diff --git a/README.md b/README.md
index 4922f6f..234c5d5 100644
--- a/README.md
+++ b/README.md
@@ -8,7 +8,7 @@
     <a href="https://www.npmjs.com/package/codeburn"><img src="https://img.shields.io/npm/v/codeburn.svg" alt="npm version" /></a>
     <a href="https://www.npmjs.com/package/codeburn"><img src="https://img.shields.io/npm/dt/codeburn.svg" alt="total downloads" /></a>                                                       
     <a href="https://github.com/getagentseal/codeburn/blob/main/LICENSE"><img src="https://img.shields.io/npm/l/codeburn.svg" alt="license" /></a>                                            
-    <a href="https://github.com/getagentseal/codeburn"><img src="https://img.shields.io/badge/node-%3E%3D22-brightgreen.svg" alt="node version" /></a>                                        
+    <a href="https://github.com/getagentseal/codeburn"><img src="https://img.shields.io/badge/node-%3E%3D20-brightgreen.svg" alt="node version" /></a>                                       
     <a href="https://discord.gg/pJ2DMWvtAx"><img src="https://img.shields.io/badge/discord-join-5865F2?logo=discord&logoColor=white" alt="Discord" /></a>                                     
     <a href="https://github.com/sponsors/iamtoruk"><img src="https://img.shields.io/badge/sponsor-♥-ea4aaa?logo=github" alt="Sponsor" /></a>                                                  
   </p> 
@@ -38,9 +38,9 @@ Everything runs locally. No wrapper, no proxy, no API keys. CodeBurn reads sessi
 
 ## Requirements
 
-- Node.js 22+
+- Node.js 20+
 - At least one supported AI coding tool with session data on disk
-- SQLite-backed providers (Cursor, OpenCode, Goose, Crush, Warp) require Node's built-in `node:sqlite` module
+- For Cursor and OpenCode support, `better-sqlite3` is installed automatically as an optional dependency
 
 ## Install
 
diff --git a/src/models.ts b/src/models.ts
index c4b4a7b..08204c2 100644
--- a/src/models.ts
+++ b/src/models.ts
@@ -173,8 +173,6 @@ const BUILTIN_ALIASES: Record<string, string> = {
   'openclaw-auto':                 'claude-sonnet-4-5',
   'warp-auto-efficient':           'gpt-5.3-codex',
   'warp-auto-powerful':            'claude-opus-4-6',
-  'auto-efficient':                'gpt-5.3-codex',
-  'auto-powerful':                 'claude-opus-4-6',
   'GPT-5.3 Codex (low reasoning)': 'gpt-5.3-codex',
   'GPT-5.3 Codex (medium reasoning)': 'gpt-5.3-codex',
   'GPT-5.3 Codex (high reasoning)': 'gpt-5.3-codex',
diff --git a/src/providers/warp.ts b/src/providers/warp.ts
index 9ee0055..76ff018 100644
--- a/src/providers/warp.ts
+++ b/src/providers/warp.ts
@@ -399,6 +399,8 @@ function createParser(source: SessionSource, seenKeys: Set<string>): SessionPars
             provider: 'warp',
             model,
             inputTokens,
+            // Warp exposes only conversation-level usage totals in these tables,
+            // so we cannot reliably split per-exchange input vs output tokens.
             outputTokens: 0,
             cacheCreationInputTokens: 0,
             cacheReadInputTokens: 0,