{
  "slug": "browse-env-local-auto-discovers-debuggable-chrome-instances-c5dd707934e0",
  "title": "browse env local auto-discovers debuggable Chrome instances",
  "tools": [
    "browse"
  ],
  "tags": [
    "agent"
  ],
  "introduced_at": "2026-03-31T00:10:45.322Z",
  "announced_at": "2026-03-31T00:10:45.322Z",
  "effective_at": null,
  "date_basis": "source-publication",
  "status": "unknown",
  "how": {
    "incantation": "When automating in an existing Chrome instance with remote debugging enabled, run `browse env local` to auto-discover and attach; use `--isolated` to launch an isolated browser, a positional CDP target to select a target, or `--ws <port>` with a bare port number. If no debuggable Chrome is found, it falls back to an isolated launch.",
    "gotchas": [
      "Version: 0.4.0",
      "Auto-discovery attaches only to Chrome instances with remote debugging enabled.",
      "When no debuggable Chrome is found, the command falls back to an isolated launch."
    ]
  },
  "why_it_matters": "Run local browser automation against an existing Chrome instance with remote debugging enabled.",
  "before": "Run `browse env local`, which always launches an isolated browser.",
  "sources": [
    "https://github.com/browserbase/stagehand/blob/@browserbasehq/browse-cli@0.6.0/packages/cli/CHANGELOG.md#040"
  ],
  "rank": 0.97055,
  "judge": {
    "publish": true,
    "judge_model": "codex-cli/gpt-6-luna+typesafe/jev-1.13.0",
    "prompt_version": "extract-v7+enrich-v2+judge-v2x3+jev-publish-v1"
  },
  "review_state": "approved",
  "provenance": {
    "run_id": "browsecli-20261017",
    "verdict_id": "browsecli-20261017:browsecli-20261017-0b128d6b685539b0-1:gate",
    "evidence_hash": "eab58c59d259d5486f0606b089e5785db79a4437a3c6f3a7e4ed3fe2d5d91f41"
  },
  "review": {
    "draft_hash": "eede2d99aa29e49557507c8e9f0cdaa0e2d67105dc629d41a0e2ee9109b04150",
    "reviewer": "publication-gate",
    "reviewed_at": "2026-10-07T00:00:00.000Z",
    "decision": "browsecli-20261017:gate",
    "reason": "3 of 3 judge runs approved with p_yes >= 0.9 (mean 0.97 >= 0.9; 2 needed) and Jev gave 0.75 (>= 0.6 needed)."
  }
}