", required_suffix="/api/")
+
+    def test_empty_url_returns_default(self):
+        """Test empty URL returns default"""
+        result = validate_url_with_path("", "https://default.com")
+        assert result == "https://default.com"
+
+    def test_none_url_returns_default(self):
+        """Test None URL returns default"""
+        result = validate_url_with_path(None, "https://default.com")
+        assert result == "https://default.com"
+
+    def test_invalid_scheme_raises_error(self):
+        """Test invalid scheme raises ValueError"""
+        with pytest.raises(ValueError, match="URL must start with https:// or http://"):
+            validate_url_with_path("ftp://example.com", "https://default.com")
+
+    def test_no_scheme_raises_error(self):
+        """Test URL without scheme raises ValueError"""
+        with pytest.raises(ValueError, match="URL must start with https:// or http://"):
+            validate_url_with_path("example.com", "https://default.com")
+
+
+class TestValidateProjectName:
+    """Test cases for validate_project_name function"""
+
+    def test_valid_project_name(self):
+        """Test valid project name"""
+        result = validate_project_name("my-project", "default")
+        assert result == "my-project"
+
+    def test_empty_project_name_returns_default(self):
+        """Test empty project name returns default"""
+        result = validate_project_name("", "default")
+        assert result == "default"
+
+    def test_none_project_name_returns_default(self):
+        """Test None project name returns default"""
+        result = validate_project_name(None, "default")
+        assert result == "default"
+
+    def test_whitespace_project_name_returns_default(self):
+        """Test whitespace project name returns default"""
+        result = validate_project_name("   ", "default")
+        assert result == "default"
+
+    def test_project_name_with_whitespace_trimmed(self):
+        """Test project name with whitespace is trimmed"""
+        result = validate_project_name("  my-project  ", "default")
+        assert result == "my-project"
+
+    def test_custom_default_name(self):
+        """Test custom default name"""
+        result = validate_project_name("", "Custom Default")
+        assert result == "Custom Default"

api/tests/unit_tests/core/workflow/graph_engine/test_graph_engine.py

@@ -1,3 +1,4 @@
+import time
 from unittest.mock import patch
 
 import pytest
@@ -19,6 +20,7 @@ from core.workflow.graph_engine.entities.event import (
     NodeRunSucceededEvent,
 )
 from core.workflow.graph_engine.entities.graph import Graph
+from core.workflow.graph_engine.entities.graph_runtime_state import GraphRuntimeState
 from core.workflow.graph_engine.entities.runtime_route_state import RouteNodeState
 from core.workflow.graph_engine.graph_engine import GraphEngine
 from core.workflow.nodes.code.code_node import CodeNode
@@ -172,6 +174,7 @@ def test_run_parallel_in_workflow(mock_close, mock_remove):
         system_variables={SystemVariableKey.FILES: [], SystemVariableKey.USER_ID: "aaa"}, user_inputs={"query": "hi"}
     )
 
+    graph_runtime_state = GraphRuntimeState(variable_pool=variable_pool, start_at=time.perf_counter())
     graph_engine = GraphEngine(
         tenant_id="111",
         app_id="222",
@@ -183,7 +186,7 @@ def test_run_parallel_in_workflow(mock_close, mock_remove):
         invoke_from=InvokeFrom.WEB_APP,
         call_depth=0,
         graph=graph,
-        variable_pool=variable_pool,
+        graph_runtime_state=graph_runtime_state,
         max_execution_steps=500,
         max_execution_time=1200,
     )
@@ -299,6 +302,7 @@ def test_run_parallel_in_chatflow(mock_close, mock_remove):
         user_inputs={},
     )
 
+    graph_runtime_state = GraphRuntimeState(variable_pool=variable_pool, start_at=time.perf_counter())
     graph_engine = GraphEngine(
         tenant_id="111",
         app_id="222",
@@ -310,7 +314,7 @@ def test_run_parallel_in_chatflow(mock_close, mock_remove):
         invoke_from=InvokeFrom.WEB_APP,
         call_depth=0,
         graph=graph,
-        variable_pool=variable_pool,
+        graph_runtime_state=graph_runtime_state,
         max_execution_steps=500,
         max_execution_time=1200,
     )
@@ -479,6 +483,7 @@ def test_run_branch(mock_close, mock_remove):
         user_inputs={"uid": "takato"},
     )
 
+    graph_runtime_state = GraphRuntimeState(variable_pool=variable_pool, start_at=time.perf_counter())
     graph_engine = GraphEngine(
         tenant_id="111",
         app_id="222",
@@ -490,7 +495,7 @@ def test_run_branch(mock_close, mock_remove):
         invoke_from=InvokeFrom.WEB_APP,
         call_depth=0,
         graph=graph,
-        variable_pool=variable_pool,
+        graph_runtime_state=graph_runtime_state,
         max_execution_steps=500,
         max_execution_time=1200,
     )
@@ -813,6 +818,7 @@ def test_condition_parallel_correct_output(mock_close, mock_remove, app):
         system_variables={SystemVariableKey.FILES: [], SystemVariableKey.USER_ID: "aaa"}, user_inputs={"query": "hi"}
     )
 
+    graph_runtime_state = GraphRuntimeState(variable_pool=variable_pool, start_at=time.perf_counter())
     graph_engine = GraphEngine(
         tenant_id="111",
         app_id="222",
@@ -824,7 +830,7 @@ def test_condition_parallel_correct_output(mock_close, mock_remove, app):
         invoke_from=InvokeFrom.WEB_APP,
         call_depth=0,
         graph=graph,
-        variable_pool=variable_pool,
+        graph_runtime_state=graph_runtime_state,
         max_execution_steps=500,
         max_execution_time=1200,
     )

api/tests/unit_tests/core/workflow/nodes/test_continue_on_error.py

@@ -1,7 +1,9 @@
+import time
 from unittest.mock import patch
 
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.workflow.entities.node_entities import NodeRunResult, WorkflowNodeExecutionMetadataKey
+from core.workflow.entities.variable_pool import VariablePool
 from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionStatus
 from core.workflow.enums import SystemVariableKey
 from core.workflow.graph_engine.entities.event import (
@@ -11,6 +13,7 @@ from core.workflow.graph_engine.entities.event import (
     NodeRunStreamChunkEvent,
 )
 from core.workflow.graph_engine.entities.graph import Graph
+from core.workflow.graph_engine.entities.graph_runtime_state import GraphRuntimeState
 from core.workflow.graph_engine.graph_engine import GraphEngine
 from core.workflow.nodes.event.event import RunCompletedEvent, RunStreamChunkEvent
 from core.workflow.nodes.llm.node import LLMNode
@@ -163,15 +166,16 @@ class ContinueOnErrorTestHelper:
     def create_test_graph_engine(graph_config: dict, user_inputs: dict | None = None):
         """Helper method to create a graph engine instance for testing"""
         graph = Graph.init(graph_config=graph_config)
-        variable_pool = {
-            "system_variables": {
+        variable_pool = VariablePool(
+            system_variables={
                 SystemVariableKey.QUERY: "clear",
                 SystemVariableKey.FILES: [],
                 SystemVariableKey.CONVERSATION_ID: "abababa",
                 SystemVariableKey.USER_ID: "aaa",
             },
-            "user_inputs": user_inputs or {"uid": "takato"},
-        }
+            user_inputs=user_inputs or {"uid": "takato"},
+        )
+        graph_runtime_state = GraphRuntimeState(variable_pool=variable_pool, start_at=time.perf_counter())
 
         return GraphEngine(
             tenant_id="111",
@@ -184,7 +188,7 @@ class ContinueOnErrorTestHelper:
             invoke_from=InvokeFrom.WEB_APP,
             call_depth=0,
             graph=graph,
-            variable_pool=variable_pool,
+            graph_runtime_state=graph_runtime_state,
             max_execution_steps=500,
             max_execution_time=1200,
         )

api/tests/unit_tests/libs/test_password.py

@@ -0,0 +1,74 @@
+import base64
+import binascii
+import os
+
+import pytest
+
+from libs.password import compare_password, hash_password, valid_password
+
+
+class TestValidPassword:
+    """Test password format validation"""
+
+    def test_should_accept_valid_passwords(self):
+        """Test accepting valid password formats"""
+        assert valid_password("password123") == "password123"
+        assert valid_password("test1234") == "test1234"
+        assert valid_password("Test123456") == "Test123456"
+
+    def test_should_reject_invalid_passwords(self):
+        """Test rejecting invalid password formats"""
+        # Too short
+        with pytest.raises(ValueError) as exc_info:
+            valid_password("abc123")
+        assert "Password must contain letters and numbers" in str(exc_info.value)
+
+        # No numbers
+        with pytest.raises(ValueError):
+            valid_password("abcdefgh")
+
+        # No letters
+        with pytest.raises(ValueError):
+            valid_password("12345678")
+
+        # Empty
+        with pytest.raises(ValueError):
+            valid_password("")
+
+
+class TestPasswordHashing:
+    """Test password hashing and comparison"""
+
+    def setup_method(self):
+        """Setup test data"""
+        self.password = "test123password"
+        self.salt = os.urandom(16)
+        self.salt_base64 = base64.b64encode(self.salt).decode()
+
+        password_hash = hash_password(self.password, self.salt)
+        self.password_hash_base64 = base64.b64encode(password_hash).decode()
+
+    def test_should_verify_correct_password(self):
+        """Test correct password verification"""
+        result = compare_password(self.password, self.password_hash_base64, self.salt_base64)
+        assert result is True
+
+    def test_should_reject_wrong_password(self):
+        """Test rejection of incorrect passwords"""
+        result = compare_password("wrongpassword", self.password_hash_base64, self.salt_base64)
+        assert result is False
+
+    def test_should_handle_invalid_base64(self):
+        """Test handling of invalid base64 data"""
+        # Invalid base64 hash
+        with pytest.raises(binascii.Error):
+            compare_password(self.password, "invalid_base64!", self.salt_base64)
+
+        # Invalid base64 salt
+        with pytest.raises(binascii.Error):
+            compare_password(self.password, self.password_hash_base64, "invalid_base64!")
+
+    def test_should_be_case_sensitive(self):
+        """Test password case sensitivity"""
+        result = compare_password(self.password.upper(), self.password_hash_base64, self.salt_base64)
+        assert result is False

api/tests/unit_tests/utils/structured_output_parser/test_structured_output_parser.py

@@ -0,0 +1,465 @@
+from decimal import Decimal
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from core.llm_generator.output_parser.errors import OutputParserError
+from core.llm_generator.output_parser.structured_output import invoke_llm_with_structured_output
+from core.model_runtime.entities.llm_entities import (
+    LLMResult,
+    LLMResultChunk,
+    LLMResultChunkDelta,
+    LLMResultChunkWithStructuredOutput,
+    LLMResultWithStructuredOutput,
+    LLMUsage,
+)
+from core.model_runtime.entities.message_entities import (
+    AssistantPromptMessage,
+    SystemPromptMessage,
+    TextPromptMessageContent,
+    UserPromptMessage,
+)
+from core.model_runtime.entities.model_entities import AIModelEntity, ModelType
+
+
+def create_mock_usage(prompt_tokens: int = 10, completion_tokens: int = 5) -> LLMUsage:
+    """Create a mock LLMUsage with all required fields"""
+    return LLMUsage(
+        prompt_tokens=prompt_tokens,
+        prompt_unit_price=Decimal("0.001"),
+        prompt_price_unit=Decimal("1"),
+        prompt_price=Decimal(str(prompt_tokens)) * Decimal("0.001"),
+        completion_tokens=completion_tokens,
+        completion_unit_price=Decimal("0.002"),
+        completion_price_unit=Decimal("1"),
+        completion_price=Decimal(str(completion_tokens)) * Decimal("0.002"),
+        total_tokens=prompt_tokens + completion_tokens,
+        total_price=Decimal(str(prompt_tokens)) * Decimal("0.001") + Decimal(str(completion_tokens)) * Decimal("0.002"),
+        currency="USD",
+        latency=1.5,
+    )
+
+
+def get_model_entity(provider: str, model_name: str, support_structure_output: bool = False) -> AIModelEntity:
+    """Create a mock AIModelEntity for testing"""
+    model_schema = MagicMock()
+    model_schema.model = model_name
+    model_schema.provider = provider
+    model_schema.model_type = ModelType.LLM
+    model_schema.model_provider = provider
+    model_schema.model_name = model_name
+    model_schema.support_structure_output = support_structure_output
+    model_schema.parameter_rules = []
+
+    return model_schema
+
+
+def get_model_instance() -> MagicMock:
+    """Create a mock ModelInstance for testing"""
+    mock_instance = MagicMock()
+    mock_instance.provider = "openai"
+    mock_instance.credentials = {}
+    return mock_instance
+
+
+def test_structured_output_parser():
+    """Test cases for invoke_llm_with_structured_output function"""
+
+    testcases = [
+        # Test case 1: Model with native structured output support, non-streaming
+        {
+            "name": "native_structured_output_non_streaming",
+            "provider": "openai",
+            "model_name": "gpt-4o",
+            "support_structure_output": True,
+            "stream": False,
+            "json_schema": {"type": "object", "properties": {"name": {"type": "string"}}},
+            "expected_llm_response": LLMResult(
+                model="gpt-4o",
+                message=AssistantPromptMessage(content='{"name": "test"}'),
+                usage=create_mock_usage(prompt_tokens=10, completion_tokens=5),
+            ),
+            "expected_result_type": LLMResultWithStructuredOutput,
+            "should_raise": False,
+        },
+        # Test case 2: Model with native structured output support, streaming
+        {
+            "name": "native_structured_output_streaming",
+            "provider": "openai",
+            "model_name": "gpt-4o",
+            "support_structure_output": True,
+            "stream": True,
+            "json_schema": {"type": "object", "properties": {"name": {"type": "string"}}},
+            "expected_llm_response": [
+                LLMResultChunk(
+                    model="gpt-4o",
+                    prompt_messages=[UserPromptMessage(content="test")],
+                    system_fingerprint="test",
+                    delta=LLMResultChunkDelta(
+                        index=0,
+                        message=AssistantPromptMessage(content='{"name":'),
+                        usage=create_mock_usage(prompt_tokens=10, completion_tokens=2),
+                    ),
+                ),
+                LLMResultChunk(
+                    model="gpt-4o",
+                    prompt_messages=[UserPromptMessage(content="test")],
+                    system_fingerprint="test",
+                    delta=LLMResultChunkDelta(
+                        index=0,
+                        message=AssistantPromptMessage(content=' "test"}'),
+                        usage=create_mock_usage(prompt_tokens=10, completion_tokens=3),
+                    ),
+                ),
+            ],
+            "expected_result_type": "generator",
+            "should_raise": False,
+        },
+        # Test case 3: Model without native structured output support, non-streaming
+        {
+            "name": "prompt_based_structured_output_non_streaming",
+            "provider": "anthropic",
+            "model_name": "claude-3-sonnet",
+            "support_structure_output": False,
+            "stream": False,
+            "json_schema": {"type": "object", "properties": {"answer": {"type": "string"}}},
+            "expected_llm_response": LLMResult(
+                model="claude-3-sonnet",
+                message=AssistantPromptMessage(content='{"answer": "test response"}'),
+                usage=create_mock_usage(prompt_tokens=15, completion_tokens=8),
+            ),
+            "expected_result_type": LLMResultWithStructuredOutput,
+            "should_raise": False,
+        },
+        # Test case 4: Model without native structured output support, streaming
+        {
+            "name": "prompt_based_structured_output_streaming",
+            "provider": "anthropic",
+            "model_name": "claude-3-sonnet",
+            "support_structure_output": False,
+            "stream": True,
+            "json_schema": {"type": "object", "properties": {"answer": {"type": "string"}}},
+            "expected_llm_response": [
+                LLMResultChunk(
+                    model="claude-3-sonnet",
+                    prompt_messages=[UserPromptMessage(content="test")],
+                    system_fingerprint="test",
+                    delta=LLMResultChunkDelta(
+                        index=0,
+                        message=AssistantPromptMessage(content='{"answer": "test'),
+                        usage=create_mock_usage(prompt_tokens=15, completion_tokens=3),
+                    ),
+                ),
+                LLMResultChunk(
+                    model="claude-3-sonnet",
+                    prompt_messages=[UserPromptMessage(content="test")],
+                    system_fingerprint="test",
+                    delta=LLMResultChunkDelta(
+                        index=0,
+                        message=AssistantPromptMessage(content=' response"}'),
+                        usage=create_mock_usage(prompt_tokens=15, completion_tokens=5),
+                    ),
+                ),
+            ],
+            "expected_result_type": "generator",
+            "should_raise": False,
+        },
+        # Test case 5: Streaming with list content
+        {
+            "name": "streaming_with_list_content",
+            "provider": "openai",
+            "model_name": "gpt-4o",
+            "support_structure_output": True,
+            "stream": True,
+            "json_schema": {"type": "object", "properties": {"data": {"type": "string"}}},
+            "expected_llm_response": [
+                LLMResultChunk(
+                    model="gpt-4o",
+                    prompt_messages=[UserPromptMessage(content="test")],
+                    system_fingerprint="test",
+                    delta=LLMResultChunkDelta(
+                        index=0,
+                        message=AssistantPromptMessage(
+                            content=[
+                                TextPromptMessageContent(data='{"data":'),
+                            ]
+                        ),
+                        usage=create_mock_usage(prompt_tokens=10, completion_tokens=2),
+                    ),
+                ),
+                LLMResultChunk(
+                    model="gpt-4o",
+                    prompt_messages=[UserPromptMessage(content="test")],
+                    system_fingerprint="test",
+                    delta=LLMResultChunkDelta(
+                        index=0,
+                        message=AssistantPromptMessage(
+                            content=[
+                                TextPromptMessageContent(data=' "value"}'),
+                            ]
+                        ),
+                        usage=create_mock_usage(prompt_tokens=10, completion_tokens=3),
+                    ),
+                ),
+            ],
+            "expected_result_type": "generator",
+            "should_raise": False,
+        },
+        # Test case 6: Error case - non-string LLM response content (non-streaming)
+        {
+            "name": "error_non_string_content_non_streaming",
+            "provider": "openai",
+            "model_name": "gpt-4o",
+            "support_structure_output": True,
+            "stream": False,
+            "json_schema": {"type": "object", "properties": {"name": {"type": "string"}}},
+            "expected_llm_response": LLMResult(
+                model="gpt-4o",
+                message=AssistantPromptMessage(content=None),  # Non-string content
+                usage=create_mock_usage(prompt_tokens=10, completion_tokens=5),
+            ),
+            "expected_result_type": None,
+            "should_raise": True,
+            "expected_error": OutputParserError,
+        },
+        # Test case 7: JSON repair scenario
+        {
+            "name": "json_repair_scenario",
+            "provider": "openai",
+            "model_name": "gpt-4o",
+            "support_structure_output": True,
+            "stream": False,
+            "json_schema": {"type": "object", "properties": {"name": {"type": "string"}}},
+            "expected_llm_response": LLMResult(
+                model="gpt-4o",
+                message=AssistantPromptMessage(content='{"name": "test"'),  # Invalid JSON - missing closing brace
+                usage=create_mock_usage(prompt_tokens=10, completion_tokens=5),
+            ),
+            "expected_result_type": LLMResultWithStructuredOutput,
+            "should_raise": False,
+        },
+        # Test case 8: Model with parameter rules for response format
+        {
+            "name": "model_with_parameter_rules",
+            "provider": "openai",
+            "model_name": "gpt-4o",
+            "support_structure_output": True,
+            "stream": False,
+            "json_schema": {"type": "object", "properties": {"result": {"type": "string"}}},
+            "parameter_rules": [
+                MagicMock(name="response_format", options=["json_schema"], required=False),
+            ],
+            "expected_llm_response": LLMResult(
+                model="gpt-4o",
+                message=AssistantPromptMessage(content='{"result": "success"}'),
+                usage=create_mock_usage(prompt_tokens=10, completion_tokens=5),
+            ),
+            "expected_result_type": LLMResultWithStructuredOutput,
+            "should_raise": False,
+        },
+        # Test case 9: Model without native support but with JSON response format rules
+        {
+            "name": "non_native_with_json_rules",
+            "provider": "anthropic",
+            "model_name": "claude-3-sonnet",
+            "support_structure_output": False,
+            "stream": False,
+            "json_schema": {"type": "object", "properties": {"output": {"type": "string"}}},
+            "parameter_rules": [
+                MagicMock(name="response_format", options=["JSON"], required=False),
+            ],
+            "expected_llm_response": LLMResult(
+                model="claude-3-sonnet",
+                message=AssistantPromptMessage(content='{"output": "result"}'),
+                usage=create_mock_usage(prompt_tokens=15, completion_tokens=8),
+            ),
+            "expected_result_type": LLMResultWithStructuredOutput,
+            "should_raise": False,
+        },
+    ]
+
+    for case in testcases:
+        print(f"Running test case: {case['name']}")
+
+        # Setup model entity
+        model_schema = get_model_entity(case["provider"], case["model_name"], case["support_structure_output"])
+
+        # Add parameter rules if specified
+        if "parameter_rules" in case:
+            model_schema.parameter_rules = case["parameter_rules"]
+
+        # Setup model instance
+        model_instance = get_model_instance()
+        model_instance.invoke_llm.return_value = case["expected_llm_response"]
+
+        # Setup prompt messages
+        prompt_messages = [
+            SystemPromptMessage(content="You are a helpful assistant."),
+            UserPromptMessage(content="Generate a response according to the schema."),
+        ]
+
+        if case["should_raise"]:
+            # Test error cases
+            with pytest.raises(case["expected_error"]):  # noqa: PT012
+                if case["stream"]:
+                    result_generator = invoke_llm_with_structured_output(
+                        provider=case["provider"],
+                        model_schema=model_schema,
+                        model_instance=model_instance,
+                        prompt_messages=prompt_messages,
+                        json_schema=case["json_schema"],
+                        stream=case["stream"],
+                    )
+                    # Consume the generator to trigger the error
+                    list(result_generator)
+                else:
+                    invoke_llm_with_structured_output(
+                        provider=case["provider"],
+                        model_schema=model_schema,
+                        model_instance=model_instance,
+                        prompt_messages=prompt_messages,
+                        json_schema=case["json_schema"],
+                        stream=case["stream"],
+                    )
+        else:
+            # Test successful cases
+            with patch("core.llm_generator.output_parser.structured_output.json_repair.loads") as mock_json_repair:
+                # Configure json_repair mock for cases that need it
+                if case["name"] == "json_repair_scenario":
+                    mock_json_repair.return_value = {"name": "test"}
+
+                result = invoke_llm_with_structured_output(
+                    provider=case["provider"],
+                    model_schema=model_schema,
+                    model_instance=model_instance,
+                    prompt_messages=prompt_messages,
+                    json_schema=case["json_schema"],
+                    stream=case["stream"],
+                    model_parameters={"temperature": 0.7, "max_tokens": 100},
+                    user="test_user",
+                )
+
+                if case["expected_result_type"] == "generator":
+                    # Test streaming results
+                    assert hasattr(result, "__iter__")
+                    chunks = list(result)
+                    assert len(chunks) > 0
+
+                    # Verify all chunks are LLMResultChunkWithStructuredOutput
+                    for chunk in chunks[:-1]:  # All except last
+                        assert isinstance(chunk, LLMResultChunkWithStructuredOutput)
+                        assert chunk.model == case["model_name"]
+
+                    # Last chunk should have structured output
+                    last_chunk = chunks[-1]
+                    assert isinstance(last_chunk, LLMResultChunkWithStructuredOutput)
+                    assert last_chunk.structured_output is not None
+                    assert isinstance(last_chunk.structured_output, dict)
+                else:
+                    # Test non-streaming results
+                    assert isinstance(result, case["expected_result_type"])
+                    assert result.model == case["model_name"]
+                    assert result.structured_output is not None
+                    assert isinstance(result.structured_output, dict)
+
+                # Verify model_instance.invoke_llm was called with correct parameters
+                model_instance.invoke_llm.assert_called_once()
+                call_args = model_instance.invoke_llm.call_args
+
+                assert call_args.kwargs["stream"] == case["stream"]
+                assert call_args.kwargs["user"] == "test_user"
+                assert "temperature" in call_args.kwargs["model_parameters"]
+                assert "max_tokens" in call_args.kwargs["model_parameters"]
+
+
+def test_parse_structured_output_edge_cases():
+    """Test edge cases for structured output parsing"""
+
+    # Test case with list that contains dict (reasoning model scenario)
+    testcase_list_with_dict = {
+        "name": "list_with_dict_parsing",
+        "provider": "deepseek",
+        "model_name": "deepseek-r1",
+        "support_structure_output": False,
+        "stream": False,
+        "json_schema": {"type": "object", "properties": {"thought": {"type": "string"}}},
+        "expected_llm_response": LLMResult(
+            model="deepseek-r1",
+            message=AssistantPromptMessage(content='[{"thought": "reasoning process"}, "other content"]'),
+            usage=create_mock_usage(prompt_tokens=10, completion_tokens=5),
+        ),
+        "expected_result_type": LLMResultWithStructuredOutput,
+        "should_raise": False,
+    }
+
+    # Setup for list parsing test
+    model_schema = get_model_entity(
+        testcase_list_with_dict["provider"],
+        testcase_list_with_dict["model_name"],
+        testcase_list_with_dict["support_structure_output"],
+    )
+
+    model_instance = get_model_instance()
+    model_instance.invoke_llm.return_value = testcase_list_with_dict["expected_llm_response"]
+
+    prompt_messages = [UserPromptMessage(content="Test reasoning")]
+
+    with patch("core.llm_generator.output_parser.structured_output.json_repair.loads") as mock_json_repair:
+        # Mock json_repair to return a list with dict
+        mock_json_repair.return_value = [{"thought": "reasoning process"}, "other content"]
+
+        result = invoke_llm_with_structured_output(
+            provider=testcase_list_with_dict["provider"],
+            model_schema=model_schema,
+            model_instance=model_instance,
+            prompt_messages=prompt_messages,
+            json_schema=testcase_list_with_dict["json_schema"],
+            stream=testcase_list_with_dict["stream"],
+        )
+
+        assert isinstance(result, LLMResultWithStructuredOutput)
+        assert result.structured_output == {"thought": "reasoning process"}
+
+
+def test_model_specific_schema_preparation():
+    """Test schema preparation for different model types"""
+
+    # Test Gemini model
+    gemini_case = {
+        "provider": "google",
+        "model_name": "gemini-pro",
+        "support_structure_output": True,
+        "stream": False,
+        "json_schema": {"type": "object", "properties": {"result": {"type": "boolean"}}, "additionalProperties": False},
+    }
+
+    model_schema = get_model_entity(
+        gemini_case["provider"], gemini_case["model_name"], gemini_case["support_structure_output"]
+    )
+
+    model_instance = get_model_instance()
+    model_instance.invoke_llm.return_value = LLMResult(
+        model="gemini-pro",
+        message=AssistantPromptMessage(content='{"result": "true"}'),
+        usage=create_mock_usage(prompt_tokens=10, completion_tokens=5),
+    )
+
+    prompt_messages = [UserPromptMessage(content="Test")]
+
+    result = invoke_llm_with_structured_output(
+        provider=gemini_case["provider"],
+        model_schema=model_schema,
+        model_instance=model_instance,
+        prompt_messages=prompt_messages,
+        json_schema=gemini_case["json_schema"],
+        stream=gemini_case["stream"],
+    )
+
+    assert isinstance(result, LLMResultWithStructuredOutput)
+
+    # Verify model_instance.invoke_llm was called and check the schema preparation
+    model_instance.invoke_llm.assert_called_once()
+    call_args = model_instance.invoke_llm.call_args
+
+    # For Gemini, the schema should not have additionalProperties and boolean should be converted to string
+    assert "json_schema" in call_args.kwargs["model_parameters"]

api/uv.lock

@@ -350,6 +350,24 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/d0/ae/9a053dd9229c0fde6b1f1f33f609ccff1ee79ddda364c756a924c6d8563b/APScheduler-3.11.0-py3-none-any.whl", hash = "sha256:fc134ca32e50f5eadcc4938e3a4545ab19131435e851abb40b34d63d5141c6da", size = 64004, upload-time = "2024-11-24T19:39:24.442Z" },
 ]
 
+[[package]]
+name = "arize-phoenix-otel"
+version = "0.9.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "openinference-instrumentation" },
+    { name = "openinference-semantic-conventions" },
+    { name = "opentelemetry-exporter-otlp" },
+    { name = "opentelemetry-proto" },
+    { name = "opentelemetry-sdk" },
+    { name = "opentelemetry-semantic-conventions" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/27/b9/8c89191eb46915e9ba7bdb473e2fb1c510b7db3635ae5ede5e65b2176b9d/arize_phoenix_otel-0.9.2.tar.gz", hash = "sha256:a48c7d41f3ac60dc75b037f036bf3306d2af4af371cdb55e247e67957749bc31", size = 11599, upload-time = "2025-04-14T22:05:28.637Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/3a/3d/f64136a758c649e883315939f30fe51ad0747024b0db05fd78450801a78d/arize_phoenix_otel-0.9.2-py3-none-any.whl", hash = "sha256:5286b33c58b596ef8edd9a4255ee00fd74f774b1e5dbd9393e77e87870a14d76", size = 12560, upload-time = "2025-04-14T22:05:27.162Z" },
+]
+
 [[package]]
 name = "asgiref"
 version = "3.8.1"
@@ -391,16 +409,16 @@ wheels = [
 
 [[package]]
 name = "azure-core"
-version = "1.34.0"
+version = "1.35.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "requests" },
     { name = "six" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/c9/29/ff7a519a315e41c85bab92a7478c6acd1cf0b14353139a08caee4c691f77/azure_core-1.34.0.tar.gz", hash = "sha256:bdb544989f246a0ad1c85d72eeb45f2f835afdcbc5b45e43f0dbde7461c81ece", size = 297999, upload-time = "2025-05-01T23:17:27.59Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/ce/89/f53968635b1b2e53e4aad2dd641488929fef4ca9dfb0b97927fa7697ddf3/azure_core-1.35.0.tar.gz", hash = "sha256:c0be528489485e9ede59b6971eb63c1eaacf83ef53001bfe3904e475e972be5c", size = 339689, upload-time = "2025-07-03T00:55:23.496Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/84/9e/5c87b49f65bb16571599bc789857d0ded2f53014d3392bc88a5d1f3ad779/azure_core-1.34.0-py3-none-any.whl", hash = "sha256:0615d3b756beccdb6624d1c0ae97284f38b78fb59a2a9839bf927c66fbbdddd6", size = 207409, upload-time = "2025-05-01T23:17:29.818Z" },
+    { url = "https://files.pythonhosted.org/packages/d4/78/bf94897361fdd650850f0f2e405b2293e2f12808239046232bdedf554301/azure_core-1.35.0-py3-none-any.whl", hash = "sha256:8db78c72868a58f3de8991eb4d22c4d368fae226dac1002998d6c50437e7dad1", size = 210708, upload-time = "2025-07-03T00:55:25.238Z" },
 ]
 
 [[package]]
@@ -541,16 +559,16 @@ wheels = [
 
 [[package]]
 name = "boto3-stubs"
-version = "1.39.1"
+version = "1.39.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "botocore-stubs" },
     { name = "types-s3transfer" },
     { name = "typing-extensions", marker = "python_full_version < '3.12'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/ab/15/53ffddd602040a5d6ef2f39c3e6eda0f2b722dd60fef9088fa9723469d00/boto3_stubs-1.39.1.tar.gz", hash = "sha256:30afcb6d44f47cd0beb83bccce6f8b0161266baa2e0507075ae94d89f448cca6", size = 99951, upload-time = "2025-07-01T19:33:05.689Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/06/09/206a17938bfc7ec6e7c0b13ed58ad78146e46c29436d324ed55ceb5136ed/boto3_stubs-1.39.2.tar.gz", hash = "sha256:b1f1baef1658bd575a29ca85cc0877dbb3adeb376ffa8cbf242b876719ae0f95", size = 99939, upload-time = "2025-07-02T19:28:20.423Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/05/79/2c6839315f04e2e9ac7c072aa1b36d774d705acb31d07e8f4d8af27d8899/boto3_stubs-1.39.1-py3-none-any.whl", hash = "sha256:59229c5c938ffd3ac55d7c323ea6504b11478189f66ba46d49e6a74bf9babcd3", size = 69198, upload-time = "2025-07-01T19:32:56.849Z" },
+    { url = "https://files.pythonhosted.org/packages/39/be/9c65f2bfc6df27ec5f16d28c454e2e3cb9a7af3ef8588440658334325a85/boto3_stubs-1.39.2-py3-none-any.whl", hash = "sha256:ce98d96fe1a7177b05067be3cd933277c88f745de836752f9ef8b4286dbfa53b", size = 69196, upload-time = "2025-07-02T19:28:07.025Z" },
 ]
 
 [package.optional-dependencies]
@@ -1102,43 +1120,43 @@ sdist = { url = "https://files.pythonhosted.org/packages/6b/b0/e595ce2a2527e169c
 
 [[package]]
 name = "cryptography"
-version = "45.0.4"
+version = "45.0.5"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "cffi", marker = "platform_python_implementation != 'PyPy'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/fe/c8/a2a376a8711c1e11708b9c9972e0c3223f5fc682552c82d8db844393d6ce/cryptography-45.0.4.tar.gz", hash = "sha256:7405ade85c83c37682c8fe65554759800a4a8c54b2d96e0f8ad114d31b808d57", size = 744890, upload-time = "2025-06-10T00:03:51.297Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/95/1e/49527ac611af559665f71cbb8f92b332b5ec9c6fbc4e88b0f8e92f5e85df/cryptography-45.0.5.tar.gz", hash = "sha256:72e76caa004ab63accdf26023fccd1d087f6d90ec6048ff33ad0445abf7f605a", size = 744903, upload-time = "2025-07-02T13:06:25.941Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/cc/1c/92637793de053832523b410dbe016d3f5c11b41d0cf6eef8787aabb51d41/cryptography-45.0.4-cp311-abi3-macosx_10_9_universal2.whl", hash = "sha256:425a9a6ac2823ee6e46a76a21a4e8342d8fa5c01e08b823c1f19a8b74f096069", size = 7055712, upload-time = "2025-06-10T00:02:38.826Z" },
-    { url = "https://files.pythonhosted.org/packages/ba/14/93b69f2af9ba832ad6618a03f8a034a5851dc9a3314336a3d71c252467e1/cryptography-45.0.4-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:680806cf63baa0039b920f4976f5f31b10e772de42f16310a6839d9f21a26b0d", size = 4205335, upload-time = "2025-06-10T00:02:41.64Z" },
-    { url = "https://files.pythonhosted.org/packages/67/30/fae1000228634bf0b647fca80403db5ca9e3933b91dd060570689f0bd0f7/cryptography-45.0.4-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:4ca0f52170e821bc8da6fc0cc565b7bb8ff8d90d36b5e9fdd68e8a86bdf72036", size = 4431487, upload-time = "2025-06-10T00:02:43.696Z" },
-    { url = "https://files.pythonhosted.org/packages/6d/5a/7dffcf8cdf0cb3c2430de7404b327e3db64735747d641fc492539978caeb/cryptography-45.0.4-cp311-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:f3fe7a5ae34d5a414957cc7f457e2b92076e72938423ac64d215722f6cf49a9e", size = 4208922, upload-time = "2025-06-10T00:02:45.334Z" },
-    { url = "https://files.pythonhosted.org/packages/c6/f3/528729726eb6c3060fa3637253430547fbaaea95ab0535ea41baa4a6fbd8/cryptography-45.0.4-cp311-abi3-manylinux_2_28_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:25eb4d4d3e54595dc8adebc6bbd5623588991d86591a78c2548ffb64797341e2", size = 3900433, upload-time = "2025-06-10T00:02:47.359Z" },
-    { url = "https://files.pythonhosted.org/packages/d9/4a/67ba2e40f619e04d83c32f7e1d484c1538c0800a17c56a22ff07d092ccc1/cryptography-45.0.4-cp311-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:ce1678a2ccbe696cf3af15a75bb72ee008d7ff183c9228592ede9db467e64f1b", size = 4464163, upload-time = "2025-06-10T00:02:49.412Z" },
-    { url = "https://files.pythonhosted.org/packages/7e/9a/b4d5aa83661483ac372464809c4b49b5022dbfe36b12fe9e323ca8512420/cryptography-45.0.4-cp311-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:49fe9155ab32721b9122975e168a6760d8ce4cffe423bcd7ca269ba41b5dfac1", size = 4208687, upload-time = "2025-06-10T00:02:50.976Z" },
-    { url = "https://files.pythonhosted.org/packages/db/b7/a84bdcd19d9c02ec5807f2ec2d1456fd8451592c5ee353816c09250e3561/cryptography-45.0.4-cp311-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:2882338b2a6e0bd337052e8b9007ced85c637da19ef9ecaf437744495c8c2999", size = 4463623, upload-time = "2025-06-10T00:02:52.542Z" },
-    { url = "https://files.pythonhosted.org/packages/d8/84/69707d502d4d905021cac3fb59a316344e9f078b1da7fb43ecde5e10840a/cryptography-45.0.4-cp311-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:23b9c3ea30c3ed4db59e7b9619272e94891f8a3a5591d0b656a7582631ccf750", size = 4332447, upload-time = "2025-06-10T00:02:54.63Z" },
-    { url = "https://files.pythonhosted.org/packages/f3/ee/d4f2ab688e057e90ded24384e34838086a9b09963389a5ba6854b5876598/cryptography-45.0.4-cp311-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:b0a97c927497e3bc36b33987abb99bf17a9a175a19af38a892dc4bbb844d7ee2", size = 4572830, upload-time = "2025-06-10T00:02:56.689Z" },
-    { url = "https://files.pythonhosted.org/packages/70/d4/994773a261d7ff98034f72c0e8251fe2755eac45e2265db4c866c1c6829c/cryptography-45.0.4-cp311-abi3-win32.whl", hash = "sha256:e00a6c10a5c53979d6242f123c0a97cff9f3abed7f064fc412c36dc521b5f257", size = 2932769, upload-time = "2025-06-10T00:02:58.467Z" },
-    { url = "https://files.pythonhosted.org/packages/5a/42/c80bd0b67e9b769b364963b5252b17778a397cefdd36fa9aa4a5f34c599a/cryptography-45.0.4-cp311-abi3-win_amd64.whl", hash = "sha256:817ee05c6c9f7a69a16200f0c90ab26d23a87701e2a284bd15156783e46dbcc8", size = 3410441, upload-time = "2025-06-10T00:03:00.14Z" },
-    { url = "https://files.pythonhosted.org/packages/ce/0b/2488c89f3a30bc821c9d96eeacfcab6ff3accc08a9601ba03339c0fd05e5/cryptography-45.0.4-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:964bcc28d867e0f5491a564b7debb3ffdd8717928d315d12e0d7defa9e43b723", size = 7031836, upload-time = "2025-06-10T00:03:01.726Z" },
-    { url = "https://files.pythonhosted.org/packages/fe/51/8c584ed426093aac257462ae62d26ad61ef1cbf5b58d8b67e6e13c39960e/cryptography-45.0.4-cp37-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:6a5bf57554e80f75a7db3d4b1dacaa2764611ae166ab42ea9a72bcdb5d577637", size = 4195746, upload-time = "2025-06-10T00:03:03.94Z" },
-    { url = "https://files.pythonhosted.org/packages/5c/7d/4b0ca4d7af95a704eef2f8f80a8199ed236aaf185d55385ae1d1610c03c2/cryptography-45.0.4-cp37-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:46cf7088bf91bdc9b26f9c55636492c1cce3e7aaf8041bbf0243f5e5325cfb2d", size = 4424456, upload-time = "2025-06-10T00:03:05.589Z" },
-    { url = "https://files.pythonhosted.org/packages/1d/45/5fabacbc6e76ff056f84d9f60eeac18819badf0cefc1b6612ee03d4ab678/cryptography-45.0.4-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:7bedbe4cc930fa4b100fc845ea1ea5788fcd7ae9562e669989c11618ae8d76ee", size = 4198495, upload-time = "2025-06-10T00:03:09.172Z" },
-    { url = "https://files.pythonhosted.org/packages/55/b7/ffc9945b290eb0a5d4dab9b7636706e3b5b92f14ee5d9d4449409d010d54/cryptography-45.0.4-cp37-abi3-manylinux_2_28_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:eaa3e28ea2235b33220b949c5a0d6cf79baa80eab2eb5607ca8ab7525331b9ff", size = 3885540, upload-time = "2025-06-10T00:03:10.835Z" },
-    { url = "https://files.pythonhosted.org/packages/7f/e3/57b010282346980475e77d414080acdcb3dab9a0be63071efc2041a2c6bd/cryptography-45.0.4-cp37-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:7ef2dde4fa9408475038fc9aadfc1fb2676b174e68356359632e980c661ec8f6", size = 4452052, upload-time = "2025-06-10T00:03:12.448Z" },
-    { url = "https://files.pythonhosted.org/packages/37/e6/ddc4ac2558bf2ef517a358df26f45bc774a99bf4653e7ee34b5e749c03e3/cryptography-45.0.4-cp37-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:6a3511ae33f09094185d111160fd192c67aa0a2a8d19b54d36e4c78f651dc5ad", size = 4198024, upload-time = "2025-06-10T00:03:13.976Z" },
-    { url = "https://files.pythonhosted.org/packages/3a/c0/85fa358ddb063ec588aed4a6ea1df57dc3e3bc1712d87c8fa162d02a65fc/cryptography-45.0.4-cp37-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:06509dc70dd71fa56eaa138336244e2fbaf2ac164fc9b5e66828fccfd2b680d6", size = 4451442, upload-time = "2025-06-10T00:03:16.248Z" },
-    { url = "https://files.pythonhosted.org/packages/33/67/362d6ec1492596e73da24e669a7fbbaeb1c428d6bf49a29f7a12acffd5dc/cryptography-45.0.4-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:5f31e6b0a5a253f6aa49be67279be4a7e5a4ef259a9f33c69f7d1b1191939872", size = 4325038, upload-time = "2025-06-10T00:03:18.4Z" },
-    { url = "https://files.pythonhosted.org/packages/53/75/82a14bf047a96a1b13ebb47fb9811c4f73096cfa2e2b17c86879687f9027/cryptography-45.0.4-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:944e9ccf67a9594137f942d5b52c8d238b1b4e46c7a0c2891b7ae6e01e7c80a4", size = 4560964, upload-time = "2025-06-10T00:03:20.06Z" },
-    { url = "https://files.pythonhosted.org/packages/cd/37/1a3cba4c5a468ebf9b95523a5ef5651244693dc712001e276682c278fc00/cryptography-45.0.4-cp37-abi3-win32.whl", hash = "sha256:c22fe01e53dc65edd1945a2e6f0015e887f84ced233acecb64b4daadb32f5c97", size = 2924557, upload-time = "2025-06-10T00:03:22.563Z" },
-    { url = "https://files.pythonhosted.org/packages/2a/4b/3256759723b7e66380397d958ca07c59cfc3fb5c794fb5516758afd05d41/cryptography-45.0.4-cp37-abi3-win_amd64.whl", hash = "sha256:627ba1bc94f6adf0b0a2e35d87020285ead22d9f648c7e75bb64f367375f3b22", size = 3395508, upload-time = "2025-06-10T00:03:24.586Z" },
-    { url = "https://files.pythonhosted.org/packages/ea/ba/cf442ae99ef363855ed84b39e0fb3c106ac66b7a7703f3c9c9cfe05412cb/cryptography-45.0.4-pp311-pypy311_pp73-macosx_10_9_x86_64.whl", hash = "sha256:4828190fb6c4bcb6ebc6331f01fe66ae838bb3bd58e753b59d4b22eb444b996c", size = 3590512, upload-time = "2025-06-10T00:03:36.982Z" },
-    { url = "https://files.pythonhosted.org/packages/28/9a/a7d5bb87d149eb99a5abdc69a41e4e47b8001d767e5f403f78bfaafc7aa7/cryptography-45.0.4-pp311-pypy311_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:03dbff8411206713185b8cebe31bc5c0eb544799a50c09035733716b386e61a4", size = 4146899, upload-time = "2025-06-10T00:03:38.659Z" },
-    { url = "https://files.pythonhosted.org/packages/17/11/9361c2c71c42cc5c465cf294c8030e72fb0c87752bacbd7a3675245e3db3/cryptography-45.0.4-pp311-pypy311_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:51dfbd4d26172d31150d84c19bbe06c68ea4b7f11bbc7b3a5e146b367c311349", size = 4388900, upload-time = "2025-06-10T00:03:40.233Z" },
-    { url = "https://files.pythonhosted.org/packages/c0/76/f95b83359012ee0e670da3e41c164a0c256aeedd81886f878911581d852f/cryptography-45.0.4-pp311-pypy311_pp73-manylinux_2_34_aarch64.whl", hash = "sha256:0339a692de47084969500ee455e42c58e449461e0ec845a34a6a9b9bf7df7fb8", size = 4146422, upload-time = "2025-06-10T00:03:41.827Z" },
-    { url = "https://files.pythonhosted.org/packages/09/ad/5429fcc4def93e577a5407988f89cf15305e64920203d4ac14601a9dc876/cryptography-45.0.4-pp311-pypy311_pp73-manylinux_2_34_x86_64.whl", hash = "sha256:0cf13c77d710131d33e63626bd55ae7c0efb701ebdc2b3a7952b9b23a0412862", size = 4388475, upload-time = "2025-06-10T00:03:43.493Z" },
-    { url = "https://files.pythonhosted.org/packages/99/49/0ab9774f64555a1b50102757811508f5ace451cf5dc0a2d074a4b9deca6a/cryptography-45.0.4-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:bbc505d1dc469ac12a0a064214879eac6294038d6b24ae9f71faae1448a9608d", size = 3337594, upload-time = "2025-06-10T00:03:45.523Z" },
+    { url = "https://files.pythonhosted.org/packages/f0/fb/09e28bc0c46d2c547085e60897fea96310574c70fb21cd58a730a45f3403/cryptography-45.0.5-cp311-abi3-macosx_10_9_universal2.whl", hash = "sha256:101ee65078f6dd3e5a028d4f19c07ffa4dd22cce6a20eaa160f8b5219911e7d8", size = 7043092, upload-time = "2025-07-02T13:05:01.514Z" },
+    { url = "https://files.pythonhosted.org/packages/b1/05/2194432935e29b91fb649f6149c1a4f9e6d3d9fc880919f4ad1bcc22641e/cryptography-45.0.5-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:3a264aae5f7fbb089dbc01e0242d3b67dffe3e6292e1f5182122bdf58e65215d", size = 4205926, upload-time = "2025-07-02T13:05:04.741Z" },
+    { url = "https://files.pythonhosted.org/packages/07/8b/9ef5da82350175e32de245646b1884fc01124f53eb31164c77f95a08d682/cryptography-45.0.5-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e74d30ec9c7cb2f404af331d5b4099a9b322a8a6b25c4632755c8757345baac5", size = 4429235, upload-time = "2025-07-02T13:05:07.084Z" },
+    { url = "https://files.pythonhosted.org/packages/7c/e1/c809f398adde1994ee53438912192d92a1d0fc0f2d7582659d9ef4c28b0c/cryptography-45.0.5-cp311-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:3af26738f2db354aafe492fb3869e955b12b2ef2e16908c8b9cb928128d42c57", size = 4209785, upload-time = "2025-07-02T13:05:09.321Z" },
+    { url = "https://files.pythonhosted.org/packages/d0/8b/07eb6bd5acff58406c5e806eff34a124936f41a4fb52909ffa4d00815f8c/cryptography-45.0.5-cp311-abi3-manylinux_2_28_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:e6c00130ed423201c5bc5544c23359141660b07999ad82e34e7bb8f882bb78e0", size = 3893050, upload-time = "2025-07-02T13:05:11.069Z" },
+    { url = "https://files.pythonhosted.org/packages/ec/ef/3333295ed58d900a13c92806b67e62f27876845a9a908c939f040887cca9/cryptography-45.0.5-cp311-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:dd420e577921c8c2d31289536c386aaa30140b473835e97f83bc71ea9d2baf2d", size = 4457379, upload-time = "2025-07-02T13:05:13.32Z" },
+    { url = "https://files.pythonhosted.org/packages/d9/9d/44080674dee514dbb82b21d6fa5d1055368f208304e2ab1828d85c9de8f4/cryptography-45.0.5-cp311-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:d05a38884db2ba215218745f0781775806bde4f32e07b135348355fe8e4991d9", size = 4209355, upload-time = "2025-07-02T13:05:15.017Z" },
+    { url = "https://files.pythonhosted.org/packages/c9/d8/0749f7d39f53f8258e5c18a93131919ac465ee1f9dccaf1b3f420235e0b5/cryptography-45.0.5-cp311-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:ad0caded895a00261a5b4aa9af828baede54638754b51955a0ac75576b831b27", size = 4456087, upload-time = "2025-07-02T13:05:16.945Z" },
+    { url = "https://files.pythonhosted.org/packages/09/d7/92acac187387bf08902b0bf0699816f08553927bdd6ba3654da0010289b4/cryptography-45.0.5-cp311-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:9024beb59aca9d31d36fcdc1604dd9bbeed0a55bface9f1908df19178e2f116e", size = 4332873, upload-time = "2025-07-02T13:05:18.743Z" },
+    { url = "https://files.pythonhosted.org/packages/03/c2/840e0710da5106a7c3d4153c7215b2736151bba60bf4491bdb421df5056d/cryptography-45.0.5-cp311-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:91098f02ca81579c85f66df8a588c78f331ca19089763d733e34ad359f474174", size = 4564651, upload-time = "2025-07-02T13:05:21.382Z" },
+    { url = "https://files.pythonhosted.org/packages/2e/92/cc723dd6d71e9747a887b94eb3827825c6c24b9e6ce2bb33b847d31d5eaa/cryptography-45.0.5-cp311-abi3-win32.whl", hash = "sha256:926c3ea71a6043921050eaa639137e13dbe7b4ab25800932a8498364fc1abec9", size = 2929050, upload-time = "2025-07-02T13:05:23.39Z" },
+    { url = "https://files.pythonhosted.org/packages/1f/10/197da38a5911a48dd5389c043de4aec4b3c94cb836299b01253940788d78/cryptography-45.0.5-cp311-abi3-win_amd64.whl", hash = "sha256:b85980d1e345fe769cfc57c57db2b59cff5464ee0c045d52c0df087e926fbe63", size = 3403224, upload-time = "2025-07-02T13:05:25.202Z" },
+    { url = "https://files.pythonhosted.org/packages/fe/2b/160ce8c2765e7a481ce57d55eba1546148583e7b6f85514472b1d151711d/cryptography-45.0.5-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:f3562c2f23c612f2e4a6964a61d942f891d29ee320edb62ff48ffb99f3de9ae8", size = 7017143, upload-time = "2025-07-02T13:05:27.229Z" },
+    { url = "https://files.pythonhosted.org/packages/c2/e7/2187be2f871c0221a81f55ee3105d3cf3e273c0a0853651d7011eada0d7e/cryptography-45.0.5-cp37-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:3fcfbefc4a7f332dece7272a88e410f611e79458fab97b5efe14e54fe476f4fd", size = 4197780, upload-time = "2025-07-02T13:05:29.299Z" },
+    { url = "https://files.pythonhosted.org/packages/b9/cf/84210c447c06104e6be9122661159ad4ce7a8190011669afceeaea150524/cryptography-45.0.5-cp37-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:460f8c39ba66af7db0545a8c6f2eabcbc5a5528fc1cf6c3fa9a1e44cec33385e", size = 4420091, upload-time = "2025-07-02T13:05:31.221Z" },
+    { url = "https://files.pythonhosted.org/packages/3e/6a/cb8b5c8bb82fafffa23aeff8d3a39822593cee6e2f16c5ca5c2ecca344f7/cryptography-45.0.5-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:9b4cf6318915dccfe218e69bbec417fdd7c7185aa7aab139a2c0beb7468c89f0", size = 4198711, upload-time = "2025-07-02T13:05:33.062Z" },
+    { url = "https://files.pythonhosted.org/packages/04/f7/36d2d69df69c94cbb2473871926daf0f01ad8e00fe3986ac3c1e8c4ca4b3/cryptography-45.0.5-cp37-abi3-manylinux_2_28_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:2089cc8f70a6e454601525e5bf2779e665d7865af002a5dec8d14e561002e135", size = 3883299, upload-time = "2025-07-02T13:05:34.94Z" },
+    { url = "https://files.pythonhosted.org/packages/82/c7/f0ea40f016de72f81288e9fe8d1f6748036cb5ba6118774317a3ffc6022d/cryptography-45.0.5-cp37-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:0027d566d65a38497bc37e0dd7c2f8ceda73597d2ac9ba93810204f56f52ebc7", size = 4450558, upload-time = "2025-07-02T13:05:37.288Z" },
+    { url = "https://files.pythonhosted.org/packages/06/ae/94b504dc1a3cdf642d710407c62e86296f7da9e66f27ab12a1ee6fdf005b/cryptography-45.0.5-cp37-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:be97d3a19c16a9be00edf79dca949c8fa7eff621763666a145f9f9535a5d7f42", size = 4198020, upload-time = "2025-07-02T13:05:39.102Z" },
+    { url = "https://files.pythonhosted.org/packages/05/2b/aaf0adb845d5dabb43480f18f7ca72e94f92c280aa983ddbd0bcd6ecd037/cryptography-45.0.5-cp37-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:7760c1c2e1a7084153a0f68fab76e754083b126a47d0117c9ed15e69e2103492", size = 4449759, upload-time = "2025-07-02T13:05:41.398Z" },
+    { url = "https://files.pythonhosted.org/packages/91/e4/f17e02066de63e0100a3a01b56f8f1016973a1d67551beaf585157a86b3f/cryptography-45.0.5-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:6ff8728d8d890b3dda5765276d1bc6fb099252915a2cd3aff960c4c195745dd0", size = 4319991, upload-time = "2025-07-02T13:05:43.64Z" },
+    { url = "https://files.pythonhosted.org/packages/f2/2e/e2dbd629481b499b14516eed933f3276eb3239f7cee2dcfa4ee6b44d4711/cryptography-45.0.5-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:7259038202a47fdecee7e62e0fd0b0738b6daa335354396c6ddebdbe1206af2a", size = 4554189, upload-time = "2025-07-02T13:05:46.045Z" },
+    { url = "https://files.pythonhosted.org/packages/f8/ea/a78a0c38f4c8736287b71c2ea3799d173d5ce778c7d6e3c163a95a05ad2a/cryptography-45.0.5-cp37-abi3-win32.whl", hash = "sha256:1e1da5accc0c750056c556a93c3e9cb828970206c68867712ca5805e46dc806f", size = 2911769, upload-time = "2025-07-02T13:05:48.329Z" },
+    { url = "https://files.pythonhosted.org/packages/79/b3/28ac139109d9005ad3f6b6f8976ffede6706a6478e21c889ce36c840918e/cryptography-45.0.5-cp37-abi3-win_amd64.whl", hash = "sha256:90cb0a7bb35959f37e23303b7eed0a32280510030daba3f7fdfbb65defde6a97", size = 3390016, upload-time = "2025-07-02T13:05:50.811Z" },
+    { url = "https://files.pythonhosted.org/packages/c0/71/9bdbcfd58d6ff5084687fe722c58ac718ebedbc98b9f8f93781354e6d286/cryptography-45.0.5-pp311-pypy311_pp73-macosx_10_9_x86_64.whl", hash = "sha256:8c4a6ff8a30e9e3d38ac0539e9a9e02540ab3f827a3394f8852432f6b0ea152e", size = 3587878, upload-time = "2025-07-02T13:06:06.339Z" },
+    { url = "https://files.pythonhosted.org/packages/f0/63/83516cfb87f4a8756eaa4203f93b283fda23d210fc14e1e594bd5f20edb6/cryptography-45.0.5-pp311-pypy311_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:bd4c45986472694e5121084c6ebbd112aa919a25e783b87eb95953c9573906d6", size = 4152447, upload-time = "2025-07-02T13:06:08.345Z" },
+    { url = "https://files.pythonhosted.org/packages/22/11/d2823d2a5a0bd5802b3565437add16f5c8ce1f0778bf3822f89ad2740a38/cryptography-45.0.5-pp311-pypy311_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:982518cd64c54fcada9d7e5cf28eabd3ee76bd03ab18e08a48cad7e8b6f31b18", size = 4386778, upload-time = "2025-07-02T13:06:10.263Z" },
+    { url = "https://files.pythonhosted.org/packages/5f/38/6bf177ca6bce4fe14704ab3e93627c5b0ca05242261a2e43ef3168472540/cryptography-45.0.5-pp311-pypy311_pp73-manylinux_2_34_aarch64.whl", hash = "sha256:12e55281d993a793b0e883066f590c1ae1e802e3acb67f8b442e721e475e6463", size = 4151627, upload-time = "2025-07-02T13:06:13.097Z" },
+    { url = "https://files.pythonhosted.org/packages/38/6a/69fc67e5266bff68a91bcb81dff8fb0aba4d79a78521a08812048913e16f/cryptography-45.0.5-pp311-pypy311_pp73-manylinux_2_34_x86_64.whl", hash = "sha256:5aa1e32983d4443e310f726ee4b071ab7569f58eedfdd65e9675484a4eb67bd1", size = 4385593, upload-time = "2025-07-02T13:06:15.689Z" },
+    { url = "https://files.pythonhosted.org/packages/f6/34/31a1604c9a9ade0fdab61eb48570e09a796f4d9836121266447b0eaf7feb/cryptography-45.0.5-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:e357286c1b76403dd384d938f93c46b2b058ed4dfcdce64a770f0537ed3feb6f", size = 3331106, upload-time = "2025-07-02T13:06:18.058Z" },
 ]
 
 [[package]]
@@ -1201,6 +1219,7 @@ name = "dify-api"
 version = "1.5.1"
 source = { virtual = "." }
 dependencies = [
+    { name = "arize-phoenix-otel" },
     { name = "authlib" },
     { name = "azure-identity" },
     { name = "beautifulsoup4" },
@@ -1382,6 +1401,7 @@ vdb = [
 
 [package.metadata]
 requires-dist = [
+    { name = "arize-phoenix-otel", specifier = "~=0.9.2" },
     { name = "authlib", specifier = "==1.3.1" },
     { name = "azure-identity", specifier = "==1.16.1" },
     { name = "beautifulsoup4", specifier = "==4.12.2" },
@@ -2527,7 +2547,7 @@ wheels = [
 
 [[package]]
 name = "huggingface-hub"
-version = "0.33.1"
+version = "0.33.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "filelock" },
@@ -2539,9 +2559,9 @@ dependencies = [
     { name = "tqdm" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/a4/01/bfe0534a63ce7a2285e90dbb33e8a5b815ff096d8f7743b135c256916589/huggingface_hub-0.33.1.tar.gz", hash = "sha256:589b634f979da3ea4b8bdb3d79f97f547840dc83715918daf0b64209c0844c7b", size = 426728, upload-time = "2025-06-25T12:02:57.605Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/fa/42/8a95c5632080ae312c0498744b2b852195e10b05a20b1be11c5141092f4c/huggingface_hub-0.33.2.tar.gz", hash = "sha256:84221defaec8fa09c090390cd68c78b88e3c4c2b7befba68d3dc5aacbc3c2c5f", size = 426637, upload-time = "2025-07-02T06:26:05.156Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/d0/fb/5307bd3612eb0f0e62c3a916ae531d3a31e58fb5c82b58e3ebf7fd6f47a1/huggingface_hub-0.33.1-py3-none-any.whl", hash = "sha256:ec8d7444628210c0ba27e968e3c4c973032d44dcea59ca0d78ef3f612196f095", size = 515377, upload-time = "2025-06-25T12:02:55.611Z" },
+    { url = "https://files.pythonhosted.org/packages/44/f4/5f3f22e762ad1965f01122b42dae5bf0e009286e2dba601ce1d0dba72424/huggingface_hub-0.33.2-py3-none-any.whl", hash = "sha256:3749498bfa91e8cde2ddc2c1db92c79981f40e66434c20133b39e5928ac9bcc5", size = 515373, upload-time = "2025-07-02T06:26:03.072Z" },
 ]
 
 [[package]]
@@ -2567,15 +2587,15 @@ wheels = [
 
 [[package]]
 name = "hypothesis"
-version = "6.135.20"
+version = "6.135.24"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "attrs" },
     { name = "sortedcontainers" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/37/8d/4cbc0c3185c994d010c4b051dda221900412e9fa50424f49aaecbb61df72/hypothesis-6.135.20.tar.gz", hash = "sha256:cef91cf893337b90a4df427ff77674f38bb5bc6c5e1e3d3db1764faee77df7a5", size = 452856, upload-time = "2025-06-30T19:51:10.117Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/cf/ae/f846b67ce9fc80cf51cece6b7adaa3fe2de4251242d142e241ce5d4aa26f/hypothesis-6.135.24.tar.gz", hash = "sha256:e301aeb2691ec0a1f62bfc405eaa966055d603e328cd854c1ed59e1728e35ab6", size = 454011, upload-time = "2025-07-03T02:46:51.776Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/88/78/d920c93db6cff52afaf3bc2a4a32863861ddcbae614a264a6776c190a4ec/hypothesis-6.135.20-py3-none-any.whl", hash = "sha256:77c21f888c458ddcab23708c240c5d1fa9e20f4b52f7c136c9d0e9a79c5c1337", size = 519582, upload-time = "2025-06-30T19:51:06.283Z" },
+    { url = "https://files.pythonhosted.org/packages/ed/cb/c38acf27826a96712302229622f32dd356b9c4fbe52a3e9f615706027af8/hypothesis-6.135.24-py3-none-any.whl", hash = "sha256:88ed21fbfa481ca9851a9080841b3caca14cd4ed51a165dfae8006325775ee72", size = 520920, upload-time = "2025-07-03T02:46:48.286Z" },
 ]
 
 [[package]]
@@ -3414,6 +3434,29 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/74/83/cc7c6de29b0a7585cd445258d174ca204d37729c3874ad08e515b0bf331c/opendal-0.45.20-cp311-abi3-win_amd64.whl", hash = "sha256:145efd56aa33b493d5b652c3e4f5ae5097ab69d38c132d80f108e9f5c1e4d863", size = 14929888, upload-time = "2025-05-26T07:01:46.929Z" },
 ]
 
+[[package]]
+name = "openinference-instrumentation"
+version = "0.1.34"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "openinference-semantic-conventions" },
+    { name = "opentelemetry-api" },
+    { name = "opentelemetry-sdk" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/2e/18/d074b45b04ba69bd03260d2dc0a034e5d586d8854e957695f40569278136/openinference_instrumentation-0.1.34.tar.gz", hash = "sha256:fa0328e8b92fc3e22e150c46f108794946ce39fe13670aed15f23ba0105f72ab", size = 22373, upload-time = "2025-06-17T16:47:22.641Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c1/ad/1a0a5c0a755918269f71fbca225fd70759dd79dd5bffc4723e44f0d87240/openinference_instrumentation-0.1.34-py3-none-any.whl", hash = "sha256:0fff1cc6d9b86f3450fc1c88347c51c5467855992b75e7addb85bf09fd048d2d", size = 28137, upload-time = "2025-06-17T16:47:21.658Z" },
+]
+
+[[package]]
+name = "openinference-semantic-conventions"
+version = "0.1.21"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/75/0f/b794eb009846d4b10af50e205a323ca359f284563ef4d1778f35a80522ac/openinference_semantic_conventions-0.1.21.tar.gz", hash = "sha256:328405b9f79ff72a659c7712b8429c0d7ea68c6a4a1679e3eb44372aa228119b", size = 12534, upload-time = "2025-06-13T05:22:18.982Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/6e/4d/092766f8e610f2c513e483c4adc892eea1634945022a73371fe01f621165/openinference_semantic_conventions-0.1.21-py3-none-any.whl", hash = "sha256:acde8282c20da1de900cdc0d6258a793ec3eb8031bfc496bd823dae17d32e326", size = 10167, upload-time = "2025-06-13T05:22:18.118Z" },
+]
+
 [[package]]
 name = "openpyxl"
 version = "3.1.5"
@@ -3702,7 +3745,7 @@ wheels = [
 
 [[package]]
 name = "opik"
-version = "1.7.40"
+version = "1.7.41"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "boto3-stubs", extra = ["bedrock-runtime"] },
@@ -3721,9 +3764,9 @@ dependencies = [
     { name = "tqdm" },
     { name = "uuid6" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/04/1b/894bf9e938724eeb0ff07a7d74f9d245273e7ef140b846df515c19428fc2/opik-1.7.40.tar.gz", hash = "sha256:9e744885fcb3ee11cc49c1cb494a59f788636d403efd5a36a3c44d252ab136a5", size = 320003, upload-time = "2025-06-30T10:26:21.357Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/82/81/6cddb705b3f416cfe4f0507916f51d0886087695f9dab49cfc6b00eb0266/opik-1.7.41.tar.gz", hash = "sha256:6ce2f72c7d23a62e2c13d419ce50754f6e17234825dcf26506e7def34dd38e26", size = 323333, upload-time = "2025-07-02T12:35:31.76Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/27/dc/1fec00af7e138468276898b4537c1f8abc4fabc733922993824b1e3dd047/opik-1.7.40-py3-none-any.whl", hash = "sha256:a1e9ed831e241f6158fccbdba1de25d1b2215031066f73fb7c9aed1f0d47c57a", size = 600604, upload-time = "2025-06-30T10:26:19.749Z" },
+    { url = "https://files.pythonhosted.org/packages/e9/46/ee27d06cc2049619806c992bdaa10e25b93d19ecedbc5c0fa772d8ac9a6d/opik-1.7.41-py3-none-any.whl", hash = "sha256:99df9c7b7b504777a51300b27a72bc646903201629611082b9b1f3c3adfbb3bf", size = 614890, upload-time = "2025-07-02T12:35:29.562Z" },
 ]
 
 [[package]]
@@ -4035,7 +4078,7 @@ wheels = [
 
 [[package]]
 name = "posthog"
-version = "6.0.1"
+version = "6.0.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "backoff" },
@@ -4045,9 +4088,9 @@ dependencies = [
     { name = "six" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/86/0f/442860ec60985705b4ca5465274284e6bd1916eda535586198fe0a7edb77/posthog-6.0.1.tar.gz", hash = "sha256:c0f28bfc0f1dc8d4b47aa2bed670343273fa1d69f1e775313d78eec3cb169daa", size = 88108, upload-time = "2025-07-01T12:27:23.935Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/d9/10/37ea988b3ae73cbfd1f2d5e523cca31cecfcc40cbd0de6511f40462fdb78/posthog-6.0.2.tar.gz", hash = "sha256:94a28e65d7a2d1b2952e53a1b97fa4d6504b8d7e4c197c57f653621e55b549eb", size = 88141, upload-time = "2025-07-02T19:21:50.306Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/0f/09/4f3dc1c5f330f76da0cc5c85d7eb42aa5da9d9d1d22f1385d95466cec7da/posthog-6.0.1-py3-none-any.whl", hash = "sha256:fab081cba269b743cfdc995692f97d71ef3e952c414188415158f5a5c37b1848", size = 104956, upload-time = "2025-07-01T12:27:21.48Z" },
+    { url = "https://files.pythonhosted.org/packages/85/2c/0c5dbbf9bc30401ae2a1b6b52b8abc19e4060cf28c3288ae9d962e65e3ad/posthog-6.0.2-py3-none-any.whl", hash = "sha256:756cc9adad9e42961454f8ac391b92a2f70ebb6607d29b0c568de08e5d8f1b18", size = 104946, upload-time = "2025-07-02T19:21:48.77Z" },
 ]
 
 [[package]]
@@ -4363,7 +4406,7 @@ crypto = [
 
 [[package]]
 name = "pymilvus"
-version = "2.5.11"
+version = "2.5.12"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "grpcio" },
@@ -4374,9 +4417,9 @@ dependencies = [
     { name = "setuptools" },
     { name = "ujson" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/e4/d9/3a76b1f5014a20efcfe1bb0aa46423d9cf1df5ab2ce8b1479248b943692a/pymilvus-2.5.11.tar.gz", hash = "sha256:cb1c291c659da73c58f2f5c2bd5bcbb87feb76f720afd72b9e7ace813d384c83", size = 1262466, upload-time = "2025-06-10T00:41:54.295Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/fa/53/4af820a37163225a76656222ee43a0eb8f1bd2ceec063315680a585435da/pymilvus-2.5.12.tar.gz", hash = "sha256:79ec7dc0616c2484f77abe98bca8deafb613645b5703c492b51961afd4f985d8", size = 1265893, upload-time = "2025-07-02T15:34:00.385Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/e7/2c/a9f2c2daff511e127616a4294e597bf4c7626d49865f62865432698c7ba9/pymilvus-2.5.11-py3-none-any.whl", hash = "sha256:20417ea0f364cd8e9d3783b432ad25c32cff8f3ceb40cdfdf54f8bbcf052cd7e", size = 228115, upload-time = "2025-06-10T00:41:52.354Z" },
+    { url = "https://files.pythonhosted.org/packages/68/4f/80a4940f2772d10272c3292444af767a5aa1a5bbb631874568713ca01d54/pymilvus-2.5.12-py3-none-any.whl", hash = "sha256:ef77a4a0076469a30b05f0bb23b5a058acfbdca83d82af9574ca651764017f44", size = 231425, upload-time = "2025-07-02T15:33:58.938Z" },
 ]
 
 [[package]]