mirror of
https://github.com/langgenius/dify.git
synced 2026-08-29 02:16:23 +08:00
482a004efe
1. Remove StreamChunkEvent from AgentV2Node._run_without_tools():
The agent-v2 node was yielding StreamChunkEvent during LLM streaming,
AND the downstream answer node was outputting the same text via
{{#agent.text#}} variable reference, causing "FourFour" duplication.
Now text only flows through outputs.text -> answer node (single path).
2. Map inputs to query for completion app transparent upgrade:
Completion apps send {inputs: {query: "..."}} not {query: "..."}.
VirtualWorkflowSynthesizer route now extracts query from inputs
when the top-level query is missing.
Verified:
- Old chat app: "What is 2+2?" -> "Four" (was "FourFour")
- Old completion app: {inputs: {query: "What is 3+3?"}} -> "3 + 3 = 6" (was failing)
- Old agent-chat app: still works
Made-with: Cursor
|
||
|---|---|---|
| .. | ||
| nodes | ||
| __init__.py | ||
| file_reference.py | ||
| human_input_compat.py | ||
| human_input_forms.py | ||
| node_factory.py | ||
| node_runtime.py | ||
| system_variables.py | ||
| template_rendering.py | ||
| variable_pool_initializer.py | ||
| variable_prefixes.py | ||
| workflow_entry.py | ||
| workflow_run_outputs.py | ||