@askalf/dario 3.2.4 → 3.2.5

package/README.md

@@ -452,7 +452,6 @@ Your app sends whatever it wants — any tools, any parameters. dario replaces t
 | `DARIO_API_KEY` | If set, all endpoints (except `/health`) require matching `x-api-key` header or `Authorization: Bearer` header | unset (open) |
 | `DARIO_NO_BUN` | Disable automatic Bun relaunch (stay on Node.js) | unset |
 | `DARIO_MIN_INTERVAL_MS` | Minimum ms between requests (rate governor) | `500` |
-| `DARIO_EXTENDED_CONTEXT` | Enable 1M context window for Sonnet 4.6 (requires [Extra Usage](https://support.claude.com/en/articles/12429409-manage-extra-usage-for-paid-claude-plans) enabled) | unset |
 
 ## Supported Features
 

package/dist/proxy.js

@@ -731,12 +731,9 @@ export async function startProxy(opts = {}) {
                     beta += ',' + clientBeta;
             }
             else {
-                // CC v2.1.104 base beta set. context-1m is opt-in via DARIO_EXTENDED_CONTEXT=1
-                // because it requires Extra Usage enabled on the account.
-                const baseBeta = 'claude-code-20250219,oauth-2025-04-20,interleaved-thinking-2025-05-14,context-management-2025-06-27,prompt-caching-scope-2026-01-05,advisor-tool-2026-03-01,effort-2025-11-24';
-                beta = process.env.DARIO_EXTENDED_CONTEXT
-                    ? `claude-code-20250219,oauth-2025-04-20,context-1m-2025-08-07,interleaved-thinking-2025-05-14,context-management-2025-06-27,prompt-caching-scope-2026-01-05,advisor-tool-2026-03-01,effort-2025-11-24`
-                    : baseBeta;
+                // CC v2.1.104 beta set (exact 8 from MITM capture, exact order).
+                // context-1m requires Extra Usage — if it 400s, we auto-retry without it.
+                beta = 'claude-code-20250219,oauth-2025-04-20,context-1m-2025-08-07,interleaved-thinking-2025-05-14,context-management-2025-06-27,prompt-caching-scope-2026-01-05,advisor-tool-2026-03-01,effort-2025-11-24';
                 if (clientBeta) {
                     const baseSet = new Set(beta.split(','));
                     const filtered = filterBillableBetas(clientBeta)
@@ -764,12 +761,52 @@ export async function startProxy(opts = {}) {
                 // CC sends 600 on first request per session. With rotation, every request is "first"
                 'x-stainless-timeout': '600',
             };
-            const upstream = await fetch(targetBase, {
+            let upstream = await fetch(targetBase, {
                 method: req.method ?? 'POST',
                 headers,
                 body: finalBody ? new Uint8Array(finalBody) : undefined,
                 signal: AbortSignal.timeout(UPSTREAM_TIMEOUT_MS),
             });
+            // Auto-retry without context-1m if it triggers a long-context billing error
+            if (upstream.status === 429 && !passthrough) {
+                const peekBody = await upstream.text().catch(() => '');
+                if (peekBody.includes('long context') || peekBody.includes('Extra usage is required')) {
+                    if (verbose)
+                        console.log(`[dario] #${requestCount} context-1m rejected — retrying without it`);
+                    const reducedBeta = beta.replace(',context-1m-2025-08-07', '').replace('context-1m-2025-08-07,', '');
+                    const retryHeaders = { ...headers, 'anthropic-beta': reducedBeta };
+                    const retry = await fetch(targetBase, {
+                        method: req.method ?? 'POST',
+                        headers: retryHeaders,
+                        body: finalBody ? new Uint8Array(finalBody) : undefined,
+                        signal: AbortSignal.timeout(UPSTREAM_TIMEOUT_MS),
+                    });
+                    // Use the retry response from here on
+                    upstream = retry;
+                }
+                else {
+                    // Not a context-1m issue — handle as normal 429 below
+                    // Re-wrap the already-consumed body for downstream handling
+                    const enriched = enrich429(peekBody, upstream.headers);
+                    if (!(cliAvailable && !useCli)) {
+                        const responseHeaders = {
+                            'Content-Type': 'application/json',
+                            'Access-Control-Allow-Origin': corsOrigin,
+                            ...SECURITY_HEADERS,
+                        };
+                        for (const [key, value] of upstream.headers.entries()) {
+                            if (key.startsWith('x-ratelimit') || key.startsWith('anthropic-ratelimit') || key === 'request-id') {
+                                responseHeaders[key] = value;
+                            }
+                        }
+                        requestCount++;
+                        res.writeHead(429, responseHeaders);
+                        res.end(enriched);
+                        return;
+                    }
+                    // Fall through to CLI fallback below
+                }
+            }
             // Enrich 429 errors with rate limit details from headers (Anthropic only returns "Error")
             if (upstream.status === 429 && !(cliAvailable && !useCli)) {
                 const errBody = await upstream.text().catch(() => '');

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@askalf/dario",
-  "version": "3.2.4",
+  "version": "3.2.5",
   "description": "Use your Claude subscription as an API. No API key needed. Local proxy for Claude Max/Pro subscriptions.",
   "type": "module",
   "bin": {