feat(bashkit): Phase 7 - Resource limits for sandboxing

[chaliy]

Summary

• Add ExecutionLimits struct for configuring sandboxing limits
• Add ExecutionCounters struct for tracking resource usage
• Integrate limits into interpreter for command count, loop iterations, and function depth
• Add LimitExceeded error type for limit violations
• Add comprehensive integration tests for limit enforcement

Resource Limits

Limit	Default	Purpose
max_commands	10,000	Total commands per execution (fuel model)
max_loop_iterations	10,000	Maximum iterations per loop
max_function_depth	100	Maximum recursion depth
timeout	30s	Execution timeout (not yet enforced)

Usage

let limits = ExecutionLimits::new()
    .max_commands(100)
    .max_loop_iterations(50)
    .max_function_depth(10);

let mut bash = Bash::builder()
    .limits(limits)
    .build();

Test plan

• Unit tests for ExecutionLimits builder pattern
• Unit tests for ExecutionCounters tick/push/pop
• Integration test: command limit enforcement
• Integration test: loop iteration limit enforcement
• Integration test: function depth limit enforcement
• Integration test: default limits allow normal scripts
• All 118 tests pass
• Clippy clean

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.
To continue using code reviews, you can upgrade your account or add credits to your account and enable them for code reviews in your settings.