- Fix type errors in dify_graph/nodes/agent/agent_node.py:
- Add missing user_id param to get_agent_tool_runtime call
- Use create_plugin_provider_manager instead of bare ProviderManager()
- Pass provider_manager to ModelManager constructor
- Add access_controller param to file_factory.build_from_mapping
- Fix return type annotation for _fetch_memory
- Fix DB migration chain: update workflow_comments migration to point
to correct parent after sandbox migration removal
- Fix test_app_generate_service: set AGENT_V2_TRANSPARENT_UPGRADE=False
in mock config to prevent transparent upgrade intercepting test flow
- Fix test_app_generator: add scalar method to mock db.session
- Fix test_app_models: add AppMode.AGENT to expected modes set
- Remove unnecessary db.session.close() from agent_chat app_runner
Made-with: Cursor
Full pipeline working: Agent V2 node → Docker container creation →
CLI binary upload (linux/arm64) → dify init (fetch tools from API) →
dify execute (tool callback via CLI API) → result returned.
Fixes:
- Use sandbox.id (not vm.metadata.id) for CLI paths
- Upload CLI binary to container during sandbox creation
- Resolve linux binary separately for Docker containers on macOS
- Save Docker provider config via SandboxProviderService (proper
encryption) instead of raw DB insert
- Add verbose logging for sandbox tool execution path
- Fix NameError: binary not defined
Made-with: Cursor
- Skip Local sandbox provider under gevent worker (subprocess pipes
cause cooperative threading deadlock with Celery's gevent pool).
- Add non-blocking sandbox readiness check before tool execution.
- Add gevent timeout wrapper for sandbox bash session.
- Fix CLI binary resolution: add SANDBOX_DIFY_CLI_ROOT config field.
- Fix ExecutionContext.node_id propagation.
- Fix SkillInitializer to gracefully handle missing skill bundles.
- Update _invoke_tool_in_sandbox to use correct `dify execute` CLI
subcommand format (not `invoke-tool`).
The full sandbox-in-agent pipeline works end-to-end for network-based
providers (Docker, E2B, SSH). Local provider is skipped under gevent
but works in non-gevent contexts.
Made-with: Cursor
Close 3 integration gaps between the ported Sandbox system and Agent V2:
1. Fix _invoke_tool_in_sandbox to use SandboxBashSession context manager
API correctly (keyword args, bash_tool, ToolReference), with graceful
fallback to direct invocation when DifyCli binary is unavailable.
2. Inject sandbox into run_context via _resolve_sandbox_context() in
WorkflowBasedAppRunner — automatically creates a sandbox when a
tenant has an active sandbox provider configured.
3. Register SandboxLayer in both advanced_chat and workflow app runners
for proper sandbox lifecycle cleanup on graph end.
Also: make SkillInitializer non-fatal when no skill bundle exists,
add node_id to ExecutionContext for sandbox session scoping.
Made-with: Cursor
- Auto-resolve parent_message_id when not provided by client,
querying the latest message in the conversation to maintain
the thread chain that extract_thread_messages() relies on.
- Add AppMode.AGENT to TokenBufferMemory mode checks so file
attachments in memory are handled via the workflow branch.
- Add debug logging for memory injection in node_factory and node.
Made-with: Cursor
1. Fix workflow-level total_tokens=0:
Call graph_runtime_state.add_tokens(usage.total_tokens) in both
_run_without_tools and _run_with_tools paths after node execution.
Previously only graphon's internal ModelInvokeCompletedEvent handler
called add_tokens, which agent-v2 doesn't emit.
2. Fix Turn 2 SSE empty response:
Set PUBSUB_REDIS_CHANNEL_TYPE=streams in .env. Redis Streams
provides durable event delivery (consumers can replay past events),
solving the pub/sub at-most-once timing issue.
3. Skill -> Agent runtime integration:
SandboxBuilder.build() now auto-includes SkillInitializer if not
already present. This ensures sandbox.attrs has the skill bundle
loaded for downstream consumers (tool execution in sandbox).
4. LegacyResponseAdapter:
New module at core/app/apps/common/legacy_response_adapter.py.
Filters workflow-specific SSE events (workflow_started, node_started,
node_finished, workflow_finished) from the stream, passing through
only message/message_end/agent_log/error/ping events that old
clients expect.
46 unit tests pass.
Made-with: Cursor
Replace the hardcoded FunctionCallAgentRunner / CotChatAgentRunner /
CotCompletionAgentRunner selection in AgentChatAppRunner with the new
AgentAppRunner class that uses StrategyFactory from Phase 1.
Before: AgentChatAppRunner manually selects FC/CoT runner class based on
model features and LLM mode, then instantiates it directly.
After: AgentChatAppRunner instantiates AgentAppRunner (from sandbox branch),
which internally uses StrategyFactory.create_strategy() to auto-select
the right strategy, and uses ToolInvokeHook for proper agent_invoke
with file handling and thought persistence.
This unifies the agent execution engine: both the new Agent V2 workflow
node and the legacy agent-chat app now use the same StrategyFactory
and AgentPattern implementations.
Also fix: command and file_upload nodes use string node_type instead of
BuiltinNodeTypes.COMMAND/FILE_UPLOAD (not in current graphon version).
46 tests pass. Flask starts successfully.
Made-with: Cursor
The frontend and backend implementation for the human input node.
Co-authored-by: twwu <twwu@dify.ai>
Co-authored-by: JzoNg <jzongcode@gmail.com>
Co-authored-by: yyh <92089059+lyzno1@users.noreply.github.com>
Co-authored-by: zhsama <torvalds@linux.do>
