selfhostyourtech/reflector
2
0
Fork 0
mirror of https://github.com/Monadical-SAS/reflector.git synced 2025-12-24 14:19:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: durable (#794)

Browse Source 
* durable (no-mistakes)

* hatchet no-mistake

* hatchet no-mistake

* hatchet no-mistake, better logging

* remove conductor and add hatchet tests (no-mistakes)

* self-review (no-mistakes)

* hatched logs

* remove shadow mode for hatchet

* and add hatchet processor setting to room

* .

* cleanup

* hatchet init db

* self-review (no-mistakes)

* self-review (no-mistakes)

* hatchet: restore zullip report

* self-review round

* self-review round

* self-review round

* dry hatchet with celery

* dry hatched with celery - 2

* self-review round

* more NES instead of str

* self-review wip

* self-review round

* self-review round

* self-review round

* can_replay cancelled

* add forgotten file

* pr autoreviewer fixes

* better log webhook events

* durable_started return

* migration sync

* latest changes feature parity

* migration merge

* pr review

---------

Co-authored-by: Igor Loskutov <igor.loskutoff@gmail.com>
This commit is contained in:
Igor Monadical
2025-12-22 12:09:20 -05:00
committed by GitHub
parent f580b996ee
commit 1dac999b56
36 changed files with 4908 additions and 2009 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
server/reflector/pipelines/topic_processing.py
View File

@@ -74,13 +74,24 @@ async def generate_title(
logger.warning("No topics for title generation")
return
logger.info(
"generate_title: creating TranscriptFinalTitleProcessor",
topic_count=len(topics),
)
processor = TranscriptFinalTitleProcessor(callback=on_title_callback)
processor.set_pipeline(empty_pipeline)
for topic in topics:
for i, topic in enumerate(topics):
logger.info(
"generate_title: pushing topic to processor",
topic_index=i,
topic_title=topic.title[:50] if topic.title else None,
)
await processor.push(topic)
logger.info("generate_title: calling processor.flush() - this triggers LLM call")
await processor.flush()
logger.info("generate_title: processor.flush() completed")
async def generate_summaries(
@@ -97,6 +108,10 @@ async def generate_summaries(
logger.warning("No topics for summary generation")
return
logger.info(
"generate_summaries: creating TranscriptFinalSummaryProcessor",
topic_count=len(topics),
)
processor_kwargs = {
"transcript": transcript,
"callback": on_long_summary_callback,
@@ -107,7 +122,16 @@ async def generate_summaries(
processor = TranscriptFinalSummaryProcessor(**processor_kwargs)
processor.set_pipeline(empty_pipeline)
for topic in topics:
for i, topic in enumerate(topics):
logger.info(
"generate_summaries: pushing topic to processor",
topic_index=i,
topic_title=topic.title[:50] if topic.title else None,
)
await processor.push(topic)
logger.info(
"generate_summaries: calling processor.flush() - this triggers LLM calls"
)
await processor.flush()
logger.info("generate_summaries: processor.flush() completed")