docs(llm): trim first-token timeout comments to the essentials

Keep only the non-obvious constraints (unit contract, daemon no-keep-alive
assumption, ContextVar fail-open threading, replace-not-narrow intent) and
cut prose that restates the code. The module docstring in
first_token_timeout.py stays the single canonical description of the path.

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

@@ -9,11 +9,12 @@ Use this skill for Vitest work under `web/` and `packages/dify-ui/`. Do not use
 
 ## Required Source
 
-Before writing, changing, or reviewing frontend tests, read `web/docs/test.md` completely. It is the single source of truth. This skill provides an execution checklist and must not redefine or extend that policy.
+Before writing, changing, or reviewing frontend tests, read `web/docs/test.md` completely. It is the single source of truth. This skill defines the execution workflow and must not add requirements that conflict with or duplicate that guide.
 
 ## Workflow
 
 1. Read the source, its behavior owner, nearby specs, and relevant public dependencies.
+1. Identify whether the contract belongs in `web/`, Dify UI Browser Mode, or a styled Storybook test.
 1. Apply the canonical guide to decide whether a test is needed and choose its boundary.
 1. For a behavior change or bug fix, write or identify the failing scenario first when practical.
 1. Implement one coherent scenario at a time and run the focused spec before expanding scope.
@@ -32,4 +33,4 @@ vp test run path/to/spec-or-directory
 vp test run --project unit src/path/to/spec
 ```
 
-Run Dify UI Storybook tests with `vp test --project storybook --run`. Run broader checks only after the focused behavior passes.
+For styled Dify UI behavior, run `vp test --project storybook --run`. Run broader checks only after the focused behavior passes.

.github/workflows/api-tests.yml

@@ -47,6 +47,9 @@ jobs:
       - name: Install dependencies
         run: uv sync --project api --dev
 
+      - name: Run dify config tests
+        run: uv run --project api pytest api/tests/unit_tests/configs/test_env_consistency.py
+
       - name: Run Unit Tests
         run: |
           uv run --project api pytest \

.github/workflows/main-ci.yml

@@ -27,7 +27,7 @@ jobs:
     steps:
       - id: skip_check
         continue-on-error: true
-        uses: fkirc/skip-duplicate-actions@b974a9395958c231af965b70070979a577efa578 # v5.3.2
+        uses: fkirc/skip-duplicate-actions@f75f66ce1886f00957d99748a42c724f4330bdcf # v5.3.1
         with:
           cancel_others: 'true'
           concurrent_skipping: same_content_newer
@@ -81,6 +81,7 @@ jobs:
               - '.npmrc'
               - '.nvmrc'
               - '.github/workflows/cli-tests.yml'
+              - '.github/workflows/cli-docker-build.yml'
               - '.github/actions/setup-web/**'
             web:
               - 'web/**'

.github/workflows/sandbox-runtime-tests.yml

@@ -27,7 +27,7 @@ jobs:
           persist-credentials: false
 
       - name: Setup Go
-        uses: actions/setup-go@b7ad1dad31e06c5925ef5d2fc7ad053ef454303e # v7.0.0
+        uses: actions/setup-go@d35c59abb061a4a6fb18e82ac0862c26744d6ab5 # v5.5.0
         with:
           go-version-file: dify-agent-runtime/go.mod
           cache-dependency-path: dify-agent-runtime/go.sum
@@ -51,13 +51,13 @@ jobs:
           persist-credentials: false
 
       - name: Setup Go
-        uses: actions/setup-go@b7ad1dad31e06c5925ef5d2fc7ad053ef454303e # v7.0.0
+        uses: actions/setup-go@d35c59abb061a4a6fb18e82ac0862c26744d6ab5 # v5.5.0
         with:
           go-version-file: dify-agent-runtime/go.mod
           cache-dependency-path: dify-agent-runtime/go.sum
 
       - name: Run golangci-lint
-        uses: golangci/golangci-lint-action@ba0d7d2ec06a0ea1cb5fa41b2e4a3ab91d21278a # v6.5.0
+        uses: golangci/golangci-lint-action@4afd733a84b1f43292c63897423277bb7f4313a9 # v6.5.0
         with:
           working-directory: dify-agent-runtime
           version: latest
@@ -78,7 +78,7 @@ jobs:
           persist-credentials: false
 
       - name: Setup Go
-        uses: actions/setup-go@b7ad1dad31e06c5925ef5d2fc7ad053ef454303e # v7.0.0
+        uses: actions/setup-go@d35c59abb061a4a6fb18e82ac0862c26744d6ab5 # v5.5.0
         with:
           go-version-file: dify-agent-runtime/go.mod
           cache-dependency-path: dify-agent-runtime/go.sum

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

@@ -29,7 +29,7 @@ jobs:
           persist-credentials: false
 
       - name: Use Node.js
-        uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
+        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
         with:
           node-version: 22
           cache: ''

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

@@ -158,7 +158,7 @@ jobs:
 
       - name: Run Claude Code for Translation Sync
         if: steps.context.outputs.CHANGED_FILES != ''
-        uses: anthropics/claude-code-action@af0559ee4f514d1ef21826982bed13f7edc3c35e # v1.0.178
+        uses: anthropics/claude-code-action@e90deca47693f9457b72f2b53c17d7c445a87342 # v1.0.171
         with:
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
           github_token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/web-e2e.yml

@@ -135,6 +135,16 @@ jobs:
             exit 1
           fi
 
+          if [[ -d cucumber-report ]]; then
+            rm -rf cucumber-report-non-external
+            mv cucumber-report cucumber-report-non-external
+          fi
+
+          if [[ -d .logs ]]; then
+            rm -rf .logs-non-external
+            mv .logs .logs-non-external
+          fi
+
           teardown_external_runtime() {
             local run_status=$?
             trap - EXIT

.github/workflows/web-tests.yml

@@ -17,6 +17,8 @@ jobs:
   test:
     name: Web Tests (${{ matrix.shardIndex }}/${{ matrix.shardTotal }})
     runs-on: depot-ubuntu-24.04-4
+    env:
+      VITEST_COVERAGE_SCOPE: app-components
     strategy:
       fail-fast: false
       matrix:

Makefile

@@ -107,7 +107,6 @@ test:
 		echo "Target: $(TARGET_TESTS)"; \
 		uv run --project api --dev pytest $(TARGET_TESTS); \
 	else \
-		set -e; \
 		echo "Running backend unit tests"; \
 		uv run --project api --dev pytest -p no:benchmark --timeout "$${PYTEST_TIMEOUT:-20}" -n auto \
 			api/tests/unit_tests \
@@ -125,7 +124,6 @@ test-all:
 		echo "Target: $(TARGET_TESTS)"; \
 		uv run --project api --dev pytest $(TARGET_TESTS); \
 	else \
-		set -e; \
 		echo "Running backend unit tests"; \
 		uv run --project api --dev pytest -p no:benchmark --timeout "$${PYTEST_TIMEOUT:-20}" -n auto \
 			api/tests/unit_tests \

api/.env.example

@@ -677,17 +677,6 @@ INNER_API_KEY_FOR_PLUGIN=QaHbTe77CtuXmsfyhR7+vRjI/+XbV1AaFy691iy+kGDv2Jvy0/eAh8Y
 
 # Dify Agent backend
 AGENT_BACKEND_BASE_URL=http://localhost:5050
-AGENT_BACKEND_STREAM_READ_TIMEOUT_SECONDS=30
-AGENT_BACKEND_STREAM_MAX_RECONNECTS=3
-AGENT_BACKEND_RUN_TIMEOUT_SECONDS=1200
-
-# KnowledgeFS (Dataset 2.0)
-KNOWLEDGE_FS_ENABLED=false
-KNOWLEDGE_FS_BASE_URL=
-# Shared with KnowledgeFS; use at least 32 random characters.
-KNOWLEDGE_FS_JWT_SECRET=
-KNOWLEDGE_FS_SSE_READ_TIMEOUT_SECONDS=300
-KNOWLEDGE_FS_TIMEOUT_SECONDS=10
 
 # Marketplace configuration
 MARKETPLACE_ENABLED=true

api/clients/agent_backend/client.py

@@ -8,7 +8,7 @@ creating another wire contract.
 
 from __future__ import annotations
 
-from collections.abc import Callable, Iterator
+from collections.abc import Iterator
 from typing import Protocol
 
 from dify_agent.client import (
@@ -45,13 +45,7 @@ class AgentBackendRunClient(Protocol):
     def cancel_run(self, run_id: str, request: CancelRunRequest | None = None) -> CancelRunResponse:
         """Request explicit cancellation for one Agent backend run."""
 
-    def stream_events(
-        self,
-        run_id: str,
-        *,
-        after: str | None = None,
-        should_stop: Callable[[], bool] | None = None,
-    ) -> Iterator[RunEvent]:
+    def stream_events(self, run_id: str, *, after: str | None = None) -> Iterator[RunEvent]:
         """Yield public ``dify-agent`` run events in stream order."""
 
     def wait_run(self, run_id: str, *, timeout_seconds: float | None = None) -> RunStatusResponse:
@@ -67,15 +61,7 @@ class _DifyAgentSyncClient(Protocol):
     def cancel_run_sync(self, run_id: str, request: CancelRunRequest | None = None) -> CancelRunResponse:
         """Cancel one run synchronously."""
 
-    def stream_events_sync(
-        self,
-        run_id: str,
-        *,
-        after: str | None = None,
-        max_reconnects: int | None = None,
-        timeout_seconds: float | None = None,
-        should_stop: Callable[[], bool] | None = None,
-    ) -> Iterator[RunEvent]:
+    def stream_events_sync(self, run_id: str, *, after: str | None = None) -> Iterator[RunEvent]:
         """Stream run events synchronously."""
 
     def wait_run_sync(self, run_id: str, *, timeout_seconds: float | None = None) -> RunStatusResponse:
@@ -87,16 +73,8 @@ class DifyAgentBackendRunClient:
 
     client: _DifyAgentSyncClient
 
-    def __init__(
-        self,
-        client: _DifyAgentSyncClient,
-        *,
-        stream_max_reconnects: int = 3,
-        stream_timeout_seconds: float = 1200,
-    ) -> None:
+    def __init__(self, client: _DifyAgentSyncClient) -> None:
         self.client = client
-        self._stream_max_reconnects = stream_max_reconnects
-        self._stream_timeout_seconds = stream_timeout_seconds
 
     def create_run(self, request: CreateRunRequest) -> CreateRunResponse:
         """Create one run through ``POST /runs`` and normalize client exceptions."""
@@ -112,22 +90,10 @@ class DifyAgentBackendRunClient:
         except Exception as exc:
             raise _normalize_dify_agent_error(exc) from exc
 
-    def stream_events(
-        self,
-        run_id: str,
-        *,
-        after: str | None = None,
-        should_stop: Callable[[], bool] | None = None,
-    ) -> Iterator[RunEvent]:
+    def stream_events(self, run_id: str, *, after: str | None = None) -> Iterator[RunEvent]:
         """Stream run events from ``/events/sse`` with the wrapped client's reconnect policy."""
         try:
-            yield from self.client.stream_events_sync(
-                run_id,
-                after=after,
-                max_reconnects=self._stream_max_reconnects,
-                timeout_seconds=self._stream_timeout_seconds,
-                should_stop=should_stop,
-            )
+            yield from self.client.stream_events_sync(run_id, after=after)
         except Exception as exc:
             raise _normalize_dify_agent_error(exc) from exc
 

api/clients/agent_backend/factory.py

@@ -13,17 +13,10 @@ def create_agent_backend_run_client(
     base_url: str | None = None,
     use_fake: bool = False,
     fake_scenario: str | FakeAgentBackendScenario = FakeAgentBackendScenario.SUCCESS,
-    stream_read_timeout_seconds: float = 30,
-    stream_max_reconnects: int = 3,
-    stream_run_timeout_seconds: float = 1200,
 ) -> AgentBackendRunClient:
     """Create the API-side run client without hiding the ``dify-agent`` protocol."""
     if use_fake:
         return FakeAgentBackendRunClient(scenario=FakeAgentBackendScenario(fake_scenario))
     if base_url is None:
         raise ValueError("base_url is required when creating a real Agent backend client")
-    return DifyAgentBackendRunClient(
-        Client(base_url=base_url, stream_timeout=stream_read_timeout_seconds),
-        stream_max_reconnects=stream_max_reconnects,
-        stream_timeout_seconds=stream_run_timeout_seconds,
-    )
+    return DifyAgentBackendRunClient(Client(base_url=base_url))

api/clients/agent_backend/fake_client.py

@@ -7,7 +7,7 @@ separate ``agent-backend.v1`` event stream.
 
 from __future__ import annotations
 
-from collections.abc import Callable, Iterator
+from collections.abc import Iterator
 from datetime import UTC, datetime
 from enum import StrEnum
 
@@ -69,17 +69,9 @@ class FakeAgentBackendRunClient:
         del request
         return CancelRunResponse(run_id=run_id, status="cancelled")
 
-    def stream_events(
-        self,
-        run_id: str,
-        *,
-        after: str | None = None,
-        should_stop: Callable[[], bool] | None = None,
-    ) -> Iterator[RunEvent]:
+    def stream_events(self, run_id: str, *, after: str | None = None) -> Iterator[RunEvent]:
         """Yield the deterministic public ``RunEvent`` sequence for ``run_id``."""
         for event in self._events(run_id):
-            if should_stop is not None and should_stop():
-                return
             if after is not None and event.id is not None and event.id <= after:
                 continue
             yield event

api/commands/retention.py

@@ -1,8 +1,6 @@
 import datetime
 import logging
-import re
 import time
-import uuid
 from collections.abc import Callable
 from typing import TypedDict
 
@@ -23,7 +21,6 @@ from tasks.remove_app_and_related_data_task import delete_draft_variables_batch
 logger = logging.getLogger(__name__)
 
 _HEX_PREFIXES = tuple("0123456789abcdef")
-_TARGET_MONTH_PATTERN = re.compile(r"^\d{4}-(0[1-9]|1[0-2])$")
 
 
 class WorkflowRunArchivePlanRow(TypedDict):
@@ -69,7 +66,6 @@ def _parse_tenant_prefixes(prefixes: str | None) -> list[str]:
 
 
 def _parse_comma_separated_ids(raw_ids: str | None, *, param_name: str) -> list[str] | None:
-    """Keep an omitted scope unset while rejecting an explicitly empty scope."""
     if raw_ids is None:
         return None
     parsed = sorted({raw_id.strip() for raw_id in raw_ids.split(",") if raw_id.strip()})
@@ -78,27 +74,6 @@ def _parse_comma_separated_ids(raw_ids: str | None, *, param_name: str) -> list[
     return parsed
 
 
-def _parse_archive_target_month(target_month: str) -> tuple[int, int]:
-    """Validate the V2 catalog month selector and return its numeric components."""
-    if not _TARGET_MONTH_PATTERN.fullmatch(target_month):
-        raise click.BadParameter("target-month must use YYYY-MM format", param_hint="--target-month")
-    year_text, month_text = target_month.split("-", maxsplit=1)
-    return int(year_text), int(month_text)
-
-
-def _parse_archive_catalog_cursor(after_catalog_id: str | None) -> str | None:
-    """Normalize the exclusive V2 catalog keyset cursor when one is provided."""
-    if after_catalog_id is None:
-        return None
-    try:
-        return str(uuid.UUID(after_catalog_id))
-    except ValueError as exc:
-        raise click.BadParameter(
-            "after-catalog-id must be a UUID returned by the same V2 operation and scope",
-            param_hint="--after-catalog-id",
-        ) from exc
-
-
 def _get_archive_candidate_tenant_ids_by_prefix(
     session: Session,
     prefix: str,
@@ -835,11 +810,9 @@ def backfill_workflow_run_archive_bundles(
         click.echo(click.style(f"  ... and {len(summary.errors) - 10} more failures", fg="red"))
 
 
-def _echo_bundle_archive_operation_summary(summary, *, dry_run: bool) -> None:
+def _echo_bundle_archive_operation_summary(summary) -> None:
     status = "completed successfully" if summary.bundles_failed == 0 else "completed with failures"
     fg = "green" if summary.bundles_failed == 0 else "red"
-    cursor_label = "preview_next_catalog_id" if dry_run else "next_catalog_id"
-    cursor_value = summary.preview_next_catalog_id if dry_run else summary.next_catalog_id
     click.echo(
         click.style(
             f"{summary.operation} {status}. "
@@ -848,12 +821,10 @@ def _echo_bundle_archive_operation_summary(summary, *, dry_run: bool) -> None:
             f"archive_bytes={summary.archive_bytes} duration={summary.elapsed_time:.2f}s "
             f"validation_time={summary.validation_time:.2f}s "
             f"runs_per_second={summary.runs_per_second:.2f} rows_per_second={summary.rows_per_second:.2f} "
-            f"bytes_per_second={summary.bytes_per_second:.2f} {cursor_label}={cursor_value or 'none'}",
+            f"bytes_per_second={summary.bytes_per_second:.2f}",
             fg=fg,
         )
     )
-    if dry_run:
-        click.echo(click.style("Dry-run cursor is preview-only; do not persist it for a destructive run.", fg="yellow"))
     click.echo(click.style("table,row_count", fg="white"))
     for table_name in [
         "workflow_runs",
@@ -871,8 +842,7 @@ def _echo_bundle_archive_operation_summary(summary, *, dry_run: bool) -> None:
                 click.style(
                     f"  bundle={result.bundle_id} tenant={result.tenant_id} runs={result.run_count} "
                     f"rows={result.row_count} archive_bytes={result.archive_bytes} "
-                    f"catalog_id={result.catalog_id} time={result.elapsed_time:.2f}s "
-                    f"validation={result.validation_time:.2f}s",
+                    f"time={result.elapsed_time:.2f}s validation={result.validation_time:.2f}s",
                     fg="white",
                 )
             )
@@ -880,7 +850,7 @@ def _echo_bundle_archive_operation_summary(summary, *, dry_run: bool) -> None:
             click.echo(
                 click.style(
                     f"  failed bundle={result.bundle_id} tenant={result.tenant_id} "
-                    f"catalog_id={result.catalog_id} object_prefix={result.object_prefix} error={result.error}",
+                    f"object_prefix={result.object_prefix} error={result.error}",
                     fg="red",
                 )
             )
@@ -897,24 +867,25 @@ def _echo_bundle_archive_operation_summary(summary, *, dry_run: bool) -> None:
 )
 @click.option("--run-id", required=False, help="Workflow run ID to restore.")
 @click.option(
-    "--target-month",
-    metavar="YYYY-MM",
+    "--start-from",
+    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
     default=None,
-    help="V2 catalog month to restore; required unless --run-id is used.",
+    help="Optional lower bound (inclusive) for created_at; must be paired with --end-before.",
 )
 @click.option(
-    "--after-catalog-id",
+    "--end-before",
+    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
     default=None,
-    help="Exclusive V2 cursor from the same restore month and tenant scope.",
+    help="Optional upper bound (exclusive) for created_at; must be paired with --start-from.",
 )
 @click.option("--workers", default=1, show_default=True, type=int, help="V1 --run-id compatibility only.")
-@click.option("--limit", type=click.IntRange(min=1), default=100, show_default=True, help="Maximum V2 catalog rows.")
+@click.option("--limit", type=int, default=100, show_default=True, help="Maximum number of V2 bundles to restore.")
 @click.option("--dry-run", is_flag=True, help="Preview without restoring.")
 def restore_workflow_runs(
     tenant_ids: str | None,
     run_id: str | None,
-    target_month: str | None,
-    after_catalog_id: str | None,
+    start_from: datetime.datetime | None,
+    end_before: datetime.datetime | None,
     workers: int,
     limit: int,
     dry_run: bool,
@@ -934,20 +905,23 @@ def restore_workflow_runs(
     from services.retention.workflow_run.bundle_archive_maintenance import WorkflowRunBundleArchiveMaintenance
     from services.retention.workflow_run.restore_archived_workflow_run import WorkflowRunRestore
 
-    parsed_tenant_ids = _parse_comma_separated_ids(tenant_ids, param_name="tenant-ids")
+    parsed_tenant_ids = None
+    if tenant_ids:
+        parsed_tenant_ids = [tid.strip() for tid in tenant_ids.split(",") if tid.strip()]
+        if not parsed_tenant_ids:
+            raise click.BadParameter("tenant-ids must not be empty")
 
+    if (start_from is None) ^ (end_before is None):
+        raise click.UsageError("--start-from and --end-before must be provided together.")
+    if run_id is None and (start_from is None or end_before is None):
+        raise click.UsageError("--start-from and --end-before are required for batch restore.")
     if workers < 1:
         raise click.BadParameter("workers must be at least 1")
-    if run_id is not None and (target_month is not None or after_catalog_id is not None):
-        raise click.UsageError("--target-month and --after-catalog-id are only valid for V2 batch restore.")
-    if run_id is None and target_month is None:
-        raise click.UsageError("--target-month is required for V2 batch restore.")
 
     start_time = datetime.datetime.now(datetime.UTC)
-    target_desc = f"workflow run {run_id}" if run_id else f"workflow archive catalog month {target_month}"
     click.echo(
         click.style(
-            f"Starting restore of {target_desc} at {start_time.isoformat()}.",
+            f"Starting restore of workflow run {run_id} at {start_time.isoformat()}.",
             fg="white",
         )
     )
@@ -981,20 +955,17 @@ def restore_workflow_runs(
         click.echo(
             click.style("--workers is ignored for V2 bundle restore; bundles are processed serially.", fg="yellow")
         )
-    assert target_month is not None
-    target_year, target_month_number = _parse_archive_target_month(target_month)
-    catalog_cursor = _parse_archive_catalog_cursor(after_catalog_id)
+    assert start_from is not None
+    assert end_before is not None
     bundle_restorer = WorkflowRunBundleArchiveMaintenance(dry_run=dry_run, strict_content_validation=True)
     summary = bundle_restorer.restore_batch(
         tenant_ids=parsed_tenant_ids,
-        target_year=target_year,
-        target_month=target_month_number,
-        after_catalog_id=catalog_cursor,
+        start_date=start_from,
+        end_date=end_before,
         limit=limit,
     )
-    _echo_bundle_archive_operation_summary(summary, dry_run=dry_run)
-    if summary.bundles_failed:
-        raise click.exceptions.Exit(1)
+    _echo_bundle_archive_operation_summary(summary)
+    return
 
 
 @click.command(
@@ -1008,41 +979,23 @@ def restore_workflow_runs(
 )
 @click.option("--run-id", required=False, help="Workflow run ID to delete.")
 @click.option(
-    "--target-month",
-    metavar="YYYY-MM",
+    "--start-from",
+    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
     default=None,
-    help="V2 catalog month to delete; required unless --run-id is used.",
+    help="Optional lower bound (inclusive) for created_at; must be paired with --end-before.",
 )
 @click.option(
-    "--after-catalog-id",
+    "--end-before",
+    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
     default=None,
-    help="Exclusive V2 cursor from the same delete month and tenant scope.",
-)
-@click.option(
-    "--run-shard-index",
-    default=None,
-    type=click.IntRange(min=0),
-    help="Zero-based archive shard index. Must be paired with --run-shard-total.",
-)
-@click.option(
-    "--run-shard-total",
-    default=None,
-    type=click.IntRange(min=1, max=16),
-    help="Total archive shard count. Must be paired with --run-shard-index.",
-)
-@click.option("--all-pages", is_flag=True, help="Process catalog pages until an empty page is reached.")
-@click.option(
-    "--limit",
-    type=click.IntRange(min=1),
-    default=100,
-    show_default=True,
-    help="Maximum V2 catalog rows per page.",
+    help="Optional upper bound (exclusive) for created_at; must be paired with --start-from.",
 )
+@click.option("--limit", type=int, default=100, show_default=True, help="Maximum number of V2 bundles to delete.")
 @click.option("--dry-run", is_flag=True, help="Preview without deleting.")
 @click.option(
     "--skip-bad-archives",
     is_flag=True,
-    help="V1 --run-id only: continue when one archive object fails validation.",
+    help="Continue batch deletion when one archive object fails validation.",
 )
 @click.option(
     "--restore-sample-interval",
@@ -1054,11 +1007,8 @@ def restore_workflow_runs(
 def delete_archived_workflow_runs(
     tenant_ids: str | None,
     run_id: str | None,
-    target_month: str | None,
-    after_catalog_id: str | None,
-    run_shard_index: int | None,
-    run_shard_total: int | None,
-    all_pages: bool,
+    start_from: datetime.datetime | None,
+    end_before: datetime.datetime | None,
     limit: int,
     dry_run: bool,
     skip_bad_archives: bool,
@@ -1068,38 +1018,26 @@ def delete_archived_workflow_runs(
     Delete archived workflow runs from the database.
 
     Batch delete uses V2 bundle metadata and validates object existence, manifest schema, object size, checksum, row
-    counts, and source/archive content checksums before deleting source rows. Parallel workers may select one exact
-    archive shard; all-pages mode keeps only the current bounded page in memory. `--run-id` keeps the V1 per-run path.
+    counts, and source/archive content checksums before deleting source rows. `--run-id` keeps the V1 per-run path.
     """
     from services.retention.workflow_run.bundle_archive_maintenance import WorkflowRunBundleArchiveMaintenance
     from services.retention.workflow_run.delete_archived_workflow_run import ArchivedWorkflowRunDeletion
 
-    parsed_tenant_ids = _parse_comma_separated_ids(tenant_ids, param_name="tenant-ids")
+    parsed_tenant_ids = None
+    if tenant_ids:
+        parsed_tenant_ids = [tid.strip() for tid in tenant_ids.split(",") if tid.strip()]
+        if not parsed_tenant_ids:
+            raise click.BadParameter("tenant-ids must not be empty")
 
+    if (start_from is None) ^ (end_before is None):
+        raise click.UsageError("--start-from and --end-before must be provided together.")
+    if run_id is None and (start_from is None or end_before is None):
+        raise click.UsageError("--start-from and --end-before are required for batch delete.")
     if restore_sample_interval < 0:
         raise click.BadParameter("restore-sample-interval must be >= 0")
-    if run_id is not None and (
-        target_month is not None
-        or after_catalog_id is not None
-        or run_shard_index is not None
-        or run_shard_total is not None
-        or all_pages
-    ):
-        raise click.UsageError(
-            "--target-month, --after-catalog-id, --run-shard-index, --run-shard-total, and --all-pages "
-            "are only valid for V2 batch delete."
-        )
-    if run_id is None and target_month is None:
-        raise click.UsageError("--target-month is required for V2 batch delete.")
-    if run_id is None and skip_bad_archives:
-        raise click.UsageError("--skip-bad-archives is not supported for V2 catalog batches; they fail fast.")
-    if (run_shard_index is None) ^ (run_shard_total is None):
-        raise click.UsageError("--run-shard-index and --run-shard-total must be provided together.")
-    if run_shard_index is not None and run_shard_total is not None and run_shard_index >= run_shard_total:
-        raise click.UsageError("--run-shard-index must be less than --run-shard-total.")
 
     start_time = datetime.datetime.now(datetime.UTC)
-    target_desc = f"workflow run {run_id}" if run_id else f"workflow archive catalog month {target_month}"
+    target_desc = f"workflow run {run_id}" if run_id else "workflow runs"
     click.echo(
         click.style(
             f"Starting delete of {target_desc} at {start_time.isoformat()}.",
@@ -1172,104 +1110,20 @@ def delete_archived_workflow_runs(
 
     if restore_sample_interval:
         click.echo(click.style("--restore-sample-interval is ignored for V2 bundle delete.", fg="yellow"))
-    assert target_month is not None
-    target_year, target_month_number = _parse_archive_target_month(target_month)
-    catalog_cursor = _parse_archive_catalog_cursor(after_catalog_id)
-    shard = (
-        f"{run_shard_index:02d}-of-{run_shard_total:02d}"
-        if run_shard_index is not None and run_shard_total is not None
-        else None
+    assert start_from is not None
+    assert end_before is not None
+    bundle_deleter = WorkflowRunBundleArchiveMaintenance(
+        dry_run=dry_run,
+        strict_content_validation=True,
+        stop_on_error=not skip_bad_archives,
     )
-    bundle_deleter = WorkflowRunBundleArchiveMaintenance(dry_run=dry_run, strict_content_validation=True)
-    if run_shard_total is not None:
-        try:
-            bundle_deleter.validate_catalog_shards(
-                target_year=target_year,
-                target_month=target_month_number,
-                shard_total=run_shard_total,
-                tenant_ids=parsed_tenant_ids,
-            )
-        except ValueError as exc:
-            logger.exception(
-                "Archive catalog shard preflight failed: target_month=%s shard=%s",
-                target_month,
-                shard,
-            )
-            raise click.ClickException(
-                f"Archive catalog shard preflight failed for target_month={target_month} shard={shard}: {exc}"
-            ) from exc
-
-    initial_catalog_cursor = catalog_cursor
-    pages_processed = 0
-    bundles_succeeded = 0
-    runs_processed = 0
-    rows_processed = 0
-    archive_bytes = 0
-    while True:
-        summary = bundle_deleter.delete_batch(
-            tenant_ids=parsed_tenant_ids,
-            target_year=target_year,
-            target_month=target_month_number,
-            after_catalog_id=catalog_cursor,
-            limit=limit,
-            shard=shard,
-        )
-        _echo_bundle_archive_operation_summary(summary, dry_run=dry_run)
-        if summary.bundles_failed:
-            failed_result = next((result for result in summary.results if not result.success), None)
-            failed_catalog_id = failed_result.catalog_id if failed_result is not None else "unknown"
-            page_resume_cursor = summary.preview_next_catalog_id if dry_run else summary.next_catalog_id
-            resume_cursor = page_resume_cursor or catalog_cursor
-            if dry_run:
-                cursor_details = (
-                    f"preview_after_catalog_id={resume_cursor or 'none'} "
-                    f"destructive_retry_after_catalog_id={initial_catalog_cursor or 'none'}"
-                )
-            else:
-                cursor_details = f"resume_after_catalog_id={resume_cursor or 'none'}"
-            click.echo(
-                click.style(
-                    f"Delete stopped: target_month={target_month} shard={shard or 'all'} "
-                    f"failed_catalog_id={failed_catalog_id} "
-                    f"{cursor_details}",
-                    fg="red",
-                )
-            )
-            raise click.exceptions.Exit(1)
-
-        if not all_pages:
-            break
-        if summary.bundles_processed == 0:
-            break
-
-        pages_processed += 1
-        bundles_succeeded += summary.bundles_succeeded
-        runs_processed += summary.runs_processed
-        rows_processed += summary.rows_processed
-        archive_bytes += summary.archive_bytes
-        next_catalog_id = summary.preview_next_catalog_id if dry_run else summary.next_catalog_id
-        if next_catalog_id is None or (catalog_cursor is not None and next_catalog_id <= catalog_cursor):
-            click.echo(
-                click.style(
-                    f"Delete cursor did not advance: target_month={target_month} shard={shard or 'all'} "
-                    f"after_catalog_id={catalog_cursor or 'none'} next_catalog_id={next_catalog_id or 'none'}",
-                    fg="red",
-                )
-            )
-            raise click.exceptions.Exit(1)
-        catalog_cursor = next_catalog_id
-
-    if all_pages:
-        final_cursor_label = "preview_final_catalog_id" if dry_run else "final_catalog_id"
-        click.echo(
-            click.style(
-                f"Delete all-pages completed successfully. target_month={target_month} shard={shard or 'all'} "
-                f"pages={pages_processed} bundles_success={bundles_succeeded} runs={runs_processed} "
-                f"rows={rows_processed} archive_bytes={archive_bytes} "
-                f"{final_cursor_label}={catalog_cursor or 'none'}",
-                fg="green",
-            )
-        )
+    summary = bundle_deleter.delete_batch(
+        tenant_ids=parsed_tenant_ids,
+        start_date=start_from,
+        end_date=end_before,
+        limit=limit,
+    )
+    _echo_bundle_archive_operation_summary(summary)
 
 
 def _find_orphaned_draft_variables(batch_size: int = 1000) -> list[str]:

api/configs/enterprise/__init__.py

@@ -14,12 +14,6 @@ class EnterpriseFeatureConfig(BaseSettings):
         default=False,
     )
 
-    WEBAPP_PUBLIC_ACCESS_ENABLED: bool = Field(
-        description="Whether admins are allowed to set a webapp's access mode to public (anyone with the link, "
-        "no auth). Disable in security-sensitive on-prem deployments.",
-        default=True,
-    )
-
     CAN_REPLACE_LOGO: bool = Field(
         description="Allow customization of the enterprise logo.",
         default=False,

api/configs/extra/__init__.py

@@ -1,6 +1,5 @@
 from configs.extra.agent_backend_config import AgentBackendConfig
 from configs.extra.archive_config import ArchiveStorageConfig
-from configs.extra.knowledge_fs_config import KnowledgeFSConfig
 from configs.extra.notion_config import NotionConfig
 from configs.extra.sentry_config import SentryConfig
 
@@ -9,7 +8,6 @@ class ExtraServiceConfig(
     # place the configs in alphabet order
     AgentBackendConfig,
     ArchiveStorageConfig,
-    KnowledgeFSConfig,
     NotionConfig,
     SentryConfig,
 ):

api/configs/extra/agent_backend_config.py

@@ -1,4 +1,4 @@
-from pydantic import Field, NonNegativeFloat, NonNegativeInt, PositiveFloat
+from pydantic import Field, NonNegativeFloat
 from pydantic_settings import BaseSettings
 
 
@@ -22,21 +22,6 @@ class AgentBackendConfig(BaseSettings):
         default="success",
     )
 
-    AGENT_BACKEND_STREAM_READ_TIMEOUT_SECONDS: PositiveFloat = Field(
-        description="Read timeout for one Agent backend SSE connection.",
-        default=30,
-    )
-
-    AGENT_BACKEND_STREAM_MAX_RECONNECTS: NonNegativeInt = Field(
-        description="Maximum Agent backend SSE reconnects before failing the run.",
-        default=3,
-    )
-
-    AGENT_BACKEND_RUN_TIMEOUT_SECONDS: PositiveFloat = Field(
-        description="Total deadline for one Agent backend run event stream.",
-        default=1200,
-    )
-
     AGENT_SHELL_ENABLED: bool = Field(
         description=(
             "Inject the dify.shell layer (sandboxed bash workspace) into Agent runs. "

api/configs/extra/knowledge_fs_config.py

@@ -1,64 +0,0 @@
-"""Configuration for the optional KnowledgeFS Console bridge."""
-
-from urllib.parse import urlsplit
-
-from pydantic import Field, PositiveFloat, SecretStr, field_validator, model_validator
-from pydantic_settings import BaseSettings
-
-
-class KnowledgeFSConfig(BaseSettings):
-    """Server-only settings for the KnowledgeFS production connection."""
-
-    KNOWLEDGE_FS_ENABLED: bool = Field(
-        default=False,
-        description="Enable the private KnowledgeFS Console bridge.",
-    )
-    KNOWLEDGE_FS_BASE_URL: str | None = Field(default=None, description="KnowledgeFS gateway base URL.")
-    KNOWLEDGE_FS_JWT_SECRET: SecretStr | None = Field(
-        default=None,
-        min_length=32,
-        description="Shared secret used to sign short-lived KnowledgeFS service JWTs.",
-    )
-    KNOWLEDGE_FS_SSE_READ_TIMEOUT_SECONDS: PositiveFloat = Field(default=300.0, le=3600.0, allow_inf_nan=False)
-    KNOWLEDGE_FS_TIMEOUT_SECONDS: PositiveFloat = Field(default=10.0, le=60.0, allow_inf_nan=False)
-
-    @field_validator(
-        "KNOWLEDGE_FS_BASE_URL",
-        "KNOWLEDGE_FS_JWT_SECRET",
-        mode="before",
-    )
-    @classmethod
-    def normalize_optional_string(cls, value: object) -> object:
-        if isinstance(value, SecretStr):
-            normalized = value.get_secret_value().strip()
-            return SecretStr(normalized) if normalized else None
-        if isinstance(value, str):
-            normalized = value.strip()
-            return normalized or None
-        return value
-
-    @field_validator("KNOWLEDGE_FS_BASE_URL")
-    @classmethod
-    def validate_base_url(cls, value: str | None) -> str | None:
-        if value is None:
-            return None
-        parsed = urlsplit(value)
-        if parsed.scheme not in {"http", "https"} or not parsed.netloc:
-            raise ValueError("KNOWLEDGE_FS_BASE_URL must be an absolute HTTP(S) URL")
-        try:
-            _ = parsed.port
-        except ValueError as exc:
-            raise ValueError("KNOWLEDGE_FS_BASE_URL must include a valid port") from exc
-        if parsed.username or parsed.password or parsed.query or parsed.fragment:
-            raise ValueError("KNOWLEDGE_FS_BASE_URL must not include credentials, query, or fragment")
-        return value.rstrip("/")
-
-    @model_validator(mode="after")
-    def validate_enabled_connection(self) -> "KnowledgeFSConfig":
-        if not self.KNOWLEDGE_FS_ENABLED:
-            return self
-        if bool(self.KNOWLEDGE_FS_BASE_URL) != bool(self.KNOWLEDGE_FS_JWT_SECRET):
-            raise ValueError("KNOWLEDGE_FS_BASE_URL and KNOWLEDGE_FS_JWT_SECRET must be configured together")
-        if not self.KNOWLEDGE_FS_BASE_URL:
-            raise ValueError("KnowledgeFS connection settings are required when the integration is enabled")
-        return self

api/configs/feature/__init__.py

@@ -1,4 +1,4 @@
-from datetime import datetime, timedelta
+from datetime import timedelta
 from enum import StrEnum
 from typing import Literal
 
@@ -11,7 +11,6 @@ from pydantic import (
     PositiveFloat,
     PositiveInt,
     computed_field,
-    field_validator,
 )
 from pydantic_settings import BaseSettings
 
@@ -281,27 +280,6 @@ class PluginConfig(BaseSettings):
         default="",
     )
 
-    @field_validator("PLUGIN_REMOTE_INSTALL_PORT", mode="before")
-    @classmethod
-    def _reject_host_port_shaped_plugin_remote_install_port(cls, v):
-        """Reject ``host:port``-shaped values with an actionable hint.
-
-        ``EXPOSE_PLUGIN_DEBUGGING_PORT`` is overloaded: it feeds both the
-        plugin_daemon ``ports:`` mapping (where ``127.0.0.1:5003`` is valid
-        compose syntax) and this integer app setting advertised in the console.
-        Without this guard a loopback bind spec crashloops the api container
-        with an opaque ``int_parsing`` traceback. See issue #39323.
-        """
-        if isinstance(v, str) and ":" in v.strip():
-            raise ValueError(
-                "PLUGIN_REMOTE_INSTALL_PORT must be a bare port number, got "
-                f"{v!r}. A 'host:port' value usually means "
-                "EXPOSE_PLUGIN_DEBUGGING_PORT was set to a compose publish spec "
-                "like '127.0.0.1:5003'; bind loopback via a "
-                "docker-compose.override.yaml instead of overloading this var."
-            )
-        return v
-
     @property
     def NEW_USER_DEFAULT_PLUGIN_ID_LIST(self) -> list[str]:
         return [item.strip() for item in self.NEW_USER_DEFAULT_PLUGIN_IDS.split(",") if item.strip()]
@@ -1160,16 +1138,6 @@ class HomepageConfig(BaseSettings):
         default=True,
     )
 
-    ENABLE_STEP_BY_STEP_TOUR: bool = Field(
-        description="Enable account-level Step-by-step Tour eligibility checks",
-        default=False,
-    )
-
-    STEP_BY_STEP_TOUR_ROLLOUT_STARTED_AT: datetime | None = Field(
-        description="UTC timestamp after which newly initialized accounts are eligible for Step-by-step Tour",
-        default=None,
-    )
-
 
 class RagEtlConfig(BaseSettings):
     """

api/controllers/console/__init__.py

@@ -38,9 +38,7 @@ from . import (
     feature,
     human_input_form,
     init_validate,
-    knowledge_fs_proxy,
     notification,
-    onboarding,
     ping,
     setup,
     spec,
@@ -197,7 +195,6 @@ __all__ = [
     "human_input_form",
     "init_validate",
     "installed_app",
-    "knowledge_fs_proxy",
     "load_balancing_config",
     "login",
     "mcp_server",
@@ -210,7 +207,6 @@ __all__ = [
     "notification",
     "oauth",
     "oauth_server",
-    "onboarding",
     "ops_trace",
     "parameter",
     "ping",

api/controllers/console/app/workflow.py

@@ -105,7 +105,6 @@ class SyncDraftWorkflowPayload(BaseModel):
     graph: dict[str, Any]
     features: dict[str, Any]
     hash: str | None = None
-    is_collaborative: bool = Field(default=False, alias="_is_collaborative")
     environment_variables: list[dict[str, Any]] = Field(
         default_factory=list,
     )
@@ -611,7 +610,6 @@ class DraftWorkflowApi(Resource):
                 environment_variables=environment_variables,
                 conversation_variables=conversation_variables,
                 session=db.session(),
-                graph_only=args["is_collaborative"],
             )
         except WorkflowHashNotEqualError:
             raise DraftWorkflowNotSync()

api/controllers/console/datasets/datasets.py

@@ -607,13 +607,6 @@ class DatasetListApi(Resource):
                     ReplaceMemberBindings(scope=RBACResourceWhitelistScope.ALL),
                 )
                 initialize_created_app_rbac_access_task.delay(current_tenant_id, current_user.id, dataset_id=dataset.id)
-            else:
-                enterprise_rbac_service.RBACService.DatasetAccess.replace_whitelist(
-                    current_tenant_id,
-                    current_user.id,
-                    dataset.id,
-                    ReplaceMemberBindings(scope=RBACResourceWhitelistScope.SPECIFIC),
-                )
 
         permission_keys_map = enterprise_rbac_service.RBACService.DatasetPermissions.batch_get(
             current_tenant_id,
@@ -882,7 +875,7 @@ class DatasetIndexingEstimateApi(Resource):
                 file_details = session.scalars(
                     select(UploadFile).where(UploadFile.tenant_id == current_tenant_id, UploadFile.id.in_(file_ids))
                 ).all()
-                if not file_details:
+                if file_details is None:
                     raise NotFound("File not found.")
 
                 if file_details:

api/controllers/console/explore/trial.py

@@ -47,9 +47,7 @@ from controllers.console.explore.error import (
     NotWorkflowAppError,
 )
 from controllers.console.explore.wraps import TrialAppResource, trial_feature_enable
-from controllers.console.files import FILE_UPLOAD_PARAMS, upload_file_from_request
-from controllers.console.remote_files import RemoteFileUploadPayload, upload_remote_file_from_request
-from controllers.console.wraps import cloud_edition_billing_resource_check, with_current_user
+from controllers.console.wraps import with_current_user
 from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
 from core.app.app_config.common.parameters_mapping import get_parameters_from_feature_dict
 from core.app.apps.base_app_queue_manager import AppQueueManager
@@ -63,13 +61,12 @@ from extensions.ext_database import db
 from extensions.ext_redis import redis_client
 from fields.base import ResponseModel
 from fields.conversation_variable_fields import WorkflowConversationVariableResponse
-from fields.file_fields import FileResponse, FileWithSignedUrl
 from fields.message_fields import SuggestedQuestionsResponse
 from graphon.graph_engine.manager import GraphEngineManager
 from graphon.model_runtime.errors.invoke import InvokeError
 from libs import helper
 from libs.helper import dump_response, to_timestamp, uuid_value
-from models import Account, App
+from models import Account
 from models.account import TenantStatus
 from models.model import AppMode, Site, load_annotation_reply_config
 from models.workflow import Workflow
@@ -431,36 +428,6 @@ register_response_schema_models(
 simple_account_model = console_ns.models[TrialSimpleAccount.__name__]
 
 
-class TrialAppFileUploadApi(TrialAppResource):
-    @trial_feature_enable
-    @cloud_edition_billing_resource_check("documents")
-    @console_ns.doc(consumes=["multipart/form-data"], params=FILE_UPLOAD_PARAMS)
-    @console_ns.response(201, "File uploaded successfully", console_ns.models[FileResponse.__name__])
-    @with_current_user
-    def post(self, current_user: Account, app_model: App):
-        """Upload a file into the tenant that owns the trial app."""
-        upload_file = upload_file_from_request(
-            current_user=current_user,
-            resource_tenant_id=app_model.tenant_id,
-        )
-        return dump_response(FileResponse, upload_file), 201
-
-
-class TrialAppRemoteFileUploadApi(TrialAppResource):
-    @trial_feature_enable
-    @cloud_edition_billing_resource_check("documents")
-    @console_ns.expect(console_ns.models[RemoteFileUploadPayload.__name__])
-    @console_ns.response(201, "File uploaded successfully", console_ns.models[FileWithSignedUrl.__name__])
-    @with_current_user
-    def post(self, current_user: Account, app_model: App):
-        """Upload a remote file into the tenant that owns the trial app."""
-        remote_file = upload_remote_file_from_request(
-            current_user=current_user,
-            resource_tenant_id=app_model.tenant_id,
-        )
-        return remote_file.model_dump(mode="json"), 201
-
-
 class TrialAppWorkflowRunApi(TrialAppResource):
     @trial_feature_enable
     @console_ns.expect(console_ns.models[WorkflowRunRequest.__name__])
@@ -645,7 +612,7 @@ class TrialChatAudioApi(TrialAppResource):
     def post(self, current_user: Account, trial_app):
         app_model = trial_app
 
-        file = request.files.get("file")
+        file = request.files["file"]
 
         try:
             # Get IDs before they might be detached from session
@@ -920,18 +887,6 @@ class DatasetListApi(Resource):
 
 console_ns.add_resource(TrialChatApi, "/trial-apps/<uuid:app_id>/chat-messages", endpoint="trial_app_chat_completion")
 
-console_ns.add_resource(
-    TrialAppFileUploadApi,
-    "/trial-apps/<uuid:app_id>/files/upload",
-    endpoint="trial_app_file_upload",
-)
-
-console_ns.add_resource(
-    TrialAppRemoteFileUploadApi,
-    "/trial-apps/<uuid:app_id>/remote-files/upload",
-    endpoint="trial_app_remote_file_upload",
-)
-
 console_ns.add_resource(
     TrialMessageSuggestedQuestionApi,
     "/trial-apps/<uuid:app_id>/messages/<uuid:message_id>/suggested-questions",

api/controllers/console/files.py

@@ -29,7 +29,7 @@ from extensions.ext_database import db
 from fields.file_fields import FileResponse, UploadConfig
 from libs.helper import dump_response
 from libs.login import login_required
-from models import Account, UploadFile
+from models import Account
 from services.file_service import FileService
 
 from . import console_ns
@@ -39,7 +39,7 @@ register_response_schema_models(console_ns, AllowedExtensionsResponse, TextConte
 
 PREVIEW_WORDS_LIMIT = 3000
 
-FILE_UPLOAD_PARAMS = {
+_FILE_UPLOAD_PARAMS = {
     "file": {
         "description": "File to upload",
         "in": "formData",
@@ -56,43 +56,6 @@ FILE_UPLOAD_PARAMS = {
 }
 
 
-def upload_file_from_request(*, current_user: Account, resource_tenant_id: str | None = None) -> UploadFile:
-    """Validate the multipart request and persist the file under the requested resource tenant."""
-    source_str = request.form.get("source")
-    source: Literal["datasets"] | None = "datasets" if source_str == "datasets" else None
-
-    if "file" not in request.files:
-        raise NoFileUploadedError()
-
-    if len(request.files) > 1:
-        raise TooManyFilesError()
-    file = request.files["file"]
-
-    if not file.filename:
-        raise FilenameNotExistsError
-    if source == "datasets" and not current_user.is_dataset_editor:
-        raise Forbidden()
-
-    if source not in ("datasets", None):
-        source = None
-
-    try:
-        return FileService(db.engine).upload_file(
-            filename=file.filename,
-            content=file.stream.read(),
-            mimetype=file.mimetype,
-            user=current_user,
-            tenant_id=resource_tenant_id,
-            source=source,
-        )
-    except services.errors.file.FileTooLargeError as file_too_large_error:
-        raise FileTooLargeError(file_too_large_error.description)
-    except services.errors.file.UnsupportedFileTypeError:
-        raise UnsupportedFileTypeError()
-    except services.errors.file.BlockedFileExtensionError as blocked_extension_error:
-        raise BlockedFileExtensionError(blocked_extension_error.description)
-
-
 @console_ns.route("/files/upload")
 class FileApi(Resource):
     @setup_required
@@ -118,11 +81,42 @@ class FileApi(Resource):
     @login_required
     @account_initialization_required
     @cloud_edition_billing_resource_check("documents")
-    @console_ns.doc(consumes=["multipart/form-data"], params=FILE_UPLOAD_PARAMS)
+    @console_ns.doc(consumes=["multipart/form-data"], params=_FILE_UPLOAD_PARAMS)
     @console_ns.response(201, "File uploaded successfully", console_ns.models[FileResponse.__name__])
     @with_current_user
     def post(self, current_user: Account):
-        upload_file = upload_file_from_request(current_user=current_user)
+        source_str = request.form.get("source")
+        source: Literal["datasets"] | None = "datasets" if source_str == "datasets" else None
+
+        if "file" not in request.files:
+            raise NoFileUploadedError()
+
+        if len(request.files) > 1:
+            raise TooManyFilesError()
+        file = request.files["file"]
+
+        if not file.filename:
+            raise FilenameNotExistsError
+        if source == "datasets" and not current_user.is_dataset_editor:
+            raise Forbidden()
+
+        if source not in ("datasets", None):
+            source = None
+
+        try:
+            upload_file = FileService(db.engine).upload_file(
+                filename=file.filename,
+                content=file.stream.read(),
+                mimetype=file.mimetype,
+                user=current_user,
+                source=source,
+            )
+        except services.errors.file.FileTooLargeError as file_too_large_error:
+            raise FileTooLargeError(file_too_large_error.description)
+        except services.errors.file.UnsupportedFileTypeError:
+            raise UnsupportedFileTypeError()
+        except services.errors.file.BlockedFileExtensionError as blocked_extension_error:
+            raise BlockedFileExtensionError(blocked_extension_error.description)
 
         return dump_response(FileResponse, upload_file), 201
 

api/controllers/console/knowledge_fs_proxy.py

@@ -1,332 +0,0 @@
-"""Authenticated transport adapter for the Console-to-KnowledgeFS proxy.
-
-These raw Blueprint routes deliberately stay outside Dify's OpenAPI surface:
-KnowledgeFS owns the wire contract consumed by the frontend. The catch-all path
-avoids resource-specific Dify controllers, while the forwarding module consumes
-only the operations explicitly enabled by Dify's product registry. The registry
-can be validated explicitly against the pinned KnowledgeFS contract during development.
-Console auth and contract-specific dataset RBAC run before forwarding. Request
-bodies are capped at 64 MiB, JSON and binary responses have separate bounds,
-SSE responses remain streaming with a bounded idle read timeout, and only safe
-response headers are exposed. Upstream 401 responses become 502 so they cannot
-trigger Dify browser-session recovery; resource-level 403 responses remain 403.
-"""
-
-from __future__ import annotations
-
-import logging
-from collections.abc import Callable, Iterator
-from functools import wraps
-from http import HTTPStatus
-from typing import NoReturn, cast
-
-import httpx
-from flask import Response, request, stream_with_context
-from flask.typing import ResponseReturnValue
-from werkzeug.exceptions import (
-    BadGateway,
-    Forbidden,
-    GatewayTimeout,
-    NotFound,
-    RequestEntityTooLarge,
-    ServiceUnavailable,
-)
-
-from configs import dify_config
-from controllers.console import api, bp
-from controllers.console.wraps import (
-    account_initialization_required,
-    cloud_edition_billing_rate_limit_check,
-    setup_required,
-)
-from core.helper import ssrf_proxy
-from libs.login import current_account_with_tenant, login_required
-from services.knowledge_fs_proxy import (
-    KnowledgeFSAccessDeniedError,
-    KnowledgeFSConfigurationError,
-    KnowledgeFSMethod,
-    KnowledgeFSRouteNotAllowedError,
-    KnowledgeFSTimeoutError,
-    KnowledgeFSTransportError,
-    KnowledgeFSUpstreamResponse,
-    authorize_knowledge_fs_request,
-    get_knowledge_fs_operation,
-    proxy_knowledge_fs_request,
-)
-
-logger = logging.getLogger(__name__)
-
-_MAX_PROXY_BODY_BYTES = 64 * 1024 * 1024
-_RESPONSE_HEADER_ALLOWLIST = (
-    "Cache-Control",
-    "Content-Disposition",
-    "Content-Type",
-    "Retry-After",
-    "X-Trace-Id",
-)
-_RESPONSE_HEADER_DENYLIST = frozenset(
-    {
-        "authorization",
-        "connection",
-        "cookie",
-        "keep-alive",
-        "proxy-authenticate",
-        "proxy-authorization",
-        "set-cookie",
-        "te",
-        "trailer",
-        "transfer-encoding",
-        "upgrade",
-    }
-)
-
-
-def _console_api_errors[**P](
-    view: Callable[P, ResponseReturnValue],
-) -> Callable[P, ResponseReturnValue]:
-    """Route raw Blueprint exceptions through the Console API JSON handlers."""
-
-    @wraps(view)
-    def decorated(*args: P.args, **kwargs: P.kwargs) -> ResponseReturnValue:
-        try:
-            return view(*args, **kwargs)
-        except Exception as exc:
-            return api.handle_error(exc)
-
-    return decorated
-
-
-def _knowledge_fs_enabled[**P](
-    view: Callable[P, ResponseReturnValue],
-) -> Callable[P, ResponseReturnValue]:
-    """Hide the complete KnowledgeFS route surface while the bridge is disabled."""
-
-    @wraps(view)
-    def decorated(*args: P.args, **kwargs: P.kwargs) -> ResponseReturnValue:
-        if not dify_config.KNOWLEDGE_FS_ENABLED:
-            raise NotFound()
-        return view(*args, **kwargs)
-
-    return decorated
-
-
-def _translate_proxy_error(exc: Exception, *, tenant_id: str) -> NoReturn:
-    """Map forwarding failures to the stable Console HTTP error surface."""
-    if isinstance(exc, KnowledgeFSRouteNotAllowedError):
-        raise NotFound() from exc
-    if isinstance(exc, KnowledgeFSAccessDeniedError):
-        raise Forbidden() from exc
-    if isinstance(exc, KnowledgeFSConfigurationError):
-        logger.error("KnowledgeFS request was blocked by invalid configuration for tenant_id=%s", tenant_id)
-        raise ServiceUnavailable("KnowledgeFS integration is misconfigured") from exc
-    if isinstance(exc, KnowledgeFSTimeoutError):
-        raise GatewayTimeout("KnowledgeFS request timed out") from exc
-    if isinstance(exc, KnowledgeFSTransportError):
-        logger.warning("KnowledgeFS transport request failed for tenant_id=%s", tenant_id)
-        raise BadGateway("KnowledgeFS is unavailable") from exc
-    raise exc
-
-
-def _knowledge_fs_operation_access_required(
-    view: Callable[[KnowledgeFSMethod, str], ResponseReturnValue],
-) -> Callable[[KnowledgeFSMethod, str], ResponseReturnValue]:
-    """Authorize one declared operation before billing and request-body work."""
-
-    @wraps(view)
-    def decorated(method: KnowledgeFSMethod, upstream_path: str) -> ResponseReturnValue:
-        try:
-            operation = get_knowledge_fs_operation(method, upstream_path)
-        except KnowledgeFSRouteNotAllowedError as exc:
-            raise NotFound() from exc
-
-        current_user, tenant_id = current_account_with_tenant()
-        try:
-            authorize_knowledge_fs_request(
-                account=current_user,
-                tenant_id=tenant_id,
-                operation=operation,
-            )
-        except KnowledgeFSAccessDeniedError as exc:
-            _translate_proxy_error(exc, tenant_id=tenant_id)
-        return view(method, upstream_path)
-
-    return decorated
-
-
-def _request_body() -> bytes:
-    """Read the raw body up to the proxy limit or raise RequestEntityTooLarge."""
-    body = request.stream.read(_MAX_PROXY_BODY_BYTES + 1)
-    if len(body) > _MAX_PROXY_BODY_BYTES:
-        raise RequestEntityTooLarge("KnowledgeFS proxy request body is too large")
-    return body
-
-
-def _stream_response_body(
-    upstream: httpx.Response,
-    *,
-    tenant_id: str,
-    max_response_bytes: int,
-) -> Iterator[bytes]:
-    """Yield one bounded SSE response and always release its pooled connection."""
-    total_bytes = 0
-    try:
-        for chunk in upstream.iter_bytes():
-            total_bytes += len(chunk)
-            if total_bytes > max_response_bytes:
-                logger.warning("KnowledgeFS stream exceeded the proxy limit for tenant_id=%s", tenant_id)
-                raise ssrf_proxy.ResponseTooLargeError(f"response exceeded {max_response_bytes} bytes")
-            yield chunk
-    finally:
-        upstream.close()
-
-
-def _proxy_response(
-    upstream_result: KnowledgeFSUpstreamResponse,
-    *,
-    tenant_id: str,
-    contract_response_headers: tuple[str, ...],
-    max_response_bytes: int,
-) -> Response:
-    """Expose raw content, status, and allowlisted headers from KnowledgeFS.
-
-    Raises:
-        BadGateway: KnowledgeFS rejects the configured server credential.
-        Forbidden: KnowledgeFS denies the account access to the requested resource.
-    """
-    upstream = upstream_result.response
-    if upstream.status_code == HTTPStatus.UNAUTHORIZED:
-        upstream.close()
-        logger.error(
-            "KnowledgeFS rejected the Dify server credential with HTTP %s for tenant_id=%s",
-            upstream.status_code,
-            tenant_id,
-        )
-        raise BadGateway("KnowledgeFS authentication failed")
-    if upstream.status_code == HTTPStatus.FORBIDDEN:
-        upstream.close()
-        raise Forbidden()
-
-    allowed_header_names = dict.fromkeys(
-        name.lower() for name in (*_RESPONSE_HEADER_ALLOWLIST, *contract_response_headers)
-    )
-    headers = {
-        name: value
-        for name in allowed_header_names
-        if name not in _RESPONSE_HEADER_DENYLIST
-        if (value := upstream.headers.get(name)) is not None
-    }
-    if upstream_result.response_kind == "stream":
-        response = Response(
-            stream_with_context(  # pyrefly: ignore[no-matching-overload]
-                _stream_response_body(
-                    upstream,
-                    tenant_id=tenant_id,
-                    max_response_bytes=max_response_bytes,
-                )
-            ),
-            status=upstream.status_code,
-            headers=headers,
-        )
-        response.call_on_close(upstream.close)
-        return response
-
-    try:
-        content = upstream.content
-    finally:
-        upstream.close()
-    return Response(content, status=upstream.status_code, headers=headers)
-
-
-def _proxy_request(method: KnowledgeFSMethod, upstream_path: str) -> Response:
-    """Forward the current raw request and return its filtered upstream response.
-
-    The call performs one outbound KnowledgeFS request. Integration failures are
-    converted to Console HTTP exceptions for the outer JSON error adapter.
-    """
-    if not dify_config.KNOWLEDGE_FS_ENABLED:
-        raise NotFound()
-    current_user, tenant_id = current_account_with_tenant()
-    try:
-        proxy_result = proxy_knowledge_fs_request(
-            account=current_user,
-            method=method,
-            path=upstream_path,
-            tenant_id=tenant_id,
-            accept=request.headers.get("Accept"),
-            content_type=request.content_type,
-            query=request.query_string or None,
-            body=_request_body() if method != "GET" else None,
-            request_headers=request.headers,
-        )
-    except (
-        KnowledgeFSConfigurationError,
-        KnowledgeFSAccessDeniedError,
-        KnowledgeFSRouteNotAllowedError,
-        KnowledgeFSTimeoutError,
-        KnowledgeFSTransportError,
-    ) as exc:
-        _translate_proxy_error(exc, tenant_id=tenant_id)
-    return _proxy_response(
-        proxy_result,
-        tenant_id=tenant_id,
-        contract_response_headers=proxy_result.operation.response_headers,
-        max_response_bytes=proxy_result.operation.max_response_bytes,
-    )
-
-
-@_knowledge_fs_enabled
-@_knowledge_fs_operation_access_required
-@cloud_edition_billing_rate_limit_check("knowledge")
-def _proxy_knowledge_fs_non_get(
-    method: KnowledgeFSMethod,
-    upstream_path: str,
-) -> ResponseReturnValue:
-    """Apply knowledge billing checks to one allowlisted non-GET operation."""
-    return _proxy_request(method, upstream_path)
-
-
-@bp.route(
-    "/knowledge-fs/<path:upstream_path>",
-    methods=["GET", "OPTIONS"],
-    provide_automatic_options=False,
-)
-@_console_api_errors
-@_knowledge_fs_enabled
-@setup_required
-@login_required
-@account_initialization_required
-def proxy_knowledge_fs_get(upstream_path: str) -> ResponseReturnValue:
-    """Forward one authenticated, dataset-readable GET request.
-
-    Args:
-        upstream_path: Relative KFS path captured after the Console proxy prefix.
-
-    Returns:
-        The filtered raw KnowledgeFS response or a Console JSON error response.
-    """
-    if request.method != "GET":
-        raise NotFound()
-    return _proxy_request("GET", upstream_path)
-
-
-@bp.route(
-    "/knowledge-fs/<path:upstream_path>",
-    methods=["DELETE", "PATCH", "POST", "PUT"],
-    provide_automatic_options=False,
-)
-@_console_api_errors
-@_knowledge_fs_enabled
-@setup_required
-@login_required
-@account_initialization_required
-def proxy_knowledge_fs_write(upstream_path: str) -> ResponseReturnValue:
-    """Forward one authenticated non-GET request under its contract access policy.
-
-    Args:
-        upstream_path: Relative KFS path captured after the Console proxy prefix.
-
-    Returns:
-        The filtered raw KnowledgeFS response or a Console JSON error response.
-    """
-    method = cast(KnowledgeFSMethod, request.method)
-    return _proxy_knowledge_fs_non_get(method, upstream_path)

api/controllers/console/onboarding.py

@@ -1,106 +0,0 @@
-"""Console onboarding APIs.
-
-This module keeps Step-by-step Tour persistence account-scoped. Workspace IDs
-are accepted only as presentation overrides; UI-only state such as minimized
-panels or the currently active task stays on the frontend. PATCH requests are
-action-based so callers do not replace server-side arrays with stale snapshots.
-"""
-
-from datetime import datetime
-from typing import Literal, cast
-
-from flask_restx import Resource
-from pydantic import BaseModel, ConfigDict, Field, model_validator
-
-from controllers.common.schema import register_response_schema_models, register_schema_models
-from extensions.ext_database import db
-from fields.base import ResponseModel
-from libs.helper import dump_response
-from libs.login import login_required
-from models import Account
-from services.step_by_step_tour_service import StepByStepTourPatch, StepByStepTourService
-
-from . import console_ns
-from .wraps import account_initialization_required, setup_required, with_current_tenant_id, with_current_user
-
-StepByStepTourAction = Literal[
-    "skip",
-    "complete_task",
-    "uncomplete_task",
-    "enable_current_workspace",
-    "disable_current_workspace",
-]
-StepByStepTourTaskId = Literal["home", "studio", "knowledge", "integration"]
-
-
-class StepByStepTourStatePatchPayload(BaseModel):
-    action: StepByStepTourAction = Field(description="State update action")
-    task_id: StepByStepTourTaskId | None = Field(default=None, description="Task ID for task actions")
-
-    model_config = ConfigDict(extra="forbid")
-
-    @model_validator(mode="after")
-    def validate_patch_shape(self) -> "StepByStepTourStatePatchPayload":
-        task_actions = {"complete_task", "uncomplete_task"}
-        if self.action in task_actions and self.task_id is None:
-            raise ValueError("task_id is required for task actions")
-        if self.action not in task_actions and self.task_id is not None:
-            raise ValueError("task_id is only supported for task actions")
-
-        return self
-
-
-class StepByStepTourStateResponse(ResponseModel):
-    first_workspace_id: str | None = None
-    skipped: bool = False
-    completed_task_ids: list[StepByStepTourTaskId] = Field(default_factory=list)
-    manually_enabled_workspace_ids: list[str] = Field(default_factory=list)
-    manually_disabled_workspace_ids: list[str] = Field(default_factory=list)
-    updated_at: datetime | None = None
-
-
-register_schema_models(console_ns, StepByStepTourStatePatchPayload)
-register_response_schema_models(console_ns, StepByStepTourStateResponse)
-
-
-@console_ns.route("/onboarding/step-by-step-tour/state")
-class StepByStepTourStateApi(Resource):
-    @console_ns.doc("get_step_by_step_tour_state")
-    @console_ns.doc(description="Get account-level Step-by-step Tour state")
-    @console_ns.response(200, "Success", console_ns.models[StepByStepTourStateResponse.__name__])
-    @setup_required
-    @login_required
-    @account_initialization_required
-    @with_current_user
-    @with_current_tenant_id
-    def get(self, current_tenant_id: str, current_user: Account):
-        return dump_response(
-            StepByStepTourStateResponse,
-            StepByStepTourService.get_state(
-                account=current_user,
-                current_tenant_id=current_tenant_id,
-                session=db.session,
-            ),
-        )
-
-    @console_ns.doc("patch_step_by_step_tour_state")
-    @console_ns.doc(description="Update account-level Step-by-step Tour state")
-    @console_ns.expect(console_ns.models[StepByStepTourStatePatchPayload.__name__])
-    @console_ns.response(200, "Success", console_ns.models[StepByStepTourStateResponse.__name__])
-    @setup_required
-    @login_required
-    @account_initialization_required
-    @with_current_user
-    @with_current_tenant_id
-    def patch(self, current_tenant_id: str, current_user: Account):
-        payload = StepByStepTourStatePatchPayload.model_validate(console_ns.payload or {})
-        patch = cast(StepByStepTourPatch, payload.model_dump(exclude_unset=True, exclude_none=True))
-        return dump_response(
-            StepByStepTourStateResponse,
-            StepByStepTourService.patch_state(
-                account=current_user,
-                current_tenant_id=current_tenant_id,
-                patch=patch,
-                session=db.session,
-            ),
-        )

api/controllers/console/remote_files.py

@@ -46,61 +46,6 @@ class GetRemoteFileInfo(Resource):
         ).model_dump(mode="json")
 
 
-def upload_remote_file_from_request(
-    *,
-    current_user: Account,
-    resource_tenant_id: str | None = None,
-) -> FileWithSignedUrl:
-    """Validate the JSON request, fetch its remote file, and persist it under the requested tenant."""
-    payload = RemoteFileUploadPayload.model_validate(console_ns.payload)
-    url = payload.url
-
-    # Try to fetch remote file metadata/content first
-    try:
-        resp = remote_fetcher.make_request("HEAD", url=url)
-        if resp.status_code != httpx.codes.OK:
-            resp = remote_fetcher.make_request("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)}")
-
-    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 remote_fetcher.make_request("GET", url).content
-
-    try:
-        upload_file = FileService(db.engine).upload_file(
-            filename=file_info.filename,
-            content=content,
-            mimetype=file_info.mimetype,
-            user=current_user,
-            tenant_id=resource_tenant_id,
-            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()
-
-    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()),
-    )
-
-
 @console_ns.route("/remote-files/upload")
 class RemoteFileUpload(Resource):
     @console_ns.expect(console_ns.models[RemoteFileUploadPayload.__name__])
@@ -108,8 +53,53 @@ class RemoteFileUpload(Resource):
     @login_required
     @with_current_user
     def post(self, current_user: Account):
-        remote_file = upload_remote_file_from_request(current_user=current_user)
+        payload = RemoteFileUploadPayload.model_validate(console_ns.payload)
+        url = payload.url
+
+        # Try to fetch remote file metadata/content first
+        try:
+            resp = remote_fetcher.make_request("HEAD", url=url)
+            if resp.status_code != httpx.codes.OK:
+                resp = remote_fetcher.make_request("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)}")
+
+        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 remote_fetcher.make_request("GET", url).content
+
+        try:
+            upload_file = FileService(db.engine).upload_file(
+                filename=file_info.filename,
+                content=content,
+                mimetype=file_info.mimetype,
+                user=current_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 (
-            remote_file.model_dump(mode="json"),
+            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,
         )

api/controllers/console/socketio/workflow.py

@@ -98,7 +98,6 @@ def handle_collaboration_event(sid, data):
     6. workflow_update
     7. comments_update
     8. node_panel_presence
-    9. graph_view_state (session reports tab visibility; drives leader election)
     """
     return collaboration_service.relay_collaboration_event(sid, data)
 

api/controllers/console/workflow_run_archive.py

@@ -4,16 +4,20 @@ from http import HTTPStatus
 from flask import redirect
 from flask_restx import Resource
 from pydantic import BaseModel, Field
-from werkzeug.exceptions import Conflict, Forbidden, NotFound
+from werkzeug.exceptions import Conflict, NotFound
 
 from controllers.common.fields import RedirectResponse
 from controllers.common.schema import register_response_schema_models, register_schema_models
 from controllers.console import console_ns
 from controllers.console.wraps import (
+    RBACPermission,
+    RBACResourceScope,
     account_initialization_required,
     cloud_edition_billing_enabled,
     cloud_edition_billing_paid_plan_required,
+    is_admin_or_owner_required,
     only_edition_cloud,
+    rbac_permission_required,
     setup_required,
 )
 from extensions.ext_database import db
@@ -21,7 +25,6 @@ from fields.base import ResponseModel
 from libs.archive_storage import get_export_storage
 from libs.helper import dump_response
 from libs.login import current_account_with_tenant, login_required
-from models import TenantAccountRole
 from services.retention.workflow_run.archive_download_preparation import ARCHIVE_DOWNLOAD_MIME_TYPE
 from services.retention.workflow_run.archive_download_task_cache import (
     WorkflowRunArchiveDownloadStatus,
@@ -95,13 +98,11 @@ register_response_schema_models(
 )
 
 
-def _current_owner_or_admin_ids() -> tuple[str, str]:
-    """Return current Cloud workspace IDs for an owner or admin, independently of enterprise RBAC."""
+def _current_ids() -> tuple[str, str]:
+    """Return current `(tenant_id, account_id)` or raise when no workspace is selected."""
     current_user, current_tenant_id = current_account_with_tenant()
     if not current_tenant_id:
         raise NotFound("Current workspace not found")
-    if not TenantAccountRole.is_privileged_role(current_user.current_role):
-        raise Forbidden()
     return current_tenant_id, current_user.id
 
 
@@ -123,8 +124,12 @@ class WorkflowRunArchivesApi(Resource):
     @only_edition_cloud
     @cloud_edition_billing_enabled
     @cloud_edition_billing_paid_plan_required
+    @is_admin_or_owner_required
+    @rbac_permission_required(
+        RBACResourceScope.WORKSPACE, RBACPermission.WORKSPACE_ROLE_MANAGE, resource_required=False
+    )
     def get(self):
-        tenant_id, _ = _current_owner_or_admin_ids()
+        tenant_id, _ = _current_ids()
         return dump_response(WorkflowRunArchiveListResponse, list_workflow_run_archives(db.session(), tenant_id))
 
 
@@ -144,8 +149,12 @@ class WorkflowRunArchiveDownloadsApi(Resource):
     @only_edition_cloud
     @cloud_edition_billing_enabled
     @cloud_edition_billing_paid_plan_required
+    @is_admin_or_owner_required
+    @rbac_permission_required(
+        RBACResourceScope.WORKSPACE, RBACPermission.WORKSPACE_ROLE_MANAGE, resource_required=False
+    )
     def post(self):
-        tenant_id, account_id = _current_owner_or_admin_ids()
+        tenant_id, account_id = _current_ids()
         payload = WorkflowRunArchiveDownloadPayload.model_validate(console_ns.payload or {})
         try:
             task = create_workflow_run_archive_download_task(
@@ -171,8 +180,12 @@ class WorkflowRunArchiveDownloadApi(Resource):
     @only_edition_cloud
     @cloud_edition_billing_enabled
     @cloud_edition_billing_paid_plan_required
+    @is_admin_or_owner_required
+    @rbac_permission_required(
+        RBACResourceScope.WORKSPACE, RBACPermission.WORKSPACE_ROLE_MANAGE, resource_required=False
+    )
     def get(self, download_id: str):
-        tenant_id, _ = _current_owner_or_admin_ids()
+        tenant_id, _ = _current_ids()
         try:
             task = get_workflow_run_archive_download_task(tenant_id=tenant_id, download_id=download_id)
         except WorkflowRunArchiveDownloadTaskNotFoundError as exc:
@@ -196,8 +209,12 @@ class WorkflowRunArchiveDownloadFileApi(Resource):
     @only_edition_cloud
     @cloud_edition_billing_enabled
     @cloud_edition_billing_paid_plan_required
+    @is_admin_or_owner_required
+    @rbac_permission_required(
+        RBACResourceScope.WORKSPACE, RBACPermission.WORKSPACE_ROLE_MANAGE, resource_required=False
+    )
     def get(self, download_id: str):
-        tenant_id, _ = _current_owner_or_admin_ids()
+        tenant_id, _ = _current_ids()
         try:
             task = get_ready_workflow_run_archive_download_task(tenant_id=tenant_id, download_id=download_id)
         except WorkflowRunArchiveDownloadTaskNotFoundError as exc:

api/controllers/service_api/app/audio.py

@@ -101,7 +101,7 @@ class AudioApi(Resource):
 
         Accepts an audio file upload and returns the transcribed text.
         """
-        file = request.files.get("file")
+        file = request.files["file"]
 
         try:
             response = AudioService.transcript_asr(

api/controllers/service_api/dataset/dataset.py

@@ -531,22 +531,14 @@ class DatasetListApi(DatasetApiResource):
         except services.errors.dataset.DatasetNameDuplicateError:
             raise DatasetNameDuplicateError()
 
-        if dify_config.RBAC_ENABLED:
-            if payload.permission == DatasetPermissionEnum.ALL_TEAM:
-                RBACService.DatasetAccess.replace_whitelist(
-                    tenant_id,
-                    current_user.id,
-                    dataset.id,
-                    ReplaceMemberBindings(scope=RBACResourceWhitelistScope.ALL),
-                )
-                initialize_created_app_rbac_access_task.delay(tenant_id, current_user.id, dataset_id=dataset.id)
-            else:
-                RBACService.DatasetAccess.replace_whitelist(
-                    tenant_id,
-                    current_user.id,
-                    dataset.id,
-                    ReplaceMemberBindings(scope=RBACResourceWhitelistScope.SPECIFIC),
-                )
+        if payload.permission == DatasetPermissionEnum.ALL_TEAM and dify_config.RBAC_ENABLED:
+            RBACService.DatasetAccess.replace_whitelist(
+                tenant_id,
+                current_user.id,
+                dataset.id,
+                ReplaceMemberBindings(scope=RBACResourceWhitelistScope.ALL),
+            )
+            initialize_created_app_rbac_access_task.delay(tenant_id, current_user.id, dataset_id=dataset.id)
 
         return _dump_service_dataset_detail(dataset, session=session), 200
 

api/controllers/web/audio.py

@@ -76,7 +76,7 @@ class AudioApi(WebApiResource):
     @web_ns.response(200, "Success", web_ns.models[AudioToTextResponse.__name__])
     def post(self, app_model: App, end_user: EndUser):
         """Convert audio to text"""
-        file = request.files.get("file")
+        file = request.files["file"]
 
         try:
             response = AudioService.transcript_asr(

api/core/app/app_config/easy_ui_based_app/model_config/converter.py

@@ -62,6 +62,8 @@ class ModelConfigConverter:
         if "stop" in completion_params:
             stop = completion_params["stop"]
             del completion_params["stop"]
+        # Workflow-only setting; never forward it to providers.
+        completion_params.pop("first_token_timeout_ms", None)
 
         model_schema = model_type_instance.get_model_schema(model_config.model, model_credentials)
 

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

@@ -625,11 +625,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
                 message=message_snapshot,
                 user=user,
                 stream=stream,
-                draft_var_saver_factory=self._get_draft_var_saver_factory(
-                    invoke_from,
-                    account=user,
-                    tenant_id=application_generate_entity.app_config.tenant_id,
-                ),
+                draft_var_saver_factory=self._get_draft_var_saver_factory(invoke_from, account=user),
             )
 
             return AdvancedChatAppGenerateResponseConverter.convert(response=response, invoke_from=invoke_from)

api/core/app/apps/agent_app/app_generator.py

@@ -540,9 +540,6 @@ class AgentAppGenerator(MessageBasedAppGenerator):
                 base_url=dify_config.AGENT_BACKEND_BASE_URL,
                 use_fake=dify_config.AGENT_BACKEND_USE_FAKE,
                 fake_scenario=dify_config.AGENT_BACKEND_FAKE_SCENARIO,
-                stream_read_timeout_seconds=dify_config.AGENT_BACKEND_STREAM_READ_TIMEOUT_SECONDS,
-                stream_max_reconnects=dify_config.AGENT_BACKEND_STREAM_MAX_RECONNECTS,
-                stream_run_timeout_seconds=dify_config.AGENT_BACKEND_RUN_TIMEOUT_SECONDS,
             ),
             event_adapter=AgentBackendRunEventAdapter(),
             session_store=AgentAppRuntimeSessionStore(),

api/core/app/apps/agent_app/app_runner.py

@@ -941,64 +941,48 @@ class AgentAppRunner:
             if pending_text:
                 persist_answer_text(pending_text)
 
-        try:
-            public_events = self._agent_backend_client.stream_events(
-                run_id,
-                should_stop=queue_manager.is_stopped,
-            )
-            for public_event in public_events:
+        for public_event in self._agent_backend_client.stream_events(run_id):
+            if queue_manager.is_stopped():
+                flush_pending_agent_message_text()
+                self._cancel_run(run_id)
+                raise GenerateTaskStoppedError()
+            for internal_event in self._event_adapter.adapt(public_event):
                 if queue_manager.is_stopped():
                     flush_pending_agent_message_text()
                     self._cancel_run(run_id)
                     raise GenerateTaskStoppedError()
-                for internal_event in self._event_adapter.adapt(public_event):
-                    if queue_manager.is_stopped():
-                        flush_pending_agent_message_text()
-                        self._cancel_run(run_id)
-                        raise GenerateTaskStoppedError()
-                    if internal_event.type in (
-                        AgentBackendInternalEventType.RUN_STARTED,
-                        AgentBackendInternalEventType.STREAM_EVENT,
-                        AgentBackendInternalEventType.AGENT_MESSAGE_DELTA,
-                    ):
-                        if isinstance(internal_event, AgentBackendAgentMessageDeltaInternalEvent):
-                            debounced_delta = text_delta_debouncer.push(internal_event.delta)
-                            if debounced_delta:
-                                persist_answer_text(debounced_delta)
-                            continue
-
-                        if isinstance(internal_event, AgentBackendStreamInternalEvent):
-                            flush_pending_agent_message_text()
-                            try:
-                                process_recorder.handle_stream_event(internal_event)
-                            except Exception:
-                                db.session.rollback()
-                                logger.warning(
-                                    "Failed to persist Agent App process event: run_id=%s message_id=%s event_kind=%s",
-                                    run_id,
-                                    message_id,
-                                    internal_event.event_kind,
-                                    exc_info=True,
-                                )
-                            continue
+                if internal_event.type in (
+                    AgentBackendInternalEventType.RUN_STARTED,
+                    AgentBackendInternalEventType.STREAM_EVENT,
+                    AgentBackendInternalEventType.AGENT_MESSAGE_DELTA,
+                ):
+                    if isinstance(internal_event, AgentBackendAgentMessageDeltaInternalEvent):
+                        debounced_delta = text_delta_debouncer.push(internal_event.delta)
+                        if debounced_delta:
+                            persist_answer_text(debounced_delta)
                         continue
-                    flush_pending_agent_message_text()
-                    terminal = internal_event
-                    break
-                if terminal is not None:
-                    break
-        except GenerateTaskStoppedError:
-            raise
-        except Exception as error:
-            flush_pending_agent_message_text()
-            self._cancel_run(run_id)
-            if queue_manager.is_stopped():
-                raise GenerateTaskStoppedError() from error
-            raise
+
+                    if isinstance(internal_event, AgentBackendStreamInternalEvent):
+                        flush_pending_agent_message_text()
+                        try:
+                            process_recorder.handle_stream_event(internal_event)
+                        except Exception:
+                            db.session.rollback()
+                            logger.warning(
+                                "Failed to persist Agent App process event: run_id=%s message_id=%s event_kind=%s",
+                                run_id,
+                                message_id,
+                                internal_event.event_kind,
+                                exc_info=True,
+                            )
+                        continue
+                    continue
+                flush_pending_agent_message_text()
+                terminal = internal_event
+                break
+            if terminal is not None:
+                break
         flush_pending_agent_message_text()
-        if queue_manager.is_stopped():
-            self._cancel_run(run_id)
-            raise GenerateTaskStoppedError()
         return terminal, process_recorder
 
     def _cancel_run(self, run_id: str) -> None:

api/core/app/apps/base_app_generator.py

@@ -32,7 +32,6 @@ class _DebuggerDraftVariableSaver:
         self,
         *,
         account: Account,
-        tenant_id: str,
         app_id: str,
         node_id: str,
         node_type: NodeType,
@@ -40,7 +39,6 @@ class _DebuggerDraftVariableSaver:
         enclosing_node_id: str | None = None,
     ) -> None:
         self._account = account
-        self._tenant_id = tenant_id
         self._app_id = app_id
         self._node_id = node_id
         self._node_type = node_type
@@ -51,7 +49,6 @@ class _DebuggerDraftVariableSaver:
         with Session(db.engine) as session, session.begin():
             DraftVariableSaverImpl(
                 session=session,
-                tenant_id=self._tenant_id,
                 app_id=self._app_id,
                 node_id=self._node_id,
                 node_type=self._node_type,
@@ -290,12 +287,7 @@ class BaseAppGenerator:
 
     @final
     @staticmethod
-    def _get_draft_var_saver_factory(
-        invoke_from: InvokeFrom,
-        account: Account | EndUser,
-        *,
-        tenant_id: str,
-    ) -> DraftVariableSaverFactory:
+    def _get_draft_var_saver_factory(invoke_from: InvokeFrom, account: Account | EndUser) -> DraftVariableSaverFactory:
         if invoke_from == InvokeFrom.DEBUGGER:
             assert isinstance(account, Account)
 
@@ -308,7 +300,6 @@ class BaseAppGenerator:
             ) -> DraftVariableSaver:
                 return _DebuggerDraftVariableSaver(
                     account=account,
-                    tenant_id=tenant_id,
                     app_id=app_id,
                     node_id=node_id,
                     node_type=node_type,

api/core/app/apps/base_app_queue_manager.py

@@ -21,7 +21,6 @@ from core.app.entities.queue_entities import (
     WorkflowQueueMessage,
 )
 from extensions.ext_redis import redis_client
-from graphon.graph_engine.manager import GraphEngineManager
 from graphon.runtime import GraphRuntimeState
 
 logger = logging.getLogger(__name__)
@@ -52,9 +51,6 @@ class AppQueueManager(ABC):
         self._graph_runtime_state: GraphRuntimeState | None = None
         self._stopped_cache: TTLCache[tuple, bool] = TTLCache(maxsize=1, ttl=1)
         self._cache_lock = threading.Lock()
-        self._execution_terminal = threading.Event()
-        self._abort_sent = threading.Event()
-        self._lifecycle_lock = threading.Lock()
 
     def listen(self):
         """
@@ -63,7 +59,7 @@ class AppQueueManager(ABC):
         """
         # wait for APP_MAX_EXECUTION_TIME seconds to stop listen
         listen_timeout = dify_config.APP_MAX_EXECUTION_TIME
-        start_time = time.monotonic()
+        start_time = time.time()
         last_ping_time: int | float = 0
         try:
             while True:
@@ -76,14 +72,8 @@ class AppQueueManager(ABC):
                 except queue.Empty:
                     continue
                 finally:
-                    elapsed_time = time.monotonic() - start_time
-                    timed_out = elapsed_time >= listen_timeout
-                    manually_stopped = self._is_stopped()
-                    if not self._execution_terminal.is_set() and (timed_out or manually_stopped):
-                        reason = (
-                            f"App execution exceeded {listen_timeout} seconds" if timed_out else "App task was stopped"
-                        )
-                        self._abort_execution(reason)
+                    elapsed_time = time.time() - start_time
+                    if elapsed_time >= listen_timeout or self._is_stopped():
                         # publish two messages to make sure the client can receive the stop signal
                         # and stop listening after the stop signal processed
                         self.publish(
@@ -94,33 +84,16 @@ class AppQueueManager(ABC):
                         self.publish(QueuePingEvent(), PublishFrom.TASK_PIPELINE)
                         last_ping_time = elapsed_time // 10
         finally:
-            if not self._execution_terminal.is_set():
-                self._abort_execution("Client response stream closed before app execution completed")
             self._graph_runtime_state = None  # Release reference once consumers finish or close the generator.
 
-    def stop_listen(self, *, execution_terminal: bool = False):
+    def stop_listen(self):
         """
         Stop listen to queue
         :return:
         """
-        if execution_terminal:
-            self._execution_terminal.set()
         self._clear_task_belong_cache()
         self._q.put(None)
 
-    def _abort_execution(self, reason: str) -> None:
-        """Propagate response timeout/disconnect to legacy and GraphEngine runners."""
-        with self._lifecycle_lock:
-            if self._execution_terminal.is_set() or self._abort_sent.is_set():
-                return
-            self._abort_sent.set()
-
-        try:
-            self.set_stop_flag_no_user_check(self._task_id)
-            GraphEngineManager(redis_client).send_stop_command(self._task_id, reason=reason)
-        except Exception:
-            logger.exception("Failed to abort app execution for task %s", self._task_id)
-
     def _clear_task_belong_cache(self) -> None:
         """
         Remove the task belong cache key once listening is finished.

api/core/app/apps/message_based_app_queue_manager.py

@@ -45,7 +45,7 @@ class MessageBasedAppQueueManager(AppQueueManager):
         if isinstance(
             event, QueueStopEvent | QueueErrorEvent | QueueMessageEndEvent | QueueAdvancedChatMessageEndEvent
         ):
-            self.stop_listen(execution_terminal=True)
+            self.stop_listen()
 
         if pub_from == PublishFrom.APPLICATION_MANAGER and self._is_stopped():
             if self._app_mode == AppMode.ADVANCED_CHAT.value:

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

@@ -349,7 +349,6 @@ class PipelineGenerator(BaseAppGenerator):
             draft_var_saver_factory = self._get_draft_var_saver_factory(
                 invoke_from,
                 user,
-                tenant_id=pipeline.tenant_id,
             )
             # return response or stream generator
             response = self._handle_response(

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

@@ -42,7 +42,7 @@ class PipelineQueueManager(AppQueueManager):
             | QueueWorkflowFailedEvent
             | QueueWorkflowPartialSuccessEvent,
         ):
-            self.stop_listen(execution_terminal=True)
+            self.stop_listen()
 
         if pub_from == PublishFrom.APPLICATION_MANAGER and self._is_stopped():
             raise GenerateTaskStoppedError()

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

@@ -399,11 +399,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
 
             worker_thread.start()
 
-            draft_var_saver_factory = self._get_draft_var_saver_factory(
-                invoke_from,
-                user,
-                tenant_id=app_model.tenant_id,
-            )
+            draft_var_saver_factory = self._get_draft_var_saver_factory(invoke_from, user)
 
             # return response or stream generator
             response = self._handle_response(

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

@@ -41,4 +41,4 @@ class WorkflowAppQueueManager(AppQueueManager):
             | QueueWorkflowFailedEvent
             | QueueWorkflowPartialSuccessEvent,
         ):
-            self.stop_listen(execution_terminal=True)
+            self.stop_listen()

api/core/app/apps/workflow_app_runner.py

@@ -26,7 +26,6 @@ from core.app.entities.queue_entities import (
     QueueNodeSucceededEvent,
     QueueReasoningChunkEvent,
     QueueRetrieverResourcesEvent,
-    QueueStopEvent,
     QueueTextChunkEvent,
     QueueWorkflowFailedEvent,
     QueueWorkflowPartialSuccessEvent,
@@ -425,12 +424,7 @@ class WorkflowBasedAppRunner:
                     QueueWorkflowFailedEvent(error=event.error, exceptions_count=event.exceptions_count)
                 )
             case GraphRunAbortedEvent():
-                self._publish_event(
-                    QueueStopEvent(
-                        stopped_by=QueueStopEvent.StopBy.USER_MANUAL,
-                        reason=event.reason or "Workflow execution aborted",
-                    )
-                )
+                self._publish_event(QueueWorkflowFailedEvent(error=event.reason or "Unknown error", exceptions_count=0))
             case GraphRunPausedEvent():
                 runtime_state = workflow_entry.graph_engine.graph_runtime_state
                 paused_nodes = runtime_state.get_paused_nodes()

api/core/app/entities/queue_entities.py

@@ -500,15 +500,11 @@ class QueueStopEvent(AppQueueEvent):
 
     event: QueueEvent = QueueEvent.STOP
     stopped_by: StopBy
-    reason: str | None = None
 
     def get_stop_reason(self) -> str:
         """
         To stop reason
         """
-        if self.reason:
-            return self.reason
-
         reason_mapping = {
             QueueStopEvent.StopBy.USER_MANUAL: "Stopped by user.",
             QueueStopEvent.StopBy.ANNOTATION_REPLY: "Stopped by annotation reply.",

api/core/app/llm/model_access.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import logging
 from copy import deepcopy
 from typing import Any
 
@@ -14,6 +15,8 @@ from graphon.nodes.llm.entities import ModelConfig
 from graphon.nodes.llm.exc import LLMModeRequiredError, ModelNotExistError
 from graphon.nodes.llm.protocols import CredentialsProvider
 
+logger = logging.getLogger(__name__)
+
 
 class DifyCredentialsProvider:
     """Resolves and returns LLM credentials for a given provider and model.
@@ -128,21 +131,35 @@ def build_dify_model_access(run_context: DifyRunContext) -> tuple[CredentialsPro
     )
 
 
-def _normalize_completion_params(completion_params: dict[str, Any]) -> tuple[dict[str, Any], list[str]]:
+def _normalize_completion_params(
+    completion_params: dict[str, Any],
+) -> tuple[dict[str, Any], list[str], float | None]:
     """
-    Split node-level completion params into provider parameters and stop sequences.
+    Split node-level completion params into provider parameters, stop sequences,
+    and the first-token timeout.
 
     Workflow LLM-compatible nodes still consume runtime invocation settings from
-    ``ModelInstance.parameters`` and ``ModelInstance.stop``. Keep the
-    ``ModelInstance`` view and the returned config entity aligned here so callers
-    do not need to duplicate normalization logic.
+    ``ModelInstance.parameters``, ``ModelInstance.stop`` and
+    ``ModelInstance.first_token_timeout``. Keep the ``ModelInstance`` view and the
+    returned config entity aligned here so callers do not need to duplicate
+    normalization logic.
+
+    ``first_token_timeout_ms`` never reaches providers; this is the only ms->s
+    conversion on the path. Invalid values disable the gate.
     """
     normalized_parameters = dict(completion_params)
     stop = normalized_parameters.pop("stop", [])
     if not isinstance(stop, list) or not all(isinstance(item, str) for item in stop):
         stop = []
 
-    return normalized_parameters, stop
+    raw_timeout_ms = normalized_parameters.pop("first_token_timeout_ms", None)
+    first_token_timeout: float | None = None
+    if isinstance(raw_timeout_ms, (int, float)) and not isinstance(raw_timeout_ms, bool) and raw_timeout_ms > 0:
+        first_token_timeout = float(raw_timeout_ms) / 1000
+    elif raw_timeout_ms is not None:
+        logger.debug("Ignoring invalid first_token_timeout_ms in completion_params: %r", raw_timeout_ms)
+
+    return normalized_parameters, stop, first_token_timeout
 
 
 def fetch_model_config(
@@ -178,12 +195,13 @@ def fetch_model_config(
     if model_schema is None:
         raise ModelNotExistError(f"Model {node_data_model.name} schema does not exist.")
 
-    parameters, stop = _normalize_completion_params(node_data_model.completion_params)
+    parameters, stop, first_token_timeout = _normalize_completion_params(node_data_model.completion_params)
     model_instance.provider = node_data_model.provider
     model_instance.model_name = node_data_model.name
     model_instance.credentials = credentials
     model_instance.parameters = parameters
     model_instance.stop = tuple(stop)
+    model_instance.first_token_timeout = first_token_timeout
 
     return model_instance, ModelConfigWithCredentialsEntity(
         provider=node_data_model.provider,

api/core/helper/ssrf_proxy.py

@@ -47,24 +47,6 @@ class MaxRetriesExceededError(ValueError):
     pass
 
 
-class ResponseLimitError(ValueError):
-    """Base error for responses that cannot be safely bounded."""
-
-    pass
-
-
-class ResponseTooLargeError(ResponseLimitError):
-    """Raised when an identity response exceeds the configured byte limit."""
-
-    pass
-
-
-class UnsupportedResponseEncodingError(ResponseLimitError):
-    """Raised when response encoding prevents safe decoded-size enforcement."""
-
-    pass
-
-
 request_error = httpx.RequestError
 max_retries_exceeded_error = MaxRetriesExceededError
 
@@ -160,31 +142,7 @@ def _inject_trace_headers(headers: Headers | None) -> Headers:
     return headers
 
 
-def make_request(
-    method: str,
-    url: str,
-    max_retries: int = SSRF_DEFAULT_MAX_RETRIES,
-    stream_response: bool = False,
-    **kwargs: Any,
-) -> httpx.Response:
-    """Send one SSRF-protected request with optional streaming.
-
-    Args:
-        method: HTTP method sent through the configured SSRF client.
-        url: Absolute request URL.
-        max_retries: Number of retry attempts after the initial request.
-        stream_response: Return an open streaming response that the caller must close.
-        **kwargs: Additional keyword arguments forwarded to ``httpx.Client``.
-
-    Returns:
-        A buffered response, or an open response when ``stream_response`` is true.
-
-    Raises:
-        ToolSSRFError: The configured SSRF proxy rejects the destination.
-        MaxRetriesExceededError: All configured request attempts fail.
-        httpx.RequestError: A request fails while retries are disabled.
-        ValueError: The SSL verification option or request headers are invalid.
-    """
+def make_request(method: str, url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> httpx.Response:
     # Convert requests-style allow_redirects to httpx-style follow_redirects
     if "allow_redirects" in kwargs:
         allow_redirects = kwargs.pop("allow_redirects")
@@ -217,11 +175,6 @@ def make_request(
     # When using a forward proxy, httpx may override the Host header based on the URL.
     # We extract and preserve any explicitly set Host header to support virtual hosting.
     user_provided_host = _get_user_provided_host_header(headers)
-    send_kwargs: dict[str, Any] = {}
-    if "auth" in kwargs:
-        send_kwargs["auth"] = kwargs.pop("auth")
-    if "follow_redirects" in kwargs:
-        send_kwargs["follow_redirects"] = kwargs.pop("follow_redirects")
 
     retries = 0
     while retries <= max_retries:
@@ -232,11 +185,7 @@ def make_request(
             if user_provided_host is not None:
                 headers["host"] = user_provided_host
             kwargs["headers"] = headers
-            request = client.build_request(method=method, url=url, **kwargs)
-            if stream_response:
-                response = client.send(request, stream=True, **send_kwargs)
-            else:
-                response = client.send(request, **send_kwargs)
+            response = client.request(method=method, url=url, **kwargs)
 
             # Check for SSRF protection by Squid proxy
             if response.status_code in (401, 403):
@@ -246,7 +195,6 @@ def make_request(
 
                 # Squid typically identifies itself in Server or Via headers
                 if "squid" in server_header or "squid" in via_header:
-                    response.close()
                     raise ToolSSRFError(
                         f"Access to '{url}' was blocked by SSRF protection. "
                         f"The URL may point to a private or local network address. "
@@ -260,7 +208,6 @@ def make_request(
                     response.status_code,
                     url,
                 )
-                response.close()
 
         except httpx.RequestError as e:
             logger.warning("Request to URL %s failed on attempt %s: %s", url, retries + 1, e)
@@ -273,42 +220,6 @@ def make_request(
     raise MaxRetriesExceededError(f"Reached maximum retries ({max_retries}) for URL {url}")
 
 
-def buffer_response(response: httpx.Response, *, max_response_bytes: int) -> httpx.Response:
-    """Consume one open identity response under a decoded byte limit and close its stream."""
-    if max_response_bytes <= 0:
-        raise ValueError("max_response_bytes must be positive")
-
-    try:
-        content_encoding = response.headers.get("content-encoding", "identity").strip().lower()
-        if content_encoding not in {"", "identity"}:
-            raise UnsupportedResponseEncodingError(f"content encoding {content_encoding} cannot be safely bounded")
-        content = bytearray()
-        for chunk in response.iter_bytes():
-            if len(content) + len(chunk) > max_response_bytes:
-                raise ResponseTooLargeError(f"response exceeded {max_response_bytes} bytes")
-            content.extend(chunk)
-        decoded_headers = {
-            name: value
-            for name, value in response.headers.items()
-            if name.lower() not in {"content-encoding", "content-length", "transfer-encoding"}
-        }
-        try:
-            request = response.request
-        except RuntimeError:
-            request = None
-        return httpx.Response(
-            response.status_code,
-            headers=decoded_headers,
-            content=bytes(content),
-            request=request,
-            extensions=response.extensions,
-            history=response.history,
-            default_encoding=response.default_encoding,
-        )
-    finally:
-        response.close()
-
-
 def get(url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> httpx.Response:
     return make_request("GET", url, max_retries=max_retries, **kwargs)
 

api/core/model_manager.py

@@ -47,6 +47,7 @@ class ModelInstance:
         # Runtime LLM invocation fields.
         self.parameters: Mapping[str, Any] = {}
         self.stop: Sequence[str] = ()
+        self.first_token_timeout: float | None = None
         self.model_type_instance = self.provider_model_bundle.model_type_instance
         self.load_balancing_manager = self._get_load_balancing_manager(
             configuration=provider_model_bundle.configuration,

api/core/plugin/impl/base.py

@@ -25,6 +25,7 @@ from core.plugin.impl.exc import (
     PluginPermissionDeniedError,
     PluginUniqueIdentifierError,
 )
+from core.plugin.impl.first_token_timeout import FirstTokenTimeoutError, first_token_timeout_ctx
 from core.trigger.errors import (
     EventIgnoreError,
     TriggerInvokeError,
@@ -54,6 +55,22 @@ match _plugin_daemon_timeout_config:
     case _:
         plugin_daemon_request_timeout = httpx.Timeout(_plugin_daemon_timeout_config)
 
+
+def _read_timeout_for(first_token_timeout: float | None) -> httpx.Timeout | None:
+    """Replace the daemon request timeout's ``read`` component with the first-token budget.
+
+    Deliberately a replacement rather than a narrowing, so the budget may exceed
+    ``PLUGIN_DAEMON_TIMEOUT`` for slow reasoning models. ``httpx.Timeout(base, read=x)``
+    rejects a ``Timeout`` base, so the other components are copied explicitly.
+    """
+    base = plugin_daemon_request_timeout
+    if not first_token_timeout or first_token_timeout <= 0:
+        return base
+    if base is None:
+        return httpx.Timeout(None, read=first_token_timeout)
+    return httpx.Timeout(connect=base.connect, read=first_token_timeout, write=base.write, pool=base.pool)
+
+
 logger = logging.getLogger(__name__)
 
 PLUGIN_DAEMON_MAX_PATH_LENGTH = 4096
@@ -181,30 +198,49 @@ class BasePluginClient:
         """
         url, headers, prepared_data, params, files = self._prepare_request(path, headers, data, params, files)
 
+        first_token_timeout = first_token_timeout_ctx.get()
+        first_token_gate = bool(first_token_timeout and first_token_timeout > 0)
         stream_kwargs: dict[str, Any] = {
             "method": method,
             "url": url,
             "headers": headers,
             "params": params,
             "files": files,
-            "timeout": plugin_daemon_request_timeout,
+            # The daemon sends nothing before the first token, so the read timeout gates TTFT.
+            "timeout": _read_timeout_for(first_token_timeout),
         }
         if isinstance(prepared_data, dict):
             stream_kwargs["data"] = prepared_data
         elif prepared_data is not None:
             stream_kwargs["content"] = prepared_data
 
+        first_token_seen = False
+
         try:
             with _httpx_client.stream(**stream_kwargs) as response:
                 for raw_line in response.iter_lines():
+                    # Blank frames don't count as the first token, yet each read refreshes the
+                    # read window -- gating relies on no keep-alives before the first token.
                     if not raw_line:
                         continue
                     line = raw_line.decode("utf-8") if isinstance(raw_line, bytes) else raw_line
                     line = line.strip()
                     if line.startswith("data:"):
                         line = line[5:].strip()
-                    if line:
-                        yield line
+                    if not line:
+                        continue
+                    first_token_seen = True
+                    yield line
+        except httpx.ReadTimeout as e:
+            if first_token_gate and not first_token_seen:
+                raise FirstTokenTimeoutError(f"The first token was not received within {first_token_timeout}s.") from e
+            logger.exception("Stream request to Plugin Daemon Service failed")
+            message = "Request to Plugin Daemon Service failed"
+            if first_token_gate:
+                # An inter-token stall past the read window is a plain transport error,
+                # but name the window so it stays traceable to the user's setting.
+                message += f" (stream stalled beyond the {first_token_timeout}s first-token timeout window)"
+            raise PluginDaemonInnerError(code=-500, message=message)
         except httpx.RequestError:
             logger.exception("Stream request to Plugin Daemon Service failed")
             raise PluginDaemonInnerError(code=-500, message="Request to Plugin Daemon Service failed")

api/core/plugin/impl/first_token_timeout.py

@@ -0,0 +1,27 @@
+"""First-token timeout plumbing for LLM streaming through the plugin daemon.
+
+Configured per model as ``completion_params.first_token_timeout_ms`` and popped into
+``ModelInstance.first_token_timeout`` by ``_normalize_completion_params`` -- the only
+ms->s conversion; everything below the pop point is seconds. ``DifyPreparedLLM`` sets
+the ContextVar around invocation, and ``BasePluginClient._stream_request`` applies it
+as the per-request httpx ``read`` timeout. The daemon sends neither response headers
+nor keep-alives before the first token, so the read timeout measures
+time-to-first-token directly.
+
+The ContextVar only reaches the transport on the thread that set it; a
+background-thread stream consumer would read ``None`` and the gate fails open.
+"""
+
+from contextvars import ContextVar
+
+from graphon.model_runtime.errors.invoke import InvokeError
+
+
+class FirstTokenTimeoutError(InvokeError):
+    """The model did not stream its first token within the configured budget."""
+
+    description = "The first streamed token was not received in time."
+
+
+# Seconds; None or non-positive disables the gate.
+first_token_timeout_ctx: ContextVar[float | None] = ContextVar("first_token_timeout", default=None)

api/core/rag/extractor/watercrawl/client.py

@@ -131,10 +131,7 @@ class WaterCrawlAPIClient(BaseAPIClient):
         content_type = response.headers.get("Content-Type", "")
         media_type = content_type.split(";", 1)[0].strip().lower()
         if media_type == "application/json":
-            try:
-                return response.json() or {}
-            except ValueError as exc:
-                raise ValueError("Invalid JSON response from WaterCrawl") from exc
+            return response.json() or {}
 
         if media_type == "application/octet-stream":
             return response.content

api/core/rag/extractor/watercrawl/exceptions.py

@@ -1,15 +1,5 @@
-"""WaterCrawl domain exceptions.
-
-These exceptions are constructed from upstream HTTP responses, which may be
-JSON API errors or plain text/HTML proxy errors. Keep the exception type stable
-even when the body is not JSON so callers can handle WaterCrawl failures by
-domain type instead of low-level parser errors.
-"""
-
 import json
-from typing import Any, override
-
-from httpx import Response
+from typing import override
 
 
 class WaterCrawlError(Exception):
@@ -17,16 +7,11 @@ class WaterCrawlError(Exception):
 
 
 class WaterCrawlBadRequestError(WaterCrawlError):
-    def __init__(self, response: Response):
+    def __init__(self, response):
         self.status_code = response.status_code
         self.response = response
-        try:
-            data: Any = response.json()
-        except ValueError:
-            data = {}
-        if not isinstance(data, dict):
-            data = {}
-        self.message = data.get("message") or response.text or "Unknown error occurred"
+        data = response.json()
+        self.message = data.get("message", "Unknown error occurred")
         self.errors = data.get("errors", {})
         super().__init__(self.message)
 

api/core/workflow/node_factory.py

@@ -499,9 +499,6 @@ class DifyNodeFactory(NodeFactory):
                     base_url=dify_config.AGENT_BACKEND_BASE_URL,
                     use_fake=dify_config.AGENT_BACKEND_USE_FAKE,
                     fake_scenario=dify_config.AGENT_BACKEND_FAKE_SCENARIO,
-                    stream_read_timeout_seconds=dify_config.AGENT_BACKEND_STREAM_READ_TIMEOUT_SECONDS,
-                    stream_max_reconnects=dify_config.AGENT_BACKEND_STREAM_MAX_RECONNECTS,
-                    stream_run_timeout_seconds=dify_config.AGENT_BACKEND_RUN_TIMEOUT_SECONDS,
                 ),
                 "event_adapter": AgentBackendRunEventAdapter(),
                 # Agent Files §4.6: reback file outputs from the ToolFile row so

api/core/workflow/node_runtime.py

@@ -22,6 +22,7 @@ from core.llm_generator.output_parser.errors import OutputParserError
 from core.llm_generator.output_parser.structured_output import invoke_llm_with_structured_output
 from core.model_manager import ModelInstance
 from core.plugin.impl.exc import PluginDaemonClientSideError, PluginInvokeError
+from core.plugin.impl.first_token_timeout import first_token_timeout_ctx
 from core.plugin.impl.plugin import PluginInstaller
 from core.prompt.utils.prompt_message_util import PromptMessageUtil
 from core.repositories.human_input_repository import (
@@ -147,6 +148,42 @@ class DifyFileReferenceFactory(FileReferenceFactoryProtocol):
         )
 
 
+def _guarded_stream(
+    seconds: float,
+    inner: Generator[Any, None, None],
+) -> Generator[Any, None, None]:
+    """Iterate ``inner`` with the first-token-timeout ContextVar set.
+
+    Keeps the value active for exactly the span of iteration, which is when the
+    plugin-daemon transport reads it. Same-thread only: a background-thread SSE
+    prefetch would not see it and the gate fails open.
+    """
+    token = first_token_timeout_ctx.set(seconds)
+    try:
+        yield from inner
+    finally:
+        first_token_timeout_ctx.reset(token)
+
+
+def _with_first_token_timeout[T](first_token_timeout: float | None, invoke: Callable[[], T]) -> T:
+    """Run ``invoke`` with the first-token-timeout ContextVar applied.
+
+    ``first_token_timeout`` is seconds, from ``ModelInstance.first_token_timeout``.
+    A streaming result is lazy, so its generator is wrapped to keep the ContextVar
+    set during iteration; a non-positive timeout disables the gate.
+    """
+    if first_token_timeout is None or first_token_timeout <= 0:
+        return invoke()
+    token = first_token_timeout_ctx.set(first_token_timeout)
+    try:
+        result = invoke()
+    finally:
+        first_token_timeout_ctx.reset(token)
+    if isinstance(result, Generator):
+        return cast("T", _guarded_stream(first_token_timeout, result))
+    return result
+
+
 class DifyPreparedLLM(LLMProtocol):
     """Workflow-layer adapter that hides the full `ModelInstance` API from `graphon` nodes."""
 
@@ -225,13 +262,16 @@ class DifyPreparedLLM(LLMProtocol):
         stop: Sequence[str] | None,
         stream: bool,
     ) -> LLMResult | Generator[LLMResultChunk, None, None]:
-        return self._model_instance.invoke_llm(
-            prompt_messages=list(prompt_messages),
-            model_parameters=dict(model_parameters),
-            tools=list(tools or []),
-            stop=list(stop or []),
-            stream=stream,
-            request_metadata=self._request_metadata,
+        return _with_first_token_timeout(
+            self._model_instance.first_token_timeout,
+            lambda: self._model_instance.invoke_llm(
+                prompt_messages=list(prompt_messages),
+                model_parameters=dict(model_parameters),
+                tools=list(tools or []),
+                stop=list(stop or []),
+                stream=stream,
+                request_metadata=self._request_metadata,
+            ),
         )
 
     @overload
@@ -266,15 +306,18 @@ class DifyPreparedLLM(LLMProtocol):
         stop: Sequence[str] | None,
         stream: bool,
     ) -> LLMResultWithStructuredOutput | Generator[LLMResultChunkWithStructuredOutput, None, None]:
-        return invoke_llm_with_structured_output(
-            provider=self.provider,
-            model_schema=self.get_model_schema(),
-            model_instance=self._model_instance,
-            prompt_messages=prompt_messages,
-            json_schema=json_schema,
-            model_parameters=model_parameters,
-            stop=list(stop or []),
-            stream=stream,
+        return _with_first_token_timeout(
+            self._model_instance.first_token_timeout,
+            lambda: invoke_llm_with_structured_output(
+                provider=self.provider,
+                model_schema=self.get_model_schema(),
+                model_instance=self._model_instance,
+                prompt_messages=prompt_messages,
+                json_schema=json_schema,
+                model_parameters=model_parameters,
+                stop=list(stop or []),
+                stream=stream,
+            ),
         )
 
     @override

api/core/workflow/nodes/agent_v2/agent_node.py

@@ -5,7 +5,6 @@ from collections.abc import Generator, Mapping, Sequence
 from typing import TYPE_CHECKING, Any, override
 
 from agenton.compositor import CompositorSessionSnapshot
-from dify_agent.protocol import CancelRunRequest
 
 from clients.agent_backend import (
     AgentBackendAgentMessageDeltaInternalEvent,
@@ -474,10 +473,7 @@ class DifyAgentNode(Node[DifyAgentNodeData]):
         """
         stream_event_count = 0
         try:
-            for public_event in self._agent_backend_client.stream_events(
-                run_id,
-                should_stop=self._is_graph_aborted,
-            ):
+            for public_event in self._agent_backend_client.stream_events(run_id):
                 stream_event_count += 1
                 for internal_event in self._event_adapter.adapt(public_event):
                     if internal_event.type == AgentBackendInternalEventType.RUN_STARTED:
@@ -505,7 +501,6 @@ class DifyAgentNode(Node[DifyAgentNodeData]):
                         | AgentBackendDeferredToolCallInternalEvent,
                     ):
                         return internal_event, None
-                    self._cancel_backend_run(run_id, reason="unexpected_event")
                     return None, self._failure_event(
                         inputs={},
                         process_data={},
@@ -514,7 +509,6 @@ class DifyAgentNode(Node[DifyAgentNodeData]):
                         error_type="agent_backend_stream_error",
                     )
         except AgentBackendError as error:
-            self._cancel_backend_run(run_id, reason=self._stream_stop_reason())
             return None, self._failure_event(
                 inputs={},
                 process_data={},
@@ -523,7 +517,6 @@ class DifyAgentNode(Node[DifyAgentNodeData]):
                 error_type=self._agent_backend_error_type(error),
             )
         except Exception as error:
-            self._cancel_backend_run(run_id, reason=self._stream_stop_reason())
             return None, self._failure_event(
                 inputs={},
                 process_data={},
@@ -532,28 +525,8 @@ class DifyAgentNode(Node[DifyAgentNodeData]):
                 error_type="agent_backend_stream_error",
             )
 
-        self._cancel_backend_run(run_id, reason="stream_ended_without_terminal_event")
         return None, None
 
-    def _is_graph_aborted(self) -> bool:
-        """Let Agent SSE consumption observe GraphEngine's cooperative abort state."""
-        try:
-            return self.graph_runtime_state.graph_execution.aborted
-        except (AttributeError, RuntimeError):
-            return False
-
-    def _stream_stop_reason(self) -> str:
-        return "workflow_graph_aborted" if self._is_graph_aborted() else "event_stream_failed"
-
-    def _cancel_backend_run(self, run_id: str, *, reason: str) -> None:
-        try:
-            self._agent_backend_client.cancel_run(
-                run_id,
-                CancelRunRequest(reason=reason, message="Workflow Agent event consumption stopped"),
-            )
-        except Exception:
-            logger.warning("Failed to cancel Workflow Agent backend run: run_id=%s", run_id, exc_info=True)
-
     @staticmethod
     def _record_type_check_metadata(metadata: dict[str, Any], outcome: OutputTypeCheckOutcome) -> None:
         # Surface enough detail in metadata for Inspector / debug logs without

api/core/workflow/nodes/agent_v2/validators.py

@@ -61,33 +61,16 @@ class WorkflowAgentNodeValidator:
 
     @classmethod
     def validate_draft_workflow(cls, *, session: Session, workflow: Workflow) -> None:
-        cls._validate_workflow(
-            session=session,
-            workflow=workflow,
-            require_binding=False,
-            validate_previous_node_topology=False,
-        )
+        cls._validate_workflow(session=session, workflow=workflow, require_binding=False)
 
     @classmethod
     def validate_published_workflow(cls, *, session: Session, workflow: Workflow) -> None:
-        cls._validate_workflow(
-            session=session,
-            workflow=workflow,
-            require_binding=True,
-            validate_previous_node_topology=True,
-        )
+        cls._validate_workflow(session=session, workflow=workflow, require_binding=True)
 
     @classmethod
-    def _validate_workflow(
-        cls,
-        *,
-        session: Session,
-        workflow: Workflow,
-        require_binding: bool,
-        validate_previous_node_topology: bool,
-    ) -> None:
+    def _validate_workflow(cls, *, session: Session, workflow: Workflow, require_binding: bool) -> None:
         graph = workflow.graph_dict
-        topology = _WorkflowGraphTopology.from_graph(graph) if validate_previous_node_topology else None
+        topology = _WorkflowGraphTopology.from_graph(graph)
         for node_id, node_data in cls.iter_agent_v2_nodes(graph):
             cls._validate_node_schema(node_id=node_id, node_data=node_data)
             binding = cls._find_binding(
@@ -202,12 +185,12 @@ class WorkflowAgentNodeValidator:
                 raise WorkflowAgentNodeValidationError(
                     f"Workflow Agent node {binding.node_id} has invalid previous node output ref."
                 )
+            if topology is None:
+                continue
             if len(selector) < 2:
                 raise WorkflowAgentNodeValidationError(
                     f"Workflow Agent node {binding.node_id} has incomplete previous node output ref."
                 )
-            if topology is None:
-                continue
             source_node_id = selector[0]
             if not topology.has_node(source_node_id):
                 raise WorkflowAgentNodeValidationError(

api/dev/generate_knowledge_fs_contract.py

@@ -1,255 +0,0 @@
-"""Validate Dify Console KnowledgeFS declarations against a pinned OpenAPI document.
-
-The OpenAPI document is exported only during explicit development validation. Runtime declarations live with Dify
-product policy; this module validates their transport metadata without generating a complete operation catalog.
-"""
-
-from __future__ import annotations
-
-import argparse
-import hashlib
-import json
-import subprocess
-import sys
-import tempfile
-from pathlib import Path
-from typing import Any, Literal, TypedDict
-
-API_ROOT = Path(__file__).resolve().parents[1]
-if str(API_ROOT) not in sys.path:
-    sys.path.insert(0, str(API_ROOT))
-
-WORKSPACE_ROOT = API_ROOT.parent
-LOCK_PATH = API_ROOT / "knowledge-fs-contract.lock.json"
-DEFAULT_REPOSITORY = WORKSPACE_ROOT.parent / "knowledge-fs"
-OPENAPI_METHODS = ("delete", "get", "head", "options", "patch", "post", "put", "trace")
-PROXY_METHODS = frozenset({"delete", "get", "patch", "post", "put"})
-
-
-class ContractDeclaration(TypedDict):
-    """KnowledgeFS transport contract declared by one Dify Console registry entry."""
-
-    operation_id: str
-    method: str
-    path: str
-    required_scope: str | None
-    response_kind: str
-    max_response_bytes: int
-    request_headers: tuple[str, ...]
-    response_headers: tuple[str, ...]
-    response_media_types: tuple[str, ...]
-
-
-type DeclarationField = Literal[
-    "method",
-    "path",
-    "required_scope",
-    "response_kind",
-    "max_response_bytes",
-    "request_headers",
-    "response_headers",
-    "response_media_types",
-]
-
-DECLARATION_FIELDS: tuple[DeclarationField, ...] = (
-    "method",
-    "path",
-    "required_scope",
-    "response_kind",
-    "max_response_bytes",
-    "request_headers",
-    "response_headers",
-    "response_media_types",
-)
-
-
-def main() -> None:
-    """Update or verify the pin and validate Console declarations against its OpenAPI document."""
-    parser = argparse.ArgumentParser()
-    mode = parser.add_mutually_exclusive_group()
-    mode.add_argument("--check", action="store_true")
-    mode.add_argument("--update-lock", action="store_true")
-    parser.add_argument("--repository", type=Path, default=DEFAULT_REPOSITORY)
-    args = parser.parse_args()
-
-    repository = args.repository.resolve()
-    lock = json.loads(LOCK_PATH.read_text())
-    tracked_changes = run("git", "status", "--porcelain", "--untracked-files=no", cwd=repository).strip()
-    if tracked_changes:
-        raise RuntimeError("KnowledgeFS checkout must not contain tracked changes during contract export")
-
-    commit = run("git", "rev-parse", "HEAD", cwd=repository).strip()
-    if not args.update_lock and commit != lock["commit"]:
-        raise RuntimeError(
-            f"KnowledgeFS checkout mismatch: expected {lock['commit']}, received {commit}. "
-            "Use the pinned commit or pass --update-lock intentionally."
-        )
-
-    with tempfile.TemporaryDirectory(prefix="dify-knowledge-fs-contract-") as directory:
-        openapi_path = Path(directory) / "knowledge-fs.openapi.json"
-        subprocess.run(
-            ["pnpm", "openapi:export", "--", "--output", str(openapi_path)],
-            cwd=repository,
-            check=True,
-        )
-        openapi_content = openapi_path.read_bytes()
-
-    openapi_sha256 = sha256(openapi_content)
-    if not args.update_lock and openapi_sha256 != lock["openapiSha256"]:
-        raise RuntimeError(
-            f"KnowledgeFS OpenAPI hash mismatch: expected {lock['openapiSha256']}, received {openapi_sha256}"
-        )
-
-    document: dict[str, Any] = json.loads(openapi_content)
-    validate_declarations(document, console_contract_declarations())
-
-    if args.update_lock:
-        LOCK_PATH.write_text(
-            json.dumps(
-                {
-                    "commit": commit,
-                    "openapiSha256": openapi_sha256,
-                    "repository": lock["repository"],
-                },
-                indent=2,
-            )
-            + "\n"
-        )
-
-
-def validate_declarations(document: dict[str, Any], declarations: tuple[ContractDeclaration, ...]) -> None:
-    """Validate Dify Console declarations against matching pinned OpenAPI operations."""
-    operations_by_id: dict[str, list[tuple[str, str, dict[str, Any], dict[str, Any]]]] = {}
-    for path, path_item in document.get("paths", {}).items():
-        for method in OPENAPI_METHODS:
-            operation = path_item.get(method)
-            if operation is None:
-                continue
-            operation_id = operation.get("operationId")
-            if isinstance(operation_id, str) and operation_id:
-                operations_by_id.setdefault(operation_id, []).append((method, path, path_item, operation))
-
-    declared_ids: set[str] = set()
-    for declaration in declarations:
-        operation_id = declaration["operation_id"]
-        if operation_id in declared_ids:
-            raise ValueError(f"Dify Console registry has duplicate operationId: {operation_id}")
-        declared_ids.add(operation_id)
-
-        matches = operations_by_id.get(operation_id, [])
-        if not matches:
-            raise ValueError(f"KnowledgeFS OpenAPI has no operationId: {operation_id}")
-        if len(matches) > 1:
-            raise ValueError(f"KnowledgeFS OpenAPI has duplicate operationId: {operation_id}")
-
-        method, path, path_item, operation = matches[0]
-        if not path.startswith("/"):
-            raise ValueError(f"KnowledgeFS OpenAPI path must be absolute: {path}")
-        if method not in PROXY_METHODS:
-            raise ValueError(f"KnowledgeFS proxy does not support {method.upper()} {path}")
-        expected: ContractDeclaration = {
-            "operation_id": operation_id,
-            "method": method.upper(),
-            "path": path[1:],
-            "required_scope": required_scope(operation),
-            "response_kind": response_kind(operation),
-            "max_response_bytes": required_max_response_bytes(operation),
-            "request_headers": request_header_names(path_item, operation),
-            "response_headers": response_header_names(operation),
-            "response_media_types": response_media_types(operation),
-        }
-        for field in DECLARATION_FIELDS:
-            expected_value = expected[field]
-            received_value = declaration[field]
-            if received_value != expected_value:
-                raise ValueError(
-                    f"KnowledgeFS operation {operation_id} field {field} drifted: "
-                    f"expected {expected_value!r}, received {received_value!r}"
-                )
-
-
-def console_contract_declarations() -> tuple[ContractDeclaration, ...]:
-    """Return transport declarations from the runtime Console operation registry."""
-    from services.knowledge_fs_proxy import KNOWLEDGE_FS_CONSOLE_OPERATIONS
-
-    return tuple(
-        {
-            "operation_id": operation.operation_id,
-            "method": operation.method,
-            "path": operation.path,
-            "required_scope": operation.required_scope,
-            "response_kind": operation.response_kind,
-            "max_response_bytes": operation.max_response_bytes,
-            "request_headers": operation.request_headers,
-            "response_headers": operation.response_headers,
-            "response_media_types": operation.response_media_types,
-        }
-        for operation in KNOWLEDGE_FS_CONSOLE_OPERATIONS
-    )
-
-
-def response_kind(operation: dict[str, Any]) -> str:
-    media_types = response_media_types(operation)
-    if "text/event-stream" in media_types:
-        return "stream"
-    if "application/octet-stream" in media_types:
-        return "binary"
-    return "buffered"
-
-
-def response_media_types(operation: dict[str, Any]) -> tuple[str, ...]:
-    media_types: set[str] = set()
-    for status, response in operation.get("responses", {}).items():
-        if status == "2XX" or (len(status) == 3 and status.startswith("2") and status.isdigit()):
-            media_types.update(response.get("content", {}))
-    return tuple(sorted(media_types))
-
-
-def required_scope(operation: dict[str, Any]) -> str | None:
-    scope = operation.get("x-knowledge-fs-required-scope")
-    if scope in ("knowledge-spaces:read", "knowledge-spaces:write"):
-        return scope
-    if operation.get("security") == []:
-        return None
-    raise ValueError(f"KnowledgeFS operation has no supported required scope: {scope}")
-
-
-def required_max_response_bytes(operation: dict[str, Any]) -> int:
-    value = operation.get("x-knowledge-fs-max-response-bytes")
-    if not isinstance(value, int) or isinstance(value, bool) or value <= 0:
-        raise ValueError(f"KnowledgeFS operation has no valid response byte limit: {value}")
-    return value
-
-
-def request_header_names(path_item: dict[str, Any], operation: dict[str, Any]) -> tuple[str, ...]:
-    names: set[str] = set()
-    for parameter in [*path_item.get("parameters", []), *operation.get("parameters", [])]:
-        if "$ref" in parameter:
-            raise ValueError(f"KnowledgeFS request header references are not supported: {parameter['$ref']}")
-        if parameter.get("in") == "header":
-            names.add(parameter["name"].lower())
-    return tuple(sorted(names))
-
-
-def response_header_names(operation: dict[str, Any]) -> tuple[str, ...]:
-    return tuple(
-        sorted(
-            {
-                name.lower()
-                for response in operation.get("responses", {}).values()
-                for name in response.get("headers", {})
-            }
-        )
-    )
-
-
-def sha256(content: bytes) -> str:
-    return hashlib.sha256(content).hexdigest()
-
-
-def run(*command: str, cwd: Path) -> str:
-    return subprocess.run(command, cwd=cwd, check=True, capture_output=True, text=True).stdout
-
-
-if __name__ == "__main__":
-    main()

api/knowledge-fs-contract.lock.json

@@ -1,5 +0,0 @@
-{
-  "commit": "4310e2d582d25e7de58183f27720afab01e123cf",
-  "openapiSha256": "5827ca930ce38462bfd1b2bef387efbf37eb7ffcaedde4558af2fbaeccbfbc4b",
-  "repository": "https://github.com/langgenius/knowledge-fs"
-}

api/libs/archive_storage.py

@@ -16,19 +16,12 @@ from urllib.parse import quote
 import boto3
 import orjson
 from botocore.client import Config
-from botocore.exceptions import BotoCoreError, ClientError
+from botocore.exceptions import ClientError
 
 from configs import dify_config
 
 logger = logging.getLogger(__name__)
 
-_OBJECT_NOT_FOUND_ERROR_CODES = frozenset({"404", "NoSuchKey", "NotFound"})
-
-
-def _is_object_not_found_error(error: ClientError) -> bool:
-    error_code = str(error.response.get("Error", {}).get("Code", ""))
-    return error_code in _OBJECT_NOT_FOUND_ERROR_CODES
-
 
 class ArchiveStorageError(Exception):
     """Base exception for archive storage operations."""
@@ -145,11 +138,10 @@ class ArchiveStorage:
             response = self.client.get_object(Bucket=self.bucket, Key=key)
             return response["Body"].read()
         except ClientError as e:
-            if _is_object_not_found_error(e):
-                raise FileNotFoundError(f"Archive object not found: {key}") from e
-            raise ArchiveStorageError(f"Failed to download object '{key}': {e}") from e
-        except BotoCoreError as e:
-            raise ArchiveStorageError(f"Failed to download object '{key}': {e}") from e
+            error_code = e.response.get("Error", {}).get("Code")
+            if error_code == "NoSuchKey":
+                raise FileNotFoundError(f"Archive object not found: {key}")
+            raise ArchiveStorageError(f"Failed to download object '{key}': {e}")
 
     def get_object_stream(self, key: str) -> Generator[bytes, None, None]:
         """
@@ -169,11 +161,10 @@ class ArchiveStorage:
             response = self.client.get_object(Bucket=self.bucket, Key=key)
             yield from response["Body"].iter_chunks()
         except ClientError as e:
-            if _is_object_not_found_error(e):
-                raise FileNotFoundError(f"Archive object not found: {key}") from e
-            raise ArchiveStorageError(f"Failed to stream object '{key}': {e}") from e
-        except BotoCoreError as e:
-            raise ArchiveStorageError(f"Failed to stream object '{key}': {e}") from e
+            error_code = e.response.get("Error", {}).get("Code")
+            if error_code == "NoSuchKey":
+                raise FileNotFoundError(f"Archive object not found: {key}")
+            raise ArchiveStorageError(f"Failed to stream object '{key}': {e}")
 
     def object_exists(self, key: str) -> bool:
         """
@@ -184,19 +175,12 @@ class ArchiveStorage:
 
         Returns:
             True if object exists, False otherwise
-
-        Raises:
-            ArchiveStorageError: If storage cannot authoritatively determine object existence
         """
         try:
             self.client.head_object(Bucket=self.bucket, Key=key)
             return True
-        except ClientError as e:
-            if _is_object_not_found_error(e):
-                return False
-            raise ArchiveStorageError(f"Failed to check archive object '{key}': {e}") from e
-        except BotoCoreError as e:
-            raise ArchiveStorageError(f"Failed to check archive object '{key}': {e}") from e
+        except ClientError:
+            return False
 
     def delete_object(self, key: str) -> None:
         """
@@ -212,12 +196,7 @@ class ArchiveStorage:
             self.client.delete_object(Bucket=self.bucket, Key=key)
             logger.debug("Deleted object: %s", key)
         except ClientError as e:
-            if _is_object_not_found_error(e):
-                logger.debug("Archive object was already absent: %s", key)
-                return
-            raise ArchiveStorageError(f"Failed to delete object '{key}': {e}") from e
-        except BotoCoreError as e:
-            raise ArchiveStorageError(f"Failed to delete object '{key}': {e}") from e
+            raise ArchiveStorageError(f"Failed to delete object '{key}': {e}")
 
     def generate_presigned_url(
         self,

api/migrations/versions/2026_06_29_1200-b8c9d0e1f2a3_add_step_by_step_tour_state.py

@@ -1,39 +0,0 @@
-"""add step by step tour state
-
-Revision ID: b8c9d0e1f2a3
-Revises: 3c9f8e2a1d7b
-Create Date: 2026-06-29 12:00:00.000000
-
-"""
-
-import sqlalchemy as sa
-from alembic import op
-
-import models
-
-# revision identifiers, used by Alembic.
-revision = "b8c9d0e1f2a3"
-down_revision = "3c9f8e2a1d7b"
-branch_labels = None
-depends_on = None
-
-
-def upgrade():
-    op.create_table(
-        "account_step_by_step_tour_states",
-        sa.Column("id", models.types.StringUUID(), nullable=False),
-        sa.Column("account_id", models.types.StringUUID(), nullable=False),
-        sa.Column("first_workspace_id", models.types.StringUUID(), nullable=True),
-        sa.Column("skipped", sa.Boolean(), server_default=sa.text("false"), nullable=False),
-        sa.Column("completed_task_ids", models.types.AdjustedJSON(), nullable=False),
-        sa.Column("manually_enabled_workspace_ids", models.types.AdjustedJSON(), nullable=False),
-        sa.Column("manually_disabled_workspace_ids", models.types.AdjustedJSON(), nullable=False),
-        sa.Column("created_at", sa.DateTime(), server_default=sa.text("CURRENT_TIMESTAMP"), nullable=False),
-        sa.Column("updated_at", sa.DateTime(), server_default=sa.text("CURRENT_TIMESTAMP"), nullable=False),
-        sa.PrimaryKeyConstraint("id", name="account_step_by_step_tour_state_pkey"),
-        sa.UniqueConstraint("account_id", name="account_step_by_step_tour_state_account_id_key"),
-    )
-
-
-def downgrade():
-    op.drop_table("account_step_by_step_tour_states")

api/migrations/versions/2026_07_15_1600-3c9f8e2a1d7b_add_workflow_run_archive_bundle_cursor_indexes.py

@@ -1,45 +0,0 @@
-"""add workflow-run archive bundle cursor indexes
-
-Revision ID: 3c9f8e2a1d7b
-Revises: 7a1c2d9e4b60
-Create Date: 2026-07-15 16:00:00.000000
-
-"""
-
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision = "3c9f8e2a1d7b"
-down_revision = "7a1c2d9e4b60"
-branch_labels = None
-depends_on = None
-
-_TABLE_NAME = "workflow_run_archive_bundles"
-_INDEXES = (
-    ("workflow_run_archive_bundle_month_id_idx", ("year", "month", "id")),
-    ("workflow_run_archive_bundle_month_shard_id_idx", ("year", "month", "shard", "id")),
-)
-
-
-def _is_postgresql() -> bool:
-    return op.get_bind().dialect.name == "postgresql"
-
-
-def upgrade() -> None:
-    if _is_postgresql():
-        with op.get_context().autocommit_block():
-            for index_name, columns in _INDEXES:
-                op.create_index(index_name, _TABLE_NAME, columns, postgresql_concurrently=True)
-        return
-    for index_name, columns in _INDEXES:
-        op.create_index(index_name, _TABLE_NAME, columns)
-
-
-def downgrade() -> None:
-    if _is_postgresql():
-        with op.get_context().autocommit_block():
-            for index_name, _ in reversed(_INDEXES):
-                op.drop_index(index_name, table_name=_TABLE_NAME, postgresql_concurrently=True)
-        return
-    for index_name, _ in reversed(_INDEXES):
-        op.drop_index(index_name, table_name=_TABLE_NAME)

api/models/__init__.py

@@ -101,7 +101,6 @@ from .model import (
     UploadFile,
 )
 from .oauth import DatasourceOauthParamConfig, DatasourceProvider, OAuthAccessToken
-from .onboarding import AccountStepByStepTourState
 from .provider import (
     LoadBalancingModelConfig,
     Provider,
@@ -156,7 +155,6 @@ __all__ = [
     "Account",
     "AccountIntegrate",
     "AccountStatus",
-    "AccountStepByStepTourState",
     "AccountTrialAppRecord",
     "Agent",
     "AgentConfigDraft",

api/models/onboarding.py

@@ -1,59 +0,0 @@
-"""Account-level onboarding state models."""
-
-from datetime import datetime
-
-import sqlalchemy as sa
-from sqlalchemy import DateTime, func
-from sqlalchemy.orm import Mapped, mapped_column
-
-from .base import TypeBase, gen_uuidv7_string
-from .types import AdjustedJSON, StringUUID
-
-
-class AccountStepByStepTourState(TypeBase):
-    """Persistent account-level Step-by-step Tour state.
-
-    The tour is account-owned, with workspace IDs stored only as presentation
-    overrides. The first workspace is the workspace context where an eligible
-    account first asks for tour state; subsequent workspaces are opt-in only.
-    """
-
-    __tablename__ = "account_step_by_step_tour_states"
-    __table_args__ = (
-        sa.PrimaryKeyConstraint("id", name="account_step_by_step_tour_state_pkey"),
-        sa.UniqueConstraint("account_id", name="account_step_by_step_tour_state_account_id_key"),
-    )
-
-    id: Mapped[str] = mapped_column(
-        StringUUID,
-        insert_default=gen_uuidv7_string,
-        default_factory=gen_uuidv7_string,
-        init=False,
-    )
-    account_id: Mapped[str] = mapped_column(StringUUID, nullable=False)
-    first_workspace_id: Mapped[str | None] = mapped_column(StringUUID, nullable=True, default=None)
-    skipped: Mapped[bool] = mapped_column(sa.Boolean, nullable=False, server_default=sa.text("false"), default=False)
-    completed_task_ids: Mapped[list[str]] = mapped_column(AdjustedJSON, nullable=False, default_factory=list)
-    manually_enabled_workspace_ids: Mapped[list[str]] = mapped_column(
-        AdjustedJSON,
-        nullable=False,
-        default_factory=list,
-    )
-    manually_disabled_workspace_ids: Mapped[list[str]] = mapped_column(
-        AdjustedJSON,
-        nullable=False,
-        default_factory=list,
-    )
-    created_at: Mapped[datetime] = mapped_column(
-        DateTime,
-        server_default=func.current_timestamp(),
-        nullable=False,
-        init=False,
-    )
-    updated_at: Mapped[datetime] = mapped_column(
-        DateTime,
-        server_default=func.current_timestamp(),
-        nullable=False,
-        init=False,
-        onupdate=func.current_timestamp(),
-    )

api/models/workflow.py

@@ -1476,8 +1476,6 @@ class WorkflowRunArchiveBundle(DefaultFieldsDCMixin, TypeBase):
             name="workflow_run_archive_bundle_identity_uq",
         ),
         sa.Index("workflow_run_archive_bundle_tenant_month_idx", "tenant_id", "year", "month"),
-        sa.Index("workflow_run_archive_bundle_month_id_idx", "year", "month", "id"),
-        sa.Index("workflow_run_archive_bundle_month_shard_id_idx", "year", "month", "shard", "id"),
     )
 
     tenant_id: Mapped[str] = mapped_column(StringUUID, nullable=False)

api/openapi/markdown/console-openapi.md

@@ -7787,30 +7787,6 @@ Initiate OAuth login process
 | ---- | ----------- | ------ |
 | 200 | Success | **application/json**: [OAuthProviderTokenResponse](#oauthprovidertokenresponse)<br> |
 
-### [GET] /onboarding/step-by-step-tour/state
-Get account-level Step-by-step Tour state
-
-#### Responses
-
-| Code | Description | Schema |
-| ---- | ----------- | ------ |
-| 200 | Success | **application/json**: [StepByStepTourStateResponse](#stepbysteptourstateresponse)<br> |
-
-### [PATCH] /onboarding/step-by-step-tour/state
-Update account-level Step-by-step Tour state
-
-#### Request Body
-
-| Required | Schema |
-| -------- | ------ |
-|  Yes | **application/json**: [StepByStepTourStatePatchPayload](#stepbysteptourstatepatchpayload)<br> |
-
-#### Responses
-
-| Code | Description | Schema |
-| ---- | ----------- | ------ |
-| 200 | Success | **application/json**: [StepByStepTourStateResponse](#stepbysteptourstateresponse)<br> |
-
 ### [DELETE] /rag/pipeline/customized/templates/{template_id}
 #### Parameters
 
@@ -9663,27 +9639,6 @@ Bedrock retrieval test (internal use only)
 | ---- | ----------- | ------ |
 | 200 | Success | **application/json**: [TrialDatasetListResponse](#trialdatasetlistresponse)<br> |
 
-### [POST] /trial-apps/{app_id}/files/upload
-**Upload a file into the tenant that owns the trial app**
-
-#### Parameters
-
-| Name | Located in | Description | Required | Schema |
-| ---- | ---------- | ----------- | -------- | ------ |
-| app_id | path |  | Yes | string (uuid) |
-
-#### Request Body
-
-| Required | Schema |
-| -------- | ------ |
-|  Yes | **multipart/form-data**: { **"file"**: binary, **"source"**: string, <br>**Available values:** "datasets" }<br> |
-
-#### Responses
-
-| Code | Description | Schema |
-| ---- | ----------- | ------ |
-| 201 | File uploaded successfully | **application/json**: [FileResponse](#fileresponse)<br> |
-
 ### [GET] /trial-apps/{app_id}/messages/{message_id}/suggested-questions
 #### Parameters
 
@@ -9713,27 +9668,6 @@ Bedrock retrieval test (internal use only)
 | ---- | ----------- | ------ |
 | 200 | Success | **application/json**: [Parameters](#parameters)<br> |
 
-### [POST] /trial-apps/{app_id}/remote-files/upload
-**Upload a remote file into the tenant that owns the trial app**
-
-#### Parameters
-
-| Name | Located in | Description | Required | Schema |
-| ---- | ---------- | ----------- | -------- | ------ |
-| app_id | path |  | Yes | string (uuid) |
-
-#### Request Body
-
-| Required | Schema |
-| -------- | ------ |
-|  Yes | **application/json**: [RemoteFileUploadPayload](#remotefileuploadpayload)<br> |
-
-#### Responses
-
-| Code | Description | Schema |
-| ---- | ----------- | ------ |
-| 201 | File uploaded successfully | **application/json**: [FileWithSignedUrl](#filewithsignedurl)<br> |
-
 ### [GET] /trial-apps/{app_id}/site
 **Retrieve app site info**
 
@@ -21812,24 +21746,6 @@ Query parameters for listing snippet published workflows.
 | paused | integer |  | Yes |
 | success | integer |  | Yes |
 
-#### StepByStepTourStatePatchPayload
-
-| Name | Type | Description | Required |
-| ---- | ---- | ----------- | -------- |
-| action | string, <br>**Available values:** "complete_task", "disable_current_workspace", "enable_current_workspace", "skip", "uncomplete_task" | State update action<br>*Enum:* `"complete_task"`, `"disable_current_workspace"`, `"enable_current_workspace"`, `"skip"`, `"uncomplete_task"` | Yes |
-| task_id | string | Task ID for task actions | No |
-
-#### StepByStepTourStateResponse
-
-| Name | Type | Description | Required |
-| ---- | ---- | ----------- | -------- |
-| completed_task_ids | [ string, <br>**Available values:** "home", "integration", "knowledge", "studio" ] |  | No |
-| first_workspace_id | string |  | No |
-| manually_disabled_workspace_ids | [ string ] |  | No |
-| manually_enabled_workspace_ids | [ string ] |  | No |
-| skipped | boolean |  | No |
-| updated_at | string |  | No |
-
 #### Storage
 
 | Name | Type | Description | Required |
@@ -21943,7 +21859,6 @@ The subscription constructor of the trigger provider
 
 | Name | Type | Description | Required |
 | ---- | ---- | ----------- | -------- |
-| _is_collaborative | boolean |  | No |
 | conversation_variables | [ object ] |  | No |
 | environment_variables | [ object ] |  | No |
 | features | object |  | Yes |
@@ -21983,7 +21898,6 @@ Model class for provider system configuration response.
 | enable_learn_app | boolean, <br>**Default:** true |  | Yes |
 | enable_marketplace | boolean |  | Yes |
 | enable_social_oauth_login | boolean |  | Yes |
-| enable_step_by_step_tour | boolean |  | Yes |
 | enable_trial_app | boolean |  | Yes |
 | is_allow_create_workspace | boolean |  | Yes |
 | is_allow_register | boolean |  | Yes |
@@ -22940,7 +22854,6 @@ in form definiton, or a variable while the workflow is running.
 | ---- | ---- | ----------- | -------- |
 | allow_email_code_login | boolean |  | Yes |
 | allow_email_password_login | boolean |  | Yes |
-| allow_public_access | boolean, <br>**Default:** true |  | Yes |
 | allow_sso | boolean |  | Yes |
 | enabled | boolean |  | Yes |
 | sso_config | [WebAppAuthSSOModel](#webappauthssomodel) |  | Yes |

api/openapi/markdown/web-openapi.md

@@ -1577,7 +1577,6 @@ Default configuration for form inputs.
 | enable_learn_app | boolean, <br>**Default:** true |  | Yes |
 | enable_marketplace | boolean |  | Yes |
 | enable_social_oauth_login | boolean |  | Yes |
-| enable_step_by_step_tour | boolean |  | Yes |
 | enable_trial_app | boolean |  | Yes |
 | is_allow_create_workspace | boolean |  | Yes |
 | is_allow_register | boolean |  | Yes |
@@ -1643,7 +1642,6 @@ in form definiton, or a variable while the workflow is running.
 | ---- | ---- | ----------- | -------- |
 | allow_email_code_login | boolean |  | Yes |
 | allow_email_password_login | boolean |  | Yes |
-| allow_public_access | boolean, <br>**Default:** true |  | Yes |
 | allow_sso | boolean |  | Yes |
 | enabled | boolean |  | Yes |
 | sso_config | [WebAppAuthSSOModel](#webappauthssomodel) |  | Yes |

api/providers/conftest.py

@@ -1,35 +0,0 @@
-"""Shared database fixtures for provider tests.
-
-Provider tests live outside ``tests/unit_tests`` and therefore cannot use that
-suite's SQLite fixtures. Keep this fixture scoped to ``providers`` so each
-provider package can exercise real SQLAlchemy queries without a service
-database or mocked sessions.
-"""
-
-from collections.abc import Iterator
-
-import pytest
-from sqlalchemy import create_engine
-from sqlalchemy.orm import Session
-
-from models.base import TypeBase
-
-
-@pytest.fixture
-def sqlite3_session(request: pytest.FixtureRequest) -> Iterator[Session]:
-    """Yield an isolated SQLite session with the parametrized model tables.
-
-    Pass the required ORM classes through indirect parametrization. The engine
-    is per-test so committed rows and identity-map state cannot leak between
-    provider packages.
-    """
-
-    models: tuple[type[TypeBase], ...] = request.param
-    engine = create_engine("sqlite:///:memory:")
-    tables = [model.metadata.tables[model.__tablename__] for model in models]
-    TypeBase.metadata.create_all(engine, tables=tables)
-    try:
-        with Session(engine, expire_on_commit=False) as session:
-            yield session
-    finally:
-        engine.dispose()

api/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dify-api"
-version = "1.16.0"
+version = "1.16.0-rc1"
 requires-python = "~=3.12.0"
 
 dependencies = [

api/repositories/workflow_collaboration_repository.py

@@ -3,10 +3,7 @@ from __future__ import annotations
 import json
 from typing import NotRequired, TypedDict, override
 
-from redis.lock import Lock
-
 from extensions.ext_redis import redis_client
-from extensions.redis_names import serialize_redis_name
 
 SESSION_STATE_TTL_SECONDS = 3600
 SERVER_HEARTBEAT_TTL_SECONDS = 90
@@ -15,31 +12,6 @@ WORKFLOW_LEADER_PREFIX = "workflow_leader:"
 WS_SID_MAP_PREFIX = "ws_sid_map:"
 WS_SERVER_HEARTBEAT_PREFIX = "ws_server_heartbeat:"
 WS_SERVER_SESSIONS_PREFIX = "ws_server_sessions:"
-GRAPH_VIEW_STATE_LOCK_PREFIX = "workflow_graph_view_state_lock:"
-GRAPH_VIEW_STATE_LOCK_TIMEOUT_SECONDS = 15
-
-_UPDATE_SESSION_GRAPH_ACTIVE_LUA = """
-local raw = redis.call('HGET', KEYS[1], ARGV[1])
-if not raw then
-    return 0
-end
-
-local decoded_ok, session_info = pcall(cjson.decode, raw)
-if not decoded_ok or type(session_info) ~= 'table' then
-    return 0
-end
-
-local incoming_sequence = tonumber(ARGV[3])
-local current_sequence = tonumber(session_info.graph_active_sequence)
-if current_sequence and incoming_sequence <= current_sequence then
-    return 0
-end
-
-session_info.graph_active = ARGV[2] == '1'
-session_info.graph_active_sequence = incoming_sequence
-redis.call('HSET', KEYS[1], ARGV[1], cjson.encode(session_info))
-return 1
-"""
 
 
 class WorkflowSessionInfo(TypedDict):
@@ -184,55 +156,6 @@ class WorkflowCollaborationRepository:
 
         return users
 
-    def get_session_info(self, workflow_id: str, sid: str) -> WorkflowSessionInfo | None:
-        raw = self._redis.hget(self.workflow_key(workflow_id), sid)
-        value = self._decode(raw)
-        if not value:
-            return None
-        try:
-            session_info = json.loads(value)
-        except (TypeError, json.JSONDecodeError):
-            return None
-
-        if not isinstance(session_info, dict):
-            return None
-        if "user_id" not in session_info or "username" not in session_info or "sid" not in session_info:
-            return None
-
-        user: WorkflowSessionInfo = {
-            "user_id": str(session_info["user_id"]),
-            "username": str(session_info["username"]),
-            "avatar": session_info.get("avatar"),
-            "sid": str(session_info["sid"]),
-            "connected_at": int(session_info.get("connected_at") or 0),
-        }
-        if isinstance(session_info.get("server_id"), str):
-            user["server_id"] = session_info["server_id"]
-        if isinstance(session_info.get("graph_active"), bool):
-            user["graph_active"] = session_info["graph_active"]
-        return user
-
-    def update_session_graph_active(self, workflow_id: str, sid: str, active: bool, sequence: int) -> bool:
-        """Atomically apply a graph visibility update when its client sequence is newer."""
-        # RedisClientWrapper prefixes regular hash calls, but eval is delegated to the raw client.
-        workflow_key = serialize_redis_name(self.workflow_key(workflow_id))
-        result = self._redis.eval(
-            _UPDATE_SESSION_GRAPH_ACTIVE_LUA,
-            1,
-            workflow_key,
-            sid,
-            "1" if active else "0",
-            sequence,
-        )
-        return bool(result)
-
-    def graph_view_state_lock(self, workflow_id: str) -> Lock:
-        """Serialize visibility state changes and their leader-election side effects."""
-        return self._redis.lock(
-            f"{GRAPH_VIEW_STATE_LOCK_PREFIX}{workflow_id}",
-            timeout=GRAPH_VIEW_STATE_LOCK_TIMEOUT_SECONDS,
-        )
-
     def refresh_server_heartbeat(self, server_id: str) -> None:
         self._redis.set(self.server_key(server_id), "1", ex=SERVER_HEARTBEAT_TTL_SECONDS)
 

api/services/agent/observability_service.py

@@ -9,13 +9,12 @@ import sqlalchemy as sa
 from sqlalchemy import and_, func, or_, select
 from sqlalchemy.orm import aliased
 
-from configs import dify_config
 from core.app.entities.app_invoke_entities import InvokeFrom
 from libs.helper import convert_datetime_to_date, escape_like_pattern, to_timestamp
 from models.agent import WorkflowAgentNodeBinding
-from models.enums import CreatorUserRole, MessageStatus
+from models.enums import MessageStatus
 from models.model import App, Conversation, Message
-from models.workflow import WorkflowNodeExecutionModel, WorkflowRun, WorkflowType
+from models.workflow import WorkflowNodeExecutionModel, WorkflowRun
 
 
 @dataclass(frozen=True)
@@ -581,26 +580,9 @@ class AgentObservabilityService:
 
     def _load_daily_statistics(
         self, *, app: App, agent_id: str, params: AgentStatisticsQueryParams, source_filter: AgentSourceFilter
-    ) -> list[dict[str, Any]]:
-        rows: list[dict[str, Any]] = []
-        if source_filter.kind in {"all", "webapp"}:
-            rows.extend(self._load_webapp_daily_statistics(app=app, params=params, source_filter=source_filter))
-        if source_filter.kind in {"all", "workflow"}:
-            rows.extend(
-                self._load_workflow_daily_statistics(
-                    app=app,
-                    agent_id=agent_id,
-                    params=params,
-                    source_filter=source_filter,
-                )
-            )
-        return self._merge_daily_statistics(rows)
-
-    def _load_webapp_daily_statistics(
-        self, *, app: App, params: AgentStatisticsQueryParams, source_filter: AgentSourceFilter
     ) -> list[dict[str, Any]]:
         converted_created_at = convert_datetime_to_date("m.created_at")
-        message_scope = self._statistics_webapp_message_scope_sql(source_filter)
+        message_scope = self._statistics_message_scope_sql(source_filter)
         sql_query = f"""SELECT
     {converted_created_at} AS date,
     COUNT(m.id) AS message_count,
@@ -620,9 +602,20 @@ WHERE
         args: dict[str, Any] = {
             "tz": params.timezone,
             "app_id": app.id,
+            "tenant_id": app.tenant_id,
+            "agent_id": agent_id,
+            "debugger": InvokeFrom.DEBUGGER,
         }
         if source_filter.invoke_from is not None:
             args["source"] = source_filter.invoke_from
+        if source_filter.app_id:
+            args["source_app_id"] = source_filter.app_id
+        if source_filter.workflow_id:
+            args["workflow_id"] = source_filter.workflow_id
+        if source_filter.workflow_version:
+            args["workflow_version"] = source_filter.workflow_version
+        if source_filter.node_id:
+            args["node_id"] = source_filter.node_id
         if params.start:
             sql_query += " AND m.created_at >= :start"
             args["start"] = params.start
@@ -634,160 +627,10 @@ WHERE
         return [dict(row._mapping) for row in self._session.execute(sa.text(sql_query), args).all()]
 
     @staticmethod
-    def _statistics_webapp_message_scope_sql(source_filter: AgentSourceFilter) -> str:
+    def _statistics_message_scope_sql(source_filter: AgentSourceFilter) -> str:
         app_scope = "m.app_id = :app_id"
         if source_filter.invoke_from is not None:
             app_scope += " AND m.invoke_from = :source"
-        return app_scope
-
-    def _load_workflow_daily_statistics(
-        self,
-        *,
-        app: App,
-        agent_id: str,
-        params: AgentStatisticsQueryParams,
-        source_filter: AgentSourceFilter,
-    ) -> list[dict[str, Any]]:
-        converted_run_created_at = convert_datetime_to_date("aru.created_at")
-        total_tokens = self._workflow_execution_metadata_numeric_sql(("total_tokens",), "BIGINT")
-        nested_total_tokens = self._workflow_execution_metadata_numeric_sql(
-            ("agent_log", "agent_backend", "usage", "total_tokens"), "BIGINT"
-        )
-        total_price = self._workflow_execution_metadata_numeric_sql(("total_price",), "DECIMAL(65, 30)")
-        nested_total_price = self._workflow_execution_metadata_numeric_sql(
-            ("agent_log", "agent_backend", "usage", "total_price"), "DECIMAL(65, 30)"
-        )
-        completion_tokens = self._workflow_execution_metadata_numeric_sql(
-            ("agent_log", "agent_backend", "usage", "completion_tokens"), "BIGINT"
-        )
-        binding_filters = self._statistics_workflow_binding_filters_sql(source_filter)
-        run_date_filters = ""
-        args: dict[str, Any] = {
-            "tz": params.timezone,
-            "tenant_id": app.tenant_id,
-            "agent_id": agent_id,
-            "chat_workflow_type": WorkflowType.CHAT,
-            "end_user_role": CreatorUserRole.END_USER,
-        }
-        if source_filter.app_id:
-            args["source_app_id"] = source_filter.app_id
-        if source_filter.workflow_id:
-            args["workflow_id"] = source_filter.workflow_id
-        if source_filter.workflow_version:
-            args["workflow_version"] = source_filter.workflow_version
-        if source_filter.node_id:
-            args["node_id"] = source_filter.node_id
-        if params.start:
-            run_date_filters += " AND wr.created_at >= :start"
-            args["start"] = params.start
-        if params.end:
-            run_date_filters += " AND wr.created_at < :end"
-            args["end"] = params.end
-
-        run_query = f"""WITH agent_run_usage AS (
-    SELECT
-        wr.id,
-        wr.created_by_role,
-        wr.created_by,
-        wr.created_at,
-        COALESCE(SUM(COALESCE({total_tokens}, {nested_total_tokens}, 0)), 0) AS token_count,
-        COALESCE(SUM(COALESCE({total_price}, {nested_total_price}, 0)), 0) AS total_price,
-        COALESCE(SUM(COALESCE(wne.elapsed_time, 0)), 0) AS latency,
-        COALESCE(SUM(COALESCE({completion_tokens}, 0)), 0) AS answer_tokens
-    FROM workflow_runs wr
-    JOIN workflow_agent_node_bindings wanb
-        ON wanb.tenant_id = :tenant_id
-        AND wanb.agent_id = :agent_id
-        AND wanb.app_id = wr.app_id
-        AND wanb.workflow_id = wr.workflow_id
-        AND wanb.workflow_version = wr.version
-        {binding_filters}
-    JOIN workflow_node_executions wne
-        ON wne.workflow_run_id = wr.id
-        AND wne.node_id = wanb.node_id
-    WHERE wr.type != :chat_workflow_type{run_date_filters}
-    GROUP BY wr.id, wr.created_by_role, wr.created_by, wr.created_at
-)
-SELECT
-    {converted_run_created_at} AS date,
-    COUNT(aru.id) AS message_count,
-    COUNT(aru.id) AS conversation_count,
-    COUNT(DISTINCT CASE
-        WHEN aru.created_by_role = :end_user_role THEN aru.created_by
-        ELSE NULL
-    END) AS end_user_count,
-    COALESCE(SUM(aru.token_count), 0) AS token_count,
-    COALESCE(SUM(aru.total_price), 0) AS total_price,
-    COALESCE(AVG(aru.latency), 0) AS avg_latency,
-    COALESCE(SUM(aru.latency), 0) AS latency_sum,
-    COALESCE(SUM(aru.answer_tokens), 0) AS answer_tokens,
-    0 AS like_count
-FROM agent_run_usage aru
-GROUP BY date
-ORDER BY date"""
-        rows = [dict(row._mapping) for row in self._session.execute(sa.text(run_query), args).all()]
-        rows.extend(
-            self._load_workflow_chat_daily_context(
-                app=app,
-                agent_id=agent_id,
-                params=params,
-                source_filter=source_filter,
-            )
-        )
-        return self._merge_daily_statistics(rows)
-
-    def _load_workflow_chat_daily_context(
-        self,
-        *,
-        app: App,
-        agent_id: str,
-        params: AgentStatisticsQueryParams,
-        source_filter: AgentSourceFilter,
-    ) -> list[dict[str, Any]]:
-        converted_created_at = convert_datetime_to_date("m.created_at")
-        workflow_scope = self._statistics_workflow_message_scope_sql(source_filter)
-        sql_query = f"""SELECT
-    {converted_created_at} AS date,
-    COUNT(m.id) AS message_count,
-    COUNT(DISTINCT m.conversation_id) AS conversation_count,
-    COUNT(DISTINCT m.from_end_user_id) AS end_user_count,
-    COALESCE(SUM(COALESCE(m.message_tokens, 0) + COALESCE(m.answer_tokens, 0)), 0) AS token_count,
-    COALESCE(SUM(COALESCE(m.total_price, 0)), 0) AS total_price,
-    COALESCE(AVG(m.provider_response_latency), 0) AS avg_latency,
-    COALESCE(SUM(m.provider_response_latency), 0) AS latency_sum,
-    COALESCE(SUM(m.answer_tokens), 0) AS answer_tokens,
-    COUNT(mf.id) AS like_count
-FROM messages m
-LEFT JOIN message_feedbacks mf
-    ON mf.message_id = m.id AND mf.rating = 'like'
-WHERE
-    {workflow_scope}"""
-        args: dict[str, Any] = {
-            "tz": params.timezone,
-            "tenant_id": app.tenant_id,
-            "agent_id": agent_id,
-            "chat_workflow_type": WorkflowType.CHAT,
-        }
-        if source_filter.app_id:
-            args["source_app_id"] = source_filter.app_id
-        if source_filter.workflow_id:
-            args["workflow_id"] = source_filter.workflow_id
-        if source_filter.workflow_version:
-            args["workflow_version"] = source_filter.workflow_version
-        if source_filter.node_id:
-            args["node_id"] = source_filter.node_id
-        if params.start:
-            sql_query += " AND m.created_at >= :start"
-            args["start"] = params.start
-        if params.end:
-            sql_query += " AND m.created_at < :end"
-            args["end"] = params.end
-        sql_query += " GROUP BY date ORDER BY date"
-
-        return [dict(row._mapping) for row in self._session.execute(sa.text(sql_query), args).all()]
-
-    @staticmethod
-    def _statistics_workflow_binding_filters_sql(source_filter: AgentSourceFilter) -> str:
         workflow_binding_filters = []
         if source_filter.app_id:
             workflow_binding_filters.append("wanb.app_id = :source_app_id")
@@ -797,12 +640,8 @@ WHERE
             workflow_binding_filters.append("wanb.workflow_version = :workflow_version")
         if source_filter.node_id:
             workflow_binding_filters.append("wanb.node_id = :node_id")
-        return f"AND {' AND '.join(workflow_binding_filters)}" if workflow_binding_filters else ""
-
-    @classmethod
-    def _statistics_workflow_message_scope_sql(cls, source_filter: AgentSourceFilter) -> str:
-        binding_filters = cls._statistics_workflow_binding_filters_sql(source_filter)
-        return f"""m.workflow_run_id IS NOT NULL
+        extra_workflow_filters = f"AND {' AND '.join(workflow_binding_filters)}" if workflow_binding_filters else ""
+        workflow_scope = f"""m.workflow_run_id IS NOT NULL
         AND EXISTS (
             SELECT 1
             FROM workflow_runs wr
@@ -812,65 +651,17 @@ WHERE
                 AND wanb.app_id = wr.app_id
                 AND wanb.workflow_id = wr.workflow_id
                 AND wanb.workflow_version = wr.version
-                {binding_filters}
+                {extra_workflow_filters}
             JOIN workflow_node_executions wne
                 ON wne.workflow_run_id = wr.id
                 AND wne.node_id = wanb.node_id
             WHERE wr.id = m.workflow_run_id
-                AND wr.type = :chat_workflow_type
         )"""
-
-    @staticmethod
-    def _workflow_execution_metadata_numeric_sql(path: tuple[str, ...], numeric_type: str) -> str:
-        if dify_config.DB_TYPE == "postgresql":
-            json_path = ",".join(path)
-            value = f"CAST(wne.execution_metadata AS JSONB) #>> '{{{json_path}}}'"
-            return f"CAST(NULLIF({value}, '') AS {numeric_type})"
-        if dify_config.DB_TYPE in {"mysql", "oceanbase", "seekdb"}:
-            json_path = "$." + ".".join(path)
-            mysql_numeric_type = "UNSIGNED" if numeric_type == "BIGINT" else numeric_type
-            value = f"JSON_UNQUOTE(JSON_EXTRACT(wne.execution_metadata, '{json_path}'))"
-            return f"CAST(NULLIF(NULLIF({value}, ''), 'null') AS {mysql_numeric_type})"
-        raise NotImplementedError(f"Unsupported database type: {dify_config.DB_TYPE}")
-
-    @staticmethod
-    def _merge_daily_statistics(rows: list[dict[str, Any]]) -> list[dict[str, Any]]:
-        merged: dict[Any, dict[str, Any]] = {}
-        weighted_latency: dict[Any, float] = {}
-        for row in rows:
-            date = row["date"]
-            target = merged.setdefault(
-                date,
-                {
-                    "date": date,
-                    "message_count": 0,
-                    "conversation_count": 0,
-                    "end_user_count": 0,
-                    "token_count": 0,
-                    "total_price": Decimal(0),
-                    "avg_latency": 0.0,
-                    "latency_sum": 0.0,
-                    "answer_tokens": 0,
-                    "like_count": 0,
-                },
-            )
-            message_count = int(row.get("message_count") or 0)
-            target["message_count"] += message_count
-            target["conversation_count"] += int(row.get("conversation_count") or 0)
-            target["end_user_count"] += int(row.get("end_user_count") or 0)
-            target["token_count"] += int(row.get("token_count") or 0)
-            target["total_price"] += Decimal(str(row.get("total_price") or 0))
-            target["latency_sum"] += float(row.get("latency_sum") or 0)
-            target["answer_tokens"] += int(row.get("answer_tokens") or 0)
-            target["like_count"] += int(row.get("like_count") or 0)
-            weighted_latency[date] = (
-                weighted_latency.get(date, 0.0) + float(row.get("avg_latency") or 0) * message_count
-            )
-
-        for date, row in merged.items():
-            message_count = int(row["message_count"])
-            row["avg_latency"] = weighted_latency[date] / message_count if message_count else 0.0
-        return sorted(merged.values(), key=lambda row: str(row["date"]))
+        if source_filter.kind == "webapp":
+            return app_scope
+        if source_filter.kind == "workflow":
+            return workflow_scope
+        return f"(({app_scope}) OR ({workflow_scope}))"
 
     @staticmethod
     def _build_charts(rows: list[dict[str, Any]]) -> dict[str, list[dict[str, Any]]]:

api/services/app_service.py

@@ -408,7 +408,6 @@ class AppService:
         default_model_config = app_template.get("model_config")
         default_model_config = default_model_config.copy() if default_model_config else None
         if default_model_config and "model" in default_model_config:
-            default_model_dict = default_model_config["model"]
             # get model provider
             model_manager = ModelManager.for_tenant(tenant_id=account.current_tenant_id or "")
 
@@ -423,7 +422,7 @@ class AppService:
                 logger.exception("Get default model instance failed, tenant_id: %s", tenant_id)
                 model_instance = None
 
-            if model_instance is not None:
+            if model_instance:
                 if (
                     model_instance.model_name == default_model_config["model"]["name"]
                     and model_instance.provider == default_model_config["model"]["provider"]
@@ -431,28 +430,17 @@ class AppService:
                     default_model_dict = default_model_config["model"]
                 else:
                     llm_model = cast(LargeLanguageModel, model_instance.model_type_instance)
-                    try:
-                        model_schema = llm_model.get_model_schema(model_instance.model_name, model_instance.credentials)
-                        if model_schema is None:
-                            raise ValueError(f"model schema not found for model {model_instance.model_name}")
-                    except Exception:
-                        # A removed provider model must not prevent creating an app.
-                        logger.warning(
-                            "Default model schema is unavailable, tenant_id: %s, provider: %s, model: %s",
-                            tenant_id,
-                            model_instance.provider,
-                            model_instance.model_name,
-                            exc_info=True,
-                        )
-                        model_instance = None
-                    else:
-                        default_model_dict = {
-                            "provider": model_instance.provider,
-                            "name": model_instance.model_name,
-                            "mode": model_schema.model_properties.get(ModelPropertyKey.MODE),
-                            "completion_params": {},
-                        }
-            if model_instance is None:
+                    model_schema = llm_model.get_model_schema(model_instance.model_name, model_instance.credentials)
+                    if model_schema is None:
+                        raise ValueError(f"model schema not found for model {model_instance.model_name}")
+
+                    default_model_dict = {
+                        "provider": model_instance.provider,
+                        "name": model_instance.model_name,
+                        "mode": model_schema.model_properties.get(ModelPropertyKey.MODE),
+                        "completion_params": {},
+                    }
+            else:
                 try:
                     provider, model = model_manager.get_default_provider_model_name(
                         tenant_id=account.current_tenant_id or "", model_type=ModelType.LLM

api/services/dataset_service.py

@@ -739,13 +739,8 @@ class DatasetService:
             dataset.id, external_knowledge_id, external_knowledge_api_id, session
         )
 
-        # Flush changes to the database without closing the caller-managed
-        # transaction. This helper receives a session opened by the caller
-        # (`with Session(...) as session`); calling commit() here closed that
-        # context manager early and raised
-        # sqlalchemy.exc.InvalidRequestError: Can't operate on closed transaction
-        # (#39191).
-        session.flush()
+        # Commit changes to database
+        session.commit()
 
         return dataset
 
@@ -815,15 +810,9 @@ class DatasetService:
         if data.get("icon_info"):
             filtered_data["icon_info"] = data.get("icon_info")
 
-        # Update dataset in database. Use flush() rather than commit() so the
-        # caller-managed transaction (opened with `with Session(...) as session`)
-        # stays open for subsequent operations — _update_pipeline_knowledge_base
-        # node data and any caller follow-ups run on the same session. Calling
-        # commit() here closed the context manager early and raised
-        # sqlalchemy.exc.InvalidRequestError: Can't operate on closed transaction
-        # (#39191).
+        # Update dataset in database
         session.execute(update(Dataset).where(Dataset.id == dataset.id).values(**filtered_data))
-        session.flush()
+        session.commit()
 
         # Reload dataset to get updated values
         session.refresh(dataset)

api/services/enterprise/rbac_service.py

@@ -317,6 +317,9 @@ _LEGACY_WORKSPACE_OWNER_KEYS: list[str] = [
     "credential.use",
     "credential.create",
     "credential.manage",
+    "billing.view",
+    "billing.subscription.manage",
+    "billing.manage",
     "app.acl.preview",
     "app_library.access",
     "app.create_and_management",
@@ -346,6 +349,9 @@ _LEGACY_WORKSPACE_ADMIN_KEYS: list[str] = [
     "credential.use",
     "credential.create",
     "credential.manage",
+    "billing.view",
+    "billing.subscription.manage",
+    "billing.manage",
     "app_library.access",
     "app.create_and_management",
     "app.tag.manage",
@@ -371,6 +377,9 @@ _LEGACY_WORKSPACE_EDITOR_KEYS: list[str] = [
     "dataset.external.connect",
     "snippets.create_and_modify",
     "tool.manage",
+    "billing.view",
+    "billing.subscription.manage",
+    "billing.manage",
 ]
 
 _LEGACY_WORKSPACE_NORMAL_KEYS: list[str] = [
@@ -378,6 +387,9 @@ _LEGACY_WORKSPACE_NORMAL_KEYS: list[str] = [
     "plugin.install",
     "credential.use",
     "app_library.access",
+    "billing.view",
+    "billing.subscription.manage",
+    "billing.manage",
 ]
 
 _LEGACY_WORKSPACE_DATASET_OPERATOR_KEYS: list[str] = [
@@ -793,6 +805,7 @@ class RBACService:
             data = _inner_call(
                 "GET",
                 f"{_INNER_PREFIX}/role-permissions/catalog",
+                params={"billing_enabled": dify_config.BILLING_ENABLED},
                 tenant_id=tenant_id,
                 account_id=account_id,
             )

api/services/feature_service.py

@@ -100,7 +100,6 @@ class WebAppAuthModel(FeatureResponseModel):
     sso_config: WebAppAuthSSOModel = WebAppAuthSSOModel()
     allow_email_code_login: bool = False
     allow_email_password_login: bool = False
-    allow_public_access: bool = True
 
 
 class KnowledgePipeline(FeatureResponseModel):
@@ -184,7 +183,6 @@ class SystemFeatureModel(FeatureResponseModel):
     enable_trial_app: bool = False
     enable_explore_banner: bool = False
     enable_learn_app: bool = True
-    enable_step_by_step_tour: bool = False
     rbac_enabled: bool = False
 
 
@@ -287,8 +285,6 @@ class FeatureService:
         system_features.enable_trial_app = dify_config.ENABLE_TRIAL_APP
         system_features.enable_explore_banner = dify_config.ENABLE_EXPLORE_BANNER
         system_features.enable_learn_app = dify_config.ENABLE_LEARN_APP
-        system_features.webapp_auth.allow_public_access = dify_config.WEBAPP_PUBLIC_ACCESS_ENABLED
-        system_features.enable_step_by_step_tour = dify_config.ENABLE_STEP_BY_STEP_TOUR
 
     @classmethod
     def _fulfill_trial_models_from_env(cls) -> list[str]:

api/services/knowledge_fs_proxy.py

@@ -1,358 +0,0 @@
-"""Transport-only forwarding for the explicitly enabled KnowledgeFS Console operations.
-
-KnowledgeFS owns the request and response contract. This module binds short-lived
-account and workspace identities, enforces Dify's coarse workspace policy, and
-normalizes transport failures. Dify deliberately maintains a small product-facing
-operation registry instead of exposing the full upstream OpenAPI surface. The
-dedicated request path uses Dify's shared SSRF policy, never follows redirects,
-bounds buffered responses, and rejects compressed responses.
-"""
-
-from __future__ import annotations
-
-from collections.abc import Iterable, Mapping
-from datetime import UTC, datetime, timedelta
-from http import HTTPStatus
-from typing import Final, Literal, NamedTuple, Protocol
-
-import httpx
-import jwt
-
-from configs import dify_config
-from core.helper import ssrf_proxy
-from core.rbac import RBACPermission, RBACResourceScope
-from core.tools.errors import ToolSSRFError
-from models import Account
-from services.enterprise.rbac_service import RBACService
-
-type KnowledgeFSMethod = Literal["DELETE", "GET", "PATCH", "POST", "PUT"]
-type KnowledgeFSResponseKind = Literal["binary", "buffered", "stream"]
-type KnowledgeFSRequiredScope = Literal["knowledge-spaces:read", "knowledge-spaces:write"]
-
-_JWT_AUDIENCE = "knowledge-fs"
-_JWT_ISSUER = "dify"
-_JWT_TTL_SECONDS = 60
-_MAX_BUFFERED_RESPONSE_BYTES = 1024 * 1024
-
-
-class KnowledgeFSOperation(NamedTuple):
-    operation_id: str
-    method: KnowledgeFSMethod
-    path: str
-    response_kind: KnowledgeFSResponseKind
-    required_scope: KnowledgeFSRequiredScope
-    rbac_permission: RBACPermission
-    requires_dataset_editor: bool
-    max_response_bytes: int
-    request_headers: tuple[str, ...]
-    response_headers: tuple[str, ...]
-    response_media_types: tuple[str, ...]
-
-
-KNOWLEDGE_FS_CONSOLE_OPERATIONS: Final[tuple[KnowledgeFSOperation, ...]] = (
-    KnowledgeFSOperation(
-        operation_id="listKnowledgeSpaces",
-        method="GET",
-        path="knowledge-spaces",
-        response_kind="buffered",
-        required_scope="knowledge-spaces:read",
-        rbac_permission=RBACPermission.DATASET_READONLY,
-        requires_dataset_editor=False,
-        max_response_bytes=1_048_576,
-        request_headers=("x-trace-id",),
-        response_headers=("x-trace-id",),
-        response_media_types=("application/json",),
-    ),
-    KnowledgeFSOperation(
-        operation_id="createKnowledgeSpace",
-        method="POST",
-        path="knowledge-spaces",
-        response_kind="buffered",
-        required_scope="knowledge-spaces:write",
-        rbac_permission=RBACPermission.DATASET_CREATE_AND_MANAGEMENT,
-        requires_dataset_editor=True,
-        max_response_bytes=1_048_576,
-        request_headers=("x-trace-id",),
-        response_headers=("x-trace-id",),
-        response_media_types=("application/json",),
-    ),
-)
-
-
-class KnowledgeFSUpstreamResponse(NamedTuple):
-    response: httpx.Response
-    response_kind: KnowledgeFSResponseKind
-    operation: KnowledgeFSOperation
-
-
-class _RequestHeaders(Protocol):
-    def items(self) -> Iterable[tuple[str, str]]: ...
-
-
-class KnowledgeFSConfigurationError(RuntimeError):
-    """KnowledgeFS is incompletely configured or blocked by outbound policy."""
-
-
-class KnowledgeFSTimeoutError(RuntimeError):
-    """KnowledgeFS exceeded the configured request timeout."""
-
-
-class KnowledgeFSTransportError(RuntimeError):
-    """KnowledgeFS could not be reached or returned a response outside safety bounds."""
-
-
-class KnowledgeFSRouteNotAllowedError(RuntimeError):
-    """The requested path is outside the Console-visible KnowledgeFS surface."""
-
-
-class KnowledgeFSAccessDeniedError(RuntimeError):
-    """The Dify account lacks the workspace permission required by the operation."""
-
-
-def authorize_knowledge_fs_request(
-    *,
-    account: Account,
-    tenant_id: str,
-    operation: KnowledgeFSOperation,
-) -> None:
-    """Enforce Dify's workspace policy before KFS performs resource authorization.
-
-    Args:
-        account: Authenticated Dify account with its current workspace role.
-        tenant_id: Current Dify workspace identifier.
-        operation: Dify-maintained KnowledgeFS operation and policy metadata.
-
-    Raises:
-        KnowledgeFSAccessDeniedError: The account lacks a required legacy or enterprise permission.
-    """
-    if operation.requires_dataset_editor and not account.is_dataset_editor:
-        raise KnowledgeFSAccessDeniedError("KnowledgeFS mutations require dataset edit access")
-    if not RBACService.CheckAccess.check(
-        tenant_id,
-        account.id,
-        scene=operation.rbac_permission.value,
-        resource_type=RBACResourceScope.DATASET.value,
-    ):
-        raise KnowledgeFSAccessDeniedError("KnowledgeFS operation is denied by workspace RBAC")
-
-
-def proxy_knowledge_fs_request(
-    *,
-    account: Account,
-    method: KnowledgeFSMethod,
-    path: str,
-    tenant_id: str,
-    accept: str | None = None,
-    content_type: str | None = None,
-    query: bytes | None = None,
-    body: bytes | None = None,
-    request_headers: _RequestHeaders | None = None,
-) -> KnowledgeFSUpstreamResponse:
-    """Authorize and forward one allowlisted KnowledgeFS request as a single use case."""
-    operation = get_knowledge_fs_operation(method, path)
-    authorize_knowledge_fs_request(
-        account=account,
-        tenant_id=tenant_id,
-        operation=operation,
-    )
-    incoming_request_headers = {name.lower(): value for name, value in (request_headers or {}).items()}
-    contract_request_headers = {
-        name: incoming_request_headers[name] for name in operation.request_headers if name in incoming_request_headers
-    }
-    return _forward_knowledge_fs_request(
-        account_id=account.id,
-        method=method,
-        path=path,
-        tenant_id=tenant_id,
-        accept=accept,
-        content_type=content_type,
-        query=query,
-        body=body,
-        request_headers=contract_request_headers,
-    )
-
-
-def _forward_knowledge_fs_request(
-    *,
-    account_id: str,
-    method: KnowledgeFSMethod,
-    path: str,
-    tenant_id: str,
-    accept: str | None = None,
-    content_type: str | None = None,
-    query: bytes | None = None,
-    body: bytes | None = None,
-    request_headers: Mapping[str, str] | None = None,
-) -> KnowledgeFSUpstreamResponse:
-    """Forward one fixed-route request without parsing its KnowledgeFS payload.
-
-    Args:
-        account_id: Current Dify account used as the KFS member identity.
-        method: Allowlisted upstream HTTP method.
-        path: Relative KnowledgeFS path under an allowlisted product surface.
-        tenant_id: Current Dify workspace used as the KFS tenant identity.
-        accept: Original Accept header, when present.
-        content_type: Original request Content-Type header, when present.
-        query: Original encoded query string from the Console request.
-        body: Original request body, when present.
-        request_headers: Contract-declared request headers forwarded by the Console adapter.
-
-    Returns:
-        The KnowledgeFS response and its actual transport kind. Non-success responses are buffered.
-
-    Raises:
-        KnowledgeFSConfigurationError: The connection is incomplete or blocked by outbound policy.
-        KnowledgeFSRouteNotAllowedError: The path is outside the allowlisted product surface.
-        KnowledgeFSTimeoutError: KnowledgeFS exceeds the configured timeout.
-        KnowledgeFSTransportError: The request fails or its response cannot be safely bounded.
-
-    Each request is bound to stable Dify account and workspace principals with a short expiration.
-    """
-    operation = get_knowledge_fs_operation(method, path)
-    base_url = dify_config.KNOWLEDGE_FS_BASE_URL
-    jwt_secret = dify_config.KNOWLEDGE_FS_JWT_SECRET
-    if base_url is None or jwt_secret is None:
-        raise KnowledgeFSConfigurationError("KnowledgeFS connection configuration is incomplete")
-    now = datetime.now(UTC)
-    token = jwt.encode(
-        {
-            "aud": _JWT_AUDIENCE,
-            "caller_kind": "interactive",
-            "dify_account_id": f"dify-account:{account_id}",
-            "exp": now + timedelta(seconds=_JWT_TTL_SECONDS),
-            "iat": now,
-            "iss": _JWT_ISSUER,
-            "scopes": [operation.required_scope],
-            "sub": f"dify-workspace:{tenant_id}",
-            "tenant_id": tenant_id,
-        },
-        jwt_secret.get_secret_value(),
-        algorithm="HS256",
-    )
-    headers = {
-        "Accept": accept or "application/json",
-        "Accept-Encoding": "identity",
-        "Authorization": f"Bearer {token}",
-    }
-    if body is not None:
-        headers["Content-Type"] = content_type or "application/json"
-    allowed_request_headers = set(operation.request_headers)
-    for name, value in (request_headers or {}).items():
-        normalized_name = name.lower()
-        if normalized_name not in allowed_request_headers:
-            raise KnowledgeFSRouteNotAllowedError("KnowledgeFS request header is not allowed")
-        headers[normalized_name] = value
-
-    try:
-        upstream_url = httpx.URL(f"{base_url}/").join(operation.path)
-        response = ssrf_proxy.make_request(
-            method=operation.method,
-            url=str(upstream_url),
-            params=query,
-            content=body,
-            headers=headers,
-            timeout=dify_config.KNOWLEDGE_FS_TIMEOUT_SECONDS,
-            follow_redirects=False,
-            max_retries=0,
-            stream_response=True,
-        )
-        response_kind = _classify_response(operation, response)
-        if response_kind == "stream":
-            content_encoding = response.headers.get("content-encoding", "identity").strip().lower()
-            if content_encoding not in {"", "identity"}:
-                response.close()
-                raise KnowledgeFSTransportError("KnowledgeFS streaming response used an unsupported encoding")
-            _set_response_read_timeout(response, dify_config.KNOWLEDGE_FS_SSE_READ_TIMEOUT_SECONDS)
-            return KnowledgeFSUpstreamResponse(response, response_kind, operation)
-
-        max_response_bytes = (
-            operation.max_response_bytes
-            if HTTPStatus.OK <= response.status_code < HTTPStatus.MULTIPLE_CHOICES
-            else _MAX_BUFFERED_RESPONSE_BYTES
-        )
-        buffered_response = ssrf_proxy.buffer_response(response, max_response_bytes=max_response_bytes)
-        if buffered_response.content and not buffered_response.headers.get("content-type", "").strip():
-            buffered_response.close()
-            raise KnowledgeFSTransportError("KnowledgeFS buffered response used an unsupported media type")
-        return KnowledgeFSUpstreamResponse(buffered_response, response_kind, operation)
-    except ssrf_proxy.ResponseLimitError as exc:
-        raise KnowledgeFSTransportError("KnowledgeFS response violated the proxy limit") from exc
-    except ToolSSRFError as exc:
-        raise KnowledgeFSConfigurationError("KnowledgeFS origin was blocked by outbound policy") from exc
-    except httpx.TimeoutException as exc:
-        raise KnowledgeFSTimeoutError("KnowledgeFS request timed out") from exc
-    except httpx.RequestError as exc:
-        raise KnowledgeFSTransportError("KnowledgeFS transport request failed") from exc
-
-
-def get_knowledge_fs_operation(method: KnowledgeFSMethod, path: str) -> KnowledgeFSOperation:
-    """Resolve an exact operation and its transport/access contract metadata."""
-    for operation in KNOWLEDGE_FS_CONSOLE_OPERATIONS:
-        if method == operation.method and _matches_route_template(operation.path, path):
-            return operation._replace(path=path)
-    raise KnowledgeFSRouteNotAllowedError("KnowledgeFS route is not allowed")
-
-
-def _classify_response(operation: KnowledgeFSOperation, response: httpx.Response) -> KnowledgeFSResponseKind:
-    """Resolve the actual response kind from status and Content-Type before reading its body."""
-    content_type = response.headers.get("content-type", "").partition(";")[0].strip().lower()
-    is_success = HTTPStatus.OK <= response.status_code < HTTPStatus.MULTIPLE_CHOICES
-    if not is_success:
-        if content_type and not _is_json_content_type(content_type):
-            response.close()
-            raise KnowledgeFSTransportError("KnowledgeFS error response used an unsupported media type")
-        return "buffered"
-
-    if operation.response_kind == "stream":
-        if content_type != "text/event-stream":
-            response.close()
-            raise KnowledgeFSTransportError("KnowledgeFS stream response used an unsupported media type")
-        return "stream"
-    if operation.response_kind == "binary":
-        if content_type not in operation.response_media_types:
-            response.close()
-            raise KnowledgeFSTransportError("KnowledgeFS binary response used an unsupported media type")
-        return "binary"
-    if content_type and not _is_json_content_type(content_type):
-        response.close()
-        raise KnowledgeFSTransportError("KnowledgeFS buffered response used an unsupported media type")
-    return "buffered"
-
-
-def _is_json_content_type(content_type: str) -> bool:
-    return content_type == "application/json" or content_type.endswith("+json")
-
-
-def _set_response_read_timeout(response: httpx.Response, timeout_seconds: float | None) -> None:
-    """Set the body-read timeout after headers identify a valid SSE response."""
-    try:
-        request = response.request
-    except RuntimeError:
-        return
-    timeout = request.extensions.get("timeout")
-    if isinstance(timeout, dict):
-        timeout["read"] = timeout_seconds
-
-
-def _matches_route_template(template: str, path: str) -> bool:
-    """Match path parameters without permitting encoded or traversal-like segments."""
-    template_segments = template.split("/")
-    path_segments = path.split("/")
-    if len(template_segments) != len(path_segments):
-        return False
-
-    for template_segment, path_segment in zip(template_segments, path_segments, strict=True):
-        if template_segment.startswith("{") and template_segment.endswith("}"):
-            if (
-                not path_segment
-                or path_segment in {".", ".."}
-                or "\\" in path_segment
-                or "%" in path_segment
-                or "?" in path_segment
-                or "#" in path_segment
-            ):
-                return False
-            continue
-        if template_segment != path_segment:
-            return False
-    return True

api/services/rag_pipeline/rag_pipeline.py

@@ -601,7 +601,6 @@ class RagPipelineService:
         with sessionmaker(bind=db.engine).begin() as session:
             draft_var_saver = DraftVariableSaver(
                 session=session,
-                tenant_id=pipeline.tenant_id,
                 app_id=pipeline.id,
                 node_id=workflow_node_execution.node_id,
                 node_type=workflow_node_execution.node_type,
@@ -1392,7 +1391,6 @@ class RagPipelineService:
         with sessionmaker(bind=db.engine).begin() as session:
             draft_var_saver = DraftVariableSaver(
                 session=session,
-                tenant_id=pipeline.tenant_id,
                 app_id=pipeline.id,
                 node_id=workflow_node_execution_db_model.node_id,
                 node_type=workflow_node_execution_db_model.node_type,

api/services/retention/workflow_run/archive_paid_plan_workflow_run.py

@@ -6,10 +6,7 @@ This service archives workflow run logs for paid plan users older than the confi
 
 Archive V2 writes bundle-level Parquet objects. A bundle contains many workflow runs and their related table rows.
 Bundle metadata lives in the object-store manifest as the recoverable source of truth. Completed bundles are also
-published into a small database catalog so console listing, download, and maintenance jobs do not list object storage
-online. Archive success requires that catalog publication to commit. A retry reconciles only its known manifest key
-against an already-published shard index; a missing shard index fails closed rather than rebuilding it by scanning
-historical manifests.
+mirrored into a small database index so console listing and download jobs do not list object storage online.
 
 Archive campaigns should use fixed absolute UTC windows for every tenant-prefix/shard execution. Relative windows are
 evaluated at process start and are not safe for multi-day rollout because each command would scan a different window.
@@ -642,6 +639,7 @@ class WorkflowRunArchiver:
                 if storage is None:
                     raise ArchiveStorageNotConfiguredError("Archive storage not configured")
                 if storage.object_exists(self._get_manifest_object_key(identity)):
+                    self._write_bundle_index(storage, identity)
                     self._sync_existing_bundle_index(session, storage, identity)
                     result.success = True
                     result.skipped = True
@@ -653,8 +651,6 @@ class WorkflowRunArchiver:
                 runs = [run for run in runs if run.id not in archived_run_ids]
                 result.skipped_run_count = original_run_count - len(runs)
                 if not runs:
-                    # Historical catalog rows are a rollout precondition. New bundles commit their catalog row before
-                    # publishing the shard index, so this idempotency path never needs to rescan prior manifests.
                     result.run_count = 0
                     result.success = True
                     result.skipped = True
@@ -667,6 +663,7 @@ class WorkflowRunArchiver:
                 result.object_prefix = identity.object_prefix
                 result.run_count = len(runs)
                 if storage.object_exists(self._get_manifest_object_key(identity)):
+                    self._write_bundle_index(storage, identity)
                     self._sync_existing_bundle_index(session, storage, identity)
                     result.success = True
                     result.skipped = True
@@ -698,10 +695,10 @@ class WorkflowRunArchiver:
                 for table_name, payload in table_payloads.items():
                     storage.put_object(self._get_table_object_key(identity, table_name), payload)
                 storage.put_object(self._get_manifest_object_key(identity), manifest_data)
+                self._merge_bundle_manifest_into_index(storage, identity, [run.id for run in runs])
                 manifest = decode_archive_bundle_manifest(manifest_data)
                 upsert_archive_bundle_index_from_manifest(session, manifest, len(manifest_data))
                 session.commit()
-                self._merge_bundle_manifest_into_index(storage, identity, [run.id for run in runs])
 
                 logger.info(
                     "Archived workflow run bundle %s: tenant=%s runs=%s tables=%s object_prefix=%s",
@@ -733,18 +730,16 @@ class WorkflowRunArchiver:
         storage: ArchiveStorage,
         identity: ArchiveBundleIdentity,
     ) -> None:
-        """Publish a known manifest to the DB catalog and reconcile its existing shard index."""
+        """Best-effort DB index sync for a bundle whose manifest already exists in archive storage."""
         manifest_key = self._get_manifest_object_key(identity)
-        manifest_data = storage.get_object(manifest_key)
-        manifest = decode_archive_bundle_manifest(manifest_data)
-        upsert_archive_bundle_index_from_manifest(session, manifest, len(manifest_data))
-        session.commit()
-        self._merge_bundle_manifest_into_index(
-            storage,
-            identity,
-            manifest["run_ids"],
-            require_existing_index=True,
-        )
+        try:
+            manifest_data = storage.get_object(manifest_key)
+            manifest = decode_archive_bundle_manifest(manifest_data)
+            upsert_archive_bundle_index_from_manifest(session, manifest, len(manifest_data))
+            session.commit()
+        except Exception:
+            session.rollback()
+            logger.warning("Failed to sync workflow archive bundle index for %s", manifest_key, exc_info=True)
 
     def _lock_runs_for_archive(
         self,
@@ -1034,20 +1029,10 @@ class WorkflowRunArchiver:
         storage: ArchiveStorage,
         identity: ArchiveBundleIdentity,
         run_ids: Sequence[str],
-        *,
-        require_existing_index: bool = False,
     ) -> ArchiveBundleIndexDict:
-        """
-        Merge one bundle into its shard index.
-
-        Retries for a known manifest set ``require_existing_index`` so they never create a partial index by scanning
-        or overwriting a shard whose historical entries cannot be proven from this one manifest.
-        """
         index_key = self._get_index_object_key(identity)
         if storage.object_exists(index_key):
             index = self._load_bundle_index(storage, identity)
-        elif require_existing_index:
-            raise RuntimeError(f"archive shard index missing while reconciling known manifest: {index_key}")
         else:
             index = self._build_bundle_index(storage, identity)
 

api/services/retention/workflow_run/bundle_archive_maintenance.py

@@ -1,16 +1,14 @@
 """
 Maintain V2 workflow-run archive bundles.
 
-Archive V2 keeps object-store manifests as the recoverable bundle source of truth. Delete and restore discover a
-bounded page of candidates from `workflow_run_archive_bundles`, optionally restricted to one exact archive shard, then
-construct each immutable manifest key from the catalog identity. They never list the object-store namespace.
-Object-store marker files keep delete/restore idempotent, while the caller persists a non-dry-run cursor only after a
-candidate succeeds.
+Archive V2 keeps object-store manifests as the recoverable bundle source of truth. This maintenance module still
+discovers delete/restore targets by listing `manifest.json` objects and uses object-store marker files for
+delete/restore state. The separate database bundle index is intended for console listing and download jobs, not as the
+source of truth for destructive maintenance.
 
 Each bundle is processed in its own database transaction. A failed bundle leaves source rows unchanged unless the
 transaction has already committed; marker handling makes the next run able to reconcile the common committed-but-marker
-not-updated case. Restore never skips a bundle with a missing deleted marker when deletion started or source rows have
-drifted, so an external cursor cannot pass an interrupted delete.
+not-updated case.
 """
 
 import datetime
@@ -40,7 +38,6 @@ from models.workflow import (
     WorkflowPause,
     WorkflowPauseReason,
     WorkflowRun,
-    WorkflowRunArchiveBundle,
 )
 from services.retention.workflow_run.constants import (
     ARCHIVE_BUNDLE_DELETE_STARTED_MARKER_NAME,
@@ -54,6 +51,7 @@ from services.retention.workflow_run.constants import (
 
 logger = logging.getLogger(__name__)
 
+_ARCHIVE_ROOT_PREFIX = "workflow-runs/v2/"
 _CHUNK_SIZE = 5_000
 
 
@@ -85,29 +83,12 @@ class BundleManifest(TypedDict):
     run_ids: list[str]
 
 
-@dataclass(frozen=True)
-class ArchiveBundleCatalogEntry:
-    """Immutable catalog identity and manifest-derived metrics for one V2 archive bundle."""
-
-    catalog_id: str
-    tenant_id: str
-    year: int
-    month: int
-    shard: str
-    bundle_id: str
-    workflow_run_count: int
-    row_count: int
-    archive_bytes: int
-
-
 @dataclass(frozen=True)
 class BundleReference:
-    """Verified object-store reference for one catalog candidate."""
+    """Object-store reference for one V2 archive bundle."""
 
-    catalog: ArchiveBundleCatalogEntry
     object_prefix: str
     manifest_key: str
-    manifest_size_bytes: int
     manifest: BundleManifest
 
 
@@ -115,7 +96,6 @@ class BundleReference:
 class BundleOperationResult:
     """Result for one V2 bundle delete or restore operation."""
 
-    catalog_id: str
     bundle_id: str
     tenant_id: str
     object_prefix: str
@@ -148,8 +128,6 @@ class BundleOperationSummary:
     archive_bytes: int = 0
     elapsed_time: float = 0.0
     validation_time: float = 0.0
-    next_catalog_id: str | None = None
-    preview_next_catalog_id: str | None = None
     table_counts: dict[str, int] = field(default_factory=dict)
     results: list[BundleOperationResult] = field(default_factory=list)
 
@@ -202,334 +180,162 @@ RESTORE_ORDER = [
     "workflow_trigger_logs",
 ]
 
-DELETE_ORDER = [
-    "workflow_pause_reasons",
-    "workflow_node_execution_offload",
-    "workflow_trigger_logs",
-    "workflow_app_logs",
-    "workflow_node_executions",
-    "workflow_pauses",
-    "workflow_runs",
-]
-
 
 class WorkflowRunBundleArchiveMaintenance:
     """
     Delete and restore V2 workflow-run archive bundles.
 
-    Delete accepts already-missing source rows only when every remaining row in the bundle scope is an unchanged
-    archive subset. It then removes only those verified primary keys, so unrelated or unarchived rows fail closed.
-    Non-dry-run delete and restore serialize on the existing archive catalog row before checking markers or changing
-    source rows.
-
     Args:
         dry_run: Validate and report counts without changing source rows or object-store markers.
-        strict_content_validation: Compare restored source-table content checksums against Parquet content. Delete
-            always validates that every remaining live row belongs to and matches the archive before removing it.
-        storage: Optional archive storage implementation. Tests may provide an in-memory implementation.
-        session_factory: Optional session factory. Each candidate is processed in its own transaction.
-
-    Batches stop at the first error so a returned cursor cannot pass an unhandled candidate.
+        strict_content_validation: Compare source-table content checksums against Parquet content before destructive
+            delete and after restore. Keep enabled for real maintenance.
+        stop_on_error: Stop batch processing after the first failed bundle.
     """
 
     dry_run: bool
     strict_content_validation: bool
-    storage: ArchiveStorage | None
-    session_factory: sessionmaker[Session]
+    stop_on_error: bool
 
     def __init__(
         self,
         *,
         dry_run: bool = False,
         strict_content_validation: bool = True,
-        storage: ArchiveStorage | None = None,
-        session_factory: sessionmaker[Session] | None = None,
+        stop_on_error: bool = True,
     ) -> None:
         self.dry_run = dry_run
         self.strict_content_validation = strict_content_validation
-        self.storage = storage
-        self.session_factory = session_factory or sessionmaker(bind=db.engine, expire_on_commit=False)
+        self.stop_on_error = stop_on_error
 
     def delete_batch(
         self,
         *,
         tenant_ids: Sequence[str] | None,
-        target_year: int,
-        target_month: int,
-        after_catalog_id: str | None,
+        start_date: datetime.datetime,
+        end_date: datetime.datetime,
         limit: int,
-        shard: str | None = None,
     ) -> BundleOperationSummary:
-        """Validate and delete one keyset page, optionally scoped to an exact archive shard."""
+        """Validate and delete source rows for archived V2 bundles in the requested created_at window."""
         return self._process_batch(
             operation="delete",
             tenant_ids=tenant_ids,
-            target_year=target_year,
-            target_month=target_month,
-            after_catalog_id=after_catalog_id,
+            start_date=start_date,
+            end_date=end_date,
             limit=limit,
-            shard=shard,
         )
 
     def restore_batch(
         self,
         *,
         tenant_ids: Sequence[str] | None,
-        target_year: int,
-        target_month: int,
-        after_catalog_id: str | None,
+        start_date: datetime.datetime,
+        end_date: datetime.datetime,
         limit: int,
     ) -> BundleOperationSummary:
-        """Restore source rows for a keyset page of deleted V2 bundles in one calendar month."""
+        """Restore source rows for deleted V2 bundles in the requested created_at window."""
         return self._process_batch(
             operation="restore",
             tenant_ids=tenant_ids,
-            target_year=target_year,
-            target_month=target_month,
-            after_catalog_id=after_catalog_id,
+            start_date=start_date,
+            end_date=end_date,
             limit=limit,
-            shard=None,
         )
 
-    def validate_catalog_shards(
-        self,
-        *,
-        target_year: int,
-        target_month: int,
-        shard_total: int,
-        tenant_ids: Sequence[str] | None = None,
-    ) -> None:
-        """
-        Fail before a parallel delete when the requested closed-month scope contains a different shard layout.
-
-        A subset of the expected shards is valid because an archive shard may legitimately contain no bundles. Any
-        other shard name indicates a historical or mixed-layout month that must be handled by the serial delete path.
-        """
-        if not 1 <= shard_total <= 16:
-            raise ValueError("shard_total must be between 1 and 16")
-        expected_shards = tuple(f"{index:02d}-of-{shard_total:02d}" for index in range(shard_total))
-        conditions = [
-            WorkflowRunArchiveBundle.year == target_year,
-            WorkflowRunArchiveBundle.month == target_month,
-        ]
-        if tenant_ids is not None:
-            conditions.append(WorkflowRunArchiveBundle.tenant_id.in_(tenant_ids))
-        statement = (
-            select(WorkflowRunArchiveBundle.shard)
-            .where(
-                *conditions,
-                WorkflowRunArchiveBundle.shard.not_in(expected_shards),
-            )
-            .distinct()
-            .order_by(WorkflowRunArchiveBundle.shard.asc())
-        )
-        with self.session_factory() as session:
-            unexpected_shards = list(session.scalars(statement))
-        if unexpected_shards:
-            raise ValueError(
-                "archive catalog month contains unexpected shards for "
-                f"{shard_total}-way delete: {', '.join(unexpected_shards)}"
-            )
-
     def _process_batch(
         self,
         *,
         operation: str,
         tenant_ids: Sequence[str] | None,
-        target_year: int,
-        target_month: int,
-        after_catalog_id: str | None,
+        start_date: datetime.datetime,
+        end_date: datetime.datetime,
         limit: int,
-        shard: str | None,
     ) -> BundleOperationSummary:
         start_time = time.time()
         summary = BundleOperationSummary(operation=operation)
         if tenant_ids is not None and not tenant_ids:
             return summary
 
-        storage = self.storage or self._get_archive_storage()
-        catalog_entries = self._list_catalog_entries(
+        storage = self._get_archive_storage()
+        bundle_refs = self._list_bundle_refs(
+            storage,
+            operation=operation,
             tenant_ids=tenant_ids,
-            target_year=target_year,
-            target_month=target_month,
-            after_catalog_id=after_catalog_id,
+            start_date=start_date,
+            end_date=end_date,
             limit=limit,
-            shard=shard,
         )
 
-        logger.info(
-            "Found %s V2 archive catalog candidates for %s: year=%s month=%s shard=%s after_catalog_id=%s",
-            len(catalog_entries),
-            operation,
-            target_year,
-            target_month,
-            shard,
-            after_catalog_id,
-        )
-        for catalog_entry in catalog_entries:
-            try:
-                bundle_ref = self._build_bundle_reference(storage, catalog_entry)
-                with self.session_factory() as session:
-                    if operation == "delete":
-                        result = self._delete_bundle(session, storage, bundle_ref)
-                    elif operation == "restore":
-                        result = self._restore_bundle(session, storage, bundle_ref)
-                    else:
-                        raise ValueError(f"Unsupported operation: {operation}")
-            except Exception as exc:
-                result = self._new_result_from_catalog_entry(catalog_entry)
-                result.error = str(exc)
-                logger.exception(
-                    "Failed to prepare V2 archive bundle %s from catalog %s",
-                    catalog_entry.bundle_id,
-                    catalog_entry.catalog_id,
-                )
+        logger.info("Found %s V2 archive bundles for %s", len(bundle_refs), operation)
+        session_maker = sessionmaker(bind=db.engine, expire_on_commit=False)
+        for bundle_ref in bundle_refs:
+            with session_maker() as session:
+                if operation == "delete":
+                    result = self._delete_bundle(session, storage, bundle_ref)
+                elif operation == "restore":
+                    result = self._restore_bundle(session, storage, bundle_ref)
+                else:
+                    raise ValueError(f"Unsupported operation: {operation}")
 
             self._merge_result(summary, result)
-            if result.success:
-                if self.dry_run:
-                    summary.preview_next_catalog_id = catalog_entry.catalog_id
-                else:
-                    summary.next_catalog_id = catalog_entry.catalog_id
-            else:
+            if not result.success and self.stop_on_error:
                 logger.error("Stopping V2 bundle %s after failure: %s", operation, result.error)
                 break
 
         summary.elapsed_time = time.time() - start_time
         return summary
 
-    def _list_catalog_entries(
-        self,
-        *,
-        tenant_ids: Sequence[str] | None,
-        target_year: int,
-        target_month: int,
-        after_catalog_id: str | None,
-        limit: int,
-        shard: str | None = None,
-    ) -> list[ArchiveBundleCatalogEntry]:
-        """Read one bounded, stable-order candidate page from the database catalog."""
-        conditions = [
-            WorkflowRunArchiveBundle.year == target_year,
-            WorkflowRunArchiveBundle.month == target_month,
-        ]
-        if tenant_ids:
-            conditions.append(WorkflowRunArchiveBundle.tenant_id.in_(tenant_ids))
-        if shard is not None:
-            conditions.append(WorkflowRunArchiveBundle.shard == shard)
-        if after_catalog_id:
-            conditions.append(WorkflowRunArchiveBundle.id > after_catalog_id)
-
-        statement = (
-            select(WorkflowRunArchiveBundle).where(*conditions).order_by(WorkflowRunArchiveBundle.id.asc()).limit(limit)
-        )
-        with self.session_factory() as session:
-            if after_catalog_id:
-                cursor_bundle = session.get(WorkflowRunArchiveBundle, after_catalog_id)
-                self._validate_catalog_cursor_scope(
-                    cursor_bundle,
-                    tenant_ids=tenant_ids,
-                    target_year=target_year,
-                    target_month=target_month,
-                    shard=shard,
-                )
-            bundles = list(session.scalars(statement))
-        return [
-            ArchiveBundleCatalogEntry(
-                catalog_id=bundle.id,
-                tenant_id=bundle.tenant_id,
-                year=bundle.year,
-                month=bundle.month,
-                shard=bundle.shard,
-                bundle_id=bundle.bundle_id,
-                workflow_run_count=bundle.workflow_run_count,
-                row_count=bundle.row_count,
-                archive_bytes=bundle.archive_bytes,
-            )
-            for bundle in bundles
-        ]
-
-    @staticmethod
-    def _validate_catalog_cursor_scope(
-        cursor_bundle: WorkflowRunArchiveBundle | None,
-        *,
-        tenant_ids: Sequence[str] | None,
-        target_year: int,
-        target_month: int,
-        shard: str | None,
-    ) -> None:
-        """Reject a keyset cursor that cannot safely represent the requested catalog scope."""
-        if cursor_bundle is None:
-            raise ValueError("after_catalog_id does not exist in the workflow run archive bundle catalog")
-        if cursor_bundle.year != target_year or cursor_bundle.month != target_month:
-            raise ValueError("after_catalog_id is outside the requested archive month")
-        if tenant_ids is not None and cursor_bundle.tenant_id not in tenant_ids:
-            raise ValueError("after_catalog_id is outside the requested tenant scope")
-        if shard is not None and cursor_bundle.shard != shard:
-            raise ValueError("after_catalog_id is outside the requested archive shard")
-
-    def _build_bundle_reference(
+    def _list_bundle_refs(
         self,
         storage: ArchiveStorage,
-        catalog_entry: ArchiveBundleCatalogEntry,
-    ) -> BundleReference:
-        """Load and bind one manifest to the catalog row that selected it."""
-        object_prefix = self._catalog_object_prefix(catalog_entry)
-        manifest_key = f"{object_prefix}/{ARCHIVE_BUNDLE_MANIFEST_NAME}"
-        manifest_data = storage.get_object(manifest_key)
-        manifest = self._load_and_validate_manifest(manifest_data, object_prefix=object_prefix)
-        self._validate_manifest_catalog_identity(manifest, catalog_entry)
-        return BundleReference(
-            catalog=catalog_entry,
-            object_prefix=object_prefix,
-            manifest_key=manifest_key,
-            manifest_size_bytes=len(manifest_data),
-            manifest=manifest,
-        )
+        *,
+        operation: str,
+        tenant_ids: Sequence[str] | None,
+        start_date: datetime.datetime,
+        end_date: datetime.datetime,
+        limit: int,
+    ) -> list[BundleReference]:
+        start_date = self._to_naive_utc(start_date)
+        end_date = self._to_naive_utc(end_date)
+        manifest_keys = self._list_manifest_keys(storage, tenant_ids)
+        refs: list[BundleReference] = []
+        for manifest_key in manifest_keys:
+            manifest_data = self._get_checked_object(storage, manifest_key)
+            object_prefix = manifest_key.removesuffix(f"/{ARCHIVE_BUNDLE_MANIFEST_NAME}")
+            manifest = self._load_and_validate_manifest(manifest_data, object_prefix=object_prefix)
+            min_created_at = self._parse_manifest_datetime(manifest["min_created_at"])
+            max_created_at = self._parse_manifest_datetime(manifest["max_created_at"])
+            if max_created_at < start_date or min_created_at >= end_date:
+                continue
+            if tenant_ids and manifest["tenant_id"] not in tenant_ids:
+                continue
+            if operation == "delete" and self._is_deleted(storage, object_prefix):
+                continue
+            if operation == "restore" and not self._is_deleted(storage, object_prefix):
+                continue
+            refs.append(BundleReference(object_prefix=object_prefix, manifest_key=manifest_key, manifest=manifest))
 
-    @staticmethod
-    def _catalog_object_prefix(catalog_entry: ArchiveBundleCatalogEntry) -> str:
-        """Construct the immutable V2 bundle prefix from its database catalog identity."""
-        if not catalog_entry.tenant_id:
-            raise ValueError("archive catalog tenant_id must not be empty")
-        if not 1 <= catalog_entry.month <= 12:
-            raise ValueError(f"archive catalog month is invalid: {catalog_entry.month}")
-        return (
-            f"workflow-runs/v2/tenant_prefix={catalog_entry.tenant_id[0].lower()}/"
-            f"tenant_id={catalog_entry.tenant_id}/year={catalog_entry.year:04d}/"
-            f"month={catalog_entry.month:02d}/shard={catalog_entry.shard}/bundle={catalog_entry.bundle_id}"
-        )
-
-    @staticmethod
-    def _validate_manifest_catalog_identity(
-        manifest: BundleManifest,
-        catalog_entry: ArchiveBundleCatalogEntry,
-    ) -> None:
-        """Fail closed when the catalog locator and manifest identify different immutable bundles."""
-        expected_identity = (
-            catalog_entry.tenant_id,
-            catalog_entry.year,
-            catalog_entry.month,
-            catalog_entry.shard,
-            catalog_entry.bundle_id,
-        )
-        manifest_identity = (
-            manifest["tenant_id"],
-            manifest["year"],
-            manifest["month"],
-            manifest["shard"],
-            manifest["bundle_id"],
-        )
-        if manifest_identity != expected_identity:
-            raise ValueError(
-                f"archive manifest identity does not match catalog: expected={expected_identity}, "
-                f"actual={manifest_identity}"
+        refs.sort(
+            key=lambda ref: (
+                self._parse_manifest_datetime(ref.manifest["min_created_at"]),
+                ref.manifest["tenant_id"],
+                ref.manifest["bundle_id"],
             )
-        if manifest["workflow_run_count"] != catalog_entry.workflow_run_count:
-            raise ValueError("archive manifest workflow_run_count does not match catalog")
-        manifest_row_count = sum(table["row_count"] for table in manifest["tables"].values())
-        if manifest_row_count != catalog_entry.row_count:
-            raise ValueError("archive manifest row_count does not match catalog")
+        )
+        return refs[:limit]
+
+    @staticmethod
+    def _list_manifest_keys(storage: ArchiveStorage, tenant_ids: Sequence[str] | None) -> list[str]:
+        keys: list[str] = []
+        if tenant_ids:
+            prefixes = [
+                f"{_ARCHIVE_ROOT_PREFIX}tenant_prefix={tenant_id[0].lower()}/tenant_id={tenant_id}/"
+                for tenant_id in tenant_ids
+            ]
+        else:
+            prefixes = [_ARCHIVE_ROOT_PREFIX]
+        for prefix in prefixes:
+            keys.extend(storage.list_objects(prefix))
+        return sorted(key for key in keys if key.endswith(f"/{ARCHIVE_BUNDLE_MANIFEST_NAME}"))
 
     def _delete_bundle(
         self,
@@ -538,61 +344,37 @@ class WorkflowRunBundleArchiveMaintenance:
         bundle_ref: BundleReference,
     ) -> BundleOperationResult:
         start_time = time.time()
-        result = self._new_result(bundle_ref.manifest, bundle_ref.catalog.catalog_id)
+        result = self._new_result(bundle_ref.manifest)
         try:
             validation_start = time.time()
-            if not self.dry_run:
-                self._lock_catalog_entry(session, bundle_ref.catalog)
-            if self._is_restore_started(storage, bundle_ref.object_prefix):
-                raise ValueError("restore started marker exists; reconcile restore before delete")
-
-            deleted_marker_exists = self._is_deleted(storage, bundle_ref.object_prefix)
             manifest, table_records, archive_bytes = self._validate_archive_object(storage, bundle_ref)
             result.table_counts = self._manifest_table_counts(manifest)
             result.archive_bytes = archive_bytes
 
-            live_records = self._load_live_bundle_records(
-                session,
-                manifest,
-                table_records,
-                lock=not self.dry_run,
-            )
-            if deleted_marker_exists:
-                live_counts = {table_name: len(live_records[table_name]) for table_name in ARCHIVED_TABLES}
-                if any(live_counts.values()):
-                    raise ValueError(f"Live rows exist for bundle with deleted marker: {live_counts}")
-                if not self.dry_run:
-                    self._delete_marker(storage, bundle_ref.object_prefix, ARCHIVE_BUNDLE_DELETE_STARTED_MARKER_NAME)
-                    self._delete_marker(storage, bundle_ref.object_prefix, ARCHIVE_BUNDLE_RESTORED_MARKER_NAME)
+            self._lock_workflow_runs(session, manifest["run_ids"])
+            if self._is_delete_started(storage, bundle_ref.object_prefix) and self._live_counts_match(
+                session, manifest, expected_present=False
+            ):
                 result.validation_time = time.time() - validation_start
-                result.success = True
-                result.elapsed_time = time.time() - start_time
-                return result
-
-            self._validate_live_archive_subset(manifest, table_records, live_records)
-            result.validation_time = time.time() - validation_start
-
-            if not any(live_records[table_name] for table_name in ARCHIVED_TABLES):
                 if not self.dry_run:
                     self._mark_deleted(storage, bundle_ref.object_prefix)
                     self._delete_marker(storage, bundle_ref.object_prefix, ARCHIVE_BUNDLE_DELETE_STARTED_MARKER_NAME)
-                    self._delete_marker(storage, bundle_ref.object_prefix, ARCHIVE_BUNDLE_RESTORED_MARKER_NAME)
                 result.success = True
-                result.elapsed_time = time.time() - start_time
                 return result
 
+            self._validate_live_counts(session, manifest, expected_present=True)
+            if self.strict_content_validation:
+                self._validate_live_content(session, table_records)
+            result.validation_time = time.time() - validation_start
+
             if not self.dry_run:
                 self._put_marker(storage, bundle_ref.object_prefix, ARCHIVE_BUNDLE_DELETE_STARTED_MARKER_NAME)
-                expected_deleted_counts = {table_name: len(live_records[table_name]) for table_name in ARCHIVED_TABLES}
-                deleted_counts = self._delete_bundle_rows(session, live_records)
-                if deleted_counts != expected_deleted_counts:
+                deleted_counts = self._delete_bundle_rows(session, table_records)
+                if deleted_counts != result.table_counts:
                     raise ValueError(
-                        f"Deleted row count mismatch: expected={expected_deleted_counts}, actual={deleted_counts}"
+                        f"Deleted row count mismatch: expected={result.table_counts}, actual={deleted_counts}"
                     )
-                remaining_records = self._load_live_bundle_records(session, manifest, table_records, lock=True)
-                remaining_counts = {table_name: len(remaining_records[table_name]) for table_name in ARCHIVED_TABLES}
-                if any(remaining_counts.values()):
-                    raise ValueError(f"Live rows remain after bundle delete: {remaining_counts}")
+                self._validate_live_counts(session, manifest, expected_present=False)
                 session.commit()
                 self._mark_deleted(storage, bundle_ref.object_prefix)
                 self._delete_marker(storage, bundle_ref.object_prefix, ARCHIVE_BUNDLE_DELETE_STARTED_MARKER_NAME)
@@ -612,25 +394,9 @@ class WorkflowRunBundleArchiveMaintenance:
         bundle_ref: BundleReference,
     ) -> BundleOperationResult:
         start_time = time.time()
-        result = self._new_result(bundle_ref.manifest, bundle_ref.catalog.catalog_id)
+        result = self._new_result(bundle_ref.manifest)
         try:
             validation_start = time.time()
-            if not self.dry_run:
-                self._lock_catalog_entry(session, bundle_ref.catalog)
-            if not self._is_deleted(storage, bundle_ref.object_prefix):
-                # A committed delete may be interrupted before `.deleted` is written. Do not let restore advance its
-                # cursor over that state: retry delete to reconcile it, or investigate source-row drift first.
-                if self._is_delete_started(storage, bundle_ref.object_prefix):
-                    raise ValueError("delete started marker exists without a deleted marker; reconcile delete first")
-                restore_started = self._is_restore_started(storage, bundle_ref.object_prefix)
-                self._validate_live_counts(session, bundle_ref.manifest, expected_present=True)
-                result.validation_time = time.time() - validation_start
-                if restore_started and not self.dry_run:
-                    self._mark_restored(storage, bundle_ref.object_prefix)
-                result.success = True
-                result.elapsed_time = time.time() - start_time
-                return result
-
             manifest, table_records, archive_bytes = self._validate_archive_object(storage, bundle_ref)
             result.table_counts = self._manifest_table_counts(manifest)
             result.archive_bytes = archive_bytes
@@ -642,7 +408,6 @@ class WorkflowRunBundleArchiveMaintenance:
                 if not self.dry_run:
                     self._mark_restored(storage, bundle_ref.object_prefix)
                 result.success = True
-                result.elapsed_time = time.time() - start_time
                 return result
 
             self._validate_live_counts(session, manifest, expected_present=False)
@@ -667,40 +432,13 @@ class WorkflowRunBundleArchiveMaintenance:
         return result
 
     @staticmethod
-    def _new_result(manifest: BundleManifest, catalog_id: str) -> BundleOperationResult:
+    def _new_result(manifest: BundleManifest) -> BundleOperationResult:
         return BundleOperationResult(
-            catalog_id=catalog_id,
             bundle_id=manifest["bundle_id"],
             tenant_id=manifest["tenant_id"],
             object_prefix=manifest["object_prefix"],
         )
 
-    @staticmethod
-    def _new_result_from_catalog_entry(catalog_entry: ArchiveBundleCatalogEntry) -> BundleOperationResult:
-        try:
-            object_prefix = WorkflowRunBundleArchiveMaintenance._catalog_object_prefix(catalog_entry)
-        except ValueError:
-            object_prefix = "<invalid archive catalog identity>"
-        return BundleOperationResult(
-            catalog_id=catalog_entry.catalog_id,
-            bundle_id=catalog_entry.bundle_id,
-            tenant_id=catalog_entry.tenant_id,
-            object_prefix=object_prefix,
-        )
-
-    @staticmethod
-    def _lock_catalog_entry(session: Session, catalog_entry: ArchiveBundleCatalogEntry) -> None:
-        locked_catalog_id = session.scalar(
-            select(WorkflowRunArchiveBundle.id)
-            .where(
-                WorkflowRunArchiveBundle.id == catalog_entry.catalog_id,
-                WorkflowRunArchiveBundle.tenant_id == catalog_entry.tenant_id,
-            )
-            .with_for_update()
-        )
-        if locked_catalog_id is None:
-            raise ValueError("archive catalog row disappeared before bundle maintenance")
-
     def _validate_archive_object(
         self,
         storage: ArchiveStorage,
@@ -708,7 +446,7 @@ class WorkflowRunBundleArchiveMaintenance:
     ) -> tuple[BundleManifest, dict[str, list[dict[str, Any]]], int]:
         manifest = bundle_ref.manifest
         table_records: dict[str, list[dict[str, Any]]] = {}
-        total_size = bundle_ref.manifest_size_bytes
+        total_size = len(storage.get_object(bundle_ref.manifest_key))
         for table_name in ARCHIVED_TABLES:
             info = manifest["tables"][table_name]
             payload = self._get_checked_object(storage, info["object_key"])
@@ -731,14 +469,12 @@ class WorkflowRunBundleArchiveMaintenance:
                     f"expected={info['row_count']}, actual={len(records)}"
                 )
             table_records[table_name] = records
-        if total_size != bundle_ref.catalog.archive_bytes:
-            raise ValueError(
-                f"Archive object total size mismatch: expected={bundle_ref.catalog.archive_bytes}, actual={total_size}"
-            )
         return manifest, table_records, total_size
 
     @staticmethod
     def _get_checked_object(storage: ArchiveStorage, object_key: str) -> bytes:
+        if not storage.object_exists(object_key):
+            raise FileNotFoundError(f"Archive object not found: {object_key}")
         return storage.get_object(object_key)
 
     @staticmethod
@@ -803,110 +539,6 @@ class WorkflowRunBundleArchiveMaintenance:
         table = pq.read_table(io.BytesIO(payload))
         return table.to_pylist()
 
-    def _load_live_bundle_records(
-        self,
-        session: Session,
-        manifest: BundleManifest,
-        table_records: dict[str, list[dict[str, Any]]],
-        *,
-        lock: bool,
-    ) -> dict[str, list[dict[str, Any]]]:
-        """Load the complete live scope for a bundle, including archived rows whose relationship fields drifted."""
-        run_ids = manifest["run_ids"]
-        archive_ids = {
-            table_name: [str(record["id"]) for record in table_records[table_name]] for table_name in ARCHIVED_TABLES
-        }
-        live_node_ids = self._select_ids_by_run_ids(session, WorkflowNodeExecutionModel, run_ids)
-        live_pause_ids = self._select_ids_by_run_ids(session, WorkflowPause, run_ids)
-        node_ids = sorted(set(archive_ids["workflow_node_executions"]) | set(live_node_ids))
-        pause_ids = sorted(set(archive_ids["workflow_pauses"]) | set(live_pause_ids))
-
-        def load_scope(
-            table_name: str,
-            model: Any,
-            scope_column: Any,
-            scope_ids: Sequence[str],
-        ) -> list[dict[str, Any]]:
-            return self._merge_records_by_id(
-                self._load_records_by_column(session, model, scope_column, scope_ids, lock=lock),
-                self._load_records_by_column(session, model, model.id, archive_ids[table_name], lock=lock),
-            )
-
-        return {
-            "workflow_pause_reasons": load_scope(
-                "workflow_pause_reasons", WorkflowPauseReason, WorkflowPauseReason.pause_id, pause_ids
-            ),
-            "workflow_node_execution_offload": load_scope(
-                "workflow_node_execution_offload",
-                WorkflowNodeExecutionOffload,
-                WorkflowNodeExecutionOffload.node_execution_id,
-                node_ids,
-            ),
-            "workflow_trigger_logs": load_scope(
-                "workflow_trigger_logs", WorkflowTriggerLog, WorkflowTriggerLog.workflow_run_id, run_ids
-            ),
-            "workflow_app_logs": load_scope(
-                "workflow_app_logs", WorkflowAppLog, WorkflowAppLog.workflow_run_id, run_ids
-            ),
-            "workflow_node_executions": load_scope(
-                "workflow_node_executions",
-                WorkflowNodeExecutionModel,
-                WorkflowNodeExecutionModel.workflow_run_id,
-                run_ids,
-            ),
-            "workflow_pauses": load_scope("workflow_pauses", WorkflowPause, WorkflowPause.workflow_run_id, run_ids),
-            "workflow_runs": self._load_records_by_column(
-                session,
-                WorkflowRun,
-                WorkflowRun.id,
-                sorted(set(run_ids) | set(archive_ids["workflow_runs"])),
-                lock=lock,
-            ),
-        }
-
-    @classmethod
-    def _validate_live_archive_subset(
-        cls,
-        manifest: BundleManifest,
-        table_records: dict[str, list[dict[str, Any]]],
-        live_records: dict[str, list[dict[str, Any]]],
-    ) -> None:
-        """Require every live row in the bundle scope to exist unchanged in the validated archive."""
-        manifest_run_ids = {str(run_id) for run_id in manifest["run_ids"]}
-        if len(manifest_run_ids) != len(manifest["run_ids"]):
-            raise ValueError("archive manifest contains duplicate workflow run IDs")
-
-        archive_records_by_id: dict[str, dict[str, dict[str, Any]]] = {}
-        for table_name in ARCHIVED_TABLES:
-            records_by_id = {str(record["id"]): record for record in table_records[table_name]}
-            if len(records_by_id) != len(table_records[table_name]):
-                raise ValueError(f"archive contains duplicate row IDs for {table_name}")
-            archive_records_by_id[table_name] = records_by_id
-
-        if set(archive_records_by_id["workflow_runs"]) != manifest_run_ids:
-            raise ValueError("archive workflow run IDs do not match manifest run_ids")
-
-        for table_name in ARCHIVED_TABLES:
-            live_ids = [str(record["id"]) for record in live_records[table_name]]
-            if len(set(live_ids)) != len(live_ids):
-                raise ValueError(f"live scope contains duplicate row IDs for {table_name}")
-
-            archive_by_id = archive_records_by_id[table_name]
-            extra_ids = sorted(set(live_ids) - set(archive_by_id))
-            if extra_ids:
-                raise ValueError(
-                    f"Live bundle scope contains rows missing from archive for {table_name}: {extra_ids[:10]}"
-                )
-
-            archive_subset = [archive_by_id[row_id] for row_id in live_ids]
-            live_checksum = cls._records_checksum(live_records[table_name])
-            archive_checksum = cls._records_checksum(archive_subset)
-            if live_checksum != archive_checksum:
-                raise ValueError(
-                    f"Live/archive subset content checksum mismatch for {table_name}: "
-                    f"expected={archive_checksum}, actual={live_checksum}"
-                )
-
     def _validate_live_counts(
         self,
         session: Session,
@@ -985,13 +617,26 @@ class WorkflowRunBundleArchiveMaintenance:
     def _delete_bundle_rows(
         self,
         session: Session,
-        live_records: dict[str, list[dict[str, Any]]],
+        table_records: dict[str, list[dict[str, Any]]],
     ) -> dict[str, int]:
+        run_ids = [str(record["id"]) for record in table_records["workflow_runs"]]
+        node_ids = [str(record["id"]) for record in table_records["workflow_node_executions"]]
+        pause_ids = [str(record["id"]) for record in table_records["workflow_pauses"]]
+
         deleted_counts = dict.fromkeys(ARCHIVED_TABLES, 0)
-        for table_name in DELETE_ORDER:
-            model = TABLE_MODELS[table_name]
-            row_ids = [str(record["id"]) for record in live_records[table_name]]
-            deleted_counts[table_name] = self._delete_by_column(session, model, model.id, row_ids)
+        deleted_counts["workflow_pause_reasons"] = self._delete_by_column(
+            session, WorkflowPauseReason, WorkflowPauseReason.pause_id, pause_ids
+        )
+        deleted_counts["workflow_node_execution_offload"] = self._delete_by_column(
+            session, WorkflowNodeExecutionOffload, WorkflowNodeExecutionOffload.node_execution_id, node_ids
+        )
+        deleted_counts["workflow_trigger_logs"] = self._delete_by_run_ids(session, WorkflowTriggerLog, run_ids)
+        deleted_counts["workflow_app_logs"] = self._delete_by_run_ids(session, WorkflowAppLog, run_ids)
+        deleted_counts["workflow_node_executions"] = self._delete_by_run_ids(
+            session, WorkflowNodeExecutionModel, run_ids
+        )
+        deleted_counts["workflow_pauses"] = self._delete_by_run_ids(session, WorkflowPause, run_ids)
+        deleted_counts["workflow_runs"] = self._delete_by_run_ids(session, WorkflowRun, run_ids)
         return deleted_counts
 
     def _restore_bundle_rows(
@@ -1063,6 +708,11 @@ class WorkflowRunBundleArchiveMaintenance:
         payload = json.dumps(normalized, sort_keys=True, default=str, ensure_ascii=False, separators=(",", ":"))
         return ArchiveStorage.compute_checksum(payload.encode("utf-8"))
 
+    @staticmethod
+    def _lock_workflow_runs(session: Session, run_ids: Sequence[str]) -> None:
+        for chunk in WorkflowRunBundleArchiveMaintenance._chunks(run_ids, _CHUNK_SIZE):
+            list(session.scalars(select(WorkflowRun.id).where(WorkflowRun.id.in_(chunk)).with_for_update()))
+
     @staticmethod
     def _select_ids_by_run_ids(
         session: Session,
@@ -1107,16 +757,8 @@ class WorkflowRunBundleArchiveMaintenance:
         session: Session,
         model: Any,
         run_ids: Sequence[str],
-        *,
-        lock: bool = False,
     ) -> list[dict[str, Any]]:
-        return self._load_records_by_column(
-            session,
-            model,
-            self._run_id_column(model),
-            run_ids,
-            lock=lock,
-        )
+        return self._load_records_by_column(session, model, self._run_id_column(model), run_ids)
 
     def _load_records_by_column(
         self,
@@ -1124,23 +766,23 @@ class WorkflowRunBundleArchiveMaintenance:
         model: Any,
         column: Any,
         values: Sequence[str],
-        *,
-        lock: bool = False,
     ) -> list[dict[str, Any]]:
         if not values:
             return []
         rows: list[Any] = []
         for chunk in self._chunks(values, _CHUNK_SIZE):
-            statement = select(model).where(column.in_(chunk)).order_by(model.id.asc())
-            if lock:
-                statement = statement.with_for_update()
-            rows.extend(session.scalars(statement))
+            rows.extend(session.scalars(select(model).where(column.in_(chunk))))
         return [self._row_to_dict(row) for row in rows]
 
     @staticmethod
-    def _merge_records_by_id(*record_groups: list[dict[str, Any]]) -> list[dict[str, Any]]:
-        records_by_id = {str(record["id"]): record for record_group in record_groups for record in record_group}
-        return [records_by_id[row_id] for row_id in sorted(records_by_id)]
+    def _delete_by_run_ids(
+        session: Session,
+        model: Any,
+        run_ids: Sequence[str],
+    ) -> int:
+        return WorkflowRunBundleArchiveMaintenance._delete_by_column(
+            session, model, WorkflowRunBundleArchiveMaintenance._run_id_column(model), run_ids
+        )
 
     @staticmethod
     def _run_id_column(model: Any) -> Any:
@@ -1171,10 +813,6 @@ class WorkflowRunBundleArchiveMaintenance:
     def _is_delete_started(storage: ArchiveStorage, object_prefix: str) -> bool:
         return storage.object_exists(f"{object_prefix}/{ARCHIVE_BUNDLE_DELETE_STARTED_MARKER_NAME}")
 
-    @staticmethod
-    def _is_restore_started(storage: ArchiveStorage, object_prefix: str) -> bool:
-        return storage.object_exists(f"{object_prefix}/{ARCHIVE_BUNDLE_RESTORE_STARTED_MARKER_NAME}")
-
     @staticmethod
     def _mark_deleted(storage: ArchiveStorage, object_prefix: str) -> None:
         WorkflowRunBundleArchiveMaintenance._put_marker(storage, object_prefix, ARCHIVE_BUNDLE_DELETED_MARKER_NAME)
@@ -1182,13 +820,10 @@ class WorkflowRunBundleArchiveMaintenance:
     @staticmethod
     def _mark_restored(storage: ArchiveStorage, object_prefix: str) -> None:
         WorkflowRunBundleArchiveMaintenance._delete_marker(storage, object_prefix, ARCHIVE_BUNDLE_DELETED_MARKER_NAME)
-        WorkflowRunBundleArchiveMaintenance._put_marker(storage, object_prefix, ARCHIVE_BUNDLE_RESTORED_MARKER_NAME)
-        WorkflowRunBundleArchiveMaintenance._delete_marker(
-            storage, object_prefix, ARCHIVE_BUNDLE_DELETE_STARTED_MARKER_NAME
-        )
         WorkflowRunBundleArchiveMaintenance._delete_marker(
             storage, object_prefix, ARCHIVE_BUNDLE_RESTORE_STARTED_MARKER_NAME
         )
+        WorkflowRunBundleArchiveMaintenance._put_marker(storage, object_prefix, ARCHIVE_BUNDLE_RESTORED_MARKER_NAME)
 
     @staticmethod
     def _put_marker(storage: ArchiveStorage, object_prefix: str, marker_name: str) -> None:
@@ -1201,6 +836,16 @@ class WorkflowRunBundleArchiveMaintenance:
         if storage.object_exists(marker_key):
             storage.delete_object(marker_key)
 
+    @staticmethod
+    def _parse_manifest_datetime(value: str) -> datetime.datetime:
+        return WorkflowRunBundleArchiveMaintenance._to_naive_utc(datetime.datetime.fromisoformat(value))
+
+    @staticmethod
+    def _to_naive_utc(value: datetime.datetime) -> datetime.datetime:
+        if value.tzinfo is None:
+            return value
+        return value.astimezone(datetime.UTC).replace(tzinfo=None)
+
     @staticmethod
     def _chunks(values: Sequence[Any], size: int) -> list[Sequence[Any]]:
         return [values[index : index + size] for index in range(0, len(values), size)]

api/services/step_by_step_tour_service.py

@@ -1,221 +0,0 @@
-"""Account-level Step-by-step Tour persistence."""
-
-from datetime import datetime
-from typing import NotRequired, TypedDict
-
-from sqlalchemy import select
-from sqlalchemy.exc import IntegrityError
-from sqlalchemy.orm import Session, scoped_session
-
-from configs import dify_config
-from libs.datetime_utils import ensure_naive_utc
-from models.account import Account
-from models.onboarding import AccountStepByStepTourState
-
-STEP_BY_STEP_TOUR_TASK_IDS = frozenset(("home", "studio", "knowledge", "integration"))
-
-
-class StepByStepTourStateResponse(TypedDict):
-    first_workspace_id: str | None
-    skipped: bool
-    completed_task_ids: list[str]
-    manually_enabled_workspace_ids: list[str]
-    manually_disabled_workspace_ids: list[str]
-    updated_at: datetime | None
-
-
-class StepByStepTourPatch(TypedDict):
-    action: str
-    task_id: NotRequired[str | None]
-
-
-class StepByStepTourService:
-    """Coordinate persisted tour state with account eligibility rules."""
-
-    @classmethod
-    def get_state(
-        cls,
-        *,
-        account: Account,
-        current_tenant_id: str,
-        session: Session | scoped_session,
-    ) -> StepByStepTourStateResponse:
-        eligible = cls.is_eligible(account)
-        state = cls._get_state(account.id, session=session)
-
-        if eligible:
-            state = cls._ensure_state(account.id, session=session, state=state)
-            if state.first_workspace_id is None:
-                state.first_workspace_id = current_tenant_id
-                session.commit()
-                session.refresh(state)
-
-        return cls._build_response(state=state)
-
-    @classmethod
-    def patch_state(
-        cls,
-        *,
-        account: Account,
-        current_tenant_id: str,
-        patch: StepByStepTourPatch,
-        session: Session | scoped_session,
-    ) -> StepByStepTourStateResponse:
-        state = cls._ensure_state(account.id, session=session, state=None)
-        cls._apply_action(
-            state=state,
-            action=patch["action"],
-            task_id=patch.get("task_id"),
-            current_tenant_id=current_tenant_id,
-        )
-
-        session.commit()
-        session.refresh(state)
-        return cls._build_response(state=state)
-
-    @classmethod
-    def is_eligible(cls, account: Account) -> bool:
-        if not dify_config.ENABLE_STEP_BY_STEP_TOUR:
-            return False
-
-        rollout_started_at = dify_config.STEP_BY_STEP_TOUR_ROLLOUT_STARTED_AT
-        if rollout_started_at is None:
-            return False
-
-        account_started_at = account.initialized_at or account.created_at
-        if account_started_at is None:
-            return False
-
-        return ensure_naive_utc(account_started_at) >= ensure_naive_utc(rollout_started_at)
-
-    @classmethod
-    def _get_state(
-        cls,
-        account_id: str,
-        *,
-        session: Session | scoped_session,
-    ) -> AccountStepByStepTourState | None:
-        stmt = select(AccountStepByStepTourState).where(AccountStepByStepTourState.account_id == account_id).limit(1)
-        return session.execute(stmt).scalar_one_or_none()
-
-    @classmethod
-    def _ensure_state(
-        cls,
-        account_id: str,
-        *,
-        session: Session | scoped_session,
-        state: AccountStepByStepTourState | None,
-    ) -> AccountStepByStepTourState:
-        if state is None:
-            state = cls._get_state(account_id, session=session)
-        if state is not None:
-            return state
-
-        state = AccountStepByStepTourState(account_id=account_id)
-        session.add(state)
-        try:
-            session.flush()
-        except IntegrityError:
-            # Another tab/device can create the account row between our read and insert.
-            session.rollback()
-            state = cls._get_state(account_id, session=session)
-            if state is None:
-                raise
-        return state
-
-    @classmethod
-    def _apply_action(
-        cls,
-        *,
-        state: AccountStepByStepTourState,
-        action: str,
-        task_id: str | None,
-        current_tenant_id: str,
-    ) -> None:
-        match action:
-            case "skip":
-                state.skipped = True
-                state.manually_enabled_workspace_ids = cls._remove_id(
-                    state.manually_enabled_workspace_ids,
-                    current_tenant_id,
-                )
-            case "complete_task":
-                if task_id is None:
-                    raise ValueError("task_id is required")
-                cls._validate_task_id(task_id)
-                state.completed_task_ids = cls._add_id(state.completed_task_ids, task_id)
-            case "uncomplete_task":
-                if task_id is None:
-                    raise ValueError("task_id is required")
-                cls._validate_task_id(task_id)
-                state.completed_task_ids = cls._remove_id(state.completed_task_ids, task_id)
-            case "enable_current_workspace":
-                state.skipped = False
-                state.manually_enabled_workspace_ids = cls._add_id(
-                    state.manually_enabled_workspace_ids,
-                    current_tenant_id,
-                )
-                state.manually_disabled_workspace_ids = cls._remove_id(
-                    state.manually_disabled_workspace_ids,
-                    current_tenant_id,
-                )
-            case "disable_current_workspace":
-                state.manually_enabled_workspace_ids = cls._remove_id(
-                    state.manually_enabled_workspace_ids,
-                    current_tenant_id,
-                )
-                state.manually_disabled_workspace_ids = cls._add_id(
-                    state.manually_disabled_workspace_ids,
-                    current_tenant_id,
-                )
-            case _:
-                raise ValueError(f"Unsupported action: {action}")
-
-    @classmethod
-    def _build_response(
-        cls,
-        *,
-        state: AccountStepByStepTourState | None,
-    ) -> StepByStepTourStateResponse:
-        if state is None:
-            return {
-                "first_workspace_id": None,
-                "skipped": False,
-                "completed_task_ids": [],
-                "manually_enabled_workspace_ids": [],
-                "manually_disabled_workspace_ids": [],
-                "updated_at": None,
-            }
-
-        return {
-            "first_workspace_id": state.first_workspace_id,
-            "skipped": state.skipped,
-            "completed_task_ids": cls._normalize_ids(state.completed_task_ids),
-            "manually_enabled_workspace_ids": cls._normalize_ids(state.manually_enabled_workspace_ids),
-            "manually_disabled_workspace_ids": cls._normalize_ids(state.manually_disabled_workspace_ids),
-            "updated_at": state.updated_at,
-        }
-
-    @staticmethod
-    def _validate_task_id(task_id: str) -> None:
-        if task_id not in STEP_BY_STEP_TOUR_TASK_IDS:
-            raise ValueError(f"Unsupported task_id: {task_id}")
-
-    @classmethod
-    def _add_id(cls, values: list[str], value: str) -> list[str]:
-        normalized = cls._normalize_ids(values)
-        if value in normalized:
-            return normalized
-        return [*normalized, value]
-
-    @classmethod
-    def _remove_id(cls, values: list[str], value: str) -> list[str]:
-        return [item for item in cls._normalize_ids(values) if item != value]
-
-    @staticmethod
-    def _normalize_ids(values: list[str]) -> list[str]:
-        normalized: list[str] = []
-        for value in values:
-            if value not in normalized:
-                normalized.append(value)
-        return normalized

api/services/workflow_collaboration_service.py

@@ -8,7 +8,6 @@ import uuid
 from collections.abc import Mapping
 from typing import Any, override
 
-from socketio.exceptions import TimeoutError as SocketIOTimeoutError  # type: ignore[reportMissingTypeStubs]
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 
@@ -19,7 +18,6 @@ from repositories.workflow_collaboration_repository import WorkflowCollaboration
 logger = logging.getLogger(__name__)
 
 SERVER_HEARTBEAT_INTERVAL_SECONDS = 30
-SYNC_REQUEST_TIMEOUT_SECONDS = 15
 _PROCESS_SERVER_ID: str | None = None
 _PROCESS_SERVER_ID_PID: int | None = None
 
@@ -40,8 +38,7 @@ class WorkflowCollaborationService:
 
     Socket.IO rooms are process-local unless backed by a message queue, while online users and leader election live in
     Redis. Each websocket worker writes a small heartbeat keyed by `server_id`; session rows store their owner so a
-    worker can distinguish a live remote sid from a stale sid left behind by a dead worker. Visibility events are
-    ordered per socket, and sync requests wait for the selected saver to acknowledge its draft write.
+    worker can distinguish a live remote sid from a stale sid left behind by a dead worker.
     """
 
     _heartbeat_started: bool
@@ -131,9 +128,6 @@ class WorkflowCollaborationService:
             "sid": sid,
             "connected_at": int(time.time()),
             "server_id": self.server_id,
-            # Joins are assumed visible; hidden tabs re-report via a graph_view_state
-            # event right after receiving the post-join "status" emit.
-            "graph_active": True,
         }
 
         self._repository.set_session_info(workflow_id, session_info)
@@ -164,8 +158,7 @@ class WorkflowCollaborationService:
         self.handle_leader_disconnect(workflow_id, sid)
         self.broadcast_online_users(workflow_id)
 
-    def relay_collaboration_event(self, sid: str, data: Mapping[str, object]) -> tuple[dict[str, object], int]:
-        """Route collaboration control events, directing save and graph-resync requests to the active leader."""
+    def relay_collaboration_event(self, sid: str, data: Mapping[str, object]) -> tuple[dict[str, str], int]:
         mapping = self._repository.get_sid_mapping(sid)
         if not mapping:
             return {"msg": "unauthorized"}, 401
@@ -181,54 +174,11 @@ class WorkflowCollaborationService:
         if not event_type:
             return {"msg": "invalid event type"}, 400
 
-        if event_type == "graph_view_state":
-            if not isinstance(event_data, Mapping):
-                return {"msg": "invalid graph_view_state"}, 400
-
-            graph_active = event_data.get("graphActive")
-            sequence = event_data.get("sequence")
-            if not isinstance(graph_active, bool):
-                return {"msg": "invalid graph_view_state"}, 400
-            if not isinstance(sequence, int) or isinstance(sequence, bool) or sequence < 0:
-                return {"msg": "invalid graph_view_state"}, 400
-
-            # Sequence the visibility write together with its leader side effect. Otherwise a newer
-            # visible event can land after the Lua write but before an older hidden handler demotes.
-            with self._repository.graph_view_state_lock(workflow_id):
-                applied = self._repository.update_session_graph_active(workflow_id, sid, graph_active, sequence)
-                if not applied:
-                    return {"msg": "graph_view_state_ignored"}, 200
-
-                # Write the flag before re-electing so tier-1 selection already excludes the
-                # session that just went hidden (including one _ensure_leader just promoted).
-                if not graph_active:
-                    self._demote_leader_if_hidden(workflow_id, sid)
-            return {"msg": "graph_view_state_updated"}, 200
-
         if event_type == "sync_request":
-            if not isinstance(event_data, Mapping):
-                return {"msg": "invalid sync_request"}, 400
-            request_id = event_data.get("requestId")
-            if not isinstance(request_id, str) or not request_id.strip():
-                return {"msg": "invalid sync_request"}, 400
-
             leader_sid = self._repository.get_current_leader(workflow_id)
             target_sid: str | None
             if leader_sid and self.is_session_active(workflow_id, leader_sid):
-                if self._is_session_graph_active(workflow_id, leader_sid):
-                    target_sid = leader_sid
-                else:
-                    # The leader is connected but its tab is hidden: its canvas is frozen
-                    # (rAF paused), so saving through it would persist stale data. Hand
-                    # leadership to a visible session — or, if every tab is hidden, to the
-                    # requester, whose canvas at least contains its own edits.
-                    replacement = self._select_graph_leader(workflow_id, preferred_sid=sid)
-                    if replacement and replacement != leader_sid:
-                        self._repository.set_leader(workflow_id, replacement)
-                        self.broadcast_leader_change(workflow_id, replacement)
-                        target_sid = replacement
-                    else:
-                        target_sid = leader_sid
+                target_sid = leader_sid
             else:
                 if leader_sid:
                     self._repository.delete_leader(workflow_id)
@@ -238,73 +188,15 @@ class WorkflowCollaborationService:
                     self.broadcast_leader_change(workflow_id, target_sid)
 
             if not target_sid:
-                return {"msg": "no_active_leader", "requestId": request_id}, 503
-
-            target_data = dict(event_data)
-            target_data["requestId"] = request_id
-            try:
-                result = self._socketio.call(
-                    "collaboration_update",
-                    {"type": event_type, "userId": user_id, "data": target_data, "timestamp": timestamp},
-                    to=target_sid,
-                    timeout=SYNC_REQUEST_TIMEOUT_SECONDS,
-                )
-            except SocketIOTimeoutError:
-                logger.warning(
-                    "Workflow collaboration sync request timed out: workflow_id=%s requester_sid=%s target_sid=%s",
-                    workflow_id,
-                    sid,
-                    target_sid,
-                )
-                return {"msg": "sync_request_timeout", "requestId": request_id}, 504
-
-            if not isinstance(result, Mapping) or result.get("success") is not True:
-                response: dict[str, object] = {
-                    "msg": "workflow_sync_failed",
-                    "requestId": request_id,
-                    "success": False,
-                }
-                if isinstance(result, Mapping) and isinstance(result.get("error"), str):
-                    response["error"] = result["error"]
-                return response, 502
-
-            workflow_hash = result.get("hash")
-            updated_at = result.get("updatedAt")
-            if not isinstance(workflow_hash, str) or not workflow_hash:
-                return {"msg": "invalid_sync_response", "requestId": request_id}, 502
-            if not isinstance(updated_at, int) or isinstance(updated_at, bool):
-                return {"msg": "invalid_sync_response", "requestId": request_id}, 502
-
-            return {
-                "msg": "workflow_synced",
-                "requestId": request_id,
-                "success": True,
-                "hash": workflow_hash,
-                "updatedAt": updated_at,
-            }, 200
-
-        if event_type == "graph_resync_request":
-            leader_sid = self._repository.get_current_leader(workflow_id)
-            resync_target_sid: str | None
-            if leader_sid and self.is_session_active(workflow_id, leader_sid):
-                resync_target_sid = leader_sid
-            else:
-                if leader_sid:
-                    self._repository.delete_leader(workflow_id)
-                resync_target_sid = self._select_graph_leader(workflow_id, preferred_sid=sid)
-                if resync_target_sid:
-                    self._repository.set_leader(workflow_id, resync_target_sid)
-                    self.broadcast_leader_change(workflow_id, resync_target_sid)
-
-            if not resync_target_sid:
-                return {"msg": "no_active_leader"}, 503
+                return {"msg": "no_active_leader"}, 200
 
             self._socketio.emit(
                 "collaboration_update",
                 {"type": event_type, "userId": user_id, "data": event_data, "timestamp": timestamp},
-                to=resync_target_sid,
+                room=target_sid,
             )
-            return {"msg": "graph_resync_request_forwarded"}, 200
+
+            return {"msg": "sync_request_forwarded"}, 200
 
         self._socketio.emit(
             "collaboration_update",
@@ -437,56 +329,17 @@ class WorkflowCollaborationService:
         self._repository.set_leader(workflow_id, sid)
         self.broadcast_leader_change(workflow_id, sid)
 
-    def _select_graph_leader(
-        self,
-        workflow_id: str,
-        preferred_sid: str | None = None,
-        *,
-        require_graph_active: bool = False,
-    ) -> str | None:
-        """Pick a leader, preferring sessions whose canvas tab is visible.
-
-        Hidden tabs freeze rAF-driven CRDT->canvas application, so a visible session is
-        always the freshest saver. When every tab is hidden the room must still keep a
-        leader (followers drop sync_requests unless they believe they are the leader),
-        so tier 2 falls back to any active session unless require_graph_active is set.
-        """
-        active_sessions = [
-            session
+    def _select_graph_leader(self, workflow_id: str, preferred_sid: str | None = None) -> str | None:
+        session_sids = [
+            session["sid"]
             for session in self._repository.list_sessions(workflow_id)
-            if self.is_session_active(workflow_id, session["sid"])
+            if session.get("graph_active", True) and self.is_session_active(workflow_id, session["sid"])
         ]
-        visible_sids = [session["sid"] for session in active_sessions if session.get("graph_active", True)]
-
-        candidate_sids = visible_sids
-        if not candidate_sids and not require_graph_active:
-            candidate_sids = [session["sid"] for session in active_sessions]
-
-        if not candidate_sids:
+        if not session_sids:
             return None
-        if preferred_sid and preferred_sid in candidate_sids:
+        if preferred_sid and preferred_sid in session_sids:
             return preferred_sid
-        return candidate_sids[0]
-
-    def _is_session_graph_active(self, workflow_id: str, sid: str) -> bool:
-        """Default to True on missing/unreadable session data so read failures never churn leadership."""
-        session_info = self._repository.get_session_info(workflow_id, sid)
-        if session_info is None:
-            return True
-        return bool(session_info.get("graph_active", True))
-
-    def _demote_leader_if_hidden(self, workflow_id: str, hidden_sid: str) -> None:
-        current_leader = self._repository.get_current_leader(workflow_id)
-        if current_leader != hidden_sid:
-            return
-
-        new_leader = self._select_graph_leader(workflow_id, require_graph_active=True)
-        # No visible session: keep the hidden leader rather than leaving the room leaderless.
-        if not new_leader or new_leader == hidden_sid:
-            return
-
-        self._repository.set_leader(workflow_id, new_leader)
-        self.broadcast_leader_change(workflow_id, new_leader)
+        return session_sids[0]
 
     def is_session_active(self, workflow_id: str, sid: str) -> bool:
         if not sid:

api/services/workflow_draft_variable_service.py

@@ -823,8 +823,6 @@ _FILENAME_TRANS_TABLE = _make_filename_trans_table()
 
 
 class DraftVariableSaver:
-    """Persist draft outputs under the tenant that owns the app or pipeline."""
-
     # _DUMMY_OUTPUT_IDENTITY is a placeholder output for workflow nodes.
     # Its sole possible value is `None`.
     #
@@ -844,10 +842,6 @@ class DraftVariableSaver:
     # Database session used for persisting draft variables.
     _session: Session
 
-    # Resource owner tenant. An account's current tenant may be unset or point elsewhere
-    # when draft variables are persisted by an asynchronous workflow execution.
-    _tenant_id: str
-
     # The application ID associated with the draft variables.
     # This should match the `Workflow.app_id` of the workflow to which the current node belongs.
     _app_id: str
@@ -873,7 +867,6 @@ class DraftVariableSaver:
     def __init__(
         self,
         session: Session,
-        tenant_id: str,
         app_id: str,
         node_id: str,
         node_type: NodeType,
@@ -885,7 +878,6 @@ class DraftVariableSaver:
         # WorkflowNodeExecutionModel/WorkflowNodeExecution, not their `node_execution_id`
         # field. These are distinct database fields with different purposes.
         self._session = session
-        self._tenant_id = tenant_id
         self._app_id = app_id
         self._node_id = node_id
         self._node_type = node_type
@@ -893,6 +885,12 @@ class DraftVariableSaver:
         self._user = user
         self._enclosing_node_id = enclosing_node_id
 
+    def _resolve_app_tenant_id(self) -> str:
+        tenant_id = self._session.scalar(select(App.tenant_id).where(App.id == self._app_id))
+        if not tenant_id:
+            raise ValueError(f"Unable to resolve tenant_id for app {self._app_id}")
+        return tenant_id
+
     def _create_dummy_output_variable(self):
         return WorkflowDraftVariable.new_node_variable(
             app_id=self._app_id,
@@ -951,10 +949,11 @@ class DraftVariableSaver:
                 if name == SystemVariableKey.FILES:
                     # Here we know the type of variable must be `array[file]`, we
                     # just rebuild files from the serialized payload.
+                    tenant_id = self._resolve_app_tenant_id()
                     files = [
                         build_file_from_stored_mapping(
                             file_mapping=v,
-                            tenant_id=self._tenant_id,
+                            tenant_id=tenant_id,
                         )
                         for v in value
                     ]
@@ -1097,8 +1096,8 @@ class DraftVariableSaver:
             content=original_content_serialized.encode(),
             mimetype=content_type,
             user=self._user,
-            tenant_id=self._tenant_id,
         )
+        assert self._user.current_tenant_id
         # Create WorkflowDraftVariableFile record
         variable_file = WorkflowDraftVariableFile(
             upload_file_id=upload_file.id,
@@ -1106,7 +1105,7 @@ class DraftVariableSaver:
             length=original_length,
             value_type=value_seg.value_type,
             app_id=self._app_id,
-            tenant_id=self._tenant_id,
+            tenant_id=self._user.current_tenant_id,
             user_id=self._user.id,
         )
         variable_file.id = str(uuidv7())

api/services/workflow_event_snapshot_service.py

@@ -13,7 +13,6 @@ from sqlalchemy import desc, select
 from sqlalchemy.orm import Session, sessionmaker
 
 from core.app.apps.message_generator import MessageGenerator
-from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity
 from core.app.entities.task_entities import (
     HumanInputRequiredResponse,
     MessageReplaceStreamResponse,
@@ -85,6 +84,9 @@ def build_workflow_event_stream(
     topic = MessageGenerator.get_response_topic(app_mode, workflow_run.id)
     workflow_run_repo = DifyAPIRepositoryFactory.create_api_workflow_run_repository(session_maker)
     node_execution_repo = DifyAPIRepositoryFactory.create_api_workflow_node_execution_repository(session_maker)
+    message_context = (
+        _get_message_context(session_maker, workflow_run.id) if app_mode == AppMode.ADVANCED_CHAT else None
+    )
 
     pause_entity: WorkflowPauseEntity | None = None
     if workflow_run.status == WorkflowExecutionStatus.PAUSED:
@@ -95,38 +97,6 @@ def build_workflow_event_stream(
             pause_entity = None
 
     resumption_context = _load_resumption_context(pause_entity)
-    message_context: MessageContext | None = None
-    if app_mode == AppMode.ADVANCED_CHAT:
-        if workflow_run.status == WorkflowExecutionStatus.PAUSED:
-            if resumption_context is None:
-                raise AssertionError(
-                    "WorkflowResumptionContext is required for advanced-chat snapshot replay, "
-                    f"workflow_run_id={workflow_run.id}"
-                )
-            generate_entity = resumption_context.get_generate_entity()
-            if not isinstance(generate_entity, AdvancedChatAppGenerateEntity):
-                raise AssertionError(
-                    "AdvancedChatAppGenerateEntity is required for advanced-chat snapshot replay, "
-                    f"workflow_run_id={workflow_run.id}, generate_entity_type={type(generate_entity).__name__}"
-                )
-            if not generate_entity.conversation_id:
-                raise AssertionError(
-                    f"conversation_id is required for advanced-chat snapshot replay, workflow_run_id={workflow_run.id}"
-                )
-            message_context = _get_message_context_by_conversation(
-                session_maker,
-                conversation_id=generate_entity.conversation_id,
-                workflow_run_id=workflow_run.id,
-            )
-        else:
-            # Compatibility fallback for non-suspended snapshot requests. This app-scoped lookup is not optimal;
-            # a dedicated index or stronger lookup key would be preferable.
-            message_context = _get_message_context_by_app(
-                session_maker,
-                app_id=app_id,
-                workflow_run_id=workflow_run.id,
-            )
-
     node_snapshots = node_execution_repo.get_execution_snapshots_by_workflow_run(
         tenant_id=tenant_id,
         app_id=app_id,
@@ -205,68 +175,19 @@ def build_workflow_event_stream(
     return _generate()
 
 
-def _get_message_context_by_conversation(
-    session_maker: sessionmaker[Session],
-    *,
-    conversation_id: str,
-    workflow_run_id: str,
-) -> MessageContext | None:
-    """Look up a paused or suspended Advanced Chat snapshot message by conversation and workflow run.
-
-    Use this exact lookup after recovering ``conversation_id`` from persisted resumption context. Its predicates match
-    ``message_workflow_run_id_idx``.
-    """
+def _get_message_context(session_maker: sessionmaker[Session], workflow_run_id: str) -> MessageContext | None:
     with session_maker() as session:
-        stmt = (
-            select(Message)
-            .where(
-                Message.conversation_id == conversation_id,
-                Message.workflow_run_id == workflow_run_id,
-            )
-            .order_by(desc(Message.created_at))
-            .limit(1)
-        )
+        stmt = select(Message).where(Message.workflow_run_id == workflow_run_id).order_by(desc(Message.created_at))
         message = session.scalar(stmt)
         if message is None:
             return None
-        return _to_message_context(message)
-
-
-def _get_message_context_by_app(
-    session_maker: sessionmaker[Session],
-    *,
-    app_id: str,
-    workflow_run_id: str,
-) -> MessageContext | None:
-    """Look up a non-suspended or running Advanced Chat reconnect snapshot by app and workflow run.
-
-    This compatibility path applies only when no resumption context is expected. The app-scoped query is not optimal;
-    a dedicated index or stronger lookup key would be preferable.
-    """
-    with session_maker() as session:
-        stmt = (
-            select(Message)
-            .where(
-                Message.app_id == app_id,
-                Message.workflow_run_id == workflow_run_id,
-            )
-            .order_by(desc(Message.created_at))
-            .limit(1)
+        created_at = int(message.created_at.timestamp()) if message.created_at else 0
+        return MessageContext(
+            conversation_id=message.conversation_id,
+            message_id=message.id,
+            created_at=created_at,
+            answer=message.answer,
         )
-        message = session.scalar(stmt)
-        if message is None:
-            return None
-        return _to_message_context(message)
-
-
-def _to_message_context(message: Message) -> MessageContext:
-    created_at = int(message.created_at.timestamp()) if message.created_at else 0
-    return MessageContext(
-        conversation_id=message.conversation_id,
-        message_id=message.id,
-        created_at=created_at,
-        answer=message.answer,
-    )
 
 
 def _load_resumption_context(pause_entity: WorkflowPauseEntity | None) -> WorkflowResumptionContext | None:

api/services/workflow_service.py

@@ -322,7 +322,6 @@ class WorkflowService:
         session: Session,
         commit: bool = True,
         sync_agent_bindings: bool = True,
-        graph_only: bool = False,
     ) -> Workflow:
         """
         Sync draft workflow.
@@ -339,10 +338,8 @@ class WorkflowService:
         if workflow and workflow.unique_hash != unique_hash:
             raise WorkflowHashNotEqualError()
 
-        # Collaboration persists features and variables through dedicated endpoints. A graph save
-        # must not overwrite those newer database values with another collaborator's stale cache.
-        if not graph_only or not workflow:
-            self.validate_features_structure(app_model=app_model, features=features)
+        # validate features structure
+        self.validate_features_structure(app_model=app_model, features=features)
 
         # validate graph structure
         self.validate_graph_structure(graph=graph)
@@ -364,12 +361,11 @@ class WorkflowService:
         # update draft workflow if found
         else:
             workflow.graph = json.dumps(graph)
+            workflow.features = json.dumps(features)
             workflow.updated_by = account.id
             workflow.updated_at = naive_utc_now()
-            if not graph_only:
-                workflow.features = json.dumps(features)
-                workflow.environment_variables = environment_variables
-                workflow.conversation_variables = conversation_variables
+            workflow.environment_variables = environment_variables
+            workflow.conversation_variables = conversation_variables
 
         from services.agent.workflow_publish_service import WorkflowAgentPublishService
 
@@ -1060,7 +1056,6 @@ class WorkflowService:
         with sessionmaker(bind=db.engine).begin() as session:
             draft_var_saver = DraftVariableSaver(
                 session=session,
-                tenant_id=app_model.tenant_id,
                 app_id=app_model.id,
                 node_id=workflow_node_execution.node_id,
                 node_type=workflow_node_execution.node_type,
@@ -1211,7 +1206,6 @@ class WorkflowService:
         with sessionmaker(bind=db.engine).begin() as session:
             draft_var_saver = DraftVariableSaver(
                 session=session,
-                tenant_id=app_model.tenant_id,
                 app_id=app_model.id,
                 node_id=node_id,
                 node_type=BuiltinNodeTypes.HUMAN_INPUT,

api/tasks/agent_backend_session_cleanup_task.py

@@ -24,9 +24,6 @@ def _create_agent_backend_client():
         base_url=dify_config.AGENT_BACKEND_BASE_URL,
         use_fake=dify_config.AGENT_BACKEND_USE_FAKE,
         fake_scenario=dify_config.AGENT_BACKEND_FAKE_SCENARIO,
-        stream_read_timeout_seconds=dify_config.AGENT_BACKEND_STREAM_READ_TIMEOUT_SECONDS,
-        stream_max_reconnects=dify_config.AGENT_BACKEND_STREAM_MAX_RECONNECTS,
-        stream_run_timeout_seconds=dify_config.AGENT_BACKEND_RUN_TIMEOUT_SECONDS,
     )
 
 

api/tests/integration_tests/.env.example

@@ -1,6 +1,5 @@
 FLASK_APP=app.py
 FLASK_DEBUG=0
-ENABLE_COLLABORATION_MODE=false
 SECRET_KEY='uhySf6a3aZuvRNfAlcr47paOw9TRYBY6j8ZHXpVw1yx5RP27Yj3w2uvI'
 
 CONSOLE_API_URL=http://127.0.0.1:5001

api/tests/integration_tests/services/retention/test_workflow_run_archiver.py

@@ -513,94 +513,11 @@ class TestArchiveRunIdempotency:
         storage = MagicMock()
         storage.object_exists.return_value = True
 
-        with patch.object(archiver, "_sync_existing_bundle_index") as sync_existing_bundle_index:
-            result = archiver._archive_bundle(MagicMock(), storage, [run])
+        result = archiver._archive_bundle(MagicMock(), storage, [run])
 
         assert result.success is True
         assert result.skipped is True
         assert result.error == "bundle already archived"
-        sync_existing_bundle_index.assert_called_once()
-
-    def test_existing_bundle_catalog_publication_failure_is_not_success(self):
-        archiver = WorkflowRunArchiver(days=90)
-        run = _run()
-        session = MagicMock()
-        storage = MagicMock()
-        storage.object_exists.return_value = True
-
-        with patch.object(archiver, "_sync_existing_bundle_index", side_effect=RuntimeError("catalog unavailable")):
-            result = archiver._archive_bundle(session, storage, [run])
-
-        assert result.success is False
-        assert result.error == "catalog unavailable"
-        session.rollback.assert_called_once()
-
-    def test_retry_repairs_index_after_catalog_commit_then_index_write_failure(self):
-        archiver = WorkflowRunArchiver(days=90)
-        run = _run()
-        identity = archiver._build_bundle_identity([run])
-        index_key = archiver._get_index_object_key(identity)
-        manifest_key = archiver._get_manifest_object_key(identity)
-        storage = FakeArchiveStorage()
-        original_put_object = storage.put_object
-        index_write_count = 0
-
-        def put_object(key: str, data: bytes) -> str:
-            nonlocal index_write_count
-            if key == index_key:
-                index_write_count += 1
-                if index_write_count == 2:
-                    raise RuntimeError("index write failed")
-            return original_put_object(key, data)
-
-        storage.put_object = MagicMock(side_effect=put_object)
-        first_session = MagicMock()
-        first_session.scalar.return_value = None
-        table_data = {"workflow_runs": [{"id": run.id, "tenant_id": run.tenant_id}]}
-
-        with (
-            patch.object(archiver, "_lock_runs_for_archive", return_value=[run]),
-            patch.object(archiver, "_extract_bundle_data", return_value=table_data),
-        ):
-            first_result = archiver._archive_bundle(first_session, storage, [run])
-
-        assert first_result.success is False
-        assert first_result.error == "index write failed"
-        assert manifest_key in storage.objects
-        assert json.loads(storage.objects[index_key])["run_ids"] == []
-
-        storage.list_objects = MagicMock(wraps=storage.list_objects)
-        retry_session = MagicMock()
-        retry_session.scalar.return_value = None
-
-        retry_result = archiver._archive_bundle(retry_session, storage, [run])
-
-        assert retry_result.success is True
-        assert retry_result.skipped is True
-        assert json.loads(storage.objects[index_key])["manifest_keys"] == [manifest_key]
-        assert json.loads(storage.objects[index_key])["run_ids"] == [run.id]
-        storage.list_objects.assert_not_called()
-
-    def test_existing_manifest_with_missing_index_fails_without_partial_rebuild(self):
-        archiver = WorkflowRunArchiver(days=90)
-        run = _run()
-        identity = archiver._build_bundle_identity([run])
-        _, _, manifest_data = archiver._build_archive_payload(
-            identity,
-            [run],
-            {"workflow_runs": [{"id": run.id, "tenant_id": run.tenant_id}]},
-        )
-        manifest_key = archiver._get_manifest_object_key(identity)
-        index_key = archiver._get_index_object_key(identity)
-        storage = FakeArchiveStorage({manifest_key: manifest_data})
-        storage.list_objects = MagicMock(wraps=storage.list_objects)
-
-        result = archiver._archive_bundle(MagicMock(), storage, [run])
-
-        assert result.success is False
-        assert "archive shard index missing" in (result.error or "")
-        assert index_key not in storage.objects
-        storage.list_objects.assert_not_called()
 
     def test_successful_bundle_persists_archive_index(self):
         archiver = WorkflowRunArchiver(days=90)
@@ -633,28 +550,6 @@ class TestArchiveRunIdempotency:
         assert archived_bundle.row_count == 2
         session.commit.assert_called_once()
 
-    def test_new_bundle_catalog_commit_failure_is_not_success(self):
-        archiver = WorkflowRunArchiver(days=90)
-        run = _run(str(uuid.uuid4()))
-        run.tenant_id = str(uuid.uuid4())
-        session = MagicMock()
-        session.scalar.return_value = None
-        session.commit.side_effect = RuntimeError("catalog commit failed")
-        storage = MagicMock()
-        storage.object_exists.return_value = False
-        storage.list_objects.return_value = []
-        table_data = {"workflow_runs": [{"id": run.id, "tenant_id": run.tenant_id}]}
-
-        with (
-            patch.object(archiver, "_lock_runs_for_archive", return_value=[run]),
-            patch.object(archiver, "_extract_bundle_data", return_value=table_data),
-        ):
-            result = archiver._archive_bundle(session, storage, [run])
-
-        assert result.success is False
-        assert result.error == "catalog commit failed"
-        session.rollback.assert_called_once()
-
     def test_index_skips_all_already_archived_runs(self):
         archiver = WorkflowRunArchiver(days=90)
         run = MagicMock()

api/tests/integration_tests/services/test_workflow_draft_variable_service.py

@@ -311,7 +311,6 @@ class TestDraftVariableLoader(unittest.TestCase):
                 # Use DraftVariableSaver to create offloaded variable (this mimics production)
                 saver = DraftVariableSaver(
                     session=session,
-                    tenant_id=self._test_tenant_id,
                     app_id=self._test_app_id,
                     node_id="test_offload_node",
                     node_type=BuiltinNodeTypes.LLM,  # Use a real node type

api/tests/test_containers_integration_tests/controllers/console/app/test_app_import_api.py

@@ -0,0 +1,179 @@
+"""Testcontainers integration tests for controllers.console.app.app_import endpoints."""
+
+from __future__ import annotations
+
+from inspect import unwrap
+from types import SimpleNamespace
+from unittest.mock import MagicMock
+
+import pytest
+from flask import Flask
+
+from controllers.console.app import app_import as app_import_module
+from services.app_dsl_service import ImportStatus
+
+
+class _Result:
+    def __init__(self, status: ImportStatus, app_id: str | None = "app-1"):
+        self.status = status
+        self.app_id = app_id
+
+    def model_dump(self, mode: str = "json"):
+        return {"status": self.status, "app_id": self.app_id}
+
+
+def _install_features(monkeypatch: pytest.MonkeyPatch, enabled: bool) -> None:
+    features = SimpleNamespace(webapp_auth=SimpleNamespace(enabled=enabled))
+    monkeypatch.setattr(app_import_module.FeatureService, "get_system_features", lambda: features)
+
+
+class TestAppImportApi:
+    @pytest.fixture
+    def app(self, flask_app_with_containers: Flask):
+        return flask_app_with_containers
+
+    def test_import_post_returns_failed_status(self, app: Flask, monkeypatch: pytest.MonkeyPatch) -> None:
+        api = app_import_module.AppImportApi()
+        method = unwrap(api.post)
+
+        _install_features(monkeypatch, enabled=False)
+        monkeypatch.setattr(
+            app_import_module.AppDslService,
+            "import_app",
+            lambda *_args, **_kwargs: _Result(ImportStatus.FAILED, app_id=None),
+        )
+
+        with app.test_request_context("/console/api/apps/imports", method="POST", json={"mode": "yaml-content"}):
+            response, status = method(api, SimpleNamespace(id="u1"))
+
+        assert status == 400
+        assert response["status"] == ImportStatus.FAILED
+
+    def test_import_post_returns_pending_status(self, app: Flask, monkeypatch: pytest.MonkeyPatch) -> None:
+        api = app_import_module.AppImportApi()
+        method = unwrap(api.post)
+
+        _install_features(monkeypatch, enabled=False)
+        monkeypatch.setattr(
+            app_import_module.AppDslService,
+            "import_app",
+            lambda *_args, **_kwargs: _Result(ImportStatus.PENDING),
+        )
+
+        with app.test_request_context("/console/api/apps/imports", method="POST", json={"mode": "yaml-content"}):
+            response, status = method(api, SimpleNamespace(id="u1"))
+
+        assert status == 202
+        assert response["status"] == ImportStatus.PENDING
+
+    def test_import_post_updates_webapp_auth_when_enabled(self, app: Flask, monkeypatch: pytest.MonkeyPatch) -> None:
+        api = app_import_module.AppImportApi()
+        method = unwrap(api.post)
+
+        _install_features(monkeypatch, enabled=True)
+        monkeypatch.setattr(
+            app_import_module.AppDslService,
+            "import_app",
+            lambda *_args, **_kwargs: _Result(ImportStatus.COMPLETED, app_id="app-123"),
+        )
+        update_access = MagicMock()
+        monkeypatch.setattr(app_import_module.EnterpriseService.WebAppAuth, "update_app_access_mode", update_access)
+
+        with app.test_request_context("/console/api/apps/imports", method="POST", json={"mode": "yaml-content"}):
+            response, status = method(api, SimpleNamespace(id="u1"))
+
+        update_access.assert_called_once_with("app-123", "private")
+        assert status == 200
+        assert response["status"] == ImportStatus.COMPLETED
+
+    def test_import_post_commits_session_on_success(self, app: Flask, monkeypatch: pytest.MonkeyPatch) -> None:
+        api = app_import_module.AppImportApi()
+        method = unwrap(api.post)
+
+        _install_features(monkeypatch, enabled=False)
+        monkeypatch.setattr(
+            app_import_module.AppDslService,
+            "import_app",
+            lambda *_args, **_kwargs: _Result(ImportStatus.COMPLETED, app_id="app-123"),
+        )
+
+        fake_session = MagicMock()
+        fake_session.__enter__.return_value = fake_session
+        fake_session.__exit__.return_value = None
+        monkeypatch.setattr(app_import_module, "Session", lambda *_args, **_kwargs: fake_session)
+
+        with app.test_request_context("/console/api/apps/imports", method="POST", json={"mode": "yaml-content"}):
+            response, status = method(api, SimpleNamespace(id="u1"))
+
+        fake_session.commit.assert_called_once_with()
+        fake_session.rollback.assert_not_called()
+        assert status == 200
+        assert response["status"] == ImportStatus.COMPLETED
+
+    def test_import_post_rolls_back_session_on_failure(self, app: Flask, monkeypatch: pytest.MonkeyPatch) -> None:
+        api = app_import_module.AppImportApi()
+        method = unwrap(api.post)
+
+        _install_features(monkeypatch, enabled=False)
+        monkeypatch.setattr(
+            app_import_module.AppDslService,
+            "import_app",
+            lambda *_args, **_kwargs: _Result(ImportStatus.FAILED, app_id=None),
+        )
+
+        fake_session = MagicMock()
+        fake_session.__enter__.return_value = fake_session
+        fake_session.__exit__.return_value = None
+        monkeypatch.setattr(app_import_module, "Session", lambda *_args, **_kwargs: fake_session)
+
+        with app.test_request_context("/console/api/apps/imports", method="POST", json={"mode": "yaml-content"}):
+            response, status = method(api, SimpleNamespace(id="u1"))
+
+        fake_session.rollback.assert_called_once_with()
+        fake_session.commit.assert_not_called()
+        assert status == 400
+        assert response["status"] == ImportStatus.FAILED
+
+
+class TestAppImportConfirmApi:
+    @pytest.fixture
+    def app(self, flask_app_with_containers: Flask):
+        return flask_app_with_containers
+
+    def test_import_confirm_returns_failed_status(self, app: Flask, monkeypatch: pytest.MonkeyPatch) -> None:
+        api = app_import_module.AppImportConfirmApi()
+        method = unwrap(api.post)
+
+        monkeypatch.setattr(
+            app_import_module.AppDslService,
+            "confirm_import",
+            lambda *_args, **_kwargs: _Result(ImportStatus.FAILED),
+        )
+
+        with app.test_request_context("/console/api/apps/imports/import-1/confirm", method="POST"):
+            response, status = method(api, SimpleNamespace(id="u1"), import_id="import-1")
+
+        assert status == 400
+        assert response["status"] == ImportStatus.FAILED
+
+
+class TestAppImportCheckDependenciesApi:
+    @pytest.fixture
+    def app(self, flask_app_with_containers: Flask):
+        return flask_app_with_containers
+
+    def test_import_check_dependencies_returns_result(self, app: Flask, monkeypatch: pytest.MonkeyPatch) -> None:
+        api = app_import_module.AppImportCheckDependenciesApi()
+        method = unwrap(api.get)
+
+        monkeypatch.setattr(
+            app_import_module.AppDslService,
+            "check_dependencies",
+            lambda *_args, **_kwargs: SimpleNamespace(model_dump=lambda mode="json": {"leaked_dependencies": []}),
+        )
+
+        with app.test_request_context("/console/api/apps/imports/app-1/check-dependencies", method="GET"):
+            response, status = method(api, app_model=SimpleNamespace(id="app-1"))
+
+        assert status == 200
+        assert response["leaked_dependencies"] == []

api/tests/test_containers_integration_tests/services/test_api_token_service.py

@@ -1,38 +1,22 @@
-"""Unit tests for API token caching and SQLite-backed token lookup."""
-
 from __future__ import annotations
 
-from collections.abc import Iterator
 from datetime import datetime
 from unittest.mock import MagicMock, patch
 from uuid import uuid4
 
 import pytest
 from flask import Flask
-from sqlalchemy.orm import Session
 from werkzeug.exceptions import Unauthorized
 
 import services.api_token_service as api_token_service_module
-from models.engine import db
 from models.model import ApiToken
 from services.api_token_service import ApiTokenCache, CachedApiToken
 
 
-@pytest.fixture
-def api_token_db() -> Iterator[Session]:
-    """Provide the production database extension with an isolated SQLite token table."""
-    app = Flask(__name__)
-    app.config["SQLALCHEMY_DATABASE_URI"] = "sqlite:///:memory:"
-    db.init_app(app)
-
-    with app.app_context():
-        ApiToken.__table__.create(db.engine)
-        with Session(db.engine, expire_on_commit=False) as session:
-            yield session
-
-
 class TestQueryTokenFromDb:
-    def test_should_return_api_token_and_cache_when_token_exists(self, api_token_db: Session) -> None:
+    def test_should_return_api_token_and_cache_when_token_exists(
+        self, flask_app_with_containers: Flask, db_session_with_containers
+    ):
         tenant_id = str(uuid4())
         app_id = str(uuid4())
         token_value = f"app-test-{uuid4()}"
@@ -43,8 +27,8 @@ class TestQueryTokenFromDb:
         api_token.tenant_id = tenant_id
         api_token.type = "app"
         api_token.token = token_value
-        api_token_db.add(api_token)
-        api_token_db.commit()
+        db_session_with_containers.add(api_token)
+        db_session_with_containers.commit()
 
         with (
             patch.object(api_token_service_module.ApiTokenCache, "set") as mock_cache_set,
@@ -57,7 +41,9 @@ class TestQueryTokenFromDb:
         mock_cache_set.assert_called_once()
         mock_record_usage.assert_called_once_with(token_value, "app")
 
-    def test_should_cache_null_and_raise_unauthorized_when_token_not_found(self, api_token_db: Session) -> None:
+    def test_should_cache_null_and_raise_unauthorized_when_token_not_found(
+        self, flask_app_with_containers: Flask, db_session_with_containers
+    ):
         with (
             patch.object(api_token_service_module.ApiTokenCache, "set") as mock_cache_set,
             patch.object(api_token_service_module, "record_token_usage") as mock_record_usage,

api/tests/test_containers_integration_tests/services/test_human_input_delivery_test_service.py

@@ -1,7 +1,6 @@
-"""Unit tests for human-input test delivery with SQLite-backed member lookup."""
-
 from __future__ import annotations
 
+from types import SimpleNamespace
 from unittest.mock import MagicMock, patch
 from uuid import uuid4
 
@@ -20,9 +19,7 @@ from core.workflow.human_input_adapter import (
 )
 from graphon.runtime import VariablePool
 from models.account import Account, TenantAccountJoin
-from models.engine import db
 from services import human_input_delivery_test_service as service_module
-from services.feature_service import FeatureModel
 from services.human_input_delivery_test_service import (
     DeliveryTestContext,
     DeliveryTestEmailRecipient,
@@ -93,14 +90,8 @@ class TestDeliveryTestRegistry:
         with pytest.raises(DeliveryTestUnsupportedError, match="Delivery method does not support test send."):
             registry.dispatch(context=context, method=method)
 
-    def test_default(self) -> None:
-        app = Flask(__name__)
-        app.config["SQLALCHEMY_DATABASE_URI"] = "sqlite:///:memory:"
-        db.init_app(app)
-
-        with app.app_context():
-            registry = DeliveryTestRegistry.default()
-
+    def test_default(self, flask_app_with_containers: Flask, db_session_with_containers: Session):
+        registry = DeliveryTestRegistry.default()
         assert len(registry._handlers) == 1
         assert isinstance(registry._handlers[0], EmailDeliveryTestHandler)
 
@@ -121,24 +112,24 @@ class TestEmailDeliveryTestHandler:
         handler = EmailDeliveryTestHandler(session_factory=engine)
         assert handler._session_factory.kw["bind"] == engine
 
-    def test_supports(self, sqlite_engine: Engine) -> None:
-        handler = EmailDeliveryTestHandler(session_factory=sqlite_engine)
+    def test_supports(self):
+        handler = EmailDeliveryTestHandler(session_factory=MagicMock())
         method = EmailDeliveryMethod(config=_make_valid_email_config())
         assert handler.supports(method) is True
         assert handler.supports(MagicMock()) is False
 
-    def test_send_test_unsupported_method(self, sqlite_engine: Engine) -> None:
-        handler = EmailDeliveryTestHandler(session_factory=sqlite_engine)
+    def test_send_test_unsupported_method(self):
+        handler = EmailDeliveryTestHandler(session_factory=MagicMock())
         with pytest.raises(DeliveryTestUnsupportedError):
             handler.send_test(context=MagicMock(), method=MagicMock())
 
-    def test_send_test_feature_disabled(self, monkeypatch: pytest.MonkeyPatch, sqlite_engine: Engine) -> None:
+    def test_send_test_feature_disabled(self, monkeypatch: pytest.MonkeyPatch):
         monkeypatch.setattr(
             service_module.FeatureService,
             "get_features",
-            lambda _tenant_id, **_kwargs: FeatureModel(human_input_email_delivery_enabled=False),
+            lambda _tenant_id, **_kwargs: SimpleNamespace(human_input_email_delivery_enabled=False),
         )
-        handler = EmailDeliveryTestHandler(session_factory=sqlite_engine)
+        handler = EmailDeliveryTestHandler(session_factory=MagicMock())
         context = DeliveryTestContext(
             tenant_id="t1", app_id="a1", node_id="n1", node_title="title", rendered_content="content"
         )
@@ -147,15 +138,15 @@ class TestEmailDeliveryTestHandler:
         with pytest.raises(DeliveryTestError, match="Email delivery is not available"):
             handler.send_test(context=context, method=method)
 
-    def test_send_test_mail_not_inited(self, monkeypatch: pytest.MonkeyPatch, sqlite_engine: Engine) -> None:
+    def test_send_test_mail_not_inited(self, monkeypatch: pytest.MonkeyPatch):
         monkeypatch.setattr(
             service_module.FeatureService,
             "get_features",
-            lambda _id, **_kwargs: FeatureModel(human_input_email_delivery_enabled=True),
+            lambda _id, **_kwargs: SimpleNamespace(human_input_email_delivery_enabled=True),
         )
         monkeypatch.setattr(service_module.mail, "is_inited", lambda: False)
 
-        handler = EmailDeliveryTestHandler(session_factory=sqlite_engine)
+        handler = EmailDeliveryTestHandler(session_factory=MagicMock())
         context = DeliveryTestContext(
             tenant_id="t1", app_id="a1", node_id="n1", node_title="title", rendered_content="content"
         )
@@ -164,15 +155,15 @@ class TestEmailDeliveryTestHandler:
         with pytest.raises(DeliveryTestError, match="Mail client is not initialized."):
             handler.send_test(context=context, method=method)
 
-    def test_send_test_no_recipients(self, monkeypatch: pytest.MonkeyPatch, sqlite_engine: Engine) -> None:
+    def test_send_test_no_recipients(self, monkeypatch: pytest.MonkeyPatch):
         monkeypatch.setattr(
             service_module.FeatureService,
             "get_features",
-            lambda _id, **_kwargs: FeatureModel(human_input_email_delivery_enabled=True),
+            lambda _id, **_kwargs: SimpleNamespace(human_input_email_delivery_enabled=True),
         )
         monkeypatch.setattr(service_module.mail, "is_inited", lambda: True)
 
-        handler = EmailDeliveryTestHandler(session_factory=sqlite_engine)
+        handler = EmailDeliveryTestHandler(session_factory=MagicMock())
         handler._resolve_recipients = MagicMock(return_value=[])
 
         context = DeliveryTestContext(
@@ -183,18 +174,18 @@ class TestEmailDeliveryTestHandler:
         with pytest.raises(DeliveryTestError, match="No recipients configured"):
             handler.send_test(context=context, method=method)
 
-    def test_send_test_success(self, monkeypatch: pytest.MonkeyPatch, sqlite_engine: Engine) -> None:
+    def test_send_test_success(self, monkeypatch: pytest.MonkeyPatch):
         monkeypatch.setattr(
             service_module.FeatureService,
             "get_features",
-            lambda _id, **_kwargs: FeatureModel(human_input_email_delivery_enabled=True),
+            lambda _id, **_kwargs: SimpleNamespace(human_input_email_delivery_enabled=True),
         )
         monkeypatch.setattr(service_module.mail, "is_inited", lambda: True)
         mock_mail_send = MagicMock()
         monkeypatch.setattr(service_module.mail, "send", mock_mail_send)
         monkeypatch.setattr(service_module, "render_email_template", lambda t, s: f"RENDERED_{t}")
 
-        handler = EmailDeliveryTestHandler(session_factory=sqlite_engine)
+        handler = EmailDeliveryTestHandler(session_factory=MagicMock())
         handler._resolve_recipients = MagicMock(return_value=["test@example.com"])
 
         variable_pool = VariablePool()
@@ -219,11 +210,11 @@ class TestEmailDeliveryTestHandler:
         assert kwargs["to"] == "test@example.com"
         assert "RENDERED_Subj" in kwargs["subject"]
 
-    def test_send_test_sanitizes_subject(self, monkeypatch: pytest.MonkeyPatch, sqlite_engine: Engine) -> None:
+    def test_send_test_sanitizes_subject(self, monkeypatch: pytest.MonkeyPatch):
         monkeypatch.setattr(
             service_module.FeatureService,
             "get_features",
-            lambda _id, **_kwargs: FeatureModel(human_input_email_delivery_enabled=True),
+            lambda _id, **_kwargs: SimpleNamespace(human_input_email_delivery_enabled=True),
         )
         monkeypatch.setattr(service_module.mail, "is_inited", lambda: True)
         mock_mail_send = MagicMock()
@@ -234,7 +225,7 @@ class TestEmailDeliveryTestHandler:
             lambda template, substitutions: template.replace("{{ recipient_email }}", substitutions["recipient_email"]),
         )
 
-        handler = EmailDeliveryTestHandler(session_factory=sqlite_engine)
+        handler = EmailDeliveryTestHandler(session_factory=MagicMock())
         handler._resolve_recipients = MagicMock(return_value=["test@example.com"])
 
         context = DeliveryTestContext(
@@ -258,8 +249,8 @@ class TestEmailDeliveryTestHandler:
         _, kwargs = mock_mail_send.call_args
         assert kwargs["subject"] == "Notice BCC:test@example.com"
 
-    def test_resolve_recipients_external(self, sqlite_engine: Engine) -> None:
-        handler = EmailDeliveryTestHandler(session_factory=sqlite_engine)
+    def test_resolve_recipients_external(self):
+        handler = EmailDeliveryTestHandler(session_factory=MagicMock())
         method = EmailDeliveryMethod(
             config=EmailDeliveryConfig(
                 recipients=EmailRecipients(
@@ -271,18 +262,19 @@ class TestEmailDeliveryTestHandler:
         )
         assert handler._resolve_recipients(tenant_id="t1", method=method) == ["ext@example.com"]
 
-    @pytest.mark.parametrize("sqlite_session", [(Account, TenantAccountJoin)], indirect=True)
-    def test_resolve_recipients_member(self, sqlite_engine: Engine, sqlite_session: Session) -> None:
+    def test_resolve_recipients_member(self, flask_app_with_containers: Flask, db_session_with_containers: Session):
         tenant_id = str(uuid4())
         account = Account(name="Test User", email="member@example.com")
-        sqlite_session.add(account)
-        sqlite_session.commit()
+        db_session_with_containers.add(account)
+        db_session_with_containers.commit()
 
         join = TenantAccountJoin(tenant_id=tenant_id, account_id=account.id)
-        sqlite_session.add(join)
-        sqlite_session.commit()
+        db_session_with_containers.add(join)
+        db_session_with_containers.commit()
 
-        handler = EmailDeliveryTestHandler(session_factory=sqlite_engine)
+        from extensions.ext_database import db
+
+        handler = EmailDeliveryTestHandler(session_factory=db.engine)
         method = EmailDeliveryMethod(
             config=EmailDeliveryConfig(
                 recipients=EmailRecipients(items=[MemberRecipient(reference_id=account.id)], include_bound_group=False),
@@ -292,20 +284,23 @@ class TestEmailDeliveryTestHandler:
         )
         assert handler._resolve_recipients(tenant_id=tenant_id, method=method) == ["member@example.com"]
 
-    @pytest.mark.parametrize("sqlite_session", [(Account, TenantAccountJoin)], indirect=True)
-    def test_resolve_recipients_whole_workspace(self, sqlite_engine: Engine, sqlite_session: Session) -> None:
+    def test_resolve_recipients_whole_workspace(
+        self, flask_app_with_containers: Flask, db_session_with_containers: Session
+    ):
         tenant_id = str(uuid4())
         account1 = Account(name="User 1", email=f"u1-{uuid4()}@example.com")
         account2 = Account(name="User 2", email=f"u2-{uuid4()}@example.com")
-        sqlite_session.add_all([account1, account2])
-        sqlite_session.commit()
+        db_session_with_containers.add_all([account1, account2])
+        db_session_with_containers.commit()
 
         for acc in [account1, account2]:
             join = TenantAccountJoin(tenant_id=tenant_id, account_id=acc.id)
-            sqlite_session.add(join)
-        sqlite_session.commit()
+            db_session_with_containers.add(join)
+        db_session_with_containers.commit()
 
-        handler = EmailDeliveryTestHandler(session_factory=sqlite_engine)
+        from extensions.ext_database import db
+
+        handler = EmailDeliveryTestHandler(session_factory=db.engine)
         method = EmailDeliveryMethod(
             config=EmailDeliveryConfig(
                 recipients=EmailRecipients(items=[], include_bound_group=True),
@@ -316,8 +311,8 @@ class TestEmailDeliveryTestHandler:
         recipients = handler._resolve_recipients(tenant_id=tenant_id, method=method)
         assert set(recipients) == {account1.email, account2.email}
 
-    def test_query_workspace_member_emails_empty_ids(self, sqlite_engine: Engine) -> None:
-        handler = EmailDeliveryTestHandler(session_factory=sqlite_engine)
+    def test_query_workspace_member_emails_empty_ids(self):
+        handler = EmailDeliveryTestHandler(session_factory=MagicMock())
         assert handler._query_workspace_member_emails(tenant_id="t1", user_ids=[]) == {}
 
     def test_build_substitutions(self):

api/tests/unit_tests/clients/agent_backend/test_client.py

@@ -1,4 +1,4 @@
-from collections.abc import Callable, Iterator
+from collections.abc import Iterator
 from typing import override
 
 import pytest
@@ -47,8 +47,6 @@ def _request():
 
 
 class _SuccessfulClient:
-    stream_options: tuple[int | None, float | None, Callable[[], bool] | None] | None = None
-
     def create_run_sync(self, request: CreateRunRequest) -> CreateRunResponse:
         assert isinstance(request, CreateRunRequest)
         return CreateRunResponse(run_id="run-1", status="running")
@@ -57,17 +55,8 @@ class _SuccessfulClient:
         del request
         return CancelRunResponse(run_id=run_id, status="cancelled")
 
-    def stream_events_sync(
-        self,
-        run_id: str,
-        *,
-        after: str | None = None,
-        max_reconnects: int | None = None,
-        timeout_seconds: float | None = None,
-        should_stop: Callable[[], bool] | None = None,
-    ) -> Iterator[RunEvent]:
+    def stream_events_sync(self, run_id: str, *, after: str | None = None) -> Iterator[RunEvent]:
         del after
-        self.stream_options = (max_reconnects, timeout_seconds, should_stop)
         yield RunStartedEvent(id="1-0", run_id=run_id)
 
     def wait_run_sync(self, run_id: str, *, timeout_seconds: float | None = None) -> RunStatusResponse:
@@ -83,22 +72,17 @@ class _SuccessfulClient:
 
 
 def test_dify_agent_backend_run_client_delegates_sync_methods():
-    wrapped = _SuccessfulClient()
-    client = DifyAgentBackendRunClient(wrapped, stream_max_reconnects=2, stream_timeout_seconds=45)
-
-    def should_stop() -> bool:
-        return False
+    client = DifyAgentBackendRunClient(_SuccessfulClient())
 
     created = client.create_run(_request())
     cancelled = client.cancel_run(created.run_id)
-    events = list(client.stream_events(created.run_id, should_stop=should_stop))
+    events = list(client.stream_events(created.run_id))
     status = client.wait_run(created.run_id)
 
     assert created.run_id == "run-1"
     assert cancelled.status == "cancelled"
     assert events[0].type == "run_started"
     assert status.status == "succeeded"
-    assert wrapped.stream_options == (2, 45, should_stop)
 
 
 def test_dify_agent_backend_run_client_maps_validation_error():
@@ -141,16 +125,7 @@ def test_dify_agent_backend_run_client_maps_timeout_error():
 def test_dify_agent_backend_run_client_maps_stream_error():
     class StreamClient(_SuccessfulClient):
         @override
-        def stream_events_sync(
-            self,
-            run_id: str,
-            *,
-            after: str | None = None,
-            max_reconnects: int | None = None,
-            timeout_seconds: float | None = None,
-            should_stop: Callable[[], bool] | None = None,
-        ) -> Iterator[RunEvent]:
-            del run_id, after, max_reconnects, timeout_seconds, should_stop
+        def stream_events_sync(self, run_id: str, *, after: str | None = None) -> Iterator[RunEvent]:
             raise DifyAgentStreamError("bad stream")
             yield
 

api/tests/unit_tests/clients/agent_backend/test_event_adapter.py

@@ -1,5 +1,3 @@
-from decimal import Decimal
-
 import pytest
 from agenton.compositor import CompositorSessionSnapshot
 from dify_agent.protocol import (
@@ -85,19 +83,7 @@ def test_event_adapter_maps_run_succeeded_to_final_output():
             data=RunSucceededEventData(
                 output={"summary": "done"},
                 session_snapshot=snapshot,
-                usage=AgentRunUsage(
-                    prompt_tokens=2,
-                    prompt_unit_price=Decimal(5),
-                    prompt_price_unit=Decimal("0.000001"),
-                    prompt_price=Decimal("0.000010"),
-                    completion_tokens=3,
-                    completion_unit_price=Decimal(30),
-                    completion_price_unit=Decimal("0.000001"),
-                    completion_price=Decimal("0.000090"),
-                    total_price=Decimal("0.000100"),
-                    currency="USD",
-                    latency=0.4,
-                ),
+                usage=AgentRunUsage(prompt_tokens=2, completion_tokens=3),
             ),
         )
     )
@@ -108,22 +94,7 @@ def test_event_adapter_maps_run_succeeded_to_final_output():
             source_event_id="3-0",
             output={"summary": "done"},
             session_snapshot=snapshot,
-            usage={
-                "prompt_tokens": 2,
-                "prompt_unit_price": "5",
-                "prompt_price_unit": "0.000001",
-                "prompt_price": "0.000010",
-                "completion_tokens": 3,
-                "completion_unit_price": "30",
-                "completion_price_unit": "0.000001",
-                "completion_price": "0.000090",
-                "total_tokens": 5,
-                "total_price": "0.000100",
-                "currency": "USD",
-                "latency": 0.4,
-                "time_to_first_token": None,
-                "time_to_generate": None,
-            },
+            usage={"prompt_tokens": 2, "completion_tokens": 3, "total_tokens": 5},
         )
     ]
 

api/tests/unit_tests/commands/test_archive_workflow_runs.py

@@ -3,19 +3,9 @@ from unittest.mock import MagicMock
 
 import click
 import pytest
-from click.testing import CliRunner
 from sqlalchemy.exc import OperationalError
 
 from commands import retention
-from services.retention.workflow_run import bundle_archive_maintenance
-from services.retention.workflow_run.bundle_archive_maintenance import (
-    BundleOperationResult,
-    BundleOperationSummary,
-)
-
-_CURSOR_0 = "00000000-0000-0000-0000-000000000000"
-_CURSOR_1 = "00000000-0000-0000-0000-000000000001"
-_CURSOR_2 = "00000000-0000-0000-0000-000000000002"
 
 
 def _db_disconnect_error() -> OperationalError:
@@ -34,58 +24,6 @@ def _session_context(session):
     return context
 
 
-def _delete_summary(
-    *,
-    processed: int,
-    succeeded: int = 0,
-    failed: int = 0,
-    next_catalog_id: str | None = None,
-    preview_next_catalog_id: str | None = None,
-    results: list[BundleOperationResult] | None = None,
-) -> BundleOperationSummary:
-    return BundleOperationSummary(
-        operation="delete",
-        bundles_processed=processed,
-        bundles_succeeded=succeeded,
-        bundles_failed=failed,
-        next_catalog_id=next_catalog_id,
-        preview_next_catalog_id=preview_next_catalog_id,
-        results=results or [],
-    )
-
-
-def _patch_bundle_deleter(
-    monkeypatch: pytest.MonkeyPatch,
-    summaries: list[BundleOperationSummary],
-) -> MagicMock:
-    deleter = MagicMock()
-    deleter.delete_batch.side_effect = summaries
-    monkeypatch.setattr(
-        bundle_archive_maintenance,
-        "WorkflowRunBundleArchiveMaintenance",
-        MagicMock(return_value=deleter),
-    )
-    return deleter
-
-
-@pytest.mark.parametrize(
-    "command",
-    [retention.restore_workflow_runs, retention.delete_archived_workflow_runs],
-)
-def test_v2_archive_maintenance_rejects_explicitly_empty_tenant_ids(command):
-    result = CliRunner().invoke(
-        command,
-        ["--tenant-ids", "", "--target-month", "2025-03"],
-    )
-
-    assert result.exit_code == 2
-    assert "tenant-ids must not be empty" in result.output
-
-
-def test_archive_tenant_id_parser_keeps_omitted_scope_unset():
-    assert retention._parse_comma_separated_ids(None, param_name="tenant-ids") is None
-
-
 def test_resolve_archive_tenant_ids_from_plan_uses_explicit_sessions(monkeypatch):
     end_before = datetime.datetime(2025, 4, 1, tzinfo=datetime.UTC)
     sessions = [MagicMock(name="session-a"), MagicMock(name="session-b")]
@@ -199,265 +137,3 @@ def test_archive_workflow_runs_raises_click_exception_when_tenant_plan_fails(mon
             dry_run=True,
             delete_after_archive=False,
         )
-
-
-def test_delete_archived_workflow_runs_keeps_single_page_behavior_without_all_pages(monkeypatch):
-    deleter = _patch_bundle_deleter(
-        monkeypatch,
-        [_delete_summary(processed=2, succeeded=2, next_catalog_id=_CURSOR_1)],
-    )
-
-    result = CliRunner().invoke(
-        retention.delete_archived_workflow_runs,
-        ["--target-month", "2025-03", "--limit", "2"],
-    )
-
-    assert result.exit_code == 0
-    deleter.delete_batch.assert_called_once()
-    assert deleter.delete_batch.call_args.kwargs["target_year"] == 2025
-    assert deleter.delete_batch.call_args.kwargs["target_month"] == 3
-    assert deleter.delete_batch.call_args.kwargs["after_catalog_id"] is None
-    assert deleter.delete_batch.call_args.kwargs["limit"] == 2
-
-
-def test_delete_archived_workflow_runs_all_pages_continues_until_empty_page(monkeypatch):
-    deleter = _patch_bundle_deleter(
-        monkeypatch,
-        [
-            _delete_summary(processed=2, succeeded=2, next_catalog_id=_CURSOR_1),
-            _delete_summary(processed=1, succeeded=1, next_catalog_id=_CURSOR_2),
-            _delete_summary(processed=0),
-        ],
-    )
-
-    result = CliRunner().invoke(
-        retention.delete_archived_workflow_runs,
-        ["--target-month", "2025-03", "--all-pages", "--limit", "2"],
-    )
-
-    assert result.exit_code == 0
-    assert [call.kwargs["after_catalog_id"] for call in deleter.delete_batch.call_args_list] == [
-        None,
-        _CURSOR_1,
-        _CURSOR_2,
-    ]
-
-
-def test_delete_archived_workflow_runs_all_pages_fetches_empty_page_after_exact_full_page(monkeypatch):
-    deleter = _patch_bundle_deleter(
-        monkeypatch,
-        [
-            _delete_summary(processed=2, succeeded=2, next_catalog_id=_CURSOR_1),
-            _delete_summary(processed=0),
-        ],
-    )
-
-    result = CliRunner().invoke(
-        retention.delete_archived_workflow_runs,
-        ["--target-month", "2025-03", "--all-pages", "--limit", "2"],
-    )
-
-    assert result.exit_code == 0
-    assert deleter.delete_batch.call_count == 2
-    assert deleter.delete_batch.call_args_list[1].kwargs["after_catalog_id"] == _CURSOR_1
-
-
-def test_delete_archived_workflow_runs_all_pages_stops_at_first_failed_page(monkeypatch):
-    failed_result = BundleOperationResult(
-        catalog_id=_CURSOR_2,
-        bundle_id="bundle-failed",
-        tenant_id="tenant-1",
-        object_prefix="workflow-runs/v2/tenant-1/2025/03/00-of-16/bundle-failed",
-        error="archive checksum mismatch",
-    )
-    deleter = _patch_bundle_deleter(
-        monkeypatch,
-        [
-            _delete_summary(processed=1, succeeded=1, next_catalog_id=_CURSOR_1),
-            _delete_summary(processed=1, failed=1, results=[failed_result]),
-            _delete_summary(processed=0),
-        ],
-    )
-
-    result = CliRunner().invoke(
-        retention.delete_archived_workflow_runs,
-        ["--target-month", "2025-03", "--all-pages"],
-    )
-
-    assert result.exit_code == 1
-    assert deleter.delete_batch.call_count == 2
-    assert "target_month=2025-03" in result.output
-    assert f"failed_catalog_id={_CURSOR_2}" in result.output
-    assert f"resume_after_catalog_id={_CURSOR_1}" in result.output
-
-
-def test_delete_archived_workflow_runs_all_pages_fails_when_cursor_does_not_advance(monkeypatch):
-    deleter = _patch_bundle_deleter(
-        monkeypatch,
-        [_delete_summary(processed=1, succeeded=1, next_catalog_id=None)],
-    )
-
-    result = CliRunner().invoke(
-        retention.delete_archived_workflow_runs,
-        ["--target-month", "2025-03", "--all-pages"],
-    )
-
-    assert result.exit_code == 1
-    deleter.delete_batch.assert_called_once()
-    assert "cursor did not advance" in result.output.lower()
-
-
-def test_delete_archived_workflow_runs_all_pages_uses_preview_cursor_for_dry_run(monkeypatch):
-    deleter = _patch_bundle_deleter(
-        monkeypatch,
-        [
-            _delete_summary(processed=1, succeeded=1, preview_next_catalog_id=_CURSOR_1),
-            _delete_summary(processed=0),
-        ],
-    )
-
-    result = CliRunner().invoke(
-        retention.delete_archived_workflow_runs,
-        ["--target-month", "2025-03", "--all-pages", "--dry-run"],
-    )
-
-    assert result.exit_code == 0
-    assert [call.kwargs["after_catalog_id"] for call in deleter.delete_batch.call_args_list] == [
-        None,
-        _CURSOR_1,
-    ]
-
-
-def test_delete_archived_workflow_runs_dry_run_failure_separates_preview_and_destructive_cursors(monkeypatch):
-    failed_result = BundleOperationResult(
-        catalog_id=_CURSOR_2,
-        bundle_id="bundle-failed",
-        tenant_id="tenant-1",
-        object_prefix="workflow-runs/v2/tenant-1/2025/03/00-of-16/bundle-failed",
-        error="archive checksum mismatch",
-    )
-    deleter = _patch_bundle_deleter(
-        monkeypatch,
-        [
-            _delete_summary(
-                processed=1,
-                succeeded=1,
-                preview_next_catalog_id=_CURSOR_1,
-            ),
-            _delete_summary(
-                processed=1,
-                failed=1,
-                results=[failed_result],
-            ),
-        ],
-    )
-
-    result = CliRunner().invoke(
-        retention.delete_archived_workflow_runs,
-        [
-            "--target-month",
-            "2025-03",
-            "--after-catalog-id",
-            _CURSOR_0,
-            "--all-pages",
-            "--dry-run",
-        ],
-    )
-
-    assert result.exit_code == 1
-    assert deleter.delete_batch.call_count == 2
-    assert f"failed_catalog_id={_CURSOR_2}" in result.output
-    assert f"preview_after_catalog_id={_CURSOR_1}" in result.output
-    assert f"destructive_retry_after_catalog_id={_CURSOR_0}" in result.output
-
-
-def test_delete_archived_workflow_runs_all_pages_starts_after_explicit_cursor(monkeypatch):
-    deleter = _patch_bundle_deleter(monkeypatch, [_delete_summary(processed=0)])
-
-    result = CliRunner().invoke(
-        retention.delete_archived_workflow_runs,
-        [
-            "--target-month",
-            "2025-03",
-            "--after-catalog-id",
-            _CURSOR_0,
-            "--all-pages",
-        ],
-    )
-
-    assert result.exit_code == 0
-    deleter.delete_batch.assert_called_once()
-    assert deleter.delete_batch.call_args.kwargs["after_catalog_id"] == _CURSOR_0
-
-
-@pytest.mark.parametrize(
-    "shard_args",
-    [
-        ["--run-shard-index", "0"],
-        ["--run-shard-total", "16"],
-        ["--run-shard-index", "16", "--run-shard-total", "16"],
-        ["--run-shard-index", "-1", "--run-shard-total", "16"],
-        ["--run-shard-index", "0", "--run-shard-total", "0"],
-        ["--run-shard-index", "0", "--run-shard-total", "17"],
-    ],
-)
-def test_delete_archived_workflow_runs_rejects_invalid_run_shard_options(monkeypatch, shard_args):
-    deleter = _patch_bundle_deleter(monkeypatch, [_delete_summary(processed=0)])
-
-    result = CliRunner().invoke(
-        retention.delete_archived_workflow_runs,
-        ["--target-month", "2025-03", *shard_args],
-    )
-
-    assert result.exit_code == 2
-    deleter.delete_batch.assert_not_called()
-
-
-def test_delete_archived_workflow_runs_passes_formatted_run_shard_to_service(monkeypatch):
-    deleter = _patch_bundle_deleter(monkeypatch, [_delete_summary(processed=0)])
-
-    result = CliRunner().invoke(
-        retention.delete_archived_workflow_runs,
-        [
-            "--target-month",
-            "2025-03",
-            "--tenant-ids",
-            "tenant-1",
-            "--run-shard-index",
-            "3",
-            "--run-shard-total",
-            "16",
-        ],
-    )
-
-    assert result.exit_code == 0
-    deleter.validate_catalog_shards.assert_called_once_with(
-        target_year=2025,
-        target_month=3,
-        shard_total=16,
-        tenant_ids=["tenant-1"],
-    )
-    deleter.delete_batch.assert_called_once()
-    assert deleter.delete_batch.call_args.kwargs["shard"] == "03-of-16"
-
-
-def test_delete_archived_workflow_runs_rejects_mixed_catalog_shards_before_delete(monkeypatch):
-    deleter = _patch_bundle_deleter(monkeypatch, [_delete_summary(processed=0)])
-    deleter.validate_catalog_shards.side_effect = ValueError("unexpected shards: 00-of-01")
-
-    result = CliRunner().invoke(
-        retention.delete_archived_workflow_runs,
-        [
-            "--target-month",
-            "2025-03",
-            "--run-shard-index",
-            "3",
-            "--run-shard-total",
-            "16",
-        ],
-    )
-
-    assert result.exit_code == 1
-    assert "shard preflight failed" in result.output.lower()
-    assert "00-of-01" in result.output
-    deleter.delete_batch.assert_not_called()

api/tests/unit_tests/configs/test_dify_config.py

@@ -8,13 +8,8 @@ from yarl import URL
 from configs.app_config import DifyConfig
 
 
-def _clear_environment(monkeypatch: pytest.MonkeyPatch) -> None:
-    for name in tuple(os.environ):
-        monkeypatch.delenv(name)
-
-
 def _set_basic_config_env(monkeypatch: pytest.MonkeyPatch) -> None:
-    _clear_environment(monkeypatch)
+    os.environ.clear()
     monkeypatch.setenv("CONSOLE_API_URL", "https://example.com")
     monkeypatch.setenv("CONSOLE_WEB_URL", "https://example.com")
     monkeypatch.setenv("DB_TYPE", "postgresql")
@@ -56,7 +51,7 @@ def test_dify_config_preserves_explicit_secret_key(
 
 def test_dify_config(monkeypatch: pytest.MonkeyPatch):
     # clear system environment variables
-    _clear_environment(monkeypatch)
+    os.environ.clear()
 
     # Set environment variables using monkeypatch
     monkeypatch.setenv("CONSOLE_API_URL", "https://example.com")
@@ -109,24 +104,6 @@ def test_new_user_default_plugin_ids_are_parsed_from_env(monkeypatch: pytest.Mon
     ]
 
 
-def test_plugin_remote_install_port_rejects_host_port_spec(monkeypatch: pytest.MonkeyPatch) -> None:
-    """A 'host:port' compose publish spec must produce an actionable error, not an opaque int_parsing traceback."""
-    _set_basic_config_env(monkeypatch)
-    monkeypatch.setenv("PLUGIN_REMOTE_INSTALL_PORT", "127.0.0.1:5003")
-
-    with pytest.raises(ValueError, match="must be a bare port number"):
-        DifyConfig(_env_file=None)
-
-
-def test_plugin_remote_install_port_accepts_bare_port(monkeypatch: pytest.MonkeyPatch) -> None:
-    _set_basic_config_env(monkeypatch)
-    monkeypatch.setenv("PLUGIN_REMOTE_INSTALL_PORT", "5003")
-
-    config = DifyConfig(_env_file=None)
-
-    assert config.PLUGIN_REMOTE_INSTALL_PORT == 5003
-
-
 def test_new_user_default_models_are_parsed_from_env(monkeypatch: pytest.MonkeyPatch) -> None:
     _set_basic_config_env(monkeypatch)
     monkeypatch.setenv(
@@ -163,7 +140,7 @@ def test_new_user_default_models_reject_duplicate_model_types(monkeypatch: pytes
 def test_http_timeout_defaults(monkeypatch: pytest.MonkeyPatch):
     """Test that HTTP timeout defaults are correctly set"""
     # clear system environment variables
-    _clear_environment(monkeypatch)
+    os.environ.clear()
 
     # Set minimal required env vars
     monkeypatch.setenv("DB_TYPE", "postgresql")
@@ -183,7 +160,7 @@ def test_http_timeout_defaults(monkeypatch: pytest.MonkeyPatch):
 
 
 def test_internal_files_url_falls_back_to_server_console_api_url(monkeypatch: pytest.MonkeyPatch):
-    _clear_environment(monkeypatch)
+    os.environ.clear()
     monkeypatch.setenv("SERVER_CONSOLE_API_URL", "http://api:5001")
 
     config = DifyConfig(_env_file=None)
@@ -192,7 +169,7 @@ def test_internal_files_url_falls_back_to_server_console_api_url(monkeypatch: py
 
 
 def test_internal_files_url_prefers_explicit_value(monkeypatch: pytest.MonkeyPatch):
-    _clear_environment(monkeypatch)
+    os.environ.clear()
     monkeypatch.setenv("INTERNAL_FILES_URL", "http://files-internal:5001")
     monkeypatch.setenv("SERVER_CONSOLE_API_URL", "http://api:5001")
 
@@ -206,7 +183,7 @@ def test_internal_files_url_prefers_explicit_value(monkeypatch: pytest.MonkeyPat
 def test_flask_configs(monkeypatch: pytest.MonkeyPatch):
     flask_app = Flask("app")
     # clear system environment variables
-    _clear_environment(monkeypatch)
+    os.environ.clear()
 
     # Set environment variables using monkeypatch
     monkeypatch.setenv("CONSOLE_API_URL", "https://example.com")
@@ -313,7 +290,7 @@ def test_db_session_timezone_override_can_disable_app_level_timezone_injection(m
 
 
 def test_pubsub_redis_url_default(monkeypatch: pytest.MonkeyPatch):
-    _clear_environment(monkeypatch)
+    os.environ.clear()
 
     monkeypatch.setenv("CONSOLE_API_URL", "https://example.com")
     monkeypatch.setenv("CONSOLE_WEB_URL", "https://example.com")
@@ -336,7 +313,7 @@ def test_pubsub_redis_url_default(monkeypatch: pytest.MonkeyPatch):
 
 
 def test_pubsub_redis_url_override(monkeypatch: pytest.MonkeyPatch):
-    _clear_environment(monkeypatch)
+    os.environ.clear()
 
     monkeypatch.setenv("CONSOLE_API_URL", "https://example.com")
     monkeypatch.setenv("CONSOLE_WEB_URL", "https://example.com")
@@ -353,7 +330,7 @@ def test_pubsub_redis_url_override(monkeypatch: pytest.MonkeyPatch):
 
 
 def test_pubsub_redis_url_required_when_default_unavailable(monkeypatch: pytest.MonkeyPatch):
-    _clear_environment(monkeypatch)
+    os.environ.clear()
 
     monkeypatch.setenv("CONSOLE_API_URL", "https://example.com")
     monkeypatch.setenv("CONSOLE_WEB_URL", "https://example.com")
@@ -369,7 +346,7 @@ def test_pubsub_redis_url_required_when_default_unavailable(monkeypatch: pytest.
 
 
 def test_dify_config_exposes_redis_key_prefix_default(monkeypatch: pytest.MonkeyPatch):
-    _clear_environment(monkeypatch)
+    os.environ.clear()
 
     monkeypatch.setenv("CONSOLE_API_URL", "https://example.com")
     monkeypatch.setenv("CONSOLE_WEB_URL", "https://example.com")
@@ -386,7 +363,7 @@ def test_dify_config_exposes_redis_key_prefix_default(monkeypatch: pytest.Monkey
 
 
 def test_dify_config_reads_redis_key_prefix_from_env(monkeypatch: pytest.MonkeyPatch):
-    _clear_environment(monkeypatch)
+    os.environ.clear()
 
     monkeypatch.setenv("CONSOLE_API_URL", "https://example.com")
     monkeypatch.setenv("CONSOLE_WEB_URL", "https://example.com")
@@ -438,7 +415,7 @@ def test_celery_broker_url_with_special_chars_password(
     from kombu.utils.url import parse_url
 
     # clear system environment variables
-    _clear_environment(monkeypatch)
+    os.environ.clear()
 
     # Set up basic required environment variables (following existing pattern)
     monkeypatch.setenv("CONSOLE_API_URL", "https://example.com")

api/tests/unit_tests/configs/test_knowledge_fs_config.py

@@ -1,142 +0,0 @@
-from __future__ import annotations
-
-from pathlib import Path
-
-import pytest
-from pydantic import SecretStr, ValidationError
-
-from configs.extra.knowledge_fs_config import KnowledgeFSConfig
-
-_REPOSITORY_ROOT = Path(__file__).resolve().parents[4]
-_KNOWLEDGE_FS_DOCKER_VARIABLES = (
-    "KNOWLEDGE_FS_ENABLED",
-    "KNOWLEDGE_FS_BASE_URL",
-    "KNOWLEDGE_FS_JWT_SECRET",
-    "KNOWLEDGE_FS_SSE_READ_TIMEOUT_SECONDS",
-    "KNOWLEDGE_FS_TIMEOUT_SECONDS",
-)
-
-
-def test_knowledge_fs_config_normalizes_complete_connection() -> None:
-    config = KnowledgeFSConfig(
-        KNOWLEDGE_FS_ENABLED=True,
-        KNOWLEDGE_FS_BASE_URL="  https://knowledge-fs.test/  ",
-        KNOWLEDGE_FS_JWT_SECRET="  production-secret-with-at-least-32-bytes  ",
-    )
-
-    assert config.KNOWLEDGE_FS_BASE_URL == "https://knowledge-fs.test"
-    assert isinstance(config.KNOWLEDGE_FS_JWT_SECRET, SecretStr)
-    assert config.KNOWLEDGE_FS_JWT_SECRET.get_secret_value() == "production-secret-with-at-least-32-bytes"
-    assert "production-secret" not in repr(config)
-    assert "production-secret" not in config.model_dump_json()
-    assert config.KNOWLEDGE_FS_SSE_READ_TIMEOUT_SECONDS == 300.0
-
-
-def test_knowledge_fs_config_treats_blank_connection_as_disabled() -> None:
-    config = KnowledgeFSConfig(
-        KNOWLEDGE_FS_BASE_URL=" ",
-        KNOWLEDGE_FS_JWT_SECRET="",
-    )
-
-    assert config.KNOWLEDGE_FS_BASE_URL is None
-    assert config.KNOWLEDGE_FS_JWT_SECRET is None
-    assert config.KNOWLEDGE_FS_ENABLED is False
-
-
-def test_knowledge_fs_config_requires_connection_when_enabled() -> None:
-    with pytest.raises(ValidationError, match="connection settings are required"):
-        KnowledgeFSConfig(KNOWLEDGE_FS_ENABLED=True)
-
-
-@pytest.mark.parametrize(
-    ("base_url", "jwt_secret"),
-    [
-        ("https://knowledge-fs.test", None),
-        (None, "production-secret-with-at-least-32-bytes"),
-    ],
-)
-def test_disabled_knowledge_fs_config_allows_partial_connection(base_url: str | None, jwt_secret: str | None) -> None:
-    config = KnowledgeFSConfig(
-        KNOWLEDGE_FS_ENABLED=False,
-        KNOWLEDGE_FS_BASE_URL=base_url,
-        KNOWLEDGE_FS_JWT_SECRET=jwt_secret,
-    )
-
-    assert config.KNOWLEDGE_FS_ENABLED is False
-
-
-def test_knowledge_fs_docker_config_is_not_shadowed_by_root_env() -> None:
-    root_env_example = (_REPOSITORY_ROOT / "docker/.env.example").read_text(encoding="utf-8")
-    api_env_example = (_REPOSITORY_ROOT / "docker/envs/core-services/api.env.example").read_text(encoding="utf-8")
-
-    for variable in _KNOWLEDGE_FS_DOCKER_VARIABLES:
-        assert f"{variable}=" not in root_env_example
-        assert f"{variable}=" in api_env_example
-
-
-@pytest.mark.parametrize(
-    ("base_url", "jwt_secret"),
-    [
-        ("https://knowledge-fs.test", None),
-        (None, "production-secret-with-at-least-32-bytes"),
-    ],
-)
-def test_knowledge_fs_config_rejects_partial_connection(base_url: str | None, jwt_secret: str | None) -> None:
-    with pytest.raises(ValidationError, match="must be configured together"):
-        KnowledgeFSConfig(
-            KNOWLEDGE_FS_ENABLED=True,
-            KNOWLEDGE_FS_BASE_URL=base_url,
-            KNOWLEDGE_FS_JWT_SECRET=jwt_secret,
-        )
-
-
-@pytest.mark.parametrize("base_url", ["knowledge-fs.test", "ftp://knowledge-fs.test", "http:///missing-host"])
-def test_knowledge_fs_config_rejects_non_http_absolute_urls(base_url: str) -> None:
-    with pytest.raises(ValidationError, match="absolute HTTP\\(S\\) URL"):
-        KnowledgeFSConfig(
-            KNOWLEDGE_FS_BASE_URL=base_url,
-            KNOWLEDGE_FS_JWT_SECRET="production-secret-with-at-least-32-bytes",
-        )
-
-
-@pytest.mark.parametrize(
-    "base_url",
-    [
-        "https://knowledge-fs.test:notaport",
-        "https://knowledge-fs.test:65536",
-    ],
-)
-def test_knowledge_fs_config_rejects_invalid_ports(base_url: str) -> None:
-    with pytest.raises(ValidationError, match="valid port"):
-        KnowledgeFSConfig(
-            KNOWLEDGE_FS_BASE_URL=base_url,
-            KNOWLEDGE_FS_JWT_SECRET="production-secret-with-at-least-32-bytes",
-        )
-
-
-@pytest.mark.parametrize(
-    "base_url",
-    [
-        "https://user:password@knowledge-fs.test",
-        "https://knowledge-fs.test?region=us",
-        "https://knowledge-fs.test#gateway",
-    ],
-)
-def test_knowledge_fs_config_rejects_unsafe_base_url_components(base_url: str) -> None:
-    with pytest.raises(ValidationError, match="must not include credentials, query, or fragment"):
-        KnowledgeFSConfig(
-            KNOWLEDGE_FS_BASE_URL=base_url,
-            KNOWLEDGE_FS_JWT_SECRET="production-secret-with-at-least-32-bytes",
-        )
-
-
-@pytest.mark.parametrize("timeout_seconds", [float("inf"), float("nan"), 60.0001])
-def test_knowledge_fs_config_rejects_unbounded_timeouts(timeout_seconds: float) -> None:
-    with pytest.raises(ValidationError):
-        KnowledgeFSConfig(KNOWLEDGE_FS_TIMEOUT_SECONDS=timeout_seconds)
-
-
-@pytest.mark.parametrize("timeout_seconds", [float("inf"), float("nan"), 3600.0001])
-def test_knowledge_fs_config_rejects_unbounded_sse_read_timeouts(timeout_seconds: float) -> None:
-    with pytest.raises(ValidationError):
-        KnowledgeFSConfig(KNOWLEDGE_FS_SSE_READ_TIMEOUT_SECONDS=timeout_seconds)

api/tests/unit_tests/controllers/common/test_agent_app_parameters.py

@@ -1,82 +1,23 @@
 from types import SimpleNamespace
-from typing import Any
-from uuid import NAMESPACE_URL, uuid5
+from unittest.mock import MagicMock
 
 import pytest
-from sqlalchemy.orm import Session
 
 from controllers.common.agent_app_parameters import get_published_agent_app_feature_dict_and_user_input_form
 from core.app.app_config.common.parameters_mapping import get_parameters_from_feature_dict
 from core.app.apps.agent_app.errors import AgentAppGeneratorError, AgentAppNotPublishedError
-from models.agent import Agent, AgentConfigSnapshot, AgentScope, AgentSource, AgentStatus
-from models.model import AppAnnotationSetting
 
 
-def _stable_uuid(value: str) -> str:
-    return str(uuid5(NAMESPACE_URL, value))
-
-
-def _app_model(*, tenant_id: str, bound_agent_id: str | None, app_model_config: object | None = None):
+def _app_model(*, bound_agent_id: str | None, app_model_config=None):
     return SimpleNamespace(
-        id=_stable_uuid(f"app:{tenant_id}"),
-        tenant_id=tenant_id,
+        id="app-1",
+        tenant_id="tenant-1",
         bound_agent_id=bound_agent_id,
         app_model_config_with_session=lambda *, session: app_model_config,
     )
 
 
-def _persist_agent(
-    session: Session,
-    *,
-    tenant_id: str,
-    agent_id: str,
-    active_config_snapshot_id: str | None,
-    active_config_is_published: bool,
-) -> Agent:
-    agent = Agent(
-        id=agent_id,
-        tenant_id=tenant_id,
-        name="Agent",
-        scope=AgentScope.ROSTER,
-        source=AgentSource.AGENT_APP,
-        status=AgentStatus.ACTIVE,
-        active_config_snapshot_id=active_config_snapshot_id,
-        active_config_is_published=active_config_is_published,
-    )
-    session.add(agent)
-    session.commit()
-    return agent
-
-
-def _persist_snapshot(
-    session: Session,
-    *,
-    snapshot_id: str,
-    tenant_id: str,
-    agent_id: str,
-    config_snapshot: dict[str, Any],
-) -> AgentConfigSnapshot:
-    snapshot = AgentConfigSnapshot(
-        id=snapshot_id,
-        tenant_id=tenant_id,
-        agent_id=agent_id,
-        version=1,
-        config_snapshot=config_snapshot,
-    )
-    session.add(snapshot)
-    session.commit()
-    return snapshot
-
-
-@pytest.mark.parametrize(
-    "sqlite_session",
-    [(Agent, AgentConfigSnapshot, AppAnnotationSetting)],
-    indirect=True,
-)
-def test_published_agent_app_parameters_use_soul_file_upload(sqlite_session: Session):
-    tenant_id = _stable_uuid("tenant:one")
-    agent_id = _stable_uuid("agent:one")
-    snapshot_id = _stable_uuid("snapshot:one")
+def test_published_agent_app_parameters_use_soul_file_upload():
     app_model_config = SimpleNamespace(
         to_dict=lambda **_kwargs: {
             "opening_statement": "Hi from legacy presentation config",
@@ -86,24 +27,14 @@ def test_published_agent_app_parameters_use_soul_file_upload(sqlite_session: Ses
             },
         }
     )
-    app_model = _app_model(
-        tenant_id=tenant_id,
-        bound_agent_id=agent_id,
-        app_model_config=app_model_config,
-    )
-    _persist_agent(
-        sqlite_session,
-        tenant_id=tenant_id,
-        agent_id=agent_id,
-        active_config_snapshot_id=snapshot_id,
+    app_model = _app_model(bound_agent_id="agent-1", app_model_config=app_model_config)
+    agent = SimpleNamespace(
+        id="agent-1",
+        active_config_snapshot_id="snapshot-1",
         active_config_is_published=True,
     )
-    _persist_snapshot(
-        sqlite_session,
-        snapshot_id=snapshot_id,
-        tenant_id=tenant_id,
-        agent_id=agent_id,
-        config_snapshot={
+    snapshot = SimpleNamespace(
+        config_snapshot_dict={
             "app_features": {
                 "file_upload": {
                     "enabled": True,
@@ -115,12 +46,14 @@ def test_published_agent_app_parameters_use_soul_file_upload(sqlite_session: Ses
                 }
             },
             "app_variables": [{"name": "topic", "type": "string", "required": True}],
-        },
+        }
     )
+    session = MagicMock()
+    session.scalar.side_effect = [agent, snapshot, None]
 
     features_dict, user_input_form = get_published_agent_app_feature_dict_and_user_input_form(
         app_model,
-        session=sqlite_session,
+        session=session,
     )
     parameters = get_parameters_from_feature_dict(features_dict=features_dict, user_input_form=user_input_form)
 
@@ -136,30 +69,20 @@ def test_published_agent_app_parameters_use_soul_file_upload(sqlite_session: Ses
     assert parameters["user_input_form"] == [{"text-input": {"label": "topic", "variable": "topic", "required": True}}]
 
 
-@pytest.mark.parametrize("sqlite_session", [(Agent, AgentConfigSnapshot)], indirect=True)
-def test_published_agent_app_parameters_requires_bound_agent(sqlite_session: Session):
-    tenant_id = _stable_uuid("tenant:unbound")
-    app_model = _app_model(tenant_id=tenant_id, bound_agent_id=None)
+def test_published_agent_app_parameters_requires_bound_agent():
+    app_model = _app_model(bound_agent_id=None)
 
     with pytest.raises(AgentAppGeneratorError, match="no bound Agent"):
-        get_published_agent_app_feature_dict_and_user_input_form(app_model, session=sqlite_session)
+        get_published_agent_app_feature_dict_and_user_input_form(app_model, session=MagicMock())
 
 
-@pytest.mark.parametrize("sqlite_session", [(Agent, AgentConfigSnapshot)], indirect=True)
-def test_published_agent_app_parameters_requires_existing_active_agent(sqlite_session: Session):
-    requested_tenant_id = _stable_uuid("tenant:requested")
-    agent_id = _stable_uuid("agent:cross-tenant")
-    app_model = _app_model(tenant_id=requested_tenant_id, bound_agent_id=agent_id)
-    _persist_agent(
-        sqlite_session,
-        tenant_id=_stable_uuid("tenant:other"),
-        agent_id=agent_id,
-        active_config_snapshot_id=None,
-        active_config_is_published=False,
-    )
+def test_published_agent_app_parameters_requires_existing_active_agent():
+    app_model = _app_model(bound_agent_id="agent-1")
+    session = MagicMock()
+    session.scalar.return_value = None
 
     with pytest.raises(AgentAppGeneratorError, match="no bound Agent"):
-        get_published_agent_app_feature_dict_and_user_input_form(app_model, session=sqlite_session)
+        get_published_agent_app_feature_dict_and_user_input_form(app_model, session=session)
 
 
 @pytest.mark.parametrize(
@@ -169,96 +92,68 @@ def test_published_agent_app_parameters_requires_existing_active_agent(sqlite_se
         False,
     ],
 )
-@pytest.mark.parametrize("sqlite_session", [(Agent, AgentConfigSnapshot)], indirect=True)
-def test_published_agent_app_parameters_requires_published_agent(
-    active_config_is_published: bool, sqlite_session: Session
-):
-    tenant_id = _stable_uuid(f"tenant:published:{active_config_is_published}")
-    agent_id = _stable_uuid(f"agent:published:{active_config_is_published}")
-    app_model = _app_model(tenant_id=tenant_id, bound_agent_id=agent_id)
-    _persist_agent(
-        sqlite_session,
-        tenant_id=tenant_id,
-        agent_id=agent_id,
+def test_published_agent_app_parameters_requires_published_agent(active_config_is_published):
+    app_model = _app_model(bound_agent_id="agent-1")
+    agent = SimpleNamespace(
+        id="agent-1",
         active_config_snapshot_id=None,
         active_config_is_published=active_config_is_published,
     )
+    session = MagicMock()
+    session.scalar.return_value = agent
 
     with pytest.raises(AgentAppNotPublishedError, match="not been published"):
-        get_published_agent_app_feature_dict_and_user_input_form(app_model, session=sqlite_session)
+        get_published_agent_app_feature_dict_and_user_input_form(app_model, session=session)
 
 
-@pytest.mark.parametrize("sqlite_session", [(Agent, AgentConfigSnapshot)], indirect=True)
-def test_published_agent_app_parameters_allows_unpublished_draft_with_active_snapshot(sqlite_session: Session):
-    tenant_id = _stable_uuid("tenant:unpublished-draft")
-    agent_id = _stable_uuid("agent:unpublished-draft")
-    snapshot_id = _stable_uuid("snapshot:unpublished-draft")
-    app_model = _app_model(tenant_id=tenant_id, bound_agent_id=agent_id)
-    _persist_agent(
-        sqlite_session,
-        tenant_id=tenant_id,
-        agent_id=agent_id,
-        active_config_snapshot_id=snapshot_id,
+def test_published_agent_app_parameters_allows_unpublished_draft_with_active_snapshot():
+    app_model = _app_model(bound_agent_id="agent-1")
+    agent = SimpleNamespace(
+        id="agent-1",
+        active_config_snapshot_id="snapshot-1",
         active_config_is_published=False,
     )
-    _persist_snapshot(
-        sqlite_session,
-        snapshot_id=snapshot_id,
-        tenant_id=tenant_id,
-        agent_id=agent_id,
-        config_snapshot={},
-    )
+    snapshot = SimpleNamespace(config_snapshot_dict={})
+    session = MagicMock()
+    session.scalar.side_effect = [agent, snapshot]
 
     features_dict, user_input_form = get_published_agent_app_feature_dict_and_user_input_form(
         app_model,
-        session=sqlite_session,
+        session=session,
     )
 
     assert features_dict["file_upload"]["enabled"] is True
     assert user_input_form == []
 
 
-@pytest.mark.parametrize("sqlite_session", [(Agent, AgentConfigSnapshot)], indirect=True)
-def test_published_agent_app_parameters_requires_published_snapshot(sqlite_session: Session):
-    tenant_id = _stable_uuid("tenant:missing-snapshot")
-    agent_id = _stable_uuid("agent:missing-snapshot")
-    app_model = _app_model(tenant_id=tenant_id, bound_agent_id=agent_id)
-    _persist_agent(
-        sqlite_session,
-        tenant_id=tenant_id,
-        agent_id=agent_id,
-        active_config_snapshot_id=_stable_uuid("snapshot:missing"),
+def test_published_agent_app_parameters_requires_published_snapshot():
+    app_model = _app_model(bound_agent_id="agent-1")
+    agent = SimpleNamespace(
+        id="agent-1",
+        active_config_snapshot_id="snapshot-1",
         active_config_is_published=True,
     )
+    session = MagicMock()
+    session.scalar.side_effect = [agent, None]
 
     with pytest.raises(AgentAppGeneratorError, match="published version not found"):
-        get_published_agent_app_feature_dict_and_user_input_form(app_model, session=sqlite_session)
+        get_published_agent_app_feature_dict_and_user_input_form(app_model, session=session)
 
 
-@pytest.mark.parametrize("sqlite_session", [(Agent, AgentConfigSnapshot)], indirect=True)
-def test_published_agent_app_parameters_allows_missing_legacy_app_model_config(sqlite_session: Session):
-    tenant_id = _stable_uuid("tenant:no-legacy-config")
-    agent_id = _stable_uuid("agent:no-legacy-config")
-    snapshot_id = _stable_uuid("snapshot:no-legacy-config")
-    app_model = _app_model(tenant_id=tenant_id, bound_agent_id=agent_id)
-    _persist_agent(
-        sqlite_session,
-        tenant_id=tenant_id,
-        agent_id=agent_id,
-        active_config_snapshot_id=snapshot_id,
+def test_published_agent_app_parameters_allows_missing_legacy_app_model_config():
+    app_model = _app_model(bound_agent_id="agent-1")
+    agent = SimpleNamespace(
+        id="agent-1",
+        active_config_snapshot_id="snapshot-1",
         active_config_is_published=True,
     )
-    _persist_snapshot(
-        sqlite_session,
-        snapshot_id=snapshot_id,
-        tenant_id=tenant_id,
-        agent_id=agent_id,
-        config_snapshot={},
-    )
+    snapshot = SimpleNamespace(config_snapshot_dict={})
+    session = MagicMock()
+    session.scalar.side_effect = [agent, snapshot]
 
     features_dict, user_input_form = get_published_agent_app_feature_dict_and_user_input_form(
         app_model,
-        session=sqlite_session,
+        session=session,
     )
 
     assert features_dict["file_upload"] == {

api/tests/unit_tests/controllers/console/app/test_app_apis.py

@@ -398,12 +398,6 @@ class TestWorkflowEndpoints:
     def test_workflow_copy_payload(self):
         payload = SyncDraftWorkflowPayload(graph={}, features={})
         assert payload.graph == {}
-        assert payload.model_dump()["is_collaborative"] is False
-
-    def test_workflow_sync_payload_accepts_collaboration_marker(self):
-        payload = SyncDraftWorkflowPayload.model_validate({"graph": {}, "features": {}, "_is_collaborative": True})
-        assert payload.is_collaborative is True
-        assert payload.model_dump()["is_collaborative"] is True
 
     def test_workflow_mode_query(self):
         payload = AdvancedChatWorkflowRunPayload(inputs={}, query="hi")

api/tests/unit_tests/controllers/console/app/test_app_import_api.py

@@ -2,23 +2,15 @@
 
 from __future__ import annotations
 
-from collections.abc import Iterator
-from dataclasses import dataclass
 from inspect import unwrap
+from types import SimpleNamespace
 from unittest.mock import MagicMock
 
 import pytest
 from flask import Flask
-from sqlalchemy import event
-from sqlalchemy.orm import Session
 
 from controllers.console.app import app_import as app_import_module
-from models.account import Account
-from models.engine import db
-from models.model import App
 from services.app_dsl_service import ImportStatus
-from services.entities.dsl_entities import CheckDependenciesResult
-from services.feature_service import SystemFeatureModel, WebAppAuthModel
 
 
 def _unwrap(func):
@@ -46,58 +38,17 @@ class _Result:
 
 
 def _install_features(monkeypatch: pytest.MonkeyPatch, enabled: bool) -> None:
-    features = SystemFeatureModel(webapp_auth=WebAppAuthModel(enabled=enabled))
+    features = SimpleNamespace(webapp_auth=SimpleNamespace(enabled=enabled))
     monkeypatch.setattr(app_import_module.FeatureService, "get_system_features", lambda: features)
 
 
-def _make_account(account_id: str = "u1") -> Account:
-    account = Account(name="Test User", email="test@example.com")
-    account.id = account_id
-    return account
-
-
-@pytest.fixture
-def app() -> Iterator[Flask]:
-    app = Flask(__name__)
-    app.config["SQLALCHEMY_DATABASE_URI"] = "sqlite:///:memory:"
-    db.init_app(app)
-
-    with app.app_context():
-        yield app
-
-
-@dataclass
-class TransactionEvents:
-    commits: int = 0
-    rollbacks: int = 0
-
-
-@pytest.fixture
-def transaction_events() -> TransactionEvents:
-    """Observe transaction decisions while keeping the controller on a real SQLAlchemy session."""
-
-    observed = TransactionEvents()
-
-    def record_commit(_session: Session) -> None:
-        observed.commits += 1
-
-    def record_rollback(_session: Session) -> None:
-        observed.rollbacks += 1
-
-    event.listen(Session, "after_commit", record_commit)
-    event.listen(Session, "after_rollback", record_rollback)
-    try:
-        yield observed
-    finally:
-        event.remove(Session, "after_commit", record_commit)
-        event.remove(Session, "after_rollback", record_rollback)
-
-
-def _failed_result_after_starting_transaction(
-    service: app_import_module.AppDslService, *, app_id: str | None = None
-) -> _Result:
-    service._session.begin()
-    return _Result(ImportStatus.FAILED, app_id=app_id)
+def _mock_session(monkeypatch: pytest.MonkeyPatch) -> MagicMock:
+    fake_session = MagicMock()
+    fake_session.__enter__.return_value = fake_session
+    fake_session.__exit__.return_value = None
+    monkeypatch.setattr(app_import_module, "db", SimpleNamespace(engine=object()))
+    monkeypatch.setattr(app_import_module, "Session", lambda *_args, **_kwargs: fake_session)
+    return fake_session
 
 
 class TestAppImportApi:
@@ -106,39 +57,33 @@ class TestAppImportApi:
         return app_import_module.AppImportApi()
 
     def test_import_post_returns_failed_status_and_rolls_back(
-        self,
-        api,
-        app: Flask,
-        monkeypatch: pytest.MonkeyPatch,
-        transaction_events: TransactionEvents,
+        self, api, app: Flask, monkeypatch: pytest.MonkeyPatch
     ) -> None:
         method = unwrap(api.post)
 
         _install_features(monkeypatch, enabled=False)
+        session = _mock_session(monkeypatch)
         monkeypatch.setattr(
             app_import_module.AppDslService,
             "import_app",
-            lambda service, *_args, **_kwargs: _failed_result_after_starting_transaction(service, app_id=None),
+            lambda *_args, **_kwargs: _Result(ImportStatus.FAILED, app_id=None),
         )
 
         with app.test_request_context("/console/api/apps/imports", method="POST", json={"mode": "yaml-content"}):
-            response, status = method(api, _make_account())
+            response, status = method(api, SimpleNamespace(id="u1"))
 
-        assert transaction_events.rollbacks == 1
-        assert transaction_events.commits == 0
+        session.rollback.assert_called_once_with()
+        session.commit.assert_not_called()
         assert status == 400
         assert response["status"] == ImportStatus.FAILED
 
     def test_import_post_returns_pending_status_and_commits(
-        self,
-        api,
-        app: Flask,
-        monkeypatch: pytest.MonkeyPatch,
-        transaction_events: TransactionEvents,
+        self, api, app: Flask, monkeypatch: pytest.MonkeyPatch
     ) -> None:
         method = unwrap(api.post)
 
         _install_features(monkeypatch, enabled=False)
+        session = _mock_session(monkeypatch)
         monkeypatch.setattr(
             app_import_module.AppDslService,
             "import_app",
@@ -146,23 +91,20 @@ class TestAppImportApi:
         )
 
         with app.test_request_context("/console/api/apps/imports", method="POST", json={"mode": "yaml-content"}):
-            response, status = method(api, _make_account())
+            response, status = method(api, SimpleNamespace(id="u1"))
 
-        assert transaction_events.commits == 1
-        assert transaction_events.rollbacks == 0
+        session.commit.assert_called_once_with()
+        session.rollback.assert_not_called()
         assert status == 202
         assert response["status"] == ImportStatus.PENDING
 
     def test_import_post_updates_webapp_auth_when_enabled(
-        self,
-        api,
-        app: Flask,
-        monkeypatch: pytest.MonkeyPatch,
-        transaction_events: TransactionEvents,
+        self, api, app: Flask, monkeypatch: pytest.MonkeyPatch
     ) -> None:
         method = unwrap(api.post)
 
         _install_features(monkeypatch, enabled=True)
+        session = _mock_session(monkeypatch)
         monkeypatch.setattr(
             app_import_module.AppDslService,
             "import_app",
@@ -172,28 +114,25 @@ class TestAppImportApi:
         monkeypatch.setattr(app_import_module.EnterpriseService.WebAppAuth, "update_app_access_mode", update_access)
 
         with app.test_request_context("/console/api/apps/imports", method="POST", json={"mode": "yaml-content"}):
-            response, status = method(api, _make_account())
+            response, status = method(api, SimpleNamespace(id="u1"))
 
-        assert transaction_events.commits == 1
-        assert transaction_events.rollbacks == 0
+        session.commit.assert_called_once_with()
+        session.rollback.assert_not_called()
         update_access.assert_called_once_with("app-123", "private")
         assert status == 200
         assert response["status"] == ImportStatus.COMPLETED
 
     def test_import_post_attaches_permission_keys_when_creating_new_app_and_rbac_enabled(
-        self,
-        api,
-        app: Flask,
-        monkeypatch: pytest.MonkeyPatch,
-        transaction_events: TransactionEvents,
+        self, api, app: Flask, monkeypatch: pytest.MonkeyPatch
     ) -> None:
         method = _unwrap(api.post)
 
         _install_features(monkeypatch, enabled=False)
+        session = _mock_session(monkeypatch)
         monkeypatch.setattr(
             app_import_module,
             "current_account_with_tenant",
-            lambda: (_make_account(), "tenant-1"),
+            lambda: (SimpleNamespace(id="u1"), "tenant-1"),
         )
         monkeypatch.setattr(app_import_module.dify_config, "RBAC_ENABLED", True)
         monkeypatch.setattr(
@@ -210,24 +149,21 @@ class TestAppImportApi:
         with app.test_request_context("/console/api/apps/imports", method="POST", json={"mode": "yaml-content"}):
             response, status = method()
 
-        assert transaction_events.commits == 1
+        session.commit.assert_called_once_with()
         assert status == 200
         assert response["permission_keys"] == ["app.acl.view_layout", "app.acl.edit"]
 
     def test_import_post_does_not_attach_permission_keys_when_overwriting_existing_app(
-        self,
-        api,
-        app: Flask,
-        monkeypatch: pytest.MonkeyPatch,
-        transaction_events: TransactionEvents,
+        self, api, app: Flask, monkeypatch: pytest.MonkeyPatch
     ) -> None:
         method = _unwrap(api.post)
 
         _install_features(monkeypatch, enabled=False)
+        session = _mock_session(monkeypatch)
         monkeypatch.setattr(
             app_import_module,
             "current_account_with_tenant",
-            lambda: (_make_account(), "tenant-1"),
+            lambda: (SimpleNamespace(id="u1"), "tenant-1"),
         )
         monkeypatch.setattr(app_import_module.dify_config, "RBAC_ENABLED", True)
         monkeypatch.setattr(
@@ -248,7 +184,7 @@ class TestAppImportApi:
         ):
             response, status = method()
 
-        assert transaction_events.commits == 1
+        session.commit.assert_called_once_with()
         assert status == 200
         assert response["permission_keys"] == []
 
@@ -259,41 +195,35 @@ class TestAppImportConfirmApi:
         return app_import_module.AppImportConfirmApi()
 
     def test_import_confirm_returns_failed_status_and_rolls_back(
-        self,
-        api,
-        app: Flask,
-        monkeypatch: pytest.MonkeyPatch,
-        transaction_events: TransactionEvents,
+        self, api, app: Flask, monkeypatch: pytest.MonkeyPatch
     ) -> None:
         method = unwrap(api.post)
 
+        session = _mock_session(monkeypatch)
         monkeypatch.setattr(
             app_import_module.AppDslService,
             "confirm_import",
-            lambda service, *_args, **_kwargs: _failed_result_after_starting_transaction(service),
+            lambda *_args, **_kwargs: _Result(ImportStatus.FAILED),
         )
 
         with app.test_request_context("/console/api/apps/imports/import-1/confirm", method="POST"):
-            response, status = method(api, _make_account(), import_id="import-1")
+            response, status = method(api, SimpleNamespace(id="u1"), import_id="import-1")
 
-        assert transaction_events.rollbacks == 1
-        assert transaction_events.commits == 0
+        session.rollback.assert_called_once_with()
+        session.commit.assert_not_called()
         assert status == 400
         assert response["status"] == ImportStatus.FAILED
 
     def test_import_confirm_attaches_permission_keys_when_creating_new_app_and_rbac_enabled(
-        self,
-        api,
-        app: Flask,
-        monkeypatch: pytest.MonkeyPatch,
-        transaction_events: TransactionEvents,
+        self, api, app: Flask, monkeypatch: pytest.MonkeyPatch
     ) -> None:
         method = _unwrap(api.post)
 
+        session = _mock_session(monkeypatch)
         monkeypatch.setattr(
             app_import_module,
             "current_account_with_tenant",
-            lambda: (_make_account(), "tenant-1"),
+            lambda: (SimpleNamespace(id="u1"), "tenant-1"),
         )
         monkeypatch.setattr(
             app_import_module.redis_client,
@@ -318,23 +248,20 @@ class TestAppImportConfirmApi:
         with app.test_request_context("/console/api/apps/imports/import-1/confirm", method="POST"):
             response, status = method(import_id="import-1")
 
-        assert transaction_events.commits == 1
+        session.commit.assert_called_once_with()
         assert status == 200
         assert response["permission_keys"] == ["app.acl.view_layout", "app.acl.edit"]
 
     def test_import_confirm_does_not_attach_permission_keys_when_overwriting_existing_app(
-        self,
-        api,
-        app: Flask,
-        monkeypatch: pytest.MonkeyPatch,
-        transaction_events: TransactionEvents,
+        self, api, app: Flask, monkeypatch: pytest.MonkeyPatch
     ) -> None:
         method = _unwrap(api.post)
 
+        session = _mock_session(monkeypatch)
         monkeypatch.setattr(
             app_import_module,
             "current_account_with_tenant",
-            lambda: (_make_account(), "tenant-1"),
+            lambda: (SimpleNamespace(id="u1"), "tenant-1"),
         )
         monkeypatch.setattr(
             app_import_module.redis_client,
@@ -359,27 +286,6 @@ class TestAppImportConfirmApi:
         with app.test_request_context("/console/api/apps/imports/import-1/confirm", method="POST"):
             response, status = method(import_id="import-1")
 
-        assert transaction_events.commits == 1
+        session.commit.assert_called_once_with()
         assert status == 200
         assert response["permission_keys"] == []
-
-
-class TestAppImportCheckDependenciesApi:
-    def test_import_check_dependencies_returns_result(
-        self,
-        app: Flask,
-        monkeypatch: pytest.MonkeyPatch,
-    ) -> None:
-        api = app_import_module.AppImportCheckDependenciesApi()
-        method = unwrap(api.get)
-        monkeypatch.setattr(
-            app_import_module.AppDslService,
-            "check_dependencies",
-            lambda *_args, **_kwargs: CheckDependenciesResult(leaked_dependencies=[]),
-        )
-
-        with app.test_request_context("/console/api/apps/imports/app-1/check-dependencies", method="GET"):
-            response, status = method(api, app_model=App(id="app-1"))
-
-        assert status == 200
-        assert response["leaked_dependencies"] == []

api/tests/unit_tests/controllers/console/app/test_generator_api.py

@@ -7,28 +7,10 @@ from unittest.mock import MagicMock
 
 import pytest
 from flask import Flask
-from sqlalchemy.orm import Session
 
 from controllers.console.app import generator as generator_module
 from controllers.console.app.error import ProviderNotInitializeError
 from core.errors.error import ProviderTokenNotInitError
-from models.model import App, AppMode
-
-
-def _persist_app(session: Session, *, tenant_id: str = "t1") -> App:
-    app_model = App(
-        id="app-1",
-        tenant_id=tenant_id,
-        name="Workflow App",
-        description="",
-        mode=AppMode.WORKFLOW,
-        enable_site=False,
-        enable_api=False,
-        max_active_requests=None,
-    )
-    session.add(app_model)
-    session.commit()
-    return app_model
 
 
 def _model_config_payload():
@@ -84,11 +66,12 @@ def test_rule_code_generate_maps_token_error(app: Flask, monkeypatch: pytest.Mon
             method(api, "t1")
 
 
-@pytest.mark.parametrize("sqlite_session", [(App,)], indirect=True)
-def test_instruction_generate_app_not_found(app: Flask, sqlite_session: Session) -> None:
+def test_instruction_generate_app_not_found(app: Flask, monkeypatch: pytest.MonkeyPatch) -> None:
     api = generator_module.InstructionGenerateApi()
     method = unwrap(api.post)
-    _persist_app(sqlite_session, tenant_id="other-tenant")
+
+    session = MagicMock()
+    session.scalar.return_value = None
 
     with app.test_request_context(
         "/console/api/instruction-generate",
@@ -100,21 +83,25 @@ def test_instruction_generate_app_not_found(app: Flask, sqlite_session: Session)
             "model_config": _model_config_payload(),
         },
     ):
-        response, status = method(api, sqlite_session, "t1")
+        response, status = method(api, session, "t1")
 
     assert status == 400
     assert response["error"] == "app app-1 not found"
-    assert sqlite_session.get(App, "app-1") is not None
+    stmt = session.scalar.call_args.args[0]
+    compiled = stmt.compile()
+    statement = str(compiled)
+    assert "apps.id" in statement
+    assert "apps.tenant_id" in statement
+    assert "app-1" in compiled.params.values()
+    assert "t1" in compiled.params.values()
 
 
-@pytest.mark.parametrize("sqlite_session", [(App,)], indirect=True)
-def test_instruction_generate_workflow_not_found(
-    app: Flask, monkeypatch: pytest.MonkeyPatch, sqlite_session: Session
-) -> None:
+def test_instruction_generate_workflow_not_found(app: Flask, monkeypatch: pytest.MonkeyPatch) -> None:
     api = generator_module.InstructionGenerateApi()
     method = unwrap(api.post)
 
-    app_model = _persist_app(sqlite_session)
+    app_model = SimpleNamespace(id="app-1")
+    session = SimpleNamespace(scalar=lambda *_args, **_kwargs: app_model)
     _install_workflow_service(monkeypatch, workflow=None)
 
     with app.test_request_context(
@@ -127,20 +114,18 @@ def test_instruction_generate_workflow_not_found(
             "model_config": _model_config_payload(),
         },
     ):
-        response, status = method(api, sqlite_session, "t1")
+        response, status = method(api, session, "t1")
 
     assert status == 400
     assert response["error"] == "workflow app-1 not found"
 
 
-@pytest.mark.parametrize("sqlite_session", [(App,)], indirect=True)
-def test_instruction_generate_node_missing(
-    app: Flask, monkeypatch: pytest.MonkeyPatch, sqlite_session: Session
-) -> None:
+def test_instruction_generate_node_missing(app: Flask, monkeypatch: pytest.MonkeyPatch) -> None:
     api = generator_module.InstructionGenerateApi()
     method = unwrap(api.post)
 
-    app_model = _persist_app(sqlite_session)
+    app_model = SimpleNamespace(id="app-1")
+    session = SimpleNamespace(scalar=lambda *_args, **_kwargs: app_model)
 
     workflow = SimpleNamespace(graph_dict={"nodes": []})
     _install_workflow_service(monkeypatch, workflow=workflow)
@@ -155,18 +140,18 @@ def test_instruction_generate_node_missing(
             "model_config": _model_config_payload(),
         },
     ):
-        response, status = method(api, sqlite_session, "t1")
+        response, status = method(api, session, "t1")
 
     assert status == 400
     assert response["error"] == "node node-1 not found"
 
 
-@pytest.mark.parametrize("sqlite_session", [(App,)], indirect=True)
-def test_instruction_generate_code_node(app: Flask, monkeypatch: pytest.MonkeyPatch, sqlite_session: Session) -> None:
+def test_instruction_generate_code_node(app: Flask, monkeypatch: pytest.MonkeyPatch) -> None:
     api = generator_module.InstructionGenerateApi()
     method = unwrap(api.post)
 
-    app_model = _persist_app(sqlite_session)
+    app_model = SimpleNamespace(id="app-1")
+    session = SimpleNamespace(scalar=lambda *_args, **_kwargs: app_model)
 
     workflow = SimpleNamespace(
         graph_dict={
@@ -188,19 +173,18 @@ def test_instruction_generate_code_node(app: Flask, monkeypatch: pytest.MonkeyPa
             "model_config": _model_config_payload(),
         },
     ):
-        response = method(api, sqlite_session, "t1")
+        response = method(api, session, "t1")
 
     assert response == {"code": "x"}
     assert workflow_service.app_model is app_model
-    assert workflow_service.session is sqlite_session
+    assert workflow_service.session is session
 
 
-@pytest.mark.parametrize("sqlite_session", [(App,)], indirect=True)
-def test_instruction_generate_legacy_modify(
-    app: Flask, monkeypatch: pytest.MonkeyPatch, sqlite_session: Session
-) -> None:
+def test_instruction_generate_legacy_modify(app: Flask, monkeypatch: pytest.MonkeyPatch) -> None:
     api = generator_module.InstructionGenerateApi()
     method = unwrap(api.post)
+    session = SimpleNamespace()
+
     monkeypatch.setattr(
         generator_module.LLMGenerator,
         "instruction_modify_legacy",
@@ -218,15 +202,16 @@ def test_instruction_generate_legacy_modify(
             "model_config": _model_config_payload(),
         },
     ):
-        response = method(api, sqlite_session, "t1")
+        response = method(api, session, "t1")
 
     assert response == {"instruction": "ok"}
 
 
-@pytest.mark.parametrize("sqlite_session", [(App,)], indirect=True)
-def test_instruction_generate_incompatible_params(app: Flask, sqlite_session: Session) -> None:
+def test_instruction_generate_incompatible_params(app: Flask, monkeypatch: pytest.MonkeyPatch) -> None:
     api = generator_module.InstructionGenerateApi()
     method = unwrap(api.post)
+    session = SimpleNamespace()
+
     with app.test_request_context(
         "/console/api/instruction-generate",
         method="POST",
@@ -238,7 +223,7 @@ def test_instruction_generate_incompatible_params(app: Flask, sqlite_session: Se
             "model_config": _model_config_payload(),
         },
     ):
-        response, status = method(api, sqlite_session, "t1")
+        response, status = method(api, session, "t1")
 
     assert status == 400
     assert response["error"] == "incompatible parameters"

api/tests/unit_tests/controllers/console/datasets/rag_pipeline/test_rag_pipeline.py

@@ -2,7 +2,6 @@ from __future__ import annotations
 
 from collections.abc import Iterator
 from inspect import unwrap
-from types import SimpleNamespace
 from unittest.mock import PropertyMock, patch
 
 import pytest
@@ -276,9 +275,9 @@ class TestCustomizedPipelineTemplateApi:
         assert (response, status) == ("", 204)
         assert deleted_templates == [("template-1", tenant_id)]
 
-    @pytest.mark.parametrize("sqlite_session", [(PipelineCustomizedTemplate,)], indirect=True)
     def test_post_exports_yaml_from_orm_template(
-        self, app: Flask, monkeypatch: pytest.MonkeyPatch, sqlite_engine: Engine, sqlite_session: Session
+        self,
+        database_app: Flask,
     ) -> None:
         api = CustomizedPipelineTemplateApi()
         method = unwrap(api.post)
@@ -294,29 +293,26 @@ class TestCustomizedPipelineTemplateApi:
             language="en-US",
             created_by="00000000-0000-0000-0000-000000000002",
         )
-        template.id = "template-1"
-        sqlite_session.add(template)
-        sqlite_session.commit()
-        monkeypatch.setattr(module, "db", SimpleNamespace(engine=sqlite_engine))
+        db.session.add(template)
+        db.session.commit()
 
-        with app.test_request_context("/rag/pipeline/customized/templates/template-1", method="POST"):
-            response, status = method(api, "template-1")
+        with database_app.test_request_context("/rag/pipeline/customized/templates/template-1", method="POST"):
+            response, status = method(api, template.id)
 
         assert status == 200
         assert response == {"data": "dsl: value"}
 
-    @pytest.mark.parametrize("sqlite_session", [(PipelineCustomizedTemplate,)], indirect=True)
     def test_post_raises_when_template_is_missing(
-        self, app: Flask, monkeypatch: pytest.MonkeyPatch, sqlite_engine: Engine, sqlite_session: Session
+        self,
+        database_app: Flask,
     ) -> None:
         api = CustomizedPipelineTemplateApi()
         method = unwrap(api.post)
-        assert sqlite_session.get(PipelineCustomizedTemplate, "missing") is None
-        monkeypatch.setattr(module, "db", SimpleNamespace(engine=sqlite_engine))
-
-        with app.test_request_context("/rag/pipeline/customized/templates/missing", method="POST"):
-            with pytest.raises(ValueError, match="Customized pipeline template not found"):
-                method(api, "missing")
+        with (
+            database_app.test_request_context("/rag/pipeline/customized/templates/missing", method="POST"),
+            pytest.raises(ValueError, match="Customized pipeline template not found"),
+        ):
+            method(api, "44444444-4444-4444-4444-444444444444")
 
 
 class TestPublishCustomizedPipelineTemplateApi: