claude-autorouter 0.2.0 → 0.3.2

package/src/onboarding.mjs

@@ -6,11 +6,14 @@ import { promisify } from 'node:util';
 import { readConfig, requireKeys } from './config.mjs';
 import { buildClaudeEnv, conflictingProviders, LOCAL_AUTH_HEADER } from './auth.mjs';
 import { getConfigPath, loadUserConfig, saveUserConfig } from './user-config.mjs';
-import { selectOllamaModel } from './ollama-models.mjs';
+import { DEFAULT_OLLAMA_MODEL, validateOllamaModel } from './ollama-models.mjs';
 import { inspectOllama, setupOllama } from './ollama-setup.mjs';
 
 const execute = promisify(execFile);
 
+export const ollamaDeadlineText = timeoutMs => timeoutMs === 0
+  ? 'routing deadline disabled' : `routing deadline ${timeoutMs} ms per request`;
+
 // Readline manages editing and restores terminal state; its output is discarded
 // so neither typing nor pasted credentials are echoed to the terminal.
 export async function askSecret(label, { input = process.stdin, output = process.stderr } = {}) {
@@ -31,27 +34,32 @@ export async function askSecret(label, { input = process.stdin, output = process
 }
 
 export async function setup(args, {
-  env = process.env, write = console.log, prompt = askSecret, fetchImpl = fetch, signal, totalMemory,
+  env = process.env, write = console.log, prompt = askSecret, fetchImpl = fetch, signal,
 } = {}) {
   let authMode = env.AUTOROUTER_AUTH_MODE ?? 'subscription';
   let evaluator = env.AUTOROUTER_EVALUATOR ?? 'jev';
-  let preset = 'compact';
-  let explicitPreset = false;
   let model;
+  let ollamaTimeoutMs;
   let pull = false;
   let overwrite = false;
   for (let i = 0; i < args.length; i++) {
     if (args[i] === '--auth-mode') authMode = args[++i];
     else if (args[i] === '--evaluator') evaluator = args[++i];
-    else if (args[i] === '--ollama-preset') { preset = args[++i]; explicitPreset = true; if (preset === undefined) throw new Error('--ollama-preset requires compact, quality, or auto'); }
     else if (args[i] === '--ollama-model') { model = args[++i]; if (model === undefined) throw new Error('--ollama-model requires a model tag'); }
+    else if (args[i] === '--ollama-timeout-ms') {
+      const value = args[++i];
+      if (typeof value !== 'string' || !/^[0-9]+$/.test(value.trim()) || Number(value) > 30000) {
+        throw new Error('--ollama-timeout-ms requires an integer between 0 and 30000 (0 disables the routing deadline)');
+      }
+      ollamaTimeoutMs = String(Number(value));
+    }
     else if (args[i] === '--pull') pull = true;
     else if (args[i] === '--force') overwrite = true;
-    else throw new Error('Usage: claude-autorouter setup [--auth-mode subscription|api-key] [--evaluator jev|ollama] [--ollama-preset compact|quality|auto] [--ollama-model TAG] [--pull] [--force]');
+    else throw new Error('Usage: claude-autorouter setup [--auth-mode subscription|api-key] [--evaluator jev|ollama] [--ollama-model TAG] [--ollama-timeout-ms N] [--pull] [--force]');
   }
   if (!['subscription', 'api-key'].includes(authMode)) throw new Error('--auth-mode must be subscription or api-key');
   if (!['jev', 'ollama'].includes(evaluator)) throw new Error('--evaluator must be jev or ollama');
-  if (evaluator !== 'ollama' && (explicitPreset || model !== undefined || pull)) throw new Error('Ollama model and download options require --evaluator ollama');
+  if (evaluator !== 'ollama' && (model !== undefined || ollamaTimeoutMs !== undefined || pull)) throw new Error('Ollama model, deadline and download options require --evaluator ollama');
   const path = getConfigPath(env);
   if (!overwrite && existsSync(path)) throw new Error('AutoRouter configuration already exists. Use setup --force to replace it.');
   write(evaluator === 'ollama'
@@ -59,11 +67,11 @@ export async function setup(args, {
     : 'AutoRouter sends bounded prompt excerpts to TypeSafe Jev and complete requests to Anthropic.');
   const values = { AUTOROUTER_AUTH_MODE: authMode, AUTOROUTER_CLIENT_PROFILE: 'compatible', AUTOROUTER_EVALUATOR: evaluator };
   if (evaluator === 'ollama') {
-    values.AUTOROUTER_OLLAMA_MODEL = selectOllamaModel({ preset, model: model ?? (explicitPreset ? undefined : env.AUTOROUTER_OLLAMA_MODEL), totalMemory });
+    values.AUTOROUTER_OLLAMA_MODEL = validateOllamaModel(model ?? env.AUTOROUTER_OLLAMA_MODEL ?? DEFAULT_OLLAMA_MODEL);
     for (const key of ['AUTOROUTER_OLLAMA_URL', 'AUTOROUTER_OLLAMA_TIMEOUT_MS', 'AUTOROUTER_OLLAMA_KEEP_ALIVE']) {
       if (env[key] !== undefined) values[key] = env[key];
     }
-    write(`Local evaluator model: ${values.AUTOROUTER_OLLAMA_MODEL}.`);
+    if (ollamaTimeoutMs !== undefined) values.AUTOROUTER_OLLAMA_TIMEOUT_MS = ollamaTimeoutMs;
   }
   const keys = [...(evaluator === 'jev' ? ['TYPESAFE_API_KEY'] : []), ...(authMode === 'api-key' ? ['ANTHROPIC_API_KEY'] : [])];
   for (const key of keys) {
@@ -74,6 +82,7 @@ export async function setup(args, {
   const config = readConfig(values);
   requireKeys(config);
   if (evaluator === 'ollama') {
+    write(`Local evaluator: ${config.ollamaModel}; ${ollamaDeadlineText(config.ollamaTimeoutMs)}.`);
     const controller = new AbortController();
     const cancel = () => controller.abort();
     if (!signal) for (const name of ['SIGINT', 'SIGTERM']) process.once(name, cancel);
@@ -107,6 +116,8 @@ export async function doctor({ env = process.env, write = console.log, run = exe
     report(false, `Unset ${key}; AutoRouter uses the Anthropic Messages API`);
   }
   if (config?.evaluator === 'ollama') {
+    write(`Local evaluator: ${config.ollamaModel}; ${ollamaDeadlineText(config.ollamaTimeoutMs)}.`);
+    write('Model availability is checked below; classification speed and accuracy are not tested.');
     try {
       const result = await inspectOllama(config, { fetchImpl, signal });
       report(result.installed, result.installed

package/src/statusline.mjs

@@ -6,6 +6,9 @@ const REASONS = {
   context_capacity: 'large context',
   internal_request: 'internal request', unknown_model: 'custom model', low_confidence: 'low confidence',
 };
+const CLASSIFIER_ERRORS = {
+  timeout: 'timeout', http_error: 'HTTP error', invalid_response: 'invalid response', network_error: 'network error',
+};
 const clean = (value, limit = 64) => typeof value === 'string' ? value
   .replace(/\x1b\][\s\S]*?(?:\x07|\x1b\\)/g, '')
   .replace(/\x1b\[[0-?]*[ -/]*[@-~]/g, '')
@@ -125,21 +128,28 @@ export function renderStatusLine(input, snapshot, { now = Date.now(), color = tr
 
   const details = [];
   const source = ['jev', 'ollama', 'cache', 'fallback'].includes(state?.source) ? state.source : undefined;
+  const evaluator = ['jev', 'ollama'].includes(state?.evaluator) ? state.evaluator : undefined;
+  const evaluatorLabel = evaluator === 'ollama' ? 'Ollama' : evaluator === 'jev' ? 'Jev' : '';
+  let fallbackCause = '';
+  let fallbackPhase = '';
+  let compactFallback = false;
   if (source) {
-    const evaluator = ['jev', 'ollama'].includes(state.evaluator) ? state.evaluator : undefined;
-    const evaluatorLabel = evaluator === 'ollama' ? 'Ollama' : evaluator === 'jev' ? 'Jev' : '';
     const sourceLabel = source === 'jev' ? 'Jev' : source === 'ollama' ? 'Ollama'
       : evaluatorLabel ? `${evaluatorLabel} ${source}` : source;
     const timing = Number.isFinite(state.latency_ms) && state.latency_ms >= 0 ? ` ${Math.round(Math.min(state.latency_ms, 999999))}ms` : '';
     const classified = ['haiku', 'sonnet', 'opus'].includes(state.classified_tier) ? state.classified_tier : undefined;
     const chosenFamily = /^claude-(haiku|sonnet|opus)-/.exec(state.selected_model ?? '')?.[1];
-    const override = classified && chosenFamily && classified !== chosenFamily
+    const override = source !== 'fallback' && classified && chosenFamily && classified !== chosenFamily
       ? `→${classified[0].toUpperCase()}${classified.slice(1)}` : '';
     details.push(`${sourceLabel}${override}${timing}`);
   }
   if (source === 'fallback') {
-    const classifierError = clean(state.classifier_error, 24);
-    if (classifierError) details.push(classifierError.replaceAll('_', ' '));
+    // Snapshots normally contain allowlisted categories, but the renderer also
+    // rejects raw error messages so paths and provider response text stay out.
+    fallbackCause = Object.hasOwn(CLASSIFIER_ERRORS, state.classifier_error) ? CLASSIFIER_ERRORS[state.classifier_error] : '';
+    if (state.classifier_error === 'http_error' && Number.isInteger(state.classifier_status)
+      && state.classifier_status >= 100 && state.classifier_status <= 599) fallbackCause = `HTTP ${state.classifier_status}`;
+    if (fallbackCause) details.push(fallbackCause);
   }
   if (Object.hasOwn(REASONS, state?.reason)) details.push(state.reason === 'context_capacity' && state.context_check === 'count_unavailable'
     ? 'size unverified' : REASONS[state.reason]);
@@ -157,11 +167,23 @@ export function renderStatusLine(input, snapshot, { now = Date.now(), color = tr
   if (width(plain()) > available && source !== 'fallback' && phase !== 'error') detail = '';
   if (width(plain()) > available && saving) saving = savings.compact;
   if (width(plain()) > available) saving = '';
+  if (width(plain()) > available && source === 'fallback') {
+    // A successful Claude response can still follow evaluator failure. When
+    // space is tight, retain that cause instead of an ordinary "ready" phase,
+    // evaluator timing, or the guard details that followed the fallback.
+    compactFallback = true;
+    fallbackPhase = ['error', 'cancelled'].includes(phase) ? status : '';
+    status = [fallbackPhase, `${evaluatorLabel ? `${evaluatorLabel} ` : ''}fallback${fallbackCause ? `: ${fallbackCause}` : ''}`].filter(Boolean).join(' · ');
+    detail = '';
+  }
   if (width(plain()) > available) detail = '';
   if (width(plain()) > available) brand = '● AR';
   if (width(plain()) > available) brand = '';
+  if (width(plain()) > available && compactFallback) {
+    status = [fallbackPhase, `fallback${fallbackCause ? `: ${fallbackCause}` : ''}`].filter(Boolean).join(' · ');
+  }
   if (width(plain()) > available && model) {
-    if (phase === 'streaming') status = 'stream';
+    if (phase === 'streaming' && !compactFallback) status = 'stream';
     const room = available - width(prefix + suffix + status) - 3;
     if (room >= 1) model = shorten(model, room);
     else {
@@ -172,6 +194,8 @@ export function renderStatusLine(input, snapshot, { now = Date.now(), color = tr
       else if (width('● AR · ' + status) <= available) brand = '● AR';
     }
   }
+  if (width(plain()) > available && compactFallback && !fallbackPhase && available >= width('fallback')
+    && available < width('fallback: ') + 2) status = 'fallback';
   if (width(plain()) > available) status = shorten(status, Math.max(1, available - width(modelLabel()) - (model ? 3 : 0)));
   const attention = phase === 'error' ? '31' : source === 'fallback' ? '33' : phase === 'cancelled' ? '2' : phase === 'streaming' || phase === 'ready' ? '32' : '36';
   const chunks = [];