Merge pull request #2374 from VooDisss/codex-cache-clean

fix(codex): restore prompt cache continuity for Codex requests

internal/runtime/executor/codex_continuity.go

@@ -0,0 +1,125 @@
+package executor
+
+import (
+	"context"
+	"fmt"
+	"net/http"
+	"strings"
+
+	"github.com/google/uuid"
+	cliproxyauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
+	cliproxyexecutor "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/executor"
+	log "github.com/sirupsen/logrus"
+	"github.com/tidwall/gjson"
+	"github.com/tidwall/sjson"
+)
+
+type codexContinuity struct {
+	Key    string
+	Source string
+}
+
+func metadataString(meta map[string]any, key string) string {
+	if len(meta) == 0 {
+		return ""
+	}
+	raw, ok := meta[key]
+	if !ok || raw == nil {
+		return ""
+	}
+	switch v := raw.(type) {
+	case string:
+		return strings.TrimSpace(v)
+	case []byte:
+		return strings.TrimSpace(string(v))
+	default:
+		return ""
+	}
+}
+
+func principalString(raw any) string {
+	switch v := raw.(type) {
+	case string:
+		return strings.TrimSpace(v)
+	case fmt.Stringer:
+		return strings.TrimSpace(v.String())
+	default:
+		return strings.TrimSpace(fmt.Sprintf("%v", raw))
+	}
+}
+
+func resolveCodexContinuity(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) codexContinuity {
+	if promptCacheKey := strings.TrimSpace(gjson.GetBytes(req.Payload, "prompt_cache_key").String()); promptCacheKey != "" {
+		return codexContinuity{Key: promptCacheKey, Source: "prompt_cache_key"}
+	}
+	if executionSession := metadataString(opts.Metadata, cliproxyexecutor.ExecutionSessionMetadataKey); executionSession != "" {
+		return codexContinuity{Key: executionSession, Source: "execution_session"}
+	}
+	if ginCtx := ginContextFrom(ctx); ginCtx != nil {
+		if ginCtx.Request != nil {
+			if v := strings.TrimSpace(ginCtx.GetHeader("Idempotency-Key")); v != "" {
+				return codexContinuity{Key: v, Source: "idempotency_key"}
+			}
+		}
+		if v, exists := ginCtx.Get("apiKey"); exists && v != nil {
+			if trimmed := principalString(v); trimmed != "" {
+				return codexContinuity{Key: uuid.NewSHA1(uuid.NameSpaceOID, []byte("cli-proxy-api:codex:prompt-cache:"+trimmed)).String(), Source: "client_principal"}
+			}
+		}
+	}
+	if auth != nil {
+		if authID := strings.TrimSpace(auth.ID); authID != "" {
+			return codexContinuity{Key: uuid.NewSHA1(uuid.NameSpaceOID, []byte("cli-proxy-api:codex:prompt-cache:auth:"+authID)).String(), Source: "auth_id"}
+		}
+	}
+	return codexContinuity{}
+}
+
+func applyCodexContinuityBody(rawJSON []byte, continuity codexContinuity) []byte {
+	if continuity.Key == "" {
+		return rawJSON
+	}
+	rawJSON, _ = sjson.SetBytes(rawJSON, "prompt_cache_key", continuity.Key)
+	return rawJSON
+}
+
+func applyCodexContinuityHeaders(headers http.Header, continuity codexContinuity) {
+	if headers == nil || continuity.Key == "" {
+		return
+	}
+	headers.Set("session_id", continuity.Key)
+}
+
+func logCodexRequestDiagnostics(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options, headers http.Header, body []byte, continuity codexContinuity) {
+	if !log.IsLevelEnabled(log.DebugLevel) {
+		return
+	}
+	entry := logWithRequestID(ctx)
+	authID := ""
+	authFile := ""
+	if auth != nil {
+		authID = strings.TrimSpace(auth.ID)
+		authFile = strings.TrimSpace(auth.FileName)
+	}
+	selectedAuthID := metadataString(opts.Metadata, cliproxyexecutor.SelectedAuthMetadataKey)
+	executionSessionID := metadataString(opts.Metadata, cliproxyexecutor.ExecutionSessionMetadataKey)
+	entry.Debugf(
+		"codex request diagnostics auth_id=%s selected_auth_id=%s auth_file=%s exec_session=%s continuity_source=%s session_id=%s prompt_cache_key=%s prompt_cache_retention=%s store=%t has_instructions=%t reasoning_effort=%s reasoning_summary=%s chatgpt_account_id=%t originator=%s model=%s source_format=%s",
+		authID,
+		selectedAuthID,
+		authFile,
+		executionSessionID,
+		continuity.Source,
+		strings.TrimSpace(headers.Get("session_id")),
+		gjson.GetBytes(body, "prompt_cache_key").String(),
+		gjson.GetBytes(body, "prompt_cache_retention").String(),
+		gjson.GetBytes(body, "store").Bool(),
+		gjson.GetBytes(body, "instructions").Exists(),
+		gjson.GetBytes(body, "reasoning.effort").String(),
+		gjson.GetBytes(body, "reasoning.summary").String(),
+		strings.TrimSpace(headers.Get("Chatgpt-Account-Id")) != "",
+		strings.TrimSpace(headers.Get("Originator")),
+		req.Model,
+		opts.SourceFormat.String(),
+	)
+}

internal/runtime/executor/codex_executor.go

@@ -111,7 +111,6 @@ func (e *CodexExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, re
 	body, _ = sjson.SetBytes(body, "model", baseModel)
 	body, _ = sjson.SetBytes(body, "stream", true)
 	body, _ = sjson.DeleteBytes(body, "previous_response_id")
-	body, _ = sjson.DeleteBytes(body, "prompt_cache_retention")
 	body, _ = sjson.DeleteBytes(body, "safety_identifier")
 	body, _ = sjson.DeleteBytes(body, "stream_options")
 	if !gjson.GetBytes(body, "instructions").Exists() {
@@ -119,11 +118,12 @@ func (e *CodexExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, re
 	}
 
 	url := strings.TrimSuffix(baseURL, "/") + "/responses"
-	httpReq, err := e.cacheHelper(ctx, from, url, req, body)
+	httpReq, continuity, err := e.cacheHelper(ctx, auth, from, url, req, opts, body)
 	if err != nil {
 		return resp, err
 	}
 	applyCodexHeaders(httpReq, auth, apiKey, true, e.cfg)
+	logCodexRequestDiagnostics(ctx, auth, req, opts, httpReq.Header, body, continuity)
 	var authID, authLabel, authType, authValue string
 	if auth != nil {
 		authID = auth.ID
@@ -223,11 +223,12 @@ func (e *CodexExecutor) executeCompact(ctx context.Context, auth *cliproxyauth.A
 	body, _ = sjson.DeleteBytes(body, "stream")
 
 	url := strings.TrimSuffix(baseURL, "/") + "/responses/compact"
-	httpReq, err := e.cacheHelper(ctx, from, url, req, body)
+	httpReq, continuity, err := e.cacheHelper(ctx, auth, from, url, req, opts, body)
 	if err != nil {
 		return resp, err
 	}
 	applyCodexHeaders(httpReq, auth, apiKey, false, e.cfg)
+	logCodexRequestDiagnostics(ctx, auth, req, opts, httpReq.Header, body, continuity)
 	var authID, authLabel, authType, authValue string
 	if auth != nil {
 		authID = auth.ID
@@ -310,7 +311,6 @@ func (e *CodexExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Au
 	requestedModel := payloadRequestedModel(opts, req.Model)
 	body = applyPayloadConfigWithRoot(e.cfg, baseModel, to.String(), "", body, originalTranslated, requestedModel)
 	body, _ = sjson.DeleteBytes(body, "previous_response_id")
-	body, _ = sjson.DeleteBytes(body, "prompt_cache_retention")
 	body, _ = sjson.DeleteBytes(body, "safety_identifier")
 	body, _ = sjson.DeleteBytes(body, "stream_options")
 	body, _ = sjson.SetBytes(body, "model", baseModel)
@@ -319,11 +319,12 @@ func (e *CodexExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Au
 	}
 
 	url := strings.TrimSuffix(baseURL, "/") + "/responses"
-	httpReq, err := e.cacheHelper(ctx, from, url, req, body)
+	httpReq, continuity, err := e.cacheHelper(ctx, auth, from, url, req, opts, body)
 	if err != nil {
 		return nil, err
 	}
 	applyCodexHeaders(httpReq, auth, apiKey, true, e.cfg)
+	logCodexRequestDiagnostics(ctx, auth, req, opts, httpReq.Header, body, continuity)
 	var authID, authLabel, authType, authValue string
 	if auth != nil {
 		authID = auth.ID
@@ -599,8 +600,9 @@ func (e *CodexExecutor) Refresh(ctx context.Context, auth *cliproxyauth.Auth) (*
 	return auth, nil
 }
 
-func (e *CodexExecutor) cacheHelper(ctx context.Context, from sdktranslator.Format, url string, req cliproxyexecutor.Request, rawJSON []byte) (*http.Request, error) {
+func (e *CodexExecutor) cacheHelper(ctx context.Context, auth *cliproxyauth.Auth, from sdktranslator.Format, url string, req cliproxyexecutor.Request, opts cliproxyexecutor.Options, rawJSON []byte) (*http.Request, codexContinuity, error) {
 	var cache codexCache
+	continuity := codexContinuity{}
 	if from == "claude" {
 		userIDResult := gjson.GetBytes(req.Payload, "metadata.user_id")
 		if userIDResult.Exists() {
@@ -613,30 +615,26 @@ func (e *CodexExecutor) cacheHelper(ctx context.Context, from sdktranslator.Form
 				}
 				setCodexCache(key, cache)
 			}
+			continuity = codexContinuity{Key: cache.ID, Source: "claude_user_cache"}
 		}
 	} else if from == "openai-response" {
 		promptCacheKey := gjson.GetBytes(req.Payload, "prompt_cache_key")
 		if promptCacheKey.Exists() {
 			cache.ID = promptCacheKey.String()
+			continuity = codexContinuity{Key: cache.ID, Source: "prompt_cache_key"}
 		}
 	} else if from == "openai" {
-		if apiKey := strings.TrimSpace(apiKeyFromContext(ctx)); apiKey != "" {
+		continuity = resolveCodexContinuity(ctx, auth, req, opts)
-			cache.ID = uuid.NewSHA1(uuid.NameSpaceOID, []byte("cli-proxy-api:codex:prompt-cache:"+apiKey)).String()
+		cache.ID = continuity.Key
-		}
 	}
 
-	if cache.ID != "" {
+	rawJSON = applyCodexContinuityBody(rawJSON, continuity)
-		rawJSON, _ = sjson.SetBytes(rawJSON, "prompt_cache_key", cache.ID)
-	}
 	httpReq, err := http.NewRequestWithContext(ctx, http.MethodPost, url, bytes.NewReader(rawJSON))
 	if err != nil {
-		return nil, err
+		return nil, continuity, err
 	}
-	if cache.ID != "" {
+	applyCodexContinuityHeaders(httpReq.Header, continuity)
-		httpReq.Header.Set("Conversation_id", cache.ID)
+	return httpReq, continuity, nil
-		httpReq.Header.Set("Session_id", cache.ID)
-	}
-	return httpReq, nil
 }
 
 func applyCodexHeaders(r *http.Request, auth *cliproxyauth.Auth, token string, stream bool, cfg *config.Config) {
@@ -649,7 +647,7 @@ func applyCodexHeaders(r *http.Request, auth *cliproxyauth.Auth, token string, s
 	}
 
 	misc.EnsureHeader(r.Header, ginHeaders, "Version", "")
-	misc.EnsureHeader(r.Header, ginHeaders, "Session_id", uuid.NewString())
+	misc.EnsureHeader(r.Header, ginHeaders, "session_id", uuid.NewString())
 	misc.EnsureHeader(r.Header, ginHeaders, "X-Codex-Turn-Metadata", "")
 	misc.EnsureHeader(r.Header, ginHeaders, "X-Client-Request-Id", "")
 	cfgUserAgent, _ := codexHeaderDefaults(cfg, auth)

internal/runtime/executor/codex_executor_cache_test.go

@@ -8,6 +8,7 @@ import (
 
 	"github.com/gin-gonic/gin"
 	"github.com/google/uuid"
+	cliproxyauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
 	cliproxyexecutor "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/executor"
 	sdktranslator "github.com/router-for-me/CLIProxyAPI/v6/sdk/translator"
 	"github.com/tidwall/gjson"
@@ -27,7 +28,7 @@ func TestCodexExecutorCacheHelper_OpenAIChatCompletions_StablePromptCacheKeyFrom
 	}
 	url := "https://example.com/responses"
 
-	httpReq, err := executor.cacheHelper(ctx, sdktranslator.FromString("openai"), url, req, rawJSON)
+	httpReq, _, err := executor.cacheHelper(ctx, nil, sdktranslator.FromString("openai"), url, req, cliproxyexecutor.Options{}, rawJSON)
 	if err != nil {
 		t.Fatalf("cacheHelper error: %v", err)
 	}
@@ -42,14 +43,14 @@ func TestCodexExecutorCacheHelper_OpenAIChatCompletions_StablePromptCacheKeyFrom
 	if gotKey != expectedKey {
 		t.Fatalf("prompt_cache_key = %q, want %q", gotKey, expectedKey)
 	}
-	if gotConversation := httpReq.Header.Get("Conversation_id"); gotConversation != expectedKey {
+	if gotSession := httpReq.Header.Get("session_id"); gotSession != expectedKey {
-		t.Fatalf("Conversation_id = %q, want %q", gotConversation, expectedKey)
+		t.Fatalf("session_id = %q, want %q", gotSession, expectedKey)
 	}
-	if gotSession := httpReq.Header.Get("Session_id"); gotSession != expectedKey {
+	if got := httpReq.Header.Get("Conversation_id"); got != "" {
-		t.Fatalf("Session_id = %q, want %q", gotSession, expectedKey)
+		t.Fatalf("Conversation_id = %q, want empty", got)
 	}
 
-	httpReq2, err := executor.cacheHelper(ctx, sdktranslator.FromString("openai"), url, req, rawJSON)
+	httpReq2, _, err := executor.cacheHelper(ctx, nil, sdktranslator.FromString("openai"), url, req, cliproxyexecutor.Options{}, rawJSON)
 	if err != nil {
 		t.Fatalf("cacheHelper error (second call): %v", err)
 	}
@@ -62,3 +63,118 @@ func TestCodexExecutorCacheHelper_OpenAIChatCompletions_StablePromptCacheKeyFrom
 		t.Fatalf("prompt_cache_key (second call) = %q, want %q", gotKey2, expectedKey)
 	}
 }
+
+func TestCodexExecutorCacheHelper_OpenAIResponses_PreservesPromptCacheRetention(t *testing.T) {
+	executor := &CodexExecutor{}
+	url := "https://example.com/responses"
+	req := cliproxyexecutor.Request{
+		Model:   "gpt-5.3-codex",
+		Payload: []byte(`{"model":"gpt-5.3-codex","prompt_cache_key":"cache-key-1","prompt_cache_retention":"persistent"}`),
+	}
+	rawJSON := []byte(`{"model":"gpt-5.3-codex","stream":true,"prompt_cache_retention":"persistent"}`)
+
+	httpReq, _, err := executor.cacheHelper(context.Background(), nil, sdktranslator.FromString("openai-response"), url, req, cliproxyexecutor.Options{}, rawJSON)
+	if err != nil {
+		t.Fatalf("cacheHelper error: %v", err)
+	}
+
+	body, err := io.ReadAll(httpReq.Body)
+	if err != nil {
+		t.Fatalf("read request body: %v", err)
+	}
+
+	if got := gjson.GetBytes(body, "prompt_cache_key").String(); got != "cache-key-1" {
+		t.Fatalf("prompt_cache_key = %q, want %q", got, "cache-key-1")
+	}
+	if got := gjson.GetBytes(body, "prompt_cache_retention").String(); got != "persistent" {
+		t.Fatalf("prompt_cache_retention = %q, want %q", got, "persistent")
+	}
+	if got := httpReq.Header.Get("session_id"); got != "cache-key-1" {
+		t.Fatalf("session_id = %q, want %q", got, "cache-key-1")
+	}
+	if got := httpReq.Header.Get("Conversation_id"); got != "" {
+		t.Fatalf("Conversation_id = %q, want empty", got)
+	}
+}
+
+func TestCodexExecutorCacheHelper_OpenAIChatCompletions_UsesExecutionSessionForContinuity(t *testing.T) {
+	executor := &CodexExecutor{}
+	rawJSON := []byte(`{"model":"gpt-5.4","stream":true}`)
+	req := cliproxyexecutor.Request{
+		Model:   "gpt-5.4",
+		Payload: []byte(`{"model":"gpt-5.4"}`),
+	}
+	opts := cliproxyexecutor.Options{Metadata: map[string]any{cliproxyexecutor.ExecutionSessionMetadataKey: "exec-session-1"}}
+
+	httpReq, _, err := executor.cacheHelper(context.Background(), nil, sdktranslator.FromString("openai"), "https://example.com/responses", req, opts, rawJSON)
+	if err != nil {
+		t.Fatalf("cacheHelper error: %v", err)
+	}
+
+	body, err := io.ReadAll(httpReq.Body)
+	if err != nil {
+		t.Fatalf("read request body: %v", err)
+	}
+
+	if got := gjson.GetBytes(body, "prompt_cache_key").String(); got != "exec-session-1" {
+		t.Fatalf("prompt_cache_key = %q, want %q", got, "exec-session-1")
+	}
+	if got := httpReq.Header.Get("session_id"); got != "exec-session-1" {
+		t.Fatalf("session_id = %q, want %q", got, "exec-session-1")
+	}
+}
+
+func TestCodexExecutorCacheHelper_OpenAIChatCompletions_FallsBackToStableAuthID(t *testing.T) {
+	executor := &CodexExecutor{}
+	rawJSON := []byte(`{"model":"gpt-5.4","stream":true}`)
+	req := cliproxyexecutor.Request{
+		Model:   "gpt-5.4",
+		Payload: []byte(`{"model":"gpt-5.4"}`),
+	}
+	auth := &cliproxyauth.Auth{ID: "codex-auth-1", Provider: "codex"}
+
+	httpReq, _, err := executor.cacheHelper(context.Background(), auth, sdktranslator.FromString("openai"), "https://example.com/responses", req, cliproxyexecutor.Options{}, rawJSON)
+	if err != nil {
+		t.Fatalf("cacheHelper error: %v", err)
+	}
+
+	body, err := io.ReadAll(httpReq.Body)
+	if err != nil {
+		t.Fatalf("read request body: %v", err)
+	}
+
+	expected := uuid.NewSHA1(uuid.NameSpaceOID, []byte("cli-proxy-api:codex:prompt-cache:auth:codex-auth-1")).String()
+	if got := gjson.GetBytes(body, "prompt_cache_key").String(); got != expected {
+		t.Fatalf("prompt_cache_key = %q, want %q", got, expected)
+	}
+	if got := httpReq.Header.Get("session_id"); got != expected {
+		t.Fatalf("session_id = %q, want %q", got, expected)
+	}
+}
+
+func TestCodexExecutorCacheHelper_ClaudePreservesCacheContinuity(t *testing.T) {
+	executor := &CodexExecutor{}
+	req := cliproxyexecutor.Request{
+		Model:   "claude-3-7-sonnet",
+		Payload: []byte(`{"metadata":{"user_id":"user-1"}}`),
+	}
+	rawJSON := []byte(`{"model":"gpt-5.4","stream":true}`)
+
+	httpReq, continuity, err := executor.cacheHelper(context.Background(), nil, sdktranslator.FromString("claude"), "https://example.com/responses", req, cliproxyexecutor.Options{}, rawJSON)
+	if err != nil {
+		t.Fatalf("cacheHelper error: %v", err)
+	}
+	if continuity.Key == "" {
+		t.Fatal("continuity.Key = empty, want non-empty")
+	}
+	body, err := io.ReadAll(httpReq.Body)
+	if err != nil {
+		t.Fatalf("read request body: %v", err)
+	}
+	if got := gjson.GetBytes(body, "prompt_cache_key").String(); got != continuity.Key {
+		t.Fatalf("prompt_cache_key = %q, want %q", got, continuity.Key)
+	}
+	if got := httpReq.Header.Get("session_id"); got != continuity.Key {
+		t.Fatalf("session_id = %q, want %q", got, continuity.Key)
+	}
+}

internal/runtime/executor/codex_websockets_executor.go

@@ -178,7 +178,6 @@ func (e *CodexWebsocketsExecutor) Execute(ctx context.Context, auth *cliproxyaut
 	body, _ = sjson.SetBytes(body, "model", baseModel)
 	body, _ = sjson.SetBytes(body, "stream", true)
 	body, _ = sjson.DeleteBytes(body, "previous_response_id")
-	body, _ = sjson.DeleteBytes(body, "prompt_cache_retention")
 	body, _ = sjson.DeleteBytes(body, "safety_identifier")
 	if !gjson.GetBytes(body, "instructions").Exists() {
 		body, _ = sjson.SetBytes(body, "instructions", "")
@@ -190,7 +189,7 @@ func (e *CodexWebsocketsExecutor) Execute(ctx context.Context, auth *cliproxyaut
 		return resp, err
 	}
 
-	body, wsHeaders := applyCodexPromptCacheHeaders(from, req, body)
+	body, wsHeaders, continuity := applyCodexPromptCacheHeaders(ctx, auth, from, req, opts, body)
 	wsHeaders = applyCodexWebsocketHeaders(ctx, wsHeaders, auth, apiKey, e.cfg)
 
 	var authID, authLabel, authType, authValue string
@@ -209,6 +208,7 @@ func (e *CodexWebsocketsExecutor) Execute(ctx context.Context, auth *cliproxyaut
 	}
 
 	wsReqBody := buildCodexWebsocketRequestBody(body)
+	logCodexRequestDiagnostics(ctx, auth, req, opts, wsHeaders, body, continuity)
 	recordAPIRequest(ctx, e.cfg, upstreamRequestLog{
 		URL:       wsURL,
 		Method:    "WEBSOCKET",
@@ -385,7 +385,7 @@ func (e *CodexWebsocketsExecutor) ExecuteStream(ctx context.Context, auth *clipr
 		return nil, err
 	}
 
-	body, wsHeaders := applyCodexPromptCacheHeaders(from, req, body)
+	body, wsHeaders, continuity := applyCodexPromptCacheHeaders(ctx, auth, from, req, opts, body)
 	wsHeaders = applyCodexWebsocketHeaders(ctx, wsHeaders, auth, apiKey, e.cfg)
 
 	var authID, authLabel, authType, authValue string
@@ -403,6 +403,7 @@ func (e *CodexWebsocketsExecutor) ExecuteStream(ctx context.Context, auth *clipr
 	}
 
 	wsReqBody := buildCodexWebsocketRequestBody(body)
+	logCodexRequestDiagnostics(ctx, auth, req, opts, wsHeaders, body, continuity)
 	recordAPIRequest(ctx, e.cfg, upstreamRequestLog{
 		URL:       wsURL,
 		Method:    "WEBSOCKET",
@@ -761,13 +762,14 @@ func buildCodexResponsesWebsocketURL(httpURL string) (string, error) {
 	return parsed.String(), nil
 }
 
-func applyCodexPromptCacheHeaders(from sdktranslator.Format, req cliproxyexecutor.Request, rawJSON []byte) ([]byte, http.Header) {
+func applyCodexPromptCacheHeaders(ctx context.Context, auth *cliproxyauth.Auth, from sdktranslator.Format, req cliproxyexecutor.Request, opts cliproxyexecutor.Options, rawJSON []byte) ([]byte, http.Header, codexContinuity) {
 	headers := http.Header{}
 	if len(rawJSON) == 0 {
-		return rawJSON, headers
+		return rawJSON, headers, codexContinuity{}
 	}
 
 	var cache codexCache
+	continuity := codexContinuity{}
 	if from == "claude" {
 		userIDResult := gjson.GetBytes(req.Payload, "metadata.user_id")
 		if userIDResult.Exists() {
@@ -781,20 +783,22 @@ func applyCodexPromptCacheHeaders(from sdktranslator.Format, req cliproxyexecuto
 				}
 				setCodexCache(key, cache)
 			}
+			continuity = codexContinuity{Key: cache.ID, Source: "claude_user_cache"}
 		}
 	} else if from == "openai-response" {
 		if promptCacheKey := gjson.GetBytes(req.Payload, "prompt_cache_key"); promptCacheKey.Exists() {
 			cache.ID = promptCacheKey.String()
+			continuity = codexContinuity{Key: cache.ID, Source: "prompt_cache_key"}
 		}
+	} else if from == "openai" {
+		continuity = resolveCodexContinuity(ctx, auth, req, opts)
+		cache.ID = continuity.Key
 	}
 
-	if cache.ID != "" {
+	rawJSON = applyCodexContinuityBody(rawJSON, continuity)
-		rawJSON, _ = sjson.SetBytes(rawJSON, "prompt_cache_key", cache.ID)
+	applyCodexContinuityHeaders(headers, continuity)
-		headers.Set("Conversation_id", cache.ID)
-		headers.Set("Session_id", cache.ID)
-	}
 
-	return rawJSON, headers
+	return rawJSON, headers, continuity
 }
 
 func applyCodexWebsocketHeaders(ctx context.Context, headers http.Header, auth *cliproxyauth.Auth, token string, cfg *config.Config) http.Header {
@@ -826,7 +830,7 @@ func applyCodexWebsocketHeaders(ctx context.Context, headers http.Header, auth *
 		betaHeader = codexResponsesWebsocketBetaHeaderValue
 	}
 	headers.Set("OpenAI-Beta", betaHeader)
-	misc.EnsureHeader(headers, ginHeaders, "Session_id", uuid.NewString())
+	misc.EnsureHeader(headers, ginHeaders, "session_id", uuid.NewString())
 	ensureHeaderWithConfigPrecedence(headers, ginHeaders, "User-Agent", cfgUserAgent, codexUserAgent)
 
 	isAPIKey := false

internal/runtime/executor/codex_websockets_executor_test.go

@@ -9,7 +9,9 @@ import (
 	"github.com/gin-gonic/gin"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
 	cliproxyauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
+	cliproxyexecutor "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/executor"
 	sdkconfig "github.com/router-for-me/CLIProxyAPI/v6/sdk/config"
+	sdktranslator "github.com/router-for-me/CLIProxyAPI/v6/sdk/translator"
 	"github.com/tidwall/gjson"
 )
 
@@ -32,6 +34,49 @@ func TestBuildCodexWebsocketRequestBodyPreservesPreviousResponseID(t *testing.T)
 	}
 }
 
+func TestApplyCodexPromptCacheHeaders_PreservesPromptCacheRetention(t *testing.T) {
+	req := cliproxyexecutor.Request{
+		Model:   "gpt-5-codex",
+		Payload: []byte(`{"prompt_cache_key":"cache-key-1","prompt_cache_retention":"persistent"}`),
+	}
+	body := []byte(`{"model":"gpt-5-codex","stream":true,"prompt_cache_retention":"persistent"}`)
+
+	updatedBody, headers, _ := applyCodexPromptCacheHeaders(context.Background(), nil, sdktranslator.FromString("openai-response"), req, cliproxyexecutor.Options{}, body)
+
+	if got := gjson.GetBytes(updatedBody, "prompt_cache_key").String(); got != "cache-key-1" {
+		t.Fatalf("prompt_cache_key = %q, want %q", got, "cache-key-1")
+	}
+	if got := gjson.GetBytes(updatedBody, "prompt_cache_retention").String(); got != "persistent" {
+		t.Fatalf("prompt_cache_retention = %q, want %q", got, "persistent")
+	}
+	if got := headers.Get("session_id"); got != "cache-key-1" {
+		t.Fatalf("session_id = %q, want %q", got, "cache-key-1")
+	}
+	if got := headers.Get("Conversation_id"); got != "" {
+		t.Fatalf("Conversation_id = %q, want empty", got)
+	}
+}
+
+func TestApplyCodexPromptCacheHeaders_ClaudePreservesContinuity(t *testing.T) {
+	req := cliproxyexecutor.Request{
+		Model:   "claude-3-7-sonnet",
+		Payload: []byte(`{"metadata":{"user_id":"user-1"}}`),
+	}
+	body := []byte(`{"model":"gpt-5.4","stream":true}`)
+
+	updatedBody, headers, continuity := applyCodexPromptCacheHeaders(context.Background(), nil, sdktranslator.FromString("claude"), req, cliproxyexecutor.Options{}, body)
+
+	if continuity.Key == "" {
+		t.Fatal("continuity.Key = empty, want non-empty")
+	}
+	if got := gjson.GetBytes(updatedBody, "prompt_cache_key").String(); got != continuity.Key {
+		t.Fatalf("prompt_cache_key = %q, want %q", got, continuity.Key)
+	}
+	if got := headers.Get("session_id"); got != continuity.Key {
+		t.Fatalf("session_id = %q, want %q", got, continuity.Key)
+	}
+}
+
 func TestApplyCodexWebsocketHeadersDefaultsToCurrentResponsesBeta(t *testing.T) {
 	headers := applyCodexWebsocketHeaders(context.Background(), http.Header{}, nil, "", nil)