@askalf/dario 2.8.5 → 2.8.7

package/README.md

@@ -68,7 +68,7 @@ Opus, Sonnet, Haiku — all models, streaming, tool use. Works with Cursor, Cont
 <tr>
 <td colspan="3" valign="top">
 
-*"The 429s were driving us crazy running a multi-agent stack on Claude Max — the CLI fallback was duct tape until you found the real fix. Billing tag in the system prompt is wild. v2.8.0 running clean, zero 429s."* — [@belangertrading](https://github.com/belangertrading), multi-agent stack on Claude Max
+*"The 429s were driving us crazy running a multi-agent stack on Claude Max. You found the billing tag, fixed the checksum, reverse-engineered the per-request hash from the binary — v2.8.5 running clean, zero reclassification."* — [@belangertrading](https://github.com/belangertrading), multi-agent stack on Claude Max
 
 </td>
 </tr>
@@ -80,7 +80,7 @@ Opus, Sonnet, Haiku — all models, streaming, tool use. Works with Cursor, Cont
 
 Most Claude subscription proxies have a critical billing problem: **Anthropic classifies their requests as third-party and routes all usage to Extra Usage billing** — even when you have Max plan limits available. You're paying for your subscription twice.
 
-dario is the only proxy that solves this. It injects native Claude Code device identity, billing classification tags, and priority routing into every request — so Anthropic's billing system treats your requests exactly like Claude Code itself. Your Max plan limits work correctly, and Opus/Sonnet stay available even at high utilization.
+dario is the only proxy that solves this. It injects native Claude Code device identity, per-request billing checksums (reverse-engineered from the Claude Code binary), and priority routing into every request — so Anthropic's billing system treats your requests exactly like Claude Code itself. Your Max plan limits work correctly, and Opus/Sonnet stay available even at high utilization.
 
 | | dario | Other proxies |
 |---|---|---|
@@ -88,6 +88,7 @@ dario is the only proxy that solves this. It injects native Claude Code device i
 | **Max plan limits** | Used correctly | Bypassed — billed separately |
 | **Device identity** | Injected automatically | Missing |
 | **Priority routing** | Billing tag + service_tier auto | Missing |
+| **Billing tag fingerprint** | Per-request SHA-256 matching binary RE | Static or missing |
 | **Beta flags** | Match Claude Code v2.1.100 | Outdated or missing |
 | **Billable beta filtering** | Strips surprise charges | Passes everything through |
 
@@ -415,7 +416,7 @@ Then run `hermes` normally — it routes through dario using your Claude subscri
 
 ### Direct API Mode
 - All Claude models (Opus 4.6, Sonnet 4.6, Haiku 4.5) + 1M extended context aliases (`opus1m`, `sonnet1m`)
-- **Native billing classification** — device identity metadata ensures Max plan limits work correctly
+- **Native billing classification** — device identity, per-request billing tag with SHA-256 checksums matching real Claude Code (extracted via binary RE), ensures Max plan limits work correctly
 - **Priority routing** — billing tag injection + `service_tier: 'auto'` activates per-model rate limits, keeping Opus/Sonnet available even at 100% overall utilization
 - **Adaptive thinking** — matches Claude Code's `{ type: 'adaptive' }` mode for optimal reasoning (auto-skipped for Haiku 4.5)
 - **Effort control** — injects `output_config: { effort: 'high' }` by default, or passes through client-specified effort level
@@ -585,7 +586,7 @@ npm run dev   # runs with tsx (no build needed)
 | Who | Contributions |
 |-----|---------------|
 | [@GodsBoy](https://github.com/GodsBoy) | Proxy authentication, token redaction, error sanitization ([#2](https://github.com/askalf/dario/pull/2)) |
-| [@belangertrading](https://github.com/belangertrading) | Billing classification investigation ([#4](https://github.com/askalf/dario/issues/4)), Opus/Sonnet 429 diagnosis + CLI fallback workaround ([#6](https://github.com/askalf/dario/issues/6)) |
+| [@belangertrading](https://github.com/belangertrading) | Billing classification investigation ([#4](https://github.com/askalf/dario/issues/4)), Opus/Sonnet 429 diagnosis + CLI fallback workaround ([#6](https://github.com/askalf/dario/issues/6)), billing reclassification root cause ([#7](https://github.com/askalf/dario/issues/7)) |
 
 ## Also by AskAlf
 

package/dist/proxy.js

@@ -1,10 +1,10 @@
 import { createServer } from 'node:http';
-import { randomUUID, timingSafeEqual, createHash } from 'node:crypto';
+import { randomUUID, randomBytes, timingSafeEqual, createHash } from 'node:crypto';
 import { execSync, spawn } from 'node:child_process';
 import { readFileSync, readdirSync, writeFileSync, unlinkSync } from 'node:fs';
 import { join } from 'node:path';
 import { homedir, tmpdir } from 'node:os';
-import { arch, platform, version as nodeVersion } from 'node:process';
+import { arch, platform } from 'node:process';
 import { getAccessToken, getStatus } from './oauth.js';
 const ANTHROPIC_API = 'https://api.anthropic.com';
 const DEFAULT_PORT = 3456;
@@ -43,12 +43,10 @@ function computeBuildTag(userMessage, version) {
     const chars = [4, 7, 20].map(i => userMessage[i] || '0').join('');
     return createHash('sha256').update(`${BILLING_SEED}${chars}${version}`).digest('hex').slice(0, 3);
 }
-// Compute per-request cch checksum matching Claude Code's algorithm:
-// SHA-256(seed + chars[4,7,20] of user message + version).slice(0,5)
-// Real Claude Code uses a similar but separate computation that produces 5 hex chars
-function computeCch(userMessage, version) {
-    const chars = [4, 7, 20].map(i => userMessage[i] || '0').join('');
-    return createHash('sha256').update(`${BILLING_SEED}${version}${chars}`).digest('hex').slice(0, 5);
+// Per-request cch: real Claude Code generates a random 5-char hex value each request.
+// Confirmed via MITM: 10 identical requests → 10 unique cch values, no deterministic pattern.
+function computeCch() {
+    return randomBytes(3).toString('hex').slice(0, 5);
 }
 // Detect installed Claude Code binary at startup (single exec for both version + availability)
 let cliAvailable = false;
@@ -512,7 +510,8 @@ export async function startProxy(opts = {}) {
         'x-stainless-package-version': '0.81.0',
         'x-stainless-retry-count': '0',
         'x-stainless-runtime': 'node',
-        'x-stainless-runtime-version': nodeVersion,
+        // Claude Code runs on Bun which reports v24.3.0 as Node compat version
+        'x-stainless-runtime-version': 'v24.3.0',
     };
     const useCli = opts.cliBackend ?? false;
     let requestCount = 0;
@@ -686,18 +685,15 @@ export async function startProxy(opts = {}) {
                         const supportsThinking = !modelName.includes('haiku');
                         if (supportsThinking && !r.thinking) {
                             r.thinking = { type: 'adaptive' };
-                            // Ensure max_tokens is reasonable for thinking models
-                            const clientMax = r.max_tokens || 8192;
-                            r.max_tokens = Math.max(clientMax, 16000);
                         }
-                        // Request priority capacity when available
-                        if (!r.service_tier) {
-                            r.service_tier = 'auto';
+                        // Match Claude Code's default max_tokens (64000) when client sends low values
+                        if (!r.max_tokens || r.max_tokens < 16000) {
+                            r.max_tokens = 64000;
                         }
-                        // Set reasoning effort (pass through client value or default)
+                        // Set reasoning effort (pass through client value or default to 'medium' matching Claude Code)
                         // Haiku does not support the effort parameter
                         if (supportsThinking && !r.output_config) {
-                            r.output_config = { effort: 'high' };
+                            r.output_config = { effort: 'medium' };
                         }
                         // Enable context management (matches Claude Code default)
                         // Requires thinking to be enabled — skip for models without thinking support (e.g. Haiku)
@@ -714,24 +710,39 @@ export async function startProxy(opts = {}) {
                         // as the real Claude Code binary (Oz$ function):
                         // - build tag = SHA-256(seed + msg_chars[4,7,20] + version).slice(0,3)
                         // - cch = SHA-256(seed + version + msg_chars[4,7,20]).slice(0,5)
+                        // Build per-request billing tag matching Claude Code binary
                         const userMsg = extractFirstUserMessage(r);
                         const buildTag = computeBuildTag(userMsg, cliVersion);
-                        const cch = computeCch(userMsg, cliVersion);
+                        const cch = computeCch();
                         const fullVersion = `${cliVersion}.${buildTag}`;
                         const billingTag = `x-anthropic-billing-header: cc_version=${fullVersion}; cc_entrypoint=cli; cch=${cch};`;
+                        // Structure system prompt as 3 blocks matching real Claude Code:
+                        // [0] billing tag (no cache_control)
+                        // [1] agent identity string (cache 1h)
+                        // [2] actual system prompt (cache 1h)
+                        const AGENT_IDENTITY = 'You are a Claude agent, built on Anthropic\'s Claude Agent SDK.';
+                        const CACHE_1H = { type: 'ephemeral', ttl: '1h' };
                         if (typeof r.system === 'string') {
                             if (!r.system.includes('x-anthropic-billing-header:')) {
-                                r.system = billingTag + '\n' + r.system;
+                                r.system = [
+                                    { type: 'text', text: billingTag },
+                                    { type: 'text', text: AGENT_IDENTITY, cache_control: CACHE_1H },
+                                    { type: 'text', text: r.system, cache_control: CACHE_1H },
+                                ];
                             }
                         }
                         else if (Array.isArray(r.system)) {
                             const hasTag = r.system.some(b => typeof b.text === 'string' && b.text.includes('x-anthropic-billing-header:'));
                             if (!hasTag) {
-                                r.system.unshift({ type: 'text', text: billingTag });
+                                // Prepend billing tag and agent identity before existing blocks
+                                r.system.unshift({ type: 'text', text: billingTag }, { type: 'text', text: AGENT_IDENTITY, cache_control: CACHE_1H });
                             }
                         }
                         else {
-                            r.system = billingTag;
+                            r.system = [
+                                { type: 'text', text: billingTag },
+                                { type: 'text', text: AGENT_IDENTITY, cache_control: CACHE_1H },
+                            ];
                         }
                     }
                     finalBody = Buffer.from(JSON.stringify(r));
@@ -752,8 +763,8 @@ export async function startProxy(opts = {}) {
                     beta += ',' + clientBeta;
             }
             else {
-                // Claude-optimized: full beta set matching CLI v2.1.100
-                beta = 'oauth-2025-04-20,interleaved-thinking-2025-05-14,context-management-2025-06-27,prompt-caching-scope-2026-01-05,claude-code-20250219,advisor-tool-2026-03-01,effort-2025-11-24';
+                // Claude-optimized: full beta set matching real Claude Code (exact order from MITM capture)
+                beta = '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';
                 if (clientBeta) {
                     const filtered = filterBillableBetas(clientBeta);
                     if (filtered)
@@ -765,7 +776,6 @@ export async function startProxy(opts = {}) {
                 'Authorization': `Bearer ${accessToken}`,
                 'anthropic-version': req.headers['anthropic-version'] || '2023-06-01',
                 'anthropic-beta': beta,
-                'x-client-request-id': randomUUID(),
                 // Real Claude Code sends 600 on first request, 300 on subsequent
                 'x-stainless-timeout': requestCount <= 1 ? '600' : '300',
             };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@askalf/dario",
-  "version": "2.8.5",
+  "version": "2.8.7",
   "description": "Use your Claude subscription as an API. No API key needed. Local proxy for Claude Max/Pro subscriptions.",
   "type": "module",
   "bin": {