feat(ponytail): introduce "Ponytail" feature for minimalistic code generation

README.md

@@ -409,6 +409,7 @@ Default URLs:
 | 🚀 **RTK Token Saver** ([RTK](https://github.com/rtk-ai/rtk) ⭐40K) | Compress tool outputs (`git diff`, `grep`, `ls`, `tree`...) before sending to LLM | Save **20-40% input tokens** per request |
 | 🧠 **Headroom Token Saver** ([Headroom](https://github.com/chopratejas/headroom)) | Optional external `/v1/compress` proxy before provider routing | Save more context tokens without changing clients |
 | 🪨 **Caveman Mode** ([Caveman](https://github.com/JuliusBrussee/caveman) ⭐52K) | Inject caveman-speak prompt → LLM replies terse, technical substance preserved | Save **up to 65% output tokens** |
+| 🐴 **Ponytail** ([Ponytail](https://github.com/DietrichGebert/ponytail)) | Inject "lazy senior dev" prompt → LLM writes minimal, YAGNI-first code (Lite/Full/Ultra) | **Fewer output tokens, less refactoring** |
 | 🎯 **Smart 3-Tier Fallback** | Auto-route: Subscription → Cheap → Free | Never stop coding, zero downtime |
 | 📊 **Real-Time Quota Tracking** | Live token count + reset countdown | Maximize subscription value |
 | 🔄 **Format Translation** | OpenAI ↔ Claude ↔ Gemini ↔ Cursor ↔ Kiro ↔ Vertex | Works with any CLI tool |
@@ -467,6 +468,21 @@ http://host.docker.internal:8787
 
 If Headroom is down or returns an error, 9Router fails open and sends the original request.
 
+### 🐴 Ponytail (Lazy Senior Dev)
+
+Ponytail injects a *"lazy senior dev"* system prompt into every request, biasing the LLM toward minimal, YAGNI-first code — deletion over addition, stdlib over new deps, one-liners over abstractions. Adapted from [DietrichGebert/ponytail](https://github.com/DietrichGebert/ponytail).
+
+- **Lite** — Build what's asked, name the lazier alternative.
+- **Full** — YAGNI ladder enforced: stdlib → native → existing deps → one-liner → minimal code.
+- **Ultra** — YAGNI extremist: deletion first, ship the one-liner, challenge the rest of the requirement in the same response.
+
+```
+Without Ponytail: verbose code, extra abstractions, "just in case" scaffolding
+With Ponytail:    shortest working diff, no unrequested abstractions, fewer tokens
+```
+
+Never trades away: input validation, error handling that prevents data loss, security, accessibility, or anything explicitly requested. Enable in Dashboard → Endpoint → Ponytail. Stacks with Caveman (output terseness) and RTK (input compression).
+
 ### 🎯 Smart 3-Tier Fallback
 
 Create combos with automatic fallback:
@@ -1348,6 +1364,7 @@ Built on the shoulders of giants:
 - **[CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI)** — original Go implementation that inspired this JavaScript port.
 - **[RTK](https://github.com/rtk-ai/rtk)** ![Stars](https://img.shields.io/github/stars/rtk-ai/rtk?style=flat&color=yellow) — Rust token-saver. 9Router ports its compression pipeline to JS → **−20-40% input tokens** on every request.
 - **[Caveman](https://github.com/JuliusBrussee/caveman)** ![Stars](https://img.shields.io/github/stars/JuliusBrussee/caveman?style=flat&color=yellow) by **[@JuliusBrussee](https://github.com/JuliusBrussee)** — viral *"why use many token when few token do trick"*. 9Router adapts its prompt → **−65% output tokens**.
+- **[Ponytail](https://github.com/DietrichGebert/ponytail)** ![Stars](https://img.shields.io/github/stars/DietrichGebert/ponytail?style=flat&color=yellow) by **[@DietrichGebert](https://github.com/DietrichGebert)** — *"lazy senior dev"* skill. 9Router injects its YAGNI-first ladder → **fewer tokens, less code, shorter diffs**.
 
 Huge thanks to these authors — without their work, 9Router's token-saving features wouldn't exist. ⭐ them on GitHub!
 

cli/hooks/sqliteRuntime.js

@@ -7,6 +7,7 @@ const os = require("os");
 const path = require("path");
 
 const BETTER_SQLITE3_VERSION = "12.6.2";
+const SQL_JS_VERSION = "1.14.1";
 
 function getDataDir() {
   if (process.env.DATA_DIR) return process.env.DATA_DIR;
@@ -102,20 +103,36 @@ function npmInstall(pkgs, opts = {}) {
 }
 
 // Public: ensure better-sqlite3 native module is installed in user-writable
-// runtime dir. sql.js is bundled in bin/app already; node:sqlite is built-in.
+// runtime dir. sql.js may be bundled in bin/app, but npm publish strips .wasm
-// This is purely a *speed optimization* — app works without it via fallbacks.
+// from nested node_modules — verify and reinstall if missing. node:sqlite is
+// built-in. This is purely a *speed optimization* — app works without
+// better-sqlite3 via fallbacks.
+function isSqlJsWasmValid() {
+  const bundledWasm = path.join(__dirname, "..", "app", "node_modules", "sql.js", "dist", "sql-wasm.wasm");
+  if (fs.existsSync(bundledWasm)) return true;
+  const runtimeWasm = path.join(getRuntimeNodeModules(), "sql.js", "dist", "sql-wasm.wasm");
+  return fs.existsSync(runtimeWasm);
+}
+
 function ensureSqliteRuntime({ silent = false } = {}) {
   ensureRuntimeDir();
 
+  let sqlJsOk = isSqlJsWasmValid();
+  if (!sqlJsOk) {
+    sqlJsOk = npmInstall([`sql.js@${SQL_JS_VERSION}`], { silent });
+    if (sqlJsOk) sqlJsOk = isSqlJsWasmValid();
+  }
+
   const needBetterSqlite = !hasModule("better-sqlite3") || !isBetterSqliteBinaryValid();
   if (!needBetterSqlite) {
     if (!silent) console.log("✅ SQLite engine ready");
-    return { betterSqlite: true };
+    return { betterSqlite: true, sqlJs: sqlJsOk };
   }
 
   const ok = npmInstall([`better-sqlite3@${BETTER_SQLITE3_VERSION}`], { optional: true, silent });
   return {
     betterSqlite: ok && hasModule("better-sqlite3") && isBetterSqliteBinaryValid(),
+    sqlJs: sqlJsOk,
   };
 }
 

open-sse/translator/formats/claude.js

@@ -4,6 +4,7 @@ import { ROLE, CLAUDE_BLOCK } from "../schema/index.js";
 import { adjustMaxTokens } from "./maxTokens.js";
 import { applyCloaking } from "../../utils/claudeCloaking.js";
 import { resolveSessionId } from "../../utils/sessionManager.js";
+import { isValidClaudeSignature } from "../../utils/claudeSignature.js";
 import { PROVIDERS } from "../../providers/index.js";
 import { getCapabilitiesForModel } from "../../providers/capabilities.js";
 import { DEFAULT_MAX_TOKENS } from "../../config/runtimeConfig.js";
@@ -213,14 +214,26 @@ export function prepareClaudeRequest(body, provider = null, apiKey = null, conne
           let hasToolUse = false;
           let hasThinking = false;
 
-          // Always replace signature for all thinking blocks
+          // Claude native: preserve valid signatures, drop invalid blocks.
+          // anthropic-compatible: replace with default (safe fallback for lenient upstreams).
+          const isClaudeNative = provider === "claude";
+          const kept = [];
           for (const block of msg.content) {
-            if (block.type === CLAUDE_BLOCK.THINKING || block.type === CLAUDE_BLOCK.REDACTED_THINKING) {
+            const isThinking = block.type === CLAUDE_BLOCK.THINKING || block.type === CLAUDE_BLOCK.REDACTED_THINKING;
-              block.signature = DEFAULT_THINKING_CLAUDE_SIGNATURE;
+            if (isThinking) {
               hasThinking = true;
+              if (isClaudeNative) {
+                if (isValidClaudeSignature(block.signature)) kept.push(block);
+              } else {
+                block.signature = DEFAULT_THINKING_CLAUDE_SIGNATURE;
+                kept.push(block);
+              }
+              continue;
             }
             if (block.type === CLAUDE_BLOCK.TOOL_USE) hasToolUse = true;
+            kept.push(block);
           }
+          msg.content = kept;
 
           // Add thinking block if thinking enabled + has tool_use but no thinking
           if (thinkingEnabled && !hasThinking && hasToolUse) {

open-sse/utils/claudeSignature.js

@@ -0,0 +1,41 @@
+// Claude thinking signature validation (ported from CLIProxyAPI internal/signature).
+// E-form: single-layer base64, decoded[0] == 0x12 (Claude marker).
+// R-form: double-layer base64, outer decoded[0] == 'E', inner decoded[0] == 0x12.
+// Cache prefix "...#sig" stripped before validation.
+
+const MAX_CLAUDE_SIGNATURE_LEN = 32 * 1024 * 1024;
+const CLAUDE_SIGNATURE_MARKER = 0x12;
+
+function stripCachePrefix(rawSignature) {
+  const sig = (rawSignature || "").trim();
+  if (!sig) return "";
+  const idx = sig.indexOf("#");
+  return idx >= 0 ? sig.slice(idx + 1).trim() : sig;
+}
+
+export function hasClaudeSignaturePrefix(rawSignature) {
+  const sig = stripCachePrefix(rawSignature);
+  return sig.length > 0 && (sig[0] === "E" || sig[0] === "R");
+}
+
+// Strict-ish: validates base64 layers + Claude marker byte.
+export function isValidClaudeSignature(rawSignature) {
+  const sig = stripCachePrefix(rawSignature);
+  if (!sig || sig.length > MAX_CLAUDE_SIGNATURE_LEN) return false;
+
+  try {
+    if (sig[0] === "E") {
+      const decoded = Buffer.from(sig, "base64");
+      return decoded.length > 0 && decoded[0] === CLAUDE_SIGNATURE_MARKER;
+    }
+    if (sig[0] === "R") {
+      const outer = Buffer.from(sig, "base64");
+      if (!outer.length || outer[0] !== 0x45) return false; // 'E'
+      const inner = Buffer.from(outer.toString(), "base64");
+      return inner.length > 0 && inner[0] === CLAUDE_SIGNATURE_MARKER;
+    }
+    return false;
+  } catch {
+    return false;
+  }
+}