vforclaude2 0.3.87

package/open-sse/services/accountFallback.js

@@ -0,0 +1,251 @@
+import { COOLDOWN_MS, BACKOFF_CONFIG, HTTP_STATUS } from "../config/runtimeConfig.js";
+
+/**
+ * Calculate exponential backoff cooldown for rate limits (429)
+ * Level 0: 1s, Level 1: 2s, Level 2: 4s... → max 2 min
+ * @param {number} backoffLevel - Current backoff level
+ * @returns {number} Cooldown in milliseconds
+ */
+export function getQuotaCooldown(backoffLevel = 0) {
+  const cooldown = BACKOFF_CONFIG.base * Math.pow(2, backoffLevel);
+  return Math.min(cooldown, BACKOFF_CONFIG.max);
+}
+
+/**
+ * Check if error should trigger account fallback (switch to next account)
+ * @param {number} status - HTTP status code
+ * @param {string} errorText - Error message text
+ * @param {number} backoffLevel - Current backoff level for exponential backoff
+ * @returns {{ shouldFallback: boolean, cooldownMs: number, newBackoffLevel?: number }}
+ */
+export function checkFallbackError(status, errorText, backoffLevel = 0) {
+  // Check error message FIRST - specific patterns take priority over status codes
+  if (errorText) {
+    const errorStr = typeof errorText === "string" ? errorText : JSON.stringify(errorText);
+    const lowerError = errorStr.toLowerCase();
+
+    if (lowerError.includes("no credentials")) {
+      return { shouldFallback: true, cooldownMs: COOLDOWN_MS.notFound };
+    }
+
+    if (lowerError.includes("request not allowed")) {
+      return { shouldFallback: true, cooldownMs: COOLDOWN_MS.requestNotAllowed };
+    }
+
+    // Rate limit keywords - exponential backoff
+    if (
+      lowerError.includes("rate limit") ||
+      lowerError.includes("too many requests") ||
+      lowerError.includes("quota exceeded") ||
+      lowerError.includes("capacity") ||
+      lowerError.includes("overloaded")
+    ) {
+      const newLevel = Math.min(backoffLevel + 1, BACKOFF_CONFIG.maxLevel);
+      return {
+        shouldFallback: true,
+        cooldownMs: getQuotaCooldown(backoffLevel),
+        newBackoffLevel: newLevel
+      };
+    }
+  }
+
+  if (status === HTTP_STATUS.UNAUTHORIZED) {
+    return { shouldFallback: true, cooldownMs: COOLDOWN_MS.unauthorized };
+  }
+
+  if (status === HTTP_STATUS.PAYMENT_REQUIRED || status === HTTP_STATUS.FORBIDDEN) {
+    return { shouldFallback: true, cooldownMs: COOLDOWN_MS.paymentRequired };
+  }
+
+  if (status === HTTP_STATUS.NOT_FOUND) {
+    return { shouldFallback: true, cooldownMs: COOLDOWN_MS.notFound };
+  }
+
+  // 429 - Rate limit with exponential backoff
+  if (status === HTTP_STATUS.RATE_LIMITED) {
+    const newLevel = Math.min(backoffLevel + 1, BACKOFF_CONFIG.maxLevel);
+    return {
+      shouldFallback: true,
+      cooldownMs: getQuotaCooldown(backoffLevel),
+      newBackoffLevel: newLevel
+    };
+  }
+
+  // Transient errors
+  const transientStatuses = [
+    HTTP_STATUS.NOT_ACCEPTABLE, HTTP_STATUS.REQUEST_TIMEOUT,
+    HTTP_STATUS.SERVER_ERROR, HTTP_STATUS.BAD_GATEWAY,
+    HTTP_STATUS.SERVICE_UNAVAILABLE, HTTP_STATUS.GATEWAY_TIMEOUT
+  ];
+  if (transientStatuses.includes(status)) {
+    return { shouldFallback: true, cooldownMs: COOLDOWN_MS.transient };
+  }
+
+  // All other errors - fallback with transient cooldown
+  return { shouldFallback: true, cooldownMs: COOLDOWN_MS.transient };
+}
+
+/**
+ * Check if account is currently unavailable (cooldown not expired)
+ */
+export function isAccountUnavailable(unavailableUntil) {
+  if (!unavailableUntil) return false;
+  return new Date(unavailableUntil).getTime() > Date.now();
+}
+
+/**
+ * Calculate unavailable until timestamp
+ */
+export function getUnavailableUntil(cooldownMs) {
+  return new Date(Date.now() + cooldownMs).toISOString();
+}
+
+/**
+ * Get the earliest rateLimitedUntil from a list of accounts
+ * @param {Array} accounts - Array of account objects with rateLimitedUntil
+ * @returns {string|null} Earliest rateLimitedUntil ISO string, or null
+ */
+export function getEarliestRateLimitedUntil(accounts) {
+  let earliest = null;
+  const now = Date.now();
+  for (const acc of accounts) {
+    if (!acc.rateLimitedUntil) continue;
+    const until = new Date(acc.rateLimitedUntil).getTime();
+    if (until <= now) continue;
+    if (!earliest || until < earliest) earliest = until;
+  }
+  if (!earliest) return null;
+  return new Date(earliest).toISOString();
+}
+
+/**
+ * Format rateLimitedUntil to human-readable "reset after Xm Ys"
+ * @param {string} rateLimitedUntil - ISO timestamp
+ * @returns {string} e.g. "reset after 2m 30s"
+ */
+export function formatRetryAfter(rateLimitedUntil) {
+  if (!rateLimitedUntil) return "";
+  const diffMs = new Date(rateLimitedUntil).getTime() - Date.now();
+  if (diffMs <= 0) return "reset after 0s";
+  const totalSec = Math.ceil(diffMs / 1000);
+  const h = Math.floor(totalSec / 3600);
+  const m = Math.floor((totalSec % 3600) / 60);
+  const s = totalSec % 60;
+  const parts = [];
+  if (h > 0) parts.push(`${h}h`);
+  if (m > 0) parts.push(`${m}m`);
+  if (s > 0 || parts.length === 0) parts.push(`${s}s`);
+  return `reset after ${parts.join(" ")}`;
+}
+
+/** Prefix for model lock flat fields on connection record */
+export const MODEL_LOCK_PREFIX = "modelLock_";
+
+/** Special key used when no model is known (account-level lock) */
+export const MODEL_LOCK_ALL = `${MODEL_LOCK_PREFIX}__all`;
+
+/** Build the flat field key for a model lock */
+export function getModelLockKey(model) {
+  return model ? `${MODEL_LOCK_PREFIX}${model}` : MODEL_LOCK_ALL;
+}
+
+/**
+ * Check if a model lock on a connection is still active.
+ * Reads flat field `modelLock_${model}` (or `modelLock___all` when model=null).
+ */
+export function isModelLockActive(connection, model) {
+  const key = getModelLockKey(model);
+  const expiry = connection[key] || connection[MODEL_LOCK_ALL];
+  if (!expiry) return false;
+  return new Date(expiry).getTime() > Date.now();
+}
+
+/**
+ * Get earliest active model lock expiry across all modelLock_* fields.
+ * Used for UI cooldown display.
+ */
+export function getEarliestModelLockUntil(connection) {
+  if (!connection) return null;
+  let earliest = null;
+  const now = Date.now();
+  for (const [key, val] of Object.entries(connection)) {
+    if (!key.startsWith(MODEL_LOCK_PREFIX) || !val) continue;
+    const t = new Date(val).getTime();
+    if (t <= now) continue;
+    if (!earliest || t < earliest) earliest = t;
+  }
+  return earliest ? new Date(earliest).toISOString() : null;
+}
+
+/**
+ * Build update object to set a model lock on a connection.
+ */
+export function buildModelLockUpdate(model, cooldownMs) {
+  const key = getModelLockKey(model);
+  return { [key]: new Date(Date.now() + cooldownMs).toISOString() };
+}
+
+/**
+ * Build update object to clear all model locks on a connection.
+ */
+export function buildClearModelLocksUpdate(connection) {
+  const cleared = {};
+  for (const key of Object.keys(connection)) {
+    if (key.startsWith(MODEL_LOCK_PREFIX)) cleared[key] = null;
+  }
+  return cleared;
+}
+
+/**
+ * Filter available accounts (not in cooldown)
+ */
+export function filterAvailableAccounts(accounts, excludeId = null) {
+  const now = Date.now();
+  return accounts.filter(acc => {
+    if (excludeId && acc.id === excludeId) return false;
+    if (acc.rateLimitedUntil) {
+      const until = new Date(acc.rateLimitedUntil).getTime();
+      if (until > now) return false;
+    }
+    return true;
+  });
+}
+
+/**
+ * Reset account state when request succeeds
+ * Clears cooldown and resets backoff level to 0
+ * @param {object} account - Account object
+ * @returns {object} Updated account with reset state
+ */
+export function resetAccountState(account) {
+  if (!account) return account;
+  return {
+    ...account,
+    rateLimitedUntil: null,
+    backoffLevel: 0,
+    lastError: null,
+    status: "active"
+  };
+}
+
+/**
+ * Apply error state to account
+ * @param {object} account - Account object
+ * @param {number} status - HTTP status code
+ * @param {string} errorText - Error message
+ * @returns {object} Updated account with error state
+ */
+export function applyErrorState(account, status, errorText) {
+  if (!account) return account;
+
+  const backoffLevel = account.backoffLevel || 0;
+  const { cooldownMs, newBackoffLevel } = checkFallbackError(status, errorText, backoffLevel);
+
+  return {
+    ...account,
+    rateLimitedUntil: cooldownMs > 0 ? getUnavailableUntil(cooldownMs) : null,
+    backoffLevel: newBackoffLevel ?? backoffLevel,
+    lastError: { status, message: errorText, timestamp: new Date().toISOString() },
+    status: "error"
+  };
+}

package/open-sse/services/combo.js

@@ -0,0 +1,111 @@
+/**
+ * Shared combo (model combo) handling with fallback support
+ */
+
+import { checkFallbackError, formatRetryAfter } from "./accountFallback.js";
+import { unavailableResponse } from "../utils/error.js";
+
+/**
+ * Get combo models from combos data
+ * @param {string} modelStr - Model string to check
+ * @param {Array|Object} combosData - Array of combos or object with combos
+ * @returns {string[]|null} Array of models or null if not a combo
+ */
+export function getComboModelsFromData(modelStr, combosData) {
+  // Don't check if it's in provider/model format
+  if (modelStr.includes("/")) return null;
+  
+  // Handle both array and object formats
+  const combos = Array.isArray(combosData) ? combosData : (combosData?.combos || []);
+  
+  const combo = combos.find(c => c.name === modelStr);
+  if (combo && combo.models && combo.models.length > 0) {
+    return combo.models;
+  }
+  return null;
+}
+
+/**
+ * Handle combo chat with fallback
+ * @param {Object} options
+ * @param {Object} options.body - Request body
+ * @param {string[]} options.models - Array of model strings to try
+ * @param {Function} options.handleSingleModel - Function to handle single model: (body, modelStr) => Promise<Response>
+ * @param {Object} options.log - Logger object
+ * @returns {Promise<Response>}
+ */
+export async function handleComboChat({ body, models, handleSingleModel, log }) {
+  let lastError = null;
+  let earliestRetryAfter = null;
+  let lastStatus = null;
+
+  for (let i = 0; i < models.length; i++) {
+    const modelStr = models[i];
+    log.info("COMBO", `Trying model ${i + 1}/${models.length}: ${modelStr}`);
+
+    try {
+      const result = await handleSingleModel(body, modelStr);
+      
+      // Success (2xx) - return response
+      if (result.ok) {
+        log.info("COMBO", `Model ${modelStr} succeeded`);
+        return result;
+      }
+
+      // Extract error info from response
+      let errorText = result.statusText || "";
+      let retryAfter = null;
+      try {
+        const errorBody = await result.clone().json();
+        errorText = errorBody?.error?.message || errorBody?.error || errorBody?.message || errorText;
+        retryAfter = errorBody?.retryAfter || null;
+      } catch {
+        // Ignore JSON parse errors
+      }
+
+      // Track earliest retryAfter across all combo models
+      if (retryAfter && (!earliestRetryAfter || new Date(retryAfter) < new Date(earliestRetryAfter))) {
+        earliestRetryAfter = retryAfter;
+      }
+
+      // Normalize error text to string (Worker-safe)
+      if (typeof errorText !== "string") {
+        try { errorText = JSON.stringify(errorText); } catch { errorText = String(errorText); }
+      }
+
+      // Check if should fallback to next model
+      const { shouldFallback } = checkFallbackError(result.status, errorText);
+      
+      if (!shouldFallback) {
+        log.warn("COMBO", `Model ${modelStr} failed (no fallback)`, { status: result.status });
+        return result;
+      }
+
+      // Fallback to next model
+      lastError = errorText || String(result.status);
+      if (!lastStatus) lastStatus = result.status;
+      log.warn("COMBO", `Model ${modelStr} failed, trying next`, { status: result.status });
+    } catch (error) {
+      // Catch unexpected exceptions to ensure fallback continues
+      lastError = error.message || String(error);
+      if (!lastStatus) lastStatus = 500;
+      log.warn("COMBO", `Model ${modelStr} threw error, trying next`, { error: lastError });
+    }
+  }
+
+  // All models failed
+  const status =  406;
+  const msg = lastError || "All combo models unavailable";
+
+  if (earliestRetryAfter) {
+    const retryHuman = formatRetryAfter(earliestRetryAfter);
+    log.warn("COMBO", `All models failed | ${msg} (${retryHuman})`);
+    return unavailableResponse(status, msg, earliestRetryAfter, retryHuman);
+  }
+
+  log.warn("COMBO", `All models failed | ${msg}`);
+  return new Response(
+    JSON.stringify({ error: { message: msg } }),
+    { status, headers: { "Content-Type": "application/json" } }
+  );
+}

package/open-sse/services/compact.js

@@ -0,0 +1,71 @@
+/**
+ * Shared combo (model combo) handling with fallback support
+ */
+
+/**
+ * Get combo models from combos data
+ * @param {string} modelStr - Model string to check
+ * @param {Array|Object} combosData - Array of combos or object with combos
+ * @returns {string[]|null} Array of models or null if not a combo
+ */
+export function getComboModelsFromData(modelStr, combosData) {
+  // Don't check if it's in provider/model format
+  if (modelStr.includes("/")) return null;
+  
+  // Handle both array and object formats
+  const combos = Array.isArray(combosData) ? combosData : (combosData?.combos || []);
+  
+  const combo = combos.find(c => c.name === modelStr);
+  if (combo && combo.models && combo.models.length > 0) {
+    return combo.models;
+  }
+  return null;
+}
+
+/**
+ * Handle combo chat with fallback
+ * @param {Object} options
+ * @param {Object} options.body - Request body
+ * @param {string[]} options.models - Array of model strings to try
+ * @param {Function} options.handleSingleModel - Function to handle single model: (body, modelStr) => Promise<Response>
+ * @param {Object} options.log - Logger object
+ * @returns {Promise<Response>}
+ */
+export async function handleComboChat({ body, models, handleSingleModel, log }) {
+  let lastError = null;
+
+  for (let i = 0; i < models.length; i++) {
+    const modelStr = models[i];
+    log.info("COMBO", `Trying model ${i + 1}/${models.length}: ${modelStr}`);
+
+    let result;
+    try {
+      result = await handleSingleModel(body, modelStr);
+    } catch (e) {
+      lastError = `${modelStr}: ${e.message}`;
+      log.warn("COMBO", `Model threw exception, trying next`, { model: modelStr, error: e.message });
+      continue;
+    }
+
+    // Success or client error - return response
+    if (result.ok || result.status < 500) {
+      return result;
+    }
+
+    // 5xx error - try next model
+    lastError = `${modelStr}: ${result.statusText || result.status}`;
+    log.warn("COMBO", `Model failed, trying next`, { model: modelStr, status: result.status });
+  }
+
+  log.warn("COMBO", "All models failed");
+  
+  // Return 503 with last error
+  return new Response(
+    JSON.stringify({ error: lastError || "All combo models unavailable" }),
+    { 
+      status: 503, 
+      headers: { "Content-Type": "application/json" }
+    }
+  );
+}
+

package/open-sse/services/model.js

@@ -0,0 +1,169 @@
+// 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",
+  // API Key providers
+  openai: "openai",
+  anthropic: "anthropic",
+  gemini: "gemini",
+  openrouter: "openrouter",
+  glm: "glm",
+  kimi: "kimi",
+  minimax: "minimax",
+  "minimax-cn": "minimax-cn",
+  ds: "deepseek",
+  deepseek: "deepseek",
+  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",
+  cursor: "cursor",
+  vx: "vertex",
+  vertex: "vertex",
+  vxp: "vertex-partner",
+  "vertex-partner": "vertex-partner",
+};
+
+/**
+ * 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";
+}