Review finding on #94633: _sanitize_label_value is lossy ('team/workspace'
and 'team_workspace' both sanitize to 'team_workspace'; >63-char keys
truncate identically), and container reuse is label-keyed — so two teams
with DIFFERENT shared keys could silently attach to one running container
(filesystem, processes, env) while their host sandboxes stayed separate.
Shared-key labels now carry a sha256 digest suffix of the raw key
(deterministic across processes; plain profile labels unchanged for
backward compat). Docs also state the first-creator-wins rule for image/
mounts on a shared container. Adds adversarial collision tests.
Follow-up on @fangliquanflq's opt-in (#84775): after the profile-scoping fix
(#94560) the container cache key is resolved in _resolve_container_task_id,
so the shared key must unify profiles there too — 'shared:<key>' for every
session of every opted-in profile AND for CLI/no-session runs. Delivery adds
the shared sandbox layout as the first translation candidate. Empty key
keeps strict per-profile isolation; SSH ignores the key entirely.
Full-screen captures carry no element tree, so the CaptureResult now has a
'note' field surfaced in the tool summary telling the model to call
capture(app='<AppName>') or capture(app='desktop') when it needs to act on
what it sees. Schema description updated to distinguish app='screen'
(composited full-screen image) from app='desktop' (shell surface with
clickable elements); docs + regression tests (14, sabotage-verified) added.
'Screenshot my screen' previously resolved the 'screen' sentinel to the OS
shell window (Progman/WorkerW) via list_windows — capturing the wallpaper +
icons layer, never the windows actually displayed. cua-driver's
get_desktop_state does a real composited full-screen grab; the
screen/fullscreen/all sentinels now route there directly, bypassing window
enumeration (which also keeps screenshots working when Windows UIA
enumeration hangs — trycua/cua#2110/#2113).
app='desktop' keeps the shell-window lane so desktop icons/taskbar stay
clickable.
Salvaged from PR #60081 by @2ndNatureAI (surgical reapply; original branch
predates the capture-routing refactor).
Commit a270c4ade's session-key fallback in _resolve_container_task_id was
added to stop cross-profile SSH environment reuse, but it wasn't backend-
gated: persistent Docker silently fragmented into one container per gateway
session, breaking the product contract (one long-lived container per profile,
shared by CLI and every session of that profile). #93950's vanishing MEDIA
attachments were downstream damage.
- persistent Docker (container_persistent: true) now keys to the profile:
literal 'default' for the default profile (same container as CLI),
'profile:<name>' for named profiles
- SSH and non-persistent Docker keep session scoping (the original leak fix
and the #82731 isolation contract are untouched)
- gateway MEDIA translation follows the profile layout and keeps the legacy
bug-window per-session sandboxes as fallback candidates, trying each until
the file resolves — old sessions self-heal, no migration
- /root/.hermes credential-surface refusal preserved across all layouts
find_spec("microsoft_teams") can be true from sibling namespace packages
while App is still None, so a failed lazy-install crashed connect with
'NoneType' object is not callable instead of a missing-SDK error.
Probe microsoft_teams.apps via the parent first — a dotted find_spec
raises ModuleNotFoundError on 3.11 when the namespace is absent.
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.
Audit finding (Blank Slate): the system prompt advertised web_search,
skill_view, todo, and the hermes-agent skill even when the toolset had
none of them — the model chases phantoms it can't call.
- hermes-agent skill is now essential: cannot be disabled (config reads
strip it, hermes tools writes drop it), cannot be deleted by
skill_manage, is re-seeded past curator suppression, and is seeded
even on .no-bundled-skills profiles (Blank Slate / --no-skills).
- Blank Slate core toolsets grow from file+terminal to
file+terminal+vision+skills: read_file cannot read images and points
at vision_analyze; the essential skill needs skill_view to load.
- HERMES_AGENT_HELP_GUIDANCE degrades to a docs-URL-only variant when
skill tools are absent.
- Execution-discipline guidance drops its web_search lines when web
tools are off (execution_guidance_text renderer).
- Skills-index preamble says 'basic tools like terminal' instead of
naming web_search when web tools are off.
- Coding operating brief drops the todo-tracking sentence when the todo
tool isn't loaded.
All gating keys off agent.valid_tool_names, fixed at session
construction — prompt stays byte-stable per session (cache-safe).
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
Follow-up to lkz-de's adapter chunking commit: long Signal messages no
longer truncate on ANY delivery path.
- tools/send_message_tool.py: register Signal's 8000-char limit in
_MAX_LENGTHS (imported from the adapter module so the two paths can't
drift) so hermes send / cron standalone / MCP sends split via the
shared truncate_message() pass instead of signal-cli rejecting them.
Standalone-path idea credited to @5L-hermes01 (#67279).
- tests: regression test proving standalone Signal sends chunk at the
adapter limit with no truncation footer (fails on pre-fix main).
- docs: Long Messages section on the Signal page (en + zh-Hans).
Both fixes verified by sabotage A/B (tests fail with the respective
half reverted to origin/main) and a real-import E2E: 27k-char message
with emoji + cross-boundary bold + code blocks -> 4 chunks, all styles
in-range UTF-16, lossless reassembly.
The docstring and all four caller comments still said the helper
refuses only / and top-level directories. Since #93757 it also refuses
the entire hermes-agent install tree. Bring the docstring and the
comments at the four credential-write call sites in line with the
actual behavior so future changes are not misled by a stale safety
description.
Follow-up to #93757.
An MCP call_tool deadline hit left the cua-driver session wedged for
all later computer-use calls. Mark the session suspect on a
concurrent.futures.TimeoutError and tear down + recreate it before the
next non-lifecycle call; healthy sessions are never restarted.
Fail-closed: the timed-out action may still have taken effect on the
remote screen, so it is never silently replayed — the error result
carries structuredContent.code=timeout_outcome_unknown with
next_step=fresh_state.
Informed by #74877 by BlackishGreen33.
Co-authored-by: BlackishGreen33 <s5460703@gmail.com>
LocalEnvironment._kill_process kills the process GROUP (SIGTERM ->
1s wait -> SIGKILL -> 2s wait), but a descendant that called setsid
escapes the group and survives — the #71148 orphan class, terminal
flavor (issue #84967's local sibling).
Fix: snapshot the descendant set via psutil BEFORE the first SIGTERM
(children reparent to init once the wrapper dies, so a later parent
walk finds nothing — same snapshot-before-signal design as
agent/deadline.py kill_process_tree), then after the existing group
escalation completes, SIGKILL any snapshotted survivor whose pgid is
no longer the (now-dead) group. The TERM->KILL grace window for
in-group members is preserved (interrupts use this path too), the
Windows branch is untouched, and the snapshot is fully guarded — a
broken psutil never breaks the kill path (unit-tested).
Tests: live_system_guard_bypass acceptance test spawning a setsid
grandchild and forcing the timeout path (RED on unmodified file,
GREEN after), plus a psutil-failure unit test.
Docker design note (#84967 open question 1, condensed; full note at
/tmp/4b-docker-design-note.md): the docker backend inherits
base.py:1378 _kill_process, which only proc.kill()s the HOST-side
`docker exec` client — the in-container tree (child of containerd-
shim, not the client) survives every timeout entirely. Option A,
`docker exec <cid> kill -- -<pgid>` with TERM->KILL escalation using
a PGID captured at command start, is surgical and preserves container
state but needs a live container + shell and still misses in-container
setsid escapees. Option B, container restart, is absolute (PID-
namespace teardown kills everything) but destroys all in-container
state mid-session and punishes every other consumer of the shared
persistent container. Recommendation: Option A as a best-effort
_kill_process override (degrade to today's behavior on failure);
reserve restart for the existing container-gone recovery path.
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).
Fixes the four poisoned-connection classes (#81051, #77765, #84132,
#81995) with the SuspectableBackend cheap-mark/lazy-verify contract:
- mark_suspect/ensure_healthy protocol (agent/deadline.py): noticing a
poisoned state never does I/O; the NEXT caller pays once for a health
probe that clears the suspicion or forces a reconnect. A single
teardown-vs-keepalive race or auth-lock corruption can no longer park
a connection permanently — park stays reserved for genuinely
exhausted reconnect budgets.
- keepalive failure marks the connection suspect before requesting
reconnect; the next tool call probes and recycles if unhealthy.
- auth-classified permanent failures on a previously-proven session get
a suspect+reconnect path instead of an immediate park.
- fast-fail (#81995): stdio child pids are tracked at spawn and an
in-flight RPC races a child-watcher task, so a dead subprocess fails
the call immediately with a retryable timeout instead of riding out
the full 300s. Deliberate teardown/reconnect also fails in-flight
calls now instead of leaving them attached to a dying transport.
Dispatch-boundary hardening for test doubles: stubbed sessions
(MagicMock/non-awaitable call_tool, absent child-watcher) fall back to
the exact pre-change inline-await semantics, so only real transports
gain the race guard.
Salvage credit: in-flight approach from #73377 (@luijoc, wedged
transport recovery) and #48069 (@arminanton, keepalive/in-flight
interaction); both PRs' bases predate main's current park/reconnect
architecture, so this is a fresh implementation of their contracts.
Tests: tests/tools/ -k mcp = 639 passed (was 22 new failures during
development; final tree zero).
Both readers of the per-server MCP tool timeout (the connection's run()
and the cache-path registration) read config.get("timeout", 300) as
their own private resolution. Route them through _resolve_tool_timeout:
per-server mcp_servers.<name>.timeout still ALWAYS wins (most specific),
then timeouts.mcp.tool_call from the unified timeouts: section, then
the unchanged 300s default. Values pass through resolve_timeout's
platform clamp; resolution failure falls back to the historical default.
Default-behavior invariance pinned by contract tests (nothing
configured -> exactly 300, per-server beats section, section beats
default, invalid/failed resolution falls back).
Simplify-pass follow-ups on the #87033 fix:
- _gateway_liveness_notice(plural=) authors both wording variants at one
site; removes the exact-substring .replace() that would silently no-op
if the create-path text is ever edited.
- Collapse the operator-precedence-trap conditional in list to a plain
'if jobs' — an empty list has nothing inert and now skips the probe.
- Fix docstring/code mismatch (builder returns gateway_running: True on
the happy path) and drop the dead try/except in
_warn_if_gateway_not_running (the helper never raises).
Follow-ups for the salvaged #93098:
- Move the tri-state liveness heuristic into hermes_cli.cron
(_builtin_gateway_liveness) so the CLI warning and the cronjob tool
share one implementation instead of two drifting copies.
- Surface gateway_running/warning on the list action too — an agent
inspecting jobs in a gateway-less environment has the same silent-
inert-job failure mode (#87033) as create. Empty lists stay quiet.
The builtin cron ticker only runs inside the gateway process. The CLI
surfaces this ('hermes cron list' / 'hermes cron status' both warn when
no gateway is running), but the model-facing cronjob tool returned a
clean success on create even with no gateway running - so the agent
confidently told the user a recurring task was scheduled while the job
could never fire.
Mirror the CLI's liveness heuristic in the tool's create path and attach
a tri-state gateway_running field to the result:
- true -> gateway running (or a non-builtin scheduler provider owns
firing, e.g. Chronos, which is exempt by design)
- false -> explicit warning telling the model the job is saved but will
NOT fire until the gateway starts, so it can relay that to
the user instead of reporting unqualified success
- null -> probe failed; claim neither way
Fixes#87033
Follow-ups on top of the cherry-picked #93532 cap:
- Regression tests: suppressed (in-cooldown) matches must NOT consume the
lifetime budget; the cap trips exactly at the Nth DELIVERED match and
promotes to notify_on_complete with the watch_disabled summary queued
right after the final match.
- Extract _emit_lifetime_watch_disabled() and emit the summary even when
the global breaker drops the final match, so the user always learns why
watching went quiet (parity with the strike-limit path).
- Mention the lifetime cap in the terminal tool docstring (the schema text
was already updated by #93532).
Refs #93513
Per-session rate limiting only counts consecutive strike windows, so a
pattern that recurs at a cadence just above WATCH_MIN_INTERVAL_SECONDS
(e.g. a service restarted repeatedly over a day) never trips the
existing strike-limit disable — each match lands in its own clean
cooldown window. Every one of those matches still forces a full-context
agent turn, which stalls the event loop on large sessions (#93513).
Add WATCH_LIFETIME_MAX_HITS: once a session has delivered this many
watch_match notifications over its whole life, disable watch_patterns
and fall back to notify_on_complete, reusing the existing disable path.
Salvage hardening on top of #93601 (with #93597 covering the same core
mechanisms) for #93590:
- _hermes_cli(): after the venv-sibling check (hermes.exe on win32),
try shutil.which('hermes') before the bare-name fallback, so
environments with a PATH but no venv sibling resolve exactly what an
interactive shell would. Platform test switched os.name -> sys.platform
('win32') per repo convention.
- tui_gateway/methods_bot_relay.py deliver: pin encoding='utf-8',
errors='replace' on both subprocess.run sites — without them the
child's UTF-8 output is decoded with the locale codec (cp1252/GBK on
Windows), mangling non-ASCII replies or raising on undecodable bytes.
- Regression tests: shutil.which resolution step, bare-name fallback
with which=None, and encoding-pin assertions in the deliver transport
test.
Refs #93590, #93597, #93601
Two failures on a Windows desktop install relaying to a remote gateway
(#93590):
1. waiter_command embeds the reply path in generated python -c source
with !r. repr escapes each backslash, but the Windows execution layer
folds \\ back to \, so \U in C:\Users\... parses as a unicode escape
and SyntaxErrors the whole waiter script. Raw-string literals keep
the folded single backslash a literal; POSIX paths have no
backslashes so the prefix is a no-op there, and \' inside a raw
literal still cannot terminate the string, keeping the #93091
injection defense intact.
2. local_delivery_command hardcoded "hermes", relying on PATH — absent
in service contexts (systemd units, desktop launchers, non-login SSH
shells), so delivery died with ENOENT. It now resolves the CLI next
to this gateway's own interpreter (venv bin/Scripts sibling,
hermes.exe on Windows) with a bare-name fallback. The #93091
per-profile turn-lock recognition in bot_mode_dm now matches the CLI
element by basename (split on both separators) so resolved absolute
paths still take the lock instead of silently bypassing it.
Fixes#93590
#93392 was not just one pattern: every hardline rule with a bare \b anchor
fired on its token anywhere in the command line, including inside quoted
prose handed to echo, git commit -m, or gh --body. Anchor the
command-name-token rules and quote-mask the positionless ones:
- dd-to-block-device and kill -1 get the same _CMDPOS anchor as the
format/rm/shutdown families, keeping their argument tails.
- redirect-to-block-device and the fork bomb have no command-name token to
anchor (`>` appears mid-command; the bomb is a function definition), so
they now match a quote-masked variant (_mask_quoted_prose) where quoted
string content is blanked. $() and backtick spans inside double quotes
stay raw (the shell executes them), and any command whose command-position
words include a shell carrier (sh/bash/zsh/ksh/dash -c, eval, source, .)
is scanned unmasked -- quoting is not a bypass. bash/sh -c payloads also
still surface as raw detection variants via _execution_flag_findings.
Regression tests cover both directions for every touched pattern: quoted
prose passes, and every true-positive shape (bare, ; && | separators,
sudo/env prefix, $(), backticks, sh -c/bash -c/eval payloads) stays on the
unconditional floor.
mkfs was the only HARDLINE_PATTERNS entry without a _CMDPOS anchor, so
the unconditional floor blocked any command that merely mentioned the
token inside quoted prose — `echo "does this workflow use mkfs
anywhere?"` was refused outright (#93392) instead of running the echo.
Anchor mkfs to command position like every sibling entry (rm root-
delete, shutdown family, dd): it matches at the start of a command,
after separators, or behind sudo/env/exec/nohup/setsid wrappers, and
no longer fires on argument-position mentions. The quote-aware
_mark_command_starts pass already keeps separators inside quoted
strings from looking like command starts, and \b still protects
mkfs_helper-style names.
- Reject cron jobs with empty runnable payload (blank prompt, no script, no skills) on create and update
- Auto-pause legacy unrunnable jobs at schedule time to prevent infinite fire loops
- Prevent blank name string in cron update tool from unintentionally wiping job names
- Add comprehensive test coverage (34 tests)
Hoist the sandbox-directory sanitizer into tools/environments/base.py as
sanitize_task_id_for_path() and route BOTH host-path consumers through it:
the docker persistent sandbox (get_sandbox_dir()/docker/<id>) and the
singularity persistent overlay (hermes-overlays/overlay-<id>). One helper,
one mapping, whole bug class fixed in one place instead of per-backend
copies (#92414, #92640, #93044).
docker.py keeps _sandbox_dir_name as an alias of the shared helper so the
sanitized mapping (safe ids verbatim, digest suffix on rewrite for
collision safety) is unchanged for existing sandboxes.
Co-authored-by: salch-cred <salch-cred@users.noreply.github.com>
Co-authored-by: Parker Fawcett <259203091+Parker-Fawcett@users.noreply.github.com>
With terminal.backend: docker and container_persistent: true, every gateway
session failed on its first tool call: docker run exited 125 with
"invalid spec ... too many colons" and no command could execute.
_resolve_container_task_id() returns "session:<key>" whenever a session key
is present, and gateway session keys are colon-delimited
(session:agent:main:telegram:dm:<chat_id>). DockerEnvironment joined that id
into the persistent sandbox path verbatim, so the -v spec became
".../docker/session:agent:main:telegram:dm:<id>/home:/root" — docker splits a
spec on ':', read the extra fields as extra mount options, and refused the
run. The container label a few lines below already guards this exact value
class via _sanitize_label_value(); the bind-mount source did not.
Derive the directory name through _sandbox_dir_name() instead. Ids that are
already bind-mountable are returned verbatim, so the shared "default" sandbox
and RL/benchmark rollouts keep their existing directory and no installed
package or /root state moves; only ids that could never have produced a
working mount are rewritten. A rewrite carries a digest of the original id,
because ':' -> '_' alone is not injective and would otherwise collapse two
chats onto one persistent /root.
Review feedback on #93149:
- _cmd_unpin now checks set_pinned's return (same false-success defect
existed symmetrically on the unpin path)
- curated_report() pinned-visibility branch requires a local skill dir,
so stale records for deleted dirs don't render as ghost rows
- test 2 asserts rc==0 unconditionally instead of vacuous-passing
- error message points to list-unmanaged (status doesn't render reasons)
`hermes curator pin <skill>` printed success even when the underlying
write never landed. set_pinned() routes through _mutate() with
require_curation_eligible=True, which silently returns None for skills
that pass is_agent_created() but fail is_curation_eligible() — e.g. a
user-created skill named "plan", which PROTECTED_BUILTIN_SKILLS blocks
by name. The CLI then announced a pin that does not exist (#92993).
Also, a pin that DID land on an eligible-but-unmanaged skill (no
created_by marker) was invisible: curated_report() only iterated
list_agent_created_skill_names(), which requires the management marker,
so the skill showed up under 'unmanaged' with no trace of its pin.
- set_pinned() now returns bool write success; _cmd_pin() checks it,
exits nonzero and explains the refusal when the write did not land
- curated_report() additionally includes curation-eligible skills whose
usage record carries pinned=true, so their pins are visible in status
Fixes#92993
message_agent callers previously got provider prose (a raw 401
paragraph, a missing-provider essay) and could not branch on the
failure class. Now the #93091 item-1 reason enum rides the whole relay
roundtrip:
- Desktop relay drain forwards bot_relay.deliver's error.data.reason
into bot_relay.reply (and prefers it for the attention badge over
free-text re-parsing);
- write_reply already persisted reason / classified fallbacks;
- the sender-side waiter prints "[reason: <code>]" ahead of the free
text, so the completion notification the sending agent receives is
machine-branchable.
Additive everywhere: healthy replies unchanged, reasonless errors
classify to a code, old consumers keep working.
_auth_env fell through to os.environ on a scoped miss, so one profile
could inherit another profile's allowlists and allow-all flags.
bot_relay.waiter_command put connection_id into python -c source. A
quote in the id broke the waiter. A crafted id could run extra Python
in the sender gateway.
Maintainer ruling (2026-08-23): a retried bot turn never mints a fresh
session. retry_action() maps the #93091 item-1 reason enum to one of
resume / compress_then_resume / none:
- transient classes (runtime_offline, delivery_timeout, rate limit,
server error) re-run the same Bot Chat session once;
- context_overflow also re-runs the same session — the retried turn
goes through the pre-API compaction pass in conversation_loop.py,
which compacts the over-threshold transcript first (the one
sanctioned context mutation); no fresh-session escape hatch exists;
- auth/quota/config/model classes never auto-retry.
Wired at both delivery surfaces (fix the class, not one site):
bot_relay.deliver (relay handler) and _run_delivery (local
message_agent runner). Failed deliveries now carry the classified
reason in the structured error payload (error.data.reason).
Sabotage-verified: with the retry blocks removed, 3 consumer tests
fail; with them present, 22/22 pass.
Widened from /review to the class: _build_child_system_prompt now runs
the parent's resolved workspace_path through
agent.prompt_builder.build_context_files_prompt (same discovery/
priority/caps as the main system prompt: .hermes.md > AGENTS.md chain >
CLAUDE.md > .cursorrules; SOUL.md skipped) and embeds the result as
binding conventions. All delegate_task children get it — reviewer
included — since children are built with skip_context_files=True and
previously worked in repos without the repo's own conventions.
The review-engine-local load_workspace_context duplicate is removed;
the reviewer inherits the block via the shared child prompt path.
workspace_path comes only from explicit sources (_resolve_workspace_hint
— TERMINAL_CWD / agent cwd hints, never bare getcwd), so the #64590
install-tree-fallback guard concern doesn't apply.
Tests moved to pin the generalized path (real-filesystem AGENTS.md via
_build_child_system_prompt, empty/no-workspace negatives, reviewer E2E
through start_review). Docs: subagent-context section + /review flow
(en + zh-Hans).
delegate_task children run on worker threads of the parent process and
inherit the process-wide HERMES_INTERACTIVE=1 the CLI sets at startup.
_transform_sudo_command's interactive gate therefore fired inside
children with no sudo callback registered, falling through to the raw
/dev/tty password prompt: a password box printed mid-TUI from a
background thread, parallel children racing for the tty, and each child
blocked for the full 45s timeout.
Gate the prompt (and the sibling 'you will be prompted again' message
after an auth failure) on agent.delegation_context.is_delegated_child_context(),
the ContextVar set around every child run and propagated through
contextvars.copy_context onto the executor thread. Children now behave
as headless for sudo: configured SUDO_PASSWORD, the session cache, and
the NOPASSWD probe still work; otherwise the command fails gracefully
with a subagent-specific tip.
A/B verified: 3 regression tests fail on merge-base, 7/7 pass at head.
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.
When the managed openai-audio gateway is unavailable,
_resolve_openai_audio_client_config() raises a ValueError that names the
blocker (and, for managed-Nous users, the `hermes tools` remediation).
The boolean probe in _get_provider's explicit-openai branch flattened
that into False, so the log claimed "no API key available" and the
transcription result returned the all-provider install hint -- pointing
operators at unrelated setup instead of their managed route (#93045).
Resolve the config directly in the branch so the warning names the real
blocker, and let the dispatch's "none" fallback surface the
selection-specific error for an explicit openai choice. No fallback is
added: an unavailable selection still resolves to "none", it just
reports why.
Teknium