Module: ClaudeAgentSDK::OptionWarnings

Defined in:
lib/claude_agent_sdk/option_warnings.rb

Overview

Advisory warnings for option combinations that silently change behavior.

Class Method Summary collapse

Class Method Details

.reset! ⇒ Object

Test hook: forget which messages were already emitted.



33
34
35
 
# File 'lib/claude_agent_sdk/option_warnings.rb', line 33

def reset!
  @mutex.synchronize { @emitted.clear }
end

.warn_if_can_use_tool_shadowed(options) ⇒ Object

can_use_tool is only consulted when the CLI's permission ladder lands on "ask". Anything that auto-approves a tool call earlier in the ladder means the callback never runs — so a callback written for security purposes can silently be dead code (real callers have shipped path-jails that never fired because the same tools were listed bare in allowed_tools).

Advisory only (never raises): shadowing can be intentional, e.g. a callback used solely for tools outside allowed_tools. Deliberately silent on permission_mode 'acceptEdits' (it only auto-approves in-cwd file edits, so warning would be a false positive for anyone gating Bash/network/MCP tools) and on real specifiers like "Bash(ls:*)" (they only shadow matching invocations, not the whole tool).



25
26
27
28
29
30
 
# File 'lib/claude_agent_sdk/option_warnings.rb', line 25

def warn_if_can_use_tool_shadowed(options)
  return unless options.can_use_tool

  message = can_use_tool_shadowed_message(options)
  emit(message) if message
end