3 Commits

Author	SHA1	Message	Date
vikingowl	7851af14a9	refactor(core): remove provider module, migrate to LLMProvider, add client mode handling, improve serialization error handling, update workspace edition, and clean up conditionals and imports	2025-10-12 12:38:55 +02:00
vikingowl	33d11ae223	fix(agent): improve ReAct parser and tool schemas for better LLM compatibility ... - Fix ACTION_INPUT regex to properly capture multiline JSON responses - Changed from stopping at first newline to capturing all remaining text - Resolves parsing errors when LLM generates formatted JSON with line breaks - Enhance tool schemas with detailed descriptions and parameter specifications - Add comprehensive Message schema for generate_text tool - Clarify distinction between resources/get (file read) and resources/list (directory listing) - Include clear usage guidance in tool descriptions - Set default model to llama3.2:latest instead of invalid "ollama" - Add parse error debugging to help troubleshoot LLM response issues The agent infrastructure now correctly handles multiline tool arguments and provides better guidance to LLMs through improved tool schemas. Remaining errors are due to LLM quality (model making poor tool choices or generating malformed responses), not infrastructure bugs. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-10-09 19:43:07 +02:00
vikingowl	9c777c8429	Add extensible tool system with code execution and web search ... Introduces a tool registry architecture with sandboxed code execution, web search capabilities, and consent-based permission management. Enables safe, pluggable LLM tool integration with schema validation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-10-06 18:32:07 +02:00