iSH perl tested

README.md

@@ -2,7 +2,7 @@
 
 ## About
 
-Bantam is a minimalist, dependency-free AI agent specification with reference implementations in **Python** (`bantam.py`, ~300 SLOC), **Go** (`main.go` + `term_*.go`, module `code.luxferre.top/luxferre/bantam`), and **Perl 5** (`bantam.pl`, ~300 SLOC). It provides an agentic loop capable of autonomous tool execution, shell interaction, real-time response streaming, Fibonacci backoff network resilience, and subagent delegation using any OpenAI-compatible completions API.
+Bantam is a minimalist, dependency-free AI agent specification with reference implementations in **Python** (`bantam.py`, ~280 SLOC), **Go** (`main.go` + `term_*.go`, module `code.luxferre.top/luxferre/bantam`), and **Perl 5** (`bantam.pl`, ~360 SLOC). It provides an agentic loop capable of autonomous tool execution, shell interaction, real-time response streaming, Fibonacci backoff network resilience, and subagent delegation using any OpenAI-compatible completions API.
 
 The entire philosophy of Bantam is built upon two principles:
 
@@ -175,6 +175,12 @@ Same philosophy as the Pi agent: there's nothing a simple chroot environment can
 
 You can pair Bantam with the [Dynagate](https://code.luxferre.top/luxferre/dynagate) LLM gateway to achieve all that.
 
+### How to run on mobiles?
+
+On Android, any current Bantam implementation is easily runnable within the Termux environment. Go implementation is preferred for performance reasons.
+
+On iOS/iPadOS, the easiest way to use Bantam is to run the Perl version inside iSH. Some terminal features may not be available, but the agent itself is fully functional.
+
 ## Credits
 
 Created by Luxferre in 2026, released into the public domain with no warranties.

bantam.pl

@@ -45,7 +45,7 @@ sub col {
 sub get_cfg {
   my ($path) = @_;
   $path //= 'model.cfg';
-  my %d = (endpoint => 'https://opencode.ai/zen/v1', model => 'deepseek-v4-flash-free', temperature => '0.7', api_key => '-', timeout => '300', shell_timeout => '120', max_al_iterations => '1000', stream => 'true', color => 'auto');
+  my %d = (endpoint => 'https://opencode.ai/zen/v1', model => 'big-pickle', temperature => '0.7', api_key => '-', timeout => '300', shell_timeout => '120', max_al_iterations => '1000', stream => 'true', color => 'auto');
   if (-f $path) {
     open my $fh, '<:encoding(UTF-8)', $path or die "Cannot open $path: $!";
     while (my $ln = <$fh>) {