Clarify INTERNAL_FILES_URL comments

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

.agents/skills/backend-code-review/SKILL.md

@@ -0,0 +1,168 @@
+---
+name: backend-code-review
+description: Review backend code for quality, security, maintainability, and best practices based on established checklist rules. Use when the user requests a review, analysis, or improvement of backend files (e.g., `.py`) under the `api/` directory. Do NOT use for frontend files (e.g., `.tsx`, `.ts`, `.js`). Supports pending-change review, code snippets review, and file-focused review.
+---
+
+# Backend Code Review
+
+## When to use this skill
+
+Use this skill whenever the user asks to **review, analyze, or improve** backend code (e.g., `.py`) under the `api/` directory. Supports the following review modes:
+
+- **Pending-change review**: when the user asks to review current changes (inspect staged/working-tree files slated for commit to get the changes).
+- **Code snippets review**: when the user pastes code snippets (e.g., a function/class/module excerpt) into the chat and asks for a review.
+- **File-focused review**: when the user points to specific files and asks for a review of those files (one file or a small, explicit set of files, e.g., `api/...`, `api/app.py`).
+
+Do NOT use this skill when:
+
+- The request is about frontend code or UI (e.g., `.tsx`, `.ts`, `.js`, `web/`).
+- The user is not asking for a review/analysis/improvement of backend code.
+- The scope is not under `api/` (unless the user explicitly asks to review backend-related changes outside `api/`).
+
+## How to use this skill
+
+Follow these steps when using this skill:
+
+1. **Identify the review mode** (pending-change vs snippet vs file-focused) based on the user’s input. Keep the scope tight: review only what the user provided or explicitly referenced.
+2. Follow the rules defined in **Checklist** to perform the review. If no Checklist rule matches, apply **General Review Rules** as a fallback to perform the best-effort review.
+3. Compose the final output strictly follow the **Required Output Format**.
+
+Notes when using this skill:
+- Always include actionable fixes or suggestions (including possible code snippets).
+- Use best-effort `File:Line` references when a file path and line numbers are available; otherwise, use the most specific identifier you can.
+
+## Checklist
+
+- db schema design: if the review scope includes code/files under `api/models/` or `api/migrations/`, follow [references/db-schema-rule.md](references/db-schema-rule.md) to perform the review
+- architecture: if the review scope involves controller/service/core-domain/libs/model layering, dependency direction, or moving responsibilities across modules, follow [references/architecture-rule.md](references/architecture-rule.md) to perform the review
+- repositories abstraction: if the review scope contains table/model operations (e.g., `select(...)`, `session.execute(...)`, joins, CRUD) and is not under `api/repositories`, `api/core/repositories`, or `api/extensions/*/repositories/`, follow [references/repositories-rule.md](references/repositories-rule.md) to perform the review
+- sqlalchemy patterns: if the review scope involves SQLAlchemy session/query usage, db transaction/crud usage, or raw SQL usage, follow [references/sqlalchemy-rule.md](references/sqlalchemy-rule.md) to perform the review
+
+## General Review Rules
+
+### 1. Security Review
+
+Check for:
+- SQL injection vulnerabilities
+- Server-Side Request Forgery (SSRF)
+- Command injection
+- Insecure deserialization
+- Hardcoded secrets/credentials
+- Improper authentication/authorization
+- Insecure direct object references
+
+### 2. Performance Review
+
+Check for:
+- N+1 queries
+- Missing database indexes
+- Memory leaks
+- Blocking operations in async code
+- Missing caching opportunities
+
+### 3. Code Quality Review
+
+Check for:
+- Code forward compatibility
+- Code duplication (DRY violations)
+- Functions doing too much (SRP violations)
+- Deep nesting / complex conditionals
+- Magic numbers/strings
+- Poor naming
+- Missing error handling
+- Incomplete type coverage
+
+### 4. Testing Review
+
+Check for:
+- Missing test coverage for new code
+- Tests that don't test behavior
+- Flaky test patterns
+- Missing edge cases
+
+## Required Output Format
+
+When this skill invoked, the response must exactly follow one of the two templates:
+
+### Template A (any findings)
+
+```markdown
+# Code Review Summary
+
+Found <X> critical issues need to be fixed:
+
+## 🔴 Critical (Must Fix)
+
+### 1. <brief description of the issue>
+
+FilePath: <path> line <line>
+<relevant code snippet or pointer>
+
+#### Explanation
+
+<detailed explanation and references of the issue>
+
+#### Suggested Fix
+
+1. <brief description of suggested fix>
+2. <code example> (optional, omit if not applicable)
+
+---
+... (repeat for each critical issue) ...
+
+Found <Y> suggestions for improvement:
+
+## 🟡 Suggestions (Should Consider)
+
+### 1. <brief description of the suggestion>
+
+FilePath: <path> line <line>
+<relevant code snippet or pointer>
+
+#### Explanation
+
+<detailed explanation and references of the suggestion>
+
+#### Suggested Fix
+
+1. <brief description of suggested fix>
+2. <code example> (optional, omit if not applicable)
+
+---
+... (repeat for each suggestion) ...
+
+Found <Z> optional nits:
+
+## 🟢 Nits (Optional)
+### 1. <brief description of the nit>
+
+FilePath: <path> line <line>
+<relevant code snippet or pointer>
+
+#### Explanation
+
+<explanation and references of the optional nit>
+
+#### Suggested Fix
+
+- <minor suggestions>
+
+---
+... (repeat for each nits) ...
+
+## ✅ What's Good
+
+- <Positive feedback on good patterns>
+```
+
+- If there are no critical issues or suggestions or option nits or good points, just omit that section.
+- If the issue number is more than 10, summarize as "Found 10+ critical issues/suggestions/optional nits" and only output the first 10 items.
+- Don't compress the blank lines between sections; keep them as-is for readability.
+- If there is any issue requires code changes, append a brief follow-up question to ask whether the user wants to apply the fix(es) after the structured output. For example: "Would you like me to use the Suggested fix(es) to address these issues?"
+
+### Template B (no issues)
+
+```markdown
+## Code Review Summary
+✅ No issues found.
+```

.agents/skills/backend-code-review/references/architecture-rule.md

@@ -0,0 +1,91 @@
+# Rule Catalog — Architecture
+
+## Scope
+- Covers: controller/service/core-domain/libs/model layering, dependency direction, responsibility placement, observability-friendly flow.
+
+## Rules
+
+### Keep business logic out of controllers
+- Category: maintainability
+- Severity: critical
+- Description: Controllers should parse input, call services, and return serialized responses. Business decisions inside controllers make behavior hard to reuse and test.
+- Suggested fix: Move domain/business logic into the service or core/domain layer. Keep controller handlers thin and orchestration-focused.
+- Example:
+  - Bad:
+    ```python
+    @bp.post("/apps/<app_id>/publish")
+    def publish_app(app_id: str):
+        payload = request.get_json() or {}
+        if payload.get("force") and current_user.role != "admin":
+            raise ValueError("only admin can force publish")
+        app = App.query.get(app_id)
+        app.status = "published"
+        db.session.commit()
+        return {"result": "ok"}
+    ```
+  - Good:
+    ```python
+    @bp.post("/apps/<app_id>/publish")
+    def publish_app(app_id: str):
+        payload = PublishRequest.model_validate(request.get_json() or {})
+        app_service.publish_app(app_id=app_id, force=payload.force, actor_id=current_user.id)
+        return {"result": "ok"}
+    ```
+
+### Preserve layer dependency direction
+- Category: best practices
+- Severity: critical
+- Description: Controllers may depend on services, and services may depend on core/domain abstractions. Reversing this direction (for example, core importing controller/web modules) creates cycles and leaks transport concerns into domain code.
+- Suggested fix: Extract shared contracts into core/domain or service-level modules and make upper layers depend on lower, not the reverse.
+- Example:
+  - Bad:
+    ```python
+    # core/policy/publish_policy.py
+    from controllers.console.app import request_context
+
+    def can_publish() -> bool:
+        return request_context.current_user.is_admin
+    ```
+  - Good:
+    ```python
+    # core/policy/publish_policy.py
+    def can_publish(role: str) -> bool:
+        return role == "admin"
+
+    # service layer adapts web/user context to domain input
+    allowed = can_publish(role=current_user.role)
+    ```
+
+### Keep libs business-agnostic
+- Category: maintainability
+- Severity: critical
+- Description: Modules under `api/libs/` should remain reusable, business-agnostic building blocks. They must not encode product/domain-specific rules, workflow orchestration, or business decisions.
+- Suggested fix:
+  - If business logic appears in `api/libs/`, extract it into the appropriate `services/` or `core/` module and keep `libs` focused on generic, cross-cutting helpers.
+  - Keep `libs` dependencies clean: avoid importing service/controller/domain-specific modules into `api/libs/`.
+- Example:
+  - Bad:
+    ```python
+    # api/libs/conversation_filter.py
+    from services.conversation_service import ConversationService
+
+    def should_archive_conversation(conversation, tenant_id: str) -> bool:
+        # Domain policy and service dependency are leaking into libs.
+        service = ConversationService()
+        if service.has_paid_plan(tenant_id):
+            return conversation.idle_days > 90
+        return conversation.idle_days > 30
+    ```
+  - Good:
+    ```python
+    # api/libs/datetime_utils.py (business-agnostic helper)
+    def older_than_days(idle_days: int, threshold_days: int) -> bool:
+        return idle_days > threshold_days
+
+    # services/conversation_service.py (business logic stays in service/core)
+    from libs.datetime_utils import older_than_days
+
+    def should_archive_conversation(conversation, tenant_id: str) -> bool:
+        threshold_days = 90 if has_paid_plan(tenant_id) else 30
+        return older_than_days(conversation.idle_days, threshold_days)
+    ```

.agents/skills/backend-code-review/references/db-schema-rule.md

@@ -0,0 +1,157 @@
+# Rule Catalog — DB Schema Design
+
+## Scope
+- Covers: model/base inheritance, schema boundaries in model properties, tenant-aware schema design, index redundancy checks, dialect portability in models, and cross-database compatibility in migrations.
+- Does NOT cover: session lifecycle, transaction boundaries, and query execution patterns (handled by `sqlalchemy-rule.md`).
+
+## Rules
+
+### Do not query other tables inside `@property`
+- Category: [maintainability, performance]
+- Severity: critical
+- Description: A model `@property` must not open sessions or query other tables. This hides dependencies across models, tightly couples schema objects to data access, and can cause N+1 query explosions when iterating collections.
+- Suggested fix:
+  - Keep model properties pure and local to already-loaded fields.
+  - Move cross-table data fetching to service/repository methods.
+  - For list/batch reads, fetch required related data explicitly (join/preload/bulk query) before rendering derived values.
+- Example:
+  - Bad:
+    ```python
+    class Conversation(TypeBase):
+        __tablename__ = "conversations"
+
+        @property
+        def app_name(self) -> str:
+            with Session(db.engine, expire_on_commit=False) as session:
+                app = session.execute(select(App).where(App.id == self.app_id)).scalar_one()
+                return app.name
+    ```
+  - Good:
+    ```python
+    class Conversation(TypeBase):
+        __tablename__ = "conversations"
+
+        @property
+        def display_title(self) -> str:
+            return self.name or "Untitled"
+
+
+    # Service/repository layer performs explicit batch fetch for related App rows.
+    ```
+
+### Prefer including `tenant_id` in model definitions
+- Category: maintainability
+- Severity: suggestion
+- Description: In multi-tenant domains, include `tenant_id` in schema definitions whenever the entity belongs to tenant-owned data. This improves data isolation safety and keeps future partitioning/sharding strategies practical as data volume grows.
+- Suggested fix:
+  - Add a `tenant_id` column and ensure related unique/index constraints include tenant dimension when applicable.
+  - Propagate `tenant_id` through service/repository contracts to keep access paths tenant-aware.
+  - Exception: if a table is explicitly designed as non-tenant-scoped global metadata, document that design decision clearly.
+- Example:
+  - Bad:
+    ```python
+    from sqlalchemy.orm import Mapped
+
+    class Dataset(TypeBase):
+        __tablename__ = "datasets"
+        id: Mapped[str] = mapped_column(StringUUID, primary_key=True)
+        name: Mapped[str] = mapped_column(sa.String(255), nullable=False)
+    ```
+  - Good:
+    ```python
+    from sqlalchemy.orm import Mapped
+
+    class Dataset(TypeBase):
+        __tablename__ = "datasets"
+        id: Mapped[str] = mapped_column(StringUUID, primary_key=True)
+        tenant_id: Mapped[str] = mapped_column(StringUUID, nullable=False, index=True)
+        name: Mapped[str] = mapped_column(sa.String(255), nullable=False)
+    ```
+
+### Detect and avoid duplicate/redundant indexes
+- Category: performance
+- Severity: suggestion
+- Description: Review index definitions for leftmost-prefix redundancy. For example, index `(a, b, c)` can safely cover most lookups for `(a, b)`. Keeping both may increase write overhead and can mislead the optimizer into suboptimal execution plans.
+- Suggested fix:
+  - Before adding an index, compare against existing composite indexes by leftmost-prefix rules.
+  - Drop or avoid creating redundant prefixes unless there is a proven query-pattern need.
+  - Apply the same review standard in both model `__table_args__` and migration index DDL.
+- Example:
+  - Bad:
+    ```python
+    __table_args__ = (
+        sa.Index("idx_msg_tenant_app", "tenant_id", "app_id"),
+        sa.Index("idx_msg_tenant_app_created", "tenant_id", "app_id", "created_at"),
+    )
+    ```
+  - Good:
+    ```python
+    __table_args__ = (
+        # Keep the wider index unless profiling proves a dedicated short index is needed.
+        sa.Index("idx_msg_tenant_app_created", "tenant_id", "app_id", "created_at"),
+    )
+    ```
+
+### Avoid PostgreSQL-only dialect usage in models; wrap in `models.types`
+- Category: maintainability
+- Severity: critical
+- Description: Model/schema definitions should avoid PostgreSQL-only constructs directly in business models. When database-specific behavior is required, encapsulate it in `api/models/types.py` using both PostgreSQL and MySQL dialect implementations, then consume that abstraction from model code.
+- Suggested fix:
+  - Do not directly place dialect-only types/operators in model columns when a portable wrapper can be used.
+  - Add or extend wrappers in `models.types` (for example, `AdjustedJSON`, `LongText`, `BinaryData`) to normalize behavior across PostgreSQL and MySQL.
+- Example:
+  - Bad:
+    ```python
+    from sqlalchemy.dialects.postgresql import JSONB
+    from sqlalchemy.orm import Mapped
+
+    class ToolConfig(TypeBase):
+        __tablename__ = "tool_configs"
+        config: Mapped[dict] = mapped_column(JSONB, nullable=False)
+    ```
+  - Good:
+    ```python
+    from sqlalchemy.orm import Mapped
+
+    from models.types import AdjustedJSON
+
+    class ToolConfig(TypeBase):
+        __tablename__ = "tool_configs"
+        config: Mapped[dict] = mapped_column(AdjustedJSON(), nullable=False)
+    ```
+
+### Guard migration incompatibilities with dialect checks and shared types
+- Category: maintainability
+- Severity: critical
+- Description: Migration scripts under `api/migrations/versions/` must account for PostgreSQL/MySQL incompatibilities explicitly. For dialect-sensitive DDL or defaults, branch on the active dialect (for example, `conn.dialect.name == "postgresql"`), and prefer reusable compatibility abstractions from `models.types` where applicable.
+- Suggested fix:
+  - In migration upgrades/downgrades, bind connection and branch by dialect for incompatible SQL fragments.
+  - Reuse `models.types` wrappers in column definitions when that keeps behavior aligned with runtime models.
+  - Avoid one-dialect-only migration logic unless there is a documented, deliberate compatibility exception.
+- Example:
+  - Bad:
+    ```python
+    with op.batch_alter_table("dataset_keyword_tables") as batch_op:
+        batch_op.add_column(
+            sa.Column(
+                "data_source_type",
+                sa.String(255),
+                server_default=sa.text("'database'::character varying"),
+                nullable=False,
+            )
+        )
+    ```
+  - Good:
+    ```python
+    def _is_pg(conn) -> bool:
+        return conn.dialect.name == "postgresql"
+
+
+    conn = op.get_bind()
+    default_expr = sa.text("'database'::character varying") if _is_pg(conn) else sa.text("'database'")
+
+    with op.batch_alter_table("dataset_keyword_tables") as batch_op:
+        batch_op.add_column(
+            sa.Column("data_source_type", sa.String(255), server_default=default_expr, nullable=False)
+        )
+    ```

.agents/skills/backend-code-review/references/repositories-rule.md

@@ -0,0 +1,61 @@
+# Rule Catalog - Repositories Abstraction
+
+## Scope
+- Covers: when to reuse existing repository abstractions, when to introduce new repositories, and how to preserve dependency direction between service/core and infrastructure implementations.
+- Does NOT cover: SQLAlchemy session lifecycle and query-shape specifics (handled by `sqlalchemy-rule.md`), and table schema/migration design (handled by `db-schema-rule.md`).
+
+## Rules
+
+### Introduce repositories abstraction
+- Category: maintainability
+- Severity: suggestion
+- Description: If a table/model already has a repository abstraction, all reads/writes/queries for that table should use the existing repository. If no repository exists, introduce one only when complexity justifies it, such as large/high-volume tables, repeated complex query logic, or likely storage-strategy variation.
+- Suggested fix:
+  - First check  `api/repositories`, `api/core/repositories`, and `api/extensions/*/repositories/` to verify whether the table/model already has a repository abstraction. If it exists, route all operations through it and add missing repository methods instead of bypassing it with ad-hoc SQLAlchemy access.
+  - If no repository exists, add one only when complexity warrants it (for example, repeated complex queries, large data domains, or multiple storage strategies), while preserving dependency direction (service/core depends on abstraction; infra provides implementation).
+- Example:
+  - Bad:
+    ```python
+    # Existing repository is ignored and service uses ad-hoc table queries.
+    class AppService:
+        def archive_app(self, app_id: str, tenant_id: str) -> None:
+            app = self.session.execute(
+                select(App).where(App.id == app_id, App.tenant_id == tenant_id)
+            ).scalar_one()
+            app.archived = True
+            self.session.commit()
+    ```
+  - Good:
+    ```python
+    # Case A: Existing repository must be reused for all table operations.
+    class AppService:
+        def archive_app(self, app_id: str, tenant_id: str) -> None:
+            app = self.app_repo.get_by_id(app_id=app_id, tenant_id=tenant_id)
+            app.archived = True
+            self.app_repo.save(app)
+
+    # If the query is missing, extend the existing abstraction.
+    active_apps = self.app_repo.list_active_for_tenant(tenant_id=tenant_id)
+    ```
+  - Bad:
+    ```python
+    # No repository exists, but large-domain query logic is scattered in service code.
+    class ConversationService:
+        def list_recent_for_app(self, app_id: str, tenant_id: str, limit: int) -> list[Conversation]:
+            ...
+            # many filters/joins/pagination variants duplicated across services
+    ```
+  - Good:
+    ```python
+    # Case B: Introduce repository for large/complex domains or storage variation.
+    class ConversationRepository(Protocol):
+        def list_recent_for_app(self, app_id: str, tenant_id: str, limit: int) -> list[Conversation]: ...
+
+    class SqlAlchemyConversationRepository:
+        def list_recent_for_app(self, app_id: str, tenant_id: str, limit: int) -> list[Conversation]:
+            ...
+
+    class ConversationService:
+        def __init__(self, conversation_repo: ConversationRepository):
+            self.conversation_repo = conversation_repo
+    ```

.agents/skills/backend-code-review/references/sqlalchemy-rule.md

@@ -0,0 +1,139 @@
+# Rule Catalog — SQLAlchemy Patterns
+
+## Scope
+- Covers: SQLAlchemy session and transaction lifecycle, query construction, tenant scoping, raw SQL boundaries, and write-path concurrency safeguards.
+- Does NOT cover: table/model schema and migration design details (handled by `db-schema-rule.md`).
+
+## Rules
+
+### Use Session context manager with explicit transaction control behavior
+- Category: best practices
+- Severity: critical
+- Description: Session and transaction lifecycle must be explicit and bounded on write paths. Missing commits can silently drop intended updates, while ad-hoc or long-lived transactions increase contention, lock duration, and deadlock risk.
+- Suggested fix:
+  - Use **explicit `session.commit()`** after completing a related write unit.
+  - Or use **`session.begin()` context manager** for automatic commit/rollback on a scoped block.
+  - Keep transaction windows short: avoid network I/O, heavy computation, or unrelated work inside the transaction.
+- Example:
+  - Bad:
+    ```python
+    # Missing commit: write may never be persisted.
+    with Session(db.engine, expire_on_commit=False) as session:
+        run = session.get(WorkflowRun, run_id)
+        run.status = "cancelled"
+
+    # Long transaction: external I/O inside a DB transaction.
+    with Session(db.engine, expire_on_commit=False) as session, session.begin():
+        run = session.get(WorkflowRun, run_id)
+        run.status = "cancelled"
+        call_external_api()
+    ```
+  - Good:
+    ```python
+    # Option 1: explicit commit.
+    with Session(db.engine, expire_on_commit=False) as session:
+        run = session.get(WorkflowRun, run_id)
+        run.status = "cancelled"
+        session.commit()
+
+    # Option 2: scoped transaction with automatic commit/rollback.
+    with Session(db.engine, expire_on_commit=False) as session, session.begin():
+        run = session.get(WorkflowRun, run_id)
+        run.status = "cancelled"
+
+    # Keep non-DB work outside transaction scope.
+    call_external_api()
+    ```
+
+### Enforce tenant_id scoping on shared-resource queries
+- Category: security
+- Severity: critical
+- Description: Reads and writes against shared tables must be scoped by `tenant_id` to prevent cross-tenant data leakage or corruption.
+- Suggested fix: Add `tenant_id` predicate to all tenant-owned entity queries and propagate tenant context through service/repository interfaces.
+- Example:
+  - Bad:
+    ```python
+    stmt = select(Workflow).where(Workflow.id == workflow_id)
+    workflow = session.execute(stmt).scalar_one_or_none()
+    ```
+  - Good:
+    ```python
+    stmt = select(Workflow).where(
+        Workflow.id == workflow_id,
+        Workflow.tenant_id == tenant_id,
+    )
+    workflow = session.execute(stmt).scalar_one_or_none()
+    ```
+
+### Prefer SQLAlchemy expressions over raw SQL by default
+- Category: maintainability
+- Severity: suggestion
+- Description: Raw SQL should be exceptional. ORM/Core expressions are easier to evolve, safer to compose, and more consistent with the codebase.
+- Suggested fix: Rewrite straightforward raw SQL into SQLAlchemy `select/update/delete` expressions; keep raw SQL only when required by clear technical constraints.
+- Example:
+  - Bad:
+    ```python
+    row = session.execute(
+        text("SELECT * FROM workflows WHERE id = :id AND tenant_id = :tenant_id"),
+        {"id": workflow_id, "tenant_id": tenant_id},
+    ).first()
+    ```
+  - Good:
+    ```python
+    stmt = select(Workflow).where(
+        Workflow.id == workflow_id,
+        Workflow.tenant_id == tenant_id,
+    )
+    row = session.execute(stmt).scalar_one_or_none()
+    ```
+
+### Protect write paths with concurrency safeguards
+- Category: quality
+- Severity: critical
+- Description: Multi-writer paths without explicit concurrency control can silently overwrite data. Choose the safeguard based on contention level, lock scope, and throughput cost instead of defaulting to one strategy.
+- Suggested fix:
+  - **Optimistic locking**: Use when contention is usually low and retries are acceptable. Add a version (or updated_at) guard in `WHERE` and treat `rowcount == 0` as a conflict.
+  - **Redis distributed lock**: Use when the critical section spans multiple steps/processes (or includes non-DB side effects) and you need cross-worker mutual exclusion.
+  - **SELECT ... FOR UPDATE**: Use when contention is high on the same rows and strict in-transaction serialization is required. Keep transactions short to reduce lock wait/deadlock risk.
+  - In all cases, scope by `tenant_id` and verify affected row counts for conditional writes.
+- Example:
+  - Bad:
+    ```python
+    # No tenant scope, no conflict detection, and no lock on a contested write path.
+    session.execute(update(WorkflowRun).where(WorkflowRun.id == run_id).values(status="cancelled"))
+    session.commit()  # silently overwrites concurrent updates
+    ```
+  - Good:
+    ```python
+    # 1) Optimistic lock (low contention, retry on conflict)
+    result = session.execute(
+        update(WorkflowRun)
+        .where(
+            WorkflowRun.id == run_id,
+            WorkflowRun.tenant_id == tenant_id,
+            WorkflowRun.version == expected_version,
+        )
+        .values(status="cancelled", version=WorkflowRun.version + 1)
+    )
+    if result.rowcount == 0:
+        raise WorkflowStateConflictError("stale version, retry")
+
+    # 2) Redis distributed lock (cross-worker critical section)
+    lock_name = f"workflow_run_lock:{tenant_id}:{run_id}"
+    with redis_client.lock(lock_name, timeout=20):
+        session.execute(
+            update(WorkflowRun)
+            .where(WorkflowRun.id == run_id, WorkflowRun.tenant_id == tenant_id)
+            .values(status="cancelled")
+        )
+        session.commit()
+
+    # 3) Pessimistic lock with SELECT ... FOR UPDATE (high contention)
+    run = session.execute(
+        select(WorkflowRun)
+        .where(WorkflowRun.id == run_id, WorkflowRun.tenant_id == tenant_id)
+        .with_for_update()
+    ).scalar_one()
+    run.status = "cancelled"
+    session.commit()
+    ```

.agents/skills/frontend-testing/SKILL.md

@@ -204,6 +204,16 @@ When assigned to test a directory/path, test **ALL content** within that path:
 
 > See [Test Structure Template](#test-structure-template) for correct import/mock patterns.
 
+### `nuqs` Query State Testing (Required for URL State Hooks)
+
+When a component or hook uses `useQueryState` / `useQueryStates`:
+
+- ✅ Use `NuqsTestingAdapter` (prefer shared helpers in `web/test/nuqs-testing.tsx`)
+- ✅ Assert URL synchronization via `onUrlUpdate` (`searchParams`, `options.history`)
+- ✅ For custom parsers (`createParser`), keep `parse` and `serialize` bijective and add round-trip edge cases (`%2F`, `%25`, spaces, legacy encoded values)
+- ✅ Verify default-clearing behavior (default values should be removed from URL when applicable)
+- ⚠️ Only mock `nuqs` directly when URL behavior is explicitly out of scope for the test
+
 ## Core Principles
 
 ### 1. AAA Pattern (Arrange-Act-Assert)

.agents/skills/frontend-testing/references/checklist.md

@@ -80,6 +80,9 @@ Use this checklist when generating or reviewing tests for Dify frontend componen
 - [ ] Router mocks match actual Next.js API
 - [ ] Mocks reflect actual component conditional behavior
 - [ ] Only mock: API services, complex context providers, third-party libs
+- [ ] For `nuqs` URL-state tests, wrap with `NuqsTestingAdapter` (prefer `web/test/nuqs-testing.tsx`)
+- [ ] For `nuqs` URL-state tests, assert `onUrlUpdate` payload (`searchParams`, `options.history`)
+- [ ] If custom `nuqs` parser exists, add round-trip tests for encoded edge cases (`%2F`, `%25`, spaces, legacy encoded values)
 
 ### Queries
 

.agents/skills/frontend-testing/references/mocking.md

@@ -125,6 +125,31 @@ describe('Component', () => {
 })
 ```
 
+### 2.1 `nuqs` Query State (Preferred: Testing Adapter)
+
+For tests that validate URL query behavior, use `NuqsTestingAdapter` instead of mocking `nuqs` directly.
+
+```typescript
+import { renderHookWithNuqs } from '@/test/nuqs-testing'
+
+it('should sync query to URL with push history', async () => {
+  const { result, onUrlUpdate } = renderHookWithNuqs(() => useMyQueryState(), {
+    searchParams: '?page=1',
+  })
+
+  act(() => {
+    result.current.setQuery({ page: 2 })
+  })
+
+  await waitFor(() => expect(onUrlUpdate).toHaveBeenCalled())
+  const update = onUrlUpdate.mock.calls[onUrlUpdate.mock.calls.length - 1][0]
+  expect(update.options.history).toBe('push')
+  expect(update.searchParams.get('page')).toBe('2')
+})
+```
+
+Use direct `vi.mock('nuqs')` only when URL synchronization is intentionally out of scope.
+
 ### 3. Portal Components (with Shared State)
 
 ```typescript

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

@@ -1,43 +1,100 @@
 ---
 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.
+description: Guide for implementing oRPC contract-first API patterns in Dify frontend. Trigger when creating or updating contracts in web/contract, wiring router composition, integrating TanStack Query with typed contracts, migrating legacy service calls to oRPC, or deciding whether to call queryOptions directly vs extracting a helper or use-* hook in web/service.
 ---
 
 # oRPC Contract-First Development
 
-## Project Structure
+## Intent
 
-```
+- Keep contract as single source of truth in `web/contract/*`.
+- Default query usage: call-site `useQuery(consoleQuery|marketplaceQuery.xxx.queryOptions(...))` when endpoint behavior maps 1:1 to the contract.
+- Keep abstractions minimal and preserve TypeScript inference.
+
+## Minimal Structure
+
+```text
 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
+├── base.ts
+├── router.ts
+├── marketplace.ts
+└── console/
+    ├── billing.ts
+    └── ...other domains
+web/service/client.ts
 ```
 
-## Workflow
+## Core 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`
+1. Define contract in `web/contract/console/{domain}.ts` or `web/contract/marketplace.ts`
+   - Use `base.route({...}).output(type<...>())` as baseline.
+   - Add `.input(type<...>())` only when request has `params/query/body`.
+   - For `GET` without input, omit `.input(...)` (do not use `.input(type<unknown>())`).
+2. Register contract in `web/contract/router.ts`
+   - Import directly from domain files and nest by API prefix.
+3. Consume from UI call sites via oRPC query utils.
 
-2. **Register in router** at `web/contract/router.ts`
-   - Import directly from domain file (no barrel files)
-   - Nest by API prefix: `billing: { invoices, bindPartnerStack }`
+```typescript
+import { useQuery } from '@tanstack/react-query'
+import { consoleQuery } from '@/service/client'
 
-3. **Create hooks** in `web/service/use-{domain}.ts`
-   - Use `consoleQuery.{group}.{contract}.queryKey()` for query keys
-   - Use `consoleClient.{group}.{contract}()` for API calls
+const invoiceQuery = useQuery(consoleQuery.billing.invoices.queryOptions({
+  staleTime: 5 * 60 * 1000,
+  throwOnError: true,
+  select: invoice => invoice.url,
+}))
+```
 
-## Key Rules
+## Query Usage Decision Rule
+
+1. Default: call site directly uses `*.queryOptions(...)`.
+2. If 3+ call sites share the same extra options (for example `retry: false`), extract a small queryOptions helper, not a `use-*` passthrough hook.
+3. Create `web/service/use-{domain}.ts` only for orchestration:
+   - Combine multiple queries/mutations.
+   - Share domain-level derived state or invalidation helpers.
+
+```typescript
+const invoicesBaseQueryOptions = () =>
+  consoleQuery.billing.invoices.queryOptions({ retry: false })
+
+const invoiceQuery = useQuery({
+  ...invoicesBaseQueryOptions(),
+  throwOnError: true,
+})
+```
+
+## Mutation Usage Decision Rule
+
+1. Default: call mutation helpers from `consoleQuery` / `marketplaceQuery`, for example `useMutation(consoleQuery.billing.bindPartnerStack.mutationOptions(...))`.
+2. If mutation flow is heavily custom, use oRPC clients as `mutationFn` (for example `consoleClient.xxx` / `marketplaceClient.xxx`), instead of generic handwritten non-oRPC mutation logic.
+
+## Key API Guide (`.key` vs `.queryKey` vs `.mutationKey`)
+
+- `.key(...)`:
+  - Use for partial matching operations (recommended for invalidation/refetch/cancel patterns).
+  - Example: `queryClient.invalidateQueries({ queryKey: consoleQuery.billing.key() })`
+- `.queryKey(...)`:
+  - Use for a specific query's full key (exact query identity / direct cache addressing).
+- `.mutationKey(...)`:
+  - Use for a specific mutation's full key.
+  - Typical use cases: mutation defaults registration, mutation-status filtering (`useIsMutating`, `queryClient.isMutating`), or explicit devtools grouping.
+
+## Anti-Patterns
+
+- Do not wrap `useQuery` with `options?: Partial<UseQueryOptions>`.
+- Do not split local `queryKey/queryFn` when oRPC `queryOptions` already exists and fits the use case.
+- Do not create thin `use-*` passthrough hooks for a single endpoint.
+- Reason: these patterns can degrade inference (`data` may become `unknown`, especially around `throwOnError`/`select`) and add unnecessary indirection.
+
+## Contract Rules
 
 - **Input structure**: Always use `{ params, query?, body? }` format
+- **No-input GET**: Omit `.input(...)`; do not use `.input(type<unknown>())`
 - **Path params**: Use `{paramName}` in path, match in `params` object
-- **Router nesting**: Group by API prefix (e.g., `/billing/*` → `billing: {}`)
+- **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
+- **Mutations**: Prefer `mutationOptions`; use explicit `mutationKey` mainly for defaults/filtering/devtools
 
 ## Type Export
 

.claude/skills/backend-code-review

@@ -0,0 +1 @@
+../../.agents/skills/backend-code-review

.devcontainer/post_create_command.sh

@@ -7,7 +7,7 @@ cd web && pnpm install
 pipx install uv
 
 echo "alias start-api=\"cd $WORKSPACE_ROOT/api && uv run python -m flask run --host 0.0.0.0 --port=5001 --debug\"" >> ~/.bashrc
-echo "alias start-worker=\"cd $WORKSPACE_ROOT/api && uv run python -m celery -A app.celery worker -P threads -c 1 --loglevel INFO -Q dataset,priority_dataset,priority_pipeline,pipeline,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,workflow,schedule_poller,schedule_executor,triggered_workflow_dispatcher,trigger_refresh_executor,retention\"" >> ~/.bashrc
+echo "alias start-worker=\"cd $WORKSPACE_ROOT/api && uv run python -m celery -A app.celery worker -P threads -c 1 --loglevel INFO -Q dataset,dataset_summary,priority_dataset,priority_pipeline,pipeline,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,workflow,schedule_poller,schedule_executor,triggered_workflow_dispatcher,trigger_refresh_executor,retention\"" >> ~/.bashrc
 echo "alias start-web=\"cd $WORKSPACE_ROOT/web && pnpm dev:inspect\"" >> ~/.bashrc
 echo "alias start-web-prod=\"cd $WORKSPACE_ROOT/web && pnpm build && pnpm start\"" >> ~/.bashrc
 echo "alias start-containers=\"cd $WORKSPACE_ROOT/docker && docker-compose -f docker-compose.middleware.yaml -p dify --env-file middleware.env up -d\"" >> ~/.bashrc

.github/CODEOWNERS

@@ -36,7 +36,7 @@
 /api/core/workflow/graph/ @laipz8200 @QuantumGhost
 /api/core/workflow/graph_events/ @laipz8200 @QuantumGhost
 /api/core/workflow/node_events/ @laipz8200 @QuantumGhost
-/api/core/model_runtime/ @laipz8200 @QuantumGhost
+/api/dify_graph/model_runtime/ @laipz8200 @QuantumGhost
 
 # Backend - Workflow - Nodes (Agent, Iteration, Loop, LLM)
 /api/core/workflow/nodes/agent/ @Nov1c444

.github/actions/setup-web/action.yml

@@ -0,0 +1,13 @@
+name: Setup Web Environment
+
+runs:
+  using: composite
+  steps:
+    - name: Setup Vite+
+      uses: voidzero-dev/setup-vp@b5d848f5a62488f3d3d920f8aa6ac318a60c5f07 # v1
+      with:
+        node-version-file: "./web/.nvmrc"
+        cache: true
+        run-install: |
+          - cwd: ./web
+            args: ['--frozen-lockfile']

.github/dependabot.yml

@@ -1,12 +1,212 @@
 version: 2
+
 updates:
-  - package-ecosystem: "npm"
-    directory: "/web"
+  - package-ecosystem: "pip"
+    directory: "/api"
+    open-pull-requests-limit: 10
     schedule:
       interval: "weekly"
-    open-pull-requests-limit: 2
+    groups:
+      flask:
+        patterns:
+          - "flask"
+          - "flask-*"
+          - "werkzeug"
+          - "gunicorn"
+      google:
+        patterns:
+          - "google-*"
+          - "googleapis-*"
+      opentelemetry:
+        patterns:
+          - "opentelemetry-*"
+      pydantic:
+        patterns:
+          - "pydantic"
+          - "pydantic-*"
+      llm:
+        patterns:
+          - "langfuse"
+          - "langsmith"
+          - "litellm"
+          - "mlflow*"
+          - "opik"
+          - "weave*"
+          - "arize*"
+          - "tiktoken"
+          - "transformers"
+      database:
+        patterns:
+          - "sqlalchemy"
+          - "psycopg2*"
+          - "psycogreen"
+          - "redis*"
+          - "alembic*"
+      storage:
+        patterns:
+          - "boto3*"
+          - "botocore*"
+          - "azure-*"
+          - "bce-*"
+          - "cos-python-*"
+          - "esdk-obs-*"
+          - "google-cloud-storage"
+          - "opendal"
+          - "oss2"
+          - "supabase*"
+          - "tos*"
+      vdb:
+        patterns:
+          - "alibabacloud*"
+          - "chromadb"
+          - "clickhouse-*"
+          - "clickzetta-*"
+          - "couchbase"
+          - "elasticsearch"
+          - "opensearch-py"
+          - "oracledb"
+          - "pgvect*"
+          - "pymilvus"
+          - "pymochow"
+          - "pyobvector"
+          - "qdrant-client"
+          - "intersystems-*"
+          - "tablestore"
+          - "tcvectordb"
+          - "tidb-vector"
+          - "upstash-*"
+          - "volcengine-*"
+          - "weaviate-*"
+          - "xinference-*"
+          - "mo-vector"
+          - "mysql-connector-*"
+      dev:
+        patterns:
+          - "coverage"
+          - "dotenv-linter"
+          - "faker"
+          - "lxml-stubs"
+          - "basedpyright"
+          - "ruff"
+          - "pytest*"
+          - "types-*"
+          - "boto3-stubs"
+          - "hypothesis"
+          - "pandas-stubs"
+          - "scipy-stubs"
+          - "import-linter"
+          - "celery-types"
+          - "mypy*"
+          - "pyrefly"
+      python-packages:
+        patterns:
+          - "*"
   - package-ecosystem: "uv"
     directory: "/api"
+    open-pull-requests-limit: 10
     schedule:
       interval: "weekly"
-    open-pull-requests-limit: 2
+    groups:
+      flask:
+        patterns:
+          - "flask"
+          - "flask-*"
+          - "werkzeug"
+          - "gunicorn"
+      google:
+        patterns:
+          - "google-*"
+          - "googleapis-*"
+      opentelemetry:
+        patterns:
+          - "opentelemetry-*"
+      pydantic:
+        patterns:
+          - "pydantic"
+          - "pydantic-*"
+      llm:
+        patterns:
+          - "langfuse"
+          - "langsmith"
+          - "litellm"
+          - "mlflow*"
+          - "opik"
+          - "weave*"
+          - "arize*"
+          - "tiktoken"
+          - "transformers"
+      database:
+        patterns:
+          - "sqlalchemy"
+          - "psycopg2*"
+          - "psycogreen"
+          - "redis*"
+          - "alembic*"
+      storage:
+        patterns:
+          - "boto3*"
+          - "botocore*"
+          - "azure-*"
+          - "bce-*"
+          - "cos-python-*"
+          - "esdk-obs-*"
+          - "google-cloud-storage"
+          - "opendal"
+          - "oss2"
+          - "supabase*"
+          - "tos*"
+      vdb:
+        patterns:
+          - "alibabacloud*"
+          - "chromadb"
+          - "clickhouse-*"
+          - "clickzetta-*"
+          - "couchbase"
+          - "elasticsearch"
+          - "opensearch-py"
+          - "oracledb"
+          - "pgvect*"
+          - "pymilvus"
+          - "pymochow"
+          - "pyobvector"
+          - "qdrant-client"
+          - "intersystems-*"
+          - "tablestore"
+          - "tcvectordb"
+          - "tidb-vector"
+          - "upstash-*"
+          - "volcengine-*"
+          - "weaviate-*"
+          - "xinference-*"
+          - "mo-vector"
+          - "mysql-connector-*"
+      dev:
+        patterns:
+          - "coverage"
+          - "dotenv-linter"
+          - "faker"
+          - "lxml-stubs"
+          - "basedpyright"
+          - "ruff"
+          - "pytest*"
+          - "types-*"
+          - "boto3-stubs"
+          - "hypothesis"
+          - "pandas-stubs"
+          - "scipy-stubs"
+          - "import-linter"
+          - "celery-types"
+          - "mypy*"
+          - "pyrefly"
+      python-packages:
+        patterns:
+          - "*"
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    open-pull-requests-limit: 5
+    schedule:
+      interval: "weekly"
+    groups:
+      github-actions-dependencies:
+        patterns:
+          - "*"

.github/workflows/anti-slop.yml

@@ -0,0 +1,19 @@
+name: Anti-Slop PR Check
+
+on:
+  pull_request_target:
+    types: [opened, edited, synchronize]
+
+permissions:
+  pull-requests: write
+  contents: read
+
+jobs:
+  anti-slop:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: peakoss/anti-slop@v0
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          close-pr: false
+          failure-add-pr-labels: "needs-revision"

.github/workflows/api-tests.yml

@@ -22,12 +22,12 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Setup UV and Python
-        uses: astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@6ee6290f1cbc4156c0bdd66691b2c144ef8df19a # v7.4.0
         with:
           enable-cache: true
           python-version: ${{ matrix.python-version }}
@@ -51,7 +51,7 @@ jobs:
         run: sh .github/workflows/expose_service_ports.sh
 
       - name: Set up Sandbox
-        uses: hoverkraft-tech/compose-action@v2
+        uses: hoverkraft-tech/compose-action@4894d2492015c1774ee5a13a95b1072093087ec3 # v2.5.0
         with:
           compose-file: |
             docker/docker-compose.middleware.yaml

.github/workflows/autofix.yml

@@ -12,22 +12,34 @@ jobs:
     if: github.repository == 'langgenius/dify'
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
       - name: Check Docker Compose inputs
         id: docker-compose-changes
-        uses: tj-actions/changed-files@v47
+        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
         with:
           files: |
             docker/generate_docker_compose
             docker/.env.example
             docker/docker-compose-template.yaml
             docker/docker-compose.yaml
-      - uses: actions/setup-python@v6
+      - name: Check web inputs
+        id: web-changes
+        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
+        with:
+          files: |
+            web/**
+      - name: Check api inputs
+        id: api-changes
+        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
+        with:
+          files: |
+            api/**
+      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
         with:
           python-version: "3.11"
 
-      - uses: astral-sh/setup-uv@v7
+      - uses: astral-sh/setup-uv@6ee6290f1cbc4156c0bdd66691b2c144ef8df19a # v7.4.0
 
       - name: Generate Docker Compose
         if: steps.docker-compose-changes.outputs.any_changed == 'true'
@@ -35,7 +47,8 @@ jobs:
           cd docker
           ./generate_docker_compose
 
-      - run: |
+      - if: steps.api-changes.outputs.any_changed == 'true'
+        run: |
           cd api
           uv sync --dev
           # fmt first to avoid line too long
@@ -46,11 +59,13 @@ jobs:
           uv run ruff format ..
 
       - name: count migration progress
+        if: steps.api-changes.outputs.any_changed == 'true'
         run: |
           cd api
           ./cnt_base.sh
 
       - name: ast-grep
+        if: steps.api-changes.outputs.any_changed == 'true'
         run: |
           # ast-grep exits 1 if no matches are found; allow idempotent runs.
           uvx --from ast-grep-cli ast-grep --pattern 'db.session.query($WHATEVER).filter($HERE)' --rewrite 'db.session.query($WHATEVER).where($HERE)' -l py --update-all || true
@@ -84,4 +99,14 @@ jobs:
         run: |
           uvx --python 3.13 mdformat . --exclude ".agents/skills/**"
 
-      - uses: autofix-ci/action@635ffb0c9798bd160680f18fd73371e355b85f27
+      - name: Setup web environment
+        if: steps.web-changes.outputs.any_changed == 'true'
+        uses: ./.github/actions/setup-web
+
+      - name: ESLint autofix
+        if: steps.web-changes.outputs.any_changed == 'true'
+        run: |
+          cd web
+          vp exec eslint --concurrency=2 --prune-suppressions --quiet || true
+
+      - uses: autofix-ci/action@7a166d7532b277f34e16238930461bf77f9d7ed8 # v1.3.3

.github/workflows/build-push.yml

@@ -8,6 +8,7 @@ on:
       - "build/**"
       - "release/e-*"
       - "hotfix/**"
+      - "feat/hitl-backend"
     tags:
       - "*"
 
@@ -52,26 +53,26 @@ jobs:
           echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
 
       - name: Login to Docker Hub
-        uses: docker/login-action@v3
+        uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v4.0.0
         with:
           username: ${{ env.DOCKERHUB_USER }}
           password: ${{ env.DOCKERHUB_TOKEN }}
 
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
+        uses: docker/setup-qemu-action@ce360397dd3f832beb865e1373c09c0e9f86d70a # v4.0.0
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4.0.0
 
       - name: Extract metadata for Docker
         id: meta
-        uses: docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # v6.0.0
         with:
           images: ${{ env[matrix.image_name_env] }}
 
       - name: Build Docker image
         id: build
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@d08e5c354a6adb9ed34480a06d141179aa583294 # v7.0.0
         with:
           context: "{{defaultContext}}:${{ matrix.context }}"
           platforms: ${{ matrix.platform }}
@@ -90,7 +91,7 @@ jobs:
           touch "/tmp/digests/${sanitized_digest}"
 
       - name: Upload digest
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
         with:
           name: digests-${{ matrix.context }}-${{ env.PLATFORM_PAIR }}
           path: /tmp/digests/*
@@ -112,21 +113,21 @@ jobs:
             context: "web"
     steps:
       - name: Download digests
-        uses: actions/download-artifact@v7
+        uses: actions/download-artifact@70fc10c6e5e1ce46ad2ea6f2b72d43f7d47b13c3 # v8.0.0
         with:
           path: /tmp/digests
           pattern: digests-${{ matrix.context }}-*
           merge-multiple: true
 
       - name: Login to Docker Hub
-        uses: docker/login-action@v3
+        uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v4.0.0
         with:
           username: ${{ env.DOCKERHUB_USER }}
           password: ${{ env.DOCKERHUB_TOKEN }}
 
       - name: Extract metadata for Docker
         id: meta
-        uses: docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # v6.0.0
         with:
           images: ${{ env[matrix.image_name_env] }}
           tags: |

.github/workflows/db-migration-test.yml

@@ -13,13 +13,13 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-depth: 0
           persist-credentials: false
 
       - name: Setup UV and Python
-        uses: astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@6ee6290f1cbc4156c0bdd66691b2c144ef8df19a # v7.4.0
         with:
           enable-cache: true
           python-version: "3.12"
@@ -40,7 +40,7 @@ jobs:
           cp middleware.env.example middleware.env
 
       - name: Set up Middlewares
-        uses: hoverkraft-tech/compose-action@v2.0.2
+        uses: hoverkraft-tech/compose-action@4894d2492015c1774ee5a13a95b1072093087ec3 # v2.5.0
         with:
           compose-file: |
             docker/docker-compose.middleware.yaml
@@ -63,13 +63,13 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-depth: 0
           persist-credentials: false
 
       - name: Setup UV and Python
-        uses: astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@6ee6290f1cbc4156c0bdd66691b2c144ef8df19a # v7.4.0
         with:
           enable-cache: true
           python-version: "3.12"
@@ -94,7 +94,7 @@ jobs:
           sed -i 's/DB_USERNAME=postgres/DB_USERNAME=mysql/' middleware.env
 
       - name: Set up Middlewares
-        uses: hoverkraft-tech/compose-action@v2.0.2
+        uses: hoverkraft-tech/compose-action@4894d2492015c1774ee5a13a95b1072093087ec3 # v2.5.0
         with:
           compose-file: |
             docker/docker-compose.middleware.yaml

.github/workflows/deploy-agent-dev.yml

@@ -19,7 +19,7 @@ jobs:
       github.event.workflow_run.head_branch == 'deploy/agent-dev'
     steps:
       - name: Deploy to server
-        uses: appleboy/ssh-action@v1
+        uses: appleboy/ssh-action@0ff4204d59e8e51228ff73bce53f80d53301dee2 # v1.2.5
         with:
           host: ${{ secrets.AGENT_DEV_SSH_HOST }}
           username: ${{ secrets.SSH_USER }}

.github/workflows/deploy-dev.yml

@@ -16,7 +16,7 @@ jobs:
       github.event.workflow_run.head_branch == 'deploy/dev'
     steps:
       - name: Deploy to server
-        uses: appleboy/ssh-action@v1
+        uses: appleboy/ssh-action@0ff4204d59e8e51228ff73bce53f80d53301dee2 # v1.2.5
         with:
           host: ${{ secrets.SSH_HOST }}
           username: ${{ secrets.SSH_USER }}

.github/workflows/deploy-hitl.yml

@@ -4,8 +4,7 @@ on:
   workflow_run:
     workflows: ["Build and Push API & Web"]
     branches:
-      - "feat/hitl-frontend"
-      - "feat/hitl-backend"
+      - "build/feat/hitl"
     types:
       - completed
 
@@ -14,13 +13,10 @@ jobs:
     runs-on: ubuntu-latest
     if: |
       github.event.workflow_run.conclusion == 'success' &&
-      (
-        github.event.workflow_run.head_branch == 'feat/hitl-frontend' ||
-        github.event.workflow_run.head_branch == 'feat/hitl-backend'
-      )
+      github.event.workflow_run.head_branch == 'build/feat/hitl'
     steps:
       - name: Deploy to server
-        uses: appleboy/ssh-action@v1
+        uses: appleboy/ssh-action@0ff4204d59e8e51228ff73bce53f80d53301dee2 # v1.2.5
         with:
           host: ${{ secrets.HITL_SSH_HOST }}
           username: ${{ secrets.SSH_USER }}

.github/workflows/docker-build.yml

@@ -32,13 +32,13 @@ jobs:
             context: "web"
     steps:
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
+        uses: docker/setup-qemu-action@ce360397dd3f832beb865e1373c09c0e9f86d70a # v4.0.0
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4.0.0
 
       - name: Build Docker Image
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@d08e5c354a6adb9ed34480a06d141179aa583294 # v7.0.0
         with:
           push: false
           context: "{{defaultContext}}:${{ matrix.context }}"

.github/workflows/labeler.yml

@@ -9,6 +9,6 @@ jobs:
       pull-requests: write
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/labeler@v6
+      - uses: actions/labeler@634933edcd8ababfe52f92936142cc22ac488b1b # v6.0.1
         with:
           sync-labels: true

.github/workflows/main-ci.yml

@@ -27,8 +27,8 @@ jobs:
       vdb-changed: ${{ steps.changes.outputs.vdb }}
       migration-changed: ${{ steps.changes.outputs.migration }}
     steps:
-      - uses: actions/checkout@v6
-      - uses: dorny/paths-filter@v3
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+      - uses: dorny/paths-filter@de90cc6fb38fc0963ad72b210f1f284cd68cea36 # v3.0.2
         id: changes
         with:
           filters: |
@@ -39,6 +39,7 @@ jobs:
             web:
               - 'web/**'
               - '.github/workflows/web-tests.yml'
+              - '.github/actions/setup-web/**'
             vdb:
               - 'api/core/rag/datasource/**'
               - 'docker/**'
@@ -61,6 +62,9 @@ jobs:
     needs: check-changes
     if: needs.check-changes.outputs.web-changed == 'true'
     uses: ./.github/workflows/web-tests.yml
+    with:
+      base_sha: ${{ github.event_name == 'pull_request' && github.event.pull_request.base.sha || github.event.before }}
+      head_sha: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
 
   style-check:
     name: Style Check

.github/workflows/pyrefly-diff-comment.yml

@@ -0,0 +1,88 @@
+name: Comment with Pyrefly Diff
+
+on:
+  workflow_run:
+    workflows:
+      - Pyrefly Diff Check
+    types:
+      - completed
+
+permissions: {}
+
+jobs:
+  comment:
+    name: Comment PR with pyrefly diff
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      contents: read
+      issues: write
+      pull-requests: write
+    if: ${{ github.event.workflow_run.conclusion == 'success' && github.event.workflow_run.pull_requests[0].head.repo.full_name != github.repository }}
+    steps:
+      - name: Download pyrefly diff artifact
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const fs = require('fs');
+            const artifacts = await github.rest.actions.listWorkflowRunArtifacts({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              run_id: ${{ github.event.workflow_run.id }},
+            });
+            const match = artifacts.data.artifacts.find((artifact) =>
+              artifact.name === 'pyrefly_diff'
+            );
+            if (!match) {
+              throw new Error('pyrefly_diff artifact not found');
+            }
+            const download = await github.rest.actions.downloadArtifact({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              artifact_id: match.id,
+              archive_format: 'zip',
+            });
+            fs.writeFileSync('pyrefly_diff.zip', Buffer.from(download.data));
+
+      - name: Unzip artifact
+        run: unzip -o pyrefly_diff.zip
+
+      - name: Post comment
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const fs = require('fs');
+            let diff = fs.readFileSync('pyrefly_diff.txt', { encoding: 'utf8' });
+            let prNumber = null;
+            try {
+              prNumber = parseInt(fs.readFileSync('pr_number.txt', { encoding: 'utf8' }), 10);
+            } catch (err) {
+              // Fallback to workflow_run payload if artifact is missing or incomplete.
+              const prs = context.payload.workflow_run.pull_requests || [];
+              if (prs.length > 0 && prs[0].number) {
+                prNumber = prs[0].number;
+              }
+            }
+            if (!prNumber) {
+              throw new Error('PR number not found in artifact or workflow_run payload');
+            }
+
+            const MAX_CHARS = 65000;
+            if (diff.length > MAX_CHARS) {
+              diff = diff.slice(0, MAX_CHARS);
+              diff = diff.slice(0, diff.lastIndexOf('\\n'));
+              diff += '\\n\\n... (truncated) ...';
+            }
+
+            const body = diff.trim()
+              ? '### Pyrefly Diff\n<details>\n<summary>base → PR</summary>\n\n```diff\n' + diff + '\n```\n</details>'
+              : '### Pyrefly Diff\nNo changes detected.';
+
+            await github.rest.issues.createComment({
+              issue_number: prNumber,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body,
+            });

.github/workflows/pyrefly-diff.yml

@@ -0,0 +1,100 @@
+name: Pyrefly Diff Check
+
+on:
+  pull_request:
+    paths:
+      - 'api/**/*.py'
+
+permissions:
+  contents: read
+
+jobs:
+  pyrefly-diff:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      issues: write
+      pull-requests: write
+    steps:
+      - name: Checkout PR branch
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          fetch-depth: 0
+
+      - name: Setup Python & UV
+        uses: astral-sh/setup-uv@6ee6290f1cbc4156c0bdd66691b2c144ef8df19a # v7.4.0
+        with:
+          enable-cache: true
+
+      - name: Install dependencies
+        run: uv sync --project api --dev
+
+      - name: Prepare diagnostics extractor
+        run: |
+          git show ${{ github.event.pull_request.head.sha }}:api/libs/pyrefly_diagnostics.py > /tmp/pyrefly_diagnostics.py
+
+      - name: Run pyrefly on PR branch
+        run: |
+          uv run --directory api --dev pyrefly check 2>&1 \
+            | uv run --directory api python /tmp/pyrefly_diagnostics.py > /tmp/pyrefly_pr.txt || true
+
+      - name: Checkout base branch
+        run: git checkout ${{ github.base_ref }}
+
+      - name: Run pyrefly on base branch
+        run: |
+          uv run --directory api --dev pyrefly check 2>&1 \
+            | uv run --directory api python /tmp/pyrefly_diagnostics.py > /tmp/pyrefly_base.txt || true
+
+      - name: Compute diff
+        run: |
+          diff -u /tmp/pyrefly_base.txt /tmp/pyrefly_pr.txt > pyrefly_diff.txt || true
+
+      - name: Save PR number
+        run: |
+          echo ${{ github.event.pull_request.number }} > pr_number.txt
+
+      - name: Upload pyrefly diff
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        with:
+          name: pyrefly_diff
+          path: |
+            pyrefly_diff.txt
+            pr_number.txt
+
+      - name: Comment PR with pyrefly diff
+        if: ${{ github.event.pull_request.head.repo.full_name == github.repository }}
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const fs = require('fs');
+            let diff = fs.readFileSync('pyrefly_diff.txt', { encoding: 'utf8' });
+            const prNumber = context.payload.pull_request.number;
+
+            const MAX_CHARS = 65000;
+            if (diff.length > MAX_CHARS) {
+              diff = diff.slice(0, MAX_CHARS);
+              diff = diff.slice(0, diff.lastIndexOf('\n'));
+              diff += '\n\n... (truncated) ...';
+            }
+
+            const body = diff.trim()
+              ? [
+                  '### Pyrefly Diff',
+                  '<details>',
+                  '<summary>base → PR</summary>',
+                  '',
+                  '```diff',
+                  diff,
+                  '```',
+                  '</details>',
+                ].join('\n')
+              : '### Pyrefly Diff\nNo changes detected.';
+
+            await github.rest.issues.createComment({
+              issue_number: prNumber,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body,
+            });

.github/workflows/semantic-pull-request.yml

@@ -16,6 +16,6 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Check title
-        uses: amannn/action-semantic-pull-request@v6.1.1
+        uses: amannn/action-semantic-pull-request@48f256284bd46cdaab1048c3721360e808335d50 # v6.1.1
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/stale.yml

@@ -18,7 +18,7 @@ jobs:
       pull-requests: write
 
     steps:
-      - uses: actions/stale@v10
+      - uses: actions/stale@b5d41d4e1d5dceea10e7104786b73624c18a190f # v10.2.0
         with:
           days-before-issue-stale: 15
           days-before-issue-close: 3

.github/workflows/style.yml

@@ -19,13 +19,13 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Check changed files
         id: changed-files
-        uses: tj-actions/changed-files@v47
+        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
         with:
           files: |
             api/**
@@ -33,7 +33,7 @@ jobs:
 
       - name: Setup UV and Python
         if: steps.changed-files.outputs.any_changed == 'true'
-        uses: astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@6ee6290f1cbc4156c0bdd66691b2c144ef8df19a # v7.4.0
         with:
           enable-cache: false
           python-version: "3.12"
@@ -67,42 +67,28 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Check changed files
         id: changed-files
-        uses: tj-actions/changed-files@v47
+        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
         with:
           files: |
             web/**
             .github/workflows/style.yml
+            .github/actions/setup-web/**
 
-      - name: Install pnpm
-        uses: pnpm/action-setup@v4
-        with:
-          package_json_file: web/package.json
-          run_install: false
-
-      - name: Setup NodeJS
-        uses: actions/setup-node@v6
+      - name: Setup web environment
         if: steps.changed-files.outputs.any_changed == 'true'
-        with:
-          node-version: 24
-          cache: pnpm
-          cache-dependency-path: ./web/pnpm-lock.yaml
-
-      - name: Web dependencies
-        if: steps.changed-files.outputs.any_changed == 'true'
-        working-directory: ./web
-        run: pnpm install --frozen-lockfile
+        uses: ./.github/actions/setup-web
 
       - name: Web style check
         if: steps.changed-files.outputs.any_changed == 'true'
         working-directory: ./web
         run: |
-          pnpm run lint:ci
+          vp run lint:ci
         # pnpm run lint:report
         # continue-on-error: true
 
@@ -116,17 +102,17 @@ jobs:
       - name: Web tsslint
         if: steps.changed-files.outputs.any_changed == 'true'
         working-directory: ./web
-        run: pnpm run lint:tss
+        run: vp run lint:tss
 
       - name: Web type check
         if: steps.changed-files.outputs.any_changed == 'true'
         working-directory: ./web
-        run: pnpm run type-check
+        run: vp run type-check
 
       - name: Web dead code check
         if: steps.changed-files.outputs.any_changed == 'true'
         working-directory: ./web
-        run: pnpm run knip
+        run: vp run knip
 
   superlinter:
     name: SuperLinter
@@ -134,14 +120,14 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-depth: 0
           persist-credentials: false
 
       - name: Check changed files
         id: changed-files
-        uses: tj-actions/changed-files@v47
+        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
         with:
           files: |
             **.sh
@@ -152,7 +138,7 @@ jobs:
             .editorconfig
 
       - name: Super-linter
-        uses: super-linter/super-linter/slim@v8
+        uses: super-linter/super-linter/slim@61abc07d755095a68f4987d1c2c3d1d64408f1f9 # v8.5.0
         if: steps.changed-files.outputs.any_changed == 'true'
         env:
           BASH_SEVERITY: warning

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

@@ -21,14 +21,14 @@ jobs:
         working-directory: sdks/nodejs-client
 
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Use Node.js
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
         with:
-          node-version: 24
+          node-version: 22
           cache: ''
           cache-dependency-path: 'pnpm-lock.yaml'
 

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

@@ -38,7 +38,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-depth: 0
           token: ${{ secrets.GITHUB_TOKEN }}
@@ -48,18 +48,8 @@ jobs:
           git config --global user.name "github-actions[bot]"
           git config --global user.email "github-actions[bot]@users.noreply.github.com"
 
-      - name: Install pnpm
-        uses: pnpm/action-setup@v4
-        with:
-          package_json_file: web/package.json
-          run_install: false
-
-      - name: Set up Node.js
-        uses: actions/setup-node@v6
-        with:
-          node-version: 24
-          cache: pnpm
-          cache-dependency-path: ./web/pnpm-lock.yaml
+      - name: Setup web environment
+        uses: ./.github/actions/setup-web
 
       - name: Detect changed files and generate diff
         id: detect_changes
@@ -130,7 +120,7 @@ jobs:
 
       - name: Run Claude Code for Translation Sync
         if: steps.detect_changes.outputs.CHANGED_FILES != ''
-        uses: anthropics/claude-code-action@v1
+        uses: anthropics/claude-code-action@26ec041249acb0a944c0a47b6c0c13f05dbc5b44 # v1.0.70
         with:
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
           github_token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/trigger-i18n-sync.yml

@@ -21,7 +21,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-depth: 0
 
@@ -59,7 +59,7 @@ jobs:
 
       - name: Trigger i18n sync workflow
         if: steps.detect.outputs.has_changes == 'true'
-        uses: peter-evans/repository-dispatch@v3
+        uses: peter-evans/repository-dispatch@28959ce8df70de7be546dd1250a005dd32156697 # v4.0.1
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
           event-type: i18n-sync

.github/workflows/vdb-tests.yml

@@ -19,19 +19,19 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Free Disk Space
-        uses: endersonmenezes/free-disk-space@v3
+        uses: endersonmenezes/free-disk-space@7901478139cff6e9d44df5972fd8ab8fcade4db1 # v3.2.2
         with:
           remove_dotnet: true
           remove_haskell: true
           remove_tool_cache: true
 
       - name: Setup UV and Python
-        uses: astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@6ee6290f1cbc4156c0bdd66691b2c144ef8df19a # v7.4.0
         with:
           enable-cache: true
           python-version: ${{ matrix.python-version }}
@@ -60,7 +60,7 @@ jobs:
 #            tiflash
 
       - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase, OceanBase)
-        uses: hoverkraft-tech/compose-action@v2.0.2
+        uses: hoverkraft-tech/compose-action@4894d2492015c1774ee5a13a95b1072093087ec3 # v2.5.0
         with:
           compose-file: |
             docker/docker-compose.yaml

.github/workflows/web-tests.yml

@@ -2,6 +2,16 @@ name: Web Tests
 
 on:
   workflow_call:
+    inputs:
+      base_sha:
+        required: false
+        type: string
+      head_sha:
+        required: false
+        type: string
+
+permissions:
+  contents: read
 
 concurrency:
   group: web-tests-${{ github.head_ref || github.run_id }}
@@ -9,8 +19,15 @@ concurrency:
 
 jobs:
   test:
-    name: Web Tests
+    name: Web Tests (${{ matrix.shardIndex }}/${{ matrix.shardTotal }})
     runs-on: ubuntu-latest
+    env:
+      VITEST_COVERAGE_SCOPE: app-components
+    strategy:
+      fail-fast: false
+      matrix:
+        shardIndex: [1, 2, 3, 4]
+        shardTotal: [4]
     defaults:
       run:
         shell: bash
@@ -18,28 +35,62 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
-      - name: Install pnpm
-        uses: pnpm/action-setup@v4
-        with:
-          package_json_file: web/package.json
-          run_install: false
-
-      - name: Setup Node.js
-        uses: actions/setup-node@v6
-        with:
-          node-version: 24
-          cache: pnpm
-          cache-dependency-path: ./web/pnpm-lock.yaml
-
-      - name: Install dependencies
-        run: pnpm install --frozen-lockfile
+      - name: Setup web environment
+        uses: ./.github/actions/setup-web
 
       - name: Run tests
-        run: pnpm test:ci
+        run: vp test run --reporter=blob --shard=${{ matrix.shardIndex }}/${{ matrix.shardTotal }} --coverage
+
+      - name: Upload blob report
+        if: ${{ !cancelled() }}
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        with:
+          name: blob-report-${{ matrix.shardIndex }}
+          path: web/.vitest-reports/*
+          include-hidden-files: true
+          retention-days: 1
+
+  merge-reports:
+    name: Merge Test Reports
+    if: ${{ !cancelled() }}
+    needs: [test]
+    runs-on: ubuntu-latest
+    env:
+      VITEST_COVERAGE_SCOPE: app-components
+    defaults:
+      run:
+        shell: bash
+        working-directory: ./web
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+
+      - name: Setup web environment
+        uses: ./.github/actions/setup-web
+
+      - name: Download blob reports
+        uses: actions/download-artifact@70fc10c6e5e1ce46ad2ea6f2b72d43f7d47b13c3 # v8.0.0
+        with:
+          path: web/.vitest-reports
+          pattern: blob-report-*
+          merge-multiple: true
+
+      - name: Merge reports
+        run: vp test --merge-reports --reporter=json --reporter=agent --coverage
+
+      - name: Check app/components diff coverage
+        env:
+          BASE_SHA: ${{ inputs.base_sha }}
+          HEAD_SHA: ${{ inputs.head_sha }}
+        run: node ./scripts/check-components-diff-coverage.mjs
 
       - name: Coverage Summary
         if: always()
@@ -360,7 +411,7 @@ jobs:
 
       - name: Upload Coverage Artifact
         if: steps.coverage-summary.outputs.has_coverage == 'true'
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
         with:
           name: web-coverage-report
           path: web/coverage
@@ -376,38 +427,24 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Check changed files
         id: changed-files
-        uses: tj-actions/changed-files@v47
+        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
         with:
           files: |
             web/**
             .github/workflows/web-tests.yml
+            .github/actions/setup-web/**
 
-      - name: Install pnpm
-        uses: pnpm/action-setup@v4
-        with:
-          package_json_file: web/package.json
-          run_install: false
-
-      - name: Setup NodeJS
-        uses: actions/setup-node@v6
+      - name: Setup web environment
         if: steps.changed-files.outputs.any_changed == 'true'
-        with:
-          node-version: 24
-          cache: pnpm
-          cache-dependency-path: ./web/pnpm-lock.yaml
-
-      - name: Web dependencies
-        if: steps.changed-files.outputs.any_changed == 'true'
-        working-directory: ./web
-        run: pnpm install --frozen-lockfile
+        uses: ./.github/actions/setup-web
 
       - name: Web build check
         if: steps.changed-files.outputs.any_changed == 'true'
         working-directory: ./web
-        run: pnpm run build
+        run: vp run build

.gitignore

@@ -222,6 +222,7 @@ mise.toml
 
 # AI Assistant
 .roo/
+/.claude/worktrees/
 api/.env.backup
 /clickzetta
 

.vscode/launch.json.template

@@ -37,7 +37,7 @@
                 "-c",
                 "1",
                 "-Q",
-                "dataset,priority_dataset,priority_pipeline,pipeline,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,workflow,schedule_poller,schedule_executor,triggered_workflow_dispatcher,trigger_refresh_executor,retention",
+                "dataset,dataset_summary,priority_dataset,priority_pipeline,pipeline,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,workflow,schedule_poller,schedule_executor,triggered_workflow_dispatcher,trigger_refresh_executor,retention,workflow_based_app_execution",
                 "--loglevel",
                 "INFO"
             ],

AGENTS.md

@@ -29,7 +29,7 @@ The codebase is split into:
 
 ## Language Style
 
-- **Python**: Keep type hints on functions and attributes, and implement relevant special methods (e.g., `__repr__`, `__str__`).
+- **Python**: Keep type hints on functions and attributes, and implement relevant special methods (e.g., `__repr__`, `__str__`). Prefer `TypedDict` over `dict` or `Mapping` for type safety and better code documentation.
 - **TypeScript**: Use the strict config, rely on ESLint (`pnpm lint:fix` preferred) plus `pnpm type-check:tsgo`, and avoid `any` types.
 
 ## General Practices

Makefile

@@ -68,10 +68,10 @@ lint:
 	@echo "✅ Linting complete"
 
 type-check:
-	@echo "📝 Running type checks (basedpyright + mypy + ty)..."
+	@echo "📝 Running type checks (basedpyright + pyrefly + mypy)..."
 	@./dev/basedpyright-check $(PATH_TO_CHECK)
+	@./dev/pyrefly-check-local
 	@uv --directory api run mypy --exclude-gitignore --exclude 'tests/' --exclude 'migrations/' --check-untyped-defs --disable-error-code=import-untyped .
-	@cd api && uv run ty check
 	@echo "✅ Type checks complete"
 
 test:
@@ -132,7 +132,7 @@ help:
 	@echo "  make format         - Format code with ruff"
 	@echo "  make check          - Check code with ruff"
 	@echo "  make lint           - Format, fix, and lint code (ruff, imports, dotenv)"
-	@echo "  make type-check     - Run type checks (basedpyright, mypy, ty)"
+	@echo "  make type-check     - Run type checks (basedpyright, pyrefly, mypy)"
 	@echo "  make test           - Run backend unit tests (or TARGET_TESTS=./api/tests/<target_tests>)"
 	@echo ""
 	@echo "Docker Build Targets:"

README.md

@@ -1,9 +1,5 @@
 ![cover-v5-optimized](./images/GitHub_README_if.png)
 
-<p align="center">
-  📌 <a href="https://dify.ai/blog/introducing-dify-workflow-file-upload-a-demo-on-ai-podcast">Introducing Dify Workflow File Upload: Recreate Google NotebookLM Podcast</a>
-</p>
-
 <p align="center">
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
   <a href="https://docs.dify.ai/getting-started/install-self-hosted">Self-hosting</a> ·
@@ -60,7 +56,7 @@
   <a href="./docs/bn-BD/README.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
 </p>
 
-Dify is an open-source platform for developing LLM applications. Its intuitive interface combines agentic AI workflows, RAG pipelines, agent capabilities, model management, observability features, and more—allowing you to quickly move from prototype to production.
+Dify is an open-source LLM app development platform. Its intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features (including [Opik](https://www.comet.com/docs/opik/integrations/dify), [Langfuse](https://docs.langfuse.com), and [Arize Phoenix](https://docs.arize.com/phoenix)) and more, letting you quickly go from prototype to production. Here's a list of the core features:
 
 ## Quick start
 
@@ -137,7 +133,7 @@ Star Dify on GitHub and be instantly notified of new releases.
 
 ### Custom configurations
 
-If you need to customize the configuration, please refer to the comments in our [.env.example](docker/.env.example) file and update the corresponding values in your `.env` file. Additionally, you might need to make adjustments to the `docker-compose.yaml` file itself, such as changing image versions, port mappings, or volume mounts, based on your specific deployment environment and requirements. After making any changes, please re-run `docker-compose up -d`. You can find the full list of available environment variables [here](https://docs.dify.ai/getting-started/install-self-hosted/environments).
+If you need to customize the configuration, please refer to the comments in our [.env.example](docker/.env.example) file and update the corresponding values in your `.env` file. Additionally, you might need to make adjustments to the `docker-compose.yaml` file itself, such as changing image versions, port mappings, or volume mounts, based on your specific deployment environment and requirements. After making any changes, please re-run `docker compose up -d`. You can find the full list of available environment variables [here](https://docs.dify.ai/getting-started/install-self-hosted/environments).
 
 #### Customizing Suggested Questions
 

api/.env.example

@@ -22,10 +22,10 @@ APP_WEB_URL=http://localhost:3000
 # Files URL
 FILES_URL=http://localhost:5001
 
-# INTERNAL_FILES_URL is used for plugin daemon communication within Docker network.
-# Set this to the internal Docker service URL for proper plugin file access.
-# Example: INTERNAL_FILES_URL=http://api:5001
-INTERNAL_FILES_URL=http://127.0.0.1:5001
+# INTERNAL_FILES_URL is used by services running in Docker to reach the API file endpoints.
+# For Docker Desktop (Mac/Windows), use http://host.docker.internal:5001 when the API runs on the host.
+# For Docker Compose on Linux, use http://api:5001 when the API runs inside the Docker network.
+INTERNAL_FILES_URL=http://host.docker.internal:5001
 
 # TRIGGER URL
 TRIGGER_URL=http://localhost:5001
@@ -42,6 +42,8 @@ REFRESH_TOKEN_EXPIRE_DAYS=30
 # redis configuration
 REDIS_HOST=localhost
 REDIS_PORT=6379
+# Optional: limit total connections in connection pool (unset for default)
+# REDIS_MAX_CONNECTIONS=200
 REDIS_USERNAME=
 REDIS_PASSWORD=difyai123456
 REDIS_USE_SSL=false
@@ -186,7 +188,6 @@ VECTOR_INDEX_NAME_PREFIX=Vector_index
 # Weaviate configuration
 WEAVIATE_ENDPOINT=http://localhost:8080
 WEAVIATE_API_KEY=WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih
-WEAVIATE_GRPC_ENABLED=false
 WEAVIATE_BATCH_SIZE=100
 WEAVIATE_TOKENIZATION=word
 
@@ -553,6 +554,8 @@ WORKFLOW_LOG_CLEANUP_ENABLED=false
 WORKFLOW_LOG_RETENTION_DAYS=30
 # Batch size for workflow log cleanup operations (default: 100)
 WORKFLOW_LOG_CLEANUP_BATCH_SIZE=100
+# Comma-separated list of workflow IDs to clean logs for
+WORKFLOW_LOG_CLEANUP_SPECIFIC_WORKFLOW_IDS=
 
 # App configuration
 APP_MAX_EXECUTION_TIME=1200
@@ -715,5 +718,31 @@ ANNOTATION_IMPORT_MAX_CONCURRENT=5
 # Sandbox expired records clean configuration
 SANDBOX_EXPIRED_RECORDS_CLEAN_GRACEFUL_PERIOD=21
 SANDBOX_EXPIRED_RECORDS_CLEAN_BATCH_SIZE=1000
+SANDBOX_EXPIRED_RECORDS_CLEAN_BATCH_MAX_INTERVAL=200
 SANDBOX_EXPIRED_RECORDS_RETENTION_DAYS=30
 SANDBOX_EXPIRED_RECORDS_CLEAN_TASK_LOCK_TTL=90000
+
+
+# Redis URL used for PubSub between API and
+# celery worker
+# defaults to url constructed from `REDIS_*`
+# configurations
+PUBSUB_REDIS_URL=
+# Pub/sub channel type for streaming events.
+# valid options are:
+#
+# - pubsub: for normal Pub/Sub
+# - sharded: for sharded Pub/Sub
+#
+# It's highly recommended to use sharded Pub/Sub AND redis cluster
+# for large deployments.
+PUBSUB_REDIS_CHANNEL_TYPE=pubsub
+# Whether to use Redis cluster mode while running
+# PubSub.
+#  It's highly recommended to enable this for large deployments.
+PUBSUB_REDIS_USE_CLUSTERS=false
+
+# Whether to Enable human input timeout check task
+ENABLE_HUMAN_INPUT_TIMEOUT_TASK=true
+# Human input timeout check interval in minutes
+HUMAN_INPUT_TIMEOUT_TASK_INTERVAL=1

api/.importlinter

@@ -1,6 +1,7 @@
 [importlinter]
 root_packages =
     core
+    dify_graph
     configs
     controllers
     extensions
@@ -21,49 +22,37 @@ layers =
     runtime
     entities
 containers =
-    core.workflow
+    dify_graph
 ignore_imports =
-    core.workflow.nodes.base.node -> core.workflow.graph_events
-    core.workflow.nodes.iteration.iteration_node -> core.workflow.graph_events
-    core.workflow.nodes.loop.loop_node -> core.workflow.graph_events
+    dify_graph.nodes.base.node -> dify_graph.graph_events
+    dify_graph.nodes.iteration.iteration_node -> dify_graph.graph_events
+    dify_graph.nodes.loop.loop_node -> dify_graph.graph_events
 
-    core.workflow.nodes.iteration.iteration_node -> core.app.workflow.node_factory
-    core.workflow.nodes.loop.loop_node -> core.app.workflow.node_factory
-
-    core.workflow.nodes.iteration.iteration_node -> core.workflow.graph_engine
-    core.workflow.nodes.iteration.iteration_node -> core.workflow.graph
-    core.workflow.nodes.iteration.iteration_node -> core.workflow.graph_engine.command_channels
-    core.workflow.nodes.loop.loop_node -> core.workflow.graph_engine
-    core.workflow.nodes.loop.loop_node -> core.workflow.graph
-    core.workflow.nodes.loop.loop_node -> core.workflow.graph_engine.command_channels
+    dify_graph.nodes.iteration.iteration_node -> dify_graph.graph_engine
+    dify_graph.nodes.loop.loop_node -> dify_graph.graph_engine
+    # TODO(QuantumGhost): fix the import violation later
+    dify_graph.entities.pause_reason -> dify_graph.nodes.human_input.entities
 
 [importlinter:contract:workflow-infrastructure-dependencies]
 name = Workflow Infrastructure Dependencies
 type = forbidden
 source_modules =
-    core.workflow
+    dify_graph
 forbidden_modules =
     extensions.ext_database
     extensions.ext_redis
 allow_indirect_imports = True
 ignore_imports =
-    core.workflow.nodes.agent.agent_node -> extensions.ext_database
-    core.workflow.nodes.datasource.datasource_node -> extensions.ext_database
-    core.workflow.nodes.knowledge_index.knowledge_index_node -> extensions.ext_database
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> extensions.ext_database
-    core.workflow.nodes.llm.file_saver -> extensions.ext_database
-    core.workflow.nodes.llm.llm_utils -> extensions.ext_database
-    core.workflow.nodes.llm.node -> extensions.ext_database
-    core.workflow.nodes.tool.tool_node -> extensions.ext_database
-    core.workflow.graph_engine.command_channels.redis_channel -> extensions.ext_redis
-    core.workflow.graph_engine.manager -> extensions.ext_redis
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> extensions.ext_redis
+    dify_graph.nodes.agent.agent_node -> extensions.ext_database
+    dify_graph.nodes.llm.node -> extensions.ext_database
+    dify_graph.model_runtime.model_providers.__base.ai_model -> extensions.ext_redis
+    dify_graph.model_runtime.model_providers.model_provider_factory -> extensions.ext_redis
 
 [importlinter:contract:workflow-external-imports]
 name = Workflow External Imports
 type = forbidden
 source_modules =
-    core.workflow
+    dify_graph
 forbidden_modules =
     configs
     controllers
@@ -89,7 +78,6 @@ forbidden_modules =
     core.logging
     core.mcp
     core.memory
-    core.model_manager
     core.moderation
     core.ops
     core.plugin
@@ -102,259 +90,59 @@ forbidden_modules =
     core.trigger
     core.variables
 ignore_imports =
-    core.workflow.nodes.agent.agent_node -> core.db.session_factory
-    core.workflow.nodes.agent.agent_node -> models.tools
-    core.workflow.nodes.loop.loop_node -> core.app.workflow.node_factory
-    core.workflow.graph_engine.command_channels.redis_channel -> extensions.ext_redis
-    core.workflow.workflow_entry -> core.app.workflow.layers.observability
-    core.workflow.nodes.agent.agent_node -> core.model_manager
-    core.workflow.nodes.agent.agent_node -> core.provider_manager
-    core.workflow.nodes.agent.agent_node -> core.tools.tool_manager
-    core.workflow.nodes.code.code_node -> core.helper.code_executor.code_executor
-    core.workflow.nodes.datasource.datasource_node -> models.model
-    core.workflow.nodes.datasource.datasource_node -> models.tools
-    core.workflow.nodes.datasource.datasource_node -> services.datasource_provider_service
-    core.workflow.nodes.document_extractor.node -> configs
-    core.workflow.nodes.document_extractor.node -> core.file.file_manager
-    core.workflow.nodes.document_extractor.node -> core.helper.ssrf_proxy
-    core.workflow.nodes.http_request.entities -> configs
-    core.workflow.nodes.http_request.executor -> configs
-    core.workflow.nodes.http_request.executor -> core.file.file_manager
-    core.workflow.nodes.http_request.node -> configs
-    core.workflow.nodes.http_request.node -> core.tools.tool_file_manager
-    core.workflow.nodes.iteration.iteration_node -> core.app.workflow.node_factory
-    core.workflow.nodes.knowledge_index.knowledge_index_node -> core.rag.index_processor.index_processor_factory
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.rag.datasource.retrieval_service
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.rag.retrieval.dataset_retrieval
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> models.dataset
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> services.feature_service
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.model_runtime.model_providers.__base.large_language_model
-    core.workflow.nodes.llm.llm_utils -> configs
-    core.workflow.nodes.llm.llm_utils -> core.app.entities.app_invoke_entities
-    core.workflow.nodes.llm.llm_utils -> core.file.models
-    core.workflow.nodes.llm.llm_utils -> core.model_manager
-    core.workflow.nodes.llm.llm_utils -> core.model_runtime.model_providers.__base.large_language_model
-    core.workflow.nodes.llm.llm_utils -> models.model
-    core.workflow.nodes.llm.llm_utils -> models.provider
-    core.workflow.nodes.llm.llm_utils -> services.credit_pool_service
-    core.workflow.nodes.llm.node -> core.tools.signature
-    core.workflow.nodes.tool.tool_node -> core.callback_handler.workflow_tool_callback_handler
-    core.workflow.nodes.tool.tool_node -> core.tools.tool_engine
-    core.workflow.nodes.tool.tool_node -> core.tools.tool_manager
-    core.workflow.workflow_entry -> configs
-    core.workflow.workflow_entry -> models.workflow
-    core.workflow.nodes.agent.agent_node -> core.agent.entities
-    core.workflow.nodes.agent.agent_node -> core.agent.plugin_entities
-    core.workflow.nodes.base.node -> core.app.entities.app_invoke_entities
-    core.workflow.nodes.knowledge_index.knowledge_index_node -> core.app.entities.app_invoke_entities
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.app.app_config.entities
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.app.entities.app_invoke_entities
-    core.workflow.nodes.llm.node -> core.app.entities.app_invoke_entities
-    core.workflow.nodes.parameter_extractor.parameter_extractor_node -> core.app.entities.app_invoke_entities
-    core.workflow.nodes.parameter_extractor.parameter_extractor_node -> core.prompt.advanced_prompt_transform
-    core.workflow.nodes.parameter_extractor.parameter_extractor_node -> core.prompt.simple_prompt_transform
-    core.workflow.nodes.parameter_extractor.parameter_extractor_node -> core.model_runtime.model_providers.__base.large_language_model
-    core.workflow.nodes.question_classifier.question_classifier_node -> core.app.entities.app_invoke_entities
-    core.workflow.nodes.question_classifier.question_classifier_node -> core.prompt.advanced_prompt_transform
-    core.workflow.nodes.question_classifier.question_classifier_node -> core.prompt.simple_prompt_transform
-    core.workflow.nodes.start.entities -> core.app.app_config.entities
-    core.workflow.nodes.start.start_node -> core.app.app_config.entities
-    core.workflow.workflow_entry -> core.app.apps.exc
-    core.workflow.workflow_entry -> core.app.entities.app_invoke_entities
-    core.workflow.workflow_entry -> core.app.workflow.node_factory
-    core.workflow.nodes.datasource.datasource_node -> core.datasource.datasource_manager
-    core.workflow.nodes.datasource.datasource_node -> core.datasource.utils.message_transformer
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.entities.agent_entities
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.entities.model_entities
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.model_manager
-    core.workflow.nodes.llm.llm_utils -> core.entities.provider_entities
-    core.workflow.nodes.parameter_extractor.parameter_extractor_node -> core.model_manager
-    core.workflow.nodes.question_classifier.question_classifier_node -> core.model_manager
-    core.workflow.node_events.node -> core.file
-    core.workflow.nodes.agent.agent_node -> core.file
-    core.workflow.nodes.datasource.datasource_node -> core.file
-    core.workflow.nodes.datasource.datasource_node -> core.file.enums
-    core.workflow.nodes.document_extractor.node -> core.file
-    core.workflow.nodes.http_request.executor -> core.file.enums
-    core.workflow.nodes.http_request.node -> core.file
-    core.workflow.nodes.http_request.node -> core.file.file_manager
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.file.models
-    core.workflow.nodes.list_operator.node -> core.file
-    core.workflow.nodes.llm.file_saver -> core.file
-    core.workflow.nodes.llm.llm_utils -> core.variables.segments
-    core.workflow.nodes.llm.node -> core.file
-    core.workflow.nodes.llm.node -> core.file.file_manager
-    core.workflow.nodes.llm.node -> core.file.models
-    core.workflow.nodes.loop.entities -> core.variables.types
-    core.workflow.nodes.parameter_extractor.parameter_extractor_node -> core.file
-    core.workflow.nodes.protocols -> core.file
-    core.workflow.nodes.question_classifier.question_classifier_node -> core.file.models
-    core.workflow.nodes.tool.tool_node -> core.file
-    core.workflow.nodes.tool.tool_node -> core.tools.utils.message_transformer
-    core.workflow.nodes.tool.tool_node -> models
-    core.workflow.nodes.trigger_webhook.node -> core.file
-    core.workflow.runtime.variable_pool -> core.file
-    core.workflow.runtime.variable_pool -> core.file.file_manager
-    core.workflow.system_variable -> core.file.models
-    core.workflow.utils.condition.processor -> core.file
-    core.workflow.utils.condition.processor -> core.file.file_manager
-    core.workflow.workflow_entry -> core.file.models
-    core.workflow.workflow_type_encoder -> core.file.models
-    core.workflow.nodes.agent.agent_node -> models.model
-    core.workflow.nodes.code.code_node -> core.helper.code_executor.code_node_provider
-    core.workflow.nodes.code.code_node -> core.helper.code_executor.javascript.javascript_code_provider
-    core.workflow.nodes.code.code_node -> core.helper.code_executor.python3.python3_code_provider
-    core.workflow.nodes.code.entities -> core.helper.code_executor.code_executor
-    core.workflow.nodes.datasource.datasource_node -> core.variables.variables
-    core.workflow.nodes.http_request.executor -> core.helper.ssrf_proxy
-    core.workflow.nodes.http_request.node -> core.helper.ssrf_proxy
-    core.workflow.nodes.llm.file_saver -> core.helper.ssrf_proxy
-    core.workflow.nodes.llm.node -> core.helper.code_executor
-    core.workflow.nodes.template_transform.template_renderer -> core.helper.code_executor.code_executor
-    core.workflow.nodes.llm.node -> core.llm_generator.output_parser.errors
-    core.workflow.nodes.llm.node -> core.llm_generator.output_parser.structured_output
-    core.workflow.nodes.llm.node -> core.model_manager
-    core.workflow.nodes.agent.entities -> core.prompt.entities.advanced_prompt_entities
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.prompt.simple_prompt_transform
-    core.workflow.nodes.llm.entities -> core.prompt.entities.advanced_prompt_entities
-    core.workflow.nodes.llm.llm_utils -> core.prompt.entities.advanced_prompt_entities
-    core.workflow.nodes.llm.node -> core.prompt.entities.advanced_prompt_entities
-    core.workflow.nodes.llm.node -> core.prompt.utils.prompt_message_util
-    core.workflow.nodes.parameter_extractor.entities -> core.prompt.entities.advanced_prompt_entities
-    core.workflow.nodes.parameter_extractor.parameter_extractor_node -> core.prompt.entities.advanced_prompt_entities
-    core.workflow.nodes.parameter_extractor.parameter_extractor_node -> core.prompt.utils.prompt_message_util
-    core.workflow.nodes.question_classifier.entities -> core.prompt.entities.advanced_prompt_entities
-    core.workflow.nodes.question_classifier.question_classifier_node -> core.prompt.utils.prompt_message_util
-    core.workflow.nodes.knowledge_index.entities -> core.rag.retrieval.retrieval_methods
-    core.workflow.nodes.knowledge_index.knowledge_index_node -> core.rag.retrieval.retrieval_methods
-    core.workflow.nodes.knowledge_index.knowledge_index_node -> models.dataset
-    core.workflow.nodes.knowledge_index.knowledge_index_node -> services.summary_index_service
-    core.workflow.nodes.knowledge_index.knowledge_index_node -> tasks.generate_summary_index_task
-    core.workflow.nodes.knowledge_index.knowledge_index_node -> core.rag.index_processor.processor.paragraph_index_processor
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.rag.retrieval.retrieval_methods
-    core.workflow.nodes.llm.node -> models.dataset
-    core.workflow.nodes.agent.agent_node -> core.tools.utils.message_transformer
-    core.workflow.nodes.llm.file_saver -> core.tools.signature
-    core.workflow.nodes.llm.file_saver -> core.tools.tool_file_manager
-    core.workflow.nodes.tool.tool_node -> core.tools.errors
-    core.workflow.conversation_variable_updater -> core.variables
-    core.workflow.graph_engine.entities.commands -> core.variables.variables
-    core.workflow.nodes.agent.agent_node -> core.variables.segments
-    core.workflow.nodes.answer.answer_node -> core.variables
-    core.workflow.nodes.code.code_node -> core.variables.segments
-    core.workflow.nodes.code.code_node -> core.variables.types
-    core.workflow.nodes.code.entities -> core.variables.types
-    core.workflow.nodes.datasource.datasource_node -> core.variables.segments
-    core.workflow.nodes.document_extractor.node -> core.variables
-    core.workflow.nodes.document_extractor.node -> core.variables.segments
-    core.workflow.nodes.http_request.executor -> core.variables.segments
-    core.workflow.nodes.http_request.node -> core.variables.segments
-    core.workflow.nodes.iteration.iteration_node -> core.variables
-    core.workflow.nodes.iteration.iteration_node -> core.variables.segments
-    core.workflow.nodes.iteration.iteration_node -> core.variables.variables
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.variables
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.variables.segments
-    core.workflow.nodes.list_operator.node -> core.variables
-    core.workflow.nodes.list_operator.node -> core.variables.segments
-    core.workflow.nodes.llm.node -> core.variables
-    core.workflow.nodes.loop.loop_node -> core.variables
-    core.workflow.nodes.parameter_extractor.entities -> core.variables.types
-    core.workflow.nodes.parameter_extractor.exc -> core.variables.types
-    core.workflow.nodes.parameter_extractor.parameter_extractor_node -> core.variables.types
-    core.workflow.nodes.tool.tool_node -> core.variables.segments
-    core.workflow.nodes.tool.tool_node -> core.variables.variables
-    core.workflow.nodes.trigger_webhook.node -> core.variables.types
-    core.workflow.nodes.trigger_webhook.node -> core.variables.variables
-    core.workflow.nodes.variable_aggregator.entities -> core.variables.types
-    core.workflow.nodes.variable_aggregator.variable_aggregator_node -> core.variables.segments
-    core.workflow.nodes.variable_assigner.common.helpers -> core.variables
-    core.workflow.nodes.variable_assigner.common.helpers -> core.variables.consts
-    core.workflow.nodes.variable_assigner.common.helpers -> core.variables.types
-    core.workflow.nodes.variable_assigner.v1.node -> core.variables
-    core.workflow.nodes.variable_assigner.v2.helpers -> core.variables
-    core.workflow.nodes.variable_assigner.v2.node -> core.variables
-    core.workflow.nodes.variable_assigner.v2.node -> core.variables.consts
-    core.workflow.runtime.graph_runtime_state_protocol -> core.variables.segments
-    core.workflow.runtime.read_only_wrappers -> core.variables.segments
-    core.workflow.runtime.variable_pool -> core.variables
-    core.workflow.runtime.variable_pool -> core.variables.consts
-    core.workflow.runtime.variable_pool -> core.variables.segments
-    core.workflow.runtime.variable_pool -> core.variables.variables
-    core.workflow.utils.condition.processor -> core.variables
-    core.workflow.utils.condition.processor -> core.variables.segments
-    core.workflow.variable_loader -> core.variables
-    core.workflow.variable_loader -> core.variables.consts
-    core.workflow.workflow_type_encoder -> core.variables
-    core.workflow.graph_engine.manager -> extensions.ext_redis
-    core.workflow.nodes.agent.agent_node -> extensions.ext_database
-    core.workflow.nodes.datasource.datasource_node -> extensions.ext_database
-    core.workflow.nodes.knowledge_index.knowledge_index_node -> extensions.ext_database
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> extensions.ext_database
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> extensions.ext_redis
-    core.workflow.nodes.llm.file_saver -> extensions.ext_database
-    core.workflow.nodes.llm.llm_utils -> extensions.ext_database
-    core.workflow.nodes.llm.node -> extensions.ext_database
-    core.workflow.nodes.tool.tool_node -> extensions.ext_database
-    core.workflow.workflow_entry -> extensions.otel.runtime
-    core.workflow.nodes.agent.agent_node -> models
-    core.workflow.nodes.base.node -> models.enums
-    core.workflow.nodes.llm.llm_utils -> models.provider_ids
-    core.workflow.nodes.llm.node -> models.model
-    core.workflow.workflow_entry -> models.enums
-    core.workflow.nodes.agent.agent_node -> services
-    core.workflow.nodes.tool.tool_node -> services
-
-[importlinter:contract:model-runtime-no-internal-imports]
-name = Model Runtime Internal Imports
-type = forbidden
-source_modules =
-    core.model_runtime
-forbidden_modules =
-    configs
-    controllers
-    extensions
-    models
-    services
-    tasks
-    core.agent
-    core.app
-    core.base
-    core.callback_handler
-    core.datasource
-    core.db
-    core.entities
-    core.errors
-    core.extension
-    core.external_data_tool
-    core.file
-    core.helper
-    core.hosting_configuration
-    core.indexing_runner
-    core.llm_generator
-    core.logging
-    core.mcp
-    core.memory
-    core.model_manager
-    core.moderation
-    core.ops
-    core.plugin
-    core.prompt
-    core.provider_manager
-    core.rag
-    core.repositories
-    core.schemas
-    core.tools
-    core.trigger
-    core.variables
-    core.workflow
-ignore_imports =
-    core.model_runtime.model_providers.__base.ai_model -> configs
-    core.model_runtime.model_providers.__base.ai_model -> extensions.ext_redis
-    core.model_runtime.model_providers.__base.large_language_model -> configs
-    core.model_runtime.model_providers.__base.text_embedding_model -> core.entities.embedding_type
-    core.model_runtime.model_providers.model_provider_factory -> configs
-    core.model_runtime.model_providers.model_provider_factory -> extensions.ext_redis
-    core.model_runtime.model_providers.model_provider_factory -> models.provider_ids
+    dify_graph.nodes.agent.agent_node -> core.model_manager
+    dify_graph.nodes.agent.agent_node -> core.provider_manager
+    dify_graph.nodes.agent.agent_node -> core.tools.tool_manager
+    dify_graph.nodes.llm.llm_utils -> core.model_manager
+    dify_graph.nodes.llm.protocols -> core.model_manager
+    dify_graph.nodes.llm.llm_utils -> dify_graph.model_runtime.model_providers.__base.large_language_model
+    dify_graph.nodes.llm.node -> core.tools.signature
+    dify_graph.nodes.tool.tool_node -> core.callback_handler.workflow_tool_callback_handler
+    dify_graph.nodes.tool.tool_node -> core.tools.tool_engine
+    dify_graph.nodes.tool.tool_node -> core.tools.tool_manager
+    dify_graph.nodes.agent.agent_node -> core.agent.entities
+    dify_graph.nodes.agent.agent_node -> core.agent.plugin_entities
+    dify_graph.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.app.app_config.entities
+    dify_graph.nodes.parameter_extractor.parameter_extractor_node -> core.prompt.advanced_prompt_transform
+    dify_graph.nodes.parameter_extractor.parameter_extractor_node -> core.prompt.simple_prompt_transform
+    dify_graph.nodes.parameter_extractor.parameter_extractor_node -> dify_graph.model_runtime.model_providers.__base.large_language_model
+    dify_graph.nodes.question_classifier.question_classifier_node -> core.prompt.simple_prompt_transform
+    dify_graph.nodes.parameter_extractor.parameter_extractor_node -> core.model_manager
+    dify_graph.nodes.question_classifier.question_classifier_node -> core.model_manager
+    dify_graph.nodes.tool.tool_node -> core.tools.utils.message_transformer
+    dify_graph.nodes.agent.agent_node -> models.model
+    dify_graph.nodes.llm.node -> core.helper.code_executor
+    dify_graph.nodes.llm.node -> core.llm_generator.output_parser.errors
+    dify_graph.nodes.llm.node -> core.llm_generator.output_parser.structured_output
+    dify_graph.nodes.llm.node -> core.model_manager
+    dify_graph.nodes.agent.entities -> core.prompt.entities.advanced_prompt_entities
+    dify_graph.nodes.llm.entities -> core.prompt.entities.advanced_prompt_entities
+    dify_graph.nodes.llm.node -> core.prompt.entities.advanced_prompt_entities
+    dify_graph.nodes.llm.node -> core.prompt.utils.prompt_message_util
+    dify_graph.nodes.parameter_extractor.entities -> core.prompt.entities.advanced_prompt_entities
+    dify_graph.nodes.parameter_extractor.parameter_extractor_node -> core.prompt.entities.advanced_prompt_entities
+    dify_graph.nodes.parameter_extractor.parameter_extractor_node -> core.prompt.utils.prompt_message_util
+    dify_graph.nodes.question_classifier.entities -> core.prompt.entities.advanced_prompt_entities
+    dify_graph.nodes.question_classifier.question_classifier_node -> core.prompt.utils.prompt_message_util
+    dify_graph.nodes.knowledge_index.entities -> core.rag.retrieval.retrieval_methods
+    dify_graph.nodes.llm.node -> models.dataset
+    dify_graph.nodes.agent.agent_node -> core.tools.utils.message_transformer
+    dify_graph.nodes.llm.file_saver -> core.tools.signature
+    dify_graph.nodes.llm.file_saver -> core.tools.tool_file_manager
+    dify_graph.nodes.tool.tool_node -> core.tools.errors
+    dify_graph.nodes.agent.agent_node -> extensions.ext_database
+    dify_graph.nodes.llm.node -> extensions.ext_database
+    dify_graph.nodes.agent.agent_node -> models
+    dify_graph.nodes.llm.node -> models.model
+    dify_graph.nodes.agent.agent_node -> services
+    dify_graph.nodes.tool.tool_node -> services
+    dify_graph.model_runtime.model_providers.__base.ai_model -> configs
+    dify_graph.model_runtime.model_providers.__base.ai_model -> extensions.ext_redis
+    dify_graph.model_runtime.model_providers.__base.large_language_model -> configs
+    dify_graph.model_runtime.model_providers.__base.text_embedding_model -> core.entities.embedding_type
+    dify_graph.model_runtime.model_providers.model_provider_factory -> configs
+    dify_graph.model_runtime.model_providers.model_provider_factory -> extensions.ext_redis
+    dify_graph.model_runtime.model_providers.model_provider_factory -> models.provider_ids
 
 [importlinter:contract:rsc]
 name = RSC
@@ -363,7 +151,7 @@ layers =
     graph_engine
     response_coordinator
 containers =
-    core.workflow.graph_engine
+    dify_graph.graph_engine
 
 [importlinter:contract:worker]
 name = Worker
@@ -372,7 +160,7 @@ layers =
     graph_engine
     worker
 containers =
-    core.workflow.graph_engine
+    dify_graph.graph_engine
 
 [importlinter:contract:graph-engine-architecture]
 name = Graph Engine Architecture
@@ -388,28 +176,28 @@ layers =
     worker_management
     domain
 containers =
-    core.workflow.graph_engine
+    dify_graph.graph_engine
 
 [importlinter:contract:domain-isolation]
 name = Domain Model Isolation
 type = forbidden
 source_modules =
-    core.workflow.graph_engine.domain
+    dify_graph.graph_engine.domain
 forbidden_modules =
-    core.workflow.graph_engine.worker_management
-    core.workflow.graph_engine.command_channels
-    core.workflow.graph_engine.layers
-    core.workflow.graph_engine.protocols
+    dify_graph.graph_engine.worker_management
+    dify_graph.graph_engine.command_channels
+    dify_graph.graph_engine.layers
+    dify_graph.graph_engine.protocols
 
 [importlinter:contract:worker-management]
 name = Worker Management
 type = forbidden
 source_modules =
-    core.workflow.graph_engine.worker_management
+    dify_graph.graph_engine.worker_management
 forbidden_modules =
-    core.workflow.graph_engine.orchestration
-    core.workflow.graph_engine.command_processing
-    core.workflow.graph_engine.event_management
+    dify_graph.graph_engine.orchestration
+    dify_graph.graph_engine.command_processing
+    dify_graph.graph_engine.event_management
 
 
 [importlinter:contract:graph-traversal-components]
@@ -419,11 +207,11 @@ layers =
     edge_processor
     skip_propagator
 containers =
-    core.workflow.graph_engine.graph_traversal
+    dify_graph.graph_engine.graph_traversal
 
 [importlinter:contract:command-channels]
 name = Command Channels Independence
 type = independence
 modules =
-    core.workflow.graph_engine.command_channels.in_memory_channel
-    core.workflow.graph_engine.command_channels.redis_channel
+    dify_graph.graph_engine.command_channels.in_memory_channel
+    dify_graph.graph_engine.command_channels.redis_channel

api/.ruff.toml

@@ -100,7 +100,7 @@ ignore = [
 "configs/*" = [
     "N802", # invalid-function-name
 ]
-"core/model_runtime/callbacks/base_callback.py" = ["T201"]
+"dify_graph/model_runtime/callbacks/base_callback.py" = ["T201"]
 "core/workflow/callbacks/workflow_logging_callback.py" = ["T201"]
 "libs/gmpy2_pkcs10aep_cipher.py" = [
     "N803", # invalid-argument-name

api/.vscode/launch.json.example

@@ -54,7 +54,7 @@
                 "--loglevel",
                 "DEBUG",
                 "-Q",
-                "dataset,priority_pipeline,pipeline,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,workflow,schedule_poller,schedule_executor,triggered_workflow_dispatcher,trigger_refresh_executor"
+                "dataset,priority_pipeline,pipeline,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,workflow,workflow_based_app_execution,schedule_poller,schedule_executor,triggered_workflow_dispatcher,trigger_refresh_executor"
             ]
         }
     ]

api/AGENTS.md

@@ -62,6 +62,22 @@ This is the default standard for backend code in this repo. Follow it for new co
 
 - Code should usually include type annotations that match the repo’s current Python version (avoid untyped public APIs and “mystery” values).
 - Prefer modern typing forms (e.g. `list[str]`, `dict[str, int]`) and avoid `Any` unless there’s a strong reason.
+- For dictionary-like data with known keys and value types, prefer `TypedDict` over `dict[...]` or `Mapping[...]`.
+- For optional keys in typed payloads, use `NotRequired[...]` (or `total=False` when most fields are optional).
+- Keep `dict[...]` / `Mapping[...]` for truly dynamic key spaces where the key set is unknown.
+
+```python
+from datetime import datetime
+from typing import NotRequired, TypedDict
+
+
+class UserProfile(TypedDict):
+    user_id: str
+    email: str
+    created_at: datetime
+    nickname: NotRequired[str]
+```
+
 - For classes, declare member variables at the top of the class body (before `__init__`) so the class shape is obvious at a glance:
 
 ```python

api/README.md

@@ -42,7 +42,7 @@ The scripts resolve paths relative to their location, so you can run them from a
 
 1. Set up your application by visiting `http://localhost:3000`.
 
-1. Optional: start the worker service (async tasks, runs from `api`).
+1. Start the worker service (async and scheduler tasks, runs from `api`).
 
    ```bash
    ./dev/start-worker
@@ -54,86 +54,6 @@ The scripts resolve paths relative to their location, so you can run them from a
    ./dev/start-beat
    ```
 
-### Manual commands
-
-<details>
-<summary>Show manual setup and run steps</summary>
-
-These commands assume you start from the repository root.
-
-1. Start the docker-compose stack.
-
-   The backend requires middleware, including PostgreSQL, Redis, and Weaviate, which can be started together using `docker-compose`.
-
-   ```bash
-   cp docker/middleware.env.example docker/middleware.env
-   # Use mysql or another vector database profile if you are not using postgres/weaviate.
-   docker compose -f docker/docker-compose.middleware.yaml --profile postgresql --profile weaviate -p dify up -d
-   ```
-
-1. Copy env files.
-
-   ```bash
-   cp api/.env.example api/.env
-   cp web/.env.example web/.env.local
-   ```
-
-1. Install UV if needed.
-
-   ```bash
-   pip install uv
-   # Or on macOS
-   brew install uv
-   ```
-
-1. Install API dependencies.
-
-   ```bash
-   cd api
-   uv sync --group dev
-   ```
-
-1. Install web dependencies.
-
-   ```bash
-   cd web
-   pnpm install
-   cd ..
-   ```
-
-1. Start backend (runs migrations first, in a new terminal).
-
-   ```bash
-   cd api
-   uv run flask db upgrade
-   uv run flask run --host 0.0.0.0 --port=5001 --debug
-   ```
-
-1. Start Dify [web](../web) service (in a new terminal).
-
-   ```bash
-   cd web
-   pnpm dev:inspect
-   ```
-
-1. Set up your application by visiting `http://localhost:3000`.
-
-1. Optional: start the worker service (async tasks, in a new terminal).
-
-   ```bash
-   cd api
-   uv run celery -A app.celery worker -P threads -c 2 --loglevel INFO -Q dataset,priority_dataset,priority_pipeline,pipeline,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,workflow,schedule_poller,schedule_executor,triggered_workflow_dispatcher,trigger_refresh_executor,retention
-   ```
-
-1. Optional: start Celery Beat (scheduled tasks, in a new terminal).
-
-   ```bash
-   cd api
-   uv run celery -A app.celery beat
-   ```
-
-</details>
-
 ### Environment notes
 
 > [!IMPORTANT]

api/commands/__init__.py

@@ -0,0 +1,71 @@
+"""
+CLI command modules extracted from `commands.py`.
+"""
+
+from .account import create_tenant, reset_email, reset_password
+from .plugin import (
+    extract_plugins,
+    extract_unique_plugins,
+    install_plugins,
+    install_rag_pipeline_plugins,
+    migrate_data_for_plugin,
+    setup_datasource_oauth_client,
+    setup_system_tool_oauth_client,
+    setup_system_trigger_oauth_client,
+    transform_datasource_credentials,
+)
+from .retention import (
+    archive_workflow_runs,
+    clean_expired_messages,
+    clean_workflow_runs,
+    cleanup_orphaned_draft_variables,
+    clear_free_plan_tenant_expired_logs,
+    delete_archived_workflow_runs,
+    export_app_messages,
+    restore_workflow_runs,
+)
+from .storage import clear_orphaned_file_records, file_usage, migrate_oss, remove_orphaned_files_on_storage
+from .system import convert_to_agent_apps, fix_app_site_missing, reset_encrypt_key_pair, upgrade_db
+from .vector import (
+    add_qdrant_index,
+    migrate_annotation_vector_database,
+    migrate_knowledge_vector_database,
+    old_metadata_migration,
+    vdb_migrate,
+)
+
+__all__ = [
+    "add_qdrant_index",
+    "archive_workflow_runs",
+    "clean_expired_messages",
+    "clean_workflow_runs",
+    "cleanup_orphaned_draft_variables",
+    "clear_free_plan_tenant_expired_logs",
+    "clear_orphaned_file_records",
+    "convert_to_agent_apps",
+    "create_tenant",
+    "delete_archived_workflow_runs",
+    "export_app_messages",
+    "extract_plugins",
+    "extract_unique_plugins",
+    "file_usage",
+    "fix_app_site_missing",
+    "install_plugins",
+    "install_rag_pipeline_plugins",
+    "migrate_annotation_vector_database",
+    "migrate_data_for_plugin",
+    "migrate_knowledge_vector_database",
+    "migrate_oss",
+    "old_metadata_migration",
+    "remove_orphaned_files_on_storage",
+    "reset_email",
+    "reset_encrypt_key_pair",
+    "reset_password",
+    "restore_workflow_runs",
+    "setup_datasource_oauth_client",
+    "setup_system_tool_oauth_client",
+    "setup_system_trigger_oauth_client",
+    "transform_datasource_credentials",
+    "upgrade_db",
+    "vdb_migrate",
+]

api/commands/account.py

@@ -0,0 +1,130 @@
+import base64
+import secrets
+
+import click
+from sqlalchemy.orm import sessionmaker
+
+from constants.languages import languages
+from extensions.ext_database import db
+from libs.helper import email as email_validate
+from libs.password import hash_password, password_pattern, valid_password
+from services.account_service import AccountService, RegisterService, TenantService
+
+
+@click.command("reset-password", help="Reset the account password.")
+@click.option("--email", prompt=True, help="Account email to reset password for")
+@click.option("--new-password", prompt=True, help="New password")
+@click.option("--password-confirm", prompt=True, help="Confirm new password")
+def reset_password(email, new_password, password_confirm):
+    """
+    Reset password of owner account
+    Only available in SELF_HOSTED mode
+    """
+    if str(new_password).strip() != str(password_confirm).strip():
+        click.echo(click.style("Passwords do not match.", fg="red"))
+        return
+    normalized_email = email.strip().lower()
+
+    with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
+        account = AccountService.get_account_by_email_with_case_fallback(email.strip(), session=session)
+
+        if not account:
+            click.echo(click.style(f"Account not found for email: {email}", fg="red"))
+            return
+
+        try:
+            valid_password(new_password)
+        except:
+            click.echo(click.style(f"Invalid password. Must match {password_pattern}", fg="red"))
+            return
+
+        # generate password salt
+        salt = secrets.token_bytes(16)
+        base64_salt = base64.b64encode(salt).decode()
+
+        # encrypt password with salt
+        password_hashed = hash_password(new_password, salt)
+        base64_password_hashed = base64.b64encode(password_hashed).decode()
+        account.password = base64_password_hashed
+        account.password_salt = base64_salt
+        AccountService.reset_login_error_rate_limit(normalized_email)
+        click.echo(click.style("Password reset successfully.", fg="green"))
+
+
+@click.command("reset-email", help="Reset the account email.")
+@click.option("--email", prompt=True, help="Current account email")
+@click.option("--new-email", prompt=True, help="New email")
+@click.option("--email-confirm", prompt=True, help="Confirm new email")
+def reset_email(email, new_email, email_confirm):
+    """
+    Replace account email
+    :return:
+    """
+    if str(new_email).strip() != str(email_confirm).strip():
+        click.echo(click.style("New emails do not match.", fg="red"))
+        return
+    normalized_new_email = new_email.strip().lower()
+
+    with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
+        account = AccountService.get_account_by_email_with_case_fallback(email.strip(), session=session)
+
+        if not account:
+            click.echo(click.style(f"Account not found for email: {email}", fg="red"))
+            return
+
+        try:
+            email_validate(normalized_new_email)
+        except:
+            click.echo(click.style(f"Invalid email: {new_email}", fg="red"))
+            return
+
+        account.email = normalized_new_email
+        click.echo(click.style("Email updated successfully.", fg="green"))
+
+
+@click.command("create-tenant", help="Create account and tenant.")
+@click.option("--email", prompt=True, help="Tenant account email.")
+@click.option("--name", prompt=True, help="Workspace name.")
+@click.option("--language", prompt=True, help="Account language, default: en-US.")
+def create_tenant(email: str, language: str | None = None, name: str | None = None):
+    """
+    Create tenant account
+    """
+    if not email:
+        click.echo(click.style("Email is required.", fg="red"))
+        return
+
+    # Create account
+    email = email.strip().lower()
+
+    if "@" not in email:
+        click.echo(click.style("Invalid email address.", fg="red"))
+        return
+
+    account_name = email.split("@")[0]
+
+    if language not in languages:
+        language = "en-US"
+
+    # Validates name encoding for non-Latin characters.
+    name = name.strip().encode("utf-8").decode("utf-8") if name else None
+
+    # generate random password
+    new_password = secrets.token_urlsafe(16)
+
+    # register account
+    account = RegisterService.register(
+        email=email,
+        name=account_name,
+        password=new_password,
+        language=language,
+        create_workspace_required=False,
+    )
+    TenantService.create_owner_tenant_if_not_exist(account, name)
+
+    click.echo(
+        click.style(
+            f"Account and tenant created.\nAccount: {email}\nPassword: {new_password}",
+            fg="green",
+        )
+    )

api/commands/plugin.py

@@ -0,0 +1,467 @@
+import json
+import logging
+from typing import Any
+
+import click
+from pydantic import TypeAdapter
+
+from configs import dify_config
+from core.helper import encrypter
+from core.plugin.entities.plugin_daemon import CredentialType
+from core.plugin.impl.plugin import PluginInstaller
+from core.tools.utils.system_oauth_encryption import encrypt_system_oauth_params
+from extensions.ext_database import db
+from models import Tenant
+from models.oauth import DatasourceOauthParamConfig, DatasourceProvider
+from models.provider_ids import DatasourceProviderID, ToolProviderID
+from models.source import DataSourceApiKeyAuthBinding, DataSourceOauthBinding
+from models.tools import ToolOAuthSystemClient
+from services.plugin.data_migration import PluginDataMigration
+from services.plugin.plugin_migration import PluginMigration
+from services.plugin.plugin_service import PluginService
+
+logger = logging.getLogger(__name__)
+
+
+@click.command("setup-system-tool-oauth-client", help="Setup system tool oauth client.")
+@click.option("--provider", prompt=True, help="Provider name")
+@click.option("--client-params", prompt=True, help="Client Params")
+def setup_system_tool_oauth_client(provider, client_params):
+    """
+    Setup system tool oauth client
+    """
+    provider_id = ToolProviderID(provider)
+    provider_name = provider_id.provider_name
+    plugin_id = provider_id.plugin_id
+
+    try:
+        # json validate
+        click.echo(click.style(f"Validating client params: {client_params}", fg="yellow"))
+        client_params_dict = TypeAdapter(dict[str, Any]).validate_json(client_params)
+        click.echo(click.style("Client params validated successfully.", fg="green"))
+
+        click.echo(click.style(f"Encrypting client params: {client_params}", fg="yellow"))
+        click.echo(click.style(f"Using SECRET_KEY: `{dify_config.SECRET_KEY}`", fg="yellow"))
+        oauth_client_params = encrypt_system_oauth_params(client_params_dict)
+        click.echo(click.style("Client params encrypted successfully.", fg="green"))
+    except Exception as e:
+        click.echo(click.style(f"Error parsing client params: {str(e)}", fg="red"))
+        return
+
+    deleted_count = (
+        db.session.query(ToolOAuthSystemClient)
+        .filter_by(
+            provider=provider_name,
+            plugin_id=plugin_id,
+        )
+        .delete()
+    )
+    if deleted_count > 0:
+        click.echo(click.style(f"Deleted {deleted_count} existing oauth client params.", fg="yellow"))
+
+    oauth_client = ToolOAuthSystemClient(
+        provider=provider_name,
+        plugin_id=plugin_id,
+        encrypted_oauth_params=oauth_client_params,
+    )
+    db.session.add(oauth_client)
+    db.session.commit()
+    click.echo(click.style(f"OAuth client params setup successfully. id: {oauth_client.id}", fg="green"))
+
+
+@click.command("setup-system-trigger-oauth-client", help="Setup system trigger oauth client.")
+@click.option("--provider", prompt=True, help="Provider name")
+@click.option("--client-params", prompt=True, help="Client Params")
+def setup_system_trigger_oauth_client(provider, client_params):
+    """
+    Setup system trigger oauth client
+    """
+    from models.provider_ids import TriggerProviderID
+    from models.trigger import TriggerOAuthSystemClient
+
+    provider_id = TriggerProviderID(provider)
+    provider_name = provider_id.provider_name
+    plugin_id = provider_id.plugin_id
+
+    try:
+        # json validate
+        click.echo(click.style(f"Validating client params: {client_params}", fg="yellow"))
+        client_params_dict = TypeAdapter(dict[str, Any]).validate_json(client_params)
+        click.echo(click.style("Client params validated successfully.", fg="green"))
+
+        click.echo(click.style(f"Encrypting client params: {client_params}", fg="yellow"))
+        click.echo(click.style(f"Using SECRET_KEY: `{dify_config.SECRET_KEY}`", fg="yellow"))
+        oauth_client_params = encrypt_system_oauth_params(client_params_dict)
+        click.echo(click.style("Client params encrypted successfully.", fg="green"))
+    except Exception as e:
+        click.echo(click.style(f"Error parsing client params: {str(e)}", fg="red"))
+        return
+
+    deleted_count = (
+        db.session.query(TriggerOAuthSystemClient)
+        .filter_by(
+            provider=provider_name,
+            plugin_id=plugin_id,
+        )
+        .delete()
+    )
+    if deleted_count > 0:
+        click.echo(click.style(f"Deleted {deleted_count} existing oauth client params.", fg="yellow"))
+
+    oauth_client = TriggerOAuthSystemClient(
+        provider=provider_name,
+        plugin_id=plugin_id,
+        encrypted_oauth_params=oauth_client_params,
+    )
+    db.session.add(oauth_client)
+    db.session.commit()
+    click.echo(click.style(f"OAuth client params setup successfully. id: {oauth_client.id}", fg="green"))
+
+
+@click.command("setup-datasource-oauth-client", help="Setup datasource oauth client.")
+@click.option("--provider", prompt=True, help="Provider name")
+@click.option("--client-params", prompt=True, help="Client Params")
+def setup_datasource_oauth_client(provider, client_params):
+    """
+    Setup datasource oauth client
+    """
+    provider_id = DatasourceProviderID(provider)
+    provider_name = provider_id.provider_name
+    plugin_id = provider_id.plugin_id
+
+    try:
+        # json validate
+        click.echo(click.style(f"Validating client params: {client_params}", fg="yellow"))
+        client_params_dict = TypeAdapter(dict[str, Any]).validate_json(client_params)
+        click.echo(click.style("Client params validated successfully.", fg="green"))
+    except Exception as e:
+        click.echo(click.style(f"Error parsing client params: {str(e)}", fg="red"))
+        return
+
+    click.echo(click.style(f"Ready to delete existing oauth client params: {provider_name}", fg="yellow"))
+    deleted_count = (
+        db.session.query(DatasourceOauthParamConfig)
+        .filter_by(
+            provider=provider_name,
+            plugin_id=plugin_id,
+        )
+        .delete()
+    )
+    if deleted_count > 0:
+        click.echo(click.style(f"Deleted {deleted_count} existing oauth client params.", fg="yellow"))
+
+    click.echo(click.style(f"Ready to setup datasource oauth client: {provider_name}", fg="yellow"))
+    oauth_client = DatasourceOauthParamConfig(
+        provider=provider_name,
+        plugin_id=plugin_id,
+        system_credentials=client_params_dict,
+    )
+    db.session.add(oauth_client)
+    db.session.commit()
+    click.echo(click.style(f"provider: {provider_name}", fg="green"))
+    click.echo(click.style(f"plugin_id: {plugin_id}", fg="green"))
+    click.echo(click.style(f"params: {json.dumps(client_params_dict, indent=2, ensure_ascii=False)}", fg="green"))
+    click.echo(click.style(f"Datasource oauth client setup successfully. id: {oauth_client.id}", fg="green"))
+
+
+@click.command("transform-datasource-credentials", help="Transform datasource credentials.")
+@click.option(
+    "--environment", prompt=True, help="the environment to transform datasource credentials", default="online"
+)
+def transform_datasource_credentials(environment: str):
+    """
+    Transform datasource credentials
+    """
+    try:
+        installer_manager = PluginInstaller()
+        plugin_migration = PluginMigration()
+
+        notion_plugin_id = "langgenius/notion_datasource"
+        firecrawl_plugin_id = "langgenius/firecrawl_datasource"
+        jina_plugin_id = "langgenius/jina_datasource"
+        if environment == "online":
+            notion_plugin_unique_identifier = plugin_migration._fetch_plugin_unique_identifier(notion_plugin_id)  # pyright: ignore[reportPrivateUsage]
+            firecrawl_plugin_unique_identifier = plugin_migration._fetch_plugin_unique_identifier(firecrawl_plugin_id)  # pyright: ignore[reportPrivateUsage]
+            jina_plugin_unique_identifier = plugin_migration._fetch_plugin_unique_identifier(jina_plugin_id)  # pyright: ignore[reportPrivateUsage]
+        else:
+            notion_plugin_unique_identifier = None
+            firecrawl_plugin_unique_identifier = None
+            jina_plugin_unique_identifier = None
+        oauth_credential_type = CredentialType.OAUTH2
+        api_key_credential_type = CredentialType.API_KEY
+
+        # deal notion credentials
+        deal_notion_count = 0
+        notion_credentials = db.session.query(DataSourceOauthBinding).filter_by(provider="notion").all()
+        if notion_credentials:
+            notion_credentials_tenant_mapping: dict[str, list[DataSourceOauthBinding]] = {}
+            for notion_credential in notion_credentials:
+                tenant_id = notion_credential.tenant_id
+                if tenant_id not in notion_credentials_tenant_mapping:
+                    notion_credentials_tenant_mapping[tenant_id] = []
+                notion_credentials_tenant_mapping[tenant_id].append(notion_credential)
+            for tenant_id, notion_tenant_credentials in notion_credentials_tenant_mapping.items():
+                tenant = db.session.query(Tenant).filter_by(id=tenant_id).first()
+                if not tenant:
+                    continue
+                try:
+                    # check notion plugin is installed
+                    installed_plugins = installer_manager.list_plugins(tenant_id)
+                    installed_plugins_ids = [plugin.plugin_id for plugin in installed_plugins]
+                    if notion_plugin_id not in installed_plugins_ids:
+                        if notion_plugin_unique_identifier:
+                            # install notion plugin
+                            PluginService.install_from_marketplace_pkg(tenant_id, [notion_plugin_unique_identifier])
+                    auth_count = 0
+                    for notion_tenant_credential in notion_tenant_credentials:
+                        auth_count += 1
+                        # get credential oauth params
+                        access_token = notion_tenant_credential.access_token
+                        # notion info
+                        notion_info = notion_tenant_credential.source_info
+                        workspace_id = notion_info.get("workspace_id")
+                        workspace_name = notion_info.get("workspace_name")
+                        workspace_icon = notion_info.get("workspace_icon")
+                        new_credentials = {
+                            "integration_secret": encrypter.encrypt_token(tenant_id, access_token),
+                            "workspace_id": workspace_id,
+                            "workspace_name": workspace_name,
+                            "workspace_icon": workspace_icon,
+                        }
+                        datasource_provider = DatasourceProvider(
+                            provider="notion_datasource",
+                            tenant_id=tenant_id,
+                            plugin_id=notion_plugin_id,
+                            auth_type=oauth_credential_type.value,
+                            encrypted_credentials=new_credentials,
+                            name=f"Auth {auth_count}",
+                            avatar_url=workspace_icon or "default",
+                            is_default=False,
+                        )
+                        db.session.add(datasource_provider)
+                        deal_notion_count += 1
+                except Exception as e:
+                    click.echo(
+                        click.style(
+                            f"Error transforming notion credentials: {str(e)}, tenant_id: {tenant_id}", fg="red"
+                        )
+                    )
+                    continue
+                db.session.commit()
+        # deal firecrawl credentials
+        deal_firecrawl_count = 0
+        firecrawl_credentials = db.session.query(DataSourceApiKeyAuthBinding).filter_by(provider="firecrawl").all()
+        if firecrawl_credentials:
+            firecrawl_credentials_tenant_mapping: dict[str, list[DataSourceApiKeyAuthBinding]] = {}
+            for firecrawl_credential in firecrawl_credentials:
+                tenant_id = firecrawl_credential.tenant_id
+                if tenant_id not in firecrawl_credentials_tenant_mapping:
+                    firecrawl_credentials_tenant_mapping[tenant_id] = []
+                firecrawl_credentials_tenant_mapping[tenant_id].append(firecrawl_credential)
+            for tenant_id, firecrawl_tenant_credentials in firecrawl_credentials_tenant_mapping.items():
+                tenant = db.session.query(Tenant).filter_by(id=tenant_id).first()
+                if not tenant:
+                    continue
+                try:
+                    # check firecrawl plugin is installed
+                    installed_plugins = installer_manager.list_plugins(tenant_id)
+                    installed_plugins_ids = [plugin.plugin_id for plugin in installed_plugins]
+                    if firecrawl_plugin_id not in installed_plugins_ids:
+                        if firecrawl_plugin_unique_identifier:
+                            # install firecrawl plugin
+                            PluginService.install_from_marketplace_pkg(tenant_id, [firecrawl_plugin_unique_identifier])
+
+                    auth_count = 0
+                    for firecrawl_tenant_credential in firecrawl_tenant_credentials:
+                        auth_count += 1
+                        if not firecrawl_tenant_credential.credentials:
+                            click.echo(
+                                click.style(
+                                    f"Skipping firecrawl credential for tenant {tenant_id} due to missing credentials.",
+                                    fg="yellow",
+                                )
+                            )
+                            continue
+                        # get credential api key
+                        credentials_json = json.loads(firecrawl_tenant_credential.credentials)
+                        api_key = credentials_json.get("config", {}).get("api_key")
+                        base_url = credentials_json.get("config", {}).get("base_url")
+                        new_credentials = {
+                            "firecrawl_api_key": api_key,
+                            "base_url": base_url,
+                        }
+                        datasource_provider = DatasourceProvider(
+                            provider="firecrawl",
+                            tenant_id=tenant_id,
+                            plugin_id=firecrawl_plugin_id,
+                            auth_type=api_key_credential_type.value,
+                            encrypted_credentials=new_credentials,
+                            name=f"Auth {auth_count}",
+                            avatar_url="default",
+                            is_default=False,
+                        )
+                        db.session.add(datasource_provider)
+                        deal_firecrawl_count += 1
+                except Exception as e:
+                    click.echo(
+                        click.style(
+                            f"Error transforming firecrawl credentials: {str(e)}, tenant_id: {tenant_id}", fg="red"
+                        )
+                    )
+                    continue
+                db.session.commit()
+        # deal jina credentials
+        deal_jina_count = 0
+        jina_credentials = db.session.query(DataSourceApiKeyAuthBinding).filter_by(provider="jinareader").all()
+        if jina_credentials:
+            jina_credentials_tenant_mapping: dict[str, list[DataSourceApiKeyAuthBinding]] = {}
+            for jina_credential in jina_credentials:
+                tenant_id = jina_credential.tenant_id
+                if tenant_id not in jina_credentials_tenant_mapping:
+                    jina_credentials_tenant_mapping[tenant_id] = []
+                jina_credentials_tenant_mapping[tenant_id].append(jina_credential)
+            for tenant_id, jina_tenant_credentials in jina_credentials_tenant_mapping.items():
+                tenant = db.session.query(Tenant).filter_by(id=tenant_id).first()
+                if not tenant:
+                    continue
+                try:
+                    # check jina plugin is installed
+                    installed_plugins = installer_manager.list_plugins(tenant_id)
+                    installed_plugins_ids = [plugin.plugin_id for plugin in installed_plugins]
+                    if jina_plugin_id not in installed_plugins_ids:
+                        if jina_plugin_unique_identifier:
+                            # install jina plugin
+                            logger.debug("Installing Jina plugin %s", jina_plugin_unique_identifier)
+                            PluginService.install_from_marketplace_pkg(tenant_id, [jina_plugin_unique_identifier])
+
+                    auth_count = 0
+                    for jina_tenant_credential in jina_tenant_credentials:
+                        auth_count += 1
+                        if not jina_tenant_credential.credentials:
+                            click.echo(
+                                click.style(
+                                    f"Skipping jina credential for tenant {tenant_id} due to missing credentials.",
+                                    fg="yellow",
+                                )
+                            )
+                            continue
+                        # get credential api key
+                        credentials_json = json.loads(jina_tenant_credential.credentials)
+                        api_key = credentials_json.get("config", {}).get("api_key")
+                        new_credentials = {
+                            "integration_secret": api_key,
+                        }
+                        datasource_provider = DatasourceProvider(
+                            provider="jinareader",
+                            tenant_id=tenant_id,
+                            plugin_id=jina_plugin_id,
+                            auth_type=api_key_credential_type.value,
+                            encrypted_credentials=new_credentials,
+                            name=f"Auth {auth_count}",
+                            avatar_url="default",
+                            is_default=False,
+                        )
+                        db.session.add(datasource_provider)
+                        deal_jina_count += 1
+                except Exception as e:
+                    click.echo(
+                        click.style(f"Error transforming jina credentials: {str(e)}, tenant_id: {tenant_id}", fg="red")
+                    )
+                    continue
+                db.session.commit()
+    except Exception as e:
+        click.echo(click.style(f"Error parsing client params: {str(e)}", fg="red"))
+        return
+    click.echo(click.style(f"Transforming notion successfully. deal_notion_count: {deal_notion_count}", fg="green"))
+    click.echo(
+        click.style(f"Transforming firecrawl successfully. deal_firecrawl_count: {deal_firecrawl_count}", fg="green")
+    )
+    click.echo(click.style(f"Transforming jina successfully. deal_jina_count: {deal_jina_count}", fg="green"))
+
+
+@click.command("migrate-data-for-plugin", help="Migrate data for plugin.")
+def migrate_data_for_plugin():
+    """
+    Migrate data for plugin.
+    """
+    click.echo(click.style("Starting migrate data for plugin.", fg="white"))
+
+    PluginDataMigration.migrate()
+
+    click.echo(click.style("Migrate data for plugin completed.", fg="green"))
+
+
+@click.command("extract-plugins", help="Extract plugins.")
+@click.option("--output_file", prompt=True, help="The file to store the extracted plugins.", default="plugins.jsonl")
+@click.option("--workers", prompt=True, help="The number of workers to extract plugins.", default=10)
+def extract_plugins(output_file: str, workers: int):
+    """
+    Extract plugins.
+    """
+    click.echo(click.style("Starting extract plugins.", fg="white"))
+
+    PluginMigration.extract_plugins(output_file, workers)
+
+    click.echo(click.style("Extract plugins completed.", fg="green"))
+
+
+@click.command("extract-unique-identifiers", help="Extract unique identifiers.")
+@click.option(
+    "--output_file",
+    prompt=True,
+    help="The file to store the extracted unique identifiers.",
+    default="unique_identifiers.json",
+)
+@click.option(
+    "--input_file", prompt=True, help="The file to store the extracted unique identifiers.", default="plugins.jsonl"
+)
+def extract_unique_plugins(output_file: str, input_file: str):
+    """
+    Extract unique plugins.
+    """
+    click.echo(click.style("Starting extract unique plugins.", fg="white"))
+
+    PluginMigration.extract_unique_plugins_to_file(input_file, output_file)
+
+    click.echo(click.style("Extract unique plugins completed.", fg="green"))
+
+
+@click.command("install-plugins", help="Install plugins.")
+@click.option(
+    "--input_file", prompt=True, help="The file to store the extracted unique identifiers.", default="plugins.jsonl"
+)
+@click.option(
+    "--output_file", prompt=True, help="The file to store the installed plugins.", default="installed_plugins.jsonl"
+)
+@click.option("--workers", prompt=True, help="The number of workers to install plugins.", default=100)
+def install_plugins(input_file: str, output_file: str, workers: int):
+    """
+    Install plugins.
+    """
+    click.echo(click.style("Starting install plugins.", fg="white"))
+
+    PluginMigration.install_plugins(input_file, output_file, workers)
+
+    click.echo(click.style("Install plugins completed.", fg="green"))
+
+
+@click.command("install-rag-pipeline-plugins", help="Install rag pipeline plugins.")
+@click.option(
+    "--input_file", prompt=True, help="The file to store the extracted unique identifiers.", default="plugins.jsonl"
+)
+@click.option(
+    "--output_file", prompt=True, help="The file to store the installed plugins.", default="installed_plugins.jsonl"
+)
+@click.option("--workers", prompt=True, help="The number of workers to install plugins.", default=100)
+def install_rag_pipeline_plugins(input_file, output_file, workers):
+    """
+    Install rag pipeline plugins
+    """
+    click.echo(click.style("Installing rag pipeline plugins", fg="yellow"))
+    plugin_migration = PluginMigration()
+    plugin_migration.install_rag_pipeline_plugins(
+        input_file,
+        output_file,
+        workers,
+    )
+    click.echo(click.style("Installing rag pipeline plugins successfully", fg="green"))

api/commands/retention.py

@@ -0,0 +1,830 @@
+import datetime
+import logging
+import time
+from typing import Any
+
+import click
+import sqlalchemy as sa
+
+from extensions.ext_database import db
+from libs.datetime_utils import naive_utc_now
+from services.clear_free_plan_tenant_expired_logs import ClearFreePlanTenantExpiredLogs
+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
+
+logger = logging.getLogger(__name__)
+
+
+@click.command("clear-free-plan-tenant-expired-logs", help="Clear free plan tenant expired logs.")
+@click.option("--days", prompt=True, help="The days to clear free plan tenant expired logs.", default=30)
+@click.option("--batch", prompt=True, help="The batch size to clear free plan tenant expired logs.", default=100)
+@click.option(
+    "--tenant_ids",
+    prompt=True,
+    multiple=True,
+    help="The tenant ids to clear free plan tenant expired logs.",
+)
+def clear_free_plan_tenant_expired_logs(days: int, batch: int, tenant_ids: list[str]):
+    """
+    Clear free plan tenant expired logs.
+    """
+    click.echo(click.style("Starting clear free plan tenant expired logs.", fg="white"))
+
+    ClearFreePlanTenantExpiredLogs.process(days, batch, tenant_ids)
+
+    click.echo(click.style("Clear free plan tenant expired logs completed.", fg="green"))
+
+
+@click.command("clean-workflow-runs", help="Clean expired workflow runs and related data for free tenants.")
+@click.option(
+    "--before-days",
+    "--days",
+    default=30,
+    show_default=True,
+    type=click.IntRange(min=0),
+    help="Delete workflow runs created before N days ago.",
+)
+@click.option("--batch-size", default=200, show_default=True, help="Batch size for selecting workflow runs.")
+@click.option(
+    "--from-days-ago",
+    default=None,
+    type=click.IntRange(min=0),
+    help="Lower bound in days ago (older). Must be paired with --to-days-ago.",
+)
+@click.option(
+    "--to-days-ago",
+    default=None,
+    type=click.IntRange(min=0),
+    help="Upper bound in days ago (newer). Must be paired with --from-days-ago.",
+)
+@click.option(
+    "--start-from",
+    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
+    default=None,
+    help="Optional lower bound (inclusive) for created_at; must be paired with --end-before.",
+)
+@click.option(
+    "--end-before",
+    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
+    default=None,
+    help="Optional upper bound (exclusive) for created_at; must be paired with --start-from.",
+)
+@click.option(
+    "--dry-run",
+    is_flag=True,
+    help="Preview cleanup results without deleting any workflow run data.",
+)
+def clean_workflow_runs(
+    before_days: int,
+    batch_size: int,
+    from_days_ago: int | None,
+    to_days_ago: int | None,
+    start_from: datetime.datetime | None,
+    end_before: datetime.datetime | None,
+    dry_run: bool,
+):
+    """
+    Clean workflow runs and related workflow data for free tenants.
+    """
+    if (start_from is None) ^ (end_before is None):
+        raise click.UsageError("--start-from and --end-before must be provided together.")
+
+    if (from_days_ago is None) ^ (to_days_ago is None):
+        raise click.UsageError("--from-days-ago and --to-days-ago must be provided together.")
+
+    if from_days_ago is not None and to_days_ago is not None:
+        if start_from or end_before:
+            raise click.UsageError("Choose either day offsets or explicit dates, not both.")
+        if from_days_ago <= to_days_ago:
+            raise click.UsageError("--from-days-ago must be greater than --to-days-ago.")
+        now = datetime.datetime.now()
+        start_from = now - datetime.timedelta(days=from_days_ago)
+        end_before = now - datetime.timedelta(days=to_days_ago)
+        before_days = 0
+
+    start_time = datetime.datetime.now(datetime.UTC)
+    click.echo(click.style(f"Starting workflow run cleanup at {start_time.isoformat()}.", fg="white"))
+
+    WorkflowRunCleanup(
+        days=before_days,
+        batch_size=batch_size,
+        start_from=start_from,
+        end_before=end_before,
+        dry_run=dry_run,
+    ).run()
+
+    end_time = datetime.datetime.now(datetime.UTC)
+    elapsed = end_time - start_time
+    click.echo(
+        click.style(
+            f"Workflow run cleanup completed. start={start_time.isoformat()} "
+            f"end={end_time.isoformat()} duration={elapsed}",
+            fg="green",
+        )
+    )
+
+
+@click.command(
+    "archive-workflow-runs",
+    help="Archive workflow runs for paid plan tenants to S3-compatible storage.",
+)
+@click.option("--tenant-ids", default=None, help="Optional comma-separated tenant IDs for grayscale rollout.")
+@click.option("--before-days", default=90, show_default=True, help="Archive runs older than N days.")
+@click.option(
+    "--from-days-ago",
+    default=None,
+    type=click.IntRange(min=0),
+    help="Lower bound in days ago (older). Must be paired with --to-days-ago.",
+)
+@click.option(
+    "--to-days-ago",
+    default=None,
+    type=click.IntRange(min=0),
+    help="Upper bound in days ago (newer). Must be paired with --from-days-ago.",
+)
+@click.option(
+    "--start-from",
+    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
+    default=None,
+    help="Archive runs created at or after this timestamp (UTC if no timezone).",
+)
+@click.option(
+    "--end-before",
+    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
+    default=None,
+    help="Archive runs created before this timestamp (UTC if no timezone).",
+)
+@click.option("--batch-size", default=100, show_default=True, help="Batch size for processing.")
+@click.option("--workers", default=1, show_default=True, type=int, help="Concurrent workflow runs to archive.")
+@click.option("--limit", default=None, type=int, help="Maximum number of runs to archive.")
+@click.option("--dry-run", is_flag=True, help="Preview without archiving.")
+@click.option("--delete-after-archive", is_flag=True, help="Delete runs and related data after archiving.")
+def archive_workflow_runs(
+    tenant_ids: str | None,
+    before_days: int,
+    from_days_ago: int | None,
+    to_days_ago: int | None,
+    start_from: datetime.datetime | None,
+    end_before: datetime.datetime | None,
+    batch_size: int,
+    workers: int,
+    limit: int | None,
+    dry_run: bool,
+    delete_after_archive: bool,
+):
+    """
+    Archive workflow runs for paid plan tenants older than the specified days.
+
+    This command archives the following tables to storage:
+    - workflow_node_executions
+    - workflow_node_execution_offload
+    - workflow_pauses
+    - workflow_pause_reasons
+    - workflow_trigger_logs
+
+    The workflow_runs and workflow_app_logs tables are preserved for UI listing.
+    """
+    from services.retention.workflow_run.archive_paid_plan_workflow_run import WorkflowRunArchiver
+
+    run_started_at = datetime.datetime.now(datetime.UTC)
+    click.echo(
+        click.style(
+            f"Starting workflow run archiving at {run_started_at.isoformat()}.",
+            fg="white",
+        )
+    )
+
+    if (start_from is None) ^ (end_before is None):
+        click.echo(click.style("start-from and end-before must be provided together.", fg="red"))
+        return
+
+    if (from_days_ago is None) ^ (to_days_ago is None):
+        click.echo(click.style("from-days-ago and to-days-ago must be provided together.", fg="red"))
+        return
+
+    if from_days_ago is not None and to_days_ago is not None:
+        if start_from or end_before:
+            click.echo(click.style("Choose either day offsets or explicit dates, not both.", fg="red"))
+            return
+        if from_days_ago <= to_days_ago:
+            click.echo(click.style("from-days-ago must be greater than to-days-ago.", fg="red"))
+            return
+        now = datetime.datetime.now()
+        start_from = now - datetime.timedelta(days=from_days_ago)
+        end_before = now - datetime.timedelta(days=to_days_ago)
+        before_days = 0
+
+    if start_from and end_before and start_from >= end_before:
+        click.echo(click.style("start-from must be earlier than end-before.", fg="red"))
+        return
+    if workers < 1:
+        click.echo(click.style("workers must be at least 1.", fg="red"))
+        return
+
+    archiver = WorkflowRunArchiver(
+        days=before_days,
+        batch_size=batch_size,
+        start_from=start_from,
+        end_before=end_before,
+        workers=workers,
+        tenant_ids=[tid.strip() for tid in tenant_ids.split(",")] if tenant_ids else None,
+        limit=limit,
+        dry_run=dry_run,
+        delete_after_archive=delete_after_archive,
+    )
+    summary = archiver.run()
+    click.echo(
+        click.style(
+            f"Summary: processed={summary.total_runs_processed}, archived={summary.runs_archived}, "
+            f"skipped={summary.runs_skipped}, failed={summary.runs_failed}, "
+            f"time={summary.total_elapsed_time:.2f}s",
+            fg="cyan",
+        )
+    )
+
+    run_finished_at = datetime.datetime.now(datetime.UTC)
+    elapsed = run_finished_at - run_started_at
+    click.echo(
+        click.style(
+            f"Workflow run archiving completed. start={run_started_at.isoformat()} "
+            f"end={run_finished_at.isoformat()} duration={elapsed}",
+            fg="green",
+        )
+    )
+
+
+@click.command(
+    "restore-workflow-runs",
+    help="Restore archived workflow runs from S3-compatible storage.",
+)
+@click.option(
+    "--tenant-ids",
+    required=False,
+    help="Tenant IDs (comma-separated).",
+)
+@click.option("--run-id", required=False, help="Workflow run ID to restore.")
+@click.option(
+    "--start-from",
+    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
+    default=None,
+    help="Optional lower bound (inclusive) for created_at; must be paired with --end-before.",
+)
+@click.option(
+    "--end-before",
+    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
+    default=None,
+    help="Optional upper bound (exclusive) for created_at; must be paired with --start-from.",
+)
+@click.option("--workers", default=1, show_default=True, type=int, help="Concurrent workflow runs to restore.")
+@click.option("--limit", type=int, default=100, show_default=True, help="Maximum number of runs to restore.")
+@click.option("--dry-run", is_flag=True, help="Preview without restoring.")
+def restore_workflow_runs(
+    tenant_ids: str | None,
+    run_id: str | None,
+    start_from: datetime.datetime | None,
+    end_before: datetime.datetime | None,
+    workers: int,
+    limit: int,
+    dry_run: bool,
+):
+    """
+    Restore an archived workflow run from storage to the database.
+
+    This restores the following tables:
+    - workflow_node_executions
+    - workflow_node_execution_offload
+    - workflow_pauses
+    - workflow_pause_reasons
+    - workflow_trigger_logs
+    """
+    from services.retention.workflow_run.restore_archived_workflow_run import WorkflowRunRestore
+
+    parsed_tenant_ids = None
+    if tenant_ids:
+        parsed_tenant_ids = [tid.strip() for tid in tenant_ids.split(",") if tid.strip()]
+        if not parsed_tenant_ids:
+            raise click.BadParameter("tenant-ids must not be empty")
+
+    if (start_from is None) ^ (end_before is None):
+        raise click.UsageError("--start-from and --end-before must be provided together.")
+    if run_id is None and (start_from is None or end_before is None):
+        raise click.UsageError("--start-from and --end-before are required for batch restore.")
+    if workers < 1:
+        raise click.BadParameter("workers must be at least 1")
+
+    start_time = datetime.datetime.now(datetime.UTC)
+    click.echo(
+        click.style(
+            f"Starting restore of workflow run {run_id} at {start_time.isoformat()}.",
+            fg="white",
+        )
+    )
+
+    restorer = WorkflowRunRestore(dry_run=dry_run, workers=workers)
+    if run_id:
+        results = [restorer.restore_by_run_id(run_id)]
+    else:
+        assert start_from is not None
+        assert end_before is not None
+        results = restorer.restore_batch(
+            parsed_tenant_ids,
+            start_date=start_from,
+            end_date=end_before,
+            limit=limit,
+        )
+
+    end_time = datetime.datetime.now(datetime.UTC)
+    elapsed = end_time - start_time
+
+    successes = sum(1 for result in results if result.success)
+    failures = len(results) - successes
+
+    if failures == 0:
+        click.echo(
+            click.style(
+                f"Restore completed successfully. success={successes} duration={elapsed}",
+                fg="green",
+            )
+        )
+    else:
+        click.echo(
+            click.style(
+                f"Restore completed with failures. success={successes} failed={failures} duration={elapsed}",
+                fg="red",
+            )
+        )
+
+
+@click.command(
+    "delete-archived-workflow-runs",
+    help="Delete archived workflow runs from the database.",
+)
+@click.option(
+    "--tenant-ids",
+    required=False,
+    help="Tenant IDs (comma-separated).",
+)
+@click.option("--run-id", required=False, help="Workflow run ID to delete.")
+@click.option(
+    "--start-from",
+    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
+    default=None,
+    help="Optional lower bound (inclusive) for created_at; must be paired with --end-before.",
+)
+@click.option(
+    "--end-before",
+    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
+    default=None,
+    help="Optional upper bound (exclusive) for created_at; must be paired with --start-from.",
+)
+@click.option("--limit", type=int, default=100, show_default=True, help="Maximum number of runs to delete.")
+@click.option("--dry-run", is_flag=True, help="Preview without deleting.")
+def delete_archived_workflow_runs(
+    tenant_ids: str | None,
+    run_id: str | None,
+    start_from: datetime.datetime | None,
+    end_before: datetime.datetime | None,
+    limit: int,
+    dry_run: bool,
+):
+    """
+    Delete archived workflow runs from the database.
+    """
+    from services.retention.workflow_run.delete_archived_workflow_run import ArchivedWorkflowRunDeletion
+
+    parsed_tenant_ids = None
+    if tenant_ids:
+        parsed_tenant_ids = [tid.strip() for tid in tenant_ids.split(",") if tid.strip()]
+        if not parsed_tenant_ids:
+            raise click.BadParameter("tenant-ids must not be empty")
+
+    if (start_from is None) ^ (end_before is None):
+        raise click.UsageError("--start-from and --end-before must be provided together.")
+    if run_id is None and (start_from is None or end_before is None):
+        raise click.UsageError("--start-from and --end-before are required for batch delete.")
+
+    start_time = datetime.datetime.now(datetime.UTC)
+    target_desc = f"workflow run {run_id}" if run_id else "workflow runs"
+    click.echo(
+        click.style(
+            f"Starting delete of {target_desc} at {start_time.isoformat()}.",
+            fg="white",
+        )
+    )
+
+    deleter = ArchivedWorkflowRunDeletion(dry_run=dry_run)
+    if run_id:
+        results = [deleter.delete_by_run_id(run_id)]
+    else:
+        assert start_from is not None
+        assert end_before is not None
+        results = deleter.delete_batch(
+            parsed_tenant_ids,
+            start_date=start_from,
+            end_date=end_before,
+            limit=limit,
+        )
+
+    for result in results:
+        if result.success:
+            click.echo(
+                click.style(
+                    f"{'[DRY RUN] Would delete' if dry_run else 'Deleted'} "
+                    f"workflow run {result.run_id} (tenant={result.tenant_id})",
+                    fg="green",
+                )
+            )
+        else:
+            click.echo(
+                click.style(
+                    f"Failed to delete workflow run {result.run_id}: {result.error}",
+                    fg="red",
+                )
+            )
+
+    end_time = datetime.datetime.now(datetime.UTC)
+    elapsed = end_time - start_time
+
+    successes = sum(1 for result in results if result.success)
+    failures = len(results) - successes
+
+    if failures == 0:
+        click.echo(
+            click.style(
+                f"Delete completed successfully. success={successes} duration={elapsed}",
+                fg="green",
+            )
+        )
+    else:
+        click.echo(
+            click.style(
+                f"Delete completed with failures. success={successes} failed={failures} duration={elapsed}",
+                fg="red",
+            )
+        )
+
+
+def _find_orphaned_draft_variables(batch_size: int = 1000) -> list[str]:
+    """
+    Find draft variables that reference non-existent apps.
+
+    Args:
+        batch_size: Maximum number of orphaned app IDs to return
+
+    Returns:
+        List of app IDs that have draft variables but don't exist in the apps table
+    """
+    query = """
+        SELECT DISTINCT wdv.app_id
+        FROM workflow_draft_variables AS wdv
+        WHERE NOT EXISTS(
+            SELECT 1 FROM apps WHERE apps.id = wdv.app_id
+        )
+        LIMIT :batch_size
+    """
+
+    with db.engine.connect() as conn:
+        result = conn.execute(sa.text(query), {"batch_size": batch_size})
+        return [row[0] for row in result]
+
+
+def _count_orphaned_draft_variables() -> dict[str, Any]:
+    """
+    Count orphaned draft variables by app, including associated file counts.
+
+    Returns:
+        Dictionary with statistics about orphaned variables and files
+    """
+    # Count orphaned variables by app
+    variables_query = """
+        SELECT
+            wdv.app_id,
+            COUNT(*) as variable_count,
+            COUNT(wdv.file_id) as file_count
+        FROM workflow_draft_variables AS wdv
+        WHERE NOT EXISTS(
+            SELECT 1 FROM apps WHERE apps.id = wdv.app_id
+        )
+        GROUP BY wdv.app_id
+        ORDER BY variable_count DESC
+    """
+
+    with db.engine.connect() as conn:
+        result = conn.execute(sa.text(variables_query))
+        orphaned_by_app = {}
+        total_files = 0
+
+        for row in result:
+            app_id, variable_count, file_count = row
+            orphaned_by_app[app_id] = {"variables": variable_count, "files": file_count}
+            total_files += file_count
+
+        total_orphaned = sum(app_data["variables"] for app_data in orphaned_by_app.values())
+        app_count = len(orphaned_by_app)
+
+        return {
+            "total_orphaned_variables": total_orphaned,
+            "total_orphaned_files": total_files,
+            "orphaned_app_count": app_count,
+            "orphaned_by_app": orphaned_by_app,
+        }
+
+
+@click.command()
+@click.option("--dry-run", is_flag=True, help="Show what would be deleted without actually deleting")
+@click.option("--batch-size", default=1000, help="Number of records to process per batch (default 1000)")
+@click.option("--max-apps", default=None, type=int, help="Maximum number of apps to process (default: no limit)")
+@click.option("-f", "--force", is_flag=True, help="Skip user confirmation and force the command to execute.")
+def cleanup_orphaned_draft_variables(
+    dry_run: bool,
+    batch_size: int,
+    max_apps: int | None,
+    force: bool = False,
+):
+    """
+    Clean up orphaned draft variables from the database.
+
+    This script finds and removes draft variables that belong to apps
+    that no longer exist in the database.
+    """
+    logger = logging.getLogger(__name__)
+
+    # Get statistics
+    stats = _count_orphaned_draft_variables()
+
+    logger.info("Found %s orphaned draft variables", stats["total_orphaned_variables"])
+    logger.info("Found %s associated offload files", stats["total_orphaned_files"])
+    logger.info("Across %s non-existent apps", stats["orphaned_app_count"])
+
+    if stats["total_orphaned_variables"] == 0:
+        logger.info("No orphaned draft variables found. Exiting.")
+        return
+
+    if dry_run:
+        logger.info("DRY RUN: Would delete the following:")
+        for app_id, data in sorted(stats["orphaned_by_app"].items(), key=lambda x: x[1]["variables"], reverse=True)[
+            :10
+        ]:  # Show top 10
+            logger.info("  App %s: %s variables, %s files", app_id, data["variables"], data["files"])
+        if len(stats["orphaned_by_app"]) > 10:
+            logger.info("  ... and %s more apps", len(stats["orphaned_by_app"]) - 10)
+        return
+
+    # Confirm deletion
+    if not force:
+        click.confirm(
+            f"Are you sure you want to delete {stats['total_orphaned_variables']} "
+            f"orphaned draft variables and {stats['total_orphaned_files']} associated files "
+            f"from {stats['orphaned_app_count']} apps?",
+            abort=True,
+        )
+
+    total_deleted = 0
+    processed_apps = 0
+
+    while True:
+        if max_apps and processed_apps >= max_apps:
+            logger.info("Reached maximum app limit (%s). Stopping.", max_apps)
+            break
+
+        orphaned_app_ids = _find_orphaned_draft_variables(batch_size=10)
+        if not orphaned_app_ids:
+            logger.info("No more orphaned draft variables found.")
+            break
+
+        for app_id in orphaned_app_ids:
+            if max_apps and processed_apps >= max_apps:
+                break
+
+            try:
+                deleted_count = delete_draft_variables_batch(app_id, batch_size)
+                total_deleted += deleted_count
+                processed_apps += 1
+
+                logger.info("Deleted %s variables for app %s", deleted_count, app_id)
+
+            except Exception:
+                logger.exception("Error processing app %s", app_id)
+                continue
+
+    logger.info("Cleanup completed. Total deleted: %s variables across %s apps", total_deleted, processed_apps)
+
+
+@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=False,
+    default=None,
+    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=False,
+    default=None,
+    help="Upper bound (exclusive) for created_at.",
+)
+@click.option(
+    "--from-days-ago",
+    type=int,
+    default=None,
+    help="Relative lower bound in days ago (inclusive). Must be used with --before-days.",
+)
+@click.option(
+    "--before-days",
+    type=int,
+    default=None,
+    help="Relative upper bound in days ago (exclusive). Required for relative mode.",
+)
+@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 | None,
+    end_before: datetime.datetime | None,
+    from_days_ago: int | None,
+    before_days: int | None,
+    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:
+        abs_mode = start_from is not None and end_before is not None
+        rel_mode = before_days is not None
+
+        if abs_mode and rel_mode:
+            raise click.UsageError(
+                "Options are mutually exclusive: use either (--start-from,--end-before) "
+                "or (--from-days-ago,--before-days)."
+            )
+
+        if from_days_ago is not None and before_days is None:
+            raise click.UsageError("--from-days-ago must be used together with --before-days.")
+
+        if (start_from is None) ^ (end_before is None):
+            raise click.UsageError("Both --start-from and --end-before are required when using absolute time range.")
+
+        if not abs_mode and not rel_mode:
+            raise click.UsageError(
+                "You must provide either (--start-from,--end-before) or (--before-days [--from-days-ago])."
+            )
+
+        if rel_mode:
+            assert before_days is not None
+            if before_days < 0:
+                raise click.UsageError("--before-days must be >= 0.")
+            if from_days_ago is not None:
+                if from_days_ago < 0:
+                    raise click.UsageError("--from-days-ago must be >= 0.")
+                if from_days_ago <= before_days:
+                    raise click.UsageError("--from-days-ago must be greater than --before-days.")
+
+        # 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
+        if abs_mode:
+            assert start_from is not None
+            assert end_before is not None
+            service = MessagesCleanService.from_time_range(
+                policy=policy,
+                start_from=start_from,
+                end_before=end_before,
+                batch_size=batch_size,
+                dry_run=dry_run,
+            )
+        elif from_days_ago is None:
+            assert before_days is not None
+            service = MessagesCleanService.from_days(
+                policy=policy,
+                days=before_days,
+                batch_size=batch_size,
+                dry_run=dry_run,
+            )
+        else:
+            assert before_days is not None
+            assert from_days_ago is not None
+            now = naive_utc_now()
+            service = MessagesCleanService.from_time_range(
+                policy=policy,
+                start_from=now - datetime.timedelta(days=from_days_ago),
+                end_before=now - datetime.timedelta(days=before_days),
+                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"))
+
+
+@click.command("export-app-messages", help="Export messages for an app to JSONL.GZ.")
+@click.option("--app-id", required=True, help="Application ID to export messages for.")
+@click.option(
+    "--start-from",
+    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
+    default=None,
+    help="Optional 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(
+    "--filename",
+    required=True,
+    help="Base filename (relative path). Do not include suffix like .jsonl.gz.",
+)
+@click.option("--use-cloud-storage", is_flag=True, default=False, help="Upload to cloud storage instead of local file.")
+@click.option("--batch-size", default=1000, show_default=True, help="Batch size for cursor pagination.")
+@click.option("--dry-run", is_flag=True, default=False, help="Scan only, print stats without writing any file.")
+def export_app_messages(
+    app_id: str,
+    start_from: datetime.datetime | None,
+    end_before: datetime.datetime,
+    filename: str,
+    use_cloud_storage: bool,
+    batch_size: int,
+    dry_run: bool,
+):
+    if start_from and start_from >= end_before:
+        raise click.UsageError("--start-from must be before --end-before.")
+
+    from services.retention.conversation.message_export_service import AppMessageExportService
+
+    try:
+        validated_filename = AppMessageExportService.validate_export_filename(filename)
+    except ValueError as e:
+        raise click.BadParameter(str(e), param_hint="--filename") from e
+
+    click.echo(click.style(f"export_app_messages: starting export for app {app_id}.", fg="green"))
+    start_at = time.perf_counter()
+
+    try:
+        service = AppMessageExportService(
+            app_id=app_id,
+            end_before=end_before,
+            filename=validated_filename,
+            start_from=start_from,
+            batch_size=batch_size,
+            use_cloud_storage=use_cloud_storage,
+            dry_run=dry_run,
+        )
+        stats = service.run()
+
+        elapsed = time.perf_counter() - start_at
+        click.echo(
+            click.style(
+                f"export_app_messages: completed in {elapsed:.2f}s\n"
+                f"  - Batches: {stats.batches}\n"
+                f"  - Total messages: {stats.total_messages}\n"
+                f"  - Messages with feedback: {stats.messages_with_feedback}\n"
+                f"  - Total feedbacks: {stats.total_feedbacks}",
+                fg="green",
+            )
+        )
+    except Exception as e:
+        elapsed = time.perf_counter() - start_at
+        logger.exception("export_app_messages failed")
+        click.echo(click.style(f"export_app_messages: failed after {elapsed:.2f}s - {e}", fg="red"))
+        raise

api/commands/storage.py

@@ -0,0 +1,755 @@
+import json
+
+import click
+import sqlalchemy as sa
+
+from configs import dify_config
+from extensions.ext_database import db
+from extensions.ext_storage import storage
+from extensions.storage.opendal_storage import OpenDALStorage
+from extensions.storage.storage_type import StorageType
+from models.model import UploadFile
+
+
+@click.option("-f", "--force", is_flag=True, help="Skip user confirmation and force the command to execute.")
+@click.command("clear-orphaned-file-records", help="Clear orphaned file records.")
+def clear_orphaned_file_records(force: bool):
+    """
+    Clear orphaned file records in the database.
+    """
+
+    # define tables and columns to process
+    files_tables = [
+        {"table": "upload_files", "id_column": "id", "key_column": "key"},
+        {"table": "tool_files", "id_column": "id", "key_column": "file_key"},
+    ]
+    ids_tables = [
+        {"type": "uuid", "table": "message_files", "column": "upload_file_id"},
+        {"type": "text", "table": "documents", "column": "data_source_info"},
+        {"type": "text", "table": "document_segments", "column": "content"},
+        {"type": "text", "table": "messages", "column": "answer"},
+        {"type": "text", "table": "workflow_node_executions", "column": "inputs"},
+        {"type": "text", "table": "workflow_node_executions", "column": "process_data"},
+        {"type": "text", "table": "workflow_node_executions", "column": "outputs"},
+        {"type": "text", "table": "conversations", "column": "introduction"},
+        {"type": "text", "table": "conversations", "column": "system_instruction"},
+        {"type": "text", "table": "accounts", "column": "avatar"},
+        {"type": "text", "table": "apps", "column": "icon"},
+        {"type": "text", "table": "sites", "column": "icon"},
+        {"type": "json", "table": "messages", "column": "inputs"},
+        {"type": "json", "table": "messages", "column": "message"},
+    ]
+
+    # notify user and ask for confirmation
+    click.echo(
+        click.style(
+            "This command will first find and delete orphaned file records from the message_files table,", fg="yellow"
+        )
+    )
+    click.echo(
+        click.style(
+            "and then it will find and delete orphaned file records in the following tables:",
+            fg="yellow",
+        )
+    )
+    for files_table in files_tables:
+        click.echo(click.style(f"- {files_table['table']}", fg="yellow"))
+    click.echo(
+        click.style("The following tables and columns will be scanned to find orphaned file records:", fg="yellow")
+    )
+    for ids_table in ids_tables:
+        click.echo(click.style(f"- {ids_table['table']} ({ids_table['column']})", fg="yellow"))
+    click.echo("")
+
+    click.echo(click.style("!!! USE WITH CAUTION !!!", fg="red"))
+    click.echo(
+        click.style(
+            (
+                "Since not all patterns have been fully tested, "
+                "please note that this command may delete unintended file records."
+            ),
+            fg="yellow",
+        )
+    )
+    click.echo(
+        click.style("This cannot be undone. Please make sure to back up your database before proceeding.", fg="yellow")
+    )
+    click.echo(
+        click.style(
+            (
+                "It is also recommended to run this during the maintenance window, "
+                "as this may cause high load on your instance."
+            ),
+            fg="yellow",
+        )
+    )
+    if not force:
+        click.confirm("Do you want to proceed?", abort=True)
+
+    # start the cleanup process
+    click.echo(click.style("Starting orphaned file records cleanup.", fg="white"))
+
+    # clean up the orphaned records in the message_files table where message_id doesn't exist in messages table
+    try:
+        click.echo(
+            click.style("- Listing message_files records where message_id doesn't exist in messages table", fg="white")
+        )
+        query = (
+            "SELECT mf.id, mf.message_id "
+            "FROM message_files mf LEFT JOIN messages m ON mf.message_id = m.id "
+            "WHERE m.id IS NULL"
+        )
+        orphaned_message_files = []
+        with db.engine.begin() as conn:
+            rs = conn.execute(sa.text(query))
+            for i in rs:
+                orphaned_message_files.append({"id": str(i[0]), "message_id": str(i[1])})
+
+        if orphaned_message_files:
+            click.echo(click.style(f"Found {len(orphaned_message_files)} orphaned message_files records:", fg="white"))
+            for record in orphaned_message_files:
+                click.echo(click.style(f"  - id: {record['id']}, message_id: {record['message_id']}", fg="black"))
+
+            if not force:
+                click.confirm(
+                    (
+                        f"Do you want to proceed "
+                        f"to delete all {len(orphaned_message_files)} orphaned message_files records?"
+                    ),
+                    abort=True,
+                )
+
+            click.echo(click.style("- Deleting orphaned message_files records", fg="white"))
+            query = "DELETE FROM message_files WHERE id IN :ids"
+            with db.engine.begin() as conn:
+                conn.execute(sa.text(query), {"ids": tuple(record["id"] for record in orphaned_message_files)})
+            click.echo(
+                click.style(f"Removed {len(orphaned_message_files)} orphaned message_files records.", fg="green")
+            )
+        else:
+            click.echo(click.style("No orphaned message_files records found. There is nothing to delete.", fg="green"))
+    except Exception as e:
+        click.echo(click.style(f"Error deleting orphaned message_files records: {str(e)}", fg="red"))
+
+    # clean up the orphaned records in the rest of the *_files tables
+    try:
+        # fetch file id and keys from each table
+        all_files_in_tables = []
+        for files_table in files_tables:
+            click.echo(click.style(f"- Listing file records in table {files_table['table']}", fg="white"))
+            query = f"SELECT {files_table['id_column']}, {files_table['key_column']} FROM {files_table['table']}"
+            with db.engine.begin() as conn:
+                rs = conn.execute(sa.text(query))
+            for i in rs:
+                all_files_in_tables.append({"table": files_table["table"], "id": str(i[0]), "key": i[1]})
+        click.echo(click.style(f"Found {len(all_files_in_tables)} files in tables.", fg="white"))
+
+        # fetch referred table and columns
+        guid_regexp = "[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{12}"
+        all_ids_in_tables = []
+        for ids_table in ids_tables:
+            query = ""
+            match ids_table["type"]:
+                case "uuid":
+                    click.echo(
+                        click.style(
+                            f"- Listing file ids in column {ids_table['column']} in table {ids_table['table']}",
+                            fg="white",
+                        )
+                    )
+                    c = ids_table["column"]
+                    query = f"SELECT {c} FROM {ids_table['table']} WHERE {c} IS NOT NULL"
+                    with db.engine.begin() as conn:
+                        rs = conn.execute(sa.text(query))
+                    for i in rs:
+                        all_ids_in_tables.append({"table": ids_table["table"], "id": str(i[0])})
+                case "text":
+                    t = ids_table["table"]
+                    click.echo(
+                        click.style(
+                            f"- Listing file-id-like strings in column {ids_table['column']} in table {t}",
+                            fg="white",
+                        )
+                    )
+                    query = (
+                        f"SELECT regexp_matches({ids_table['column']}, '{guid_regexp}', 'g') AS extracted_id "
+                        f"FROM {ids_table['table']}"
+                    )
+                    with db.engine.begin() as conn:
+                        rs = conn.execute(sa.text(query))
+                    for i in rs:
+                        for j in i[0]:
+                            all_ids_in_tables.append({"table": ids_table["table"], "id": j})
+                case "json":
+                    click.echo(
+                        click.style(
+                            (
+                                f"- Listing file-id-like JSON string in column {ids_table['column']} "
+                                f"in table {ids_table['table']}"
+                            ),
+                            fg="white",
+                        )
+                    )
+                    query = (
+                        f"SELECT regexp_matches({ids_table['column']}::text, '{guid_regexp}', 'g') AS extracted_id "
+                        f"FROM {ids_table['table']}"
+                    )
+                    with db.engine.begin() as conn:
+                        rs = conn.execute(sa.text(query))
+                    for i in rs:
+                        for j in i[0]:
+                            all_ids_in_tables.append({"table": ids_table["table"], "id": j})
+                case _:
+                    pass
+        click.echo(click.style(f"Found {len(all_ids_in_tables)} file ids in tables.", fg="white"))
+
+    except Exception as e:
+        click.echo(click.style(f"Error fetching keys: {str(e)}", fg="red"))
+        return
+
+    # find orphaned files
+    all_files = [file["id"] for file in all_files_in_tables]
+    all_ids = [file["id"] for file in all_ids_in_tables]
+    orphaned_files = list(set(all_files) - set(all_ids))
+    if not orphaned_files:
+        click.echo(click.style("No orphaned file records found. There is nothing to delete.", fg="green"))
+        return
+    click.echo(click.style(f"Found {len(orphaned_files)} orphaned file records.", fg="white"))
+    for file in orphaned_files:
+        click.echo(click.style(f"- orphaned file id: {file}", fg="black"))
+    if not force:
+        click.confirm(f"Do you want to proceed to delete all {len(orphaned_files)} orphaned file records?", abort=True)
+
+    # delete orphaned records for each file
+    try:
+        for files_table in files_tables:
+            click.echo(click.style(f"- Deleting orphaned file records in table {files_table['table']}", fg="white"))
+            query = f"DELETE FROM {files_table['table']} WHERE {files_table['id_column']} IN :ids"
+            with db.engine.begin() as conn:
+                conn.execute(sa.text(query), {"ids": tuple(orphaned_files)})
+    except Exception as e:
+        click.echo(click.style(f"Error deleting orphaned file records: {str(e)}", fg="red"))
+        return
+    click.echo(click.style(f"Removed {len(orphaned_files)} orphaned file records.", fg="green"))
+
+
+@click.option("-f", "--force", is_flag=True, help="Skip user confirmation and force the command to execute.")
+@click.command("remove-orphaned-files-on-storage", help="Remove orphaned files on the storage.")
+def remove_orphaned_files_on_storage(force: bool):
+    """
+    Remove orphaned files on the storage.
+    """
+
+    # define tables and columns to process
+    files_tables = [
+        {"table": "upload_files", "key_column": "key"},
+        {"table": "tool_files", "key_column": "file_key"},
+    ]
+    storage_paths = ["image_files", "tools", "upload_files"]
+
+    # notify user and ask for confirmation
+    click.echo(click.style("This command will find and remove orphaned files on the storage,", fg="yellow"))
+    click.echo(
+        click.style("by comparing the files on the storage with the records in the following tables:", fg="yellow")
+    )
+    for files_table in files_tables:
+        click.echo(click.style(f"- {files_table['table']}", fg="yellow"))
+    click.echo(click.style("The following paths on the storage will be scanned to find orphaned files:", fg="yellow"))
+    for storage_path in storage_paths:
+        click.echo(click.style(f"- {storage_path}", fg="yellow"))
+    click.echo("")
+
+    click.echo(click.style("!!! USE WITH CAUTION !!!", fg="red"))
+    click.echo(
+        click.style(
+            "Currently, this command will work only for opendal based storage (STORAGE_TYPE=opendal).", fg="yellow"
+        )
+    )
+    click.echo(
+        click.style(
+            "Since not all patterns have been fully tested, please note that this command may delete unintended files.",
+            fg="yellow",
+        )
+    )
+    click.echo(
+        click.style("This cannot be undone. Please make sure to back up your storage before proceeding.", fg="yellow")
+    )
+    click.echo(
+        click.style(
+            (
+                "It is also recommended to run this during the maintenance window, "
+                "as this may cause high load on your instance."
+            ),
+            fg="yellow",
+        )
+    )
+    if not force:
+        click.confirm("Do you want to proceed?", abort=True)
+
+    # start the cleanup process
+    click.echo(click.style("Starting orphaned files cleanup.", fg="white"))
+
+    # fetch file id and keys from each table
+    all_files_in_tables = []
+    try:
+        for files_table in files_tables:
+            click.echo(click.style(f"- Listing files from table {files_table['table']}", fg="white"))
+            query = f"SELECT {files_table['key_column']} FROM {files_table['table']}"
+            with db.engine.begin() as conn:
+                rs = conn.execute(sa.text(query))
+            for i in rs:
+                all_files_in_tables.append(str(i[0]))
+        click.echo(click.style(f"Found {len(all_files_in_tables)} files in tables.", fg="white"))
+    except Exception as e:
+        click.echo(click.style(f"Error fetching keys: {str(e)}", fg="red"))
+        return
+
+    all_files_on_storage = []
+    for storage_path in storage_paths:
+        try:
+            click.echo(click.style(f"- Scanning files on storage path {storage_path}", fg="white"))
+            files = storage.scan(path=storage_path, files=True, directories=False)
+            all_files_on_storage.extend(files)
+        except FileNotFoundError:
+            click.echo(click.style(f"  -> Skipping path {storage_path} as it does not exist.", fg="yellow"))
+            continue
+        except Exception as e:
+            click.echo(click.style(f"  -> Error scanning files on storage path {storage_path}: {str(e)}", fg="red"))
+            continue
+    click.echo(click.style(f"Found {len(all_files_on_storage)} files on storage.", fg="white"))
+
+    # find orphaned files
+    orphaned_files = list(set(all_files_on_storage) - set(all_files_in_tables))
+    if not orphaned_files:
+        click.echo(click.style("No orphaned files found. There is nothing to remove.", fg="green"))
+        return
+    click.echo(click.style(f"Found {len(orphaned_files)} orphaned files.", fg="white"))
+    for file in orphaned_files:
+        click.echo(click.style(f"- orphaned file: {file}", fg="black"))
+    if not force:
+        click.confirm(f"Do you want to proceed to remove all {len(orphaned_files)} orphaned files?", abort=True)
+
+    # delete orphaned files
+    removed_files = 0
+    error_files = 0
+    for file in orphaned_files:
+        try:
+            storage.delete(file)
+            removed_files += 1
+            click.echo(click.style(f"- Removing orphaned file: {file}", fg="white"))
+        except Exception as e:
+            error_files += 1
+            click.echo(click.style(f"- Error deleting orphaned file {file}: {str(e)}", fg="red"))
+            continue
+    if error_files == 0:
+        click.echo(click.style(f"Removed {removed_files} orphaned files without errors.", fg="green"))
+    else:
+        click.echo(click.style(f"Removed {removed_files} orphaned files, with {error_files} errors.", fg="yellow"))
+
+
+@click.command("file-usage", help="Query file usages and show where files are referenced.")
+@click.option("--file-id", type=str, default=None, help="Filter by file UUID.")
+@click.option("--key", type=str, default=None, help="Filter by storage key.")
+@click.option("--src", type=str, default=None, help="Filter by table.column pattern (e.g., 'documents.%' or '%.icon').")
+@click.option("--limit", type=int, default=100, help="Limit number of results (default: 100).")
+@click.option("--offset", type=int, default=0, help="Offset for pagination (default: 0).")
+@click.option("--json", "output_json", is_flag=True, help="Output results in JSON format.")
+def file_usage(
+    file_id: str | None,
+    key: str | None,
+    src: str | None,
+    limit: int,
+    offset: int,
+    output_json: bool,
+):
+    """
+    Query file usages and show where files are referenced in the database.
+
+    This command reuses the same reference checking logic as clear-orphaned-file-records
+    and displays detailed information about where each file is referenced.
+    """
+    # define tables and columns to process
+    files_tables = [
+        {"table": "upload_files", "id_column": "id", "key_column": "key"},
+        {"table": "tool_files", "id_column": "id", "key_column": "file_key"},
+    ]
+    ids_tables = [
+        {"type": "uuid", "table": "message_files", "column": "upload_file_id", "pk_column": "id"},
+        {"type": "text", "table": "documents", "column": "data_source_info", "pk_column": "id"},
+        {"type": "text", "table": "document_segments", "column": "content", "pk_column": "id"},
+        {"type": "text", "table": "messages", "column": "answer", "pk_column": "id"},
+        {"type": "text", "table": "workflow_node_executions", "column": "inputs", "pk_column": "id"},
+        {"type": "text", "table": "workflow_node_executions", "column": "process_data", "pk_column": "id"},
+        {"type": "text", "table": "workflow_node_executions", "column": "outputs", "pk_column": "id"},
+        {"type": "text", "table": "conversations", "column": "introduction", "pk_column": "id"},
+        {"type": "text", "table": "conversations", "column": "system_instruction", "pk_column": "id"},
+        {"type": "text", "table": "accounts", "column": "avatar", "pk_column": "id"},
+        {"type": "text", "table": "apps", "column": "icon", "pk_column": "id"},
+        {"type": "text", "table": "sites", "column": "icon", "pk_column": "id"},
+        {"type": "json", "table": "messages", "column": "inputs", "pk_column": "id"},
+        {"type": "json", "table": "messages", "column": "message", "pk_column": "id"},
+    ]
+
+    # Stream file usages with pagination to avoid holding all results in memory
+    paginated_usages = []
+    total_count = 0
+
+    # First, build a mapping of file_id -> storage_key from the base tables
+    file_key_map = {}
+    for files_table in files_tables:
+        query = f"SELECT {files_table['id_column']}, {files_table['key_column']} FROM {files_table['table']}"
+        with db.engine.begin() as conn:
+            rs = conn.execute(sa.text(query))
+            for row in rs:
+                file_key_map[str(row[0])] = f"{files_table['table']}:{row[1]}"
+
+    # If filtering by key or file_id, verify it exists
+    if file_id and file_id not in file_key_map:
+        if output_json:
+            click.echo(json.dumps({"error": f"File ID {file_id} not found in base tables"}))
+        else:
+            click.echo(click.style(f"File ID {file_id} not found in base tables.", fg="red"))
+        return
+
+    if key:
+        valid_prefixes = {f"upload_files:{key}", f"tool_files:{key}"}
+        matching_file_ids = [fid for fid, fkey in file_key_map.items() if fkey in valid_prefixes]
+        if not matching_file_ids:
+            if output_json:
+                click.echo(json.dumps({"error": f"Key {key} not found in base tables"}))
+            else:
+                click.echo(click.style(f"Key {key} not found in base tables.", fg="red"))
+            return
+
+    guid_regexp = "[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{12}"
+
+    # For each reference table/column, find matching file IDs and record the references
+    for ids_table in ids_tables:
+        src_filter = f"{ids_table['table']}.{ids_table['column']}"
+
+        # Skip if src filter doesn't match (use fnmatch for wildcard patterns)
+        if src:
+            if "%" in src or "_" in src:
+                import fnmatch
+
+                # Convert SQL LIKE wildcards to fnmatch wildcards (% -> *, _ -> ?)
+                pattern = src.replace("%", "*").replace("_", "?")
+                if not fnmatch.fnmatch(src_filter, pattern):
+                    continue
+            else:
+                if src_filter != src:
+                    continue
+
+        match ids_table["type"]:
+            case "uuid":
+                # Direct UUID match
+                query = (
+                    f"SELECT {ids_table['pk_column']}, {ids_table['column']} "
+                    f"FROM {ids_table['table']} WHERE {ids_table['column']} IS NOT NULL"
+                )
+                with db.engine.begin() as conn:
+                    rs = conn.execute(sa.text(query))
+                    for row in rs:
+                        record_id = str(row[0])
+                        ref_file_id = str(row[1])
+                        if ref_file_id not in file_key_map:
+                            continue
+                        storage_key = file_key_map[ref_file_id]
+
+                        # Apply filters
+                        if file_id and ref_file_id != file_id:
+                            continue
+                        if key and not storage_key.endswith(key):
+                            continue
+
+                        # Only collect items within the requested page range
+                        if offset <= total_count < offset + limit:
+                            paginated_usages.append(
+                                {
+                                    "src": f"{ids_table['table']}.{ids_table['column']}",
+                                    "record_id": record_id,
+                                    "file_id": ref_file_id,
+                                    "key": storage_key,
+                                }
+                            )
+                        total_count += 1
+
+            case "text" | "json":
+                # Extract UUIDs from text/json content
+                column_cast = f"{ids_table['column']}::text" if ids_table["type"] == "json" else ids_table["column"]
+                query = (
+                    f"SELECT {ids_table['pk_column']}, {column_cast} "
+                    f"FROM {ids_table['table']} WHERE {ids_table['column']} IS NOT NULL"
+                )
+                with db.engine.begin() as conn:
+                    rs = conn.execute(sa.text(query))
+                    for row in rs:
+                        record_id = str(row[0])
+                        content = str(row[1])
+
+                        # Find all UUIDs in the content
+                        import re
+
+                        uuid_pattern = re.compile(guid_regexp, re.IGNORECASE)
+                        matches = uuid_pattern.findall(content)
+
+                        for ref_file_id in matches:
+                            if ref_file_id not in file_key_map:
+                                continue
+                            storage_key = file_key_map[ref_file_id]
+
+                            # Apply filters
+                            if file_id and ref_file_id != file_id:
+                                continue
+                            if key and not storage_key.endswith(key):
+                                continue
+
+                            # Only collect items within the requested page range
+                            if offset <= total_count < offset + limit:
+                                paginated_usages.append(
+                                    {
+                                        "src": f"{ids_table['table']}.{ids_table['column']}",
+                                        "record_id": record_id,
+                                        "file_id": ref_file_id,
+                                        "key": storage_key,
+                                    }
+                                )
+                            total_count += 1
+            case _:
+                pass
+
+    # Output results
+    if output_json:
+        result = {
+            "total": total_count,
+            "offset": offset,
+            "limit": limit,
+            "usages": paginated_usages,
+        }
+        click.echo(json.dumps(result, indent=2))
+    else:
+        click.echo(
+            click.style(f"Found {total_count} file usages (showing {len(paginated_usages)} results)", fg="white")
+        )
+        click.echo("")
+
+        if not paginated_usages:
+            click.echo(click.style("No file usages found matching the specified criteria.", fg="yellow"))
+            return
+
+        # Print table header
+        click.echo(
+            click.style(
+                f"{'Src (Table.Column)':<50} {'Record ID':<40} {'File ID':<40} {'Storage Key':<60}",
+                fg="cyan",
+            )
+        )
+        click.echo(click.style("-" * 190, fg="white"))
+
+        # Print each usage
+        for usage in paginated_usages:
+            click.echo(f"{usage['src']:<50} {usage['record_id']:<40} {usage['file_id']:<40} {usage['key']:<60}")
+
+        # Show pagination info
+        if offset + limit < total_count:
+            click.echo("")
+            click.echo(
+                click.style(
+                    f"Showing {offset + 1}-{offset + len(paginated_usages)} of {total_count} results", fg="white"
+                )
+            )
+            click.echo(click.style(f"Use --offset {offset + limit} to see next page", fg="white"))
+
+
+@click.command(
+    "migrate-oss",
+    help="Migrate files from Local or OpenDAL source to a cloud OSS storage (destination must NOT be local/opendal).",
+)
+@click.option(
+    "--path",
+    "paths",
+    multiple=True,
+    help="Storage path prefixes to migrate (repeatable). Defaults: privkeys, upload_files, image_files,"
+    " tools, website_files, keyword_files, ops_trace",
+)
+@click.option(
+    "--source",
+    type=click.Choice(["local", "opendal"], case_sensitive=False),
+    default="opendal",
+    show_default=True,
+    help="Source storage type to read from",
+)
+@click.option("--overwrite", is_flag=True, default=False, help="Overwrite destination if file already exists")
+@click.option("--dry-run", is_flag=True, default=False, help="Show what would be migrated without uploading")
+@click.option("-f", "--force", is_flag=True, help="Skip confirmation and run without prompts")
+@click.option(
+    "--update-db/--no-update-db",
+    default=True,
+    help="Update upload_files.storage_type from source type to current storage after migration",
+)
+def migrate_oss(
+    paths: tuple[str, ...],
+    source: str,
+    overwrite: bool,
+    dry_run: bool,
+    force: bool,
+    update_db: bool,
+):
+    """
+    Copy all files under selected prefixes from a source storage
+    (Local filesystem or OpenDAL-backed) into the currently configured
+    destination storage backend, then optionally update DB records.
+
+    Expected usage: set STORAGE_TYPE (and its credentials) to your target backend.
+    """
+    # Ensure target storage is not local/opendal
+    if dify_config.STORAGE_TYPE in (StorageType.LOCAL, StorageType.OPENDAL):
+        click.echo(
+            click.style(
+                "Target STORAGE_TYPE must be a cloud OSS (not 'local' or 'opendal').\n"
+                "Please set STORAGE_TYPE to one of: s3, aliyun-oss, azure-blob, google-storage, tencent-cos, \n"
+                "volcengine-tos, supabase, oci-storage, huawei-obs, baidu-obs, clickzetta-volume.",
+                fg="red",
+            )
+        )
+        return
+
+    # Default paths if none specified
+    default_paths = ("privkeys", "upload_files", "image_files", "tools", "website_files", "keyword_files", "ops_trace")
+    path_list = list(paths) if paths else list(default_paths)
+    is_source_local = source.lower() == "local"
+
+    click.echo(click.style("Preparing migration to target storage.", fg="yellow"))
+    click.echo(click.style(f"Target storage type: {dify_config.STORAGE_TYPE}", fg="white"))
+    if is_source_local:
+        src_root = dify_config.STORAGE_LOCAL_PATH
+        click.echo(click.style(f"Source: local fs, root: {src_root}", fg="white"))
+    else:
+        click.echo(click.style(f"Source: opendal scheme={dify_config.OPENDAL_SCHEME}", fg="white"))
+    click.echo(click.style(f"Paths to migrate: {', '.join(path_list)}", fg="white"))
+    click.echo("")
+
+    if not force:
+        click.confirm("Proceed with migration?", abort=True)
+
+    # Instantiate source storage
+    try:
+        if is_source_local:
+            src_root = dify_config.STORAGE_LOCAL_PATH
+            source_storage = OpenDALStorage(scheme="fs", root=src_root)
+        else:
+            source_storage = OpenDALStorage(scheme=dify_config.OPENDAL_SCHEME)
+    except Exception as e:
+        click.echo(click.style(f"Failed to initialize source storage: {str(e)}", fg="red"))
+        return
+
+    total_files = 0
+    copied_files = 0
+    skipped_files = 0
+    errored_files = 0
+    copied_upload_file_keys: list[str] = []
+
+    for prefix in path_list:
+        click.echo(click.style(f"Scanning source path: {prefix}", fg="white"))
+        try:
+            keys = source_storage.scan(path=prefix, files=True, directories=False)
+        except FileNotFoundError:
+            click.echo(click.style(f"  -> Skipping missing path: {prefix}", fg="yellow"))
+            continue
+        except NotImplementedError:
+            click.echo(click.style("  -> Source storage does not support scanning.", fg="red"))
+            return
+        except Exception as e:
+            click.echo(click.style(f"  -> Error scanning '{prefix}': {str(e)}", fg="red"))
+            continue
+
+        click.echo(click.style(f"Found {len(keys)} files under {prefix}", fg="white"))
+
+        for key in keys:
+            total_files += 1
+
+            # check destination existence
+            if not overwrite:
+                try:
+                    if storage.exists(key):
+                        skipped_files += 1
+                        continue
+                except Exception as e:
+                    # existence check failures should not block migration attempt
+                    # but should be surfaced to user as a warning for visibility
+                    click.echo(
+                        click.style(
+                            f"  -> Warning: failed target existence check for {key}: {str(e)}",
+                            fg="yellow",
+                        )
+                    )
+
+            if dry_run:
+                copied_files += 1
+                continue
+
+            # read from source and write to destination
+            try:
+                data = source_storage.load_once(key)
+            except FileNotFoundError:
+                errored_files += 1
+                click.echo(click.style(f"  -> Missing on source: {key}", fg="yellow"))
+                continue
+            except Exception as e:
+                errored_files += 1
+                click.echo(click.style(f"  -> Error reading {key}: {str(e)}", fg="red"))
+                continue
+
+            try:
+                storage.save(key, data)
+                copied_files += 1
+                if prefix == "upload_files":
+                    copied_upload_file_keys.append(key)
+            except Exception as e:
+                errored_files += 1
+                click.echo(click.style(f"  -> Error writing {key} to target: {str(e)}", fg="red"))
+                continue
+
+    click.echo("")
+    click.echo(click.style("Migration summary:", fg="yellow"))
+    click.echo(click.style(f"  Total:   {total_files}", fg="white"))
+    click.echo(click.style(f"  Copied:  {copied_files}", fg="green"))
+    click.echo(click.style(f"  Skipped: {skipped_files}", fg="white"))
+    if errored_files:
+        click.echo(click.style(f"  Errors:  {errored_files}", fg="red"))
+
+    if dry_run:
+        click.echo(click.style("Dry-run complete. No changes were made.", fg="green"))
+        return
+
+    if errored_files:
+        click.echo(
+            click.style(
+                "Some files failed to migrate. Review errors above before updating DB records.",
+                fg="yellow",
+            )
+        )
+        if update_db and not force:
+            if not click.confirm("Proceed to update DB storage_type despite errors?", default=False):
+                update_db = False
+
+    # Optionally update DB records for upload_files.storage_type (only for successfully copied upload_files)
+    if update_db:
+        if not copied_upload_file_keys:
+            click.echo(click.style("No upload_files copied. Skipping DB storage_type update.", fg="yellow"))
+        else:
+            try:
+                source_storage_type = StorageType.LOCAL if is_source_local else StorageType.OPENDAL
+                updated = (
+                    db.session.query(UploadFile)
+                    .where(
+                        UploadFile.storage_type == source_storage_type,
+                        UploadFile.key.in_(copied_upload_file_keys),
+                    )
+                    .update({UploadFile.storage_type: dify_config.STORAGE_TYPE}, synchronize_session=False)
+                )
+                db.session.commit()
+                click.echo(click.style(f"Updated storage_type for {updated} upload_files records.", fg="green"))
+            except Exception as e:
+                db.session.rollback()
+                click.echo(click.style(f"Failed to update DB storage_type: {str(e)}", fg="red"))

api/commands/system.py

@@ -0,0 +1,204 @@
+import logging
+
+import click
+import sqlalchemy as sa
+from sqlalchemy.orm import sessionmaker
+
+from configs import dify_config
+from events.app_event import app_was_created
+from extensions.ext_database import db
+from extensions.ext_redis import redis_client
+from libs.db_migration_lock import DbMigrationAutoRenewLock
+from libs.rsa import generate_key_pair
+from models import Tenant
+from models.model import App, AppMode, Conversation
+from models.provider import Provider, ProviderModel
+
+logger = logging.getLogger(__name__)
+
+DB_UPGRADE_LOCK_TTL_SECONDS = 60
+
+
+@click.command(
+    "reset-encrypt-key-pair",
+    help="Reset the asymmetric key pair of workspace for encrypt LLM credentials. "
+    "After the reset, all LLM credentials will become invalid, "
+    "requiring re-entry."
+    "Only support SELF_HOSTED mode.",
+)
+@click.confirmation_option(
+    prompt=click.style(
+        "Are you sure you want to reset encrypt key pair? This operation cannot be rolled back!", fg="red"
+    )
+)
+def reset_encrypt_key_pair():
+    """
+    Reset the encrypted key pair of workspace for encrypt LLM credentials.
+    After the reset, all LLM credentials will become invalid, requiring re-entry.
+    Only support SELF_HOSTED mode.
+    """
+    if dify_config.EDITION != "SELF_HOSTED":
+        click.echo(click.style("This command is only for SELF_HOSTED installations.", fg="red"))
+        return
+    with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
+        tenants = session.query(Tenant).all()
+        for tenant in tenants:
+            if not tenant:
+                click.echo(click.style("No workspaces found. Run /install first.", fg="red"))
+                return
+
+            tenant.encrypt_public_key = generate_key_pair(tenant.id)
+
+            session.query(Provider).where(Provider.provider_type == "custom", Provider.tenant_id == tenant.id).delete()
+            session.query(ProviderModel).where(ProviderModel.tenant_id == tenant.id).delete()
+
+            click.echo(
+                click.style(
+                    f"Congratulations! The asymmetric key pair of workspace {tenant.id} has been reset.",
+                    fg="green",
+                )
+            )
+
+
+@click.command("convert-to-agent-apps", help="Convert Agent Assistant to Agent App.")
+def convert_to_agent_apps():
+    """
+    Convert Agent Assistant to Agent App.
+    """
+    click.echo(click.style("Starting convert to agent apps.", fg="green"))
+
+    proceeded_app_ids = []
+
+    while True:
+        # fetch first 1000 apps
+        sql_query = """SELECT a.id AS id FROM apps a
+            INNER JOIN app_model_configs am ON a.app_model_config_id=am.id
+            WHERE a.mode = 'chat'
+            AND am.agent_mode is not null
+            AND (
+                am.agent_mode like '%"strategy": "function_call"%'
+                OR am.agent_mode  like '%"strategy": "react"%'
+            )
+            AND (
+                am.agent_mode like '{"enabled": true%'
+                OR am.agent_mode like '{"max_iteration": %'
+            ) ORDER BY a.created_at DESC LIMIT 1000
+        """
+
+        with db.engine.begin() as conn:
+            rs = conn.execute(sa.text(sql_query))
+
+            apps = []
+            for i in rs:
+                app_id = str(i.id)
+                if app_id not in proceeded_app_ids:
+                    proceeded_app_ids.append(app_id)
+                    app = db.session.query(App).where(App.id == app_id).first()
+                    if app is not None:
+                        apps.append(app)
+
+            if len(apps) == 0:
+                break
+
+        for app in apps:
+            click.echo(f"Converting app: {app.id}")
+
+            try:
+                app.mode = AppMode.AGENT_CHAT
+                db.session.commit()
+
+                # update conversation mode to agent
+                db.session.query(Conversation).where(Conversation.app_id == app.id).update(
+                    {Conversation.mode: AppMode.AGENT_CHAT}
+                )
+
+                db.session.commit()
+                click.echo(click.style(f"Converted app: {app.id}", fg="green"))
+            except Exception as e:
+                click.echo(click.style(f"Convert app error: {e.__class__.__name__} {str(e)}", fg="red"))
+
+    click.echo(click.style(f"Conversion complete. Converted {len(proceeded_app_ids)} agent apps.", fg="green"))
+
+
+@click.command("upgrade-db", help="Upgrade the database")
+def upgrade_db():
+    click.echo("Preparing database migration...")
+    lock = DbMigrationAutoRenewLock(
+        redis_client=redis_client,
+        name="db_upgrade_lock",
+        ttl_seconds=DB_UPGRADE_LOCK_TTL_SECONDS,
+        logger=logger,
+        log_context="db_migration",
+    )
+    if lock.acquire(blocking=False):
+        migration_succeeded = False
+        try:
+            click.echo(click.style("Starting database migration.", fg="green"))
+
+            # run db migration
+            import flask_migrate
+
+            flask_migrate.upgrade()
+
+            migration_succeeded = True
+            click.echo(click.style("Database migration successful!", fg="green"))
+
+        except Exception as e:
+            logger.exception("Failed to execute database migration")
+            click.echo(click.style(f"Database migration failed: {e}", fg="red"))
+            raise SystemExit(1)
+        finally:
+            status = "successful" if migration_succeeded else "failed"
+            lock.release_safely(status=status)
+    else:
+        click.echo("Database migration skipped")
+
+
+@click.command("fix-app-site-missing", help="Fix app related site missing issue.")
+def fix_app_site_missing():
+    """
+    Fix app related site missing issue.
+    """
+    click.echo(click.style("Starting fix for missing app-related sites.", fg="green"))
+
+    failed_app_ids = []
+    while True:
+        sql = """select apps.id as id from apps left join sites on sites.app_id=apps.id
+where sites.id is null limit 1000"""
+        with db.engine.begin() as conn:
+            rs = conn.execute(sa.text(sql))
+
+            processed_count = 0
+            for i in rs:
+                processed_count += 1
+                app_id = str(i.id)
+
+                if app_id in failed_app_ids:
+                    continue
+
+                try:
+                    app = db.session.query(App).where(App.id == app_id).first()
+                    if not app:
+                        logger.info("App %s not found", app_id)
+                        continue
+
+                    tenant = app.tenant
+                    if tenant:
+                        accounts = tenant.get_accounts()
+                        if not accounts:
+                            logger.info("Fix failed for app %s", app.id)
+                            continue
+
+                        account = accounts[0]
+                        logger.info("Fixing missing site for app %s", app.id)
+                        app_was_created.send(app, account=account)
+                except Exception:
+                    failed_app_ids.append(app_id)
+                    click.echo(click.style(f"Failed to fix missing site for app {app_id}", fg="red"))
+                    logger.exception("Failed to fix app related site missing issue, app_id: %s", app_id)
+                    continue
+
+            if not processed_count:
+                break
+
+    click.echo(click.style("Fix for missing app-related sites completed successfully!", fg="green"))

api/commands/vector.py

@@ -0,0 +1,466 @@
+import json
+
+import click
+from flask import current_app
+from sqlalchemy import select
+from sqlalchemy.exc import SQLAlchemyError
+from sqlalchemy.orm import sessionmaker
+
+from configs import dify_config
+from core.rag.datasource.vdb.vector_factory import Vector
+from core.rag.datasource.vdb.vector_type import VectorType
+from core.rag.index_processor.constant.built_in_field import BuiltInField
+from core.rag.models.document import ChildDocument, Document
+from extensions.ext_database import db
+from models.dataset import Dataset, DatasetCollectionBinding, DatasetMetadata, DatasetMetadataBinding, DocumentSegment
+from models.dataset import Document as DatasetDocument
+from models.model import App, AppAnnotationSetting, MessageAnnotation
+
+
+@click.command("vdb-migrate", help="Migrate vector db.")
+@click.option("--scope", default="all", prompt=False, help="The scope of vector database to migrate, Default is All.")
+def vdb_migrate(scope: str):
+    if scope in {"knowledge", "all"}:
+        migrate_knowledge_vector_database()
+    if scope in {"annotation", "all"}:
+        migrate_annotation_vector_database()
+
+
+def migrate_annotation_vector_database():
+    """
+    Migrate annotation datas to target vector database .
+    """
+    click.echo(click.style("Starting annotation data migration.", fg="green"))
+    create_count = 0
+    skipped_count = 0
+    total_count = 0
+    page = 1
+    while True:
+        try:
+            # get apps info
+            per_page = 50
+            with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
+                apps = (
+                    session.query(App)
+                    .where(App.status == "normal")
+                    .order_by(App.created_at.desc())
+                    .limit(per_page)
+                    .offset((page - 1) * per_page)
+                    .all()
+                )
+            if not apps:
+                break
+        except SQLAlchemyError:
+            raise
+
+        page += 1
+        for app in apps:
+            total_count = total_count + 1
+            click.echo(
+                f"Processing the {total_count} app {app.id}. " + f"{create_count} created, {skipped_count} skipped."
+            )
+            try:
+                click.echo(f"Creating app annotation index: {app.id}")
+                with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
+                    app_annotation_setting = (
+                        session.query(AppAnnotationSetting).where(AppAnnotationSetting.app_id == app.id).first()
+                    )
+
+                    if not app_annotation_setting:
+                        skipped_count = skipped_count + 1
+                        click.echo(f"App annotation setting disabled: {app.id}")
+                        continue
+                    # get dataset_collection_binding info
+                    dataset_collection_binding = (
+                        session.query(DatasetCollectionBinding)
+                        .where(DatasetCollectionBinding.id == app_annotation_setting.collection_binding_id)
+                        .first()
+                    )
+                    if not dataset_collection_binding:
+                        click.echo(f"App annotation collection binding not found: {app.id}")
+                        continue
+                    annotations = session.scalars(
+                        select(MessageAnnotation).where(MessageAnnotation.app_id == app.id)
+                    ).all()
+                dataset = Dataset(
+                    id=app.id,
+                    tenant_id=app.tenant_id,
+                    indexing_technique="high_quality",
+                    embedding_model_provider=dataset_collection_binding.provider_name,
+                    embedding_model=dataset_collection_binding.model_name,
+                    collection_binding_id=dataset_collection_binding.id,
+                )
+                documents = []
+                if annotations:
+                    for annotation in annotations:
+                        document = Document(
+                            page_content=annotation.question_text,
+                            metadata={"annotation_id": annotation.id, "app_id": app.id, "doc_id": annotation.id},
+                        )
+                        documents.append(document)
+
+                vector = Vector(dataset, attributes=["doc_id", "annotation_id", "app_id"])
+                click.echo(f"Migrating annotations for app: {app.id}.")
+
+                try:
+                    vector.delete()
+                    click.echo(click.style(f"Deleted vector index for app {app.id}.", fg="green"))
+                except Exception as e:
+                    click.echo(click.style(f"Failed to delete vector index for app {app.id}.", fg="red"))
+                    raise e
+                if documents:
+                    try:
+                        click.echo(
+                            click.style(
+                                f"Creating vector index with {len(documents)} annotations for app {app.id}.",
+                                fg="green",
+                            )
+                        )
+                        vector.create(documents)
+                        click.echo(click.style(f"Created vector index for app {app.id}.", fg="green"))
+                    except Exception as e:
+                        click.echo(click.style(f"Failed to created vector index for app {app.id}.", fg="red"))
+                        raise e
+                click.echo(f"Successfully migrated app annotation {app.id}.")
+                create_count += 1
+            except Exception as e:
+                click.echo(
+                    click.style(f"Error creating app annotation index: {e.__class__.__name__} {str(e)}", fg="red")
+                )
+                continue
+
+    click.echo(
+        click.style(
+            f"Migration complete. Created {create_count} app annotation indexes. Skipped {skipped_count} apps.",
+            fg="green",
+        )
+    )
+
+
+def migrate_knowledge_vector_database():
+    """
+    Migrate vector database datas to target vector database .
+    """
+    click.echo(click.style("Starting vector database migration.", fg="green"))
+    create_count = 0
+    skipped_count = 0
+    total_count = 0
+    vector_type = dify_config.VECTOR_STORE
+    upper_collection_vector_types = {
+        VectorType.MILVUS,
+        VectorType.PGVECTOR,
+        VectorType.VASTBASE,
+        VectorType.RELYT,
+        VectorType.WEAVIATE,
+        VectorType.ORACLE,
+        VectorType.ELASTICSEARCH,
+        VectorType.OPENGAUSS,
+        VectorType.TABLESTORE,
+        VectorType.MATRIXONE,
+    }
+    lower_collection_vector_types = {
+        VectorType.ANALYTICDB,
+        VectorType.CHROMA,
+        VectorType.MYSCALE,
+        VectorType.PGVECTO_RS,
+        VectorType.TIDB_VECTOR,
+        VectorType.OPENSEARCH,
+        VectorType.TENCENT,
+        VectorType.BAIDU,
+        VectorType.VIKINGDB,
+        VectorType.UPSTASH,
+        VectorType.COUCHBASE,
+        VectorType.OCEANBASE,
+    }
+    page = 1
+    while True:
+        try:
+            stmt = (
+                select(Dataset).where(Dataset.indexing_technique == "high_quality").order_by(Dataset.created_at.desc())
+            )
+
+            datasets = db.paginate(select=stmt, page=page, per_page=50, max_per_page=50, error_out=False)
+            if not datasets.items:
+                break
+        except SQLAlchemyError:
+            raise
+
+        page += 1
+        for dataset in datasets:
+            total_count = total_count + 1
+            click.echo(
+                f"Processing the {total_count} dataset {dataset.id}. {create_count} created, {skipped_count} skipped."
+            )
+            try:
+                click.echo(f"Creating dataset vector database index: {dataset.id}")
+                if dataset.index_struct_dict:
+                    if dataset.index_struct_dict["type"] == vector_type:
+                        skipped_count = skipped_count + 1
+                        continue
+                collection_name = ""
+                dataset_id = dataset.id
+                if vector_type in upper_collection_vector_types:
+                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
+                elif vector_type == VectorType.QDRANT:
+                    if dataset.collection_binding_id:
+                        dataset_collection_binding = (
+                            db.session.query(DatasetCollectionBinding)
+                            .where(DatasetCollectionBinding.id == dataset.collection_binding_id)
+                            .one_or_none()
+                        )
+                        if dataset_collection_binding:
+                            collection_name = dataset_collection_binding.collection_name
+                        else:
+                            raise ValueError("Dataset Collection Binding not found")
+                    else:
+                        collection_name = Dataset.gen_collection_name_by_id(dataset_id)
+
+                elif vector_type in lower_collection_vector_types:
+                    collection_name = Dataset.gen_collection_name_by_id(dataset_id).lower()
+                else:
+                    raise ValueError(f"Vector store {vector_type} is not supported.")
+
+                index_struct_dict = {"type": vector_type, "vector_store": {"class_prefix": collection_name}}
+                dataset.index_struct = json.dumps(index_struct_dict)
+                vector = Vector(dataset)
+                click.echo(f"Migrating dataset {dataset.id}.")
+
+                try:
+                    vector.delete()
+                    click.echo(
+                        click.style(f"Deleted vector index {collection_name} for dataset {dataset.id}.", fg="green")
+                    )
+                except Exception as e:
+                    click.echo(
+                        click.style(
+                            f"Failed to delete vector index {collection_name} for dataset {dataset.id}.", fg="red"
+                        )
+                    )
+                    raise e
+
+                dataset_documents = db.session.scalars(
+                    select(DatasetDocument).where(
+                        DatasetDocument.dataset_id == dataset.id,
+                        DatasetDocument.indexing_status == "completed",
+                        DatasetDocument.enabled == True,
+                        DatasetDocument.archived == False,
+                    )
+                ).all()
+
+                documents = []
+                segments_count = 0
+                for dataset_document in dataset_documents:
+                    segments = db.session.scalars(
+                        select(DocumentSegment).where(
+                            DocumentSegment.document_id == dataset_document.id,
+                            DocumentSegment.status == "completed",
+                            DocumentSegment.enabled == True,
+                        )
+                    ).all()
+
+                    for segment in segments:
+                        document = Document(
+                            page_content=segment.content,
+                            metadata={
+                                "doc_id": segment.index_node_id,
+                                "doc_hash": segment.index_node_hash,
+                                "document_id": segment.document_id,
+                                "dataset_id": segment.dataset_id,
+                            },
+                        )
+                        if dataset_document.doc_form == "hierarchical_model":
+                            child_chunks = segment.get_child_chunks()
+                            if child_chunks:
+                                child_documents = []
+                                for child_chunk in child_chunks:
+                                    child_document = ChildDocument(
+                                        page_content=child_chunk.content,
+                                        metadata={
+                                            "doc_id": child_chunk.index_node_id,
+                                            "doc_hash": child_chunk.index_node_hash,
+                                            "document_id": segment.document_id,
+                                            "dataset_id": segment.dataset_id,
+                                        },
+                                    )
+                                    child_documents.append(child_document)
+                                document.children = child_documents
+
+                        documents.append(document)
+                        segments_count = segments_count + 1
+
+                if documents:
+                    try:
+                        click.echo(
+                            click.style(
+                                f"Creating vector index with {len(documents)} documents of {segments_count}"
+                                f" segments for dataset {dataset.id}.",
+                                fg="green",
+                            )
+                        )
+                        all_child_documents = []
+                        for doc in documents:
+                            if doc.children:
+                                all_child_documents.extend(doc.children)
+                        vector.create(documents)
+                        if all_child_documents:
+                            vector.create(all_child_documents)
+                        click.echo(click.style(f"Created vector index for dataset {dataset.id}.", fg="green"))
+                    except Exception as e:
+                        click.echo(click.style(f"Failed to created vector index for dataset {dataset.id}.", fg="red"))
+                        raise e
+                db.session.add(dataset)
+                db.session.commit()
+                click.echo(f"Successfully migrated dataset {dataset.id}.")
+                create_count += 1
+            except Exception as e:
+                db.session.rollback()
+                click.echo(click.style(f"Error creating dataset index: {e.__class__.__name__} {str(e)}", fg="red"))
+                continue
+
+    click.echo(
+        click.style(
+            f"Migration complete. Created {create_count} dataset indexes. Skipped {skipped_count} datasets.", fg="green"
+        )
+    )
+
+
+@click.command("add-qdrant-index", help="Add Qdrant index.")
+@click.option("--field", default="metadata.doc_id", prompt=False, help="Index field , default is metadata.doc_id.")
+def add_qdrant_index(field: str):
+    click.echo(click.style("Starting Qdrant index creation.", fg="green"))
+
+    create_count = 0
+
+    try:
+        bindings = db.session.query(DatasetCollectionBinding).all()
+        if not bindings:
+            click.echo(click.style("No dataset collection bindings found.", fg="red"))
+            return
+        import qdrant_client
+        from qdrant_client.http.exceptions import UnexpectedResponse
+        from qdrant_client.http.models import PayloadSchemaType
+
+        from core.rag.datasource.vdb.qdrant.qdrant_vector import PathQdrantParams, QdrantConfig
+
+        for binding in bindings:
+            if dify_config.QDRANT_URL is None:
+                raise ValueError("Qdrant URL is required.")
+            qdrant_config = QdrantConfig(
+                endpoint=dify_config.QDRANT_URL,
+                api_key=dify_config.QDRANT_API_KEY,
+                root_path=current_app.root_path,
+                timeout=dify_config.QDRANT_CLIENT_TIMEOUT,
+                grpc_port=dify_config.QDRANT_GRPC_PORT,
+                prefer_grpc=dify_config.QDRANT_GRPC_ENABLED,
+            )
+            try:
+                params = qdrant_config.to_qdrant_params()
+                # Check the type before using
+                if isinstance(params, PathQdrantParams):
+                    # PathQdrantParams case
+                    client = qdrant_client.QdrantClient(path=params.path)
+                else:
+                    # UrlQdrantParams case - params is UrlQdrantParams
+                    client = qdrant_client.QdrantClient(
+                        url=params.url,
+                        api_key=params.api_key,
+                        timeout=int(params.timeout),
+                        verify=params.verify,
+                        grpc_port=params.grpc_port,
+                        prefer_grpc=params.prefer_grpc,
+                    )
+                # create payload index
+                client.create_payload_index(binding.collection_name, field, field_schema=PayloadSchemaType.KEYWORD)
+                create_count += 1
+            except UnexpectedResponse as e:
+                # Collection does not exist, so return
+                if e.status_code == 404:
+                    click.echo(click.style(f"Collection not found: {binding.collection_name}.", fg="red"))
+                    continue
+                # Some other error occurred, so re-raise the exception
+                else:
+                    click.echo(
+                        click.style(
+                            f"Failed to create Qdrant index for collection: {binding.collection_name}.", fg="red"
+                        )
+                    )
+
+    except Exception:
+        click.echo(click.style("Failed to create Qdrant client.", fg="red"))
+
+    click.echo(click.style(f"Index creation complete. Created {create_count} collection indexes.", fg="green"))
+
+
+@click.command("old-metadata-migration", help="Old metadata migration.")
+def old_metadata_migration():
+    """
+    Old metadata migration.
+    """
+    click.echo(click.style("Starting old metadata migration.", fg="green"))
+
+    page = 1
+    while True:
+        try:
+            stmt = (
+                select(DatasetDocument)
+                .where(DatasetDocument.doc_metadata.is_not(None))
+                .order_by(DatasetDocument.created_at.desc())
+            )
+            documents = db.paginate(select=stmt, page=page, per_page=50, max_per_page=50, error_out=False)
+        except SQLAlchemyError:
+            raise
+        if not documents:
+            break
+        for document in documents:
+            if document.doc_metadata:
+                doc_metadata = document.doc_metadata
+                for key in doc_metadata:
+                    for field in BuiltInField:
+                        if field.value == key:
+                            break
+                    else:
+                        dataset_metadata = (
+                            db.session.query(DatasetMetadata)
+                            .where(DatasetMetadata.dataset_id == document.dataset_id, DatasetMetadata.name == key)
+                            .first()
+                        )
+                        if not dataset_metadata:
+                            dataset_metadata = DatasetMetadata(
+                                tenant_id=document.tenant_id,
+                                dataset_id=document.dataset_id,
+                                name=key,
+                                type="string",
+                                created_by=document.created_by,
+                            )
+                            db.session.add(dataset_metadata)
+                            db.session.flush()
+                            dataset_metadata_binding = DatasetMetadataBinding(
+                                tenant_id=document.tenant_id,
+                                dataset_id=document.dataset_id,
+                                metadata_id=dataset_metadata.id,
+                                document_id=document.id,
+                                created_by=document.created_by,
+                            )
+                            db.session.add(dataset_metadata_binding)
+                        else:
+                            dataset_metadata_binding = (
+                                db.session.query(DatasetMetadataBinding)  # type: ignore
+                                .where(
+                                    DatasetMetadataBinding.dataset_id == document.dataset_id,
+                                    DatasetMetadataBinding.document_id == document.id,
+                                    DatasetMetadataBinding.metadata_id == dataset_metadata.id,
+                                )
+                                .first()
+                            )
+                            if not dataset_metadata_binding:
+                                dataset_metadata_binding = DatasetMetadataBinding(
+                                    tenant_id=document.tenant_id,
+                                    dataset_id=document.dataset_id,
+                                    metadata_id=dataset_metadata.id,
+                                    document_id=document.id,
+                                    created_by=document.created_by,
+                                )
+                                db.session.add(dataset_metadata_binding)
+                        db.session.commit()
+        page += 1
+    click.echo(click.style("Old metadata migration completed.", fg="green"))

api/configs/enterprise/__init__.py

@@ -18,3 +18,7 @@ class EnterpriseFeatureConfig(BaseSettings):
         description="Allow customization of the enterprise logo.",
         default=False,
     )
+
+    ENTERPRISE_REQUEST_TIMEOUT: int = Field(
+        ge=1, description="Maximum timeout in seconds for enterprise requests", default=5
+    )

api/configs/feature/__init__.py

@@ -1,3 +1,4 @@
+from datetime import timedelta
 from enum import StrEnum
 from typing import Literal
 
@@ -48,6 +49,16 @@ class SecurityConfig(BaseSettings):
         default=5,
     )
 
+    WEB_FORM_SUBMIT_RATE_LIMIT_MAX_ATTEMPTS: PositiveInt = Field(
+        description="Maximum number of web form submissions allowed per IP within the rate limit window",
+        default=30,
+    )
+
+    WEB_FORM_SUBMIT_RATE_LIMIT_WINDOW_SECONDS: PositiveInt = Field(
+        description="Time window in seconds for web form submission rate limiting",
+        default=60,
+    )
+
     LOGIN_DISABLED: bool = Field(
         description="Whether to disable login checks",
         default=False,
@@ -82,6 +93,12 @@ class AppExecutionConfig(BaseSettings):
         default=0,
     )
 
+    HUMAN_INPUT_GLOBAL_TIMEOUT_SECONDS: PositiveInt = Field(
+        description="Maximum seconds a workflow run can stay paused waiting for human input before global timeout.",
+        default=int(timedelta(days=7).total_seconds()),
+        ge=1,
+    )
+
 
 class CodeExecutionSandboxConfig(BaseSettings):
     """
@@ -248,6 +265,11 @@ class PluginConfig(BaseSettings):
         default=60 * 60,
     )
 
+    PLUGIN_MAX_FILE_SIZE: PositiveInt = Field(
+        description="Maximum allowed size (bytes) for plugin-generated files",
+        default=50 * 1024 * 1024,
+    )
+
 
 class MarketplaceConfig(BaseSettings):
     """
@@ -1134,6 +1156,14 @@ class CeleryScheduleTasksConfig(BaseSettings):
         description="Enable queue monitor task",
         default=False,
     )
+    ENABLE_HUMAN_INPUT_TIMEOUT_TASK: bool = Field(
+        description="Enable human input timeout check task",
+        default=True,
+    )
+    HUMAN_INPUT_TIMEOUT_TASK_INTERVAL: PositiveInt = Field(
+        description="Human input timeout check interval in minutes",
+        default=1,
+    )
     ENABLE_CHECK_UPGRADABLE_PLUGIN_TASK: bool = Field(
         description="Enable check upgradable plugin task",
         default=True,
@@ -1155,6 +1185,16 @@ class CeleryScheduleTasksConfig(BaseSettings):
         default=0,
     )
 
+    # API token last_used_at batch update
+    ENABLE_API_TOKEN_LAST_USED_UPDATE_TASK: bool = Field(
+        description="Enable periodic batch update of API token last_used_at timestamps",
+        default=True,
+    )
+    API_TOKEN_LAST_USED_UPDATE_INTERVAL: int = Field(
+        description="Interval in minutes for batch updating API token last_used_at (default 30)",
+        default=30,
+    )
+
     # Trigger provider refresh (simple version)
     ENABLE_TRIGGER_PROVIDER_REFRESH_TASK: bool = Field(
         description="Enable trigger provider refresh poller",
@@ -1279,6 +1319,9 @@ class WorkflowLogConfig(BaseSettings):
     WORKFLOW_LOG_CLEANUP_BATCH_SIZE: int = Field(
         default=100, description="Batch size for workflow run log cleanup operations"
     )
+    WORKFLOW_LOG_CLEANUP_SPECIFIC_WORKFLOW_IDS: str = Field(
+        default="", description="Comma-separated list of workflow IDs to clean logs for"
+    )
 
 
 class SwaggerUIConfig(BaseSettings):
@@ -1309,6 +1352,10 @@ class SandboxExpiredRecordsCleanConfig(BaseSettings):
         description="Maximum number of records to process in each batch",
         default=1000,
     )
+    SANDBOX_EXPIRED_RECORDS_CLEAN_BATCH_MAX_INTERVAL: PositiveInt = Field(
+        description="Maximum interval in milliseconds between batches",
+        default=200,
+    )
     SANDBOX_EXPIRED_RECORDS_RETENTION_DAYS: PositiveInt = Field(
         description="Retention days for sandbox expired workflow_run records and message records",
         default=30,

api/configs/middleware/__init__.py

@@ -6,6 +6,7 @@ from pydantic import Field, NonNegativeFloat, NonNegativeInt, PositiveFloat, Pos
 from pydantic_settings import BaseSettings
 
 from .cache.redis_config import RedisConfig
+from .cache.redis_pubsub_config import RedisPubSubConfig
 from .storage.aliyun_oss_storage_config import AliyunOSSStorageConfig
 from .storage.amazon_s3_storage_config import S3StorageConfig
 from .storage.azure_blob_storage_config import AzureBlobStorageConfig
@@ -258,11 +259,20 @@ class CeleryConfig(DatabaseConfig):
         description="Password of the Redis Sentinel master.",
         default=None,
     )
+
     CELERY_SENTINEL_SOCKET_TIMEOUT: PositiveFloat | None = Field(
         description="Timeout for Redis Sentinel socket operations in seconds.",
         default=0.1,
     )
 
+    CELERY_TASK_ANNOTATIONS: dict[str, Any] | None = Field(
+        description=(
+            "Annotations for Celery tasks as a JSON mapping of task name -> options "
+            "(for example, rate limits or other task-specific settings)."
+        ),
+        default=None,
+    )
+
     @computed_field
     def CELERY_RESULT_BACKEND(self) -> str | None:
         if self.CELERY_BACKEND in ("database", "rabbitmq"):
@@ -317,6 +327,7 @@ class MiddlewareConfig(
     CeleryConfig,  # Note: CeleryConfig already inherits from DatabaseConfig
     KeywordStoreConfig,
     RedisConfig,
+    RedisPubSubConfig,
     # configs of storage and storage providers
     StorageConfig,
     AliyunOSSStorageConfig,

api/configs/middleware/cache/redis_config.py

@@ -111,3 +111,8 @@ class RedisConfig(BaseSettings):
         description="Enable client side cache in redis",
         default=False,
     )
+
+    REDIS_MAX_CONNECTIONS: PositiveInt | None = Field(
+        description="Maximum connections in the Redis connection pool (unset for library default)",
+        default=None,
+    )

api/configs/middleware/cache/redis_pubsub_config.py

@@ -0,0 +1,111 @@
+from typing import Literal, Protocol
+from urllib.parse import quote_plus, urlunparse
+
+from pydantic import AliasChoices, Field
+from pydantic_settings import BaseSettings
+
+
+class RedisConfigDefaults(Protocol):
+    REDIS_HOST: str
+    REDIS_PORT: int
+    REDIS_USERNAME: str | None
+    REDIS_PASSWORD: str | None
+    REDIS_DB: int
+    REDIS_USE_SSL: bool
+    REDIS_USE_SENTINEL: bool | None
+    REDIS_USE_CLUSTERS: bool
+
+
+class RedisConfigDefaultsMixin:
+    def _redis_defaults(self: RedisConfigDefaults) -> RedisConfigDefaults:
+        return self
+
+
+class RedisPubSubConfig(BaseSettings, RedisConfigDefaultsMixin):
+    """
+    Configuration settings for event transport between API and workers.
+
+    Supported transports:
+    - pubsub: Redis PUBLISH/SUBSCRIBE (at-most-once)
+    - sharded: Redis 7+ Sharded Pub/Sub (at-most-once, better scaling)
+    - streams: Redis Streams (at-least-once, supports late subscribers)
+    """
+
+    PUBSUB_REDIS_URL: str | None = Field(
+        validation_alias=AliasChoices("EVENT_BUS_REDIS_URL", "PUBSUB_REDIS_URL"),
+        description=(
+            "Redis connection URL for streaming events between API and celery worker; "
+            "defaults to URL constructed from `REDIS_*` configurations. Also accepts ENV: EVENT_BUS_REDIS_URL."
+        ),
+        default=None,
+    )
+
+    PUBSUB_REDIS_USE_CLUSTERS: bool = Field(
+        validation_alias=AliasChoices("EVENT_BUS_REDIS_CLUSTERS", "PUBSUB_REDIS_USE_CLUSTERS"),
+        description=(
+            "Enable Redis Cluster mode for pub/sub or streams transport. Recommended for large deployments. "
+            "Also accepts ENV: EVENT_BUS_REDIS_CLUSTERS."
+        ),
+        default=False,
+    )
+
+    PUBSUB_REDIS_CHANNEL_TYPE: Literal["pubsub", "sharded", "streams"] = Field(
+        validation_alias=AliasChoices("EVENT_BUS_REDIS_CHANNEL_TYPE", "PUBSUB_REDIS_CHANNEL_TYPE"),
+        description=(
+            "Event transport type. Options are:\n\n"
+            " - pubsub: normal Pub/Sub (at-most-once)\n"
+            " - sharded: sharded Pub/Sub (at-most-once)\n"
+            " - streams: Redis Streams (at-least-once, recommended to avoid subscriber races)\n\n"
+            "Note: Before enabling 'streams' in production, estimate your expected event volume and retention needs.\n"
+            "Configure Redis memory limits and stream trimming appropriately (e.g., MAXLEN and key expiry) to reduce\n"
+            "the risk of data loss from Redis auto-eviction under memory pressure.\n"
+            "Also accepts ENV: EVENT_BUS_REDIS_CHANNEL_TYPE."
+        ),
+        default="pubsub",
+    )
+
+    PUBSUB_STREAMS_RETENTION_SECONDS: int = Field(
+        validation_alias=AliasChoices("EVENT_BUS_STREAMS_RETENTION_SECONDS", "PUBSUB_STREAMS_RETENTION_SECONDS"),
+        description=(
+            "When using 'streams', expire each stream key this many seconds after the last event is published. "
+            "Also accepts ENV: EVENT_BUS_STREAMS_RETENTION_SECONDS."
+        ),
+        default=600,
+    )
+
+    def _build_default_pubsub_url(self) -> str:
+        defaults = self._redis_defaults()
+        if not defaults.REDIS_HOST or not defaults.REDIS_PORT:
+            raise ValueError("PUBSUB_REDIS_URL must be set when default Redis URL cannot be constructed")
+
+        scheme = "rediss" if defaults.REDIS_USE_SSL else "redis"
+        username = defaults.REDIS_USERNAME or None
+        password = defaults.REDIS_PASSWORD or None
+
+        userinfo = ""
+        if username:
+            userinfo = quote_plus(username)
+        if password:
+            password_part = quote_plus(password)
+            userinfo = f"{userinfo}:{password_part}" if userinfo else f":{password_part}"
+        if userinfo:
+            userinfo = f"{userinfo}@"
+
+        host = defaults.REDIS_HOST
+        port = defaults.REDIS_PORT
+        db = defaults.REDIS_DB
+
+        netloc = f"{userinfo}{host}:{port}"
+        return urlunparse((scheme, netloc, f"/{db}", "", "", ""))
+
+    @property
+    def normalized_pubsub_redis_url(self) -> str:
+        pubsub_redis_url = self.PUBSUB_REDIS_URL
+        if pubsub_redis_url:
+            cleaned = pubsub_redis_url.strip()
+            pubsub_redis_url = cleaned or None
+
+        if pubsub_redis_url:
+            return pubsub_redis_url
+
+        return self._build_default_pubsub_url()

api/configs/middleware/vdb/oceanbase_config.py

@@ -1,3 +1,5 @@
+from typing import Literal
+
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -49,3 +51,43 @@ class OceanBaseVectorConfig(BaseSettings):
         ),
         default="ik",
     )
+
+    OCEANBASE_VECTOR_BATCH_SIZE: PositiveInt = Field(
+        description="Number of documents to insert per batch",
+        default=100,
+    )
+
+    OCEANBASE_VECTOR_METRIC_TYPE: Literal["l2", "cosine", "inner_product"] = Field(
+        description="Distance metric type for vector index: l2, cosine, or inner_product",
+        default="l2",
+    )
+
+    OCEANBASE_HNSW_M: PositiveInt = Field(
+        description="HNSW M parameter (max number of connections per node)",
+        default=16,
+    )
+
+    OCEANBASE_HNSW_EF_CONSTRUCTION: PositiveInt = Field(
+        description="HNSW efConstruction parameter (index build-time search width)",
+        default=256,
+    )
+
+    OCEANBASE_HNSW_EF_SEARCH: int = Field(
+        description="HNSW efSearch parameter (query-time search width, -1 uses server default)",
+        default=-1,
+    )
+
+    OCEANBASE_VECTOR_POOL_SIZE: PositiveInt = Field(
+        description="SQLAlchemy connection pool size",
+        default=5,
+    )
+
+    OCEANBASE_VECTOR_MAX_OVERFLOW: int = Field(
+        description="SQLAlchemy connection pool max overflow connections",
+        default=10,
+    )
+
+    OCEANBASE_HNSW_REFRESH_THRESHOLD: int = Field(
+        description="Minimum number of inserted documents to trigger an automatic HNSW index refresh (0 to disable)",
+        default=1000,
+    )

api/configs/middleware/vdb/weaviate_config.py

@@ -17,11 +17,6 @@ class WeaviateConfig(BaseSettings):
         default=None,
     )
 
-    WEAVIATE_GRPC_ENABLED: bool = Field(
-        description="Whether to enable gRPC for Weaviate connection (True for gRPC, False for HTTP)",
-        default=True,
-    )
-
     WEAVIATE_GRPC_ENDPOINT: str | None = Field(
         description="URL of the Weaviate gRPC server (e.g., 'grpc://localhost:50051' or 'grpcs://weaviate.example.com:443')",
         default=None,

api/constants/languages.py

@@ -21,6 +21,7 @@ language_timezone_mapping = {
     "th-TH": "Asia/Bangkok",
     "id-ID": "Asia/Jakarta",
     "ar-TN": "Africa/Tunis",
+    "nl-NL": "Europe/Amsterdam",
 }
 
 languages = list(language_timezone_mapping.keys())

api/context/__init__.py

@@ -12,7 +12,7 @@ or any other web framework.
 import contextvars
 from collections.abc import Callable
 
-from core.workflow.context.execution_context import (
+from dify_graph.context.execution_context import (
     ExecutionContext,
     IExecutionContext,
     NullAppContext,

api/context/flask_app_context.py

@@ -10,8 +10,8 @@ from typing import Any, final
 
 from flask import Flask, current_app, g
 
-from core.workflow.context import register_context_capturer
-from core.workflow.context.execution_context import (
+from dify_graph.context import register_context_capturer
+from dify_graph.context.execution_context import (
     AppContext,
     IExecutionContext,
 )

api/controllers/common/fields.py

@@ -4,7 +4,7 @@ from typing import Any, TypeAlias
 
 from pydantic import BaseModel, ConfigDict, computed_field
 
-from core.file import helpers as file_helpers
+from dify_graph.file import helpers as file_helpers
 from models.model import IconType
 
 JSONValue: TypeAlias = str | int | float | bool | None | dict[str, Any] | list[Any]

api/controllers/common/schema.py

@@ -5,8 +5,6 @@ from enum import StrEnum
 from flask_restx import Namespace
 from pydantic import BaseModel, TypeAdapter
 
-from controllers.console import console_ns
-
 DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
 
 
@@ -24,6 +22,9 @@ def register_schema_models(namespace: Namespace, *models: type[BaseModel]) -> No
 
 
 def get_or_create_model(model_name: str, field_def):
+    # Import lazily to avoid circular imports between console controllers and schema helpers.
+    from controllers.console import console_ns
+
     existing = console_ns.models.get(model_name)
     if existing is None:
         existing = console_ns.model(model_name, field_def)

api/controllers/console/__init__.py

@@ -37,7 +37,9 @@ from . import (
     apikey,
     extension,
     feature,
+    human_input_form,
     init_validate,
+    notification,
     ping,
     setup,
     spec,
@@ -171,6 +173,7 @@ __all__ = [
     "forgot_password",
     "generator",
     "hit_testing",
+    "human_input_form",
     "init_validate",
     "installed_app",
     "load_balancing_config",
@@ -182,6 +185,7 @@ __all__ = [
     "model_config",
     "model_providers",
     "models",
+    "notification",
     "oauth",
     "oauth_server",
     "ops_trace",

api/controllers/console/admin.py

@@ -1,3 +1,5 @@
+import csv
+import io
 from collections.abc import Callable
 from functools import wraps
 from typing import ParamSpec, TypeVar
@@ -6,7 +8,7 @@ from flask import request
 from flask_restx import Resource
 from pydantic import BaseModel, Field, field_validator
 from sqlalchemy import select
-from werkzeug.exceptions import NotFound, Unauthorized
+from werkzeug.exceptions import BadRequest, NotFound, Unauthorized
 
 from configs import dify_config
 from constants.languages import supported_language
@@ -16,6 +18,7 @@ from core.db.session_factory import session_factory
 from extensions.ext_database import db
 from libs.token import extract_access_token
 from models.model import App, ExporleBanner, InstalledApp, RecommendedApp, TrialApp
+from services.billing_service import BillingService
 
 P = ParamSpec("P")
 R = TypeVar("R")
@@ -277,3 +280,168 @@ class DeleteExploreBannerApi(Resource):
         db.session.commit()
 
         return {"result": "success"}, 204
+
+
+class LangContentPayload(BaseModel):
+    lang: str = Field(..., description="Language tag: 'zh' | 'en' | 'jp'")
+    title: str = Field(...)
+    subtitle: str | None = Field(default=None)
+    body: str = Field(...)
+    title_pic_url: str | None = Field(default=None)
+
+
+class UpsertNotificationPayload(BaseModel):
+    notification_id: str | None = Field(default=None, description="Omit to create; supply UUID to update")
+    contents: list[LangContentPayload] = Field(..., min_length=1)
+    start_time: str | None = Field(default=None, description="RFC3339, e.g. 2026-03-01T00:00:00Z")
+    end_time: str | None = Field(default=None, description="RFC3339, e.g. 2026-03-20T23:59:59Z")
+    frequency: str = Field(default="once", description="'once' | 'every_page_load'")
+    status: str = Field(default="active", description="'active' | 'inactive'")
+
+
+class BatchAddNotificationAccountsPayload(BaseModel):
+    notification_id: str = Field(...)
+    user_email: list[str] = Field(..., description="List of account email addresses")
+
+
+console_ns.schema_model(
+    UpsertNotificationPayload.__name__,
+    UpsertNotificationPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    BatchAddNotificationAccountsPayload.__name__,
+    BatchAddNotificationAccountsPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+
+@console_ns.route("/admin/upsert_notification")
+class UpsertNotificationApi(Resource):
+    @console_ns.doc("upsert_notification")
+    @console_ns.doc(
+        description=(
+            "Create or update an in-product notification. "
+            "Supply notification_id to update an existing one; omit it to create a new one. "
+            "Pass at least one language variant in contents (zh / en / jp)."
+        )
+    )
+    @console_ns.expect(console_ns.models[UpsertNotificationPayload.__name__])
+    @console_ns.response(200, "Notification upserted successfully")
+    @only_edition_cloud
+    @admin_required
+    def post(self):
+        payload = UpsertNotificationPayload.model_validate(console_ns.payload)
+        result = BillingService.upsert_notification(
+            contents=[c.model_dump() for c in payload.contents],
+            frequency=payload.frequency,
+            status=payload.status,
+            notification_id=payload.notification_id,
+            start_time=payload.start_time,
+            end_time=payload.end_time,
+        )
+        return {"result": "success", "notification_id": result.get("notificationId")}, 200
+
+
+@console_ns.route("/admin/batch_add_notification_accounts")
+class BatchAddNotificationAccountsApi(Resource):
+    @console_ns.doc("batch_add_notification_accounts")
+    @console_ns.doc(
+        description=(
+            "Register target accounts for a notification by email address. "
+            'JSON body: {"notification_id": "...", "user_email": ["a@example.com", ...]}. '
+            "File upload: multipart/form-data with a 'file' field (CSV or TXT, one email per line) "
+            "plus a 'notification_id' field. "
+            "Emails that do not match any account are silently skipped."
+        )
+    )
+    @console_ns.response(200, "Accounts added successfully")
+    @only_edition_cloud
+    @admin_required
+    def post(self):
+        from models.account import Account
+
+        if "file" in request.files:
+            notification_id = request.form.get("notification_id", "").strip()
+            if not notification_id:
+                raise BadRequest("notification_id is required.")
+            emails = self._parse_emails_from_file()
+        else:
+            payload = BatchAddNotificationAccountsPayload.model_validate(console_ns.payload)
+            notification_id = payload.notification_id
+            emails = payload.user_email
+
+        if not emails:
+            raise BadRequest("No valid email addresses provided.")
+
+        # Resolve emails → account IDs in chunks to avoid large IN-clause
+        account_ids: list[str] = []
+        chunk_size = 500
+        for i in range(0, len(emails), chunk_size):
+            chunk = emails[i : i + chunk_size]
+            rows = db.session.execute(select(Account.id, Account.email).where(Account.email.in_(chunk))).all()
+            account_ids.extend(str(row.id) for row in rows)
+
+        if not account_ids:
+            raise BadRequest("None of the provided emails matched an existing account.")
+
+        # Send to dify-saas in batches of 1000
+        total_count = 0
+        batch_size = 1000
+        for i in range(0, len(account_ids), batch_size):
+            batch = account_ids[i : i + batch_size]
+            result = BillingService.batch_add_notification_accounts(
+                notification_id=notification_id,
+                account_ids=batch,
+            )
+            total_count += result.get("count", 0)
+
+        return {
+            "result": "success",
+            "emails_provided": len(emails),
+            "accounts_matched": len(account_ids),
+            "count": total_count,
+        }, 200
+
+    @staticmethod
+    def _parse_emails_from_file() -> list[str]:
+        """Parse email addresses from an uploaded CSV or TXT file."""
+        file = request.files["file"]
+        if not file.filename:
+            raise BadRequest("Uploaded file has no filename.")
+
+        filename_lower = file.filename.lower()
+        if not filename_lower.endswith((".csv", ".txt")):
+            raise BadRequest("Invalid file type. Only CSV (.csv) and TXT (.txt) files are allowed.")
+
+        try:
+            content = file.read().decode("utf-8")
+        except UnicodeDecodeError:
+            try:
+                file.seek(0)
+                content = file.read().decode("gbk")
+            except UnicodeDecodeError:
+                raise BadRequest("Unable to decode the file. Please use UTF-8 or GBK encoding.")
+
+        emails: list[str] = []
+        if filename_lower.endswith(".csv"):
+            reader = csv.reader(io.StringIO(content))
+            for row in reader:
+                for cell in row:
+                    cell = cell.strip()
+                    if cell:
+                        emails.append(cell)
+        else:
+            for line in content.splitlines():
+                line = line.strip()
+                if line:
+                    emails.append(line)
+
+        # Deduplicate while preserving order
+        seen: set[str] = set()
+        unique_emails: list[str] = []
+        for email in emails:
+            if email.lower() not in seen:
+                seen.add(email.lower())
+                unique_emails.append(email)
+
+        return unique_emails

api/controllers/console/apikey.py

@@ -10,6 +10,7 @@ from libs.helper import TimestampField
 from libs.login import current_account_with_tenant, login_required
 from models.dataset import Dataset
 from models.model import ApiToken, App
+from services.api_token_service import ApiTokenCache
 
 from . import console_ns
 from .wraps import account_initialization_required, edit_permission_required, setup_required
@@ -131,6 +132,11 @@ class BaseApiKeyResource(Resource):
         if key is None:
             flask_restx.abort(HTTPStatus.NOT_FOUND, message="API key not found")
 
+        # Invalidate cache before deleting from database
+        # Type assertion: key is guaranteed to be non-None here because abort() raises
+        assert key is not None  # nosec - for type checker only
+        ApiTokenCache.delete(key.token, key.type)
+
         db.session.query(ApiToken).where(ApiToken.id == api_key_id).delete()
         db.session.commit()
 

api/controllers/console/app/app.py

@@ -23,10 +23,10 @@ from controllers.console.wraps import (
     is_admin_or_owner_required,
     setup_required,
 )
-from core.file import helpers as file_helpers
 from core.ops.ops_trace_manager import OpsTraceManager
 from core.rag.retrieval.retrieval_methods import RetrievalMethod
-from core.workflow.enums import NodeType, WorkflowExecutionStatus
+from dify_graph.enums import NodeType, WorkflowExecutionStatus
+from dify_graph.file import helpers as file_helpers
 from extensions.ext_database import db
 from libs.login import current_account_with_tenant, login_required
 from models import App, DatasetPermissionEnum, Workflow
@@ -660,6 +660,19 @@ class AppCopyApi(Resource):
             )
             session.commit()
 
+            # Inherit web app permission from original app
+            if result.app_id and FeatureService.get_system_features().webapp_auth.enabled:
+                try:
+                    # Get the original app's access mode
+                    original_settings = EnterpriseService.WebAppAuth.get_app_access_mode_by_id(app_model.id)
+                    access_mode = original_settings.access_mode
+                except Exception:
+                    # If original app has no settings (old app), default to public to match fallback behavior
+                    access_mode = "public"
+
+                # Apply the same access mode to the copied app
+                EnterpriseService.WebAppAuth.update_app_access_mode(result.app_id, access_mode)
+
             stmt = select(App).where(App.id == result.app_id)
             app = session.scalar(stmt)
 

api/controllers/console/app/audio.py

@@ -22,7 +22,7 @@ from controllers.console.app.error import (
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
-from core.model_runtime.errors.invoke import InvokeError
+from dify_graph.model_runtime.errors.invoke import InvokeError
 from libs.login import login_required
 from models import App, AppMode
 from services.audio_service import AudioService

api/controllers/console/app/completion.py

@@ -26,7 +26,7 @@ from core.errors.error import (
     QuotaExceededError,
 )
 from core.helper.trace_id_helper import get_external_trace_id
-from core.model_runtime.errors.invoke import InvokeError
+from dify_graph.model_runtime.errors.invoke import InvokeError
 from libs import helper
 from libs.helper import uuid_value
 from libs.login import current_user, login_required

api/controllers/console/app/conversation.py

@@ -89,6 +89,7 @@ status_count_model = console_ns.model(
         "success": fields.Integer,
         "failed": fields.Integer,
         "partial_success": fields.Integer,
+        "paused": fields.Integer,
     },
 )
 
@@ -598,7 +599,12 @@ def _get_conversation(app_model, conversation_id):
     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)
+        # Keep updated_at unchanged when only marking a conversation as read.
+        .values(
+            read_at=naive_utc_now(),
+            read_account_id=current_user.id,
+            updated_at=Conversation.updated_at,
+        )
     )
     db.session.commit()
     db.session.refresh(conversation)

api/controllers/console/app/generator.py

@@ -18,7 +18,7 @@ from core.helper.code_executor.javascript.javascript_code_provider import Javasc
 from core.helper.code_executor.python3.python3_code_provider import Python3CodeProvider
 from core.llm_generator.entities import RuleCodeGeneratePayload, RuleGeneratePayload, RuleStructuredOutputPayload
 from core.llm_generator.llm_generator import LLMGenerator
-from core.model_runtime.errors.invoke import InvokeError
+from dify_graph.model_runtime.errors.invoke import InvokeError
 from extensions.ext_database import db
 from libs.login import current_account_with_tenant, login_required
 from models import App

api/controllers/console/app/message.py

@@ -24,7 +24,7 @@ from controllers.console.wraps import (
 )
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
-from core.model_runtime.errors.invoke import InvokeError
+from dify_graph.model_runtime.errors.invoke import InvokeError
 from extensions.ext_database import db
 from fields.raws import FilesContainedField
 from libs.helper import TimestampField, uuid_value
@@ -33,7 +33,7 @@ from libs.login import current_account_with_tenant, login_required
 from models.model import AppMode, Conversation, Message, MessageAnnotation, MessageFeedback
 from services.errors.conversation import ConversationNotExistsError
 from services.errors.message import MessageNotExistsError, SuggestedQuestionsAfterAnswerDisabledError
-from services.message_service import MessageService
+from services.message_service import MessageService, attach_message_extra_contents
 
 logger = logging.getLogger(__name__)
 
@@ -207,6 +207,7 @@ message_detail_model = console_ns.model(
         "created_at": TimestampField,
         "agent_thoughts": fields.List(fields.Nested(agent_thought_model)),
         "message_files": fields.List(fields.Nested(message_file_model)),
+        "extra_contents": fields.List(fields.Raw),
         "metadata": fields.Raw(attribute="message_metadata_dict"),
         "status": fields.String,
         "error": fields.String,
@@ -299,6 +300,7 @@ class ChatMessageListApi(Resource):
             has_more = False
 
         history_messages = list(reversed(history_messages))
+        attach_message_extra_contents(history_messages)
 
         return InfiniteScrollPagination(data=history_messages, limit=args.limit, has_more=has_more)
 
@@ -481,4 +483,5 @@ class MessageApi(Resource):
         if not message:
             raise NotFound("Message Not Exists.")
 
+        attach_message_extra_contents([message])
         return message

api/controllers/console/app/workflow.py

@@ -20,9 +20,7 @@ from core.app.app_config.features.file_upload.manager import FileUploadConfigMan
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.apps.workflow.app_generator import SKIP_PREPARE_USER_INPUTS_KEY
 from core.app.entities.app_invoke_entities import InvokeFrom
-from core.file.models import File
 from core.helper.trace_id_helper import get_external_trace_id
-from core.model_runtime.utils.encoders import jsonable_encoder
 from core.plugin.impl.exc import PluginInvokeError
 from core.trigger.debug.event_selectors import (
     TriggerDebugEvent,
@@ -30,9 +28,12 @@ from core.trigger.debug.event_selectors import (
     create_event_poller,
     select_trigger_debug_events,
 )
-from core.workflow.enums import NodeType
-from core.workflow.graph_engine.manager import GraphEngineManager
+from dify_graph.enums import NodeType
+from dify_graph.file.models import File
+from dify_graph.graph_engine.manager import GraphEngineManager
+from dify_graph.model_runtime.utils.encoders import jsonable_encoder
 from extensions.ext_database import db
+from extensions.ext_redis import redis_client
 from factories import file_factory, variable_factory
 from fields.member_fields import simple_account_fields
 from fields.workflow_fields import workflow_fields, workflow_pagination_fields
@@ -507,6 +508,179 @@ class WorkflowDraftRunLoopNodeApi(Resource):
             raise InternalServerError()
 
 
+class HumanInputFormPreviewPayload(BaseModel):
+    inputs: dict[str, Any] = Field(
+        default_factory=dict,
+        description="Values used to fill missing upstream variables referenced in form_content",
+    )
+
+
+class HumanInputFormSubmitPayload(BaseModel):
+    form_inputs: dict[str, Any] = Field(..., description="Values the user provides for the form's own fields")
+    inputs: dict[str, Any] = Field(
+        ...,
+        description="Values used to fill missing upstream variables referenced in form_content",
+    )
+    action: str = Field(..., description="Selected action ID")
+
+
+class HumanInputDeliveryTestPayload(BaseModel):
+    delivery_method_id: str = Field(..., description="Delivery method ID")
+    inputs: dict[str, Any] = Field(
+        default_factory=dict,
+        description="Values used to fill missing upstream variables referenced in form_content",
+    )
+
+
+reg(HumanInputFormPreviewPayload)
+reg(HumanInputFormSubmitPayload)
+reg(HumanInputDeliveryTestPayload)
+
+
+@console_ns.route("/apps/<uuid:app_id>/advanced-chat/workflows/draft/human-input/nodes/<string:node_id>/form/preview")
+class AdvancedChatDraftHumanInputFormPreviewApi(Resource):
+    @console_ns.doc("get_advanced_chat_draft_human_input_form")
+    @console_ns.doc(description="Get human input form preview for advanced chat workflow")
+    @console_ns.doc(params={"app_id": "Application ID", "node_id": "Node ID"})
+    @console_ns.expect(console_ns.models[HumanInputFormPreviewPayload.__name__])
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT])
+    @edit_permission_required
+    def post(self, app_model: App, node_id: str):
+        """
+        Preview human input form content and placeholders
+        """
+        current_user, _ = current_account_with_tenant()
+        args = HumanInputFormPreviewPayload.model_validate(console_ns.payload or {})
+        inputs = args.inputs
+
+        workflow_service = WorkflowService()
+        preview = workflow_service.get_human_input_form_preview(
+            app_model=app_model,
+            account=current_user,
+            node_id=node_id,
+            inputs=inputs,
+        )
+        return jsonable_encoder(preview)
+
+
+@console_ns.route("/apps/<uuid:app_id>/advanced-chat/workflows/draft/human-input/nodes/<string:node_id>/form/run")
+class AdvancedChatDraftHumanInputFormRunApi(Resource):
+    @console_ns.doc("submit_advanced_chat_draft_human_input_form")
+    @console_ns.doc(description="Submit human input form preview for advanced chat workflow")
+    @console_ns.doc(params={"app_id": "Application ID", "node_id": "Node ID"})
+    @console_ns.expect(console_ns.models[HumanInputFormSubmitPayload.__name__])
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT])
+    @edit_permission_required
+    def post(self, app_model: App, node_id: str):
+        """
+        Submit human input form preview
+        """
+        current_user, _ = current_account_with_tenant()
+        args = HumanInputFormSubmitPayload.model_validate(console_ns.payload or {})
+        workflow_service = WorkflowService()
+        result = workflow_service.submit_human_input_form_preview(
+            app_model=app_model,
+            account=current_user,
+            node_id=node_id,
+            form_inputs=args.form_inputs,
+            inputs=args.inputs,
+            action=args.action,
+        )
+        return jsonable_encoder(result)
+
+
+@console_ns.route("/apps/<uuid:app_id>/workflows/draft/human-input/nodes/<string:node_id>/form/preview")
+class WorkflowDraftHumanInputFormPreviewApi(Resource):
+    @console_ns.doc("get_workflow_draft_human_input_form")
+    @console_ns.doc(description="Get human input form preview for workflow")
+    @console_ns.doc(params={"app_id": "Application ID", "node_id": "Node ID"})
+    @console_ns.expect(console_ns.models[HumanInputFormPreviewPayload.__name__])
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model(mode=[AppMode.WORKFLOW])
+    @edit_permission_required
+    def post(self, app_model: App, node_id: str):
+        """
+        Preview human input form content and placeholders
+        """
+        current_user, _ = current_account_with_tenant()
+        args = HumanInputFormPreviewPayload.model_validate(console_ns.payload or {})
+        inputs = args.inputs
+
+        workflow_service = WorkflowService()
+        preview = workflow_service.get_human_input_form_preview(
+            app_model=app_model,
+            account=current_user,
+            node_id=node_id,
+            inputs=inputs,
+        )
+        return jsonable_encoder(preview)
+
+
+@console_ns.route("/apps/<uuid:app_id>/workflows/draft/human-input/nodes/<string:node_id>/form/run")
+class WorkflowDraftHumanInputFormRunApi(Resource):
+    @console_ns.doc("submit_workflow_draft_human_input_form")
+    @console_ns.doc(description="Submit human input form preview for workflow")
+    @console_ns.doc(params={"app_id": "Application ID", "node_id": "Node ID"})
+    @console_ns.expect(console_ns.models[HumanInputFormSubmitPayload.__name__])
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model(mode=[AppMode.WORKFLOW])
+    @edit_permission_required
+    def post(self, app_model: App, node_id: str):
+        """
+        Submit human input form preview
+        """
+        current_user, _ = current_account_with_tenant()
+        workflow_service = WorkflowService()
+        args = HumanInputFormSubmitPayload.model_validate(console_ns.payload or {})
+        result = workflow_service.submit_human_input_form_preview(
+            app_model=app_model,
+            account=current_user,
+            node_id=node_id,
+            form_inputs=args.form_inputs,
+            inputs=args.inputs,
+            action=args.action,
+        )
+        return jsonable_encoder(result)
+
+
+@console_ns.route("/apps/<uuid:app_id>/workflows/draft/human-input/nodes/<string:node_id>/delivery-test")
+class WorkflowDraftHumanInputDeliveryTestApi(Resource):
+    @console_ns.doc("test_workflow_draft_human_input_delivery")
+    @console_ns.doc(description="Test human input delivery for workflow")
+    @console_ns.doc(params={"app_id": "Application ID", "node_id": "Node ID"})
+    @console_ns.expect(console_ns.models[HumanInputDeliveryTestPayload.__name__])
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model(mode=[AppMode.WORKFLOW, AppMode.ADVANCED_CHAT])
+    @edit_permission_required
+    def post(self, app_model: App, node_id: str):
+        """
+        Test human input delivery
+        """
+        current_user, _ = current_account_with_tenant()
+        workflow_service = WorkflowService()
+        args = HumanInputDeliveryTestPayload.model_validate(console_ns.payload or {})
+        workflow_service.test_human_input_delivery(
+            app_model=app_model,
+            account=current_user,
+            node_id=node_id,
+            delivery_method_id=args.delivery_method_id,
+            inputs=args.inputs,
+        )
+        return jsonable_encoder({})
+
+
 @console_ns.route("/apps/<uuid:app_id>/workflows/draft/run")
 class DraftWorkflowRunApi(Resource):
     @console_ns.doc("run_draft_workflow")
@@ -567,7 +741,7 @@ class WorkflowTaskStopApi(Resource):
         AppQueueManager.set_stop_flag_no_user_check(task_id)
 
         # New graph engine command channel mechanism
-        GraphEngineManager.send_stop_command(task_id)
+        GraphEngineManager(redis_client).send_stop_command(task_id)
 
         return {"result": "success"}
 

api/controllers/console/app/workflow_app_log.py

@@ -9,7 +9,7 @@ from sqlalchemy.orm import Session
 from controllers.console import console_ns
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
-from core.workflow.enums import WorkflowExecutionStatus
+from dify_graph.enums import WorkflowExecutionStatus
 from extensions.ext_database import db
 from fields.workflow_app_log_fields import (
     build_workflow_app_log_pagination_model,

api/controllers/console/app/workflow_draft_variable.py

@@ -15,11 +15,11 @@ from controllers.console.app.error import (
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, edit_permission_required, setup_required
 from controllers.web.error import InvalidArgumentError, NotFoundError
-from core.file import helpers as file_helpers
-from core.variables.segment_group import SegmentGroup
-from core.variables.segments import ArrayFileSegment, FileSegment, Segment
-from core.variables.types import SegmentType
-from core.workflow.constants import CONVERSATION_VARIABLE_NODE_ID, SYSTEM_VARIABLE_NODE_ID
+from dify_graph.constants import CONVERSATION_VARIABLE_NODE_ID, SYSTEM_VARIABLE_NODE_ID
+from dify_graph.file import helpers as file_helpers
+from dify_graph.variables.segment_group import SegmentGroup
+from dify_graph.variables.segments import ArrayFileSegment, FileSegment, Segment
+from dify_graph.variables.types import SegmentType
 from extensions.ext_database import db
 from factories.file_factory import build_from_mapping, build_from_mappings
 from factories.variable_factory import build_segment_with_type
@@ -112,11 +112,11 @@ _WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS = {
     "is_truncated": fields.Boolean(attribute=lambda model: model.file_id is not None),
 }
 
-_WORKFLOW_DRAFT_VARIABLE_FIELDS = dict(
-    _WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS,
-    value=fields.Raw(attribute=_serialize_var_value),
-    full_content=fields.Raw(attribute=_serialize_full_content),
-)
+_WORKFLOW_DRAFT_VARIABLE_FIELDS = {
+    **_WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS,
+    "value": fields.Raw(attribute=_serialize_var_value),
+    "full_content": fields.Raw(attribute=_serialize_full_content),
+}
 
 _WORKFLOW_DRAFT_ENV_VARIABLE_FIELDS = {
     "id": fields.String,

api/controllers/console/app/workflow_run.py

@@ -5,10 +5,15 @@ from flask import request
 from flask_restx import Resource, fields, marshal_with
 from pydantic import BaseModel, Field, field_validator
 from sqlalchemy import select
+from sqlalchemy.orm import sessionmaker
 
+from configs import dify_config
 from controllers.console import console_ns
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
+from controllers.web.error import NotFoundError
+from dify_graph.entities.pause_reason import HumanInputRequired
+from dify_graph.enums import WorkflowExecutionStatus
 from extensions.ext_database import db
 from fields.end_user_fields import simple_end_user_fields
 from fields.member_fields import simple_account_fields
@@ -27,9 +32,21 @@ from libs.custom_inputs import time_duration
 from libs.helper import uuid_value
 from libs.login import current_user, login_required
 from models import Account, App, AppMode, EndUser, WorkflowArchiveLog, WorkflowRunTriggeredFrom
+from models.workflow import WorkflowRun
+from repositories.factory import DifyAPIRepositoryFactory
 from services.retention.workflow_run.constants import ARCHIVE_BUNDLE_NAME
 from services.workflow_run_service import WorkflowRunService
 
+
+def _build_backstage_input_url(form_token: str | None) -> str | None:
+    if not form_token:
+        return None
+    base_url = dify_config.APP_WEB_URL
+    if not base_url:
+        return None
+    return f"{base_url.rstrip('/')}/form/{form_token}"
+
+
 # Workflow run status choices for filtering
 WORKFLOW_RUN_STATUS_CHOICES = ["running", "succeeded", "failed", "stopped", "partial-succeeded"]
 EXPORT_SIGNED_URL_EXPIRE_SECONDS = 3600
@@ -440,3 +457,68 @@ class WorkflowRunNodeExecutionListApi(Resource):
         )
 
         return {"data": node_executions}
+
+
+@console_ns.route("/workflow/<string:workflow_run_id>/pause-details")
+class ConsoleWorkflowPauseDetailsApi(Resource):
+    """Console API for getting workflow pause details."""
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, workflow_run_id: str):
+        """
+        Get workflow pause details.
+
+        GET /console/api/workflow/<workflow_run_id>/pause-details
+
+        Returns information about why and where the workflow is paused.
+        """
+
+        # Query WorkflowRun to determine if workflow is suspended
+        session_maker = sessionmaker(bind=db.engine)
+        workflow_run_repo = DifyAPIRepositoryFactory.create_api_workflow_run_repository(session_maker=session_maker)
+
+        workflow_run = db.session.get(WorkflowRun, workflow_run_id)
+        if not workflow_run:
+            raise NotFoundError("Workflow run not found")
+
+        if workflow_run.tenant_id != current_user.current_tenant_id:
+            raise NotFoundError("Workflow run not found")
+
+        # Check if workflow is suspended
+        is_paused = workflow_run.status == WorkflowExecutionStatus.PAUSED
+        if not is_paused:
+            return {
+                "paused_at": None,
+                "paused_nodes": [],
+            }, 200
+
+        pause_entity = workflow_run_repo.get_workflow_pause(workflow_run_id)
+        pause_reasons = pause_entity.get_pause_reasons() if pause_entity else []
+
+        # Build response
+        paused_at = pause_entity.paused_at if pause_entity else None
+        paused_nodes = []
+        response = {
+            "paused_at": paused_at.isoformat() + "Z" if paused_at else None,
+            "paused_nodes": paused_nodes,
+        }
+
+        for reason in pause_reasons:
+            if isinstance(reason, HumanInputRequired):
+                paused_nodes.append(
+                    {
+                        "node_id": reason.node_id,
+                        "node_title": reason.node_title,
+                        "pause_type": {
+                            "type": "human_input",
+                            "form_id": reason.form_id,
+                            "backstage_input_url": _build_backstage_input_url(reason.form_token),
+                        },
+                    }
+                )
+            else:
+                raise AssertionError("unimplemented.")
+
+        return response, 200

api/controllers/console/auth/oauth_server.py

@@ -8,7 +8,7 @@ from pydantic import BaseModel
 from werkzeug.exceptions import BadRequest, NotFound
 
 from controllers.console.wraps import account_initialization_required, setup_required
-from core.model_runtime.utils.encoders import jsonable_encoder
+from dify_graph.model_runtime.utils.encoders import jsonable_encoder
 from libs.login import current_account_with_tenant, login_required
 from models import Account
 from models.model import OAuthProviderApp

api/controllers/console/datasets/datasets.py

@@ -25,12 +25,12 @@ from controllers.console.wraps import (
 )
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.indexing_runner import IndexingRunner
-from core.model_runtime.entities.model_entities import ModelType
 from core.provider_manager import ProviderManager
 from core.rag.datasource.vdb.vector_type import VectorType
 from core.rag.extractor.entity.datasource_type import DatasourceType
 from core.rag.extractor.entity.extract_setting import ExtractSetting, NotionInfo, WebsiteInfo
 from core.rag.retrieval.retrieval_methods import RetrievalMethod
+from dify_graph.model_runtime.entities.model_entities import ModelType
 from extensions.ext_database import db
 from fields.app_fields import app_detail_kernel_fields, related_app_list
 from fields.dataset_fields import (
@@ -53,8 +53,9 @@ from fields.dataset_fields import (
 from fields.document_fields import document_status_fields
 from libs.login import current_account_with_tenant, login_required
 from models import ApiToken, Dataset, Document, DocumentSegment, UploadFile
-from models.dataset import DatasetPermissionEnum
+from models.dataset import DatasetPermission, DatasetPermissionEnum
 from models.provider_ids import ModelProviderID
+from services.api_token_service import ApiTokenCache
 from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService
 
 # Register models for flask_restx to avoid dict type issues in Swagger
@@ -118,6 +119,14 @@ def _validate_indexing_technique(value: str | None) -> str | None:
     return value
 
 
+def _validate_doc_form(value: str | None) -> str | None:
+    if value is None:
+        return value
+    if value not in Dataset.DOC_FORM_LIST:
+        raise ValueError("Invalid doc_form.")
+    return value
+
+
 class DatasetCreatePayload(BaseModel):
     name: str = Field(..., min_length=1, max_length=40)
     description: str = Field("", max_length=400)
@@ -178,6 +187,14 @@ class IndexingEstimatePayload(BaseModel):
             raise ValueError("indexing_technique is required.")
         return result
 
+    @field_validator("doc_form")
+    @classmethod
+    def validate_doc_form(cls, value: str) -> str:
+        result = _validate_doc_form(value)
+        if result is None:
+            return "text_model"
+        return result
+
 
 class ConsoleDatasetListQuery(BaseModel):
     page: int = Field(default=1, description="Page number")
@@ -322,6 +339,18 @@ class DatasetListApi(Resource):
             model_names.append(f"{embedding_model.model}:{embedding_model.provider.provider}")
 
         data = cast(list[dict[str, Any]], marshal(datasets, dataset_detail_fields))
+        dataset_ids = [item["id"] for item in data if item.get("permission") == "partial_members"]
+        partial_members_map: dict[str, list[str]] = {}
+        if dataset_ids:
+            permissions = db.session.execute(
+                select(DatasetPermission.dataset_id, DatasetPermission.account_id).where(
+                    DatasetPermission.dataset_id.in_(dataset_ids)
+                )
+            ).all()
+
+            for dataset_id, account_id in permissions:
+                partial_members_map.setdefault(dataset_id, []).append(account_id)
+
         for item in data:
             # convert embedding_model_provider to plugin standard format
             if item["indexing_technique"] == "high_quality" and item["embedding_model_provider"]:
@@ -335,8 +364,7 @@ class DatasetListApi(Resource):
                 item["embedding_available"] = True
 
             if item.get("permission") == "partial_members":
-                part_users_list = DatasetPermissionService.get_dataset_partial_member_list(item["id"])
-                item.update({"partial_member_list": part_users_list})
+                item.update({"partial_member_list": partial_members_map.get(item["id"], [])})
             else:
                 item.update({"partial_member_list": []})
 
@@ -779,7 +807,7 @@ class DatasetApiKeyApi(Resource):
             console_ns.abort(
                 400,
                 message=f"Cannot create more than {self.max_keys} API keys for this resource type.",
-                code="max_keys_exceeded",
+                custom="max_keys_exceeded",
             )
 
         key = ApiToken.generate_api_key(self.token_prefix, 24)
@@ -820,6 +848,11 @@ class DatasetApiDeleteApi(Resource):
         if key is None:
             console_ns.abort(404, message="API key not found")
 
+        # Invalidate cache before deleting from database
+        # Type assertion: key is guaranteed to be non-None here because abort() raises
+        assert key is not None  # nosec - for type checker only
+        ApiTokenCache.delete(key.token, key.type)
+
         db.session.query(ApiToken).where(ApiToken.id == api_key_id).delete()
         db.session.commit()
 

api/controllers/console/datasets/datasets_document.py

@@ -24,11 +24,11 @@ from core.errors.error import (
 )
 from core.indexing_runner import IndexingRunner
 from core.model_manager import ModelManager
-from core.model_runtime.entities.model_entities import ModelType
-from core.model_runtime.errors.invoke import InvokeAuthorizationError
 from core.plugin.impl.exc import PluginDaemonClientSideError
 from core.rag.extractor.entity.datasource_type import DatasourceType
 from core.rag.extractor.entity.extract_setting import ExtractSetting, NotionInfo, WebsiteInfo
+from dify_graph.model_runtime.entities.model_entities import ModelType
+from dify_graph.model_runtime.errors.invoke import InvokeAuthorizationError
 from extensions.ext_database import db
 from fields.dataset_fields import dataset_fields
 from fields.document_fields import (

api/controllers/console/datasets/datasets_segments.py

@@ -26,7 +26,7 @@ from controllers.console.wraps import (
 )
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.model_manager import ModelManager
-from core.model_runtime.entities.model_entities import ModelType
+from dify_graph.model_runtime.entities.model_entities import ModelType
 from extensions.ext_database import db
 from extensions.ext_redis import redis_client
 from fields.segment_fields import child_chunk_fields, segment_fields

api/controllers/console/datasets/hit_testing_base.py

@@ -19,7 +19,7 @@ from core.errors.error import (
     ProviderTokenNotInitError,
     QuotaExceededError,
 )
-from core.model_runtime.errors.invoke import InvokeError
+from dify_graph.model_runtime.errors.invoke import InvokeError
 from fields.hit_testing_fields import hit_testing_record_fields
 from libs.login import current_user
 from models.account import Account

api/controllers/console/datasets/rag_pipeline/datasource_auth.py

@@ -9,9 +9,9 @@ from configs import dify_config
 from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
 from controllers.console.wraps import account_initialization_required, edit_permission_required, setup_required
-from core.model_runtime.errors.validate import CredentialsValidateFailedError
-from core.model_runtime.utils.encoders import jsonable_encoder
 from core.plugin.impl.oauth import OAuthHandler
+from dify_graph.model_runtime.errors.validate import CredentialsValidateFailedError
+from dify_graph.model_runtime.utils.encoders import jsonable_encoder
 from libs.login import current_account_with_tenant, login_required
 from models.provider_ids import DatasourceProviderID
 from services.datasource_provider_service import DatasourceProviderService

api/controllers/console/datasets/rag_pipeline/rag_pipeline_draft_variable.py

@@ -21,8 +21,8 @@ from controllers.console.app.workflow_draft_variable import (
 from controllers.console.datasets.wraps import get_rag_pipeline
 from controllers.console.wraps import account_initialization_required, setup_required
 from controllers.web.error import InvalidArgumentError, NotFoundError
-from core.variables.types import SegmentType
-from core.workflow.constants import CONVERSATION_VARIABLE_NODE_ID, SYSTEM_VARIABLE_NODE_ID
+from dify_graph.constants import CONVERSATION_VARIABLE_NODE_ID, SYSTEM_VARIABLE_NODE_ID
+from dify_graph.variables.types import SegmentType
 from extensions.ext_database import db
 from factories.file_factory import build_from_mapping, build_from_mappings
 from factories.variable_factory import build_segment_with_type

api/controllers/console/datasets/rag_pipeline/rag_pipeline_workflow.py

@@ -33,7 +33,7 @@ from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpErr
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.apps.pipeline.pipeline_generator import PipelineGenerator
 from core.app.entities.app_invoke_entities import InvokeFrom
-from core.model_runtime.utils.encoders import jsonable_encoder
+from dify_graph.model_runtime.utils.encoders import jsonable_encoder
 from extensions.ext_database import db
 from factories import variable_factory
 from libs import helper

api/controllers/console/explore/audio.py

@@ -19,7 +19,7 @@ from controllers.console.app.error import (
 )
 from controllers.console.explore.wraps import InstalledAppResource
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
-from core.model_runtime.errors.invoke import InvokeError
+from dify_graph.model_runtime.errors.invoke import InvokeError
 from services.audio_service import AudioService
 from services.errors.audio import (
     AudioTooLargeServiceError,

api/controllers/console/explore/completion.py

@@ -24,7 +24,7 @@ from core.errors.error import (
     ProviderTokenNotInitError,
     QuotaExceededError,
 )
-from core.model_runtime.errors.invoke import InvokeError
+from dify_graph.model_runtime.errors.invoke import InvokeError
 from extensions.ext_database import db
 from libs import helper
 from libs.datetime_utils import naive_utc_now

api/controllers/console/explore/message.py

@@ -21,7 +21,7 @@ from controllers.console.explore.error import (
 from controllers.console.explore.wraps import InstalledAppResource
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
-from core.model_runtime.errors.invoke import InvokeError
+from dify_graph.model_runtime.errors.invoke import InvokeError
 from fields.conversation_fields import ResultResponse
 from fields.message_fields import MessageInfiniteScrollPagination, MessageListItem, SuggestedQuestionsResponse
 from libs import helper

api/controllers/console/explore/parameter.py

@@ -1,3 +1,5 @@
+from typing import Any, cast
+
 from controllers.common import fields
 from controllers.console import console_ns
 from controllers.console.app.error import AppUnavailableError
@@ -23,14 +25,14 @@ class AppParameterApi(InstalledAppResource):
             if workflow is None:
                 raise AppUnavailableError()
 
-            features_dict = workflow.features_dict
+            features_dict: dict[str, Any] = workflow.features_dict
             user_input_form = workflow.user_input_form(to_old_structure=True)
         else:
             app_model_config = app_model.app_model_config
             if app_model_config is None:
                 raise AppUnavailableError()
 
-            features_dict = app_model_config.to_dict()
+            features_dict = cast(dict[str, Any], app_model_config.to_dict())
 
             user_input_form = features_dict.get("user_input_form", [])
 

api/controllers/console/explore/trial.py

@@ -10,7 +10,7 @@ import services
 from controllers.common.fields import Parameters as ParametersResponse
 from controllers.common.fields import Site as SiteResponse
 from controllers.common.schema import get_or_create_model
-from controllers.console import api, console_ns
+from controllers.console import console_ns
 from controllers.console.app.error import (
     AppUnavailableError,
     AudioTooLargeError,
@@ -41,9 +41,10 @@ from core.errors.error import (
     ProviderTokenNotInitError,
     QuotaExceededError,
 )
-from core.model_runtime.errors.invoke import InvokeError
-from core.workflow.graph_engine.manager import GraphEngineManager
+from dify_graph.graph_engine.manager import GraphEngineManager
+from dify_graph.model_runtime.errors.invoke import InvokeError
 from extensions.ext_database import db
+from extensions.ext_redis import redis_client
 from fields.app_fields import (
     app_detail_fields_with_site,
     deleted_tool_fields,
@@ -225,7 +226,7 @@ class TrialAppWorkflowTaskStopApi(TrialAppResource):
         AppQueueManager.set_stop_flag_no_user_check(task_id)
 
         # New graph engine command channel mechanism
-        GraphEngineManager.send_stop_command(task_id)
+        GraphEngineManager(redis_client).send_stop_command(task_id)
 
         return {"result": "success"}
 
@@ -469,7 +470,7 @@ class TrialSitApi(Resource):
     """Resource for trial app sites."""
 
     @trial_feature_enable
-    @get_app_model_with_trial
+    @get_app_model_with_trial(None)
     def get(self, app_model):
         """Retrieve app site info.
 
@@ -491,7 +492,7 @@ class TrialAppParameterApi(Resource):
     """Resource for app variables."""
 
     @trial_feature_enable
-    @get_app_model_with_trial
+    @get_app_model_with_trial(None)
     def get(self, app_model):
         """Retrieve app parameters."""
 
@@ -520,7 +521,7 @@ class TrialAppParameterApi(Resource):
 
 class AppApi(Resource):
     @trial_feature_enable
-    @get_app_model_with_trial
+    @get_app_model_with_trial(None)
     @marshal_with(app_detail_with_site_model)
     def get(self, app_model):
         """Get app detail"""
@@ -533,7 +534,7 @@ class AppApi(Resource):
 
 class AppWorkflowApi(Resource):
     @trial_feature_enable
-    @get_app_model_with_trial
+    @get_app_model_with_trial(None)
     @marshal_with(workflow_model)
     def get(self, app_model):
         """Get workflow detail"""
@@ -552,7 +553,7 @@ class AppWorkflowApi(Resource):
 
 class DatasetListApi(Resource):
     @trial_feature_enable
-    @get_app_model_with_trial
+    @get_app_model_with_trial(None)
     def get(self, app_model):
         page = request.args.get("page", default=1, type=int)
         limit = request.args.get("limit", default=20, type=int)
@@ -570,27 +571,31 @@ class DatasetListApi(Resource):
         return response
 
 
-api.add_resource(TrialChatApi, "/trial-apps/<uuid:app_id>/chat-messages", endpoint="trial_app_chat_completion")
+console_ns.add_resource(TrialChatApi, "/trial-apps/<uuid:app_id>/chat-messages", endpoint="trial_app_chat_completion")
 
-api.add_resource(
+console_ns.add_resource(
     TrialMessageSuggestedQuestionApi,
     "/trial-apps/<uuid:app_id>/messages/<uuid:message_id>/suggested-questions",
     endpoint="trial_app_suggested_question",
 )
 
-api.add_resource(TrialChatAudioApi, "/trial-apps/<uuid:app_id>/audio-to-text", endpoint="trial_app_audio")
-api.add_resource(TrialChatTextApi, "/trial-apps/<uuid:app_id>/text-to-audio", endpoint="trial_app_text")
+console_ns.add_resource(TrialChatAudioApi, "/trial-apps/<uuid:app_id>/audio-to-text", endpoint="trial_app_audio")
+console_ns.add_resource(TrialChatTextApi, "/trial-apps/<uuid:app_id>/text-to-audio", endpoint="trial_app_text")
 
-api.add_resource(TrialCompletionApi, "/trial-apps/<uuid:app_id>/completion-messages", endpoint="trial_app_completion")
+console_ns.add_resource(
+    TrialCompletionApi, "/trial-apps/<uuid:app_id>/completion-messages", endpoint="trial_app_completion"
+)
 
-api.add_resource(TrialSitApi, "/trial-apps/<uuid:app_id>/site")
+console_ns.add_resource(TrialSitApi, "/trial-apps/<uuid:app_id>/site")
 
-api.add_resource(TrialAppParameterApi, "/trial-apps/<uuid:app_id>/parameters", endpoint="trial_app_parameters")
+console_ns.add_resource(TrialAppParameterApi, "/trial-apps/<uuid:app_id>/parameters", endpoint="trial_app_parameters")
 
-api.add_resource(AppApi, "/trial-apps/<uuid:app_id>", endpoint="trial_app")
+console_ns.add_resource(AppApi, "/trial-apps/<uuid:app_id>", endpoint="trial_app")
 
-api.add_resource(TrialAppWorkflowRunApi, "/trial-apps/<uuid:app_id>/workflows/run", endpoint="trial_app_workflow_run")
-api.add_resource(TrialAppWorkflowTaskStopApi, "/trial-apps/<uuid:app_id>/workflows/tasks/<string:task_id>/stop")
+console_ns.add_resource(
+    TrialAppWorkflowRunApi, "/trial-apps/<uuid:app_id>/workflows/run", endpoint="trial_app_workflow_run"
+)
+console_ns.add_resource(TrialAppWorkflowTaskStopApi, "/trial-apps/<uuid:app_id>/workflows/tasks/<string:task_id>/stop")
 
-api.add_resource(AppWorkflowApi, "/trial-apps/<uuid:app_id>/workflows", endpoint="trial_app_workflow")
-api.add_resource(DatasetListApi, "/trial-apps/<uuid:app_id>/datasets", endpoint="trial_app_datasets")
+console_ns.add_resource(AppWorkflowApi, "/trial-apps/<uuid:app_id>/workflows", endpoint="trial_app_workflow")
+console_ns.add_resource(DatasetListApi, "/trial-apps/<uuid:app_id>/datasets", endpoint="trial_app_datasets")

api/controllers/console/explore/workflow.py

@@ -21,8 +21,9 @@ from core.errors.error import (
     ProviderTokenNotInitError,
     QuotaExceededError,
 )
-from core.model_runtime.errors.invoke import InvokeError
-from core.workflow.graph_engine.manager import GraphEngineManager
+from dify_graph.graph_engine.manager import GraphEngineManager
+from dify_graph.model_runtime.errors.invoke import InvokeError
+from extensions.ext_redis import redis_client
 from libs import helper
 from libs.login import current_account_with_tenant
 from models.model import AppMode, InstalledApp
@@ -100,6 +101,6 @@ class InstalledAppWorkflowTaskStopApi(InstalledAppResource):
         AppQueueManager.set_stop_flag_no_user_check(task_id)
 
         # New graph engine command channel mechanism
-        GraphEngineManager.send_stop_command(task_id)
+        GraphEngineManager(redis_client).send_stop_command(task_id)
 
         return {"result": "success"}

api/controllers/console/explore/wraps.py

@@ -105,9 +105,9 @@ def trial_app_required(view: Callable[Concatenate[App, P], R] | None = None):
     return decorator
 
 
-def trial_feature_enable(view: Callable[..., R]) -> Callable[..., R]:
+def trial_feature_enable(view: Callable[P, R]):
     @wraps(view)
-    def decorated(*args, **kwargs):
+    def decorated(*args: P.args, **kwargs: P.kwargs):
         features = FeatureService.get_system_features()
         if not features.enable_trial_app:
             abort(403, "Trial app feature is not enabled.")
@@ -116,9 +116,9 @@ def trial_feature_enable(view: Callable[..., R]) -> Callable[..., R]:
     return decorated
 
 
-def explore_banner_enabled(view: Callable[..., R]) -> Callable[..., R]:
+def explore_banner_enabled(view: Callable[P, R]):
     @wraps(view)
-    def decorated(*args, **kwargs):
+    def decorated(*args: P.args, **kwargs: P.kwargs):
         features = FeatureService.get_system_features()
         if not features.enable_explore_banner:
             abort(403, "Explore banner feature is not enabled.")

api/controllers/console/human_input_form.py

@@ -0,0 +1,217 @@
+"""
+Console/Studio Human Input Form APIs.
+"""
+
+import json
+import logging
+from collections.abc import Generator
+
+from flask import Response, jsonify, request
+from flask_restx import Resource, reqparse
+from sqlalchemy import select
+from sqlalchemy.orm import Session, sessionmaker
+
+from controllers.console import console_ns
+from controllers.console.wraps import account_initialization_required, setup_required
+from controllers.web.error import InvalidArgumentError, NotFoundError
+from core.app.apps.advanced_chat.app_generator import AdvancedChatAppGenerator
+from core.app.apps.common.workflow_response_converter import WorkflowResponseConverter
+from core.app.apps.message_generator import MessageGenerator
+from core.app.apps.workflow.app_generator import WorkflowAppGenerator
+from extensions.ext_database import db
+from libs.login import current_account_with_tenant, login_required
+from models import App
+from models.enums import CreatorUserRole
+from models.human_input import RecipientType
+from models.model import AppMode
+from models.workflow import WorkflowRun
+from repositories.factory import DifyAPIRepositoryFactory
+from services.human_input_service import Form, HumanInputService
+from services.workflow_event_snapshot_service import build_workflow_event_stream
+
+logger = logging.getLogger(__name__)
+
+
+def _jsonify_form_definition(form: Form) -> Response:
+    payload = form.get_definition().model_dump()
+    payload["expiration_time"] = int(form.expiration_time.timestamp())
+    return Response(json.dumps(payload, ensure_ascii=False), mimetype="application/json")
+
+
+@console_ns.route("/form/human_input/<string:form_token>")
+class ConsoleHumanInputFormApi(Resource):
+    """Console API for getting human input form definition."""
+
+    @staticmethod
+    def _ensure_console_access(form: Form):
+        _, current_tenant_id = current_account_with_tenant()
+
+        if form.tenant_id != current_tenant_id:
+            raise NotFoundError("App not found")
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, form_token: str):
+        """
+        Get human input form definition by form token.
+
+        GET /console/api/form/human_input/<form_token>
+        """
+        service = HumanInputService(db.engine)
+        form = service.get_form_definition_by_token_for_console(form_token)
+        if form is None:
+            raise NotFoundError(f"form not found, token={form_token}")
+
+        self._ensure_console_access(form)
+
+        return _jsonify_form_definition(form)
+
+    @account_initialization_required
+    @login_required
+    def post(self, form_token: str):
+        """
+        Submit human input form by form token.
+
+        POST /console/api/form/human_input/<form_token>
+
+        Request body:
+        {
+            "inputs": {
+                "content": "User input content"
+            },
+            "action": "Approve"
+        }
+        """
+        parser = reqparse.RequestParser()
+        parser.add_argument("inputs", type=dict, required=True, location="json")
+        parser.add_argument("action", type=str, required=True, location="json")
+        args = parser.parse_args()
+        current_user, _ = current_account_with_tenant()
+
+        service = HumanInputService(db.engine)
+        form = service.get_form_by_token(form_token)
+        if form is None:
+            raise NotFoundError(f"form not found, token={form_token}")
+
+        self._ensure_console_access(form)
+
+        recipient_type = form.recipient_type
+        if recipient_type not in {RecipientType.CONSOLE, RecipientType.BACKSTAGE}:
+            raise NotFoundError(f"form not found, token={form_token}")
+        # The type checker is not smart enought to validate the following invariant.
+        # So we need to assert it manually.
+        assert recipient_type is not None, "recipient_type cannot be None here."
+
+        service.submit_form_by_token(
+            recipient_type=recipient_type,
+            form_token=form_token,
+            selected_action_id=args["action"],
+            form_data=args["inputs"],
+            submission_user_id=current_user.id,
+        )
+
+        return jsonify({})
+
+
+@console_ns.route("/workflow/<string:workflow_run_id>/events")
+class ConsoleWorkflowEventsApi(Resource):
+    """Console API for getting workflow execution events after resume."""
+
+    @account_initialization_required
+    @login_required
+    def get(self, workflow_run_id: str):
+        """
+        Get workflow execution events stream after resume.
+
+        GET /console/api/workflow/<workflow_run_id>/events
+
+        Returns Server-Sent Events stream.
+        """
+
+        user, tenant_id = current_account_with_tenant()
+        session_maker = sessionmaker(db.engine)
+        repo = DifyAPIRepositoryFactory.create_api_workflow_run_repository(session_maker)
+        workflow_run = repo.get_workflow_run_by_id_and_tenant_id(
+            tenant_id=tenant_id,
+            run_id=workflow_run_id,
+        )
+        if workflow_run is None:
+            raise NotFoundError(f"WorkflowRun not found, id={workflow_run_id}")
+
+        if workflow_run.created_by_role != CreatorUserRole.ACCOUNT:
+            raise NotFoundError(f"WorkflowRun not created by account, id={workflow_run_id}")
+
+        if workflow_run.created_by != user.id:
+            raise NotFoundError(f"WorkflowRun not created by the current account, id={workflow_run_id}")
+
+        with Session(expire_on_commit=False, bind=db.engine) as session:
+            app = _retrieve_app_for_workflow_run(session, workflow_run)
+
+        if workflow_run.finished_at is not None:
+            # TODO(QuantumGhost): should we modify the handling for finished workflow run here?
+            response = WorkflowResponseConverter.workflow_run_result_to_finish_response(
+                task_id=workflow_run.id,
+                workflow_run=workflow_run,
+                creator_user=user,
+            )
+
+            payload = response.model_dump(mode="json")
+            payload["event"] = response.event.value
+
+            def _generate_finished_events() -> Generator[str, None, None]:
+                yield f"data: {json.dumps(payload)}\n\n"
+
+            event_generator = _generate_finished_events
+
+        else:
+            msg_generator = MessageGenerator()
+            if app.mode == AppMode.ADVANCED_CHAT:
+                generator = AdvancedChatAppGenerator()
+            elif app.mode == AppMode.WORKFLOW:
+                generator = WorkflowAppGenerator()
+            else:
+                raise InvalidArgumentError(f"cannot subscribe to workflow run, workflow_run_id={workflow_run.id}")
+
+            include_state_snapshot = request.args.get("include_state_snapshot", "false").lower() == "true"
+
+            def _generate_stream_events():
+                if include_state_snapshot:
+                    return generator.convert_to_event_stream(
+                        build_workflow_event_stream(
+                            app_mode=AppMode(app.mode),
+                            workflow_run=workflow_run,
+                            tenant_id=workflow_run.tenant_id,
+                            app_id=workflow_run.app_id,
+                            session_maker=session_maker,
+                        )
+                    )
+                return generator.convert_to_event_stream(
+                    msg_generator.retrieve_events(AppMode(app.mode), workflow_run.id),
+                )
+
+            event_generator = _generate_stream_events
+
+        return Response(
+            event_generator(),
+            mimetype="text/event-stream",
+            headers={
+                "Cache-Control": "no-cache",
+                "Connection": "keep-alive",
+            },
+        )
+
+
+def _retrieve_app_for_workflow_run(session: Session, workflow_run: WorkflowRun):
+    query = select(App).where(
+        App.id == workflow_run.app_id,
+        App.tenant_id == workflow_run.tenant_id,
+    )
+    app = session.scalars(query).first()
+    if app is None:
+        raise AssertionError(
+            f"App not found for WorkflowRun, workflow_run_id={workflow_run.id}, "
+            f"app_id={workflow_run.app_id}, tenant_id={workflow_run.tenant_id}"
+        )
+
+    return app

api/controllers/console/notification.py

@@ -0,0 +1,90 @@
+from flask import request
+from flask_restx import Resource
+from pydantic import BaseModel, Field
+
+from controllers.console import console_ns
+from controllers.console.wraps import account_initialization_required, only_edition_cloud, setup_required
+from libs.login import current_account_with_tenant, login_required
+from services.billing_service import BillingService
+
+# Notification content is stored under three lang tags.
+_FALLBACK_LANG = "en-US"
+
+
+def _pick_lang_content(contents: dict, lang: str) -> dict:
+    """Return the single LangContent for *lang*, falling back to English."""
+    return contents.get(lang) or contents.get(_FALLBACK_LANG) or next(iter(contents.values()), {})
+
+
+class DismissNotificationPayload(BaseModel):
+    notification_id: str = Field(...)
+
+
+@console_ns.route("/notification")
+class NotificationApi(Resource):
+    @console_ns.doc("get_notification")
+    @console_ns.doc(
+        description=(
+            "Return the active in-product notification for the current user "
+            "in their interface language (falls back to English if unavailable). "
+            "The notification is NOT marked as seen here; call POST /notification/dismiss "
+            "when the user explicitly closes the modal."
+        ),
+        responses={
+            200: "Success — inspect should_show to decide whether to render the modal",
+            401: "Unauthorized",
+        },
+    )
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @only_edition_cloud
+    def get(self):
+        current_user, _ = current_account_with_tenant()
+
+        result = BillingService.get_account_notification(str(current_user.id))
+
+        # Proto JSON uses camelCase field names (Kratos default marshaling).
+        if not result.get("shouldShow"):
+            return {"should_show": False, "notifications": []}, 200
+
+        lang = current_user.interface_language or _FALLBACK_LANG
+
+        notifications = []
+        for notification in result.get("notifications") or []:
+            contents: dict = notification.get("contents") or {}
+            lang_content = _pick_lang_content(contents, lang)
+            notifications.append(
+                {
+                    "notification_id": notification.get("notificationId"),
+                    "frequency": notification.get("frequency"),
+                    "lang": lang_content.get("lang", lang),
+                    "title": lang_content.get("title", ""),
+                    "subtitle": lang_content.get("subtitle", ""),
+                    "body": lang_content.get("body", ""),
+                    "title_pic_url": lang_content.get("titlePicUrl", ""),
+                }
+            )
+
+        return {"should_show": bool(notifications), "notifications": notifications}, 200
+
+
+@console_ns.route("/notification/dismiss")
+class NotificationDismissApi(Resource):
+    @console_ns.doc("dismiss_notification")
+    @console_ns.doc(
+        description="Mark a notification as dismissed for the current user.",
+        responses={200: "Success", 401: "Unauthorized"},
+    )
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @only_edition_cloud
+    def post(self):
+        current_user, _ = current_account_with_tenant()
+        payload = DismissNotificationPayload.model_validate(request.get_json())
+        BillingService.dismiss_notification(
+            notification_id=payload.notification_id,
+            account_id=str(current_user.id),
+        )
+        return {"result": "success"}, 200

api/controllers/console/remote_files.py

@@ -1,6 +1,7 @@
 import urllib.parse
 
 import httpx
+from flask_restx import Resource
 from pydantic import BaseModel, Field
 
 import services
@@ -10,12 +11,12 @@ from controllers.common.errors import (
     RemoteFileUploadError,
     UnsupportedFileTypeError,
 )
-from controllers.fastopenapi import console_router
-from core.file import helpers as file_helpers
+from controllers.console import console_ns
 from core.helper import ssrf_proxy
+from dify_graph.file import helpers as file_helpers
 from extensions.ext_database import db
 from fields.file_fields import FileWithSignedUrl, RemoteFileInfo
-from libs.login import current_account_with_tenant
+from libs.login import current_account_with_tenant, login_required
 from services.file_service import FileService
 
 
@@ -23,69 +24,73 @@ class RemoteFileUploadPayload(BaseModel):
     url: str = Field(..., description="URL to fetch")
 
 
-@console_router.get(
-    "/remote-files/<path:url>",
-    response_model=RemoteFileInfo,
-    tags=["console"],
-)
-def get_remote_file_info(url: str) -> RemoteFileInfo:
-    decoded_url = urllib.parse.unquote(url)
-    resp = ssrf_proxy.head(decoded_url)
-    if resp.status_code != httpx.codes.OK:
-        resp = ssrf_proxy.get(decoded_url, timeout=3)
-    resp.raise_for_status()
-    return RemoteFileInfo(
-        file_type=resp.headers.get("Content-Type", "application/octet-stream"),
-        file_length=int(resp.headers.get("Content-Length", 0)),
-    )
-
-
-@console_router.post(
-    "/remote-files/upload",
-    response_model=FileWithSignedUrl,
-    tags=["console"],
-    status_code=201,
-)
-def upload_remote_file(payload: RemoteFileUploadPayload) -> FileWithSignedUrl:
-    url = payload.url
-
-    try:
-        resp = ssrf_proxy.head(url=url)
+@console_ns.route("/remote-files/<path:url>")
+class GetRemoteFileInfo(Resource):
+    @login_required
+    def get(self, url: str):
+        decoded_url = urllib.parse.unquote(url)
+        resp = ssrf_proxy.head(decoded_url)
         if resp.status_code != httpx.codes.OK:
-            resp = ssrf_proxy.get(url=url, timeout=3, follow_redirects=True)
-        if resp.status_code != httpx.codes.OK:
-            raise RemoteFileUploadError(f"Failed to fetch file from {url}: {resp.text}")
-    except httpx.RequestError as e:
-        raise RemoteFileUploadError(f"Failed to fetch file from {url}: {str(e)}")
+            resp = ssrf_proxy.get(decoded_url, timeout=3)
+        resp.raise_for_status()
+        return RemoteFileInfo(
+            file_type=resp.headers.get("Content-Type", "application/octet-stream"),
+            file_length=int(resp.headers.get("Content-Length", 0)),
+        ).model_dump(mode="json")
 
-    file_info = helpers.guess_file_info_from_response(resp)
 
-    if not FileService.is_file_size_within_limit(extension=file_info.extension, file_size=file_info.size):
-        raise FileTooLargeError
+@console_ns.route("/remote-files/upload")
+class RemoteFileUpload(Resource):
+    @login_required
+    def post(self):
+        payload = RemoteFileUploadPayload.model_validate(console_ns.payload)
+        url = payload.url
 
-    content = resp.content if resp.request.method == "GET" else ssrf_proxy.get(url).content
+        # Try to fetch remote file metadata/content first
+        try:
+            resp = ssrf_proxy.head(url=url)
+            if resp.status_code != httpx.codes.OK:
+                resp = ssrf_proxy.get(url=url, timeout=3, follow_redirects=True)
+            if resp.status_code != httpx.codes.OK:
+                # Normalize into a user-friendly error message expected by tests
+                raise RemoteFileUploadError(f"Failed to fetch file from {url}: {resp.text}")
+        except httpx.RequestError as e:
+            raise RemoteFileUploadError(f"Failed to fetch file from {url}: {str(e)}")
 
-    try:
-        user, _ = current_account_with_tenant()
-        upload_file = FileService(db.engine).upload_file(
-            filename=file_info.filename,
-            content=content,
-            mimetype=file_info.mimetype,
-            user=user,
-            source_url=url,
+        file_info = helpers.guess_file_info_from_response(resp)
+
+        # Enforce file size limit with 400 (Bad Request) per tests' expectation
+        if not FileService.is_file_size_within_limit(extension=file_info.extension, file_size=file_info.size):
+            raise FileTooLargeError()
+
+        # Load content if needed
+        content = resp.content if resp.request.method == "GET" else ssrf_proxy.get(url).content
+
+        try:
+            user, _ = current_account_with_tenant()
+            upload_file = FileService(db.engine).upload_file(
+                filename=file_info.filename,
+                content=content,
+                mimetype=file_info.mimetype,
+                user=user,
+                source_url=url,
+            )
+        except services.errors.file.FileTooLargeError as file_too_large_error:
+            raise FileTooLargeError(file_too_large_error.description)
+        except services.errors.file.UnsupportedFileTypeError:
+            raise UnsupportedFileTypeError()
+
+        # Success: return created resource with 201 status
+        return (
+            FileWithSignedUrl(
+                id=upload_file.id,
+                name=upload_file.name,
+                size=upload_file.size,
+                extension=upload_file.extension,
+                url=file_helpers.get_signed_file_url(upload_file_id=upload_file.id),
+                mime_type=upload_file.mime_type,
+                created_by=upload_file.created_by,
+                created_at=int(upload_file.created_at.timestamp()),
+            ).model_dump(mode="json"),
+            201,
         )
-    except services.errors.file.FileTooLargeError as file_too_large_error:
-        raise FileTooLargeError(file_too_large_error.description)
-    except services.errors.file.UnsupportedFileTypeError:
-        raise UnsupportedFileTypeError()
-
-    return FileWithSignedUrl(
-        id=upload_file.id,
-        name=upload_file.name,
-        size=upload_file.size,
-        extension=upload_file.extension,
-        url=file_helpers.get_signed_file_url(upload_file_id=upload_file.id),
-        mime_type=upload_file.mime_type,
-        created_by=upload_file.created_by,
-        created_at=int(upload_file.created_at.timestamp()),
-    )

api/controllers/console/setup.py

@@ -42,7 +42,15 @@ class SetupResponse(BaseModel):
     tags=["console"],
 )
 def get_setup_status_api() -> SetupStatusResponse:
-    """Get system setup status."""
+    """Get system setup status.
+
+    NOTE: This endpoint is unauthenticated by design.
+
+    During first-time bootstrap there is no admin account yet, so frontend initialization must be
+    able to query setup progress before any login flow exists.
+
+    Only bootstrap-safe status information should be returned by this endpoint.
+    """
     if dify_config.EDITION == "SELF_HOSTED":
         setup_status = get_setup_status()
         if setup_status and not isinstance(setup_status, bool):
@@ -61,7 +69,12 @@ def get_setup_status_api() -> SetupStatusResponse:
 )
 @only_edition_self_hosted
 def setup_system(payload: SetupRequestPayload) -> SetupResponse:
-    """Initialize system setup with admin account."""
+    """Initialize system setup with admin account.
+
+    NOTE: This endpoint is unauthenticated by design for first-time bootstrap.
+    Access is restricted by deployment mode (`SELF_HOSTED`), one-time setup guards,
+    and init-password validation rather than user session authentication.
+    """
     if get_setup_status():
         raise AlreadySetupError()
 

api/controllers/console/tag/tags.py

@@ -120,7 +120,7 @@ class TagUpdateDeleteApi(Resource):
 
         TagService.delete_tag(tag_id)
 
-        return 204
+        return "", 204
 
 
 @console_ns.route("/tag-bindings/create")