dragonked2/alphacode/debug

WHAT:    What exactly happens? (error message, wrong behavior, crash)
WHEN:    When does it happen? (specific input, time, condition)
WHERE:   Where does it happen? (file, function, line)
HOW:     How do you reproduce it? (steps to trigger)
SCOPE:   How many people affected? (all users, some, one)

# Check logs
tail -100 /var/log/app/error.log
docker logs container_name --tail 100
 
# Check recent changes
git log --oneline -10
git diff HEAD~3
 
# Check system state
free -h          # memory
df -h            # disk
top              # CPU
netstat -tlnp    # ports

TypeError: Cannot read property 'x' of undefined

ECONNREFUSED 127.0.0.1:5432
connect EHOSTUNREACH 10.0.0.1:3306

ETIMEDOUT: Connection timed out after 30000ms
Operation timed out after 5000ms

JavaScript heap out of memory
MemoryError: Unable to allocate memory

# Compile with debug info
cargo build
 
# Run with RUST_BACKTRACE
RUST_BACKTRACE=1 cargo run
 
# Run with debug assertions
cargo test
 
# Use rust-gdb
rust-gdb target/debug/myapp
(gdb) run
(gdb) backtrace
(gdb) info locals

// Console debugging
console.log('variable:', variable);
console.table(arrayOfObjects);
console.time('operation');
// ... code ...
console.timeEnd('operation');
// Node.js inspector
node --inspect app.js
# Then open chrome://inspect in Chrome
// Chrome DevTools
// Sources tab → Breakpoints → Step through code
// Profiler tab → Record → Find hot functions
// Memory tab → Take heap snapshot → Compare

# Interactive debugging
import pdb; pdb.set_trace()  # Python 3.6-
breakpoint()                  # Python 3.7+
# In debugger:
# n (next line)
# s (step into)
# c (continue)
# p variable (print)
# l (list source)
# q (quit)
# Better debugger: ipdb
import ipdb; ipdb.set_trace()
# Traceback inspection
import traceback
try:
    risky_operation()
except Exception:
    traceback.print_exc()

# Delve debugger
dlv debug main.go
(dlv) break main.main
(dlv) continue
(dlv) step
(dlv) print variable
(dlv) goroutines
(dlv) stack
 
# Race detector
go run -race main.go
go test -race ./...

ERROR   — something broke, needs immediate attention
WARN    — something unexpected, but not broken
INFO    — normal operations worth recording
DEBUG   — detailed info for troubleshooting
TRACE   — extremely detailed, function-level

{
  "timestamp": "2024-01-15T10:30:00Z",
  "level": "error",
  "message": "Failed to process payment",
  "error": "Connection refused",
  "user_id": "usr_123",
  "order_id": "ord_456",
  "amount": 99.99,
  "provider": "stripe"
}

# Check DNS resolution
dig example.com
nslookup example.com
 
# Check connectivity
curl -v https://api.example.com/health
telnet api.example.com 443
 
# Capture traffic
tcpdump -i eth0 port 443
wireshark  # GUI packet analyzer
 
# Test API endpoints
curl -X POST https://api.example.com/users \
  -H "Content-Type: application/json" \
  -d '{"name": "test"}' \
  -v

# Find process using a port
lsof -i :3000
ss -tlnp | grep 3000
 
# strace a process
strace -p <pid> -e trace=network
 
# Check open file descriptors
ls -la /proc/<pid>/fd
 
# Check environment variables
cat /proc/<pid>/environ | tr '\0' '\n'

-- Check for locks
SELECT * FROM pg_locks WHERE NOT granted;
 
-- Check slow queries
SELECT * FROM pg_stat_activity WHERE state = 'active' AND query_start < NOW() - INTERVAL '5 minutes';
 
-- Check table sizes
SELECT relname, pg_size_pretty(pg_total_relation_size(relid))
FROM pg_catalog.pg_statio_user_tables
ORDER BY pg_total_relation_size(relid) DESC;
 
-- Check index usage
SELECT relname, indexrelname, idx_scan
FROM pg_stat_user_indexes
ORDER BY idx_scan ASC;

# Write a test that reproduces the bug
def test_user_email_uniqueness():
    """Regression: concurrent signups could create duplicate emails."""
    create_user(email="test@example.com")
    with pytest.raises(IntegrityError):
        create_user(email="test@example.com")

# Validate inputs at boundaries
def process_order(order_data: dict) -> Order:
    if not order_data.get("items"):
        raise ValueError("Order must have at least one item")
    if order_data["total"] < 0:
        raise ValueError("Order total cannot be negative")
    # ... proceed with processing

# Alert on conditions that caused the bug
if error_rate > 0.01:
    alert("Error rate exceeded 1% threshold")
if response_time_p99 > 2000:
    alert("P99 response time exceeded 2 seconds")