kentutai 1.5.0 → 1.7.0

package/open-sse/services/kiroModels.js

@@ -0,0 +1,332 @@
+/**
+ * Kiro model catalog fetcher.
+ *
+ * Calls AWS CodeWhisperer's `ListAvailableModels` endpoint to get the live
+ * catalog for an authenticated Kiro account, then expands each upstream model
+ * into 9router-shaped variants:
+ *
+ *   {upstream}                          - base model
+ *   {upstream}-thinking                 - same model, thinking on at request time
+ *   {upstream}-agentic                  - same model, chunked-write prompt prepended
+ *   {upstream}-thinking-agentic         - both
+ *
+ * The `-thinking` and `-agentic` suffixes do not exist on the Kiro upstream
+ * API. They are 9router fictions and the `openai-to-kiro` translator strips
+ * them before the request leaves this process.
+ *
+ * The runtime UA is built to match what Kiro IDE itself sends, because the
+ * upstream rejects requests with malformed `User-Agent` headers (returns 400
+ * "format of value 'os/win/10 lang/js ...' is invalid").
+ */
+
+import { v4 as uuidv4 } from "uuid";
+import { createHash } from "crypto";
+import { refreshKiroToken } from "./tokenRefresh.js";
+
+const KIRO_RUNTIME_SDK_VERSION = "1.0.0";
+const KIRO_AGENT_OS = "windows";
+const KIRO_AGENT_OS_VERSION = "10.0.26200";
+const KIRO_NODE_VERSION = "22.21.1";
+const KIRO_VERSION = "0.10.32";
+
+const DEFAULT_REGION = "us-east-1";
+const FETCH_TIMEOUT_MS = 30_000;
+const CACHE_TTL_MS = 5 * 60 * 1000; // 5 minutes per credential
+
+/** @type {Map<string, { expiresAt: number, models: any[] }>} */
+const catalogCache = new Map();
+
+/**
+ * Strip the `-agentic` and/or `-thinking` suffixes from a synthetic id, if
+ * any. Used only for display naming when a Kiro upstream id happens to look
+ * synthetic (defensive).
+ */
+function stripSyntheticSuffixes(id) {
+  let out = id;
+  if (out.endsWith("-agentic")) out = out.slice(0, -"-agentic".length);
+  if (out.endsWith("-thinking")) out = out.slice(0, -"-thinking".length);
+  return out;
+}
+
+/**
+ * Extract region from a profileArn like
+ *   arn:aws:codewhisperer:us-east-1:123456789012:profile/ABC
+ */
+function regionFromProfileArn(profileArn) {
+  if (!profileArn || typeof profileArn !== "string") return DEFAULT_REGION;
+  const parts = profileArn.split(":");
+  if (parts.length >= 4 && parts[3]) return parts[3];
+  return DEFAULT_REGION;
+}
+
+/**
+ * Build the per-account fingerprint headers Kiro upstream validates.
+ * Keyed off whatever stable identifier we have for this credential, so the
+ * same account always presents the same machineId.
+ */
+function buildKiroFingerprintHeaders(credentials) {
+  const seed =
+    credentials?.providerSpecificData?.clientId
+    || credentials?.refreshToken
+    || credentials?.providerSpecificData?.profileArn
+    || credentials?.accessToken
+    || "kiro-anonymous";
+  const machineId = createHash("sha256").update(String(seed)).digest("hex");
+
+  const userAgent =
+    `aws-sdk-js/${KIRO_RUNTIME_SDK_VERSION} ua/2.1 ` +
+    `os/${KIRO_AGENT_OS}#${KIRO_AGENT_OS_VERSION} ` +
+    `lang/js md/nodejs#${KIRO_NODE_VERSION} ` +
+    `api/codewhispererruntime#${KIRO_RUNTIME_SDK_VERSION} m/N,E ` +
+    `KiroIDE-${KIRO_VERSION}-${machineId}`;
+  const amzUserAgent = `aws-sdk-js/${KIRO_RUNTIME_SDK_VERSION} KiroIDE-${KIRO_VERSION}-${machineId}`;
+
+  return {
+    "User-Agent": userAgent,
+    "x-amz-user-agent": amzUserAgent,
+    "x-amzn-kiro-agent-mode": "vibe",
+    "x-amzn-codewhisperer-optout": "true",
+    "amz-sdk-request": "attempt=1; max=1",
+    "amz-sdk-invocation-id": uuidv4(),
+    "Accept": "application/json"
+  };
+}
+
+/**
+ * Build the synthetic 9router variant set for a single upstream Kiro model.
+ *
+ * Returns objects shaped for `PROVIDER_MODELS` (`{ id, name }`) so they can
+ * be slotted directly into the existing model registry.
+ *
+ * The `auto` model is special: Kiro picks the underlying model server-side,
+ * so the chunked-write `-agentic` prompt is not meaningful (the prompt
+ * targets coding-agent file writes). Match CLIProxyAPIPlus and skip
+ * `-agentic` / `-thinking-agentic` for `auto`.
+ */
+function buildVariants(upstream, displayName) {
+  const safeUpstream = stripSyntheticSuffixes(upstream);
+  const display = displayName || `Kiro ${safeUpstream}`;
+  const isAuto = safeUpstream === "auto";
+
+  const variants = [
+    {
+      id: safeUpstream,
+      name: display,
+      capabilities: { thinking: false, agentic: false }
+    },
+    {
+      id: `${safeUpstream}-thinking`,
+      name: `${display} (Thinking)`,
+      capabilities: { thinking: true, agentic: false }
+    }
+  ];
+
+  if (!isAuto) {
+    variants.push({
+      id: `${safeUpstream}-agentic`,
+      name: `${display} (Agentic)`,
+      capabilities: { thinking: false, agentic: true }
+    });
+    variants.push({
+      id: `${safeUpstream}-thinking-agentic`,
+      name: `${display} (Thinking + Agentic)`,
+      capabilities: { thinking: true, agentic: true }
+    });
+  }
+
+  return variants;
+}
+
+/**
+ * Format the human-friendly display name for a Kiro model, including the
+ * rate multiplier when it is something other than 1.0x.
+ */
+function formatDisplayName(modelName, modelId, rateMultiplier) {
+  const base = (modelName || modelId || "Kiro").trim();
+  const rate = Number(rateMultiplier);
+  if (!Number.isFinite(rate) || Math.abs(rate - 1.0) < 1e-9 || rate <= 0) {
+    return `Kiro ${base}`;
+  }
+  // Locale-independent decimal formatting.
+  const rateStr = rate.toFixed(1).replace(",", ".");
+  return `Kiro ${base} (${rateStr}x credit)`;
+}
+
+/**
+ * Fetch the raw model catalog from Kiro. Returns the array under `.models`
+ * from the API response, or throws on network/HTTP error.
+ */
+async function fetchKiroCatalogRaw(credentials, signal) {
+  const profileArn = credentials?.providerSpecificData?.profileArn || "";
+  const region = regionFromProfileArn(profileArn);
+  const params = new URLSearchParams();
+  params.set("origin", "AI_EDITOR");
+  if (profileArn) params.set("profileArn", profileArn);
+  const url = `https://q.${region}.amazonaws.com/ListAvailableModels?${params.toString()}`;
+
+  const headers = {
+    ...buildKiroFingerprintHeaders(credentials),
+    "Authorization": `Bearer ${credentials?.accessToken || ""}`
+  };
+
+  const controller = new AbortController();
+  const timer = setTimeout(() => controller.abort("timeout"), FETCH_TIMEOUT_MS);
+  // Forward outer cancellation if any.
+  if (signal && typeof signal.addEventListener === "function") {
+    signal.addEventListener("abort", () => controller.abort(signal.reason));
+  }
+
+  let response;
+  try {
+    response = await fetch(url, {
+      method: "GET",
+      headers,
+      signal: controller.signal
+    });
+  } finally {
+    clearTimeout(timer);
+  }
+
+  if (!response.ok) {
+    const text = await response.text().catch(() => "");
+    const err = new Error(`Kiro ListAvailableModels ${response.status}: ${text || response.statusText}`);
+    err.status = response.status;
+    err.body = text;
+    throw err;
+  }
+
+  const data = await response.json();
+  const models = Array.isArray(data?.models) ? data.models : [];
+  return models;
+}
+
+/**
+ * Build a stable cache key for a Kiro credential. Uses the most stable id we
+ * have available so different login sessions for the same account share a
+ * cache entry.
+ */
+function cacheKey(credentials) {
+  const psd = credentials?.providerSpecificData || {};
+  const seed =
+    psd.profileArn
+    || psd.clientId
+    || credentials?.refreshToken
+    || credentials?.accessToken
+    || "anonymous";
+  return createHash("sha256").update(`kiro:${seed}`).digest("hex");
+}
+
+/**
+ * Resolve the live Kiro model catalog for a credential and expand each entry
+ * into 9router variants (`-thinking`, `-agentic`, `-thinking-agentic`).
+ *
+ * On any error (network, 4xx, 5xx), returns `null` so callers can fall back
+ * to the static catalog without taking down the dashboard or `/v1/models`.
+ *
+ * @param {object} credentials Connection record (accessToken, refreshToken,
+ *   providerSpecificData {profileArn, authMethod, clientId, clientSecret, region})
+ * @param {object} [options]
+ * @param {boolean} [options.forceRefresh] Bypass the per-credential cache.
+ * @param {object}  [options.log] Logger.
+ * @param {function} [options.onCredentialsRefreshed] Persist refreshed token
+ *   back to your credential store. Called with `{ accessToken, refreshToken,
+ *   expiresIn }` whenever a 401 triggers a token refresh.
+ * @returns {Promise<{ models: object[], rawModels: object[] } | null>}
+ */
+export async function resolveKiroModels(credentials, options = {}) {
+  if (!credentials || !credentials.accessToken) {
+    options.log?.debug?.("KIRO_MODELS", "No accessToken; skipping live fetch");
+    return null;
+  }
+
+  const key = cacheKey(credentials);
+  const now = Date.now();
+  if (!options.forceRefresh) {
+    const cached = catalogCache.get(key);
+    if (cached && cached.expiresAt > now) {
+      return { models: cached.models, rawModels: cached.rawModels };
+    }
+  }
+
+  let raw;
+  try {
+    raw = await fetchKiroCatalogRaw(credentials, options.signal);
+  } catch (err) {
+    if (err && err.status === 401 && credentials.refreshToken) {
+      options.log?.info?.("KIRO_MODELS", "Got 401 from Kiro; refreshing token");
+      const refreshed = await refreshKiroToken(
+        credentials.refreshToken,
+        credentials.providerSpecificData,
+        options.log
+      );
+      if (refreshed?.accessToken) {
+        const next = { ...credentials, ...refreshed };
+        if (typeof options.onCredentialsRefreshed === "function") {
+          try { await options.onCredentialsRefreshed(refreshed); } catch (e) {
+            options.log?.warn?.("KIRO_MODELS", `onCredentialsRefreshed failed: ${e?.message || e}`);
+          }
+        }
+        try {
+          raw = await fetchKiroCatalogRaw(next, options.signal);
+          // Update the in-memory credential reference too so retry logic uses
+          // the fresh token consistently.
+          credentials.accessToken = next.accessToken;
+          if (next.refreshToken) credentials.refreshToken = next.refreshToken;
+        } catch (err2) {
+          options.log?.warn?.("KIRO_MODELS", `Retry after refresh failed: ${err2?.message || err2}`);
+          return null;
+        }
+      } else {
+        options.log?.warn?.("KIRO_MODELS", "Token refresh did not return accessToken");
+        return null;
+      }
+    } else {
+      options.log?.warn?.("KIRO_MODELS", `ListAvailableModels failed: ${err?.message || err}`);
+      return null;
+    }
+  }
+
+  const expanded = [];
+  for (const m of raw) {
+    if (!m || typeof m !== "object") continue;
+    const upstreamId = m.modelId || m.id;
+    if (!upstreamId) continue;
+    const display = formatDisplayName(m.modelName, upstreamId, m.rateMultiplier);
+    const ctx = Number(m?.tokenLimits?.maxInputTokens) || 200_000;
+    for (const v of buildVariants(upstreamId, display)) {
+      expanded.push({
+        ...v,
+        // Carry over context window + raw upstream metadata so the caller
+        // (e.g. the dashboard models endpoint) can render it.
+        contextLength: ctx,
+        rateMultiplier: Number.isFinite(Number(m.rateMultiplier)) ? Number(m.rateMultiplier) : 1.0,
+        upstreamModelId: upstreamId,
+        description: m.description || ""
+      });
+    }
+  }
+
+  catalogCache.set(key, {
+    expiresAt: now + CACHE_TTL_MS,
+    models: expanded,
+    rawModels: raw
+  });
+
+  return { models: expanded, rawModels: raw };
+}
+
+/**
+ * Drop any cached catalog for this credential. Call this after rotating /
+ * importing tokens so the next fetch is fresh.
+ */
+export function invalidateKiroModelCache(credentials) {
+  if (!credentials) return;
+  catalogCache.delete(cacheKey(credentials));
+}
+
+/**
+ * Drop the entire in-memory cache. Mostly for tests / manual debug.
+ */
+export function clearKiroModelCache() {
+  catalogCache.clear();
+}

package/open-sse/services/model.js

@@ -0,0 +1,255 @@
+// Provider alias to ID mapping
+const ALIAS_TO_PROVIDER_ID = {
+  cc: "claude",
+  cx: "codex",
+  gc: "gemini-cli",
+  qw: "qwen",
+  if: "iflow",
+  ag: "antigravity",
+  gh: "github",
+  kr: "kiro",
+  cu: "cursor",
+  kc: "kilocode",
+  kmc: "kimi-coding",
+  cl: "cline",
+  oc: "opencode",
+  ocg: "opencode-go",
+  // TTS providers
+  el: "elevenlabs",
+  // API Key providers
+  openai: "openai",
+  vercel: "vercel-ai-gateway",
+  "vercel-ai-gateway": "vercel-ai-gateway",
+  anthropic: "anthropic",
+  gemini: "gemini",
+  openrouter: "openrouter",
+  glm: "glm",
+  kimi: "kimi",
+  minimax: "minimax",
+  "minimax-cn": "minimax-cn",
+  ds: "deepseek",
+  deepseek: "deepseek",
+  cmc: "commandcode",
+  commandcode: "commandcode",
+  groq: "groq",
+  xai: "xai",
+  mistral: "mistral",
+  pplx: "perplexity",
+  perplexity: "perplexity",
+  together: "together",
+  fireworks: "fireworks",
+  cerebras: "cerebras",
+  cohere: "cohere",
+  nvidia: "nvidia",
+  nebius: "nebius",
+  siliconflow: "siliconflow",
+  hyp: "hyperbolic",
+  hyperbolic: "hyperbolic",
+  dg: "deepgram",
+  deepgram: "deepgram",
+  aai: "assemblyai",
+  assemblyai: "assemblyai",
+  nb: "nanobanana",
+  nanobanana: "nanobanana",
+  ch: "chutes",
+  chutes: "chutes",
+  ark: "volcengine-ark",
+  "volcengine-ark": "volcengine-ark",
+  byteplus: "byteplus",
+  bpm: "byteplus",
+  cursor: "cursor",
+  vx: "vertex",
+  vertex: "vertex",
+  vxp: "vertex-partner",
+  "vertex-partner": "vertex-partner",
+  // Web cookie providers
+  gw: "grok-web",
+  "grok-web": "grok-web",
+  pw: "perplexity-web",
+  "perplexity-web": "perplexity-web",
+  mimo: "xiaomi-mimo",
+  "xiaomi-mimo": "xiaomi-mimo",
+  xmtp: "xiaomi-tokenplan",
+  "xiaomi-tokenplan": "xiaomi-tokenplan",
+  cf: "cloudflare-ai",
+  "cloudflare-ai": "cloudflare-ai",
+  // Image/video providers
+  fal: "fal-ai",
+  "fal-ai": "fal-ai",
+  stability: "stability-ai",
+  "stability-ai": "stability-ai",
+  bfl: "black-forest-labs",
+  "black-forest-labs": "black-forest-labs",
+  recraft: "recraft",
+  topaz: "topaz",
+  runway: "runwayml",
+  runwayml: "runwayml",
+  // Embedding/rerank
+  jina: "jina-ai",
+  "jina-ai": "jina-ai",
+  // TTS
+  polly: "aws-polly",
+  "aws-polly": "aws-polly",
+  // Free-tier providers (synced from OmniRoute)
+  agentrouter: "agentrouter",
+  aimlapi: "aimlapi",
+  aiml: "aimlapi",
+  novita: "novita",
+  modal: "modal",
+  mdl: "modal",
+  reka: "reka",
+  nlpcloud: "nlpcloud",
+  nlpc: "nlpcloud",
+  bazaarlink: "bazaarlink",
+  bzl: "bazaarlink",
+  completions: "completions",
+  cpl: "completions",
+  enally: "enally",
+  enly: "enally",
+  freetheai: "freetheai",
+  fta: "freetheai",
+  llm7: "llm7",
+  lepton: "lepton",
+  kluster: "kluster",
+  ai21: "ai21",
+  "inference-net": "inference-net",
+  inet: "inference-net",
+  predibase: "predibase",
+  bytez: "bytez",
+  morph: "morph",
+  longcat: "longcat",
+  lc: "longcat",
+  puter: "puter",
+  pu: "puter",
+  uncloseai: "uncloseai",
+  unc: "uncloseai",
+  scaleway: "scaleway",
+  scw: "scaleway",
+  deepinfra: "deepinfra",
+  sambanova: "sambanova",
+  samba: "sambanova",
+  nscale: "nscale",
+  baseten: "baseten",
+  publicai: "publicai",
+  "nous-research": "nous-research",
+  nous: "nous-research",
+  glhf: "glhf",
+  bb: "blackbox",
+  blackbox: "blackbox",
+};
+
+/**
+ * Resolve provider alias to provider ID
+ */
+export function resolveProviderAlias(aliasOrId) {
+  return ALIAS_TO_PROVIDER_ID[aliasOrId] || aliasOrId;
+}
+
+/**
+ * Parse model string: "alias/model" or "provider/model" or just alias
+ */
+export function parseModel(modelStr) {
+  if (!modelStr) {
+    return { provider: null, model: null, isAlias: false, providerAlias: null };
+  }
+
+  // Check if standard format: provider/model or alias/model
+  if (modelStr.includes("/")) {
+    const firstSlash = modelStr.indexOf("/");
+    const providerOrAlias = modelStr.slice(0, firstSlash);
+    const model = modelStr.slice(firstSlash + 1);
+    const provider = resolveProviderAlias(providerOrAlias);
+    return { provider, model, isAlias: false, providerAlias: providerOrAlias };
+  }
+
+  // Alias format (model alias, not provider alias)
+  return {
+    provider: null,
+    model: modelStr,
+    isAlias: true,
+    providerAlias: null,
+  };
+}
+
+/**
+ * Resolve model alias from aliases object
+ * Format: { "alias": "provider/model" }
+ */
+export function resolveModelAliasFromMap(alias, aliases) {
+  if (!aliases) return null;
+
+  // Check if alias exists
+  const resolved = aliases[alias];
+  if (!resolved) return null;
+
+  // Resolved value is "provider/model" format
+  if (typeof resolved === "string" && resolved.includes("/")) {
+    const firstSlash = resolved.indexOf("/");
+    const providerOrAlias = resolved.slice(0, firstSlash);
+    return {
+      provider: resolveProviderAlias(providerOrAlias),
+      model: resolved.slice(firstSlash + 1),
+    };
+  }
+
+  // Or object { provider, model }
+  if (typeof resolved === "object" && resolved.provider && resolved.model) {
+    return {
+      provider: resolveProviderAlias(resolved.provider),
+      model: resolved.model,
+    };
+  }
+
+  return null;
+}
+
+/**
+ * Get full model info (parse or resolve)
+ * @param {string} modelStr - Model string
+ * @param {object|function} aliasesOrGetter - Aliases object or async function to get aliases
+ */
+export async function getModelInfoCore(modelStr, aliasesOrGetter) {
+  const parsed = parseModel(modelStr);
+
+  if (!parsed.isAlias) {
+    return {
+      provider: parsed.provider,
+      model: parsed.model,
+    };
+  }
+
+  // Get aliases (from object or function)
+  const aliases =
+    typeof aliasesOrGetter === "function"
+      ? await aliasesOrGetter()
+      : aliasesOrGetter;
+
+  // Resolve alias
+  const resolved = resolveModelAliasFromMap(parsed.model, aliases);
+  if (resolved) {
+    return resolved;
+  }
+
+  // Fallback: infer provider from model name prefix
+  return {
+    provider: inferProviderFromModelName(parsed.model),
+    model: parsed.model,
+  };
+}
+
+/**
+ * Infer provider from model name prefix
+ * Used as fallback when no provider prefix or alias is given
+ */
+function inferProviderFromModelName(modelName) {
+  if (!modelName) return "openai";
+  const m = modelName.toLowerCase();
+  if (m.startsWith("claude-")) return "anthropic";
+  if (m.startsWith("gemini-")) return "gemini";
+  if (m.startsWith("gpt-")) return "openai";
+  if (m.startsWith("o1") || m.startsWith("o3") || m.startsWith("o4"))
+    return "openai";
+  if (m.startsWith("deepseek-")) return "openrouter";
+  // Default fallback
+  return "openai";
+}