Merge remote-tracking branch 'origin/main' into yanli/docx-image-render

# Conflicts: # api/tests/unit_tests/core/rag/extractor/test_word_extractor.py
2026-03-10 18:10:16 +08:00 · 2026-03-10 18:10:16 +08:00 · cb094558e3
parent 60c858aa48 125ece1d0c
commit cb094558e3
3347 changed files with 286224 additions and 75976 deletions
--- a/.agents/skills/backend-code-review/SKILL.md
+++ b/.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.
+```
--- a/.agents/skills/backend-code-review/references/architecture-rule.md
+++ b/.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)
+    ```
--- a/.agents/skills/backend-code-review/references/db-schema-rule.md
+++ b/.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)
+        )
+    ```
--- a/.agents/skills/backend-code-review/references/repositories-rule.md
+++ b/.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
+    ```
--- a/.agents/skills/backend-code-review/references/sqlalchemy-rule.md
+++ b/.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()
+    ```
--- a/.agents/skills/frontend-testing/SKILL.md
+++ b/.agents/skills/frontend-testing/SKILL.md
@ -204,6 +204,16 @@ When assigned to test a directory/path, test **ALL content** within that path:

 > See [Test Structure Template](#test-structure-template) for correct import/mock patterns.

+### `nuqs` Query State Testing (Required for URL State Hooks)
+
+When a component or hook uses `useQueryState` / `useQueryStates`:
+
+- ✅ Use `NuqsTestingAdapter` (prefer shared helpers in `web/test/nuqs-testing.tsx`)
+- ✅ Assert URL synchronization via `onUrlUpdate` (`searchParams`, `options.history`)
+- ✅ For custom parsers (`createParser`), keep `parse` and `serialize` bijective and add round-trip edge cases (`%2F`, `%25`, spaces, legacy encoded values)
+- ✅ Verify default-clearing behavior (default values should be removed from URL when applicable)
+- ⚠️ Only mock `nuqs` directly when URL behavior is explicitly out of scope for the test
+
 ## Core Principles

 ### 1. AAA Pattern (Arrange-Act-Assert)
--- a/.agents/skills/frontend-testing/references/checklist.md
+++ b/.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

--- a/.agents/skills/frontend-testing/references/mocking.md
+++ b/.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
--- a/.agents/skills/orpc-contract-first/SKILL.md
+++ b/.agents/skills/orpc-contract-first/SKILL.md
@ -1,43 +1,100 @@
 ---
 name: orpc-contract-first
-description: Guide for implementing oRPC contract-first API patterns in Dify frontend. Triggers when creating new API contracts, adding service endpoints, integrating TanStack Query with typed contracts, or migrating legacy service calls to oRPC. Use for all API layer work in web/contract and web/service directories.
+description: Guide for implementing oRPC contract-first API patterns in Dify frontend. Trigger when creating or updating contracts in web/contract, wiring router composition, integrating TanStack Query with typed contracts, migrating legacy service calls to oRPC, or deciding whether to call queryOptions directly vs extracting a helper or use-* hook in web/service.
 ---

 # oRPC Contract-First Development

-## Project Structure
+## Intent

-```
+- Keep contract as single source of truth in `web/contract/*`.
+- Default query usage: call-site `useQuery(consoleQuery|marketplaceQuery.xxx.queryOptions(...))` when endpoint behavior maps 1:1 to the contract.
+- Keep abstractions minimal and preserve TypeScript inference.
+
+## Minimal Structure
+
+```text
 web/contract/
-├── base.ts           # Base contract (inputStructure: 'detailed')
-├── router.ts         # Router composition & type exports
-├── marketplace.ts    # Marketplace contracts
-└── console/          # Console contracts by domain
-    ├── system.ts
-    └── billing.ts
+├── base.ts
+├── router.ts
+├── marketplace.ts
+└── console/
+    ├── billing.ts
+    └── ...other domains
+web/service/client.ts
 ```

-## Workflow
+## Core Workflow

-1. **Create contract** in `web/contract/console/{domain}.ts`
-   - Import `base` from `../base` and `type` from `@orpc/contract`
-   - Define route with `path`, `method`, `input`, `output`
+1. Define contract in `web/contract/console/{domain}.ts` or `web/contract/marketplace.ts`
+   - Use `base.route({...}).output(type<...>())` as baseline.
+   - Add `.input(type<...>())` only when request has `params/query/body`.
+   - For `GET` without input, omit `.input(...)` (do not use `.input(type<unknown>())`).
+2. Register contract in `web/contract/router.ts`
+   - Import directly from domain files and nest by API prefix.
+3. Consume from UI call sites via oRPC query utils.

-2. **Register in router** at `web/contract/router.ts`
-   - Import directly from domain file (no barrel files)
-   - Nest by API prefix: `billing: { invoices, bindPartnerStack }`
+```typescript
+import { useQuery } from '@tanstack/react-query'
+import { consoleQuery } from '@/service/client'

-3. **Create hooks** in `web/service/use-{domain}.ts`
-   - Use `consoleQuery.{group}.{contract}.queryKey()` for query keys
-   - Use `consoleClient.{group}.{contract}()` for API calls
+const invoiceQuery = useQuery(consoleQuery.billing.invoices.queryOptions({
+  staleTime: 5 * 60 * 1000,
+  throwOnError: true,
+  select: invoice => invoice.url,
+}))
+```

-## Key Rules
+## Query Usage Decision Rule
+
+1. Default: call site directly uses `*.queryOptions(...)`.
+2. If 3+ call sites share the same extra options (for example `retry: false`), extract a small queryOptions helper, not a `use-*` passthrough hook.
+3. Create `web/service/use-{domain}.ts` only for orchestration:
+   - Combine multiple queries/mutations.
+   - Share domain-level derived state or invalidation helpers.
+
+```typescript
+const invoicesBaseQueryOptions = () =>
+  consoleQuery.billing.invoices.queryOptions({ retry: false })
+
+const invoiceQuery = useQuery({
+  ...invoicesBaseQueryOptions(),
+  throwOnError: true,
+})
+```
+
+## Mutation Usage Decision Rule
+
+1. Default: call mutation helpers from `consoleQuery` / `marketplaceQuery`, for example `useMutation(consoleQuery.billing.bindPartnerStack.mutationOptions(...))`.
+2. If mutation flow is heavily custom, use oRPC clients as `mutationFn` (for example `consoleClient.xxx` / `marketplaceClient.xxx`), instead of generic handwritten non-oRPC mutation logic.
+
+## Key API Guide (`.key` vs `.queryKey` vs `.mutationKey`)
+
+- `.key(...)`:
+  - Use for partial matching operations (recommended for invalidation/refetch/cancel patterns).
+  - Example: `queryClient.invalidateQueries({ queryKey: consoleQuery.billing.key() })`
+- `.queryKey(...)`:
+  - Use for a specific query's full key (exact query identity / direct cache addressing).
+- `.mutationKey(...)`:
+  - Use for a specific mutation's full key.
+  - Typical use cases: mutation defaults registration, mutation-status filtering (`useIsMutating`, `queryClient.isMutating`), or explicit devtools grouping.
+
+## Anti-Patterns
+
+- Do not wrap `useQuery` with `options?: Partial<UseQueryOptions>`.
+- Do not split local `queryKey/queryFn` when oRPC `queryOptions` already exists and fits the use case.
+- Do not create thin `use-*` passthrough hooks for a single endpoint.
+- Reason: these patterns can degrade inference (`data` may become `unknown`, especially around `throwOnError`/`select`) and add unnecessary indirection.
+
+## Contract Rules

 - **Input structure**: Always use `{ params, query?, body? }` format
+- **No-input GET**: Omit `.input(...)`; do not use `.input(type<unknown>())`
 - **Path params**: Use `{paramName}` in path, match in `params` object
- **Router nesting**: Group by API prefix (e.g., `/billing/*` → `billing: {}`)
+- **Router nesting**: Group by API prefix (e.g., `/billing/*` -> `billing: {}`)
 - **No barrel files**: Import directly from specific files
 - **Types**: Import from `@/types/`, use `type<T>()` helper
+- **Mutations**: Prefer `mutationOptions`; use explicit `mutationKey` mainly for defaults/filtering/devtools

 ## Type Export

--- a/.claude/skills/backend-code-review
+++ b/.claude/skills/backend-code-review
@ -0,0 +1 @@
+../../.agents/skills/backend-code-review
--- a/.devcontainer/post_create_command.sh
+++ b/.devcontainer/post_create_command.sh
@ -7,7 +7,7 @@ cd web && pnpm install
 pipx install uv

 echo "alias start-api=\"cd $WORKSPACE_ROOT/api && uv run python -m flask run --host 0.0.0.0 --port=5001 --debug\"" >> ~/.bashrc
-echo "alias start-worker=\"cd $WORKSPACE_ROOT/api && uv run python -m celery -A app.celery worker -P threads -c 1 --loglevel INFO -Q dataset,priority_dataset,priority_pipeline,pipeline,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,workflow,schedule_poller,schedule_executor,triggered_workflow_dispatcher,trigger_refresh_executor,retention\"" >> ~/.bashrc
+echo "alias start-worker=\"cd $WORKSPACE_ROOT/api && uv run python -m celery -A app.celery worker -P threads -c 1 --loglevel INFO -Q dataset,dataset_summary,priority_dataset,priority_pipeline,pipeline,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,workflow,schedule_poller,schedule_executor,triggered_workflow_dispatcher,trigger_refresh_executor,retention\"" >> ~/.bashrc
 echo "alias start-web=\"cd $WORKSPACE_ROOT/web && pnpm dev:inspect\"" >> ~/.bashrc
 echo "alias start-web-prod=\"cd $WORKSPACE_ROOT/web && pnpm build && pnpm start\"" >> ~/.bashrc
 echo "alias start-containers=\"cd $WORKSPACE_ROOT/docker && docker-compose -f docker-compose.middleware.yaml -p dify --env-file middleware.env up -d\"" >> ~/.bashrc
--- a/.github/CODEOWNERS
+++ b/.github/CODEOWNERS
@ -36,7 +36,7 @@
 /api/core/workflow/graph/ @laipz8200 @QuantumGhost
 /api/core/workflow/graph_events/ @laipz8200 @QuantumGhost
 /api/core/workflow/node_events/ @laipz8200 @QuantumGhost
-/api/core/model_runtime/ @laipz8200 @QuantumGhost
+/api/dify_graph/model_runtime/ @laipz8200 @QuantumGhost

 # Backend - Workflow - Nodes (Agent, Iteration, Loop, LLM)
 /api/core/workflow/nodes/agent/ @Nov1c444
--- a/.github/actions/setup-web/action.yml
+++ b/.github/actions/setup-web/action.yml
@ -0,0 +1,33 @@
+name: Setup Web Environment
+description: Setup pnpm, Node.js, and install web dependencies.
+
+inputs:
+  node-version:
+    description: Node.js version to use
+    required: false
+    default: "22"
+  install-dependencies:
+    description: Whether to install web dependencies after setting up Node.js
+    required: false
+    default: "true"
+
+runs:
+  using: composite
+  steps:
+    - name: Install pnpm
+      uses: pnpm/action-setup@41ff72655975bd51cab0327fa583b6e92b6d3061 # v4.2.0
+      with:
+        package_json_file: web/package.json
+        run_install: false
+
+    - name: Setup Node.js
+      uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
+      with:
+        node-version: ${{ inputs.node-version }}
+        cache: pnpm
+        cache-dependency-path: ./web/pnpm-lock.yaml
+
+    - name: Install dependencies
+      if: ${{ inputs.install-dependencies == 'true' }}
+      shell: bash
+      run: pnpm --dir web install --frozen-lockfile
--- a/.github/dependabot.yml
+++ b/.github/dependabot.yml
@ -1,12 +1,57 @@
 version: 2
+
 updates:
+  - package-ecosystem: "pip"
+    directory: "/api"
+    open-pull-requests-limit: 2
+    schedule:
+      interval: "weekly"
+    groups:
+      python-dependencies:
+        patterns:
+          - "*"
+  - package-ecosystem: "uv"
+    directory: "/api"
+    open-pull-requests-limit: 2
+    schedule:
+      interval: "weekly"
+    groups:
+      uv-dependencies:
+        patterns:
+          - "*"
  - package-ecosystem: "npm"
    directory: "/web"
    schedule:
      interval: "weekly"
    open-pull-requests-limit: 2
-  - package-ecosystem: "uv"
-    directory: "/api"
-    schedule:
-      interval: "weekly"
-    open-pull-requests-limit: 2
+    ignore:
+      - dependency-name: "ky"
+      - dependency-name: "tailwind-merge"
+        update-types: ["version-update:semver-major"]
+      - dependency-name: "tailwindcss"
+        update-types: ["version-update:semver-major"]
+      - dependency-name: "react-syntax-highlighter"
+        update-types: ["version-update:semver-major"]
+      - dependency-name: "react-window"
+        update-types: ["version-update:semver-major"]
+    groups:
+      lexical:
+        patterns:
+          - "lexical"
+          - "@lexical/*"
+      storybook:
+        patterns:
+          - "storybook"
+          - "@storybook/*"
+      eslint-group:
+        patterns:
+          - "*eslint*"
+      npm-dependencies:
+        patterns:
+          - "*"
+        exclude-patterns:
+          - "lexical"
+          - "@lexical/*"
+          - "storybook"
+          - "@storybook/*"
+          - "*eslint*"
--- a/.github/workflows/anti-slop.yml
+++ b/.github/workflows/anti-slop.yml
@ -0,0 +1,17 @@
+name: Anti-Slop PR Check
+
+on:
+  pull_request_target:
+    types: [opened, edited, synchronize]
+
+permissions:
+  pull-requests: write
+  contents: read
+
+jobs:
+  anti-slop:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: peakoss/anti-slop@v0
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
--- a/.github/workflows/api-tests.yml
+++ b/.github/workflows/api-tests.yml
@ -22,12 +22,12 @@ jobs:

    steps:
      - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          persist-credentials: false

      - name: Setup UV and Python
-        uses: astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@5a095e7a2014a4212f075830d4f7277575a9d098 # v7.3.1
        with:
          enable-cache: true
          python-version: ${{ matrix.python-version }}
@ -51,7 +51,7 @@ jobs:
        run: sh .github/workflows/expose_service_ports.sh

      - name: Set up Sandbox
-        uses: hoverkraft-tech/compose-action@v2
+        uses: hoverkraft-tech/compose-action@4894d2492015c1774ee5a13a95b1072093087ec3 # v2.5.0
        with:
          compose-file: |
            docker/docker-compose.middleware.yaml
--- a/.github/workflows/autofix.yml
+++ b/.github/workflows/autofix.yml
@ -12,22 +12,22 @@ jobs:
    if: github.repository == 'langgenius/dify'
    runs-on: ubuntu-latest
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2

      - name: Check Docker Compose inputs
        id: docker-compose-changes
-        uses: tj-actions/changed-files@v47
+        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
        with:
          files: |
            docker/generate_docker_compose
            docker/.env.example
            docker/docker-compose-template.yaml
            docker/docker-compose.yaml
-      - uses: actions/setup-python@v6
+      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
        with:
          python-version: "3.11"

-      - uses: astral-sh/setup-uv@v7
+      - uses: astral-sh/setup-uv@5a095e7a2014a4212f075830d4f7277575a9d098 # v7.3.1

      - name: Generate Docker Compose
        if: steps.docker-compose-changes.outputs.any_changed == 'true'
@ -84,4 +84,14 @@ jobs:
        run: |
          uvx --python 3.13 mdformat . --exclude ".agents/skills/**"

-      - uses: autofix-ci/action@635ffb0c9798bd160680f18fd73371e355b85f27
+      - name: Setup web environment
+        uses: ./.github/actions/setup-web
+        with:
+          node-version: "24"
+
+      - name: ESLint autofix
+        run: |
+          cd web
+          pnpm eslint --concurrency=2 --prune-suppressions
+
+      - uses: autofix-ci/action@7a166d7532b277f34e16238930461bf77f9d7ed8 # v1.3.3
--- a/.github/workflows/build-push.yml
+++ b/.github/workflows/build-push.yml
@ -53,26 +53,26 @@ jobs:
          echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV

      - name: Login to Docker Hub
-        uses: docker/login-action@v3
+        uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v4.0.0
        with:
          username: ${{ env.DOCKERHUB_USER }}
          password: ${{ env.DOCKERHUB_TOKEN }}

      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
+        uses: docker/setup-qemu-action@ce360397dd3f832beb865e1373c09c0e9f86d70a # v4.0.0

      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4.0.0

      - name: Extract metadata for Docker
        id: meta
-        uses: docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # v6.0.0
        with:
          images: ${{ env[matrix.image_name_env] }}

      - name: Build Docker image
        id: build
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@d08e5c354a6adb9ed34480a06d141179aa583294 # v7.0.0
        with:
          context: "{{defaultContext}}:${{ matrix.context }}"
          platforms: ${{ matrix.platform }}
@ -91,7 +91,7 @@ jobs:
          touch "/tmp/digests/${sanitized_digest}"

      - name: Upload digest
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
        with:
          name: digests-${{ matrix.context }}-${{ env.PLATFORM_PAIR }}
          path: /tmp/digests/*
@ -113,21 +113,21 @@ jobs:
            context: "web"
    steps:
      - name: Download digests
-        uses: actions/download-artifact@v7
+        uses: actions/download-artifact@70fc10c6e5e1ce46ad2ea6f2b72d43f7d47b13c3 # v8.0.0
        with:
          path: /tmp/digests
          pattern: digests-${{ matrix.context }}-*
          merge-multiple: true

      - name: Login to Docker Hub
-        uses: docker/login-action@v3
+        uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v4.0.0
        with:
          username: ${{ env.DOCKERHUB_USER }}
          password: ${{ env.DOCKERHUB_TOKEN }}

      - name: Extract metadata for Docker
        id: meta
-        uses: docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # v6.0.0
        with:
          images: ${{ env[matrix.image_name_env] }}
          tags: |
--- a/.github/workflows/db-migration-test.yml
+++ b/.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@5a095e7a2014a4212f075830d4f7277575a9d098 # v7.3.1
        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@5a095e7a2014a4212f075830d4f7277575a9d098 # v7.3.1
        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
--- a/.github/workflows/deploy-agent-dev.yml
+++ b/.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 }}
--- a/.github/workflows/deploy-dev.yml
+++ b/.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 }}
--- a/.github/workflows/deploy-hitl.yml
+++ b/.github/workflows/deploy-hitl.yml
@ -16,7 +16,7 @@ jobs:
      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 }}
--- a/.github/workflows/docker-build.yml
+++ b/.github/workflows/docker-build.yml
@ -32,13 +32,13 @@ jobs:
            context: "web"
    steps:
      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
+        uses: docker/setup-qemu-action@ce360397dd3f832beb865e1373c09c0e9f86d70a # v4.0.0

      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4.0.0

      - name: Build Docker Image
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@d08e5c354a6adb9ed34480a06d141179aa583294 # v7.0.0
        with:
          push: false
          context: "{{defaultContext}}:${{ matrix.context }}"
--- a/.github/workflows/labeler.yml
+++ b/.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
--- a/.github/workflows/main-ci.yml
+++ b/.github/workflows/main-ci.yml
@ -27,8 +27,8 @@ jobs:
      vdb-changed: ${{ steps.changes.outputs.vdb }}
      migration-changed: ${{ steps.changes.outputs.migration }}
    steps:
-      - uses: actions/checkout@v6
-      - uses: dorny/paths-filter@v3
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+      - uses: dorny/paths-filter@de90cc6fb38fc0963ad72b210f1f284cd68cea36 # v3.0.2
        id: changes
        with:
          filters: |
@ -39,6 +39,7 @@ jobs:
            web:
              - 'web/**'
              - '.github/workflows/web-tests.yml'
+              - '.github/actions/setup-web/**'
            vdb:
              - 'api/core/rag/datasource/**'
              - 'docker/**'
--- a/.github/workflows/pyrefly-diff-comment.yml
+++ b/.github/workflows/pyrefly-diff-comment.yml
@ -0,0 +1,88 @@
+name: Comment with Pyrefly Diff
+
+on:
+  workflow_run:
+    workflows:
+      - Pyrefly Diff Check
+    types:
+      - completed
+
+permissions: {}
+
+jobs:
+  comment:
+    name: Comment PR with pyrefly diff
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      contents: read
+      issues: write
+      pull-requests: write
+    if: ${{ github.event.workflow_run.conclusion == 'success' && github.event.workflow_run.pull_requests[0].head.repo.full_name != github.repository }}
+    steps:
+      - name: Download pyrefly diff artifact
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const fs = require('fs');
+            const artifacts = await github.rest.actions.listWorkflowRunArtifacts({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              run_id: ${{ github.event.workflow_run.id }},
+            });
+            const match = artifacts.data.artifacts.find((artifact) =>
+              artifact.name === 'pyrefly_diff'
+            );
+            if (!match) {
+              throw new Error('pyrefly_diff artifact not found');
+            }
+            const download = await github.rest.actions.downloadArtifact({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              artifact_id: match.id,
+              archive_format: 'zip',
+            });
+            fs.writeFileSync('pyrefly_diff.zip', Buffer.from(download.data));
+
+      - name: Unzip artifact
+        run: unzip -o pyrefly_diff.zip
+
+      - name: Post comment
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const fs = require('fs');
+            let diff = fs.readFileSync('pyrefly_diff.txt', { encoding: 'utf8' });
+            let prNumber = null;
+            try {
+              prNumber = parseInt(fs.readFileSync('pr_number.txt', { encoding: 'utf8' }), 10);
+            } catch (err) {
+              // Fallback to workflow_run payload if artifact is missing or incomplete.
+              const prs = context.payload.workflow_run.pull_requests || [];
+              if (prs.length > 0 && prs[0].number) {
+                prNumber = prs[0].number;
+              }
+            }
+            if (!prNumber) {
+              throw new Error('PR number not found in artifact or workflow_run payload');
+            }
+
+            const MAX_CHARS = 65000;
+            if (diff.length > MAX_CHARS) {
+              diff = diff.slice(0, MAX_CHARS);
+              diff = diff.slice(0, diff.lastIndexOf('\\n'));
+              diff += '\\n\\n... (truncated) ...';
+            }
+
+            const body = diff.trim()
+              ? '### Pyrefly Diff\n<details>\n<summary>base → PR</summary>\n\n```diff\n' + diff + '\n```\n</details>'
+              : '### Pyrefly Diff\nNo changes detected.';
+
+            await github.rest.issues.createComment({
+              issue_number: prNumber,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body,
+            });
--- a/.github/workflows/pyrefly-diff.yml
+++ b/.github/workflows/pyrefly-diff.yml
@ -0,0 +1,100 @@
+name: Pyrefly Diff Check
+
+on:
+  pull_request:
+    paths:
+      - 'api/**/*.py'
+
+permissions:
+  contents: read
+
+jobs:
+  pyrefly-diff:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      issues: write
+      pull-requests: write
+    steps:
+      - name: Checkout PR branch
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          fetch-depth: 0
+
+      - name: Setup Python & UV
+        uses: astral-sh/setup-uv@5a095e7a2014a4212f075830d4f7277575a9d098 # v7.3.1
+        with:
+          enable-cache: true
+
+      - name: Install dependencies
+        run: uv sync --project api --dev
+
+      - name: Prepare diagnostics extractor
+        run: |
+          git show ${{ github.event.pull_request.head.sha }}:api/libs/pyrefly_diagnostics.py > /tmp/pyrefly_diagnostics.py
+
+      - name: Run pyrefly on PR branch
+        run: |
+          uv run --directory api --dev pyrefly check 2>&1 \
+            | uv run --directory api python /tmp/pyrefly_diagnostics.py > /tmp/pyrefly_pr.txt || true
+
+      - name: Checkout base branch
+        run: git checkout ${{ github.base_ref }}
+
+      - name: Run pyrefly on base branch
+        run: |
+          uv run --directory api --dev pyrefly check 2>&1 \
+            | uv run --directory api python /tmp/pyrefly_diagnostics.py > /tmp/pyrefly_base.txt || true
+
+      - name: Compute diff
+        run: |
+          diff -u /tmp/pyrefly_base.txt /tmp/pyrefly_pr.txt > pyrefly_diff.txt || true
+
+      - name: Save PR number
+        run: |
+          echo ${{ github.event.pull_request.number }} > pr_number.txt
+
+      - name: Upload pyrefly diff
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        with:
+          name: pyrefly_diff
+          path: |
+            pyrefly_diff.txt
+            pr_number.txt
+
+      - name: Comment PR with pyrefly diff
+        if: ${{ github.event.pull_request.head.repo.full_name == github.repository }}
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const fs = require('fs');
+            let diff = fs.readFileSync('pyrefly_diff.txt', { encoding: 'utf8' });
+            const prNumber = context.payload.pull_request.number;
+
+            const MAX_CHARS = 65000;
+            if (diff.length > MAX_CHARS) {
+              diff = diff.slice(0, MAX_CHARS);
+              diff = diff.slice(0, diff.lastIndexOf('\n'));
+              diff += '\n\n... (truncated) ...';
+            }
+
+            const body = diff.trim()
+              ? [
+                  '### Pyrefly Diff',
+                  '<details>',
+                  '<summary>base → PR</summary>',
+                  '',
+                  '```diff',
+                  diff,
+                  '```',
+                  '</details>',
+                ].join('\n')
+              : '### Pyrefly Diff\nNo changes detected.';
+
+            await github.rest.issues.createComment({
+              issue_number: prNumber,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body,
+            });
--- a/.github/workflows/semantic-pull-request.yml
+++ b/.github/workflows/semantic-pull-request.yml
@ -16,6 +16,6 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - name: Check title
-        uses: amannn/action-semantic-pull-request@v6.1.1
+        uses: amannn/action-semantic-pull-request@48f256284bd46cdaab1048c3721360e808335d50 # v6.1.1
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
--- a/.github/workflows/stale.yml
+++ b/.github/workflows/stale.yml
@ -18,7 +18,7 @@ jobs:
      pull-requests: write

    steps:
-      - uses: actions/stale@v10
+      - uses: actions/stale@b5d41d4e1d5dceea10e7104786b73624c18a190f # v10.2.0
        with:
          days-before-issue-stale: 15
          days-before-issue-close: 3
--- a/.github/workflows/style.yml
+++ b/.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@5a095e7a2014a4212f075830d4f7277575a9d098 # v7.3.1
        with:
          enable-cache: false
          python-version: "3.12"
@ -67,36 +67,22 @@ jobs:

    steps:
      - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          persist-credentials: false

      - name: Check changed files
        id: changed-files
-        uses: tj-actions/changed-files@v47
+        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
        with:
          files: |
            web/**
            .github/workflows/style.yml
+            .github/actions/setup-web/**

-      - name: Install pnpm
-        uses: pnpm/action-setup@v4
-        with:
-          package_json_file: web/package.json
-          run_install: false
-
-      - name: Setup NodeJS
-        uses: actions/setup-node@v6
+      - name: Setup web environment
        if: steps.changed-files.outputs.any_changed == 'true'
-        with:
-          node-version: 24
-          cache: pnpm
-          cache-dependency-path: ./web/pnpm-lock.yaml
-
-      - name: Web dependencies
-        if: steps.changed-files.outputs.any_changed == 'true'
-        working-directory: ./web
-        run: pnpm install --frozen-lockfile
+        uses: ./.github/actions/setup-web

      - name: Web style check
        if: steps.changed-files.outputs.any_changed == 'true'
@ -134,14 +120,14 @@ jobs:

    steps:
      - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          fetch-depth: 0
          persist-credentials: false

      - name: Check changed files
        id: changed-files
-        uses: tj-actions/changed-files@v47
+        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
        with:
          files: |
            **.sh
@ -152,7 +138,7 @@ jobs:
            .editorconfig

      - name: Super-linter
-        uses: super-linter/super-linter/slim@v8
+        uses: super-linter/super-linter/slim@61abc07d755095a68f4987d1c2c3d1d64408f1f9 # v8.5.0
        if: steps.changed-files.outputs.any_changed == 'true'
        env:
          BASH_SEVERITY: warning
--- a/.github/workflows/tool-test-sdks.yaml
+++ b/.github/workflows/tool-test-sdks.yaml
@ -21,14 +21,14 @@ jobs:
        working-directory: sdks/nodejs-client

    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          persist-credentials: false

      - name: Use Node.js
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
        with:
-          node-version: 24
+          node-version: 22
          cache: ''
          cache-dependency-path: 'pnpm-lock.yaml'

--- a/.github/workflows/translate-i18n-claude.yml
+++ b/.github/workflows/translate-i18n-claude.yml
@ -38,7 +38,7 @@ jobs:

    steps:
      - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          fetch-depth: 0
          token: ${{ secrets.GITHUB_TOKEN }}
@ -48,18 +48,10 @@ 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
+      - name: Setup web environment
+        uses: ./.github/actions/setup-web
        with:
-          package_json_file: web/package.json
-          run_install: false
-
-      - name: Set up Node.js
-        uses: actions/setup-node@v6
-        with:
-          node-version: 24
-          cache: pnpm
-          cache-dependency-path: ./web/pnpm-lock.yaml
+          install-dependencies: "false"

      - name: Detect changed files and generate diff
        id: detect_changes
@ -130,7 +122,7 @@ jobs:

      - name: Run Claude Code for Translation Sync
        if: steps.detect_changes.outputs.CHANGED_FILES != ''
-        uses: anthropics/claude-code-action@v1
+        uses: anthropics/claude-code-action@26ec041249acb0a944c0a47b6c0c13f05dbc5b44 # v1.0.70
        with:
          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
          github_token: ${{ secrets.GITHUB_TOKEN }}
--- a/.github/workflows/trigger-i18n-sync.yml
+++ b/.github/workflows/trigger-i18n-sync.yml
@ -21,7 +21,7 @@ jobs:

    steps:
      - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          fetch-depth: 0

@ -59,7 +59,7 @@ jobs:

      - name: Trigger i18n sync workflow
        if: steps.detect.outputs.has_changes == 'true'
-        uses: peter-evans/repository-dispatch@v3
+        uses: peter-evans/repository-dispatch@28959ce8df70de7be546dd1250a005dd32156697 # v4.0.1
        with:
          token: ${{ secrets.GITHUB_TOKEN }}
          event-type: i18n-sync
--- a/.github/workflows/vdb-tests.yml
+++ b/.github/workflows/vdb-tests.yml
@ -19,19 +19,19 @@ jobs:

    steps:
      - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          persist-credentials: false

      - name: Free Disk Space
-        uses: endersonmenezes/free-disk-space@v3
+        uses: endersonmenezes/free-disk-space@7901478139cff6e9d44df5972fd8ab8fcade4db1 # v3.2.2
        with:
          remove_dotnet: true
          remove_haskell: true
          remove_tool_cache: true

      - name: Setup UV and Python
-        uses: astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@5a095e7a2014a4212f075830d4f7277575a9d098 # v7.3.1
        with:
          enable-cache: true
          python-version: ${{ matrix.python-version }}
@ -60,7 +60,7 @@ jobs:
 #            tiflash

      - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase, OceanBase)
-        uses: hoverkraft-tech/compose-action@v2.0.2
+        uses: hoverkraft-tech/compose-action@4894d2492015c1774ee5a13a95b1072093087ec3 # v2.5.0
        with:
          compose-file: |
            docker/docker-compose.yaml
--- a/.github/workflows/web-tests.yml
+++ b/.github/workflows/web-tests.yml
@ -3,13 +3,52 @@ name: Web Tests
 on:
  workflow_call:

+permissions:
+  contents: read
+
 concurrency:
  group: web-tests-${{ github.head_ref || github.run_id }}
  cancel-in-progress: true

 jobs:
  test:
-    name: Web Tests
+    name: Web Tests (${{ matrix.shardIndex }}/${{ matrix.shardTotal }})
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        shardIndex: [1, 2, 3, 4]
+        shardTotal: [4]
+    defaults:
+      run:
+        shell: bash
+        working-directory: ./web
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+
+      - name: Setup web environment
+        uses: ./.github/actions/setup-web
+
+      - name: Run tests
+        run: pnpm vitest run --reporter=blob --shard=${{ matrix.shardIndex }}/${{ matrix.shardTotal }} --coverage
+
+      - name: Upload blob report
+        if: ${{ !cancelled() }}
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        with:
+          name: blob-report-${{ matrix.shardIndex }}
+          path: web/.vitest-reports/*
+          include-hidden-files: true
+          retention-days: 1
+
+  merge-reports:
+    name: Merge Test Reports
+    if: ${{ !cancelled() }}
+    needs: [test]
    runs-on: ubuntu-latest
    defaults:
      run:
@ -18,28 +57,22 @@ 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
+      - name: Setup web environment
+        uses: ./.github/actions/setup-web
+
+      - name: Download blob reports
+        uses: actions/download-artifact@70fc10c6e5e1ce46ad2ea6f2b72d43f7d47b13c3 # v8.0.0
        with:
-          package_json_file: web/package.json
-          run_install: false
+          path: web/.vitest-reports
+          pattern: blob-report-*
+          merge-multiple: true

-      - 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: Run tests
-        run: pnpm test:ci
+      - name: Merge reports
+        run: pnpm vitest --merge-reports --coverage --silent=passed-only

      - name: Coverage Summary
        if: always()
@ -360,7 +393,7 @@ jobs:

      - name: Upload Coverage Artifact
        if: steps.coverage-summary.outputs.has_coverage == 'true'
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
        with:
          name: web-coverage-report
          path: web/coverage
@ -376,36 +409,22 @@ jobs:

    steps:
      - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          persist-credentials: false

      - name: Check changed files
        id: changed-files
-        uses: tj-actions/changed-files@v47
+        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
        with:
          files: |
            web/**
            .github/workflows/web-tests.yml
+            .github/actions/setup-web/**

-      - name: Install pnpm
-        uses: pnpm/action-setup@v4
-        with:
-          package_json_file: web/package.json
-          run_install: false
-
-      - name: Setup NodeJS
-        uses: actions/setup-node@v6
+      - name: Setup web environment
        if: steps.changed-files.outputs.any_changed == 'true'
-        with:
-          node-version: 24
-          cache: pnpm
-          cache-dependency-path: ./web/pnpm-lock.yaml
-
-      - name: Web dependencies
-        if: steps.changed-files.outputs.any_changed == 'true'
-        working-directory: ./web
-        run: pnpm install --frozen-lockfile
+        uses: ./.github/actions/setup-web

      - name: Web build check
        if: steps.changed-files.outputs.any_changed == 'true'
--- a/.gitignore
+++ b/.gitignore
@ -222,6 +222,7 @@ mise.toml

 # AI Assistant
 .roo/
+/.claude/worktrees/
 api/.env.backup
 /clickzetta

--- a/.vscode/launch.json.template
+++ b/.vscode/launch.json.template
@ -37,7 +37,7 @@
                "-c",
                "1",
                "-Q",
-                "dataset,priority_dataset,priority_pipeline,pipeline,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,workflow,schedule_poller,schedule_executor,triggered_workflow_dispatcher,trigger_refresh_executor,retention,workflow_based_app_execution",
+                "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"
            ],
--- a/AGENTS.md
+++ b/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
--- a/6
+++ b/6
@ -68,10 +68,10 @@ lint:
 	@echo "✅ Linting complete"

 type-check:
-	@echo "📝 Running type checks (basedpyright + mypy + ty)..."
+	@echo "📝 Running type checks (basedpyright + pyrefly + mypy)..."
 	@./dev/basedpyright-check $(PATH_TO_CHECK)
+	@./dev/pyrefly-check-local
 	@uv --directory api run mypy --exclude-gitignore --exclude 'tests/' --exclude 'migrations/' --check-untyped-defs --disable-error-code=import-untyped .
-	@cd api && uv run ty check
 	@echo "✅ Type checks complete"

 test:
@ -132,7 +132,7 @@ help:
 	@echo "  make format         - Format code with ruff"
 	@echo "  make check          - Check code with ruff"
 	@echo "  make lint           - Format, fix, and lint code (ruff, imports, dotenv)"
-	@echo "  make type-check     - Run type checks (basedpyright, mypy, ty)"
+	@echo "  make type-check     - Run type checks (basedpyright, pyrefly, mypy)"
 	@echo "  make test           - Run backend unit tests (or TARGET_TESTS=./api/tests/<target_tests>)"
 	@echo ""
 	@echo "Docker Build Targets:"
--- a/README.md
+++ b/README.md
@ -1,9 +1,5 @@
 ![cover-v5-optimized](./images/GitHub_README_if.png)

-<p align="center">
-  📌 <a href="https://dify.ai/blog/introducing-dify-workflow-file-upload-a-demo-on-ai-podcast">Introducing Dify Workflow File Upload: Recreate Google NotebookLM Podcast</a>
-</p>
-
 <p align="center">
  <a href="https://cloud.dify.ai">Dify Cloud</a> ·
  <a href="https://docs.dify.ai/getting-started/install-self-hosted">Self-hosting</a> ·
@ -60,7 +56,7 @@
  <a href="./docs/bn-BD/README.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
 </p>

-Dify is an open-source platform for developing LLM applications. Its intuitive interface combines agentic AI workflows, RAG pipelines, agent capabilities, model management, observability features, and more—allowing you to quickly move from prototype to production.
+Dify is an open-source LLM app development platform. Its intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features (including [Opik](https://www.comet.com/docs/opik/integrations/dify), [Langfuse](https://docs.langfuse.com), and [Arize Phoenix](https://docs.arize.com/phoenix)) and more, letting you quickly go from prototype to production. Here's a list of the core features:

 ## Quick start

@ -137,7 +133,7 @@ Star Dify on GitHub and be instantly notified of new releases.

 ### Custom configurations

-If you need to customize the configuration, please refer to the comments in our [.env.example](docker/.env.example) file and update the corresponding values in your `.env` file. Additionally, you might need to make adjustments to the `docker-compose.yaml` file itself, such as changing image versions, port mappings, or volume mounts, based on your specific deployment environment and requirements. After making any changes, please re-run `docker-compose up -d`. You can find the full list of available environment variables [here](https://docs.dify.ai/getting-started/install-self-hosted/environments).
+If you need to customize the configuration, please refer to the comments in our [.env.example](docker/.env.example) file and update the corresponding values in your `.env` file. Additionally, you might need to make adjustments to the `docker-compose.yaml` file itself, such as changing image versions, port mappings, or volume mounts, based on your specific deployment environment and requirements. After making any changes, please re-run `docker compose up -d`. You can find the full list of available environment variables [here](https://docs.dify.ai/getting-started/install-self-hosted/environments).

 #### Customizing Suggested Questions

--- a/api/.env.example
+++ b/api/.env.example
@ -42,6 +42,8 @@ REFRESH_TOKEN_EXPIRE_DAYS=30
 # redis configuration
 REDIS_HOST=localhost
 REDIS_PORT=6379
+# Optional: limit total connections in connection pool (unset for default)
+# REDIS_MAX_CONNECTIONS=200
 REDIS_USERNAME=
 REDIS_PASSWORD=difyai123456
 REDIS_USE_SSL=false
@ -553,6 +555,8 @@ 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
@ -715,6 +719,7 @@ 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

--- a/api/.importlinter
+++ b/api/.importlinter
@ -1,6 +1,7 @@
 [importlinter]
 root_packages =
    core
+    dify_graph
    configs
    controllers
    extensions
@ -21,51 +22,37 @@ layers =
    runtime
    entities
 containers =
-    core.workflow
+    dify_graph
 ignore_imports =
-    core.workflow.nodes.base.node -> core.workflow.graph_events
-    core.workflow.nodes.iteration.iteration_node -> core.workflow.graph_events
-    core.workflow.nodes.loop.loop_node -> core.workflow.graph_events
+    dify_graph.nodes.base.node -> dify_graph.graph_events
+    dify_graph.nodes.iteration.iteration_node -> dify_graph.graph_events
+    dify_graph.nodes.loop.loop_node -> dify_graph.graph_events

-    core.workflow.nodes.iteration.iteration_node -> core.app.workflow.node_factory
-    core.workflow.nodes.loop.loop_node -> core.app.workflow.node_factory
-
-    core.workflow.nodes.iteration.iteration_node -> core.workflow.graph_engine
-    core.workflow.nodes.iteration.iteration_node -> core.workflow.graph
-    core.workflow.nodes.iteration.iteration_node -> core.workflow.graph_engine.command_channels
-    core.workflow.nodes.loop.loop_node -> core.workflow.graph_engine
-    core.workflow.nodes.loop.loop_node -> core.workflow.graph
-    core.workflow.nodes.loop.loop_node -> core.workflow.graph_engine.command_channels
+    dify_graph.nodes.iteration.iteration_node -> dify_graph.graph_engine
+    dify_graph.nodes.loop.loop_node -> dify_graph.graph_engine
    # TODO(QuantumGhost): fix the import violation later
-    core.workflow.entities.pause_reason -> core.workflow.nodes.human_input.entities
+    dify_graph.entities.pause_reason -> dify_graph.nodes.human_input.entities

 [importlinter:contract:workflow-infrastructure-dependencies]
 name = Workflow Infrastructure Dependencies
 type = forbidden
 source_modules =
-    core.workflow
+    dify_graph
 forbidden_modules =
    extensions.ext_database
    extensions.ext_redis
 allow_indirect_imports = True
 ignore_imports =
-    core.workflow.nodes.agent.agent_node -> extensions.ext_database
-    core.workflow.nodes.datasource.datasource_node -> extensions.ext_database
-    core.workflow.nodes.knowledge_index.knowledge_index_node -> extensions.ext_database
-    core.workflow.nodes.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
-    # TODO(QuantumGhost): use DI to avoid depending on global DB.
-    core.workflow.nodes.human_input.human_input_node -> extensions.ext_database
+    dify_graph.nodes.agent.agent_node -> extensions.ext_database
+    dify_graph.nodes.llm.node -> extensions.ext_database
+    dify_graph.model_runtime.model_providers.__base.ai_model -> extensions.ext_redis
+    dify_graph.model_runtime.model_providers.model_provider_factory -> extensions.ext_redis

 [importlinter:contract:workflow-external-imports]
 name = Workflow External Imports
 type = forbidden
 source_modules =
-    core.workflow
+    dify_graph
 forbidden_modules =
    configs
    controllers
@ -91,7 +78,6 @@ forbidden_modules =
    core.logging
    core.mcp
    core.memory
-    core.model_manager
    core.moderation
    core.ops
    core.plugin
@ -104,248 +90,59 @@ forbidden_modules =
    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.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.human_input.human_input_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.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.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.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.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.human_input.entities -> core.variables.consts
-    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.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.nodes.human_input.human_input_node -> extensions.ext_database
-    core.workflow.nodes.human_input.human_input_node -> core.repositories.human_input_repository
-    core.workflow.workflow_entry -> extensions.otel.runtime
-    core.workflow.nodes.agent.agent_node -> models
-    core.workflow.nodes.base.node -> models.enums
-    core.workflow.nodes.llm.llm_utils -> models.provider_ids
-    core.workflow.nodes.llm.node -> models.model
-    core.workflow.workflow_entry -> models.enums
-    core.workflow.nodes.agent.agent_node -> services
-    core.workflow.nodes.tool.tool_node -> services
-
-[importlinter:contract:model-runtime-no-internal-imports]
-name = Model Runtime Internal Imports
-type = forbidden
-source_modules =
-    core.model_runtime
-forbidden_modules =
-    configs
-    controllers
-    extensions
-    models
-    services
-    tasks
-    core.agent
-    core.app
-    core.base
-    core.callback_handler
-    core.datasource
-    core.db
-    core.entities
-    core.errors
-    core.extension
-    core.external_data_tool
-    core.file
-    core.helper
-    core.hosting_configuration
-    core.indexing_runner
-    core.llm_generator
-    core.logging
-    core.mcp
-    core.memory
-    core.model_manager
-    core.moderation
-    core.ops
-    core.plugin
-    core.prompt
-    core.provider_manager
-    core.rag
-    core.repositories
-    core.schemas
-    core.tools
-    core.trigger
-    core.variables
-    core.workflow
-ignore_imports =
-    core.model_runtime.model_providers.__base.ai_model -> configs
-    core.model_runtime.model_providers.__base.ai_model -> extensions.ext_redis
-    core.model_runtime.model_providers.__base.large_language_model -> configs
-    core.model_runtime.model_providers.__base.text_embedding_model -> core.entities.embedding_type
-    core.model_runtime.model_providers.model_provider_factory -> configs
-    core.model_runtime.model_providers.model_provider_factory -> extensions.ext_redis
-    core.model_runtime.model_providers.model_provider_factory -> models.provider_ids
+    dify_graph.nodes.agent.agent_node -> core.model_manager
+    dify_graph.nodes.agent.agent_node -> core.provider_manager
+    dify_graph.nodes.agent.agent_node -> core.tools.tool_manager
+    dify_graph.nodes.llm.llm_utils -> core.model_manager
+    dify_graph.nodes.llm.protocols -> core.model_manager
+    dify_graph.nodes.llm.llm_utils -> dify_graph.model_runtime.model_providers.__base.large_language_model
+    dify_graph.nodes.llm.node -> core.tools.signature
+    dify_graph.nodes.tool.tool_node -> core.callback_handler.workflow_tool_callback_handler
+    dify_graph.nodes.tool.tool_node -> core.tools.tool_engine
+    dify_graph.nodes.tool.tool_node -> core.tools.tool_manager
+    dify_graph.nodes.agent.agent_node -> core.agent.entities
+    dify_graph.nodes.agent.agent_node -> core.agent.plugin_entities
+    dify_graph.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.app.app_config.entities
+    dify_graph.nodes.parameter_extractor.parameter_extractor_node -> core.prompt.advanced_prompt_transform
+    dify_graph.nodes.parameter_extractor.parameter_extractor_node -> core.prompt.simple_prompt_transform
+    dify_graph.nodes.parameter_extractor.parameter_extractor_node -> dify_graph.model_runtime.model_providers.__base.large_language_model
+    dify_graph.nodes.question_classifier.question_classifier_node -> core.prompt.simple_prompt_transform
+    dify_graph.nodes.parameter_extractor.parameter_extractor_node -> core.model_manager
+    dify_graph.nodes.question_classifier.question_classifier_node -> core.model_manager
+    dify_graph.nodes.tool.tool_node -> core.tools.utils.message_transformer
+    dify_graph.nodes.agent.agent_node -> models.model
+    dify_graph.nodes.llm.node -> core.helper.code_executor
+    dify_graph.nodes.llm.node -> core.llm_generator.output_parser.errors
+    dify_graph.nodes.llm.node -> core.llm_generator.output_parser.structured_output
+    dify_graph.nodes.llm.node -> core.model_manager
+    dify_graph.nodes.agent.entities -> core.prompt.entities.advanced_prompt_entities
+    dify_graph.nodes.llm.entities -> core.prompt.entities.advanced_prompt_entities
+    dify_graph.nodes.llm.node -> core.prompt.entities.advanced_prompt_entities
+    dify_graph.nodes.llm.node -> core.prompt.utils.prompt_message_util
+    dify_graph.nodes.parameter_extractor.entities -> core.prompt.entities.advanced_prompt_entities
+    dify_graph.nodes.parameter_extractor.parameter_extractor_node -> core.prompt.entities.advanced_prompt_entities
+    dify_graph.nodes.parameter_extractor.parameter_extractor_node -> core.prompt.utils.prompt_message_util
+    dify_graph.nodes.question_classifier.entities -> core.prompt.entities.advanced_prompt_entities
+    dify_graph.nodes.question_classifier.question_classifier_node -> core.prompt.utils.prompt_message_util
+    dify_graph.nodes.knowledge_index.entities -> core.rag.retrieval.retrieval_methods
+    dify_graph.nodes.llm.node -> models.dataset
+    dify_graph.nodes.agent.agent_node -> core.tools.utils.message_transformer
+    dify_graph.nodes.llm.file_saver -> core.tools.signature
+    dify_graph.nodes.llm.file_saver -> core.tools.tool_file_manager
+    dify_graph.nodes.tool.tool_node -> core.tools.errors
+    dify_graph.nodes.agent.agent_node -> extensions.ext_database
+    dify_graph.nodes.llm.node -> extensions.ext_database
+    dify_graph.nodes.agent.agent_node -> models
+    dify_graph.nodes.llm.node -> models.model
+    dify_graph.nodes.agent.agent_node -> services
+    dify_graph.nodes.tool.tool_node -> services
+    dify_graph.model_runtime.model_providers.__base.ai_model -> configs
+    dify_graph.model_runtime.model_providers.__base.ai_model -> extensions.ext_redis
+    dify_graph.model_runtime.model_providers.__base.large_language_model -> configs
+    dify_graph.model_runtime.model_providers.__base.text_embedding_model -> core.entities.embedding_type
+    dify_graph.model_runtime.model_providers.model_provider_factory -> configs
+    dify_graph.model_runtime.model_providers.model_provider_factory -> extensions.ext_redis
+    dify_graph.model_runtime.model_providers.model_provider_factory -> models.provider_ids

 [importlinter:contract:rsc]
 name = RSC
@ -354,7 +151,7 @@ layers =
    graph_engine
    response_coordinator
 containers =
-    core.workflow.graph_engine
+    dify_graph.graph_engine

 [importlinter:contract:worker]
 name = Worker
@ -363,7 +160,7 @@ layers =
    graph_engine
    worker
 containers =
-    core.workflow.graph_engine
+    dify_graph.graph_engine

 [importlinter:contract:graph-engine-architecture]
 name = Graph Engine Architecture
@ -379,28 +176,28 @@ layers =
    worker_management
    domain
 containers =
-    core.workflow.graph_engine
+    dify_graph.graph_engine

 [importlinter:contract:domain-isolation]
 name = Domain Model Isolation
 type = forbidden
 source_modules =
-    core.workflow.graph_engine.domain
+    dify_graph.graph_engine.domain
 forbidden_modules =
-    core.workflow.graph_engine.worker_management
-    core.workflow.graph_engine.command_channels
-    core.workflow.graph_engine.layers
-    core.workflow.graph_engine.protocols
+    dify_graph.graph_engine.worker_management
+    dify_graph.graph_engine.command_channels
+    dify_graph.graph_engine.layers
+    dify_graph.graph_engine.protocols

 [importlinter:contract:worker-management]
 name = Worker Management
 type = forbidden
 source_modules =
-    core.workflow.graph_engine.worker_management
+    dify_graph.graph_engine.worker_management
 forbidden_modules =
-    core.workflow.graph_engine.orchestration
-    core.workflow.graph_engine.command_processing
-    core.workflow.graph_engine.event_management
+    dify_graph.graph_engine.orchestration
+    dify_graph.graph_engine.command_processing
+    dify_graph.graph_engine.event_management


 [importlinter:contract:graph-traversal-components]
@ -410,11 +207,11 @@ layers =
    edge_processor
    skip_propagator
 containers =
-    core.workflow.graph_engine.graph_traversal
+    dify_graph.graph_engine.graph_traversal

 [importlinter:contract:command-channels]
 name = Command Channels Independence
 type = independence
 modules =
-    core.workflow.graph_engine.command_channels.in_memory_channel
-    core.workflow.graph_engine.command_channels.redis_channel
+    dify_graph.graph_engine.command_channels.in_memory_channel
+    dify_graph.graph_engine.command_channels.redis_channel
--- a/api/.ruff.toml
+++ b/api/.ruff.toml
@ -100,7 +100,7 @@ ignore = [
 "configs/*" = [
    "N802", # invalid-function-name
 ]
-"core/model_runtime/callbacks/base_callback.py" = ["T201"]
+"dify_graph/model_runtime/callbacks/base_callback.py" = ["T201"]
 "core/workflow/callbacks/workflow_logging_callback.py" = ["T201"]
 "libs/gmpy2_pkcs10aep_cipher.py" = [
    "N803", # invalid-argument-name
--- a/api/.vscode/launch.json.example
+++ b/api/.vscode/launch.json.example
@ -54,7 +54,7 @@
                "--loglevel",
                "DEBUG",
                "-Q",
-                "dataset,priority_pipeline,pipeline,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,workflow,schedule_poller,schedule_executor,triggered_workflow_dispatcher,trigger_refresh_executor"
+                "dataset,priority_pipeline,pipeline,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,workflow,workflow_based_app_execution,schedule_poller,schedule_executor,triggered_workflow_dispatcher,trigger_refresh_executor"
            ]
        }
    ]
--- a/api/AGENTS.md
+++ b/api/AGENTS.md
@ -62,6 +62,22 @@ This is the default standard for backend code in this repo. Follow it for new co

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

 ```python
--- a/api/README.md
+++ b/api/README.md
@ -42,7 +42,7 @@ The scripts resolve paths relative to their location, so you can run them from a

 1. Set up your application by visiting `http://localhost:3000`.

-1. Optional: start the worker service (async tasks, runs from `api`).
+1. Start the worker service (async and scheduler tasks, runs from `api`).

   ```bash
   ./dev/start-worker
@ -54,86 +54,6 @@ The scripts resolve paths relative to their location, so you can run them from a
   ./dev/start-beat
   ```

-### Manual commands
-
-<details>
-<summary>Show manual setup and run steps</summary>
-
-These commands assume you start from the repository root.
-
-1. Start the docker-compose stack.
-
-   The backend requires middleware, including PostgreSQL, Redis, and Weaviate, which can be started together using `docker-compose`.
-
-   ```bash
-   cp docker/middleware.env.example docker/middleware.env
-   # Use mysql or another vector database profile if you are not using postgres/weaviate.
-   docker compose -f docker/docker-compose.middleware.yaml --profile postgresql --profile weaviate -p dify up -d
-   ```
-
-1. Copy env files.
-
-   ```bash
-   cp api/.env.example api/.env
-   cp web/.env.example web/.env.local
-   ```
-
-1. Install UV if needed.
-
-   ```bash
-   pip install uv
-   # Or on macOS
-   brew install uv
-   ```
-
-1. Install API dependencies.
-
-   ```bash
-   cd api
-   uv sync --group dev
-   ```
-
-1. Install web dependencies.
-
-   ```bash
-   cd web
-   pnpm install
-   cd ..
-   ```
-
-1. Start backend (runs migrations first, in a new terminal).
-
-   ```bash
-   cd api
-   uv run flask db upgrade
-   uv run flask run --host 0.0.0.0 --port=5001 --debug
-   ```
-
-1. Start Dify [web](../web) service (in a new terminal).
-
-   ```bash
-   cd web
-   pnpm dev:inspect
-   ```
-
-1. Set up your application by visiting `http://localhost:3000`.
-
-1. Optional: start the worker service (async tasks, in a new terminal).
-
-   ```bash
-   cd api
-   uv run celery -A app.celery worker -P threads -c 2 --loglevel INFO -Q api_token,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]
--- a/api/commands.py
+++ b/api/commands.py
@ -30,6 +30,8 @@ from extensions.ext_redis import redis_client
 from extensions.ext_storage import storage
 from extensions.storage.opendal_storage import OpenDALStorage
 from extensions.storage.storage_type import StorageType
+from libs.datetime_utils import naive_utc_now
+from libs.db_migration_lock import DbMigrationAutoRenewLock
 from libs.helper import email as email_validate
 from libs.password import hash_password, password_pattern, valid_password
 from libs.rsa import generate_key_pair
@ -54,6 +56,8 @@ from tasks.remove_app_and_related_data_task import delete_draft_variables_batch

 logger = logging.getLogger(__name__)

+DB_UPGRADE_LOCK_TTL_SECONDS = 60
+

@click.command("reset-password", help="Reset the account password.")
@click.option("--email", prompt=True, help="Account email to reset password for")
@ -727,8 +731,15 @@ def create_tenant(email: str, language: str | None = None, name: str | None = No
@click.command("upgrade-db", help="Upgrade the database")
 def upgrade_db():
    click.echo("Preparing database migration...")
-    lock = redis_client.lock(name="db_upgrade_lock", timeout=60)
+    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"))

@ -737,6 +748,7 @@ def upgrade_db():

            flask_migrate.upgrade()

+            migration_succeeded = True
            click.echo(click.style("Database migration successful!", fg="green"))

        except Exception as e:
@ -744,7 +756,8 @@ def upgrade_db():
            click.echo(click.style(f"Database migration failed: {e}", fg="red"))
            raise SystemExit(1)
        finally:
-            lock.release()
+            status = "successful" if migration_succeeded else "failed"
+            lock.release_safely(status=status)
    else:
        click.echo("Database migration skipped")

@ -2586,15 +2599,29 @@ def migrate_oss(
@click.option(
    "--start-from",
    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
-    required=True,
+    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=True,
+    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",
@ -2606,8 +2633,10 @@ def migrate_oss(
 def clean_expired_messages(
    batch_size: int,
    graceful_period: int,
-    start_from: datetime.datetime,
-    end_before: datetime.datetime,
+    start_from: datetime.datetime | None,
+    end_before: datetime.datetime | None,
+    from_days_ago: int | None,
+    before_days: int | None,
    dry_run: bool,
 ):
    """
@ -2618,18 +2647,70 @@ def clean_expired_messages(
    start_at = time.perf_counter()

    try:
+        abs_mode = start_from is not None and end_before is not None
+        rel_mode = before_days is not None
+
+        if abs_mode and rel_mode:
+            raise click.UsageError(
+                "Options are mutually exclusive: use either (--start-from,--end-before) "
+                "or (--from-days-ago,--before-days)."
+            )
+
+        if from_days_ago is not None and before_days is None:
+            raise click.UsageError("--from-days-ago must be used together with --before-days.")
+
+        if (start_from is None) ^ (end_before is None):
+            raise click.UsageError("Both --start-from and --end-before are required when using absolute time range.")
+
+        if not abs_mode and not rel_mode:
+            raise click.UsageError(
+                "You must provide either (--start-from,--end-before) or (--before-days [--from-days-ago])."
+            )
+
+        if rel_mode:
+            assert before_days is not None
+            if before_days < 0:
+                raise click.UsageError("--before-days must be >= 0.")
+            if from_days_ago is not None:
+                if from_days_ago < 0:
+                    raise click.UsageError("--from-days-ago must be >= 0.")
+                if from_days_ago <= before_days:
+                    raise click.UsageError("--from-days-ago must be greater than --before-days.")
+
        # Create policy based on billing configuration
        # NOTE: graceful_period will be ignored when billing is disabled.
        policy = create_message_clean_policy(graceful_period_days=graceful_period)

        # Create and run the cleanup service
-        service = MessagesCleanService.from_time_range(
-            policy=policy,
-            start_from=start_from,
-            end_before=end_before,
-            batch_size=batch_size,
-            dry_run=dry_run,
-        )
+        if abs_mode:
+            assert start_from is not None
+            assert end_before is not None
+            service = MessagesCleanService.from_time_range(
+                policy=policy,
+                start_from=start_from,
+                end_before=end_before,
+                batch_size=batch_size,
+                dry_run=dry_run,
+            )
+        elif from_days_ago is None:
+            assert before_days is not None
+            service = MessagesCleanService.from_days(
+                policy=policy,
+                days=before_days,
+                batch_size=batch_size,
+                dry_run=dry_run,
+            )
+        else:
+            assert before_days is not None
+            assert from_days_ago is not None
+            now = naive_utc_now()
+            service = MessagesCleanService.from_time_range(
+                policy=policy,
+                start_from=now - datetime.timedelta(days=from_days_ago),
+                end_before=now - datetime.timedelta(days=before_days),
+                batch_size=batch_size,
+                dry_run=dry_run,
+            )
        stats = service.run()

        end_at = time.perf_counter()
@ -2656,3 +2737,77 @@ def clean_expired_messages(
        raise

    click.echo(click.style("messages cleanup completed.", fg="green"))
+
+
+@click.command("export-app-messages", help="Export messages for an app to JSONL.GZ.")
+@click.option("--app-id", required=True, help="Application ID to export messages for.")
+@click.option(
+    "--start-from",
+    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
+    default=None,
+    help="Optional lower bound (inclusive) for created_at.",
+)
+@click.option(
+    "--end-before",
+    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
+    required=True,
+    help="Upper bound (exclusive) for created_at.",
+)
+@click.option(
+    "--filename",
+    required=True,
+    help="Base filename (relative path). Do not include suffix like .jsonl.gz.",
+)
+@click.option("--use-cloud-storage", is_flag=True, default=False, help="Upload to cloud storage instead of local file.")
+@click.option("--batch-size", default=1000, show_default=True, help="Batch size for cursor pagination.")
+@click.option("--dry-run", is_flag=True, default=False, help="Scan only, print stats without writing any file.")
+def export_app_messages(
+    app_id: str,
+    start_from: datetime.datetime | None,
+    end_before: datetime.datetime,
+    filename: str,
+    use_cloud_storage: bool,
+    batch_size: int,
+    dry_run: bool,
+):
+    if start_from and start_from >= end_before:
+        raise click.UsageError("--start-from must be before --end-before.")
+
+    from services.retention.conversation.message_export_service import AppMessageExportService
+
+    try:
+        validated_filename = AppMessageExportService.validate_export_filename(filename)
+    except ValueError as e:
+        raise click.BadParameter(str(e), param_hint="--filename") from e
+
+    click.echo(click.style(f"export_app_messages: starting export for app {app_id}.", fg="green"))
+    start_at = time.perf_counter()
+
+    try:
+        service = AppMessageExportService(
+            app_id=app_id,
+            end_before=end_before,
+            filename=validated_filename,
+            start_from=start_from,
+            batch_size=batch_size,
+            use_cloud_storage=use_cloud_storage,
+            dry_run=dry_run,
+        )
+        stats = service.run()
+
+        elapsed = time.perf_counter() - start_at
+        click.echo(
+            click.style(
+                f"export_app_messages: completed in {elapsed:.2f}s\n"
+                f"  - Batches: {stats.batches}\n"
+                f"  - Total messages: {stats.total_messages}\n"
+                f"  - Messages with feedback: {stats.messages_with_feedback}\n"
+                f"  - Total feedbacks: {stats.total_feedbacks}",
+                fg="green",
+            )
+        )
+    except Exception as e:
+        elapsed = time.perf_counter() - start_at
+        logger.exception("export_app_messages failed")
+        click.echo(click.style(f"export_app_messages: failed after {elapsed:.2f}s - {e}", fg="red"))
+        raise
--- a/api/configs/enterprise/init.py
+++ b/api/configs/enterprise/init.py
@ -18,3 +18,7 @@ class EnterpriseFeatureConfig(BaseSettings):
        description="Allow customization of the enterprise logo.",
        default=False,
    )
+
+    ENTERPRISE_REQUEST_TIMEOUT: int = Field(
+        ge=1, description="Maximum timeout in seconds for enterprise requests", default=5
+    )
--- a/api/configs/feature/init.py
+++ b/api/configs/feature/init.py
@ -265,6 +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):
    """
@ -1314,6 +1319,9 @@ class WorkflowLogConfig(BaseSettings):
    WORKFLOW_LOG_CLEANUP_BATCH_SIZE: int = Field(
        default=100, description="Batch size for workflow run log cleanup operations"
    )
+    WORKFLOW_LOG_CLEANUP_SPECIFIC_WORKFLOW_IDS: str = Field(
+        default="", description="Comma-separated list of workflow IDs to clean logs for"
+    )


 class SwaggerUIConfig(BaseSettings):
@ -1344,6 +1352,10 @@ class SandboxExpiredRecordsCleanConfig(BaseSettings):
        description="Maximum number of records to process in each batch",
        default=1000,
    )
+    SANDBOX_EXPIRED_RECORDS_CLEAN_BATCH_MAX_INTERVAL: PositiveInt = Field(
+        description="Maximum interval in milliseconds between batches",
+        default=200,
+    )
    SANDBOX_EXPIRED_RECORDS_RETENTION_DAYS: PositiveInt = Field(
        description="Retention days for sandbox expired workflow_run records and message records",
        default=30,
--- a/api/configs/middleware/init.py
+++ b/api/configs/middleware/init.py
@ -259,11 +259,20 @@ class CeleryConfig(DatabaseConfig):
        description="Password of the Redis Sentinel master.",
        default=None,
    )
+
    CELERY_SENTINEL_SOCKET_TIMEOUT: PositiveFloat | None = Field(
        description="Timeout for Redis Sentinel socket operations in seconds.",
        default=0.1,
    )

+    CELERY_TASK_ANNOTATIONS: dict[str, Any] | None = Field(
+        description=(
+            "Annotations for Celery tasks as a JSON mapping of task name -> options "
+            "(for example, rate limits or other task-specific settings)."
+        ),
+        default=None,
+    )
+
    @computed_field
    def CELERY_RESULT_BACKEND(self) -> str | None:
        if self.CELERY_BACKEND in ("database", "rabbitmq"):
--- a/api/configs/middleware/cache/redis_config.py
+++ b/api/configs/middleware/cache/redis_config.py
@ -111,3 +111,8 @@ class RedisConfig(BaseSettings):
        description="Enable client side cache in redis",
        default=False,
    )
+
+    REDIS_MAX_CONNECTIONS: PositiveInt | None = Field(
+        description="Maximum connections in the Redis connection pool (unset for library default)",
+        default=None,
+    )
--- a/api/configs/middleware/cache/redis_pubsub_config.py
+++ b/api/configs/middleware/cache/redis_pubsub_config.py
@ -1,7 +1,7 @@
 from typing import Literal, Protocol
 from urllib.parse import quote_plus, urlunparse

-from pydantic import Field
+from pydantic import AliasChoices, Field
 from pydantic_settings import BaseSettings


@ -23,41 +23,56 @@ class RedisConfigDefaultsMixin:

 class RedisPubSubConfig(BaseSettings, RedisConfigDefaultsMixin):
    """
-    Configuration settings for Redis pub/sub streaming.
+    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(
-        alias="PUBSUB_REDIS_URL",
+        validation_alias=AliasChoices("EVENT_BUS_REDIS_URL", "PUBSUB_REDIS_URL"),
        description=(
-            "Redis connection URL for pub/sub streaming events between API "
-            "and celery worker, defaults to url constructed from "
-            "`REDIS_*` configurations"
+            "Redis connection URL for streaming events between API and celery worker; "
+            "defaults to URL constructed from `REDIS_*` configurations. Also accepts ENV: EVENT_BUS_REDIS_URL."
        ),
        default=None,
    )

    PUBSUB_REDIS_USE_CLUSTERS: bool = Field(
+        validation_alias=AliasChoices("EVENT_BUS_REDIS_CLUSTERS", "PUBSUB_REDIS_USE_CLUSTERS"),
        description=(
-            "Enable Redis Cluster mode for pub/sub streaming. It's highly "
-            "recommended to enable this for large deployments."
+            "Enable Redis Cluster mode for pub/sub or streams transport. Recommended for large deployments. "
+            "Also accepts ENV: EVENT_BUS_REDIS_CLUSTERS."
        ),
        default=False,
    )

-    PUBSUB_REDIS_CHANNEL_TYPE: Literal["pubsub", "sharded"] = Field(
+    PUBSUB_REDIS_CHANNEL_TYPE: Literal["pubsub", "sharded", "streams"] = Field(
+        validation_alias=AliasChoices("EVENT_BUS_REDIS_CHANNEL_TYPE", "PUBSUB_REDIS_CHANNEL_TYPE"),
        description=(
-            "Pub/sub channel type for streaming events. "
-            "Valid options are:\n"
-            "\n"
-            " - pubsub: for normal Pub/Sub\n"
-            " - sharded: for sharded Pub/Sub\n"
-            "\n"
-            "It's highly recommended to use sharded Pub/Sub AND redis cluster "
-            "for large deployments."
+            "Event transport type. Options are:\n\n"
+            " - pubsub: normal Pub/Sub (at-most-once)\n"
+            " - sharded: sharded Pub/Sub (at-most-once)\n"
+            " - streams: Redis Streams (at-least-once, recommended to avoid subscriber races)\n\n"
+            "Note: Before enabling 'streams' in production, estimate your expected event volume and retention needs.\n"
+            "Configure Redis memory limits and stream trimming appropriately (e.g., MAXLEN and key expiry) to reduce\n"
+            "the risk of data loss from Redis auto-eviction under memory pressure.\n"
+            "Also accepts ENV: EVENT_BUS_REDIS_CHANNEL_TYPE."
        ),
        default="pubsub",
    )

+    PUBSUB_STREAMS_RETENTION_SECONDS: int = Field(
+        validation_alias=AliasChoices("EVENT_BUS_STREAMS_RETENTION_SECONDS", "PUBSUB_STREAMS_RETENTION_SECONDS"),
+        description=(
+            "When using 'streams', expire each stream key this many seconds after the last event is published. "
+            "Also accepts ENV: EVENT_BUS_STREAMS_RETENTION_SECONDS."
+        ),
+        default=600,
+    )
+
    def _build_default_pubsub_url(self) -> str:
        defaults = self._redis_defaults()
        if not defaults.REDIS_HOST or not defaults.REDIS_PORT:
--- a/api/configs/middleware/vdb/oceanbase_config.py
+++ b/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,
+    )
--- a/api/constants/languages.py
+++ b/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())
--- a/api/constants/pipeline_templates.json
+++ b/api/constants/pipeline_templates.json
--- a/api/context/init.py
+++ b/api/context/init.py
@ -12,7 +12,7 @@ or any other web framework.
 import contextvars
 from collections.abc import Callable

-from core.workflow.context.execution_context import (
+from dify_graph.context.execution_context import (
    ExecutionContext,
    IExecutionContext,
    NullAppContext,
--- a/api/context/flask_app_context.py
+++ b/api/context/flask_app_context.py
@ -10,8 +10,8 @@ from typing import Any, final

 from flask import Flask, current_app, g

-from core.workflow.context import register_context_capturer
-from core.workflow.context.execution_context import (
+from dify_graph.context import register_context_capturer
+from dify_graph.context.execution_context import (
    AppContext,
    IExecutionContext,
 )
--- a/api/controllers/common/fields.py
+++ b/api/controllers/common/fields.py
@ -4,7 +4,7 @@ from typing import Any, TypeAlias

 from pydantic import BaseModel, ConfigDict, computed_field

-from core.file import helpers as file_helpers
+from dify_graph.file import helpers as file_helpers
 from models.model import IconType

 JSONValue: TypeAlias = str | int | float | bool | None | dict[str, Any] | list[Any]
--- a/api/controllers/console/app/app.py
+++ b/api/controllers/console/app/app.py
@ -23,10 +23,10 @@ from controllers.console.wraps import (
    is_admin_or_owner_required,
    setup_required,
 )
-from core.file import helpers as file_helpers
 from core.ops.ops_trace_manager import OpsTraceManager
 from core.rag.retrieval.retrieval_methods import RetrievalMethod
-from core.workflow.enums import NodeType, WorkflowExecutionStatus
+from dify_graph.enums import NodeType, WorkflowExecutionStatus
+from dify_graph.file import helpers as file_helpers
 from extensions.ext_database import db
 from libs.login import current_account_with_tenant, login_required
 from models import App, DatasetPermissionEnum, Workflow
@ -660,6 +660,19 @@ class AppCopyApi(Resource):
            )
            session.commit()

+            # Inherit web app permission from original app
+            if result.app_id and FeatureService.get_system_features().webapp_auth.enabled:
+                try:
+                    # Get the original app's access mode
+                    original_settings = EnterpriseService.WebAppAuth.get_app_access_mode_by_id(app_model.id)
+                    access_mode = original_settings.access_mode
+                except Exception:
+                    # If original app has no settings (old app), default to public to match fallback behavior
+                    access_mode = "public"
+
+                # Apply the same access mode to the copied app
+                EnterpriseService.WebAppAuth.update_app_access_mode(result.app_id, access_mode)
+
            stmt = select(App).where(App.id == result.app_id)
            app = session.scalar(stmt)

--- a/api/controllers/console/app/audio.py
+++ b/api/controllers/console/app/audio.py
@ -22,7 +22,7 @@ from controllers.console.app.error import (
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
-from core.model_runtime.errors.invoke import InvokeError
+from dify_graph.model_runtime.errors.invoke import InvokeError
 from libs.login import login_required
 from models import App, AppMode
 from services.audio_service import AudioService
--- a/api/controllers/console/app/completion.py
+++ b/api/controllers/console/app/completion.py
@ -26,7 +26,7 @@ from core.errors.error import (
    QuotaExceededError,
 )
 from core.helper.trace_id_helper import get_external_trace_id
-from core.model_runtime.errors.invoke import InvokeError
+from dify_graph.model_runtime.errors.invoke import InvokeError
 from libs import helper
 from libs.helper import uuid_value
 from libs.login import current_user, login_required
--- a/api/controllers/console/app/conversation.py
+++ b/api/controllers/console/app/conversation.py
@ -599,7 +599,12 @@ def _get_conversation(app_model, conversation_id):
    db.session.execute(
        sa.update(Conversation)
        .where(Conversation.id == conversation_id, Conversation.read_at.is_(None))
-        .values(read_at=naive_utc_now(), read_account_id=current_user.id)
+        # Keep updated_at unchanged when only marking a conversation as read.
+        .values(
+            read_at=naive_utc_now(),
+            read_account_id=current_user.id,
+            updated_at=Conversation.updated_at,
+        )
    )
    db.session.commit()
    db.session.refresh(conversation)
--- a/api/controllers/console/app/generator.py
+++ b/api/controllers/console/app/generator.py
@ -18,7 +18,7 @@ from core.helper.code_executor.javascript.javascript_code_provider import Javasc
 from core.helper.code_executor.python3.python3_code_provider import Python3CodeProvider
 from core.llm_generator.entities import RuleCodeGeneratePayload, RuleGeneratePayload, RuleStructuredOutputPayload
 from core.llm_generator.llm_generator import LLMGenerator
-from core.model_runtime.errors.invoke import InvokeError
+from dify_graph.model_runtime.errors.invoke import InvokeError
 from extensions.ext_database import db
 from libs.login import current_account_with_tenant, login_required
 from models import App
--- a/api/controllers/console/app/message.py
+++ b/api/controllers/console/app/message.py
@ -24,7 +24,7 @@ from controllers.console.wraps import (
 )
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
-from core.model_runtime.errors.invoke import InvokeError
+from dify_graph.model_runtime.errors.invoke import InvokeError
 from extensions.ext_database import db
 from fields.raws import FilesContainedField
 from libs.helper import TimestampField, uuid_value
--- a/api/controllers/console/app/workflow.py
+++ b/api/controllers/console/app/workflow.py
@ -20,9 +20,7 @@ from core.app.app_config.features.file_upload.manager import FileUploadConfigMan
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.apps.workflow.app_generator import SKIP_PREPARE_USER_INPUTS_KEY
 from core.app.entities.app_invoke_entities import InvokeFrom
-from core.file.models import File
 from core.helper.trace_id_helper import get_external_trace_id
-from core.model_runtime.utils.encoders import jsonable_encoder
 from core.plugin.impl.exc import PluginInvokeError
 from core.trigger.debug.event_selectors import (
    TriggerDebugEvent,
@ -30,9 +28,12 @@ from core.trigger.debug.event_selectors import (
    create_event_poller,
    select_trigger_debug_events,
 )
-from core.workflow.enums import NodeType
-from core.workflow.graph_engine.manager import GraphEngineManager
+from dify_graph.enums import NodeType
+from dify_graph.file.models import File
+from dify_graph.graph_engine.manager import GraphEngineManager
+from dify_graph.model_runtime.utils.encoders import jsonable_encoder
 from extensions.ext_database import db
+from extensions.ext_redis import redis_client
 from factories import file_factory, variable_factory
 from fields.member_fields import simple_account_fields
 from fields.workflow_fields import workflow_fields, workflow_pagination_fields
@ -740,7 +741,7 @@ class WorkflowTaskStopApi(Resource):
        AppQueueManager.set_stop_flag_no_user_check(task_id)

        # New graph engine command channel mechanism
-        GraphEngineManager.send_stop_command(task_id)
+        GraphEngineManager(redis_client).send_stop_command(task_id)

        return {"result": "success"}

--- a/api/controllers/console/app/workflow_app_log.py
+++ b/api/controllers/console/app/workflow_app_log.py
@ -9,7 +9,7 @@ from sqlalchemy.orm import Session
 from controllers.console import console_ns
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
-from core.workflow.enums import WorkflowExecutionStatus
+from dify_graph.enums import WorkflowExecutionStatus
 from extensions.ext_database import db
 from fields.workflow_app_log_fields import (
    build_workflow_app_log_pagination_model,
--- a/api/controllers/console/app/workflow_draft_variable.py
+++ b/api/controllers/console/app/workflow_draft_variable.py
@ -15,11 +15,11 @@ from controllers.console.app.error import (
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, edit_permission_required, setup_required
 from controllers.web.error import InvalidArgumentError, NotFoundError
-from core.file import helpers as file_helpers
-from core.variables.segment_group import SegmentGroup
-from core.variables.segments import ArrayFileSegment, FileSegment, Segment
-from core.variables.types import SegmentType
-from core.workflow.constants import CONVERSATION_VARIABLE_NODE_ID, SYSTEM_VARIABLE_NODE_ID
+from dify_graph.constants import CONVERSATION_VARIABLE_NODE_ID, SYSTEM_VARIABLE_NODE_ID
+from dify_graph.file import helpers as file_helpers
+from dify_graph.variables.segment_group import SegmentGroup
+from dify_graph.variables.segments import ArrayFileSegment, FileSegment, Segment
+from dify_graph.variables.types import SegmentType
 from extensions.ext_database import db
 from factories.file_factory import build_from_mapping, build_from_mappings
 from factories.variable_factory import build_segment_with_type
@ -112,11 +112,11 @@ _WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS = {
    "is_truncated": fields.Boolean(attribute=lambda model: model.file_id is not None),
 }

-_WORKFLOW_DRAFT_VARIABLE_FIELDS = dict(
-    _WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS,
-    value=fields.Raw(attribute=_serialize_var_value),
-    full_content=fields.Raw(attribute=_serialize_full_content),
-)
+_WORKFLOW_DRAFT_VARIABLE_FIELDS = {
+    **_WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS,
+    "value": fields.Raw(attribute=_serialize_var_value),
+    "full_content": fields.Raw(attribute=_serialize_full_content),
+}

 _WORKFLOW_DRAFT_ENV_VARIABLE_FIELDS = {
    "id": fields.String,
--- a/api/controllers/console/app/workflow_run.py
+++ b/api/controllers/console/app/workflow_run.py
@ -12,8 +12,8 @@ from controllers.console import console_ns
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
 from controllers.web.error import NotFoundError
-from core.workflow.entities.pause_reason import HumanInputRequired
-from core.workflow.enums import WorkflowExecutionStatus
+from dify_graph.entities.pause_reason import HumanInputRequired
+from dify_graph.enums import WorkflowExecutionStatus
 from extensions.ext_database import db
 from fields.end_user_fields import simple_end_user_fields
 from fields.member_fields import simple_account_fields
--- a/api/controllers/console/auth/oauth_server.py
+++ b/api/controllers/console/auth/oauth_server.py
@ -8,7 +8,7 @@ from pydantic import BaseModel
 from werkzeug.exceptions import BadRequest, NotFound

 from controllers.console.wraps import account_initialization_required, setup_required
-from core.model_runtime.utils.encoders import jsonable_encoder
+from dify_graph.model_runtime.utils.encoders import jsonable_encoder
 from libs.login import current_account_with_tenant, login_required
 from models import Account
 from models.model import OAuthProviderApp
--- a/api/controllers/console/datasets/datasets.py
+++ b/api/controllers/console/datasets/datasets.py
@ -25,12 +25,12 @@ from controllers.console.wraps import (
 )
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.indexing_runner import IndexingRunner
-from core.model_runtime.entities.model_entities import ModelType
 from core.provider_manager import ProviderManager
 from core.rag.datasource.vdb.vector_type import VectorType
 from core.rag.extractor.entity.datasource_type import DatasourceType
 from core.rag.extractor.entity.extract_setting import ExtractSetting, NotionInfo, WebsiteInfo
 from core.rag.retrieval.retrieval_methods import RetrievalMethod
+from dify_graph.model_runtime.entities.model_entities import ModelType
 from extensions.ext_database import db
 from fields.app_fields import app_detail_kernel_fields, related_app_list
 from fields.dataset_fields import (
@ -53,7 +53,7 @@ from fields.dataset_fields import (
 from fields.document_fields import document_status_fields
 from libs.login import current_account_with_tenant, login_required
 from models import ApiToken, Dataset, Document, DocumentSegment, UploadFile
-from models.dataset import DatasetPermissionEnum
+from models.dataset import DatasetPermission, DatasetPermissionEnum
 from models.provider_ids import ModelProviderID
 from services.api_token_service import ApiTokenCache
 from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService
@ -119,6 +119,14 @@ def _validate_indexing_technique(value: str | None) -> str | None:
    return value


+def _validate_doc_form(value: str | None) -> str | None:
+    if value is None:
+        return value
+    if value not in Dataset.DOC_FORM_LIST:
+        raise ValueError("Invalid doc_form.")
+    return value
+
+
 class DatasetCreatePayload(BaseModel):
    name: str = Field(..., min_length=1, max_length=40)
    description: str = Field("", max_length=400)
@ -179,6 +187,14 @@ class IndexingEstimatePayload(BaseModel):
            raise ValueError("indexing_technique is required.")
        return result

+    @field_validator("doc_form")
+    @classmethod
+    def validate_doc_form(cls, value: str) -> str:
+        result = _validate_doc_form(value)
+        if result is None:
+            return "text_model"
+        return result
+

 class ConsoleDatasetListQuery(BaseModel):
    page: int = Field(default=1, description="Page number")
@ -323,6 +339,18 @@ class DatasetListApi(Resource):
            model_names.append(f"{embedding_model.model}:{embedding_model.provider.provider}")

        data = cast(list[dict[str, Any]], marshal(datasets, dataset_detail_fields))
+        dataset_ids = [item["id"] for item in data if item.get("permission") == "partial_members"]
+        partial_members_map: dict[str, list[str]] = {}
+        if dataset_ids:
+            permissions = db.session.execute(
+                select(DatasetPermission.dataset_id, DatasetPermission.account_id).where(
+                    DatasetPermission.dataset_id.in_(dataset_ids)
+                )
+            ).all()
+
+            for dataset_id, account_id in permissions:
+                partial_members_map.setdefault(dataset_id, []).append(account_id)
+
        for item in data:
            # convert embedding_model_provider to plugin standard format
            if item["indexing_technique"] == "high_quality" and item["embedding_model_provider"]:
@ -336,8 +364,7 @@ class DatasetListApi(Resource):
                item["embedding_available"] = True

            if item.get("permission") == "partial_members":
-                part_users_list = DatasetPermissionService.get_dataset_partial_member_list(item["id"])
-                item.update({"partial_member_list": part_users_list})
+                item.update({"partial_member_list": partial_members_map.get(item["id"], [])})
            else:
                item.update({"partial_member_list": []})

@ -780,7 +807,7 @@ class DatasetApiKeyApi(Resource):
            console_ns.abort(
                400,
                message=f"Cannot create more than {self.max_keys} API keys for this resource type.",
-                code="max_keys_exceeded",
+                custom="max_keys_exceeded",
            )

        key = ApiToken.generate_api_key(self.token_prefix, 24)
--- a/api/controllers/console/datasets/datasets_document.py
+++ b/api/controllers/console/datasets/datasets_document.py
@ -24,11 +24,11 @@ from core.errors.error import (
 )
 from core.indexing_runner import IndexingRunner
 from core.model_manager import ModelManager
-from core.model_runtime.entities.model_entities import ModelType
-from core.model_runtime.errors.invoke import InvokeAuthorizationError
 from core.plugin.impl.exc import PluginDaemonClientSideError
 from core.rag.extractor.entity.datasource_type import DatasourceType
 from core.rag.extractor.entity.extract_setting import ExtractSetting, NotionInfo, WebsiteInfo
+from dify_graph.model_runtime.entities.model_entities import ModelType
+from dify_graph.model_runtime.errors.invoke import InvokeAuthorizationError
 from extensions.ext_database import db
 from fields.dataset_fields import dataset_fields
 from fields.document_fields import (
--- a/api/controllers/console/datasets/datasets_segments.py
+++ b/api/controllers/console/datasets/datasets_segments.py
@ -26,7 +26,7 @@ from controllers.console.wraps import (
 )
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.model_manager import ModelManager
-from core.model_runtime.entities.model_entities import ModelType
+from dify_graph.model_runtime.entities.model_entities import ModelType
 from extensions.ext_database import db
 from extensions.ext_redis import redis_client
 from fields.segment_fields import child_chunk_fields, segment_fields
--- a/api/controllers/console/datasets/hit_testing_base.py
+++ b/api/controllers/console/datasets/hit_testing_base.py
@ -19,7 +19,7 @@ from core.errors.error import (
    ProviderTokenNotInitError,
    QuotaExceededError,
 )
-from core.model_runtime.errors.invoke import InvokeError
+from dify_graph.model_runtime.errors.invoke import InvokeError
 from fields.hit_testing_fields import hit_testing_record_fields
 from libs.login import current_user
 from models.account import Account
--- a/api/controllers/console/datasets/rag_pipeline/datasource_auth.py
+++ b/api/controllers/console/datasets/rag_pipeline/datasource_auth.py
@ -9,9 +9,9 @@ from configs import dify_config
 from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
 from controllers.console.wraps import account_initialization_required, edit_permission_required, setup_required
-from core.model_runtime.errors.validate import CredentialsValidateFailedError
-from core.model_runtime.utils.encoders import jsonable_encoder
 from core.plugin.impl.oauth import OAuthHandler
+from dify_graph.model_runtime.errors.validate import CredentialsValidateFailedError
+from dify_graph.model_runtime.utils.encoders import jsonable_encoder
 from libs.login import current_account_with_tenant, login_required
 from models.provider_ids import DatasourceProviderID
 from services.datasource_provider_service import DatasourceProviderService
--- a/api/controllers/console/datasets/rag_pipeline/rag_pipeline_draft_variable.py
+++ b/api/controllers/console/datasets/rag_pipeline/rag_pipeline_draft_variable.py
@ -21,8 +21,8 @@ from controllers.console.app.workflow_draft_variable import (
 from controllers.console.datasets.wraps import get_rag_pipeline
 from controllers.console.wraps import account_initialization_required, setup_required
 from controllers.web.error import InvalidArgumentError, NotFoundError
-from core.variables.types import SegmentType
-from core.workflow.constants import CONVERSATION_VARIABLE_NODE_ID, SYSTEM_VARIABLE_NODE_ID
+from dify_graph.constants import CONVERSATION_VARIABLE_NODE_ID, SYSTEM_VARIABLE_NODE_ID
+from dify_graph.variables.types import SegmentType
 from extensions.ext_database import db
 from factories.file_factory import build_from_mapping, build_from_mappings
 from factories.variable_factory import build_segment_with_type
--- a/api/controllers/console/datasets/rag_pipeline/rag_pipeline_workflow.py
+++ b/api/controllers/console/datasets/rag_pipeline/rag_pipeline_workflow.py
@ -33,7 +33,7 @@ from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpErr
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.apps.pipeline.pipeline_generator import PipelineGenerator
 from core.app.entities.app_invoke_entities import InvokeFrom
-from core.model_runtime.utils.encoders import jsonable_encoder
+from dify_graph.model_runtime.utils.encoders import jsonable_encoder
 from extensions.ext_database import db
 from factories import variable_factory
 from libs import helper
--- a/api/controllers/console/explore/audio.py
+++ b/api/controllers/console/explore/audio.py
@ -19,7 +19,7 @@ from controllers.console.app.error import (
 )
 from controllers.console.explore.wraps import InstalledAppResource
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
-from core.model_runtime.errors.invoke import InvokeError
+from dify_graph.model_runtime.errors.invoke import InvokeError
 from services.audio_service import AudioService
 from services.errors.audio import (
    AudioTooLargeServiceError,
--- a/api/controllers/console/explore/completion.py
+++ b/api/controllers/console/explore/completion.py
@ -24,7 +24,7 @@ from core.errors.error import (
    ProviderTokenNotInitError,
    QuotaExceededError,
 )
-from core.model_runtime.errors.invoke import InvokeError
+from dify_graph.model_runtime.errors.invoke import InvokeError
 from extensions.ext_database import db
 from libs import helper
 from libs.datetime_utils import naive_utc_now
--- a/api/controllers/console/explore/message.py
+++ b/api/controllers/console/explore/message.py
@ -21,7 +21,7 @@ from controllers.console.explore.error import (
 from controllers.console.explore.wraps import InstalledAppResource
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
-from core.model_runtime.errors.invoke import InvokeError
+from dify_graph.model_runtime.errors.invoke import InvokeError
 from fields.conversation_fields import ResultResponse
 from fields.message_fields import MessageInfiniteScrollPagination, MessageListItem, SuggestedQuestionsResponse
 from libs import helper
--- a/api/controllers/console/explore/parameter.py
+++ b/api/controllers/console/explore/parameter.py
@ -1,3 +1,5 @@
+from typing import Any, cast
+
 from controllers.common import fields
 from controllers.console import console_ns
 from controllers.console.app.error import AppUnavailableError
@ -23,14 +25,14 @@ class AppParameterApi(InstalledAppResource):
            if workflow is None:
                raise AppUnavailableError()

-            features_dict = workflow.features_dict
+            features_dict: dict[str, Any] = workflow.features_dict
            user_input_form = workflow.user_input_form(to_old_structure=True)
        else:
            app_model_config = app_model.app_model_config
            if app_model_config is None:
                raise AppUnavailableError()

-            features_dict = app_model_config.to_dict()
+            features_dict = cast(dict[str, Any], app_model_config.to_dict())

            user_input_form = features_dict.get("user_input_form", [])

--- a/api/controllers/console/explore/trial.py
+++ b/api/controllers/console/explore/trial.py
@ -10,7 +10,7 @@ import services
 from controllers.common.fields import Parameters as ParametersResponse
 from controllers.common.fields import Site as SiteResponse
 from controllers.common.schema import get_or_create_model
-from controllers.console import api, console_ns
+from controllers.console import console_ns
 from controllers.console.app.error import (
    AppUnavailableError,
    AudioTooLargeError,
@ -41,9 +41,10 @@ from core.errors.error import (
    ProviderTokenNotInitError,
    QuotaExceededError,
 )
-from core.model_runtime.errors.invoke import InvokeError
-from core.workflow.graph_engine.manager import GraphEngineManager
+from dify_graph.graph_engine.manager import GraphEngineManager
+from dify_graph.model_runtime.errors.invoke import InvokeError
 from extensions.ext_database import db
+from extensions.ext_redis import redis_client
 from fields.app_fields import (
    app_detail_fields_with_site,
    deleted_tool_fields,
@ -225,7 +226,7 @@ class TrialAppWorkflowTaskStopApi(TrialAppResource):
        AppQueueManager.set_stop_flag_no_user_check(task_id)

        # New graph engine command channel mechanism
-        GraphEngineManager.send_stop_command(task_id)
+        GraphEngineManager(redis_client).send_stop_command(task_id)

        return {"result": "success"}

@ -469,7 +470,7 @@ class TrialSitApi(Resource):
    """Resource for trial app sites."""

    @trial_feature_enable
-    @get_app_model_with_trial
+    @get_app_model_with_trial(None)
    def get(self, app_model):
        """Retrieve app site info.

@ -491,7 +492,7 @@ class TrialAppParameterApi(Resource):
    """Resource for app variables."""

    @trial_feature_enable
-    @get_app_model_with_trial
+    @get_app_model_with_trial(None)
    def get(self, app_model):
        """Retrieve app parameters."""

@ -520,7 +521,7 @@ class TrialAppParameterApi(Resource):

 class AppApi(Resource):
    @trial_feature_enable
-    @get_app_model_with_trial
+    @get_app_model_with_trial(None)
    @marshal_with(app_detail_with_site_model)
    def get(self, app_model):
        """Get app detail"""
@ -533,7 +534,7 @@ class AppApi(Resource):

 class AppWorkflowApi(Resource):
    @trial_feature_enable
-    @get_app_model_with_trial
+    @get_app_model_with_trial(None)
    @marshal_with(workflow_model)
    def get(self, app_model):
        """Get workflow detail"""
@ -552,7 +553,7 @@ class AppWorkflowApi(Resource):

 class DatasetListApi(Resource):
    @trial_feature_enable
-    @get_app_model_with_trial
+    @get_app_model_with_trial(None)
    def get(self, app_model):
        page = request.args.get("page", default=1, type=int)
        limit = request.args.get("limit", default=20, type=int)
@ -570,27 +571,31 @@ class DatasetListApi(Resource):
        return response


-api.add_resource(TrialChatApi, "/trial-apps/<uuid:app_id>/chat-messages", endpoint="trial_app_chat_completion")
+console_ns.add_resource(TrialChatApi, "/trial-apps/<uuid:app_id>/chat-messages", endpoint="trial_app_chat_completion")

-api.add_resource(
+console_ns.add_resource(
    TrialMessageSuggestedQuestionApi,
    "/trial-apps/<uuid:app_id>/messages/<uuid:message_id>/suggested-questions",
    endpoint="trial_app_suggested_question",
 )

-api.add_resource(TrialChatAudioApi, "/trial-apps/<uuid:app_id>/audio-to-text", endpoint="trial_app_audio")
-api.add_resource(TrialChatTextApi, "/trial-apps/<uuid:app_id>/text-to-audio", endpoint="trial_app_text")
+console_ns.add_resource(TrialChatAudioApi, "/trial-apps/<uuid:app_id>/audio-to-text", endpoint="trial_app_audio")
+console_ns.add_resource(TrialChatTextApi, "/trial-apps/<uuid:app_id>/text-to-audio", endpoint="trial_app_text")

-api.add_resource(TrialCompletionApi, "/trial-apps/<uuid:app_id>/completion-messages", endpoint="trial_app_completion")
+console_ns.add_resource(
+    TrialCompletionApi, "/trial-apps/<uuid:app_id>/completion-messages", endpoint="trial_app_completion"
+)

-api.add_resource(TrialSitApi, "/trial-apps/<uuid:app_id>/site")
+console_ns.add_resource(TrialSitApi, "/trial-apps/<uuid:app_id>/site")

-api.add_resource(TrialAppParameterApi, "/trial-apps/<uuid:app_id>/parameters", endpoint="trial_app_parameters")
+console_ns.add_resource(TrialAppParameterApi, "/trial-apps/<uuid:app_id>/parameters", endpoint="trial_app_parameters")

-api.add_resource(AppApi, "/trial-apps/<uuid:app_id>", endpoint="trial_app")
+console_ns.add_resource(AppApi, "/trial-apps/<uuid:app_id>", endpoint="trial_app")

-api.add_resource(TrialAppWorkflowRunApi, "/trial-apps/<uuid:app_id>/workflows/run", endpoint="trial_app_workflow_run")
-api.add_resource(TrialAppWorkflowTaskStopApi, "/trial-apps/<uuid:app_id>/workflows/tasks/<string:task_id>/stop")
+console_ns.add_resource(
+    TrialAppWorkflowRunApi, "/trial-apps/<uuid:app_id>/workflows/run", endpoint="trial_app_workflow_run"
+)
+console_ns.add_resource(TrialAppWorkflowTaskStopApi, "/trial-apps/<uuid:app_id>/workflows/tasks/<string:task_id>/stop")

-api.add_resource(AppWorkflowApi, "/trial-apps/<uuid:app_id>/workflows", endpoint="trial_app_workflow")
-api.add_resource(DatasetListApi, "/trial-apps/<uuid:app_id>/datasets", endpoint="trial_app_datasets")
+console_ns.add_resource(AppWorkflowApi, "/trial-apps/<uuid:app_id>/workflows", endpoint="trial_app_workflow")
+console_ns.add_resource(DatasetListApi, "/trial-apps/<uuid:app_id>/datasets", endpoint="trial_app_datasets")
--- a/api/controllers/console/explore/workflow.py
+++ b/api/controllers/console/explore/workflow.py
@ -21,8 +21,9 @@ from core.errors.error import (
    ProviderTokenNotInitError,
    QuotaExceededError,
 )
-from core.model_runtime.errors.invoke import InvokeError
-from core.workflow.graph_engine.manager import GraphEngineManager
+from dify_graph.graph_engine.manager import GraphEngineManager
+from dify_graph.model_runtime.errors.invoke import InvokeError
+from extensions.ext_redis import redis_client
 from libs import helper
 from libs.login import current_account_with_tenant
 from models.model import AppMode, InstalledApp
@ -100,6 +101,6 @@ class InstalledAppWorkflowTaskStopApi(InstalledAppResource):
        AppQueueManager.set_stop_flag_no_user_check(task_id)

        # New graph engine command channel mechanism
-        GraphEngineManager.send_stop_command(task_id)
+        GraphEngineManager(redis_client).send_stop_command(task_id)

        return {"result": "success"}
--- a/api/controllers/console/explore/wraps.py
+++ b/api/controllers/console/explore/wraps.py
@ -105,9 +105,9 @@ def trial_app_required(view: Callable[Concatenate[App, P], R] | None = None):
    return decorator


-def trial_feature_enable(view: Callable[..., R]) -> Callable[..., R]:
+def trial_feature_enable(view: Callable[P, R]):
    @wraps(view)
-    def decorated(*args, **kwargs):
+    def decorated(*args: P.args, **kwargs: P.kwargs):
        features = FeatureService.get_system_features()
        if not features.enable_trial_app:
            abort(403, "Trial app feature is not enabled.")
@ -116,9 +116,9 @@ def trial_feature_enable(view: Callable[..., R]) -> Callable[..., R]:
    return decorated


-def explore_banner_enabled(view: Callable[..., R]) -> Callable[..., R]:
+def explore_banner_enabled(view: Callable[P, R]):
    @wraps(view)
-    def decorated(*args, **kwargs):
+    def decorated(*args: P.args, **kwargs: P.kwargs):
        features = FeatureService.get_system_features()
        if not features.enable_explore_banner:
            abort(403, "Explore banner feature is not enabled.")
--- a/api/controllers/console/remote_files.py
+++ b/api/controllers/console/remote_files.py
@ -1,6 +1,7 @@
 import urllib.parse

 import httpx
+from flask_restx import Resource
 from pydantic import BaseModel, Field

 import services
@ -10,12 +11,12 @@ from controllers.common.errors import (
    RemoteFileUploadError,
    UnsupportedFileTypeError,
 )
-from controllers.fastopenapi import console_router
-from core.file import helpers as file_helpers
+from controllers.console import console_ns
 from core.helper import ssrf_proxy
+from dify_graph.file import helpers as file_helpers
 from extensions.ext_database import db
 from fields.file_fields import FileWithSignedUrl, RemoteFileInfo
-from libs.login import current_account_with_tenant
+from libs.login import current_account_with_tenant, login_required
 from services.file_service import FileService


@ -23,69 +24,73 @@ class RemoteFileUploadPayload(BaseModel):
    url: str = Field(..., description="URL to fetch")


-@console_router.get(
-    "/remote-files/<path:url>",
-    response_model=RemoteFileInfo,
-    tags=["console"],
-)
-def get_remote_file_info(url: str) -> RemoteFileInfo:
-    decoded_url = urllib.parse.unquote(url)
-    resp = ssrf_proxy.head(decoded_url)
-    if resp.status_code != httpx.codes.OK:
-        resp = ssrf_proxy.get(decoded_url, timeout=3)
-    resp.raise_for_status()
-    return RemoteFileInfo(
-        file_type=resp.headers.get("Content-Type", "application/octet-stream"),
-        file_length=int(resp.headers.get("Content-Length", 0)),
-    )
-
-
-@console_router.post(
-    "/remote-files/upload",
-    response_model=FileWithSignedUrl,
-    tags=["console"],
-    status_code=201,
-)
-def upload_remote_file(payload: RemoteFileUploadPayload) -> FileWithSignedUrl:
-    url = payload.url
-
-    try:
-        resp = ssrf_proxy.head(url=url)
+@console_ns.route("/remote-files/<path:url>")
+class GetRemoteFileInfo(Resource):
+    @login_required
+    def get(self, url: str):
+        decoded_url = urllib.parse.unquote(url)
+        resp = ssrf_proxy.head(decoded_url)
        if resp.status_code != httpx.codes.OK:
-            resp = ssrf_proxy.get(url=url, timeout=3, follow_redirects=True)
-        if resp.status_code != httpx.codes.OK:
-            raise RemoteFileUploadError(f"Failed to fetch file from {url}: {resp.text}")
-    except httpx.RequestError as e:
-        raise RemoteFileUploadError(f"Failed to fetch file from {url}: {str(e)}")
+            resp = ssrf_proxy.get(decoded_url, timeout=3)
+        resp.raise_for_status()
+        return RemoteFileInfo(
+            file_type=resp.headers.get("Content-Type", "application/octet-stream"),
+            file_length=int(resp.headers.get("Content-Length", 0)),
+        ).model_dump(mode="json")

-    file_info = helpers.guess_file_info_from_response(resp)

-    if not FileService.is_file_size_within_limit(extension=file_info.extension, file_size=file_info.size):
-        raise FileTooLargeError
+@console_ns.route("/remote-files/upload")
+class RemoteFileUpload(Resource):
+    @login_required
+    def post(self):
+        payload = RemoteFileUploadPayload.model_validate(console_ns.payload)
+        url = payload.url

-    content = resp.content if resp.request.method == "GET" else ssrf_proxy.get(url).content
+        # Try to fetch remote file metadata/content first
+        try:
+            resp = ssrf_proxy.head(url=url)
+            if resp.status_code != httpx.codes.OK:
+                resp = ssrf_proxy.get(url=url, timeout=3, follow_redirects=True)
+            if resp.status_code != httpx.codes.OK:
+                # Normalize into a user-friendly error message expected by tests
+                raise RemoteFileUploadError(f"Failed to fetch file from {url}: {resp.text}")
+        except httpx.RequestError as e:
+            raise RemoteFileUploadError(f"Failed to fetch file from {url}: {str(e)}")

-    try:
-        user, _ = current_account_with_tenant()
-        upload_file = FileService(db.engine).upload_file(
-            filename=file_info.filename,
-            content=content,
-            mimetype=file_info.mimetype,
-            user=user,
-            source_url=url,
+        file_info = helpers.guess_file_info_from_response(resp)
+
+        # Enforce file size limit with 400 (Bad Request) per tests' expectation
+        if not FileService.is_file_size_within_limit(extension=file_info.extension, file_size=file_info.size):
+            raise FileTooLargeError()
+
+        # Load content if needed
+        content = resp.content if resp.request.method == "GET" else ssrf_proxy.get(url).content
+
+        try:
+            user, _ = current_account_with_tenant()
+            upload_file = FileService(db.engine).upload_file(
+                filename=file_info.filename,
+                content=content,
+                mimetype=file_info.mimetype,
+                user=user,
+                source_url=url,
+            )
+        except services.errors.file.FileTooLargeError as file_too_large_error:
+            raise FileTooLargeError(file_too_large_error.description)
+        except services.errors.file.UnsupportedFileTypeError:
+            raise UnsupportedFileTypeError()
+
+        # Success: return created resource with 201 status
+        return (
+            FileWithSignedUrl(
+                id=upload_file.id,
+                name=upload_file.name,
+                size=upload_file.size,
+                extension=upload_file.extension,
+                url=file_helpers.get_signed_file_url(upload_file_id=upload_file.id),
+                mime_type=upload_file.mime_type,
+                created_by=upload_file.created_by,
+                created_at=int(upload_file.created_at.timestamp()),
+            ).model_dump(mode="json"),
+            201,
        )
-    except services.errors.file.FileTooLargeError as file_too_large_error:
-        raise FileTooLargeError(file_too_large_error.description)
-    except services.errors.file.UnsupportedFileTypeError:
-        raise UnsupportedFileTypeError()
-
-    return FileWithSignedUrl(
-        id=upload_file.id,
-        name=upload_file.name,
-        size=upload_file.size,
-        extension=upload_file.extension,
-        url=file_helpers.get_signed_file_url(upload_file_id=upload_file.id),
-        mime_type=upload_file.mime_type,
-        created_by=upload_file.created_by,
-        created_at=int(upload_file.created_at.timestamp()),
-    )
--- a/api/controllers/console/setup.py
+++ b/api/controllers/console/setup.py
@ -42,7 +42,15 @@ class SetupResponse(BaseModel):
    tags=["console"],
 )
 def get_setup_status_api() -> SetupStatusResponse:
-    """Get system setup status."""
+    """Get system setup status.
+
+    NOTE: This endpoint is unauthenticated by design.
+
+    During first-time bootstrap there is no admin account yet, so frontend initialization must be
+    able to query setup progress before any login flow exists.
+
+    Only bootstrap-safe status information should be returned by this endpoint.
+    """
    if dify_config.EDITION == "SELF_HOSTED":
        setup_status = get_setup_status()
        if setup_status and not isinstance(setup_status, bool):
@ -61,7 +69,12 @@ def get_setup_status_api() -> SetupStatusResponse:
 )
@only_edition_self_hosted
 def setup_system(payload: SetupRequestPayload) -> SetupResponse:
-    """Initialize system setup with admin account."""
+    """Initialize system setup with admin account.
+
+    NOTE: This endpoint is unauthenticated by design for first-time bootstrap.
+    Access is restricted by deployment mode (`SELF_HOSTED`), one-time setup guards,
+    and init-password validation rather than user session authentication.
+    """
    if get_setup_status():
        raise AlreadySetupError()

--- a/api/controllers/console/workspace/agent_providers.py
+++ b/api/controllers/console/workspace/agent_providers.py
@ -2,7 +2,7 @@ from flask_restx import Resource, fields

 from controllers.console import console_ns
 from controllers.console.wraps import account_initialization_required, setup_required
-from core.model_runtime.utils.encoders import jsonable_encoder
+from dify_graph.model_runtime.utils.encoders import jsonable_encoder
 from libs.login import current_account_with_tenant, login_required
 from services.agent_service import AgentService

--- a/api/controllers/console/workspace/endpoint.py
+++ b/api/controllers/console/workspace/endpoint.py
@ -7,8 +7,8 @@ from pydantic import BaseModel, Field
 from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
 from controllers.console.wraps import account_initialization_required, is_admin_or_owner_required, setup_required
-from core.model_runtime.utils.encoders import jsonable_encoder
 from core.plugin.impl.exc import PluginPermissionDeniedError
+from dify_graph.model_runtime.utils.encoders import jsonable_encoder
 from libs.login import current_account_with_tenant, login_required
 from services.plugin.endpoint_service import EndpointService

--- a/api/controllers/console/workspace/load_balancing_config.py
+++ b/api/controllers/console/workspace/load_balancing_config.py
@ -5,8 +5,8 @@ from werkzeug.exceptions import Forbidden
 from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
 from controllers.console.wraps import account_initialization_required, setup_required
-from core.model_runtime.entities.model_entities import ModelType
-from core.model_runtime.errors.validate import CredentialsValidateFailedError
+from dify_graph.model_runtime.entities.model_entities import ModelType
+from dify_graph.model_runtime.errors.validate import CredentialsValidateFailedError
 from libs.login import current_account_with_tenant, login_required
 from models import TenantAccountRole
 from services.model_load_balancing_service import ModelLoadBalancingService
--- a/api/controllers/console/workspace/model_providers.py
+++ b/api/controllers/console/workspace/model_providers.py
@ -7,9 +7,9 @@ from pydantic import BaseModel, Field, field_validator

 from controllers.console import console_ns
 from controllers.console.wraps import account_initialization_required, is_admin_or_owner_required, setup_required
-from core.model_runtime.entities.model_entities import ModelType
-from core.model_runtime.errors.validate import CredentialsValidateFailedError
-from core.model_runtime.utils.encoders import jsonable_encoder
+from dify_graph.model_runtime.entities.model_entities import ModelType
+from dify_graph.model_runtime.errors.validate import CredentialsValidateFailedError
+from dify_graph.model_runtime.utils.encoders import jsonable_encoder
 from libs.helper import uuid_value
 from libs.login import current_account_with_tenant, login_required
 from services.billing_service import BillingService
--- a/api/controllers/console/workspace/models.py
+++ b/api/controllers/console/workspace/models.py
@ -8,9 +8,9 @@ from pydantic import BaseModel, Field, field_validator
 from controllers.common.schema import register_enum_models, register_schema_models
 from controllers.console import console_ns
 from controllers.console.wraps import account_initialization_required, is_admin_or_owner_required, setup_required
-from core.model_runtime.entities.model_entities import ModelType
-from core.model_runtime.errors.validate import CredentialsValidateFailedError
-from core.model_runtime.utils.encoders import jsonable_encoder
+from dify_graph.model_runtime.entities.model_entities import ModelType
+from dify_graph.model_runtime.errors.validate import CredentialsValidateFailedError
+from dify_graph.model_runtime.utils.encoders import jsonable_encoder
 from libs.helper import uuid_value
 from libs.login import current_account_with_tenant, login_required
 from services.model_load_balancing_service import ModelLoadBalancingService
--- a/api/controllers/console/workspace/plugin.py
+++ b/api/controllers/console/workspace/plugin.py
@ -12,8 +12,8 @@ from controllers.common.schema import register_enum_models, register_schema_mode
 from controllers.console import console_ns
 from controllers.console.workspace import plugin_permission_required
 from controllers.console.wraps import account_initialization_required, is_admin_or_owner_required, setup_required
-from core.model_runtime.utils.encoders import jsonable_encoder
 from core.plugin.impl.exc import PluginDaemonClientSideError
+from dify_graph.model_runtime.utils.encoders import jsonable_encoder
 from libs.login import current_account_with_tenant, login_required
 from models.account import TenantPluginAutoUpgradeStrategy, TenantPluginPermission
 from services.plugin.plugin_auto_upgrade_service import PluginAutoUpgradeService
--- a/api/controllers/console/workspace/tool_providers.py
+++ b/api/controllers/console/workspace/tool_providers.py
@ -23,10 +23,10 @@ from core.entities.mcp_provider import MCPAuthentication, MCPConfiguration
 from core.mcp.auth.auth_flow import auth, handle_callback
 from core.mcp.error import MCPAuthError, MCPError, MCPRefreshTokenError
 from core.mcp.mcp_client import MCPClient
-from core.model_runtime.utils.encoders import jsonable_encoder
 from core.plugin.entities.plugin_daemon import CredentialType
 from core.plugin.impl.oauth import OAuthHandler
 from core.tools.entities.tool_entities import ApiProviderSchemaType, WorkflowToolParameterConfiguration
+from dify_graph.model_runtime.utils.encoders import jsonable_encoder
 from extensions.ext_database import db
 from libs.helper import alphanumeric, uuid_value
 from libs.login import current_account_with_tenant, login_required
--- a/api/controllers/console/workspace/trigger_providers.py
+++ b/api/controllers/console/workspace/trigger_providers.py
@ -10,11 +10,11 @@ from werkzeug.exceptions import BadRequest, Forbidden
 from configs import dify_config
 from controllers.common.schema import register_schema_models
 from controllers.web.error import NotFoundError
-from core.model_runtime.utils.encoders import jsonable_encoder
 from core.plugin.entities.plugin_daemon import CredentialType
 from core.plugin.impl.oauth import OAuthHandler
 from core.trigger.entities.entities import SubscriptionBuilderUpdater
 from core.trigger.trigger_manager import TriggerManager
+from dify_graph.model_runtime.utils.encoders import jsonable_encoder
 from extensions.ext_database import db
 from libs.login import current_user, login_required
 from models.account import Account
--- a/api/controllers/console/wraps.py
+++ b/api/controllers/console/wraps.py
@ -36,9 +36,9 @@ ERROR_MSG_INVALID_ENCRYPTED_DATA = "Invalid encrypted data"
 ERROR_MSG_INVALID_ENCRYPTED_CODE = "Invalid encrypted code"


-def account_initialization_required(view: Callable[P, R]):
+def account_initialization_required(view: Callable[P, R]) -> Callable[P, R]:
    @wraps(view)
-    def decorated(*args: P.args, **kwargs: P.kwargs):
+    def decorated(*args: P.args, **kwargs: P.kwargs) -> R:
        # check account initialization
        current_user, _ = current_account_with_tenant()
        if current_user.status == AccountStatus.UNINITIALIZED:
@ -214,9 +214,9 @@ def cloud_utm_record(view: Callable[P, R]):
    return decorated


-def setup_required(view: Callable[P, R]):
+def setup_required(view: Callable[P, R]) -> Callable[P, R]:
    @wraps(view)
-    def decorated(*args: P.args, **kwargs: P.kwargs):
+    def decorated(*args: P.args, **kwargs: P.kwargs) -> R:
        # check setup
        if (
            dify_config.EDITION == "SELF_HOSTED"
--- a/api/controllers/files/image_preview.py
+++ b/api/controllers/files/image_preview.py
@ -137,7 +137,7 @@ class FilePreviewApi(Resource):
        if args.as_attachment:
            encoded_filename = quote(upload_file.name)
            response.headers["Content-Disposition"] = f"attachment; filename*=UTF-8''{encoded_filename}"
-            response.headers["Content-Type"] = "application/octet-stream"
+        response.headers["Content-Type"] = "application/octet-stream"

        enforce_download_for_html(
            response,
--- a/api/controllers/files/tool_files.py
+++ b/api/controllers/files/tool_files.py
@ -10,7 +10,6 @@ from controllers.common.file_response import enforce_download_for_html
 from controllers.files import files_ns
 from core.tools.signature import verify_tool_file_signature
 from core.tools.tool_file_manager import ToolFileManager
-from extensions.ext_database import db as global_db

 DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"

@ -57,13 +56,17 @@ class ToolFileApi(Resource):
            raise Forbidden("Invalid request.")

        try:
-            tool_file_manager = ToolFileManager(engine=global_db.engine)
+            tool_file_manager = ToolFileManager()
            stream, tool_file = tool_file_manager.get_file_generator_by_tool_file_id(
                file_id,
            )

            if not stream or not tool_file:
                raise NotFound("file is not found")
+
+        except NotFound:
+            raise
+
        except Exception:
            raise UnsupportedFileTypeError()

--- a/api/controllers/files/upload.py
+++ b/api/controllers/files/upload.py
@ -7,8 +7,8 @@ from pydantic import BaseModel, Field
 from werkzeug.exceptions import Forbidden

 import services
-from core.file.helpers import verify_plugin_file_signature
 from core.tools.tool_file_manager import ToolFileManager
+from dify_graph.file.helpers import verify_plugin_file_signature
 from fields.file_fields import FileResponse

 from ..common.errors import (
--- a/api/controllers/inner_api/plugin/plugin.py
+++ b/api/controllers/inner_api/plugin/plugin.py
@ -4,8 +4,6 @@ from controllers.console.wraps import setup_required
 from controllers.inner_api import inner_api_ns
 from controllers.inner_api.plugin.wraps import get_user_tenant, plugin_data
 from controllers.inner_api.wraps import plugin_inner_api_only
-from core.file.helpers import get_signed_file_url_for_plugin
-from core.model_runtime.utils.encoders import jsonable_encoder
 from core.plugin.backwards_invocation.app import PluginAppBackwardsInvocation
 from core.plugin.backwards_invocation.base import BaseBackwardsInvocationResponse
 from core.plugin.backwards_invocation.encrypt import PluginEncrypter
@ -30,6 +28,8 @@ from core.plugin.entities.request import (
    RequestRequestUploadFile,
 )
 from core.tools.entities.tool_entities import ToolProviderType
+from dify_graph.file.helpers import get_signed_file_url_for_plugin
+from dify_graph.model_runtime.utils.encoders import jsonable_encoder
 from libs.helper import length_prefixed_response
 from models import Account, Tenant
 from models.model import EndUser
--- a/api/controllers/mcp/mcp.py
+++ b/api/controllers/mcp/mcp.py
@ -8,9 +8,9 @@ from sqlalchemy.orm import Session
 from controllers.common.schema import register_schema_model
 from controllers.console.app.mcp_server import AppMCPServerStatus
 from controllers.mcp import mcp_ns
-from core.app.app_config.entities import VariableEntity
 from core.mcp import types as mcp_types
 from core.mcp.server.streamable_http import handle_mcp_request
+from dify_graph.variables.input_entities import VariableEntity
 from extensions.ext_database import db
 from libs import helper
 from models.model import App, AppMCPServer, AppMode, EndUser
--- a/api/controllers/service_api/init.py
+++ b/api/controllers/service_api/init.py
@ -34,6 +34,7 @@ from .dataset import (
    metadata,
    segment,
 )
+from .dataset.rag_pipeline import rag_pipeline_workflow
 from .end_user import end_user
 from .workspace import models

@ -53,6 +54,7 @@ __all__ = [
    "message",
    "metadata",
    "models",
+    "rag_pipeline_workflow",
    "segment",
    "site",
    "workflow",
--- a/Show More
+++ b/Show More