@fudrouter/fsrouter 0.6.72 → 0.6.74

package/dist/open-sse/services/usage/grok-cli.js

@@ -24,6 +24,11 @@
 
 import { proxyAwareFetch } from "../../utils/proxyFetch.js";
 import { U, parseResetTime, toFiniteNumber } from "./shared.js";
+import {
+  GROK_CLI_CLIENT_IDENTIFIER,
+  GROK_CLI_USER_AGENT,
+  GROK_CLI_VERSION,
+} from "../../config/grokCli.js";
 
 const USAGE = U("grok-cli");
 const BILLING_URL = USAGE.url || "https://cli-chat-proxy.grok.com/v1/billing?format=credits";
@@ -43,10 +48,11 @@ function buildGrokCliHeaders(accessToken, providerSpecificData = {}) {
   const headers = {
     Authorization: `Bearer ${accessToken}`,
     Accept: "application/json",
-    "User-Agent": "grok-pager/0.2.93 grok-shell/0.2.93 (linux; x86_64)",
+    "User-Agent": GROK_CLI_USER_AGENT,
     "x-xai-token-auth": "xai-grok-cli",
-    "x-grok-client-identifier": "grok-pager",
-    "x-grok-client-version": "0.2.93",
+    "x-grok-client-identifier": GROK_CLI_CLIENT_IDENTIFIER,
+    "x-grok-client-version": GROK_CLI_VERSION,
+    "x-grok-client-mode": "headless",
   };
   const email = psd.email;
   const userId = psd.userId || psd.principalId;
@@ -55,8 +61,18 @@ function buildGrokCliHeaders(accessToken, providerSpecificData = {}) {
   return headers;
 }
 
+function subscriptionTier(user, config) {
+  const rawTier =
+    user?.subscriptionTier ??
+    user?.subscription_tier ??
+    user?.subscription?.tier ??
+    config?.subscriptionTier ??
+    config?.subscription_tier;
+  return typeof rawTier === "string" ? rawTier.trim() : "";
+}
+
 function resolvePlan(user, config) {
-  const tier = typeof user?.subscriptionTier === "string" ? user.subscriptionTier.trim() : "";
+  const tier = subscriptionTier(user, config);
   if (tier) {
     return tier
       .replace(/[_-]+/g, " ")
@@ -105,11 +121,42 @@ export function parseGrokCliBilling(billing, user = null) {
 
   const periodEnd =
     parseResetTime(config.billingPeriodEnd) ||
+    parseResetTime(config.billing_period_end) ||
     parseResetTime(config.currentPeriod?.end) ||
+    parseResetTime(config.resetAt || config.resetsAt || config.periodEnd) ||
     parseResetTime(root.billingPeriodEnd) ||
+    parseResetTime(root.billing_period_end) ||
+    parseResetTime(root.resetAt || root.resetsAt || root.periodEnd) ||
     null;
 
   const quotas = {};
+  const tier = subscriptionTier(user, config);
+  const subscriptionAccess = Boolean(tier) && !/^(free|none|null)$/i.test(tier);
+
+  // Current Grok Build responses expose included monthly usage at top level.
+  const monthlyLimit = unwrapVal(
+    config.monthlyLimit ?? config.monthly_limit ?? root.monthlyLimit ?? root.monthly_limit,
+    NaN,
+  );
+  const includedUsed = unwrapVal(
+    config.includedUsed ?? config.included_used ?? root.includedUsed ?? root.included_used,
+    NaN,
+  );
+  const totalUsed = unwrapVal(
+    config.totalUsed ?? config.total_used ?? root.totalUsed ?? root.total_used,
+    NaN,
+  );
+  if (Number.isFinite(monthlyLimit) && monthlyLimit > 0) {
+    quotas["Monthly included"] = makeQuota({
+      used: Number.isFinite(includedUsed)
+        ? includedUsed
+        : Number.isFinite(totalUsed)
+          ? totalUsed
+          : 0,
+      total: monthlyLimit,
+      resetAt: periodEnd,
+    });
+  }
 
   // Primary: on-demand spending window (subscription / promo credits)
   const onDemandCap = unwrapVal(config.onDemandCap ?? root.onDemandCap, NaN);
@@ -121,7 +168,12 @@ export function parseGrokCliBilling(billing, user = null) {
       total: onDemandCap,
       resetAt: periodEnd,
     });
-  } else if (Number.isFinite(onDemandCap) && onDemandCap === 0 && Number.isFinite(onDemandUsed)) {
+  } else if (
+    !subscriptionAccess &&
+    Number.isFinite(onDemandCap) &&
+    onDemandCap === 0 &&
+    Number.isFinite(onDemandUsed)
+  ) {
     // Cap 0 is the exhausted free/promo state (chat returns 402 spending-limit).
     // UI treats total===0 as unlimited, so use a synthetic 1/1 depleted row.
     quotas["On-demand"] = {
@@ -199,6 +251,7 @@ export function parseGrokCliBilling(billing, user = null) {
     quotas,
     periodEnd,
     exhausted,
+    subscriptionAccess,
     rawConfig: config,
   };
 }
@@ -255,8 +308,9 @@ export async function getGrokCliUsage(accessToken, providerSpecificData = null,
     if (!parsed.quotas || Object.keys(parsed.quotas).length === 0) {
       return {
         plan: parsed.plan,
-        message:
-          "Grok Build connected, but no credit allotment was returned. Free promo may be exhausted — upgrade at https://grok.com/supergrok or add credits at https://grok.com/?_s=usage.",
+        message: parsed.subscriptionAccess
+          ? "Subscription access is active; Grok does not expose a numeric included quota."
+          : "Grok Build connected, but no credit allotment was returned. Free promo may be exhausted.",
         quotas: {},
       };
     }

package/dist/open-sse/services/usage/misc.js

@@ -267,22 +267,3 @@ export async function getQoderUsage(accessToken, proxyOptions = null) {
     return { message: `Qoder connected. Unable to fetch usage: ${error.message}` };
   }
 }
-
-/**
- * Cloudflare Workers AI Usage
- * Free tier: 10,000 neurons/day. No public usage API — returns free tier info.
- */
-export async function getCloudflareAiUsage(apiKey, providerSpecificData) {
-  return {
-    plan: "Workers AI Free",
-    quotas: {
-      neurons: {
-        used: 0,
-        total: 10000,
-        resetAt: null,
-        unlimited: false,
-        displayName: "Neurons (daily free)",
-      },
-    },
-  };
-}

package/dist/open-sse/services/usage.js

@@ -12,7 +12,6 @@ import { getKiroUsage } from "./usage/kiro.js";
 import { getMiniMaxUsage } from "./usage/minimax.js";
 import { getCodeBuddyCnUsage } from "./usage/codebuddy-cn.js";
 import { getGrokCliUsage } from "./usage/grok-cli.js";
-import { getCloudflareAiUsage } from "./usage/misc.js";
 import {
   getQwenUsage,
   getIflowUsage,
@@ -46,7 +45,6 @@ const USAGE_HANDLERS = {
   "vercel-ai-gateway": (c) => getVercelAiGatewayUsage(c.apiKey, c.proxyOptions),
   "codebuddy-cn": (c) => getCodeBuddyCnUsage(c.accessToken, c.apiKey, c.providerSpecificData, c.proxyOptions),
   "grok-cli": (c) => getGrokCliUsage(c.accessToken, c.providerSpecificData, c.proxyOptions),
-  "cloudflare-ai": (c) => getCloudflareAiUsage(c.apiKey, c.providerSpecificData),
 };
 
 export async function getUsageForProvider(connection, proxyOptions = null) {

package/dist/open-sse/translator/concerns/paramSupport.js

@@ -6,8 +6,8 @@ import { getCapabilitiesForModel } from "../../providers/capabilities.js";
 // Each rule: optional provider, regex match on model, list of params to drop.
 // A param is removed only when it is present (!== undefined).
 const STRIP_RULES = [
-  // claude-opus-4 series: temperature is deprecated (Anthropic 400). #1748
-  { match: /claude-opus-4/i, drop: ["temperature"] },
+  // All Claude models: temperature deprecated/rejected upstream (Anthropic 400). #1748
+  { match: /claude/i, drop: ["temperature"] },
   // GitHub Copilot gpt-5.4: temperature unsupported.
   { provider: "github", match: /gpt-5\.4/i, drop: ["temperature"] },
   // GitHub Copilot Claude (except opus/sonnet 4.6): thinking + reasoning_effort rejected. #713

package/dist/open-sse/translator/concerns/thinkingUnified.js

@@ -229,6 +229,12 @@ function applyFormat(fmt, body, cfg, caps) {
     }
     case "claude-adaptive": {
       if (none && canDisable) { body.thinking = { type: "disabled" }; break; }
+      // output_config.effort alone does NOT turn thinking on: Anthropic requires
+      // an explicit thinking:{type:"adaptive"} on Opus 4.6/4.7/4.8 and Sonnet 4.6
+      // ("thinking is off unless you explicitly set it"), and Anthropic-compatible
+      // shims (e.g. GitHub Copilot /v1/messages) default thinking off even for
+      // Sonnet 5. Send both fields — the documented adaptive-thinking shape.
+      body.thinking = { type: "adaptive" };
       const level = toLevel(eff);
       body.output_config = { effort: level === "xhigh" ? "high" : level };
       break;

package/dist/open-sse/translator/index.js

@@ -1,23 +1,24 @@
 import { FORMATS } from "./formats.js";
-import { ensureToolCallIds, fixMissingToolResponses } from "./helpers/toolCallHelper.js";
-import { prepareClaudeRequest } from "./helpers/claudeHelper.js";
+import { ensureToolCallIds, fixMissingToolResponses } from "./concerns/toolCall.js";
+import { prepareClaudeRequest } from "./formats/claude.js";
 import { cloakClaudeTools } from "../utils/claudeCloaking.js";
-import { filterToOpenAIFormat } from "./helpers/openaiHelper.js";
+import { filterToOpenAIFormat } from "./formats/openai.js";
 import { normalizeThinkingConfig } from "../services/provider.js";
+import { applyThinking, captureThinking } from "./concerns/thinkingUnified.js";
+import { captureSessionId } from "../utils/sessionManager.js";
 import { AntigravityExecutor } from "../executors/antigravity.js";
+import { PROVIDERS } from "../providers/index.js";
 
-// Registry for translators
-const requestRegistry = new Map();
-const responseRegistry = new Map();
-
-import { createRequire } from "module";
-const require = createRequire(import.meta.url);
-
-// Track initialization state
-let initialized = false;
+// Registry for translators. Lazy-init guards against circular-import order:
+// translator modules call register() (side-effect) before this module's body runs.
+// var (not let): hoisted as undefined so register() can run during circular import (no TDZ).
+var requestRegistry;
+var responseRegistry;
 
 // Register translator
 export function register(from, to, requestFn, responseFn) {
+  requestRegistry ??= new Map();
+  responseRegistry ??= new Map();
   const key = `${from}:${to}`;
   if (requestFn) {
     requestRegistry.set(key, requestFn);
@@ -27,35 +28,8 @@ export function register(from, to, requestFn, responseFn) {
   }
 }
 
-// Lazy load translators (called once on first use)
-function ensureInitialized() {
-  if (initialized) return;
-  initialized = true;
-
-  // Request translators - sync require pattern for bundler
-  require("./request/claude-to-openai.js");
-  require("./request/openai-to-claude.js");
-  require("./request/gemini-to-openai.js");
-  require("./request/openai-to-gemini.js");
-  require("./request/openai-to-vertex.js");
-  require("./request/antigravity-to-openai.js");
-  require("./request/openai-responses.js");
-  require("./request/openai-to-kiro.js");
-  require("./request/openai-to-cursor.js");
-  require("./request/openai-to-ollama.js");
-  require("./request/openai-to-commandcode.js");
-
-  // Response translators
-  require("./response/claude-to-openai.js");
-  require("./response/openai-to-claude.js");
-  require("./response/gemini-to-openai.js");
-  require("./response/openai-to-antigravity.js");
-  require("./response/openai-responses.js");
-  require("./response/kiro-to-openai.js");
-  require("./response/cursor-to-openai.js");
-  require("./response/ollama-to-openai.js");
-  require("./response/commandcode-to-openai.js");
-}
+// No-op: translators self-register via the static imports at the bottom of this file.
+function ensureInitialized() {}
 
 // Strip specific content types from messages (explicit opt-in via strip[] in PROVIDER_MODELS)
 function stripContentTypes(body, stripList = []) {
@@ -91,42 +65,72 @@ export function translateRequest(sourceFormat, targetFormat, model, body, stream
   // Fix missing tool responses (insert empty tool_result if needed)
   fixMissingToolResponses(result);
 
+  // Capture thinking intent from the original (pre-translation) body, before any
+  // format conversion strips/renames the fields. Applied after translation.
+  const thinkingIntent = captureThinking(result);
+
+  // Capture session id from the original body (envelope still intact, e.g. antigravity request.sessionId)
+  const clientSessionId = captureSessionId(result, credentials, connectionId, targetFormat);
+  // Expose to downstream translators (gemini-cli/antigravity envelopes) that run after envelope is stripped
+  if (credentials) credentials._clientSessionId = clientSessionId;
+
   // If same format, skip translation steps
   if (sourceFormat !== targetFormat) {
-    // Step 1: source -> openai (if source is not openai)
-    if (sourceFormat !== FORMATS.OPENAI) {
-      const toOpenAI = requestRegistry.get(`${sourceFormat}:${FORMATS.OPENAI}`);
-      if (toOpenAI) {
-        result = toOpenAI(model, result, stream, credentials);
-        // Log OpenAI intermediate format
-        reqLogger?.logOpenAIRequest?.(result);
+    // Direct route: if a translator is registered for this exact source:target
+    // pair, use it instead of pivoting through OpenAI. This is lossless for
+    // pairs like claude:kiro (avoids the claude->openai->kiro double-hop).
+    const directFn = requestRegistry.get(`${sourceFormat}:${targetFormat}`);
+    if (directFn) {
+      result = directFn(model, result, stream, credentials);
+    } else {
+      // Step 1: source -> openai (if source is not openai)
+      if (sourceFormat !== FORMATS.OPENAI) {
+        const toOpenAI = requestRegistry.get(`${sourceFormat}:${FORMATS.OPENAI}`);
+        if (toOpenAI) {
+          result = toOpenAI(model, result, stream, credentials);
+          // Log OpenAI intermediate format
+          reqLogger?.logOpenAIRequest?.(result);
+        }
       }
-    }
 
-    // Step 2: openai -> target (if target is not openai)
-    if (targetFormat !== FORMATS.OPENAI) {
-      const fromOpenAI = requestRegistry.get(`${FORMATS.OPENAI}:${targetFormat}`);
-      if (fromOpenAI) {
-        result = fromOpenAI(model, result, stream, credentials);
+      // Step 2: openai -> target (if target is not openai)
+      if (targetFormat !== FORMATS.OPENAI) {
+        const fromOpenAI = requestRegistry.get(`${FORMATS.OPENAI}:${targetFormat}`);
+        if (fromOpenAI) {
+          result = fromOpenAI(model, result, stream, credentials);
+        }
       }
     }
   }
 
+  // Normalize thinking to the target provider-native format (config-driven, capability-aware).
+  // Kiro's GenerateAssistantResponse request does not accept the generic top-level
+  // `thinking` field; its translators map thinking intent to KAS-compatible
+  // systemPrompt/additionalModelRequestFields instead.
+  const kiroThinkingMappedByTranslator =
+    targetFormat === FORMATS.KIRO &&
+    (sourceFormat === FORMATS.OPENAI || sourceFormat === FORMATS.CLAUDE);
+  if (!kiroThinkingMappedByTranslator) {
+    applyThinking(targetFormat, model, result, provider, thinkingIntent);
+  }
+
   // Always normalize to clean OpenAI format when target is OpenAI
   // This handles hybrid requests (e.g., OpenAI messages + Claude tools)
   if (targetFormat === FORMATS.OPENAI) {
-    result = filterToOpenAIFormat(result);
+    result = filterToOpenAIFormat(result, {
+      preserveCacheControl: !!PROVIDERS[provider]?.quirks?.preserveCacheControl,
+    });
   }
 
   // Final step: prepare request for Claude format endpoints
   if (targetFormat === FORMATS.CLAUDE) {
     const apiKey = credentials?.accessToken || credentials?.apiKey || null;
-    result = prepareClaudeRequest(result, provider, apiKey, connectionId);
+    result = prepareClaudeRequest(result, provider, apiKey, connectionId, credentials?.rawHeaders, clientSessionId);
   }
 
   // Claude cloaking: rename client tools with _cc suffix (anti-ban)
-  // Only for claude provider (not anthropic-compatible-*) with OAuth token
-  if (provider === "claude") {
+  // quirk: only providers flagged cloakToolsOnOAuth, and only with an OAuth token
+  if (PROVIDERS[provider]?.quirks?.cloakToolsOnOAuth) {
     const apiKey = credentials?.accessToken || credentials?.apiKey || null;
     if (apiKey?.includes("sk-ant-oat")) {
       const { body: cloakedBody, toolNameMap } = cloakClaudeTools(result);
@@ -160,6 +164,16 @@ export function translateResponse(targetFormat, sourceFormat, chunk, state) {
   let results = [chunk];
   let openaiResults = null; // Store OpenAI intermediate results
 
+  // Direct route: if a response translator is registered for this exact
+  // target:source pair, use it instead of pivoting through OpenAI. Mirrors the
+  // request-side direct route (e.g. kiro:claude — KiroExecutor already emits
+  // OpenAI-shaped chunks, so this converts them straight to Claude SSE).
+  const directFn = responseRegistry.get(`${targetFormat}:${sourceFormat}`);
+  if (directFn) {
+    const converted = directFn(chunk, state);
+    return converted ? (Array.isArray(converted) ? converted : [converted]) : [];
+  }
+
   // Step 1: target -> openai (if target is not openai)
   if (targetFormat !== FORMATS.OPENAI) {
     const toOpenAI = responseRegistry.get(`${targetFormat}:${FORMATS.OPENAI}`);
@@ -248,7 +262,31 @@ export function initState(sourceFormat) {
   return base;
 }
 
-// Initialize all translators (kept for backward compatibility)
+// Kept for backward compatibility; translators are already registered at import time.
 export function initTranslators() {
   ensureInitialized();
 }
+
+// Static side-effect imports: each module calls register() at load (works in ESM + bundler).
+import "./request/claude-to-openai.js";
+import "./request/openai-to-claude.js";
+import "./request/gemini-to-openai.js";
+import "./request/openai-to-gemini.js";
+import "./request/openai-to-vertex.js";
+import "./request/antigravity-to-openai.js";
+import "./request/openai-responses.js";
+import "./request/openai-to-kiro.js";
+import "./request/openai-to-cursor.js";
+import "./request/openai-to-ollama.js";
+import "./request/openai-to-commandcode.js";
+import "./request/claude-to-kiro.js";
+import "./response/claude-to-openai.js";
+import "./response/openai-to-claude.js";
+import "./response/gemini-to-openai.js";
+import "./response/openai-to-antigravity.js";
+import "./response/openai-responses.js";
+import "./response/kiro-to-openai.js";
+import "./response/cursor-to-openai.js";
+import "./response/ollama-to-openai.js";
+import "./response/commandcode-to-openai.js";
+import "./response/kiro-to-claude.js";

package/dist/open-sse/translator/request/claude-to-kiro.js

@@ -24,14 +24,16 @@
  */
 import { register } from "../index.js";
 import { FORMATS } from "../formats.js";
-import { v4 as uuidv4 } from "uuid";
+import { applyKiroSessionReplay } from "../../utils/kiroSessionReplay.js";
+import { resolveContinuationId, resolveSessionIdentity } from "../../utils/sessionManager.js";
 import {
   resolveKiroModel,
+  resolveKiroThinkingBudget,
   buildThinkingSystemPrefix,
   KIRO_AGENTIC_SYSTEM_PROMPT,
   resolveDefaultProfileArn,
+  buildKiroAdditionalModelRequestFieldsForModel,
 } from "../../config/kiroConstants.js";
-import { resolveKiroThinkingBudget } from "../../services/thinkingBudget.js";
 import { DEFAULT_IMAGE_MIME } from "../schema/index.js";
 import { ROLE, CLAUDE_BLOCK } from "../schema/index.js";
 
@@ -363,6 +365,18 @@ function reconcileOrphanedToolResults(history, currentMessage) {
   }
 }
 
+function extractClaudeSystemText(system) {
+  if (!system) return "";
+  if (typeof system === "string") return system;
+  if (Array.isArray(system)) {
+    return system.map((s) => {
+      if (typeof s === "string") return s;
+      return s?.text || "";
+    }).filter(Boolean).join("\n");
+  }
+  return "";
+}
+
 /**
  * Build a Kiro payload directly from a Claude Messages API request body.
  */
@@ -402,62 +416,75 @@ export function claudeToKiroRequest(model, body, stream, credentials) {
     ? (credentials?.providerSpecificData?.profileArn || "")
     : (credentials?.providerSpecificData?.profileArn || resolveDefaultProfileArn(authMethod));
 
-  let finalContent = currentMessage?.userInputMessage?.content || "";
-
-  // System prompt: pass via native systemInstruction field (Kiro/Q API supports it)
-  // and also prepend as <instructions> in user content as fallback for upstreams
-  // that don't support the native field.
-  let systemInstruction = undefined;
-  if (body.system) {
-    let systemText = "";
-    if (typeof body.system === "string") {
-      systemText = body.system;
-    } else if (Array.isArray(body.system)) {
-      systemText = body.system.map((s) => s.text || "").join("\n");
-    }
-    if (systemText) {
-      systemInstruction = systemText;
-      finalContent = `<instructions>\n${systemText}\n</instructions>\n\n${finalContent}`;
-    }
-  }
-
-  // Prefix order: thinking_mode tag, timestamp marker, then agentic prompt.
+  // Kiro CLI/KAS sends system prompt as top-level `systemPrompt`. Keep a
+  // content fallback too because the CodeWhisperer surface does not always
+  // enforce top-level systemPrompt for direct calls.
   const timestamp = new Date().toISOString();
-  const prefixParts = [];
-  if (thinkingBudget !== null) prefixParts.push(buildThinkingSystemPrefix(thinkingBudget));
-  prefixParts.push(`[Context: Current time is ${timestamp}]`);
-  if (agentic) prefixParts.push(KIRO_AGENTIC_SYSTEM_PROMPT);
-  finalContent = `${prefixParts.join("\n\n")}\n\n${finalContent}`;
-
+  const systemPromptParts = [];
+  if (thinkingBudget !== null) systemPromptParts.push(buildThinkingSystemPrefix(thinkingBudget));
+  if (agentic) systemPromptParts.push(KIRO_AGENTIC_SYSTEM_PROMPT);
+  const systemInstruction = extractClaudeSystemText(body.system);
+  if (systemInstruction) systemPromptParts.push(systemInstruction);
+  const systemPrompt = systemPromptParts.filter(Boolean).join("\n\n");
+  const currentTimeContext = `[Context: Current time is ${timestamp}]`;
+  const contentPrefix = [systemPrompt, currentTimeContext].filter(Boolean).join("\n\n");
+
+  const sessionIdentity = resolveSessionIdentity({
+    headers: credentials?.rawHeaders,
+    body,
+    connectionId: credentials?.connectionId,
+    scope: "kiro",
+  });
+  const conversationId = sessionIdentity.sessionId;
+  const continuationId = resolveContinuationId({
+    sessionId: conversationId,
+    connectionId: credentials?.connectionId,
+    scope: "kiro",
+    ephemeral: sessionIdentity.ephemeral,
+  });
+  const replay = applyKiroSessionReplay({
+    conversationId,
+    connectionId: credentials?.connectionId,
+    modelId: upstreamModel,
+    systemPrompt,
+    contentPrefix,
+    currentContentPrefix: currentTimeContext,
+    history,
+    currentMessage,
+  });
+  const replayCurrent = replay.currentMessage?.userInputMessage || {};
   const userInputMessage = {
-    content: finalContent,
+    content: replayCurrent.content || "",
     modelId: upstreamModel,
     origin: "AI_EDITOR",
-    ...(currentMessage?.userInputMessage?.userInputMessageContext && {
-      userInputMessageContext:
-        currentMessage.userInputMessage.userInputMessageContext,
+    ...(replayCurrent.userInputMessageContext && {
+      userInputMessageContext: replayCurrent.userInputMessageContext,
     }),
-    ...(currentMessage?.userInputMessage?.images && {
-      images: currentMessage.userInputMessage.images,
+    ...(replayCurrent.images && {
+      images: replayCurrent.images,
     }),
   };
 
-  if (systemInstruction) {
-    userInputMessage.systemInstruction = systemInstruction;
-  }
-
   const payload = {
     conversationState: {
       chatTriggerType: "MANUAL",
-      conversationId: uuidv4(),
+      conversationId,
+      agentContinuationId: continuationId,
+      agentTaskType: "vibe",
       currentMessage: {
         userInputMessage,
       },
-      history,
+      history: replay.history,
     },
+    agentMode: "vibe",
   };
 
   if (profileArn) payload.profileArn = profileArn;
+  if (systemPrompt) payload.systemPrompt = systemPrompt;
+  const additionalModelRequestFields = buildKiroAdditionalModelRequestFieldsForModel(body, upstreamModel);
+  if (additionalModelRequestFields) {
+    payload.additionalModelRequestFields = additionalModelRequestFields;
+  }
 
   if (maxTokens || temperature !== undefined || topP !== undefined) {
     payload.inferenceConfig = {};

package/dist/open-sse/translator/request/openai-responses.js

@@ -201,6 +201,7 @@ export function openaiResponsesToOpenAIRequest(model, body, stream, credentials)
   delete result.prompt_cache_key;
   delete result.store;
   delete result.reasoning;
+  delete result.client_metadata;
 
   return result;
 }

package/dist/open-sse/translator/request/openai-to-commandcode.js

@@ -170,7 +170,3 @@ export function openaiToCommandCodeRequest(model, body, stream /* , credentials
 }
 
 register(FORMATS.OPENAI, FORMATS.COMMANDCODE, openaiToCommandCodeRequest, null);
-
-// Backwards-compatible alias
-export const openaiToCommandCode = openaiToCommandCodeRequest;
-