fix: correcciones de scraping/DB y mejoras de robustez

Sección crítica:
- is_blacklisted: match por dominio/subdominio exacto (antes "x.com" como
  substring bloqueaba netflix.com, phoenix.com, etc.)
- normalize_url: conserva el query string (rompía YouTube watch?v= y URLs
  con ?id=); solo borra el fragment
- get_db: PRAGMA busy_timeout=5000 para evitar "database is locked" en
  /compare y watches solapados
- OllamaClient.embed: usa OLLAMA_EMBED_MODEL en vez del modelo de chat
- log_api_call: coste por modelo (opus/sonnet/haiku) en vez de Haiku fijo

Mejoras:
- src/llm.py: cliente Anthropic compartido y cacheado (antes se instanciaba
  uno por cada llamada/chunk)
- SEARXNG_URL configurable via env
- get_running_loop() en vez de get_event_loop() (deprecado)
- soup.title.get_text() robusto ante <title> con tags anidados
- limpieza: import muerto, total_words duplicado, w_id no usado

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
ChemaVX
2026-06-15 14:38:03 +00:00
co-authored by Claude Opus 4.8
parent fd9aaa193b
commit bf275b7f82
7 changed files with 67 additions and 25 deletions
+5 -8
View File
@@ -12,6 +12,7 @@ import time
import structlog
from src.config import settings
from src.llm import get_anthropic_client
from src.processor.processor import OllamaClient, ContentProcessor
from src.db.database import ResearchDB, OutputType
@@ -442,10 +443,9 @@ class OutputGenerator:
async def _generate_with_claude(self, prompt: str, system: str, output_type: OutputType,
session_id: int | None = None) -> str:
import anthropic
max_tokens = 4096 if output_type == OutputType.THREAD else 16000
try:
client = anthropic.AsyncAnthropic(api_key=settings.anthropic_api_key)
client = get_anthropic_client()
msg = await client.messages.create(
model=settings.claude_model,
max_tokens=max_tokens,
@@ -613,9 +613,8 @@ class OutputGenerator:
async def _generate_raw(self, prompt: str,
session_id: int | None = None) -> str:
if settings.anthropic_api_key:
import anthropic
try:
client = anthropic.AsyncAnthropic(api_key=settings.anthropic_api_key)
client = get_anthropic_client()
msg = await client.messages.create(
model=settings.claude_model,
max_tokens=2048,
@@ -819,8 +818,7 @@ async def generate_diff_summary(
)
try:
import anthropic
client = anthropic.AsyncAnthropic(api_key=settings.anthropic_api_key)
client = get_anthropic_client()
prompt = (
f'Analiza el siguiente material de investigación sobre "{topic}" '
f'y genera un resumen BREVE (máximo 300 palabras) de las novedades '
@@ -906,8 +904,7 @@ async def generate_comparison(
)
try:
import anthropic
client = anthropic.AsyncAnthropic(api_key=settings.anthropic_api_key)
client = get_anthropic_client()
msg = await client.messages.create(
model=settings.claude_model,
max_tokens=8192,