feat: Configurable security settings and improved output formatting#27
Closed
alexx-ftw wants to merge 1 commit intoRichardAtCT:mainfrom
Closed
feat: Configurable security settings and improved output formatting#27alexx-ftw wants to merge 1 commit intoRichardAtCT:mainfrom
alexx-ftw wants to merge 1 commit intoRichardAtCT:mainfrom
Conversation
## Security Configuration - Add DISABLE_SECURITY_PATTERNS env var to disable dangerous pattern validation (allows pipes, redirections, etc. for trusted environments) - Add DISABLE_TOOL_VALIDATION env var to allow all Claude tools (bypasses tool allowlist for unrestricted access) - Add SHOW_TOOL_DETAILS env var to control detailed tool output in responses - Security options default to OFF (secure by default) ## Bug Fixes - Fix /new command to properly clear ALL user sessions (previously only cleared current directory session) - Fix session_manager access path (via claude_integration) - Fix claude_cli_path usage instead of deprecated claude_binary_path ## Output Improvements - Add real-time tool call display during execution - Add detailed tool results in final responses - Add tool usage summary at end of responses - Improve formatting of tool inputs and outputs - Better handling of Task subagent results Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Owner
|
Hey @alexx-ftw - I have implemented most/all of the output formatting change in #29. Would you be interested in creating a new PR with just the security config changes? |
Contributor
Author
|
This PR has been split as requested into focused PRs:
Closing #27 in favor of those scoped PRs. |
Contributor
Author
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR introduces configurable security settings and significantly improves the output formatting for tool usage in agentic mode.
Security Configuration (via Environment Variables)
DISABLE_SECURITY_PATTERNS: When set toTrue, disables dangerous pattern validation (pipes, redirections, shell operators, etc.) for trusted environmentsDISABLE_TOOL_VALIDATION: When set toTrue, allows all Claude tools without restrictionSHOW_TOOL_DETAILS: Controls whether detailed tool call information is shown in responses (default:True)These settings allow administrators to relax security restrictions in trusted environments while maintaining the default secure-by-default behavior.
Output Formatting Improvements
Bug Fixes
/newcommand not properly clearing all user sessions - now correctly accesses the session manager through the Claude integration facadeclaude_cli_pathover default binary pathFiles Changed
src/config/settings.py- Added new security configuration fieldssrc/security/validators.py- Made dangerous patterns configurablesrc/claude/monitor.py- Made tool validation configurablesrc/claude/integration.py- Fixed CLI path resolutionsrc/bot/orchestrator.py- Fixed session clearing, improved output formattingsrc/main.py- Pass security config to validators