fix(openapi/apps): move uuid fast-path before tag guard in list endpoint

Explicit re-raise list at L230-238 only covered UnprocessableEntity +
NotChatAppError/NotWorkflowAppError. Other HTTPException subclasses
raised inside handlers (NotFound, BadRequest, ConversationCompletedError,
ProviderNotInitializeError, ProviderQuotaExceededError, ...) hit
`except Exception` and got squashed to 500. Replace with
`except HTTPException: raise`.

Refactor bundled: collapse 3x try/except ladder into
_translate_service_errors() ctxmgr, inline single-call constraint
enforcers, drop wasted dict() copy in _unpack_blocking, trim module
docstring and stale spec doc reference. -60 net lines.

.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/component-refactoring/SKILL.md

@@ -187,53 +187,12 @@ const Template = useMemo(() => {
 
 **When**: Component directly handles API calls, data transformation, or complex async operations.
 
-**Dify Convention**: Use `@tanstack/react-query` hooks from `web/service/use-*.ts` or create custom data hooks.
-
-```typescript
-// ❌ Before: API logic in component
-const MCPServiceCard = () => {
-  const [basicAppConfig, setBasicAppConfig] = useState({})
-  
-  useEffect(() => {
-    if (isBasicApp && appId) {
-      (async () => {
-        const res = await fetchAppDetail({ url: '/apps', id: appId })
-        setBasicAppConfig(res?.model_config || {})
-      })()
-    }
-  }, [appId, isBasicApp])
-  
-  // More API-related logic...
-}
-
-// ✅ After: Extract to data hook using React Query
-// use-app-config.ts
-import { useQuery } from '@tanstack/react-query'
-import { get } from '@/service/base'
-
-const NAME_SPACE = 'appConfig'
-
-export const useAppConfig = (appId: string, isBasicApp: boolean) => {
-  return useQuery({
-    enabled: isBasicApp && !!appId,
-    queryKey: [NAME_SPACE, 'detail', appId],
-    queryFn: () => get<AppDetailResponse>(`/apps/${appId}`),
-    select: data => data?.model_config || {},
-  })
-}
-
-// Component becomes cleaner
-const MCPServiceCard = () => {
-  const { data: config, isLoading } = useAppConfig(appId, isBasicApp)
-  // UI only
-}
-```
-
-**React Query Best Practices in Dify**:
-- Define `NAME_SPACE` for query key organization
-- Use `enabled` option for conditional fetching
-- Use `select` for data transformation
-- Export invalidation hooks: `useInvalidXxx`
+**Dify Convention**:
+- This skill is for component decomposition, not query/mutation design.
+- When refactoring data fetching, follow `web/AGENTS.md`.
+- Use `frontend-query-mutation` for contracts, query shape, data-fetching wrappers, query/mutation call-site patterns, conditional queries, invalidation, and mutation error handling.
+- Do not introduce deprecated `useInvalid` / `useReset`.
+- Do not add thin passthrough `useQuery` wrappers during refactoring; only extract a custom hook when it truly orchestrates multiple queries/mutations or shared derived state.
 
 **Dify Examples**:
 - `web/service/use-workflow.ts`

.agents/skills/component-refactoring/references/hook-extraction.md

@@ -155,48 +155,14 @@ const Configuration: FC = () => {
 
 ## Common Hook Patterns in Dify
 
-### 1. Data Fetching Hook (React Query)
+### 1. Data Fetching / Mutation Hooks
 
-```typescript
-// Pattern: Use @tanstack/react-query for data fetching
-import { useQuery, useQueryClient } from '@tanstack/react-query'
-import { get } from '@/service/base'
-import { useInvalid } from '@/service/use-base'
+When hook extraction touches query or mutation code, do not use this reference as the source of truth for data-layer patterns.
 
-const NAME_SPACE = 'appConfig'
-
-// Query keys for cache management
-export const appConfigQueryKeys = {
-  detail: (appId: string) => [NAME_SPACE, 'detail', appId] as const,
-}
-
-// Main data hook
-export const useAppConfig = (appId: string) => {
-  return useQuery({
-    enabled: !!appId,
-    queryKey: appConfigQueryKeys.detail(appId),
-    queryFn: () => get<AppDetailResponse>(`/apps/${appId}`),
-    select: data => data?.model_config || null,
-  })
-}
-
-// Invalidation hook for refreshing data
-export const useInvalidAppConfig = () => {
-  return useInvalid([NAME_SPACE])
-}
-
-// Usage in component
-const Component = () => {
-  const { data: config, isLoading, error, refetch } = useAppConfig(appId)
-  const invalidAppConfig = useInvalidAppConfig()
-  
-  const handleRefresh = () => {
-    invalidAppConfig() // Invalidates cache and triggers refetch
-  }
-  
-  return <div>...</div>
-}
-```
+- Follow `web/AGENTS.md` first.
+- Use `frontend-query-mutation` for contracts, query shape, data-fetching wrappers, query/mutation call-site patterns, conditional queries, invalidation, and mutation error handling.
+- Do not introduce deprecated `useInvalid` / `useReset`.
+- Do not extract thin passthrough `useQuery` hooks; only extract orchestration hooks.
 
 ### 2. Form State Hook
 

.agents/skills/e2e-cucumber-playwright/SKILL.md

@@ -0,0 +1,79 @@
+---
+name: e2e-cucumber-playwright
+description: Write, update, or review Dify end-to-end tests under `e2e/` that use Cucumber, Gherkin, and Playwright. Use when the task involves `.feature` files, `features/step-definitions/`, `features/support/`, `DifyWorld`, scenario tags, locator/assertion choices, or E2E testing best practices for this repository.
+---
+
+# Dify E2E Cucumber + Playwright
+
+Use this skill for Dify's repository-level E2E suite in `e2e/`. Use [`e2e/AGENTS.md`](../../../e2e/AGENTS.md) as the canonical guide for local architecture and conventions, then apply Playwright/Cucumber best practices only where they fit the current suite.
+
+## Scope
+
+- Use this skill for `.feature` files, Cucumber step definitions, `DifyWorld`, hooks, tags, and E2E review work under `e2e/`.
+- Do not use this skill for Vitest or React Testing Library work under `web/`; use `frontend-testing` instead.
+- Do not use this skill for backend test or API review tasks under `api/`.
+
+## Read Order
+
+1. Read [`e2e/AGENTS.md`](../../../e2e/AGENTS.md) first.
+2. Read only the files directly involved in the task:
+   - target `.feature` files under `e2e/features/`
+   - related step files under `e2e/features/step-definitions/`
+   - `e2e/features/support/hooks.ts` and `e2e/features/support/world.ts` when session lifecycle or shared state matters
+   - `e2e/scripts/run-cucumber.ts` and `e2e/cucumber.config.ts` when tags or execution flow matter
+3. Read [`references/playwright-best-practices.md`](references/playwright-best-practices.md) only when locator, assertion, isolation, or waiting choices are involved.
+4. Read [`references/cucumber-best-practices.md`](references/cucumber-best-practices.md) only when scenario wording, step granularity, tags, or expression design are involved.
+5. Re-check official docs with Context7 before introducing a new Playwright or Cucumber pattern.
+
+## Local Rules
+
+- `e2e/` uses Cucumber for scenarios and Playwright as the browser layer.
+- `DifyWorld` is the per-scenario context object. Type `this` as `DifyWorld` and use `async function`, not arrow functions.
+- Keep glue organized by capability under `e2e/features/step-definitions/`; use `common/` only for broadly reusable steps.
+- Browser session behavior comes from `features/support/hooks.ts`:
+  - default: authenticated session with shared storage state
+  - `@unauthenticated`: clean browser context
+  - `@authenticated`: readability/selective-run tag only unless implementation changes
+  - `@fresh`: only for `e2e:full*` flows
+- Do not import Playwright Test runner patterns that bypass the current Cucumber + `DifyWorld` architecture unless the task is explicitly about changing that architecture.
+
+## Workflow
+
+1. Rebuild local context.
+   - Inspect the target feature area.
+   - Reuse an existing step when wording and behavior already match.
+   - Add a new step only for a genuinely new user action or assertion.
+   - Keep edits close to the current capability folder unless the step is broadly reusable.
+2. Write behavior-first scenarios.
+   - Describe user-observable behavior, not DOM mechanics.
+   - Keep each scenario focused on one workflow or outcome.
+   - Keep scenarios independent and re-runnable.
+3. Write step definitions in the local style.
+   - Keep one step to one user-visible action or one assertion.
+   - Prefer Cucumber Expressions such as `{string}` and `{int}`.
+   - Scope locators to stable containers when the page has repeated elements.
+   - Avoid page-object layers or extra helper abstractions unless repeated complexity clearly justifies them.
+4. Use Playwright in the local style.
+   - Prefer user-facing locators: `getByRole`, `getByLabel`, `getByPlaceholder`, `getByText`, then `getByTestId` for explicit contracts.
+   - Use web-first `expect(...)` assertions.
+   - Do not use `waitForTimeout`, manual polling, or raw visibility checks when a locator action or retrying assertion already expresses the behavior.
+5. Validate narrowly.
+   - Run the narrowest tagged scenario or flow that exercises the change.
+   - Run `pnpm -C e2e check`.
+   - Broaden verification only when the change affects hooks, tags, setup, or shared step semantics.
+
+## Review Checklist
+
+- Does the scenario describe behavior rather than implementation?
+- Does it fit the current session model, tags, and `DifyWorld` usage?
+- Should an existing step be reused instead of adding a new one?
+- Are locators user-facing and assertions web-first?
+- Does the change introduce hidden coupling across scenarios, tags, or instance state?
+- Does it document or implement behavior that differs from the real hooks or configuration?
+
+Lead findings with correctness, flake risk, and architecture drift.
+
+## References
+
+- [`references/playwright-best-practices.md`](references/playwright-best-practices.md)
+- [`references/cucumber-best-practices.md`](references/cucumber-best-practices.md)

.agents/skills/e2e-cucumber-playwright/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: "E2E Cucumber + Playwright"
+  short_description: "Write and review Dify E2E scenarios."
+  default_prompt: "Use $e2e-cucumber-playwright to write or review a Dify E2E scenario under e2e/."

.agents/skills/e2e-cucumber-playwright/references/cucumber-best-practices.md

@@ -0,0 +1,93 @@
+# Cucumber Best Practices For Dify E2E
+
+Use this reference when writing or reviewing Gherkin scenarios, step definitions, parameter expressions, and step reuse in Dify's `e2e/` suite.
+
+Official sources:
+
+- https://cucumber.io/docs/guides/10-minute-tutorial/
+- https://cucumber.io/docs/cucumber/step-definitions/
+- https://cucumber.io/docs/cucumber/cucumber-expressions/
+
+## What Matters Most
+
+### 1. Treat scenarios as executable specifications
+
+Cucumber scenarios should describe examples of behavior, not test implementation recipes.
+
+Apply it like this:
+
+- write what the user does and what should happen
+- avoid UI-internal wording such as selector details, DOM structure, or component names
+- keep language concrete enough that the scenario reads like living documentation
+
+### 2. Keep scenarios focused
+
+A scenario should usually prove one workflow or business outcome. If a scenario wanders across several unrelated behaviors, split it.
+
+In Dify's suite, this means:
+
+- one capability-focused scenario per feature path
+- no long setup chains when existing bootstrap or reusable steps already cover them
+- no hidden dependency on another scenario's side effects
+
+### 3. Reuse steps, but only when behavior really matches
+
+Good reuse reduces duplication. Bad reuse hides meaning.
+
+Prefer reuse when:
+
+- the user action is genuinely the same
+- the expected outcome is genuinely the same
+- the wording stays natural across features
+
+Write a new step when:
+
+- the behavior is materially different
+- reusing the old wording would make the scenario misleading
+- a supposedly generic step would become an implementation-detail wrapper
+
+### 4. Prefer Cucumber Expressions
+
+Use Cucumber Expressions for parameters unless regex is clearly necessary.
+
+Common examples:
+
+- `{string}` for labels, names, and visible text
+- `{int}` for counts
+- `{float}` for decimal values
+- `{word}` only when the value is truly a single token
+
+Keep expressions readable. If a step needs complicated parsing logic, first ask whether the scenario wording should be simpler.
+
+### 5. Keep step definitions thin and meaningful
+
+Step definitions are glue between Gherkin and automation, not a second abstraction language.
+
+For Dify:
+
+- type `this` as `DifyWorld`
+- use `async function`
+- keep each step to one user-visible action or assertion
+- rely on `DifyWorld` and existing support code for shared context
+- avoid leaking cross-scenario state
+
+### 6. Use tags intentionally
+
+Tags should communicate run scope or session semantics, not become ad hoc metadata.
+
+In Dify's current suite:
+
+- capability tags group related scenarios
+- `@unauthenticated` changes session behavior
+- `@authenticated` is descriptive/selective, not a behavior switch by itself
+- `@fresh` belongs to reset/full-install flows only
+
+If a proposed tag implies behavior, verify that hooks or runner configuration actually implement it.
+
+## Review Questions
+
+- Does the scenario read like a real example of product behavior?
+- Are the steps behavior-oriented instead of implementation-oriented?
+- Is a reused step still truthful in this feature?
+- Is a new tag documenting real behavior, or inventing semantics that the suite does not implement?
+- Would a new reader understand the outcome without opening the step-definition file?

.agents/skills/e2e-cucumber-playwright/references/playwright-best-practices.md

@@ -0,0 +1,96 @@
+# Playwright Best Practices For Dify E2E
+
+Use this reference when writing or reviewing locator, assertion, isolation, or synchronization logic for Dify's Cucumber-based E2E suite.
+
+Official sources:
+
+- https://playwright.dev/docs/best-practices
+- https://playwright.dev/docs/locators
+- https://playwright.dev/docs/test-assertions
+- https://playwright.dev/docs/browser-contexts
+
+## What Matters Most
+
+### 1. Keep scenarios isolated
+
+Playwright's model is built around clean browser contexts so one test does not leak into another. In Dify's suite, that principle maps to per-scenario session setup in `features/support/hooks.ts` and `DifyWorld`.
+
+Apply it like this:
+
+- do not depend on another scenario having run first
+- do not persist ad hoc scenario state outside `DifyWorld`
+- do not couple ordinary scenarios to `@fresh` behavior
+- when a flow needs special auth/session semantics, express that through the existing tag model or explicit hook changes
+
+### 2. Prefer user-facing locators
+
+Playwright recommends built-in locators that reflect what users perceive on the page.
+
+Preferred order in this repository:
+
+1. `getByRole`
+2. `getByLabel`
+3. `getByPlaceholder`
+4. `getByText`
+5. `getByTestId` when an explicit test contract is the most stable option
+
+Avoid raw CSS/XPath selectors unless no stable user-facing contract exists and adding one is not practical.
+
+Also remember:
+
+- repeated content usually needs scoping to a stable container
+- exact text matching is often too brittle when role/name or label already exists
+- `getByTestId` is acceptable when semantics are weak but the contract is intentional
+
+### 3. Use web-first assertions
+
+Playwright assertions auto-wait and retry. Prefer them over manual state inspection.
+
+Prefer:
+
+- `await expect(page).toHaveURL(...)`
+- `await expect(locator).toBeVisible()`
+- `await expect(locator).toBeHidden()`
+- `await expect(locator).toBeEnabled()`
+- `await expect(locator).toHaveText(...)`
+
+Avoid:
+
+- `expect(await locator.isVisible()).toBe(true)`
+- custom polling loops for DOM state
+- `waitForTimeout` as synchronization
+
+If a condition genuinely needs custom retry logic, use Playwright's polling/assertion tools deliberately and keep that choice local and explicit.
+
+### 4. Let actions wait for actionability
+
+Locator actions already wait for the element to be actionable. Do not preface every click/fill with extra timing logic unless the action needs a specific visible/ready assertion for clarity.
+
+Good pattern:
+
+- assert a meaningful visible state when that is part of the behavior
+- then click/fill/select via locator APIs
+
+Bad pattern:
+
+- stack arbitrary waits before every action
+- wait on unstable implementation details instead of the visible state the user cares about
+
+### 5. Match debugging to the current suite
+
+Playwright's wider ecosystem supports traces and rich debugging tools. Dify's current suite already captures:
+
+- full-page screenshots
+- page HTML
+- console errors
+- page errors
+
+Use the existing artifact flow by default. If a task is specifically about improving diagnostics, confirm the change fits the current Cucumber architecture before importing broader Playwright tooling.
+
+## Review Questions
+
+- Would this locator survive DOM refactors that do not change user-visible behavior?
+- Is this assertion using Playwright's retrying semantics?
+- Is any explicit wait masking a real readiness problem?
+- Does this code preserve per-scenario isolation?
+- Is a new abstraction really needed, or does it bypass the existing `DifyWorld` + step-definition model?

.agents/skills/frontend-query-mutation/SKILL.md

@@ -0,0 +1,44 @@
+---
+name: frontend-query-mutation
+description: Guide for implementing Dify frontend query and mutation patterns with TanStack Query and oRPC. Trigger when creating or updating contracts in web/contract, wiring router composition, consuming consoleQuery or marketplaceQuery in components or services, deciding whether to call queryOptions() directly or extract a helper or use-* hook, handling conditional queries, cache invalidation, mutation error handling, or migrating legacy service calls to contract-first query and mutation helpers.
+---
+
+# Frontend Query & Mutation
+
+## Intent
+
+- Keep contract as the single source of truth in `web/contract/*`.
+- Prefer contract-shaped `queryOptions()` and `mutationOptions()`.
+- Keep invalidation and mutation flow knowledge in the service layer.
+- Keep abstractions minimal to preserve TypeScript inference.
+
+## Workflow
+
+1. Identify the change surface.
+   - Read `references/contract-patterns.md` for contract files, router composition, client helpers, and query or mutation call-site shape.
+   - Read `references/runtime-rules.md` for conditional queries, invalidation, error handling, and legacy migrations.
+   - Read both references when a task spans contract shape and runtime behavior.
+2. Implement the smallest abstraction that fits the task.
+   - Default to direct `useQuery(...)` or `useMutation(...)` calls with oRPC helpers at the call site.
+   - Extract a small shared query helper only when multiple call sites share the same extra options.
+   - Create `web/service/use-{domain}.ts` only for orchestration or shared domain behavior.
+3. Preserve Dify conventions.
+   - Keep contract inputs in `{ params, query?, body? }` shape.
+   - Bind invalidation in the service-layer mutation definition.
+   - Prefer `mutate(...)`; use `mutateAsync(...)` only when Promise semantics are required.
+
+## Files Commonly Touched
+
+- `web/contract/console/*.ts`
+- `web/contract/marketplace.ts`
+- `web/contract/router.ts`
+- `web/service/client.ts`
+- `web/service/use-*.ts`
+- component and hook call sites using `consoleQuery` or `marketplaceQuery`
+
+## References
+
+- Use `references/contract-patterns.md` for contract shape, router registration, query and mutation helpers, and anti-patterns that degrade inference.
+- Use `references/runtime-rules.md` for conditional queries, invalidation, `mutate` versus `mutateAsync`, and legacy migration rules.
+
+Treat this skill as the single query and mutation entry point for Dify frontend work. Keep detailed rules in the reference files instead of duplicating them in project docs.

.agents/skills/frontend-query-mutation/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: "Frontend Query & Mutation"
+  short_description: "Dify TanStack Query and oRPC patterns"
+  default_prompt: "Use this skill when implementing or reviewing Dify frontend contracts, query and mutation call sites, conditional queries, invalidation, or legacy query/mutation migrations."

.agents/skills/frontend-query-mutation/references/contract-patterns.md

@@ -0,0 +1,98 @@
+# Contract Patterns
+
+## Table of Contents
+
+- Intent
+- Minimal structure
+- Core workflow
+- Query usage decision rule
+- Mutation usage decision rule
+- Anti-patterns
+- Contract rules
+- Type export
+
+## Intent
+
+- Keep contract as the single source of truth in `web/contract/*`.
+- Default query usage to 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
+├── router.ts
+├── marketplace.ts
+└── console/
+    ├── billing.ts
+    └── ...other domains
+web/service/client.ts
+```
+
+## Core Workflow
+
+1. Define contract in `web/contract/console/{domain}.ts` or `web/contract/marketplace.ts`.
+   - Use `base.route({...}).output(type<...>())` as the baseline.
+   - Add `.input(type<...>())` only when the request has `params`, `query`, or `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 utilities.
+
+```typescript
+import { useQuery } from '@tanstack/react-query'
+import { consoleQuery } from '@/service/client'
+
+const invoiceQuery = useQuery(consoleQuery.billing.invoices.queryOptions({
+  staleTime: 5 * 60 * 1000,
+  throwOnError: true,
+  select: invoice => invoice.url,
+}))
+```
+
+## Query Usage Decision Rule
+
+1. Default to direct `*.queryOptions(...)` usage at the call site.
+2. If 3 or more call sites share the same extra options, extract a small query helper, not a `use-*` passthrough hook.
+3. Create `web/service/use-{domain}.ts` only for orchestration.
+   - Combine multiple queries or 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 to mutation helpers from `consoleQuery` or `marketplaceQuery`, for example `useMutation(consoleQuery.billing.bindPartnerStack.mutationOptions(...))`.
+2. If the mutation flow is heavily custom, use oRPC clients as `mutationFn`, for example `consoleClient.xxx` or `marketplaceClient.xxx`, instead of handwritten non-oRPC mutation logic.
+
+## Anti-Patterns
+
+- Do not wrap `useQuery` with `options?: Partial<UseQueryOptions>`.
+- Do not split local `queryKey` and `queryFn` when oRPC `queryOptions` already exists and fits the use case.
+- Do not create thin `use-*` passthrough hooks for a single endpoint.
+- These patterns can degrade inference, especially around `throwOnError` and `select`, and add unnecessary indirection.
+
+## Contract Rules
+
+- Input structure: always use `{ params, query?, body? }`.
+- No-input `GET`: omit `.input(...)`; do not use `.input(type<unknown>())`.
+- Path params: use `{paramName}` in the path and match it in the `params` object.
+- Router nesting: group by API prefix, for example `/billing/*` becomes `billing: {}`.
+- No barrel files: import directly from specific files.
+- Types: import from `@/types/` and use the `type<T>()` helper.
+- Mutations: prefer `mutationOptions`; use explicit `mutationKey` mainly for defaults, filtering, and devtools.
+
+## Type Export
+
+```typescript
+export type ConsoleInputs = InferContractRouterInputs<typeof consoleRouterContract>
+```

.agents/skills/frontend-query-mutation/references/runtime-rules.md

@@ -0,0 +1,130 @@
+# Runtime Rules
+
+## Table of Contents
+
+- Conditional queries
+- Cache invalidation
+- Key API guide
+- `mutate` vs `mutateAsync`
+- Legacy migration
+
+## Conditional Queries
+
+Prefer contract-shaped `queryOptions(...)`.
+When required input is missing, prefer `input: skipToken` instead of placeholder params or non-null assertions.
+Use `enabled` only for extra business gating after the input itself is already valid.
+
+```typescript
+import { skipToken, useQuery } from '@tanstack/react-query'
+
+// Disable the query by skipping input construction.
+function useAccessMode(appId: string | undefined) {
+  return useQuery(consoleQuery.accessControl.appAccessMode.queryOptions({
+    input: appId
+      ? { params: { appId } }
+      : skipToken,
+  }))
+}
+
+// Avoid runtime-only guards that bypass type checking.
+function useBadAccessMode(appId: string | undefined) {
+  return useQuery(consoleQuery.accessControl.appAccessMode.queryOptions({
+    input: { params: { appId: appId! } },
+    enabled: !!appId,
+  }))
+}
+```
+
+## Cache Invalidation
+
+Bind invalidation in the service-layer mutation definition.
+Components may add UI feedback in call-site callbacks, but they should not decide which queries to invalidate.
+
+Use:
+
+- `.key()` for namespace or prefix invalidation
+- `.queryKey(...)` only for exact cache reads or writes such as `getQueryData` and `setQueryData`
+- `queryClient.invalidateQueries(...)` in mutation `onSuccess`
+
+Do not use deprecated `useInvalid` from `use-base.ts`.
+
+```typescript
+// Service layer owns cache invalidation.
+export const useUpdateAccessMode = () => {
+  const queryClient = useQueryClient()
+
+  return useMutation(consoleQuery.accessControl.updateAccessMode.mutationOptions({
+    onSuccess: () => {
+      queryClient.invalidateQueries({
+        queryKey: consoleQuery.accessControl.appWhitelistSubjects.key(),
+      })
+    },
+  }))
+}
+
+// Component only adds UI behavior.
+updateAccessMode({ appId, mode }, {
+  onSuccess: () => toast.success('...'),
+})
+
+// Avoid putting invalidation knowledge in the component.
+mutate({ appId, mode }, {
+  onSuccess: () => {
+    queryClient.invalidateQueries({
+      queryKey: consoleQuery.accessControl.appWhitelistSubjects.key(),
+    })
+  },
+})
+```
+
+## Key API Guide
+
+- `.key(...)`
+  - Use for partial matching operations.
+  - Prefer it for invalidation, refetch, and cancel patterns.
+  - Example: `queryClient.invalidateQueries({ queryKey: consoleQuery.billing.key() })`
+- `.queryKey(...)`
+  - Use for a specific query's full key.
+  - Prefer it for exact cache addressing and direct reads or writes.
+- `.mutationKey(...)`
+  - Use for a specific mutation's full key.
+  - Prefer it for mutation defaults registration, mutation-status filtering, and devtools grouping.
+
+## `mutate` vs `mutateAsync`
+
+Prefer `mutate` by default.
+Use `mutateAsync` only when Promise semantics are truly required, such as parallel mutations or sequential steps with result dependencies.
+
+Rules:
+
+- Event handlers should usually call `mutate(...)` with `onSuccess` or `onError`.
+- Every `await mutateAsync(...)` must be wrapped in `try/catch`.
+- Do not use `mutateAsync` when callbacks already express the flow clearly.
+
+```typescript
+// Default case.
+mutation.mutate(data, {
+  onSuccess: result => router.push(result.url),
+})
+
+// Promise semantics are required.
+try {
+  const order = await createOrder.mutateAsync(orderData)
+  await confirmPayment.mutateAsync({ orderId: order.id, token })
+  router.push(`/orders/${order.id}`)
+}
+catch (error) {
+  toast.error(error instanceof Error ? error.message : 'Unknown error')
+}
+```
+
+## Legacy Migration
+
+When touching old code, migrate it toward these rules:
+
+| Old pattern | New pattern |
+|---|---|
+| `useInvalid(key)` in service layer | `queryClient.invalidateQueries(...)` inside mutation `onSuccess` |
+| component-triggered invalidation after mutation | move invalidation into the service-layer mutation definition |
+| imperative fetch plus manual invalidation | wrap it in `useMutation(...mutationOptions(...))` |
+| `await mutateAsync()` without `try/catch` | switch to `mutate(...)` or add `try/catch` |

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

@@ -63,7 +63,8 @@ pnpm analyze-component <path> --review
 
 ### File Naming
 
-- Test files: `ComponentName.spec.tsx` (same directory as component)
+- Test files: `ComponentName.spec.tsx` inside a same-level `__tests__/` directory
+- Placement rule: Component, hook, and utility tests must live in a sibling `__tests__/` folder at the same level as the source under test. For example, `foo/index.tsx` maps to `foo/__tests__/index.spec.tsx`, and `foo/bar.ts` maps to `foo/__tests__/bar.spec.ts`.
 - Integration tests: `web/__tests__/` directory
 
 ## Test Structure Template
@@ -204,6 +205,16 @@ 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/assets/component-test.template.tsx

@@ -41,7 +41,7 @@ import userEvent from '@testing-library/user-event'
 // Router (if component uses useRouter, usePathname, useSearchParams)
 // WHY: Isolates tests from Next.js routing, enables testing navigation behavior
 // const mockPush = vi.fn()
-// vi.mock('next/navigation', () => ({
+// vi.mock('@/next/navigation', () => ({
 //   useRouter: () => ({ push: mockPush }),
 //   usePathname: () => '/test-path',
 // }))

.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

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

.claude/skills/backend-code-review

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

.claude/skills/e2e-cucumber-playwright

@@ -0,0 +1 @@
+../../.agents/skills/e2e-cucumber-playwright

.claude/skills/frontend-query-mutation

@@ -0,0 +1 @@
+../../.agents/skills/frontend-query-mutation

.claude/skills/orpc-contract-first

@@ -1 +0,0 @@
-../../.agents/skills/orpc-contract-first

.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_publisher,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

.gemini/config.yaml

@@ -0,0 +1,13 @@
+have_fun: false
+memory_config:
+  disabled: false
+code_review:
+  disable: true
+  comment_severity_threshold: MEDIUM
+  max_review_comments: -1
+  pull_request_opened:
+    help: false
+    summary: false
+    code_review: false
+    include_drafts: false
+ignore_patterns: []

.github/CODEOWNERS

@@ -36,7 +36,6 @@
 /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
 
 # Backend - Workflow - Nodes (Agent, Iteration, Loop, LLM)
 /api/core/workflow/nodes/agent/ @Nov1c444

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

@@ -0,0 +1,11 @@
+name: Setup Web Environment
+
+runs:
+  using: composite
+  steps:
+    - name: Setup Vite+
+      uses: voidzero-dev/setup-vp@20553a7a7429c429a74894104a2835d7fed28a72 # v1.3.0
+      with:
+        node-version-file: .nvmrc
+        cache: true
+        run-install: true

.github/dependabot.yml

@@ -1,12 +1,112 @@
 version: 2
+
 updates:
-  - package-ecosystem: "npm"
-    directory: "/web"
-    schedule:
-      interval: "weekly"
-    open-pull-requests-limit: 2
   - 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/labeler.yml

@@ -1,3 +1,10 @@
 web:
   - changed-files:
-      - any-glob-to-any-file: 'web/**'
+      - any-glob-to-any-file:
+          - 'web/**'
+          - 'packages/**'
+          - 'package.json'
+          - 'pnpm-lock.yaml'
+          - 'pnpm-workspace.yaml'
+          - '.npmrc'
+          - '.nvmrc'

.github/pull_request_template.md

@@ -7,6 +7,7 @@
 ## Summary
 
 <!-- Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change. -->
+<!-- If this PR was created by an automated agent, add `From <Tool Name>` as the final line of the description. Example: `From Codex`. -->
 
 ## Screenshots
 
@@ -17,7 +18,7 @@
 ## Checklist
 
 - [ ] This change requires a documentation update, included: [Dify Document](https://github.com/langgenius/dify-docs)
-- [x] I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
-- [x] I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
-- [x] I've updated the documentation accordingly.
-- [x] I ran `make lint` and `make type-check` (backend) and `cd web && npx lint-staged` (frontend) to appease the lint gods
+- [ ] I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
+- [ ] I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
+- [ ] I've updated the documentation accordingly.
+- [ ] I ran `make lint && make type-check` (backend) and `cd web && pnpm exec vp staged` (frontend) to appease the lint gods

.github/scripts/generate-i18n-changes.mjs

@@ -0,0 +1,82 @@
+import { execFileSync } from 'node:child_process'
+import fs from 'node:fs'
+import path from 'node:path'
+
+const repoRoot = process.cwd()
+const baseSha = process.env.BASE_SHA || ''
+const headSha = process.env.HEAD_SHA || ''
+const files = (process.env.CHANGED_FILES || '').split(/\s+/).filter(Boolean)
+const outputPath = process.env.I18N_CHANGES_OUTPUT_PATH || '/tmp/i18n-changes.json'
+
+const englishPath = fileStem => path.join(repoRoot, 'web', 'i18n', 'en-US', `${fileStem}.json`)
+
+const readCurrentJson = (fileStem) => {
+  const filePath = englishPath(fileStem)
+  if (!fs.existsSync(filePath))
+    return null
+
+  return JSON.parse(fs.readFileSync(filePath, 'utf8'))
+}
+
+const readBaseJson = (fileStem) => {
+  if (!baseSha)
+    return null
+
+  try {
+    const relativePath = `web/i18n/en-US/${fileStem}.json`
+    const content = execFileSync('git', ['show', `${baseSha}:${relativePath}`], { encoding: 'utf8' })
+    return JSON.parse(content)
+  }
+  catch {
+    return null
+  }
+}
+
+const compareJson = (beforeValue, afterValue) => JSON.stringify(beforeValue) === JSON.stringify(afterValue)
+
+const changes = {}
+
+for (const fileStem of files) {
+  const currentJson = readCurrentJson(fileStem)
+  const beforeJson = readBaseJson(fileStem) || {}
+  const afterJson = currentJson || {}
+  const added = {}
+  const updated = {}
+  const deleted = []
+
+  for (const [key, value] of Object.entries(afterJson)) {
+    if (!(key in beforeJson)) {
+      added[key] = value
+      continue
+    }
+
+    if (!compareJson(beforeJson[key], value)) {
+      updated[key] = {
+        before: beforeJson[key],
+        after: value,
+      }
+    }
+  }
+
+  for (const key of Object.keys(beforeJson)) {
+    if (!(key in afterJson))
+      deleted.push(key)
+  }
+
+  changes[fileStem] = {
+    fileDeleted: currentJson === null,
+    added,
+    updated,
+    deleted,
+  }
+}
+
+fs.writeFileSync(
+  outputPath,
+  JSON.stringify({
+    baseSha,
+    headSha,
+    files,
+    changes,
+  })
+)

.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@85daca1880e9e1af197fc06ea03349daf08f4202 # v0.2.1
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          close-pr: false
+          failure-add-pr-labels: "needs-revision"

.github/workflows/api-tests.yml

@@ -2,32 +2,40 @@ name: Run Pytest
 
 on:
   workflow_call:
+    secrets:
+      CODECOV_TOKEN:
+        required: false
+
+permissions:
+  contents: read
 
 concurrency:
   group: api-tests-${{ github.head_ref || github.run_id }}
   cancel-in-progress: true
 
 jobs:
-  test:
-    name: API Tests
+  api-unit:
+    name: API Unit Tests
     runs-on: ubuntu-latest
+    env:
+      COVERAGE_FILE: coverage-unit
     defaults:
       run:
         shell: bash
     strategy:
       matrix:
         python-version:
-          - "3.11"
           - "3.12"
 
     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@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
         with:
           enable-cache: true
           python-version: ${{ matrix.python-version }}
@@ -42,6 +50,52 @@ jobs:
       - name: Run dify config tests
         run: uv run --project api dev/pytest/pytest_config_tests.py
 
+      - name: Run Unit Tests
+        run: uv run --project api bash dev/pytest/pytest_unit_tests.sh
+
+      - name: Upload unit coverage data
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: api-coverage-unit
+          path: coverage-unit
+          retention-days: 1
+
+  api-integration:
+    name: API Integration Tests
+    runs-on: ubuntu-latest
+    env:
+      COVERAGE_FILE: coverage-integration
+      STORAGE_TYPE: opendal
+      OPENDAL_SCHEME: fs
+      OPENDAL_FS_ROOT: /tmp/dify-storage
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      matrix:
+        python-version:
+          - "3.12"
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+
+      - name: Setup UV and Python
+        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        with:
+          enable-cache: true
+          python-version: ${{ matrix.python-version }}
+          cache-dependency-glob: api/uv.lock
+
+      - name: Check UV lockfile
+        run: uv lock --project api --check
+
+      - name: Install dependencies
+        run: uv sync --project api --dev
+
       - name: Set up dotenvs
         run: |
           cp docker/.env.example docker/.env
@@ -51,7 +105,7 @@ 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
@@ -65,35 +119,94 @@ jobs:
         run: |
           cp api/tests/integration_tests/.env.example api/tests/integration_tests/.env
 
-      - name: Run API Tests
-        env:
-          STORAGE_TYPE: opendal
-          OPENDAL_SCHEME: fs
-          OPENDAL_FS_ROOT: /tmp/dify-storage
+      - name: Run Integration Tests
         run: |
           uv run --project api pytest \
             -n auto \
             --timeout "${PYTEST_TIMEOUT:-180}" \
             api/tests/integration_tests/workflow \
             api/tests/integration_tests/tools \
-            api/tests/test_containers_integration_tests \
-            api/tests/unit_tests
+            api/tests/test_containers_integration_tests
 
-      - name: Coverage Summary
+      - name: Upload integration coverage data
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: api-coverage-integration
+          path: coverage-integration
+          retention-days: 1
+
+  api-coverage:
+    name: API Coverage
+    runs-on: ubuntu-latest
+    needs:
+      - api-unit
+      - api-integration
+    env:
+      CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+      COVERAGE_FILE: .coverage
+    defaults:
+      run:
+        shell: bash
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+
+      - name: Setup UV and Python
+        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        with:
+          enable-cache: true
+          python-version: "3.12"
+          cache-dependency-glob: api/uv.lock
+
+      - name: Install dependencies
+        run: uv sync --project api --dev
+
+      - name: Download coverage data
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
+        with:
+          path: coverage-data
+          pattern: api-coverage-*
+          merge-multiple: true
+
+      - name: Combine coverage
         run: |
-          set -x
-          # Extract coverage percentage and create a summary
-          TOTAL_COVERAGE=$(python -c 'import json; print(json.load(open("coverage.json"))["totals"]["percent_covered_display"])')
+          set -euo pipefail
 
-          # Create a detailed coverage summary
-          echo "### Test Coverage Summary :test_tube:" >> $GITHUB_STEP_SUMMARY
-          echo "Total Coverage: ${TOTAL_COVERAGE}%" >> $GITHUB_STEP_SUMMARY
+          echo "### API Coverage" >> "$GITHUB_STEP_SUMMARY"
+          echo "" >> "$GITHUB_STEP_SUMMARY"
+          echo "Merged backend coverage report generated for Codecov project status." >> "$GITHUB_STEP_SUMMARY"
+          echo "" >> "$GITHUB_STEP_SUMMARY"
+
+          unit_coverage="$(find coverage-data -type f -name coverage-unit -print -quit)"
+          integration_coverage="$(find coverage-data -type f -name coverage-integration -print -quit)"
+          : "${unit_coverage:?coverage-unit artifact not found}"
+          : "${integration_coverage:?coverage-integration artifact not found}"
+
+          report_file="$(mktemp)"
+          uv run --project api coverage combine "$unit_coverage" "$integration_coverage"
+          uv run --project api coverage report --show-missing | tee "$report_file"
+          echo "Summary: \`$(tail -n 1 "$report_file")\`" >> "$GITHUB_STEP_SUMMARY"
           {
             echo ""
-            echo "<details><summary>File-level coverage (click to expand)</summary>"
+            echo "<details><summary>Coverage report</summary>"
             echo ""
             echo '```'
-            uv run --project api coverage report -m
+            cat "$report_file"
             echo '```'
             echo "</details>"
-          } >> $GITHUB_STEP_SUMMARY
+          } >> "$GITHUB_STEP_SUMMARY"
+          uv run --project api coverage xml -o coverage.xml
+
+      - name: Report coverage
+        if: ${{ env.CODECOV_TOKEN != '' }}
+        uses: codecov/codecov-action@57e3a136b779b570ffcdbf80b3bdc90e7fab3de2 # v6.0.0
+        with:
+          files: ./coverage.xml
+          disable_search: true
+          flags: api
+        env:
+          CODECOV_TOKEN: ${{ env.CODECOV_TOKEN }}

.github/workflows/autofix.yml

@@ -2,6 +2,9 @@ name: autofix.ci
 on:
   pull_request:
     branches: ["main"]
+  merge_group:
+    branches: ["main"]
+    types: [checks_requested]
   push:
     branches: ["main"]
 permissions:
@@ -12,30 +15,59 @@ jobs:
     if: github.repository == 'langgenius/dify'
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - name: Complete merge group check
+        if: github.event_name == 'merge_group'
+        run: echo "autofix.ci updates pull request branches, not merge group refs."
+
+      - if: github.event_name != 'merge_group'
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
       - name: Check Docker Compose inputs
+        if: github.event_name != 'merge_group'
         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
+        if: github.event_name != 'merge_group'
+        id: web-changes
+        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
+        with:
+          files: |
+            web/**
+            packages/**
+            package.json
+            pnpm-lock.yaml
+            pnpm-workspace.yaml
+            .npmrc
+            .nvmrc
+      - name: Check api inputs
+        if: github.event_name != 'merge_group'
+        id: api-changes
+        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
+        with:
+          files: |
+            api/**
+      - if: github.event_name != 'merge_group'
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
         with:
           python-version: "3.11"
 
-      - uses: astral-sh/setup-uv@v7
+      - if: github.event_name != 'merge_group'
+        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
 
       - name: Generate Docker Compose
-        if: steps.docker-compose-changes.outputs.any_changed == 'true'
+        if: github.event_name != 'merge_group' && steps.docker-compose-changes.outputs.any_changed == 'true'
         run: |
           cd docker
           ./generate_docker_compose
 
-      - run: |
+      - if: github.event_name != 'merge_group' && steps.api-changes.outputs.any_changed == 'true'
+        run: |
           cd api
           uv sync --dev
           # fmt first to avoid line too long
@@ -46,11 +78,13 @@ jobs:
           uv run ruff format ..
 
       - name: count migration progress
+        if: github.event_name != 'merge_group' && steps.api-changes.outputs.any_changed == 'true'
         run: |
           cd api
           ./cnt_base.sh
 
       - name: ast-grep
+        if: github.event_name != 'merge_group' && 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
@@ -79,9 +113,14 @@ jobs:
           find . -name "*.py" -type f -exec sed -i.bak -E 's/"([^"]+)" \| None/Optional["\1"]/g; s/'"'"'([^'"'"']+)'"'"' \| None/Optional['"'"'\1'"'"']/g' {} \;
           find . -name "*.py.bak" -type f -delete
 
-      # mdformat breaks YAML front matter in markdown files. Add --exclude for directories containing YAML front matter.
-      - name: mdformat
-        run: |
-          uvx --python 3.13 mdformat . --exclude ".agents/skills/**"
+      - name: Setup web environment
+        if: github.event_name != 'merge_group' && steps.web-changes.outputs.any_changed == 'true'
+        uses: ./.github/actions/setup-web
 
-      - uses: autofix-ci/action@635ffb0c9798bd160680f18fd73371e355b85f27
+      - name: ESLint autofix
+        if: github.event_name != 'merge_group' && steps.web-changes.outputs.any_changed == 'true'
+        run: |
+          vp exec eslint --concurrency=2 --prune-suppressions --quiet || true
+
+      - if: github.event_name != 'merge_group'
+        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:
       - "*"
 
@@ -23,27 +24,39 @@ env:
 
 jobs:
   build:
-    runs-on: ${{ matrix.platform == 'linux/arm64' && 'arm64_runner' || 'ubuntu-latest' }}
+    runs-on: ${{ matrix.runs_on }}
     if: github.repository == 'langgenius/dify'
     strategy:
       matrix:
         include:
           - service_name: "build-api-amd64"
             image_name_env: "DIFY_API_IMAGE_NAME"
-            context: "api"
+            artifact_context: "api"
+            build_context: "{{defaultContext}}:api"
+            file: "Dockerfile"
             platform: linux/amd64
+            runs_on: ubuntu-latest
           - service_name: "build-api-arm64"
             image_name_env: "DIFY_API_IMAGE_NAME"
-            context: "api"
+            artifact_context: "api"
+            build_context: "{{defaultContext}}:api"
+            file: "Dockerfile"
             platform: linux/arm64
+            runs_on: ubuntu-24.04-arm
           - service_name: "build-web-amd64"
             image_name_env: "DIFY_WEB_IMAGE_NAME"
-            context: "web"
+            artifact_context: "web"
+            build_context: "{{defaultContext}}"
+            file: "web/Dockerfile"
             platform: linux/amd64
+            runs_on: ubuntu-latest
           - service_name: "build-web-arm64"
             image_name_env: "DIFY_WEB_IMAGE_NAME"
-            context: "web"
+            artifact_context: "web"
+            build_context: "{{defaultContext}}"
+            file: "web/Dockerfile"
             platform: linux/arm64
+            runs_on: ubuntu-24.04-arm
 
     steps:
       - name: Prepare
@@ -52,28 +65,26 @@ jobs:
           echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
 
       - name: Login to Docker Hub
-        uses: docker/login-action@v3
+        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4.1.0
         with:
           username: ${{ env.DOCKERHUB_USER }}
           password: ${{ env.DOCKERHUB_TOKEN }}
 
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-
       - 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@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
         with:
-          context: "{{defaultContext}}:${{ matrix.context }}"
+          context: ${{ matrix.build_context }}
+          file: ${{ matrix.file }}
           platforms: ${{ matrix.platform }}
           build-args: COMMIT_SHA=${{ fromJSON(steps.meta.outputs.json).labels['org.opencontainers.image.revision'] }}
           labels: ${{ steps.meta.outputs.labels }}
@@ -90,9 +101,9 @@ jobs:
           touch "/tmp/digests/${sanitized_digest}"
 
       - name: Upload digest
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
-          name: digests-${{ matrix.context }}-${{ env.PLATFORM_PAIR }}
+          name: digests-${{ matrix.artifact_context }}-${{ env.PLATFORM_PAIR }}
           path: /tmp/digests/*
           if-no-files-found: error
           retention-days: 1
@@ -112,21 +123,21 @@ jobs:
             context: "web"
     steps:
       - name: Download digests
-        uses: actions/download-artifact@v7
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
         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@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4.1.0
         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@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
         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@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
         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

@@ -4,7 +4,7 @@ on:
   workflow_run:
     workflows: ["Build and Push API & Web"]
     branches:
-      - "feat/hitl"
+      - "build/feat/hitl"
     types:
       - completed
 
@@ -13,10 +13,10 @@ jobs:
     runs-on: ubuntu-latest
     if: |
       github.event.workflow_run.conclusion == 'success' &&
-      github.event.workflow_run.head_branch == 'feat/hitl'
+      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

@@ -14,35 +14,40 @@ concurrency:
 
 jobs:
   build-docker:
-    runs-on: ubuntu-latest
+    runs-on: ${{ matrix.runs_on }}
     strategy:
       matrix:
         include:
           - service_name: "api-amd64"
             platform: linux/amd64
-            context: "api"
+            runs_on: ubuntu-latest
+            context: "{{defaultContext}}:api"
+            file: "Dockerfile"
           - service_name: "api-arm64"
             platform: linux/arm64
-            context: "api"
+            runs_on: ubuntu-24.04-arm
+            context: "{{defaultContext}}:api"
+            file: "Dockerfile"
           - service_name: "web-amd64"
             platform: linux/amd64
-            context: "web"
+            runs_on: ubuntu-latest
+            context: "{{defaultContext}}"
+            file: "web/Dockerfile"
           - service_name: "web-arm64"
             platform: linux/arm64
-            context: "web"
+            runs_on: ubuntu-24.04-arm
+            context: "{{defaultContext}}"
+            file: "web/Dockerfile"
     steps:
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-
       - 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@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
         with:
           push: false
-          context: "{{defaultContext}}:${{ matrix.context }}"
-          file: "${{ matrix.file }}"
+          context: ${{ matrix.context }}
+          file: ${{ matrix.file }}
           platforms: ${{ matrix.platform }}
           cache-from: type=gha
           cache-to: type=gha,mode=max

.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

@@ -3,10 +3,14 @@ name: Main CI Pipeline
 on:
   pull_request:
     branches: ["main"]
+  merge_group:
+    branches: ["main"]
+    types: [checks_requested]
   push:
     branches: ["main"]
 
 permissions:
+  actions: write
   contents: write
   pull-requests: write
   checks: write
@@ -17,63 +21,410 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
+  pre_job:
+    name: Skip Duplicate Checks
+    runs-on: ubuntu-latest
+    outputs:
+      should_skip: ${{ steps.skip_check.outputs.should_skip || 'false' }}
+    steps:
+      - id: skip_check
+        continue-on-error: true
+        uses: fkirc/skip-duplicate-actions@f75f66ce1886f00957d99748a42c724f4330bdcf # v5.3.1
+        with:
+          cancel_others: 'true'
+          concurrent_skipping: same_content_newer
+
   # Check which paths were changed to determine which tests to run
   check-changes:
     name: Check Changed Files
+    needs: pre_job
+    if: needs.pre_job.outputs.should_skip != 'true'
     runs-on: ubuntu-latest
     outputs:
       api-changed: ${{ steps.changes.outputs.api }}
+      e2e-changed: ${{ steps.changes.outputs.e2e }}
       web-changed: ${{ steps.changes.outputs.web }}
       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@fbd0ab8f3e69293af611ebaee6363fc25e6d187d # v4.0.1
         id: changes
         with:
           filters: |
             api:
               - 'api/**'
-              - 'docker/**'
               - '.github/workflows/api-tests.yml'
+              - '.github/workflows/expose_service_ports.sh'
+              - 'docker/.env.example'
+              - 'docker/middleware.env.example'
+              - 'docker/docker-compose.middleware.yaml'
+              - 'docker/docker-compose-template.yaml'
+              - 'docker/generate_docker_compose'
+              - 'docker/ssrf_proxy/**'
+              - 'docker/volumes/sandbox/conf/**'
             web:
               - 'web/**'
+              - 'packages/**'
+              - 'package.json'
+              - 'pnpm-lock.yaml'
+              - 'pnpm-workspace.yaml'
+              - '.npmrc'
+              - '.nvmrc'
               - '.github/workflows/web-tests.yml'
+              - '.github/actions/setup-web/**'
+            e2e:
+              - 'api/**'
+              - 'api/pyproject.toml'
+              - 'api/uv.lock'
+              - 'e2e/**'
+              - 'web/**'
+              - 'packages/**'
+              - 'package.json'
+              - 'pnpm-lock.yaml'
+              - 'pnpm-workspace.yaml'
+              - '.npmrc'
+              - '.nvmrc'
+              - 'docker/docker-compose.middleware.yaml'
+              - 'docker/middleware.env.example'
+              - '.github/workflows/web-e2e.yml'
+              - '.github/actions/setup-web/**'
             vdb:
               - 'api/core/rag/datasource/**'
-              - 'docker/**'
+              - 'api/tests/integration_tests/vdb/**'
+              - 'api/providers/vdb/*/tests/**'
               - '.github/workflows/vdb-tests.yml'
+              - '.github/workflows/expose_service_ports.sh'
+              - 'docker/.env.example'
+              - 'docker/middleware.env.example'
+              - 'docker/docker-compose.yaml'
+              - 'docker/docker-compose-template.yaml'
+              - 'docker/generate_docker_compose'
+              - 'docker/certbot/**'
+              - 'docker/couchbase-server/**'
+              - 'docker/elasticsearch/**'
+              - 'docker/iris/**'
+              - 'docker/nginx/**'
+              - 'docker/pgvector/**'
+              - 'docker/ssrf_proxy/**'
+              - 'docker/startupscripts/**'
+              - 'docker/tidb/**'
+              - 'docker/volumes/**'
               - 'api/uv.lock'
               - 'api/pyproject.toml'
             migration:
               - 'api/migrations/**'
+              - 'api/.env.example'
               - '.github/workflows/db-migration-test.yml'
+              - '.github/workflows/expose_service_ports.sh'
+              - 'docker/.env.example'
+              - 'docker/middleware.env.example'
+              - 'docker/docker-compose.middleware.yaml'
+              - 'docker/docker-compose-template.yaml'
+              - 'docker/generate_docker_compose'
+              - 'docker/ssrf_proxy/**'
+              - 'docker/volumes/sandbox/conf/**'
+
+  # Run tests in parallel while always emitting stable required checks.
+  api-tests-run:
+    name: Run API Tests
+    needs:
+      - pre_job
+      - check-changes
+    if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.api-changed == 'true'
+    uses: ./.github/workflows/api-tests.yml
+    secrets: inherit
+
+  api-tests-skip:
+    name: Skip API Tests
+    needs:
+      - pre_job
+      - check-changes
+    if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.api-changed != 'true'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Report skipped API tests
+        run: echo "No API-related changes detected; skipping API tests."
 
-  # Run tests in parallel
   api-tests:
     name: API Tests
-    needs: check-changes
-    if: needs.check-changes.outputs.api-changed == 'true'
-    uses: ./.github/workflows/api-tests.yml
+    if: ${{ always() }}
+    needs:
+      - pre_job
+      - check-changes
+      - api-tests-run
+      - api-tests-skip
+    runs-on: ubuntu-latest
+    steps:
+      - name: Finalize API Tests status
+        env:
+          SHOULD_SKIP_WORKFLOW: ${{ needs.pre_job.outputs.should_skip }}
+          TESTS_CHANGED: ${{ needs.check-changes.outputs.api-changed }}
+          RUN_RESULT: ${{ needs.api-tests-run.result }}
+          SKIP_RESULT: ${{ needs.api-tests-skip.result }}
+        run: |
+          if [[ "$SHOULD_SKIP_WORKFLOW" == 'true' ]]; then
+            echo "API tests were skipped because this workflow run duplicated a successful or newer run."
+            exit 0
+          fi
+
+          if [[ "$TESTS_CHANGED" == 'true' ]]; then
+            if [[ "$RUN_RESULT" == 'success' ]]; then
+              echo "API tests ran successfully."
+              exit 0
+            fi
+
+            echo "API tests were required but finished with result: $RUN_RESULT" >&2
+            exit 1
+          fi
+
+          if [[ "$SKIP_RESULT" == 'success' ]]; then
+            echo "API tests were skipped because no API-related files changed."
+            exit 0
+          fi
+
+          echo "API tests were not required, but the skip job finished with result: $SKIP_RESULT" >&2
+          exit 1
+
+  web-tests-run:
+    name: Run Web Tests
+    needs:
+      - pre_job
+      - check-changes
+    if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.web-changed == 'true'
+    uses: ./.github/workflows/web-tests.yml
+    secrets: inherit
+
+  web-tests-skip:
+    name: Skip Web Tests
+    needs:
+      - pre_job
+      - check-changes
+    if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.web-changed != 'true'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Report skipped web tests
+        run: echo "No web-related changes detected; skipping web tests."
 
   web-tests:
     name: Web Tests
-    needs: check-changes
-    if: needs.check-changes.outputs.web-changed == 'true'
-    uses: ./.github/workflows/web-tests.yml
+    if: ${{ always() }}
+    needs:
+      - pre_job
+      - check-changes
+      - web-tests-run
+      - web-tests-skip
+    runs-on: ubuntu-latest
+    steps:
+      - name: Finalize Web Tests status
+        env:
+          SHOULD_SKIP_WORKFLOW: ${{ needs.pre_job.outputs.should_skip }}
+          TESTS_CHANGED: ${{ needs.check-changes.outputs.web-changed }}
+          RUN_RESULT: ${{ needs.web-tests-run.result }}
+          SKIP_RESULT: ${{ needs.web-tests-skip.result }}
+        run: |
+          if [[ "$SHOULD_SKIP_WORKFLOW" == 'true' ]]; then
+            echo "Web tests were skipped because this workflow run duplicated a successful or newer run."
+            exit 0
+          fi
+
+          if [[ "$TESTS_CHANGED" == 'true' ]]; then
+            if [[ "$RUN_RESULT" == 'success' ]]; then
+              echo "Web tests ran successfully."
+              exit 0
+            fi
+
+            echo "Web tests were required but finished with result: $RUN_RESULT" >&2
+            exit 1
+          fi
+
+          if [[ "$SKIP_RESULT" == 'success' ]]; then
+            echo "Web tests were skipped because no web-related files changed."
+            exit 0
+          fi
+
+          echo "Web tests were not required, but the skip job finished with result: $SKIP_RESULT" >&2
+          exit 1
+
+  web-e2e-run:
+    name: Run Web Full-Stack E2E
+    needs:
+      - pre_job
+      - check-changes
+    if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.e2e-changed == 'true'
+    uses: ./.github/workflows/web-e2e.yml
+
+  web-e2e-skip:
+    name: Skip Web Full-Stack E2E
+    needs:
+      - pre_job
+      - check-changes
+    if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.e2e-changed != 'true'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Report skipped web full-stack e2e
+        run: echo "No E2E-related changes detected; skipping web full-stack E2E."
+
+  web-e2e:
+    name: Web Full-Stack E2E
+    if: ${{ always() }}
+    needs:
+      - pre_job
+      - check-changes
+      - web-e2e-run
+      - web-e2e-skip
+    runs-on: ubuntu-latest
+    steps:
+      - name: Finalize Web Full-Stack E2E status
+        env:
+          SHOULD_SKIP_WORKFLOW: ${{ needs.pre_job.outputs.should_skip }}
+          TESTS_CHANGED: ${{ needs.check-changes.outputs.e2e-changed }}
+          RUN_RESULT: ${{ needs.web-e2e-run.result }}
+          SKIP_RESULT: ${{ needs.web-e2e-skip.result }}
+        run: |
+          if [[ "$SHOULD_SKIP_WORKFLOW" == 'true' ]]; then
+            echo "Web full-stack E2E was skipped because this workflow run duplicated a successful or newer run."
+            exit 0
+          fi
+
+          if [[ "$TESTS_CHANGED" == 'true' ]]; then
+            if [[ "$RUN_RESULT" == 'success' ]]; then
+              echo "Web full-stack E2E ran successfully."
+              exit 0
+            fi
+
+            echo "Web full-stack E2E was required but finished with result: $RUN_RESULT" >&2
+            exit 1
+          fi
+
+          if [[ "$SKIP_RESULT" == 'success' ]]; then
+            echo "Web full-stack E2E was skipped because no E2E-related files changed."
+            exit 0
+          fi
+
+          echo "Web full-stack E2E was not required, but the skip job finished with result: $SKIP_RESULT" >&2
+          exit 1
 
   style-check:
     name: Style Check
+    needs: pre_job
+    if: needs.pre_job.outputs.should_skip != 'true'
     uses: ./.github/workflows/style.yml
 
+  vdb-tests-run:
+    name: Run VDB Tests
+    needs:
+      - pre_job
+      - check-changes
+    if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.vdb-changed == 'true'
+    uses: ./.github/workflows/vdb-tests.yml
+
+  vdb-tests-skip:
+    name: Skip VDB Tests
+    needs:
+      - pre_job
+      - check-changes
+    if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.vdb-changed != 'true'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Report skipped VDB tests
+        run: echo "No VDB-related changes detected; skipping VDB tests."
+
   vdb-tests:
     name: VDB Tests
-    needs: check-changes
-    if: needs.check-changes.outputs.vdb-changed == 'true'
-    uses: ./.github/workflows/vdb-tests.yml
+    if: ${{ always() }}
+    needs:
+      - pre_job
+      - check-changes
+      - vdb-tests-run
+      - vdb-tests-skip
+    runs-on: ubuntu-latest
+    steps:
+      - name: Finalize VDB Tests status
+        env:
+          SHOULD_SKIP_WORKFLOW: ${{ needs.pre_job.outputs.should_skip }}
+          TESTS_CHANGED: ${{ needs.check-changes.outputs.vdb-changed }}
+          RUN_RESULT: ${{ needs.vdb-tests-run.result }}
+          SKIP_RESULT: ${{ needs.vdb-tests-skip.result }}
+        run: |
+          if [[ "$SHOULD_SKIP_WORKFLOW" == 'true' ]]; then
+            echo "VDB tests were skipped because this workflow run duplicated a successful or newer run."
+            exit 0
+          fi
+
+          if [[ "$TESTS_CHANGED" == 'true' ]]; then
+            if [[ "$RUN_RESULT" == 'success' ]]; then
+              echo "VDB tests ran successfully."
+              exit 0
+            fi
+
+            echo "VDB tests were required but finished with result: $RUN_RESULT" >&2
+            exit 1
+          fi
+
+          if [[ "$SKIP_RESULT" == 'success' ]]; then
+            echo "VDB tests were skipped because no VDB-related files changed."
+            exit 0
+          fi
+
+          echo "VDB tests were not required, but the skip job finished with result: $SKIP_RESULT" >&2
+          exit 1
+
+  db-migration-test-run:
+    name: Run DB Migration Test
+    needs:
+      - pre_job
+      - check-changes
+    if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.migration-changed == 'true'
+    uses: ./.github/workflows/db-migration-test.yml
+
+  db-migration-test-skip:
+    name: Skip DB Migration Test
+    needs:
+      - pre_job
+      - check-changes
+    if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.migration-changed != 'true'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Report skipped DB migration tests
+        run: echo "No migration-related changes detected; skipping DB migration tests."
 
   db-migration-test:
     name: DB Migration Test
-    needs: check-changes
-    if: needs.check-changes.outputs.migration-changed == 'true'
-    uses: ./.github/workflows/db-migration-test.yml
+    if: ${{ always() }}
+    needs:
+      - pre_job
+      - check-changes
+      - db-migration-test-run
+      - db-migration-test-skip
+    runs-on: ubuntu-latest
+    steps:
+      - name: Finalize DB Migration Test status
+        env:
+          SHOULD_SKIP_WORKFLOW: ${{ needs.pre_job.outputs.should_skip }}
+          TESTS_CHANGED: ${{ needs.check-changes.outputs.migration-changed }}
+          RUN_RESULT: ${{ needs.db-migration-test-run.result }}
+          SKIP_RESULT: ${{ needs.db-migration-test-skip.result }}
+        run: |
+          if [[ "$SHOULD_SKIP_WORKFLOW" == 'true' ]]; then
+            echo "DB migration tests were skipped because this workflow run duplicated a successful or newer run."
+            exit 0
+          fi
+
+          if [[ "$TESTS_CHANGED" == 'true' ]]; then
+            if [[ "$RUN_RESULT" == 'success' ]]; then
+              echo "DB migration tests ran successfully."
+              exit 0
+            fi
+
+            echo "DB migration tests were required but finished with result: $RUN_RESULT" >&2
+            exit 1
+          fi
+
+          if [[ "$SKIP_RESULT" == 'success' ]]; then
+            echo "DB migration tests were skipped because no migration-related files changed."
+            exit 0
+          fi
+
+          echo "DB migration tests were not required, but the skip job finished with result: $SKIP_RESULT" >&2
+          exit 1

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

@@ -0,0 +1,86 @@
+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@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
+        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@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
+        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) ...';
+            }
+
+            if (diff.trim()) {
+              await github.rest.issues.createComment({
+                issue_number: prNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body: '### Pyrefly Diff\n<details>\n<summary>base → PR</summary>\n\n```diff\n' + diff + '\n```\n</details>',
+              });
+            }

.github/workflows/pyrefly-diff.yml

@@ -0,0 +1,111 @@
+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@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        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 ${{ github.base_ref }}
+
+      - name: Run pyrefly on base branch
+        run: |
+          uv run --directory api --dev pyrefly check 2>&1 \
+            | uv run --directory api python /tmp/pyrefly_diagnostics.py > /tmp/pyrefly_base.txt || true
+
+      - name: Compute diff
+        run: |
+          diff -u /tmp/pyrefly_base.txt /tmp/pyrefly_pr.txt > pyrefly_diff.txt || true
+
+      - name: Check if line counts match
+        id: line_count_check
+        run: |
+          base_lines=$(wc -l < /tmp/pyrefly_base.txt)
+          pr_lines=$(wc -l < /tmp/pyrefly_pr.txt)
+          if [ "$base_lines" -eq "$pr_lines" ]; then
+            echo "same=true" >> $GITHUB_OUTPUT
+          else
+            echo "same=false" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Save PR number
+        run: |
+          echo ${{ github.event.pull_request.number }} > pr_number.txt
+
+      - name: Upload pyrefly diff
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        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 && steps.line_count_check.outputs.same == 'false' }}
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
+        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/pyrefly-type-coverage-comment.yml

@@ -0,0 +1,118 @@
+name: Comment with Pyrefly Type Coverage
+
+on:
+  workflow_run:
+    workflows:
+      - Pyrefly Type Coverage
+    types:
+      - completed
+
+permissions: {}
+
+jobs:
+  comment:
+    name: Comment PR with type coverage
+    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: Checkout default branch (trusted code)
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+
+      - name: Setup Python & UV
+        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        with:
+          enable-cache: true
+
+      - name: Install dependencies
+        run: uv sync --project api --dev
+
+      - name: Download type coverage artifact
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
+        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: ${{ github.event.workflow_run.id }},
+            });
+            const match = artifacts.data.artifacts.find((artifact) =>
+              artifact.name === 'pyrefly_type_coverage'
+            );
+            if (!match) {
+              throw new Error('pyrefly_type_coverage artifact not found');
+            }
+            const download = await github.rest.actions.downloadArtifact({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              artifact_id: match.id,
+              archive_format: 'zip',
+            });
+            fs.writeFileSync('pyrefly_type_coverage.zip', Buffer.from(download.data));
+
+      - name: Unzip artifact
+        run: unzip -o pyrefly_type_coverage.zip
+
+      - name: Render coverage markdown from structured data
+        id: render
+        run: |
+          comment_body="$(uv run --directory api python libs/pyrefly_type_coverage.py \
+            --base base_report.json \
+            < pr_report.json)"
+
+          {
+            echo "### Pyrefly Type Coverage"
+            echo ""
+            echo "$comment_body"
+          } > /tmp/type_coverage_comment.md
+
+      - name: Post comment
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const fs = require('fs');
+            const body = fs.readFileSync('/tmp/type_coverage_comment.md', { encoding: 'utf8' });
+            let prNumber = null;
+            try {
+              prNumber = parseInt(fs.readFileSync('pr_number.txt', { encoding: 'utf8' }), 10);
+            } catch (err) {
+              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');
+            }
+
+            // Update existing comment if one exists, otherwise create new
+            const { data: comments } = await github.rest.issues.listComments({
+              issue_number: prNumber,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+            });
+            const marker = '### Pyrefly Type Coverage';
+            const existing = comments.find(c => c.body.startsWith(marker));
+
+            if (existing) {
+              await github.rest.issues.updateComment({
+                comment_id: existing.id,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body,
+              });
+            } else {
+              await github.rest.issues.createComment({
+                issue_number: prNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body,
+              });
+            }

.github/workflows/pyrefly-type-coverage.yml

@@ -0,0 +1,120 @@
+name: Pyrefly Type Coverage
+
+on:
+  pull_request:
+    paths:
+      - 'api/**/*.py'
+
+permissions:
+  contents: read
+
+jobs:
+  pyrefly-type-coverage:
+    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@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        with:
+          enable-cache: true
+
+      - name: Install dependencies
+        run: uv sync --project api --dev
+
+      - name: Run pyrefly report on PR branch
+        run: |
+          uv run --directory api --dev pyrefly report 2>/dev/null > /tmp/pyrefly_report_pr.tmp && \
+            mv /tmp/pyrefly_report_pr.tmp /tmp/pyrefly_report_pr.json || \
+            echo '{}' > /tmp/pyrefly_report_pr.json
+
+      - name: Save helper script from base branch
+        run: |
+          git show ${{ github.event.pull_request.base.sha }}:api/libs/pyrefly_type_coverage.py > /tmp/pyrefly_type_coverage.py 2>/dev/null \
+            || cp api/libs/pyrefly_type_coverage.py /tmp/pyrefly_type_coverage.py
+
+      - name: Checkout base branch
+        run: git checkout ${{ github.base_ref }}
+
+      - name: Run pyrefly report on base branch
+        run: |
+          uv run --directory api --dev pyrefly report 2>/dev/null > /tmp/pyrefly_report_base.tmp && \
+            mv /tmp/pyrefly_report_base.tmp /tmp/pyrefly_report_base.json || \
+            echo '{}' > /tmp/pyrefly_report_base.json
+
+      - name: Generate coverage comparison
+        id: coverage
+        run: |
+          comment_body="$(uv run --directory api python /tmp/pyrefly_type_coverage.py \
+            --base /tmp/pyrefly_report_base.json \
+            < /tmp/pyrefly_report_pr.json)"
+
+          {
+            echo "### Pyrefly Type Coverage"
+            echo ""
+            echo "$comment_body"
+          } | tee -a "$GITHUB_STEP_SUMMARY" > /tmp/type_coverage_comment.md
+
+          # Save structured data for the fork-PR comment workflow
+          cp /tmp/pyrefly_report_pr.json pr_report.json
+          cp /tmp/pyrefly_report_base.json base_report.json
+
+      - name: Save PR number
+        run: |
+          echo ${{ github.event.pull_request.number }} > pr_number.txt
+
+      - name: Upload type coverage artifact
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: pyrefly_type_coverage
+          path: |
+            pr_report.json
+            base_report.json
+            pr_number.txt
+
+      - name: Comment PR with type coverage
+        if: ${{ github.event.pull_request.head.repo.full_name == github.repository }}
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const fs = require('fs');
+            const marker = '### Pyrefly Type Coverage';
+            let body;
+            try {
+              body = fs.readFileSync('/tmp/type_coverage_comment.md', { encoding: 'utf8' });
+            } catch {
+              body = `${marker}\n\n_Coverage report unavailable._`;
+            }
+            const prNumber = context.payload.pull_request.number;
+
+            // Update existing comment if one exists, otherwise create new
+            const { data: comments } = await github.rest.issues.listComments({
+              issue_number: prNumber,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+            });
+            const existing = comments.find(c => c.body.startsWith(marker));
+
+            if (existing) {
+              await github.rest.issues.updateComment({
+                comment_id: existing.id,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body,
+              });
+            } else {
+              await github.rest.issues.createComment({
+                issue_number: prNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body,
+              });
+            }

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

@@ -7,6 +7,9 @@ on:
       - edited
       - reopened
       - synchronize
+  merge_group:
+    branches: ["main"]
+    types: [checks_requested]
 
 jobs:
   lint:
@@ -15,7 +18,11 @@ jobs:
       pull-requests: read
     runs-on: ubuntu-latest
     steps:
+      - name: Complete merge group check
+        if: github.event_name == 'merge_group'
+        run: echo "Semantic PR title validation is handled on pull requests."
       - name: Check title
-        uses: amannn/action-semantic-pull-request@v6.1.1
+        if: github.event_name == 'pull_request'
+        uses: amannn/action-semantic-pull-request@48f256284bd46cdaab1048c3721360e808335d50 # v6.1.1
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/stale.yml

@@ -18,13 +18,13 @@ 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
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-          stale-issue-message: "Close due to it's no longer active, if you have any questions, you can reopen it."
-          stale-pr-message: "Close due to it's no longer active, if you have any questions, you can reopen it."
+          stale-issue-message: "Closed due to inactivity. If you have any questions, you can reopen it."
+          stale-pr-message: "Closed due to inactivity. If you have any questions, you can reopen it."
           stale-issue-label: 'no-issue-activity'
           stale-pr-label: 'no-pr-activity'
-          any-of-labels: 'duplicate,question,invalid,wontfix,no-issue-activity,no-pr-activity,enhancement,cant-reproduce,help-wanted'
+          any-of-labels: '🌚 invalid,🙋‍♂️ question,wont-fix,no-issue-activity,no-pr-activity,💪 enhancement,🤔 cant-reproduce,🙏 help wanted'

.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@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
         with:
           enable-cache: false
           python-version: "3.12"
@@ -49,7 +49,7 @@ jobs:
 
       - name: Run Type Checks
         if: steps.changed-files.outputs.any_changed == 'true'
-        run: make type-check
+        run: make type-check-core
 
       - name: Dotenv check
         if: steps.changed-files.outputs.any_changed == 'true'
@@ -67,66 +67,67 @@ 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/**
+            e2e/**
+            sdks/nodejs-client/**
+            packages/**
+            package.json
+            pnpm-lock.yaml
+            pnpm-workspace.yaml
+            .npmrc
+            .nvmrc
             .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
+        uses: ./.github/actions/setup-web
 
-      - name: Web dependencies
+      - name: Restore ESLint cache
         if: steps.changed-files.outputs.any_changed == 'true'
-        working-directory: ./web
-        run: pnpm install --frozen-lockfile
+        id: eslint-cache-restore
+        uses: actions/cache/restore@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
+        with:
+          path: .eslintcache
+          key: ${{ runner.os }}-eslint-${{ hashFiles('pnpm-lock.yaml', 'eslint.config.mjs', 'web/eslint.config.mjs', 'web/eslint.constants.mjs', 'web/plugins/eslint/**') }}-${{ github.sha }}
+          restore-keys: |
+            ${{ runner.os }}-eslint-${{ hashFiles('pnpm-lock.yaml', 'eslint.config.mjs', 'web/eslint.config.mjs', 'web/eslint.constants.mjs', 'web/plugins/eslint/**') }}-
 
       - name: Web style check
         if: steps.changed-files.outputs.any_changed == 'true'
-        working-directory: ./web
-        run: |
-          pnpm run lint:ci
-        # pnpm run lint:report
-        # continue-on-error: true
-
-      # - name: Annotate Code
-      #   if: steps.changed-files.outputs.any_changed == 'true' && github.event_name == 'pull_request'
-      #   uses: DerLev/eslint-annotations@51347b3a0abfb503fc8734d5ae31c4b151297fae
-      #   with:
-      #     eslint-report: web/eslint_report.json
-      #     github-token: ${{ secrets.GITHUB_TOKEN }}
+        working-directory: .
+        run: vp run lint:ci
 
       - 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
+        working-directory: .
+        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
+
+      - name: Save ESLint cache
+        if: steps.changed-files.outputs.any_changed == 'true' && success() && steps.eslint-cache-restore.outputs.cache-hit != 'true'
+        uses: actions/cache/save@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
+        with:
+          path: .eslintcache
+          key: ${{ steps.eslint-cache-restore.outputs.cache-primary-key }}
 
   superlinter:
     name: SuperLinter
@@ -134,14 +135,14 @@ 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 +153,7 @@ jobs:
             .editorconfig
 
       - name: Super-linter
-        uses: super-linter/super-linter/slim@v8
+        uses: super-linter/super-linter/slim@9e863354e3ff62e0727d37183162c4a88873df41 # v8.6.0
         if: steps.changed-files.outputs.any_changed == 'true'
         env:
           BASH_SEVERITY: warning

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

@@ -6,6 +6,10 @@ on:
       - main
     paths:
       - sdks/**
+      - package.json
+      - pnpm-lock.yaml
+      - pnpm-workspace.yaml
+      - .npmrc
 
 concurrency:
   group: sdk-tests-${{ github.head_ref || github.run_id }}
@@ -21,14 +25,14 @@ 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

@@ -1,26 +1,24 @@
 name: Translate i18n Files with Claude Code
 
 # Note: claude-code-action doesn't support push events directly.
-# Push events are handled by trigger-i18n-sync.yml which sends repository_dispatch.
-# See: https://github.com/langgenius/dify/issues/30743
-
+# Push events are bridged by trigger-i18n-sync.yml via repository_dispatch.
 on:
   repository_dispatch:
     types: [i18n-sync]
   workflow_dispatch:
     inputs:
       files:
-        description: 'Specific files to translate (space-separated, e.g., "app common"). Leave empty for all files.'
+        description: 'Specific files to translate (space-separated, e.g., "app common"). Required for full mode; leave empty in incremental mode to use en-US files changed since HEAD~1.'
         required: false
         type: string
       languages:
-        description: 'Specific languages to translate (space-separated, e.g., "zh-Hans ja-JP"). Leave empty for all supported languages.'
+        description: 'Specific languages to translate (space-separated, e.g., "zh-Hans ja-JP"). Leave empty for all supported target languages except en-US.'
         required: false
         type: string
       mode:
-        description: 'Sync mode: incremental (only changes) or full (re-check all keys)'
+        description: 'Sync mode: incremental (compare with previous en-US revision) or full (sync all keys in scope)'
         required: false
-        default: 'incremental'
+        default: incremental
         type: choice
         options:
           - incremental
@@ -30,15 +28,19 @@ permissions:
   contents: write
   pull-requests: write
 
+concurrency:
+  group: translate-i18n-${{ github.event_name }}-${{ github.ref }}
+  cancel-in-progress: false
+
 jobs:
   translate:
     if: github.repository == 'langgenius/dify'
     runs-on: ubuntu-latest
-    timeout-minutes: 60
+    timeout-minutes: 120
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-depth: 0
           token: ${{ secrets.GITHUB_TOKEN }}
@@ -48,393 +50,296 @@ 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: Setup web environment
+        uses: ./.github/actions/setup-web
 
-      - name: Set up Node.js
-        uses: actions/setup-node@v6
-        with:
-          node-version: 24
-          cache: pnpm
-          cache-dependency-path: ./web/pnpm-lock.yaml
-
-      - name: Detect changed files and generate diff
-        id: detect_changes
+      - name: Prepare sync context
+        id: context
+        shell: bash
         run: |
-          if [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
-            # Manual trigger
-            if [ -n "${{ github.event.inputs.files }}" ]; then
-              echo "CHANGED_FILES=${{ github.event.inputs.files }}" >> $GITHUB_OUTPUT
-            else
-              # Get all JSON files in en-US directory
-              files=$(ls web/i18n/en-US/*.json 2>/dev/null | xargs -n1 basename | sed 's/.json$//' | tr '\n' ' ')
-              echo "CHANGED_FILES=$files" >> $GITHUB_OUTPUT
-            fi
-            echo "TARGET_LANGS=${{ github.event.inputs.languages }}" >> $GITHUB_OUTPUT
-            echo "SYNC_MODE=${{ github.event.inputs.mode || 'incremental' }}" >> $GITHUB_OUTPUT
+          DEFAULT_TARGET_LANGS=$(awk "
+            /value: '/ {
+              value=\$2
+              gsub(/[',]/, \"\", value)
+            }
+            /supported: true/ && value != \"en-US\" {
+              printf \"%s \", value
+            }
+          " web/i18n-config/languages.ts | sed 's/[[:space:]]*$//')
 
-            # For manual trigger with incremental mode, get diff from last commit
-            # For full mode, we'll do a complete check anyway
-            if [ "${{ github.event.inputs.mode }}" == "full" ]; then
-              echo "Full mode: will check all keys" > /tmp/i18n-diff.txt
-              echo "DIFF_AVAILABLE=false" >> $GITHUB_OUTPUT
-            else
-              git diff HEAD~1..HEAD -- 'web/i18n/en-US/*.json' > /tmp/i18n-diff.txt 2>/dev/null || echo "" > /tmp/i18n-diff.txt
-              if [ -s /tmp/i18n-diff.txt ]; then
-                echo "DIFF_AVAILABLE=true" >> $GITHUB_OUTPUT
-              else
-                echo "DIFF_AVAILABLE=false" >> $GITHUB_OUTPUT
-              fi
-            fi
-          elif [ "${{ github.event_name }}" == "repository_dispatch" ]; then
-            # Triggered by push via trigger-i18n-sync.yml workflow
-            # Validate required payload fields
-            if [ -z "${{ github.event.client_payload.changed_files }}" ]; then
-              echo "Error: repository_dispatch payload missing required 'changed_files' field" >&2
-              exit 1
-            fi
-            echo "CHANGED_FILES=${{ github.event.client_payload.changed_files }}" >> $GITHUB_OUTPUT
-            echo "TARGET_LANGS=" >> $GITHUB_OUTPUT
-            echo "SYNC_MODE=${{ github.event.client_payload.sync_mode || 'incremental' }}" >> $GITHUB_OUTPUT
+          generate_changes_json() {
+            node .github/scripts/generate-i18n-changes.mjs
+          }
 
-            # Decode the base64-encoded diff from the trigger workflow
-            if [ -n "${{ github.event.client_payload.diff_base64 }}" ]; then
-              if ! echo "${{ github.event.client_payload.diff_base64 }}" | base64 -d > /tmp/i18n-diff.txt 2>&1; then
-                echo "Warning: Failed to decode base64 diff payload" >&2
-                echo "" > /tmp/i18n-diff.txt
-                echo "DIFF_AVAILABLE=false" >> $GITHUB_OUTPUT
-              elif [ -s /tmp/i18n-diff.txt ]; then
-                echo "DIFF_AVAILABLE=true" >> $GITHUB_OUTPUT
-              else
-                echo "DIFF_AVAILABLE=false" >> $GITHUB_OUTPUT
-              fi
+          if [ "${{ github.event_name }}" = "repository_dispatch" ]; then
+            BASE_SHA="${{ github.event.client_payload.base_sha }}"
+            HEAD_SHA="${{ github.event.client_payload.head_sha }}"
+            CHANGED_FILES="${{ github.event.client_payload.changed_files }}"
+            TARGET_LANGS="$DEFAULT_TARGET_LANGS"
+            SYNC_MODE="${{ github.event.client_payload.sync_mode || 'incremental' }}"
+
+            if [ -n "${{ github.event.client_payload.changes_base64 }}" ]; then
+              printf '%s' '${{ github.event.client_payload.changes_base64 }}' | base64 -d > /tmp/i18n-changes.json
+              CHANGES_AVAILABLE="true"
+              CHANGES_SOURCE="embedded"
+            elif [ -n "$BASE_SHA" ] && [ -n "$CHANGED_FILES" ]; then
+              export BASE_SHA HEAD_SHA CHANGED_FILES
+              generate_changes_json
+              CHANGES_AVAILABLE="true"
+              CHANGES_SOURCE="recomputed"
             else
-              echo "" > /tmp/i18n-diff.txt
-              echo "DIFF_AVAILABLE=false" >> $GITHUB_OUTPUT
+              printf '%s' '{"baseSha":"","headSha":"","files":[],"changes":{}}' > /tmp/i18n-changes.json
+              CHANGES_AVAILABLE="false"
+              CHANGES_SOURCE="unavailable"
             fi
           else
-            echo "Unsupported event type: ${{ github.event_name }}"
-            exit 1
+            BASE_SHA=""
+            HEAD_SHA=$(git rev-parse HEAD)
+            if [ -n "${{ github.event.inputs.languages }}" ]; then
+              TARGET_LANGS="${{ github.event.inputs.languages }}"
+            else
+              TARGET_LANGS="$DEFAULT_TARGET_LANGS"
+            fi
+            SYNC_MODE="${{ github.event.inputs.mode || 'incremental' }}"
+            if [ -n "${{ github.event.inputs.files }}" ]; then
+              CHANGED_FILES="${{ github.event.inputs.files }}"
+            elif [ "$SYNC_MODE" = "incremental" ]; then
+              BASE_SHA=$(git rev-parse HEAD~1 2>/dev/null || true)
+              if [ -n "$BASE_SHA" ]; then
+                CHANGED_FILES=$(git diff --name-only "$BASE_SHA" "$HEAD_SHA" -- 'web/i18n/en-US/*.json' 2>/dev/null | sed -n 's@^.*/@@p' | sed 's/\.json$//' | tr '\n' ' ' | sed 's/[[:space:]]*$//')
+              else
+                CHANGED_FILES=$(find web/i18n/en-US -maxdepth 1 -type f -name '*.json' -print | sed -n 's@^.*/@@p' | sed 's/\.json$//' | sort | tr '\n' ' ' | sed 's/[[:space:]]*$//')
+              fi
+            elif [ "$SYNC_MODE" = "full" ]; then
+              echo "workflow_dispatch full mode requires the files input to stay within CI limits." >&2
+              exit 1
+            else
+              CHANGED_FILES=""
+            fi
+
+            if [ "$SYNC_MODE" = "incremental" ] && [ -n "$CHANGED_FILES" ]; then
+              export BASE_SHA HEAD_SHA CHANGED_FILES
+              generate_changes_json
+              CHANGES_AVAILABLE="true"
+              CHANGES_SOURCE="local"
+            else
+              printf '%s' '{"baseSha":"","headSha":"","files":[],"changes":{}}' > /tmp/i18n-changes.json
+              CHANGES_AVAILABLE="false"
+              CHANGES_SOURCE="unavailable"
+            fi
           fi
 
-          # Truncate diff if too large (keep first 50KB)
-          if [ -f /tmp/i18n-diff.txt ]; then
-            head -c 50000 /tmp/i18n-diff.txt > /tmp/i18n-diff-truncated.txt
-            mv /tmp/i18n-diff-truncated.txt /tmp/i18n-diff.txt
+          FILE_ARGS=""
+          if [ -n "$CHANGED_FILES" ]; then
+            FILE_ARGS="--file $CHANGED_FILES"
           fi
 
-          echo "Detected files: $(cat $GITHUB_OUTPUT | grep CHANGED_FILES || echo 'none')"
+          LANG_ARGS=""
+          if [ -n "$TARGET_LANGS" ]; then
+            LANG_ARGS="--lang $TARGET_LANGS"
+          fi
+
+          {
+            echo "DEFAULT_TARGET_LANGS=$DEFAULT_TARGET_LANGS"
+            echo "BASE_SHA=$BASE_SHA"
+            echo "HEAD_SHA=$HEAD_SHA"
+            echo "CHANGED_FILES=$CHANGED_FILES"
+            echo "TARGET_LANGS=$TARGET_LANGS"
+            echo "SYNC_MODE=$SYNC_MODE"
+            echo "CHANGES_AVAILABLE=$CHANGES_AVAILABLE"
+            echo "CHANGES_SOURCE=$CHANGES_SOURCE"
+            echo "FILE_ARGS=$FILE_ARGS"
+            echo "LANG_ARGS=$LANG_ARGS"
+          } >> "$GITHUB_OUTPUT"
+
+          echo "Files: ${CHANGED_FILES:-<none>}"
+          echo "Languages: ${TARGET_LANGS:-<none>}"
+          echo "Mode: $SYNC_MODE"
 
       - name: Run Claude Code for Translation Sync
-        if: steps.detect_changes.outputs.CHANGED_FILES != ''
-        uses: anthropics/claude-code-action@v1
+        if: steps.context.outputs.CHANGED_FILES != ''
+        uses: anthropics/claude-code-action@b47fd721da662d48c5680e154ad16a73ed74d2e0 # v1.0.93
         with:
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
           github_token: ${{ secrets.GITHUB_TOKEN }}
-          # Allow github-actions bot to trigger this workflow via repository_dispatch
-          # See: https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
           allowed_bots: 'github-actions[bot]'
+          show_full_output: ${{ github.event_name == 'workflow_dispatch' }}
           prompt: |
-            You are a professional i18n synchronization engineer for the Dify project.
-            Your task is to keep all language translations in sync with the English source (en-US).
+            You are the i18n sync agent for the Dify repository.
+            Your job is to keep translations synchronized with the English source files under `${{ github.workspace }}/web/i18n/en-US/`.
 
-            ## CRITICAL TOOL RESTRICTIONS
-            - Use **Read** tool to read files (NOT cat or bash)
-            - Use **Edit** tool to modify JSON files (NOT node, jq, or bash scripts)
-            - Use **Bash** ONLY for: git commands, gh commands, pnpm commands
-            - Run bash commands ONE BY ONE, never combine with && or ||
-            - NEVER use `$()` command substitution - it's not supported. Split into separate commands instead.
+            Use absolute paths at all times:
+            - Repo root: `${{ github.workspace }}`
+            - Web directory: `${{ github.workspace }}/web`
+            - Language config: `${{ github.workspace }}/web/i18n-config/languages.ts`
 
-            ## WORKING DIRECTORY & ABSOLUTE PATHS
-            Claude Code sandbox working directory may vary. Always use absolute paths:
-            - For pnpm: `pnpm --dir ${{ github.workspace }}/web <command>`
-            - For git: `git -C ${{ github.workspace }} <command>`
-            - For gh: `gh --repo ${{ github.repository }} <command>`
-            - For file paths: `${{ github.workspace }}/web/i18n/`
+            Inputs:
+            - Files in scope: `${{ steps.context.outputs.CHANGED_FILES }}`
+            - Target languages: `${{ steps.context.outputs.TARGET_LANGS }}`
+            - Sync mode: `${{ steps.context.outputs.SYNC_MODE }}`
+            - Base SHA: `${{ steps.context.outputs.BASE_SHA }}`
+            - Head SHA: `${{ steps.context.outputs.HEAD_SHA }}`
+            - Scoped file args: `${{ steps.context.outputs.FILE_ARGS }}`
+            - Scoped language args: `${{ steps.context.outputs.LANG_ARGS }}`
+            - Structured change set available: `${{ steps.context.outputs.CHANGES_AVAILABLE }}`
+            - Structured change set source: `${{ steps.context.outputs.CHANGES_SOURCE }}`
+            - Structured change set file: `/tmp/i18n-changes.json`
 
-            ## EFFICIENCY RULES
-            - **ONE Edit per language file** - batch all key additions into a single Edit
-            - Insert new keys at the beginning of JSON (after `{`), lint:fix will sort them
-            - Translate ALL keys for a language mentally first, then do ONE Edit
-
-            ## Context
-            - Changed/target files: ${{ steps.detect_changes.outputs.CHANGED_FILES }}
-            - Target languages (empty means all supported): ${{ steps.detect_changes.outputs.TARGET_LANGS }}
-            - Sync mode: ${{ steps.detect_changes.outputs.SYNC_MODE }}
-            - Translation files are located in: ${{ github.workspace }}/web/i18n/{locale}/{filename}.json
-            - Language configuration is in: ${{ github.workspace }}/web/i18n-config/languages.ts
-            - Git diff is available: ${{ steps.detect_changes.outputs.DIFF_AVAILABLE }}
-
-            ## CRITICAL DESIGN: Verify First, Then Sync
-
-            You MUST follow this three-phase approach:
-
-            ═══════════════════════════════════════════════════════════════
-            ║  PHASE 1: VERIFY - Analyze and Generate Change Report       ║
-            ═══════════════════════════════════════════════════════════════
-
-            ### Step 1.1: Analyze Git Diff (for incremental mode)
-            Use the Read tool to read `/tmp/i18n-diff.txt` to see the git diff.
-
-            Parse the diff to categorize changes:
-            - Lines with `+` (not `+++`): Added or modified values
-            - Lines with `-` (not `---`): Removed or old values
-            - Identify specific keys for each category:
-              * ADD: Keys that appear only in `+` lines (new keys)
-              * UPDATE: Keys that appear in both `-` and `+` lines (value changed)
-              * DELETE: Keys that appear only in `-` lines (removed keys)
-
-            ### Step 1.2: Read Language Configuration
-            Use the Read tool to read `${{ github.workspace }}/web/i18n-config/languages.ts`.
-            Extract all languages with `supported: true`.
-
-            ### Step 1.3: Run i18n:check for Each Language
-            ```bash
-            pnpm --dir ${{ github.workspace }}/web install --frozen-lockfile
-            ```
-            ```bash
-            pnpm --dir ${{ github.workspace }}/web run i18n:check
-            ```
-
-            This will report:
-            - Missing keys (need to ADD)
-            - Extra keys (need to DELETE)
-
-            ### Step 1.4: Generate Change Report
-
-            Create a structured report identifying:
-            ```
-            ╔══════════════════════════════════════════════════════════════╗
-            ║                    I18N SYNC CHANGE REPORT                   ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ Files to process: [list]                                     ║
-            ║ Languages to sync: [list]                                    ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ ADD (New Keys):                                              ║
-            ║   - [filename].[key]: "English value"                        ║
-            ║   ...                                                        ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ UPDATE (Modified Keys - MUST re-translate):                  ║
-            ║   - [filename].[key]: "Old value" → "New value"              ║
-            ║   ...                                                        ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ DELETE (Extra Keys):                                         ║
-            ║   - [language]/[filename].[key]                              ║
-            ║   ...                                                        ║
-            ╚══════════════════════════════════════════════════════════════╝
-            ```
-
-            **IMPORTANT**: For UPDATE detection, compare git diff to find keys where
-            the English value changed. These MUST be re-translated even if target
-            language already has a translation (it's now stale!).
-
-            ═══════════════════════════════════════════════════════════════
-            ║  PHASE 2: SYNC - Execute Changes Based on Report            ║
-            ═══════════════════════════════════════════════════════════════
-
-            ### Step 2.1: Process ADD Operations (BATCH per language file)
-
-            **CRITICAL WORKFLOW for efficiency:**
-            1. First, translate ALL new keys for ALL languages mentally
-            2. Then, for EACH language file, do ONE Edit operation:
-               - Read the file once
-               - Insert ALL new keys at the beginning (right after the opening `{`)
-               - Don't worry about alphabetical order - lint:fix will sort them later
-
-            Example Edit (adding 3 keys to zh-Hans/app.json):
-            ```
-            old_string: '{\n  "accessControl"'
-            new_string: '{\n  "newKey1": "translation1",\n  "newKey2": "translation2",\n  "newKey3": "translation3",\n  "accessControl"'
-            ```
-
-            **IMPORTANT**:
-            - ONE Edit per language file (not one Edit per key!)
-            - Always use the Edit tool. NEVER use bash scripts, node, or jq.
-
-            ### Step 2.2: Process UPDATE Operations
-
-            **IMPORTANT: Special handling for zh-Hans and ja-JP**
-            If zh-Hans or ja-JP files were ALSO modified in the same push:
-            - Run: `git -C ${{ github.workspace }} diff HEAD~1 --name-only` and check for zh-Hans or ja-JP files
-            - If found, it means someone manually translated them. Apply these rules:
-
-            1. **Missing keys**: Still ADD them (completeness required)
-            2. **Existing translations**: Compare with the NEW English value:
-               - If translation is **completely wrong** or **unrelated** → Update it
-               - If translation is **roughly correct** (captures the meaning) → Keep it, respect manual work
-               - When in doubt, **keep the manual translation**
-
-            Example:
-            - English changed: "Save" → "Save Changes"
-            - Manual translation: "保存更改" → Keep it (correct meaning)
-            - Manual translation: "删除" → Update it (completely wrong)
-
-            For other languages:
-            Use Edit tool to replace the old value with the new translation.
-            You can batch multiple updates in one Edit if they are adjacent.
-
-            ### Step 2.3: Process DELETE Operations
-            For extra keys reported by i18n:check:
-            - Run: `pnpm --dir ${{ github.workspace }}/web run i18n:check --auto-remove`
-            - Or manually remove from target language JSON files
-
-            ## Translation Guidelines
-
-            - PRESERVE all placeholders exactly as-is:
-              - `{{variable}}` - Mustache interpolation
-              - `${variable}` - Template literal
-              - `<tag>content</tag>` - HTML tags
-              - `_one`, `_other` - Pluralization suffixes (these are KEY suffixes, not values)
-
-              **CRITICAL: Variable names and tag names MUST stay in English - NEVER translate them**
-
-              ✅ CORRECT examples:
-              - English: "{{count}} items" → Japanese: "{{count}} 個のアイテム"
-              - English: "{{name}} updated" → Korean: "{{name}} 업데이트됨"
-              - English: "<email>{{email}}</email>" → Chinese: "<email>{{email}}</email>"
-              - English: "<CustomLink>Marketplace</CustomLink>" → Japanese: "<CustomLink>マーケットプレイス</CustomLink>"
-
-              ❌ WRONG examples (NEVER do this - will break the application):
-              - "{{count}}" → "{{カウント}}" ❌ (variable name translated to Japanese)
-              - "{{name}}" → "{{이름}}" ❌ (variable name translated to Korean)
-              - "{{email}}" → "{{邮箱}}" ❌ (variable name translated to Chinese)
-              - "<email>" → "<メール>" ❌ (tag name translated)
-              - "<CustomLink>" → "<自定义链接>" ❌ (component name translated)
-
-            - Use appropriate language register (formal/informal) based on existing translations
-            - Match existing translation style in each language
-            - Technical terms: check existing conventions per language
-            - For CJK languages: no spaces between characters unless necessary
-            - For RTL languages (ar-TN, fa-IR): ensure proper text handling
-
-            ## Output Format Requirements
-            - Alphabetical key ordering (if original file uses it)
-            - 2-space indentation
-            - Trailing newline at end of file
-            - Valid JSON (use proper escaping for special characters)
-
-            ═══════════════════════════════════════════════════════════════
-            ║  PHASE 3: RE-VERIFY - Confirm All Issues Resolved           ║
-            ═══════════════════════════════════════════════════════════════
-
-            ### Step 3.1: Run Lint Fix (IMPORTANT!)
-            ```bash
-            pnpm --dir ${{ github.workspace }}/web lint:fix --quiet -- 'i18n/**/*.json'
-            ```
-            This ensures:
-            - JSON keys are sorted alphabetically (jsonc/sort-keys rule)
-            - Valid i18n keys (dify-i18n/valid-i18n-keys rule)
-            - No extra keys (dify-i18n/no-extra-keys rule)
-
-            ### Step 3.2: Run Final i18n Check
-            ```bash
-            pnpm --dir ${{ github.workspace }}/web run i18n:check
-            ```
-
-            ### Step 3.3: Fix Any Remaining Issues
-            If check reports issues:
-            - Go back to PHASE 2 for unresolved items
-            - Repeat until check passes
-
-            ### Step 3.4: Generate Final Summary
-            ```
-            ╔══════════════════════════════════════════════════════════════╗
-            ║                    SYNC COMPLETED SUMMARY                    ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ Language      │ Added │ Updated │ Deleted │ Status          ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ zh-Hans       │  5    │   2     │    1    │ ✓ Complete      ║
-            ║ ja-JP         │  5    │   2     │    1    │ ✓ Complete      ║
-            ║ ...           │ ...   │  ...    │   ...   │ ...             ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ i18n:check    │ PASSED - All keys in sync                   ║
-            ╚══════════════════════════════════════════════════════════════╝
-            ```
-
-            ## Mode-Specific Behavior
-
-            **SYNC_MODE = "incremental"** (default):
-            - Focus on keys identified from git diff
-            - Also check i18n:check output for any missing/extra keys
-            - Efficient for small changes
-
-            **SYNC_MODE = "full"**:
-            - Compare ALL keys between en-US and each language
-            - Run i18n:check to identify all discrepancies
-            - Use for first-time sync or fixing historical issues
-
-            ## Important Notes
-
-            1. Always run i18n:check BEFORE and AFTER making changes
-            2. The check script is the source of truth for missing/extra keys
-            3. For UPDATE scenario: git diff is the source of truth for changed values
-            4. Create a single commit with all translation changes
-            5. If any translation fails, continue with others and report failures
-
-            ═══════════════════════════════════════════════════════════════
-            ║  PHASE 4: COMMIT AND CREATE PR                              ║
-            ═══════════════════════════════════════════════════════════════
-
-            After all translations are complete and verified:
-
-            ### Step 4.1: Check for changes
-            ```bash
-            git -C ${{ github.workspace }} status --porcelain
-            ```
-
-            If there are changes:
-
-            ### Step 4.2: Create a new branch and commit
-            Run these git commands ONE BY ONE (not combined with &&).
-            **IMPORTANT**: Do NOT use `$()` command substitution. Use two separate commands:
-
-            1. First, get the timestamp:
-            ```bash
-            date +%Y%m%d-%H%M%S
-            ```
-            (Note the output, e.g., "20260115-143052")
-
-            2. Then create branch using the timestamp value:
-            ```bash
-            git -C ${{ github.workspace }} checkout -b chore/i18n-sync-20260115-143052
-            ```
-            (Replace "20260115-143052" with the actual timestamp from step 1)
-
-            3. Stage changes:
-            ```bash
-            git -C ${{ github.workspace }} add web/i18n/
-            ```
-
-            4. Commit:
-            ```bash
-            git -C ${{ github.workspace }} commit -m "chore(i18n): sync translations with en-US - Mode: ${{ steps.detect_changes.outputs.SYNC_MODE }}"
-            ```
-
-            5. Push:
-            ```bash
-            git -C ${{ github.workspace }} push origin HEAD
-            ```
-
-            ### Step 4.3: Create Pull Request
-            ```bash
-            gh pr create --repo ${{ github.repository }} --title "chore(i18n): sync translations with en-US" --body "## Summary
-
-            This PR was automatically generated to sync i18n translation files.
-
-            ### Changes
-            - Mode: ${{ steps.detect_changes.outputs.SYNC_MODE }}
-            - Files processed: ${{ steps.detect_changes.outputs.CHANGED_FILES }}
-
-            ### Verification
-            - [x] \`i18n:check\` passed
-            - [x] \`lint:fix\` applied
-
-            🤖 Generated with Claude Code GitHub Action" --base main
-            ```
+            Tool rules:
+            - Use Read for repository files.
+            - Use Edit for JSON updates.
+            - Use Bash only for `vp`.
+            - Do not use Bash for `git`, `gh`, or branch management.
 
+            Required execution plan:
+            1. Resolve target languages.
+               - Use the provided `Target languages` value as the source of truth.
+               - If it is unexpectedly empty, read `${{ github.workspace }}/web/i18n-config/languages.ts` and use every language with `supported: true` except `en-US`.
+            2. Stay strictly in scope.
+               - Only process the files listed in `Files in scope`.
+               - Only process the resolved target languages, never `en-US`.
+               - Do not touch unrelated i18n files.
+               - Do not modify `${{ github.workspace }}/web/i18n/en-US/`.
+            3. Resolve source changes.
+               - If `Structured change set available` is `true`, read `/tmp/i18n-changes.json` and use it as the source of truth for file-level and key-level changes.
+               - For each file entry:
+                 - `added` contains new English keys that need translations.
+                 - `updated` contains stale keys whose English source changed; re-translate using the `after` value.
+                 - `deleted` contains keys that should be removed from locale files.
+                 - `fileDeleted: true` means the English file no longer exists; remove the matching locale file if present.
+               - Read the current English JSON file for any file that still exists so wording, placeholders, and surrounding terminology stay accurate.
+               - If `Structured change set available` is `false`, treat this as a scoped full sync and use the current English files plus scoped checks as the source of truth.
+            4. Run a scoped pre-check before editing:
+               - `vp run dify-web#i18n:check ${{ steps.context.outputs.FILE_ARGS }} ${{ steps.context.outputs.LANG_ARGS }}`
+               - Use this command as the source of truth for missing and extra keys inside the current scope.
+            5. Apply translations.
+               - For every target language and scoped file:
+                 - If `fileDeleted` is `true`, remove the locale file if it exists and skip the rest of that file.
+                 - If the locale file does not exist yet, create it with `Write` and then continue with `Edit` as needed.
+                 - ADD missing keys.
+                 - UPDATE stale translations when the English value changed.
+                 - DELETE removed keys. Prefer `vp run dify-web#i18n:check ${{ steps.context.outputs.FILE_ARGS }} ${{ steps.context.outputs.LANG_ARGS }} --auto-remove` for extra keys so deletions stay in scope.
+               - Preserve placeholders exactly: `{{variable}}`, `${variable}`, HTML tags, component tags, and variable names.
+               - Match the existing terminology and register used by each locale.
+               - Prefer one Edit per file when stable, but prioritize correctness over batching.
+            6. Verify only the edited files.
+               - Run `vp run dify-web#lint:fix --quiet -- <relative edited i18n file paths under web/>`
+               - Run `vp run dify-web#i18n:check ${{ steps.context.outputs.FILE_ARGS }} ${{ steps.context.outputs.LANG_ARGS }}`
+               - If verification fails, fix the remaining problems before continuing.
+            7. Stop after the scoped locale files are updated and verification passes.
+               - Do not create branches, commits, or pull requests.
           claude_args: |
-            --max-turns 150
-            --allowedTools "Read,Write,Edit,Bash(git *),Bash(git:*),Bash(gh *),Bash(gh:*),Bash(pnpm *),Bash(pnpm:*),Bash(date *),Bash(date:*),Glob,Grep"
+            --max-turns 120
+            --allowedTools "Read,Write,Edit,Bash(vp *),Bash(vp:*),Glob,Grep"
+
+      - name: Prepare branch metadata
+        id: pr_meta
+        if: steps.context.outputs.CHANGED_FILES != ''
+        shell: bash
+        run: |
+          if [ -z "$(git -C "${{ github.workspace }}" status --porcelain -- web/i18n/)" ]; then
+            echo "has_changes=false" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+
+          SCOPE_HASH=$(printf '%s|%s|%s' "${{ steps.context.outputs.CHANGED_FILES }}" "${{ steps.context.outputs.TARGET_LANGS }}" "${{ steps.context.outputs.SYNC_MODE }}" | sha256sum | cut -c1-8)
+          HEAD_SHORT=$(printf '%s' "${{ steps.context.outputs.HEAD_SHA }}" | cut -c1-12)
+          BRANCH_NAME="chore/i18n-sync-${HEAD_SHORT}-${SCOPE_HASH}"
+
+          {
+            echo "has_changes=true"
+            echo "branch_name=$BRANCH_NAME"
+          } >> "$GITHUB_OUTPUT"
+
+      - name: Commit translation changes
+        if: steps.pr_meta.outputs.has_changes == 'true'
+        shell: bash
+        run: |
+          git -C "${{ github.workspace }}" checkout -B "${{ steps.pr_meta.outputs.branch_name }}"
+          git -C "${{ github.workspace }}" add web/i18n/
+          git -C "${{ github.workspace }}" commit -m "chore(i18n): sync translations with en-US"
+
+      - name: Push translation branch
+        if: steps.pr_meta.outputs.has_changes == 'true'
+        shell: bash
+        run: |
+          if git -C "${{ github.workspace }}" ls-remote --exit-code --heads origin "${{ steps.pr_meta.outputs.branch_name }}" >/dev/null 2>&1; then
+            git -C "${{ github.workspace }}" push --force-with-lease origin "${{ steps.pr_meta.outputs.branch_name }}"
+          else
+            git -C "${{ github.workspace }}" push --set-upstream origin "${{ steps.pr_meta.outputs.branch_name }}"
+          fi
+
+      - name: Create or update translation PR
+        if: steps.pr_meta.outputs.has_changes == 'true'
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          BRANCH_NAME: ${{ steps.pr_meta.outputs.branch_name }}
+          FILES_IN_SCOPE: ${{ steps.context.outputs.CHANGED_FILES }}
+          TARGET_LANGS: ${{ steps.context.outputs.TARGET_LANGS }}
+          SYNC_MODE: ${{ steps.context.outputs.SYNC_MODE }}
+          CHANGES_SOURCE: ${{ steps.context.outputs.CHANGES_SOURCE }}
+          BASE_SHA: ${{ steps.context.outputs.BASE_SHA }}
+          HEAD_SHA: ${{ steps.context.outputs.HEAD_SHA }}
+          REPO_NAME: ${{ github.repository }}
+        shell: bash
+        run: |
+          PR_BODY_FILE=/tmp/i18n-pr-body.md
+          LANG_COUNT=$(printf '%s\n' "$TARGET_LANGS" | wc -w | tr -d ' ')
+          if [ "$LANG_COUNT" = "0" ]; then
+            LANG_COUNT="0"
+          fi
+          export LANG_COUNT
+
+          node <<'NODE' > "$PR_BODY_FILE"
+          const fs = require('node:fs')
+
+          const changesPath = '/tmp/i18n-changes.json'
+          const changes = fs.existsSync(changesPath)
+            ? JSON.parse(fs.readFileSync(changesPath, 'utf8'))
+            : { changes: {} }
+
+          const filesInScope = (process.env.FILES_IN_SCOPE || '').split(/\s+/).filter(Boolean)
+          const lines = [
+            '## Summary',
+            '',
+            `- **Files synced**: \`${process.env.FILES_IN_SCOPE || '<none>'}\``,
+            `- **Languages updated**: ${process.env.TARGET_LANGS || '<none>'} (${process.env.LANG_COUNT} languages)`,
+            `- **Sync mode**: ${process.env.SYNC_MODE}${process.env.BASE_SHA ? ` (base: \`${process.env.BASE_SHA.slice(0, 10)}\`, head: \`${process.env.HEAD_SHA.slice(0, 10)}\`)` : ` (head: \`${process.env.HEAD_SHA.slice(0, 10)}\`)`}`,
+            '',
+            '### Key changes',
+          ]
+
+          for (const fileName of filesInScope) {
+            const fileChange = changes.changes?.[fileName] || { added: {}, updated: {}, deleted: [], fileDeleted: false }
+            const addedKeys = Object.keys(fileChange.added || {})
+            const updatedKeys = Object.keys(fileChange.updated || {})
+            const deletedKeys = fileChange.deleted || []
+            lines.push(`- \`${fileName}\`: +${addedKeys.length} / ~${updatedKeys.length} / -${deletedKeys.length}${fileChange.fileDeleted ? ' (file deleted in en-US)' : ''}`)
+          }
+
+          lines.push(
+            '',
+            '## Verification',
+            '',
+            `- \`vp run dify-web#i18n:check --file ${process.env.FILES_IN_SCOPE} --lang ${process.env.TARGET_LANGS}\``,
+            `- \`vp run dify-web#lint:fix --quiet -- <edited i18n files under web/>\``,
+            '',
+            '## Notes',
+            '',
+            '- This PR was generated from structured en-US key changes produced by `trigger-i18n-sync.yml`.',
+            `- Structured change source: ${process.env.CHANGES_SOURCE || 'unknown'}.`,
+            '- Branch name is deterministic for the head SHA and scope, so reruns update the same PR instead of opening duplicates.',
+            '',
+            '🤖 Generated with [Claude Code](https://claude.com/claude-code)'
+          )
+
+          process.stdout.write(lines.join('\n'))
+          NODE
+
+          EXISTING_PR_NUMBER=$(gh pr list --repo "$REPO_NAME" --head "$BRANCH_NAME" --state open --json number --jq '.[0].number')
+
+          if [ -n "$EXISTING_PR_NUMBER" ] && [ "$EXISTING_PR_NUMBER" != "null" ]; then
+            gh pr edit "$EXISTING_PR_NUMBER" --repo "$REPO_NAME" --title "chore(i18n): sync translations with en-US" --body-file "$PR_BODY_FILE"
+          else
+            gh pr create --repo "$REPO_NAME" --head "$BRANCH_NAME" --base main --title "chore(i18n): sync translations with en-US" --body-file "$PR_BODY_FILE"
+          fi

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

@@ -1,9 +1,5 @@
 name: Trigger i18n Sync on Push
 
-# This workflow bridges the push event to repository_dispatch
-# because claude-code-action doesn't support push events directly.
-# See: https://github.com/langgenius/dify/issues/30743
-
 on:
   push:
     branches: [main]
@@ -13,6 +9,10 @@ on:
 permissions:
   contents: write
 
+concurrency:
+  group: trigger-i18n-sync-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
   trigger:
     if: github.repository == 'langgenius/dify'
@@ -21,46 +21,70 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-depth: 0
 
-      - name: Detect changed files and generate diff
+      - name: Detect changed files and build structured change set
         id: detect
+        shell: bash
         run: |
-          BEFORE_SHA="${{ github.event.before }}"
-          # Handle edge case: force push may have null/zero SHA
-          if [ -z "$BEFORE_SHA" ] || [ "$BEFORE_SHA" = "0000000000000000000000000000000000000000" ]; then
-            BEFORE_SHA="HEAD~1"
+          BASE_SHA="${{ github.event.before }}"
+          if [ -z "$BASE_SHA" ] || [ "$BASE_SHA" = "0000000000000000000000000000000000000000" ]; then
+            BASE_SHA=$(git rev-parse HEAD~1 2>/dev/null || true)
           fi
+          HEAD_SHA="${{ github.sha }}"
 
-          # Detect changed i18n files
-          changed=$(git diff --name-only "$BEFORE_SHA" "${{ github.sha }}" -- 'web/i18n/en-US/*.json' 2>/dev/null | xargs -n1 basename 2>/dev/null | sed 's/.json$//' | tr '\n' ' ' || echo "")
-          echo "changed_files=$changed" >> $GITHUB_OUTPUT
-
-          # Generate diff for context
-          git diff "$BEFORE_SHA" "${{ github.sha }}" -- 'web/i18n/en-US/*.json' > /tmp/i18n-diff.txt 2>/dev/null || echo "" > /tmp/i18n-diff.txt
-
-          # Truncate if too large (keep first 50KB to match receiving workflow)
-          head -c 50000 /tmp/i18n-diff.txt > /tmp/i18n-diff-truncated.txt
-          mv /tmp/i18n-diff-truncated.txt /tmp/i18n-diff.txt
-
-          # Base64 encode the diff for safe JSON transport (portable, single-line)
-          diff_base64=$(base64 < /tmp/i18n-diff.txt | tr -d '\n')
-          echo "diff_base64=$diff_base64" >> $GITHUB_OUTPUT
-
-          if [ -n "$changed" ]; then
-            echo "has_changes=true" >> $GITHUB_OUTPUT
-            echo "Detected changed files: $changed"
+          if [ -n "$BASE_SHA" ]; then
+            CHANGED_FILES=$(git diff --name-only "$BASE_SHA" "$HEAD_SHA" -- 'web/i18n/en-US/*.json' 2>/dev/null | sed -n 's@^.*/@@p' | sed 's/\.json$//' | tr '\n' ' ' | sed 's/[[:space:]]*$//')
           else
-            echo "has_changes=false" >> $GITHUB_OUTPUT
-            echo "No i18n changes detected"
+            CHANGED_FILES=$(find web/i18n/en-US -maxdepth 1 -type f -name '*.json' -print | sed -n 's@^.*/@@p' | sed 's/\.json$//' | sort | tr '\n' ' ' | sed 's/[[:space:]]*$//')
           fi
 
+          export BASE_SHA HEAD_SHA CHANGED_FILES
+          node .github/scripts/generate-i18n-changes.mjs
+
+          if [ -n "$CHANGED_FILES" ]; then
+            echo "has_changes=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "has_changes=false" >> "$GITHUB_OUTPUT"
+          fi
+
+          echo "base_sha=$BASE_SHA" >> "$GITHUB_OUTPUT"
+          echo "head_sha=$HEAD_SHA" >> "$GITHUB_OUTPUT"
+          echo "changed_files=$CHANGED_FILES" >> "$GITHUB_OUTPUT"
+
       - name: Trigger i18n sync workflow
         if: steps.detect.outputs.has_changes == 'true'
-        uses: peter-evans/repository-dispatch@v3
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
+        env:
+          BASE_SHA: ${{ steps.detect.outputs.base_sha }}
+          HEAD_SHA: ${{ steps.detect.outputs.head_sha }}
+          CHANGED_FILES: ${{ steps.detect.outputs.changed_files }}
         with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          event-type: i18n-sync
-          client-payload: '{"changed_files": "${{ steps.detect.outputs.changed_files }}", "diff_base64": "${{ steps.detect.outputs.diff_base64 }}", "sync_mode": "incremental", "trigger_sha": "${{ github.sha }}"}'
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const fs = require('fs')
+
+            const changesJson = fs.readFileSync('/tmp/i18n-changes.json', 'utf8')
+            const changesBase64 = Buffer.from(changesJson).toString('base64')
+            const maxEmbeddedChangesChars = 48000
+            const changesEmbedded = changesBase64.length <= maxEmbeddedChangesChars
+
+            if (!changesEmbedded) {
+              console.log(`Structured change set too large to embed safely (${changesBase64.length} chars). Downstream workflow will regenerate it from git history.`)
+            }
+
+            await github.rest.repos.createDispatchEvent({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              event_type: 'i18n-sync',
+              client_payload: {
+                changed_files: process.env.CHANGED_FILES,
+                changes_base64: changesEmbedded ? changesBase64 : '',
+                changes_embedded: changesEmbedded,
+                sync_mode: 'incremental',
+                base_sha: process.env.BASE_SHA,
+                head_sha: process.env.HEAD_SHA,
+              },
+            })

.github/workflows/vdb-tests-full.yml

@@ -0,0 +1,95 @@
+name: Run Full VDB Tests
+
+on:
+  schedule:
+    - cron: '0 3 * * 1'
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+concurrency:
+  group: vdb-tests-full-${{ github.ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    name: Full VDB Tests
+    if: github.repository == 'langgenius/dify'
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version:
+          - "3.12"
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+
+      - name: Free Disk Space
+        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@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        with:
+          enable-cache: true
+          python-version: ${{ matrix.python-version }}
+          cache-dependency-glob: api/uv.lock
+
+      - name: Check UV lockfile
+        run: uv lock --project api --check
+
+      - name: Install dependencies
+        run: uv sync --project api --dev
+
+      - name: Set up dotenvs
+        run: |
+          cp docker/.env.example docker/.env
+          cp docker/middleware.env.example docker/middleware.env
+
+      - name: Expose Service Ports
+        run: sh .github/workflows/expose_service_ports.sh
+
+#      - name: Set up Vector Store (TiDB)
+#        uses: hoverkraft-tech/compose-action@v2.0.2
+#        with:
+#          compose-file: docker/tidb/docker-compose.yaml
+#          services: |
+#            tidb
+#            tiflash
+
+      - name: Set up Full Vector Store Matrix
+        uses: hoverkraft-tech/compose-action@4894d2492015c1774ee5a13a95b1072093087ec3 # v2.5.0
+        with:
+          compose-file: |
+            docker/docker-compose.yaml
+          services: |
+            weaviate
+            qdrant
+            couchbase-server
+            etcd
+            minio
+            milvus-standalone
+            pgvecto-rs
+            pgvector
+            chroma
+            elasticsearch
+            oceanbase
+
+      - name: setup test config
+        run: |
+          echo $(pwd)
+          ls -lah .
+          cp api/tests/integration_tests/.env.example api/tests/integration_tests/.env
+
+#      - name: Check VDB Ready (TiDB)
+#        run: uv run --project api python api/providers/vdb/tidb-vector/tests/integration_tests/check_tiflash_ready.py
+
+      - name: Test Vector Stores
+        run: uv run --project api bash dev/pytest/pytest_vdb.sh

.github/workflows/vdb-tests.yml

@@ -1,37 +1,39 @@
-name: Run VDB Tests
+name: Run VDB Smoke Tests
 
 on:
   workflow_call:
 
+permissions:
+  contents: read
+
 concurrency:
   group: vdb-tests-${{ github.head_ref || github.run_id }}
   cancel-in-progress: true
 
 jobs:
   test:
-    name: VDB Tests
+    name: VDB Smoke Tests
     runs-on: ubuntu-latest
     strategy:
       matrix:
         python-version:
-          - "3.11"
           - "3.12"
 
     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@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
         with:
           enable-cache: true
           python-version: ${{ matrix.python-version }}
@@ -59,23 +61,18 @@ jobs:
 #            tidb
 #            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
+      - name: Set up Vector Stores for Smoke Coverage
+        uses: hoverkraft-tech/compose-action@4894d2492015c1774ee5a13a95b1072093087ec3 # v2.5.0
         with:
           compose-file: |
             docker/docker-compose.yaml
           services: |
+            db_postgres
+            redis
             weaviate
             qdrant
-            couchbase-server
-            etcd
-            minio
-            milvus-standalone
-            pgvecto-rs
             pgvector
             chroma
-            elasticsearch
-            oceanbase
 
       - name: setup test config
         run: |
@@ -84,7 +81,12 @@ jobs:
           cp api/tests/integration_tests/.env.example api/tests/integration_tests/.env
 
 #      - name: Check VDB Ready (TiDB)
-#        run: uv run --project api python api/tests/integration_tests/vdb/tidb_vector/check_tiflash_ready.py
+#        run: uv run --project api python api/providers/vdb/tidb-vector/tests/integration_tests/check_tiflash_ready.py
 
       - name: Test Vector Stores
-        run: uv run --project api bash dev/pytest/pytest_vdb.sh
+        run: |
+          uv run --project api pytest --timeout "${PYTEST_TIMEOUT:-180}" \
+            api/providers/vdb/vdb-chroma/tests/integration_tests \
+            api/providers/vdb/vdb-pgvector/tests/integration_tests \
+            api/providers/vdb/vdb-qdrant/tests/integration_tests \
+            api/providers/vdb/vdb-weaviate/tests/integration_tests

.github/workflows/web-e2e.yml

@@ -0,0 +1,68 @@
+name: Web Full-Stack E2E
+
+on:
+  workflow_call:
+
+permissions:
+  contents: read
+
+concurrency:
+  group: web-e2e-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    name: Web Full-Stack E2E
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        shell: bash
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+
+      - name: Setup web dependencies
+        uses: ./.github/actions/setup-web
+
+      - name: Setup UV and Python
+        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        with:
+          enable-cache: true
+          python-version: "3.12"
+          cache-dependency-glob: api/uv.lock
+
+      - name: Install API dependencies
+        run: uv sync --project api --dev
+
+      - name: Install Playwright browser
+        working-directory: ./e2e
+        run: vp run e2e:install
+
+      - name: Run isolated source-api and built-web Cucumber E2E tests
+        working-directory: ./e2e
+        env:
+          E2E_ADMIN_EMAIL: e2e-admin@example.com
+          E2E_ADMIN_NAME: E2E Admin
+          E2E_ADMIN_PASSWORD: E2eAdmin12345
+          E2E_FORCE_WEB_BUILD: "1"
+          E2E_INIT_PASSWORD: E2eInit12345
+        run: vp run e2e:full
+
+      - name: Upload Cucumber report
+        if: ${{ !cancelled() }}
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: cucumber-report
+          path: e2e/cucumber-report
+          retention-days: 7
+
+      - name: Upload E2E logs
+        if: ${{ !cancelled() }}
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: e2e-logs
+          path: e2e/.logs
+          retention-days: 7

.github/workflows/web-tests.yml

@@ -2,6 +2,12 @@ name: Web Tests
 
 on:
   workflow_call:
+    secrets:
+      CODECOV_TOKEN:
+        required: false
+
+permissions:
+  contents: read
 
 concurrency:
   group: web-tests-${{ github.head_ref || github.run_id }}
@@ -9,8 +15,15 @@ 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
@@ -18,396 +31,95 @@ 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: Coverage Summary
-        if: always()
-        id: coverage-summary
-        run: |
-          set -eo pipefail
-
-          COVERAGE_FILE="coverage/coverage-final.json"
-          COVERAGE_SUMMARY_FILE="coverage/coverage-summary.json"
-
-          if [ ! -f "$COVERAGE_FILE" ] && [ ! -f "$COVERAGE_SUMMARY_FILE" ]; then
-            echo "has_coverage=false" >> "$GITHUB_OUTPUT"
-            echo "### 🚨 Test Coverage Report :test_tube:" >> "$GITHUB_STEP_SUMMARY"
-            echo "Coverage data not found. Ensure Vitest runs with coverage enabled." >> "$GITHUB_STEP_SUMMARY"
-            exit 0
-          fi
-
-          echo "has_coverage=true" >> "$GITHUB_OUTPUT"
-
-          node <<'NODE' >> "$GITHUB_STEP_SUMMARY"
-          const fs = require('fs');
-          const path = require('path');
-          let libCoverage = null;
-
-          try {
-            libCoverage = require('istanbul-lib-coverage');
-          } catch (error) {
-            libCoverage = null;
-          }
-
-          const summaryPath = path.join('coverage', 'coverage-summary.json');
-          const finalPath = path.join('coverage', 'coverage-final.json');
-
-          const hasSummary = fs.existsSync(summaryPath);
-          const hasFinal = fs.existsSync(finalPath);
-
-          if (!hasSummary && !hasFinal) {
-            console.log('### Test Coverage Summary :test_tube:');
-            console.log('');
-            console.log('No coverage data found.');
-            process.exit(0);
-          }
-
-          const summary = hasSummary
-            ? JSON.parse(fs.readFileSync(summaryPath, 'utf8'))
-            : null;
-          const coverage = hasFinal
-            ? JSON.parse(fs.readFileSync(finalPath, 'utf8'))
-            : null;
-
-          const getLineCoverageFromStatements = (statementMap, statementHits) => {
-            const lineHits = {};
-
-            if (!statementMap || !statementHits) {
-              return lineHits;
-            }
-
-            Object.entries(statementMap).forEach(([key, statement]) => {
-              const line = statement?.start?.line;
-              if (!line) {
-                return;
-              }
-              const hits = statementHits[key] ?? 0;
-              const previous = lineHits[line];
-              lineHits[line] = previous === undefined ? hits : Math.max(previous, hits);
-            });
-
-            return lineHits;
-          };
-
-          const getFileCoverage = (entry) => (
-            libCoverage ? libCoverage.createFileCoverage(entry) : null
-          );
-
-          const getLineHits = (entry, fileCoverage) => {
-            const lineHits = entry.l ?? {};
-            if (Object.keys(lineHits).length > 0) {
-              return lineHits;
-            }
-            if (fileCoverage) {
-              return fileCoverage.getLineCoverage();
-            }
-            return getLineCoverageFromStatements(entry.statementMap ?? {}, entry.s ?? {});
-          };
-
-          const getUncoveredLines = (entry, fileCoverage, lineHits) => {
-            if (lineHits && Object.keys(lineHits).length > 0) {
-              return Object.entries(lineHits)
-                .filter(([, count]) => count === 0)
-                .map(([line]) => Number(line))
-                .sort((a, b) => a - b);
-            }
-            if (fileCoverage) {
-              return fileCoverage.getUncoveredLines();
-            }
-            return [];
-          };
-
-          const totals = {
-            lines: { covered: 0, total: 0 },
-            statements: { covered: 0, total: 0 },
-            branches: { covered: 0, total: 0 },
-            functions: { covered: 0, total: 0 },
-          };
-          const fileSummaries = [];
-
-          if (summary) {
-            const totalEntry = summary.total ?? {};
-            ['lines', 'statements', 'branches', 'functions'].forEach((key) => {
-              if (totalEntry[key]) {
-                totals[key].covered = totalEntry[key].covered ?? 0;
-                totals[key].total = totalEntry[key].total ?? 0;
-              }
-            });
-
-            Object.entries(summary)
-              .filter(([file]) => file !== 'total')
-              .forEach(([file, data]) => {
-                fileSummaries.push({
-                  file,
-                  pct: data.lines?.pct ?? data.statements?.pct ?? 0,
-                  lines: {
-                    covered: data.lines?.covered ?? 0,
-                    total: data.lines?.total ?? 0,
-                  },
-                });
-              });
-          } else if (coverage) {
-            Object.entries(coverage).forEach(([file, entry]) => {
-              const fileCoverage = getFileCoverage(entry);
-              const lineHits = getLineHits(entry, fileCoverage);
-              const statementHits = entry.s ?? {};
-              const branchHits = entry.b ?? {};
-              const functionHits = entry.f ?? {};
-
-              const lineTotal = Object.keys(lineHits).length;
-              const lineCovered = Object.values(lineHits).filter((n) => n > 0).length;
-
-              const statementTotal = Object.keys(statementHits).length;
-              const statementCovered = Object.values(statementHits).filter((n) => n > 0).length;
-
-              const branchTotal = Object.values(branchHits).reduce((acc, branches) => acc + branches.length, 0);
-              const branchCovered = Object.values(branchHits).reduce(
-                (acc, branches) => acc + branches.filter((n) => n > 0).length,
-                0,
-              );
-
-              const functionTotal = Object.keys(functionHits).length;
-              const functionCovered = Object.values(functionHits).filter((n) => n > 0).length;
-
-              totals.lines.total += lineTotal;
-              totals.lines.covered += lineCovered;
-              totals.statements.total += statementTotal;
-              totals.statements.covered += statementCovered;
-              totals.branches.total += branchTotal;
-              totals.branches.covered += branchCovered;
-              totals.functions.total += functionTotal;
-              totals.functions.covered += functionCovered;
-
-              const pct = (covered, tot) => (tot > 0 ? (covered / tot) * 100 : 0);
-
-              fileSummaries.push({
-                file,
-                pct: pct(lineCovered || statementCovered, lineTotal || statementTotal),
-                lines: {
-                  covered: lineCovered || statementCovered,
-                  total: lineTotal || statementTotal,
-                },
-              });
-            });
-          }
-
-          const pct = (covered, tot) => (tot > 0 ? ((covered / tot) * 100).toFixed(2) : '0.00');
-
-          console.log('### Test Coverage Summary :test_tube:');
-          console.log('');
-          console.log('| Metric | Coverage | Covered / Total |');
-          console.log('|--------|----------|-----------------|');
-          console.log(`| Lines | ${pct(totals.lines.covered, totals.lines.total)}% | ${totals.lines.covered} / ${totals.lines.total} |`);
-          console.log(`| Statements | ${pct(totals.statements.covered, totals.statements.total)}% | ${totals.statements.covered} / ${totals.statements.total} |`);
-          console.log(`| Branches | ${pct(totals.branches.covered, totals.branches.total)}% | ${totals.branches.covered} / ${totals.branches.total} |`);
-          console.log(`| Functions | ${pct(totals.functions.covered, totals.functions.total)}% | ${totals.functions.covered} / ${totals.functions.total} |`);
-
-          console.log('');
-          console.log('<details><summary>File coverage (lowest lines first)</summary>');
-          console.log('');
-          console.log('```');
-          fileSummaries
-            .sort((a, b) => (a.pct - b.pct) || (b.lines.total - a.lines.total))
-            .slice(0, 25)
-            .forEach(({ file, pct, lines }) => {
-              console.log(`${pct.toFixed(2)}%\t${lines.covered}/${lines.total}\t${file}`);
-            });
-          console.log('```');
-          console.log('</details>');
-
-          if (coverage) {
-            const pctValue = (covered, tot) => {
-              if (tot === 0) {
-                return '0';
-              }
-              return ((covered / tot) * 100)
-                .toFixed(2)
-                .replace(/\.?0+$/, '');
-            };
-
-            const formatLineRanges = (lines) => {
-              if (lines.length === 0) {
-                return '';
-              }
-              const ranges = [];
-              let start = lines[0];
-              let end = lines[0];
-
-              for (let i = 1; i < lines.length; i += 1) {
-                const current = lines[i];
-                if (current === end + 1) {
-                  end = current;
-                  continue;
-                }
-                ranges.push(start === end ? `${start}` : `${start}-${end}`);
-                start = current;
-                end = current;
-              }
-              ranges.push(start === end ? `${start}` : `${start}-${end}`);
-              return ranges.join(',');
-            };
-
-            const tableTotals = {
-              statements: { covered: 0, total: 0 },
-              branches: { covered: 0, total: 0 },
-              functions: { covered: 0, total: 0 },
-              lines: { covered: 0, total: 0 },
-            };
-            const tableRows = Object.entries(coverage)
-              .map(([file, entry]) => {
-                const fileCoverage = getFileCoverage(entry);
-                const lineHits = getLineHits(entry, fileCoverage);
-                const statementHits = entry.s ?? {};
-                const branchHits = entry.b ?? {};
-                const functionHits = entry.f ?? {};
-
-                const lineTotal = Object.keys(lineHits).length;
-                const lineCovered = Object.values(lineHits).filter((n) => n > 0).length;
-                const statementTotal = Object.keys(statementHits).length;
-                const statementCovered = Object.values(statementHits).filter((n) => n > 0).length;
-                const branchTotal = Object.values(branchHits).reduce((acc, branches) => acc + branches.length, 0);
-                const branchCovered = Object.values(branchHits).reduce(
-                  (acc, branches) => acc + branches.filter((n) => n > 0).length,
-                  0,
-                );
-                const functionTotal = Object.keys(functionHits).length;
-                const functionCovered = Object.values(functionHits).filter((n) => n > 0).length;
-
-                tableTotals.lines.total += lineTotal;
-                tableTotals.lines.covered += lineCovered;
-                tableTotals.statements.total += statementTotal;
-                tableTotals.statements.covered += statementCovered;
-                tableTotals.branches.total += branchTotal;
-                tableTotals.branches.covered += branchCovered;
-                tableTotals.functions.total += functionTotal;
-                tableTotals.functions.covered += functionCovered;
-
-                const uncoveredLines = getUncoveredLines(entry, fileCoverage, lineHits);
-
-                const filePath = entry.path ?? file;
-                const relativePath = path.isAbsolute(filePath)
-                  ? path.relative(process.cwd(), filePath)
-                  : filePath;
-
-                return {
-                  file: relativePath || file,
-                  statements: pctValue(statementCovered, statementTotal),
-                  branches: pctValue(branchCovered, branchTotal),
-                  functions: pctValue(functionCovered, functionTotal),
-                  lines: pctValue(lineCovered, lineTotal),
-                  uncovered: formatLineRanges(uncoveredLines),
-                };
-              })
-              .sort((a, b) => a.file.localeCompare(b.file));
-
-            const columns = [
-              { key: 'file', header: 'File', align: 'left' },
-              { key: 'statements', header: '% Stmts', align: 'right' },
-              { key: 'branches', header: '% Branch', align: 'right' },
-              { key: 'functions', header: '% Funcs', align: 'right' },
-              { key: 'lines', header: '% Lines', align: 'right' },
-              { key: 'uncovered', header: 'Uncovered Line #s', align: 'left' },
-            ];
-
-            const allFilesRow = {
-              file: 'All files',
-              statements: pctValue(tableTotals.statements.covered, tableTotals.statements.total),
-              branches: pctValue(tableTotals.branches.covered, tableTotals.branches.total),
-              functions: pctValue(tableTotals.functions.covered, tableTotals.functions.total),
-              lines: pctValue(tableTotals.lines.covered, tableTotals.lines.total),
-              uncovered: '',
-            };
-
-            const rowsForOutput = [allFilesRow, ...tableRows];
-            const formatRow = (row) => `| ${columns
-              .map(({ key }) => String(row[key] ?? ''))
-              .join(' | ')} |`;
-            const headerRow = `| ${columns.map(({ header }) => header).join(' | ')} |`;
-            const dividerRow = `| ${columns
-              .map(({ align }) => (align === 'right' ? '---:' : ':---'))
-              .join(' | ')} |`;
-
-            console.log('');
-            console.log('<details><summary>Vitest coverage table</summary>');
-            console.log('');
-            console.log(headerRow);
-            console.log(dividerRow);
-            rowsForOutput.forEach((row) => console.log(formatRow(row)));
-            console.log('</details>');
-          }
-          NODE
-
-      - name: Upload Coverage Artifact
-        if: steps.coverage-summary.outputs.has_coverage == 'true'
-        uses: actions/upload-artifact@v6
+      - name: Upload blob report
+        if: ${{ !cancelled() }}
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
-          name: web-coverage-report
-          path: web/coverage
-          retention-days: 30
-          if-no-files-found: error
+          name: blob-report-${{ matrix.shardIndex }}
+          path: web/.vitest-reports/*
+          include-hidden-files: true
+          retention-days: 1
 
-  web-build:
-    name: Web Build
+  merge-reports:
+    name: Merge Test Reports
+    if: ${{ !cancelled() }}
+    needs: [test]
     runs-on: ubuntu-latest
+    env:
+      CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
     defaults:
       run:
+        shell: bash
         working-directory: ./web
 
     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
+      - name: Setup web environment
+        uses: ./.github/actions/setup-web
+
+      - name: Download blob reports
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
         with:
-          files: |
-            web/**
-            .github/workflows/web-tests.yml
+          path: web/.vitest-reports
+          pattern: blob-report-*
+          merge-multiple: true
 
-      - name: Install pnpm
-        uses: pnpm/action-setup@v4
+      - name: Merge reports
+        run: vp test --merge-reports --coverage --silent=passed-only
+
+      - name: Report coverage
+        if: ${{ env.CODECOV_TOKEN != '' }}
+        uses: codecov/codecov-action@57e3a136b779b570ffcdbf80b3bdc90e7fab3de2 # v6.0.0
         with:
-          package_json_file: web/package.json
-          run_install: false
+          directory: web/coverage
+          flags: web
+        env:
+          CODECOV_TOKEN: ${{ env.CODECOV_TOKEN }}
 
-      - name: Setup NodeJS
-        uses: actions/setup-node@v6
-        if: steps.changed-files.outputs.any_changed == 'true'
+  dify-ui-test:
+    name: dify-ui Tests
+    runs-on: ubuntu-latest
+    env:
+      CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+    defaults:
+      run:
+        shell: bash
+        working-directory: ./packages/dify-ui
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
-          node-version: 24
-          cache: pnpm
-          cache-dependency-path: ./web/pnpm-lock.yaml
+          persist-credentials: false
 
-      - name: Web dependencies
-        if: steps.changed-files.outputs.any_changed == 'true'
-        working-directory: ./web
-        run: pnpm install --frozen-lockfile
+      - name: Setup web environment
+        uses: ./.github/actions/setup-web
 
-      - name: Web build check
-        if: steps.changed-files.outputs.any_changed == 'true'
-        working-directory: ./web
-        run: pnpm run build
+      - name: Install Chromium for Browser Mode
+        run: vp exec playwright install --with-deps chromium
+
+      - name: Run dify-ui tests
+        run: vp test run --coverage --silent=passed-only
+
+      - name: Report coverage
+        if: ${{ env.CODECOV_TOKEN != '' }}
+        uses: codecov/codecov-action@57e3a136b779b570ffcdbf80b3bdc90e7fab3de2 # v6.0.0
+        with:
+          directory: packages/dify-ui/coverage
+          flags: dify-ui
+        env:
+          CODECOV_TOKEN: ${{ env.CODECOV_TOKEN }}

.gitignore

@@ -203,6 +203,7 @@ sdks/python-client/dify_client.egg-info
 
 .vscode/*
 !.vscode/launch.json.template
+!.vscode/settings.example.json
 !.vscode/README.md
 api/.vscode
 # vscode Code History Extension
@@ -212,6 +213,8 @@ api/.vscode
 
 # pnpm
 /.pnpm-store
+node_modules
+.vite-hooks/_
 
 # plugin migrate
 plugins.jsonl
@@ -222,6 +225,7 @@ mise.toml
 
 # AI Assistant
 .roo/
+/.claude/worktrees/
 api/.env.backup
 /clickzetta
 
@@ -236,3 +240,8 @@ scripts/stress-test/reports/
 # settings
 *.local.json
 *.local.md
+
+# Code Agent Folder
+.qoder/*
+
+.eslintcache

.npmrc

@@ -0,0 +1 @@
+save-exact=true

.nvmrc

@@ -0,0 +1 @@
+22

.vite-hooks/pre-commit

@@ -0,0 +1,64 @@
+#!/bin/sh
+# get the list of modified files
+files=$(git diff --cached --name-only)
+
+# check if api or web directory is modified
+
+api_modified=false
+web_modified=false
+skip_web_checks=false
+
+git_path() {
+    git rev-parse --git-path "$1"
+}
+
+if [ -f "$(git_path MERGE_HEAD)" ] || \
+   [ -f "$(git_path CHERRY_PICK_HEAD)" ] || \
+   [ -f "$(git_path REVERT_HEAD)" ] || \
+   [ -f "$(git_path SQUASH_MSG)" ] || \
+   [ -d "$(git_path rebase-merge)" ] || \
+   [ -d "$(git_path rebase-apply)" ]; then
+    skip_web_checks=true
+fi
+
+for file in $files
+do
+    # Use POSIX compliant pattern matching
+    case "$file" in
+        api/*.py)
+            # set api_modified flag to true
+            api_modified=true
+            ;;
+        web/*)
+            # set web_modified flag to true
+            web_modified=true
+            ;;
+    esac
+done
+
+# run linters based on the modified modules
+
+if $api_modified; then
+    echo "Running Ruff linter on api module"
+
+    # run Ruff linter auto-fixing
+    uv run --project api --dev ruff check --fix ./api
+
+    # run Ruff linter checks
+    uv run --project api --dev ruff check  ./api || status=$?
+
+    status=${status:-0}
+
+    if [ $status -ne 0 ]; then
+      echo "Ruff linter on api module error, exit code: $status"
+      echo "Please run 'dev/reformat' to fix the fixable linting errors."
+      exit 1
+    fi
+fi
+
+if $skip_web_checks; then
+    echo "Git operation in progress, skipping web checks"
+    exit 0
+fi
+
+vp staged

.vscode/launch.json.template

@@ -2,21 +2,10 @@
     "version": "0.2.0",
     "configurations": [
         {
-            "name": "Python: Flask API",
+            "name": "Python: API (gevent)",
             "type": "debugpy",
             "request": "launch",
-            "module": "flask",
-            "env": {
-                "FLASK_APP": "app.py",
-                "FLASK_ENV": "development"
-            },
-            "args": [
-                "run",
-                "--host=0.0.0.0",
-                "--port=5001",
-                "--no-debugger",
-                "--no-reload"
-            ],
+            "program": "${workspaceFolder}/api/app.py",
             "jinja": true,
             "justMyCode": true,
             "cwd": "${workspaceFolder}/api",
@@ -37,7 +26,7 @@
                 "-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"
             ],

.vscode/settings.example.json

@@ -1,12 +1,16 @@
 {
-  // Disable the default formatter, use eslint instead
-  "prettier.enable": false,
-  "editor.formatOnSave": false,
+  "cucumber.features": [
+    "e2e/features/**/*.feature",
+  ],
+  "cucumber.glue": [
+    "e2e/features/**/*.ts",
+  ],
+
+  "tailwindCSS.experimental.configFile": "web/app/styles/globals.css",
 
   // Auto fix
   "editor.codeActionsOnSave": {
     "source.fixAll.eslint": "explicit",
-    "source.organizeImports": "never"
   },
 
   // Silent the stylistic rules in your IDE, but still auto fix them

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

@@ -24,8 +24,8 @@ prepare-docker:
 # Step 2: Prepare web environment
 prepare-web:
 	@echo "🌐 Setting up web environment..."
-	@cp -n web/.env.example web/.env 2>/dev/null || echo "Web .env already exists"
-	@cd web && pnpm install
+	@cp -n web/.env.example web/.env.local 2>/dev/null || echo "Web .env.local already exists"
+	@pnpm install
 	@echo "✅ Web environment prepared (not started)"
 
 # Step 3: Prepare API environment
@@ -68,11 +68,17 @@ 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 .
+	@echo "✅ Type checks complete"
+
+type-check-core:
+	@echo "📝 Running core type checks (basedpyright + mypy)..."
 	@./dev/basedpyright-check $(PATH_TO_CHECK)
 	@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"
+	@echo "✅ Core type checks complete"
 
 test:
 	@echo "🧪 Running backend unit tests..."
@@ -87,7 +93,7 @@ test:
 # Build Docker images
 build-web:
 	@echo "Building web Docker image: $(WEB_IMAGE):$(VERSION)..."
-	docker build -t $(WEB_IMAGE):$(VERSION) ./web
+	docker build -f web/Dockerfile -t $(WEB_IMAGE):$(VERSION) .
 	@echo "Web Docker image built successfully: $(WEB_IMAGE):$(VERSION)"
 
 build-api:
@@ -132,7 +138,8 @@ 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 type-check-core - Run core type checks (basedpyright, 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> ·
@@ -57,10 +53,14 @@
   <a href="./docs/tr-TR/README.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
   <a href="./docs/vi-VN/README.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
   <a href="./docs/de-DE/README.md"><img alt="README in Deutsch" src="https://img.shields.io/badge/German-d9d9d9"></a>
+  <a href="./docs/it-IT/README.md"><img alt="README in Italiano" src="https://img.shields.io/badge/Italiano-d9d9d9"></a>
+  <a href="./docs/pt-BR/README.md"><img alt="README em Português do Brasil" src="https://img.shields.io/badge/Portugu%C3%AAs%20do%20Brasil-d9d9d9"></a>
+  <a href="./docs/sl-SI/README.md"><img alt="README Slovenščina" src="https://img.shields.io/badge/Sloven%C5%A1%C4%8Dina-d9d9d9"></a>
   <a href="./docs/bn-BD/README.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
+  <a href="./docs/hi-IN/README.md"><img alt="README in हिन्दी" src="https://img.shields.io/badge/Hindi-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 +137,7 @@ 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
@@ -33,6 +33,9 @@ TRIGGER_URL=http://localhost:5001
 # The time in seconds after the signature is rejected
 FILES_ACCESS_TIMEOUT=300
 
+# Collaboration mode toggle
+ENABLE_COLLABORATION_MODE=false
+
 # Access token expiration time in minutes
 ACCESS_TOKEN_EXPIRE_MINUTES=60
 
@@ -42,6 +45,8 @@ 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
@@ -55,6 +60,9 @@ REDIS_SSL_CERTFILE=
 REDIS_SSL_KEYFILE=
 # Path to client private key file for SSL authentication
 REDIS_DB=0
+# Optional global prefix for Redis keys, topics, streams, and Celery Redis transport artifacts.
+# Leave empty to preserve current unprefixed behavior.
+REDIS_KEY_PREFIX=
 
 # redis Sentinel configuration.
 REDIS_USE_SENTINEL=false
@@ -69,6 +77,13 @@ REDIS_USE_CLUSTERS=false
 REDIS_CLUSTERS=
 REDIS_CLUSTERS_PASSWORD=
 
+REDIS_RETRY_RETRIES=3
+REDIS_RETRY_BACKOFF_BASE=1.0
+REDIS_RETRY_BACKOFF_CAP=10.0
+REDIS_SOCKET_TIMEOUT=5.0
+REDIS_SOCKET_CONNECT_TIMEOUT=5.0
+REDIS_HEALTH_CHECK_INTERVAL=30
+
 # celery configuration
 CELERY_BROKER_URL=redis://:difyai123456@localhost:${REDIS_PORT}/1
 CELERY_BACKEND=redis
@@ -100,6 +115,7 @@ S3_BUCKET_NAME=your-bucket-name
 S3_ACCESS_KEY=your-access-key
 S3_SECRET_KEY=your-secret-key
 S3_REGION=your-region
+S3_ADDRESS_STYLE=auto
 
 # Workflow run and Conversation archive storage (S3-compatible)
 ARCHIVE_STORAGE_ENABLED=false
@@ -125,7 +141,8 @@ ALIYUN_OSS_AUTH_VERSION=v1
 ALIYUN_OSS_REGION=your-region
 # Don't start with '/'. OSS doesn't support leading slash in object names.
 ALIYUN_OSS_PATH=your-path
-ALIYUN_CLOUDBOX_ID=your-cloudbox-id
+# Optional CloudBox ID for Aliyun OSS, DO NOT enable it if you are not using CloudBox.
+#ALIYUN_CLOUDBOX_ID=your-cloudbox-id
 
 # Google Storage configuration
 GOOGLE_STORAGE_BUCKET_NAME=your-bucket-name
@@ -178,7 +195,7 @@ CONSOLE_CORS_ALLOW_ORIGINS=http://localhost:3000,*
 COOKIE_DOMAIN=
 
 # Vector database configuration
-# Supported values are `weaviate`, `oceanbase`, `qdrant`, `milvus`, `myscale`, `relyt`, `pgvector`, `pgvecto-rs`, `chroma`, `opensearch`, `oracle`, `tencent`, `elasticsearch`, `elasticsearch-ja`, `analyticdb`, `couchbase`, `vikingdb`,  `opengauss`, `tablestore`,`vastbase`,`tidb`,`tidb_on_qdrant`,`baidu`,`lindorm`,`huawei_cloud`,`upstash`, `matrixone`.
+# Supported values are `weaviate`, `oceanbase`, `qdrant`, `milvus`, `myscale`, `relyt`, `pgvector`, `pgvecto-rs`, `chroma`, `opensearch`, `oracle`, `tencent`, `elasticsearch`, `elasticsearch-ja`, `analyticdb`, `couchbase`, `vikingdb`,  `opengauss`, `tablestore`,`vastbase`,`tidb`,`tidb_on_qdrant`,`baidu`,`lindorm`,`huawei_cloud`,`upstash`, `matrixone`, `hologres`.
 VECTOR_STORE=weaviate
 # Prefix used to create collection name in vector database
 VECTOR_INDEX_NAME_PREFIX=Vector_index
@@ -186,7 +203,6 @@ 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
 
@@ -216,6 +232,20 @@ COUCHBASE_PASSWORD=password
 COUCHBASE_BUCKET_NAME=Embeddings
 COUCHBASE_SCOPE_NAME=_default
 
+# Hologres configuration
+# access_key_id is used as the PG username, access_key_secret is used as the PG password
+HOLOGRES_HOST=
+HOLOGRES_PORT=80
+HOLOGRES_DATABASE=
+HOLOGRES_ACCESS_KEY_ID=
+HOLOGRES_ACCESS_KEY_SECRET=
+HOLOGRES_SCHEMA=public
+HOLOGRES_TOKENIZER=jieba
+HOLOGRES_DISTANCE_METHOD=Cosine
+HOLOGRES_BASE_QUANTIZATION_TYPE=rabitq
+HOLOGRES_MAX_DEGREE=64
+HOLOGRES_EF_CONSTRUCTION=400
+
 # Milvus configuration
 MILVUS_URI=http://127.0.0.1:19530
 MILVUS_TOKEN=
@@ -338,6 +368,9 @@ BAIDU_VECTOR_DB_SHARD=1
 BAIDU_VECTOR_DB_REPLICAS=3
 BAIDU_VECTOR_DB_INVERTED_INDEX_ANALYZER=DEFAULT_ANALYZER
 BAIDU_VECTOR_DB_INVERTED_INDEX_PARSER_MODE=COARSE_MODE
+BAIDU_VECTOR_DB_AUTO_BUILD_ROW_COUNT_INCREMENT=500
+BAIDU_VECTOR_DB_AUTO_BUILD_ROW_COUNT_INCREMENT_RATIO=0.05
+BAIDU_VECTOR_DB_REBUILD_INDEX_TIMEOUT_IN_SECONDS=300
 
 # Upstash configuration
 UPSTASH_VECTOR_URL=your-server-url
@@ -553,6 +586,8 @@ 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 +750,32 @@ 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 event bus between API and
+# celery worker
+# defaults to url constructed from `REDIS_*`
+# configurations
+EVENT_BUS_REDIS_URL=
+# Event transport type. Options are:
+#
+#  - pubsub: normal Pub/Sub (at-most-once)
+#  - sharded: sharded Pub/Sub (at-most-once)
+#  - streams: Redis Streams (at-least-once, recommended to avoid subscriber races)
+#
+# Note: Before enabling 'streams' in production, estimate your expected event volume and retention needs.
+# Configure Redis memory limits and stream trimming appropriately (e.g., MAXLEN and key expiry) to reduce
+# the risk of data loss from Redis auto-eviction under memory pressure.
+# Also accepts ENV: EVENT_BUS_REDIS_CHANNEL_TYPE.
+EVENT_BUS_REDIS_CHANNEL_TYPE=pubsub
+# Whether to use Redis cluster mode while use redis as event bus.
+#  It's highly recommended to enable this for large deployments.
+EVENT_BUS_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

@@ -1,427 +1,14 @@
 [importlinter]
 root_packages =
     core
+    constants
+    context
     configs
     controllers
     extensions
+    factories
+    libs
     models
     tasks
     services
 include_external_packages = True
-
-[importlinter:contract:workflow]
-name = Workflow
-type=layers
-layers =
-    graph_engine
-    graph_events
-    graph
-    nodes
-    node_events
-    runtime
-    entities
-containers =
-    core.workflow
-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
-
-    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
-
-[importlinter:contract:workflow-infrastructure-dependencies]
-name = Workflow Infrastructure Dependencies
-type = forbidden
-source_modules =
-    core.workflow
-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
-
-[importlinter:contract:workflow-external-imports]
-name = Workflow External Imports
-type = forbidden
-source_modules =
-    core.workflow
-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
-ignore_imports =
-    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
-
-[importlinter:contract:rsc]
-name = RSC
-type = layers
-layers =
-    graph_engine
-    response_coordinator
-containers =
-    core.workflow.graph_engine
-
-[importlinter:contract:worker]
-name = Worker
-type = layers
-layers =
-    graph_engine
-    worker
-containers =
-    core.workflow.graph_engine
-
-[importlinter:contract:graph-engine-architecture]
-name = Graph Engine Architecture
-type = layers
-layers =
-    graph_engine
-    orchestration
-    command_processing
-    event_management
-    error_handler
-    graph_traversal
-    graph_state_manager
-    worker_management
-    domain
-containers =
-    core.workflow.graph_engine
-
-[importlinter:contract:domain-isolation]
-name = Domain Model Isolation
-type = forbidden
-source_modules =
-    core.workflow.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
-
-[importlinter:contract:worker-management]
-name = Worker Management
-type = forbidden
-source_modules =
-    core.workflow.graph_engine.worker_management
-forbidden_modules =
-    core.workflow.graph_engine.orchestration
-    core.workflow.graph_engine.command_processing
-    core.workflow.graph_engine.event_management
-
-
-[importlinter:contract:graph-traversal-components]
-name = Graph Traversal Components
-type = layers
-layers =
-    edge_processor
-    skip_propagator
-containers =
-    core.workflow.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

api/.ruff.toml

@@ -69,8 +69,6 @@ ignore = [
     "FURB152", # math-constant
     "UP007",   # non-pep604-annotation
     "UP032",   # f-string
-    "UP045",   # non-pep604-annotation-optional
-    "B005",    # strip-with-multi-characters
     "B006",    # mutable-argument-default
     "B007",    # unused-loop-control-variable
     "B026",    # star-arg-unpacking-after-keyword-arg
@@ -84,7 +82,6 @@ ignore = [
     "SIM102",  # collapsible-if
     "SIM103",  # needless-bool
     "SIM105",  # suppressible-exception
-    "SIM107",  # return-in-try-except-finally
     "SIM108",  # if-else-block-instead-of-if-exp
     "SIM113",  # enumerate-for-loop
     "SIM117",  # multiple-with-statements
@@ -93,38 +90,22 @@ ignore = [
 ]
 
 [lint.per-file-ignores]
-"__init__.py" = [
-    "F401", # unused-import
-    "F811", # redefined-while-unused
-]
 "configs/*" = [
     "N802", # invalid-function-name
 ]
-"core/model_runtime/callbacks/base_callback.py" = ["T201"]
-"core/workflow/callbacks/workflow_logging_callback.py" = ["T201"]
 "libs/gmpy2_pkcs10aep_cipher.py" = [
     "N803", # invalid-argument-name
 ]
 "tests/*" = [
-    "F811", # redefined-while-unused
     "T201", # allow print in tests,
     "S110", # allow ignoring exceptions in tests code (currently)
-
 ]
-"controllers/console/explore/trial.py" = ["TID251"]
-"controllers/console/human_input_form.py" = ["TID251"]
-"controllers/web/human_input_form.py" = ["TID251"]
-
-[lint.pyflakes]
-allowed-unused-imports = [
-    "tests.integration_tests",
-    "tests.unit_tests",
-]
-
-[lint.flake8-tidy-imports]
 
 [lint.flake8-tidy-imports.banned-api."flask_restx.reqparse"]
 msg = "Use Pydantic payload/query models instead of reqparse."
 
 [lint.flake8-tidy-imports.banned-api."flask_restx.reqparse.RequestParser"]
 msg = "Use Pydantic payload/query models instead of reqparse."
+
+[lint.isort]
+known-first-party = ["graphon"]

api/.vscode/launch.json.example

@@ -3,29 +3,21 @@
     "compounds": [
         {
             "name": "Launch Flask and Celery",
-            "configurations": ["Python: Flask", "Python: Celery"]
+            "configurations": ["Python: API (gevent)", "Python: Celery"]
         }
     ],
     "configurations": [
         {
-            "name": "Python: Flask",
-            "consoleName": "Flask",
+            "name": "Python: API (gevent)",
+            "consoleName": "API",
             "type": "debugpy",
             "request": "launch",
             "python": "${workspaceFolder}/.venv/bin/python",
             "cwd": "${workspaceFolder}",
             "envFile": ".env",
-            "module": "flask",
+            "program": "${workspaceFolder}/app.py",
             "justMyCode": true,
-            "jinja": true,
-            "env": {
-                "FLASK_APP": "app.py",
-                "GEVENT_SUPPORT": "True"
-            },
-            "args": [
-                "run",
-                "--port=5001"
-            ]
+            "jinja": true
         },
         {
             "name": "Python: Celery",
@@ -54,7 +46,7 @@
                 "--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

@@ -62,7 +62,23 @@ 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 classes, declare member variables at the top of the class body (before `__init__`) so the class shape is obvious at a glance:
+- 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 all member variables explicitly with types at the top of the class body (before `__init__`), even when the class is not a dataclass or Pydantic model, so the class shape is obvious at a glance:
 
 ```python
 from datetime import datetime

api/Dockerfile

@@ -21,8 +21,9 @@ RUN apt-get update \
           # for building gmpy2
           libmpfr-dev libmpc-dev
 
-# Install Python dependencies
+# Install Python dependencies (workspace members under providers/vdb/)
 COPY pyproject.toml uv.lock ./
+COPY providers ./providers
 RUN uv sync --locked --no-dev
 
 # production stage
@@ -97,7 +98,7 @@ ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"
 
 # Download nltk data
 RUN mkdir -p /usr/local/share/nltk_data \
-    && NLTK_DATA=/usr/local/share/nltk_data python -c "import nltk; from unstructured.nlp.tokenize import download_nltk_packages; nltk.download('punkt'); nltk.download('averaged_perceptron_tagger'); nltk.download('stopwords'); download_nltk_packages()" \
+    && NLTK_DATA=/usr/local/share/nltk_data python -c "import nltk; nltk.download('punkt'); nltk.download('averaged_perceptron_tagger'); nltk.download('stopwords')" \
     && chmod -R 755 /usr/local/share/nltk_data
 
 ENV TIKTOKEN_CACHE_DIR=/app/api/.tiktoken_cache

api/README.md

@@ -40,9 +40,11 @@ The scripts resolve paths relative to their location, so you can run them from a
    ./dev/start-web
    ```
 
+   `./dev/setup` and `./dev/start-web` install JavaScript dependencies through the repository root workspace, so you do not need a separate `cd web && pnpm install` step.
+
 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 +56,6 @@ 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/app.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import logging
 import sys
 from typing import TYPE_CHECKING, cast
 
@@ -9,17 +10,35 @@ if TYPE_CHECKING:
     celery: Celery
 
 
+HOST = "0.0.0.0"
+PORT = 5001
+logger = logging.getLogger(__name__)
+
+
 def is_db_command() -> bool:
     if len(sys.argv) > 1 and sys.argv[0].endswith("flask") and sys.argv[1] == "db":
         return True
     return False
 
 
+def log_startup_banner(host: str, port: int) -> None:
+    debugger_attached = sys.gettrace() is not None
+    logger.info("Serving Dify API via gevent WebSocket server")
+    logger.info("Bound to http://%s:%s", host, port)
+    logger.info("Debugger attached: %s", "on" if debugger_attached else "off")
+    logger.info("Press CTRL+C to quit")
+
+
 # create app
+flask_app = None
+socketio_app = None
+
 if is_db_command():
     from app_factory import create_migrations_app
 
     app = create_migrations_app()
+    socketio_app = app
+    flask_app = app
 else:
     # Gunicorn and Celery handle monkey patching automatically in production by
     # specifying the `gevent` worker class. Manual monkey patching is not required here.
@@ -30,8 +49,14 @@ else:
 
     from app_factory import create_app
 
-    app = create_app()
+    socketio_app, flask_app = create_app()
+    app = flask_app
     celery = cast("Celery", app.extensions["celery"])
 
 if __name__ == "__main__":
-    app.run(host="0.0.0.0", port=5001)
+    from gevent import pywsgi
+    from geventwebsocket.handler import WebSocketHandler  # type: ignore[reportMissingTypeStubs]
+
+    log_startup_banner(HOST, PORT)
+    server = pywsgi.WSGIServer((HOST, PORT), socketio_app, handler_class=WebSocketHandler)
+    server.serve_forever()

api/app_factory.py

@@ -1,16 +1,47 @@
 import logging
 import time
 
+import socketio  # type: ignore[reportMissingTypeStubs]
+from flask import request
 from opentelemetry.trace import get_current_span
 from opentelemetry.trace.span import INVALID_SPAN_ID, INVALID_TRACE_ID
 
 from configs import dify_config
 from contexts.wrapper import RecyclableContextVar
+from controllers.console.error import UnauthorizedAndForceLogout
 from core.logging.context import init_request_context
 from dify_app import DifyApp
+from extensions.ext_socketio import sio
+from services.enterprise.enterprise_service import EnterpriseService
+from services.feature_service import LicenseStatus
 
 logger = logging.getLogger(__name__)
 
+# Console bootstrap APIs exempt from license check.
+# Defined at module level to avoid per-request tuple construction.
+# - system-features: license status for expiry UI (GlobalPublicStoreProvider)
+# - setup: install/setup status check (AppInitializer)
+# - init: init password validation for fresh install (InitPasswordPopup)
+# - login: auto-login after setup completion (InstallForm)
+# - features: billing/plan features (ProviderContextProvider)
+# - account/profile: login check + user profile (AppContextProvider, useIsLogin)
+# - workspaces/current: workspace + model providers (AppContextProvider)
+# - version: version check (AppContextProvider)
+# - activate/check: invitation link validation (signin page)
+# Without these exemptions, the signin page triggers location.reload()
+# on unauthorized_and_force_logout, causing an infinite loop.
+_CONSOLE_EXEMPT_PREFIXES = (
+    "/console/api/system-features",
+    "/console/api/setup",
+    "/console/api/init",
+    "/console/api/login",
+    "/console/api/features",
+    "/console/api/account/profile",
+    "/console/api/workspaces/current",
+    "/console/api/version",
+    "/console/api/activate/check",
+)
+
 
 # ----------------------------
 # Application Factory Function
@@ -31,6 +62,39 @@ def create_flask_app_with_configs() -> DifyApp:
         init_request_context()
         RecyclableContextVar.increment_thread_recycles()
 
+        # Enterprise license validation for API endpoints (both console and webapp)
+        # When license expires, block all API access except bootstrap endpoints needed
+        # for the frontend to load the license expiration page without infinite reloads.
+        if dify_config.ENTERPRISE_ENABLED:
+            is_console_api = request.path.startswith("/console/api/")
+            is_webapp_api = request.path.startswith("/api/")
+
+            if is_console_api or is_webapp_api:
+                if is_console_api:
+                    is_exempt = any(request.path.startswith(p) for p in _CONSOLE_EXEMPT_PREFIXES)
+                else:  # webapp API
+                    is_exempt = request.path.startswith("/api/system-features")
+
+                if not is_exempt:
+                    try:
+                        # Check license status (cached — see EnterpriseService for TTL details)
+                        license_status = EnterpriseService.get_cached_license_status()
+                        if license_status in (LicenseStatus.INACTIVE, LicenseStatus.EXPIRED, LicenseStatus.LOST):
+                            raise UnauthorizedAndForceLogout(
+                                f"Enterprise license is {license_status}. Please contact your administrator."
+                            )
+                        if license_status is None:
+                            raise UnauthorizedAndForceLogout(
+                                "Unable to verify enterprise license. Please contact your administrator."
+                            )
+                    except UnauthorizedAndForceLogout:
+                        raise
+                    except Exception:
+                        logger.exception("Failed to check enterprise license status")
+                        raise UnauthorizedAndForceLogout(
+                            "Unable to verify enterprise license. Please contact your administrator."
+                        )
+
     # add after request hook for injecting trace headers from OpenTelemetry span context
     # Only adds headers when OTEL is enabled and has valid context
     @dify_app.after_request
@@ -60,14 +124,18 @@ def create_flask_app_with_configs() -> DifyApp:
     return dify_app
 
 
-def create_app() -> DifyApp:
+def create_app() -> tuple[socketio.WSGIApp, DifyApp]:
     start_time = time.perf_counter()
     app = create_flask_app_with_configs()
     initialize_extensions(app)
+
+    sio.app = app
+    socketio_app = socketio.WSGIApp(sio, app)
+
     end_time = time.perf_counter()
     if dify_config.DEBUG:
         logger.info("Finished create_app (%s ms)", round((end_time - start_time) * 1000, 2))
-    return app
+    return socketio_app, app
 
 
 def initialize_extensions(app: DifyApp):
@@ -81,6 +149,7 @@ def initialize_extensions(app: DifyApp):
         ext_commands,
         ext_compress,
         ext_database,
+        ext_enterprise_telemetry,
         ext_fastopenapi,
         ext_forward_refs,
         ext_hosting_provider,
@@ -90,6 +159,7 @@ def initialize_extensions(app: DifyApp):
         ext_logstore,
         ext_mail,
         ext_migrate,
+        ext_oauth_bearer,
         ext_orjson,
         ext_otel,
         ext_proxy_fix,
@@ -131,8 +201,10 @@ def initialize_extensions(app: DifyApp):
         ext_commands,
         ext_fastopenapi,
         ext_otel,
+        ext_enterprise_telemetry,
         ext_request_logging,
         ext_session_factory,
+        ext_oauth_bearer,
     ]
     for ext in extensions:
         short_name = ext.__name__.split(".")[-1]

api/celery_healthcheck.py

@@ -0,0 +1,18 @@
+# This module provides a lightweight Celery instance for use in Docker health checks.
+# Unlike celery_entrypoint.py, this does NOT import app.py and therefore avoids
+# initializing all Flask extensions (DB, Redis, storage, blueprints, etc.).
+# Using this module keeps the health check fast and low-cost.
+from celery import Celery
+
+from configs import dify_config
+from extensions.ext_celery import get_celery_broker_transport_options, get_celery_ssl_options
+
+celery = Celery(broker=dify_config.CELERY_BROKER_URL)
+
+broker_transport_options = get_celery_broker_transport_options()
+if broker_transport_options:
+    celery.conf.update(broker_transport_options=broker_transport_options)
+
+ssl_options = get_celery_ssl_options()
+if ssl_options:
+    celery.conf.update(broker_use_ssl=ssl_options)

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 +1,134 @@
+import base64
+import secrets
+
+import click
+from sqlalchemy.orm import Session
+
+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()
+
+    account = AccountService.get_account_by_email_with_case_fallback(email.strip())
+
+    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()
+    with Session(db.engine) as session:
+        account = session.merge(account)
+        account.password = base64_password_hashed
+        account.password_salt = base64_salt
+        session.commit()
+    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()
+
+    account = AccountService.get_account_by_email_with_case_fallback(email.strip())
+
+    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
+
+    with Session(db.engine) as session:
+        account = session.merge(account)
+        account.email = normalized_new_email
+        session.commit()
+    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 +1,478 @@
+import json
+import logging
+from typing import Any, cast
+
+import click
+from pydantic import TypeAdapter
+from sqlalchemy import delete, select
+from sqlalchemy.engine import CursorResult
+
+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 = cast(
+        CursorResult,
+        db.session.execute(
+            delete(ToolOAuthSystemClient).where(
+                ToolOAuthSystemClient.provider == provider_name,
+                ToolOAuthSystemClient.plugin_id == plugin_id,
+            )
+        ),
+    ).rowcount
+    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 = cast(
+        CursorResult,
+        db.session.execute(
+            delete(TriggerOAuthSystemClient).where(
+                TriggerOAuthSystemClient.provider == provider_name,
+                TriggerOAuthSystemClient.plugin_id == plugin_id,
+            )
+        ),
+    ).rowcount
+    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 = cast(
+        CursorResult,
+        db.session.execute(
+            delete(DatasourceOauthParamConfig).where(
+                DatasourceOauthParamConfig.provider == provider_name,
+                DatasourceOauthParamConfig.plugin_id == plugin_id,
+            )
+        ),
+    ).rowcount
+    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.scalars(
+            select(DataSourceOauthBinding).where(DataSourceOauthBinding.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.scalar(select(Tenant).where(Tenant.id == tenant_id))
+                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.scalars(
+            select(DataSourceApiKeyAuthBinding).where(DataSourceApiKeyAuthBinding.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.scalar(select(Tenant).where(Tenant.id == tenant_id))
+                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.scalars(
+            select(DataSourceApiKeyAuthBinding).where(DataSourceApiKeyAuthBinding.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.scalar(select(Tenant).where(Tenant.id == tenant_id))
+                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 +1,869 @@
+import datetime
+import logging
+import time
+from typing import TypedDict
+
+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.
+    """
+    from extensions.otel.runtime import flush_telemetry
+
+    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
+
+    if from_days_ago is not None and to_days_ago is not None:
+        task_label = f"{from_days_ago}to{to_days_ago}"
+    elif start_from is None:
+        task_label = f"before-{before_days}"
+    else:
+        task_label = "custom"
+
+    start_time = datetime.datetime.now(datetime.UTC)
+    click.echo(click.style(f"Starting workflow run cleanup at {start_time.isoformat()}.", fg="white"))
+
+    try:
+        WorkflowRunCleanup(
+            days=before_days,
+            batch_size=batch_size,
+            start_from=start_from,
+            end_before=end_before,
+            dry_run=dry_run,
+            task_label=task_label,
+        ).run()
+    finally:
+        flush_telemetry()
+
+    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]
+
+
+class _AppOrphanCounts(TypedDict):
+    variables: int
+    files: int
+
+
+class OrphanedDraftVariableStatsDict(TypedDict):
+    total_orphaned_variables: int
+    total_orphaned_files: int
+    orphaned_app_count: int
+    orphaned_by_app: dict[str, _AppOrphanCounts]
+
+
+def _count_orphaned_draft_variables() -> OrphanedDraftVariableStatsDict:
+    """
+    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: dict[str, _AppOrphanCounts] = {}
+        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.
+    """
+    from extensions.otel.runtime import flush_telemetry
+
+    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)
+
+        if from_days_ago is not None and before_days is not None:
+            task_label = f"{from_days_ago}to{before_days}"
+        elif start_from is None and before_days is not None:
+            task_label = f"before-{before_days}"
+        else:
+            task_label = "custom"
+
+        # 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,
+                task_label=task_label,
+            )
+        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,
+                task_label=task_label,
+            )
+        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,
+                task_label=task_label,
+            )
+        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
+    finally:
+        flush_telemetry()
+
+    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 +1,761 @@
+import json
+from typing import cast
+
+import click
+import sqlalchemy as sa
+from sqlalchemy import update
+from sqlalchemy.engine import CursorResult
+
+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 = cast(
+                    CursorResult,
+                    db.session.execute(
+                        update(UploadFile)
+                        .where(
+                            UploadFile.storage_type == source_storage_type,
+                            UploadFile.key.in_(copied_upload_file_keys),
+                        )
+                        .values(storage_type=dify_config.STORAGE_TYPE)
+                    ),
+                ).rowcount
+                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 +1,205 @@
+import logging
+
+import click
+import sqlalchemy as sa
+from sqlalchemy import delete, select, update
+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.scalars(select(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.execute(delete(Provider).where(Provider.provider_type == "custom", Provider.tenant_id == tenant.id))
+            session.execute(delete(ProviderModel).where(ProviderModel.tenant_id == tenant.id))
+
+            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.scalar(select(App).where(App.id == app_id))
+                    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.execute(
+                    update(Conversation).where(Conversation.app_id == app.id).values(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.scalar(select(App).where(App.id == app_id))
+                    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 +1,469 @@
+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.index_processor.constant.index_type import IndexStructureType, IndexTechniqueType
+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.enums import DatasetMetadataType, IndexingStatus, SegmentStatus
+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.scalars(
+                    select(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.scalar(
+                        select(AppAnnotationSetting).where(AppAnnotationSetting.app_id == app.id).limit(1)
+                    )
+
+                    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.scalar(
+                        select(DatasetCollectionBinding).where(
+                            DatasetCollectionBinding.id == app_annotation_setting.collection_binding_id
+                        )
+                    )
+                    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=IndexTechniqueType.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.HOLOGRES,
+        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 == IndexTechniqueType.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.execute(
+                            select(DatasetCollectionBinding).where(
+                                DatasetCollectionBinding.id == dataset.collection_binding_id
+                            )
+                        ).scalar_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 == IndexingStatus.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 == SegmentStatus.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 == IndexStructureType.PARENT_CHILD_INDEX:
+                            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.scalars(select(DatasetCollectionBinding)).all()
+        if not bindings:
+            click.echo(click.style("No dataset collection bindings found.", fg="red"))
+            return
+        import qdrant_client
+        from dify_vdb_qdrant.qdrant_vector import PathQdrantParams, QdrantConfig
+        from qdrant_client.http.exceptions import UnexpectedResponse
+        from qdrant_client.http.models import PayloadSchemaType
+
+        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.scalar(
+                            select(DatasetMetadata)
+                            .where(DatasetMetadata.dataset_id == document.dataset_id, DatasetMetadata.name == key)
+                            .limit(1)
+                        )
+                        if not dataset_metadata:
+                            dataset_metadata = DatasetMetadata(
+                                tenant_id=document.tenant_id,
+                                dataset_id=document.dataset_id,
+                                name=key,
+                                type=DatasetMetadataType.STRING,
+                                created_by=document.created_by,
+                            )
+                            db.session.add(dataset_metadata)
+                            db.session.flush()
+                            dataset_metadata_binding: DatasetMetadataBinding | None = 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.scalar(
+                                select(DatasetMetadataBinding)
+                                .where(
+                                    DatasetMetadataBinding.dataset_id == document.dataset_id,
+                                    DatasetMetadataBinding.document_id == document.id,
+                                    DatasetMetadataBinding.metadata_id == dataset_metadata.id,
+                                )
+                                .limit(1)
+                            )
+                            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/app_config.py

@@ -8,7 +8,7 @@ from pydantic_settings import BaseSettings, PydanticBaseSettingsSource, Settings
 from libs.file_utils import search_file_upwards
 
 from .deploy import DeploymentConfig
-from .enterprise import EnterpriseFeatureConfig
+from .enterprise import EnterpriseFeatureConfig, EnterpriseTelemetryConfig
 from .extra import ExtraServiceConfig
 from .feature import FeatureConfig
 from .middleware import MiddlewareConfig
@@ -73,6 +73,8 @@ class DifyConfig(
     # Enterprise feature configs
     # **Before using, please contact business@dify.ai by email to inquire about licensing matters.**
     EnterpriseFeatureConfig,
+    # Enterprise telemetry configs
+    EnterpriseTelemetryConfig,
 ):
     model_config = SettingsConfigDict(
         # read from dotenv format config file

api/configs/enterprise/__init__.py

@@ -18,3 +18,56 @@ 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
+    )
+
+
+class EnterpriseTelemetryConfig(BaseSettings):
+    """
+    Configuration for enterprise telemetry.
+    """
+
+    ENTERPRISE_TELEMETRY_ENABLED: bool = Field(
+        description="Enable enterprise telemetry collection (also requires ENTERPRISE_ENABLED=true).",
+        default=False,
+    )
+
+    ENTERPRISE_OTLP_ENDPOINT: str = Field(
+        description="Enterprise OTEL collector endpoint.",
+        default="",
+    )
+
+    ENTERPRISE_OTLP_HEADERS: str = Field(
+        description="Auth headers for OTLP export (key=value,key2=value2).",
+        default="",
+    )
+
+    ENTERPRISE_OTLP_PROTOCOL: str = Field(
+        description="OTLP protocol: 'http' or 'grpc' (default: http).",
+        default="http",
+    )
+
+    ENTERPRISE_OTLP_API_KEY: str = Field(
+        description="Bearer token for enterprise OTLP export authentication.",
+        default="",
+    )
+
+    ENTERPRISE_INCLUDE_CONTENT: bool = Field(
+        description="Include input/output content in traces (privacy toggle).",
+        # Setting the default value to False to avoid accidentally log PII data in traces.
+        default=False,
+    )
+
+    ENTERPRISE_SERVICE_NAME: str = Field(
+        description="Service name for OTEL resource.",
+        default="dify",
+    )
+
+    ENTERPRISE_OTEL_SAMPLING_RATE: float = Field(
+        description="Sampling rate for enterprise traces (0.0 to 1.0, default 1.0 = 100%).",
+        default=1.0,
+        ge=0.0,
+        le=1.0,
+    )

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):
     """
@@ -477,6 +499,35 @@ class HttpConfig(BaseSettings):
     def WEB_API_CORS_ALLOW_ORIGINS(self) -> list[str]:
         return self.inner_WEB_API_CORS_ALLOW_ORIGINS.split(",")
 
+    inner_OPENAPI_CORS_ALLOW_ORIGINS: str = Field(
+        description=(
+            "Comma-separated allowlist for /openapi/v1/* CORS. "
+            "Default empty = same-origin only. Browser-cookie routes within "
+            "the group reject cross-origin OPTIONS regardless of this list."
+        ),
+        validation_alias=AliasChoices("OPENAPI_CORS_ALLOW_ORIGINS"),
+        default="",
+    )
+
+    @computed_field
+    def OPENAPI_CORS_ALLOW_ORIGINS(self) -> list[str]:
+        return [o for o in self.inner_OPENAPI_CORS_ALLOW_ORIGINS.split(",") if o]
+
+    inner_OPENAPI_KNOWN_CLIENT_IDS: str = Field(
+        description=(
+            "Comma-separated client_id values accepted at "
+            "POST /openapi/v1/oauth/device/code. New CLIs / SDKs added here "
+            "without code changes. Unknown client_id returns 400 unsupported_client."
+        ),
+        validation_alias=AliasChoices("OPENAPI_KNOWN_CLIENT_IDS"),
+        default="difyctl",
+    )
+
+    @computed_field  # type: ignore[misc]
+    @property
+    def OPENAPI_KNOWN_CLIENT_IDS(self) -> frozenset[str]:
+        return frozenset(c for c in self.inner_OPENAPI_KNOWN_CLIENT_IDS.split(",") if c)
+
     HTTP_REQUEST_MAX_CONNECT_TIMEOUT: int = Field(
         ge=1, description="Maximum connection timeout in seconds for HTTP requests", default=10
     )
@@ -852,6 +903,17 @@ class AuthConfig(BaseSettings):
         default=86400,
     )
 
+    ENABLE_OAUTH_BEARER: bool = Field(
+        description="Enable OAuth bearer authentication (device-flow + Service API /v1/* bearer middleware).",
+        default=True,
+    )
+
+    OPENAPI_RATE_LIMIT_PER_TOKEN: PositiveInt = Field(
+        description="Per-token rate limit on /openapi/v1/* (requests per minute). "
+        "Bucket keyed on sha256(token), shared across api replicas via Redis.",
+        default=60,
+    )
+
 
 class ModerationConfig(BaseSettings):
     """
@@ -1126,6 +1188,14 @@ class CeleryScheduleTasksConfig(BaseSettings):
         description="Enable scheduled workflow run cleanup task",
         default=False,
     )
+    ENABLE_CLEAN_OAUTH_ACCESS_TOKENS_TASK: bool = Field(
+        description="Enable scheduled cleanup of revoked/expired OAuth access-token rows past retention.",
+        default=True,
+    )
+    OAUTH_ACCESS_TOKEN_RETENTION_DAYS: PositiveInt = Field(
+        description="Days to retain revoked OAuth access-token rows before deletion.",
+        default=30,
+    )
     ENABLE_MAIL_CLEAN_DOCUMENT_NOTIFY_TASK: bool = Field(
         description="Enable mail clean document notify task",
         default=False,
@@ -1134,6 +1204,14 @@ 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 +1233,16 @@ 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",
@@ -1234,6 +1322,13 @@ class PositionConfig(BaseSettings):
         return {item.strip() for item in self.POSITION_TOOL_EXCLUDES.split(",") if item.strip() != ""}
 
 
+class CollaborationConfig(BaseSettings):
+    ENABLE_COLLABORATION_MODE: bool = Field(
+        description="Whether to enable collaboration mode features across the workspace",
+        default=False,
+    )
+
+
 class LoginConfig(BaseSettings):
     ENABLE_EMAIL_CODE_LOGIN: bool = Field(
         description="whether to enable email code login",
@@ -1279,6 +1374,9 @@ 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 +1407,10 @@ 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,
@@ -1352,6 +1454,7 @@ class FeatureConfig(
     WorkflowConfig,
     WorkflowNodeExecutionConfig,
     WorkspaceConfig,
+    CollaborationConfig,
     LoginConfig,
     AccountConfig,
     SwaggerUIConfig,

api/configs/middleware/__init__.py

@@ -1,11 +1,12 @@
 import os
-from typing import Any, Literal
+from typing import Any, Literal, TypedDict
 from urllib.parse import parse_qsl, quote_plus
 
 from pydantic import Field, NonNegativeFloat, NonNegativeInt, PositiveFloat, PositiveInt, computed_field
 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
@@ -25,6 +26,7 @@ from .vdb.chroma_config import ChromaConfig
 from .vdb.clickzetta_config import ClickzettaConfig
 from .vdb.couchbase_config import CouchbaseConfig
 from .vdb.elasticsearch_config import ElasticsearchConfig
+from .vdb.hologres_config import HologresConfig
 from .vdb.huawei_cloud_config import HuaweiCloudConfig
 from .vdb.iris_config import IrisVectorConfig
 from .vdb.lindorm_config import LindormConfig
@@ -105,6 +107,17 @@ class KeywordStoreConfig(BaseSettings):
     )
 
 
+class SQLAlchemyEngineOptionsDict(TypedDict):
+    pool_size: int
+    max_overflow: int
+    pool_recycle: int
+    pool_pre_ping: bool
+    connect_args: dict[str, str]
+    pool_use_lifo: bool
+    pool_reset_on_return: None
+    pool_timeout: int
+
+
 class DatabaseConfig(BaseSettings):
     # Database type selector
     DB_TYPE: Literal["postgresql", "mysql", "oceanbase", "seekdb"] = Field(
@@ -147,6 +160,16 @@ class DatabaseConfig(BaseSettings):
         default="",
     )
 
+    DB_SESSION_TIMEZONE_OVERRIDE: str = Field(
+        description=(
+            "PostgreSQL session timezone override injected via startup options."
+            " Default is 'UTC' for out-of-the-box consistency."
+            " Set to empty string to disable app-level timezone injection, for example when using RDS Proxy"
+            " together with a database-side default timezone."
+        ),
+        default="UTC",
+    )
+
     @computed_field  # type: ignore[prop-decorator]
     @property
     def SQLALCHEMY_DATABASE_URI_SCHEME(self) -> str:
@@ -207,21 +230,22 @@ class DatabaseConfig(BaseSettings):
 
     @computed_field  # type: ignore[prop-decorator]
     @property
-    def SQLALCHEMY_ENGINE_OPTIONS(self) -> dict[str, Any]:
+    def SQLALCHEMY_ENGINE_OPTIONS(self) -> SQLAlchemyEngineOptionsDict:
         # Parse DB_EXTRAS for 'options'
         db_extras_dict = dict(parse_qsl(self.DB_EXTRAS))
         options = db_extras_dict.get("options", "")
-        connect_args = {}
+        connect_args: dict[str, str] = {}
         # Use the dynamic SQLALCHEMY_DATABASE_URI_SCHEME property
         if self.SQLALCHEMY_DATABASE_URI_SCHEME.startswith("postgresql"):
-            timezone_opt = "-c timezone=UTC"
-            if options:
-                merged_options = f"{options} {timezone_opt}"
-            else:
-                merged_options = timezone_opt
-            connect_args = {"options": merged_options}
+            merged_options = options.strip()
+            session_timezone_override = self.DB_SESSION_TIMEZONE_OVERRIDE.strip()
+            if session_timezone_override:
+                timezone_opt = f"-c timezone={session_timezone_override}"
+                merged_options = f"{merged_options} {timezone_opt}".strip() if merged_options else timezone_opt
+            if merged_options:
+                connect_args = {"options": merged_options}
 
-        return {
+        result: SQLAlchemyEngineOptionsDict = {
             "pool_size": self.SQLALCHEMY_POOL_SIZE,
             "max_overflow": self.SQLALCHEMY_MAX_OVERFLOW,
             "pool_recycle": self.SQLALCHEMY_POOL_RECYCLE,
@@ -231,6 +255,7 @@ class DatabaseConfig(BaseSettings):
             "pool_reset_on_return": None,
             "pool_timeout": self.SQLALCHEMY_POOL_TIMEOUT,
         }
+        return result
 
 
 class CeleryConfig(DatabaseConfig):
@@ -258,11 +283,20 @@ 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 +351,7 @@ class MiddlewareConfig(
     CeleryConfig,  # Note: CeleryConfig already inherits from DatabaseConfig
     KeywordStoreConfig,
     RedisConfig,
+    RedisPubSubConfig,
     # configs of storage and storage providers
     StorageConfig,
     AliyunOSSStorageConfig,
@@ -336,6 +371,7 @@ class MiddlewareConfig(
     AnalyticdbConfig,
     ChromaConfig,
     ClickzettaConfig,
+    HologresConfig,
     HuaweiCloudConfig,
     IrisVectorConfig,
     MilvusConfig,

api/configs/middleware/cache/redis_config.py

@@ -1,4 +1,4 @@
-from pydantic import Field, NonNegativeInt, PositiveFloat, PositiveInt
+from pydantic import Field, NonNegativeInt, PositiveFloat, PositiveInt, field_validator
 from pydantic_settings import BaseSettings
 
 
@@ -32,6 +32,11 @@ class RedisConfig(BaseSettings):
         default=0,
     )
 
+    REDIS_KEY_PREFIX: str = Field(
+        description="Optional global prefix for Redis keys, topics, and transport artifacts",
+        default="",
+    )
+
     REDIS_USE_SSL: bool = Field(
         description="Enable SSL/TLS for the Redis connection",
         default=False,
@@ -111,3 +116,49 @@ 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,
+    )
+
+    REDIS_RETRY_RETRIES: NonNegativeInt = Field(
+        description="Maximum number of retries per Redis command on "
+        "transient failures (ConnectionError, TimeoutError, socket.timeout)",
+        default=3,
+    )
+
+    REDIS_RETRY_BACKOFF_BASE: PositiveFloat = Field(
+        description="Base delay in seconds for exponential backoff between retries",
+        default=1.0,
+    )
+
+    REDIS_RETRY_BACKOFF_CAP: PositiveFloat = Field(
+        description="Maximum backoff delay in seconds between retries",
+        default=10.0,
+    )
+
+    REDIS_SOCKET_TIMEOUT: PositiveFloat | None = Field(
+        description="Socket timeout in seconds for Redis read/write operations",
+        default=5.0,
+    )
+
+    REDIS_SOCKET_CONNECT_TIMEOUT: PositiveFloat | None = Field(
+        description="Socket timeout in seconds for Redis connection establishment",
+        default=5.0,
+    )
+
+    REDIS_HEALTH_CHECK_INTERVAL: NonNegativeInt = Field(
+        description="Interval in seconds between Redis connection health checks (0 to disable)",
+        default=30,
+    )
+
+    @field_validator("REDIS_MAX_CONNECTIONS", mode="before")
+    @classmethod
+    def _empty_string_to_none_for_max_conns(cls, v):
+        """Allow empty string in env/.env to mean 'unset' (None)."""
+        if v is None:
+            return None
+        if isinstance(v, str) and v.strip() == "":
+            return None
+        return v

api/configs/middleware/cache/redis_pubsub_config.py

@@ -0,0 +1,106 @@
+from typing import Literal, Protocol, cast
+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
+
+
+def _redis_defaults(config: object) -> RedisConfigDefaults:
+    return cast(RedisConfigDefaults, config)
+
+
+class RedisPubSubConfig(BaseSettings):
+    """
+    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_USE_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_USE_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 = _redis_defaults(self)
+        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}@"
+
+        db = defaults.REDIS_DB
+
+        netloc = f"{userinfo}{defaults.REDIS_HOST}:{defaults.REDIS_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/baidu_vector_config.py

@@ -51,3 +51,18 @@ class BaiduVectorDBConfig(BaseSettings):
         description="Parser mode for inverted index in Baidu Vector Database (default is COARSE_MODE)",
         default="COARSE_MODE",
     )
+
+    BAIDU_VECTOR_DB_AUTO_BUILD_ROW_COUNT_INCREMENT: int = Field(
+        description="Auto build row count increment threshold (default is 500)",
+        default=500,
+    )
+
+    BAIDU_VECTOR_DB_AUTO_BUILD_ROW_COUNT_INCREMENT_RATIO: float = Field(
+        description="Auto build row count increment ratio threshold (default is 0.05)",
+        default=0.05,
+    )
+
+    BAIDU_VECTOR_DB_REBUILD_INDEX_TIMEOUT_IN_SECONDS: int = Field(
+        description="Timeout in seconds for rebuilding the index in Baidu Vector Database (default is 3600 seconds)",
+        default=300,
+    )

api/configs/middleware/vdb/hologres_config.py

@@ -0,0 +1,67 @@
+from pydantic import Field
+from pydantic_settings import BaseSettings
+
+
+class HologresConfig(BaseSettings):
+    """
+    Configuration settings for Hologres vector database.
+
+    Hologres is compatible with PostgreSQL protocol.
+    access_key_id is used as the PostgreSQL username,
+    and access_key_secret is used as the PostgreSQL password.
+    """
+
+    HOLOGRES_HOST: str | None = Field(
+        description="Hostname or IP address of the Hologres instance.",
+        default=None,
+    )
+
+    HOLOGRES_PORT: int = Field(
+        description="Port number for connecting to the Hologres instance.",
+        default=80,
+    )
+
+    HOLOGRES_DATABASE: str | None = Field(
+        description="Name of the Hologres database to connect to.",
+        default=None,
+    )
+
+    HOLOGRES_ACCESS_KEY_ID: str | None = Field(
+        description="Alibaba Cloud AccessKey ID, also used as the PostgreSQL username.",
+        default=None,
+    )
+
+    HOLOGRES_ACCESS_KEY_SECRET: str | None = Field(
+        description="Alibaba Cloud AccessKey Secret, also used as the PostgreSQL password.",
+        default=None,
+    )
+
+    HOLOGRES_SCHEMA: str = Field(
+        description="Schema name in the Hologres database.",
+        default="public",
+    )
+
+    HOLOGRES_TOKENIZER: str = Field(
+        description="Tokenizer for full-text search index (e.g., 'jieba', 'ik', 'standard', 'simple').",
+        default="jieba",
+    )
+
+    HOLOGRES_DISTANCE_METHOD: str = Field(
+        description="Distance method for vector index (e.g., 'Cosine', 'Euclidean', 'InnerProduct').",
+        default="Cosine",
+    )
+
+    HOLOGRES_BASE_QUANTIZATION_TYPE: str = Field(
+        description="Base quantization type for vector index (e.g., 'rabitq', 'sq8', 'fp16', 'fp32').",
+        default="rabitq",
+    )
+
+    HOLOGRES_MAX_DEGREE: int = Field(
+        description="Max degree (M) parameter for HNSW vector index.",
+        default=64,
+    )
+
+    HOLOGRES_EF_CONSTRUCTION: int = Field(
+        description="ef_construction parameter for HNSW vector index.",
+        default=400,
+    )

api/configs/middleware/vdb/iris_config.py

@@ -1,5 +1,7 @@
 """Configuration for InterSystems IRIS vector database."""
 
+from typing import Any
+
 from pydantic import Field, PositiveInt, model_validator
 from pydantic_settings import BaseSettings
 
@@ -64,7 +66,7 @@ class IrisVectorConfig(BaseSettings):
 
     @model_validator(mode="before")
     @classmethod
-    def validate_config(cls, values: dict) -> dict:
+    def validate_config(cls, values: dict[str, Any]) -> dict[str, Any]:
         """Validate IRIS configuration values.
 
         Args:

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/__init__.py

@@ -7,15 +7,16 @@ UUID_NIL = "00000000-0000-0000-0000-000000000000"
 
 DEFAULT_FILE_NUMBER_LIMITS = 3
 
-IMAGE_EXTENSIONS = convert_to_lower_and_upper_set({"jpg", "jpeg", "png", "webp", "gif", "svg"})
+_IMAGE_EXTENSION_BASE: frozenset[str] = frozenset(("jpg", "jpeg", "png", "webp", "gif", "svg"))
+_VIDEO_EXTENSION_BASE: frozenset[str] = frozenset(("mp4", "mov", "mpeg", "webm"))
+_AUDIO_EXTENSION_BASE: frozenset[str] = frozenset(("mp3", "m4a", "wav", "amr", "mpga"))
 
-VIDEO_EXTENSIONS = convert_to_lower_and_upper_set({"mp4", "mov", "mpeg", "webm"})
+IMAGE_EXTENSIONS: frozenset[str] = frozenset(convert_to_lower_and_upper_set(_IMAGE_EXTENSION_BASE))
+VIDEO_EXTENSIONS: frozenset[str] = frozenset(convert_to_lower_and_upper_set(_VIDEO_EXTENSION_BASE))
+AUDIO_EXTENSIONS: frozenset[str] = frozenset(convert_to_lower_and_upper_set(_AUDIO_EXTENSION_BASE))
 
-AUDIO_EXTENSIONS = convert_to_lower_and_upper_set({"mp3", "m4a", "wav", "amr", "mpga"})
-
-_doc_extensions: set[str]
-if dify_config.ETL_TYPE == "Unstructured":
-    _doc_extensions = {
+_UNSTRUCTURED_DOCUMENT_EXTENSION_BASE: frozenset[str] = frozenset(
+    (
         "txt",
         "markdown",
         "md",
@@ -35,11 +36,10 @@ if dify_config.ETL_TYPE == "Unstructured":
         "pptx",
         "xml",
         "epub",
-    }
-    if dify_config.UNSTRUCTURED_API_URL:
-        _doc_extensions.add("ppt")
-else:
-    _doc_extensions = {
+    )
+)
+_DEFAULT_DOCUMENT_EXTENSION_BASE: frozenset[str] = frozenset(
+    (
         "txt",
         "markdown",
         "md",
@@ -53,8 +53,17 @@ else:
         "csv",
         "vtt",
         "properties",
-    }
-DOCUMENT_EXTENSIONS: set[str] = convert_to_lower_and_upper_set(_doc_extensions)
+    )
+)
+
+_doc_extensions: set[str]
+if dify_config.ETL_TYPE == "Unstructured":
+    _doc_extensions = set(_UNSTRUCTURED_DOCUMENT_EXTENSION_BASE)
+    if dify_config.UNSTRUCTURED_API_URL:
+        _doc_extensions.add("ppt")
+else:
+    _doc_extensions = set(_DEFAULT_DOCUMENT_EXTENSION_BASE)
+DOCUMENT_EXTENSIONS: frozenset[str] = frozenset(convert_to_lower_and_upper_set(_doc_extensions))
 
 # console
 COOKIE_NAME_ACCESS_TOKEN = "access_token"

api/constants/dsl_version.py

@@ -0,0 +1 @@
+CURRENT_APP_DSL_VERSION = "0.6.0"

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

@@ -1,74 +1,36 @@
 """
-Core Context - Framework-agnostic context management.
+Application-layer context adapters.
 
-This module provides context management that is independent of any specific
-web framework. Framework-specific implementations register their context
-capture functions at application initialization time.
-
-This ensures the workflow layer remains completely decoupled from Flask
-or any other web framework.
+Concrete execution-context implementations live here so `graphon` only
+depends on injected context managers rather than framework state capture.
 """
 
-import contextvars
-from collections.abc import Callable
-
-from core.workflow.context.execution_context import (
+from context.execution_context import (
+    AppContext,
+    ContextProviderNotFoundError,
     ExecutionContext,
+    ExecutionContextBuilder,
     IExecutionContext,
     NullAppContext,
+    capture_current_context,
+    read_context,
+    register_context,
+    register_context_capturer,
+    reset_context_provider,
 )
-
-# Global capturer function - set by framework-specific modules
-_capturer: Callable[[], IExecutionContext] | None = None
-
-
-def register_context_capturer(capturer: Callable[[], IExecutionContext]) -> None:
-    """
-    Register a context capture function.
-
-    This should be called by framework-specific modules (e.g., Flask)
-    during application initialization.
-
-    Args:
-        capturer: Function that captures current context and returns IExecutionContext
-    """
-    global _capturer
-    _capturer = capturer
-
-
-def capture_current_context() -> IExecutionContext:
-    """
-    Capture current execution context.
-
-    This function uses the registered context capturer. If no capturer
-    is registered, it returns a minimal context with only contextvars
-    (suitable for non-framework environments like tests or standalone scripts).
-
-    Returns:
-        IExecutionContext with captured context
-    """
-    if _capturer is None:
-        # No framework registered - return minimal context
-        return ExecutionContext(
-            app_context=NullAppContext(),
-            context_vars=contextvars.copy_context(),
-        )
-
-    return _capturer()
-
-
-def reset_context_provider() -> None:
-    """
-    Reset the context capturer.
-
-    This is primarily useful for testing to ensure a clean state.
-    """
-    global _capturer
-    _capturer = None
-
+from context.models import SandboxContext
 
 __all__ = [
+    "AppContext",
+    "ContextProviderNotFoundError",
+    "ExecutionContext",
+    "ExecutionContextBuilder",
+    "IExecutionContext",
+    "NullAppContext",
+    "SandboxContext",
     "capture_current_context",
+    "read_context",
+    "register_context",
     "register_context_capturer",
     "reset_context_provider",
 ]