fix: list multiple @mentions

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: 非法操作 <[email protected]>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

.agent/skills

@@ -0,0 +1 @@
+../.claude/skills

.claude/skills/orpc-contract-first/SKILL.md

@@ -0,0 +1,46 @@
+---
+name: orpc-contract-first
+description: Guide for implementing oRPC contract-first API patterns in Dify frontend. Triggers when creating new API contracts, adding service endpoints, integrating TanStack Query with typed contracts, or migrating legacy service calls to oRPC. Use for all API layer work in web/contract and web/service directories.
+---
+
+# oRPC Contract-First Development
+
+## Project Structure
+
+```
+web/contract/
+├── base.ts           # Base contract (inputStructure: 'detailed')
+├── router.ts         # Router composition & type exports
+├── marketplace.ts    # Marketplace contracts
+└── console/          # Console contracts by domain
+    ├── system.ts
+    └── billing.ts
+```
+
+## Workflow
+
+1. **Create contract** in `web/contract/console/{domain}.ts`
+   - Import `base` from `../base` and `type` from `@orpc/contract`
+   - Define route with `path`, `method`, `input`, `output`
+
+2. **Register in router** at `web/contract/router.ts`
+   - Import directly from domain file (no barrel files)
+   - Nest by API prefix: `billing: { invoices, bindPartnerStack }`
+
+3. **Create hooks** in `web/service/use-{domain}.ts`
+   - Use `consoleQuery.{group}.{contract}.queryKey()` for query keys
+   - Use `consoleClient.{group}.{contract}()` for API calls
+
+## Key Rules
+
+- **Input structure**: Always use `{ params, query?, body? }` format
+- **Path params**: Use `{paramName}` in path, match in `params` object
+- **Router nesting**: Group by API prefix (e.g., `/billing/*` → `billing: {}`)
+- **No barrel files**: Import directly from specific files
+- **Types**: Import from `@/types/`, use `type<T>()` helper
+
+## Type Export
+
+```typescript
+export type ConsoleInputs = InferContractRouterInputs<typeof consoleRouterContract>
+```

.github/workflows/style.yml

@@ -90,7 +90,7 @@ jobs:
         uses: actions/setup-node@v6
         if: steps.changed-files.outputs.any_changed == 'true'
         with:
-          node-version: 22
+          node-version: 24
           cache: pnpm
           cache-dependency-path: ./web/pnpm-lock.yaml
 

.github/workflows/tool-test-sdks.yaml

@@ -16,10 +16,6 @@ jobs:
     name: unit test for Node.js SDK
     runs-on: ubuntu-latest
 
-    strategy:
-      matrix:
-        node-version: [16, 18, 20, 22]
-
     defaults:
       run:
         working-directory: sdks/nodejs-client
@@ -29,10 +25,10 @@ jobs:
         with:
           persist-credentials: false
 
-      - name: Use Node.js ${{ matrix.node-version }}
+      - name: Use Node.js
         uses: actions/setup-node@v6
         with:
-          node-version: ${{ matrix.node-version }}
+          node-version: 24
           cache: ''
           cache-dependency-path: 'pnpm-lock.yaml'
 

.github/workflows/translate-i18n-claude.yml

@@ -57,7 +57,7 @@ jobs:
       - name: Set up Node.js
         uses: actions/setup-node@v6
         with:
-          node-version: 'lts/*'
+          node-version: 24
           cache: pnpm
           cache-dependency-path: ./web/pnpm-lock.yaml
 

.github/workflows/web-tests.yml

@@ -31,7 +31,7 @@ jobs:
       - name: Setup Node.js
         uses: actions/setup-node@v6
         with:
-          node-version: 22
+          node-version: 24
           cache: pnpm
           cache-dependency-path: ./web/pnpm-lock.yaml
 

.gitignore

@@ -209,6 +209,7 @@ api/.vscode
 .history
 
 .idea/
+web/migration/
 
 # pnpm
 /.pnpm-store

api/.env.example

@@ -417,6 +417,8 @@ SMTP_USERNAME=123
 SMTP_PASSWORD=abc
 SMTP_USE_TLS=true
 SMTP_OPPORTUNISTIC_TLS=false
+# Optional: override the local hostname used for SMTP HELO/EHLO
+SMTP_LOCAL_HOSTNAME=
 # Sendgid configuration
 SENDGRID_API_KEY=
 # Sentry configuration
@@ -713,3 +715,4 @@ ANNOTATION_IMPORT_MAX_CONCURRENT=5
 SANDBOX_EXPIRED_RECORDS_CLEAN_GRACEFUL_PERIOD=21
 SANDBOX_EXPIRED_RECORDS_CLEAN_BATCH_SIZE=1000
 SANDBOX_EXPIRED_RECORDS_RETENTION_DAYS=30
+

api/commands.py

@@ -3,6 +3,7 @@ import datetime
 import json
 import logging
 import secrets
+import time
 from typing import Any
 
 import click
@@ -46,6 +47,8 @@ from services.clear_free_plan_tenant_expired_logs import ClearFreePlanTenantExpi
 from services.plugin.data_migration import PluginDataMigration
 from services.plugin.plugin_migration import PluginMigration
 from services.plugin.plugin_service import PluginService
+from services.retention.conversation.messages_clean_policy import create_message_clean_policy
+from services.retention.conversation.messages_clean_service import MessagesCleanService
 from services.retention.workflow_run.clear_free_plan_expired_workflow_run_logs import WorkflowRunCleanup
 from tasks.remove_app_and_related_data_task import delete_draft_variables_batch
 
@@ -2172,3 +2175,79 @@ def migrate_oss(
             except Exception as e:
                 db.session.rollback()
                 click.echo(click.style(f"Failed to update DB storage_type: {str(e)}", fg="red"))
+
+
+@click.command("clean-expired-messages", help="Clean expired messages.")
+@click.option(
+    "--start-from",
+    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
+    required=True,
+    help="Lower bound (inclusive) for created_at.",
+)
+@click.option(
+    "--end-before",
+    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
+    required=True,
+    help="Upper bound (exclusive) for created_at.",
+)
+@click.option("--batch-size", default=1000, show_default=True, help="Batch size for selecting messages.")
+@click.option(
+    "--graceful-period",
+    default=21,
+    show_default=True,
+    help="Graceful period in days after subscription expiration, will be ignored when billing is disabled.",
+)
+@click.option("--dry-run", is_flag=True, default=False, help="Show messages logs would be cleaned without deleting")
+def clean_expired_messages(
+    batch_size: int,
+    graceful_period: int,
+    start_from: datetime.datetime,
+    end_before: datetime.datetime,
+    dry_run: bool,
+):
+    """
+    Clean expired messages and related data for tenants based on clean policy.
+    """
+    click.echo(click.style("clean_messages: start clean messages.", fg="green"))
+
+    start_at = time.perf_counter()
+
+    try:
+        # Create policy based on billing configuration
+        # NOTE: graceful_period will be ignored when billing is disabled.
+        policy = create_message_clean_policy(graceful_period_days=graceful_period)
+
+        # Create and run the cleanup service
+        service = MessagesCleanService.from_time_range(
+            policy=policy,
+            start_from=start_from,
+            end_before=end_before,
+            batch_size=batch_size,
+            dry_run=dry_run,
+        )
+        stats = service.run()
+
+        end_at = time.perf_counter()
+        click.echo(
+            click.style(
+                f"clean_messages: completed successfully\n"
+                f"  - Latency: {end_at - start_at:.2f}s\n"
+                f"  - Batches processed: {stats['batches']}\n"
+                f"  - Total messages scanned: {stats['total_messages']}\n"
+                f"  - Messages filtered: {stats['filtered_messages']}\n"
+                f"  - Messages deleted: {stats['total_deleted']}",
+                fg="green",
+            )
+        )
+    except Exception as e:
+        end_at = time.perf_counter()
+        logger.exception("clean_messages failed")
+        click.echo(
+            click.style(
+                f"clean_messages: failed after {end_at - start_at:.2f}s - {str(e)}",
+                fg="red",
+            )
+        )
+        raise
+
+    click.echo(click.style("messages cleanup completed.", fg="green"))

api/configs/feature/__init__.py

@@ -949,6 +949,12 @@ class MailConfig(BaseSettings):
         default=False,
     )
 
+    SMTP_LOCAL_HOSTNAME: str | None = Field(
+        description="Override the local hostname used in SMTP HELO/EHLO. "
+        "Useful behind NAT or when the default hostname causes rejections.",
+        default=None,
+    )
+
     EMAIL_SEND_IP_LIMIT_PER_MINUTE: PositiveInt = Field(
         description="Maximum number of emails allowed to be sent from the same IP address in a minute",
         default=50,

api/controllers/console/app/conversation.py

@@ -592,9 +592,12 @@ def _get_conversation(app_model, conversation_id):
     if not conversation:
         raise NotFound("Conversation Not Exists.")
 
-    if not conversation.read_at:
-        conversation.read_at = naive_utc_now()
-        conversation.read_account_id = current_user.id
-        db.session.commit()
+    db.session.execute(
+        sa.update(Conversation)
+        .where(Conversation.id == conversation_id, Conversation.read_at.is_(None))
+        .values(read_at=naive_utc_now(), read_account_id=current_user.id)
+    )
+    db.session.commit()
+    db.session.refresh(conversation)
 
     return conversation

api/controllers/console/app/generator.py

@@ -55,6 +55,35 @@ class InstructionTemplatePayload(BaseModel):
     type: str = Field(..., description="Instruction template type")
 
 
+class ContextGeneratePayload(BaseModel):
+    """Payload for generating extractor code node."""
+
+    workflow_id: str = Field(..., description="Workflow ID")
+    node_id: str = Field(..., description="Current tool/llm node ID")
+    parameter_name: str = Field(..., description="Parameter name to generate code for")
+    language: str = Field(default="python3", description="Code language (python3/javascript)")
+    prompt_messages: list[dict[str, Any]] = Field(
+        ..., description="Multi-turn conversation history, last message is the current instruction"
+    )
+    model_config_data: dict[str, Any] = Field(..., alias="model_config", description="Model configuration")
+
+
+class SuggestedQuestionsPayload(BaseModel):
+    """Payload for generating suggested questions."""
+
+    workflow_id: str = Field(..., description="Workflow ID")
+    node_id: str = Field(..., description="Current tool/llm node ID")
+    parameter_name: str = Field(..., description="Parameter name")
+    language: str = Field(
+        default="English", description="Language for generated questions (e.g. English, Chinese, Japanese)"
+    )
+    model_config_data: dict[str, Any] | None = Field(
+        default=None,
+        alias="model_config",
+        description="Model configuration (optional, uses system default if not provided)",
+    )
+
+
 def reg(cls: type[BaseModel]):
     console_ns.schema_model(cls.__name__, cls.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0))
 
@@ -64,6 +93,8 @@ reg(RuleCodeGeneratePayload)
 reg(RuleStructuredOutputPayload)
 reg(InstructionGeneratePayload)
 reg(InstructionTemplatePayload)
+reg(ContextGeneratePayload)
+reg(SuggestedQuestionsPayload)
 
 
 @console_ns.route("/rule-generate")
@@ -278,3 +309,74 @@ class InstructionGenerationTemplateApi(Resource):
                 return {"data": INSTRUCTION_GENERATE_TEMPLATE_CODE}
             case _:
                 raise ValueError(f"Invalid type: {args.type}")
+
+
+@console_ns.route("/context-generate")
+class ContextGenerateApi(Resource):
+    @console_ns.doc("generate_with_context")
+    @console_ns.doc(description="Generate with multi-turn conversation context")
+    @console_ns.expect(console_ns.models[ContextGeneratePayload.__name__])
+    @console_ns.response(200, "Content generated successfully")
+    @console_ns.response(400, "Invalid request parameters or workflow not found")
+    @console_ns.response(402, "Provider quota exceeded")
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        from core.llm_generator.utils import deserialize_prompt_messages
+
+        args = ContextGeneratePayload.model_validate(console_ns.payload)
+        _, current_tenant_id = current_account_with_tenant()
+
+        prompt_messages = deserialize_prompt_messages(args.prompt_messages)
+
+        try:
+            return LLMGenerator.generate_with_context(
+                tenant_id=current_tenant_id,
+                workflow_id=args.workflow_id,
+                node_id=args.node_id,
+                parameter_name=args.parameter_name,
+                language=args.language,
+                prompt_messages=prompt_messages,
+                model_config=args.model_config_data,
+            )
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        except QuotaExceededError:
+            raise ProviderQuotaExceededError()
+        except ModelCurrentlyNotSupportError:
+            raise ProviderModelCurrentlyNotSupportError()
+        except InvokeError as e:
+            raise CompletionRequestError(e.description)
+
+
+@console_ns.route("/context-generate/suggested-questions")
+class SuggestedQuestionsApi(Resource):
+    @console_ns.doc("generate_suggested_questions")
+    @console_ns.doc(description="Generate suggested questions for context generation")
+    @console_ns.expect(console_ns.models[SuggestedQuestionsPayload.__name__])
+    @console_ns.response(200, "Questions generated successfully")
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        args = SuggestedQuestionsPayload.model_validate(console_ns.payload)
+        _, current_tenant_id = current_account_with_tenant()
+
+        try:
+            return LLMGenerator.generate_suggested_questions(
+                tenant_id=current_tenant_id,
+                workflow_id=args.workflow_id,
+                node_id=args.node_id,
+                parameter_name=args.parameter_name,
+                language=args.language,
+                model_config=args.model_config_data,
+            )
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        except QuotaExceededError:
+            raise ProviderQuotaExceededError()
+        except ModelCurrentlyNotSupportError:
+            raise ProviderModelCurrentlyNotSupportError()
+        except InvokeError as e:
+            raise CompletionRequestError(e.description)

api/controllers/console/datasets/external.py

@@ -81,7 +81,7 @@ class ExternalKnowledgeApiPayload(BaseModel):
 class ExternalDatasetCreatePayload(BaseModel):
     external_knowledge_api_id: str
     external_knowledge_id: str
-    name: str = Field(..., min_length=1, max_length=40)
+    name: str = Field(..., min_length=1, max_length=100)
     description: str | None = Field(None, max_length=400)
     external_retrieval_model: dict[str, object] | None = None
 

api/core/app/apps/advanced_chat/generate_response_converter.py

@@ -82,7 +82,7 @@ class AdvancedChatAppGenerateResponseConverter(AppGenerateResponseConverter):
                 data = cls._error_to_stream_response(sub_stream_response.err)
                 response_chunk.update(data)
             else:
-                response_chunk.update(sub_stream_response.model_dump(mode="json"))
+                response_chunk.update(sub_stream_response.model_dump(mode="json", exclude_none=True))
             yield response_chunk
 
     @classmethod
@@ -110,7 +110,7 @@ class AdvancedChatAppGenerateResponseConverter(AppGenerateResponseConverter):
             }
 
             if isinstance(sub_stream_response, MessageEndStreamResponse):
-                sub_stream_response_dict = sub_stream_response.model_dump(mode="json")
+                sub_stream_response_dict = sub_stream_response.model_dump(mode="json", exclude_none=True)
                 metadata = sub_stream_response_dict.get("metadata", {})
                 sub_stream_response_dict["metadata"] = cls._get_simple_metadata(metadata)
                 response_chunk.update(sub_stream_response_dict)
@@ -120,6 +120,6 @@ class AdvancedChatAppGenerateResponseConverter(AppGenerateResponseConverter):
             elif isinstance(sub_stream_response, NodeStartStreamResponse | NodeFinishStreamResponse):
                 response_chunk.update(sub_stream_response.to_ignore_detail_dict())
             else:
-                response_chunk.update(sub_stream_response.model_dump(mode="json"))
+                response_chunk.update(sub_stream_response.model_dump(mode="json", exclude_none=True))
 
             yield response_chunk

api/core/app/apps/agent_chat/generate_response_converter.py

@@ -81,7 +81,7 @@ class AgentChatAppGenerateResponseConverter(AppGenerateResponseConverter):
                 data = cls._error_to_stream_response(sub_stream_response.err)
                 response_chunk.update(data)
             else:
-                response_chunk.update(sub_stream_response.model_dump(mode="json"))
+                response_chunk.update(sub_stream_response.model_dump(mode="json", exclude_none=True))
             yield response_chunk
 
     @classmethod
@@ -109,7 +109,7 @@ class AgentChatAppGenerateResponseConverter(AppGenerateResponseConverter):
             }
 
             if isinstance(sub_stream_response, MessageEndStreamResponse):
-                sub_stream_response_dict = sub_stream_response.model_dump(mode="json")
+                sub_stream_response_dict = sub_stream_response.model_dump(mode="json", exclude_none=True)
                 metadata = sub_stream_response_dict.get("metadata", {})
                 sub_stream_response_dict["metadata"] = cls._get_simple_metadata(metadata)
                 response_chunk.update(sub_stream_response_dict)
@@ -117,6 +117,6 @@ class AgentChatAppGenerateResponseConverter(AppGenerateResponseConverter):
                 data = cls._error_to_stream_response(sub_stream_response.err)
                 response_chunk.update(data)
             else:
-                response_chunk.update(sub_stream_response.model_dump(mode="json"))
+                response_chunk.update(sub_stream_response.model_dump(mode="json", exclude_none=True))
 
             yield response_chunk

api/core/app/apps/chat/generate_response_converter.py

@@ -81,7 +81,7 @@ class ChatAppGenerateResponseConverter(AppGenerateResponseConverter):
                 data = cls._error_to_stream_response(sub_stream_response.err)
                 response_chunk.update(data)
             else:
-                response_chunk.update(sub_stream_response.model_dump(mode="json"))
+                response_chunk.update(sub_stream_response.model_dump(mode="json", exclude_none=True))
             yield response_chunk
 
     @classmethod
@@ -109,7 +109,7 @@ class ChatAppGenerateResponseConverter(AppGenerateResponseConverter):
             }
 
             if isinstance(sub_stream_response, MessageEndStreamResponse):
-                sub_stream_response_dict = sub_stream_response.model_dump(mode="json")
+                sub_stream_response_dict = sub_stream_response.model_dump(mode="json", exclude_none=True)
                 metadata = sub_stream_response_dict.get("metadata", {})
                 sub_stream_response_dict["metadata"] = cls._get_simple_metadata(metadata)
                 response_chunk.update(sub_stream_response_dict)
@@ -117,6 +117,6 @@ class ChatAppGenerateResponseConverter(AppGenerateResponseConverter):
                 data = cls._error_to_stream_response(sub_stream_response.err)
                 response_chunk.update(data)
             else:
-                response_chunk.update(sub_stream_response.model_dump(mode="json"))
+                response_chunk.update(sub_stream_response.model_dump(mode="json", exclude_none=True))
 
             yield response_chunk

api/core/app/apps/common/workflow_response_converter.py

@@ -70,6 +70,8 @@ class _NodeSnapshot:
     """Empty string means the node is not executing inside an iteration."""
     loop_id: str = ""
     """Empty string means the node is not executing inside a loop."""
+    mention_parent_id: str = ""
+    """Empty string means the node is not an extractor node."""
 
 
 class WorkflowResponseConverter:
@@ -131,6 +133,7 @@ class WorkflowResponseConverter:
             start_at=event.start_at,
             iteration_id=event.in_iteration_id or "",
             loop_id=event.in_loop_id or "",
+            mention_parent_id=event.in_mention_parent_id or "",
         )
         node_execution_id = NodeExecutionId(event.node_execution_id)
         self._node_snapshots[node_execution_id] = snapshot
@@ -287,6 +290,7 @@ class WorkflowResponseConverter:
                 created_at=int(snapshot.start_at.timestamp()),
                 iteration_id=event.in_iteration_id,
                 loop_id=event.in_loop_id,
+                mention_parent_id=event.in_mention_parent_id,
                 agent_strategy=event.agent_strategy,
             ),
         )
@@ -373,6 +377,7 @@ class WorkflowResponseConverter:
                 files=self.fetch_files_from_node_outputs(event.outputs or {}),
                 iteration_id=event.in_iteration_id,
                 loop_id=event.in_loop_id,
+                mention_parent_id=event.in_mention_parent_id,
             ),
         )
 
@@ -422,6 +427,7 @@ class WorkflowResponseConverter:
                 files=self.fetch_files_from_node_outputs(event.outputs or {}),
                 iteration_id=event.in_iteration_id,
                 loop_id=event.in_loop_id,
+                mention_parent_id=event.in_mention_parent_id,
                 retry_index=event.retry_index,
             ),
         )

api/core/app/apps/completion/generate_response_converter.py

@@ -79,7 +79,7 @@ class CompletionAppGenerateResponseConverter(AppGenerateResponseConverter):
                 data = cls._error_to_stream_response(sub_stream_response.err)
                 response_chunk.update(data)
             else:
-                response_chunk.update(sub_stream_response.model_dump(mode="json"))
+                response_chunk.update(sub_stream_response.model_dump(mode="json", exclude_none=True))
             yield response_chunk
 
     @classmethod
@@ -106,7 +106,7 @@ class CompletionAppGenerateResponseConverter(AppGenerateResponseConverter):
             }
 
             if isinstance(sub_stream_response, MessageEndStreamResponse):
-                sub_stream_response_dict = sub_stream_response.model_dump(mode="json")
+                sub_stream_response_dict = sub_stream_response.model_dump(mode="json", exclude_none=True)
                 metadata = sub_stream_response_dict.get("metadata", {})
                 if not isinstance(metadata, dict):
                     metadata = {}
@@ -116,6 +116,6 @@ class CompletionAppGenerateResponseConverter(AppGenerateResponseConverter):
                 data = cls._error_to_stream_response(sub_stream_response.err)
                 response_chunk.update(data)
             else:
-                response_chunk.update(sub_stream_response.model_dump(mode="json"))
+                response_chunk.update(sub_stream_response.model_dump(mode="json", exclude_none=True))
 
             yield response_chunk

api/core/app/apps/pipeline/generate_response_converter.py

@@ -60,7 +60,7 @@ class WorkflowAppGenerateResponseConverter(AppGenerateResponseConverter):
                 data = cls._error_to_stream_response(sub_stream_response.err)
                 response_chunk.update(cast(dict, data))
             else:
-                response_chunk.update(sub_stream_response.model_dump())
+                response_chunk.update(sub_stream_response.model_dump(exclude_none=True))
             yield response_chunk
 
     @classmethod
@@ -91,5 +91,5 @@ class WorkflowAppGenerateResponseConverter(AppGenerateResponseConverter):
             elif isinstance(sub_stream_response, NodeStartStreamResponse | NodeFinishStreamResponse):
                 response_chunk.update(cast(dict, sub_stream_response.to_ignore_detail_dict()))
             else:
-                response_chunk.update(sub_stream_response.model_dump())
+                response_chunk.update(sub_stream_response.model_dump(exclude_none=True))
             yield response_chunk

api/core/app/apps/workflow/generate_response_converter.py

@@ -60,7 +60,7 @@ class WorkflowAppGenerateResponseConverter(AppGenerateResponseConverter):
                 data = cls._error_to_stream_response(sub_stream_response.err)
                 response_chunk.update(data)
             else:
-                response_chunk.update(sub_stream_response.model_dump(mode="json"))
+                response_chunk.update(sub_stream_response.model_dump(mode="json", exclude_none=True))
             yield response_chunk
 
     @classmethod
@@ -91,5 +91,5 @@ class WorkflowAppGenerateResponseConverter(AppGenerateResponseConverter):
             elif isinstance(sub_stream_response, NodeStartStreamResponse | NodeFinishStreamResponse):
                 response_chunk.update(sub_stream_response.to_ignore_detail_dict())
             else:
-                response_chunk.update(sub_stream_response.model_dump(mode="json"))
+                response_chunk.update(sub_stream_response.model_dump(mode="json", exclude_none=True))
             yield response_chunk

api/core/app/apps/workflow_app_runner.py

@@ -385,6 +385,7 @@ class WorkflowBasedAppRunner:
                     start_at=event.start_at,
                     in_iteration_id=event.in_iteration_id,
                     in_loop_id=event.in_loop_id,
+                    in_mention_parent_id=event.in_mention_parent_id,
                     inputs=inputs,
                     process_data=process_data,
                     outputs=outputs,
@@ -405,6 +406,7 @@ class WorkflowBasedAppRunner:
                     start_at=event.start_at,
                     in_iteration_id=event.in_iteration_id,
                     in_loop_id=event.in_loop_id,
+                    in_mention_parent_id=event.in_mention_parent_id,
                     agent_strategy=event.agent_strategy,
                     provider_type=event.provider_type,
                     provider_id=event.provider_id,
@@ -428,6 +430,7 @@ class WorkflowBasedAppRunner:
                     execution_metadata=execution_metadata,
                     in_iteration_id=event.in_iteration_id,
                     in_loop_id=event.in_loop_id,
+                    in_mention_parent_id=event.in_mention_parent_id,
                 )
             )
         elif isinstance(event, NodeRunFailedEvent):
@@ -444,6 +447,7 @@ class WorkflowBasedAppRunner:
                     execution_metadata=event.node_run_result.metadata,
                     in_iteration_id=event.in_iteration_id,
                     in_loop_id=event.in_loop_id,
+                    in_mention_parent_id=event.in_mention_parent_id,
                 )
             )
         elif isinstance(event, NodeRunExceptionEvent):
@@ -460,6 +464,7 @@ class WorkflowBasedAppRunner:
                     execution_metadata=event.node_run_result.metadata,
                     in_iteration_id=event.in_iteration_id,
                     in_loop_id=event.in_loop_id,
+                    in_mention_parent_id=event.in_mention_parent_id,
                 )
             )
         elif isinstance(event, NodeRunStreamChunkEvent):
@@ -469,6 +474,7 @@ class WorkflowBasedAppRunner:
                     from_variable_selector=list(event.selector),
                     in_iteration_id=event.in_iteration_id,
                     in_loop_id=event.in_loop_id,
+                    in_mention_parent_id=event.in_mention_parent_id,
                 )
             )
         elif isinstance(event, NodeRunRetrieverResourceEvent):
@@ -477,6 +483,7 @@ class WorkflowBasedAppRunner:
                     retriever_resources=event.retriever_resources,
                     in_iteration_id=event.in_iteration_id,
                     in_loop_id=event.in_loop_id,
+                    in_mention_parent_id=event.in_mention_parent_id,
                 )
             )
         elif isinstance(event, NodeRunAgentLogEvent):

api/core/app/entities/queue_entities.py

@@ -190,6 +190,8 @@ class QueueTextChunkEvent(AppQueueEvent):
     """iteration id if node is in iteration"""
     in_loop_id: str | None = None
     """loop id if node is in loop"""
+    in_mention_parent_id: str | None = None
+    """parent node id if this is an extractor node event"""
 
 
 class QueueAgentMessageEvent(AppQueueEvent):
@@ -229,6 +231,8 @@ class QueueRetrieverResourcesEvent(AppQueueEvent):
     """iteration id if node is in iteration"""
     in_loop_id: str | None = None
     """loop id if node is in loop"""
+    in_mention_parent_id: str | None = None
+    """parent node id if this is an extractor node event"""
 
 
 class QueueAnnotationReplyEvent(AppQueueEvent):
@@ -306,6 +310,8 @@ class QueueNodeStartedEvent(AppQueueEvent):
     node_run_index: int = 1  # FIXME(-LAN-): may not used
     in_iteration_id: str | None = None
     in_loop_id: str | None = None
+    in_mention_parent_id: str | None = None
+    """parent node id if this is an extractor node event"""
     start_at: datetime
     agent_strategy: AgentNodeStrategyInit | None = None
 
@@ -328,6 +334,8 @@ class QueueNodeSucceededEvent(AppQueueEvent):
     """iteration id if node is in iteration"""
     in_loop_id: str | None = None
     """loop id if node is in loop"""
+    in_mention_parent_id: str | None = None
+    """parent node id if this is an extractor node event"""
     start_at: datetime
 
     inputs: Mapping[str, object] = Field(default_factory=dict)
@@ -383,6 +391,8 @@ class QueueNodeExceptionEvent(AppQueueEvent):
     """iteration id if node is in iteration"""
     in_loop_id: str | None = None
     """loop id if node is in loop"""
+    in_mention_parent_id: str | None = None
+    """parent node id if this is an extractor node event"""
     start_at: datetime
 
     inputs: Mapping[str, object] = Field(default_factory=dict)
@@ -407,6 +417,8 @@ class QueueNodeFailedEvent(AppQueueEvent):
     """iteration id if node is in iteration"""
     in_loop_id: str | None = None
     """loop id if node is in loop"""
+    in_mention_parent_id: str | None = None
+    """parent node id if this is an extractor node event"""
     start_at: datetime
 
     inputs: Mapping[str, object] = Field(default_factory=dict)

api/core/app/entities/task_entities.py

@@ -262,6 +262,7 @@ class NodeStartStreamResponse(StreamResponse):
         extras: dict[str, object] = Field(default_factory=dict)
         iteration_id: str | None = None
         loop_id: str | None = None
+        mention_parent_id: str | None = None
         agent_strategy: AgentNodeStrategyInit | None = None
 
     event: StreamEvent = StreamEvent.NODE_STARTED
@@ -285,6 +286,7 @@ class NodeStartStreamResponse(StreamResponse):
                 "extras": {},
                 "iteration_id": self.data.iteration_id,
                 "loop_id": self.data.loop_id,
+                "mention_parent_id": self.data.mention_parent_id,
             },
         }
 
@@ -320,6 +322,7 @@ class NodeFinishStreamResponse(StreamResponse):
         files: Sequence[Mapping[str, Any]] | None = []
         iteration_id: str | None = None
         loop_id: str | None = None
+        mention_parent_id: str | None = None
 
     event: StreamEvent = StreamEvent.NODE_FINISHED
     workflow_run_id: str
@@ -349,6 +352,7 @@ class NodeFinishStreamResponse(StreamResponse):
                 "files": [],
                 "iteration_id": self.data.iteration_id,
                 "loop_id": self.data.loop_id,
+                "mention_parent_id": self.data.mention_parent_id,
             },
         }
 
@@ -384,6 +388,7 @@ class NodeRetryStreamResponse(StreamResponse):
         files: Sequence[Mapping[str, Any]] | None = []
         iteration_id: str | None = None
         loop_id: str | None = None
+        mention_parent_id: str | None = None
         retry_index: int = 0
 
     event: StreamEvent = StreamEvent.NODE_RETRY
@@ -414,6 +419,7 @@ class NodeRetryStreamResponse(StreamResponse):
                 "files": [],
                 "iteration_id": self.data.iteration_id,
                 "loop_id": self.data.loop_id,
+                "mention_parent_id": self.data.mention_parent_id,
                 "retry_index": self.data.retry_index,
             },
         }

api/core/llm_generator/llm_generator.py

@@ -1,8 +1,8 @@
 import json
 import logging
 import re
-from collections.abc import Sequence
-from typing import Protocol, cast
+from collections.abc import Mapping, Sequence
+from typing import Any, Protocol, cast
 
 import json_repair
 
@@ -398,6 +398,488 @@ class LLMGenerator:
             logger.exception("Failed to invoke LLM model, model: %s", model_config.get("name"))
             return {"output": "", "error": f"An unexpected error occurred: {str(e)}"}
 
+    @classmethod
+    def generate_with_context(
+        cls,
+        tenant_id: str,
+        workflow_id: str,
+        node_id: str,
+        parameter_name: str,
+        language: str,
+        prompt_messages: list[PromptMessage],
+        model_config: dict,
+    ) -> dict:
+        """
+        Generate extractor code node based on conversation context.
+
+        Args:
+            tenant_id: Tenant/workspace ID
+            workflow_id: Workflow ID
+            node_id: Current tool/llm node ID
+            parameter_name: Parameter name to generate code for
+            language: Code language (python3/javascript)
+            prompt_messages: Multi-turn conversation history (last message is instruction)
+            model_config: Model configuration (provider, name, completion_params)
+
+        Returns:
+            dict with CodeNodeData format:
+            - variables: Input variable selectors
+            - code_language: Code language
+            - code: Generated code
+            - outputs: Output definitions
+            - message: Explanation
+            - error: Error message if any
+        """
+        from sqlalchemy import select
+        from sqlalchemy.orm import Session
+
+        from services.workflow_service import WorkflowService
+
+        # Get workflow
+        with Session(db.engine) as session:
+            stmt = select(App).where(App.id == workflow_id)
+            app = session.scalar(stmt)
+            if not app:
+                return cls._error_response(f"App {workflow_id} not found")
+
+            workflow = WorkflowService().get_draft_workflow(app_model=app)
+            if not workflow:
+                return cls._error_response(f"Workflow for app {workflow_id} not found")
+
+        # Get upstream nodes via edge backtracking
+        upstream_nodes = cls._get_upstream_nodes(workflow.graph_dict, node_id)
+
+        # Get current node info
+        current_node = cls._get_node_by_id(workflow.graph_dict, node_id)
+        if not current_node:
+            return cls._error_response(f"Node {node_id} not found")
+
+        # Get parameter info
+        parameter_info = cls._get_parameter_info(
+            tenant_id=tenant_id,
+            node_data=current_node.get("data", {}),
+            parameter_name=parameter_name,
+        )
+
+        # Build system prompt
+        system_prompt = cls._build_extractor_system_prompt(
+            upstream_nodes=upstream_nodes,
+            current_node=current_node,
+            parameter_info=parameter_info,
+            language=language,
+        )
+
+        # Construct complete prompt_messages with system prompt
+        complete_messages: list[PromptMessage] = [
+            SystemPromptMessage(content=system_prompt),
+            *prompt_messages,
+        ]
+
+        from core.llm_generator.output_parser.structured_output import invoke_llm_with_structured_output
+
+        # Get model instance and schema
+        provider = model_config.get("provider", "")
+        model_name = model_config.get("name", "")
+        model_instance = ModelManager().get_model_instance(
+            tenant_id=tenant_id,
+            model_type=ModelType.LLM,
+            provider=provider,
+            model=model_name,
+        )
+
+        model_schema = model_instance.model_type_instance.get_model_schema(model_name, model_instance.credentials)
+        if not model_schema:
+            return cls._error_response(f"Model schema not found for {model_name}")
+
+        model_parameters = model_config.get("completion_params", {})
+        json_schema = cls._get_code_node_json_schema()
+
+        try:
+            response = invoke_llm_with_structured_output(
+                provider=provider,
+                model_schema=model_schema,
+                model_instance=model_instance,
+                prompt_messages=complete_messages,
+                json_schema=json_schema,
+                model_parameters=model_parameters,
+                stream=False,
+                tenant_id=tenant_id,
+            )
+
+            return cls._parse_code_node_output(
+                response.structured_output, language, parameter_info.get("type", "string")
+            )
+
+        except InvokeError as e:
+            return cls._error_response(str(e))
+        except Exception as e:
+            logger.exception("Failed to generate with context, model: %s", model_config.get("name"))
+            return cls._error_response(f"An unexpected error occurred: {str(e)}")
+
+    @classmethod
+    def _error_response(cls, error: str) -> dict:
+        """Return error response in CodeNodeData format."""
+        return {
+            "variables": [],
+            "code_language": "python3",
+            "code": "",
+            "outputs": {},
+            "message": "",
+            "error": error,
+        }
+
+    @classmethod
+    def generate_suggested_questions(
+        cls,
+        tenant_id: str,
+        workflow_id: str,
+        node_id: str,
+        parameter_name: str,
+        language: str,
+        model_config: dict | None = None,
+    ) -> dict:
+        """
+        Generate suggested questions for context generation.
+
+        Returns dict with questions array and error field.
+        """
+        from sqlalchemy import select
+        from sqlalchemy.orm import Session
+
+        from core.llm_generator.output_parser.structured_output import invoke_llm_with_structured_output
+        from services.workflow_service import WorkflowService
+
+        # Get workflow context (reuse existing logic)
+        with Session(db.engine) as session:
+            stmt = select(App).where(App.id == workflow_id)
+            app = session.scalar(stmt)
+            if not app:
+                return {"questions": [], "error": f"App {workflow_id} not found"}
+
+            workflow = WorkflowService().get_draft_workflow(app_model=app)
+            if not workflow:
+                return {"questions": [], "error": f"Workflow for app {workflow_id} not found"}
+
+        upstream_nodes = cls._get_upstream_nodes(workflow.graph_dict, node_id)
+        current_node = cls._get_node_by_id(workflow.graph_dict, node_id)
+        if not current_node:
+            return {"questions": [], "error": f"Node {node_id} not found"}
+
+        parameter_info = cls._get_parameter_info(
+            tenant_id=tenant_id,
+            node_data=current_node.get("data", {}),
+            parameter_name=parameter_name,
+        )
+
+        # Build prompt
+        system_prompt = cls._build_suggested_questions_prompt(
+            upstream_nodes=upstream_nodes,
+            current_node=current_node,
+            parameter_info=parameter_info,
+            language=language,
+        )
+
+        prompt_messages: list[PromptMessage] = [
+            SystemPromptMessage(content=system_prompt),
+        ]
+
+        # Get model instance - use default if model_config not provided
+        model_manager = ModelManager()
+        if model_config:
+            provider = model_config.get("provider", "")
+            model_name = model_config.get("name", "")
+            model_instance = model_manager.get_model_instance(
+                tenant_id=tenant_id,
+                model_type=ModelType.LLM,
+                provider=provider,
+                model=model_name,
+            )
+        else:
+            model_instance = model_manager.get_default_model_instance(
+                tenant_id=tenant_id,
+                model_type=ModelType.LLM,
+            )
+            model_name = model_instance.model
+
+        model_schema = model_instance.model_type_instance.get_model_schema(model_name, model_instance.credentials)
+        if not model_schema:
+            return {"questions": [], "error": f"Model schema not found for {model_name}"}
+
+        completion_params = model_config.get("completion_params", {}) if model_config else {}
+        model_parameters = {**completion_params, "max_tokens": 256}
+        json_schema = cls._get_suggested_questions_json_schema()
+
+        try:
+            response = invoke_llm_with_structured_output(
+                provider=model_instance.provider,
+                model_schema=model_schema,
+                model_instance=model_instance,
+                prompt_messages=prompt_messages,
+                json_schema=json_schema,
+                model_parameters=model_parameters,
+                stream=False,
+                tenant_id=tenant_id,
+            )
+
+            questions = response.structured_output.get("questions", []) if response.structured_output else []
+            return {"questions": questions, "error": ""}
+
+        except InvokeError as e:
+            return {"questions": [], "error": str(e)}
+        except Exception as e:
+            logger.exception("Failed to generate suggested questions, model: %s", model_name)
+            return {"questions": [], "error": f"An unexpected error occurred: {str(e)}"}
+
+    @classmethod
+    def _build_suggested_questions_prompt(
+        cls,
+        upstream_nodes: list[dict],
+        current_node: dict,
+        parameter_info: dict,
+        language: str = "English",
+    ) -> str:
+        """Build minimal prompt for suggested questions generation."""
+        # Simplify upstream nodes to reduce tokens
+        sources = [f"{n['title']}({','.join(n.get('outputs', {}).keys())})" for n in upstream_nodes[:5]]
+        param_type = parameter_info.get("type", "string")
+        param_desc = parameter_info.get("description", "")[:100]
+
+        return f"""Suggest 3 code generation questions for extracting data.
+Sources: {", ".join(sources)}
+Target: {parameter_info.get("name")}({param_type}) - {param_desc}
+Output 3 short, practical questions in {language}."""
+
+    @classmethod
+    def _get_suggested_questions_json_schema(cls) -> dict:
+        """Return JSON Schema for suggested questions."""
+        return {
+            "type": "object",
+            "properties": {
+                "questions": {
+                    "type": "array",
+                    "items": {"type": "string"},
+                    "minItems": 3,
+                    "maxItems": 3,
+                    "description": "3 suggested questions",
+                },
+            },
+            "required": ["questions"],
+        }
+
+    @classmethod
+    def _get_code_node_json_schema(cls) -> dict:
+        """Return JSON Schema for structured output."""
+        return {
+            "type": "object",
+            "properties": {
+                "variables": {
+                    "type": "array",
+                    "items": {
+                        "type": "object",
+                        "properties": {
+                            "variable": {"type": "string", "description": "Variable name in code"},
+                            "value_selector": {
+                                "type": "array",
+                                "items": {"type": "string"},
+                                "description": "Path like [node_id, output_name]",
+                            },
+                        },
+                        "required": ["variable", "value_selector"],
+                    },
+                },
+                "code": {"type": "string", "description": "Generated code with main function"},
+                "outputs": {
+                    "type": "object",
+                    "additionalProperties": {
+                        "type": "object",
+                        "properties": {"type": {"type": "string"}},
+                    },
+                    "description": "Output definitions, key is output name",
+                },
+                "explanation": {"type": "string", "description": "Brief explanation of the code"},
+            },
+            "required": ["variables", "code", "outputs", "explanation"],
+        }
+
+    @classmethod
+    def _get_upstream_nodes(cls, graph_dict: Mapping[str, Any], node_id: str) -> list[dict]:
+        """
+        Get all upstream nodes via edge backtracking.
+
+        Traverses the graph backwards from node_id to collect all reachable nodes.
+        """
+        from collections import defaultdict
+
+        nodes = {n["id"]: n for n in graph_dict.get("nodes", [])}
+        edges = graph_dict.get("edges", [])
+
+        # Build reverse adjacency list
+        reverse_adj: dict[str, list[str]] = defaultdict(list)
+        for edge in edges:
+            reverse_adj[edge["target"]].append(edge["source"])
+
+        # BFS to find all upstream nodes
+        visited: set[str] = set()
+        queue = [node_id]
+        upstream: list[dict] = []
+
+        while queue:
+            current = queue.pop(0)
+            for source in reverse_adj.get(current, []):
+                if source not in visited:
+                    visited.add(source)
+                    queue.append(source)
+                    if source in nodes:
+                        upstream.append(cls._extract_node_info(nodes[source]))
+
+        return upstream
+
+    @classmethod
+    def _get_node_by_id(cls, graph_dict: Mapping[str, Any], node_id: str) -> dict | None:
+        """Get node by ID from graph."""
+        for node in graph_dict.get("nodes", []):
+            if node["id"] == node_id:
+                return node
+        return None
+
+    @classmethod
+    def _extract_node_info(cls, node: dict) -> dict:
+        """Extract minimal node info with outputs based on node type."""
+        node_type = node["data"]["type"]
+        node_data = node.get("data", {})
+
+        # Build outputs based on node type (only type, no description to reduce tokens)
+        outputs: dict[str, str] = {}
+        match node_type:
+            case "start":
+                for var in node_data.get("variables", []):
+                    name = var.get("variable", var.get("name", ""))
+                    outputs[name] = var.get("type", "string")
+            case "llm":
+                outputs["text"] = "string"
+            case "code":
+                for name, output in node_data.get("outputs", {}).items():
+                    outputs[name] = output.get("type", "string")
+            case "http-request":
+                outputs = {"body": "string", "status_code": "number", "headers": "object"}
+            case "knowledge-retrieval":
+                outputs["result"] = "array[object]"
+            case "tool":
+                outputs = {"text": "string", "json": "object"}
+            case _:
+                outputs["output"] = "string"
+
+        info: dict = {
+            "id": node["id"],
+            "title": node_data.get("title", node["id"]),
+            "outputs": outputs,
+        }
+        # Only include description if not empty
+        desc = node_data.get("desc", "")
+        if desc:
+            info["desc"] = desc
+
+        return info
+
+    @classmethod
+    def _get_parameter_info(cls, tenant_id: str, node_data: dict, parameter_name: str) -> dict:
+        """Get parameter info from tool schema using ToolManager."""
+        default_info = {"name": parameter_name, "type": "string", "description": ""}
+
+        if node_data.get("type") != "tool":
+            return default_info
+
+        try:
+            from core.app.entities.app_invoke_entities import InvokeFrom
+            from core.tools.entities.tool_entities import ToolProviderType
+            from core.tools.tool_manager import ToolManager
+
+            provider_type_str = node_data.get("provider_type", "")
+            provider_type = ToolProviderType(provider_type_str) if provider_type_str else ToolProviderType.BUILT_IN
+
+            tool_runtime = ToolManager.get_tool_runtime(
+                provider_type=provider_type,
+                provider_id=node_data.get("provider_id", ""),
+                tool_name=node_data.get("tool_name", ""),
+                tenant_id=tenant_id,
+                invoke_from=InvokeFrom.DEBUGGER,
+            )
+
+            parameters = tool_runtime.get_merged_runtime_parameters()
+            for param in parameters:
+                if param.name == parameter_name:
+                    return {
+                        "name": param.name,
+                        "type": param.type.value if hasattr(param.type, "value") else str(param.type),
+                        "description": param.llm_description
+                        or (param.human_description.en_US if param.human_description else ""),
+                        "required": param.required,
+                    }
+        except Exception as e:
+            logger.debug("Failed to get parameter info from ToolManager: %s", e)
+
+        return default_info
+
+    @classmethod
+    def _build_extractor_system_prompt(
+        cls,
+        upstream_nodes: list[dict],
+        current_node: dict,
+        parameter_info: dict,
+        language: str,
+    ) -> str:
+        """Build system prompt for extractor code generation."""
+        upstream_json = json.dumps(upstream_nodes, indent=2, ensure_ascii=False)
+        param_type = parameter_info.get("type", "string")
+        return f"""You are a code generator for workflow automation.
+
+Generate {language} code to extract/transform upstream node outputs for the target parameter.
+
+## Upstream Nodes
+{upstream_json}
+
+## Target
+Node: {current_node["data"].get("title", current_node["id"])}
+Parameter: {parameter_info.get("name")} ({param_type}) - {parameter_info.get("description", "")}
+
+## Requirements
+- Write a main function that returns type: {param_type}
+- Use value_selector format: ["node_id", "output_name"]
+"""
+
+    @classmethod
+    def _parse_code_node_output(cls, content: Mapping[str, Any] | None, language: str, parameter_type: str) -> dict:
+        """
+        Parse structured output to CodeNodeData format.
+
+        Args:
+            content: Structured output dict from invoke_llm_with_structured_output
+            language: Code language
+            parameter_type: Expected parameter type
+
+        Returns dict with variables, code_language, code, outputs, message, error.
+        """
+        if content is None:
+            return cls._error_response("Empty or invalid response from LLM")
+
+        # Validate and normalize variables
+        variables = [
+            {"variable": v.get("variable", ""), "value_selector": v.get("value_selector", [])}
+            for v in content.get("variables", [])
+            if isinstance(v, dict)
+        ]
+
+        outputs = content.get("outputs", {"result": {"type": parameter_type}})
+
+        return {
+            "variables": variables,
+            "code_language": language,
+            "code": content.get("code", ""),
+            "outputs": outputs,
+            "message": content.get("explanation", ""),
+            "error": "",
+        }
+
     @staticmethod
     def instruction_modify_legacy(
         tenant_id: str, flow_id: str, current: str, instruction: str, model_config: dict, ideal_output: str | None

api/core/llm_generator/output_parser/file_ref.py

@@ -0,0 +1,188 @@
+"""
+File reference detection and conversion for structured output.
+
+This module provides utilities to:
+1. Detect file reference fields in JSON Schema (format: "dify-file-ref")
+2. Convert file ID strings to File objects after LLM returns
+"""
+
+import uuid
+from collections.abc import Mapping
+from typing import Any
+
+from core.file import File
+from core.variables.segments import ArrayFileSegment, FileSegment
+from factories.file_factory import build_from_mapping
+
+FILE_REF_FORMAT = "dify-file-ref"
+
+
+def is_file_ref_property(schema: dict) -> bool:
+    """Check if a schema property is a file reference."""
+    return schema.get("type") == "string" and schema.get("format") == FILE_REF_FORMAT
+
+
+def detect_file_ref_fields(schema: Mapping[str, Any], path: str = "") -> list[str]:
+    """
+    Recursively detect file reference fields in schema.
+
+    Args:
+        schema: JSON Schema to analyze
+        path: Current path in the schema (used for recursion)
+
+    Returns:
+        List of JSON paths containing file refs, e.g., ["image_id", "files[*]"]
+    """
+    file_ref_paths: list[str] = []
+    schema_type = schema.get("type")
+
+    if schema_type == "object":
+        for prop_name, prop_schema in schema.get("properties", {}).items():
+            current_path = f"{path}.{prop_name}" if path else prop_name
+
+            if is_file_ref_property(prop_schema):
+                file_ref_paths.append(current_path)
+            elif isinstance(prop_schema, dict):
+                file_ref_paths.extend(detect_file_ref_fields(prop_schema, current_path))
+
+    elif schema_type == "array":
+        items_schema = schema.get("items", {})
+        array_path = f"{path}[*]" if path else "[*]"
+
+        if is_file_ref_property(items_schema):
+            file_ref_paths.append(array_path)
+        elif isinstance(items_schema, dict):
+            file_ref_paths.extend(detect_file_ref_fields(items_schema, array_path))
+
+    return file_ref_paths
+
+
+def convert_file_refs_in_output(
+    output: Mapping[str, Any],
+    json_schema: Mapping[str, Any],
+    tenant_id: str,
+) -> dict[str, Any]:
+    """
+    Convert file ID strings to File objects based on schema.
+
+    Args:
+        output: The structured_output from LLM result
+        json_schema: The original JSON schema (to detect file ref fields)
+        tenant_id: Tenant ID for file lookup
+
+    Returns:
+        Output with file references converted to File objects
+    """
+    file_ref_paths = detect_file_ref_fields(json_schema)
+    if not file_ref_paths:
+        return dict(output)
+
+    result = _deep_copy_dict(output)
+
+    for path in file_ref_paths:
+        _convert_path_in_place(result, path.split("."), tenant_id)
+
+    return result
+
+
+def _deep_copy_dict(obj: Mapping[str, Any]) -> dict[str, Any]:
+    """Deep copy a mapping to a mutable dict."""
+    result: dict[str, Any] = {}
+    for key, value in obj.items():
+        if isinstance(value, Mapping):
+            result[key] = _deep_copy_dict(value)
+        elif isinstance(value, list):
+            result[key] = [_deep_copy_dict(item) if isinstance(item, Mapping) else item for item in value]
+        else:
+            result[key] = value
+    return result
+
+
+def _convert_path_in_place(obj: dict, path_parts: list[str], tenant_id: str) -> None:
+    """Convert file refs at the given path in place, wrapping in Segment types."""
+    if not path_parts:
+        return
+
+    current = path_parts[0]
+    remaining = path_parts[1:]
+
+    # Handle array notation like "files[*]"
+    if current.endswith("[*]"):
+        key = current[:-3] if current != "[*]" else None
+        target = obj.get(key) if key else obj
+
+        if isinstance(target, list):
+            if remaining:
+                # Nested array with remaining path - recurse into each item
+                for item in target:
+                    if isinstance(item, dict):
+                        _convert_path_in_place(item, remaining, tenant_id)
+            else:
+                # Array of file IDs - convert all and wrap in ArrayFileSegment
+                files: list[File] = []
+                for item in target:
+                    file = _convert_file_id(item, tenant_id)
+                    if file is not None:
+                        files.append(file)
+                # Replace the array with ArrayFileSegment
+                if key:
+                    obj[key] = ArrayFileSegment(value=files)
+        return
+
+    if not remaining:
+        # Leaf node - convert the value and wrap in FileSegment
+        if current in obj:
+            file = _convert_file_id(obj[current], tenant_id)
+            if file is not None:
+                obj[current] = FileSegment(value=file)
+            else:
+                obj[current] = None
+    else:
+        # Recurse into nested object
+        if current in obj and isinstance(obj[current], dict):
+            _convert_path_in_place(obj[current], remaining, tenant_id)
+
+
+def _convert_file_id(file_id: Any, tenant_id: str) -> File | None:
+    """
+    Convert a file ID string to a File object.
+
+    Tries multiple file sources in order:
+    1. ToolFile (files generated by tools/workflows)
+    2. UploadFile (files uploaded by users)
+    """
+    if not isinstance(file_id, str):
+        return None
+
+    # Validate UUID format
+    try:
+        uuid.UUID(file_id)
+    except ValueError:
+        return None
+
+    # Try ToolFile first (files generated by tools/workflows)
+    try:
+        return build_from_mapping(
+            mapping={
+                "transfer_method": "tool_file",
+                "tool_file_id": file_id,
+            },
+            tenant_id=tenant_id,
+        )
+    except ValueError:
+        pass
+
+    # Try UploadFile (files uploaded by users)
+    try:
+        return build_from_mapping(
+            mapping={
+                "transfer_method": "local_file",
+                "upload_file_id": file_id,
+            },
+            tenant_id=tenant_id,
+        )
+    except ValueError:
+        pass
+
+    # File not found in any source
+    return None

api/core/llm_generator/output_parser/structured_output.py

@@ -8,6 +8,7 @@ import json_repair
 from pydantic import TypeAdapter, ValidationError
 
 from core.llm_generator.output_parser.errors import OutputParserError
+from core.llm_generator.output_parser.file_ref import convert_file_refs_in_output
 from core.llm_generator.prompts import STRUCTURED_OUTPUT_PROMPT
 from core.model_manager import ModelInstance
 from core.model_runtime.callbacks.base_callback import Callback
@@ -57,6 +58,7 @@ def invoke_llm_with_structured_output(
     stream: Literal[True],
     user: str | None = None,
     callbacks: list[Callback] | None = None,
+    tenant_id: str | None = None,
 ) -> Generator[LLMResultChunkWithStructuredOutput, None, None]: ...
 @overload
 def invoke_llm_with_structured_output(
@@ -72,6 +74,7 @@ def invoke_llm_with_structured_output(
     stream: Literal[False],
     user: str | None = None,
     callbacks: list[Callback] | None = None,
+    tenant_id: str | None = None,
 ) -> LLMResultWithStructuredOutput: ...
 @overload
 def invoke_llm_with_structured_output(
@@ -87,6 +90,7 @@ def invoke_llm_with_structured_output(
     stream: bool = True,
     user: str | None = None,
     callbacks: list[Callback] | None = None,
+    tenant_id: str | None = None,
 ) -> LLMResultWithStructuredOutput | Generator[LLMResultChunkWithStructuredOutput, None, None]: ...
 def invoke_llm_with_structured_output(
     *,
@@ -101,20 +105,28 @@ def invoke_llm_with_structured_output(
     stream: bool = True,
     user: str | None = None,
     callbacks: list[Callback] | None = None,
+    tenant_id: str | None = None,
 ) -> LLMResultWithStructuredOutput | Generator[LLMResultChunkWithStructuredOutput, None, None]:
     """
-    Invoke large language model with structured output
-    1. This method invokes model_instance.invoke_llm with json_schema
-    2. Try to parse the result as structured output
+    Invoke large language model with structured output.
 
+    This method invokes model_instance.invoke_llm with json_schema and parses
+    the result as structured output.
+
+    :param provider: model provider name
+    :param model_schema: model schema entity
+    :param model_instance: model instance to invoke
     :param prompt_messages: prompt messages
-    :param json_schema: json schema
+    :param json_schema: json schema for structured output
     :param model_parameters: model parameters
     :param tools: tools for tool calling
     :param stop: stop words
     :param stream: is stream response
     :param user: unique user id
     :param callbacks: callbacks
+    :param tenant_id: tenant ID for file reference conversion. When provided and
+                      json_schema contains file reference fields (format: "dify-file-ref"),
+                      file IDs in the output will be automatically converted to File objects.
     :return: full response or stream response chunk generator result
     """
 
@@ -153,8 +165,18 @@ def invoke_llm_with_structured_output(
                 f"Failed to parse structured output, LLM result is not a string: {llm_result.message.content}"
             )
 
+        structured_output = _parse_structured_output(llm_result.message.content)
+
+        # Convert file references if tenant_id is provided
+        if tenant_id is not None:
+            structured_output = convert_file_refs_in_output(
+                output=structured_output,
+                json_schema=json_schema,
+                tenant_id=tenant_id,
+            )
+
         return LLMResultWithStructuredOutput(
-            structured_output=_parse_structured_output(llm_result.message.content),
+            structured_output=structured_output,
             model=llm_result.model,
             message=llm_result.message,
             usage=llm_result.usage,
@@ -186,8 +208,18 @@ def invoke_llm_with_structured_output(
                     delta=event.delta,
                 )
 
+            structured_output = _parse_structured_output(result_text)
+
+            # Convert file references if tenant_id is provided
+            if tenant_id is not None:
+                structured_output = convert_file_refs_in_output(
+                    output=structured_output,
+                    json_schema=json_schema,
+                    tenant_id=tenant_id,
+                )
+
             yield LLMResultChunkWithStructuredOutput(
-                structured_output=_parse_structured_output(result_text),
+                structured_output=structured_output,
                 model=model_schema.model,
                 prompt_messages=prompt_messages,
                 system_fingerprint=system_fingerprint,

api/core/llm_generator/utils.py

@@ -0,0 +1,45 @@
+"""Utility functions for LLM generator."""
+
+from core.model_runtime.entities.message_entities import (
+    AssistantPromptMessage,
+    PromptMessage,
+    PromptMessageRole,
+    SystemPromptMessage,
+    ToolPromptMessage,
+    UserPromptMessage,
+)
+
+
+def deserialize_prompt_messages(messages: list[dict]) -> list[PromptMessage]:
+    """
+    Deserialize list of dicts to list[PromptMessage].
+
+    Expected format:
+        [
+            {"role": "user", "content": "..."},
+            {"role": "assistant", "content": "..."},
+        ]
+    """
+    result: list[PromptMessage] = []
+    for msg in messages:
+        role = PromptMessageRole.value_of(msg["role"])
+        content = msg.get("content", "")
+
+        match role:
+            case PromptMessageRole.USER:
+                result.append(UserPromptMessage(content=content))
+            case PromptMessageRole.ASSISTANT:
+                result.append(AssistantPromptMessage(content=content))
+            case PromptMessageRole.SYSTEM:
+                result.append(SystemPromptMessage(content=content))
+            case PromptMessageRole.TOOL:
+                result.append(ToolPromptMessage(content=content, tool_call_id=msg.get("tool_call_id", "")))
+
+    return result
+
+
+def serialize_prompt_messages(messages: list[PromptMessage]) -> list[dict]:
+    """
+    Serialize list[PromptMessage] to list of dicts.
+    """
+    return [{"role": msg.role.value, "content": msg.content} for msg in messages]

api/core/memory/README.md

@@ -0,0 +1,434 @@
+# Memory Module
+
+This module provides memory management for LLM conversations, enabling context retention across dialogue turns.
+
+## Overview
+
+The memory module contains two types of memory implementations:
+
+1. **TokenBufferMemory** - Conversation-level memory (existing)
+2. **NodeTokenBufferMemory** - Node-level memory (to be implemented, **Chatflow only**)
+
+> **Note**: `NodeTokenBufferMemory` is only available in **Chatflow** (advanced-chat mode).
+> This is because it requires both `conversation_id` and `node_id`, which are only present in Chatflow.
+> Standard Workflow mode does not have `conversation_id` and therefore cannot use node-level memory.
+
+```
+┌─────────────────────────────────────────────────────────────────────────────┐
+│                           Memory Architecture                               │
+├─────────────────────────────────────────────────────────────────────────────┤
+│                                                                             │
+│  ┌─────────────────────────────────────────────────────────────────────-┐   │
+│  │                      TokenBufferMemory                               │   │
+│  │  Scope: Conversation                                                 │   │
+│  │  Storage: Database (Message table)                                   │   │
+│  │  Key: conversation_id                                                │   │
+│  └─────────────────────────────────────────────────────────────────────-┘   │
+│                                                                             │
+│  ┌─────────────────────────────────────────────────────────────────────-┐   │
+│  │                    NodeTokenBufferMemory                             │   │
+│  │  Scope: Node within Conversation                                     │   │
+│  │  Storage: Object Storage (JSON file)                                 │   │
+│  │  Key: (app_id, conversation_id, node_id)                             │   │
+│  └─────────────────────────────────────────────────────────────────────-┘   │
+│                                                                             │
+└─────────────────────────────────────────────────────────────────────────────┘
+```
+
+---
+
+## TokenBufferMemory (Existing)
+
+### Purpose
+
+`TokenBufferMemory` retrieves conversation history from the `Message` table and converts it to `PromptMessage` objects for LLM context.
+
+### Key Features
+
+- **Conversation-scoped**: All messages within a conversation are candidates
+- **Thread-aware**: Uses `parent_message_id` to extract only the current thread (supports regeneration scenarios)
+- **Token-limited**: Truncates history to fit within `max_token_limit`
+- **File support**: Handles `MessageFile` attachments (images, documents, etc.)
+
+### Data Flow
+
+```
+Message Table                    TokenBufferMemory              LLM
+     │                                  │                        │
+     │  SELECT * FROM messages          │                        │
+     │  WHERE conversation_id = ?       │                        │
+     │  ORDER BY created_at DESC        │                        │
+     ├─────────────────────────────────▶│                        │
+     │                                  │                        │
+     │                    extract_thread_messages()              │
+     │                                  │                        │
+     │                    build_prompt_message_with_files()      │
+     │                                  │                        │
+     │                    truncate by max_token_limit            │
+     │                                  │                        │
+     │                                  │  Sequence[PromptMessage]
+     │                                  ├───────────────────────▶│
+     │                                  │                        │
+```
+
+### Thread Extraction
+
+When a user regenerates a response, a new thread is created:
+
+```
+Message A (user)
+    └── Message A' (assistant)
+            └── Message B (user)
+                    └── Message B' (assistant)
+            └── Message A'' (assistant, regenerated)  ← New thread
+                    └── Message C (user)
+                            └── Message C' (assistant)
+```
+
+`extract_thread_messages()` traces back from the latest message using `parent_message_id` to get only the current thread: `[A, A'', C, C']`
+
+### Usage
+
+```python
+from core.memory.token_buffer_memory import TokenBufferMemory
+
+memory = TokenBufferMemory(conversation=conversation, model_instance=model_instance)
+history = memory.get_history_prompt_messages(max_token_limit=2000, message_limit=100)
+```
+
+---
+
+## NodeTokenBufferMemory (To Be Implemented)
+
+### Purpose
+
+`NodeTokenBufferMemory` provides **node-scoped memory** within a conversation. Each LLM node in a workflow can maintain its own independent conversation history.
+
+### Use Cases
+
+1. **Multi-LLM Workflows**: Different LLM nodes need separate context
+2. **Iterative Processing**: An LLM node in a loop needs to accumulate context across iterations
+3. **Specialized Agents**: Each agent node maintains its own dialogue history
+
+### Design Decisions
+
+#### Storage: Object Storage for Messages (No New Database Table)
+
+| Aspect                    | Database             | Object Storage     |
+| ------------------------- | -------------------- | ------------------ |
+| Cost                      | High                 | Low                |
+| Query Flexibility         | High                 | Low                |
+| Schema Changes            | Migration required   | None               |
+| Consistency with existing | ConversationVariable | File uploads, logs |
+
+**Decision**: Store message data in object storage, but still use existing database tables for file metadata.
+
+**What is stored in Object Storage:**
+
+- Message content (text)
+- Message metadata (role, token_count, created_at)
+- File references (upload_file_id, tool_file_id, etc.)
+- Thread relationships (message_id, parent_message_id)
+
+**What still requires Database queries:**
+
+- File reconstruction: When reading node memory, file references are used to query
+  `UploadFile` / `ToolFile` tables via `file_factory.build_from_mapping()` to rebuild
+  complete `File` objects with storage_key, mime_type, etc.
+
+**Why this hybrid approach:**
+
+- No database migration required (no new tables)
+- Message data may be large, object storage is cost-effective
+- File metadata is already in database, no need to duplicate
+- Aligns with existing storage patterns (file uploads, logs)
+
+#### Storage Key Format
+
+```
+node_memory/{app_id}/{conversation_id}/{node_id}.json
+```
+
+#### Data Structure
+
+```json
+{
+  "version": 1,
+  "messages": [
+    {
+      "message_id": "msg-001",
+      "parent_message_id": null,
+      "role": "user",
+      "content": "Analyze this image",
+      "files": [
+        {
+          "type": "image",
+          "transfer_method": "local_file",
+          "upload_file_id": "file-uuid-123",
+          "belongs_to": "user"
+        }
+      ],
+      "token_count": 15,
+      "created_at": "2026-01-07T10:00:00Z"
+    },
+    {
+      "message_id": "msg-002",
+      "parent_message_id": "msg-001",
+      "role": "assistant",
+      "content": "This is a landscape image...",
+      "files": [],
+      "token_count": 50,
+      "created_at": "2026-01-07T10:00:01Z"
+    }
+  ]
+}
+```
+
+### Thread Support
+
+Node memory also supports thread extraction (for regeneration scenarios):
+
+```python
+def _extract_thread(
+    self,
+    messages: list[NodeMemoryMessage],
+    current_message_id: str
+) -> list[NodeMemoryMessage]:
+    """
+    Extract messages belonging to the thread of current_message_id.
+    Similar to extract_thread_messages() in TokenBufferMemory.
+    """
+    ...
+```
+
+### File Handling
+
+Files are stored as references (not full metadata):
+
+```python
+class NodeMemoryFile(BaseModel):
+    type: str                        # image, audio, video, document, custom
+    transfer_method: str             # local_file, remote_url, tool_file
+    upload_file_id: str | None       # for local_file
+    tool_file_id: str | None         # for tool_file
+    url: str | None                  # for remote_url
+    belongs_to: str                  # user / assistant
+```
+
+When reading, files are rebuilt using `file_factory.build_from_mapping()`.
+
+### API Design
+
+```python
+class NodeTokenBufferMemory:
+    def __init__(
+        self,
+        app_id: str,
+        conversation_id: str,
+        node_id: str,
+        model_instance: ModelInstance,
+    ):
+        """
+        Initialize node-level memory.
+
+        :param app_id: Application ID
+        :param conversation_id: Conversation ID
+        :param node_id: Node ID in the workflow
+        :param model_instance: Model instance for token counting
+        """
+        ...
+
+    def add_messages(
+        self,
+        message_id: str,
+        parent_message_id: str | None,
+        user_content: str,
+        user_files: Sequence[File],
+        assistant_content: str,
+        assistant_files: Sequence[File],
+    ) -> None:
+        """
+        Append a dialogue turn (user + assistant) to node memory.
+        Call this after LLM node execution completes.
+
+        :param message_id: Current message ID (from Message table)
+        :param parent_message_id: Parent message ID (for thread tracking)
+        :param user_content: User's text input
+        :param user_files: Files attached by user
+        :param assistant_content: Assistant's text response
+        :param assistant_files: Files generated by assistant
+        """
+        ...
+
+    def get_history_prompt_messages(
+        self,
+        current_message_id: str,
+        tenant_id: str,
+        max_token_limit: int = 2000,
+        file_upload_config: FileUploadConfig | None = None,
+    ) -> Sequence[PromptMessage]:
+        """
+        Retrieve history as PromptMessage sequence.
+
+        :param current_message_id: Current message ID (for thread extraction)
+        :param tenant_id: Tenant ID (for file reconstruction)
+        :param max_token_limit: Maximum tokens for history
+        :param file_upload_config: File upload configuration
+        :return: Sequence of PromptMessage for LLM context
+        """
+        ...
+
+    def flush(self) -> None:
+        """
+        Persist buffered changes to object storage.
+        Call this at the end of node execution.
+        """
+        ...
+
+    def clear(self) -> None:
+        """
+        Clear all messages in this node's memory.
+        """
+        ...
+```
+
+### Data Flow
+
+```
+Object Storage                  NodeTokenBufferMemory           LLM Node
+     │                                  │                           │
+     │                                  │◀── get_history_prompt_messages()
+     │  storage.load(key)               │                           │
+     │◀─────────────────────────────────┤                           │
+     │                                  │                           │
+     │  JSON data                       │                           │
+     ├─────────────────────────────────▶│                           │
+     │                                  │                           │
+     │                    _extract_thread()                         │
+     │                                  │                           │
+     │                    _rebuild_files() via file_factory         │
+     │                                  │                           │
+     │                    _build_prompt_messages()                  │
+     │                                  │                           │
+     │                    _truncate_by_tokens()                     │
+     │                                  │                           │
+     │                                  │  Sequence[PromptMessage]  │
+     │                                  ├──────────────────────────▶│
+     │                                  │                           │
+     │                                  │◀── LLM execution complete │
+     │                                  │                           │
+     │                                  │◀── add_messages()         │
+     │                                  │                           │
+     │  storage.save(key, data)         │                           │
+     │◀─────────────────────────────────┤                           │
+     │                                  │                           │
+```
+
+### Integration with LLM Node
+
+```python
+# In LLM Node execution
+
+# 1. Fetch memory based on mode
+if node_data.memory and node_data.memory.mode == MemoryMode.NODE:
+    # Node-level memory (Chatflow only)
+    memory = fetch_node_memory(
+        variable_pool=variable_pool,
+        app_id=app_id,
+        node_id=self.node_id,
+        node_data_memory=node_data.memory,
+        model_instance=model_instance,
+    )
+elif node_data.memory and node_data.memory.mode == MemoryMode.CONVERSATION:
+    # Conversation-level memory (existing behavior)
+    memory = fetch_memory(
+        variable_pool=variable_pool,
+        app_id=app_id,
+        node_data_memory=node_data.memory,
+        model_instance=model_instance,
+    )
+else:
+    memory = None
+
+# 2. Get history for context
+if memory:
+    if isinstance(memory, NodeTokenBufferMemory):
+        history = memory.get_history_prompt_messages(
+            current_message_id=current_message_id,
+            tenant_id=tenant_id,
+            max_token_limit=max_token_limit,
+        )
+    else:  # TokenBufferMemory
+        history = memory.get_history_prompt_messages(
+            max_token_limit=max_token_limit,
+        )
+    prompt_messages = [*history, *current_messages]
+else:
+    prompt_messages = current_messages
+
+# 3. Call LLM
+response = model_instance.invoke(prompt_messages)
+
+# 4. Append to node memory (only for NodeTokenBufferMemory)
+if isinstance(memory, NodeTokenBufferMemory):
+    memory.add_messages(
+        message_id=message_id,
+        parent_message_id=parent_message_id,
+        user_content=user_input,
+        user_files=user_files,
+        assistant_content=response.content,
+        assistant_files=response_files,
+    )
+    memory.flush()
+```
+
+### Configuration
+
+Add to `MemoryConfig` in `core/workflow/nodes/llm/entities.py`:
+
+```python
+class MemoryMode(StrEnum):
+    CONVERSATION = "conversation"  # Use TokenBufferMemory (default, existing behavior)
+    NODE = "node"                  # Use NodeTokenBufferMemory (new, Chatflow only)
+
+class MemoryConfig(BaseModel):
+    # Existing fields
+    role_prefix: RolePrefix | None = None
+    window: MemoryWindowConfig | None = None
+    query_prompt_template: str | None = None
+
+    # Memory mode (new)
+    mode: MemoryMode = MemoryMode.CONVERSATION
+```
+
+**Mode Behavior:**
+
+| Mode           | Memory Class          | Scope                    | Availability  |
+| -------------- | --------------------- | ------------------------ | ------------- |
+| `conversation` | TokenBufferMemory     | Entire conversation      | All app modes |
+| `node`         | NodeTokenBufferMemory | Per-node in conversation | Chatflow only |
+
+> When `mode=node` is used in a non-Chatflow context (no conversation_id), it should
+> fall back to no memory or raise a configuration error.
+
+---
+
+## Comparison
+
+| Feature        | TokenBufferMemory        | NodeTokenBufferMemory     |
+| -------------- | ------------------------ | ------------------------- |
+| Scope          | Conversation             | Node within Conversation  |
+| Storage        | Database (Message table) | Object Storage (JSON)     |
+| Thread Support | Yes                      | Yes                       |
+| File Support   | Yes (via MessageFile)    | Yes (via file references) |
+| Token Limit    | Yes                      | Yes                       |
+| Use Case       | Standard chat apps       | Complex workflows         |
+
+---
+
+## Future Considerations
+
+1. **Cleanup Task**: Add a Celery task to clean up old node memory files
+2. **Concurrency**: Consider Redis lock for concurrent node executions
+3. **Compression**: Compress large memory files to reduce storage costs
+4. **Extension**: Other nodes (Agent, Tool) may also benefit from node-level memory

api/core/memory/__init__.py

@@ -0,0 +1,15 @@
+from core.memory.base import BaseMemory
+from core.memory.node_token_buffer_memory import (
+    NodeMemoryData,
+    NodeMemoryFile,
+    NodeTokenBufferMemory,
+)
+from core.memory.token_buffer_memory import TokenBufferMemory
+
+__all__ = [
+    "BaseMemory",
+    "NodeMemoryData",
+    "NodeMemoryFile",
+    "NodeTokenBufferMemory",
+    "TokenBufferMemory",
+]

api/core/memory/base.py

@@ -0,0 +1,83 @@
+"""
+Base memory interfaces and types.
+
+This module defines the common protocol for memory implementations.
+"""
+
+from abc import ABC, abstractmethod
+from collections.abc import Sequence
+
+from core.model_runtime.entities import ImagePromptMessageContent, PromptMessage
+
+
+class BaseMemory(ABC):
+    """
+    Abstract base class for memory implementations.
+
+    Provides a common interface for both conversation-level and node-level memory.
+    """
+
+    @abstractmethod
+    def get_history_prompt_messages(
+        self,
+        *,
+        max_token_limit: int = 2000,
+        message_limit: int | None = None,
+    ) -> Sequence[PromptMessage]:
+        """
+        Get history prompt messages.
+
+        :param max_token_limit: Maximum tokens for history
+        :param message_limit: Maximum number of messages
+        :return: Sequence of PromptMessage for LLM context
+        """
+        pass
+
+    def get_history_prompt_text(
+        self,
+        human_prefix: str = "Human",
+        ai_prefix: str = "Assistant",
+        max_token_limit: int = 2000,
+        message_limit: int | None = None,
+    ) -> str:
+        """
+        Get history prompt as formatted text.
+
+        :param human_prefix: Prefix for human messages
+        :param ai_prefix: Prefix for assistant messages
+        :param max_token_limit: Maximum tokens for history
+        :param message_limit: Maximum number of messages
+        :return: Formatted history text
+        """
+        from core.model_runtime.entities import (
+            PromptMessageRole,
+            TextPromptMessageContent,
+        )
+
+        prompt_messages = self.get_history_prompt_messages(
+            max_token_limit=max_token_limit,
+            message_limit=message_limit,
+        )
+
+        string_messages = []
+        for m in prompt_messages:
+            if m.role == PromptMessageRole.USER:
+                role = human_prefix
+            elif m.role == PromptMessageRole.ASSISTANT:
+                role = ai_prefix
+            else:
+                continue
+
+            if isinstance(m.content, list):
+                inner_msg = ""
+                for content in m.content:
+                    if isinstance(content, TextPromptMessageContent):
+                        inner_msg += f"{content.data}\n"
+                    elif isinstance(content, ImagePromptMessageContent):
+                        inner_msg += "[image]\n"
+                string_messages.append(f"{role}: {inner_msg.strip()}")
+            else:
+                message = f"{role}: {m.content}"
+                string_messages.append(message)
+
+        return "\n".join(string_messages)

api/core/memory/node_token_buffer_memory.py

@@ -0,0 +1,353 @@
+"""
+Node-level Token Buffer Memory for Chatflow.
+
+This module provides node-scoped memory within a conversation.
+Each LLM node in a workflow can maintain its own independent conversation history.
+
+Note: This is only available in Chatflow (advanced-chat mode) because it requires
+both conversation_id and node_id.
+
+Design:
+- Storage is indexed by workflow_run_id (each execution stores one turn)
+- Thread tracking leverages Message table's parent_message_id structure
+- On read: query Message table for current thread, then filter Node Memory by workflow_run_ids
+"""
+
+import logging
+from collections.abc import Sequence
+
+from pydantic import BaseModel
+from sqlalchemy import select
+
+from core.file import File, FileTransferMethod
+from core.memory.base import BaseMemory
+from core.model_manager import ModelInstance
+from core.model_runtime.entities import (
+    AssistantPromptMessage,
+    ImagePromptMessageContent,
+    PromptMessage,
+    TextPromptMessageContent,
+    UserPromptMessage,
+)
+from core.prompt.utils.extract_thread_messages import extract_thread_messages
+from extensions.ext_database import db
+from extensions.ext_storage import storage
+from models.model import Message
+
+logger = logging.getLogger(__name__)
+
+
+class NodeMemoryFile(BaseModel):
+    """File reference stored in node memory."""
+
+    type: str  # image, audio, video, document, custom
+    transfer_method: str  # local_file, remote_url, tool_file
+    upload_file_id: str | None = None
+    tool_file_id: str | None = None
+    url: str | None = None
+
+
+class NodeMemoryTurn(BaseModel):
+    """A single dialogue turn (user + assistant) in node memory."""
+
+    user_content: str = ""
+    user_files: list[NodeMemoryFile] = []
+    assistant_content: str = ""
+    assistant_files: list[NodeMemoryFile] = []
+
+
+class NodeMemoryData(BaseModel):
+    """Root data structure for node memory storage."""
+
+    version: int = 1
+    # Key: workflow_run_id, Value: dialogue turn
+    turns: dict[str, NodeMemoryTurn] = {}
+
+
+class NodeTokenBufferMemory(BaseMemory):
+    """
+    Node-level Token Buffer Memory.
+
+    Provides node-scoped memory within a conversation. Each LLM node can maintain
+    its own independent conversation history, stored in object storage.
+
+    Key design: Thread tracking is delegated to Message table's parent_message_id.
+    Storage is indexed by workflow_run_id for easy filtering.
+
+    Storage key format: node_memory/{app_id}/{conversation_id}/{node_id}.json
+    """
+
+    def __init__(
+        self,
+        app_id: str,
+        conversation_id: str,
+        node_id: str,
+        tenant_id: str,
+        model_instance: ModelInstance,
+    ):
+        """
+        Initialize node-level memory.
+
+        :param app_id: Application ID
+        :param conversation_id: Conversation ID
+        :param node_id: Node ID in the workflow
+        :param tenant_id: Tenant ID for file reconstruction
+        :param model_instance: Model instance for token counting
+        """
+        self.app_id = app_id
+        self.conversation_id = conversation_id
+        self.node_id = node_id
+        self.tenant_id = tenant_id
+        self.model_instance = model_instance
+        self._storage_key = f"node_memory/{app_id}/{conversation_id}/{node_id}.json"
+        self._data: NodeMemoryData | None = None
+        self._dirty = False
+
+    def _load(self) -> NodeMemoryData:
+        """Load data from object storage."""
+        if self._data is not None:
+            return self._data
+
+        try:
+            raw = storage.load_once(self._storage_key)
+            self._data = NodeMemoryData.model_validate_json(raw)
+        except Exception:
+            # File not found or parse error, start fresh
+            self._data = NodeMemoryData()
+
+        return self._data
+
+    def _save(self) -> None:
+        """Save data to object storage."""
+        if self._data is not None:
+            storage.save(self._storage_key, self._data.model_dump_json().encode("utf-8"))
+            self._dirty = False
+
+    def _file_to_memory_file(self, file: File) -> NodeMemoryFile:
+        """Convert File object to NodeMemoryFile reference."""
+        return NodeMemoryFile(
+            type=file.type.value if hasattr(file.type, "value") else str(file.type),
+            transfer_method=(
+                file.transfer_method.value if hasattr(file.transfer_method, "value") else str(file.transfer_method)
+            ),
+            upload_file_id=file.related_id if file.transfer_method == FileTransferMethod.LOCAL_FILE else None,
+            tool_file_id=file.related_id if file.transfer_method == FileTransferMethod.TOOL_FILE else None,
+            url=file.remote_url if file.transfer_method == FileTransferMethod.REMOTE_URL else None,
+        )
+
+    def _memory_file_to_mapping(self, memory_file: NodeMemoryFile) -> dict:
+        """Convert NodeMemoryFile to mapping for file_factory."""
+        mapping: dict = {
+            "type": memory_file.type,
+            "transfer_method": memory_file.transfer_method,
+        }
+        if memory_file.upload_file_id:
+            mapping["upload_file_id"] = memory_file.upload_file_id
+        if memory_file.tool_file_id:
+            mapping["tool_file_id"] = memory_file.tool_file_id
+        if memory_file.url:
+            mapping["url"] = memory_file.url
+        return mapping
+
+    def _rebuild_files(self, memory_files: list[NodeMemoryFile]) -> list[File]:
+        """Rebuild File objects from NodeMemoryFile references."""
+        if not memory_files:
+            return []
+
+        from factories import file_factory
+
+        files = []
+        for mf in memory_files:
+            try:
+                mapping = self._memory_file_to_mapping(mf)
+                file = file_factory.build_from_mapping(mapping=mapping, tenant_id=self.tenant_id)
+                files.append(file)
+            except Exception as e:
+                logger.warning("Failed to rebuild file from memory: %s", e)
+                continue
+        return files
+
+    def _build_prompt_message(
+        self,
+        role: str,
+        content: str,
+        files: list[File],
+        detail: ImagePromptMessageContent.DETAIL = ImagePromptMessageContent.DETAIL.HIGH,
+    ) -> PromptMessage:
+        """Build PromptMessage from content and files."""
+        from core.file import file_manager
+
+        if not files:
+            if role == "user":
+                return UserPromptMessage(content=content)
+            else:
+                return AssistantPromptMessage(content=content)
+
+        # Build multimodal content
+        prompt_contents: list = []
+        for file in files:
+            try:
+                prompt_content = file_manager.to_prompt_message_content(file, image_detail_config=detail)
+                prompt_contents.append(prompt_content)
+            except Exception as e:
+                logger.warning("Failed to convert file to prompt content: %s", e)
+                continue
+
+        prompt_contents.append(TextPromptMessageContent(data=content))
+
+        if role == "user":
+            return UserPromptMessage(content=prompt_contents)
+        else:
+            return AssistantPromptMessage(content=prompt_contents)
+
+    def _get_thread_workflow_run_ids(self) -> list[str]:
+        """
+        Get workflow_run_ids for the current thread by querying Message table.
+
+        Returns workflow_run_ids in chronological order (oldest first).
+        """
+        # Query messages for this conversation
+        stmt = (
+            select(Message).where(Message.conversation_id == self.conversation_id).order_by(Message.created_at.desc())
+        )
+        messages = db.session.scalars(stmt.limit(500)).all()
+
+        if not messages:
+            return []
+
+        # Extract thread messages using existing logic
+        thread_messages = extract_thread_messages(messages)
+
+        # For newly created message, its answer is temporarily empty, skip it
+        if thread_messages and not thread_messages[0].answer and thread_messages[0].answer_tokens == 0:
+            thread_messages.pop(0)
+
+        # Reverse to get chronological order, extract workflow_run_ids
+        workflow_run_ids = []
+        for msg in reversed(thread_messages):
+            if msg.workflow_run_id:
+                workflow_run_ids.append(msg.workflow_run_id)
+
+        return workflow_run_ids
+
+    def add_messages(
+        self,
+        workflow_run_id: str,
+        user_content: str,
+        user_files: Sequence[File] | None = None,
+        assistant_content: str = "",
+        assistant_files: Sequence[File] | None = None,
+    ) -> None:
+        """
+        Add a dialogue turn to node memory.
+        Call this after LLM node execution completes.
+
+        :param workflow_run_id: Current workflow execution ID
+        :param user_content: User's text input
+        :param user_files: Files attached by user
+        :param assistant_content: Assistant's text response
+        :param assistant_files: Files generated by assistant
+        """
+        data = self._load()
+
+        # Convert files to memory file references
+        user_memory_files = [self._file_to_memory_file(f) for f in (user_files or [])]
+        assistant_memory_files = [self._file_to_memory_file(f) for f in (assistant_files or [])]
+
+        # Store the turn indexed by workflow_run_id
+        data.turns[workflow_run_id] = NodeMemoryTurn(
+            user_content=user_content,
+            user_files=user_memory_files,
+            assistant_content=assistant_content,
+            assistant_files=assistant_memory_files,
+        )
+
+        self._dirty = True
+
+    def get_history_prompt_messages(
+        self,
+        *,
+        max_token_limit: int = 2000,
+        message_limit: int | None = None,
+    ) -> Sequence[PromptMessage]:
+        """
+        Retrieve history as PromptMessage sequence.
+
+        Thread tracking is handled by querying Message table's parent_message_id structure.
+
+        :param max_token_limit: Maximum tokens for history
+        :param message_limit: unused, for interface compatibility
+        :return: Sequence of PromptMessage for LLM context
+        """
+        # message_limit is unused in NodeTokenBufferMemory (uses token limit instead)
+        _ = message_limit
+        detail = ImagePromptMessageContent.DETAIL.HIGH
+        data = self._load()
+
+        if not data.turns:
+            return []
+
+        # Get workflow_run_ids for current thread from Message table
+        thread_workflow_run_ids = self._get_thread_workflow_run_ids()
+
+        if not thread_workflow_run_ids:
+            return []
+
+        # Build prompt messages in thread order
+        prompt_messages: list[PromptMessage] = []
+        for wf_run_id in thread_workflow_run_ids:
+            turn = data.turns.get(wf_run_id)
+            if not turn:
+                # This workflow execution didn't have node memory stored
+                continue
+
+            # Build user message
+            user_files = self._rebuild_files(turn.user_files) if turn.user_files else []
+            user_msg = self._build_prompt_message(
+                role="user",
+                content=turn.user_content,
+                files=user_files,
+                detail=detail,
+            )
+            prompt_messages.append(user_msg)
+
+            # Build assistant message
+            assistant_files = self._rebuild_files(turn.assistant_files) if turn.assistant_files else []
+            assistant_msg = self._build_prompt_message(
+                role="assistant",
+                content=turn.assistant_content,
+                files=assistant_files,
+                detail=detail,
+            )
+            prompt_messages.append(assistant_msg)
+
+        if not prompt_messages:
+            return []
+
+        # Truncate by token limit
+        try:
+            current_tokens = self.model_instance.get_llm_num_tokens(prompt_messages)
+            while current_tokens > max_token_limit and len(prompt_messages) > 1:
+                prompt_messages.pop(0)
+                current_tokens = self.model_instance.get_llm_num_tokens(prompt_messages)
+        except Exception as e:
+            logger.warning("Failed to count tokens for truncation: %s", e)
+
+        return prompt_messages
+
+    def flush(self) -> None:
+        """
+        Persist buffered changes to object storage.
+        Call this at the end of node execution.
+        """
+        if self._dirty:
+            self._save()
+
+    def clear(self) -> None:
+        """Clear all messages in this node's memory."""
+        self._data = NodeMemoryData()
+        self._save()
+
+    def exists(self) -> bool:
+        """Check if node memory exists in storage."""
+        return storage.exists(self._storage_key)

api/core/memory/token_buffer_memory.py

@@ -5,12 +5,12 @@ from sqlalchemy.orm import sessionmaker
 
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
 from core.file import file_manager
+from core.memory.base import BaseMemory
 from core.model_manager import ModelInstance
 from core.model_runtime.entities import (
     AssistantPromptMessage,
     ImagePromptMessageContent,
     PromptMessage,
-    PromptMessageRole,
     TextPromptMessageContent,
     UserPromptMessage,
 )
@@ -24,7 +24,7 @@ from repositories.api_workflow_run_repository import APIWorkflowRunRepository
 from repositories.factory import DifyAPIRepositoryFactory
 
 
-class TokenBufferMemory:
+class TokenBufferMemory(BaseMemory):
     def __init__(
         self,
         conversation: Conversation,
@@ -115,10 +115,14 @@ class TokenBufferMemory:
                 return AssistantPromptMessage(content=prompt_message_contents)
 
     def get_history_prompt_messages(
-        self, max_token_limit: int = 2000, message_limit: int | None = None
+        self,
+        *,
+        max_token_limit: int = 2000,
+        message_limit: int | None = None,
     ) -> Sequence[PromptMessage]:
         """
         Get history prompt messages.
+
         :param max_token_limit: max token limit
         :param message_limit: message limit
         """
@@ -200,44 +204,3 @@ class TokenBufferMemory:
                 curr_message_tokens = self.model_instance.get_llm_num_tokens(prompt_messages)
 
         return prompt_messages
-
-    def get_history_prompt_text(
-        self,
-        human_prefix: str = "Human",
-        ai_prefix: str = "Assistant",
-        max_token_limit: int = 2000,
-        message_limit: int | None = None,
-    ) -> str:
-        """
-        Get history prompt text.
-        :param human_prefix: human prefix
-        :param ai_prefix: ai prefix
-        :param max_token_limit: max token limit
-        :param message_limit: message limit
-        :return:
-        """
-        prompt_messages = self.get_history_prompt_messages(max_token_limit=max_token_limit, message_limit=message_limit)
-
-        string_messages = []
-        for m in prompt_messages:
-            if m.role == PromptMessageRole.USER:
-                role = human_prefix
-            elif m.role == PromptMessageRole.ASSISTANT:
-                role = ai_prefix
-            else:
-                continue
-
-            if isinstance(m.content, list):
-                inner_msg = ""
-                for content in m.content:
-                    if isinstance(content, TextPromptMessageContent):
-                        inner_msg += f"{content.data}\n"
-                    elif isinstance(content, ImagePromptMessageContent):
-                        inner_msg += "[image]\n"
-
-                string_messages.append(f"{role}: {inner_msg.strip()}")
-            else:
-                message = f"{role}: {m.content}"
-                string_messages.append(message)
-
-        return "\n".join(string_messages)

api/core/plugin/impl/endpoint.py

@@ -1,5 +1,6 @@
 from core.plugin.entities.endpoint import EndpointEntityWithInstance
 from core.plugin.impl.base import BasePluginClient
+from core.plugin.impl.exc import PluginDaemonInternalServerError
 
 
 class PluginEndpointClient(BasePluginClient):
@@ -70,18 +71,27 @@ class PluginEndpointClient(BasePluginClient):
     def delete_endpoint(self, tenant_id: str, user_id: str, endpoint_id: str):
         """
         Delete the given endpoint.
+
+        This operation is idempotent: if the endpoint is already deleted (record not found),
+        it will return True instead of raising an error.
         """
-        return self._request_with_plugin_daemon_response(
-            "POST",
-            f"plugin/{tenant_id}/endpoint/remove",
-            bool,
-            data={
-                "endpoint_id": endpoint_id,
-            },
-            headers={
-                "Content-Type": "application/json",
-            },
-        )
+        try:
+            return self._request_with_plugin_daemon_response(
+                "POST",
+                f"plugin/{tenant_id}/endpoint/remove",
+                bool,
+                data={
+                    "endpoint_id": endpoint_id,
+                },
+                headers={
+                    "Content-Type": "application/json",
+                },
+            )
+        except PluginDaemonInternalServerError as e:
+            # Make delete idempotent: if record is not found, consider it a success
+            if "record not found" in str(e.description).lower():
+                return True
+            raise
 
     def enable_endpoint(self, tenant_id: str, user_id: str, endpoint_id: str):
         """

api/core/prompt/advanced_prompt_transform.py

@@ -5,7 +5,7 @@ from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEnti
 from core.file import file_manager
 from core.file.models import File
 from core.helper.code_executor.jinja2.jinja2_formatter import Jinja2Formatter
-from core.memory.token_buffer_memory import TokenBufferMemory
+from core.memory.base import BaseMemory
 from core.model_runtime.entities import (
     AssistantPromptMessage,
     PromptMessage,
@@ -43,7 +43,7 @@ class AdvancedPromptTransform(PromptTransform):
         files: Sequence[File],
         context: str | None,
         memory_config: MemoryConfig | None,
-        memory: TokenBufferMemory | None,
+        memory: BaseMemory | None,
         model_config: ModelConfigWithCredentialsEntity,
         image_detail_config: ImagePromptMessageContent.DETAIL | None = None,
     ) -> list[PromptMessage]:
@@ -84,7 +84,7 @@ class AdvancedPromptTransform(PromptTransform):
         files: Sequence[File],
         context: str | None,
         memory_config: MemoryConfig | None,
-        memory: TokenBufferMemory | None,
+        memory: BaseMemory | None,
         model_config: ModelConfigWithCredentialsEntity,
         image_detail_config: ImagePromptMessageContent.DETAIL | None = None,
     ) -> list[PromptMessage]:
@@ -145,7 +145,7 @@ class AdvancedPromptTransform(PromptTransform):
         files: Sequence[File],
         context: str | None,
         memory_config: MemoryConfig | None,
-        memory: TokenBufferMemory | None,
+        memory: BaseMemory | None,
         model_config: ModelConfigWithCredentialsEntity,
         image_detail_config: ImagePromptMessageContent.DETAIL | None = None,
     ) -> list[PromptMessage]:
@@ -270,7 +270,7 @@ class AdvancedPromptTransform(PromptTransform):
 
     def _set_histories_variable(
         self,
-        memory: TokenBufferMemory,
+        memory: BaseMemory,
         memory_config: MemoryConfig,
         raw_prompt: str,
         role_prefix: MemoryConfig.RolePrefix,

api/core/prompt/entities/advanced_prompt_entities.py

@@ -1,3 +1,4 @@
+from enum import StrEnum
 from typing import Literal
 
 from pydantic import BaseModel
@@ -5,6 +6,13 @@ from pydantic import BaseModel
 from core.model_runtime.entities.message_entities import PromptMessageRole
 
 
+class MemoryMode(StrEnum):
+    """Memory mode for LLM nodes."""
+
+    CONVERSATION = "conversation"  # Use TokenBufferMemory (default, existing behavior)
+    NODE = "node"  # Use NodeTokenBufferMemory (Chatflow only)
+
+
 class ChatModelMessage(BaseModel):
     """
     Chat Message.
@@ -48,3 +56,4 @@ class MemoryConfig(BaseModel):
     role_prefix: RolePrefix | None = None
     window: WindowConfig
     query_prompt_template: str | None = None
+    mode: MemoryMode = MemoryMode.CONVERSATION

api/core/prompt/prompt_transform.py

@@ -1,7 +1,7 @@
 from typing import Any
 
 from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEntity
-from core.memory.token_buffer_memory import TokenBufferMemory
+from core.memory.base import BaseMemory
 from core.model_manager import ModelInstance
 from core.model_runtime.entities.message_entities import PromptMessage
 from core.model_runtime.entities.model_entities import ModelPropertyKey
@@ -11,7 +11,7 @@ from core.prompt.entities.advanced_prompt_entities import MemoryConfig
 class PromptTransform:
     def _append_chat_histories(
         self,
-        memory: TokenBufferMemory,
+        memory: BaseMemory,
         memory_config: MemoryConfig,
         prompt_messages: list[PromptMessage],
         model_config: ModelConfigWithCredentialsEntity,
@@ -52,7 +52,7 @@ class PromptTransform:
 
     def _get_history_messages_from_memory(
         self,
-        memory: TokenBufferMemory,
+        memory: BaseMemory,
         memory_config: MemoryConfig,
         max_token_limit: int,
         human_prefix: str | None = None,
@@ -73,7 +73,7 @@ class PromptTransform:
         return memory.get_history_prompt_text(**kwargs)
 
     def _get_history_messages_list_from_memory(
-        self, memory: TokenBufferMemory, memory_config: MemoryConfig, max_token_limit: int
+        self, memory: BaseMemory, memory_config: MemoryConfig, max_token_limit: int
     ) -> list[PromptMessage]:
         """Get memory messages."""
         return list(

api/core/tools/tool_manager.py

@@ -1047,6 +1047,8 @@ class ToolManager:
                         continue
                     tool_input = ToolNodeData.ToolInput.model_validate(tool_configurations.get(parameter.name, {}))
                     if tool_input.type == "variable":
+                        if not isinstance(tool_input.value, list):
+                            raise ToolParameterError(f"Invalid variable selector for {parameter.name}")
                         variable = variable_pool.get(tool_input.value)
                         if variable is None:
                             raise ToolParameterError(f"Variable {tool_input.value} does not exist")
@@ -1056,6 +1058,11 @@ class ToolManager:
                     elif tool_input.type == "mixed":
                         segment_group = variable_pool.convert_template(str(tool_input.value))
                         parameter_value = segment_group.text
+                    elif tool_input.type == "mention":
+                        # Mention type not supported in agent mode
+                        raise ToolParameterError(
+                            f"Mention type not supported in agent for parameter '{parameter.name}'"
+                        )
                     else:
                         raise ToolParameterError(f"Unknown tool input type '{tool_input.type}'")
                     runtime_parameters[parameter.name] = parameter_value

api/core/variables/__init__.py

@@ -4,6 +4,7 @@ from .segments import (
     ArrayFileSegment,
     ArrayNumberSegment,
     ArrayObjectSegment,
+    ArrayPromptMessageSegment,
     ArraySegment,
     ArrayStringSegment,
     FileSegment,
@@ -20,6 +21,7 @@ from .variables import (
     ArrayFileVariable,
     ArrayNumberVariable,
     ArrayObjectVariable,
+    ArrayPromptMessageVariable,
     ArrayStringVariable,
     ArrayVariable,
     FileVariable,
@@ -42,6 +44,8 @@ __all__ = [
     "ArrayNumberVariable",
     "ArrayObjectSegment",
     "ArrayObjectVariable",
+    "ArrayPromptMessageSegment",
+    "ArrayPromptMessageVariable",
     "ArraySegment",
     "ArrayStringSegment",
     "ArrayStringVariable",

api/core/variables/segments.py

@@ -6,6 +6,7 @@ from typing import Annotated, Any, TypeAlias
 from pydantic import BaseModel, ConfigDict, Discriminator, Tag, field_validator
 
 from core.file import File
+from core.model_runtime.entities import PromptMessage
 
 from .types import SegmentType
 
@@ -208,6 +209,15 @@ class ArrayBooleanSegment(ArraySegment):
     value: Sequence[bool]
 
 
+class ArrayPromptMessageSegment(ArraySegment):
+    value_type: SegmentType = SegmentType.ARRAY_PROMPT_MESSAGE
+    value: Sequence[PromptMessage]
+
+    def to_object(self):
+        """Convert to JSON-serializable format for database storage and frontend."""
+        return [msg.model_dump() for msg in self.value]
+
+
 def get_segment_discriminator(v: Any) -> SegmentType | None:
     if isinstance(v, Segment):
         return v.value_type
@@ -248,6 +258,7 @@ SegmentUnion: TypeAlias = Annotated[
         | Annotated[ArrayObjectSegment, Tag(SegmentType.ARRAY_OBJECT)]
         | Annotated[ArrayFileSegment, Tag(SegmentType.ARRAY_FILE)]
         | Annotated[ArrayBooleanSegment, Tag(SegmentType.ARRAY_BOOLEAN)]
+        | Annotated[ArrayPromptMessageSegment, Tag(SegmentType.ARRAY_PROMPT_MESSAGE)]
     ),
     Discriminator(get_segment_discriminator),
 ]

api/core/variables/types.py

@@ -45,6 +45,7 @@ class SegmentType(StrEnum):
     ARRAY_OBJECT = "array[object]"
     ARRAY_FILE = "array[file]"
     ARRAY_BOOLEAN = "array[boolean]"
+    ARRAY_PROMPT_MESSAGE = "array[message]"
 
     NONE = "none"
 

api/core/variables/utils.py

@@ -3,8 +3,10 @@ from typing import Any
 
 import orjson
 
+from core.model_runtime.entities import PromptMessage
+
 from .segment_group import SegmentGroup
-from .segments import ArrayFileSegment, FileSegment, Segment
+from .segments import ArrayFileSegment, ArrayPromptMessageSegment, FileSegment, Segment
 
 
 def to_selector(node_id: str, name: str, paths: Iterable[str] = ()) -> Sequence[str]:
@@ -16,7 +18,7 @@ def to_selector(node_id: str, name: str, paths: Iterable[str] = ()) -> Sequence[
 
 def segment_orjson_default(o: Any):
     """Default function for orjson serialization of Segment types"""
-    if isinstance(o, ArrayFileSegment):
+    if isinstance(o, (ArrayFileSegment, ArrayPromptMessageSegment)):
         return [v.model_dump() for v in o.value]
     elif isinstance(o, FileSegment):
         return o.value.model_dump()
@@ -24,6 +26,8 @@ def segment_orjson_default(o: Any):
         return [segment_orjson_default(seg) for seg in o.value]
     elif isinstance(o, Segment):
         return o.value
+    elif isinstance(o, PromptMessage):
+        return o.model_dump()
     raise TypeError(f"Object of type {type(o).__name__} is not JSON serializable")
 
 

api/core/variables/variables.py

@@ -12,6 +12,7 @@ from .segments import (
     ArrayFileSegment,
     ArrayNumberSegment,
     ArrayObjectSegment,
+    ArrayPromptMessageSegment,
     ArraySegment,
     ArrayStringSegment,
     BooleanSegment,
@@ -110,6 +111,10 @@ class ArrayBooleanVariable(ArrayBooleanSegment, ArrayVariable):
     pass
 
 
+class ArrayPromptMessageVariable(ArrayPromptMessageSegment, ArrayVariable):
+    pass
+
+
 class RAGPipelineVariable(BaseModel):
     belong_to_node_id: str = Field(description="belong to which node id, shared means public")
     type: str = Field(description="variable type, text-input, paragraph, select, number,  file, file-list")
@@ -160,6 +165,7 @@ Variable: TypeAlias = Annotated[
         | Annotated[ArrayObjectVariable, Tag(SegmentType.ARRAY_OBJECT)]
         | Annotated[ArrayFileVariable, Tag(SegmentType.ARRAY_FILE)]
         | Annotated[ArrayBooleanVariable, Tag(SegmentType.ARRAY_BOOLEAN)]
+        | Annotated[ArrayPromptMessageVariable, Tag(SegmentType.ARRAY_PROMPT_MESSAGE)]
         | Annotated[SecretVariable, Tag(SegmentType.SECRET)]
     ),
     Discriminator(get_segment_discriminator),

api/core/workflow/enums.py

@@ -63,6 +63,7 @@ class NodeType(StrEnum):
     TRIGGER_SCHEDULE = "trigger-schedule"
     TRIGGER_PLUGIN = "trigger-plugin"
     HUMAN_INPUT = "human-input"
+    GROUP = "group"
 
     @property
     def is_trigger_node(self) -> bool:
@@ -252,6 +253,7 @@ class WorkflowNodeExecutionMetadataKey(StrEnum):
     LOOP_VARIABLE_MAP = "loop_variable_map"  # single loop variable output
     DATASOURCE_INFO = "datasource_info"
     COMPLETED_REASON = "completed_reason"  # completed reason for loop node
+    MENTION_PARENT_ID = "mention_parent_id"  # parent node id for extractor nodes
 
 
 class WorkflowNodeExecutionStatus(StrEnum):

api/core/workflow/graph/graph.py

@@ -307,7 +307,14 @@ class Graph:
         if not node_configs:
             raise ValueError("Graph must have at least one node")
 
-        node_configs = [node_config for node_config in node_configs if node_config.get("type", "") != "custom-note"]
+        # Filter out UI-only node types:
+        # - custom-note: top-level type (node_config.type == "custom-note")
+        # - group: data-level type (node_config.data.type == "group")
+        node_configs = [
+            node_config
+            for node_config in node_configs
+            if node_config.get("type", "") != "custom-note" and node_config.get("data", {}).get("type", "") != "group"
+        ]
 
         # Parse node configurations
         node_configs_map = cls._parse_node_configs(node_configs)

api/core/workflow/graph_engine/event_management/event_handlers.py

@@ -93,8 +93,8 @@ class EventHandler:
         Args:
             event: The event to handle
         """
-        # Events in loops or iterations are always collected
-        if event.in_loop_id or event.in_iteration_id:
+        # Events in loops, iterations, or extractor groups are always collected
+        if event.in_loop_id or event.in_iteration_id or event.in_mention_parent_id:
             self._event_collector.collect(event)
             return
         return self._dispatch(event)
@@ -125,6 +125,11 @@ class EventHandler:
         Args:
             event: The node started event
         """
+        # Check if this is an extractor node (has parent_node_id)
+        if self._is_extractor_node(event.node_id):
+            self._handle_extractor_node_started(event)
+            return
+
         # Track execution in domain model
         node_execution = self._graph_execution.get_or_create_node_execution(event.node_id)
         is_initial_attempt = node_execution.retry_count == 0
@@ -164,6 +169,11 @@ class EventHandler:
         Args:
             event: The node succeeded event
         """
+        # Check if this is an extractor node (has parent_node_id)
+        if self._is_extractor_node(event.node_id):
+            self._handle_extractor_node_success(event)
+            return
+
         # Update domain model
         node_execution = self._graph_execution.get_or_create_node_execution(event.node_id)
         node_execution.mark_taken()
@@ -226,6 +236,11 @@ class EventHandler:
         Args:
             event: The node failed event
         """
+        # Check if this is an extractor node (has parent_node_id)
+        if self._is_extractor_node(event.node_id):
+            self._handle_extractor_node_failed(event)
+            return
+
         # Update domain model
         node_execution = self._graph_execution.get_or_create_node_execution(event.node_id)
         node_execution.mark_failed(event.error)
@@ -345,3 +360,57 @@ class EventHandler:
                     self._graph_runtime_state.set_output("answer", value)
             else:
                 self._graph_runtime_state.set_output(key, value)
+
+    def _is_extractor_node(self, node_id: str) -> bool:
+        """
+        Check if node_id represents an extractor node (has parent_node_id).
+
+        Extractor nodes extract values from list[PromptMessage] for their parent node.
+        They have a parent_node_id field pointing to their parent node.
+        """
+        node = self._graph.nodes.get(node_id)
+        if node is None:
+            return False
+        return node.node_data.is_extractor_node
+
+    def _handle_extractor_node_started(self, event: NodeRunStartedEvent) -> None:
+        """
+        Handle extractor node started event.
+
+        Extractor nodes don't need full execution tracking, just collect the event.
+        """
+        # Track in response coordinator for stream ordering
+        self._response_coordinator.track_node_execution(event.node_id, event.id)
+
+        # Collect the event
+        self._event_collector.collect(event)
+
+    def _handle_extractor_node_success(self, event: NodeRunSucceededEvent) -> None:
+        """
+        Handle extractor node success event.
+
+        Extractor nodes need special handling:
+        - Store outputs in variable pool (for reference by other nodes)
+        - Accumulate token usage
+        - Collect the event for logging
+        - Do NOT process edges or enqueue next nodes (parent node handles that)
+        """
+        self._accumulate_node_usage(event.node_run_result.llm_usage)
+
+        # Store outputs in variable pool
+        self._store_node_outputs(event.node_id, event.node_run_result.outputs)
+
+        # Collect the event
+        self._event_collector.collect(event)
+
+    def _handle_extractor_node_failed(self, event: NodeRunFailedEvent) -> None:
+        """
+        Handle extractor node failed event.
+
+        Extractor node failures are collected for logging,
+        but the parent node is responsible for handling the error.
+        """
+        self._accumulate_node_usage(event.node_run_result.llm_usage)
+
+        # Collect the event for logging
+        self._event_collector.collect(event)

api/core/workflow/graph_engine/layers/persistence.py

@@ -68,6 +68,7 @@ class _NodeRuntimeSnapshot:
     predecessor_node_id: str | None
     iteration_id: str | None
     loop_id: str | None
+    mention_parent_id: str | None
     created_at: datetime
 
 
@@ -230,6 +231,7 @@ class WorkflowPersistenceLayer(GraphEngineLayer):
         metadata = {
             WorkflowNodeExecutionMetadataKey.ITERATION_ID: event.in_iteration_id,
             WorkflowNodeExecutionMetadataKey.LOOP_ID: event.in_loop_id,
+            WorkflowNodeExecutionMetadataKey.MENTION_PARENT_ID: event.in_mention_parent_id,
         }
 
         domain_execution = WorkflowNodeExecution(
@@ -256,6 +258,7 @@ class WorkflowPersistenceLayer(GraphEngineLayer):
             predecessor_node_id=event.predecessor_node_id,
             iteration_id=event.in_iteration_id,
             loop_id=event.in_loop_id,
+            mention_parent_id=event.in_mention_parent_id,
             created_at=event.start_at,
         )
         self._node_snapshots[event.id] = snapshot

api/core/workflow/graph_events/base.py

@@ -21,6 +21,12 @@ class GraphNodeEventBase(GraphEngineEvent):
     """iteration id if node is in iteration"""
     in_loop_id: str | None = None
     """loop id if node is in loop"""
+    in_mention_parent_id: str | None = None
+    """Parent node id if this is an extractor node event.
+    
+    When set, indicates this event belongs to an extractor node that
+    is extracting values for the specified parent node.
+    """
 
     # The version of the node, or "1" if not specified.
     node_version: str = "1"

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

@@ -12,11 +12,14 @@ from sqlalchemy.orm import Session
 from core.agent.entities import AgentToolEntity
 from core.agent.plugin_entities import AgentStrategyParameter
 from core.file import File, FileTransferMethod
+from core.memory.base import BaseMemory
+from core.memory.node_token_buffer_memory import NodeTokenBufferMemory
 from core.memory.token_buffer_memory import TokenBufferMemory
 from core.model_manager import ModelInstance, ModelManager
 from core.model_runtime.entities.llm_entities import LLMUsage, LLMUsageMetadata
 from core.model_runtime.entities.model_entities import AIModelEntity, ModelType
 from core.model_runtime.utils.encoders import jsonable_encoder
+from core.prompt.entities.advanced_prompt_entities import MemoryMode
 from core.provider_manager import ProviderManager
 from core.tools.entities.tool_entities import (
     ToolIdentity,
@@ -136,6 +139,9 @@ class AgentNode(Node[AgentNodeData]):
             )
             return
 
+        # Fetch memory for node memory saving
+        memory = self._fetch_memory_for_save()
+
         try:
             yield from self._transform_message(
                 messages=message_stream,
@@ -149,6 +155,7 @@ class AgentNode(Node[AgentNodeData]):
                 node_type=self.node_type,
                 node_id=self._node_id,
                 node_execution_id=self.id,
+                memory=memory,
             )
         except PluginDaemonClientSideError as e:
             transform_error = AgentMessageTransformError(
@@ -395,8 +402,20 @@ class AgentNode(Node[AgentNodeData]):
             icon = None
         return icon
 
-    def _fetch_memory(self, model_instance: ModelInstance) -> TokenBufferMemory | None:
-        # get conversation id
+    def _fetch_memory(self, model_instance: ModelInstance) -> BaseMemory | None:
+        """
+        Fetch memory based on configuration mode.
+
+        Returns TokenBufferMemory for conversation mode (default),
+        or NodeTokenBufferMemory for node mode (Chatflow only).
+        """
+        node_data = self.node_data
+        memory_config = node_data.memory
+
+        if not memory_config:
+            return None
+
+        # get conversation id (required for both modes in Chatflow)
         conversation_id_variable = self.graph_runtime_state.variable_pool.get(
             ["sys", SystemVariableKey.CONVERSATION_ID]
         )
@@ -404,16 +423,26 @@ class AgentNode(Node[AgentNodeData]):
             return None
         conversation_id = conversation_id_variable.value
 
-        with Session(db.engine, expire_on_commit=False) as session:
-            stmt = select(Conversation).where(Conversation.app_id == self.app_id, Conversation.id == conversation_id)
-            conversation = session.scalar(stmt)
-
-            if not conversation:
-                return None
-
-        memory = TokenBufferMemory(conversation=conversation, model_instance=model_instance)
-
-        return memory
+        # Return appropriate memory type based on mode
+        if memory_config.mode == MemoryMode.NODE:
+            # Node-level memory (Chatflow only)
+            return NodeTokenBufferMemory(
+                app_id=self.app_id,
+                conversation_id=conversation_id,
+                node_id=self._node_id,
+                tenant_id=self.tenant_id,
+                model_instance=model_instance,
+            )
+        else:
+            # Conversation-level memory (default)
+            with Session(db.engine, expire_on_commit=False) as session:
+                stmt = select(Conversation).where(
+                    Conversation.app_id == self.app_id, Conversation.id == conversation_id
+                )
+                conversation = session.scalar(stmt)
+                if not conversation:
+                    return None
+            return TokenBufferMemory(conversation=conversation, model_instance=model_instance)
 
     def _fetch_model(self, value: dict[str, Any]) -> tuple[ModelInstance, AIModelEntity | None]:
         provider_manager = ProviderManager()
@@ -457,6 +486,47 @@ class AgentNode(Node[AgentNodeData]):
         else:
             return [tool for tool in tools if tool.get("type") != ToolProviderType.MCP]
 
+    def _fetch_memory_for_save(self) -> BaseMemory | None:
+        """
+        Fetch memory instance for saving node memory.
+        This is a simplified version that doesn't require model_instance.
+        """
+        from core.model_manager import ModelManager
+        from core.model_runtime.entities.model_entities import ModelType
+
+        node_data = self.node_data
+        if not node_data.memory:
+            return None
+
+        # Get conversation_id
+        conversation_id_var = self.graph_runtime_state.variable_pool.get(["sys", SystemVariableKey.CONVERSATION_ID])
+        if not isinstance(conversation_id_var, StringSegment):
+            return None
+        conversation_id = conversation_id_var.value
+
+        # Return appropriate memory type based on mode
+        if node_data.memory.mode == MemoryMode.NODE:
+            # For node memory, we need a model_instance for token counting
+            # Use a simple default model for this purpose
+            try:
+                model_instance = ModelManager().get_default_model_instance(
+                    tenant_id=self.tenant_id,
+                    model_type=ModelType.LLM,
+                )
+            except Exception:
+                return None
+
+            return NodeTokenBufferMemory(
+                app_id=self.app_id,
+                conversation_id=conversation_id,
+                node_id=self._node_id,
+                tenant_id=self.tenant_id,
+                model_instance=model_instance,
+            )
+        else:
+            # Conversation-level memory doesn't need saving here
+            return None
+
     def _transform_message(
         self,
         messages: Generator[ToolInvokeMessage, None, None],
@@ -467,6 +537,7 @@ class AgentNode(Node[AgentNodeData]):
         node_type: NodeType,
         node_id: str,
         node_execution_id: str,
+        memory: BaseMemory | None = None,
     ) -> Generator[NodeEventBase, None, None]:
         """
         Convert ToolInvokeMessages into tuple[plain_text, files]
@@ -711,6 +782,21 @@ class AgentNode(Node[AgentNodeData]):
                 is_final=True,
             )
 
+        # Save to node memory if in node memory mode
+        from core.workflow.nodes.llm import llm_utils
+
+        # Get user query from sys.query
+        user_query_var = self.graph_runtime_state.variable_pool.get(["sys", SystemVariableKey.QUERY])
+        user_query = user_query_var.text if user_query_var else ""
+
+        llm_utils.save_node_memory(
+            memory=memory,
+            variable_pool=self.graph_runtime_state.variable_pool,
+            user_query=user_query,
+            assistant_response=text,
+            assistant_files=files,
+        )
+
         yield StreamCompletedEvent(
             node_run_result=NodeRunResult(
                 status=WorkflowNodeExecutionStatus.SUCCEEDED,

api/core/workflow/nodes/base/__init__.py

@@ -1,4 +1,10 @@
-from .entities import BaseIterationNodeData, BaseIterationState, BaseLoopNodeData, BaseLoopState, BaseNodeData
+from .entities import (
+    BaseIterationNodeData,
+    BaseIterationState,
+    BaseLoopNodeData,
+    BaseLoopState,
+    BaseNodeData,
+)
 from .usage_tracking_mixin import LLMUsageTrackingMixin
 
 __all__ = [

api/core/workflow/nodes/base/entities.py

@@ -175,6 +175,16 @@ class BaseNodeData(ABC, BaseModel):
     default_value: list[DefaultValue] | None = None
     retry_config: RetryConfig = RetryConfig()
 
+    # Parent node ID when this node is used as an extractor.
+    # If set, this node is an "attached" extractor node that extracts values
+    # from list[PromptMessage] for the parent node's parameters.
+    parent_node_id: str | None = None
+
+    @property
+    def is_extractor_node(self) -> bool:
+        """Check if this node is an extractor node (has parent_node_id)."""
+        return self.parent_node_id is not None
+
     @property
     def default_value_dict(self) -> dict[str, Any]:
         if self.default_value:

api/core/workflow/nodes/base/node.py

@@ -270,10 +270,87 @@ class Node(Generic[NodeDataT]):
         """Check if execution should be stopped."""
         return self.graph_runtime_state.stop_event.is_set()
 
+    def _find_extractor_node_configs(self) -> list[dict[str, Any]]:
+        """
+        Find all extractor node configurations that have parent_node_id == self._node_id.
+
+        Returns:
+            List of node configuration dicts for extractor nodes
+        """
+        nodes = self.graph_config.get("nodes", [])
+        extractor_configs = []
+        for node_config in nodes:
+            node_data = node_config.get("data", {})
+            if node_data.get("parent_node_id") == self._node_id:
+                extractor_configs.append(node_config)
+        return extractor_configs
+
+    def _execute_extractor_nodes(self) -> Generator[GraphNodeEventBase, None, None]:
+        """
+        Execute all extractor nodes associated with this node.
+
+        Extractor nodes are nodes with parent_node_id == self._node_id.
+        They are executed before the main node to extract values from list[PromptMessage].
+        """
+        from core.workflow.nodes.node_mapping import LATEST_VERSION, NODE_TYPE_CLASSES_MAPPING
+
+        extractor_configs = self._find_extractor_node_configs()
+        logger.debug("[Extractor] Found %d extractor nodes for parent '%s'", len(extractor_configs), self._node_id)
+        if not extractor_configs:
+            return
+
+        for config in extractor_configs:
+            node_id = config.get("id")
+            node_data = config.get("data", {})
+            node_type_str = node_data.get("type")
+
+            if not node_id or not node_type_str:
+                continue
+
+            # Get node class
+            try:
+                node_type = NodeType(node_type_str)
+            except ValueError:
+                continue
+
+            node_mapping = NODE_TYPE_CLASSES_MAPPING.get(node_type)
+            if not node_mapping:
+                continue
+
+            node_version = str(node_data.get("version", "1"))
+            node_cls = node_mapping.get(node_version) or node_mapping.get(LATEST_VERSION)
+            if not node_cls:
+                continue
+
+            # Instantiate and execute the extractor node
+            extractor_node = node_cls(
+                id=node_id,
+                config=config,
+                graph_init_params=self._graph_init_params,
+                graph_runtime_state=self.graph_runtime_state,
+            )
+
+            # Execute and process extractor node events
+            for event in extractor_node.run():
+                # Tag event with parent node id for stream ordering and history tracking
+                if isinstance(event, GraphNodeEventBase):
+                    event.in_mention_parent_id = self._node_id
+
+                if isinstance(event, NodeRunSucceededEvent):
+                    # Store extractor node outputs in variable pool
+                    outputs: Mapping[str, Any] = event.node_run_result.outputs
+                    for variable_name, variable_value in outputs.items():
+                        self.graph_runtime_state.variable_pool.add((node_id, variable_name), variable_value)
+                if not isinstance(event, NodeRunStreamChunkEvent):
+                    yield event
+
     def run(self) -> Generator[GraphNodeEventBase, None, None]:
         execution_id = self.ensure_execution_id()
         self._start_at = naive_utc_now()
 
+        # Step 1: Execute associated extractor nodes before main node execution
+        yield from self._execute_extractor_nodes()
+
         # Create and push start event with required fields
         start_event = NodeRunStartedEvent(
             id=execution_id,

api/core/workflow/nodes/llm/entities.py

@@ -1,7 +1,7 @@
 from collections.abc import Mapping, Sequence
-from typing import Any, Literal
+from typing import Annotated, Any, Literal, TypeAlias
 
-from pydantic import BaseModel, Field, field_validator
+from pydantic import BaseModel, ConfigDict, Field, field_validator
 
 from core.model_runtime.entities import ImagePromptMessageContent, LLMMode
 from core.prompt.entities.advanced_prompt_entities import ChatModelMessage, CompletionModelPromptTemplate, MemoryConfig
@@ -58,9 +58,28 @@ class LLMNodeCompletionModelPromptTemplate(CompletionModelPromptTemplate):
     jinja2_text: str | None = None
 
 
+class PromptMessageContext(BaseModel):
+    """Context variable reference in prompt template.
+
+    YAML/JSON format: { "$context": ["node_id", "variable_name"] }
+    This will be expanded to list[PromptMessage] at runtime.
+    """
+
+    model_config = ConfigDict(populate_by_name=True)
+
+    value_selector: Sequence[str] = Field(alias="$context")
+
+
+# Union type for prompt template items (static message or context variable reference)
+PromptTemplateItem: TypeAlias = Annotated[
+    LLMNodeChatModelMessage | PromptMessageContext,
+    Field(discriminator=None),
+]
+
+
 class LLMNodeData(BaseNodeData):
     model: ModelConfig
-    prompt_template: Sequence[LLMNodeChatModelMessage] | LLMNodeCompletionModelPromptTemplate
+    prompt_template: Sequence[PromptTemplateItem] | LLMNodeCompletionModelPromptTemplate
     prompt_config: PromptConfig = Field(default_factory=PromptConfig)
     memory: MemoryConfig | None = None
     context: ContextConfig

api/core/workflow/nodes/llm/llm_utils.py

@@ -8,12 +8,13 @@ from configs import dify_config
 from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEntity
 from core.entities.provider_entities import ProviderQuotaType, QuotaUnit
 from core.file.models import File
-from core.memory.token_buffer_memory import TokenBufferMemory
+from core.memory import NodeTokenBufferMemory, TokenBufferMemory
+from core.memory.base import BaseMemory
 from core.model_manager import ModelInstance, ModelManager
 from core.model_runtime.entities.llm_entities import LLMUsage
 from core.model_runtime.entities.model_entities import ModelType
 from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
-from core.prompt.entities.advanced_prompt_entities import MemoryConfig
+from core.prompt.entities.advanced_prompt_entities import MemoryConfig, MemoryMode
 from core.variables.segments import ArrayAnySegment, ArrayFileSegment, FileSegment, NoneSegment, StringSegment
 from core.workflow.enums import SystemVariableKey
 from core.workflow.nodes.llm.entities import ModelConfig
@@ -86,25 +87,100 @@ def fetch_files(variable_pool: VariablePool, selector: Sequence[str]) -> Sequenc
 
 
 def fetch_memory(
-    variable_pool: VariablePool, app_id: str, node_data_memory: MemoryConfig | None, model_instance: ModelInstance
-) -> TokenBufferMemory | None:
+    variable_pool: VariablePool,
+    app_id: str,
+    tenant_id: str,
+    node_data_memory: MemoryConfig | None,
+    model_instance: ModelInstance,
+    node_id: str = "",
+) -> BaseMemory | None:
+    """
+    Fetch memory based on configuration mode.
+
+    Returns TokenBufferMemory for conversation mode (default),
+    or NodeTokenBufferMemory for node mode (Chatflow only).
+
+    :param variable_pool: Variable pool containing system variables
+    :param app_id: Application ID
+    :param tenant_id: Tenant ID
+    :param node_data_memory: Memory configuration
+    :param model_instance: Model instance for token counting
+    :param node_id: Node ID in the workflow (required for node mode)
+    :return: Memory instance or None if not applicable
+    """
     if not node_data_memory:
         return None
 
-    # get conversation id
+    # Get conversation_id from variable pool (required for both modes in Chatflow)
     conversation_id_variable = variable_pool.get(["sys", SystemVariableKey.CONVERSATION_ID])
     if not isinstance(conversation_id_variable, StringSegment):
         return None
     conversation_id = conversation_id_variable.value
 
-    with Session(db.engine, expire_on_commit=False) as session:
-        stmt = select(Conversation).where(Conversation.app_id == app_id, Conversation.id == conversation_id)
-        conversation = session.scalar(stmt)
-        if not conversation:
+    # Return appropriate memory type based on mode
+    if node_data_memory.mode == MemoryMode.NODE:
+        # Node-level memory (Chatflow only)
+        if not node_id:
             return None
+        return NodeTokenBufferMemory(
+            app_id=app_id,
+            conversation_id=conversation_id,
+            node_id=node_id,
+            tenant_id=tenant_id,
+            model_instance=model_instance,
+        )
+    else:
+        # Conversation-level memory (default)
+        with Session(db.engine, expire_on_commit=False) as session:
+            stmt = select(Conversation).where(Conversation.app_id == app_id, Conversation.id == conversation_id)
+            conversation = session.scalar(stmt)
+            if not conversation:
+                return None
+        return TokenBufferMemory(conversation=conversation, model_instance=model_instance)
 
-    memory = TokenBufferMemory(conversation=conversation, model_instance=model_instance)
-    return memory
+
+def save_node_memory(
+    memory: BaseMemory | None,
+    variable_pool: VariablePool,
+    user_query: str,
+    assistant_response: str,
+    user_files: Sequence["File"] | None = None,
+    assistant_files: Sequence["File"] | None = None,
+) -> None:
+    """
+    Save dialogue turn to node memory if applicable.
+
+    This function handles the storage logic for NodeTokenBufferMemory.
+    For TokenBufferMemory (conversation-level), no action is taken as it uses
+    the Message table which is managed elsewhere.
+
+    :param memory: Memory instance (NodeTokenBufferMemory or TokenBufferMemory)
+    :param variable_pool: Variable pool containing system variables
+    :param user_query: User's input text
+    :param assistant_response: Assistant's response text
+    :param user_files: Files attached by user (optional)
+    :param assistant_files: Files generated by assistant (optional)
+    """
+    if not isinstance(memory, NodeTokenBufferMemory):
+        return
+
+    # Get workflow_run_id as the key for this execution
+    workflow_run_id_var = variable_pool.get(["sys", SystemVariableKey.WORKFLOW_EXECUTION_ID])
+    if not isinstance(workflow_run_id_var, StringSegment):
+        return
+
+    workflow_run_id = workflow_run_id_var.value
+    if not workflow_run_id:
+        return
+
+    memory.add_messages(
+        workflow_run_id=workflow_run_id,
+        user_content=user_query,
+        user_files=list(user_files) if user_files else None,
+        assistant_content=assistant_response,
+        assistant_files=list(assistant_files) if assistant_files else None,
+    )
+    memory.flush()
 
 
 def deduct_llm_quota(tenant_id: str, model_instance: ModelInstance, usage: LLMUsage):

api/core/workflow/nodes/llm/node.py

@@ -7,7 +7,7 @@ import logging
 import re
 import time
 from collections.abc import Generator, Mapping, Sequence
-from typing import TYPE_CHECKING, Any, Literal
+from typing import TYPE_CHECKING, Any, Literal, cast
 
 from sqlalchemy import select
 
@@ -16,10 +16,11 @@ from core.file import File, FileTransferMethod, FileType, file_manager
 from core.helper.code_executor import CodeExecutor, CodeLanguage
 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.memory.token_buffer_memory import TokenBufferMemory
+from core.memory.base import BaseMemory
 from core.model_manager import ModelInstance, ModelManager
 from core.model_runtime.entities import (
     ImagePromptMessageContent,
+    MultiModalPromptMessageContent,
     PromptMessage,
     PromptMessageContentType,
     TextPromptMessageContent,
@@ -51,6 +52,7 @@ from core.rag.entities.citation_metadata import RetrievalSourceMetadata
 from core.tools.signature import sign_upload_file
 from core.variables import (
     ArrayFileSegment,
+    ArrayPromptMessageSegment,
     ArraySegment,
     FileSegment,
     NoneSegment,
@@ -87,6 +89,7 @@ from .entities import (
     LLMNodeCompletionModelPromptTemplate,
     LLMNodeData,
     ModelConfig,
+    PromptMessageContext,
 )
 from .exc import (
     InvalidContextStructureError,
@@ -159,8 +162,9 @@ class LLMNode(Node[LLMNodeData]):
         variable_pool = self.graph_runtime_state.variable_pool
 
         try:
-            # init messages template
-            self.node_data.prompt_template = self._transform_chat_messages(self.node_data.prompt_template)
+            # Parse prompt template to separate static messages and context references
+            prompt_template = self.node_data.prompt_template
+            static_messages, context_refs, template_order = self._parse_prompt_template()
 
             # fetch variables and fetch values from variable pool
             inputs = self._fetch_inputs(node_data=self.node_data)
@@ -208,8 +212,10 @@ class LLMNode(Node[LLMNodeData]):
             memory = llm_utils.fetch_memory(
                 variable_pool=variable_pool,
                 app_id=self.app_id,
+                tenant_id=self.tenant_id,
                 node_data_memory=self.node_data.memory,
                 model_instance=model_instance,
+                node_id=self._node_id,
             )
 
             query: str | None = None
@@ -220,21 +226,40 @@ class LLMNode(Node[LLMNodeData]):
                 ):
                     query = query_variable.text
 
-            prompt_messages, stop = LLMNode.fetch_prompt_messages(
-                sys_query=query,
-                sys_files=files,
-                context=context,
-                memory=memory,
-                model_config=model_config,
-                prompt_template=self.node_data.prompt_template,
-                memory_config=self.node_data.memory,
-                vision_enabled=self.node_data.vision.enabled,
-                vision_detail=self.node_data.vision.configs.detail,
-                variable_pool=variable_pool,
-                jinja2_variables=self.node_data.prompt_config.jinja2_variables,
-                tenant_id=self.tenant_id,
-                context_files=context_files,
-            )
+            # Get prompt messages
+            prompt_messages: Sequence[PromptMessage]
+            stop: Sequence[str] | None
+            if isinstance(prompt_template, list) and context_refs:
+                prompt_messages, stop = self._build_prompt_messages_with_context(
+                    context_refs=context_refs,
+                    template_order=template_order,
+                    static_messages=static_messages,
+                    query=query,
+                    files=files,
+                    context=context,
+                    memory=memory,
+                    model_config=model_config,
+                    context_files=context_files,
+                )
+            else:
+                prompt_messages, stop = LLMNode.fetch_prompt_messages(
+                    sys_query=query,
+                    sys_files=files,
+                    context=context,
+                    memory=memory,
+                    model_config=model_config,
+                    prompt_template=cast(
+                        Sequence[LLMNodeChatModelMessage] | LLMNodeCompletionModelPromptTemplate,
+                        self.node_data.prompt_template,
+                    ),
+                    memory_config=self.node_data.memory,
+                    vision_enabled=self.node_data.vision.enabled,
+                    vision_detail=self.node_data.vision.configs.detail,
+                    variable_pool=variable_pool,
+                    jinja2_variables=self.node_data.prompt_config.jinja2_variables,
+                    tenant_id=self.tenant_id,
+                    context_files=context_files,
+                )
 
             # handle invoke result
             generator = LLMNode.invoke_llm(
@@ -250,6 +275,7 @@ class LLMNode(Node[LLMNodeData]):
                 node_id=self._node_id,
                 node_type=self.node_type,
                 reasoning_format=self.node_data.reasoning_format,
+                tenant_id=self.tenant_id,
             )
 
             structured_output: LLMStructuredOutput | None = None
@@ -301,12 +327,25 @@ class LLMNode(Node[LLMNodeData]):
                 "reasoning_content": reasoning_content,
                 "usage": jsonable_encoder(usage),
                 "finish_reason": finish_reason,
+                "context": self._build_context(prompt_messages, clean_text),
             }
             if structured_output:
                 outputs["structured_output"] = structured_output.structured_output
             if self._file_outputs:
                 outputs["files"] = ArrayFileSegment(value=self._file_outputs)
 
+            # Write to Node Memory if in node memory mode
+            # Resolve the query template to get actual user content
+            actual_query = variable_pool.convert_template(query or "").text
+            llm_utils.save_node_memory(
+                memory=memory,
+                variable_pool=variable_pool,
+                user_query=actual_query,
+                assistant_response=clean_text,
+                user_files=files,
+                assistant_files=self._file_outputs,
+            )
+
             # Send final chunk event to indicate streaming is complete
             yield StreamChunkEvent(
                 selector=[self._node_id, "text"],
@@ -367,6 +406,7 @@ class LLMNode(Node[LLMNodeData]):
         node_id: str,
         node_type: NodeType,
         reasoning_format: Literal["separated", "tagged"] = "tagged",
+        tenant_id: str | None = None,
     ) -> Generator[NodeEventBase | LLMStructuredOutput, None, None]:
         model_schema = model_instance.model_type_instance.get_model_schema(
             node_data_model.name, model_instance.credentials
@@ -390,6 +430,7 @@ class LLMNode(Node[LLMNodeData]):
                 stop=list(stop or []),
                 stream=True,
                 user=user_id,
+                tenant_id=tenant_id,
             )
         else:
             request_start_time = time.perf_counter()
@@ -566,6 +607,48 @@ class LLMNode(Node[LLMNodeData]):
         # Separated mode: always return clean text and reasoning_content
         return clean_text, reasoning_content or ""
 
+    @staticmethod
+    def _build_context(
+        prompt_messages: Sequence[PromptMessage],
+        assistant_response: str,
+    ) -> list[PromptMessage]:
+        """
+        Build context from prompt messages and assistant response.
+        Excludes system messages and includes the current LLM response.
+        Returns list[PromptMessage] for use with ArrayPromptMessageSegment.
+
+        Note: Multi-modal content base64 data is truncated to avoid storing large data in context.
+        """
+        context_messages: list[PromptMessage] = [
+            LLMNode._truncate_multimodal_content(m) for m in prompt_messages if m.role != PromptMessageRole.SYSTEM
+        ]
+        context_messages.append(AssistantPromptMessage(content=assistant_response))
+        return context_messages
+
+    @staticmethod
+    def _truncate_multimodal_content(message: PromptMessage) -> PromptMessage:
+        """
+        Truncate multi-modal content base64 data in a message to avoid storing large data.
+        Preserves the PromptMessage structure for ArrayPromptMessageSegment compatibility.
+        """
+        content = message.content
+        if content is None or isinstance(content, str):
+            return message
+
+        # Process list content, truncating multi-modal base64 data
+        new_content: list[PromptMessageContentUnionTypes] = []
+        for item in content:
+            if isinstance(item, MultiModalPromptMessageContent):
+                # Truncate base64_data similar to prompt_messages_to_prompt_for_saving
+                truncated_base64 = ""
+                if item.base64_data:
+                    truncated_base64 = item.base64_data[:10] + "...[TRUNCATED]..." + item.base64_data[-10:]
+                new_content.append(item.model_copy(update={"base64_data": truncated_base64}))
+            else:
+                new_content.append(item)
+
+        return message.model_copy(update={"content": new_content})
+
     def _transform_chat_messages(
         self, messages: Sequence[LLMNodeChatModelMessage] | LLMNodeCompletionModelPromptTemplate, /
     ) -> Sequence[LLMNodeChatModelMessage] | LLMNodeCompletionModelPromptTemplate:
@@ -581,6 +664,106 @@ class LLMNode(Node[LLMNodeData]):
 
         return messages
 
+    def _parse_prompt_template(
+        self,
+    ) -> tuple[list[LLMNodeChatModelMessage], list[PromptMessageContext], list[tuple[int, str]]]:
+        """
+        Parse prompt_template to separate static messages and context references.
+
+        Returns:
+            Tuple of (static_messages, context_refs, template_order)
+            - static_messages: list of LLMNodeChatModelMessage
+            - context_refs: list of PromptMessageContext
+            - template_order: list of (index, type) tuples preserving original order
+        """
+        prompt_template = self.node_data.prompt_template
+        static_messages: list[LLMNodeChatModelMessage] = []
+        context_refs: list[PromptMessageContext] = []
+        template_order: list[tuple[int, str]] = []
+
+        if isinstance(prompt_template, list):
+            for idx, item in enumerate(prompt_template):
+                if isinstance(item, PromptMessageContext):
+                    context_refs.append(item)
+                    template_order.append((idx, "context"))
+                else:
+                    static_messages.append(item)
+                    template_order.append((idx, "static"))
+            # Transform static messages for jinja2
+            if static_messages:
+                self.node_data.prompt_template = self._transform_chat_messages(static_messages)
+
+        return static_messages, context_refs, template_order
+
+    def _build_prompt_messages_with_context(
+        self,
+        *,
+        context_refs: list[PromptMessageContext],
+        template_order: list[tuple[int, str]],
+        static_messages: list[LLMNodeChatModelMessage],
+        query: str | None,
+        files: Sequence[File],
+        context: str | None,
+        memory: BaseMemory | None,
+        model_config: ModelConfigWithCredentialsEntity,
+        context_files: list[File],
+    ) -> tuple[list[PromptMessage], Sequence[str] | None]:
+        """
+        Build prompt messages by combining static messages and context references in DSL order.
+
+        Returns:
+            Tuple of (prompt_messages, stop_sequences)
+        """
+        variable_pool = self.graph_runtime_state.variable_pool
+
+        # Build a map from context index to its messages
+        context_messages_map: dict[int, list[PromptMessage]] = {}
+        context_idx = 0
+        for idx, type_ in template_order:
+            if type_ == "context":
+                ctx_ref = context_refs[context_idx]
+                ctx_var = variable_pool.get(ctx_ref.value_selector)
+                if ctx_var is None:
+                    raise VariableNotFoundError(f"Variable {'.'.join(ctx_ref.value_selector)} not found")
+                if not isinstance(ctx_var, ArrayPromptMessageSegment):
+                    raise InvalidVariableTypeError(f"Variable {'.'.join(ctx_ref.value_selector)} is not array[message]")
+                context_messages_map[idx] = list(ctx_var.value)
+                context_idx += 1
+
+        # Process static messages
+        static_prompt_messages: Sequence[PromptMessage] = []
+        stop: Sequence[str] | None = None
+        if static_messages:
+            static_prompt_messages, stop = LLMNode.fetch_prompt_messages(
+                sys_query=query,
+                sys_files=files,
+                context=context,
+                memory=memory,
+                model_config=model_config,
+                prompt_template=cast(Sequence[LLMNodeChatModelMessage], self.node_data.prompt_template),
+                memory_config=self.node_data.memory,
+                vision_enabled=self.node_data.vision.enabled,
+                vision_detail=self.node_data.vision.configs.detail,
+                variable_pool=variable_pool,
+                jinja2_variables=self.node_data.prompt_config.jinja2_variables,
+                tenant_id=self.tenant_id,
+                context_files=context_files,
+            )
+
+        # Combine messages according to original DSL order
+        combined_messages: list[PromptMessage] = []
+        static_msg_iter = iter(static_prompt_messages)
+        for idx, type_ in template_order:
+            if type_ == "context":
+                combined_messages.extend(context_messages_map[idx])
+            else:
+                if msg := next(static_msg_iter, None):
+                    combined_messages.append(msg)
+        # Append any remaining static messages (e.g., memory messages)
+        combined_messages.extend(static_msg_iter)
+
+        return combined_messages, stop
+
     def _fetch_jinja_inputs(self, node_data: LLMNodeData) -> dict[str, str]:
         variables: dict[str, Any] = {}
 
@@ -778,7 +961,7 @@ class LLMNode(Node[LLMNodeData]):
         sys_query: str | None = None,
         sys_files: Sequence[File],
         context: str | None = None,
-        memory: TokenBufferMemory | None = None,
+        memory: BaseMemory | None = None,
         model_config: ModelConfigWithCredentialsEntity,
         prompt_template: Sequence[LLMNodeChatModelMessage] | LLMNodeCompletionModelPromptTemplate,
         memory_config: MemoryConfig | None = None,
@@ -1337,7 +1520,7 @@ def _calculate_rest_token(
 
 def _handle_memory_chat_mode(
     *,
-    memory: TokenBufferMemory | None,
+    memory: BaseMemory | None,
     memory_config: MemoryConfig | None,
     model_config: ModelConfigWithCredentialsEntity,
 ) -> Sequence[PromptMessage]:
@@ -1354,7 +1537,7 @@ def _handle_memory_chat_mode(
 
 def _handle_memory_completion_mode(
     *,
-    memory: TokenBufferMemory | None,
+    memory: BaseMemory | None,
     memory_config: MemoryConfig | None,
     model_config: ModelConfigWithCredentialsEntity,
 ) -> str:

api/core/workflow/nodes/parameter_extractor/parameter_extractor_node.py

@@ -7,7 +7,7 @@ from typing import Any, cast
 
 from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEntity
 from core.file import File
-from core.memory.token_buffer_memory import TokenBufferMemory
+from core.memory.base import BaseMemory
 from core.model_manager import ModelInstance
 from core.model_runtime.entities import ImagePromptMessageContent
 from core.model_runtime.entities.llm_entities import LLMUsage
@@ -145,8 +145,10 @@ class ParameterExtractorNode(Node[ParameterExtractorNodeData]):
         memory = llm_utils.fetch_memory(
             variable_pool=variable_pool,
             app_id=self.app_id,
+            tenant_id=self.tenant_id,
             node_data_memory=node_data.memory,
             model_instance=model_instance,
+            node_id=self._node_id,
         )
 
         if (
@@ -244,6 +246,14 @@ class ParameterExtractorNode(Node[ParameterExtractorNodeData]):
         # transform result into standard format
         result = self._transform_result(data=node_data, result=result or {})
 
+        # Save to node memory if in node memory mode
+        llm_utils.save_node_memory(
+            memory=memory,
+            variable_pool=variable_pool,
+            user_query=query,
+            assistant_response=json.dumps(result, ensure_ascii=False),
+        )
+
         return NodeRunResult(
             status=WorkflowNodeExecutionStatus.SUCCEEDED,
             inputs=inputs,
@@ -299,7 +309,7 @@ class ParameterExtractorNode(Node[ParameterExtractorNodeData]):
         query: str,
         variable_pool: VariablePool,
         model_config: ModelConfigWithCredentialsEntity,
-        memory: TokenBufferMemory | None,
+        memory: BaseMemory | None,
         files: Sequence[File],
         vision_detail: ImagePromptMessageContent.DETAIL | None = None,
     ) -> tuple[list[PromptMessage], list[PromptMessageTool]]:
@@ -381,7 +391,7 @@ class ParameterExtractorNode(Node[ParameterExtractorNodeData]):
         query: str,
         variable_pool: VariablePool,
         model_config: ModelConfigWithCredentialsEntity,
-        memory: TokenBufferMemory | None,
+        memory: BaseMemory | None,
         files: Sequence[File],
         vision_detail: ImagePromptMessageContent.DETAIL | None = None,
     ) -> list[PromptMessage]:
@@ -419,7 +429,7 @@ class ParameterExtractorNode(Node[ParameterExtractorNodeData]):
         query: str,
         variable_pool: VariablePool,
         model_config: ModelConfigWithCredentialsEntity,
-        memory: TokenBufferMemory | None,
+        memory: BaseMemory | None,
         files: Sequence[File],
         vision_detail: ImagePromptMessageContent.DETAIL | None = None,
     ) -> list[PromptMessage]:
@@ -453,7 +463,7 @@ class ParameterExtractorNode(Node[ParameterExtractorNodeData]):
         query: str,
         variable_pool: VariablePool,
         model_config: ModelConfigWithCredentialsEntity,
-        memory: TokenBufferMemory | None,
+        memory: BaseMemory | None,
         files: Sequence[File],
         vision_detail: ImagePromptMessageContent.DETAIL | None = None,
     ) -> list[PromptMessage]:
@@ -681,7 +691,7 @@ class ParameterExtractorNode(Node[ParameterExtractorNodeData]):
         node_data: ParameterExtractorNodeData,
         query: str,
         variable_pool: VariablePool,
-        memory: TokenBufferMemory | None,
+        memory: BaseMemory | None,
         max_token_limit: int = 2000,
     ) -> list[ChatModelMessage]:
         model_mode = ModelMode(node_data.model.mode)
@@ -708,7 +718,7 @@ class ParameterExtractorNode(Node[ParameterExtractorNodeData]):
         node_data: ParameterExtractorNodeData,
         query: str,
         variable_pool: VariablePool,
-        memory: TokenBufferMemory | None,
+        memory: BaseMemory | None,
         max_token_limit: int = 2000,
     ):
         model_mode = ModelMode(node_data.model.mode)

api/core/workflow/nodes/question_classifier/question_classifier_node.py

@@ -4,7 +4,7 @@ from collections.abc import Mapping, Sequence
 from typing import TYPE_CHECKING, Any
 
 from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEntity
-from core.memory.token_buffer_memory import TokenBufferMemory
+from core.memory.base import BaseMemory
 from core.model_manager import ModelInstance
 from core.model_runtime.entities import LLMUsage, ModelPropertyKey, PromptMessageRole
 from core.model_runtime.utils.encoders import jsonable_encoder
@@ -96,8 +96,10 @@ class QuestionClassifierNode(Node[QuestionClassifierNodeData]):
         memory = llm_utils.fetch_memory(
             variable_pool=variable_pool,
             app_id=self.app_id,
+            tenant_id=self.tenant_id,
             node_data_memory=node_data.memory,
             model_instance=model_instance,
+            node_id=self._node_id,
         )
         # fetch instruction
         node_data.instruction = node_data.instruction or ""
@@ -203,6 +205,14 @@ class QuestionClassifierNode(Node[QuestionClassifierNodeData]):
                 "usage": jsonable_encoder(usage),
             }
 
+            # Save to node memory if in node memory mode
+            llm_utils.save_node_memory(
+                memory=memory,
+                variable_pool=variable_pool,
+                user_query=query or "",
+                assistant_response=f"class_name: {category_name}, class_id: {category_id}",
+            )
+
             return NodeRunResult(
                 status=WorkflowNodeExecutionStatus.SUCCEEDED,
                 inputs=variables,
@@ -312,7 +322,7 @@ class QuestionClassifierNode(Node[QuestionClassifierNodeData]):
         self,
         node_data: QuestionClassifierNodeData,
         query: str,
-        memory: TokenBufferMemory | None,
+        memory: BaseMemory | None,
         max_token_limit: int = 2000,
     ):
         model_mode = ModelMode(node_data.model.mode)

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

@@ -1,11 +1,63 @@
-from typing import Any, Literal, Union
+import re
+from collections.abc import Sequence
+from typing import Any, Literal, Self, Union
 
-from pydantic import BaseModel, field_validator
+from pydantic import BaseModel, field_validator, model_validator
 from pydantic_core.core_schema import ValidationInfo
 
 from core.tools.entities.tool_entities import ToolProviderType
 from core.workflow.nodes.base.entities import BaseNodeData
 
+# Pattern to match mention value format: {{@node.context@}}instruction
+# The placeholder {{@node.context@}} must appear at the beginning
+# Format: {{@agent_node_id.context@}} where agent_node_id is dynamic, context is fixed
+MENTION_VALUE_PATTERN = re.compile(r"^\{\{@([a-zA-Z0-9_]+)\.context@\}\}(.*)$", re.DOTALL)
+
+
+def parse_mention_value(value: str) -> tuple[str, str]:
+    """Parse mention value into (node_id, instruction).
+
+    Args:
+        value: The mention value string like "{{@llm.context@}}extract keywords"
+
+    Returns:
+        Tuple of (node_id, instruction)
+
+    Raises:
+        ValueError: If value format is invalid
+    """
+    match = MENTION_VALUE_PATTERN.match(value)
+    if not match:
+        raise ValueError(
+            "For mention type, value must start with {{@node.context@}} placeholder, "
+            "e.g., '{{@llm.context@}}extract keywords'"
+        )
+    return match.group(1), match.group(2)
+
+
+class MentionConfig(BaseModel):
+    """Configuration for extracting value from context variable.
+
+    Used when a tool parameter needs to be extracted from list[PromptMessage]
+    context using an extractor LLM node.
+
+    Note: instruction is embedded in the value field as "{{@node.context@}}instruction"
+    """
+
+    # ID of the extractor LLM node
+    extractor_node_id: str
+
+    # Output variable selector from extractor node
+    # e.g., ["text"], ["structured_output", "query"]
+    output_selector: Sequence[str]
+
+    # Strategy when output is None
+    null_strategy: Literal["raise_error", "use_default"] = "raise_error"
+
+    # Default value when null_strategy is "use_default"
+    # Type should match the parameter's expected type
+    default_value: Any = None
+
 
 class ToolEntity(BaseModel):
     provider_id: str
@@ -35,7 +87,9 @@ class ToolNodeData(BaseNodeData, ToolEntity):
     class ToolInput(BaseModel):
         # TODO: check this type
         value: Union[Any, list[str]]
-        type: Literal["mixed", "variable", "constant"]
+        type: Literal["mixed", "variable", "constant", "mention"]
+        # Required config for mention type, extracting value from context variable
+        mention_config: MentionConfig | None = None
 
         @field_validator("type", mode="before")
         @classmethod
@@ -48,6 +102,9 @@ class ToolNodeData(BaseNodeData, ToolEntity):
 
             if typ == "mixed" and not isinstance(value, str):
                 raise ValueError("value must be a string")
+            elif typ == "mention":
+                # Skip here, will be validated in model_validator
+                pass
             elif typ == "variable":
                 if not isinstance(value, list):
                     raise ValueError("value must be a list")
@@ -58,6 +115,26 @@ class ToolNodeData(BaseNodeData, ToolEntity):
                 raise ValueError("value must be a string, int, float, bool or dict")
             return typ
 
+        @model_validator(mode="after")
+        def check_mention_type(self) -> Self:
+            """Validate mention type with mention_config."""
+            if self.type != "mention":
+                return self
+
+            value = self.value
+            if value is None:
+                return self
+
+            if not isinstance(value, str):
+                raise ValueError("value must be a string for mention type")
+            # For mention type, value must match format: {{@node.context@}}instruction
+            # This will raise ValueError if format is invalid
+            parse_mention_value(value)
+            # mention_config is required for mention type
+            if self.mention_config is None:
+                raise ValueError("mention_config is required for mention type")
+            return self
+
     tool_parameters: dict[str, ToolInput]
     # The version of the tool parameter.
     # If this value is None, it indicates this is a previous version

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

@@ -1,7 +1,10 @@
+import logging
 from collections.abc import Generator, Mapping, Sequence
 from typing import TYPE_CHECKING, Any
 
 from sqlalchemy import select
+
+logger = logging.getLogger(__name__)
 from sqlalchemy.orm import Session
 
 from core.callback_handler.workflow_tool_callback_handler import DifyWorkflowCallbackHandler
@@ -184,6 +187,7 @@ class ToolNode(Node[ToolNodeData]):
             tool_parameters (Sequence[ToolParameter]): The list of tool parameters.
             variable_pool (VariablePool): The variable pool containing the variables.
             node_data (ToolNodeData): The data associated with the tool node.
+            for_log (bool): Whether to generate parameters for logging.
 
         Returns:
             Mapping[str, Any]: A dictionary containing the generated parameters.
@@ -199,14 +203,37 @@ class ToolNode(Node[ToolNodeData]):
                 continue
             tool_input = node_data.tool_parameters[parameter_name]
             if tool_input.type == "variable":
-                variable = variable_pool.get(tool_input.value)
+                if not isinstance(tool_input.value, list):
+                    raise ToolParameterError(f"Invalid variable selector for parameter '{parameter_name}'")
+                selector = tool_input.value
+                variable = variable_pool.get(selector)
                 if variable is None:
                     if parameter.required:
-                        raise ToolParameterError(f"Variable {tool_input.value} does not exist")
+                        raise ToolParameterError(f"Variable {selector} does not exist")
                     continue
                 parameter_value = variable.value
+            elif tool_input.type == "mention":
+                # Mention type: get value from extractor node's output
+                if tool_input.mention_config is None:
+                    raise ToolParameterError(
+                        f"mention_config is required for mention type parameter '{parameter_name}'"
+                    )
+                mention_config = tool_input.mention_config.model_dump()
+                try:
+                    parameter_value, found = variable_pool.resolve_mention(
+                        mention_config, parameter_name=parameter_name
+                    )
+                    if not found and parameter.required:
+                        raise ToolParameterError(
+                            f"Extractor output not found for required parameter '{parameter_name}'"
+                        )
+                    if not found:
+                        continue
+                except ValueError as e:
+                    raise ToolParameterError(str(e)) from e
             elif tool_input.type in {"mixed", "constant"}:
-                segment_group = variable_pool.convert_template(str(tool_input.value))
+                template = str(tool_input.value)
+                segment_group = variable_pool.convert_template(template)
                 parameter_value = segment_group.log if for_log else segment_group.text
             else:
                 raise ToolParameterError(f"Unknown tool input type '{tool_input.type}'")
@@ -488,8 +515,12 @@ class ToolNode(Node[ToolNodeData]):
                 for selector in selectors:
                     result[selector.variable] = selector.value_selector
             elif input.type == "variable":
-                selector_key = ".".join(input.value)
-                result[f"#{selector_key}#"] = input.value
+                if isinstance(input.value, list):
+                    selector_key = ".".join(input.value)
+                    result[f"#{selector_key}#"] = input.value
+            elif input.type == "mention":
+                # Mention type: value is handled by extractor node, no direct variable reference
+                pass
             elif input.type == "constant":
                 pass
 

api/core/workflow/runtime/variable_pool.py

@@ -268,6 +268,58 @@ class VariablePool(BaseModel):
                 continue
             self.add(selector, value)
 
+    def resolve_mention(
+        self,
+        mention_config: Mapping[str, Any],
+        /,
+        *,
+        parameter_name: str = "",
+    ) -> tuple[Any, bool]:
+        """
+        Resolve a mention parameter value from an extractor node's output.
+
+        Mention parameters reference values extracted by an extractor LLM node
+        from list[PromptMessage] context.
+
+        Args:
+            mention_config: A dict containing:
+                - extractor_node_id: ID of the extractor LLM node
+                - output_selector: Selector path for the output variable (e.g., ["text"])
+                - null_strategy: "raise_error" or "use_default"
+                - default_value: Value to use when null_strategy is "use_default"
+            parameter_name: Name of the parameter being resolved (for error messages)
+
+        Returns:
+            Tuple of (resolved_value, found):
+                - resolved_value: The extracted value, or default_value if not found
+                - found: True if value was found, False if using default
+
+        Raises:
+            ValueError: If extractor_node_id is missing, or if null_strategy is
+                       "raise_error" and the value is not found
+        """
+        extractor_node_id = mention_config.get("extractor_node_id")
+        if not extractor_node_id:
+            raise ValueError(f"Missing extractor_node_id for mention parameter '{parameter_name}'")
+
+        output_selector = list(mention_config.get("output_selector", []))
+        null_strategy = mention_config.get("null_strategy", "raise_error")
+        default_value = mention_config.get("default_value")
+
+        # Build full selector: [extractor_node_id, ...output_selector]
+        full_selector = [extractor_node_id] + output_selector
+        variable = self.get(full_selector)
+
+        if variable is None:
+            if null_strategy == "use_default":
+                return default_value, False
+            raise ValueError(
+                f"Extractor node '{extractor_node_id}' output '{'.'.join(output_selector)}' "
+                f"not found for parameter '{parameter_name}'"
+            )
+
+        return variable.value, True
+
     @classmethod
     def empty(cls) -> VariablePool:
         """Create an empty variable pool."""

api/core/workflow/workflow_entry.py

@@ -189,8 +189,7 @@ class WorkflowEntry:
             )
 
         try:
-            # run node
-            generator = node.run()
+            generator = cls._traced_node_run(node)
         except Exception as e:
             logger.exception(
                 "error while running node, workflow_id=%s, node_id=%s, node_type=%s, node_version=%s",
@@ -323,8 +322,7 @@ class WorkflowEntry:
                 tenant_id=tenant_id,
             )
 
-            # run node
-            generator = node.run()
+            generator = cls._traced_node_run(node)
 
             return node, generator
         except Exception as e:
@@ -430,3 +428,26 @@ class WorkflowEntry:
                         input_value = current_variable.value | input_value
 
                 variable_pool.add([variable_node_id] + variable_key_list, input_value)
+
+    @staticmethod
+    def _traced_node_run(node: Node) -> Generator[GraphNodeEventBase, None, None]:
+        """
+        Wraps a node's run method with OpenTelemetry tracing and returns a generator.
+        """
+        # Wrap node.run() with ObservabilityLayer hooks to produce node-level spans
+        layer = ObservabilityLayer()
+        layer.on_graph_start()
+        node.ensure_execution_id()
+
+        def _gen():
+            error: Exception | None = None
+            layer.on_node_run_start(node)
+            try:
+                yield from node.run()
+            except Exception as exc:
+                error = exc
+                raise
+            finally:
+                layer.on_node_run_end(node, error)
+
+        return _gen()

api/events/event_handlers/__init__.py

@@ -6,6 +6,7 @@ from .create_site_record_when_app_created import handle as handle_create_site_re
 from .delete_tool_parameters_cache_when_sync_draft_workflow import (
     handle as handle_delete_tool_parameters_cache_when_sync_draft_workflow,
 )
+from .queue_credential_sync_when_tenant_created import handle as handle_queue_credential_sync_when_tenant_created
 from .sync_plugin_trigger_when_app_created import handle as handle_sync_plugin_trigger_when_app_created
 from .sync_webhook_when_app_created import handle as handle_sync_webhook_when_app_created
 from .sync_workflow_schedule_when_app_published import handle as handle_sync_workflow_schedule_when_app_published
@@ -30,6 +31,7 @@ __all__ = [
     "handle_create_installed_app_when_app_created",
     "handle_create_site_record_when_app_created",
     "handle_delete_tool_parameters_cache_when_sync_draft_workflow",
+    "handle_queue_credential_sync_when_tenant_created",
     "handle_sync_plugin_trigger_when_app_created",
     "handle_sync_webhook_when_app_created",
     "handle_sync_workflow_schedule_when_app_published",

api/events/event_handlers/queue_credential_sync_when_tenant_created.py

@@ -0,0 +1,19 @@
+from configs import dify_config
+from events.tenant_event import tenant_was_created
+from services.enterprise.workspace_sync import WorkspaceSyncService
+
+
+@tenant_was_created.connect
+def handle(sender, **kwargs):
+    """Queue credential sync when a tenant/workspace is created."""
+    # Only queue sync tasks if plugin manager (enterprise feature) is enabled
+    if not dify_config.ENTERPRISE_ENABLED:
+        return
+
+    tenant = sender
+
+    # Determine source from kwargs if available, otherwise use generic
+    source = kwargs.get("source", "tenant_created")
+
+    # Queue credential sync task to Redis for enterprise backend to process
+    WorkspaceSyncService.queue_credential_sync(tenant.id, source=source)

api/extensions/ext_commands.py

@@ -4,6 +4,7 @@ from dify_app import DifyApp
 def init_app(app: DifyApp):
     from commands import (
         add_qdrant_index,
+        clean_expired_messages,
         clean_workflow_runs,
         cleanup_orphaned_draft_variables,
         clear_free_plan_tenant_expired_logs,
@@ -58,6 +59,7 @@ def init_app(app: DifyApp):
         transform_datasource_credentials,
         install_rag_pipeline_plugins,
         clean_workflow_runs,
+        clean_expired_messages,
     ]
     for cmd in cmds_to_register:
         app.cli.add_command(cmd)

api/factories/file_factory.py

@@ -115,7 +115,18 @@ def build_from_mappings(
     # TODO(QuantumGhost): Performance concern - each mapping triggers a separate database query.
     # Implement batch processing to reduce database load when handling multiple files.
     # Filter out None/empty mappings to avoid errors
-    valid_mappings = [m for m in mappings if m and m.get("transfer_method")]
+    def is_valid_mapping(m: Mapping[str, Any]) -> bool:
+        if not m or not m.get("transfer_method"):
+            return False
+        # For REMOTE_URL transfer method, ensure url or remote_url is provided and not None
+        transfer_method = m.get("transfer_method")
+        if transfer_method == FileTransferMethod.REMOTE_URL:
+            url = m.get("url") or m.get("remote_url")
+            if not url:
+                return False
+        return True
+
+    valid_mappings = [m for m in mappings if is_valid_mapping(m)]
     files = [
         build_from_mapping(
             mapping=mapping,

api/factories/variable_factory.py

@@ -4,6 +4,7 @@ from uuid import uuid4
 
 from configs import dify_config
 from core.file import File
+from core.model_runtime.entities import PromptMessage
 from core.variables.exc import VariableError
 from core.variables.segments import (
     ArrayAnySegment,
@@ -11,6 +12,7 @@ from core.variables.segments import (
     ArrayFileSegment,
     ArrayNumberSegment,
     ArrayObjectSegment,
+    ArrayPromptMessageSegment,
     ArraySegment,
     ArrayStringSegment,
     BooleanSegment,
@@ -29,6 +31,7 @@ from core.variables.variables import (
     ArrayFileVariable,
     ArrayNumberVariable,
     ArrayObjectVariable,
+    ArrayPromptMessageVariable,
     ArrayStringVariable,
     BooleanVariable,
     FileVariable,
@@ -61,6 +64,7 @@ SEGMENT_TO_VARIABLE_MAP = {
     ArrayFileSegment: ArrayFileVariable,
     ArrayNumberSegment: ArrayNumberVariable,
     ArrayObjectSegment: ArrayObjectVariable,
+    ArrayPromptMessageSegment: ArrayPromptMessageVariable,
     ArrayStringSegment: ArrayStringVariable,
     BooleanSegment: BooleanVariable,
     FileSegment: FileVariable,
@@ -156,7 +160,13 @@ def build_segment(value: Any, /) -> Segment:
         return ObjectSegment(value=value)
     if isinstance(value, File):
         return FileSegment(value=value)
+    if isinstance(value, PromptMessage):
+        # Single PromptMessage should be wrapped in a list
+        return ArrayPromptMessageSegment(value=[value])
     if isinstance(value, list):
+        # Check if all items are PromptMessage
+        if value and all(isinstance(item, PromptMessage) for item in value):
+            return ArrayPromptMessageSegment(value=value)
         items = [build_segment(item) for item in value]
         types = {item.value_type for item in items}
         if all(isinstance(item, ArraySegment) for item in items):
@@ -200,6 +210,7 @@ _segment_factory: Mapping[SegmentType, type[Segment]] = {
     SegmentType.ARRAY_OBJECT: ArrayObjectSegment,
     SegmentType.ARRAY_FILE: ArrayFileSegment,
     SegmentType.ARRAY_BOOLEAN: ArrayBooleanSegment,
+    SegmentType.ARRAY_PROMPT_MESSAGE: ArrayPromptMessageSegment,
 }
 
 

api/fields/message_fields.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 from datetime import datetime
 from typing import TypeAlias
+from uuid import uuid4
 
 from pydantic import BaseModel, ConfigDict, Field, field_validator
 
@@ -20,8 +21,8 @@ class SimpleFeedback(ResponseModel):
 
 
 class RetrieverResource(ResponseModel):
-    id: str
-    message_id: str
+    id: str = Field(default_factory=lambda: str(uuid4()))
+    message_id: str = Field(default_factory=lambda: str(uuid4()))
     position: int
     dataset_id: str | None = None
     dataset_name: str | None = None

api/libs/smtp.py

@@ -3,6 +3,8 @@ import smtplib
 from email.mime.multipart import MIMEMultipart
 from email.mime.text import MIMEText
 
+from configs import dify_config
+
 logger = logging.getLogger(__name__)
 
 
@@ -19,20 +21,21 @@ class SMTPClient:
         self.opportunistic_tls = opportunistic_tls
 
     def send(self, mail: dict):
-        smtp = None
+        smtp: smtplib.SMTP | None = None
+        local_host = dify_config.SMTP_LOCAL_HOSTNAME
         try:
-            if self.use_tls:
-                if self.opportunistic_tls:
-                    smtp = smtplib.SMTP(self.server, self.port, timeout=10)
-                    # Send EHLO command with the HELO domain name as the server address
-                    smtp.ehlo(self.server)
-                    smtp.starttls()
-                    # Resend EHLO command to identify the TLS session
-                    smtp.ehlo(self.server)
-                else:
-                    smtp = smtplib.SMTP_SSL(self.server, self.port, timeout=10)
+            if self.use_tls and not self.opportunistic_tls:
+                # SMTP with SSL (implicit TLS)
+                smtp = smtplib.SMTP_SSL(self.server, self.port, timeout=10, local_hostname=local_host)
             else:
-                smtp = smtplib.SMTP(self.server, self.port, timeout=10)
+                # Plain SMTP or SMTP with STARTTLS (explicit TLS)
+                smtp = smtplib.SMTP(self.server, self.port, timeout=10, local_hostname=local_host)
+
+            assert smtp is not None
+            if self.use_tls and self.opportunistic_tls:
+                smtp.ehlo(self.server)
+                smtp.starttls()
+                smtp.ehlo(self.server)
 
             # Only authenticate if both username and password are non-empty
             if self.username and self.password and self.username.strip() and self.password.strip():

api/migrations/versions/2026_01_12_1729-3334862ee907_feat_add_created_at_id_index_to_messages.py

@@ -0,0 +1,33 @@
+"""feat: add created_at id index to messages
+
+Revision ID: 3334862ee907
+Revises: 905527cc8fd3
+Create Date: 2026-01-12 17:29:44.846544
+
+"""
+from alembic import op
+import models as models
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = '3334862ee907'
+down_revision = '905527cc8fd3'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('messages', schema=None) as batch_op:
+        batch_op.create_index('message_created_at_id_idx', ['created_at', 'id'], unique=False)
+
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('messages', schema=None) as batch_op:
+        batch_op.drop_index('message_created_at_id_idx')
+
+    # ### end Alembic commands ###

api/models/dataset.py

@@ -1149,7 +1149,7 @@ class DatasetCollectionBinding(TypeBase):
     )
 
 
-class TidbAuthBinding(Base):
+class TidbAuthBinding(TypeBase):
     __tablename__ = "tidb_auth_bindings"
     __table_args__ = (
         sa.PrimaryKeyConstraint("id", name="tidb_auth_bindings_pkey"),
@@ -1158,7 +1158,13 @@ class TidbAuthBinding(Base):
         sa.Index("tidb_auth_bindings_created_at_idx", "created_at"),
         sa.Index("tidb_auth_bindings_status_idx", "status"),
     )
-    id: Mapped[str] = mapped_column(StringUUID, primary_key=True, default=lambda: str(uuid4()))
+    id: Mapped[str] = mapped_column(
+        StringUUID,
+        primary_key=True,
+        insert_default=lambda: str(uuid4()),
+        default_factory=lambda: str(uuid4()),
+        init=False,
+    )
     tenant_id: Mapped[str | None] = mapped_column(StringUUID, nullable=True)
     cluster_id: Mapped[str] = mapped_column(String(255), nullable=False)
     cluster_name: Mapped[str] = mapped_column(String(255), nullable=False)
@@ -1166,7 +1172,9 @@ class TidbAuthBinding(Base):
     status: Mapped[str] = mapped_column(sa.String(255), nullable=False, server_default=sa.text("'CREATING'"))
     account: Mapped[str] = mapped_column(String(255), nullable=False)
     password: Mapped[str] = mapped_column(String(255), nullable=False)
-    created_at: Mapped[datetime] = mapped_column(DateTime, nullable=False, server_default=func.current_timestamp())
+    created_at: Mapped[datetime] = mapped_column(
+        DateTime, nullable=False, server_default=func.current_timestamp(), init=False
+    )
 
 
 class Whitelist(TypeBase):

api/models/model.py

@@ -968,6 +968,7 @@ class Message(Base):
         Index("message_workflow_run_id_idx", "conversation_id", "workflow_run_id"),
         Index("message_created_at_idx", "created_at"),
         Index("message_app_mode_idx", "app_mode"),
+        Index("message_created_at_id_idx", "created_at", "id"),
     )
 
     id: Mapped[str] = mapped_column(StringUUID, default=lambda: str(uuid4()))
@@ -1447,7 +1448,7 @@ class MessageAnnotation(Base):
         return account
 
 
-class AppAnnotationHitHistory(Base):
+class AppAnnotationHitHistory(TypeBase):
     __tablename__ = "app_annotation_hit_histories"
     __table_args__ = (
         sa.PrimaryKeyConstraint("id", name="app_annotation_hit_histories_pkey"),
@@ -1457,17 +1458,19 @@ class AppAnnotationHitHistory(Base):
         sa.Index("app_annotation_hit_histories_message_idx", "message_id"),
     )
 
-    id = mapped_column(StringUUID, default=lambda: str(uuid4()))
-    app_id = mapped_column(StringUUID, nullable=False)
+    id: Mapped[str] = mapped_column(StringUUID, default=lambda: str(uuid4()), init=False)
+    app_id: Mapped[str] = mapped_column(StringUUID, nullable=False)
     annotation_id: Mapped[str] = mapped_column(StringUUID, nullable=False)
-    source = mapped_column(LongText, nullable=False)
-    question = mapped_column(LongText, nullable=False)
-    account_id = mapped_column(StringUUID, nullable=False)
-    created_at = mapped_column(sa.DateTime, nullable=False, server_default=func.current_timestamp())
-    score = mapped_column(Float, nullable=False, server_default=sa.text("0"))
-    message_id = mapped_column(StringUUID, nullable=False)
-    annotation_question = mapped_column(LongText, nullable=False)
-    annotation_content = mapped_column(LongText, nullable=False)
+    source: Mapped[str] = mapped_column(LongText, nullable=False)
+    question: Mapped[str] = mapped_column(LongText, nullable=False)
+    account_id: Mapped[str] = mapped_column(StringUUID, nullable=False)
+    created_at: Mapped[datetime] = mapped_column(
+        sa.DateTime, nullable=False, server_default=func.current_timestamp(), init=False
+    )
+    score: Mapped[float] = mapped_column(Float, nullable=False, server_default=sa.text("0"))
+    message_id: Mapped[str] = mapped_column(StringUUID, nullable=False)
+    annotation_question: Mapped[str] = mapped_column(LongText, nullable=False)
+    annotation_content: Mapped[str] = mapped_column(LongText, nullable=False)
 
     @property
     def account(self):
@@ -2083,7 +2086,7 @@ class TraceAppConfig(TypeBase):
         }
 
 
-class TenantCreditPool(Base):
+class TenantCreditPool(TypeBase):
     __tablename__ = "tenant_credit_pools"
     __table_args__ = (
         sa.PrimaryKeyConstraint("id", name="tenant_credit_pool_pkey"),
@@ -2091,14 +2094,20 @@ class TenantCreditPool(Base):
         sa.Index("tenant_credit_pool_pool_type_idx", "pool_type"),
     )
 
-    id = mapped_column(StringUUID, primary_key=True, server_default=text("uuid_generate_v4()"))
-    tenant_id = mapped_column(StringUUID, nullable=False)
-    pool_type = mapped_column(String(40), nullable=False, default="trial", server_default="trial")
-    quota_limit = mapped_column(BigInteger, nullable=False, default=0)
-    quota_used = mapped_column(BigInteger, nullable=False, default=0)
-    created_at = mapped_column(sa.DateTime, nullable=False, server_default=text("CURRENT_TIMESTAMP"))
-    updated_at = mapped_column(
-        sa.DateTime, nullable=False, server_default=func.current_timestamp(), onupdate=func.current_timestamp()
+    id: Mapped[str] = mapped_column(StringUUID, primary_key=True, server_default=text("uuid_generate_v4()"), init=False)
+    tenant_id: Mapped[str] = mapped_column(StringUUID, nullable=False)
+    pool_type: Mapped[str] = mapped_column(String(40), nullable=False, default="trial", server_default="trial")
+    quota_limit: Mapped[int] = mapped_column(BigInteger, nullable=False, default=0)
+    quota_used: Mapped[int] = mapped_column(BigInteger, nullable=False, default=0)
+    created_at: Mapped[datetime] = mapped_column(
+        sa.DateTime, nullable=False, server_default=text("CURRENT_TIMESTAMP"), init=False
+    )
+    updated_at: Mapped[datetime] = mapped_column(
+        sa.DateTime,
+        nullable=False,
+        server_default=func.current_timestamp(),
+        onupdate=func.current_timestamp(),
+        init=False,
     )
 
     @property

api/models/workflow.py

@@ -1289,7 +1289,7 @@ class WorkflowDraftVariable(Base):
     # which may differ from the original value's type. Typically, they are the same,
     # but in cases where the structurally truncated  value still exceeds the size limit,
     # text slicing is applied, and the `value_type` is converted to `STRING`.
-    value_type: Mapped[SegmentType] = mapped_column(EnumText(SegmentType, length=20))
+    value_type: Mapped[SegmentType] = mapped_column(EnumText(SegmentType, length=21))
 
     # The variable's value serialized as a JSON string
     #
@@ -1663,7 +1663,7 @@ class WorkflowDraftVariableFile(Base):
 
     # The `value_type` field records the type of the original value.
     value_type: Mapped[SegmentType] = mapped_column(
-        EnumText(SegmentType, length=20),
+        EnumText(SegmentType, length=21),
         nullable=False,
     )
 

api/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dify-api"
-version = "1.11.3"
+version = "1.11.4"
 requires-python = ">=3.11,<3.13"
 
 dependencies = [

api/schedule/clean_messages.py

@@ -1,90 +1,62 @@
-import datetime
 import logging
 import time
 
 import click
-from sqlalchemy.exc import SQLAlchemyError
 
 import app
 from configs import dify_config
-from enums.cloud_plan import CloudPlan
-from extensions.ext_database import db
-from extensions.ext_redis import redis_client
-from models.model import (
-    App,
-    Message,
-    MessageAgentThought,
-    MessageAnnotation,
-    MessageChain,
-    MessageFeedback,
-    MessageFile,
-)
-from models.web import SavedMessage
-from services.feature_service import FeatureService
+from services.retention.conversation.messages_clean_policy import create_message_clean_policy
+from services.retention.conversation.messages_clean_service import MessagesCleanService
 
 logger = logging.getLogger(__name__)
 
 
-@app.celery.task(queue="dataset")
+@app.celery.task(queue="retention")
 def clean_messages():
-    click.echo(click.style("Start clean messages.", fg="green"))
-    start_at = time.perf_counter()
-    plan_sandbox_clean_message_day = datetime.datetime.now() - datetime.timedelta(
-        days=dify_config.PLAN_SANDBOX_CLEAN_MESSAGE_DAY_SETTING
-    )
-    while True:
-        try:
-            # Main query with join and filter
-            messages = (
-                db.session.query(Message)
-                .where(Message.created_at < plan_sandbox_clean_message_day)
-                .order_by(Message.created_at.desc())
-                .limit(100)
-                .all()
-            )
+    """
+    Clean expired messages based on clean policy.
 
-        except SQLAlchemyError:
-            raise
-        if not messages:
-            break
-        for message in messages:
-            app = db.session.query(App).filter_by(id=message.app_id).first()
-            if not app:
-                logger.warning(
-                    "Expected App record to exist, but none was found, app_id=%s, message_id=%s",
-                    message.app_id,
-                    message.id,
-                )
-                continue
-            features_cache_key = f"features:{app.tenant_id}"
-            plan_cache = redis_client.get(features_cache_key)
-            if plan_cache is None:
-                features = FeatureService.get_features(app.tenant_id)
-                redis_client.setex(features_cache_key, 600, features.billing.subscription.plan)
-                plan = features.billing.subscription.plan
-            else:
-                plan = plan_cache.decode()
-            if plan == CloudPlan.SANDBOX:
-                # clean related message
-                db.session.query(MessageFeedback).where(MessageFeedback.message_id == message.id).delete(
-                    synchronize_session=False
-                )
-                db.session.query(MessageAnnotation).where(MessageAnnotation.message_id == message.id).delete(
-                    synchronize_session=False
-                )
-                db.session.query(MessageChain).where(MessageChain.message_id == message.id).delete(
-                    synchronize_session=False
-                )
-                db.session.query(MessageAgentThought).where(MessageAgentThought.message_id == message.id).delete(
-                    synchronize_session=False
-                )
-                db.session.query(MessageFile).where(MessageFile.message_id == message.id).delete(
-                    synchronize_session=False
-                )
-                db.session.query(SavedMessage).where(SavedMessage.message_id == message.id).delete(
-                    synchronize_session=False
-                )
-                db.session.query(Message).where(Message.id == message.id).delete()
-                db.session.commit()
-    end_at = time.perf_counter()
-    click.echo(click.style(f"Cleaned messages from db success latency: {end_at - start_at}", fg="green"))
+    This task uses MessagesCleanService to efficiently clean messages in batches.
+    The behavior depends on BILLING_ENABLED configuration:
+    - BILLING_ENABLED=True: only delete messages from sandbox tenants (with whitelist/grace period)
+    - BILLING_ENABLED=False: delete all messages within the time range
+    """
+    click.echo(click.style("clean_messages: start clean messages.", fg="green"))
+    start_at = time.perf_counter()
+
+    try:
+        # Create policy based on billing configuration
+        policy = create_message_clean_policy(
+            graceful_period_days=dify_config.SANDBOX_EXPIRED_RECORDS_CLEAN_GRACEFUL_PERIOD,
+        )
+
+        # Create and run the cleanup service
+        service = MessagesCleanService.from_days(
+            policy=policy,
+            days=dify_config.SANDBOX_EXPIRED_RECORDS_RETENTION_DAYS,
+            batch_size=dify_config.SANDBOX_EXPIRED_RECORDS_CLEAN_BATCH_SIZE,
+        )
+        stats = service.run()
+
+        end_at = time.perf_counter()
+        click.echo(
+            click.style(
+                f"clean_messages: completed successfully\n"
+                f"  - Latency: {end_at - start_at:.2f}s\n"
+                f"  - Batches processed: {stats['batches']}\n"
+                f"  - Total messages scanned: {stats['total_messages']}\n"
+                f"  - Messages filtered: {stats['filtered_messages']}\n"
+                f"  - Messages deleted: {stats['total_deleted']}",
+                fg="green",
+            )
+        )
+    except Exception as e:
+        end_at = time.perf_counter()
+        logger.exception("clean_messages failed")
+        click.echo(
+            click.style(
+                f"clean_messages: failed after {end_at - start_at:.2f}s - {str(e)}",
+                fg="red",
+            )
+        )
+        raise

api/schedule/create_tidb_serverless_task.py

@@ -50,10 +50,13 @@ def create_clusters(batch_size):
         )
         for new_cluster in new_clusters:
             tidb_auth_binding = TidbAuthBinding(
+                tenant_id=None,
                 cluster_id=new_cluster["cluster_id"],
                 cluster_name=new_cluster["cluster_name"],
                 account=new_cluster["account"],
                 password=new_cluster["password"],
+                active=False,
+                status="CREATING",
             )
             db.session.add(tidb_auth_binding)
         db.session.commit()

api/services/enterprise/workspace_sync.py

@@ -0,0 +1,58 @@
+import json
+import logging
+import uuid
+from datetime import UTC, datetime
+
+from redis import RedisError
+
+from extensions.ext_redis import redis_client
+
+logger = logging.getLogger(__name__)
+
+WORKSPACE_SYNC_QUEUE = "enterprise:workspace:sync:queue"
+WORKSPACE_SYNC_PROCESSING = "enterprise:workspace:sync:processing"
+
+
+class WorkspaceSyncService:
+    """Service to publish workspace sync tasks to Redis queue for enterprise backend consumption"""
+
+    @staticmethod
+    def queue_credential_sync(workspace_id: str, *, source: str) -> bool:
+        """
+        Queue a credential sync task for a newly created workspace.
+
+        This publishes a task to Redis that will be consumed by the enterprise backend
+        worker to sync credentials with the plugin-manager.
+
+        Args:
+            workspace_id: The workspace/tenant ID to sync credentials for
+            source: Source of the sync request (for debugging/tracking)
+
+        Returns:
+            bool: True if task was queued successfully, False otherwise
+        """
+        try:
+            task = {
+                "task_id": str(uuid.uuid4()),
+                "workspace_id": workspace_id,
+                "retry_count": 0,
+                "created_at": datetime.now(UTC).isoformat(),
+                "source": source,
+            }
+
+            # Push to Redis list (queue) - LPUSH adds to the head, worker consumes from tail with RPOP
+            redis_client.lpush(WORKSPACE_SYNC_QUEUE, json.dumps(task))
+
+            logger.info(
+                "Queued credential sync task for workspace %s, task_id: %s, source: %s",
+                workspace_id,
+                task["task_id"],
+                source,
+            )
+            return True
+
+        except (RedisError, TypeError) as e:
+            logger.error("Failed to queue credential sync for workspace %s: %s", workspace_id, str(e), exc_info=True)
+            # Don't raise - we don't want to fail workspace creation if queueing fails
+            # The scheduled task will catch it later
+            return False

api/services/retention/conversation/messages_clean_policy.py

@@ -0,0 +1,216 @@
+import datetime
+import logging
+from abc import ABC, abstractmethod
+from collections.abc import Callable, Sequence
+from dataclasses import dataclass
+
+from configs import dify_config
+from enums.cloud_plan import CloudPlan
+from services.billing_service import BillingService, SubscriptionPlan
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class SimpleMessage:
+    id: str
+    app_id: str
+    created_at: datetime.datetime
+
+
+class MessagesCleanPolicy(ABC):
+    """
+    Abstract base class for message cleanup policies.
+
+    A policy determines which messages from a batch should be deleted.
+    """
+
+    @abstractmethod
+    def filter_message_ids(
+        self,
+        messages: Sequence[SimpleMessage],
+        app_to_tenant: dict[str, str],
+    ) -> Sequence[str]:
+        """
+        Filter messages and return IDs of messages that should be deleted.
+
+        Args:
+            messages: Batch of messages to evaluate
+            app_to_tenant: Mapping from app_id to tenant_id
+
+        Returns:
+            List of message IDs that should be deleted
+        """
+        ...
+
+
+class BillingDisabledPolicy(MessagesCleanPolicy):
+    """
+    Policy for community or enterpriseedition (billing disabled).
+
+    No special filter logic, just return all message ids.
+    """
+
+    def filter_message_ids(
+        self,
+        messages: Sequence[SimpleMessage],
+        app_to_tenant: dict[str, str],
+    ) -> Sequence[str]:
+        return [msg.id for msg in messages]
+
+
+class BillingSandboxPolicy(MessagesCleanPolicy):
+    """
+    Policy for sandbox plan tenants in cloud edition (billing enabled).
+
+    Filters messages based on sandbox plan expiration rules:
+    - Skip tenants in the whitelist
+    - Only delete messages from sandbox plan tenants
+    - Respect grace period after subscription expiration
+    - Safe default: if tenant mapping or plan is missing, do NOT delete
+    """
+
+    def __init__(
+        self,
+        plan_provider: Callable[[Sequence[str]], dict[str, SubscriptionPlan]],
+        graceful_period_days: int = 21,
+        tenant_whitelist: Sequence[str] | None = None,
+        current_timestamp: int | None = None,
+    ) -> None:
+        self._graceful_period_days = graceful_period_days
+        self._tenant_whitelist: Sequence[str] = tenant_whitelist or []
+        self._plan_provider = plan_provider
+        self._current_timestamp = current_timestamp
+
+    def filter_message_ids(
+        self,
+        messages: Sequence[SimpleMessage],
+        app_to_tenant: dict[str, str],
+    ) -> Sequence[str]:
+        """
+        Filter messages based on sandbox plan expiration rules.
+
+        Args:
+            messages: Batch of messages to evaluate
+            app_to_tenant: Mapping from app_id to tenant_id
+
+        Returns:
+            List of message IDs that should be deleted
+        """
+        if not messages or not app_to_tenant:
+            return []
+
+        # Get unique tenant_ids and fetch subscription plans
+        tenant_ids = list(set(app_to_tenant.values()))
+        tenant_plans = self._plan_provider(tenant_ids)
+
+        if not tenant_plans:
+            return []
+
+        # Apply sandbox deletion rules
+        return self._filter_expired_sandbox_messages(
+            messages=messages,
+            app_to_tenant=app_to_tenant,
+            tenant_plans=tenant_plans,
+        )
+
+    def _filter_expired_sandbox_messages(
+        self,
+        messages: Sequence[SimpleMessage],
+        app_to_tenant: dict[str, str],
+        tenant_plans: dict[str, SubscriptionPlan],
+    ) -> list[str]:
+        """
+        Filter messages that should be deleted based on sandbox plan expiration.
+
+        A message should be deleted if:
+        1. It belongs to a sandbox tenant AND
+        2. Either:
+           a) The tenant has no previous subscription (expiration_date == -1), OR
+           b) The subscription expired more than graceful_period_days ago
+
+        Args:
+            messages: List of message objects with id and app_id attributes
+            app_to_tenant: Mapping from app_id to tenant_id
+            tenant_plans: Mapping from tenant_id to subscription plan info
+
+        Returns:
+            List of message IDs that should be deleted
+        """
+        current_timestamp = self._current_timestamp
+        if current_timestamp is None:
+            current_timestamp = int(datetime.datetime.now(datetime.UTC).timestamp())
+
+        sandbox_message_ids: list[str] = []
+        graceful_period_seconds = self._graceful_period_days * 24 * 60 * 60
+
+        for msg in messages:
+            # Get tenant_id for this message's app
+            tenant_id = app_to_tenant.get(msg.app_id)
+            if not tenant_id:
+                continue
+
+            # Skip tenant messages in whitelist
+            if tenant_id in self._tenant_whitelist:
+                continue
+
+            # Get subscription plan for this tenant
+            tenant_plan = tenant_plans.get(tenant_id)
+            if not tenant_plan:
+                continue
+
+            plan = str(tenant_plan["plan"])
+            expiration_date = int(tenant_plan["expiration_date"])
+
+            # Only process sandbox plans
+            if plan != CloudPlan.SANDBOX:
+                continue
+
+            # Case 1: No previous subscription (-1 means never had a paid subscription)
+            if expiration_date == -1:
+                sandbox_message_ids.append(msg.id)
+                continue
+
+            # Case 2: Subscription expired beyond grace period
+            if current_timestamp - expiration_date > graceful_period_seconds:
+                sandbox_message_ids.append(msg.id)
+
+        return sandbox_message_ids
+
+
+def create_message_clean_policy(
+    graceful_period_days: int = 21,
+    current_timestamp: int | None = None,
+) -> MessagesCleanPolicy:
+    """
+    Factory function to create the appropriate message clean policy.
+
+    Determines which policy to use based on BILLING_ENABLED configuration:
+    - If BILLING_ENABLED is True: returns BillingSandboxPolicy
+    - If BILLING_ENABLED is False: returns BillingDisabledPolicy
+
+    Args:
+        graceful_period_days: Grace period in days after subscription expiration (default: 21)
+        current_timestamp: Current Unix timestamp for testing (default: None, uses current time)
+    """
+    if not dify_config.BILLING_ENABLED:
+        logger.info("create_message_clean_policy: billing disabled, using BillingDisabledPolicy")
+        return BillingDisabledPolicy()
+
+    # Billing enabled - fetch whitelist from BillingService
+    tenant_whitelist = BillingService.get_expired_subscription_cleanup_whitelist()
+    plan_provider = BillingService.get_plan_bulk_with_cache
+
+    logger.info(
+        "create_message_clean_policy: billing enabled, using BillingSandboxPolicy "
+        "(graceful_period_days=%s, whitelist=%s)",
+        graceful_period_days,
+        tenant_whitelist,
+    )
+
+    return BillingSandboxPolicy(
+        plan_provider=plan_provider,
+        graceful_period_days=graceful_period_days,
+        tenant_whitelist=tenant_whitelist,
+        current_timestamp=current_timestamp,
+    )

api/services/retention/conversation/messages_clean_service.py

@@ -0,0 +1,334 @@
+import datetime
+import logging
+import random
+from collections.abc import Sequence
+from typing import cast
+
+from sqlalchemy import delete, select
+from sqlalchemy.engine import CursorResult
+from sqlalchemy.orm import Session
+
+from extensions.ext_database import db
+from models.model import (
+    App,
+    AppAnnotationHitHistory,
+    DatasetRetrieverResource,
+    Message,
+    MessageAgentThought,
+    MessageAnnotation,
+    MessageChain,
+    MessageFeedback,
+    MessageFile,
+)
+from models.web import SavedMessage
+from services.retention.conversation.messages_clean_policy import (
+    MessagesCleanPolicy,
+    SimpleMessage,
+)
+
+logger = logging.getLogger(__name__)
+
+
+class MessagesCleanService:
+    """
+    Service for cleaning expired messages based on retention policies.
+
+    Compatible with non cloud edition (billing disabled): all messages in the time range will be deleted.
+    If billing is enabled: only sandbox plan tenant messages are deleted (with whitelist and grace period support).
+    """
+
+    def __init__(
+        self,
+        policy: MessagesCleanPolicy,
+        end_before: datetime.datetime,
+        start_from: datetime.datetime | None = None,
+        batch_size: int = 1000,
+        dry_run: bool = False,
+    ) -> None:
+        """
+        Initialize the service with cleanup parameters.
+
+        Args:
+            policy: The policy that determines which messages to delete
+            end_before: End time (exclusive) of the range
+            start_from: Optional start time (inclusive) of the range
+            batch_size: Number of messages to process per batch
+            dry_run: Whether to perform a dry run (no actual deletion)
+        """
+        self._policy = policy
+        self._end_before = end_before
+        self._start_from = start_from
+        self._batch_size = batch_size
+        self._dry_run = dry_run
+
+    @classmethod
+    def from_time_range(
+        cls,
+        policy: MessagesCleanPolicy,
+        start_from: datetime.datetime,
+        end_before: datetime.datetime,
+        batch_size: int = 1000,
+        dry_run: bool = False,
+    ) -> "MessagesCleanService":
+        """
+        Create a service instance for cleaning messages within a specific time range.
+
+        Time range is [start_from, end_before).
+
+        Args:
+            policy: The policy that determines which messages to delete
+            start_from: Start time (inclusive) of the range
+            end_before: End time (exclusive) of the range
+            batch_size: Number of messages to process per batch
+            dry_run: Whether to perform a dry run (no actual deletion)
+
+        Returns:
+            MessagesCleanService instance
+
+        Raises:
+            ValueError: If start_from >= end_before or invalid parameters
+        """
+        if start_from >= end_before:
+            raise ValueError(f"start_from ({start_from}) must be less than end_before ({end_before})")
+
+        if batch_size <= 0:
+            raise ValueError(f"batch_size ({batch_size}) must be greater than 0")
+
+        logger.info(
+            "clean_messages: start_from=%s, end_before=%s, batch_size=%s, policy=%s",
+            start_from,
+            end_before,
+            batch_size,
+            policy.__class__.__name__,
+        )
+
+        return cls(
+            policy=policy,
+            end_before=end_before,
+            start_from=start_from,
+            batch_size=batch_size,
+            dry_run=dry_run,
+        )
+
+    @classmethod
+    def from_days(
+        cls,
+        policy: MessagesCleanPolicy,
+        days: int = 30,
+        batch_size: int = 1000,
+        dry_run: bool = False,
+    ) -> "MessagesCleanService":
+        """
+        Create a service instance for cleaning messages older than specified days.
+
+        Args:
+            policy: The policy that determines which messages to delete
+            days: Number of days to look back from now
+            batch_size: Number of messages to process per batch
+            dry_run: Whether to perform a dry run (no actual deletion)
+
+        Returns:
+            MessagesCleanService instance
+
+        Raises:
+            ValueError: If invalid parameters
+        """
+        if days < 0:
+            raise ValueError(f"days ({days}) must be greater than or equal to 0")
+
+        if batch_size <= 0:
+            raise ValueError(f"batch_size ({batch_size}) must be greater than 0")
+
+        end_before = datetime.datetime.now() - datetime.timedelta(days=days)
+
+        logger.info(
+            "clean_messages: days=%s, end_before=%s, batch_size=%s, policy=%s",
+            days,
+            end_before,
+            batch_size,
+            policy.__class__.__name__,
+        )
+
+        return cls(policy=policy, end_before=end_before, start_from=None, batch_size=batch_size, dry_run=dry_run)
+
+    def run(self) -> dict[str, int]:
+        """
+        Execute the message cleanup operation.
+
+        Returns:
+            Dict with statistics: batches, filtered_messages, total_deleted
+        """
+        return self._clean_messages_by_time_range()
+
+    def _clean_messages_by_time_range(self) -> dict[str, int]:
+        """
+        Clean messages within a time range using cursor-based pagination.
+
+        Time range is [start_from, end_before)
+
+        Steps:
+        1. Iterate messages using cursor pagination (by created_at, id)
+        2. Query app_id -> tenant_id mapping
+        3. Delegate to policy to determine which messages to delete
+        4. Batch delete messages and their relations
+
+        Returns:
+            Dict with statistics: batches, filtered_messages, total_deleted
+        """
+        stats = {
+            "batches": 0,
+            "total_messages": 0,
+            "filtered_messages": 0,
+            "total_deleted": 0,
+        }
+
+        # Cursor-based pagination using (created_at, id) to avoid infinite loops
+        # and ensure proper ordering with time-based filtering
+        _cursor: tuple[datetime.datetime, str] | None = None
+
+        logger.info(
+            "clean_messages: start cleaning messages (dry_run=%s), start_from=%s, end_before=%s",
+            self._dry_run,
+            self._start_from,
+            self._end_before,
+        )
+
+        while True:
+            stats["batches"] += 1
+
+            # Step 1: Fetch a batch of messages using cursor
+            with Session(db.engine, expire_on_commit=False) as session:
+                msg_stmt = (
+                    select(Message.id, Message.app_id, Message.created_at)
+                    .where(Message.created_at < self._end_before)
+                    .order_by(Message.created_at, Message.id)
+                    .limit(self._batch_size)
+                )
+
+                if self._start_from:
+                    msg_stmt = msg_stmt.where(Message.created_at >= self._start_from)
+
+                # Apply cursor condition: (created_at, id) > (last_created_at, last_message_id)
+                # This translates to:
+                #   created_at > last_created_at OR (created_at = last_created_at AND id > last_message_id)
+                if _cursor:
+                    # Continuing from previous batch
+                    msg_stmt = msg_stmt.where(
+                        (Message.created_at > _cursor[0])
+                        | ((Message.created_at == _cursor[0]) & (Message.id > _cursor[1]))
+                    )
+
+                raw_messages = list(session.execute(msg_stmt).all())
+                messages = [
+                    SimpleMessage(id=msg_id, app_id=app_id, created_at=msg_created_at)
+                    for msg_id, app_id, msg_created_at in raw_messages
+                ]
+
+                # Track total messages fetched across all batches
+                stats["total_messages"] += len(messages)
+
+                if not messages:
+                    logger.info("clean_messages (batch %s): no more messages to process", stats["batches"])
+                    break
+
+                # Update cursor to the last message's (created_at, id)
+                _cursor = (messages[-1].created_at, messages[-1].id)
+
+                # Step 2: Extract app_ids and query tenant_ids
+                app_ids = list({msg.app_id for msg in messages})
+
+                if not app_ids:
+                    logger.info("clean_messages (batch %s): no app_ids found, skip", stats["batches"])
+                    continue
+
+                app_stmt = select(App.id, App.tenant_id).where(App.id.in_(app_ids))
+                apps = list(session.execute(app_stmt).all())
+
+            if not apps:
+                logger.info("clean_messages (batch %s): no apps found, skip", stats["batches"])
+                continue
+
+            # Build app_id -> tenant_id mapping
+            app_to_tenant: dict[str, str] = {app.id: app.tenant_id for app in apps}
+
+            # Step 3: Delegate to policy to determine which messages to delete
+            message_ids_to_delete = self._policy.filter_message_ids(messages, app_to_tenant)
+
+            if not message_ids_to_delete:
+                logger.info("clean_messages (batch %s): no messages to delete, skip", stats["batches"])
+                continue
+
+            stats["filtered_messages"] += len(message_ids_to_delete)
+
+            # Step 4: Batch delete messages and their relations
+            if not self._dry_run:
+                with Session(db.engine, expire_on_commit=False) as session:
+                    # Delete related records first
+                    self._batch_delete_message_relations(session, message_ids_to_delete)
+
+                    # Delete messages
+                    delete_stmt = delete(Message).where(Message.id.in_(message_ids_to_delete))
+                    delete_result = cast(CursorResult, session.execute(delete_stmt))
+                    messages_deleted = delete_result.rowcount
+                    session.commit()
+
+                    stats["total_deleted"] += messages_deleted
+
+                    logger.info(
+                        "clean_messages (batch %s): processed %s messages, deleted %s messages",
+                        stats["batches"],
+                        len(messages),
+                        messages_deleted,
+                    )
+            else:
+                # Log random sample of message IDs that would be deleted (up to 10)
+                sample_size = min(10, len(message_ids_to_delete))
+                sampled_ids = random.sample(list(message_ids_to_delete), sample_size)
+
+                logger.info(
+                    "clean_messages (batch %s, dry_run): would delete %s messages, sampling %s ids:",
+                    stats["batches"],
+                    len(message_ids_to_delete),
+                    sample_size,
+                )
+                for msg_id in sampled_ids:
+                    logger.info("clean_messages (batch %s, dry_run) sample: message_id=%s", stats["batches"], msg_id)
+
+        logger.info(
+            "clean_messages completed: total batches: %s, total messages: %s, filtered messages: %s, total deleted: %s",
+            stats["batches"],
+            stats["total_messages"],
+            stats["filtered_messages"],
+            stats["total_deleted"],
+        )
+
+        return stats
+
+    @staticmethod
+    def _batch_delete_message_relations(session: Session, message_ids: Sequence[str]) -> None:
+        """
+        Batch delete all related records for given message IDs.
+
+        Args:
+            session: Database session
+            message_ids: List of message IDs to delete relations for
+        """
+        if not message_ids:
+            return
+
+        # Delete all related records in batch
+        session.execute(delete(MessageFeedback).where(MessageFeedback.message_id.in_(message_ids)))
+
+        session.execute(delete(MessageAnnotation).where(MessageAnnotation.message_id.in_(message_ids)))
+
+        session.execute(delete(MessageChain).where(MessageChain.message_id.in_(message_ids)))
+
+        session.execute(delete(MessageAgentThought).where(MessageAgentThought.message_id.in_(message_ids)))
+
+        session.execute(delete(MessageFile).where(MessageFile.message_id.in_(message_ids)))
+
+        session.execute(delete(SavedMessage).where(SavedMessage.message_id.in_(message_ids)))
+
+        session.execute(delete(AppAnnotationHitHistory).where(AppAnnotationHitHistory.message_id.in_(message_ids)))
+
+        session.execute(delete(DatasetRetrieverResource).where(DatasetRetrieverResource.message_id.in_(message_ids)))

api/services/variable_truncator.py

@@ -7,6 +7,7 @@ from typing import Any, Generic, TypeAlias, TypeVar, overload
 
 from configs import dify_config
 from core.file.models import File
+from core.model_runtime.entities import PromptMessage
 from core.variables.segments import (
     ArrayFileSegment,
     ArraySegment,
@@ -287,6 +288,10 @@ class VariableTruncator(BaseTruncator):
             if isinstance(item, File):
                 truncated_value.append(item)
                 continue
+            # Handle PromptMessage types - convert to dict for truncation
+            if isinstance(item, PromptMessage):
+                truncated_value.append(item)
+                continue
             if i >= target_length:
                 return _PartResult(truncated_value, used_size, True)
             if i > 0:

api/tests/fixtures/file output schema.yml

@@ -0,0 +1,181 @@
+app:
+  description: ''
+  icon: 🤖
+  icon_background: '#FFEAD5'
+  mode: advanced-chat
+  name: file output schema
+  use_icon_as_answer_icon: false
+dependencies:
+- current_identifier: null
+  type: marketplace
+  value:
+    marketplace_plugin_unique_identifier: langgenius/openai:0.2.3@5a7f82fa86e28332ad51941d0b491c1e8a38ead539656442f7bf4c6129cd15fa
+    version: null
+kind: app
+version: 0.5.0
+workflow:
+  conversation_variables: []
+  environment_variables: []
+  features:
+    file_upload:
+      allowed_file_extensions:
+      - .JPG
+      - .JPEG
+      - .PNG
+      - .GIF
+      - .WEBP
+      - .SVG
+      allowed_file_types:
+      - image
+      allowed_file_upload_methods:
+      - remote_url
+      - local_file
+      enabled: true
+      fileUploadConfig:
+        attachment_image_file_size_limit: 2
+        audio_file_size_limit: 50
+        batch_count_limit: 5
+        file_size_limit: 15
+        file_upload_limit: 10
+        image_file_batch_limit: 10
+        image_file_size_limit: 10
+        single_chunk_attachment_limit: 10
+        video_file_size_limit: 100
+        workflow_file_upload_limit: 10
+      number_limits: 3
+    opening_statement: ''
+    retriever_resource:
+      enabled: true
+    sensitive_word_avoidance:
+      enabled: false
+    speech_to_text:
+      enabled: false
+    suggested_questions: []
+    suggested_questions_after_answer:
+      enabled: false
+    text_to_speech:
+      enabled: false
+      language: ''
+      voice: ''
+  graph:
+    edges:
+    - data:
+        sourceType: start
+        targetType: llm
+      id: 1768292241666-llm
+      source: '1768292241666'
+      sourceHandle: source
+      target: llm
+      targetHandle: target
+      type: custom
+    - data:
+        sourceType: llm
+        targetType: answer
+      id: llm-answer
+      source: llm
+      sourceHandle: source
+      target: answer
+      targetHandle: target
+      type: custom
+    nodes:
+    - data:
+        selected: false
+        title: User Input
+        type: start
+        variables: []
+      height: 73
+      id: '1768292241666'
+      position:
+        x: 80
+        y: 282
+      positionAbsolute:
+        x: 80
+        y: 282
+      sourcePosition: right
+      targetPosition: left
+      type: custom
+      width: 242
+    - data:
+        context:
+          enabled: false
+          variable_selector: []
+        memory:
+          query_prompt_template: '{{#sys.query#}}
+
+
+            {{#sys.files#}}'
+          role_prefix:
+            assistant: ''
+            user: ''
+          window:
+            enabled: false
+            size: 10
+        model:
+          completion_params:
+            temperature: 0.7
+          mode: chat
+          name: gpt-4o-mini
+          provider: langgenius/openai/openai
+        prompt_template:
+        - id: e30d75d7-7d85-49ec-be3c-3baf7f6d3c5a
+          role: system
+          text: ''
+        selected: false
+        structured_output:
+          schema:
+            additionalProperties: false
+            properties:
+              image:
+                description: File ID (UUID) of the selected image
+                format: dify-file-ref
+                type: string
+            required:
+            - image
+            type: object
+        structured_output_enabled: true
+        title: LLM
+        type: llm
+        vision:
+          configs:
+            detail: high
+            variable_selector:
+            - sys
+            - files
+          enabled: true
+      height: 88
+      id: llm
+      position:
+        x: 380
+        y: 282
+      positionAbsolute:
+        x: 380
+        y: 282
+      selected: false
+      sourcePosition: right
+      targetPosition: left
+      type: custom
+      width: 242
+    - data:
+        answer: '{{#llm.structured_output.image#}}'
+        selected: false
+        title: Answer
+        type: answer
+        variables: []
+      height: 103
+      id: answer
+      position:
+        x: 680
+        y: 282
+      positionAbsolute:
+        x: 680
+        y: 282
+      selected: true
+      sourcePosition: right
+      targetPosition: left
+      type: custom
+      width: 242
+    viewport:
+      x: -149
+      y: 97.5
+      zoom: 1
+  rag_pipeline_variables: []

api/tests/fixtures/pav-test-extraction.yml

@@ -0,0 +1,307 @@
+app:
+  description: Test for variable extraction feature
+  icon: 🤖
+  icon_background: '#FFEAD5'
+  mode: advanced-chat
+  name: pav-test-extraction
+  use_icon_as_answer_icon: false
+dependencies:
+- current_identifier: null
+  type: marketplace
+  value:
+    marketplace_plugin_unique_identifier: langgenius/google:0.0.8@3efcf55ffeef9d0f77715e0afb23534952ae0cb385c051d0637e86d71199d1a6
+    version: null
+- current_identifier: null
+  type: marketplace
+  value:
+    marketplace_plugin_unique_identifier: langgenius/openai:0.2.3@5a7f82fa86e28332ad51941d0b491c1e8a38ead539656442f7bf4c6129cd15fa
+    version: null
+- current_identifier: null
+  type: marketplace
+  value:
+    marketplace_plugin_unique_identifier: langgenius/tongyi:0.1.16@d8bffbe45418f0c117fb3393e5e40e61faee98f9a2183f062e5a280e74b15d21
+    version: null
+kind: app
+version: 0.5.0
+workflow:
+  conversation_variables: []
+  environment_variables: []
+  features:
+    file_upload:
+      allowed_file_extensions:
+      - .JPG
+      - .JPEG
+      - .PNG
+      - .GIF
+      - .WEBP
+      - .SVG
+      allowed_file_types:
+      - image
+      allowed_file_upload_methods:
+      - local_file
+      - remote_url
+      enabled: false
+      image:
+        enabled: false
+        number_limits: 3
+        transfer_methods:
+        - local_file
+        - remote_url
+      number_limits: 3
+    opening_statement: 你好！我是一个搜索助手，请告诉我你想搜索什么内容。
+    retriever_resource:
+      enabled: true
+    sensitive_word_avoidance:
+      enabled: false
+    speech_to_text:
+      enabled: false
+    suggested_questions: []
+    suggested_questions_after_answer:
+      enabled: false
+    text_to_speech:
+      enabled: false
+      language: ''
+      voice: ''
+  graph:
+    edges:
+    - data:
+        sourceType: start
+        targetType: llm
+      id: 1767773675796-llm
+      source: '1767773675796'
+      sourceHandle: source
+      target: llm
+      targetHandle: target
+      type: custom
+    - data:
+        isInIteration: false
+        isInLoop: false
+        sourceType: llm
+        targetType: tool
+      id: llm-source-1767773709491-target
+      source: llm
+      sourceHandle: source
+      target: '1767773709491'
+      targetHandle: target
+      type: custom
+      zIndex: 0
+    - data:
+        isInIteration: false
+        isInLoop: false
+        sourceType: tool
+        targetType: answer
+      id: tool-source-answer-target
+      source: '1767773709491'
+      sourceHandle: source
+      target: answer
+      targetHandle: target
+      type: custom
+      zIndex: 0
+    nodes:
+    - data:
+        selected: false
+        title: User Input
+        type: start
+        variables: []
+      height: 73
+      id: '1767773675796'
+      position:
+        x: 80
+        y: 282
+      positionAbsolute:
+        x: 80
+        y: 282
+      sourcePosition: right
+      targetPosition: left
+      type: custom
+      width: 242
+    - data:
+        context:
+          enabled: false
+          variable_selector: []
+        memory:
+          mode: node
+          query_prompt_template: '{{#sys.query#}}'
+          role_prefix:
+            assistant: ''
+            user: ''
+          window:
+            enabled: true
+            size: 10
+        model:
+          completion_params:
+            temperature: 0.7
+          mode: chat
+          name: qwen-max
+          provider: langgenius/tongyi/tongyi
+        prompt_template:
+        - id: 11d06d15-914a-4915-a5b1-0e35ab4fba51
+          role: system
+          text: '你是一个智能搜索助手。用户会告诉你他们想搜索的内容。
+
+            请与用户进行对话，了解他们的搜索需求。
+
+            当用户明确表达了想要搜索的内容后，你可以回复"好的，我来帮你搜索"。
+
+            '
+        selected: false
+        title: LLM
+        type: llm
+        vision:
+          enabled: false
+      height: 88
+      id: llm
+      position:
+        x: 380
+        y: 282
+      positionAbsolute:
+        x: 380
+        y: 282
+      selected: false
+      sourcePosition: right
+      targetPosition: left
+      type: custom
+      width: 242
+    - data:
+        is_team_authorization: true
+        paramSchemas:
+        - auto_generate: null
+          default: null
+          form: llm
+          human_description:
+            en_US: used for searching
+            ja_JP: used for searching
+            pt_BR: used for searching
+            zh_Hans: 用于搜索网页内容
+          label:
+            en_US: Query string
+            ja_JP: Query string
+            pt_BR: Query string
+            zh_Hans: 查询语句
+          llm_description: key words for searching
+          max: null
+          min: null
+          name: query
+          options: []
+          placeholder: null
+          precision: null
+          required: true
+          scope: null
+          template: null
+          type: string
+        params:
+          query: ''
+        plugin_id: langgenius/google
+        plugin_unique_identifier: langgenius/google:0.0.8@3efcf55ffeef9d0f77715e0afb23534952ae0cb385c051d0637e86d71199d1a6
+        provider_icon: http://localhost:5001/console/api/workspaces/current/plugin/icon?tenant_id=7217e801-f6f5-49ec-8103-d7de97a4b98f&filename=1c5871163478957bac64c3fe33d72d003f767497d921c74b742aad27a8344a74.svg
+        provider_id: langgenius/google/google
+        provider_name: langgenius/google/google
+        provider_type: builtin
+        selected: false
+        title: GoogleSearch
+        tool_configurations: {}
+        tool_description: A tool for performing a Google SERP search and extracting
+          snippets and webpages.Input should be a search query.
+        tool_label: GoogleSearch
+        tool_name: google_search
+        tool_node_version: '2'
+        tool_parameters:
+          query:
+            type: mention
+            value: '{{@llm.context@}}请从对话历史中提取用户想要搜索的关键词，只返回关键词本身'
+            mention_config:
+              extractor_node_id: 1767773709491_ext_query
+              output_selector:
+              - structured_output
+              - query
+              null_strategy: use_default
+              default_value: ''
+        type: tool
+      height: 52
+      id: '1767773709491'
+      position:
+        x: 682
+        y: 282
+      positionAbsolute:
+        x: 682
+        y: 282
+      selected: false
+      sourcePosition: right
+      targetPosition: left
+      type: custom
+      width: 242
+    - data:
+        context:
+          enabled: false
+          variable_selector: []
+        model:
+          completion_params:
+            temperature: 0.7
+          mode: chat
+          name: gpt-4o-mini
+          provider: langgenius/openai/openai
+        parent_node_id: '1767773709491'
+        prompt_template:
+        - $context:
+          - llm
+          - context
+          id: 75d58e22-dc59-40c8-ba6f-aeb28f4f305a
+        - id: 18ba6710-77f5-47f4-b144-9191833bb547
+          role: user
+          text: 请从对话历史中提取用户想要搜索的关键词，只返回关键词本身，不要返回其他内容
+        selected: false
+        structured_output:
+          schema:
+            additionalProperties: false
+            properties:
+              query:
+                description: 搜索的关键词
+                type: string
+            required:
+            - query
+            type: object
+        structured_output_enabled: true
+        title: 提取搜索关键词
+        type: llm
+        vision:
+          enabled: false
+      height: 88
+      id: 1767773709491_ext_query
+      position:
+        x: 531
+        y: 382
+      positionAbsolute:
+        x: 531
+        y: 382
+      selected: true
+      sourcePosition: right
+      targetPosition: left
+      type: custom
+      width: 242
+    - data:
+        answer: '搜索结果：
+
+          {{#1767773709491.text#}}
+
+          '
+        selected: false
+        title: Answer
+        type: answer
+      height: 103
+      id: answer
+      position:
+        x: 984
+        y: 282
+      positionAbsolute:
+        x: 984
+        y: 282
+      selected: false
+      sourcePosition: right
+      targetPosition: left
+      type: custom
+      width: 242
+    viewport:
+      x: -151
+      y: 123
+      zoom: 1
+  rag_pipeline_variables: []

api/tests/integration_tests/.env.example

@@ -103,6 +103,8 @@ SMTP_USERNAME=123
 SMTP_PASSWORD=abc
 SMTP_USE_TLS=true
 SMTP_OPPORTUNISTIC_TLS=false
+# Optional: override the local hostname used for SMTP HELO/EHLO
+SMTP_LOCAL_HOSTNAME=
 
 # Sentry configuration
 SENTRY_DSN=

api/tests/unit_tests/controllers/console/datasets/__init__.py

@@ -0,0 +1 @@
+"""Unit tests for `controllers.console.datasets` controllers."""

api/tests/unit_tests/controllers/console/datasets/test_external_dataset_payload.py

@@ -0,0 +1,49 @@
+from __future__ import annotations
+
+"""
+Unit tests for the external dataset controller payload schemas.
+
+These tests focus on Pydantic validation rules so we can catch regressions
+in request constraints (e.g. max length changes) without exercising the
+full Flask/RESTX request stack.
+"""
+
+import pytest
+from pydantic import ValidationError
+
+from controllers.console.datasets.external import ExternalDatasetCreatePayload
+
+
+def test_external_dataset_create_payload_allows_name_length_100() -> None:
+    """Ensure the `name` field accepts up to 100 characters (inclusive)."""
+
+    # Build a request payload with a boundary-length name value.
+    name_100: str = "a" * 100
+    payload = {
+        "external_knowledge_api_id": "ek-api-1",
+        "external_knowledge_id": "ek-1",
+        "name": name_100,
+    }
+
+    model = ExternalDatasetCreatePayload.model_validate(payload)
+    assert model.name == name_100
+
+
+def test_external_dataset_create_payload_rejects_name_length_101() -> None:
+    """Ensure the `name` field rejects values longer than 100 characters."""
+
+    # Build a request payload that exceeds the max length by 1.
+    name_101: str = "a" * 101
+    payload: dict[str, object] = {
+        "external_knowledge_api_id": "ek-api-1",
+        "external_knowledge_id": "ek-1",
+        "name": name_101,
+    }
+
+    with pytest.raises(ValidationError) as exc_info:
+        ExternalDatasetCreatePayload.model_validate(payload)
+
+    errors = exc_info.value.errors()
+    assert errors[0]["loc"] == ("name",)
+    assert errors[0]["type"] == "string_too_long"
+    assert errors[0]["ctx"]["max_length"] == 100

api/tests/unit_tests/core/llm_generator/output_parser/test_file_ref.py

@@ -0,0 +1,269 @@
+"""
+Unit tests for file reference detection and conversion.
+"""
+
+import uuid
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from core.file import File, FileTransferMethod, FileType
+from core.llm_generator.output_parser.file_ref import (
+    FILE_REF_FORMAT,
+    convert_file_refs_in_output,
+    detect_file_ref_fields,
+    is_file_ref_property,
+)
+from core.variables.segments import ArrayFileSegment, FileSegment
+
+
+class TestIsFileRefProperty:
+    """Tests for is_file_ref_property function."""
+
+    def test_valid_file_ref(self):
+        schema = {"type": "string", "format": FILE_REF_FORMAT}
+        assert is_file_ref_property(schema) is True
+
+    def test_invalid_type(self):
+        schema = {"type": "number", "format": FILE_REF_FORMAT}
+        assert is_file_ref_property(schema) is False
+
+    def test_missing_format(self):
+        schema = {"type": "string"}
+        assert is_file_ref_property(schema) is False
+
+    def test_wrong_format(self):
+        schema = {"type": "string", "format": "uuid"}
+        assert is_file_ref_property(schema) is False
+
+
+class TestDetectFileRefFields:
+    """Tests for detect_file_ref_fields function."""
+
+    def test_simple_file_ref(self):
+        schema = {
+            "type": "object",
+            "properties": {
+                "image": {"type": "string", "format": FILE_REF_FORMAT},
+            },
+        }
+        paths = detect_file_ref_fields(schema)
+        assert paths == ["image"]
+
+    def test_multiple_file_refs(self):
+        schema = {
+            "type": "object",
+            "properties": {
+                "image": {"type": "string", "format": FILE_REF_FORMAT},
+                "document": {"type": "string", "format": FILE_REF_FORMAT},
+                "name": {"type": "string"},
+            },
+        }
+        paths = detect_file_ref_fields(schema)
+        assert set(paths) == {"image", "document"}
+
+    def test_array_of_file_refs(self):
+        schema = {
+            "type": "object",
+            "properties": {
+                "files": {
+                    "type": "array",
+                    "items": {"type": "string", "format": FILE_REF_FORMAT},
+                },
+            },
+        }
+        paths = detect_file_ref_fields(schema)
+        assert paths == ["files[*]"]
+
+    def test_nested_file_ref(self):
+        schema = {
+            "type": "object",
+            "properties": {
+                "data": {
+                    "type": "object",
+                    "properties": {
+                        "image": {"type": "string", "format": FILE_REF_FORMAT},
+                    },
+                },
+            },
+        }
+        paths = detect_file_ref_fields(schema)
+        assert paths == ["data.image"]
+
+    def test_no_file_refs(self):
+        schema = {
+            "type": "object",
+            "properties": {
+                "name": {"type": "string"},
+                "count": {"type": "number"},
+            },
+        }
+        paths = detect_file_ref_fields(schema)
+        assert paths == []
+
+    def test_empty_schema(self):
+        schema = {}
+        paths = detect_file_ref_fields(schema)
+        assert paths == []
+
+    def test_mixed_schema(self):
+        schema = {
+            "type": "object",
+            "properties": {
+                "query": {"type": "string"},
+                "image": {"type": "string", "format": FILE_REF_FORMAT},
+                "documents": {
+                    "type": "array",
+                    "items": {"type": "string", "format": FILE_REF_FORMAT},
+                },
+            },
+        }
+        paths = detect_file_ref_fields(schema)
+        assert set(paths) == {"image", "documents[*]"}
+
+
+class TestConvertFileRefsInOutput:
+    """Tests for convert_file_refs_in_output function."""
+
+    @pytest.fixture
+    def mock_file(self):
+        """Create a mock File object with all required attributes."""
+        file = MagicMock(spec=File)
+        file.type = FileType.IMAGE
+        file.transfer_method = FileTransferMethod.TOOL_FILE
+        file.related_id = "test-related-id"
+        file.remote_url = None
+        file.tenant_id = "tenant_123"
+        file.id = None
+        file.filename = "test.png"
+        file.extension = ".png"
+        file.mime_type = "image/png"
+        file.size = 1024
+        file.dify_model_identity = "__dify__file__"
+        return file
+
+    @pytest.fixture
+    def mock_build_from_mapping(self, mock_file):
+        """Mock the build_from_mapping function."""
+        with patch("core.llm_generator.output_parser.file_ref.build_from_mapping") as mock:
+            mock.return_value = mock_file
+            yield mock
+
+    def test_convert_simple_file_ref(self, mock_build_from_mapping, mock_file):
+        file_id = str(uuid.uuid4())
+        output = {"image": file_id}
+        schema = {
+            "type": "object",
+            "properties": {
+                "image": {"type": "string", "format": FILE_REF_FORMAT},
+            },
+        }
+
+        result = convert_file_refs_in_output(output, schema, "tenant_123")
+
+        # Result should be wrapped in FileSegment
+        assert isinstance(result["image"], FileSegment)
+        assert result["image"].value == mock_file
+        mock_build_from_mapping.assert_called_once_with(
+            mapping={"transfer_method": "tool_file", "tool_file_id": file_id},
+            tenant_id="tenant_123",
+        )
+
+    def test_convert_array_of_file_refs(self, mock_build_from_mapping, mock_file):
+        file_id1 = str(uuid.uuid4())
+        file_id2 = str(uuid.uuid4())
+        output = {"files": [file_id1, file_id2]}
+        schema = {
+            "type": "object",
+            "properties": {
+                "files": {
+                    "type": "array",
+                    "items": {"type": "string", "format": FILE_REF_FORMAT},
+                },
+            },
+        }
+
+        result = convert_file_refs_in_output(output, schema, "tenant_123")
+
+        # Result should be wrapped in ArrayFileSegment
+        assert isinstance(result["files"], ArrayFileSegment)
+        assert list(result["files"].value) == [mock_file, mock_file]
+        assert mock_build_from_mapping.call_count == 2
+
+    def test_no_conversion_without_file_refs(self):
+        output = {"name": "test", "count": 5}
+        schema = {
+            "type": "object",
+            "properties": {
+                "name": {"type": "string"},
+                "count": {"type": "number"},
+            },
+        }
+
+        result = convert_file_refs_in_output(output, schema, "tenant_123")
+
+        assert result == {"name": "test", "count": 5}
+
+    def test_invalid_uuid_returns_none(self):
+        output = {"image": "not-a-valid-uuid"}
+        schema = {
+            "type": "object",
+            "properties": {
+                "image": {"type": "string", "format": FILE_REF_FORMAT},
+            },
+        }
+
+        result = convert_file_refs_in_output(output, schema, "tenant_123")
+
+        assert result["image"] is None
+
+    def test_file_not_found_returns_none(self):
+        file_id = str(uuid.uuid4())
+        output = {"image": file_id}
+        schema = {
+            "type": "object",
+            "properties": {
+                "image": {"type": "string", "format": FILE_REF_FORMAT},
+            },
+        }
+
+        with patch("core.llm_generator.output_parser.file_ref.build_from_mapping") as mock:
+            mock.side_effect = ValueError("File not found")
+            result = convert_file_refs_in_output(output, schema, "tenant_123")
+
+        assert result["image"] is None
+
+    def test_preserves_non_file_fields(self, mock_build_from_mapping, mock_file):
+        file_id = str(uuid.uuid4())
+        output = {"query": "search term", "image": file_id, "count": 10}
+        schema = {
+            "type": "object",
+            "properties": {
+                "query": {"type": "string"},
+                "image": {"type": "string", "format": FILE_REF_FORMAT},
+                "count": {"type": "number"},
+            },
+        }
+
+        result = convert_file_refs_in_output(output, schema, "tenant_123")
+
+        assert result["query"] == "search term"
+        assert isinstance(result["image"], FileSegment)
+        assert result["image"].value == mock_file
+        assert result["count"] == 10
+
+    def test_does_not_modify_original_output(self, mock_build_from_mapping, mock_file):
+        file_id = str(uuid.uuid4())
+        original = {"image": file_id}
+        output = dict(original)
+        schema = {
+            "type": "object",
+            "properties": {
+                "image": {"type": "string", "format": FILE_REF_FORMAT},
+            },
+        }
+
+        convert_file_refs_in_output(output, schema, "tenant_123")
+
+        # Original should still contain the string ID
+        assert original["image"] == file_id

api/tests/unit_tests/core/plugin/test_endpoint_client.py

@@ -0,0 +1,279 @@
+"""Unit tests for PluginEndpointClient functionality.
+
+This test module covers the endpoint client operations including:
+- Successful endpoint deletion
+- Idempotent delete behavior (record not found)
+- Non-idempotent delete behavior (other errors)
+
+Tests follow the Arrange-Act-Assert pattern for clarity.
+"""
+
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from core.plugin.impl.endpoint import PluginEndpointClient
+from core.plugin.impl.exc import PluginDaemonInternalServerError
+
+
+class TestPluginEndpointClientDelete:
+    """Unit tests for PluginEndpointClient delete_endpoint operation.
+
+    Tests cover:
+    - Successful endpoint deletion
+    - Idempotent behavior when endpoint is already deleted (record not found)
+    - Non-idempotent behavior for other errors
+    """
+
+    @pytest.fixture
+    def endpoint_client(self):
+        """Create a PluginEndpointClient instance for testing."""
+        return PluginEndpointClient()
+
+    @pytest.fixture
+    def mock_config(self):
+        """Mock plugin daemon configuration."""
+        with (
+            patch("core.plugin.impl.base.dify_config.PLUGIN_DAEMON_URL", "http://127.0.0.1:5002"),
+            patch("core.plugin.impl.base.dify_config.PLUGIN_DAEMON_KEY", "test-api-key"),
+        ):
+            yield
+
+    def test_delete_endpoint_success(self, endpoint_client, mock_config):
+        """Test successful endpoint deletion.
+
+        Given:
+            - A valid tenant_id, user_id, and endpoint_id
+            - The plugin daemon returns success response
+        When:
+            - delete_endpoint is called
+        Then:
+            - The method should return True
+            - The request should be made with correct parameters
+        """
+        # Arrange
+        tenant_id = "tenant-123"
+        user_id = "user-456"
+        endpoint_id = "endpoint-789"
+
+        mock_response = MagicMock()
+        mock_response.status_code = 200
+        mock_response.json.return_value = {
+            "code": 0,
+            "message": "success",
+            "data": True,
+        }
+
+        with patch("httpx.request", return_value=mock_response):
+            # Act
+            result = endpoint_client.delete_endpoint(
+                tenant_id=tenant_id,
+                user_id=user_id,
+                endpoint_id=endpoint_id,
+            )
+
+            # Assert
+            assert result is True
+
+    def test_delete_endpoint_idempotent_record_not_found(self, endpoint_client, mock_config):
+        """Test idempotent delete behavior when endpoint is already deleted.
+
+        Given:
+            - A valid tenant_id, user_id, and endpoint_id
+            - The plugin daemon returns "record not found" error
+        When:
+            - delete_endpoint is called
+        Then:
+            - The method should return True (idempotent behavior)
+            - No exception should be raised
+        """
+        # Arrange
+        tenant_id = "tenant-123"
+        user_id = "user-456"
+        endpoint_id = "endpoint-789"
+
+        mock_response = MagicMock()
+        mock_response.status_code = 200
+        mock_response.json.return_value = {
+            "code": -1,
+            "message": (
+                '{"error_type": "PluginDaemonInternalServerError", '
+                '"message": "failed to remove endpoint: record not found"}'
+            ),
+        }
+
+        with patch("httpx.request", return_value=mock_response):
+            # Act
+            result = endpoint_client.delete_endpoint(
+                tenant_id=tenant_id,
+                user_id=user_id,
+                endpoint_id=endpoint_id,
+            )
+
+            # Assert - should return True instead of raising an error
+            assert result is True
+
+    def test_delete_endpoint_non_idempotent_other_errors(self, endpoint_client, mock_config):
+        """Test non-idempotent delete behavior for other errors.
+
+        Given:
+            - A valid tenant_id, user_id, and endpoint_id
+            - The plugin daemon returns a different error (not "record not found")
+        When:
+            - delete_endpoint is called
+        Then:
+            - The method should raise PluginDaemonInternalServerError
+        """
+        # Arrange
+        tenant_id = "tenant-123"
+        user_id = "user-456"
+        endpoint_id = "endpoint-789"
+
+        mock_response = MagicMock()
+        mock_response.status_code = 200
+        mock_response.json.return_value = {
+            "code": -1,
+            "message": (
+                '{"error_type": "PluginDaemonInternalServerError", '
+                '"message": "failed to remove endpoint: internal server error"}'
+            ),
+        }
+
+        with patch("httpx.request", return_value=mock_response):
+            # Act & Assert
+            with pytest.raises(PluginDaemonInternalServerError) as exc_info:
+                endpoint_client.delete_endpoint(
+                    tenant_id=tenant_id,
+                    user_id=user_id,
+                    endpoint_id=endpoint_id,
+                )
+
+            # Assert - the error message should not be "record not found"
+            assert "record not found" not in str(exc_info.value.description)
+
+    def test_delete_endpoint_idempotent_case_insensitive(self, endpoint_client, mock_config):
+        """Test idempotent delete behavior with case-insensitive error message.
+
+        Given:
+            - A valid tenant_id, user_id, and endpoint_id
+            - The plugin daemon returns "Record Not Found" error (different case)
+        When:
+            - delete_endpoint is called
+        Then:
+            - The method should return True (idempotent behavior)
+        """
+        # Arrange
+        tenant_id = "tenant-123"
+        user_id = "user-456"
+        endpoint_id = "endpoint-789"
+
+        mock_response = MagicMock()
+        mock_response.status_code = 200
+        mock_response.json.return_value = {
+            "code": -1,
+            "message": '{"error_type": "PluginDaemonInternalServerError", "message": "Record Not Found"}',
+        }
+
+        with patch("httpx.request", return_value=mock_response):
+            # Act
+            result = endpoint_client.delete_endpoint(
+                tenant_id=tenant_id,
+                user_id=user_id,
+                endpoint_id=endpoint_id,
+            )
+
+            # Assert - should still return True
+            assert result is True
+
+    def test_delete_endpoint_multiple_calls_idempotent(self, endpoint_client, mock_config):
+        """Test that multiple delete calls are idempotent.
+
+        Given:
+            - A valid tenant_id, user_id, and endpoint_id
+            - The first call succeeds
+            - Subsequent calls return "record not found"
+        When:
+            - delete_endpoint is called multiple times
+        Then:
+            - All calls should return True
+        """
+        # Arrange
+        tenant_id = "tenant-123"
+        user_id = "user-456"
+        endpoint_id = "endpoint-789"
+
+        # First call - success
+        mock_response_success = MagicMock()
+        mock_response_success.status_code = 200
+        mock_response_success.json.return_value = {
+            "code": 0,
+            "message": "success",
+            "data": True,
+        }
+
+        # Second call - record not found
+        mock_response_not_found = MagicMock()
+        mock_response_not_found.status_code = 200
+        mock_response_not_found.json.return_value = {
+            "code": -1,
+            "message": (
+                '{"error_type": "PluginDaemonInternalServerError", '
+                '"message": "failed to remove endpoint: record not found"}'
+            ),
+        }
+
+        with patch("httpx.request") as mock_request:
+            # Act - first call
+            mock_request.return_value = mock_response_success
+            result1 = endpoint_client.delete_endpoint(
+                tenant_id=tenant_id,
+                user_id=user_id,
+                endpoint_id=endpoint_id,
+            )
+
+            # Act - second call (already deleted)
+            mock_request.return_value = mock_response_not_found
+            result2 = endpoint_client.delete_endpoint(
+                tenant_id=tenant_id,
+                user_id=user_id,
+                endpoint_id=endpoint_id,
+            )
+
+            # Assert - both should return True
+            assert result1 is True
+            assert result2 is True
+
+    def test_delete_endpoint_non_idempotent_unauthorized_error(self, endpoint_client, mock_config):
+        """Test that authorization errors are not treated as idempotent.
+
+        Given:
+            - A valid tenant_id, user_id, and endpoint_id
+            - The plugin daemon returns an unauthorized error
+        When:
+            - delete_endpoint is called
+        Then:
+            - The method should raise the appropriate error (not return True)
+        """
+        # Arrange
+        tenant_id = "tenant-123"
+        user_id = "user-456"
+        endpoint_id = "endpoint-789"
+
+        mock_response = MagicMock()
+        mock_response.status_code = 200
+        mock_response.json.return_value = {
+            "code": -1,
+            "message": '{"error_type": "PluginDaemonUnauthorizedError", "message": "unauthorized access"}',
+        }
+
+        with patch("httpx.request", return_value=mock_response):
+            # Act & Assert
+            with pytest.raises(Exception) as exc_info:
+                endpoint_client.delete_endpoint(
+                    tenant_id=tenant_id,
+                    user_id=user_id,
+                    endpoint_id=endpoint_id,
+                )
+
+            # Assert - should not return True for unauthorized errors
+            assert exc_info.value.__class__.__name__ == "PluginDaemonUnauthorizedError"

api/tests/unit_tests/core/workflow/graph_engine/event_management/test_event_handlers.py

@@ -25,6 +25,12 @@ class _StubErrorHandler:
     """Minimal error handler stub for tests."""
 
 
+class _StubNodeData:
+    """Simple node data stub with is_extractor_node property."""
+
+    is_extractor_node = False
+
+
 class _StubNode:
     """Simple node stub exposing the attributes needed by the state manager."""
 
@@ -36,6 +42,7 @@ class _StubNode:
         self.error_strategy = None
         self.retry_config = RetryConfig()
         self.retry = False
+        self.node_data = _StubNodeData()
 
 
 def _build_event_handler(node_id: str) -> tuple[EventHandler, EventManager, GraphExecution]:

api/tests/unit_tests/libs/test_smtp_client.py

@@ -1,4 +1,4 @@
-from unittest.mock import MagicMock, patch
+from unittest.mock import ANY, MagicMock, patch
 
 import pytest
 
@@ -17,7 +17,7 @@ def test_smtp_plain_success(mock_smtp_cls: MagicMock):
     client = SMTPClient(server="smtp.example.com", port=25, username="", password="", _from="[email protected]")
     client.send(_mail())
 
-    mock_smtp_cls.assert_called_once_with("smtp.example.com", 25, timeout=10)
+    mock_smtp_cls.assert_called_once_with("smtp.example.com", 25, timeout=10, local_hostname=ANY)
     mock_smtp.sendmail.assert_called_once()
     mock_smtp.quit.assert_called_once()
 
@@ -38,7 +38,7 @@ def test_smtp_tls_opportunistic_success(mock_smtp_cls: MagicMock):
     )
     client.send(_mail())
 
-    mock_smtp_cls.assert_called_once_with("smtp.example.com", 587, timeout=10)
+    mock_smtp_cls.assert_called_once_with("smtp.example.com", 587, timeout=10, local_hostname=ANY)
     assert mock_smtp.ehlo.call_count == 2
     mock_smtp.starttls.assert_called_once()
     mock_smtp.login.assert_called_once_with("user", "pass")

api/tests/unit_tests/services/test_messages_clean_service.py

@@ -0,0 +1,627 @@
+import datetime
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from enums.cloud_plan import CloudPlan
+from services.retention.conversation.messages_clean_policy import (
+    BillingDisabledPolicy,
+    BillingSandboxPolicy,
+    SimpleMessage,
+    create_message_clean_policy,
+)
+from services.retention.conversation.messages_clean_service import MessagesCleanService
+
+
+def make_simple_message(msg_id: str, app_id: str) -> SimpleMessage:
+    """Helper to create a SimpleMessage with a fixed created_at timestamp."""
+    return SimpleMessage(id=msg_id, app_id=app_id, created_at=datetime.datetime(2024, 1, 1))
+
+
+def make_plan_provider(tenant_plans: dict) -> MagicMock:
+    """Helper to create a mock plan_provider that returns the given tenant_plans."""
+    provider = MagicMock()
+    provider.return_value = tenant_plans
+    return provider
+
+
+class TestBillingSandboxPolicyFilterMessageIds:
+    """Unit tests for BillingSandboxPolicy.filter_message_ids method."""
+
+    # Fixed timestamp for deterministic tests
+    CURRENT_TIMESTAMP = 1000000
+    GRACEFUL_PERIOD_DAYS = 8
+    GRACEFUL_PERIOD_SECONDS = GRACEFUL_PERIOD_DAYS * 24 * 60 * 60
+
+    def test_missing_tenant_mapping_excluded(self):
+        """Test that messages with missing app-to-tenant mapping are excluded."""
+        # Arrange
+        messages = [
+            make_simple_message("msg1", "app1"),
+            make_simple_message("msg2", "app2"),
+        ]
+        app_to_tenant = {}  # No mapping
+        tenant_plans = {"tenant1": {"plan": CloudPlan.SANDBOX, "expiration_date": -1}}
+        plan_provider = make_plan_provider(tenant_plans)
+
+        policy = BillingSandboxPolicy(
+            plan_provider=plan_provider,
+            graceful_period_days=self.GRACEFUL_PERIOD_DAYS,
+            current_timestamp=self.CURRENT_TIMESTAMP,
+        )
+
+        # Act
+        result = policy.filter_message_ids(messages, app_to_tenant)
+
+        # Assert
+        assert list(result) == []
+
+    def test_missing_tenant_plan_excluded(self):
+        """Test that messages with missing tenant plan are excluded (safe default)."""
+        # Arrange
+        messages = [
+            make_simple_message("msg1", "app1"),
+            make_simple_message("msg2", "app2"),
+        ]
+        app_to_tenant = {"app1": "tenant1", "app2": "tenant2"}
+        tenant_plans = {}  # No plans
+        plan_provider = make_plan_provider(tenant_plans)
+
+        policy = BillingSandboxPolicy(
+            plan_provider=plan_provider,
+            graceful_period_days=self.GRACEFUL_PERIOD_DAYS,
+            current_timestamp=self.CURRENT_TIMESTAMP,
+        )
+
+        # Act
+        result = policy.filter_message_ids(messages, app_to_tenant)
+
+        # Assert
+        assert list(result) == []
+
+    def test_non_sandbox_plan_excluded(self):
+        """Test that messages from non-sandbox plans (PROFESSIONAL/TEAM) are excluded."""
+        # Arrange
+        messages = [
+            make_simple_message("msg1", "app1"),
+            make_simple_message("msg2", "app2"),
+            make_simple_message("msg3", "app3"),
+        ]
+        app_to_tenant = {"app1": "tenant1", "app2": "tenant2", "app3": "tenant3"}
+        tenant_plans = {
+            "tenant1": {"plan": CloudPlan.PROFESSIONAL, "expiration_date": -1},
+            "tenant2": {"plan": CloudPlan.TEAM, "expiration_date": -1},
+            "tenant3": {"plan": CloudPlan.SANDBOX, "expiration_date": -1},  # Only this one
+        }
+        plan_provider = make_plan_provider(tenant_plans)
+
+        policy = BillingSandboxPolicy(
+            plan_provider=plan_provider,
+            graceful_period_days=self.GRACEFUL_PERIOD_DAYS,
+            current_timestamp=self.CURRENT_TIMESTAMP,
+        )
+
+        # Act
+        result = policy.filter_message_ids(messages, app_to_tenant)
+
+        # Assert - only msg3 (sandbox tenant) should be included
+        assert set(result) == {"msg3"}
+
+    def test_whitelist_skip(self):
+        """Test that whitelisted tenants are excluded even if sandbox + expired."""
+        # Arrange
+        messages = [
+            make_simple_message("msg1", "app1"),  # Whitelisted - excluded
+            make_simple_message("msg2", "app2"),  # Not whitelisted - included
+            make_simple_message("msg3", "app3"),  # Whitelisted - excluded
+        ]
+        app_to_tenant = {"app1": "tenant1", "app2": "tenant2", "app3": "tenant3"}
+        tenant_plans = {
+            "tenant1": {"plan": CloudPlan.SANDBOX, "expiration_date": -1},
+            "tenant2": {"plan": CloudPlan.SANDBOX, "expiration_date": -1},
+            "tenant3": {"plan": CloudPlan.SANDBOX, "expiration_date": -1},
+        }
+        plan_provider = make_plan_provider(tenant_plans)
+        tenant_whitelist = ["tenant1", "tenant3"]
+
+        policy = BillingSandboxPolicy(
+            plan_provider=plan_provider,
+            graceful_period_days=self.GRACEFUL_PERIOD_DAYS,
+            tenant_whitelist=tenant_whitelist,
+            current_timestamp=self.CURRENT_TIMESTAMP,
+        )
+
+        # Act
+        result = policy.filter_message_ids(messages, app_to_tenant)
+
+        # Assert - only msg2 should be included
+        assert set(result) == {"msg2"}
+
+    def test_no_previous_subscription_included(self):
+        """Test that messages with expiration_date=-1 (no previous subscription) are included."""
+        # Arrange
+        messages = [
+            make_simple_message("msg1", "app1"),
+            make_simple_message("msg2", "app2"),
+        ]
+        app_to_tenant = {"app1": "tenant1", "app2": "tenant2"}
+        tenant_plans = {
+            "tenant1": {"plan": CloudPlan.SANDBOX, "expiration_date": -1},
+            "tenant2": {"plan": CloudPlan.SANDBOX, "expiration_date": -1},
+        }
+        plan_provider = make_plan_provider(tenant_plans)
+
+        policy = BillingSandboxPolicy(
+            plan_provider=plan_provider,
+            graceful_period_days=self.GRACEFUL_PERIOD_DAYS,
+            current_timestamp=self.CURRENT_TIMESTAMP,
+        )
+
+        # Act
+        result = policy.filter_message_ids(messages, app_to_tenant)
+
+        # Assert - all messages should be included
+        assert set(result) == {"msg1", "msg2"}
+
+    def test_within_grace_period_excluded(self):
+        """Test that messages within grace period are excluded."""
+        # Arrange
+        now = self.CURRENT_TIMESTAMP
+        expired_1_day_ago = now - (1 * 24 * 60 * 60)
+        expired_5_days_ago = now - (5 * 24 * 60 * 60)
+        expired_7_days_ago = now - (7 * 24 * 60 * 60)
+
+        messages = [
+            make_simple_message("msg1", "app1"),
+            make_simple_message("msg2", "app2"),
+            make_simple_message("msg3", "app3"),
+        ]
+        app_to_tenant = {"app1": "tenant1", "app2": "tenant2", "app3": "tenant3"}
+        tenant_plans = {
+            "tenant1": {"plan": CloudPlan.SANDBOX, "expiration_date": expired_1_day_ago},
+            "tenant2": {"plan": CloudPlan.SANDBOX, "expiration_date": expired_5_days_ago},
+            "tenant3": {"plan": CloudPlan.SANDBOX, "expiration_date": expired_7_days_ago},
+        }
+        plan_provider = make_plan_provider(tenant_plans)
+
+        policy = BillingSandboxPolicy(
+            plan_provider=plan_provider,
+            graceful_period_days=self.GRACEFUL_PERIOD_DAYS,  # 8 days
+            current_timestamp=now,
+        )
+
+        # Act
+        result = policy.filter_message_ids(messages, app_to_tenant)
+
+        # Assert - all within 8-day grace period, none should be included
+        assert list(result) == []
+
+    def test_exactly_at_boundary_excluded(self):
+        """Test that messages exactly at grace period boundary are excluded (code uses >)."""
+        # Arrange
+        now = self.CURRENT_TIMESTAMP
+        expired_exactly_8_days_ago = now - self.GRACEFUL_PERIOD_SECONDS  # Exactly at boundary
+
+        messages = [make_simple_message("msg1", "app1")]
+        app_to_tenant = {"app1": "tenant1"}
+        tenant_plans = {
+            "tenant1": {"plan": CloudPlan.SANDBOX, "expiration_date": expired_exactly_8_days_ago},
+        }
+        plan_provider = make_plan_provider(tenant_plans)
+
+        policy = BillingSandboxPolicy(
+            plan_provider=plan_provider,
+            graceful_period_days=self.GRACEFUL_PERIOD_DAYS,
+            current_timestamp=now,
+        )
+
+        # Act
+        result = policy.filter_message_ids(messages, app_to_tenant)
+
+        # Assert - exactly at boundary (==) should be excluded (code uses >)
+        assert list(result) == []
+
+    def test_beyond_grace_period_included(self):
+        """Test that messages beyond grace period are included."""
+        # Arrange
+        now = self.CURRENT_TIMESTAMP
+        expired_9_days_ago = now - (9 * 24 * 60 * 60)  # Just beyond 8-day grace
+        expired_30_days_ago = now - (30 * 24 * 60 * 60)  # Well beyond
+
+        messages = [
+            make_simple_message("msg1", "app1"),
+            make_simple_message("msg2", "app2"),
+        ]
+        app_to_tenant = {"app1": "tenant1", "app2": "tenant2"}
+        tenant_plans = {
+            "tenant1": {"plan": CloudPlan.SANDBOX, "expiration_date": expired_9_days_ago},
+            "tenant2": {"plan": CloudPlan.SANDBOX, "expiration_date": expired_30_days_ago},
+        }
+        plan_provider = make_plan_provider(tenant_plans)
+
+        policy = BillingSandboxPolicy(
+            plan_provider=plan_provider,
+            graceful_period_days=self.GRACEFUL_PERIOD_DAYS,
+            current_timestamp=now,
+        )
+
+        # Act
+        result = policy.filter_message_ids(messages, app_to_tenant)
+
+        # Assert - both beyond grace period, should be included
+        assert set(result) == {"msg1", "msg2"}
+
+    def test_empty_messages_returns_empty(self):
+        """Test that empty messages returns empty list."""
+        # Arrange
+        messages: list[SimpleMessage] = []
+        app_to_tenant = {"app1": "tenant1"}
+        plan_provider = make_plan_provider({"tenant1": {"plan": CloudPlan.SANDBOX, "expiration_date": -1}})
+
+        policy = BillingSandboxPolicy(
+            plan_provider=plan_provider,
+            graceful_period_days=self.GRACEFUL_PERIOD_DAYS,
+            current_timestamp=self.CURRENT_TIMESTAMP,
+        )
+
+        # Act
+        result = policy.filter_message_ids(messages, app_to_tenant)
+
+        # Assert
+        assert list(result) == []
+
+    def test_plan_provider_called_with_correct_tenant_ids(self):
+        """Test that plan_provider is called with correct tenant_ids."""
+        # Arrange
+        messages = [
+            make_simple_message("msg1", "app1"),
+            make_simple_message("msg2", "app2"),
+            make_simple_message("msg3", "app3"),
+        ]
+        app_to_tenant = {"app1": "tenant1", "app2": "tenant2", "app3": "tenant1"}  # tenant1 appears twice
+        plan_provider = make_plan_provider({})
+
+        policy = BillingSandboxPolicy(
+            plan_provider=plan_provider,
+            graceful_period_days=self.GRACEFUL_PERIOD_DAYS,
+            current_timestamp=self.CURRENT_TIMESTAMP,
+        )
+
+        # Act
+        policy.filter_message_ids(messages, app_to_tenant)
+
+        # Assert - plan_provider should be called once with unique tenant_ids
+        plan_provider.assert_called_once()
+        called_tenant_ids = set(plan_provider.call_args[0][0])
+        assert called_tenant_ids == {"tenant1", "tenant2"}
+
+    def test_complex_mixed_scenario(self):
+        """Test complex scenario with mixed plans, expirations, whitelist, and missing mappings."""
+        # Arrange
+        now = self.CURRENT_TIMESTAMP
+        sandbox_expired_old = now - (15 * 24 * 60 * 60)  # Beyond grace
+        sandbox_expired_recent = now - (3 * 24 * 60 * 60)  # Within grace
+        future_expiration = now + (30 * 24 * 60 * 60)
+
+        messages = [
+            make_simple_message("msg1", "app1"),  # Sandbox, no subscription - included
+            make_simple_message("msg2", "app2"),  # Sandbox, expired old - included
+            make_simple_message("msg3", "app3"),  # Sandbox, within grace - excluded
+            make_simple_message("msg4", "app4"),  # Team plan, active - excluded
+            make_simple_message("msg5", "app5"),  # No tenant mapping - excluded
+            make_simple_message("msg6", "app6"),  # No plan info - excluded
+            make_simple_message("msg7", "app7"),  # Sandbox, expired old, whitelisted - excluded
+        ]
+        app_to_tenant = {
+            "app1": "tenant1",
+            "app2": "tenant2",
+            "app3": "tenant3",
+            "app4": "tenant4",
+            "app6": "tenant6",  # Has mapping but no plan
+            "app7": "tenant7",
+            # app5 has no mapping
+        }
+        tenant_plans = {
+            "tenant1": {"plan": CloudPlan.SANDBOX, "expiration_date": -1},
+            "tenant2": {"plan": CloudPlan.SANDBOX, "expiration_date": sandbox_expired_old},
+            "tenant3": {"plan": CloudPlan.SANDBOX, "expiration_date": sandbox_expired_recent},
+            "tenant4": {"plan": CloudPlan.TEAM, "expiration_date": future_expiration},
+            "tenant7": {"plan": CloudPlan.SANDBOX, "expiration_date": sandbox_expired_old},
+            # tenant6 has no plan
+        }
+        plan_provider = make_plan_provider(tenant_plans)
+        tenant_whitelist = ["tenant7"]
+
+        policy = BillingSandboxPolicy(
+            plan_provider=plan_provider,
+            graceful_period_days=self.GRACEFUL_PERIOD_DAYS,
+            tenant_whitelist=tenant_whitelist,
+            current_timestamp=now,
+        )
+
+        # Act
+        result = policy.filter_message_ids(messages, app_to_tenant)
+
+        # Assert - only msg1 and msg2 should be included
+        assert set(result) == {"msg1", "msg2"}
+
+
+class TestBillingDisabledPolicyFilterMessageIds:
+    """Unit tests for BillingDisabledPolicy.filter_message_ids method."""
+
+    def test_returns_all_message_ids(self):
+        """Test that all message IDs are returned (order-preserving)."""
+        # Arrange
+        messages = [
+            make_simple_message("msg1", "app1"),
+            make_simple_message("msg2", "app2"),
+            make_simple_message("msg3", "app3"),
+        ]
+        app_to_tenant = {"app1": "tenant1", "app2": "tenant2"}
+
+        policy = BillingDisabledPolicy()
+
+        # Act
+        result = policy.filter_message_ids(messages, app_to_tenant)
+
+        # Assert - all message IDs returned in order
+        assert list(result) == ["msg1", "msg2", "msg3"]
+
+    def test_ignores_app_to_tenant(self):
+        """Test that app_to_tenant mapping is ignored."""
+        # Arrange
+        messages = [
+            make_simple_message("msg1", "app1"),
+            make_simple_message("msg2", "app2"),
+        ]
+        app_to_tenant: dict[str, str] = {}  # Empty - should be ignored
+
+        policy = BillingDisabledPolicy()
+
+        # Act
+        result = policy.filter_message_ids(messages, app_to_tenant)
+
+        # Assert - all message IDs still returned
+        assert list(result) == ["msg1", "msg2"]
+
+    def test_empty_messages_returns_empty(self):
+        """Test that empty messages returns empty list."""
+        # Arrange
+        messages: list[SimpleMessage] = []
+        app_to_tenant = {"app1": "tenant1"}
+
+        policy = BillingDisabledPolicy()
+
+        # Act
+        result = policy.filter_message_ids(messages, app_to_tenant)
+
+        # Assert
+        assert list(result) == []
+
+
+class TestCreateMessageCleanPolicy:
+    """Unit tests for create_message_clean_policy factory function."""
+
+    @patch("services.retention.conversation.messages_clean_policy.dify_config")
+    def test_billing_disabled_returns_billing_disabled_policy(self, mock_config):
+        """Test that BILLING_ENABLED=False returns BillingDisabledPolicy."""
+        # Arrange
+        mock_config.BILLING_ENABLED = False
+
+        # Act
+        policy = create_message_clean_policy(graceful_period_days=21)
+
+        # Assert
+        assert isinstance(policy, BillingDisabledPolicy)
+
+    @patch("services.retention.conversation.messages_clean_policy.BillingService")
+    @patch("services.retention.conversation.messages_clean_policy.dify_config")
+    def test_billing_enabled_policy_has_correct_internals(self, mock_config, mock_billing_service):
+        """Test that BillingSandboxPolicy is created with correct internal values."""
+        # Arrange
+        mock_config.BILLING_ENABLED = True
+        whitelist = ["tenant1", "tenant2"]
+        mock_billing_service.get_expired_subscription_cleanup_whitelist.return_value = whitelist
+        mock_plan_provider = MagicMock()
+        mock_billing_service.get_plan_bulk_with_cache = mock_plan_provider
+
+        # Act
+        policy = create_message_clean_policy(graceful_period_days=14, current_timestamp=1234567)
+
+        # Assert
+        mock_billing_service.get_expired_subscription_cleanup_whitelist.assert_called_once()
+        assert isinstance(policy, BillingSandboxPolicy)
+        assert policy._graceful_period_days == 14
+        assert list(policy._tenant_whitelist) == whitelist
+        assert policy._plan_provider == mock_plan_provider
+        assert policy._current_timestamp == 1234567
+
+
+class TestMessagesCleanServiceFromTimeRange:
+    """Unit tests for MessagesCleanService.from_time_range factory method."""
+
+    def test_start_from_end_before_raises_value_error(self):
+        """Test that start_from == end_before raises ValueError."""
+        policy = BillingDisabledPolicy()
+
+        # Arrange
+        same_time = datetime.datetime(2024, 1, 1, 12, 0, 0)
+
+        # Act & Assert
+        with pytest.raises(ValueError, match="start_from .* must be less than end_before"):
+            MessagesCleanService.from_time_range(
+                policy=policy,
+                start_from=same_time,
+                end_before=same_time,
+            )
+
+        # Arrange
+        start_from = datetime.datetime(2024, 12, 31)
+        end_before = datetime.datetime(2024, 1, 1)
+
+        # Act & Assert
+        with pytest.raises(ValueError, match="start_from .* must be less than end_before"):
+            MessagesCleanService.from_time_range(
+                policy=policy,
+                start_from=start_from,
+                end_before=end_before,
+            )
+
+    def test_batch_size_raises_value_error(self):
+        """Test that batch_size=0 raises ValueError."""
+        # Arrange
+        start_from = datetime.datetime(2024, 1, 1)
+        end_before = datetime.datetime(2024, 2, 1)
+        policy = BillingDisabledPolicy()
+
+        # Act & Assert
+        with pytest.raises(ValueError, match="batch_size .* must be greater than 0"):
+            MessagesCleanService.from_time_range(
+                policy=policy,
+                start_from=start_from,
+                end_before=end_before,
+                batch_size=0,
+            )
+
+        start_from = datetime.datetime(2024, 1, 1)
+        end_before = datetime.datetime(2024, 2, 1)
+        policy = BillingDisabledPolicy()
+
+        # Act & Assert
+        with pytest.raises(ValueError, match="batch_size .* must be greater than 0"):
+            MessagesCleanService.from_time_range(
+                policy=policy,
+                start_from=start_from,
+                end_before=end_before,
+                batch_size=-100,
+            )
+
+    def test_valid_params_creates_instance(self):
+        """Test that valid parameters create a correctly configured instance."""
+        # Arrange
+        start_from = datetime.datetime(2024, 1, 1, 0, 0, 0)
+        end_before = datetime.datetime(2024, 12, 31, 23, 59, 59)
+        policy = BillingDisabledPolicy()
+        batch_size = 500
+        dry_run = True
+
+        # Act
+        service = MessagesCleanService.from_time_range(
+            policy=policy,
+            start_from=start_from,
+            end_before=end_before,
+            batch_size=batch_size,
+            dry_run=dry_run,
+        )
+
+        # Assert
+        assert isinstance(service, MessagesCleanService)
+        assert service._policy is policy
+        assert service._start_from == start_from
+        assert service._end_before == end_before
+        assert service._batch_size == batch_size
+        assert service._dry_run == dry_run
+
+    def test_default_params(self):
+        """Test that default parameters are applied correctly."""
+        # Arrange
+        start_from = datetime.datetime(2024, 1, 1)
+        end_before = datetime.datetime(2024, 2, 1)
+        policy = BillingDisabledPolicy()
+
+        # Act
+        service = MessagesCleanService.from_time_range(
+            policy=policy,
+            start_from=start_from,
+            end_before=end_before,
+        )
+
+        # Assert
+        assert service._batch_size == 1000  # default
+        assert service._dry_run is False  # default
+
+
+class TestMessagesCleanServiceFromDays:
+    """Unit tests for MessagesCleanService.from_days factory method."""
+
+    def test_days_raises_value_error(self):
+        """Test that days < 0 raises ValueError."""
+        # Arrange
+        policy = BillingDisabledPolicy()
+
+        # Act & Assert
+        with pytest.raises(ValueError, match="days .* must be greater than or equal to 0"):
+            MessagesCleanService.from_days(policy=policy, days=-1)
+
+        # Act
+        with patch("services.retention.conversation.messages_clean_service.datetime") as mock_datetime:
+            fixed_now = datetime.datetime(2024, 6, 15, 14, 0, 0)
+            mock_datetime.datetime.now.return_value = fixed_now
+            mock_datetime.timedelta = datetime.timedelta
+
+            service = MessagesCleanService.from_days(policy=policy, days=0)
+
+        # Assert
+        assert service._end_before == fixed_now
+
+    def test_batch_size_raises_value_error(self):
+        """Test that batch_size=0 raises ValueError."""
+        # Arrange
+        policy = BillingDisabledPolicy()
+
+        # Act & Assert
+        with pytest.raises(ValueError, match="batch_size .* must be greater than 0"):
+            MessagesCleanService.from_days(policy=policy, days=30, batch_size=0)
+
+        # Act & Assert
+        with pytest.raises(ValueError, match="batch_size .* must be greater than 0"):
+            MessagesCleanService.from_days(policy=policy, days=30, batch_size=-500)
+
+    def test_valid_params_creates_instance(self):
+        """Test that valid parameters create a correctly configured instance."""
+        # Arrange
+        policy = BillingDisabledPolicy()
+        days = 90
+        batch_size = 500
+        dry_run = True
+
+        # Act
+        with patch("services.retention.conversation.messages_clean_service.datetime") as mock_datetime:
+            fixed_now = datetime.datetime(2024, 6, 15, 10, 30, 0)
+            mock_datetime.datetime.now.return_value = fixed_now
+            mock_datetime.timedelta = datetime.timedelta
+
+            service = MessagesCleanService.from_days(
+                policy=policy,
+                days=days,
+                batch_size=batch_size,
+                dry_run=dry_run,
+            )
+
+        # Assert
+        expected_end_before = fixed_now - datetime.timedelta(days=days)
+        assert isinstance(service, MessagesCleanService)
+        assert service._policy is policy
+        assert service._start_from is None
+        assert service._end_before == expected_end_before
+        assert service._batch_size == batch_size
+        assert service._dry_run == dry_run
+
+    def test_default_params(self):
+        """Test that default parameters are applied correctly."""
+        # Arrange
+        policy = BillingDisabledPolicy()
+
+        # Act
+        with patch("services.retention.conversation.messages_clean_service.datetime") as mock_datetime:
+            fixed_now = datetime.datetime(2024, 6, 15, 10, 30, 0)
+            mock_datetime.datetime.now.return_value = fixed_now
+            mock_datetime.timedelta = datetime.timedelta
+
+            service = MessagesCleanService.from_days(policy=policy)
+
+        # Assert
+        expected_end_before = fixed_now - datetime.timedelta(days=30)  # default days=30
+        assert service._end_before == expected_end_before
+        assert service._batch_size == 1000  # default
+        assert service._dry_run is False  # default

api/tests/unit_tests/tasks/test_mail_send_task.py

@@ -9,7 +9,7 @@ This module tests the mail sending functionality including:
 """
 
 import smtplib
-from unittest.mock import MagicMock, patch
+from unittest.mock import ANY, MagicMock, patch
 
 import pytest
 
@@ -151,7 +151,7 @@ class TestSMTPIntegration:
         client.send(mail_data)
 
         # Assert
-        mock_smtp_ssl.assert_called_once_with("smtp.example.com", 465, timeout=10)
+        mock_smtp_ssl.assert_called_once_with("smtp.example.com", 465, timeout=10, local_hostname=ANY)
         mock_server.login.assert_called_once_with("[email protected]", "password123")
         mock_server.sendmail.assert_called_once()
         mock_server.quit.assert_called_once()
@@ -181,7 +181,7 @@ class TestSMTPIntegration:
         client.send(mail_data)
 
         # Assert
-        mock_smtp.assert_called_once_with("smtp.example.com", 587, timeout=10)
+        mock_smtp.assert_called_once_with("smtp.example.com", 587, timeout=10, local_hostname=ANY)
         mock_server.ehlo.assert_called()
         mock_server.starttls.assert_called_once()
         assert mock_server.ehlo.call_count == 2  # Before and after STARTTLS
@@ -213,7 +213,7 @@ class TestSMTPIntegration:
         client.send(mail_data)
 
         # Assert
-        mock_smtp.assert_called_once_with("smtp.example.com", 25, timeout=10)
+        mock_smtp.assert_called_once_with("smtp.example.com", 25, timeout=10, local_hostname=ANY)
         mock_server.login.assert_called_once()
         mock_server.sendmail.assert_called_once()
         mock_server.quit.assert_called_once()

docker/.env.example

@@ -968,6 +968,8 @@ SMTP_USERNAME=
 SMTP_PASSWORD=
 SMTP_USE_TLS=true
 SMTP_OPPORTUNISTIC_TLS=false
+# Optional: override the local hostname used for SMTP HELO/EHLO
+SMTP_LOCAL_HOSTNAME=
 
 # Sendgid configuration
 SENDGRID_API_KEY=

docker/docker-compose-template.yaml

@@ -21,7 +21,7 @@ services:
 
   # API service
   api:
-    image: langgenius/dify-api:1.11.3
+    image: langgenius/dify-api:1.11.4
     restart: always
     environment:
       # Use the shared environment variables.
@@ -63,7 +63,7 @@ services:
   # worker service
   # The Celery worker for processing all queues (dataset, workflow, mail, etc.)
   worker:
-    image: langgenius/dify-api:1.11.3
+    image: langgenius/dify-api:1.11.4
     restart: always
     environment:
       # Use the shared environment variables.
@@ -102,7 +102,7 @@ services:
   # worker_beat service
   # Celery beat for scheduling periodic tasks.
   worker_beat:
-    image: langgenius/dify-api:1.11.3
+    image: langgenius/dify-api:1.11.4
     restart: always
     environment:
       # Use the shared environment variables.
@@ -132,7 +132,7 @@ services:
 
   # Frontend web application.
   web:
-    image: langgenius/dify-web:1.11.3
+    image: langgenius/dify-web:1.11.4
     restart: always
     environment:
       CONSOLE_API_URL: ${CONSOLE_API_URL:-}

docker/docker-compose.yaml

@@ -425,6 +425,7 @@ x-shared-env: &shared-api-worker-env
   SMTP_PASSWORD: ${SMTP_PASSWORD:-}
   SMTP_USE_TLS: ${SMTP_USE_TLS:-true}
   SMTP_OPPORTUNISTIC_TLS: ${SMTP_OPPORTUNISTIC_TLS:-false}
+  SMTP_LOCAL_HOSTNAME: ${SMTP_LOCAL_HOSTNAME:-}
   SENDGRID_API_KEY: ${SENDGRID_API_KEY:-}
   INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH: ${INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH:-4000}
   INVITE_EXPIRY_HOURS: ${INVITE_EXPIRY_HOURS:-72}
@@ -704,7 +705,7 @@ services:
 
   # API service
   api:
-    image: langgenius/dify-api:1.11.3
+    image: langgenius/dify-api:1.11.4
     restart: always
     environment:
       # Use the shared environment variables.
@@ -746,7 +747,7 @@ services:
   # worker service
   # The Celery worker for processing all queues (dataset, workflow, mail, etc.)
   worker:
-    image: langgenius/dify-api:1.11.3
+    image: langgenius/dify-api:1.11.4
     restart: always
     environment:
       # Use the shared environment variables.
@@ -785,7 +786,7 @@ services:
   # worker_beat service
   # Celery beat for scheduling periodic tasks.
   worker_beat:
-    image: langgenius/dify-api:1.11.3
+    image: langgenius/dify-api:1.11.4
     restart: always
     environment:
       # Use the shared environment variables.
@@ -815,7 +816,7 @@ services:
 
   # Frontend web application.
   web:
-    image: langgenius/dify-web:1.11.3
+    image: langgenius/dify-web:1.11.4
     restart: always
     environment:
       CONSOLE_API_URL: ${CONSOLE_API_URL:-}

web/.nvmrc

@@ -1 +1 @@
-22.21.1
+24

web/Dockerfile

@@ -1,5 +1,5 @@
 # base image
-FROM node:22.21.1-alpine3.23 AS base
+FROM node:24-alpine AS base
 LABEL maintainer="[email protected]"
 
 # if you located in China, you can use aliyun mirror to speed up

web/README.md

@@ -8,8 +8,8 @@ This is a [Next.js](https://nextjs.org/) project bootstrapped with [`create-next
 
 Before starting the web frontend service, please make sure the following environment is ready.
 
-- [Node.js](https://nodejs.org) >= v22.11.x
-- [pnpm](https://pnpm.io) v10.x
+- [Node.js](https://nodejs.org)
+- [pnpm](https://pnpm.io)
 
 > [!TIP]
 > It is recommended to install and enable Corepack to manage package manager versions automatically:

web/app/(shareLayout)/webapp-signin/check-code/page.tsx

@@ -66,7 +66,9 @@ export default function CheckCode() {
       setIsLoading(true)
       const ret = await webAppEmailLoginWithCode({ email, code: encryptVerificationCode(code), token })
       if (ret.result === 'success') {
-        setWebAppAccessToken(ret.data.access_token)
+        if (ret?.data?.access_token) {
+          setWebAppAccessToken(ret.data.access_token)
+        }
         const { access_token } = await fetchAccessToken({
           appCode: appCode!,
           userId: embeddedUserId || undefined,

web/app/(shareLayout)/webapp-signin/components/mail-and-password-auth.tsx

@@ -82,7 +82,9 @@ export default function MailAndPasswordAuth({ isEmailSetup }: MailAndPasswordAut
         body: loginData,
       })
       if (res.result === 'success') {
-        setWebAppAccessToken(res.data.access_token)
+        if (res?.data?.access_token) {
+          setWebAppAccessToken(res.data.access_token)
+        }
 
         const { access_token } = await fetchAccessToken({
           appCode: appCode!,