mirror of
https://github.com/Monadical-SAS/reflector.git
synced 2026-04-10 07:36:54 +00:00
* feat: migrate file and live post-processing pipelines from Celery to Hatchet workflow engine * fix: always force reprocessing * fix: ci tests with live pipelines * fix: ci tests with live pipelines
66 lines
2.1 KiB
Python
66 lines
2.1 KiB
Python
"""
|
|
Hatchet workflow constants.
|
|
"""
|
|
|
|
from enum import StrEnum
|
|
|
|
|
|
class TaskName(StrEnum):
|
|
GET_RECORDING = "get_recording"
|
|
GET_PARTICIPANTS = "get_participants"
|
|
PROCESS_TRACKS = "process_tracks"
|
|
MIXDOWN_TRACKS = "mixdown_tracks"
|
|
GENERATE_WAVEFORM = "generate_waveform"
|
|
DETECT_TOPICS = "detect_topics"
|
|
GENERATE_TITLE = "generate_title"
|
|
EXTRACT_SUBJECTS = "extract_subjects"
|
|
PROCESS_SUBJECTS = "process_subjects"
|
|
GENERATE_RECAP = "generate_recap"
|
|
IDENTIFY_ACTION_ITEMS = "identify_action_items"
|
|
FINALIZE = "finalize"
|
|
CLEANUP_CONSENT = "cleanup_consent"
|
|
POST_ZULIP = "post_zulip"
|
|
SEND_WEBHOOK = "send_webhook"
|
|
PAD_TRACK = "pad_track"
|
|
TRANSCRIBE_TRACK = "transcribe_track"
|
|
DETECT_CHUNK_TOPIC = "detect_chunk_topic"
|
|
GENERATE_DETAILED_SUMMARY = "generate_detailed_summary"
|
|
|
|
# File pipeline tasks
|
|
EXTRACT_AUDIO = "extract_audio"
|
|
UPLOAD_AUDIO = "upload_audio"
|
|
TRANSCRIBE = "transcribe"
|
|
DIARIZE = "diarize"
|
|
ASSEMBLE_TRANSCRIPT = "assemble_transcript"
|
|
GENERATE_SUMMARIES = "generate_summaries"
|
|
|
|
# Live post-processing pipeline tasks
|
|
WAVEFORM = "waveform"
|
|
CONVERT_MP3 = "convert_mp3"
|
|
UPLOAD_MP3 = "upload_mp3"
|
|
REMOVE_UPLOAD = "remove_upload"
|
|
FINAL_SUMMARIES = "final_summaries"
|
|
|
|
|
|
# Rate limit key for LLM API calls (shared across all LLM-calling tasks)
|
|
LLM_RATE_LIMIT_KEY = "llm"
|
|
|
|
# Max LLM calls per second across all tasks
|
|
LLM_RATE_LIMIT_PER_SECOND = 10
|
|
|
|
# Task execution timeouts (seconds)
|
|
TIMEOUT_SHORT = 60 # Quick operations: API calls, DB updates
|
|
TIMEOUT_MEDIUM = (
|
|
300 # Single LLM calls, waveform generation (5m for slow LLM responses)
|
|
)
|
|
TIMEOUT_LONG = 180 # Action items (larger context LLM)
|
|
TIMEOUT_TITLE = 300 # generate_title (single LLM call; doc: reduce from 600s)
|
|
TIMEOUT_AUDIO = 720 # Audio processing: padding, mixdown (Hatchet execution_timeout)
|
|
TIMEOUT_AUDIO_HTTP = (
|
|
660 # httpx timeout for pad_track — below 720 so Hatchet doesn't race
|
|
)
|
|
TIMEOUT_HEAVY = 600 # Transcription, fan-out LLM tasks (Hatchet execution_timeout)
|
|
TIMEOUT_HEAVY_HTTP = (
|
|
540 # httpx timeout for transcribe_track — below 600 so Hatchet doesn't race
|
|
)
|