hermes-agent/scripts
Brooklyn Nicholson ac22580ae0 test(gateway): prove the GUI-tool fix against a real remote backend
The in-process check only showed the resolver branches. This launches
`hermes serve` with HERMES_DESKTOP scrubbed from its environment — what a
URL-token or cloud backend actually looks like — and asks it over the same
WebSocket the desktop app uses which tools each session's agent resolved.

Fails on the pre-fix tree (desktop gui=[]), passes after (all six).
2026-08-06 21:17:09 -05:00
..
ci
lib
observability
sandbox
tests
toolperf_abeval
whatsapp-bridge
LIVETEST_README.md
add_contributor.py
analyze_livetest.py
audit_pr_attribution.py
benchmark_browser_eval.py
build_model_catalog.py
build_skills_index.py
capture-cage-terminal.sh
check-windows-footguns.py
check_subprocess_stdin.py
contributor_audit.py
dev-sandbox.sh
discord-voice-doctor.py
docker_config_migrate.py
docker_rebootstrap_nous_session.py
generate_conformance_vectors.py
hermes-gateway
install.cmd
install.ps1
install.sh
install_psutil_android.py
iso-certify.py
keystroke_diagnostic.py
kill_modal.sh
lint_diff.py
micro_compaction_report.py
probe_remote_gui_tools.py
profile-tui.py
release.py
run_tests.sh
run_tests_parallel.py
sample_and_compress.py
smoke_nemo_relay_shared_metrics.py
tool_search_livetest.py
tool_search_livetest2.py
tool_search_livetest_ue.py
tool_search_livetest_ue_disc.py
tool_search_livetest_ue_hard.py