mirror of
https://github.com/router-for-me/CLIProxyAPI.git
synced 2026-09-03 06:35:00 +08:00
* feat(codex): add opt-in stream bootstrap buffering
The upstream smuggles capacity rejections into an HTTP 200 stream. The
handshake events arrive normally and only a later event carries
{"error":{"type":"service_unavailable_error","code":
"server_is_overloaded"}}. By then the executor has already handed the
first chunk downstream, the response is committed, and the conductor can
no longer retry on another credential, so the request fails even though
other credentials were available.
When codex.stream-bootstrap-buffering is enabled the executor holds back
the handshake events until it can tell whether the stream carries real
output or a rejection. An overload rejection then fails the attempt
before any chunk is delivered, letting the conductor retry on another
credential; every other terminal failure is flushed in order and
delivered in-stream exactly as before.
Detection uses an event-type allow-list rather than a fixed count. On the
websocket transport codex.rate_limits and codex.response.metadata arrive
before response.created, making the first generated event the fifth
frame, so a small counter would release the stream before the rejection
is visible. Buffering is bounded and hitting the bound degrades to the
original unbuffered behaviour.
Two details are load-bearing. The error must be returned synchronously:
delivering it as the first stream chunk makes ExecuteStream downgrade it
into a committed 200 and the status is lost. And the websocket path must
not signal an upstream disconnect for a rejection it intends to retry,
because the downstream handler closes the client connection on that
signal and the retry would have nowhere to deliver.
The 503 status is produced only on this path rather than in the shared
codexTerminalFailureStatus mapping, so disabling the feature restores the
previous behaviour exactly, including cooldown classification and
retry-after parsing.
Defaults to false: response headers are withheld until generation
starts, which can trip client or reverse-proxy read timeouts.
* test(codex): pin bootstrap overload failover through the conductor
Executor-level tests cannot show what the client finally receives. These
exercise ExecuteStream end to end to pin three properties that are easy
to regress:
- consecutive overloaded credentials are skipped until one serves the
request, and retries are capped by max-retry-credentials rather than
multiplying with request-retry
- exhausting the pool surfaces the upstream status instead of a
committed 200 stream
- with buffering disabled the rejection stays an in-stream error on a
committed stream, which is the behaviour the feature must preserve
The third case also documents why the executor returns its error
synchronously: an error arriving as the first stream chunk is wrapped and
downgraded into a committed 200, silently losing the status.
359 lines
14 KiB
Go
359 lines
14 KiB
Go
package executor
|
|
|
|
import (
|
|
"bufio"
|
|
"bytes"
|
|
"context"
|
|
"io"
|
|
"net/http"
|
|
"strings"
|
|
|
|
"github.com/router-for-me/CLIProxyAPI/v7/internal/config"
|
|
"github.com/router-for-me/CLIProxyAPI/v7/internal/runtime/executor/helps"
|
|
"github.com/router-for-me/CLIProxyAPI/v7/internal/thinking"
|
|
cliproxyauth "github.com/router-for-me/CLIProxyAPI/v7/sdk/cliproxy/auth"
|
|
cliproxyexecutor "github.com/router-for-me/CLIProxyAPI/v7/sdk/cliproxy/executor"
|
|
sdktranslator "github.com/router-for-me/CLIProxyAPI/v7/sdk/translator"
|
|
log "github.com/sirupsen/logrus"
|
|
"github.com/tidwall/gjson"
|
|
"github.com/tidwall/sjson"
|
|
)
|
|
|
|
func (e *CodexExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (_ *cliproxyexecutor.StreamResult, err error) {
|
|
if opts.Alt == "responses/compact" {
|
|
return nil, statusErr{code: http.StatusBadRequest, msg: "streaming not supported for /responses/compact"}
|
|
}
|
|
if isCodexOpenAIImageRequest(opts) {
|
|
return e.executeOpenAIImageStream(ctx, auth, req, opts)
|
|
}
|
|
baseModel := thinking.ParseSuffix(req.Model).ModelName
|
|
|
|
apiKey, baseURL := codexCreds(auth)
|
|
if baseURL == "" {
|
|
baseURL = "https://chatgpt.com/backend-api/codex"
|
|
}
|
|
|
|
reporter := helps.NewExecutorUsageReporter(ctx, e, baseModel, auth)
|
|
defer reporter.TrackFailure(ctx, &err)
|
|
|
|
from := opts.SourceFormat
|
|
responseFormat := cliproxyexecutor.ResponseFormatOrSource(opts)
|
|
to := sdktranslator.FromString("codex")
|
|
originalPayloadSource := req.Payload
|
|
if len(opts.OriginalRequest) > 0 {
|
|
originalPayloadSource = opts.OriginalRequest
|
|
}
|
|
originalPayload := originalPayloadSource
|
|
originalTranslated, body := translateCodexRequestPair(from, to, baseModel, originalPayload, req.Payload, true, helps.APIKeyModelIsCompat(req))
|
|
|
|
body, err = helps.ApplyRequestThinking(body, req, opts, from.String(), to.String(), e.Identifier())
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
requestedModel := helps.PayloadRequestedModel(opts, req.Model)
|
|
requestPath := helps.PayloadRequestPath(opts)
|
|
body = helps.ApplyPayloadConfigWithRequest(e.cfg, baseModel, to.String(), from.String(), "", body, originalTranslated, requestedModel, requestPath, opts.Headers)
|
|
body, _ = sjson.DeleteBytes(body, "previous_response_id")
|
|
body, _ = sjson.DeleteBytes(body, "generate")
|
|
body, _ = sjson.DeleteBytes(body, "prompt_cache_retention")
|
|
body, _ = sjson.DeleteBytes(body, "safety_identifier")
|
|
reasoningSummaryDelivery := gjson.GetBytes(body, "stream_options.reasoning_summary_delivery")
|
|
body, _ = sjson.DeleteBytes(body, "stream_options")
|
|
if reasoningSummaryDelivery.Exists() {
|
|
body, _ = sjson.SetBytes(body, "stream_options.reasoning_summary_delivery", reasoningSummaryDelivery.Value())
|
|
}
|
|
body = helps.SetStringIfDifferent(body, "model", baseModel)
|
|
body = normalizeCodexInstructions(body)
|
|
if e.cfg == nil || e.cfg.DisableImageGeneration == config.DisableImageGenerationOff {
|
|
body = ensureImageGenerationTool(body, baseModel, auth, opts.Headers)
|
|
}
|
|
body = sanitizeOpenAIResponsesReasoningEncryptedContent(ctx, "codex executor", body)
|
|
body = normalizeCodexParallelToolCalls(body, opts.Headers)
|
|
body, optimizeMultiAgentV2 := helps.OptimizeCodexMultiAgentV2RequestForAuth(ctx, opts.Headers, body, e.cfg, auth, baseModel)
|
|
body, replayScope, errReplay := applyCodexReasoningReplayCacheRequired(ctx, from, req, opts, body)
|
|
if errReplay != nil {
|
|
return nil, errReplay
|
|
}
|
|
reporter.SetTranslatedReasoningEffort(body, to.String())
|
|
|
|
url := strings.TrimSuffix(baseURL, "/") + "/responses"
|
|
var identityState codexIdentityConfuseState
|
|
httpReq, upstreamBody, identityState, err := e.cacheHelper(ctx, from, url, auth, req, originalPayloadSource, body, opts.Headers)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
applyCodexHeaders(httpReq, auth, apiKey, true, e.cfg, opts.Headers)
|
|
applyModelHeaderOverrides(httpReq.Header, baseModel)
|
|
applyCodexIdentityConfuseHeaders(httpReq.Header, &identityState)
|
|
var authID, authLabel, authType, authValue string
|
|
if auth != nil {
|
|
authID = auth.ID
|
|
authLabel = auth.Label
|
|
authType, authValue = auth.AccountInfo()
|
|
}
|
|
helps.RecordAPIRequest(ctx, e.cfg, helps.UpstreamRequestLog{
|
|
URL: url,
|
|
Method: http.MethodPost,
|
|
Headers: httpReq.Header.Clone(),
|
|
Body: upstreamBody,
|
|
Provider: e.Identifier(),
|
|
AuthID: authID,
|
|
AuthLabel: authLabel,
|
|
AuthType: authType,
|
|
AuthValue: authValue,
|
|
})
|
|
|
|
httpClient := helps.NewUtlsHTTPClient(ctx, e.cfg, auth, 0)
|
|
httpClient = reporter.TrackHTTPClient(httpClient)
|
|
httpResp, err := httpClient.Do(httpReq)
|
|
if err != nil {
|
|
helps.RecordAPIResponseError(ctx, e.cfg, err)
|
|
return nil, err
|
|
}
|
|
helps.RecordAPIResponseMetadata(ctx, e.cfg, httpResp.StatusCode, httpResp.Header.Clone())
|
|
if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
|
|
data, readErr := io.ReadAll(httpResp.Body)
|
|
if errClose := httpResp.Body.Close(); errClose != nil {
|
|
log.Errorf("codex executor: close response body error: %v", errClose)
|
|
}
|
|
if readErr != nil {
|
|
helps.RecordAPIResponseError(ctx, e.cfg, readErr)
|
|
return nil, readErr
|
|
}
|
|
data = applyCodexIdentityConfuseResponsePayload(data, identityState)
|
|
if errClearReplay := clearCodexReasoningReplayOnInvalidSignature(ctx, replayScope, httpResp.StatusCode, data); errClearReplay != nil {
|
|
return nil, errClearReplay
|
|
}
|
|
helps.AppendAPIResponseChunk(ctx, e.cfg, data)
|
|
helps.LogWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", httpResp.StatusCode, helps.SummarizeErrorBody(httpResp.Header.Get("Content-Type"), data))
|
|
err = newCodexStatusErr(httpResp.StatusCode, data)
|
|
return nil, err
|
|
}
|
|
|
|
buffering := e.cfg != nil && e.cfg.Codex.StreamBootstrapBuffering
|
|
|
|
scanner := bufio.NewScanner(httpResp.Body)
|
|
scanner.Buffer(nil, 52_428_800) // 50MB
|
|
claudeInputTokens := helps.NewClaudeInputTokenState(from, to, responseFormat, originalPayload)
|
|
var param any
|
|
outputItemsByIndex := make(map[int64][]byte)
|
|
var outputItemsFallback [][]byte
|
|
|
|
var bufferedChunks [][]byte
|
|
var initialChunks [][]byte
|
|
streamStarted := false
|
|
immediateTerminal := false
|
|
// bootstrapTerminalErr holds a non-overload terminal failure seen while buffering. It is
|
|
// delivered as an in-stream chunk after the buffered handshake so downstream behaviour stays
|
|
// identical to the unbuffered path instead of silently turning into a credential failover.
|
|
var bootstrapTerminalErr error
|
|
|
|
closeBootstrapBody := func() {
|
|
if errClose := httpResp.Body.Close(); errClose != nil {
|
|
log.Errorf("codex executor: close response body error: %v", errClose)
|
|
}
|
|
}
|
|
|
|
if buffering {
|
|
for scanner.Scan() {
|
|
line := applyCodexIdentityConfuseResponsePayload(scanner.Bytes(), identityState)
|
|
helps.AppendAPIResponseChunk(ctx, e.cfg, line)
|
|
translatedLine := bytes.Clone(line)
|
|
isHandshake := false
|
|
terminalSuccess := false
|
|
|
|
if bytes.HasPrefix(line, dataTag) {
|
|
data := bytes.TrimSpace(line[5:])
|
|
data = helps.RestoreCodexMultiAgentV2Response(data, optimizeMultiAgentV2)
|
|
translatedLine = append([]byte("data: "), data...)
|
|
eventType := gjson.GetBytes(data, "type").String()
|
|
if streamErr, terminalBody, ok := codexTerminalFailureErr(data); ok {
|
|
closeBootstrapBody()
|
|
if errClearReplay := clearCodexReasoningReplayOnInvalidSignature(ctx, replayScope, streamErr.StatusCode(), terminalBody); errClearReplay != nil {
|
|
helps.RecordAPIResponseError(ctx, e.cfg, errClearReplay)
|
|
reporter.PublishFailure(ctx, errClearReplay)
|
|
return nil, errClearReplay
|
|
}
|
|
helps.RecordAPIResponseError(ctx, e.cfg, streamErr)
|
|
reporter.PublishFailure(ctx, streamErr)
|
|
if isCodexOverloadBootstrapFailure(terminalBody) {
|
|
// Transient capacity rejection smuggled into an HTTP 200 stream. Fail the
|
|
// attempt before the downstream headers are committed so the conductor can
|
|
// transparently retry on another credential, and report the status the
|
|
// upstream refused to put on the wire.
|
|
helps.LogWithRequestID(ctx).Debugf("codex executor: bootstrap overload rejection after %d buffered handshake events, failing over", len(bufferedChunks))
|
|
return nil, newCodexBootstrapOverloadErr(terminalBody)
|
|
}
|
|
bootstrapTerminalErr = streamErr
|
|
break
|
|
}
|
|
if isCodexHandshakeMetadataEvent(eventType) {
|
|
isHandshake = true
|
|
}
|
|
switch eventType {
|
|
case "response.output_item.done":
|
|
collectCodexOutputItemDone(data, outputItemsByIndex, &outputItemsFallback)
|
|
case "response.completed", "response.incomplete":
|
|
terminalSuccess = true
|
|
if detail, ok := helps.ParseCodexUsage(data); ok {
|
|
reporter.Publish(ctx, detail)
|
|
}
|
|
publishCodexImageToolUsage(ctx, reporter, body, data)
|
|
data = patchCodexCompletedOutput(data, outputItemsByIndex, outputItemsFallback)
|
|
if eventType == "response.completed" {
|
|
cacheCodexReasoningReplayFromCompleted(replayScope, data)
|
|
}
|
|
translatedLine = append([]byte("data: "), data...)
|
|
}
|
|
} else {
|
|
isHandshake = true
|
|
}
|
|
|
|
translatedLine = applyCodexIdentityExposeResponsePayload(translatedLine, identityState)
|
|
chunks := helps.TranslateStreamWithClaudeInputTokens(ctx, to, responseFormat, req.Model, originalPayload, body, translatedLine, ¶m, claudeInputTokens)
|
|
if isHandshake && !terminalSuccess {
|
|
if len(bufferedChunks) < codexBootstrapMaxBufferedEvents {
|
|
bufferedChunks = append(bufferedChunks, chunks...)
|
|
continue
|
|
}
|
|
helps.LogWithRequestID(ctx).Debugf("codex executor: bootstrap buffer limit %d reached, releasing stream without overload probing", codexBootstrapMaxBufferedEvents)
|
|
}
|
|
|
|
initialChunks = chunks
|
|
streamStarted = true
|
|
if terminalSuccess {
|
|
immediateTerminal = true
|
|
}
|
|
break
|
|
}
|
|
|
|
if !streamStarted && bootstrapTerminalErr == nil {
|
|
closeBootstrapBody()
|
|
if errScan := scanner.Err(); errScan != nil {
|
|
// A cancelled downstream request must not be recorded as an upstream failure or
|
|
// penalise the credential; mirror the unbuffered goroutine's guard.
|
|
if ctx.Err() != nil {
|
|
return nil, ctx.Err()
|
|
}
|
|
helps.RecordAPIResponseError(ctx, e.cfg, errScan)
|
|
reporter.PublishFailure(ctx, errScan)
|
|
return nil, errScan
|
|
}
|
|
if ctx.Err() != nil {
|
|
return nil, ctx.Err()
|
|
}
|
|
streamErr := newCodexIncompleteStreamError()
|
|
helps.RecordAPIResponseError(ctx, e.cfg, streamErr)
|
|
reporter.PublishFailure(ctx, streamErr)
|
|
return nil, streamErr
|
|
}
|
|
}
|
|
|
|
chanCapacity := len(bufferedChunks) + len(initialChunks)
|
|
if bootstrapTerminalErr != nil {
|
|
chanCapacity++
|
|
}
|
|
out := make(chan cliproxyexecutor.StreamChunk, chanCapacity)
|
|
for _, chunk := range bufferedChunks {
|
|
out <- cliproxyexecutor.StreamChunk{Payload: chunk}
|
|
}
|
|
for _, chunk := range initialChunks {
|
|
out <- cliproxyexecutor.StreamChunk{Payload: chunk}
|
|
}
|
|
if bootstrapTerminalErr != nil {
|
|
// Buffered handshake payloads are flushed first so the conductor observes a committed
|
|
// stream and delivers this failure in-stream, exactly as the unbuffered path would.
|
|
out <- cliproxyexecutor.StreamChunk{Err: bootstrapTerminalErr}
|
|
close(out)
|
|
return &cliproxyexecutor.StreamResult{Headers: httpResp.Header.Clone(), Chunks: out}, nil
|
|
}
|
|
if immediateTerminal {
|
|
closeBootstrapBody()
|
|
close(out)
|
|
return &cliproxyexecutor.StreamResult{Headers: httpResp.Header.Clone(), Chunks: out}, nil
|
|
}
|
|
|
|
go func() {
|
|
defer close(out)
|
|
defer func() {
|
|
if errClose := httpResp.Body.Close(); errClose != nil {
|
|
log.Errorf("codex executor: close response body error: %v", errClose)
|
|
}
|
|
}()
|
|
for scanner.Scan() {
|
|
line := applyCodexIdentityConfuseResponsePayload(scanner.Bytes(), identityState)
|
|
helps.AppendAPIResponseChunk(ctx, e.cfg, line)
|
|
translatedLine := bytes.Clone(line)
|
|
terminalSuccess := false
|
|
|
|
if bytes.HasPrefix(line, dataTag) {
|
|
data := bytes.TrimSpace(line[5:])
|
|
data = helps.RestoreCodexMultiAgentV2Response(data, optimizeMultiAgentV2)
|
|
translatedLine = append([]byte("data: "), data...)
|
|
eventType := gjson.GetBytes(data, "type").String()
|
|
if streamErr, terminalBody, ok := codexTerminalFailureErr(data); ok {
|
|
if errClearReplay := clearCodexReasoningReplayOnInvalidSignature(ctx, replayScope, streamErr.StatusCode(), terminalBody); errClearReplay != nil {
|
|
helps.RecordAPIResponseError(ctx, e.cfg, errClearReplay)
|
|
reporter.PublishFailure(ctx, errClearReplay)
|
|
select {
|
|
case out <- cliproxyexecutor.StreamChunk{Err: errClearReplay}:
|
|
case <-ctx.Done():
|
|
}
|
|
return
|
|
}
|
|
helps.RecordAPIResponseError(ctx, e.cfg, streamErr)
|
|
reporter.PublishFailure(ctx, streamErr)
|
|
select {
|
|
case out <- cliproxyexecutor.StreamChunk{Err: streamErr}:
|
|
case <-ctx.Done():
|
|
}
|
|
return
|
|
}
|
|
switch eventType {
|
|
case "response.output_item.done":
|
|
collectCodexOutputItemDone(data, outputItemsByIndex, &outputItemsFallback)
|
|
case "response.completed", "response.incomplete":
|
|
terminalSuccess = true
|
|
if detail, ok := helps.ParseCodexUsage(data); ok {
|
|
reporter.Publish(ctx, detail)
|
|
}
|
|
publishCodexImageToolUsage(ctx, reporter, body, data)
|
|
data = patchCodexCompletedOutput(data, outputItemsByIndex, outputItemsFallback)
|
|
if eventType == "response.completed" {
|
|
cacheCodexReasoningReplayFromCompleted(replayScope, data)
|
|
}
|
|
translatedLine = append([]byte("data: "), data...)
|
|
}
|
|
}
|
|
|
|
translatedLine = applyCodexIdentityExposeResponsePayload(translatedLine, identityState)
|
|
chunks := helps.TranslateStreamWithClaudeInputTokens(ctx, to, responseFormat, req.Model, originalPayload, body, translatedLine, ¶m, claudeInputTokens)
|
|
for i := range chunks {
|
|
select {
|
|
case out <- cliproxyexecutor.StreamChunk{Payload: chunks[i]}:
|
|
case <-ctx.Done():
|
|
return
|
|
}
|
|
}
|
|
if terminalSuccess {
|
|
return
|
|
}
|
|
}
|
|
if errScan := scanner.Err(); errScan != nil {
|
|
if ctx.Err() != nil {
|
|
return
|
|
}
|
|
helps.RecordAPIResponseError(ctx, e.cfg, errScan)
|
|
}
|
|
streamErr := newCodexIncompleteStreamError()
|
|
helps.RecordAPIResponseError(ctx, e.cfg, streamErr)
|
|
reporter.PublishFailure(ctx, streamErr)
|
|
select {
|
|
case out <- cliproxyexecutor.StreamChunk{Err: streamErr}:
|
|
case <-ctx.Done():
|
|
}
|
|
}()
|
|
return &cliproxyexecutor.StreamResult{Headers: httpResp.Header.Clone(), Chunks: out}, nil
|
|
}
|