Yansong Zhang 4f010cd4f5 fix(api): stop emitting StreamChunkEvent from tool path to prevent answer duplication ... The EventAdapter was converting every LLMResultChunk from the agent strategy into StreamChunkEvent. Combined with the answer node's {{#agent.text#}} variable output, this caused the final answer to appear twice (e.g., "It is 2026-04-09 04:27:45.It is 2026-04-09 04:27:45."). Now LLMResultChunk from strategy output is silently consumed (text still accumulates in AgentResult.text via the strategy). Only AgentLogEvent (thought/tool_call/round) is forwarded to the pipeline. Known remaining issues: - workflow/message level total_tokens=0 (node level is correct at 33) because pipeline aggregation doesn't include agent-v2 node tokens - Turn 2 SSE delivery timing with Redis pubsub (celery executes OK) Made-with: Cursor		2026-04-09 12:31:49 +08:00
..
nodes	fix(api): stop emitting StreamChunkEvent from tool path to prevent answer duplication	2026-04-09 12:31:49 +08:00
__init__.py
file_reference.py
human_input_compat.py	refactor(api): use standalone graphon package (#34209)	2026-03-27 21:05:32 +00:00
human_input_forms.py
node_factory.py	feat(api): implement zero-migration transparent upgrade (Phase 8)	2026-04-09 10:30:52 +08:00
node_runtime.py	refactor(api): use standalone graphon package (#34209)	2026-03-27 21:05:32 +00:00
system_variables.py	refactor(api): rename dify_graph to graphon (#34095)	2026-03-25 21:58:56 +08:00
template_rendering.py	refactor(api): use standalone graphon package (#34209)	2026-03-27 21:05:32 +00:00
variable_pool_initializer.py	refactor(api): rename dify_graph to graphon (#34095)	2026-03-25 21:58:56 +08:00
variable_prefixes.py
workflow_entry.py	refactor(api): type single-node graph structure with TypedDicts in workflow_entry (#34671)	2026-04-07 13:18:00 +00:00
workflow_run_outputs.py	refactor(api): rename dify_graph to graphon (#34095)	2026-03-25 21:58:56 +08:00