free-coding-models 0.3.79 → 0.4.0

package/src/overlays.js

@@ -118,7 +118,8 @@ export function createOverlayRenderers(state, deps) {
     const updateRowIdx = providerKeys.length
     const themeRowIdx = updateRowIdx + 1
     const favoritesModeRowIdx = themeRowIdx + 1
-    const cleanupLegacyProxyRowIdx = favoritesModeRowIdx + 1
+    const startupAiSpeedScanRowIdx = favoritesModeRowIdx + 1
+    const cleanupLegacyProxyRowIdx = startupAiSpeedScanRowIdx + 1
     const changelogViewRowIdx = cleanupLegacyProxyRowIdx + 1
     const shellEnvRowIdx = changelogViewRowIdx + 1
     const EL = '\x1b[K'
@@ -259,6 +260,15 @@ export function createOverlayRenderers(state, deps) {
     cursorLineByRow[favoritesModeRowIdx] = lines.length
     lines.push(state.settingsCursor === favoritesModeRowIdx ? themeColors.bgCursorSettingsList(favoritesModeRow) : favoritesModeRow)
 
+    // 📖 Startup AI Speed Scan row controls the opt-in Ctrl+U auto-run at launch.
+    const startupAiSpeedScanEnabled = state.config.settings?.runAiSpeedTestOnStartup === true
+    const startupAiSpeedScanStatus = startupAiSpeedScanEnabled
+      ? themeColors.successBold('✅ Enabled — runs Ctrl+U after startup')
+      : themeColors.dim('❌ Disabled — manual Ctrl+U only')
+    const startupAiSpeedScanRow = `${bullet(state.settingsCursor === startupAiSpeedScanRowIdx)}${themeColors.textBold('Startup AI Speed Scan').padEnd(44)} ${startupAiSpeedScanStatus}`
+    cursorLineByRow[startupAiSpeedScanRowIdx] = lines.length
+    lines.push(state.settingsCursor === startupAiSpeedScanRowIdx ? themeColors.bgCursorSettingsList(startupAiSpeedScanRow) : startupAiSpeedScanRow)
+
     if (updateState === 'error' && state.settingsUpdateError) {
       lines.push(themeColors.error(`      ${state.settingsUpdateError}`))
     }
@@ -290,7 +300,7 @@ export function createOverlayRenderers(state, deps) {
     if (state.settingsEditMode) {
       lines.push(themeColors.dim('  Type API key  •  Enter Save  •  Esc Cancel'))
     } else {
-      lines.push(themeColors.dim('  ↑↓ Navigate  •  Enter Edit/Run/Cycle  •  + Add key  •  - Remove key  •  Space Toggle/Cycle  •  T Test key  •  U Updates  •  G Global theme  •  Y Favorites mode  •  Esc Close'))
+      lines.push(themeColors.dim('  ↑↓ Navigate  •  Enter Edit/Run/Cycle  •  + Add key  •  - Remove key  •  Space Toggle/Cycle  •  T Test key  •  U Updates  •  G Theme  •  Y Favorites  •  Esc Close'))
     }
     // 📖 Show sync/restore status message if set
     if (state.settingsSyncStatus) {
@@ -897,10 +907,10 @@ export function createOverlayRenderers(state, deps) {
     lines.push(`  ${label('Provider')}    Provider source (NIM, Groq, Cerebras, etc.)  ${hint('Sort:')} ${key('O')}  ${hint('Cycle:')} ${key('D')}`)
     lines.push(`              ${hint('Same model on different providers can have very different speed and uptime.')}`)
     lines.push('')
-    lines.push(`  ${label('Latest')}      Most recent ping response time (ms)  ${hint('Sort:')} ${key('L')}`)
+    lines.push(`  ${label('Last Ping')}   Most recent ping response time (ms)  ${hint('Sort:')} ${key('L')}`)
     lines.push(`              ${hint('Shows how fast the server is responding right now — useful to catch live slowdowns.')}`)
     lines.push('')
-    lines.push(`  ${label('Avg Ping')}    Average response time across all measurable pings (200 + 401) (ms)  ${hint('Sort:')} ${key('A')}`)
+    lines.push(`  ${label('Avg Ping')}   Average response time across all measurable pings (200 + 401) (ms)  ${hint('Sort:')} ${key('A')}`)
     lines.push(`              ${hint('The long-term truth. Even without a key, a 401 still gives real latency so the average stays useful.')}`)
     lines.push('')
     lines.push(`  ${label('Health')}      Live status: ✅ UP / 🔥 429 / ⏳ TIMEOUT / ❌ ERR / 🔑 NO KEY  ${hint('Sort:')} ${key('H')}`)
@@ -931,6 +941,7 @@ export function createOverlayRenderers(state, deps) {
     lines.push(`  ${key('W')}  Toggle ping mode  ${hint('(speed 2s → normal 10s → slow 30s → forced 4s)')}`)
     lines.push(`  ${key('Ctrl+P')}  Open ⚡️ command palette  ${hint('(search and run actions quickly)')}`)
     lines.push(`  ${key('Ctrl+A')}  AI Speed Test  ${hint('(benchmark selected model → time + TPS)')}`)
+    lines.push(`  ${key('Ctrl+U')}  Global AI Speed Test  ${hint('(benchmark all models; Settings can auto-run it on startup)')}`)
     lines.push(`  ${key('E')}  Cycle filter mode  ${hint('(Normal → Configured only → Usable only)')}`)
     lines.push(`  ${key('Z')}  Cycle tool mode  ${hint('(📦 OpenCode → π Pi → 🪼 jcode → 📦 Desktop → 🦞 OpenClaw → 💘 Crush → 🪿 Goose → 🛠 Aider → 🐉 Qwen → 🤲 OpenHands → ⚡ Amp → 🦘 Rovo → ♊ Gemini)')}`)
     lines.push(`  ${key('F')}  Toggle favorite on selected row  ${hint('(1️⃣2️⃣3️⃣ = router fallback order, capped at 🔟)')}`)

package/src/ping.js

@@ -16,6 +16,9 @@
  *
  *   → Functions:
  *   - `resolveCloudflareUrl`: Resolve {account_id} placeholder from CLOUDFLARE_ACCOUNT_ID env var
+ *   - `buildChatCompletionPingBody`: Build minimal chat-completion probe payloads with thinking disabled
+ *   - `markDisabledThinkingUnsupported`: Cache strict providers that reject the optional thinking control
+ *   - `shouldUseDisabledThinkingForProvider`: Decide whether a provider should receive disabled-thinking probes
  *   - `buildPingRequest`: Build provider-specific HTTP request for pinging
  *   - `ping`: Send async ping request with timeout; returns { code, ms, quotaPercent }
  *   - `getHeaderValue`: Helper to extract header value from Headers object or plain object
@@ -41,6 +44,9 @@ import { PING_TIMEOUT } from './constants.js'
 import { fetchProviderQuota as _fetchProviderQuotaFromModule } from './provider-quota-fetchers.js'
 import { supportsUsagePercent } from './quota-capabilities.js'
 
+const DISABLED_THINKING_RETRY_STATUSES = new Set([400, 422])
+const disabledThinkingUnsupportedProviders = new Set()
+
 // 📖 resolveCloudflareUrl: Cloudflare's OpenAI-compatible endpoint is account-scoped.
 // 📖 We resolve {account_id} from env so provider setup can stay simple in config.
 export function resolveCloudflareUrl(url) {
@@ -50,10 +56,37 @@ export function resolveCloudflareUrl(url) {
   return url.replace('{account_id}', encodeURIComponent(accountId))
 }
 
+// 📖 buildChatCompletionPingBody: Use the smallest useful chat-completion probe.
+// 📖 The explicit thinking toggle prevents reasoning-capable endpoints from spending
+// 📖 hidden tokens or adding thinking latency when we only need availability + RTT.
+export function buildChatCompletionPingBody(modelId, overrides = {}, options = {}) {
+  const body = {
+    model: modelId,
+    messages: [{ role: 'user', content: 'hi' }],
+    max_tokens: 1,
+    thinking: { type: 'disabled' },
+    ...overrides,
+  }
+  if (options.disableThinking === false) delete body.thinking
+  return body
+}
+
+// 📖 markDisabledThinkingUnsupported: remember strict providers that reject the
+// 📖 optional `thinking` field so future pings avoid repeated 400/422 retries.
+export function markDisabledThinkingUnsupported(providerKey) {
+  if (providerKey) disabledThinkingUnsupportedProviders.add(providerKey)
+}
+
+// 📖 shouldUseDisabledThinkingForProvider: central policy for OpenAI-compatible
+// 📖 probes, shared by regular pings and router health probes.
+export function shouldUseDisabledThinkingForProvider(providerKey) {
+  return !disabledThinkingUnsupportedProviders.has(providerKey)
+}
+
 // 📖 buildPingRequest: Build provider-specific ping request.
 // 📖 Handles Replicate's /v1/predictions format, Cloudflare's account_id in URL,
 // 📖 and standard OpenAI-compliant chat completions with provider-specific headers.
-export function buildPingRequest(apiKey, modelId, providerKey, url) {
+export function buildPingRequest(apiKey, modelId, providerKey, url, options = {}) {
   // 📖 ZAI models are stored as "zai/glm-..." in sources.js but the API expects just "glm-..."
   const apiModelId = providerKey === 'zai' ? modelId.replace(/^zai\//, '') : modelId
 
@@ -75,7 +108,9 @@ export function buildPingRequest(apiKey, modelId, providerKey, url) {
     return {
       url: resolveCloudflareUrl(url),
       headers,
-      body: { model: apiModelId, messages: [{ role: 'user', content: 'hi' }], max_tokens: 1 },
+      body: buildChatCompletionPingBody(apiModelId, {}, {
+        disableThinking: options.disableThinking ?? shouldUseDisabledThinkingForProvider(providerKey),
+      }),
     }
   }
 
@@ -90,7 +125,31 @@ export function buildPingRequest(apiKey, modelId, providerKey, url) {
   return {
     url,
     headers,
-    body: { model: apiModelId, messages: [{ role: 'user', content: 'hi' }], max_tokens: 1 },
+    body: buildChatCompletionPingBody(apiModelId, {}, {
+      disableThinking: options.disableThinking ?? shouldUseDisabledThinkingForProvider(providerKey),
+    }),
+  }
+}
+
+// 📖 sendPingFetch: keep retry code tiny and ensure both attempts use the same abort signal.
+async function sendPingFetch(req, signal) {
+  return fetch(req.url, {
+    method: 'POST', signal,
+    headers: req.headers,
+    body: JSON.stringify(req.body),
+  })
+}
+
+// 📖 isDisabledThinkingRejected: strict OpenAI-compatible gateways may reject
+// 📖 unknown root fields. We only retry when the status and error text names
+// 📖 the optional `thinking` control, avoiding retries for real model failures.
+async function isDisabledThinkingRejected(resp, req) {
+  if (!req?.body?.thinking || !DISABLED_THINKING_RETRY_STATUSES.has(resp.status)) return false
+  try {
+    const text = await resp.clone().text()
+    return /thinking/i.test(text)
+  } catch {
+    return false
   }
 }
 
@@ -104,12 +163,13 @@ export async function ping(apiKey, modelId, providerKey, url) {
   const timer = setTimeout(() => ctrl.abort(), PING_TIMEOUT)
   const t0    = performance.now()
   try {
-    const req = buildPingRequest(apiKey, modelId, providerKey, url)
-    const resp = await fetch(req.url, {
-      method: 'POST', signal: ctrl.signal,
-      headers: req.headers,
-      body: JSON.stringify(req.body),
-    })
+    let req = buildPingRequest(apiKey, modelId, providerKey, url)
+    let resp = await sendPingFetch(req, ctrl.signal)
+    if (await isDisabledThinkingRejected(resp, req)) {
+      markDisabledThinkingUnsupported(providerKey)
+      req = buildPingRequest(apiKey, modelId, providerKey, url, { disableThinking: false })
+      resp = await sendPingFetch(req, ctrl.signal)
+    }
     // 📖 Normalize all HTTP 2xx statuses to "200" so existing verdict/avg logic still works.
     const code = resp.status >= 200 && resp.status < 300 ? '200' : String(resp.status)
     return {

package/src/render-helpers.js

@@ -202,7 +202,7 @@ export function calculateViewport(terminalRows, scrollOffset, totalModels, lineB
 // 📖 Non-favorites: active sort column/direction.
 // 📖 Models that are both recommended AND favorite — show in recommended section.
 // 📖 pinFavorites=false keeps favorites highlighted but lets normal sort/filter order apply.
-export function sortResultsWithPinnedFavorites(results, sortColumn, sortDirection, { pinFavorites = true } = {}) {
+export function sortResultsWithPinnedFavorites(results, sortColumn, sortDirection, { pinFavorites = true, benchmarkResults = {} } = {}) {
   if (!pinFavorites) {
     const recommendedRows = results
       .filter((r) => r.isRecommended)
@@ -210,7 +210,8 @@ export function sortResultsWithPinnedFavorites(results, sortColumn, sortDirectio
     const nonRecommendedRows = sortResults(
       results.filter((r) => !r.isRecommended),
       sortColumn,
-      sortDirection
+      sortDirection,
+      { benchmarkResults }
     )
     return [...recommendedRows, ...nonRecommendedRows]
   }
@@ -224,7 +225,7 @@ export function sortResultsWithPinnedFavorites(results, sortColumn, sortDirectio
   const bothRows = results
     .filter((r) => r.isRecommended && r.isFavorite)
     .sort((a, b) => (b.recommendScore || 0) - (a.recommendScore || 0))
-  const nonSpecialRows = sortResults(results.filter((r) => !r.isFavorite && !r.isRecommended), sortColumn, sortDirection)
+  const nonSpecialRows = sortResults(results.filter((r) => !r.isFavorite && !r.isRecommended), sortColumn, sortDirection, { benchmarkResults })
   return [...bothRows, ...recommendedRows, ...favoriteRows, ...nonSpecialRows]
 }