opensource/dify
2
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-08-29 11:49:06 +08:00
Code Issues Packages Projects Releases Wiki Activity
9,927 Commits 815 Branches 177 Tags 1.2 GiB
edfcab6455
Commit Graph

969 Commits

Author SHA1 Message Date
Yansong Zhang
edfcab6455 fix(api): add AGENT mode to app list filtering 
Add AppMode.AGENT branch in get_paginate_apps() so that
filtering apps by mode=agent works correctly.
Discovered during comprehensive E2E testing.

14/14 E2E tests pass covering:
- A: New Agent app full lifecycle (create, draft, configs, publish, run)
- B: Old app creation compat (chat, completion, agent-chat, advanced-chat, workflow)
- C: App listing and filtering (all modes, agent filter)
- D: Workflow editor compat (block configs)
- E: DSL export

Made-with: Cursor
 2026-04-09 10:54:05 +08:00
Yansong Zhang
66212e3575 feat(api): implement zero-migration transparent upgrade (Phase 8) 
Add two feature-flag-controlled upgrade paths that allow existing apps
and LLM nodes to transparently run through the Agent V2 engine without
any database migration:

1. AGENT_V2_TRANSPARENT_UPGRADE (default: off):
   When enabled, old apps (chat/completion/agent-chat) bypass legacy
   Easy-UI runners. VirtualWorkflowSynthesizer converts AppModelConfig
   to an in-memory Workflow (start -> agent-v2 -> answer) at runtime,
   then executes via AdvancedChatAppGenerator. Falls back to legacy
   path on any synthesis error.

   VirtualWorkflowSynthesizer maps:
   - model JSON -> ModelConfig
   - pre_prompt/chat_prompt_config -> prompt_template
   - agent_mode.tools -> ToolMetadata[]
   - agent_mode.strategy -> agent_strategy
   - dataset_configs -> context
   - file_upload -> vision

2. AGENT_V2_REPLACES_LLM (default: off):
   When enabled, DifyNodeFactory.create_node() transparently remaps
   nodes with type="llm" to type="agent-v2" before class resolution.
   Since AgentV2NodeData is a strict superset of LLMNodeData, the
   mapping is lossless. With tools=[], Agent V2 behaves identically
   to LLM Node.

Both flags default to False for safety. Turn off = instant rollback.
46 existing tests pass. Flask starts successfully.

Made-with: Cursor
 2026-04-09 10:30:52 +08:00
Yansong Zhang
44491e427c feat(api): enable all sandbox/skill controller routes and resolve dependencies (P0) 
Resolve the full dependency chain to enable all previously disabled controllers:

Enabled routes:
- sandbox_files: sandbox file browser API
- sandbox_providers: sandbox provider management API
- app_asset: app asset management API
- skills: skill extraction API
- CLI API blueprint: DifyCli callback endpoints (/cli/api/*)

Dependencies extracted (64 files, ~8000 lines):
- models/sandbox.py, models/app_asset.py: DB models
- core/zip_sandbox/: zip-based sandbox execution
- core/session/: CLI API session management
- core/memory/: base memory + node token buffer
- core/helper/creators.py: helper utilities
- core/llm_generator/: context models, output models, utils
- core/workflow/nodes/command/: command node type
- core/workflow/nodes/file_upload/: file upload node type
- core/app/entities/: app_asset_entities, app_bundle_entities, llm_generation_entities
- services/: asset_content, skill, workflow_collaboration, workflow_comment
- controllers/console/app/error.py: AppAsset error classes
- core/tools/utils/system_encryption.py

Import fixes:
- dify_graph.enums -> graphon.enums in skill_service.py
- get_signed_file_url_for_plugin -> get_signed_file_url in cli_api.py

All 5 controllers verified: import OK, Flask starts successfully.
46 existing tests still pass.

Made-with: Cursor
 2026-04-09 09:36:16 +08:00
Yansong Zhang
0c7e7e0c4e feat(api): port Sandbox + VirtualEnvironment + Skill system from feat/support-agent-sandbox (Phase 5-6) 
Port the complete infrastructure for agent sandbox execution and skill system:

Sandbox & Virtual Environment (core/sandbox/, core/virtual_environment/):
- Sandbox entity with lifecycle management (ready/failed/cancelled states)
- SandboxBuilder with fluent API for configuring providers
- 5 VM providers: Local, SSH, Docker, E2B, AWS CodeInterpreter
- VirtualEnvironment base with command execution, file transfer, transport layers
- Channel transport: pipe, queue, socket implementations
- Bash session management and DifyCli binary integration
- Storage: archive storage, file storage, noop storage, presign storage
- Initializers: DifyCli, AppAssets, DraftAppAssets, Skills
- Inspector: file browser, archive/runtime source, script utils
- Security: encryption utils, debug helpers

Skill & App Assets (core/skill/, core/app_assets/, core/app_bundle/):
- Skill entity and manager
- App asset accessor, builder pipeline (file, skill builders)
- App bundle source zip extractor
- Storage and converter utilities

API Endpoints:
- CLI API blueprint (controllers/cli_api/) for sandbox callback
- Sandbox provider management (workspace/sandbox_providers)
- Sandbox file browser (console/sandbox_files)
- App asset management (console/app/app_asset)
- Skill management (console/app/skills)
- Storage file endpoints (controllers/files/storage_files)

Services:
- Sandbox service, provider service, file service
- App asset service, app bundle service

Config:
- CliApiConfig, CreatorsPlatformConfig, CollaborationConfig
- FILES_API_URL for sandbox file access

Note: Controller route registration temporarily commented out (marked TODO)
pending resolution of deep dependency chains (socketio, workflow_comment,
command node, etc.). Core sandbox modules are fully ported and syntax-validated.
110 files changed, 10,549 insertions.

Made-with: Cursor
 2026-04-08 17:39:02 +08:00
Yansong Zhang
d9d1e9b63a fix(api): resolve Agent V2 node E2E runtime issues 
Fixes discovered during end-to-end testing of Agent workflow execution:

1. ModelManager instantiation: use ModelManager.for_tenant() instead of
   ModelManager() which requires a ProviderManager argument
2. Variable template resolution: use VariableTemplateParser(template).format()
   instead of non-existent resolve_template() static method
3. invoke_llm() signature: remove unsupported 'user' keyword argument
4. Event dispatch: remove ModelInvokeCompletedEvent from _run() yield
   (graphon base Node._dispatch doesn't support it via singledispatch)
5. NodeRunResult metadata: use WorkflowNodeExecutionMetadataKey enum keys
   (TOTAL_TOKENS, TOTAL_PRICE, CURRENCY) instead of arbitrary string keys
6. SSE topic mismatch: use AppMode.AGENT (not ADVANCED_CHAT) in
   retrieve_events() so publisher and subscriber share the same channel
7. Celery task routing: add AppMode.AGENT to workflow_execute_task._run_app()
   alongside ADVANCED_CHAT

All issues verified fixed: Agent V2 node successfully invokes LLM and
returns "Hello there!" through the full SSE streaming pipeline.

Made-with: Cursor
 2026-04-08 16:21:12 +08:00
Yansong Zhang
1835a1dc5d fix(api): allow AGENT mode in workflow features validation 
Add AppMode.AGENT to validate_features_structure() match case
alongside ADVANCED_CHAT, fixing 'Invalid app mode: agent' error
when creating Agent apps (which auto-generate a workflow draft).

Discovered during E2E testing of the full create -> draft -> publish flow.

Made-with: Cursor
 2026-04-08 13:19:59 +08:00
Yansong Zhang
96641a93f6 feat(api): add Agent V2 node and new Agent app type (Phase 1-3) 
Introduce a new unified Agent V2 workflow node that combines LLM capabilities
with agent tool-calling loops, along with a new AppMode.AGENT for standalone
agent apps backed by single-node workflows.

Phase 1 — Agent Patterns:
- Add core/agent/patterns/ module (AgentPattern, FunctionCallStrategy,
  ReActStrategy, StrategyFactory) ported from feat/support-agent-sandbox
- Add ExecutionContext, AgentLog, AgentResult entities
- Add Tool.to_prompt_message_tool() for LLM-consumable tool conversion

Phase 2 — Agent V2 Workflow Node:
- Add core/workflow/nodes/agent_v2/ (AgentV2Node, AgentV2NodeData,
  AgentV2ToolManager, AgentV2EventAdapter)
- Register agent-v2 node type in DifyNodeFactory
- No-tools path: single LLM call (LLM Node equivalent)
- Tools path: FC/ReAct loop via StrategyFactory

Phase 3 — Agent App Type:
- Add AppMode.AGENT to model enum
- Add WorkflowGraphFactory for auto-generating start->agent_v2->answer graphs
- AppService.create_app() creates workflow draft for AGENT mode
- AppGenerateService.generate() routes AGENT to AdvancedChatAppGenerator
- Console API and DSL import/export support AGENT mode
- Default app template for AGENT mode

Old agent/agent-chat/LLM node paths are fully preserved.
38 unit tests all passing.

Made-with: Cursor
 2026-04-08 12:31:23 +08:00
corevibe555
c825d5dcf6
refactor(api): tighten types for Tenant.custom_config_dict and MCPToolProvider.headers (#34698) 2026-04-08 01:36:42 +00:00
corevibe555
624db69f12
refactor(api): remove duplicated RAG entities from services layer (#34689) 2026-04-07 23:36:59 +00:00
corevibe555
80a7843f45
refactor(api): migrate consumers to shared RAG domain entities from core/rag/entities/ (#34692) 2026-04-07 23:22:56 +00:00
corevibe555
f8f7b0ec1a
refactor(api): deduplicate shared auth request payloads into auth_entities.py (#34694) 2026-04-07 22:51:11 +00:00
Dream
89ce61cfea
refactor(api): replace json.loads with Pydantic validation in security and tools layers (#34380) 2026-04-07 12:11:51 +00:00
Statxc
63db9a7a2f
refactor(api): type load balancing config dicts with TypedDict (#34639) 2026-04-07 05:58:10 +00:00
YBoy
1261e5e5e8
refactor(api): type webhook validation result and workflow inputs with TypedDict (#34645) 2026-04-07 05:57:02 +00:00
Pulakesh
bceb0eee9b
refactor(api): migrate dict returns to TypedDicts in billing service (#34649) 2026-04-07 05:56:02 +00:00
Renzo
1194957fde
refactor: migrate session.query to select API in end_user_service and small tasks (#34620) 2026-04-07 04:25:55 +00:00
Renzo
68bd29eda2
refactor: migrate session.query to select API in sync task and services (#34619) 2026-04-07 04:23:14 +00:00
YBoy
f67a811f7f
refactor: replace dict params with BaseModel payloads in TagService (#34422) 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
 2026-04-07 04:20:02 +00:00
Statxc
a7b6307d32
refactor(api): type dataset service dicts with TypedDict (#34625) 2026-04-07 02:10:52 +00:00
Statxc
2883ad6764
refactor(api): type plugin migration results with TypedDict (#34627) 2026-04-07 02:10:23 +00:00
Pulakesh
0feff5b048
refactor(api): enforce strict typing on retrieval_model to resolve FIXME (#34614) 2026-04-07 01:10:53 +00:00
YBoy
89e23456f0
refactor(api): type invitation detail with InvitationDetailDict TypedDict (#34613) 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
 2026-04-07 01:03:31 +00:00
YBoy
922f9242e4
refactor(api): type crawl status dicts with CrawlStatusDict TypedDict (#34611) 2026-04-07 01:01:04 +00:00
YBoy
7fc0a791a2
refactor(api): type document summary status detail with TypedDict (#34610) 2026-04-07 01:00:39 +00:00
YBoy
5ad906ea6a
refactor(api): type workflow run related counts with RelatedCountsDict TypedDict (#34530) 2026-04-06 13:17:01 +00:00
YBoy
1e5cd69205
refactor(api): type archive manifest with ArchiveManifestDict TypedDict (#34594) 2026-04-06 11:35:11 +00:00
YBoy
b71b9f80b9
refactor(api): type workflow run delete/count results with RunsWithRelatedCountsDict TypedDict (#34531) 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
 2026-04-05 16:11:41 +00:00
agenthaulk
ee87289917
refactor: convert AppMode if/elif to match/case in app_generate_service (#30001) (#34563) 
Co-authored-by: agenthaulk <agenthaulk@users.noreply.github.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
 2026-04-05 10:23:51 +00:00
agenthaulk
5ad8c3e249
refactor: convert AppMode if/elif to match/case in service files (#30001) (#34562) 
Co-authored-by: agenthaulk <agenthaulk@users.noreply.github.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
 2026-04-05 10:22:11 +00:00
Renzo
eca0cdc7a9
refactor: select in dataset_service (SegmentService and remaining cla… (#34547) 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
 2026-04-05 00:13:06 +00:00
Renzo
779e6b8e0b
refactor: select in datasource_provider_service (#34548) 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
 2026-04-05 00:12:15 +00:00
Renzo
c2428361c4
refactor: select in dataset_service (DocumentService class) (#34528) 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
 2026-04-03 22:52:01 +00:00
Renzo
68e4d13f36
refactor: select in annotation_service (#34503) 
Co-authored-by: Asuka Minato <i@asukaminato.eu.org>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
 2026-04-03 22:47:22 +00:00
YBoy
8a398f3105
refactor(api): type messages cleanup stats with MessagesCleanStatsDict TypedDict (#34527) 2026-04-03 12:29:41 +00:00
Renzo
e85d9a0d72
refactor: select in dataset_service (DatasetService class) (#34525) 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
 2026-04-03 12:01:31 +00:00
Renzo
06dde4f503
refactor: select in account_service (TenantService class) (#34499) 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Asuka Minato <i@asukaminato.eu.org>
 2026-04-03 11:03:45 +00:00
YBoy
64ddec0d67
refactor(api): type annotation service dicts with TypedDict (#34482) 
Co-authored-by: Asuka Minato <i@asukaminato.eu.org>
 2026-04-03 06:25:52 +00:00
Renzo
da3b0caf5e
refactor: select in account_service (RegisterService class) (#34500) 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
 2026-04-03 06:21:26 +00:00
Renzo
608958de1c
refactor: select in external_knowledge_service (#34493) 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
 2026-04-03 03:42:16 +00:00
Renzo
7eb632eb34
refactor: select in rag_pipeline (#34495) 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
 2026-04-03 03:42:01 +00:00
Renzo
33d4fd357c
refactor: select in account_service (AccountService class) (#34496) 2026-04-03 03:41:46 +00:00
YBoy
71d299d0d3
refactor(api): type hit testing retrieve responses with TypedDict (#34484) 2026-04-03 02:25:30 +00:00
YBoy
9a6222f245
refactor(api): type webhook data extraction with RawWebhookDataDict TypedDict (#34486) 2026-04-03 02:24:17 +00:00
YBoy
affe5ed30b
refactor(api): type get_knowledge_rate_limit with KnowledgeRateLimitD… (#34483) 2026-04-03 02:23:32 +00:00
Renzo
dbfb474eab
refactor: select in workflow_tools_manage_service (#34477) 2026-04-02 12:35:04 +00:00
Renzo
d243de26ec
refactor: select in metadata_service (#34479) 2026-04-02 12:34:38 +00:00
Poojan
5bafb163cc
test: add unit tests for services and tasks part-4 (#33223) 
Co-authored-by: akashseth-ifp <akash.seth@infocusp.com>
Co-authored-by: rajatagarwal-oss <rajat.agarwal@infocusp.com>
Co-authored-by: Dev Sharma <50591491+cryptus-neoxys@users.noreply.github.com>
Co-authored-by: sahil-infocusp <73810410+sahil-infocusp@users.noreply.github.com>
 2026-04-02 08:35:46 +00:00
Akash Kumar
e54383d0fe
test: added test for api/services/rag_pipeline folder (#33222) 
Co-authored-by: sahil-infocusp <73810410+sahil-infocusp@users.noreply.github.com>
 2026-04-02 06:40:52 +00:00
Sedo
43c48ba4d7
fix: add tenant/dataset ownership checks to prevent IDOR vulnerabilities (#34436) 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
 2026-04-02 05:45:20 +00:00
99
8f9dbf269e
chore(api): align Python support with 3.12 (#34419) 
Co-authored-by: Asuka Minato <i@asukaminato.eu.org>
 2026-04-02 05:07:32 +00:00