lightpanda (#646)

* lightpanda

* lightpanda benchmarks

* improvements

* fixes

* improvements
This commit is contained in:
Chris Tate
2026-03-06 11:16:37 -06:00
committed by GitHub
parent 36c2e06f89
commit 0da54c7038
25 changed files with 2190 additions and 74 deletions
+1
View File
@@ -495,6 +495,7 @@ This is useful for multimodal AI models that can reason about visual layout, unl
| `--action-policy <path>` | Path to action policy JSON file (or `AGENT_BROWSER_ACTION_POLICY` env) |
| `--confirm-actions <list>` | Action categories requiring confirmation (or `AGENT_BROWSER_CONFIRM_ACTIONS` env) |
| `--confirm-interactive` | Interactive confirmation prompts; auto-denies if stdin is not a TTY (or `AGENT_BROWSER_CONFIRM_INTERACTIVE` env) |
| `--engine <name>` | Browser engine: `chrome` (default), `lightpanda`; implies `--native` (or `AGENT_BROWSER_ENGINE` env) |
| `--native` | [Experimental] Use native Rust daemon instead of Node.js (or `AGENT_BROWSER_NATIVE` env) |
| `--config <path>` | Use a custom config file (or `AGENT_BROWSER_CONFIG` env) |
| `--debug` | Debug output |