majordomo/llm/errors.go

package llm

import (
	"context"
	"errors"
	"fmt"
	"net"
	"net/http"
	"strings"
	"syscall"
)

// ErrorClass buckets errors for retry/failover decisions.
type ErrorClass int

const (
	// ClassTransient errors may succeed on retry or on another target:
	// rate limits, server errors, timeouts, connection failures.
	ClassTransient ErrorClass = iota
	// ClassPermanent errors will not improve on retry of the same request:
	// malformed requests, auth failures, model-not-found.
	ClassPermanent
)

// ErrModelNotFound marks a permanent "this target does not know this model"
// condition. Chains advance past it without penalizing the target's health.
var ErrModelNotFound = errors.New("model not found")

// ErrUnsupported marks a request the target cannot serve by declaration —
// e.g. images that cannot be normalized to its capabilities, or a feature
// (tools, structured output) it does not support. Permanent for the target,
// but chains advance past it without penalizing health: another element may
// well be able to serve the request.
var ErrUnsupported = errors.New("request unsupported by target")

// APIError is a structured provider error carrying enough context to
// classify it and to debug it.
type APIError struct {
	// Provider and Model identify the target that failed.
	Provider string
	Model    string

	// Status is the HTTP status code, or 0 when the failure was not an HTTP
	// response (connection error, decode error, ...).
	Status int

	// Code is the provider-specific error code, when one was supplied.
	Code string

	// Message is the provider's human-readable error message.
	Message string

	// Err is the wrapped underlying cause, if any.
	Err error
}

func (e *APIError) Error() string {
	var b strings.Builder
	fmt.Fprintf(&b, "%s/%s", e.Provider, e.Model)
	if e.Status != 0 {
		fmt.Fprintf(&b, ": HTTP %d", e.Status)
	}
	if e.Code != "" {
		fmt.Fprintf(&b, " [%s]", e.Code)
	}
	if e.Message != "" {
		fmt.Fprintf(&b, ": %s", e.Message)
	}
	if e.Err != nil {
		fmt.Fprintf(&b, ": %v", e.Err)
	}
	return b.String()
}

func (e *APIError) Unwrap() error {
	if e.Err != nil {
		return e.Err
	}
	if e.Status == http.StatusNotFound {
		return ErrModelNotFound
	}
	return nil
}

// Classify buckets an error as transient or permanent.
//
// The default policy (overridable via health configuration):
//   - context.Canceled is permanent — the caller gave up; retrying defies
//     their intent. context.DeadlineExceeded is transient.
//   - Network timeouts, refused/reset connections, and DNS failures are
//     transient ("high demand" conditions).
//   - HTTP 400/401/403/404/405/422 (and ErrModelNotFound) are permanent;
//     408/429 and all 5xx are transient.
//   - Anything unrecognized is transient: when in doubt, failing over to the
//     next target in a chain can only help availability.
func Classify(err error) ErrorClass {
	if err == nil {
		return ClassTransient
	}
	if errors.Is(err, context.Canceled) {
		return ClassPermanent
	}
	if errors.Is(err, context.DeadlineExceeded) {
		return ClassTransient
	}
	if errors.Is(err, ErrModelNotFound) || errors.Is(err, ErrUnsupported) {
		return ClassPermanent
	}
	if errors.Is(err, syscall.ECONNREFUSED) || errors.Is(err, syscall.ECONNRESET) {
		return ClassTransient
	}
	if _, ok := errors.AsType[net.Error](err); ok {
		return ClassTransient
	}
	if apiErr, ok := errors.AsType[*APIError](err); ok && apiErr.Status != 0 {
		switch {
		case apiErr.Status == http.StatusRequestTimeout, // 408
			apiErr.Status == http.StatusTooManyRequests, // 429
			apiErr.Status >= 500:
			return ClassTransient
		case apiErr.Status >= 400:
			return ClassPermanent
		}
	}
	return ClassTransient
}