mirror of
https://github.com/router-for-me/CLIProxyAPI.git
synced 2026-09-05 23:50:29 +08:00
Codex and Claude already emit credential-level quota watermarks on ordinary
responses. CPA used to drop them. Keep the latest watermark in memory and
return it from the management auth-file API.
Hard rule: this is observation only. It must not change scheduling, cooldown
selection, or auth-file persistence.
Snapshot, not accumulation
- QuotaState now has ObservedAt and a bounded Signals map. MarkResult fills
them from the response headers already recorded on the request.
- Signals is the current response, not a union of earlier ones. Retry-After
and "limit reached" only appear on the response that produced them; merging
across responses would keep an expired value forever.
- A response with no quota header (transport failure, 5xx, unrelated endpoint)
leaves the previous snapshot in place.
- ObservedAt is the time of the current snapshot. It advances even when the
values did not change, so a consumer can tell a fresh reading from a stale
one.
- When two model states merge, keep the newer snapshot. Do not union keys
captured at different times.
What is observed, and what is not
- One predicate, ProviderSupportsQuotaObservation, decides the provider set.
- Keep Codex and Claude. Drop Kimi, xAI/Grok, Antigravity, and the Gemini
family (gemini/vertex/aistudio): their ordinary headers are not a reliable
credential-level remaining quota.
- Count-tokens reuses the credential but is not generation traffic.
ExecuteCount sets SkipQuotaObservation so those headers cannot replace the
last generation snapshot. Cooldown and success/failure accounting still run.
Cooldown must not overwrite the last snapshot
- Observation writes only ObservedAt and Signals.
- Cooldown writes only Exceeded, Reason, NextRecoverAt, and BackoffLevel,
through applyCooldownFields. Never assign a fresh QuotaState{...} over a
live value: that would zero the snapshot on 429, Cloudflare, credential-
scope sibling updates, and cooldown clears.
- If a credential-quota cooldown is still active, MarkResult still observes
an already-present model state. It does not create scheduler state just to
record a watermark.
- .cds files persist cooldownFieldsOf(Quota) only. Restore keeps the newer
ObservedAt, so reloading cooldown cannot clobber a newer in-memory snapshot.
- cooldownQuotaEqual still ignores observation fields, so a watermark change
cannot by itself persist cooldown or move the scheduler.
- The management payload omits every cooldown field, so it cannot be mistaken
for scheduler state or wired back into scheduling.
- Manual ResetQuota still clears the full QuotaState.
Codex websocket events
- Codex WS reports quota as codex.rate_limits frames, not HTTP headers.
ParseCodexQuotaEventHeaders turns one event into the same bounded header
shape, and MergeResponseHeaders folds it into the request-scoped holder.
additional_rate_limits is accepted as an object (websocket) or an array
(/wham/usage).
- Parse only through AppendCodexAPIWebsocketResponse. The shared
AppendAPIWebsocketResponse is also used by xAI, and xAI error frames really
do carry x-ratelimit-* headers. Parsing every frame as Codex quota would
forge Codex headers into another provider's request log.
- Also capture code_review_rate_limits.
- A malformed active-limit name drops only that one header, not the window
watermarks parsed from the same event.
- The type discriminator scans a bounded frame prefix, not every byte of
every frame.
- HTTP namespaces an extra limit by short name (x-codex-bengalfox-*); WS
namespaces it by limit name (GPT-5.3-Codex-Spark). The two paths cannot
emit the same header names. The X-Codex-Additional- prefix marks the WS
origin, and snapshot replacement keeps the two spellings from piling up.
Hardening
- Reject observed values with control characters. These strings reach the
plain-text request log, and Limit-Name is upstream-controlled, so CR/LF
could forge a header line.
- When the header cap is hit, keep plan/credits/primary ahead of
additional-limit namespaces, then sort names so truncation is deterministic.
- QuotaState.Clone deep-copies Signals and is used by Auth.Clone and
ModelState.Clone.
- Token stores still serialize credential metadata only, so observation adds
no auth-file writes.
334 lines
12 KiB
Go
334 lines
12 KiB
Go
package executor
|
|
|
|
import (
|
|
"bytes"
|
|
"context"
|
|
"fmt"
|
|
"net/http"
|
|
"strings"
|
|
|
|
"github.com/gorilla/websocket"
|
|
"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 *CodexWebsocketsExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (resp cliproxyexecutor.Response, err error) {
|
|
if ctx == nil {
|
|
ctx = context.Background()
|
|
}
|
|
if opts.Alt == "responses/compact" {
|
|
return e.CodexExecutor.executeCompact(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, false)
|
|
|
|
body, err = helps.ApplyRequestThinking(body, req, opts, from.String(), to.String(), e.Identifier())
|
|
if err != nil {
|
|
return resp, 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 = helps.SetStringIfDifferent(body, "model", baseModel)
|
|
body = helps.SetBoolIfDifferent(body, "stream", true)
|
|
body, _ = sjson.DeleteBytes(body, "prompt_cache_retention")
|
|
body, _ = sjson.DeleteBytes(body, "safety_identifier")
|
|
body = normalizeCodexInstructions(body)
|
|
if e.cfg == nil || e.cfg.DisableImageGeneration == config.DisableImageGenerationOff {
|
|
body = ensureImageGenerationTool(body, baseModel, auth, opts.Headers)
|
|
}
|
|
body = sanitizeOpenAIResponsesReasoningEncryptedContent(ctx, "codex websockets executor", body)
|
|
body = normalizeCodexWebsocketParallelToolCalls(body, opts.Headers)
|
|
multiAgentV2Conflict := helps.HasCodexMultiAgentV2NamespaceConflict(body)
|
|
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 resp, errReplay
|
|
}
|
|
|
|
httpURL := strings.TrimSuffix(baseURL, "/") + "/responses"
|
|
wsURL, err := buildCodexResponsesWebsocketURL(httpURL)
|
|
if err != nil {
|
|
return resp, err
|
|
}
|
|
|
|
body, wsHeaders, errPromptCache := applyCodexPromptCacheHeadersWithContext(ctx, from, req, body, opts.Headers)
|
|
if errPromptCache != nil {
|
|
return resp, errPromptCache
|
|
}
|
|
clientBody := body
|
|
var identityState codexIdentityConfuseState
|
|
upstreamBody, identityState := applyCodexIdentityConfuseBody(e.cfg, auth, originalPayloadSource, body)
|
|
reporter.SetTranslatedReasoningEffort(clientBody, to.String())
|
|
wsHeaders = applyCodexWebsocketHeaders(ctx, wsHeaders, auth, apiKey, e.cfg, opts.Headers)
|
|
applyModelHeaderOverrides(wsHeaders, baseModel)
|
|
applyCodexIdentityConfuseHeaders(wsHeaders, &identityState)
|
|
|
|
var authID, authLabel, authType, authValue string
|
|
if auth != nil {
|
|
authID = auth.ID
|
|
authLabel = auth.Label
|
|
authType, authValue = auth.AccountInfo()
|
|
}
|
|
|
|
executionSessionID := executionSessionIDFromOptions(opts)
|
|
var sess *codexWebsocketSession
|
|
sessionLocked := false
|
|
unlockSession := func() {
|
|
if sess != nil && sessionLocked {
|
|
sess.reqMu.Unlock()
|
|
sessionLocked = false
|
|
}
|
|
}
|
|
if executionSessionID != "" {
|
|
sess = e.getOrCreateSession(executionSessionID)
|
|
sess.reqMu.Lock()
|
|
sessionLocked = true
|
|
defer unlockSession()
|
|
}
|
|
|
|
wsReqBody := buildCodexWebsocketRequestBody(upstreamBody)
|
|
wsReqLog := helps.UpstreamRequestLog{
|
|
URL: wsURL,
|
|
Method: "WEBSOCKET",
|
|
Headers: wsHeaders.Clone(),
|
|
Body: wsReqBody,
|
|
Provider: e.Identifier(),
|
|
AuthID: authID,
|
|
AuthLabel: authLabel,
|
|
AuthType: authType,
|
|
AuthValue: authValue,
|
|
}
|
|
helps.RecordAPIWebsocketRequest(ctx, e.cfg, wsReqLog)
|
|
|
|
var conn *websocket.Conn
|
|
var closer *websocketConnectionCloser
|
|
var respHS *http.Response
|
|
var errDial error
|
|
if cliproxyexecutor.RequiredUpstreamWebsocket(ctx) {
|
|
conn, closer = existingWebsocketSessionConn(sess, authID, wsURL)
|
|
if conn == nil {
|
|
return resp, cliproxyexecutor.NewUpstreamWebsocketReplayRequiredError()
|
|
}
|
|
} else {
|
|
conn, closer, respHS, errDial = e.ensureUpstreamConn(ctx, auth, sess, authID, wsURL, wsHeaders)
|
|
}
|
|
if errDial != nil {
|
|
bodyErr := websocketHandshakeBody(respHS)
|
|
if respHS != nil {
|
|
helps.RecordAPIWebsocketUpgradeRejection(ctx, e.cfg, websocketUpgradeRequestLog(wsReqLog), respHS.StatusCode, respHS.Header.Clone(), bodyErr)
|
|
}
|
|
if respHS != nil && respHS.StatusCode == http.StatusUpgradeRequired {
|
|
if opts.ExecutionLifecycle != nil || cliproxyexecutor.DownstreamWebsocket(ctx) {
|
|
return resp, statusErr{code: respHS.StatusCode, msg: string(bodyErr)}
|
|
}
|
|
return e.CodexExecutor.Execute(ctx, auth, req, opts)
|
|
}
|
|
if respHS != nil && respHS.StatusCode > 0 {
|
|
return resp, statusErr{code: respHS.StatusCode, msg: string(bodyErr)}
|
|
}
|
|
helps.RecordAPIWebsocketError(ctx, e.cfg, "dial", errDial)
|
|
return resp, errDial
|
|
}
|
|
if errBind := sess.bindExecutionLifecycle(opts, conn, closer, req.Model); errBind != nil {
|
|
unlockSession()
|
|
closeWebsocketAfterBindFailure(sess, conn, closer)
|
|
return resp, errBind
|
|
}
|
|
recordAPIWebsocketHandshake(ctx, e.cfg, respHS)
|
|
reporter.StartResponseTTFT()
|
|
if sess == nil {
|
|
logCodexWebsocketConnected(executionSessionID, authID, wsURL)
|
|
defer func() {
|
|
reason := "completed"
|
|
if err != nil {
|
|
reason = "error"
|
|
}
|
|
logCodexWebsocketDisconnected(executionSessionID, authID, wsURL, reason, err)
|
|
if errClose := closer.Close(); errClose != nil {
|
|
log.Errorf("codex websockets executor: close websocket error: %v", errClose)
|
|
}
|
|
}()
|
|
}
|
|
|
|
var readCh chan codexWebsocketRead
|
|
if sess != nil {
|
|
readCh = sess.activate(conn)
|
|
defer func() {
|
|
sess.clearActive(conn, readCh)
|
|
}()
|
|
}
|
|
restoreMultiAgentV2 := !multiAgentV2Conflict && (optimizeMultiAgentV2 || sess.isMultiAgentV2Optimized(conn))
|
|
|
|
if errSend := writeCodexWebsocketMessage(sess, conn, wsReqBody); errSend != nil {
|
|
errSend = mapCodexWebsocketWriteError(sess, conn, errSend)
|
|
if sess != nil {
|
|
if cliproxyexecutor.RequiredUpstreamWebsocket(ctx) {
|
|
e.invalidateUpstreamConnWithoutDisconnectNotify(sess, conn, "send_error", errSend)
|
|
if !shouldRetryCodexWebsocketSend(errSend) {
|
|
helps.RecordAPIWebsocketError(ctx, e.cfg, "send", errSend)
|
|
return resp, errSend
|
|
}
|
|
return resp, cliproxyexecutor.NewUpstreamWebsocketReplayRequiredError()
|
|
}
|
|
e.invalidateUpstreamConn(sess, conn, "send_error", errSend)
|
|
if !shouldRetryCodexWebsocketSend(errSend) {
|
|
helps.RecordAPIWebsocketError(ctx, e.cfg, "send", errSend)
|
|
return resp, errSend
|
|
}
|
|
|
|
// Retry once with a fresh websocket connection. This is mainly to handle
|
|
// upstream closing the socket between sequential requests within the same
|
|
// execution session.
|
|
connRetry, closerRetry, respHSRetry, errDialRetry := e.ensureUpstreamConn(ctx, auth, sess, authID, wsURL, wsHeaders)
|
|
if errDialRetry == nil && connRetry != nil {
|
|
previousConn, previousReadCh := conn, readCh
|
|
conn = connRetry
|
|
closer = closerRetry
|
|
if errBind := sess.bindExecutionLifecycle(opts, conn, closer, req.Model); errBind != nil {
|
|
clearRetryActiveState(sess, previousConn, previousReadCh)
|
|
unlockSession()
|
|
closeWebsocketAfterBindFailure(sess, conn, closer)
|
|
return resp, errBind
|
|
}
|
|
readCh = sess.activate(conn)
|
|
restoreMultiAgentV2 = !multiAgentV2Conflict && (optimizeMultiAgentV2 || sess.isMultiAgentV2Optimized(conn))
|
|
wsReqBodyRetry := buildCodexWebsocketRequestBody(upstreamBody)
|
|
helps.RecordAPIWebsocketRequest(ctx, e.cfg, helps.UpstreamRequestLog{
|
|
URL: wsURL,
|
|
Method: "WEBSOCKET",
|
|
Headers: wsHeaders.Clone(),
|
|
Body: wsReqBodyRetry,
|
|
Provider: e.Identifier(),
|
|
AuthID: authID,
|
|
AuthLabel: authLabel,
|
|
AuthType: authType,
|
|
AuthValue: authValue,
|
|
})
|
|
recordAPIWebsocketHandshake(ctx, e.cfg, respHSRetry)
|
|
reporter.StartResponseTTFT()
|
|
if errSendRetry := writeCodexWebsocketMessage(sess, conn, wsReqBodyRetry); errSendRetry == nil {
|
|
wsReqBody = wsReqBodyRetry
|
|
} else {
|
|
errSendRetry = mapCodexWebsocketWriteError(sess, connRetry, errSendRetry)
|
|
e.invalidateUpstreamConn(sess, connRetry, "send_error", errSendRetry)
|
|
helps.RecordAPIWebsocketError(ctx, e.cfg, "send_retry", errSendRetry)
|
|
return resp, errSendRetry
|
|
}
|
|
} else {
|
|
closeHTTPResponseBody(respHSRetry, "codex websockets executor: close handshake response body error")
|
|
helps.RecordAPIWebsocketError(ctx, e.cfg, "dial_retry", errDialRetry)
|
|
return resp, errDialRetry
|
|
}
|
|
} else {
|
|
helps.RecordAPIWebsocketError(ctx, e.cfg, "send", errSend)
|
|
return resp, errSend
|
|
}
|
|
}
|
|
|
|
if optimizeMultiAgentV2 || multiAgentV2Conflict {
|
|
sess.setMultiAgentV2Optimized(conn, optimizeMultiAgentV2 && !multiAgentV2Conflict)
|
|
}
|
|
|
|
outputItemsByIndex := make(map[int64][]byte)
|
|
var outputItemsFallback [][]byte
|
|
for {
|
|
if ctx != nil && ctx.Err() != nil {
|
|
return resp, ctx.Err()
|
|
}
|
|
msgType, payload, errRead := readCodexWebsocketMessage(ctx, sess, conn, readCh)
|
|
if errRead != nil {
|
|
mappedErr := mapCodexWebsocketReadError(errRead)
|
|
helps.RecordAPIWebsocketError(ctx, e.cfg, "read", mappedErr)
|
|
return resp, mappedErr
|
|
}
|
|
if msgType != websocket.TextMessage {
|
|
if msgType == websocket.BinaryMessage {
|
|
err = fmt.Errorf("codex websockets executor: unexpected binary message")
|
|
if sess != nil {
|
|
e.invalidateUpstreamConn(sess, conn, "unexpected_binary", err)
|
|
}
|
|
helps.RecordAPIWebsocketError(ctx, e.cfg, "unexpected_binary", err)
|
|
return resp, err
|
|
}
|
|
continue
|
|
}
|
|
|
|
payload = bytes.TrimSpace(payload)
|
|
if len(payload) == 0 {
|
|
continue
|
|
}
|
|
reporter.MarkFirstResponseByte()
|
|
payload = applyCodexIdentityConfuseResponsePayload(payload, identityState)
|
|
helps.AppendCodexAPIWebsocketResponse(ctx, e.cfg, payload)
|
|
payload = helps.RestoreCodexMultiAgentV2Response(payload, restoreMultiAgentV2)
|
|
|
|
if wsErr, ok := parseCodexWebsocketError(payload); ok {
|
|
if sess != nil {
|
|
e.invalidateUpstreamConn(sess, conn, "upstream_error", wsErr)
|
|
}
|
|
if errClearReplay := clearCodexReasoningReplayOnWebsocketError(ctx, replayScope, payload); errClearReplay != nil {
|
|
return resp, errClearReplay
|
|
}
|
|
helps.RecordAPIWebsocketError(ctx, e.cfg, "upstream_error", wsErr)
|
|
return resp, wsErr
|
|
}
|
|
if streamErr, terminalBody, ok := codexTerminalFailureErr(payload); ok {
|
|
if sess != nil {
|
|
unlockSession()
|
|
e.invalidateUpstreamConn(sess, conn, "terminal_failure", streamErr)
|
|
}
|
|
if errClearReplay := clearCodexReasoningReplayOnInvalidSignature(ctx, replayScope, streamErr.StatusCode(), terminalBody); errClearReplay != nil {
|
|
return resp, errClearReplay
|
|
}
|
|
return resp, streamErr
|
|
}
|
|
|
|
payload = normalizeCodexWebsocketCompletion(payload)
|
|
eventType := gjson.GetBytes(payload, "type").String()
|
|
switch eventType {
|
|
case "response.output_item.done":
|
|
collectCodexOutputItemDone(payload, outputItemsByIndex, &outputItemsFallback)
|
|
case "response.completed":
|
|
payload = patchCodexCompletedOutput(payload, outputItemsByIndex, outputItemsFallback)
|
|
cacheCodexReasoningReplayFromCompleted(replayScope, payload)
|
|
if detail, ok := helps.ParseCodexUsage(payload); ok {
|
|
reporter.Publish(ctx, detail)
|
|
}
|
|
var param any
|
|
clientPayload := applyCodexIdentityExposeResponsePayload(payload, identityState)
|
|
out := sdktranslator.TranslateNonStream(ctx, to, responseFormat, req.Model, originalPayload, clientBody, clientPayload, ¶m)
|
|
if responseFormat == sdktranslator.FormatOpenAIResponse {
|
|
out = helps.EnsureResponsesUsageDetails(out)
|
|
}
|
|
resp = cliproxyexecutor.Response{Payload: out}
|
|
return resp, nil
|
|
}
|
|
}
|
|
}
|