mirror of
https://github.com/coder/coder.git
synced 2026-10-31 11:02:50 +08:00
Susana Ferreira
dba45cede7
## Problem When a key returned 401 or 403, the pool marked it permanently unavailable for the lifetime of that in-memory pool. This is bad UX: a transient auth failure or a briefly-misconfigured key could take a key out of rotation until the operator either restarted Coder or reconfigured the key (even re-saving the same working value). ## Changes - **403 removed from key failover**: it's a per-request authorization failure, not a key-level problem, so it's surfaced to the caller as-is without marking the key or failing over. - **401 now applies a temporary cooldown** (like 429) so the key recovers on its own instead of staying blocked. - When every key is in an auth-failure cooldown, the pool reports a `502` with no `Retry-After`, but the keys still recover automatically once the cooldown elapses. Closes https://linear.app/codercom/issue/AIGOV-421/ai-gateway-a-quarantined-centralized-key-never-recovers-without-a Closes https://linear.app/codercom/issue/AIGOV-533/403s-misclassifying-keys-as-permanently-down-in-ai-gateway > [!NOTE] > Initially generated by Claude Opus 4.7, modified and reviewed by @ssncferreira
117 lines
3.3 KiB
Go
117 lines
3.3 KiB
Go
package intercept
|
|
|
|
import (
|
|
"encoding/json"
|
|
"errors"
|
|
"net/http"
|
|
"time"
|
|
|
|
"github.com/openai/openai-go/v3"
|
|
"github.com/openai/openai-go/v3/shared"
|
|
|
|
"github.com/coder/coder/v2/aibridge/keypool"
|
|
"github.com/coder/coder/v2/aibridge/utils"
|
|
)
|
|
|
|
// OpenAI error type and code constants used by the chatcompletions
|
|
// and responses interceptors. The OpenAI Go SDK does not expose
|
|
// these as typed constants, so we define our own.
|
|
// See https://platform.openai.com/docs/guides/error-codes.
|
|
const (
|
|
OpenAIErrTypeError = "error"
|
|
OpenAIErrTypeAPI = "api_error"
|
|
OpenAIErrTypeRateLimit = "rate_limit_error"
|
|
|
|
OpenAIErrCodeServer = "server_error"
|
|
OpenAIErrCodeRateLimit = "rate_limit_exceeded"
|
|
)
|
|
|
|
var _ error = &ResponseError{}
|
|
|
|
// ResponseError is the OpenAI-shaped error envelope returned to
|
|
// clients. StatusCode and RetryAfter map to HTTP headers, not JSON
|
|
// fields. The chatcompletions and responses interceptors both
|
|
// use the same response error format.
|
|
type ResponseError struct {
|
|
ErrorObject *shared.ErrorObject `json:"error"`
|
|
StatusCode int `json:"-"`
|
|
RetryAfter time.Duration `json:"-"`
|
|
}
|
|
|
|
// NewResponseError builds a ResponseError with the OpenAI-shaped
|
|
// envelope. errType and code should be one of the OpenAIErrType*
|
|
// and OpenAIErrCode* constants defined above.
|
|
func NewResponseError(msg, errType, code string, status int, retryAfter time.Duration) *ResponseError {
|
|
return &ResponseError{
|
|
ErrorObject: &shared.ErrorObject{
|
|
Code: code,
|
|
Message: msg,
|
|
Type: errType,
|
|
},
|
|
StatusCode: status,
|
|
RetryAfter: retryAfter,
|
|
}
|
|
}
|
|
|
|
func (e *ResponseError) Error() string {
|
|
if e.ErrorObject == nil {
|
|
return ""
|
|
}
|
|
return e.ErrorObject.Message
|
|
}
|
|
|
|
// ToResponse marshals e into an *http.Response shaped for the
|
|
// OpenAI API.
|
|
func (e *ResponseError) ToResponse() *http.Response {
|
|
body, err := json.Marshal(e)
|
|
if err != nil {
|
|
body = []byte(`{"error":{"type":"error","message":"error marshaling upstream error","code":"server_error"}}`)
|
|
}
|
|
return utils.NewJSONErrorResponse(e.StatusCode, e.RetryAfter, body)
|
|
}
|
|
|
|
// ResponseErrorFromKeyPool translates a *keypool.Error into
|
|
// a developer-facing ResponseError shaped for the OpenAI API.
|
|
func ResponseErrorFromKeyPool(keyPoolErr *keypool.Error) *ResponseError {
|
|
if keyPoolErr == nil {
|
|
return nil
|
|
}
|
|
switch keyPoolErr.Kind {
|
|
case keypool.ErrorKindPermanent, keypool.ErrorKindUnauthorized:
|
|
return NewResponseError(
|
|
keyPoolErr.Error(),
|
|
OpenAIErrTypeAPI,
|
|
OpenAIErrCodeServer,
|
|
http.StatusBadGateway,
|
|
0,
|
|
)
|
|
case keypool.ErrorKindRateLimited:
|
|
return NewResponseError(
|
|
keyPoolErr.Error(),
|
|
OpenAIErrTypeRateLimit,
|
|
OpenAIErrCodeRateLimit,
|
|
http.StatusTooManyRequests,
|
|
keyPoolErr.RetryAfter,
|
|
)
|
|
default:
|
|
// Fall back to a generic 502.
|
|
return NewResponseError(
|
|
keyPoolErr.Error(),
|
|
OpenAIErrTypeAPI,
|
|
OpenAIErrCodeServer,
|
|
http.StatusBadGateway,
|
|
keyPoolErr.RetryAfter,
|
|
)
|
|
}
|
|
}
|
|
|
|
// ResponseErrorFromAPIError converts an OpenAI SDK error into a
|
|
// ResponseError. Returns nil if err is not an *openai.Error.
|
|
func ResponseErrorFromAPIError(err error) *ResponseError {
|
|
var apiErr *openai.Error
|
|
if !errors.As(err, &apiErr) {
|
|
return nil
|
|
}
|
|
return NewResponseError(apiErr.Message, apiErr.Type, apiErr.Code, apiErr.StatusCode, keypool.ParseRetryAfter(apiErr.Response))
|
|
}
|