* fix(tui-clipboard): skip native safety net on OSC52-capable terminals
On terminals with first-class OSC 52 support (Ghostty, kitty, WezTerm,
Windows Terminal, VS Code), setClipboard() currently fires both OSC 52
AND a parallel native-tool write (wl-copy / xclip / pbcopy). On Wayland
+ wl-copy this corrupts the clipboard: probeLinuxCopy() runs wl-copy
with empty stdin as an existence check (destructive — wipes clipboard
to empty string), and the subsequent real wl-copy invocation races
OSC 52 plus its own daemon's previous SIGTERM.
Symptom: user on Arch + Ghostty + wl-copy (Wayland, no tmux, no SSH)
had to press Ctrl+Shift+C three times before a selection landed.
env -u WAYLAND_DISPLAY -u DISPLAY HERMES_TUI_FORCE_OSC52=1 (which
short-circuits copyNative via the DISPLAY-absent early-return) made
every copy work instantly — proving OSC 52 alone is sufficient on
Ghostty and that copyNative() is actively destructive there.
Add OSC52_CAPABLE_TERMINALS allowlist to terminal.ts (same pattern as
the existing EXTENDED_KEYS_TERMINALS), and gate copyNative() on the
terminal NOT being on it. The native safety net continues to fire on
unrecognised terminals (xterm, GNOME Terminal, Konsole, Terminal.app,
etc.) where OSC 52 is less reliable.
* fix(tui-clipboard): address Copilot review feedback
- Move OSC52_CAPABLE_TERMINALS + supportsOsc52Clipboard() from
ink/terminal.ts to utils/env.ts. ink/terminal.ts already imports
link from ink/termio/osc.ts; importing back into termio/osc.ts
introduced a circular dependency. utils/env.ts has no deps on
either file and already owns terminal detection (detectTerminal()),
so the helper sits naturally next to it.
- Replace the inline gating (!SSH_CONNECTION && !supportsOsc52Clipboard())
with a pure shouldUseNativeClipboard(env, terminal) helper. The old
expression skipped native on allowlisted terminals even when
setClipboard() wouldn't actually emit OSC 52 (e.g. inside
TMUX/STY where we use tmux load-buffer instead, or when the user
has set HERMES_TUI_FORCE_OSC52=0). That made the clipboard write
a no-op in those configurations. The new helper:
1. SSH_CONNECTION set -> false (existing behaviour)
2. TMUX or STY set -> true (we go through load-buffer, no race)
3. shouldEmitClipboardSequence() false -> true (native is the
only path left when OSC 52 is suppressed)
4. Otherwise: skip native iff terminal is allowlisted.
- Add 11 tests for shouldUseNativeClipboard covering the SSH guard,
TMUX/STY tmux-inside-Ghostty case, HERMES_TUI_FORCE_OSC52=0
override, allowlisted vs non-allowlisted terminals, precedence,
and default-args smoke. Tests follow the package's existing
parameterised-helper style (no vi.mock; helpers accept env and
terminal as arguments).
- Update test imports to the new utils/env.js path.
* fix(tui-clipboard): address Copilot round 2 feedback
* fix(tui-clipboard): address Copilot round 3 feedback
* fix(tui-clipboard): address Copilot round 4 feedback
Adds an optional dashboard side-process to the container entrypoint,
toggled by `HERMES_DASHBOARD=1` (also accepts `true` / `yes`). When set,
the entrypoint backgrounds `hermes dashboard` before `exec`-ing the main
command so the user's chosen foreground process (gateway, chat, `sleep
infinity`, …) remains PID-of-interest for the container runtime.
docker run -d \
-v ~/.hermes:/opt/data \
-p 8642:8642 -p 9119:9119 \
-e HERMES_DASHBOARD=1 \
nousresearch/hermes-agent gateway run
Defaults chosen for the container case:
- Host: 0.0.0.0 (reachable through published port; can override to
127.0.0.1 via HERMES_DASHBOARD_HOST for sidecar/reverse-proxy setups)
- Port: 9119 (matches `hermes dashboard`)
- Auto-adds `--insecure` when binding to non-localhost, matching the
dashboard's own safety gate for exposing API keys
- HERMES_DASHBOARD_TUI is read by `hermes dashboard` directly — no
entrypoint plumbing needed
Dashboard output is prefixed with `[dashboard]` via `stdbuf`+`sed -u` so
it's easy to separate from gateway logs in `docker logs`. No supervision:
if the dashboard crashes it stays down until the container restarts
(documented in the `:::note` panel).
Other changes bundled in:
- Deprecate GATEWAY_HEALTH_URL / GATEWAY_HEALTH_TIMEOUT env vars in
hermes_cli/web_server.py with a DEPRECATED block comment and a
`.. deprecated::` note on _probe_gateway_health. The feature still
works for this release; it'll be removed alongside the move to a
first-class dashboard config key.
- Rewrite the "Running the dashboard" doc section around the new
single-container pattern. Drops the previously-documented
dashboard-as-its-own-container setup — that pattern relied on the
deprecated env vars for cross-container gateway-liveness detection,
and without them the dashboard would permanently report the gateway
as "not running".
- Collapse the two-service Compose example (gateway + dashboard
container) into a single service with HERMES_DASHBOARD=1. Removes
the now-unnecessary bridge network and `depends_on`.
- Drop the ":::warning" caveat about "Running a dashboard container
alongside the gateway is safe" — that case no longer exists.
`_tui_need_npm_install()` compares the canonical `package-lock.json` against
the hidden `node_modules/.package-lock.json` to decide whether `npm install`
needs to re-run. npm 9 drops the `"peer": true` field from the hidden lock
on dev-deps that are *also* declared as peers (the canonical lock preserves
the dual annotation). That made the check flag 16 packages (`@babel/core`,
`@types/node`, `@types/react`, `@typescript-eslint/*`, `react`, `vite`,
`tsx`, `typescript`, …) as mismatched on every launch, triggering a runtime
`npm install`.
Inside the Docker image, that runtime install then fails with EACCES because
`/opt/hermes/ui-tui/node_modules/` is root-owned from build time, so
`docker run … hermes-agent --tui` prints:
Installing TUI dependencies…
npm install failed.
…and exits 1, with no preview. The empty preview is a second bug: the
launcher captured only stderr, but npm 9 writes EACCES to stdout, which
was DEVNULL'd.
Fixes:
- Add `"peer"` to `_NPM_LOCK_RUNTIME_KEYS` so the comparison ignores the
non-deterministic field, alongside the existing `"ideallyInert"`.
- Capture stdout as well as stderr in the install subprocess so future
failures surface a useful preview instead of a bare "failed." line.
Regression tests:
- `test_no_install_when_only_peer_annotation_differs` — the exact scenario
- `test_install_when_version_differs_even_with_peer_drop` — guards against
the peer-drop tolerance masking a real version skew
On-host impact: the same false-positive was firing on every `hermes --tui`
invocation from a normal checkout, silently running a no-op `npm install`
each time (it converged because the host's `node_modules/` is writable).
Startup time on the TUI should drop noticeably.
Add opt-in terminal.docker_run_as_host_user config flag that passes
--user $(id -u):$(id -g) to the Docker backend so files written into
bind-mounted directories (/workspace, /root, docker_volumes entries) are
owned by the host user instead of root.
When enabled on POSIX platforms, also drops SETUID/SETGID caps since the
container no longer needs gosu/su to switch users. Falls back cleanly on
platforms without os.getuid (e.g. native Windows Docker) with a warning.
Wired through all three config.yaml -> TERMINAL_* env-var bridges:
- cli.py env_mappings (CLI + TUI startup)
- gateway/run.py _terminal_env_map (gateway / messaging platforms)
- hermes_cli/config.py _config_to_env_sync (`hermes config set`)
Also fixes docker_mount_cwd_to_workspace silently failing in gateway
mode -- it was missing from gateway/run.py's _terminal_env_map.
Adds tests/tools/test_terminal_config_env_sync.py to guard against
future drift between the three bridges (same bug class shipped twice
in one month).
Bundled Hermes image won't work with this flag since its entrypoint
expects to start as root for the usermod/gosu hermes flow; works with
the default nikolaik/python-nodejs image and plain Debian/Ubuntu.
Previously the breaker was only cleared when the post-reconnect retry
call itself succeeded (via _reset_server_error at the end of the try
block). If OAuth recovery succeeded but the retry call happened to
fail for a different reason, control fell through to the
needs_reauth path which called _bump_server_error — adding to an
already-tripped count instead of the fresh count the reconnect
justified. With fix#1 in place this would still self-heal on the
next cooldown, but we should not pay a 60s stall when we already
have positive evidence the server is viable.
Move _reset_server_error(server_name) up to immediately after the
reconnect-and-ready-wait block, before the retry_call. The
subsequent retry still goes through _bump_server_error on failure,
so a genuinely broken server re-trips the breaker as normal — but
the retry starts from a clean count (1 after a failure), not a
stale one.
The MCP circuit breaker previously had no path back to the closed
state: once _server_error_counts[srv] reached _CIRCUIT_BREAKER_THRESHOLD
the gate short-circuited every subsequent call, so the only reset
path (on successful call) was unreachable. A single transient
3-failure blip (bad network, server restart, expired token) permanently
disabled every tool on that MCP server for the rest of the agent
session.
Introduce a classic closed/open/half-open state machine:
- Track a per-server breaker-open timestamp in _server_breaker_opened_at
alongside the existing failure count.
- Add _CIRCUIT_BREAKER_COOLDOWN_SEC (60s). Once the count reaches
threshold, calls short-circuit for the cooldown window.
- After the cooldown elapses, the *next* call falls through as a
half-open probe that actually hits the session. Success resets the
breaker via _reset_server_error; failure re-bumps the count via
_bump_server_error, which re-stamps the open timestamp and re-arms
the cooldown.
The error message now includes the live failure count and an
"Auto-retry available in ~Ns" hint so the model knows the breaker
will self-heal rather than giving up on the tool for the whole
session.
Covers tests 1 (half-opens after cooldown) and 2 (reopens on probe
failure); test 3 (cleared on reconnect) still fails pending fix#2.
The MCP circuit breaker in tools/mcp_tool.py has no half-open state and
no reset-on-reconnect behavior, so once it trips after 3 consecutive
failures it stays tripped for the process lifetime. These tests lock
in the intended recovery behavior:
1. test_circuit_breaker_half_opens_after_cooldown — after the cooldown
elapses, the next call must actually probe the session; success
closes the breaker.
2. test_circuit_breaker_reopens_on_probe_failure — a failed probe
re-arms the cooldown instead of letting every subsequent call
through.
3. test_circuit_breaker_cleared_on_reconnect — a successful OAuth
recovery resets the breaker even if the post-reconnect retry
fails (a successful reconnect is sufficient evidence the server
is viable again).
All three currently fail, as expected.
When the dashboard connects to a remote gateway via GATEWAY_HEALTH_URL,
display the URL instead of the remote PID (which is meaningless locally).
Falls back to PID display for local gateways as before.
- Backend: expose gateway_health_url in /api/status response
- Frontend: prefer gateway_health_url over PID in gatewayValue()
- Add truncate + title tooltip for long URLs that overflow the card
- Add min-w-0/overflow-hidden on status cards for proper truncation
- Tests: verify gateway_health_url in remote and no-URL scenarios
* feat: switch managed browser provider from Browserbase to Browser Use
The Nous subscription tool gateway now routes browser automation through
Browser Use instead of Browserbase. This commit:
- Adds managed Nous gateway support to BrowserUseProvider (idempotency
keys, X-BB-API-Key auth header, external_call_id persistence)
- Removes managed gateway support from BrowserbaseProvider (now
direct-only via BROWSERBASE_API_KEY/BROWSERBASE_PROJECT_ID)
- Updates browser_tool.py fallback: prefers Browser Use over Browserbase
- Updates nous_subscription.py: gateway vendor 'browser-use', auto-config
sets cloud_provider='browser-use' for new subscribers
- Updates tools_config.py: Nous Subscription entry now uses Browser Use
- Updates setup.py, cli.py, status.py, prompt_builder.py display strings
- Updates all affected tests to match new behavior
Browserbase remains fully functional for users with direct API credentials.
The change only affects the managed/subscription path.
* chore: remove redundant Browser Use hint from system prompt
* fix: upgrade Browser Use provider to v3 API
- Base URL: api/v2 -> api/v3 (v2 is legacy)
- Unified all endpoints to use native Browser Use paths:
- POST /browsers (create session, returns cdpUrl)
- PATCH /browsers/{id} with {action: stop} (close session)
- Removed managed-mode branching that used Browserbase-style
/v1/sessions paths — v3 gateway now supports /browsers directly
- Removed unused managed_mode variable in close_session
* fix(browser-use): use X-Browser-Use-API-Key header for managed mode
The managed gateway expects X-Browser-Use-API-Key, not X-BB-API-Key
(which is a Browserbase-specific header). Using the wrong header caused
a 401 AUTH_ERROR on every managed-mode browser session create.
Simplified _headers() to always use X-Browser-Use-API-Key regardless
of direct vs managed mode.
* fix(nous_subscription): browserbase explicit provider is direct-only
Since managed Nous gateway now routes through Browser Use, the
browserbase explicit provider path should not check managed_browser_available
(which resolves against the browser-use gateway). Simplified to direct-only
with managed=False.
* fix(browser-use): port missing improvements from PR #5605
- CDP URL normalization: resolve HTTP discovery URLs to websocket after
cloud provider create_session() (prevents agent-browser failures)
- Managed session payload: send timeout=5 and proxyCountryCode=us for
gateway-backed sessions (prevents billing overruns)
- Update prompt builder, browser_close schema, and module docstring to
replace remaining Browserbase references with Browser Use
- Dynamic /browser status detection via _get_cloud_provider() instead
of hardcoded env var checks (future-proof for new providers)
- Rename post_setup key from 'browserbase' to 'agent_browser'
- Update setup hint to mention Browser Use alongside Browserbase
- Add tests: CDP normalization, browserbase direct-only guard,
managed browser-use gateway, direct browserbase fallback
---------
Co-authored-by: rob-maron <132852777+rob-maron@users.noreply.github.com>
_login_nous() was passing pconfig.portal_base_url (hardcoded production
URL) as a fallback when no --portal-url CLI flag was given. This meant
_nous_device_code_login() received a truthy portal_base_url argument
and never reached the env var fallback chain.
Users setting HERMES_PORTAL_BASE_URL or NOUS_PORTAL_BASE_URL in .env
to point at a staging portal were silently ignored — login always went
to production.
Fix: pass None when no CLI flag is provided, letting the downstream
function properly check env vars before falling back to the default.
Fallback chain is now:
1. --portal-url CLI arg
2. HERMES_PORTAL_BASE_URL env var
3. NOUS_PORTAL_BASE_URL env var
4. DEFAULT_NOUS_PORTAL_URL (production)
Same fix applied to inference_base_url for consistency.
- Add missing `from agent.credential_pool import load_pool` import to
auxiliary_client.py (introduced by the credential pool feature in main)
- Thread `args` through `select_provider_and_model(args=None)` so TLS
options from `cmd_model` reach `_model_flow_nous`
- Mock `_require_tty` in test_cmd_model_forwards_nous_login_tls_options
so it can run in non-interactive test environments
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Ben Barclay