* feat(docker): publish nousresearch/hermes-sandbox:desktop for terminal backends
The terminal backends (docker, modal, daytona, singularity) all default to
nikolaik/python-nodejs:python3.11-nodejs20, a bare Python+Node base. For Bot
Screen, computer_use and the browser to run INSIDE that sandbox instead of on
the gateway host, the sandbox image needs the display stack.
docker/sandbox-desktop.Dockerfile is that base plus:
- the everyday tools it lacked (jq, ripgrep, fd, tmux, less, nano, vim,
zip, rsync, tree, procps, htop, sudo for the base's uid-1000 `pn`)
- the exact package set the Hermes -desktop image installs (TigerVNC,
Xfce components, dbus, xauth, fonts)
- Playwright's headed Chromium (same build as the -desktop image)
- cua-driver 0.28.2 from its pinned release tarball
No Hermes inside; the default user stays root like the base so nothing
changes for people who just switch docker_image. Desktop processes run as
`pn`. 4.27 GB on amd64.
docker.yml gains a `sandbox` variant with its own cache scope and repository
(nousresearch/hermes-sandbox:desktop, :main-desktop, :<release>-desktop);
the docker-integration suite is skipped for it (no Hermes to test) and
docker/sandbox-desktop-smoke.sh runs instead: as `pn`, every launcher and
cua-driver binary resolves, the real launcher.sh publishes :20, the RFB
socket completes the 3.8 handshake relayed over `docker exec -i` stdio, and
a headed Chromium maps a window on that display. hadolint lints the new
Dockerfile in docker-lint.yml.
* feat(docker): sandbox desktop base on python3.13-nodejs26
Matches the Hermes image (Python 3.13 / Node 26) and the top of requires-python;
the default docker_image tag it inherited was Python 3.11 / Node 20. Same pn
uid 1000, Debian 13; smoke (launcher, RFB relay, headed Chromium) passes.
* feat(docker): bake agent-browser into hermes-sandbox:desktop
The browser tools drive the agent-browser CLI; when the browser follows the
terminal backend that CLI has to exist inside the sandbox. Pinned to the same
^0.26.0 range the gateway resolves, --ignore-scripts like the gateway's npx path.
* feat(bot_desktop): the screen, computer_use and the browser follow the terminal backend
A user who sandboxes `terminal` (docker/ssh/singularity) had the agent's
screen, cua-driver and Chromium running on the gateway HOST beside that
sandbox: Bot Screen gave a headless host a display, the Xfce panel carries
xfce4-terminal, and `computer_use` could open a shell outside the boundary
the sandbox exists for.
Now the desktop lives where the terminal lives:
- tools/environments/streams.py: one primitive per spawn-per-call backend, the
local argv prefix that runs its remainder inside the sandbox with stdio open
(`docker exec -i`, `ssh`, `apptainer exec`). SDK backends (modal, daytona,
vercel) have none and report so.
- tools/bot_desktop/sandbox_host.py: launcher.sh runs inside the sandbox as
the image's `pn`; the pane's RFB bytes ride a 12-line python relay over that
prefix; `cua-driver mcp` is the prefix + the sandbox image's own driver.
- tools/bot_desktop/placement.py + `bot_desktop.placement` (auto|terminal|
gateway). `auto` follows the backend; a sandbox that cannot host a screen
REFUSES with the opt-in named instead of silently using the host.
- runtime.start/stop/status/published_env branch on placement; the pane,
lease, epoch fencing and CLI are unchanged.
- cua_backend: the MCP invocation is the sandbox one when the screen is
there; the host driver's runtime contract is irrelevant then; check_fn is
true under a terminal placement without a host binary.
- browser_tool_session: agent-browser invocations are wrapped in the prefix
with the daemon, socket dir and profile inside the sandbox; screenshots are
fetched back so MEDIA: paths keep working; recycle closes the sandbox
daemon.
- web_routers/display.py: the bridge pumps a relay's stdio when the screen is
in a sandbox, a unix socket otherwise.
Live on docker with nousresearch/hermes-sandbox:desktop: start/observe/RFB
handshake through the dashboard bridge, human takeover fences the agent
(HumanHasControl) and keystrokes reach the sandbox Xvnc, handback restores,
three start/stop rounds leave zero desktop processes; computer_use capture
and list_windows see only the sandbox's Xfce; browser_navigate/snapshot/
vision run with Chromium and agent-browser inside the container and zero
host processes on the bot profile; modal + auto refuses naming the opt-in.
* feat(desktop): Screen pane shows where a sandbox-placed screen runs; Install is host-only
DesktopStatus gains placement ('gateway' | 'terminal:<backend>'). A sandbox
image lacking the stack is a blocker naming hermes-sandbox:desktop, shown in
place of Start; install_command stays None there because the pane's Install
button runs the package manager on the gateway host, the wrong machine, and
display.install refuses for the same reason. The pane header carries
'Screen runs inside the docker sandbox, with the terminal' (4 locales).
* fix(bot_desktop): "is the screen in the sandbox" is a disk check on hot paths, never a config read
Every browser command and CUA spawn asked in_sandbox(), which resolves placement by
loading config, which initializes HERMES_HOME. Under a test's fake home that raised
HomeInitializationError from _run_browser_command; on a real host it read config per
click. Hot paths now ask sandbox_screen_running(): the start marker on disk, written
only by a sandbox start. Policy (in_sandbox) stays for start/install, where config is
the question. display.observe gates on "an RFB endpoint exists" for either placement.
* test(moa): late-accounting sink test asserts the wedged slot's row, not sink order
Under CI load the poll loop can see the interrupt before collecting the fast slot, so the
fast slot also arrives late and first; the test then failed on sink_calls[0]. The
contract is that the wedged slot's real usage reaches the sink.
* chore: retrigger CI (zero-job dispatch failure, auto-heal)
* fix(bot_desktop): a sandbox that died under a live screen fails loudly, never falls to the host
sandbox_screen_running() drops a start marker whose terminal environment is no longer
registered (stale after a process restart). When the environment object outlives its
container, the browser's sandbox wrap now checks the published DISPLAY and raises
"the screen inside the terminal backend's sandbox is gone; start it again" instead of
KeyError('AGENT_BROWSER_PROFILE'). Live: fresh sandbox navigate ok; docker rm -f the
container; next navigate returns that error; zero host Chromium either way.
* feat(terminal): nousresearch/hermes-sandbox:desktop is the default container sandbox
Every container backend (docker, modal, daytona, singularity) now defaults to the
sandbox image with the desktop stack, so Bot Screen, computer_use and the browser
run inside the sandbox for everyone who never chose an image; Python 3.13 / Node 26
match the Hermes image. One constant (DEFAULT_SANDBOX_IMAGE) replaces six copies of
the old literal. Migration 47 moves saved configs still holding the OLD default and
never touches an image the user pinned. Docker reuse recreates a container built
from another image, or the flip would silently never take effect for anyone with a
persisted container (live: old container removed, new one on 3.13 / Node 26 with
Xvnc, cua-driver, agent-browser present).
* chore: retrigger CI (zero-job dispatch failure)
* chore: retrigger CI (zero-job dispatch failure, auto-heal)
* chore: retrigger CI (zero-job dispatch failure, auto-heal)
* chore(config): template stamps v47 and shows the new default sandbox image
The template is what install.sh / docker / doctor --fix seed; a stamp behind
DEFAULT_CONFIG makes every fresh install migrate on first run.
* feat(sandbox): the default image change is a decision, not a surprise
A persisted Docker sandbox on another image is kept when docker_image is unset;
only a written docker_image (an explicit pin) recreates it. The pin verdict
travels as TERMINAL_DOCKER_IMAGE_PINNED through both terminal bridges (process
env and per-profile scope) and the container-config allowlist.
Approval surfaces, all through hermes_cli.sandbox_image_switch: the interactive
CLI asks once at startup (y = pin the new image, n = pin the current one, Enter =
ask later); the Screen pane shows the same choice with Switch / Keep buttons via
display.switchSandboxImage; `hermes config set terminal.docker_image …` is the
same answer from any shell. Gateways and cron never decide: they keep the sandbox
and log the notice.
Migration 47 now unsets a saved image equal to the OLD default instead of
rewriting it to the new one — that value was the template copied, not a pin, and
rewriting it would have made the runtime recreate existing sandboxes unasked.
Modal restores its snapshot and Daytona reuses its labeled sandbox regardless of
the configured image, so existing sandboxes there were already untouched.
* fix(config): both plain defaults that preceded the desktop sandbox image are template copies
main pinned nikolaik/python-nodejs:python3.14-nodejs22 (cd0f97f833) without a migration;
a saved config holding either literal is unset by migration 47, so it follows the default
and existing sandboxes get the keep-or-switch decision instead of a silent recreate.
* ci(docker): build the sandbox image on release/dispatch, not every main push
Leaves docker.yml exactly as on main. The sandbox image carries no Hermes code,
so two 4 GB multi-arch builds per merge bought nothing. sandbox-image.yml builds
and smokes on a PR that edits its own Dockerfile/smoke, and publishes only on a
release or a manual dispatch with publish=true. Stable tag stays :desktop.
* fix(config): keep main's config.py/config_defaults.py edits under the sandbox-image delta
The rebase resolved both files wholesale with the branch side, dropping main's move to
hermes_yaml (the 3.14 runtime venv has no PyYAML) and the 3.14 base pin. This is main's
version plus exactly the branch's own changes: DEFAULT_SANDBOX_IMAGE, the pin verdict in the
env bridge, placement defaults and the v47 stamp.
* test: sandbox-image tests read config.yaml through hermes_yaml (no PyYAML on the 3.14 runtime)
* fix(bot_desktop): read the sandbox marker BOM-tolerantly (windows footgun lint)
* fix(bot_desktop): placement is the authority; sandbox screen survives restarts
Review findings on the sandbox-hosted Bot Screen, each reproduced live first.
Authority. The browser preflight and the CUA invocation keyed off screen
LIVENESS, so `placement: terminal` with the screen not yet up handed the tool an
unchanged host command. `runtime.tool_placement()` is now the one resolver:
terminal placement starts the sandbox screen on demand (no auto_start opt-in
inside the user's own sandbox), refused placement raises its reason, and neither
ever yields the host. placement.resolve() answers a local backend from env alone
so the common case costs no config load on the spawn path.
Restart. sandbox_screen_running() deleted the marker whenever the process-local
terminal registry was empty, i.e. after every gateway restart, while Xvnc kept
running in the container; stop() then returned False and left it. The marker
now records the owning container; liveness comes from `docker inspect` on it,
stop/status re-attach to the recorded owner (even after the placement setting
moved), and only a container that is gone drops the marker.
SSH. remote_argv emitted `bash -c <script>` as three words; OpenSSH joins them
and the remote login shell ran `bash -c export` and the rest itself. The script
travels as one quoted word for ssh (remote_command knows the backend); docker
and apptainer keep argv.
CDP reach. agent-browser inside the sandbox reports the sandbox's loopback;
the Browser Use harness, browser_exec and the vault supervisor connect from the
host and got connection refused. streams.forward_port() proxies a local port
over the exec stream (same relay as the RFB bridge) and the CDP URL is rewritten
to the local end.
pids limit. --pids-limit 256 counts threads; measured on the desktop image the
desktop stack is 44, one Chromium tab 212, the agent's browser with two tabs
488. Past the cap every further docker exec died with "procReady not received".
Default is 2048 with the measurements in the comment.
Replacement. An approved image switch force-removed the old container before
`docker run` tried the new image; a private tag or registry outage left nothing.
The image is inspected/pulled first and the old container kept on failure.
Desktop integration. The sandbox start never passed the dock's browser launcher
(no Browser icon) and the thumbnail needed a host launcher pid + host ImageGrab
(always None). The dock runs the sandbox's Playwright Chromium on the shared
profile; the thumbnail is grabbed inside the sandbox (Pillow baked into the
image). The browser profile moves from /tmp — a 512 MB tmpfs emptied on every
container stop — to the desktop user's home, so logins follow the container.
Pin provenance. A TERMINAL_DOCKER_IMAGE written in a routed profile's .env is a
pin even when it spells the default; the scope compared values before.
* docs(bot-screen): no literal tmp path in the profile-location note
* fix(bot_desktop): docker inspect liveness probe closes stdin (TUI subprocess guard)
* fix(bot_desktop): adopting a screen the sandbox kept records the marker
Live ssh probe: after the host's state was lost while the sandbox kept its
Xvnc, start() took the idempotent early return (display already published)
and never wrote the host marker, so status/thumbnail/stop lost the screen.
Record the adopted display like a fresh launch.
Docs: what an ssh host of your own must carry, and why a Dockerfile ENV is
not enough for a login session (PLAYWRIGHT_BROWSERS_PATH via /etc/environment).
* docker(sandbox-desktop): login sessions find the browser (PLAYWRIGHT_BROWSERS_PATH via /etc/environment)
* docs(bot-screen): what the Apptainer path inherits from the image and what it does not
* chore(config): sandbox-image migration is 47→48 (main took 47 for compression.threshold_tokens)
* chore: retrigger CI (zero-job dispatch failure, auto-heal)
The default browser_exec tool ran the `browser-use` CLI from a PM side
environment (browser-use==0.13.10 in <home>/environments/browser-use),
provisioned by the installers and `hermes update`. Sealed Desktop payloads
skip that step, so the Desktop app never had it and silently fell back to
the built-in tools; the side env was also per-profile and 225 MB.
The CLI's execution path is only `browser_harness.run.main()`; the
browser-use agent framework (anthropic/openai/google-api pins, 93 MB of
googleapiclient) is never imported. browser-harness itself is 2.6 MB of
pure Python whose pins (Pillow 12.3.0, websockets 15.0.1) already match
Hermes's own, so it becomes a core dependency and runs on sys.executable:
- pyproject/uv.lock: browser-harness==0.1.13 (+ cdp-use, fetch-use).
- _find_cli() returns [sys.executable, -m, browser_harness.run]; the child
env points PYTHONPATH at the harness site dir (the Desktop store
interpreter boots without a venv and the harness daemon re-runs
sys.executable), replacing whatever the agent inherited.
- The side-env provisioning (install_cli, the update/installer step) goes.
Reconcile plugin declarations and validation through PM's atomic generation publication; preserve external runtimes, target markers, and conflict refusal. Keep one source-update completion owner and port upstream lifecycle changes to the PM desktop/runtime paths.
The native vision_analyze fast path (and the browser screenshot twins) downscaled every
embed to a fixed _EMBED_TARGET_BYTES = 256 KB. That is fine for photos but turns a
1080x2340 phone screenshot of a table into 540x1170, which the model then reads as
"unreadable" and re-requests (#112095).
The budget is now `vision.embed_target_bytes` in config.yaml (default unchanged: 256 KB,
clamped to 64 KiB..4 MiB so one setting cannot make every later request a multi-megabyte
resend), resolved in the new topical sibling tools/vision_tools_history_budget.py and read
by vision_analyze, browser_vision and browser_exec screenshots alike.
Ported from #112947 by @MohamadKanso (resolver + clamp), relocated out of the facade.
Both process-global caches were keyed by the caller's session/task id alone, so under
gateway.multiplex_profiles two profiles using the same id — a shared `browser_exec session=`
name, or two Hermes sessions whose screens report the same DISPLAY — resolved to the FIRST
profile's cloud browser / cua-driver, and a command issued in one bot's chat could act on
another bot's screen.
The key now carries the routed profile's home key whenever a served-profile scope is active
(`get_hermes_home_override()` set), the same shape `tools/approval.py::_baseline_key` and the
camofox/cloud caches already use; outside a scope every key is byte-identical to before. The
computer_use lookup, install and release paths all go through one `_scoped_sid`, so a release
under profile B never stops profile A's driver; approval-bypass state keeps the bare session id.
Fixes#110032 (report by @wolfyy970, from @vandaimer's manual test on #108914).
browser_exec with browser.cloud_provider: nous (the hermes tools picker row) fell into
the direct-API Browser Use branch and reported chrome-not-running, because
_resolve_backend_cdp gated on _use_gateway(), which only read the pre-picker
use_gateway: true flag. Recognize the picker selection too.
Under gateway.multiplex_profiles, os.environ holds the DEFAULT profile's .env; a
secondary profile's values exist only in the per-turn secret scope. Every reader
below still read os.environ/os.getenv at call time, so a secondary profile's turn
silently used the default profile's value.
Credentials (F6): FIRECRAWL_API_KEY (read_file hosted OCR), OPENVIKING_API_KEY,
mem0-OSS OPENAI_API_KEY, MODAL_TOKEN_ID/SECRET and BROWSER_USE_API_KEY presence
gates, and the xAI video plugin's os.getenv("XAI_API_KEY") fallback AFTER the
scoped resolver had already missed — the exact fallback-after-miss shape
gateway/AGENTS.md forbids. Deleted, not re-scoped: the resolver is the scope.
Identity / tenant (F7): MEM0_USER_ID/AGENT_ID/HOST/MODE, SUPERMEMORY_CONTAINER_TAG,
RETAINDB_PROJECT, OPENVIKING_ACCOUNT/USER/AGENT (and the whole layered() env
read), HINDSIGHT_BANK_ID/MODE/retain shaping, HERMES_HONCHO_HOST. A raw read
put a secondary profile's memories into the default profile's account/bank/
project/tenant and recalled them back into the default's turns. Each now uses
get_secret with the provider's own per-profile default on a miss.
Endpoints (F8): OPENAI_BASE_URL (aux custom runtime + direct-alias expansion),
XAI_BASE_URL/HERMES_XAI_BASE_URL (aux OAuth), NOUS_INFERENCE_BASE_URL (#65941,
both the aux builder and hermes_cli.auth_nous._nous_inference_env_override),
GATEWAY_PROXY_URL (same UnscopedSecretError-only fallback shape as
GATEWAY_PROXY_KEY three lines below), FIRECRAWL_API_URL, BROWSERBASE_BASE_URL,
SUPERMEMORY/RETAINDB/HONCHO/HINDSIGHT URLs. The keys beside them were already
scoped, so a secondary's key was sent to the default profile's proxy or host.
Targets / display (F11): WEIXIN_HOME_CHANNEL (message posted into the default's
chat), HERMES_LANGUAGE, and agent/i18n's process-wide lru_cache of
display.language — now keyed by HERMES_HOME.
Outbound webhooks: hooks.outbound[].secret_env resolved from os.environ while
the gateway registers each profile's targets inside that profile's scope, so a
secondary's deliveries were signed with the default's secret or left unsigned.
Agent-cache eviction: _spawn_release_thread started a bare threading.Thread, so
commit_memory_session -> provider on_session_end ran with an EMPTY context. The
thread now runs copy_context() and, for the unscoped housekeeping sweep, enters
the owning profile's _profile_runtime_scope resolved from the session key
(agent:<profile>:...). The pressure batch does the same per key.
session_search (#82903): agent/inline_tool_executors.py::_session_search
forwarded every schema argument except `profile`, so a gateway agent could
never select a named profile's store. Forwarded; the ownership-scoping design
in #87779/#87847 is a separate design call and is not attempted here.
Live repro (/tmp/mux_audit/fix-tool-memory-reads/repro.py): 28 FAIL on
origin/main -> 0 FAIL with this change; 10 new invariant tests red on base.
Fixes#82903Fixes#65941Fixes#99121
Addresses #87779
Co-authored-by: webtecnica <75556242+webtecnica@users.noreply.github.com>
Co-authored-by: Michael Versluis (Berry) <michael@wve.nl>
Use PM-selected interpreters and tool entrypoints for Browser Use, Hindsight and Python language servers. Sync the declared Google Chat extras instead of changing the active environment with pip.
Verified the affected 11-file Nix test subset: 359 passed, 7 skipped. The full suite and real third-party package installation were not run.
Found by using the feature as a user (natural prompts, real sites, CLI PTY + native Electron), not by naming tools:
- browser_vault_save_login was registered but never offered: toolsets.py is a hand-maintained list. Added, with an
invariant test that every registered browser_vault_* tool is in the browser toolset.
- Vault tools were absent on the DEFAULT backend (Browser Use): the gate deferred to check_browser_requirements(),
which is False by design there. Gate = is_browser_use_cli_mode() or check_browser_requirements().
- The model typed a page-shown demo password with browser_type and offered to take one in chat: the vault rules
lived only on the vault tools. browser_type/browser_exec now carry a vault note when the vault tools are
present ("call browser_vault_list first … never type a password with this tool, never accept one in chat, even
if the page shows it"); the browser_exec login-wall line points at the vault instead of "ask the user".
- On Browser Use the saved item was bound to chrome://new-tab-page: the supervisor's default page session is the
daemon's blank tab. browser_vault_save_login now focuses the tab holding a password field before reading its
origin (focus_page("", accept=probe); about:/chrome: pages are never candidates). Live E2E leg added.
- Settings row: "identifier · Added <date>", origin omitted when it duplicates the label.
Live (real model): CLI on Browser Use — first visit prompts, signs in, saves; second visit fills silently; GitHub
decline (Enter or ESC) stops the agent, which refuses chat passwords. CLI on the built-in stack — same three
scenarios pass. Desktop native Electron — same three scenarios plus Settings list/remove pass. Password never in
a transcript, UI, or a file outside vault/.
On the default backend (browser.backend unset → browser_exec) the vault tools were
advertised but could never fill: the CDP supervisor that carries the secret-bearing
eval is started only by the built-in browser_* session path, so _eval_js_secret
failed closed with supervisor_required and the origin pre-check fell back to an
agent-browser CLI eval against a browser browser_exec never touched.
- browser_exec now attaches SUPERVISOR_REGISTRY to the CDP endpoint it just routed
the harness to (BU_CDP_WS/BU_CDP_URL), so the fill talks to the SAME browser over
the same secret-capable WebSocket. BU direct-cloud (BU_AUTOSPAWN) exposes no
endpoint and keeps the supervisor_required refusal.
- CDPSupervisor.focus_page(origin, accept=<js>) (used by browser_vault_fill, next commits) re-attaches the page session to the
open tab on the item's origin whose DOM holds the form being filled (browser_exec
opens its own tabs; the supervisor's initial attach picks the first page target,
which is chrome://new-tab-page). browser_vault_fill uses it before the origin
pre-check with a per-kind probe (password input / card fields / address fields).
Live: evals/vault_fill_live_e2e.py drives the real browser_exec tool against Hermes'
packaged Chromium with the login page in the third tab; A/B with the attach line
disabled fails at "did not attach a supervisor", enabled fills the password into the
/login tab and card fields into the /checkout tab with every model-facing read
scrubbed.
Also: browser_vault_list/fill described the workflow as "type the identifier with
fill_input", a helper that exists only inside browser_exec code (toolset browser-use) and is
a ghost on the built-in stack. model_tools._rewrite_browser_vault substitutes the concrete
name from the session's actual tool set (`fill_input` inside browser_exec, or browser_type),
the same dynamic cross-reference pattern browser_navigate uses for web_search.
Keep upstream's reviewed catalog as the only plugin name index.
Catalog pins and custom update sources share staged PM validation.
Publish code and dependencies with recovery after process death.
Reject a concurrent enablement change before publishing disabled code.
Use the manifest loader's supported version in the installer. Keep
probe cooldowns for timeouts, not TLS failures that a CA change fixes.
Preserve the backup, uninstall, browser and memory-provider repairs.
Verified with the canonical runner on native Windows ARM64, real Git
repositories, local TLS endpoints and UV dependency generations.
Desktop catalog tests and both TypeScript checks pass. The full suite
and native release builds were not run. No remote push.
The salvaged fix only ran the CLI in its own session on POSIX and kept
plain subprocess.run on Windows — the one platform where the wedge in
#106244 is actually reproducible: CPython's run() retries an unbounded
communicate() after kill() there, so a grandchild holding the capture
pipes blocks the worker forever. On POSIX run() wait()s the PID and
returns promptly; the grandchild merely leaks (live-reproduced on Linux).
One code path for both platforms:
- _group_popen_kwargs: start_new_session=True on POSIX,
CREATE_NEW_PROCESS_GROUP + hide flags on Windows (replaces the
hide-only _windows_popen_kwargs).
- _kill_cli_process_group: os.killpg SIGKILL on POSIX, taskkill /T /F
on Windows (same kwarg set as the sibling taskkill sites).
- The Popen decodes with encoding="utf-8", errors="replace" like every
other subprocess call in this file (windows footgun rule).
- Drain test patches the kill helper instead of os.killpg so it runs on
every host.
Windows behaviour is not live-verifiable on this Linux host.
The group kill lives behind browser_exec's os.name != "nt" branch, so
os.killpg/SIGKILL are never reached on Windows; mark the line per the
scan's suppression convention.
subprocess.run only kills the direct CLI child on TimeoutExpired; a
browser_harness daemon / Chrome helper grandchild inherits the stdout/
stderr pipes and keeps them open, so the internal communicate() blocks
on pipe EOF forever. The wedged tool call never returns, its activity
heartbeat keeps stamping last_activity_at every 30s, and the session is
pinned at "now" in the desktop sidebar indefinitely (#106244).
On POSIX, run the CLI in its own session (start_new_session=True) and
SIGKILL the whole process group on timeout, then drain the pipes under
a bounded deadline. Windows keeps subprocess.run.
Pin uv and uvx to the PM interpreter instead of ambient Python discovery.
A matching dependency stamp cannot prove that installed files still exist.
Repair now rebuilds the recorded workspace and lock in a fresh generation,
checks startup imports, and publishes the selection only after success.
Run startup recovery before dependency activation. Keep manual PM repair
reachable when the selected environment is damaged. Preserve plugin
selection, retry ownership, and the previous generation on failure.
Remove the separate pip, ensurepip, per-extra, and install-time quarantine
ladders. Keep orphan launcher restoration.
Verification: 717 targeted tests passed on native Windows ARM64, with
56 skipped. Ruff, diff checks, and the source-scoped compat check passed.
A disposable real Hermes install recovered deleted YAML and dotenv files,
then printed CLI help with exit 0. Its lock and stamp stayed unchanged.
The full suite and a release build were not run for this change.
Prepare dependency generations before selecting them. Keep shipped tool
bytes separate from writable additions, and store facts beside their entries.
Validate proposed plugin sets before config publication. Restore the previous
config if the facts write fails.
Consolidate duplicate updater, backup, setup, and voice helpers. Repair
launcher selection, dependency consumers, download ownership, update feeds,
and native Windows process and file handling.
Verification: 206 changed/prior-failing Python files reported 4630 passed,
one failed, and 330 skipped. Fix the remaining Hindsight fixture boundary.
The final targeted rerun reported 234 passed and two skipped. The store
review regression batch reported 83 passed and one skipped. Desktop
TypeScript checks, 56 selected Electron tests, 24 release tests, and the
removed-import/compatibility guards passed.
This is an integration checkpoint, not full audit acceptance. The complete
Python suite has not run on this fixed tree. Crash-atomic plugin publication,
generation cleanup, receipt correlation, and packaged lifecycle acceptance
remain open in docs/pm-audit-status.md.
Symptom: with Browser Use mode (the default) and no cloud provider / CDP
override, browser_exec left BU_CDP_* unset, so the browser-use harness ran
its own local discovery — hunting for the user's INSTALLED Chrome on its
default profile. That path needs the chrome://inspect remote-debugging
toggle plus an "Allow remote debugging?" popup per run, is blocked outright
on Chrome >=136, and on a headless host (or one without Chrome) fails with
"chrome-not-running: no supported Chromium-family browser is running". The
built-in browser_* tools never had this problem: they drive the Chromium
Hermes installs, launched through agent-browser.
Change: `_resolve_backend_cdp` step 4 becomes the local ENGINE —
lightpanda when configured, otherwise `_resolve_managed_chromium_cdp`,
which runs `agent-browser --session <key> get cdp-url` through the legacy
`_run_browser_command` (Chromium preflight/auto-install, per-key session
cache, inactivity reaper, atexit) and exports the returned ws:// endpoint
as BU_CDP_WS. Each cache key (task, or bu-named-<session>) gets its own
Chromium, so named sessions are private and skip the own-tab preamble.
Running `get cdp-url` on every call also refreshes agent-browser's idle
timer (it never sees the harness's direct CDP traffic) and follows a
relaunch after the reaper closed the browser.
Live: before, browser_exec on origin/main → exit 1 "chrome-not-running";
after → new_tab/page_info succeed on a cold start, warm reuse, post-reap
relaunch, and a named session; a missing Chromium surfaces the install
hint instead of the harness's Chrome hunt.
For each issue anchor present in BASE 63279301bc non-test .py and absent on HEAD, the BASE comment/docstring block was re-attached at the HEAD location of the code it explained (matched by the distinctive code line / enclosing def). Sentences already covered by an existing HEAD comment were deduped; the issue number always survives. Insert-only: no code lines changed.
Repo scanners (check_subprocess_stdin, check-windows-footguns --all) flagged 21 sites where
the r3 single-line collapses lost stdin=DEVNULL, encoding='utf-8'/errors='replace', the
'# windows-footgun: ok' same-line marker, or the getattr(os, 'geteuid') gate. Each guard is
restored at the call site (real portability/hang fixes, not suppressions).
Introduce the pm store: a unified, hash-verified package store that
replaces lazy_deps and the old installer's ad-hoc tool downloads.
Store tools are provisioned on PATH (ffmpeg, node/npm via pinned uv),
with a resumable 8-way downloader, verify() returning failure reasons,
and adopt() made EPERM-safe. chromium ships in the payload for every
target. The 3600-line install.sh is replaced by a staged bootstrapper
(heavy deps are pm's job after this); setup-hermes.sh, Dockerfile and
nix pin tables are rewired onto the store. Old install-script tests,
lazy_deps/managed_uv/build_info, and the ps1/bash installer test
batteries are removed with the machinery they tested.
Rebuilt from ethie/pm onto upstream/main (ac6c8028e0) after the
utf-8-sig sweep. 16 hot files (main also churned them) hand-merged:
platform adapters, main.py, electron/main.ts, tui_gateway/server.py,
cua_backend, installer-tests workflow, install.sh (full rewrite),
setup-hermes.sh, plugins doc.
Browser Use mode never read browser.engine: _resolve_backend_cdp() went
BU_CDP_* env -> CDP override -> cloud provider -> local Chrome, so
`engine: lightpanda` was a silent no-op on the default backend, and on
the built-in path it was skipped whenever a cloud provider, Camofox or a
CDP override was active without anyone saying so.
- browser_use_cli: when the engine is lightpanda and nothing with higher
precedence claimed the session, get a session from _get_session_info()
and export its endpoint as BU_CDP_URL; the browser is private to the
session key, so the own-tab preamble is skipped. The browser_exec
description gains a Lightpanda header (text-first, new_tab once then
goto_url — lightpanda-io/browser#1962).
- browser_tool: _create_local_session() spawns `lightpanda serve
--host 127.0.0.1 --port <free>` per session key (new
tools/browser_lightpanda.py), reusing the session cache, inactivity
reaper and atexit cleanup; a dead process is respawned on the next call;
orphans from a crashed Hermes are reaped through per-process records in
$HERMES_HOME/cache/browser-use/lightpanda/. New lightpanda_engine_status()
reports whether the engine is in effect or what shadows it.
- tools_config: "Lightpanda" row in the Browser Automation picker
(cloud_provider: local + engine: lightpanda; "Local Browser" resets the
engine to auto) with a binary-check post-setup.
- /browser status and hermes doctor print the engine state and, when it
is shadowed, the reason.
Copy the user's default-Chromium profile (auth state only) into a managed
snapshot, launch Hermes' packaged Chromium on it via agent-browser, and hand
the CDP endpoint to the Browser Use CLI (and built-in tools) to drive. The
snapshot is a non-default dir, so it sidesteps Chrome 136+'s default-profile
remote-debugging block and never contends with the user's running browser;
launched without mock-keychain switches so keyring-encrypted cookies decrypt.
- consent-gated browser_exec 'local' arg (schema only appears with consent)
- fail-closed on non-Chromium default / snapshot failure
- stale-session guard: reuse only when the live session is on our copy dir
- snapshot excludes extensions/service-workers (renderer wedge) + caches
Profile-spawned workers (kanban bots, cron jobs) can inherit a PATH of
only version-manager dirs — observed in the wild as one nvm node dir
repeated 7x. The uv-installed browser-use binary is a POSIX sh
trampoline that resolves dirname/realpath through PATH, so it died
with 'realpath: not found … exec: /python: not found' (exit 127)
before its own Python ever started.
_base_subprocess_env now floors the child PATH via browser_tool's
_merge_browser_path (the agent-browser backend already guards the same
hazard), degrading to appending FHS bin dirs if that import is ever
unavailable. Windows is a no-op (.cmd shims don't trampoline).
Verified: unit tests + real uvx browser-use --version under a
nvm-only-PATH worker env, rc 127 -> rc 0.
Review pass findings on the force_jpeg change:
- Broaden the JPEG mode guard from {RGBA, P} to 'not in {RGB, L}':
force_jpeg newly routes PNG inputs to the JPEG encoder, and an
LA-mode PNG (grayscale+alpha) would crash img.save() with
'cannot write mode LA as JPEG'.
- browser_use_cli's _native_screenshot_result is the THIRD native
history-embed site: it baked the data URL into a _multimodal tool
result with the 5 MB one-shot default and no dimension cap. Apply
the same 256KB/1568px/force_jpeg history-reuse policy as the two
sites already migrated.
Follow-up to #86916. That fix gave named sessions their own daemon
(socket/log/pid) and their own provider browser — but on a SHARED local
Chrome / CDP browser, a fresh named daemon still attaches to the first
existing page, the same page a sibling daemon may hold. A named session
that never calls new_tab() could still stomp another's tab.
browser_exec now prepends a small preamble to the model's code for named
sessions on shared browsers: once per daemon process (marker keyed by
uid + BU_NAME + daemon pid), it creates a fresh tab via
Target.createTarget and switch_tab()s onto it before any model code
runs. Private per-name browsers (provider-keyed bu-named-<name>, or
direct-API Browser Use cloud) skip the preamble via an internal env
sentinel popped before launch — there's nobody to collide with, and the
extra tab would leak.
Best-effort by design: if the preamble's CDP calls fail, behavior
degrades to pre-fix, never blocks the exec.
E2E against a shared headless Chrome with the STOCK harness: two named
sessions issuing bare js() writes (no new_tab) kept distinct state
(EDGE-A/EDGE-B read back intact); the sabotage run without the preamble
reproduced the clobber (both read EDGE-B). Removes the dependency on the
upstream browser-harness tab-isolation PR for correctness.
session=<name> previously set BU_NAME and then skipped backend resolution
entirely — the parameter was documented as cloud-only, so all local/CDP
work funneled through the single default daemon and one IPC socket, and
concurrent sessions (parallel subagents, simultaneous chats) clobbered
each other's browser connection. Reported by @shantanugoel on X.
Now a named session composes with whatever browser source is configured:
- BU_NAME still namespaces the harness daemon (per-name IPC socket, log,
pid — upstream already isolates these), for local Chrome and CDP.
- The /browser connect CDP override is now exported for named sessions
too; previously a named daemon ignored it and fell back to scanning
local Chrome profiles.
- On provider backends (Browserbase, Firecrawl, Nous gateway), the name
keys its own provider browser via the shared _get_session_info cache
(bu-named-<name>), so each name gets its own cloud browser, the same
name reuses one across calls and tasks, and unnamed calls keep the
per-task key.
- Direct-API Browser Use cloud configs keep the native named-daemon path
(provider resolution would double-session and double-bill).
Tool schema/description updated so models reach for session=<name> for
parallel work on any backend, not just cloud.
E2E: two named sessions against a real headless Chrome (real browser-use
CLI, BU_CDP_URL) ran concurrently, set distinct page state, and read it
back intact; sabotage run confirms the new tests fail without the fix.
The browser-use CLI runs under its own Python (uv tool / uvx), which
can differ from Hermes's venv interpreter. PYTHONPATH/PYTHONHOME
inherited from the agent process point at Hermes's venv
site-packages, and a child interpreter honors them ahead of its own —
so the CLI imported compiled C-extensions (pydantic_core) built for
the wrong interpreter and crashed with ABI mismatch /
ModuleNotFoundError (issues 83427, 84841, 86006, 86104; hits the
desktop backend on py3.14 and any shell exporting PYTHONPATH).
Strip both vars in _base_subprocess_env() — the CLI manages its own
environment and never needs Hermes's import path.
Salvaged from PR 83471 by Benjamin (@n1majne3), the earliest of two
independent fixes (also PR 84022 by @jklance16, PYTHONPATH-only);
regression test covers both vars and preserves unrelated env.
Everything Browser Use is now managed by Hermes: the canonical binary
is the one install_cli() provisions into HERMES_HOME/bin, and every
resolution and provisioning site prefers it.
- _find_cli(): probe order flipped to managed bin -> PATH ->
user-level tool dir (then uvx across the same order). A user's own
uv tool install can no longer shadow the Hermes-managed copy with a
drifted version; side installs only matter when we have nothing.
- install_cli(): a browser-use on PATH no longer short-circuits the
install — only the managed copy does, so selecting any backend
provisions the copy Hermes controls and updates.
- _ensure_browser_use_cli() (hermes tools): drops its own PATH check
and always delegates to install_cli(), the single owner of the
managed-copy policy.
- install.sh / install.ps1: same short-circuit fix — only
HERMES_HOME/bin/browser-use counts as installed.
Follow-up to #86240 and #86320: with every non-Camofox backend
selection installing the CLI, managed-first closes the remaining
version-drift/shadowing class instead of guarding single sites.
Tests updated to pin the new contract: managed beats PATH and
user-local; PATH install does not satisfy install_cli; helper always
delegates. E2E-verified precedence chain with real files and a real
degraded-PATH install attempt.
Desktop/TUI workers can spawn with a minimal PATH that omits
~/.local/bin, the default location where uv tool install links the
browser-use binary. _find_cli() then failed to resolve an installed
CLI and Browser Use mode silently fell back to the built-in tools.
Probe the user-level tool dir (~/.local/bin on POSIX, APPDATA/uv/bin
on Windows) between PATH and the managed HERMES_HOME/bin, for both
the browser-use binary and the uvx fallback.
Salvaged from PR #83788 by @kimyxx onto current main; tests adapted
and extended with precedence and uvx coverage.
Sweep of open Windows issues affecting day-to-day agent operation
(explicitly excluding install/setup and locale classes):
- hermes_cli/_subprocess_compat.py: new split_command_line() — Windows-
safe command-line tokenizer (posix=False + quote stripping) so
backslash paths survive. POSIX behavior unchanged (plain shlex.split).
- hermes_cli/console_engine.py (#83934): console commands like
'sessions export C:\Users\me\out.jsonl' no longer silently mangle the
path into a relative filename in the cwd.
- agent/shell_hooks.py (#78293): hook commands with backslash paths now
spawn, resolve their script path, and pass hooks doctor instead of
reporting 'not executable'. All three shlex sites routed through the
shared splitter.
- agent/prompt_builder.py (#51755): system prompt now reports
Windows (11) on Windows 11 — platform.release() returns 10 for both;
distinguish via sys.getwindowsversion().build >= 22000.
- hermes_cli/commands.py (#42016): @ autocomplete no longer crashes the
prompt_toolkit event loop when rg emits a path on a different mount
(device paths \.\nul, other drive letters) — relpath ValueError is
skipped per-entry.
- tools/browser_use_cli.py (#83884): screenshot-path detection now
matches Windows drive-letter paths (C:\... and C:/...) in addition to
POSIX; Browser Use screenshots attach on Windows.
- tools/skills_hub.py + tools/skills_guard.py (#62310): the two 'MUST
stay symmetric' skill content hashes actually agree on Windows now.
Bundle keys are normalized to POSIX separators before hashing, and the
disk digest sorts by rel-posix STRING (case-sensitive) instead of Path
objects (case-insensitive on Windows). Fixes permanent false-positive
update_available for every installed skill.
Tests: tests/tools/test_windows_agent_loop_papercuts.py — 16 cases
covering each fix, including a disk-vs-bundle hash symmetry check built
with native Windows separators and a mixed-case filename.
The Browser Use CLI became the default browser backend, but nothing
provisioned it: users without uv/uvx (field report from DongyangHe on
macOS) silently fell back to the built-in browser tools with no notice.
- install_cli() in tools/browser_use_cli.py: uv tool install browser-use
via the managed uv (bootstrapped on demand), linked into
$HERMES_HOME/bin (UV_TOOL_BIN_DIR)
- _find_cli() now also probes $HERMES_HOME/bin for browser-use/uvx —
Hermes' managed uv is not on the user's PATH
- hermes tools post_setup actually installs (Camofox standard) instead
of printing instructions
- install.sh / install.ps1 provision the CLI at install time
(best-effort, non-fatal, honors --skip-browser)
- CLI startup shows a one-line notice (24h rate-limited) when the
default backend downgraded to the built-in tools
An unset browser.backend ("") now resolves to Browser Use mode whenever
the browser-use CLI is runnable (installed binary or uvx); otherwise the
built-in browser tools are kept so browsing never silently breaks.
Camofox setups always keep the built-in tools (no CDP surface), and
backend: off (including YAML 1.1 bare off -> False) forces the built-in
stack. hermes tools row highlighting follows the same effective-mode
resolution, and tests/tools/ pins CLI discovery off so host uvx installs
can't flip built-in-browser tests.
