ParthSareen dd74829c27 x: add experimental agent loop with tool approval ... Add `--experimental` / `--beta` flag to enable an agent loop that allows LLMs to use tools (bash, web_search) with interactive user approval. Features: - Built-in tools: bash command execution, web search via Ollama API - Interactive approval UI with arrow key navigation - Auto-allowlist for safe commands (pwd, git status, npm run, etc.) - Denylist for dangerous patterns (rm -rf, sudo, credential access) - Prefix-based allowlist for approved directories (cat src/ approves cat src/*) - Warning box for commands targeting paths outside project directory Architecture: - x/tools/: Tool registry, bash executor, web search client - x/agent/: Approval manager with TUI selector - x/cmd/: Agent loop orchestration The readline change fixes a stdin race condition where background goroutine consumption caused double-keypress issues in the approval UI.		2026-01-05 21:53:46 -08:00
..
bench	cmd/bench: fix binary name in README (#13276)	2025-12-10 14:16:58 -08:00
runner	Runner for Ollama engine	2025-02-13 17:09:26 -08:00
cmd.go	x: add experimental agent loop with tool approval	2026-01-05 21:53:46 -08:00
cmd_test.go	add REQUIRES command to Modelfile (#13361)	2025-12-18 13:21:29 -08:00
interactive.go	x: add experimental agent loop with tool approval	2026-01-05 21:53:46 -08:00
interactive_test.go	server: add webp image input support (#10653)	2025-05-12 20:41:42 -07:00
start.go	nolintlint	2024-06-04 11:13:30 -07:00
start_darwin.go	mac: handle "keep" named apps (#11031)	2025-06-09 16:29:57 -07:00
start_default.go	lint	2024-08-01 17:06:06 -07:00
start_windows.go	spawn desktop quickly (#11011)	2025-06-08 09:34:52 -07:00
warn_thinking_test.go	add thinking support to the api and cli (#10584)	2025-05-28 19:38:52 -07:00