@fudrouter/fsrouter 0.6.72 → 0.6.74

package/open-sse/translator/request/openai-to-kiro.js

@@ -5,14 +5,16 @@
 import { register } from "../index.js";
 import { FORMATS } from "../formats.js";
 import { v4 as uuidv4 } from "uuid";
-import { resolveSessionId } from "../../utils/sessionManager.js";
+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 { parseDataUri } from "../concerns/image.js";
 import { DEFAULT_IMAGE_MIME } from "../schema/index.js";
 import { ROLE, OPENAI_BLOCK, CLAUDE_BLOCK } from "../schema/index.js";
@@ -546,47 +548,74 @@ export function openaiToKiroRequest(model, body, stream, credentials) {
     ? (credentials?.providerSpecificData?.profileArn || "")
     : (credentials?.providerSpecificData?.profileArn || resolveDefaultProfileArn(authMethod));
 
-  let finalContent = currentMessage?.userInputMessage?.content || "";
-
   const timestamp = new Date().toISOString();
 
-  // Build the system-prompt prefix that goes ABOVE the user message body.
-  // Order: thinking_mode tag first (so Kiro sees it before any user text),
-  // then context/timestamp marker, then optional agentic chunked-write prompt.
-  const prefixParts = [];
+  // Kiro CLI/KAS sends these as top-level systemPrompt. Keep a content fallback
+  // too because the CodeWhisperer surface does not always enforce top-level
+  // systemPrompt for direct calls.
+  const systemPromptParts = [];
   if (thinkingBudget !== null) {
-    prefixParts.push(buildThinkingSystemPrefix(thinkingBudget));
+    systemPromptParts.push(buildThinkingSystemPrefix(thinkingBudget));
   }
-  prefixParts.push(`[Context: Current time is ${timestamp}]`);
   if (agentic) {
-    prefixParts.push(KIRO_AGENTIC_SYSTEM_PROMPT);
+    systemPromptParts.push(KIRO_AGENTIC_SYSTEM_PROMPT);
   }
-  finalContent = `${prefixParts.join("\n\n")}\n\n${finalContent}`;
+  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 payload = {
     conversationState: {
       chatTriggerType: "MANUAL",
-      conversationId: resolveSessionId({ headers: credentials?.rawHeaders, body, connectionId: credentials?.connectionId, scope: "kiro" }),
+      conversationId,
+      agentContinuationId: continuationId,
+      agentTaskType: "vibe",
       currentMessage: {
         userInputMessage: {
-          content: finalContent,
+          content: replayCurrent.content || "",
           modelId: upstreamModel,
           origin: "AI_EDITOR",
-          ...(currentMessage?.userInputMessage?.images?.length > 0 && {
-            images: currentMessage.userInputMessage.images
+          ...(replayCurrent.images?.length > 0 && {
+            images: replayCurrent.images
           }),
-          ...(currentMessage?.userInputMessage?.userInputMessageContext && {
-            userInputMessageContext: currentMessage.userInputMessage.userInputMessageContext
+          ...(replayCurrent.userInputMessageContext && {
+            userInputMessageContext: replayCurrent.userInputMessageContext
           })
         }
       },
-      history: 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/open-sse/translator/response/commandcode-to-openai.js

@@ -182,7 +182,3 @@ export function commandCodeToOpenAIResponse(chunk, state) {
 }
 
 register(FORMATS.COMMANDCODE, FORMATS.OPENAI, null, commandCodeToOpenAIResponse);
-
-// Backwards-compatible alias (executor expects this name)
-export const convertCommandCodeToOpenAI = commandCodeToOpenAIResponse;
-

package/open-sse/utils/bypassHandler.js

@@ -247,9 +247,24 @@ function mergeChunksToResponse(chunks, sourceFormat) {
 
       if (messageStart?.message) {
         finalChunk = messageStart.message;
-        // Merge usage if available
-        if (messageDelta?.usage) {
-          finalChunk.usage = messageDelta.usage;
+        // message_start.usage has input + cache; message_delta.usage has the
+        // final output_tokens. Merge so cache survives (delta omits it).
+        const startUsage = messageStart.message.usage;
+        const deltaUsage = messageDelta?.usage;
+        if (startUsage || deltaUsage) {
+          finalChunk.usage = {
+            ...(startUsage || {}),
+            ...(deltaUsage || {}),
+            ...(startUsage?.cache_read_input_tokens !== undefined
+              ? { cache_read_input_tokens: startUsage.cache_read_input_tokens }
+              : {}),
+            ...(startUsage?.cache_creation_input_tokens !== undefined
+              ? { cache_creation_input_tokens: startUsage.cache_creation_input_tokens }
+              : {}),
+            ...(startUsage?.input_tokens !== undefined
+              ? { input_tokens: startUsage.input_tokens }
+              : {})
+          };
         }
       }
     }

package/open-sse/utils/claudeCloaking.js

@@ -13,11 +13,18 @@ function generateBillingHeader(payload) {
   return `x-anthropic-billing-header: cc_version=${CLAUDE_VERSION}.${buildHash}; cc_entrypoint=${CC_ENTRYPOINT}; cch=${cch};`;
 }
 
+// Derive a deterministic UUID-v4-shaped string from a seed (stable per account)
+function deriveUuid(seed) {
+  const h = createHash("sha256").update(seed).digest("hex");
+  return `${h.slice(0, 8)}-${h.slice(8, 12)}-4${h.slice(13, 16)}-${((parseInt(h[16], 16) & 0x3) | 0x8).toString(16)}${h.slice(17, 20)}-${h.slice(20, 32)}`;
+}
+
 // Generate fake user ID in Claude Code 2.1.92+ JSON format:
 // {"device_id":"<64hex>","account_uuid":"<uuid>","session_id":"<uuid>"}
-function generateFakeUserID(sessionId) {
-  const deviceId = randomBytes(32).toString("hex");
-  const accountUuid = randomUUID();
+// device_id/account_uuid derive from apiKey (stable per account), session_id per-conversation
+function generateFakeUserID(sessionId, apiKey) {
+  const deviceId = apiKey ? createHash("sha256").update(`device:${apiKey}`).digest("hex") : randomBytes(32).toString("hex");
+  const accountUuid = apiKey ? deriveUuid(`account:${apiKey}`) : randomUUID();
   const sessionUuid = sessionId || randomUUID();
   return `{"device_id":"${deviceId}","account_uuid":"${accountUuid}","session_id":"${sessionUuid}"}`;
 }
@@ -40,8 +47,11 @@ export function cloakClaudeTools(body) {
   const clientToolNames = new Set();
   const clientDeclarations = [];
 
-  // All client tools get renamed with suffix
+  // All client tools get renamed with suffix.
+  // Built-in server tools (web_search_20250305, etc.) carry a `type` and require
+  // an exact reserved `name` — never suffix those or Claude rejects the request.
   for (const tool of tools) {
+    if (tool.type) { clientDeclarations.push(tool); continue; }
     const suffixed = suffix(tool.name);
     toolNameMap.set(suffixed, tool.name);
     clientToolNames.add(tool.name);
@@ -148,7 +158,7 @@ export function applyCloaking(body, apiKey, sessionId) {
   // Inject fake user ID into metadata (session_id must match X-Claude-Code-Session-Id)
   const existingUserId = result.metadata?.user_id;
   if (!existingUserId) {
-    result.metadata = { ...result.metadata, user_id: generateFakeUserID(sessionId) };
+    result.metadata = { ...result.metadata, user_id: generateFakeUserID(sessionId, apiKey) };
   }
 
   return result;

package/open-sse/utils/error.js

@@ -145,20 +145,3 @@ export function formatProviderError(error, provider, model, statusCode) {
   const causeStr = causeCode || causeMsg ? ` (cause: ${[causeCode, causeMsg].filter(Boolean).join(": ")})` : "";
   return `[${code}]: ${message}${causeStr}`;
 }
-
-
-/**
- * Safely escape HTML characters from error strings to prevent XSS in clients that poorly render error JSON.
- * Note: Only intended for string values. Non-string inputs will be returned as-is or cast to strings based on usage.
- * @param {string} message The raw error message
- * @returns {string} The HTML-escaped error message
- */
-export function sanitizeErrorMessage(message) {
-  if (typeof message !== 'string') return String(message);
-  return message
-    .replace(/&/g, '&')
-    .replace(/</g, '&lt;')
-    .replace(/>/g, '&gt;')
-    .replace(/"/g, '&quot;')
-    .replace(/'/g, '&#39;');
-}

package/open-sse/utils/kiroSessionReplay.js

@@ -0,0 +1,125 @@
+import { MEMORY_CONFIG } from "../config/runtimeConfig.js";
+
+const sessionStartStore = new Map();
+const MAX_SESSION_STARTS = 5000;
+
+function clone(value) {
+  return value == null ? value : JSON.parse(JSON.stringify(value));
+}
+
+function sessionKey(connectionId, conversationId) {
+  return `${connectionId || ""}:${conversationId || ""}`;
+}
+
+function ensureUserMessageModelId(message, modelId) {
+  if (message?.userInputMessage && !message.userInputMessage.modelId && modelId) {
+    message.userInputMessage.modelId = modelId;
+  }
+  return message;
+}
+
+function ensureHistoryModelIds(history, modelId) {
+  for (const item of history || []) {
+    ensureUserMessageModelId(item, modelId);
+  }
+  return history;
+}
+
+function prefixUserMessage(message, contentPrefix, modelId) {
+  const out = clone(message) || { userInputMessage: { content: "" } };
+  if (!out.userInputMessage) out.userInputMessage = { content: "" };
+  ensureUserMessageModelId(out, modelId);
+  if (contentPrefix) {
+    const content = out.userInputMessage.content || "";
+    out.userInputMessage.content = content
+      ? `${contentPrefix}\n\n${content}`
+      : contentPrefix;
+  }
+  return out;
+}
+
+function findFirstUserIndex(history) {
+  return history.findIndex((item) => item?.userInputMessage);
+}
+
+function rememberSessionStart(key, entry) {
+  if (sessionStartStore.size >= MAX_SESSION_STARTS) {
+    sessionStartStore.delete(sessionStartStore.keys().next().value);
+  }
+  sessionStartStore.set(key, { ...entry, lastUsed: Date.now() });
+}
+
+/**
+ * Preserve Kiro cacheability by freezing the first user message (`msg0`) for a
+ * session, replaying that exact message as the first history user on later
+ * turns, and injecting volatile current-time context only into the current turn.
+ */
+export function applyKiroSessionReplay({
+  conversationId,
+  connectionId,
+  modelId,
+  systemPrompt = "",
+  contentPrefix = "",
+  currentContentPrefix = "",
+  history = [],
+  currentMessage,
+} = {}) {
+  const key = sessionKey(connectionId, conversationId);
+  const existing = conversationId ? sessionStartStore.get(key) : null;
+  const baseHistory = clone(history) || [];
+  const baseCurrent = clone(currentMessage) || { userInputMessage: { content: "" } };
+
+  if (existing && existing.modelId === modelId && existing.systemPrompt === systemPrompt) {
+    existing.lastUsed = Date.now();
+    const firstUserIndex = findFirstUserIndex(baseHistory);
+    const sessionStart = ensureUserMessageModelId(clone(existing.sessionStart), modelId);
+    if (firstUserIndex >= 0) {
+      baseHistory[firstUserIndex] = sessionStart;
+    } else {
+      baseHistory.unshift(sessionStart);
+    }
+    return {
+      history: ensureHistoryModelIds(baseHistory, modelId),
+      currentMessage: prefixUserMessage(baseCurrent, currentContentPrefix, modelId),
+      replayed: true,
+    };
+  }
+
+  const firstUserIndex = findFirstUserIndex(baseHistory);
+  let sessionStart;
+  let nextCurrent = ensureUserMessageModelId(baseCurrent, modelId);
+  if (firstUserIndex >= 0) {
+    sessionStart = prefixUserMessage(baseHistory[firstUserIndex], contentPrefix, modelId);
+    baseHistory[firstUserIndex] = clone(sessionStart);
+    nextCurrent = prefixUserMessage(baseCurrent, currentContentPrefix, modelId);
+  } else {
+    sessionStart = prefixUserMessage(baseCurrent, contentPrefix, modelId);
+    nextCurrent = clone(sessionStart);
+  }
+
+  if (conversationId) {
+    rememberSessionStart(key, {
+      sessionStart: clone(sessionStart),
+      modelId,
+      systemPrompt,
+    });
+  }
+
+  return {
+    history: ensureHistoryModelIds(baseHistory, modelId),
+    currentMessage: nextCurrent,
+    replayed: false,
+  };
+}
+
+export function clearKiroSessionReplayStore() {
+  sessionStartStore.clear();
+}
+
+const cleanup = setInterval(() => {
+  const now = Date.now();
+  for (const [key, entry] of sessionStartStore) {
+    if (now - entry.lastUsed > MEMORY_CONFIG.sessionTtlMs) sessionStartStore.delete(key);
+  }
+}, MEMORY_CONFIG.sessionCleanupIntervalMs);
+if (cleanup.unref) cleanup.unref();

package/open-sse/utils/logger.js

@@ -1,4 +1,4 @@
-import { getAppLogFormat, getAppLogLevel } from "../../dist/lib/logEnv";
+import { getAppLogFormat, getAppLogLevel } from "../../src/lib/logEnv";
 const LEVELS = { debug: 0, info: 1, warn: 2, error: 3 };
 function isLogLevel(value) {
   return Object.prototype.hasOwnProperty.call(LEVELS, value);

package/open-sse/utils/proxyFetch.js

@@ -106,7 +106,6 @@ const MITM_BYPASS_HOSTS = [
   "q.us-east-1.amazonaws.com",
   "codewhisperer.us-east-1.amazonaws.com",
   "api2.cursor.sh",
-  "leonardo.ai",
 ];
 const GOOGLE_DNS_SERVERS = ["8.8.8.8", "8.8.4.4"];
 const HTTPS_PORT = 443;

package/open-sse/utils/reasoningContentInjector.js

@@ -1,15 +1,12 @@
 // Some thinking-mode providers (DeepSeek, Kimi, MiniMax, ...) require reasoning_content
 // to be echoed back on assistant messages. Clients in OpenAI format don't send it,
 // so we inject a non-empty placeholder to satisfy upstream validation.
+import { PROVIDERS } from "../config/providers.js";
 
 const PLACEHOLDER = " ";
 
-// Provider-level rules: keyed by executor.provider
-const PROVIDER_RULES = {
-  deepseek: { scope: "all" },
-  minimax: { scope: "all" },
-  "minimax-cn": { scope: "all" }
-};
+// Provider-level rules derive from registry transport.reasoningInject (single source)
+const providerRuleFor = (provider) => PROVIDERS[provider]?.reasoningInject;
 
 // Model-level rules: matched by predicate against model id
 const MODEL_RULES = [
@@ -71,7 +68,7 @@ function applyDeepSeekV4ProAlias({ provider, model, body }) {
 }
 
 export function injectReasoningContent({ provider, model, body }) {
-  const providerRule = PROVIDER_RULES[provider];
+  const providerRule = providerRuleFor(provider);
   const modelRule = MODEL_RULES.find(r => r.match(model));
   const rule = providerRule || modelRule;
   const nextBody = applyDeepSeekV4ProAlias({ provider, model, body });

package/open-sse/utils/responsesStreamHelpers.js

@@ -5,6 +5,7 @@ import { formatSSE } from "./streamHelpers.js";
 // Responses API events that signal the stream has reached a terminal state
 const OPENAI_RESPONSES_TERMINAL_EVENTS = new Set([
   "response.completed",
+  "response.done",
   "response.failed",
   "error"
 ]);

package/open-sse/utils/sessionManager.js

@@ -13,6 +13,7 @@ import { MEMORY_CONFIG } from "../config/runtimeConfig.js";
 
 // Runtime storage: Key = connectionId, Value = { sessionId, lastUsed }
 const runtimeSessionStore = new Map();
+const continuationStore = new Map();
 
 // Periodically evict entries that haven't been used within TTL
 const cleanupInterval = setInterval(() => {
@@ -80,6 +81,7 @@ export function generateBinaryStyleId() {
 export function clearSessionStore() {
     runtimeSessionStore.clear();
     assistantSessionStore.clear();
+    continuationStore.clear();
 }
 
 // Conversation-stable session store: Key = hash(scope+assistant text), Value = { sessionId, lastUsed }
@@ -87,9 +89,10 @@ const assistantSessionStore = new Map();
 const ASSISTANT_MIN_LEN = 50;
 const ASSISTANT_CAP_LEN = 50;
 const MAX_ASSISTANT_SESSIONS = 5000;
+const MAX_CONTINUATION_SESSIONS = 5000;
 
 // Client headers/body fields that carry an upstream session id (priority order)
-const SESSION_HEADER_KEYS = ["x-session-id", "session-id", "session_id", "x-amp-thread-id", "x-client-request-id"];
+const SESSION_HEADER_KEYS = ["x-session-id", "session-id", "session_id", "x-amp-thread-id"];
 const CLAUDE_CODE_SESSION_RE = /_session_([a-f0-9-]+)$/;
 
 function sha16(text) {
@@ -131,7 +134,7 @@ function extractAntigravitySession(body) {
     return m ? normalizeSessionId(m[1]) : null;
 }
 
-function extractClientSessionId(headers, body) {
+function extractClientSessionId(headers, body, scope = "") {
     const claude = extractClaudeCodeSession(body?.metadata?.user_id);
     if (claude) return `claude:${claude}`;
     const antigravity = extractAntigravitySession(body);
@@ -140,18 +143,25 @@ function extractClientSessionId(headers, body) {
         const v = headerValue(headers, key);
         if (v) return v;
     }
+    const requestId = scope === "kiro" ? null : headerValue(headers, "x-client-request-id");
+    if (requestId) return requestId;
     const fromBody =
         normalizeSessionId(body?.prompt_cache_key) ||
         normalizeSessionId(body?.session_id) ||
         normalizeSessionId(body?.conversation_id) ||
-        normalizeSessionId(body?.metadata?.user_id);
+        (scope === "kiro" ? null : normalizeSessionId(body?.metadata?.user_id));
     return fromBody || null;
 }
 
+function requestMessages(body) {
+    if (Array.isArray(body?.messages)) return body.messages;
+    if (Array.isArray(body?.input)) return body.input;
+    return [];
+}
+
 // Accumulate assistant text from OpenAI/Responses-style input/messages (cap-limited)
 function accumulateAssistantText(body) {
-    const items = Array.isArray(body?.input) ? body.input
-        : Array.isArray(body?.messages) ? body.messages : null;
+    const items = requestMessages(body);
     if (!items) return "";
     let text = "";
     for (const item of items) {
@@ -193,16 +203,39 @@ function assistantTextSessionId(scope, body) {
  * @param {string} [opts.connectionId] - Connection identifier (fallback scope)
  * @param {string} [opts.workspaceId] - Provider workspace id (account-wide fallback)
  * @param {string} [opts.scope] - Provider scope to isolate cache keys across providers
- * @returns {string} A stable session id
+ * @returns {{sessionId: string, ephemeral: boolean}} A session id plus whether it is one-shot
  */
-export function resolveSessionId({ headers, body, connectionId, workspaceId, scope = "" } = {}) {
-    const client = extractClientSessionId(headers, body);
-    if (client) return client;
-    const fromAssistant = assistantTextSessionId(`${scope}:${connectionId || ""}`, body);
-    if (fromAssistant) return fromAssistant;
+export function resolveSessionIdentity({ headers, body, connectionId, workspaceId, scope = "" } = {}) {
+    const client = extractClientSessionId(headers, body, scope);
+    if (client) return { sessionId: client, ephemeral: false };
+    const fromAssistant = scope === "kiro" ? null : assistantTextSessionId(`${scope}:${connectionId || ""}`, body);
+    if (fromAssistant) return { sessionId: fromAssistant, ephemeral: false };
     const ws = normalizeSessionId(workspaceId);
-    if (ws) return ws;
-    return deriveSessionId(connectionId);
+    if (ws) return { sessionId: ws, ephemeral: false };
+    if (scope === "kiro") return { sessionId: generateBinaryStyleId(), ephemeral: true };
+    return { sessionId: deriveSessionId(connectionId), ephemeral: false };
+}
+
+export function resolveSessionId(opts = {}) {
+    return resolveSessionIdentity(opts).sessionId;
+}
+
+export function resolveContinuationId({ sessionId, connectionId, scope = "", ephemeral = false } = {}) {
+    if (ephemeral) return crypto.randomUUID();
+    const key = `${scope}:${connectionId || ""}:${sessionId || ""}`;
+    const existing = continuationStore.get(key);
+    if (existing) {
+        existing.lastUsed = Date.now();
+        continuationStore.delete(key);
+        continuationStore.set(key, existing);
+        return existing.continuationId;
+    }
+    const continuationId = crypto.randomUUID();
+    if (continuationStore.size >= MAX_CONTINUATION_SESSIONS) {
+        continuationStore.delete(continuationStore.keys().next().value);
+    }
+    continuationStore.set(key, { continuationId, lastUsed: Date.now() });
+    return continuationId;
 }
 
 // Capture session id from request body + credentials (envelope still intact here)
@@ -227,14 +260,8 @@ const assistantCleanup = setInterval(() => {
     for (const [key, entry] of assistantSessionStore) {
         if (now - entry.lastUsed > MEMORY_CONFIG.sessionTtlMs) assistantSessionStore.delete(key);
     }
+    for (const [key, entry] of continuationStore) {
+        if (now - entry.lastUsed > MEMORY_CONFIG.sessionTtlMs) continuationStore.delete(key);
+    }
 }, MEMORY_CONFIG.sessionCleanupIntervalMs);
 if (assistantCleanup.unref) assistantCleanup.unref();
-
-/**
- * Stub: get session info by session ID.
- * Returns session object if found, null otherwise.
- * TODO: Wire to actual session store when available.
- */
-export function getSessionInfo(sessionId) {
-  return null;
-}