- 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>
The backend part of the human in the loop (HITL) feature and relevant architecture / workflow engine changes.
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: 盐粒 Yanli <yanli@dify.ai>
Co-authored-by: CrabSAMA <40541269+CrabSAMA@users.noreply.github.com>
Co-authored-by: Stephen Zhou <38493346+hyoban@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: yihong <zouzou0208@gmail.com>
Co-authored-by: Joel <iamjoel007@gmail.com>
