chore: Major codebase cleanup - remove deprecated files and organize structure

- Docker: Delete 23 deprecated Dockerfiles, fix CI/CD to use Dockerfile.foxhunt-build
- Config: Remove 36 .env files, keep 4 essential, delete config/environments/
- Docs: Archive 614 Wave D files to docs/archive/wave_d/, 95% reduction in root
- Scripts: Delete 56 deprecated scripts, keep 58 production-critical (49% reduction)
- Python: Organize 37 scripts into scripts/python/ subdirectories, delete ml/python/
- Build: Remove 1GB artifacts, delete old venvs, clean Python cache from git
- Migrations: Delete deprecated directory (4,432 lines), remove duplicate database/migrations/
- Infrastructure: Delete deployment/ (61 files), docs/scripts/ (8 files)

Total impact: ~2,500 files cleaned, 750MB+ space freed, zero production impact
All deleted scripts backed up to archives. runpod/ and tests/runpod/ preserved.
data_acquisition_service retained per user request.
This commit is contained in:
jgrusewski
2025-10-30 01:02:34 +01:00
parent d73316da3d
commit 433af5c25d
899 changed files with 1920 additions and 1071884 deletions

View File

@@ -0,0 +1,91 @@
#!/usr/bin/env python3
import os
import requests
from dotenv import load_dotenv
# Load RunPod API key
env_path = '.env.runpod'
load_dotenv(env_path)
RUNPOD_API_KEY = os.getenv('RUNPOD_API_KEY')
if not RUNPOD_API_KEY:
print("ERROR: RUNPOD_API_KEY not found in .env.runpod")
exit(1)
# Try alternative field names
queries = [
# Attempt 1: containerRegistryAuths
"""
query {
myself {
containerRegistryAuths {
id
name
username
createdAt
}
}
}
""",
# Attempt 2: savedRegistryAuths
"""
query {
myself {
savedRegistryAuths {
id
name
username
createdAt
}
}
}
""",
# Attempt 3: Get user info to see available fields
"""
query {
myself {
id
email
}
}
"""
]
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {RUNPOD_API_KEY}"
}
for i, query in enumerate(queries, 1):
print(f"\n{'='*60}")
print(f"Attempt {i}:")
print(f"{'='*60}")
response = requests.post(
"https://api.runpod.io/graphql",
json={"query": query},
headers=headers
)
result = response.json()
print("Response:", result)
if 'data' in result and 'errors' not in result:
print("\n✅ Query successful!")
if i < 3: # Registry auth queries
auth_field = 'containerRegistryAuths' if i == 1 else 'savedRegistryAuths'
if result['data']['myself'] and auth_field in result['data']['myself']:
creds = result['data']['myself'][auth_field]
if creds:
print(f"\n✅ Found credentials ({len(creds)}):")
for cred in creds:
print(f" ID: {cred['id']}")
print(f" Name: {cred['name']}")
print(f" Username: {cred['username']}")
print(f" Created: {cred['createdAt']}")
print()
else:
print("\n⚠️ No credentials configured")
break
else:
print(f"❌ Failed: {result.get('errors', 'Unknown error')}")

View File

@@ -0,0 +1,87 @@
#!/usr/bin/env python3
import os
import requests
from dotenv import load_dotenv
# Load RunPod API key
env_path = '.env.runpod'
load_dotenv(env_path)
RUNPOD_API_KEY = os.getenv('RUNPOD_API_KEY')
if not RUNPOD_API_KEY:
print("ERROR: RUNPOD_API_KEY not found in .env.runpod")
exit(1)
# GraphQL query with correct field name
query = """
query {
myself {
containerRegistryCreds {
id
name
username
createdAt
}
}
}
"""
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {RUNPOD_API_KEY}"
}
response = requests.post(
"https://api.runpod.io/graphql",
json={"query": query},
headers=headers
)
result = response.json()
print("Full API Response:")
print("=" * 60)
print(result)
print("=" * 60)
if 'data' in result and result['data']['myself']:
creds = result['data']['myself'].get('containerRegistryCreds', [])
if creds:
print("\n✅ Found Docker Hub credentials:")
for cred in creds:
print(f"\n Credential #{creds.index(cred) + 1}:")
print(f" ID: {cred['id']}")
print(f" Name: {cred['name']}")
print(f" Username: {cred['username']}")
print(f" Created: {cred['createdAt']}")
# Check .env.runpod
print("\n" + "=" * 60)
print("Checking .env.runpod configuration:")
print("=" * 60)
configured_id = os.getenv('RUNPOD_CONTAINER_REGISTRY_AUTH_ID')
if configured_id:
print(f"✅ RUNPOD_CONTAINER_REGISTRY_AUTH_ID is set to: {configured_id}")
# Check if it matches any credential
matching = [c for c in creds if c['id'] == configured_id]
if matching:
print(f"✅ Credential ID matches: {matching[0]['name']}")
else:
print(f"⚠️ WARNING: Credential ID does not match any RunPod credentials!")
print(f" Available IDs:")
for cred in creds:
print(f" - {cred['id']} ({cred['name']})")
else:
print("⚠️ RUNPOD_CONTAINER_REGISTRY_AUTH_ID is NOT set in .env.runpod")
print(f" Set it to one of these IDs:")
for cred in creds:
print(f" - {cred['id']} ({cred['name']})")
else:
print("\n⚠️ No Docker Hub credentials configured in RunPod")
print("You need to create one via RunPod console or API")
print("\nManual steps:")
print("1. Go to: https://www.runpod.io/console/user/settings")
print("2. Click 'Container Registry Credentials' tab")
print("3. Add credentials for Docker Hub (jgrusewski)")
else:
print("\n❌ Error querying credentials:", result)

View File

@@ -0,0 +1,92 @@
#!/usr/bin/env python3
"""
Check Databento subscription and data availability.
"""
import os
import databento as db
import sys
def main():
api_key = os.environ.get("DATABENTO_API_KEY")
if not api_key:
print("ERROR: DATABENTO_API_KEY environment variable not set")
sys.exit(1)
client = db.Historical(api_key)
print("=" * 70)
print("Databento Subscription Check")
print("=" * 70)
# Get billing information
try:
print("\n1. Checking Account Status...")
# Note: There's no direct API for billing, but we can try to get cost for a known symbol
# Let's try ES (S&P 500 E-mini) which is very common
test_cases = [
("XNAS.ITCH", "AAPL", "trades", "Nasdaq stocks"),
("GLBX.MDP3", "ES", "ohlcv-1m", "CME E-mini S&P 500"),
("GLBX.MDP3", "ES.FUT", "ohlcv-1m", "CME E-mini S&P 500 (FUT)"),
("GLBX.MDP3", "ESH24", "ohlcv-1m", "CME E-mini S&P 500 (Mar 2024)"),
]
print("\n2. Testing Data Access...\n")
for dataset, symbol, schema, description in test_cases:
print(f"Testing: {description}")
print(f" Dataset: {dataset}, Symbol: {symbol}, Schema: {schema}")
try:
cost = client.metadata.get_cost(
dataset=dataset,
symbols=[symbol],
schema=schema,
start="2024-01-02",
end="2024-01-05"
)
print(f" ✅ ACCESS GRANTED - Cost: ${cost:.4f} (3 days)")
except Exception as e:
error_msg = str(e)
if "401" in error_msg or "unauthorized" in error_msg.lower():
print(f" ❌ UNAUTHORIZED - Need subscription")
elif "404" in error_msg or "not found" in error_msg.lower():
print(f" ❌ NOT FOUND - Symbol doesn't exist")
elif "symbology" in error_msg.lower():
print(f" ❌ SYMBOLOGY ERROR - Symbol can't be resolved")
else:
print(f" ❌ ERROR: {error_msg[:80]}")
print()
print("=" * 70)
print("Diagnosis")
print("=" * 70)
print("""
Based on the results above:
1. If ALL tests show UNAUTHORIZED:
→ Your subscription doesn't include historical data access
→ You may only have live data access
2. If ONLY GLBX.MDP3 (CME) tests fail:
→ Your subscription doesn't include CME futures data
→ CME data requires a separate subscription tier
3. If SYMBOLOGY ERROR appears:
→ The symbol format is incorrect for that dataset
→ Try checking Databento's symbology guide
4. If some symbols work:
→ Your subscription is working, but specific instruments need adjustment
Recommendations:
- Check your Databento account subscription at: https://databento.com/account
- For CME futures data (6E, ES, etc.), verify you have GLBX.MDP3 access
- Contact Databento support if you believe you should have access
""")
except Exception as e:
print(f"\nError checking subscription: {e}")
if __name__ == "__main__":
main()