@code-yeongyu/senpi-ai 2026.7.25-2 → 2026.7.28

package/dist/api/openai-completions.js

@@ -5,8 +5,9 @@ import { AssistantMessageEventStream } from "../utils/event-stream.js";
 import { shortHash } from "../utils/hash.js";
 import { headersToRecord } from "../utils/headers.js";
 import { parseStreamingJson } from "../utils/json-parse.js";
+import { getOpenAICompletionsCompat as getCompat, } from "../utils/prompt-cache-ttl.js";
 import { getProviderEnvValue } from "../utils/provider-env.js";
-import { retryProviderRequest } from "../utils/provider-retry.js";
+import { retryProviderStreamRequest } from "../utils/provider-retry.js";
 import { sanitizeSurrogates } from "../utils/sanitize-unicode.js";
 import { isForcedToolChoiceUnsupportedError, omitToolChoiceParam } from "../utils/tool-choice-fallback.js";
 import { normalizeToolParametersForMoonshot, normalizeToolParametersForOpenAICompat, } from "../utils/tool-schema-compat.js";
@@ -15,6 +16,7 @@ import { buildCopilotDynamicHeaders, hasCopilotVisionInput } from "./github-copi
 import { clampOpenAIPromptCacheKey } from "./openai-prompt-cache.js";
 import { applyExtraBody, buildBaseOptions, clampMaxForOpenAI, OPENAI_COMPLETIONS_RESERVED_BODY_KEYS, } from "./simple-options.js";
 import { transformMessages } from "./transform-messages.js";
+export { getOpenAICompletionsCompat as getCompat, } from "../utils/prompt-cache-ttl.js";
 const KIMI_K3_THINKING_LEVEL_MAP = {
     off: null,
     minimal: null,
@@ -246,12 +248,11 @@ export const stream = (model, context, options) => {
                     throw error;
                 }
             };
-            const { data: openaiStream, response } = await retryProviderRequest(createRequest, {
-                maxRetries: options?.maxRetries,
-                maxRetryDelayMs: options?.maxRetryDelayMs,
-                signal: options?.signal,
-            });
-            await options?.onResponse?.({ status: response.status, headers: headersToRecord(response.headers) }, model);
+            const { stream: openaiStream } = await retryProviderStreamRequest(async () => {
+                const { data, response } = await createRequest();
+                await options?.onResponse?.({ status: response.status, headers: headersToRecord(response.headers) }, model);
+                return { stream: data, metadata: response };
+            }, { maxRetries: options?.maxRetries, maxRetryDelayMs: options?.maxRetryDelayMs, signal: options?.signal });
             stream.push({ type: "start", partial: output });
             let textBlock = null;
             let thinkingBlock = null;
@@ -1266,119 +1267,4 @@ function mapStopReason(reason) {
             };
     }
 }
-/**
- * Detect compatibility settings from provider and baseUrl for known providers.
- * Provider takes precedence over URL-based detection since it's explicitly configured.
- * Returns a fully resolved OpenAICompletionsCompat object with all fields set.
- */
-function detectCompat(model) {
-    const provider = model.provider;
-    const baseUrl = model.baseUrl;
-    const isZai = provider === "zai" ||
-        provider === "zai-coding-cn" ||
-        baseUrl.includes("api.z.ai") ||
-        baseUrl.includes("open.bigmodel.cn");
-    const isTogether = provider === "together" || baseUrl.includes("api.together.ai") || baseUrl.includes("api.together.xyz");
-    const isMoonshot = provider === "moonshotai" || provider === "moonshotai-cn" || baseUrl.includes("api.moonshot.");
-    const isOpenRouter = provider === "openrouter" || baseUrl.includes("openrouter.ai");
-    const isCloudflareWorkersAI = provider === "cloudflare-workers-ai" || baseUrl.includes("api.cloudflare.com");
-    const isCloudflareAiGateway = provider === "cloudflare-ai-gateway" || baseUrl.includes("gateway.ai.cloudflare.com");
-    const isNvidia = provider === "nvidia" || baseUrl.includes("integrate.api.nvidia.com");
-    const isAntLing = provider === "ant-ling" || baseUrl.includes("api.ant-ling.com");
-    const isNonStandard = isNvidia ||
-        provider === "cerebras" ||
-        baseUrl.includes("cerebras.ai") ||
-        provider === "xai" ||
-        baseUrl.includes("api.x.ai") ||
-        isTogether ||
-        baseUrl.includes("chutes.ai") ||
-        baseUrl.includes("deepseek.com") ||
-        isZai ||
-        isMoonshot ||
-        provider === "opencode" ||
-        baseUrl.includes("opencode.ai") ||
-        isCloudflareWorkersAI ||
-        isCloudflareAiGateway ||
-        isAntLing;
-    const useMaxTokens = baseUrl.includes("chutes.ai") || isMoonshot || isCloudflareAiGateway || isTogether || isNvidia || isAntLing;
-    const isGrok = provider === "xai" || baseUrl.includes("api.x.ai");
-    const isDeepSeek = provider === "deepseek" || baseUrl.includes("deepseek.com");
-    const isOpenRouterDeveloperRoleModel = isOpenRouter && (model.id.startsWith("anthropic/") || model.id.startsWith("openai/"));
-    const cacheControlFormat = provider === "openrouter" && model.id.startsWith("anthropic/") ? "anthropic" : undefined;
-    return {
-        supportsStore: !isNonStandard,
-        supportsDeveloperRole: isOpenRouterDeveloperRoleModel || (!isNonStandard && !isOpenRouter),
-        supportsReasoningEffort: !isGrok && !isZai && !isMoonshot && !isTogether && !isCloudflareAiGateway && !isNvidia && !isAntLing,
-        supportsUsageInStreaming: true,
-        maxTokensField: useMaxTokens ? "max_tokens" : "max_completion_tokens",
-        requiresToolResultName: false,
-        requiresAssistantAfterToolResult: false,
-        requiresThinkingAsText: false,
-        requiresReasoningContentOnAssistantMessages: isDeepSeek,
-        thinkingFormat: isDeepSeek
-            ? "deepseek"
-            : isZai
-                ? "zai"
-                : isTogether
-                    ? "together"
-                    : isAntLing
-                        ? "ant-ling"
-                        : isOpenRouter
-                            ? "openrouter"
-                            : "openai",
-        openRouterRouting: {},
-        vercelGatewayRouting: {},
-        chatTemplateKwargs: {},
-        zaiToolStream: false,
-        supportsStrictMode: !isMoonshot && !isTogether && !isCloudflareAiGateway && !isNvidia,
-        toolSchemaFlavor: isMoonshot ? "moonshot-mfjs" : undefined,
-        supportsDisabledThinking: true,
-        toolCallFormat: undefined,
-        supportsOpenAIGrammarTools: false,
-        cacheControlFormat,
-        sendSessionAffinityHeaders: false,
-        deferredToolsMode: undefined,
-        sessionAffinityFormat: isOpenRouter ? "openrouter" : "openai",
-        supportsLongCacheRetention: !(isTogether ||
-            isCloudflareWorkersAI ||
-            isCloudflareAiGateway ||
-            isNvidia ||
-            isAntLing),
-    };
-}
-/**
- * Get resolved compatibility settings for a model.
- * Auto-detects from provider/URL then overrides with explicit model.compat.
- */
-function getCompat(model) {
-    const detected = detectCompat(model);
-    if (!model.compat)
-        return detected;
-    return {
-        supportsStore: model.compat.supportsStore ?? detected.supportsStore,
-        supportsDeveloperRole: model.compat.supportsDeveloperRole ?? detected.supportsDeveloperRole,
-        supportsReasoningEffort: model.compat.supportsReasoningEffort ?? detected.supportsReasoningEffort,
-        supportsUsageInStreaming: model.compat.supportsUsageInStreaming ?? detected.supportsUsageInStreaming,
-        maxTokensField: model.compat.maxTokensField ?? detected.maxTokensField,
-        requiresToolResultName: model.compat.requiresToolResultName ?? detected.requiresToolResultName,
-        requiresAssistantAfterToolResult: model.compat.requiresAssistantAfterToolResult ?? detected.requiresAssistantAfterToolResult,
-        requiresThinkingAsText: model.compat.requiresThinkingAsText ?? detected.requiresThinkingAsText,
-        requiresReasoningContentOnAssistantMessages: model.compat.requiresReasoningContentOnAssistantMessages ??
-            detected.requiresReasoningContentOnAssistantMessages,
-        thinkingFormat: model.compat.thinkingFormat ?? detected.thinkingFormat,
-        supportsDisabledThinking: model.compat.supportsDisabledThinking ?? detected.supportsDisabledThinking,
-        openRouterRouting: model.compat.openRouterRouting ?? detected.openRouterRouting,
-        vercelGatewayRouting: model.compat.vercelGatewayRouting ?? detected.vercelGatewayRouting,
-        chatTemplateKwargs: model.compat.chatTemplateKwargs ?? detected.chatTemplateKwargs,
-        zaiToolStream: model.compat.zaiToolStream ?? detected.zaiToolStream,
-        supportsStrictMode: model.compat.supportsStrictMode ?? detected.supportsStrictMode,
-        toolCallFormat: model.compat.toolCallFormat ?? detected.toolCallFormat,
-        supportsOpenAIGrammarTools: model.compat.supportsOpenAIGrammarTools ?? detected.supportsOpenAIGrammarTools,
-        cacheControlFormat: model.compat.cacheControlFormat ?? detected.cacheControlFormat,
-        sendSessionAffinityHeaders: model.compat.sendSessionAffinityHeaders ?? detected.sendSessionAffinityHeaders,
-        deferredToolsMode: model.compat.deferredToolsMode ?? detected.deferredToolsMode,
-        sessionAffinityFormat: model.compat.sessionAffinityFormat ?? detected.sessionAffinityFormat,
-        supportsLongCacheRetention: model.compat.supportsLongCacheRetention ?? detected.supportsLongCacheRetention,
-    };
-}
 //# sourceMappingURL=openai-completions.js.map