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

Subscription dashboard improvements, AI text generation limit, and other fixes.

Browse Source
This commit is contained in:
ajaysi
2025-11-01 18:01:14 +05:30
parent cdb41aec1b
commit de4328175d
64 changed files with 5809 additions and 444 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
backend/services/blog_writer/core/blog_writer_service.py
View File

@@ -96,13 +96,13 @@ class BlogWriterService:
self.blog_rewriter = BlogRewriter(self.task_manager)
# Research Methods
async def research(self, request: BlogResearchRequest) -> BlogResearchResponse:
async def research(self, request: BlogResearchRequest, user_id: str) -> BlogResearchResponse:
"""Conduct comprehensive research using Google Search grounding."""
return await self.research_service.research(request)
return await self.research_service.research(request, user_id)
async def research_with_progress(self, request: BlogResearchRequest, task_id: str) -> BlogResearchResponse:
async def research_with_progress(self, request: BlogResearchRequest, task_id: str, user_id: str) -> BlogResearchResponse:
"""Conduct research with real-time progress updates."""
return await self.research_service.research_with_progress(request, task_id)
return await self.research_service.research_with_progress(request, task_id, user_id)
# Outline Methods
async def generate_outline(self, request: BlogOutlineRequest) -> BlogOutlineResponse:
@@ -204,11 +204,14 @@ class BlogWriterService:
except Exception as e:
return {"success": False, "error": str(e)}
async def seo_analyze(self, request: BlogSEOAnalyzeRequest) -> BlogSEOAnalyzeResponse:
async def seo_analyze(self, request: BlogSEOAnalyzeRequest, user_id: str = None) -> BlogSEOAnalyzeResponse:
"""Analyze content for SEO optimization using comprehensive blog-specific analyzer."""
try:
from services.blog_writer.seo.blog_content_seo_analyzer import BlogContentSEOAnalyzer
if not user_id:
raise ValueError("user_id is required for subscription checking. Please provide Clerk user ID.")
content = request.content or ""
target_keywords = request.keywords or []
@@ -231,7 +234,7 @@ class BlogWriterService:
# Use our comprehensive SEO analyzer
analyzer = BlogContentSEOAnalyzer()
analysis_results = await analyzer.analyze_blog_content(content, research_data)
analysis_results = await analyzer.analyze_blog_content(content, research_data, user_id=user_id)
# Convert results to response format
recommendations = analysis_results.get('actionable_recommendations', [])
@@ -267,11 +270,14 @@ class BlogWriterService:
recommendations=[f"SEO analysis failed: {str(e)}"]
)
async def seo_metadata(self, request: BlogSEOMetadataRequest) -> BlogSEOMetadataResponse:
async def seo_metadata(self, request: BlogSEOMetadataRequest, user_id: str = None) -> BlogSEOMetadataResponse:
"""Generate comprehensive SEO metadata for content."""
try:
from services.blog_writer.seo.blog_seo_metadata_generator import BlogSEOMetadataGenerator
if not user_id:
raise ValueError("user_id is required for subscription checking. Please provide Clerk user ID.")
# Initialize metadata generator
metadata_generator = BlogSEOMetadataGenerator()
@@ -285,7 +291,8 @@ class BlogWriterService:
blog_title=request.title or "Untitled Blog Post",
research_data=request.research_data or {},
outline=outline,
seo_analysis=seo_analysis
seo_analysis=seo_analysis,
user_id=user_id
)
# Convert to BlogSEOMetadataResponse format

9
backend/services/blog_writer/logger_config.py
View File

@@ -163,13 +163,18 @@ class BlogWriterLogger:
context: Optional[Dict[str, Any]] = None
):
"""Log error with full context."""
# Safely format error message to avoid KeyError on format strings in error messages
error_str = str(error)
# Replace any curly braces that might be in the error message to avoid format string issues
safe_error_str = error_str.replace('{', '{{').replace('}', '}}')
logger.error(
f"Error in {operation}: {str(error)}",
f"Error in {operation}: {safe_error_str}",
extra={
"event_type": "error",
"operation": operation,
"error_type": type(error).__name__,
"error_message": str(error),
"error_message": error_str, # Keep original in extra, but use safe version in format string
"context": context or {}
},
exc_info=True

5
backend/services/blog_writer/research/competitor_analyzer.py
View File

@@ -11,7 +11,7 @@ from loguru import logger
class CompetitorAnalyzer:
"""Analyzes competitors and market intelligence from research content."""
def analyze(self, content: str) -> Dict[str, Any]:
def analyze(self, content: str, user_id: str = None) -> Dict[str, Any]:
"""Parse comprehensive competitor analysis from the research content using AI."""
competitor_prompt = f"""
Analyze the following research content and extract competitor insights:
@@ -57,7 +57,8 @@ class CompetitorAnalyzer:
competitor_analysis = llm_text_gen(
prompt=competitor_prompt,
json_struct=competitor_schema
json_struct=competitor_schema,
user_id=user_id
)
if isinstance(competitor_analysis, dict) and 'error' not in competitor_analysis:

5
backend/services/blog_writer/research/content_angle_generator.py
View File

@@ -11,7 +11,7 @@ from loguru import logger
class ContentAngleGenerator:
"""Generates strategic content angles from research content."""
def generate(self, content: str, topic: str, industry: str) -> List[str]:
def generate(self, content: str, topic: str, industry: str, user_id: str = None) -> List[str]:
"""Parse strategic content angles from the research content using AI."""
angles_prompt = f"""
Analyze the following research content and create strategic content angles for: {topic} in {industry}
@@ -65,7 +65,8 @@ class ContentAngleGenerator:
angles_result = llm_text_gen(
prompt=angles_prompt,
json_struct=angles_schema
json_struct=angles_schema,
user_id=user_id
)
if isinstance(angles_result, dict) and 'content_angles' in angles_result:

5
backend/services/blog_writer/research/keyword_analyzer.py
View File

@@ -11,7 +11,7 @@ from loguru import logger
class KeywordAnalyzer:
"""Analyzes keywords from research content using AI-powered extraction."""
def analyze(self, content: str, original_keywords: List[str]) -> Dict[str, Any]:
def analyze(self, content: str, original_keywords: List[str], user_id: str = None) -> Dict[str, Any]:
"""Parse comprehensive keyword analysis from the research content using AI."""
# Use AI to extract and analyze keywords from the rich research content
keyword_prompt = f"""
@@ -64,7 +64,8 @@ class KeywordAnalyzer:
keyword_analysis = llm_text_gen(
prompt=keyword_prompt,
json_struct=keyword_schema
json_struct=keyword_schema,
user_id=user_id
)
if isinstance(keyword_analysis, dict) and 'error' not in keyword_analysis:

59
backend/services/blog_writer/research/research_service.py
View File

@@ -4,7 +4,8 @@ Research Service - Core research functionality for AI Blog Writer.
Handles Google Search grounding, caching, and research orchestration.
"""
from typing import Dict, Any, List
from typing import Dict, Any, List, Optional
from datetime import datetime
from loguru import logger
from models.blog_models import (
@@ -17,6 +18,7 @@ from models.blog_models import (
Citation,
)
from services.blog_writer.logger_config import blog_writer_logger, log_function_call
from fastapi import HTTPException
from .keyword_analyzer import KeywordAnalyzer
from .competitor_analyzer import CompetitorAnalyzer
@@ -34,7 +36,7 @@ class ResearchService:
self.data_filter = ResearchDataFilter()
@log_function_call("research_operation")
async def research(self, request: BlogResearchRequest) -> BlogResearchResponse:
async def research(self, request: BlogResearchRequest, user_id: str) -> BlogResearchResponse:
"""
Stage 1: Research & Strategy (AI Orchestration)
Uses ONLY Gemini's native Google Search grounding - ONE API call for everything.
@@ -71,6 +73,10 @@ class ResearchService:
blog_writer_logger.log_operation_end("research", 0, success=True, cache_hit=True)
return BlogResearchResponse(**cached_result)
# User ID validation (validation logic is now in Google Grounding provider)
if not user_id:
raise ValueError("user_id is required for research operation. Please provide Clerk user ID.")
# Cache miss - proceed with API call
logger.info(f"Cache miss - making API call for keywords: {request.keywords}")
blog_writer_logger.log_operation_start("gemini_api_call", api_name="gemini_grounded", operation="research")
@@ -96,12 +102,15 @@ class ResearchService:
"""
# Single Gemini call with native Google Search grounding - no fallbacks
# Validation is handled inside generate_grounded_content when validate_subsequent_operations=True
import time
api_start_time = time.time()
gemini_result = await gemini.generate_grounded_content(
prompt=research_prompt,
content_type="research",
max_tokens=2000
max_tokens=2000,
user_id=user_id,
validate_subsequent_operations=True # Validates Google Grounding + 3 LLM calls
)
api_duration_ms = (time.time() - api_start_time) * 1000
@@ -126,9 +135,9 @@ class ResearchService:
# Parse the comprehensive response for different analysis components
content = gemini_result.get("content", "")
keyword_analysis = self.keyword_analyzer.analyze(content, request.keywords)
competitor_analysis = self.competitor_analyzer.analyze(content)
suggested_angles = self.content_angle_generator.generate(content, topic, industry)
keyword_analysis = self.keyword_analyzer.analyze(content, request.keywords, user_id=user_id)
competitor_analysis = self.competitor_analyzer.analyze(content, user_id=user_id)
suggested_angles = self.content_angle_generator.generate(content, topic, industry, user_id=user_id)
logger.info(f"Research completed successfully with {len(sources)} sources and {len(search_queries)} search queries")
@@ -179,6 +188,9 @@ class ResearchService:
return filtered_response
except HTTPException:
# Re-raise HTTPException (subscription errors) - let task manager handle it
raise
except Exception as e:
error_message = str(e)
logger.error(f"Research failed: {error_message}")
@@ -244,7 +256,7 @@ class ResearchService:
)
@log_function_call("research_with_progress")
async def research_with_progress(self, request: BlogResearchRequest, task_id: str) -> BlogResearchResponse:
async def research_with_progress(self, request: BlogResearchRequest, task_id: str, user_id: str) -> BlogResearchResponse:
"""
Research method with progress updates for real-time feedback.
"""
@@ -281,6 +293,11 @@ class ResearchService:
logger.info(f"Returning cached research result for keywords: {request.keywords}")
return BlogResearchResponse(**cached_result)
# User ID validation (validation logic is now in Google Grounding provider)
if not user_id:
await task_manager.update_progress(task_id, "❌ Error: User ID is required for research operation")
raise ValueError("user_id is required for research operation. Please provide Clerk user ID.")
# Cache miss - proceed with API call
await task_manager.update_progress(task_id, "🌐 Cache miss - connecting to Google Search grounding...")
logger.info(f"Cache miss - making API call for keywords: {request.keywords}")
@@ -307,11 +324,20 @@ class ResearchService:
await task_manager.update_progress(task_id, "🤖 Making AI request to Gemini with Google Search grounding...")
# Single Gemini call with native Google Search grounding - no fallbacks
gemini_result = await gemini.generate_grounded_content(
prompt=research_prompt,
content_type="research",
max_tokens=2000
)
# Validation is handled inside generate_grounded_content when validate_subsequent_operations=True
try:
gemini_result = await gemini.generate_grounded_content(
prompt=research_prompt,
content_type="research",
max_tokens=2000,
user_id=user_id,
validate_subsequent_operations=True # Validates Google Grounding + 3 LLM calls
)
except HTTPException as http_error:
# Re-raise HTTPException so it can be properly handled by task manager
logger.error(f"Subscription limit exceeded for research: {http_error.detail}")
await task_manager.update_progress(task_id, f"❌ Subscription limit exceeded: {http_error.detail.get('message', str(http_error.detail)) if isinstance(http_error.detail, dict) else str(http_error.detail)}")
raise # Re-raise HTTPException to preserve status code and error details
await task_manager.update_progress(task_id, "📊 Processing research results and extracting insights...")
# Extract sources from grounding metadata
@@ -327,9 +353,9 @@ class ResearchService:
await task_manager.update_progress(task_id, "🔍 Analyzing keywords and content angles...")
# Parse the comprehensive response for different analysis components
content = gemini_result.get("content", "")
keyword_analysis = self.keyword_analyzer.analyze(content, request.keywords)
competitor_analysis = self.competitor_analyzer.analyze(content)
suggested_angles = self.content_angle_generator.generate(content, topic, industry)
keyword_analysis = self.keyword_analyzer.analyze(content, request.keywords, user_id=user_id)
competitor_analysis = self.competitor_analyzer.analyze(content, user_id=user_id)
suggested_angles = self.content_angle_generator.generate(content, topic, industry, user_id=user_id)
await task_manager.update_progress(task_id, "💾 Caching results for future use...")
logger.info(f"Research completed successfully with {len(sources)} sources and {len(search_queries)} search queries")
@@ -373,6 +399,9 @@ class ResearchService:
return filtered_response
except HTTPException:
# Re-raise HTTPException (subscription errors) - let task manager handle it
raise
except Exception as e:
error_message = str(e)
logger.error(f"Research failed: {error_message}")

15
backend/services/blog_writer/seo/blog_content_seo_analyzer.py
View File

@@ -34,17 +34,21 @@ class BlogContentSEOAnalyzer:
logger.info("BlogContentSEOAnalyzer initialized")
async def analyze_blog_content(self, blog_content: str, research_data: Dict[str, Any], blog_title: Optional[str] = None) -> Dict[str, Any]:
async def analyze_blog_content(self, blog_content: str, research_data: Dict[str, Any], blog_title: Optional[str] = None, user_id: str = None) -> Dict[str, Any]:
"""
Main analysis method with parallel processing
Args:
blog_content: The blog content to analyze
research_data: Research data containing keywords and other insights
blog_title: Optional blog title
user_id: Clerk user ID for subscription checking (required)
Returns:
Comprehensive SEO analysis results
"""
if not user_id:
raise ValueError("user_id is required for subscription checking. Please provide Clerk user ID.")
try:
logger.info("Starting blog content SEO analysis")
@@ -58,7 +62,7 @@ class BlogContentSEOAnalyzer:
# Phase 2: Single AI analysis for structured insights
logger.info("Running AI analysis")
ai_insights = await self._run_ai_analysis(blog_content, keywords_data, non_ai_results)
ai_insights = await self._run_ai_analysis(blog_content, keywords_data, non_ai_results, user_id=user_id)
# Phase 3: Compile and format results
logger.info("Compiling results")
@@ -599,8 +603,10 @@ class BlogContentSEOAnalyzer:
return recommendations
async def _run_ai_analysis(self, blog_content: str, keywords_data: Dict[str, Any], non_ai_results: Dict[str, Any]) -> Dict[str, Any]:
async def _run_ai_analysis(self, blog_content: str, keywords_data: Dict[str, Any], non_ai_results: Dict[str, Any], user_id: str = None) -> Dict[str, Any]:
"""Run single AI analysis for structured insights (provider-agnostic)"""
if not user_id:
raise ValueError("user_id is required for subscription checking. Please provide Clerk user ID.")
try:
# Prepare context for AI analysis
context = {
@@ -658,7 +664,8 @@ class BlogContentSEOAnalyzer:
ai_response = llm_text_gen(
prompt=prompt,
json_struct=schema,
system_prompt=None
system_prompt=None,
user_id=user_id # Pass user_id for subscription checking
)
return ai_response

26
backend/services/blog_writer/seo/blog_seo_metadata_generator.py
View File

@@ -28,7 +28,8 @@ class BlogSEOMetadataGenerator:
blog_title: str,
research_data: Dict[str, Any],
outline: Optional[List[Dict[str, Any]]] = None,
seo_analysis: Optional[Dict[str, Any]] = None
seo_analysis: Optional[Dict[str, Any]] = None,
user_id: str = None
) -> Dict[str, Any]:
"""
Generate comprehensive SEO metadata using maximum 2 AI calls
@@ -39,10 +40,13 @@ class BlogSEOMetadataGenerator:
research_data: Research data containing keywords and insights
outline: Outline structure with sections and headings
seo_analysis: SEO analysis results from previous phase
user_id: Clerk user ID for subscription checking (required)
Returns:
Comprehensive metadata including all SEO elements
"""
if not user_id:
raise ValueError("user_id is required for subscription checking. Please provide Clerk user ID.")
try:
logger.info("Starting comprehensive SEO metadata generation")
@@ -53,13 +57,13 @@ class BlogSEOMetadataGenerator:
# Call 1: Generate core SEO metadata (parallel with Call 2)
logger.info("Generating core SEO metadata")
core_metadata_task = self._generate_core_metadata(
blog_content, blog_title, keywords_data, outline, seo_analysis
blog_content, blog_title, keywords_data, outline, seo_analysis, user_id=user_id
)
# Call 2: Generate social media and structured data (parallel with Call 1)
logger.info("Generating social media and structured data")
social_metadata_task = self._generate_social_metadata(
blog_content, blog_title, keywords_data, outline, seo_analysis
blog_content, blog_title, keywords_data, outline, seo_analysis, user_id=user_id
)
# Wait for both calls to complete
@@ -114,9 +118,12 @@ class BlogSEOMetadataGenerator:
blog_title: str,
keywords_data: Dict[str, Any],
outline: Optional[List[Dict[str, Any]]] = None,
seo_analysis: Optional[Dict[str, Any]] = None
seo_analysis: Optional[Dict[str, Any]] = None,
user_id: str = None
) -> Dict[str, Any]:
"""Generate core SEO metadata (Call 1)"""
if not user_id:
raise ValueError("user_id is required for subscription checking. Please provide Clerk user ID.")
try:
# Create comprehensive prompt for core metadata
prompt = self._create_core_metadata_prompt(
@@ -170,7 +177,8 @@ class BlogSEOMetadataGenerator:
ai_response_raw = llm_text_gen(
prompt=prompt,
json_struct=schema,
system_prompt=None
system_prompt=None,
user_id=user_id # Pass user_id for subscription checking
)
# Handle response: llm_text_gen may return dict (from structured JSON) or str (needs parsing)
@@ -215,9 +223,12 @@ class BlogSEOMetadataGenerator:
blog_title: str,
keywords_data: Dict[str, Any],
outline: Optional[List[Dict[str, Any]]] = None,
seo_analysis: Optional[Dict[str, Any]] = None
seo_analysis: Optional[Dict[str, Any]] = None,
user_id: str = None
) -> Dict[str, Any]:
"""Generate social media and structured data (Call 2)"""
if not user_id:
raise ValueError("user_id is required for subscription checking. Please provide Clerk user ID.")
try:
# Create comprehensive prompt for social metadata
prompt = self._create_social_metadata_prompt(
@@ -274,7 +285,8 @@ class BlogSEOMetadataGenerator:
ai_response_raw = llm_text_gen(
prompt=prompt,
json_struct=schema,
system_prompt=None
system_prompt=None,
user_id=user_id # Pass user_id for subscription checking
)
# Handle response: llm_text_gen may return dict (from structured JSON) or str (needs parsing)

6
backend/services/blog_writer/seo/blog_seo_recommendation_applier.py
View File

@@ -20,8 +20,11 @@ class BlogSEORecommendationApplier:
def __init__(self):
logger.debug("Initialized BlogSEORecommendationApplier")
async def apply_recommendations(self, payload: Dict[str, Any]) -> Dict[str, Any]:
async def apply_recommendations(self, payload: Dict[str, Any], user_id: str = None) -> Dict[str, Any]:
"""Apply recommendations and return updated content."""
if not user_id:
raise ValueError("user_id is required for subscription checking. Please provide Clerk user ID.")
title = payload.get("title", "Untitled Blog")
sections: List[Dict[str, Any]] = payload.get("sections", [])
@@ -88,6 +91,7 @@ class BlogSEORecommendationApplier:
prompt,
None,
schema,
user_id, # Pass user_id for subscription checking
)
if not result or result.get("error"):