Every stdio MCP server was wrapped in its own CPython watchdog that polled
getppid() every 2s to notice an ungraceful Hermes exit (kill -9, OOM, crash,
force-quit), since macOS has no PR_SET_PDEATHSIG. That is a whole interpreter
per server for a job that does nothing until the moment Hermes dies: 10.1 MB
physical footprint each, measured on macOS/arm64.
Replace the fleet of pollers with a single supervisor per Hermes process
holding the read end of a pipe only Hermes writes to. Death detection becomes
EOF on that pipe -- exact and instant, rather than up to a poll interval late.
Hermes sends `register <pgid>` / `unregister <pgid>` as servers come and go;
on EOF the supervisor killpg's whatever is still registered, which is exactly
the set whose teardown never ran. A clean shutdown unregisters as it goes, so
EOF then finds nothing to kill.
Servers are now spawned unwrapped. The MCP SDK already starts each stdio child
in its own session, so the pgid recorded for killpg is the server's own group
and the existing cleanup paths reach it unchanged. That also deletes the
signal-forwarding layer the wrapper needed: wrapping had put the real server in
a different session from the pgid being tracked, so a graceful killpg would
have hit only the wrapper.
Measured on a 5-gateway host: 10 watchdogs (~98 MB) -> 5 supervisors (~49 MB).
One supervisor costs about what one watchdog did (9.9 vs 10.1 MB), so the win
is (servers_per_process - 1) x ~10 MB, and a process with no stdio servers now
spawns nothing at all.
The supervisor reads length-capped lines rather than iterating the stream: a
writer that never sends a newline would otherwise grow it without bound, which
it must not be vulnerable to when it is the last defense against leaked
servers. Found by feeding it /dev/zero, where it reached 15 GB.
Verified beyond unit coverage: a real stdio MCP server connects and its tools
are discovered on the unwrapped path; with a live Hermes holding a real
connection, kill -9 reaped the server, its grandchild (in the server's group,
the mcp-remote `node` case), and the supervisor exited on its own. The reap
tests were sabotage-checked in both directions -- a no-op reaper fails all
three, while the test pinning that a cleanly unregistered server survives keeps
passing -- and each wiring half fails independently when removed.
(cherry picked from commit a252d4ce7ff1722f687635fdbf0cff79f538c3f1)
The inactivity janitor is one process-global thread started by whichever
profile first opens a browser, so under `gateway.multiplex_profiles` it runs
with no secret scope: `cleanup_browser` -> `is_camofox_mode` ->
`get_secret("CAMOFOX_URL")` raises UnscopedSecretError, the session entry is
never removed, and the same failure repeats every 30s while the Chromium
daemon leaks.
- `_update_session_activity` records the owning Hermes home per session;
`_cleanup_inactive_browser_sessions` re-enters that owner's
`set_hermes_home_override` + `build_profile_secret_scope` around each
teardown (`_session_owner_scope`, mirroring `_profile_runtime_scope`).
copy_context at thread spawn would pin the first profile's secrets onto
every other profile's teardown; there is no os.environ fallthrough.
- 3 consecutive failures -> `_force_reap_browser_session`, which skips the
failing `close` round-trips but still closes the cloud provider session
and kills the local daemon via the shared `_release_session_resources`
tail (extracted from `_cleanup_single_browser_session`, unchanged).
An activity touch does not reset the failure budget.
Fixes#86402Fixes#100738
Co-authored-by: fangliquanflq <fangliquan@qq.com>
A multiplexed Hermes process (gateway.multiplex_profiles, unified
dashboard/TUI, or cron) serves several profiles at once, but terminal.*
resolved through process-global TERMINAL_* env vars bridged ONCE at
startup from the launch profile (gateway/run.py ~2700-2760) plus the
one-shot _ensure_terminal_env_bridged() guard. Every routed profile
therefore inherited the launch profile's backend, cwd, docker volumes,
SSH target and shared-container key: a local profile ran inside another
profile's docker sandbox (or a docker profile escaped to the host), and a
container labeled profile A carried profile B's RW bind mounts.
Fix: an authoritative per-profile terminal policy seam, mirroring
agent/secret_scope.py:
- tools/terminal_scope.py: ContextVar holding the routed profile's
COMPLETE effective TERMINAL_* policy (defined defaults <- profile .env
TERMINAL_* <- config.yaml terminal:). While bound, terminal_env()
resolves ONLY from it - an omitted key yields the defined default,
never os.environ. Unreadable/malformed policy installs a refusal
scope; terminal_tool / execute_code refuse instead of running under
ambient launch-process policy (fail closed).
- Installed at every in-process profile boundary: gateway
_profile_runtime_scope, tui_gateway session/build/turn scopes, cron
per-job fire. The unscoped single-process path is byte-identical.
- Every terminal.* consumer reads through the scope: terminal_tool
(_get_env_config, _resolve_container_task_id shared key, orphan
reaper lifetime, degraded mode), gateway/platforms/base.py docker
media translation (volumes, shared key, persistence), runtime_cwd /
agent_init / skill_utils / code_execution_tool / file_tools cwd
anchors, prompt_builder / browser_tool / env_probe backend checks,
gateway footer, @-refs and slash-command cwd. env_probe resolves the
backend in the caller's context, since the probe worker thread does
not inherit the ContextVar.
Salvage of #99225 onto current main: adds the three ambient reads the PR
missed (tools/file_tools.py TERMINAL_CWD, tools/browser_tool.py and
tools/env_probe.py TERMINAL_ENV; shape from #79117) and trims the test
module to the leak matrix driven through the real gateway boundary,
omitted-key defaults, refusal, and boundary reset.
Fixes#68559Fixes#94200Fixes#101132Fixes#95470
Co-authored-by: x7peeps <9640837+x7peeps@users.noreply.github.com>
Co-authored-by: Eva <239388517+100yenadmin@users.noreply.github.com>
Co-authored-by: ExitMaster <292490062+ExitMaster@users.noreply.github.com>
_run_chrome_fallback_command creates agent-browser-<session> in the shared
tmpdir and then opens stdout/stderr files inside it, but never writes the
<session>.owner_pid marker. _reap_orphaned_browser_sessions rmtree's any
agent-browser-* dir that carries no live owner and is not tracked in the
calling process, so a second hermes process — or a parallel test worker —
deletes the directory between the makedirs and the first os.open, and the
command dies with FileNotFoundError on _stdout_open.
Write the owner marker immediately after creating the directory, which is
what every other socket-dir user already does.
Deterministic repro on main: run any test that exercises the fallback while
a second process calls _reap_orphaned_browser_sessions() in a loop —
5/5 fail before, 6/6 pass after.
Salvage hardening on top of the three cherry-picked contributor commits
(#91297 gebilaowang404 + AlexMnrs, #96741 burak33bb, #98826 ayushnangia),
closing the remaining unverified-PID kill sites as one class (#98814, #89614):
- pid_is_hermes: token-boundary 'hermes' match (no more loose substring
false-positives), and an explicit start-time expectation is now honored
on POSIX too (a mismatched fingerprint is a recycled PID on any platform).
- kill_process_tree: drop the guard on our OWN retained Popen child — a
retained handle pins the PID, so the check could only false-refuse.
- gateway.status.terminate_pid: POSIX force-kills also refuse when a
caller-provided expected_start_time no longer matches.
- kill_gateway_processes: re-verify the LIVE cmdline at kill time (the
scan-time match is a TOCTOU window).
- _reap_unsupervised_gateway_orphans: fingerprint orphans at scan time and
require a still-matching identity before the delayed SIGKILL escalation.
- whatsapp _kill_port_process: never kill a bare netstat/lsof-scanned PID
unless the live process is actually a node bridge (was a stranger-kill).
- browser daemon reap/close paths: pass the start-time fingerprint into
ProcessRegistry._terminate_host_pid (previously unverified), and the
session-close path now runs the same daemon identity verification as
the orphan reaper.
- tests/hermes_cli/test_taskkill_identity_windows_live.py: live Windows
probes (real spawned processes, real psutil ancestry) wired into the
on-demand windows-latest wine2e lane.
Fixes#98814Fixes#89614
- lightpanda_engine_status: check use_real_profile before the cloud
provider, matching browser_exec's actual resolution order (real-profile
resolution runs before backend resolution), so /browser status and
hermes doctor name the right shadowing setting when both are set.
- launch_lightpanda: drop the unreachable Windows popen_kwargs branch
(find_lightpanda_binary returns None on nt, launch errors out earlier).
- doctor: drop the over-defensive try/except around the cached
_using_lightpanda_engine() config read.
- Docstring: 'no-I/O gates' -> 'no network I/O (config reads only)'.
- New test pinning real-profile-over-cloud-provider reason precedence.
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.
Review follow-up for the #81673 salvage: the strip was silent, which
would confuse a user whose AGENT_BROWSER_ARGS applies to Chrome commands
but vanishes on Lightpanda ones.
Strip Chromium-only launch variables from Lightpanda commands, use a non-recursive Lightpanda URL lookup for Chrome fallback, and share sandbox argument injection with the temporary Chrome path.
Co-authored-by: forjd-hermes-bot <282037251+forjd-hermes-bot@users.noreply.github.com>
Real-profile browsing (browser.use_real_profile) is meant to drive a COPY of
the user's profile headlessly in the background so they can keep working while
the agent acts on their behalf. Instead, on any host with a display it launched
the user's real browser binary HEADED, popping a window that grabbed focus on
every turn.
Root cause: the native launch (which bypasses agent-browser's own launcher to
avoid --use-mock-keychain dropping keychain-encrypted cookies) only added
--headless=new when Linux had no DISPLAY/WAYLAND_DISPLAY. On a normal desktop
the guard was false, so Chrome opened a visible window.
Fix: launch headless by default on every platform. Chrome's NEW headless mode
shares the profile's normal cookie store (unlike legacy --headless), and the
cookie drop we guard against comes from --use-mock-keychain, not from headless
— so real-profile auth still loads. Users who want to watch can opt in via the
existing browser.headed / AGENT_BROWSER_HEADED toggle (honored for real-profile
now, same as the rest of the browser stack); display-less hosts stay headless
regardless so the launch doesn't die at startup.
Live A/B on a real X seat: old argv mapped a Chrome window (focus steal),
--headless=new mapped zero windows while still exposing a working CDP port.
Updated the stale test that pinned 'never passes --headless' (a legacy-headless
premise) to positively assert the chrome launch is --headless=new by default.
- _terminate_real_profile_chrome(): directly-launched real browsers are ours
to reap (agent-browser only attaches); wired into the atexit emergency
cleanup and both launch-failure paths so orphaned Chrome processes can't
accumulate.
- Display-less Linux gate: append --headless=new (shares the profile's normal
cookie store, unlike legacy headless) so the direct-launch path doesn't
regress servers without DISPLAY/WAYLAND_DISPLAY.
- Register browser.real_profile_pin in config_defaults.py and document the
new launch model + pin in website/docs/user-guide/features/browser.md.
- Drop unused tempfile import from the cherry-picked commit.
Four fixes for real-profile browsing (browser.use_real_profile), found and
verified end-to-end on macOS with a live Chrome:
1. _copy_auth_file: sqlite3.connect('file:...?mode=ro') on a live Chrome
auth DB can block indefinitely inside lock negotiation - the busy
timeout never fires, so the 'fail fast' path hangs the launch forever.
Try immutable=1 first (reads instantly, correct for a committed
snapshot of a file another process owns); mode=ro stays as fallback.
2. Launch shape: agent-browser's own launch injects --use-mock-keychain /
--password-store=basic / --headless=new. On macOS the mock keychain
makes Chrome treat every keychain-encrypted cookie as undecryptable
and drop it - the copied profile launches signed out (~3 anonymous
cookies instead of the full jar). Launch the user's real browser
binary directly on the copy (no mock-keychain switches), wait for
DevToolsActivePort, then attach agent-browser via --cdp.
3. Snapshot copy: Local State was copied verbatim, still naming the
SOURCE profile (last_used='Profile 2', info_cache listing several)
while the copy only contains Default. Chrome opens the missing profile
dir and starts signed out. Normalize the copy's Local State to
Default-only.
4. CDP resolution: the agent-browser daemon may report the endpoint of a
browser IT spawned (throwaway temp profile) instead of the real
browser we launched on the copy. Trust the port our browser wrote to
DevToolsActivePort.
Also adds browser.real_profile_pin (optional): pin which source Chromium
profile dir is snapshotted instead of following profile.last_used - on a
machine with a work profile and a personal one, last-used roulette can
silently give the agent the wrong identity. A pin naming a missing dir
fails closed (signed out) rather than falling back to last_used.
Tests: 4 new pin tests + 3 launch tests reshaped to the direct-launch
contract (Popen the real binary, agent-browser attaches). 77 passing.
Extends the real-profile machinery (PR #95620) to Brave Origin — Brave's
standalone paid build with a fully separate install identity:
- new canonical key 'brave-origin' in _CHROMIUM_BROWSERS
- Windows: BraveOHTML ProgId -> brave-origin; channel ProgIds BraveOBHTML/
BraveODHTML/BraveOSHTM fail closed (identifiers from brave-core
install_static)
- macOS: com.brave.Browser.origin bundle id (exact match); .beta/.dev/
.nightly channel bundles fail closed; /Applications/Brave Origin.app
- Linux: brave-origin.desktop matched BEFORE the bare 'brave' fragment
(substring scan would otherwise resolve an Origin default to stable
Brave and drive the wrong profile — #95549 wrong-principal invariant);
brave-origin-{beta,nightly,dev} fail closed
- profile dirs: BraveSoftware/Brave-Origin on all three OSes (per
brave-core kProductPathName + Homebrew cask zap paths)
- /browser connect launch tables: Brave Origin split into its OWN group
so a 'brave' executable lookup can never resolve to the Origin binary
- user-facing strings/docs/desktop tooltip updated
Tests: progid/bundle/desktop map params + data-dir resolution for all
three OSes; 125 passed in the three browser test files.
Builds on e11187208f (salvage of #72206 by @luyifan, authorship
preserved) which added the post-timeout session reset. This commit
completes the Phase 3b contract:
- suspect flag: a command timeout marks the session key suspect;
the NEXT _get_session_info for that key health-checks and recycles
the session instead of handing back the poisoned handle (#72205)
- flag cleared on fresh-session store so a healthy new session is
never spuriously recycled; cross-key leakage fixed
- wedged-vs-alive rule (#68139): after a timeout, if the daemon's
socket still answers, recycle the session only; if it is
unresponsive (or no socket exists to probe — conservative), tree-
kill via agent.deadline.kill_process_tree and evict
- negative probe: successful commands never mark or recycle
Tests: tests/tools/test_browser_suspect_recycle.py (20 tests:
mark-once, recycle-then-succeed, success-never-recycles, tree-kill
invoked on the wedged path with pid assertion, flag lifecycle).
Co-authored-by: luyifan <al3060388206@gmail.com>
Refines the Windows path per three requirements:
1. Only when the toggle is set — closing is offered only if
browser.real_profile_autoclose is on.
2. Blocked when locked — snapshot_real_profile NEVER kills; a locked profile
always returns the [profile-locked] signal and the copy is refused. A later
attempt that is still locked blocks again (no loop, no auto-kill).
3. Ask approval to close — closing is an explicit, user-approved step:
(new CLI subcommand) runs
close_browser_holding_profile only when the agent has the user's OK. The
locked error tells the agent to ask first, then run it, then retry.
- browser_connect: snapshot blocks with _PROFILE_LOCKED_PREFIX (autoclose-armed
message offers the close; off message says fully-quit); no in-snapshot kill.
- main.py: subcommand (identity+binding-verified
tree kill via close_browser_holding_profile); added to _BUILTIN_SUBCOMMANDS.
- browser_tool: surfaces the locked signal + the exact approved-close command.
- Docs/config: toggle arms + agent asks + blocked-if-still-locked.
Tests: snapshot blocks-not-kills with autoclose on AND off; process matcher
identity/binding. 73 real-profile tests pass. Windows live E2E (proof): locked
blocks fast without killing → approved close terminates Chrome → snapshot then
copies a valid DB; autoclose-off blocks with quit guidance.
Addresses the round-3 findings from @Adolanium + @kshitijk4poor on #95620:
1. Overlay-before-reuse race (blocker): _real_profile_cdp ran snapshot_real_profile
BEFORE the session-reuse check, so a cold resolve that ends in reuse rewrote
Cookies/Login Data under a live Chromium holding the user-data-dir open (torn
DBs, locked txns, phantom logouts). Now: resolve copy dir as a PATH, probe
reuse first, return early on a hit; snapshot/overlay only on the relaunch
path when no live browser owns the dir.
2. Torn first copy poisoned freshness forever: freshness keyed on isdir(Default),
so a half-written copy (disk full / Ctrl+C) was treated as populated and only
ever got auth overlays. Now gated on a .hermes-snapshot-complete marker
written only after a full copy succeeds; a torn copy is rebuilt from scratch.
3. Consent revocation left copied credentials on disk: turning use_real_profile
off now deletes ~/.hermes/browser-profile/ on next browser use
(cleanup_real_profile_snapshots), so cookies/logins don't outlive consent.
4. Stale non-active profile copies: only the ACTIVE profile (last_used) is copied
into the copy's Default now — other Chrome profiles are never snapshotted
(smaller copy, no stale credential dirs lingering).
5. Docs/config/desktop wording aligned to actual behavior (active-profile only,
refresh on fresh session, consent-off cleanup).
Tests: overlay-skipped-on-reuse + overlay-runs-on-relaunch, done-marker gating +
torn-copy rebuild, active-only copy, consent-off cleanup (removes store +
idempotent + triggered from _real_profile_cdp). 206 browser + 222
backup/file_safety pass. Live: reuse skips re-snapshot; direct launch on the
active-only copy loads the real signed-in Gmail inbox.
Addresses the five findings from @kshitijk4poor + @GottZ on #95620:
1. macOS 26 LSHandlers parser returned a version number ('7559.97') from the
nested LSHandlerPreferredVersions block instead of the bundle id — detection
returned None on a machine whose default IS Chrome. Strip the nested block
before the role regex.
2. Wrong profile launched (the LinkedIn/Gmail 'logged out' bug): Chrome opens
Default, but the session lives in Local State profile.last_used (e.g.
'Profile 6'). Resolve last_used and mirror its auth files into the copy's
Default on both fresh and refresh paths, so the launched browser is signed in.
3. Private-URL sidecar carried the real cookie jar to arbitrary LAN hosts:
_create_local_session gains allow_real_profile (default True); the
force_local sidecar passes False → always a throwaway profile, and a
real-profile resolve failure no longer breaks private-URL routing.
4. Snapshot permissions were set once (fresh only): now secure the snapshot dir
AND its browser-profile parent on every consented launch.
5. browser.engine=lightpanda + consent gave an unactionable error: guard with
_using_lightpanda_engine() before detection, naming the setting and the fix.
Tests: last_used mirroring (fresh+refresh+fallback), sidecar throwaway + error
isolation, macOS26 parser + detect, perms-on-refresh, lightpanda guard. 198
browser tests pass. Live: Profile-6 cookie DB lands in copy Default (file-level);
real Gmail (Default profile) still signed in.
Addresses two P1 review blockers (kshitij / @kxee) on the real-profile feature:
Credential-store lifecycle for ~/.hermes/browser-profile/ (copied Cookies/
Login Data):
- exclude the singular 'browser-profile' dir from backup AND import
(_EXCLUDED_DIRS drives both) — was silently archiving cookies/logins
- add a browser-profile/ directory-PREFIX read-deny to agent/file_safety.py,
same class as auth.json / mcp-tokens
- secure the snapshot dir through the canonical hermes_cli.config._secure_dir
(honors managed/NixOS group-share + HERMES_UID/GID), not a bespoke chmod
Channel identity (#95549 invariant — never normalize Beta/Dev/Canary to
stable, which would drive a different account's profile):
- detect recognized pre-release channels FIRST (Win ProgIds, macOS bundle ids,
Linux .desktop) and return UNSUPPORTED_CHANNEL
- macOS bundle match is now EXACT (was startswith); Linux/Win channel-before-
stable ordering; real_profile_data_dir/chromium_executable reject the sentinel
- _real_profile_cdp fails closed with a channel-specific message, never snapshots
Tests: channel-not-normalized (linux/darwin/windows), wrong-principal fail-closed,
backup exclusion, read-guard block/allow, snapshot dir secured. 187 browser +
222 backup/file_safety pass. Live re-verified: real Gmail inbox still loads.
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
_navigation_session_key returned the ::local sidecar key for local_browser
before the cloud-provider and auto_local_for_private_urls checks. Two
consequences:
- Every private-URL gate in browser_navigate (credential-bearing query,
_is_safe_url pre-nav, post-redirect) is keyed off the sidecar key, so a
model-supplied browser_navigate(url, local_browser=True) opened LAN
addresses in a host-side Chromium — with the real profile's cookies — even
when the user had set browser.auto_local_for_private_urls: false. Consent to
the profile is not consent to override the LAN routing opt-out; a private
URL now follows auto_local_for_private_urls exactly as without the flag.
- Without a cloud provider the bare session already is the local Chromium
(and already carries the real profile when consented), so the flag created a
second session for the same task on the same user-data-dir, which Chromium's
process singleton refuses. The flag is now a no-op there.
The existing consent/CDP-precedence tests keep their assertions; the sidecar
test now states the cloud-provider precondition it silently relied on.
Today's spill/cache-writer hardening (tools/spill_safety.py,
write_text_exclusive/ensure_spill_dir with O_CREAT|O_EXCL|O_NOFOLLOW)
migrated tools/web_tools.py::_store_full_text() — which writes to the same
cache/web directory with the same content-hash filename scheme — but left
its near-identical sibling, tools/browser_tool.py::_store_full_snapshot(),
on the pre-fix plain open()/write_text() pattern. A pre-planted symlink at
the content-hash path redirected the write onto an arbitrary user-owned
file, same as the sites that commit fixed.
Reproduced live: with a symlink planted at the exact
browser-snapshot-<digest>.txt path (predictable from the snapshot content
hash), the pre-fix write followed the link and overwrote the link's
target with the (secret-redacted but otherwise user/page-controlled)
snapshot content.
Fix mirrors _store_full_text's exact usage: ensure_spill_dir(private=False)
+ write_text_exclusive(private=False, overwrite=True) — not private since
cache/web is bind-mounted into remote backends whose container UID must
read it; overwrite=True because re-snapshotting the same page state
legitimately reuses the same content-hash name (the overwrite path
lstat-unlinks the link itself, never following it to write through).
Added a regression test planting a symlink at the exact digest path and
asserting the link's target is untouched (only the link itself gets
safely replaced by a real file). Mutation-verified: with the fix stashed,
the pre-fix code wrote the snapshot content into the symlink's target
file, reproducing the vulnerability exactly.
web_extract stopped using an auxiliary LLM long ago (deterministic
truncate-and-store), but browser snapshots still routed oversized
accessibility trees through the auxiliary web_extract model, keeping a
dead-looking aux slot alive across every config/picker surface.
- tools/browser_tool.py: remove _extract_relevant_content and
_get_extraction_model; oversized snapshots always truncate at line
boundaries, store the full tree to cache/web, and append a read_file
pointer (element refs beyond the cut live in the file)
- tools/browser_camofox.py: same — no LLM path
- Remove auxiliary.web_extract slot: config_defaults (removal note, same
pattern as session_search/PR #27590), cli.py defaults + env bridge,
gateway/run.py bridged keys, hermes config display, hermes model picker,
dashboard REST slots, desktop + web AUX_TASKS, i18n labels (en/zh/
zh-hant/ja/ar)
- Docs: env-vars, configuration, fallback-providers, browser + zh-Hans
mirrors (web-search zh-Hans was stale on the old LLM pipeline — synced
to truncate-and-store truth)
- Tests updated: aux bridge uses approval slot, browser tests assert the
LLM path is gone and stored files are secret-redacted
Per-site decisions:
1. hermes_cli/_subprocess_compat.py kill_process_tree(proc) -> None:
MIGRATED. Body now delegates to agent.deadline.kill_process_tree(proc.pid)
via a function-local import; keeps the swallow-everything fail-open
contract and the (proc) -> None signature (agent/shell_hooks.py imports
it by name; _kill_git_process_tree alias preserved). The old body is kept
verbatim as _legacy_kill_process_tree and used as fallback when the
delegation import/call fails. A final proc.kill() is retained on the
happy path so Popen bookkeeping sees the exit (matches old behavior).
2. tools/browser_tool.py _kill_process_tree(proc): MIGRATED, same pattern
(delegate + _legacy_kill_process_tree fallback). Behavior delta: the old
body sent SIGTERM then SIGKILL with zero grace between them; the shared
primitive sends SIGKILL only. With no grace period the observable effect
is identical, and the psutil descendant sweep now also reaches
agent-browser's setsid'd daemon grandchild, which killpg alone missed.
tests/tools/test_browser_npx_warmup.py's TestKillProcessTree repointed at
the legacy fallback (its assertions describe the fallback's internals).
3. tools/code_execution_tool.py _kill_process_group(proc, escalate):
MIGRATED. It was a plain parent+descendants terminate (then wait 5s +
kill when escalate=True) — expressed as two delegated calls:
kill_process_tree(pid, sig=SIGTERM), then on escalate-timeout
kill_process_tree(pid, sig=SIGKILL). Delegation failure degrades to
proc.kill(), mirroring the old psutil-failure fallback. Delta: the old
body terminated children before the parent; the shared primitive
signals the group atomically (child is a session leader via
start_new_session=True) plus an identity-aware descendant sweep —
strictly wider coverage, same signals.
4. gateway/status.py: KEPT BOTH SITES.
- terminate_pid (~l305) taskkill wrapper: NOT migrated. Its contract is
incompatible with the shared primitive — it must RAISE OSError with
taskkill's stderr on non-zero exit (callers branch on that), falls back
to os.kill on FileNotFoundError, and its POSIX branch is deliberately a
single-PID SIGTERM/SIGKILL, not a tree kill. Wrapping the bool-returning
fail-soft primitive would invert the error contract.
- reap_gateway_children (~l2029): NOT migrated. It operates on a
pre-snapshotted child list from a parent that is already dead
(psutil.Process(pid) on the parent would fail), and every signal is
wrapped in identity/ownership checks the primitive lacks: is_running()
identity, zombie skip, and the skip-if-ppid-still-equals-parent guard,
plus SIGTERM -> wait_procs -> SIGKILL staging and a reaped-count return.
The coupling is the feature; migrating would delete the safety logic.
5. scripts/run_tests_parallel.py _kill_process_tree (~l253): NOT migrated.
Dev tooling that intentionally kills by CAPTURED pgid because the direct
child is usually already reaped (psutil/pid-based primitive cannot find
it), and it avoids the psutil import on the test-runner hot path. Its
docstring already documents why psutil is the wrong tool there.
New tests: tests/agent/test_treekill_consolidation.py — delegation +
raise-swallowing tests per migrated wrapper, consumer-identity checks, and
a live end-to-end probe (setsid grandchild dies through the compat wrapper,
zero survivors).
PNG has no quality ladder, so a text-dense screenshot over the 256KB
history-embed cap (#92699 / #92783) could only shrink by halving
dimensions — 1568px dropped to ~784px and on-screen text became
unreadable, the exact fidelity screenshot QA depends on.
Add force_jpeg to _resize_image_for_vision: the two history-embed call
sites (vision_analyze native, browser_vision native) re-encode
resize-needing screenshots as JPEG so the quality ladder (85/70/50)
absorbs the byte pressure and the readable resolution survives.
Under-cap images are untouched and stay PNG; one-shot/reactive paths
keep their existing format behavior.
Flagged during the #92783 salvage review.
browser_vision's native fast path base64-encoded screenshots at full
resolution and baked them into the tool result uncapped — the exact
sibling of the vision_analyze path #92699 fixed. Apply the same
proactive 256KB/1568px resize before the embed enters reusable history.
Fail-open by design: without Pillow the resize helper falls back to raw
bytes and the compressor's keep-newest pass still retires stale embeds.
Sibling-gap follow-up for the #92725 salvage; the shared-cap approach
mirrors the policy-owner idea from #92748.
Co-authored-by: joaomarcos <joaomarcosdias444@gmail.com>
Keep extension control opt-in and preserve existing browser backends unless an exact server-bound controller is available. Centralize protocol and capability admission across API and dashboard transports, make selected-controller results authoritative, bypass stale availability caches only inside bound requests, and serialize structured results for the existing tool contract.
Add a real browser_snapshot route-table/WebSocket E2E, strict admission and ownership regressions, public configuration and protocol documentation, and tests proving feature-off/no-controller compatibility.
An explicitly stored browser.cloud_provider that names no registered
plugin now raises the honest selection-naming error instead of warning
and silently auto-detecting; the auto-detect walk (including the managed
gateway entitlement probe) runs only when no cloud_provider key was ever
written. The 'nous' selection routes to the Browser Use provider, whose
config resolver is now a strict switch: 'nous' => managed only, stored
vendor => direct BROWSER_USE_API_KEY only with a selection-naming error
when missing. Camofox is selected via browser.cloud_provider: camofox;
CAMOFOX_URL stays the server ADDRESS only and can no longer override an
explicit different selection (never-configured installs keep the legacy
env-var activation).
The orphan reaper had two gaps that let agent-browser daemons accumulate
indefinitely inside a single long-lived hermes process:
1. `_reap_orphaned_browser_sessions()` ran exactly once, before the cleanup
loop started, so a leak appearing after boot could never be recovered.
2. `owner_alive is True` skipped unconditionally. In-memory session tracking
is lost on any exception path between spawn and registration, but the
owner PID stays up — so such a daemon was skipped forever.
The daemon-side `AGENT_BROWSER_IDLE_TIMEOUT_MS` is not a backstop for (2):
it does not fire when the daemon itself is wedged, e.g. after Chrome's
framework was replaced underneath it by an auto-update.
Observed on macOS: five agent-browser daemons (96 Chrome processes) built up
over 10 days inside an 18-day-uptime hermes process, holding roughly 5 CPU
cores busy and driving the load average past 100. Four of those processes
were still running a Chrome framework version that had since been replaced
on disk, spinning at ~85% CPU each.
Changes:
- Re-run the reaper every `BROWSER_ORPHAN_REAP_INTERVAL` (300s) from inside
the cleanup loop. Cycle 0 preserves the existing startup reap.
- When the owner is alive but the session is untracked, fall back to idle
age: reap past `BROWSER_ORPHAN_GRACE_SECONDS`, defined as
`max(1h, 20 x inactivity_timeout)`. Unknown age fails safe.
- Add `_socket_dir_idle_seconds()` — the newest mtime under a session's
socket dir. Every browser command writes `_stdout_<cmd>` / `_stderr_<cmd>`
there, making it a last-activity marker that survives hermes restarts and
does not depend on in-memory bookkeeping surviving an exception path. It
scans directory entries rather than reading the directory mtime alone:
command names repeat, and rewriting an existing `_stdout_click` updates
that file's mtime but not the directory's, so a dir-mtime-only check would
report a busy session as idle and reap it.
Sessions still present in `_active_sessions` are never touched at any age,
and the new path still goes through `_verify_reapable_browser_daemon`, so
the anti-spoof / anti-PID-recycle guarantees from #14073 are unchanged.
Adds 9 tests: idle-age unit tests (including the dir-mtime regression),
spared/reaped/fail-safe cases for a live owner, the identity-guard gate on
the new path, and a periodic-reap test asserting more than one reap per
cleanup-thread lifetime.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The vision tools' call_kwargs hardcode max_tokens caps (2000 for
vision_analyze/browser_vision, 4000 for video analysis), truncating
descriptions of complex images at the cap. The centralized aux client
already omits max_tokens by default (#34845) so providers use their
model max output; these three call sites were the leftovers that
bypassed that policy.
Remove the hardcoded caps entirely — the aux client handles the
mandatory-max_tokens Anthropic wire via _resolve_anthropic_messages_max_tokens
(model output ceiling) and Gemini native omits maxOutputTokens (65K ceiling),
so no wire needs an explicit cap.
- --ignore-scripts on every real npx agent-browser invocation.
AGENT_BROWSER_NPX_SPEC is a floating ^0.26.0 range, not an exact
pin, and none of these sites passed it (unlike install.sh/
install.ps1's own npm install of the same package). Verified against
the real CLI: `npx --ignore-scripts --prefer-offline -y
"agent-browser@^0.26.0" --version` resolves cleanly on npm
11.19.0/node 26.
- _resolve_npx_bin() now checks the Hermes-managed/extended search
before a bare ambient PATH lookup, validating each candidate with
node_tool_runnable before trusting it — a bare PATH-first lookup let
a broken system npx shadow a healthy managed one with no recovery.
- warm_agent_browser_npx_cache() now runs a credential-scrubbed,
PATH-propagated environment (matching every other agent-browser
subprocess spawn) instead of inheriting the full parent environment
including every provider/gateway credential Hermes holds, and kills
the whole process tree (not just the top-level npx PID) on timeout
via the new _kill_process_tree helper, since a surviving descendant
can otherwise hold a capture pipe open past the nominal deadline.
Git-clone installs resolving agent-browser via bare npx floated latest
with no integrity check, while install.sh/install.ps1 installs stayed
pinned to ^0.26.0. Pin the npx spec to match. Also extract the
"npx agent-browser" sentinel comparison (6 call sites across two
packages) into a named constant/predicate, fix a PATH-priority
inversion where a broken system npx could shadow a healthy
Hermes-managed one at the two real npx launch sites, and stop
`hermes doctor --fix` from counting a bonus npx cache warm as a fixed
issue on an otherwise-healthy run.
warm_agent_browser_npx_cache() spawns a resolved npx.cmd via
subprocess.run with a list arg and no shell=True, which Windows still
routes through cmd.exe. Without creationflags=windows_hide_flags(),
that can flash a console window during hermes update/doctor --fix,
same as the existing agent-browser subprocess spawn elsewhere in this
file already guards against.
Adds a regression test to the cross-cutting Windows no-window-flags
audit suite so a future refactor can't silently drop the flag again.
`hermes update` was pruning root-level Node dependencies (agent-browser)
because npm ci always wipes and reifies node_modules according to its
active filter -- no root-first/workspace-first ordering or flag
combination (--workspaces=false, --include-workspace-root, etc.) can
reliably keep a root-only package.json dependency from being pruned by
a subsequent workspace-scoped npm ci. Confirmed empirically and via
npm/cli source (isArboristCmd hardcodes includeWorkspaceRoot=false for
ci/install), so no amount of install-order juggling fixes this for good.
Instead of chasing install order, remove the root-only dependencies
that made the npm step fragile in the first place:
- agent-browser is no longer a root package.json dependency. It
resolves lazily via `npx agent-browser` (tools/browser_tool.py
already had this as a fallback; it's now the primary path).
warm_agent_browser_npx_cache() is called fire-and-forget from both
`hermes update` and `hermes doctor --fix` to keep npx's cache warm,
preserving the "available before any session starts" property
agent-browser had as an eager dependency without re-entangling it
with the npm workspace graph.
- @streamdown/math moves to apps/desktop/package.json, where it's
actually imported (markdown-text.tsx, katex-memo.ts) -- it was
never used anywhere else and was subject to the same pruning risk.
- _update_node_dependencies() collapses to a single
`npm ci --workspace ui-tui --workspace web` call now that root has
no dependencies of its own to protect, and keeps its original spot
ahead of `_build_web_ui()` at both call sites in update_cmd.py --
with no root-only dependencies left to protect, there's no reason
for the Node refresh and the web build to run in any particular
order relative to each other.
- hermes_cli/tools_config.py's post-setup Chromium-install path and
hermes_cli/doctor.py's agent-browser check both now resolve through
the same PATH -> Homebrew/Hermes-managed-node -> npx cascade
(_find_agent_browser / _resolve_npx_bin) instead of hand-rolling
their own node_modules/.bin lookups, so they can't diverge from what
browser tools actually invoke at runtime.
- tests-js/package-json-lazy-deps.test.ts gets a lockfile-level check
mirroring the existing camofox one, so a future regression that
reintroduces agent-browser into package-lock.json fails this test
directly instead of relying on manual review to catch it.
Fixes#43564.
After cleaning up an expired cloud browser session, re-check under
_cleanup_lock whether another thread has already created a replacement.
If so, return the live replacement instead of falling through to create
yet another session (which would be orphaned, or worse, a second
concurrent cleanup could destroy the replacement).
Follow-up to helix4u's expired-session renewal fix in PR #76356.
Three cold-start cuts, measured with .venv python, PYTHONPATH=worktree,
median of 3-5 fresh subprocesses:
1. tools/mcp_oauth.py — availability now via importlib.util.find_spec("mcp");
SDK classes (OAuthClientProvider et al.) import lazily on first use via
_ensure_sdk_loaded(). Module-level names kept as None placeholders so the
test-patch surface (patch.object(mcp_oauth, "OAuthClientProvider", ...))
still works. import tools.mcp_oauth: 242ms -> 56ms (mcp SDK no longer
loaded at import time).
2. tools/registry.py — discover_builtin_tools AST scan memoized in an
mtime_ns+size-keyed disk cache at ~/.hermes/cache/tool_discovery_cache.json
(atomic write via utils.atomic_json_write, best-effort/never raises;
corrupt or missing cache -> full rescan + rewrite; per-file stat mismatch
-> rescan just that file). Scan of 100 files: 158ms cold -> 3ms warm.
3. tools/browser_tool.py — top-level `import requests` and
agent.auxiliary_client.call_llm moved to lazy first-use (PEP 562
__getattr__ preserves patch("tools.browser_tool.requests.get") and
patch("tools.browser_tool.call_llm") surfaces; internal call sites go
through _lazy_call_llm which reads module globals so patches are honored).
Entry-point imports (median ms, before -> after):
import model_tools 392 -> 245 (warm discovery cache)
import cli 152 -> 151 (unchanged; cli doesn't hit these paths)
import gateway.run 234 -> 230
Functional verification:
- get_tool_definitions(quiet_mode=True) under temp HERMES_HOME: identical
sorted 30-tool name set before vs after (empty diff).
- Discovery cache: delete cache -> 158ms, second run -> 3ms; corrupt cache
-> clean full rescan; touching one file -> single-file rescan (12ms).
- Tests green: tests/tools/test_registry.py, all test_mcp_oauth*,
test_mcp_dashboard_oauth, test_mcp_tool_401_handling, all
tests/tools/test_browser*.py, tests/hermes_cli/test_mcp_{config,startup,
dashboard_oauth}.py, test_skills_tool_discovery_cache.py.
Tool-schema assembly at CLI/Desktop startup runs the browser-family
check_fns (browser, browser_cdp, browser_dialog, browser_vision). Each
of those gates called _get_cdp_override(), which resolves the configured
endpoint over HTTP (GET /json/version, timeout=10) — so a *stale*
browser.cdp_url pointing at a dead debug browser cost ~7 serial blocking
socket connects before the banner rendered. Measured on a real Windows
install with a dead http://[::1]:9222 config: 15.1s of an 18s launch,
with no warning or error — just mystery slowness. The value is easy to
leave behind: /browser connect writes a session-scoped env override, but
'hermes config set browser.cdp_url' persists forever while the debug
Chrome it pointed at dies on the next browser restart.
Split the helper:
- _get_cdp_override_raw() — returns the configured value (env var or
config.yaml) with zero network I/O. Used by every is-it-configured
gate: check_browser_requirements, _browser_cdp_check, _is_local_mode,
_is_local_backend, _navigation_session_key, _should_inject_engine
(via _is_local_mode), and the hermes doctor chromium-skip check.
- _get_cdp_override() — unchanged contract (raw + /json/version
resolution), now only called on paths that are about to connect:
session creation and the dialog-supervisor attach.
This follows the existing rule in check_browser_requirements ('do not
execute agent-browser --version here') and the browser.manage status
path, which already banned _get_cdp_override for exactly this reason
(test_browser_manage_status_does_not_call_get_cdp_override): schema
assembly must not perform blocking I/O.
A/B on the same machine, same dead endpoint: get_tool_definitions()
15.08s unpatched -> 1.89s patched, with browser_cdp/browser_dialog
still advertised (gate now keys off configuration, not reachability —
matching the documented lazy-supervisor contract in
_browser_dialog_check).
Adds a regression test asserting the browser_cdp check_fn never touches
the network.
On Windows with Chinese locale (GBK), subprocess.run(text=True) without
explicit encoding causes UnicodeDecodeError crashes. This fix adds
encoding='utf-8', errors='replace' to all subprocess.run() and
subprocess.Popen() calls that use text=True across 76 non-test Python files.
Fixes#53428 (master tracker for Windows GBK locale crash).
Note: credential_pool.py and electron changes excluded per reviewer request —
those will be submitted as separate focused PRs.
The per-turn `_cleanup_task_resources` unconditionally calls
`cleanup_browser`, closing the browser window immediately after each
bot reply. This makes headed mode (`AGENT_BROWSER_HEADED=1`) unusable
— the window flashes up and disappears on every response.
This mirrors the existing VM persistence pattern: skip per-turn
cleanup when headed mode is active and let the inactivity reaper
handle idle sessions instead. Full-session teardown on gateway
shutdown remains unconditional.
Also adds `browser.headed` config.yaml support and passes `--headed`
to agent-browser in local mode when configured, so users don't need
to rely solely on the `AGENT_BROWSER_HEADED` env var.
Closes#11020 (lead bug)
John Paul Soliva