feat(echo-self): tehnici pauza random din fisier
- Creat memory/tehnici-pauza.md cu banca de tehnici (BIROU + ACASA) - Creat tools/pauza_random.py - alege random in functie de ora - Actualizat job respiratie-orar sa foloseasca scriptul - Actualizat job evening-coaching sa actualizeze automat fisierul din insights
This commit is contained in:
Echo
179
tools/content_discovery.py
Executable file
179
tools/content_discovery.py
Executable file
@@ -0,0 +1,179 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Content Discovery - Căutare automată de conținut bazată pe interese.
|
||||
Rulează noaptea, pregătește note pentru morning report.
|
||||
|
||||
Usage: python3 content_discovery.py [--dry-run]
|
||||
"""
|
||||
|
||||
import os
|
||||
import json
|
||||
import re
|
||||
from datetime import datetime, timedelta
|
||||
from pathlib import Path
|
||||
|
||||
WORKSPACE = Path(__file__).parent.parent
|
||||
MEMORY_DIR = WORKSPACE / "memory"
|
||||
INSIGHTS_DIR = WORKSPACE / "kb" / "insights"
|
||||
USER_MD = WORKSPACE / "USER.md"
|
||||
|
||||
# Interese de bază (fallback)
|
||||
BASE_INTERESTS = [
|
||||
"NLP Sleight of Mouth patterns",
|
||||
"comunicare nonviolentă Marshall Rosenberg",
|
||||
"James Clear atomic habits productivity",
|
||||
"Monica Ion mindset antreprenor",
|
||||
"dezvoltare personală coaching",
|
||||
"Rumi quotes wisdom philosophy",
|
||||
"stoicism practical philosophy",
|
||||
"noua medicină germanică",
|
||||
"post negru fasting benefits",
|
||||
"80/20 principle productivity",
|
||||
"leadership entrepreneurship",
|
||||
]
|
||||
|
||||
def get_recent_files(directory: Path, days: int = 3) -> list:
|
||||
"""Get files modified in last N days"""
|
||||
cutoff = datetime.now() - timedelta(days=days)
|
||||
files = []
|
||||
if directory.exists():
|
||||
for f in directory.glob("*.md"):
|
||||
if f.stat().st_mtime > cutoff.timestamp():
|
||||
files.append(f)
|
||||
return sorted(files, key=lambda x: x.stat().st_mtime, reverse=True)
|
||||
|
||||
def extract_topics_from_file(filepath: Path) -> list:
|
||||
"""Extract potential topics/keywords from a markdown file"""
|
||||
topics = []
|
||||
try:
|
||||
content = filepath.read_text(encoding='utf-8')
|
||||
|
||||
# Extract from headers
|
||||
headers = re.findall(r'^##?\s+(.+)$', content, re.MULTILINE)
|
||||
topics.extend(headers[:5])
|
||||
|
||||
# Extract YouTube video titles
|
||||
yt_titles = re.findall(r'^#\s+(.+)$', content, re.MULTILINE)
|
||||
topics.extend(yt_titles[:3])
|
||||
|
||||
# Extract @tags
|
||||
tags = re.findall(r'@(\w+)', content)
|
||||
topics.extend(tags[:5])
|
||||
|
||||
# Extract bold terms
|
||||
bold = re.findall(r'\*\*([^*]+)\*\*', content)
|
||||
topics.extend([b for b in bold if len(b) < 50][:5])
|
||||
|
||||
except Exception as e:
|
||||
print(f" Warning: Could not read {filepath}: {e}")
|
||||
|
||||
return list(set(topics))
|
||||
|
||||
def get_recent_topics() -> list:
|
||||
"""Analyze recent memory and insights to find current interests"""
|
||||
recent_topics = []
|
||||
|
||||
# Check recent memory files
|
||||
print("Scanning recent memory...")
|
||||
for f in get_recent_files(MEMORY_DIR, days=3):
|
||||
topics = extract_topics_from_file(f)
|
||||
recent_topics.extend(topics)
|
||||
print(f" {f.name}: {len(topics)} topics")
|
||||
|
||||
# Check recent insights
|
||||
print("Scanning recent insights...")
|
||||
for f in get_recent_files(INSIGHTS_DIR, days=3):
|
||||
topics = extract_topics_from_file(f)
|
||||
recent_topics.extend(topics)
|
||||
print(f" {f.name}: {len(topics)} topics")
|
||||
|
||||
# Check recent YouTube notes
|
||||
yt_dir = WORKSPACE / "kb" / "youtube"
|
||||
print("Scanning recent YouTube notes...")
|
||||
for f in get_recent_files(yt_dir, days=3):
|
||||
topics = extract_topics_from_file(f)
|
||||
recent_topics.extend(topics)
|
||||
print(f" {f.name}: {len(topics)} topics")
|
||||
|
||||
return list(set(recent_topics))
|
||||
|
||||
def build_search_queries(recent_topics: list, base_interests: list) -> list:
|
||||
"""Build search queries with 60% recent, 40% base interests"""
|
||||
queries = []
|
||||
|
||||
# Filter and clean topics
|
||||
recent_clean = [t for t in recent_topics if len(t) > 3 and len(t) < 100][:10]
|
||||
|
||||
# 60% from recent (if available)
|
||||
if recent_clean:
|
||||
# Pick top 2-3 recent topics
|
||||
for topic in recent_clean[:3]:
|
||||
queries.append({
|
||||
"query": f"{topic} YouTube tutorial",
|
||||
"source": "recent",
|
||||
"topic": topic
|
||||
})
|
||||
|
||||
# 40% from base interests (rotate based on day)
|
||||
day_of_year = datetime.now().timetuple().tm_yday
|
||||
rotated_base = base_interests[day_of_year % len(base_interests):]
|
||||
rotated_base.extend(base_interests[:day_of_year % len(base_interests)])
|
||||
|
||||
for interest in rotated_base[:2]:
|
||||
queries.append({
|
||||
"query": interest,
|
||||
"source": "base",
|
||||
"topic": interest
|
||||
})
|
||||
|
||||
return queries[:5] # Max 5 queries
|
||||
|
||||
def save_discovery_plan(queries: list):
|
||||
"""Save the discovery plan for the agent to execute"""
|
||||
plan = {
|
||||
"generated_at": datetime.now().isoformat(),
|
||||
"queries": queries,
|
||||
"status": "pending",
|
||||
"results": []
|
||||
}
|
||||
|
||||
plan_file = WORKSPACE / "memory" / "content-discovery-plan.json"
|
||||
with open(plan_file, 'w', encoding='utf-8') as f:
|
||||
json.dump(plan, f, indent=2, ensure_ascii=False)
|
||||
|
||||
print(f"\n✅ Plan saved to {plan_file}")
|
||||
return plan_file
|
||||
|
||||
def main(dry_run: bool = False):
|
||||
print("=" * 50)
|
||||
print("🔍 Content Discovery - Pregătire căutare")
|
||||
print(f" Data: {datetime.now().strftime('%Y-%m-%d %H:%M')}")
|
||||
print("=" * 50)
|
||||
|
||||
# 1. Get recent topics
|
||||
recent_topics = get_recent_topics()
|
||||
print(f"\n📌 Topics recente găsite: {len(recent_topics)}")
|
||||
if recent_topics:
|
||||
print(f" Exemple: {recent_topics[:5]}")
|
||||
|
||||
# 2. Build search queries
|
||||
queries = build_search_queries(recent_topics, BASE_INTERESTS)
|
||||
print(f"\n🔎 Queries generate: {len(queries)}")
|
||||
for i, q in enumerate(queries, 1):
|
||||
print(f" {i}. [{q['source']}] {q['query'][:60]}...")
|
||||
|
||||
if dry_run:
|
||||
print("\n⚠️ DRY RUN - nu salvez planul")
|
||||
return
|
||||
|
||||
# 3. Save plan for agent execution
|
||||
plan_file = save_discovery_plan(queries)
|
||||
|
||||
print("\n📋 Următorul pas:")
|
||||
print(" Agentul va citi planul și va executa căutările")
|
||||
print(" Rezultatele vor fi în morning report")
|
||||
|
||||
if __name__ == "__main__":
|
||||
import sys
|
||||
dry_run = "--dry-run" in sys.argv
|
||||
main(dry_run)
|
||||
Reference in New Issue
Block a user