kunthawat/ALwrity
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Podcast Maker: Fix progress modals, research JSON, header stepper, voice/podcastMode chips

Browse Source
This commit is contained in:
ajaysi
2026-04-19 13:16:59 +05:30
parent ff61708e29
commit e704aa7d87
61 changed files with 7965 additions and 368 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
backend/api/podcast/handlers/analysis.py
View File

@@ -51,6 +51,7 @@ async def enhance_podcast_idea(
# In podcast-only mode, skip bible generation since onboarding is disabled
bible_context = ""
if not _is_podcast_only_mode():
logger.warning(f"[Podcast Enhance] Podcast mode=full — attempting Bible generation for user {user_id}")
try:
bible_service = PodcastBibleService()
if request.bible:
@@ -65,6 +66,7 @@ async def enhance_podcast_idea(
logger.warning(f"[Podcast Enhance] Failed to parse or generate bible context: {exc}")
else:
# In podcast mode, use the provided bible directly if available
logger.warning(f"[Podcast Enhance] Podcast mode=podcast_only — skipping Bible generation for user {user_id}")
if request.bible:
try:
from models.podcast_bible_models import PodcastBible
@@ -209,7 +211,11 @@ async def analyze_podcast_idea(
final_avatar_url = request.avatar_url
final_avatar_prompt = None
if not final_avatar_url:
# Skip avatar generation for audio_only mode
podcast_mode = getattr(request, 'podcast_mode', None) or 'video_only'
should_generate_avatar = not final_avatar_url and podcast_mode != 'audio_only'
if should_generate_avatar:
logger.info(f"[Podcast Analyze] No avatar_url provided, generating one for user {user_id}")
try:
# 1. PRE-FLIGHT VALIDATION: Check subscription limits for image generation
@@ -240,8 +246,9 @@ async def analyze_podcast_idea(
if image_result and image_result.image_bytes:
img_id = str(uuid.uuid4())[:8]
filename = f"presenter_podcast_{user_id}_{img_id}.png"
output_path = PODCAST_IMAGES_DIR / filename
PODCAST_IMAGES_DIR.mkdir(parents=True, exist_ok=True)
avatars_dir = PODCAST_IMAGES_DIR / "avatars"
avatars_dir.mkdir(parents=True, exist_ok=True)
output_path = avatars_dir / filename
with open(output_path, "wb") as f:
f.write(image_result.image_bytes)
@@ -253,13 +260,14 @@ async def analyze_podcast_idea(
db=db,
user_id=user_id,
asset_type="image",
file_url=final_avatar_url,
source_module="podcast_analysis",
filename=filename,
file_url=final_avatar_url,
title=f"Presenter Avatar - {request.idea[:40]}",
description=f"AI-generated podcast presenter for: {request.idea}",
provider=image_result.provider,
model=image_result.model,
cost=image_result.cost
cost=0.0 # Cost tracked in generate_image
)
logger.info(f"[Podcast Analyze] ✅ Generated and saved avatar to {final_avatar_url}")
except Exception as e:

241
backend/api/podcast/handlers/broll.py Normal file
View File

@@ -0,0 +1,241 @@
"""
B-Roll Handlers
API endpoints for B-roll chart preview and video generation.
"""
from fastapi import APIRouter, Depends, HTTPException, BackgroundTasks
from fastapi.responses import FileResponse
from typing import Dict, Any, Optional, List
from pydantic import BaseModel, Field
import uuid
from middleware.auth_middleware import get_current_user
from api.story_writer.utils.auth import require_authenticated_user
from services.podcast.broll_service import get_broll_service
from loguru import logger
router = APIRouter()
class ChartPreviewRequest(BaseModel):
"""Request model for chart preview generation."""
chart_data: Dict[str, Any] = Field(..., description="Chart data (labels, before/after, etc.)")
chart_type: str = Field(
default="bar_comparison",
description="bar_comparison | bar_horizontal | line_trend | pie | stacked_bar | bullet"
)
title: str = Field(default="", description="Chart title")
subtitle: Optional[str] = Field(default="", description="Optional subtitle at bottom")
class ChartPreviewResponse(BaseModel):
"""Response for chart preview."""
preview_url: str
chart_id: str
class BrollSceneRequest(BaseModel):
"""Request for generating B-roll video for a scene."""
scene_id: str
key_insight: str
supporting_stat: str
chart_data: Optional[Dict[str, Any]] = None
visual_cue: str = Field(default="bar_chart_comparison", description="bar_chart_comparison | bullet_points")
duration: float = Field(default=10.0, ge=3.0, le=60.0)
background_image_url: str
avatar_video_url: Optional[str] = None
class BrollSceneResponse(BaseModel):
"""Response for B-roll scene generation."""
scene_id: str
broll_video_url: str
broll_video_path: str
class BrollComposeRequest(BaseModel):
"""Request for composing multiple B-roll videos."""
scene_video_paths: List[str]
output_filename: str = "final_broll.mp4"
fade_dur: float = Field(default=0.5, ge=0.0, le=2.0)
fps: int = Field(default=24, ge=12, le=60)
class BrollComposeResponse(BaseModel):
"""Response for B-roll composition."""
final_video_url: str
final_video_path: str
@router.post("/preview/chart", response_model=ChartPreviewResponse)
async def generate_chart_preview(
request: ChartPreviewRequest,
current_user: Dict[str, Any] = Depends(get_current_user),
):
"""
Generate a chart PNG preview (static image for Write phase).
This endpoint is called from the Write phase to show users chart previews
before they commit to B-roll video generation.
"""
user_id = require_authenticated_user(current_user)
try:
broll_service = get_broll_service()
preview_path = broll_service.generate_chart_preview(
chart_data=request.chart_data,
chart_type=request.chart_type,
title=request.title,
subtitle=request.subtitle or "",
)
if not preview_path:
raise HTTPException(status_code=500, detail="Failed to generate chart preview")
chart_id = uuid.uuid4().hex[:8]
preview_url = f"/api/podcast/broll/preview/{chart_id}/{preview_path.split('/')[-1]}"
return ChartPreviewResponse(
preview_url=preview_url,
chart_id=chart_id,
)
except Exception as e:
logger.error(f"[Broll] Chart preview generation failed: {e}")
raise HTTPException(status_code=500, detail=f"Chart preview failed: {str(e)}")
@router.post("/render/broll-scene", response_model=BrollSceneResponse)
async def generate_broll_scene(
request: BrollSceneRequest,
background_tasks: BackgroundTasks,
current_user: Dict[str, Any] = Depends(get_current_user),
):
"""
Generate a B-roll video for a single scene.
This creates a programmatic video with:
- Background image with Ken Burns effect
- Chart overlay (if chart_data provided)
- Avatar circle in corner (if avatar_video_url provided)
- Insight card at bottom
Returns a task_id for polling since video generation can take time.
"""
user_id = require_authenticated_user(current_user)
try:
# Validate visual_cue
valid_cues = ["bar_chart_comparison", "bullet_points", "full_avatar"]
if request.visual_cue not in valid_cues:
raise HTTPException(
status_code=400,
detail=f"Invalid visual_cue. Must be one of: {valid_cues}"
)
# For now, return a placeholder - full video generation requires
# resolving image/video URLs to actual file paths
# In V2, this will integrate with the actual video generation
logger.info(f"[Broll] B-roll scene request for scene: {request.scene_id}")
return BrollSceneResponse(
scene_id=request.scene_id,
broll_video_url="",
broll_video_path="",
)
except HTTPException:
raise
except Exception as e:
logger.error(f"[Broll] B-roll scene generation failed: {e}")
raise HTTPException(status_code=500, detail=f"B-roll generation failed: {str(e)}")
@router.post("/render/broll-compose", response_model=BrollComposeResponse)
async def compose_broll_videos(
request: BrollComposeRequest,
current_user: Dict[str, Any] = Depends(get_current_user),
):
"""
Compose multiple B-roll scene videos into a final video.
Applies crossfade transitions between scenes.
"""
user_id = require_authenticated_user(current_user)
try:
broll_service = get_broll_service()
final_path = broll_service.compose_final_video(
video_paths=request.scene_video_paths,
output_filename=request.output_filename,
fade_dur=request.fade_dur,
fps=request.fps,
)
final_filename = final_path.split('/')[-1]
final_url = f"/api/podcast/broll/final/{final_filename}"
return BrollComposeResponse(
final_video_url=final_url,
final_video_path=final_path,
)
except Exception as e:
logger.error(f"[Broll] Video composition failed: {e}")
raise HTTPException(status_code=500, detail=f"Video composition failed: {str(e)}")
@router.get("/preview/{chart_id}/{filename}")
async def serve_chart_preview(
chart_id: str,
filename: str,
current_user: Dict[str, Any] = Depends(get_current_user),
):
"""Serve chart preview PNG files."""
from pathlib import Path
user_id = require_authenticated_user(current_user)
broll_service = get_broll_service()
file_path = broll_service.output_dir / f"chart_preview_{chart_id}.png"
if not file_path.exists():
raise HTTPException(status_code=404, detail="Chart preview not found")
return FileResponse(
path=str(file_path),
media_type="image/png",
filename=filename,
)
@router.get("/final/{filename}")
async def serve_final_broll(
filename: str,
current_user: Dict[str, Any] = Depends(get_current_user),
):
"""Serve final composed B-roll video files."""
user_id = require_authenticated_user(current_user)
broll_service = get_broll_service()
file_path = broll_service.output_dir / filename
if not file_path.exists():
raise HTTPException(status_code=404, detail="Video not found")
return FileResponse(
path=str(file_path),
media_type="video/mp4",
filename=filename,
)
@router.get("/health")
async def broll_health():
"""Health check for B-roll service."""
return {"status": "ok", "service": "broll"}

2
backend/api/podcast/handlers/projects.py
View File

@@ -119,7 +119,7 @@ async def update_project(
project = service.update_project(user_id, project_id, **updates)
if not project:
raise HTTPException(status_code=404, detail="Project not found")
raise HTTPException(status_code=404, detail=f"Project {project_id} not found")
return PodcastProjectResponse.model_validate(project)
except HTTPException:

44
backend/api/podcast/handlers/research.py
View File

@@ -22,6 +22,7 @@ from ..models import (
PodcastExaSource,
PodcastExaConfig,
PodcastResearchInsight,
PodcastResearchOutput,
)
router = APIRouter()
@@ -159,43 +160,50 @@ As a podcast research expert, analyze this data and create content that will:
4. Include a compelling call-to-action for listeners
REQUIRED OUTPUT (JSON):
=======================
======================
{{
"summary": "2-3 paragraph comprehensive summary in Markdown. Start with a hook that matches the episode intro. Include specific data points, expert quotes, and trends.",
"summary": "2-3 paragraph comprehensive summary in Markdown. Start with a hook that matches the episode intro.",
"key_insights": [
{{
"title": "Catchy, engaging title for this insight",
"content": "3-4 sentences with specific facts, quotes, or data. Write in a conversational tone suitable for a podcast host to discuss.",
"source_indices": [1, 2, 3],
"podcast_talking_points": ["Point 1 host can expand on", "Counter-point or follow-up", "Question to ask guest"]
"title": "Insight title",
"content": "3-4 sentences with specific facts, quotes, or data for podcast host.",
"source_indices": [1, 2],
"podcast_talking_points": ["Point host can expand on", "Counter-point"]
}}
],
"expert_quotes": [
{{
"quote": "Direct quote from source",
"quote": "Direct quote from source text",
"source_index": 1,
"context": "Why this quote matters for the podcast"
}}
],
"listener_cta_suggestions": ["Specific action listener can take", "Resource to share", "Next episode preview"]
"listener_cta_suggestions": ["Action listener can take", "Resource to share", "Next episode preview"],
"mapped_angles": [
{{
"title": "Content angle title",
"why": "Why compelling for audience",
"mapped_fact_ids": [1, 2]
}}
]
}}
IMPORTANT: You must include ALL fields above with valid data. expert_quotes, listener_cta_suggestions, and mapped_angles must have content - do NOT leave them empty!
QUALITY STANDARDS:
==================
- INSIGHTS MUST BE DEEP, not superficial - avoid generic statements
- Include SPECIFIC DATA POINTS, percentages, statistics when available
- Extract EXPERT QUOTES that hosts can reference
- Identify GAPS in the research where more depth is needed
- Make content naturally flow into the planned episode hook and CTA
- Write in a CONVERSATIONAL tone - how a host would actually speak
- Flag any CONTROVERSIAL or debatable claims for host to address
=================
- Include at least 2 expert_quotes with source_index
- Include at least 2 listener_cta_suggestions
- Include at least 2 mapped_angles
- Include specific data points, percentages, statistics
- Write in conversational tone
"""
try:
logger.warning(f"[Podcast Research] Calling LLM for insight extraction...")
logger.warning(f"[Podcast Research] Calling LLM with json_struct...")
llm_response = llm_text_gen(
prompt=prompt,
user_id=user_id,
json_struct=None,
json_struct=PodcastResearchOutput.model_json_schema(),
preferred_provider=None,
flow_type="premium_tool",
)