error-handling

What this skill does

# Error Handling & Observability

### When to Load

- **Trigger**: Try/catch patterns, retry logic, error responses, circuit breakers, structured logging
- **Skip**: No error handling or observability involved in the current task

## Error Handling Workflow

Copy this checklist and track progress:

```
Error Handling Progress:
- [ ] Step 1: Define error taxonomy (categories and severity)
- [ ] Step 2: Implement error handling by layer
- [ ] Step 3: Set up structured logging
- [ ] Step 4: Add retry and circuit breaker patterns
- [ ] Step 5: Configure error tracking service
- [ ] Step 6: Define user-facing error messages
- [ ] Step 7: Validate against anti-patterns checklist
```

## Error Handling Patterns by Language

### JavaScript / TypeScript

```typescript
// Custom error hierarchy
class AppError extends Error {
  constructor(
    message: string,
    public statusCode: number = 500,
    public code: string = "INTERNAL_ERROR",
    public isOperational: boolean = true,
  ) {
    super(message);
    this.name = this.constructor.name;
  }
}
class NotFoundError extends AppError {
  constructor(resource: string, id: string) {
    super(`${resource} with id ${id} not found`, 404, "NOT_FOUND");
  }
}
class ValidationError extends AppError {
  constructor(public errors: Record<string, string[]>) {
    super("Validation failed", 400, "VALIDATION_ERROR");
  }
}

// WRONG: Swallowing errors silently
try {
  await saveUser(data);
} catch (e) {
  // nothing here -- bug hides forever
}

// WRONG: Catching and re-throwing without context
try {
  await saveUser(data);
} catch (e) {
  throw e; // pointless try/catch
}

// CORRECT: Add context, handle or propagate
try {
  await saveUser(data);
} catch (error) {
  if (error instanceof ValidationError) {
    return res.status(400).json({ errors: error.errors });
  }
  logger.error("Failed to save user", { error, userId: data.id });
  throw new AppError("Unable to save user", 500, "USER_SAVE_FAILED");
}
```

### Express Global Error Handler

```typescript
// Centralized error handler middleware (must have 4 params)
app.use((err: Error, req: Request, res: Response, next: NextFunction) => {
  if (err instanceof AppError) {
    logger.warn("Operational error", {
      code: err.code,
      statusCode: err.statusCode,
      path: req.path,
    });
    return res.status(err.statusCode).json({
      error: { code: err.code, message: err.message },
    });
  }

  // Unexpected errors -- these are bugs
  logger.error("Unexpected error", {
    error: err.message,
    stack: err.stack,
    path: req.path,
  });
  res.status(500).json({
    error: { code: "INTERNAL_ERROR", message: "An unexpected error occurred" },
  });
});
```

### Python

```python
# Custom exception hierarchy
class AppError(Exception):
    def __init__(self, message: str, code: str = "INTERNAL_ERROR", status: int = 500):
        self.message = message
        self.code = code
        self.status = status
        super().__init__(message)

class NotFoundError(AppError):
    def __init__(self, resource: str, id: str):
        super().__init__(f"{resource} {id} not found", "NOT_FOUND", 404)

class ValidationError(AppError):
    def __init__(self, errors: dict[str, list[str]]):
        self.errors = errors
        super().__init__("Validation failed", "VALIDATION_ERROR", 400)

# WRONG: Bare except
try:
    result = process(data)
except:  # catches SystemExit, KeyboardInterrupt too!
    pass

# CORRECT: Specific exceptions, proper logging
try:
    result = process(data)
except ValidationError as e:
    logger.warning("Validation failed", extra={"errors": e.errors})
    raise
except DatabaseError as e:
    logger.error("Database error during processing", exc_info=True)
    raise AppError("Processing failed", "PROCESS_FAILED") from e
```

### Go

```go
// Define sentinel errors and custom types
var (
    ErrNotFound     = errors.New("resource not found")
    ErrUnauthorized = errors.New("unauthorized")
)

type ValidationError struct {
    Field   string
    Message string
}

func (e *ValidationError) Error() string {
    return fmt.Sprintf("validation: %s - %s", e.Field, e.Message)
}

// WRONG: Ignoring errors
data, _ := json.Marshal(user)  // error silently dropped

// WRONG: Only returning error string
if err != nil {
    return fmt.Errorf("failed: %s", err.Error())  // loses error chain
}

// CORRECT: Wrap errors with context
if err != nil {
    return fmt.Errorf("saving user %s: %w", user.ID, err)  // %w preserves chain
}

// CORRECT: Check error types
if errors.Is(err, ErrNotFound) {
    http.Error(w, "Not found", http.StatusNotFound)
    return
}
var valErr *ValidationError
if errors.As(err, &valErr) {
    http.Error(w, valErr.Error(), http.StatusBadRequest)
    return
}
```

## Structured Logging

### JSON Log Format

```typescript
// WRONG: Unstructured string logs
console.log(`User ${userId} created order ${orderId} at ${new Date()}`);
// Impossible to parse, filter, or aggregate

// CORRECT: Structured JSON logs
import pino from "pino";

const logger = pino({
  level: process.env.LOG_LEVEL || "info",
  formatters: {
    level: (label) => ({ level: label }),
  },
  redact: ["req.headers.authorization", "password", "ssn"],
});
logger.info({
  event: "order_created",
  userId: "123",
  orderId: "456",
  amount: 99.99,
  currency: "USD",
});
// Output: {"level":"info","event":"order_created","userId":"123","orderId":"456",...}
```

### Correlation IDs

```typescript
// Middleware to propagate correlation ID across requests
import { randomUUID } from "crypto";
import { AsyncLocalStorage } from "async_hooks";

const asyncStorage = new AsyncLocalStorage<{ correlationId: string }>();

app.use((req, res, next) => {
  const correlationId =
    (req.headers["x-correlation-id"] as string) || randomUUID();
  res.setHeader("x-correlation-id", correlationId);

  asyncStorage.run({ correlationId }, () => next());
});

// Logger automatically includes correlation ID
function getLogger() {
  const store = asyncStorage.getStore();
  return logger.child({ correlationId: store?.correlationId });
}

// Usage in any handler or service
const log = getLogger();
log.info({ event: "payment_processed", amount: 50 });
// Output includes correlationId automatically
```

### Log Levels Guide

```
TRACE: Extremely detailed (loop iterations, variable values)  -- dev only
DEBUG: Diagnostic info (function entry/exit, state changes)   -- dev/staging
INFO:  Normal operations (request handled, job completed)     -- all envs
WARN:  Unexpected but recoverable (retry succeeded, fallback used)
ERROR: Operation failed (unhandled exception, service down)
FATAL: Application cannot continue (missing config, DB unreachable)

Production default: INFO
Never log: passwords, tokens, PII, credit cards, full request bodies
```

## Error Boundaries and Graceful Degradation

### React Error Boundary

```tsx
class ErrorBoundary extends React.Component<
  { fallback: React.ReactNode; children: React.ReactNode },
  { hasError: boolean; error?: Error }
> {
  state = { hasError: false, error: undefined };
  static getDerivedStateFromError(error: Error) {
    return { hasError: true, error };
  }
  componentDidCatch(error: Error, info: React.ErrorInfo) {
    logger.error("React error boundary caught error", {
      error: error.message,
      componentStack: info.componentStack,
    });
  }
  render() {
    return this.state.hasError ? this.props.fallback : this.props.children;
  }
}

// Usage: wrap sections independently
<ErrorBoundary fallback={<p>Dashboard unavailable</p>}>
  <Dashboard />
</ErrorBoundary>
<ErrorBoundary fallback={<p>Sidebar unavailable</p>}>
  <Sidebar />
</ErrorBoundary>
```

### Service Degradation

```typescript
// Graceful degradation: serve stale data when service is down
async function getProductRecommendations(userId: string) {
  try {
    return await recommendationService.get(userId);
  } catch (error) {
    logger.warn("Recommendation service unavailable, using fallback", {
      u