L1nSn0w 43c95e562e feat(chatflow): stream and persist LLM reasoning out-of-band (backend) ...

Consume graphon's NodeRunReasoningChunkEvent: route it to a new QueueReasoningChunkEvent and a reasoning_chunk SSE event via a pure-emit handler that never touches the answer. Persist terminal reasoning_content per LLM node into message_metadata (zero migration).

2026-06-23 14:35:52 +08:00

..

app_config

fix: skip empty tool entries in legacy dataset config extraction (#37669)

2026-06-21 07:32:15 +00:00

apps

chore: not use request.scoped session (#37421)

2026-06-22 19:38:24 +00:00

entities

feat(chatflow): stream and persist LLM reasoning out-of-band (backend)

2026-06-23 14:35:52 +08:00

features

chore: Caplog type (#37603)

2026-06-18 18:53:13 +00:00

layers

chore: Caplog type (#37603)

2026-06-18 18:53:13 +00:00

task_pipeline

chore: Caplog type (#37603)

2026-06-18 18:53:13 +00:00

workflow

chore: add Type to test (#37191)

2026-06-19 16:44:20 +00:00

test_easy_ui_model_config_manager.py

chore: reorg imports (#35308)

2026-04-16 08:50:02 +00:00

test_invoke_from.py

feat(api): forward user_type for MCP identity forwarding (webapp end-users) (#37347)

2026-06-12 07:30:15 +00:00

test_llm_quota.py

fix: use Generator type annotation with @contextmanager decorators (#36297)

2026-05-18 07:12:49 +00:00