chrysopedia/backend/routers/pipeline.py
jlightner 4b0914b12b fix: restore complete project tree from ub01 canonical state
Auto-mode commit 7aa33cd accidentally deleted 78 files (14,814 lines) during M005
execution. Subsequent commits rebuilt some frontend files but backend/, alembic/,
tests/, whisper/, docker configs, and prompts were never restored in this repo.

This commit restores the full project tree by syncing from ub01's working directory,
which has all M001-M007 features running in production containers.

Restored: backend/ (config, models, routers, database, redis, search_service, worker),
alembic/ (6 migrations), docker/ (Dockerfiles, nginx, compose), prompts/ (4 stages),
tests/, whisper/, README.md, .env.example, chrysopedia-spec.md
2026-03-31 02:10:41 +00:00

375 lines
14 KiB
Python

"""Pipeline management endpoints — public trigger + admin dashboard.
Public:
POST /pipeline/trigger/{video_id} Trigger pipeline for a video
Admin:
GET /admin/pipeline/videos Video list with status + event counts
POST /admin/pipeline/trigger/{video_id} Retrigger (same as public but under admin prefix)
POST /admin/pipeline/revoke/{video_id} Revoke/cancel active tasks for a video
GET /admin/pipeline/events/{video_id} Event log for a video (paginated)
GET /admin/pipeline/worker-status Active/reserved tasks from Celery inspect
"""
import logging
import uuid
from typing import Annotated
from fastapi import APIRouter, Depends, HTTPException, Query
from sqlalchemy import func, select, case
from sqlalchemy.ext.asyncio import AsyncSession
from config import get_settings
from database import get_session
from models import PipelineEvent, SourceVideo, Creator
from redis_client import get_redis
from schemas import DebugModeResponse, DebugModeUpdate, TokenStageSummary, TokenSummaryResponse
logger = logging.getLogger("chrysopedia.pipeline")
router = APIRouter(tags=["pipeline"])
REDIS_DEBUG_MODE_KEY = "chrysopedia:debug_mode"
# ── Public trigger ───────────────────────────────────────────────────────────
@router.post("/pipeline/trigger/{video_id}")
async def trigger_pipeline(
video_id: str,
db: AsyncSession = Depends(get_session),
):
"""Manually trigger (or re-trigger) the LLM extraction pipeline for a video."""
stmt = select(SourceVideo).where(SourceVideo.id == video_id)
result = await db.execute(stmt)
video = result.scalar_one_or_none()
if video is None:
raise HTTPException(status_code=404, detail=f"Video not found: {video_id}")
from pipeline.stages import run_pipeline
try:
run_pipeline.delay(str(video.id))
logger.info("Pipeline manually triggered for video_id=%s", video_id)
except Exception as exc:
logger.warning("Failed to dispatch pipeline for video_id=%s: %s", video_id, exc)
raise HTTPException(
status_code=503,
detail="Pipeline dispatch failed — Celery/Redis may be unavailable",
) from exc
return {
"status": "triggered",
"video_id": str(video.id),
"current_processing_status": video.processing_status.value,
}
# ── Admin: Video list ────────────────────────────────────────────────────────
@router.get("/admin/pipeline/videos")
async def list_pipeline_videos(
db: AsyncSession = Depends(get_session),
):
"""List all videos with processing status and pipeline event counts."""
# Subquery for event counts per video
event_counts = (
select(
PipelineEvent.video_id,
func.count().label("event_count"),
func.sum(case(
(PipelineEvent.event_type == "llm_call", PipelineEvent.total_tokens),
else_=0
)).label("total_tokens_used"),
func.max(PipelineEvent.created_at).label("last_event_at"),
)
.group_by(PipelineEvent.video_id)
.subquery()
)
stmt = (
select(
SourceVideo.id,
SourceVideo.filename,
SourceVideo.processing_status,
SourceVideo.content_hash,
SourceVideo.created_at,
SourceVideo.updated_at,
Creator.name.label("creator_name"),
event_counts.c.event_count,
event_counts.c.total_tokens_used,
event_counts.c.last_event_at,
)
.join(Creator, SourceVideo.creator_id == Creator.id)
.outerjoin(event_counts, SourceVideo.id == event_counts.c.video_id)
.order_by(SourceVideo.updated_at.desc())
)
result = await db.execute(stmt)
rows = result.all()
return {
"items": [
{
"id": str(r.id),
"filename": r.filename,
"processing_status": r.processing_status.value if hasattr(r.processing_status, 'value') else str(r.processing_status),
"content_hash": r.content_hash,
"creator_name": r.creator_name,
"created_at": r.created_at.isoformat() if r.created_at else None,
"updated_at": r.updated_at.isoformat() if r.updated_at else None,
"event_count": r.event_count or 0,
"total_tokens_used": r.total_tokens_used or 0,
"last_event_at": r.last_event_at.isoformat() if r.last_event_at else None,
}
for r in rows
],
"total": len(rows),
}
# ── Admin: Retrigger ─────────────────────────────────────────────────────────
@router.post("/admin/pipeline/trigger/{video_id}")
async def admin_trigger_pipeline(
video_id: str,
db: AsyncSession = Depends(get_session),
):
"""Admin retrigger — same as public trigger."""
return await trigger_pipeline(video_id, db)
# ── Admin: Revoke ────────────────────────────────────────────────────────────
@router.post("/admin/pipeline/revoke/{video_id}")
async def revoke_pipeline(video_id: str):
"""Revoke/cancel active Celery tasks for a video.
Uses Celery's revoke with terminate=True to kill running tasks.
This is best-effort — the task may have already completed.
"""
from worker import celery_app
try:
# Get active tasks and revoke any matching this video_id
inspector = celery_app.control.inspect()
active = inspector.active() or {}
revoked_count = 0
for _worker, tasks in active.items():
for task in tasks:
task_args = task.get("args", [])
if task_args and str(task_args[0]) == video_id:
celery_app.control.revoke(task["id"], terminate=True)
revoked_count += 1
logger.info("Revoked task %s for video_id=%s", task["id"], video_id)
return {
"status": "revoked" if revoked_count > 0 else "no_active_tasks",
"video_id": video_id,
"tasks_revoked": revoked_count,
}
except Exception as exc:
logger.warning("Failed to revoke tasks for video_id=%s: %s", video_id, exc)
raise HTTPException(
status_code=503,
detail="Failed to communicate with Celery worker",
) from exc
# ── Admin: Event log ─────────────────────────────────────────────────────────
@router.get("/admin/pipeline/events/{video_id}")
async def list_pipeline_events(
video_id: str,
offset: Annotated[int, Query(ge=0)] = 0,
limit: Annotated[int, Query(ge=1, le=200)] = 100,
stage: Annotated[str | None, Query(description="Filter by stage name")] = None,
event_type: Annotated[str | None, Query(description="Filter by event type")] = None,
order: Annotated[str, Query(description="Sort order: asc or desc")] = "desc",
db: AsyncSession = Depends(get_session),
):
"""Get pipeline events for a video. Default: newest first (desc)."""
stmt = select(PipelineEvent).where(PipelineEvent.video_id == video_id)
if stage:
stmt = stmt.where(PipelineEvent.stage == stage)
if event_type:
stmt = stmt.where(PipelineEvent.event_type == event_type)
# Validate order param
if order not in ("asc", "desc"):
raise HTTPException(status_code=400, detail="order must be 'asc' or 'desc'")
# Count
count_stmt = select(func.count()).select_from(stmt.subquery())
total = (await db.execute(count_stmt)).scalar() or 0
# Fetch
order_clause = PipelineEvent.created_at.asc() if order == "asc" else PipelineEvent.created_at.desc()
stmt = stmt.order_by(order_clause)
stmt = stmt.offset(offset).limit(limit)
result = await db.execute(stmt)
events = result.scalars().all()
return {
"items": [
{
"id": str(e.id),
"video_id": str(e.video_id),
"stage": e.stage,
"event_type": e.event_type,
"prompt_tokens": e.prompt_tokens,
"completion_tokens": e.completion_tokens,
"total_tokens": e.total_tokens,
"model": e.model,
"duration_ms": e.duration_ms,
"payload": e.payload,
"created_at": e.created_at.isoformat() if e.created_at else None,
"system_prompt_text": e.system_prompt_text,
"user_prompt_text": e.user_prompt_text,
"response_text": e.response_text,
}
for e in events
],
"total": total,
"offset": offset,
"limit": limit,
}
# ── Admin: Debug mode ─────────────────────────────────────────────────────────
@router.get("/admin/pipeline/debug-mode", response_model=DebugModeResponse)
async def get_debug_mode() -> DebugModeResponse:
"""Get the current pipeline debug mode (on/off)."""
settings = get_settings()
try:
redis = await get_redis()
try:
value = await redis.get(REDIS_DEBUG_MODE_KEY)
if value is not None:
return DebugModeResponse(debug_mode=value.lower() == "true")
finally:
await redis.aclose()
except Exception as exc:
logger.warning("Redis unavailable for debug mode read, using config default: %s", exc)
return DebugModeResponse(debug_mode=settings.debug_mode)
@router.put("/admin/pipeline/debug-mode", response_model=DebugModeResponse)
async def set_debug_mode(body: DebugModeUpdate) -> DebugModeResponse:
"""Set the pipeline debug mode (on/off)."""
try:
redis = await get_redis()
try:
await redis.set(REDIS_DEBUG_MODE_KEY, str(body.debug_mode))
finally:
await redis.aclose()
except Exception as exc:
logger.error("Failed to set debug mode in Redis: %s", exc)
raise HTTPException(
status_code=503,
detail=f"Redis unavailable: {exc}",
)
logger.info("Pipeline debug mode set to %s", body.debug_mode)
return DebugModeResponse(debug_mode=body.debug_mode)
# ── Admin: Token summary ─────────────────────────────────────────────────────
@router.get("/admin/pipeline/token-summary/{video_id}", response_model=TokenSummaryResponse)
async def get_token_summary(
video_id: str,
db: AsyncSession = Depends(get_session),
) -> TokenSummaryResponse:
"""Get per-stage token usage summary for a video."""
stmt = (
select(
PipelineEvent.stage,
func.count().label("call_count"),
func.coalesce(func.sum(PipelineEvent.prompt_tokens), 0).label("total_prompt_tokens"),
func.coalesce(func.sum(PipelineEvent.completion_tokens), 0).label("total_completion_tokens"),
func.coalesce(func.sum(PipelineEvent.total_tokens), 0).label("total_tokens"),
)
.where(PipelineEvent.video_id == video_id)
.where(PipelineEvent.event_type == "llm_call")
.group_by(PipelineEvent.stage)
.order_by(PipelineEvent.stage)
)
result = await db.execute(stmt)
rows = result.all()
stages = [
TokenStageSummary(
stage=r.stage,
call_count=r.call_count,
total_prompt_tokens=r.total_prompt_tokens,
total_completion_tokens=r.total_completion_tokens,
total_tokens=r.total_tokens,
)
for r in rows
]
grand_total = sum(s.total_tokens for s in stages)
return TokenSummaryResponse(
video_id=video_id,
stages=stages,
grand_total_tokens=grand_total,
)
# ── Admin: Worker status ─────────────────────────────────────────────────────
@router.get("/admin/pipeline/worker-status")
async def worker_status():
"""Get current Celery worker status — active, reserved, and stats."""
from worker import celery_app
try:
inspector = celery_app.control.inspect()
active = inspector.active() or {}
reserved = inspector.reserved() or {}
stats = inspector.stats() or {}
workers = []
for worker_name in set(list(active.keys()) + list(reserved.keys()) + list(stats.keys())):
worker_active = active.get(worker_name, [])
worker_reserved = reserved.get(worker_name, [])
worker_stats = stats.get(worker_name, {})
workers.append({
"name": worker_name,
"active_tasks": [
{
"id": t.get("id"),
"name": t.get("name"),
"args": t.get("args", []),
"time_start": t.get("time_start"),
}
for t in worker_active
],
"reserved_tasks": len(worker_reserved),
"total_completed": worker_stats.get("total", {}).get("tasks.pipeline.stages.stage2_segmentation", 0)
+ worker_stats.get("total", {}).get("tasks.pipeline.stages.stage3_extraction", 0)
+ worker_stats.get("total", {}).get("tasks.pipeline.stages.stage4_classification", 0)
+ worker_stats.get("total", {}).get("tasks.pipeline.stages.stage5_synthesis", 0),
"uptime": worker_stats.get("clock", None),
"pool_size": worker_stats.get("pool", {}).get("max-concurrency") if isinstance(worker_stats.get("pool"), dict) else None,
})
return {
"online": len(workers) > 0,
"workers": workers,
}
except Exception as exc:
logger.warning("Failed to inspect Celery workers: %s", exc)
return {
"online": False,
"workers": [],
"error": str(exc),
}