electron/main.cjs is the worst god file in the desktop app (~7.6k lines, 93 IPC
handlers across unrelated domains). Begin peeling cohesive handler clusters into
sibling modules — the established main.cjs pattern.
First cluster: the 19 git/worktree/review IPC handlers (all thin delegators to
the existing git-*-ops modules) move into a new electron/git-ipc.cjs exposing
registerGitIpc({ ipcMain, resolveGitBinary, resolveGhBinary }). The git/gh
binary resolvers stay in main.cjs (Windows PATH discovery) and are injected, so
the new module is pure. Channel names are unchanged, so preload/renderer are
unaffected.
Adds electron/git-ipc.test.cjs (wired into test:desktop:platforms) asserting
the full channel surface and resolver delegation. main.cjs: 7,617 -> 7,530.
agent.coding_instructions (a string or list) is appended to the coding brief as
its own stable system block, so users can pin project-wide workflow rules
without editing the shipped brief. Coding-posture only and cache-safe (resolved
once per session; takes effect next session). Empty by default.
Add a `pre_verify` user/plugin/shell hook fired once per turn when the agent
edited code and is about to finish, after the existing verify-on-stop guard. A
hook can keep the agent going one more turn (run a check, defer it, tidy the
diff) by returning {"action":"continue","message":...} (the Claude-Code Stop
shape {"decision":"block","reason":...} is accepted too). Hooks receive coding,
attempt, final_response, and sorted changed_paths so they can self-scope and
self-throttle; the path is bounded by agent.max_verify_nudges and preserves
message-role alternation.
Hermes still ships its default coding guidance (agent.verify_guidance, on by
default), but it now rides the evidence-based verify-on-stop missing-evidence
nudge instead of a separate default pre_verify continuation, so it costs no
extra model turn of its own. Guidance reuses the shared utils.is_truthy_value
parser rather than a local copy.
Follow-up to the judge gate. judge_goal() is fail-open at the source:
when no auxiliary model is reachable it returns a "continue" verdict
that is indistinguishable from a real "not done yet" judgment. The gate
treated any non-"done" verdict as a rejection, so an unconfigured or
degraded auxiliary model would wedge every goal_mode worker — it could
never close its own task. That contradicted the gate's own "fail-open"
comment.
Probe judge availability before enforcing (the same auxiliary client
lookup judge_goal performs) and only gate when a judge is actually
reachable. When none is, completion proceeds.
Also fix the rejection guidance: kanban_create takes parents=[...], not
parent=.
Add test_complete_goal_mode_allows_when_judge_unavailable covering the
fail-open path; update the rejection test to force the availability probe.
Apply naqerl's review comments on PR #38388:
- Hoist `from hermes_cli.goals import judge_goal` to module-level
imports so an import failure surfaces at module init, not lazily
on the first goal-mode completion (no circular import: hermes_cli
package init is trivial and does not load tools.kanban_tools).
- Narrow the fail-open `try` to wrap only the judge_goal() call.
The verdict check and its rejection `return tool_error(...)` now
live outside the handler, so a failure there can no longer be
swallowed by the broad except.
- Pass `exc_info=True` to the logger.warning call per CONTRIBUTING.md.
Update the test mock target to tools.kanban_tools.judge_goal, since
the hoisted import rebinds the name into this module's namespace.
Prevents workers in goal_mode from bypassing the auxiliary judge by
calling kanban_complete before acceptance criteria are met. The tool
handler now synchronously invokes the goal judge against the task's
title/body and the completion summary. If the verdict is not "done",
the completion is rejected with actionable guidance for the agent.
This keeps kanban_db.py as a pure SQLite wrapper while intercepting
the bypass exactly at the agent tool-call boundary, aligning with
Hermes separation of concerns.
Fixes#38367
Co-authored-by: CommandCodeBot <noreply@commandcode.ai>
The Cmd-K "Install theme…" palette listed Marketplace themes with no hint
that you already had them, and clicking one re-downloaded + re-installed a
theme you owned. The Appearance settings grid already detected this, but by
parsing theme descriptions inline on every render — plumbing that never made
it to the palette.
Lift it into one reactive source and reuse it everywhere:
- $marketplaceInstalls (computed over $userThemes): extensionId -> installed
theme, derived once via marketplaceIdOf and memoized, instead of rebuilding
a Set per render.
- Both install surfaces now mark owned rows installed and, on click,
re-activate the installed theme rather than re-fetching it.
- Drops the duplicated description-parsing in settings and the per-session
"installed here" state in both surfaces (the store is the source of truth,
so previously-installed themes show correctly too).
Add a generic per-platform PlatformConfig.typing_indicator flag (default
True) that gates the _keep_typing refresh loop in
_process_message_background. When false, the loop is never spawned, so no
typing/"is thinking…" status is shown on that platform — message delivery
is otherwise unchanged.
Mirrors the gateway_restart_notification contract exactly: dataclass field
+ to_dict/from_dict (with extra-fallback resolution) + shared-key bridge in
load_gateway_config, so 'slack: typing_indicator: false' under platforms
works without a separate block. Generic by design — the same key works for
every platform (Slack 'is thinking…', Telegram/Discord/Signal typing).
Motivated by users who find Slack's assistant 'is thinking…' status noisy
(it also briefly disables the compose box, via the Assistant API).
degraded is the same wedge class as draining: the gateway came up with
some platforms queued for retry, fell through to the running state
(gateway/run.py #5196), and is serving. A hard-kill there strands
gateway_state=degraded, which (like draining) is not in _AUTOSTART_STATES
and is not an operator stop or a failed boot — so it would stay DOWN
forever on every recreate. Add degraded to _TRANSIENT_RUNNING_STATES so
the fallback path normalises it to running-intent too.
A gateway hard-killed while draining (a container/VM recreate SIGTERMs it
before _stop_impl reaches its terminal-state persist) leaves
gateway_state.json frozen at 'draining'. With no explicit desired_state to
fall back to, container_boot read that transient value literally, found it
not in _AUTOSTART_STATES, and left the gateway DOWN on every subsequent
boot — dashboard up, messaging silently dark. Observed on a relay-opted-in
staging instance (2026-06): the s6 gateway-default slot kept its 'down'
marker across recreates and the gateway never came back.
'draining' is a transient sub-state of RUNNING (written by the drain
watcher / scale-to-zero go-dormant path), never an operator stop and never
a failed boot. Normalise it to 'running' in the gateway_state fallback so a
stranded drain marker reads as the run-intent it represents. This extends
gateway/run.py's #42675 handling (persist 'running' on an unexpected signal)
to the case where the gateway died before persisting anything at all.
'starting'/'startup_failed' are deliberately NOT normalised — those mean a
mid-boot death and must stay down to avoid the crash-loop the down-marker
guard prevents. An explicit desired_state still wins verbatim, so an
operator stop survives a transient 'draining' runtime value.
Tests: draining named-profile + default-root autostart (both fail without
the fix), plus a guard that an explicit desired_state=stopped still blocks a
draining runtime.
Port the two genuinely-novel ideas from Command Code's /design skill into
our existing claude-design skill (skill-only, zero model-tool footprint):
- Surface-First: commit to one of 7 surface archetypes (Monitor/Operate/
Compare/Configure/Decide/Explore/Command) before any visual tokens. Most
AI design slop is compositional, not cosmetic — conditioning generation on
a surface choice collapses entropy the way a CoT step does. Workflow step 3.
- Slop Diagnostic: the ~10 tells that account for ~90% of the 'this is AI'
signal, as a score-out-of-10 self-audit. Diagnose-then-treat: the report is
context not a to-do list; repair only what fired, matched to the tell
(re-layout vs recolor vs de-decorate). Workflow step 7 (Verify).
Did NOT clone /design's 16-mode CLI, proprietary reference corpus, or make it
a core tool. Docs page regenerated via generate-skill-docs.py.
Add durable public-URL output and URL-based chaining to xAI Grok Imagine:
- Store generated media on files-cdn with permanent public HTTPS URLs
(public_url: true, no expiry by default).
- Chain by URL: generate -> edit -> extend each take a prior result's
public HTTPS URL (or a data URI / local file for inputs).
- Add provider-specific xai_video_edit and xai_video_extend tools.
- Image generation: public-URL/storage output, multi-reference edits,
and ~/ local-path support for image edits.
Credentials use xAI Grok device-code OAuth (separate PR).
A Slack user/legacy token (xoxp-...) makes auth.test resolve to the
installing human's member ID with no bot_id, so the adapter binds its
identity (_bot_user_id / _team_bot_user_ids) to that human. Every
"is this the bot?" check then misfires: that person's <@...> mentions
wake the bot and are stripped as the bot's own mention, so the agent is
genuinely told it was @mentioned and replies to messages merely
addressed to that human (symptom: bot responds to "@trevor ..." and
insists it was explicitly mentioned).
There is no runtime API error to catch — a user token still
sends/receives — so the only detectable moment is connect time. Add a
warning-only nudge (_warn_if_not_bot_token) alongside the existing
group-DM scope nudge: when auth.test resolves a user_id but no bot_id,
log that the token is a user token and to use the xoxb-... Bot User
OAuth Token. Warning-only: does not block a working-but-misconfigured
install. Fires once per workspace per process.
DRY: the roomier-side bias computed its probability two ways
(STROLL_TOWARD_ROOM and 1 - STROLL_TOWARD_ROOM). One draw XNOR'd against
the roomier side says the same thing more plainly.
The floating pet wandered almost constantly: every idle beat picked a new
walk and hops fired ~45% of the time, so it read as nervous rather than
alive. Make movement the exception, not the default, and split the
overgrown roam hook into focused modules.
Behavior (per ambient game-AI: GameAIPro ch.36 + idle/wander state
machines):
- Loaf, don't pace: most decision beats just keep resting (REST_CHANCE
0.62) instead of always re-walking.
- Memoryless dwell: pauses now draw from an exponential distribution
(mostly short rests, the occasional long loaf) instead of a uniform
1.8-5.2s window, so the cadence never reads as a metronome.
- Hops dialed back 0.45 -> 0.2 (the jumpiest, noisiest motion).
Structure (no god-file; a hook should own one narrow job):
- roam-behavior.ts - what to do & when (dwellMs, chooseMove,
pickStrollTarget) + tuning. Pure, rng-injectable.
- roam-geometry.ts - where it can stand (snapshotLedges, overlayLedge,
resolveLedge, overlapsX, groundTop). DOM measurement + pure ledge math.
- use-pet-roam.ts - the physics/RAF loop only.
Tests: deterministic, rng-seeded unit coverage for the decision + geometry
helpers (behavior contracts, not snapshots).
Channel users get the same context split the desktop popover shows
(PR #54907) — system prompt, tools, rules, skills, MCP, subagents,
memory, conversation — under the existing Context line in /usage.
Reuses agent.context_breakdown.compute_session_context_breakdown, so
there is no new tool and no new engine. The slices are estimates
(chars/4) and the block is labelled _(estimated)_; the headline
Context line keeps using the provider-measured last_prompt_tokens.
Rendering is fail-open: any engine error returns no breakdown and the
rest of /usage is unaffected.
- gateway/slash_commands.py: _context_breakdown_lines() helper + wire
into _handle_usage_command
- locales/*.yaml: breakdown_header, breakdown_line, and 8 category
labels across all 16 locales (parity gate)
- tests/gateway/test_usage_command.py: render + fail-open coverage
The self-hosted OIDC dashboard provider was public-client + PKCE only, with
two `# TODO(confidential-client)` seams. Authentik and Keycloak commonly
default a new OIDC client to *confidential*, whose token endpoint rejects an
unauthenticated exchange (`invalid_client`) — so a self-hoster who accepts
their IDP's default could not complete dashboard login without manually
flipping the client to public.
Add optional confidential-client support:
- New optional `client_secret` (env `HERMES_DASHBOARD_OIDC_CLIENT_SECRET`,
or `dashboard.oauth.self_hosted.client_secret`; env-wins-config, empty
treated as unset). It is a credential, so docs steer operators to the
`.env` file; config.yaml is supported only for precedence symmetry.
- `_token_endpoint_auth()` selects `client_secret_basic` (HTTP Basic header)
vs `client_secret_post` (form body) from the IDP's advertised
`token_endpoint_auth_methods_supported`, defaulting to basic (the OIDC
default) when absent. Applied to complete_login, refresh_session, and
revoke_session (RFC 7009 §2.1).
- PKCE is sent in BOTH modes — the secret is client authentication layered
on top, never a replacement (OAuth 2.1 / RFC 9700 keep PKCE mandatory).
- Basic header url-encodes client_id/secret before base64 per RFC 6749
§2.3.1, so reserved chars (`:`, `@`, space) round-trip correctly.
Non-breaking: with no secret configured the provider is a pure public PKCE
client, byte-identical to prior behaviour (no Authorization header, no
client_secret in the body). The secret is never logged — register() reports
only a `confidential=<bool>` flag.
Tests: 16 new cases covering basic/post selection, default-when-absent,
public-unchanged contract, PKCE-preserved, reserved-char url-encoding,
blank-secret-is-public, refresh + revoke auth, no-secret-in-logs, and
env/config register wiring. Full dashboard-auth suite (nous provider,
middleware, gate, cookies, WS, 401-reauth, status endpoint) — 396 tests —
green, proving no existing auth path regressed.
* feat(display): friendly human-phrased tool labels for built-in tools
Built-in tools now render ChatGPT-style status verbs ('Searching the web
for ...', 'Reading <file>', 'Browsing <url>') on the CLI spinner and
gateway/desktop tool-progress instead of the raw tool name.
- agent/display.py: _TOOL_VERBS map + build_tool_label() + set/get
friendly-labels flag (default on). Custom/plugin/MCP tools fall back to
the raw preview; verbose gateway mode left untouched (debug surface).
- tool_executor.py / tui_gateway / gateway: route the three spinner sites,
the TUI _tool_ctx, and the gateway all/new progress line through the label.
- config: display.friendly_tool_labels (default True, per-platform aware).
Zero new core tool / schema footprint — pure display layer.
* docs: add PR infographic for friendly tool labels
* fix(display): preserve arg preview in gateway friendly labels + update tests
The first gateway pass re-derived the label from the callback's `args`, which
is empty ({}) at the gateway tool.started callsite — the command/query lives in
the `preview` string, so terminal rendered as a bare '💻 Running' and dedup
collapsed consecutive commands. Now the gateway prefixes the verb onto the
already-computed preview via get_tool_verb/tool_verb_connector/verb_drops_preview,
preserving the command/url/query. CLI spinner path (real args) keeps build_tool_label.
Tests: update test_run_progress_topics exact-format assertions to the friendly
form ('💻 Running pwd'), add a format-agnostic preview extractor for the
truncation tests (works for both quoted-legacy and verb-prefixed output).
* test(tui): update resume-display context to friendly tool label
_tool_ctx now uses build_tool_label, so the desktop resume-view context for a
search_files turn reads 'Searching files for resume' instead of the bare
'resume' preview — consistent with live tool-progress. Update the assertion.
* test(tui): harden no-race worker test against sibling shard leakage
test_session_create_no_race_keeps_worker_alive flaked under -j 8: a daemon
build thread leaked from a prior session.create test in the same shard process
fires close/unregister against its own (foreign) session_key after this test
patches the global approval hooks, polluting the captured lists. Scope the
assertions to this session's own session_key so the regression intent
(this session's worker/notify must survive) is preserved while the test
becomes immune to shard composition. Not related to friendly-tool-labels.
Gateway half of relay-platform-parity Phase 2.5 (D-Q2.5). The relay wire's
platform-neutral scope discriminator is renamed guild_id → scope_id; this is the
hermes-agent side of the cross-repo wire-compatible migration.
- SessionSource: scope_id is canonical; guild_id kept as @deprecated alias.
__post_init__ mirrors the two so all existing SessionSource(guild_id=...)
constructors across native adapters keep working unchanged. to_dict dual-WRITES
scope_id+guild_id; from_dict dual-READS scope_id ?? guild_id.
- relay/adapter.py: capture + outbound metadata dual-read/write scope_id.
- relay/ws_transport.py: _frame_to_event dual-reads scope_id ?? guild_id.
- docs/relay-connector-contract.md: document scope_id (canonical) + guild_id
(deprecated alias) in the §3 SessionSource field table (conformance test).
250 relay+session+contract tests green. Solo lane (relay).
The self-hosted OIDC dashboard login rejected any http:// redirect_uri
whose host was not localhost/127.0.0.1, surfacing "redirect_uri may only use http:// for localhost/127.0.0.1" before reaching the IDP. This broke self-hosted dashboards reached over plain HTTP (including LAN IPs, internal hostnames, and reverse proxies that terminate TLS upstream).
#38827 already dropped this check from the nous provider, but the generic self-hosted provider copied the old localhost-only
branch and reintroduced the bug for HERMES_DASHBOARD_OIDC_ISSUER setups.
The IDP's own allowlist is authoritative on which redirect_uris are
permitted; this client-side _validate_redirect_uri is only a fast-fail for
obvious operator error and should not second-guess valid http:// deployments.
Fix: drop the localhost-only branch on the http scheme. Validation now enforces only that the scheme is http(s) and the path ends with
/auth/callback. Updated the docstring to explain the relaxed contract,
and added test_allows_http_with_arbitrary_host covering an internal
hostname and a LAN IP alongside the existing localhost case.
The topic-mode helpers (_telegram_topic_mode_enabled,
_recover_telegram_topic_thread_id, _record/_sync_telegram_topic_binding,
_is_telegram_topic_lane/_root_lobby, _normalize_source_for_session_key,
_telegram_topic_new_header, _schedule_telegram_topic_title_rename, and the
base.py _apply_topic_recovery hook) each run a synchronous SessionDB read or
write. They reach the event loop through async handlers, so a contended
state.db froze the loop the same way the handoff watcher did.
These helpers already run off-loop in the run_sync thread-pool closure, so
they are proven thread-safe there. Rather than colour them async, loop-side
callers now invoke them via asyncio.to_thread(...); the executor callers are
unchanged. Inside the helpers the SessionDB handle is unwrapped to the sync
door (getattr(db, '_db', db)) since they always run on a worker thread, and
AIAgent construction + query_session_listing are handed the sync SessionDB
directly. base.py wraps its single _apply_topic_recovery call in to_thread.
The guard is now alias-aware (catches db = getattr(self, '_session_db', None);
db.method(...)) and enforces the offload contract: the offloaded sync helpers
may never be called bare on the loop. Sibling test fixtures wrap their injected
SessionDB in AsyncSessionDB to match how the gateway holds it.
The migration's call-site sweep keyed on the literal self._session_db.
spelling and missed calls bound to a local first
(db = getattr(self, '_session_db', None); db.method(...)). Convert the
three in async contexts: get_telegram_topic_binding in the topic-rename
coroutine, and the two update_session_model sites on the model-switch path.
* fix(gateway): skip confirmed-dead delivery targets (deleted groups, blocked bots)
A deleted Telegram group, kicked/blocked bot, or deactivated user keeps
throwing Forbidden/not_found on every cron tick and fan-out delivery. Each
retry burns a send against the platform's flood-control envelope and spams
the logs, making the whole session feel broken even when the model call
completed.
Add a small persistent DeadTargetRegistry (per-profile JSON under
HERMES_HOME) that records a target the moment a send reports a whole-chat
death (forbidden / chat-level not_found), and have DeliveryRouter.deliver()
short-circuit it on subsequent attempts. Self-healing: any successful send
clears the flag, so a user re-adding the bot recovers with no manual cleanup.
Thread/topic-level not_found is NOT recorded (adapters already self-heal that
by retrying without reply_to). Transient/timeout errors are never marked dead.
* infographic: dead delivery target skipping
When a full-screen route overlay (settings/profiles/cron/agents/command-center) is up, the pet's walkable surface swaps to a single ledge at the overlay card's bottom edge — derived from OverlayView's shared inset, not measured — so it patrols there; closing the overlay restores the normal surfaces and it drops back down.
Walk speed is derived from the sprite's animation loop + on-screen size (one body-width per loop) instead of a fixed px/s, so it steps rather than glides; the pet also sinks a few px so its feet meet the surface instead of hovering.
Match the Restart Gateway flow with a confirm dialog that fetches cached
update metadata so users see commit-behind context before applying.
Co-authored-by: Cursor <cursoragent@cursor.com>
Prompt before restarting from the sidebar system menu, and replace native
checkboxes on the System page with the design-system Checkbox component.
Co-authored-by: Cursor <cursoragent@cursor.com>
Use momentum easing for sidebar transitions, switch sidebar typography to
sans-serif, replace the profile native select with the DS Select, and stop
clipping the Models page Use-as dropdown inside model cards.
Co-authored-by: Cursor <cursoragent@cursor.com>
Make Nous Blue terminal text readable without the inversion layer, re-mount
the backdrop plugin slot, and drop unused backdrop CSS vars from theme apply.
Co-authored-by: Cursor <cursoragent@cursor.com>
Drop the CSS lens overlay (blend modes, noise, inversion) and backdrop-blur
from the ops dashboard so compositing no longer competes with xterm on /chat.
Use flat theme backgrounds and direct Nous Blue palette colors instead of
FG-inversion authoring.
Co-authored-by: Cursor <cursoragent@cursor.com>
usePetRoam re-measures ledges from the live DOM each beat and walks/hops/falls between them, driving DOM position imperatively (no per-frame re-render).
Opt-in $petRoam (localStorage), $petMotion (run/jump pose) and $petRoamDir (-1/0/1) feed the shared $petState only while the agent is at rest ($petAtRest), so a wander never overrides real activity.
Add a generic suppress_notification flag to the drain-request marker. When a
drain that ends in process exit (e.g. a NAS auto-update image migration on the
always-on Hermes Cloud fleet) is flagged, the gateway skips ONLY the
home-channel 'gateway shutting down' broadcast — the operator-flavoured ping
that would otherwise fire on every routine auto-update, dozens of times a day.
The per-active-session interrupt ping is ALWAYS kept: on a drained shutdown
it's empty by construction, and in the force-interrupt (deadline-exceeded) case
it carries the user-valuable 'your task was cut off, message me to resume' hint.
The gateway stays agnostic about WHY a drain is quiet (generic boolean, not a
kind enum); the policy of which drain causes set the flag lives in the caller
(NAS). Default-false so legacy/operator drains behave exactly as before. The
reader reuses the NS-570 epoch-staleness check so an orphaned marker on the
durable volume can never silence a fresh gateway's legitimate broadcast.
- drain_control.py: write_drain_request gains suppress_notification; new
drain_notification_suppressed() reader (current-epoch + truthy flag).
- web_server.py: /api/gateway/drain reads + echoes the flag.
- run.py: _notify_active_sessions_of_shutdown skips the home-channel loop only.
Tests prove: flag round-trips; home-channel suppressed when set, kept when
unset; active-session ping always fires; stale/legacy/corrupt markers never
suppress.
The Gateway item is the only statusbar entry with variant === 'menu'.
Since da73223f4 wrapped every render branch in `Tip`, the menu branch
nested `<DropdownMenu>` (a Radix Root that renders no DOM node) inside
`Tip`'s `<TooltipTrigger asChild>`. With no element to attach to, Radix
could never wire hover listeners, so the tooltip silently never showed.
`Tip` also can't be moved inside `DropdownMenuTrigger asChild` (the shape
proposed in #54859): it's a plain component, not a Slot-forwarding one, so
the trigger's injected ref/handlers would land on `TooltipContent` instead
of the button and break the menu's click + popper anchoring.
Fix by composing both trigger Slots directly onto a single <button>
(`TooltipTrigger asChild` over `DropdownMenuTrigger asChild`), the pattern
already used in profile-switcher.tsx, and skip the tooltip wrapper entirely
when the item has no title.
Supersedes #54859.
Co-authored-by: wnuuee1 <wnuuee1@users.noreply.github.com>
Subagent session pop-outs (`watch=1`) spectate a run driven elsewhere, so
editing/steering the transcript from there makes no sense. Gate the composer
and the user-bubble mutations on `isWatchWindow()`:
- hide the composer (folds into `showChatBar`)
- user prompts become a read-only button that toggles the 2-line clamp so long
prompts stay fully readable, instead of opening the edit composer
- drop the stop/restore actions and the checkpoint branch-picker
Keyed off the narrow `isWatchWindow()` (not `isSecondaryWindow()`), so the
new-session and cmd-click pop-outs are unaffected.
* feat(web_extract): truncate-and-store instead of LLM summarization
web_extract no longer runs an auxiliary LLM over scraped pages. The extract
backends (Firecrawl/Tavily/Exa/Parallel) already return clean, boilerplate-
stripped markdown, so we return it directly: pages within a char budget
(default 15000, web.extract_char_limit) come back whole; larger pages get a
head+tail window plus an explicit footer giving the stored full-text path and
the read_file call to page through the omitted middle. The full clean text is
written to cache/web (mounted read-only into remote backends like the other
cache dirs), so nothing is lost.
Inline base64 images are converted to [IMAGE: alt] placeholders (token bombs
dropped) while real http(s) image URLs are preserved as links so the agent can
still web_extract/vision_analyze them.
Removes process_content_with_llm + the chunked summarizer + check_auxiliary_model
+ _resolve_web_extract_auxiliary. context_references._default_url_fetcher is
updated to the truncate path and its stale data.documents shape read is fixed
to results (it was silently returning empty).
Live before/after eval (firecrawl, 4 URLs): 11.7x faster overall (176.6s ->
15.1s); 10-60x on large pages. Quality identical; findability 4/4 (answer
recoverable from stored full text on every truncated page). web_search is
unchanged.
No own scraper added; no changes to web_search.
* fix(web_extract): add char_limit to execute_code web_extract stub
The new web_extract char_limit param must appear in the code_execution_tool
_TOOL_STUBS signature (and doc line) or test_stubs_cover_all_schema_params
fails — the stub schema must cover every real schema param.
A manually-installed venv inside the cloned repo can be destroyed by the
agent running a relative-path command against its own checkout (rm -rf venv,
uv venv venv, etc.), silently wiping the running runtime mid-session. Moving
the canonical manual-install venv to ~/.hermes/venvs/hermes-dev means no
relative path from the agent's workspace resolves to its own runtime, making
the bug class impossible without any command-detection code.
Closes the root cause of #7779. The managed install.sh layout is unchanged.
Let users click the status bar context indicator to see how tokens are
split across system prompt, tools, rules, skills, MCP, and conversation.
Co-authored-by: Cursor <cursoragent@cursor.com>
NVIDIA integrate.api.nvidia.com models such as minimaxai/minimax-m3 can
return HTTP 200 with empty choices when max_tokens is omitted. Keep the
output cap on auxiliary chat-completions routes, matching the main NVIDIA
provider profile behavior.
The register path builds each profile-gateway slot in a sibling staging
dir under /run/service (the scandir s6-svscan watches), then atomically
renames it to the live gateway-<profile> name. The staging dir was named
gateway-<profile>.tmp — a NON-dotfile — so a concurrent `s6-svscanctl -a`
rescan (fired by the cont-init reconciler registering gateway-default, or
by a sibling register) would supervise the half-built slot the moment it
had a valid type/run: s6-supervise spawns AS ROOT and mkdirs supervise/
root-owned 0700, then the in-flight _seed_supervise_skeleton early-returns
on the now-existing supervise/ and the next `mkdir supervise/event` hits
PermissionError.
That is the arm64-only CI flake on
test_s6_unregister_removes_service_dir_in_live_container
(PermissionError: /run/service/gateway-phase3test.tmp/supervise/event) —
arm64-only because the native-arm runner's wider scheduling jitter lets
the rescan land inside the ~ms seed window; amd64 ran 30/30 clean.
Fix: dot-prefix the staging dir (.gateway-<profile>.tmp) in both register
paths (S6ServiceManager.register_profile_gateway and
container_boot._register_service). s6-svscan skips any scandir entry whose
name begins with '.', so the half-built slot can never be supervised
mid-build. The atomic rename to the dotless live name is unchanged.
Verified on a real s6 image (amd64): a non-dotted staging dir is picked up
by an svscanctl -a rescan (SUPERVISED owner=root) while a dot-prefixed one
is ignored (NOT-SUPERVISED). Added a docker-harness regression test that
asserts both, plus a unit test that the staging dir is dot-prefixed.
Widen #5961's _format_untrusted_prompt_value coverage to the Matrix
room display name (**Matrix Room:**), a sibling attacker-controllable
field the original fix missed. chat_name is user-settable, so an
injected room name could render as literal markdown in the system
prompt. Adds a regression test.
Defense-in-depth on top of _safe_session_filename_component (#5958):
Sink (makes the bad write impossible regardless of entry point):
- run_agent._save_session_log: sanitize session_id before building the
session_{sid}.json snapshot path.
- agent_runtime_helpers.dump_api_request_debug: sanitize before building
the request_dump_{sid}_{ts}.json path.
Boundary (clean 400 instead of a silently-hashed filename):
- api_server rejects path-traversal-shaped X-Hermes-Session-Id on the
session-continuation path and the explicit /api/sessions create path,
reusing gateway.session._is_path_unsafe (mirrors the native gateway's
entry-boundary guard). Also enforces the session-header length cap on
the continuation path.
Tests: traversal session_id stays contained at the write site; sanitizer
always yields a traversal-free segment; the API header rejects
../, absolute, and Windows-traversal IDs with 400.
Session IDs can originate from untrusted input (e.g. the
X-Hermes-Session-Id API header) and are interpolated raw into on-disk
artifact filenames under ~/.hermes/sessions/. A traversal-shaped ID
(../../../../etc/pwned) would let a caller write the session snapshot
or request dump outside the sessions directory.
_safe_session_filename_component() collapses every non [A-Za-z0-9_-]
character to _, caps the length, and appends a short content hash when
sanitization changed the string, always yielding a single traversal-free
path segment.
Closes#5958.
The reset-had-activity tests set total_tokens (dead state) to simulate
activity; production records activity via last_prompt_tokens. Update
the fixtures to match the field the fix and runtime actually use.
reset_had_activity gated on entry.total_tokens, which is never written
(token counts migrated to agent-direct persistence) so it was always 0.
That suppressed session-reset notifications for sessions that genuinely
had activity. Switch to last_prompt_tokens, which is updated on every
turn.
Salvages the two still-valid hardenings from #5381 onto the relocated
plugin adapters (the discord/feishu/whatsapp adapters moved to
plugins/platforms/ since the PR was opened, and 4 of its 6 hunks are
already on main or superseded).
- feishu: rate limiter now denies untracked keys when the tracking table
is at capacity after pruning stale entries (was: allow through without
tracking). At-capacity-with-all-fresh-entries only happens under abuse,
so allowing untracked requests let an attacker who flooded the table
bypass the limiter entirely. Already-tracked keys and post-prune room
are unaffected.
- whatsapp: absolute file paths handed back by the Baileys bridge are now
validated to resolve inside a known media cache dir before being
attached. A compromised/buggy bridge could otherwise return an
arbitrary path (e.g. /etc/passwd) that would be sent verbatim to the
model. Guard resolves symlinks and accepts both the canonical
cache/<kind> and legacy <kind>_cache layouts.
The gateway's get_or_create_session() creates a bare session row (source +
user_id) before the agent exists. The agent's later create_session() carries
the real model/model_config/system_prompt, but _insert_session_row used
INSERT OR IGNORE — silently dropping that enrichment. Gateway sessions were
left with NULL model and NULL billing metadata.
Switch to INSERT ... ON CONFLICT(id) DO UPDATE with COALESCE so NULL columns
get backfilled while values an earlier writer already set are never
overwritten (a later bare write with source='unknown' can't clobber a real
source/model). Credit: original report and fix direction by @LucidPaths (#5048).
list_session_providers() already filters on supports_session=True, so the
new helper re-filtered an already-filtered list. Call it directly at the
single auto-SSO call site.
When the dashboard gateway has no local session cookie, it rendered a
click-through /login interstitial — even though the Nous portal's
/oauth/authorize auto-approves any current member of the dashboard's org
and is a silent 302 when the user already holds a portal session. For the
common case (clicking a hosted-agent dashboard link while signed in to the
portal) that interstitial click is pure friction.
This makes the gate auto-initiate the OAuth redirect on an unauthenticated
HTML document load instead of rendering the interstitial, when exactly one
interactive provider is registered. A one-shot loop-guard cookie
(hermes_sso_attempt, 60s TTL) ensures that a genuinely absent portal
session (the portal bounces back still-unauthenticated) falls back to the
/login page after exactly one bounce rather than ping-ponging forever. The
marker is cleared on a successful callback and whenever the gate falls back
to /login.
Security: this removes a human CLICK, not a security check. The redirect
lands on the existing /auth/login route and runs the unchanged PKCE
auth-code flow; token verification, audience checks, redirect-URI match,
and org-membership checks are all untouched. /api/* fetches still get the
401 JSON envelope (never a 302 a fetch() would follow opaquely), and with
two or more providers the /login chooser still renders.
Phase 1 of the cloud-auto-discovery work.
The five _resolved_api_call_stale_timeout_base integration tests reloaded
hermes_cli.config + hermes_cli.timeouts via importlib.reload to clear cached
config. Under xdist that mutates module-global state shared across the worker
process, so a sibling test could leave the config cache in a state that made
get_provider_stale_timeout return a leaked value — intermittently failing
test_reasoning_floor_applies_to_opus_4_thinking (shard 6 flake, #52217 area).
Patch run_agent.get_provider_stale_timeout per-test instead: floor-path tests
get None (resolver falls through to the reasoning floor / env var / default),
the explicit-config test gets 60.0 (priority-1 short-circuit). Same assertions,
no shared-module mutation, deterministic under parallel execution.
Fixes#14238. During a compression/session split at the response
boundary, the interim callback delivered unrelated commentary, setting
response_previewed=True. The suppression logic treated that as proof the
final reply had been delivered and skipped the normal send — the response
was persisted to the child session but never sent to chat.
Only suppress the normal final send when the stream consumer confirms
final delivery (final_response_sent / final_content_delivered) or the
exact final response text was delivered as a preview.
find_alias_for_profile re-scanned the whole wrapper dir (~/.local/bin) and
read_text every file for EACH profile — including large unrelated binaries
(ffmpeg etc.) read 15x over. With 16 profiles this took ~6.4s, long enough
that the desktop's per-request backend calls timed out (15s) and the sidebar
rendered '全部智能体 0 / 会话 0'.
- Add build_alias_map(): single-pass {profile -> alias} reverse map, reads
only an 8KB head slice per wrapper, skips binaries via UnicodeDecodeError.
- find_alias_for_profile now delegates to it (behavior preserved).
- Cache _count_skills by skills-dir mtime signature (+30s TTL).
list_profiles: 6.37s -> 0.84s cold / 0.44s warm. 138 profile tests pass.
(cherry picked from commit 89e593749a93bfbcc4e557a18c533d98ed0382d4)
resolve_custom_provider() previously returned api_key_env_vars=()
for every custom provider entry, silently dropping the configured
key_env field. This caused 401 errors for any custom provider that
required an API key via environment variable (e.g. Xiaomi MiMo Token
Plan, self-hosted OpenAI-compatible servers).
The key_env field is already documented in _VALID_CUSTOM_PROVIDER_FIELDS
and normalized by normalize_custom_provider_entry(), so this was just
an oversight in the ProviderDef construction.
Also adds a regression test that verifies key_env is properly
propagated into the resolved ProviderDef.
Wire the salvaged _safe_command_timeout() guard into the surviving
open-timeout call site. _get_open_command_timeout() feeds the
browser_navigate 'open' path; this closes the last call site that
could observe a None timeout from a torn cache (#14331), since the
original PR's max(_get_command_timeout(), 60) site no longer exists
on main (now routed through _get_open_command_timeout).
The first ship of verify-on-stop (config v30) defaulted
DEFAULT_CONFIG agent.verify_on_stop to a literal True, and migrate_config
persists defaults with strip_defaults=False — so every install that updated
through v30 had verify_on_stop: true written into config.yaml as a literal.
The v30->v31 migration only flipped missing/'auto' values to false and
deliberately preserved an explicit bool, so it skipped that entire population
and left verify-on-stop ON for everyone who had updated. A literal true was
never a user choice: the feature had no off-switch worth setting it against
until v31 introduced one, so a true persisted before v32 is always the old
machine default.
v32 migration flips a literal true -> false once, for both v30 (skipped v31)
and v31 (preserved-by-bug) installs. A true the user sets AFTER v32 is a
deliberate opt-in and is never touched.
The original cap held a process-global slot across the WHOLE vision
analysis (image load + encode + LLM call) with a default of min(CPUs, 4).
That serialized legitimate multi-image workflows — "compare these 6
screenshots", "read this 10-page scan", "analyze every frame" — behind a
4-wide gate, and on the native fast path it even throttled calls that make
no LLM request at all. Excess calls queued (blocking acquire, nothing
dropped), but the latency hit on real fan-out was the wrong tradeoff.
The incident was CPU exhaustion, not call count: concurrent base64/resize
bursts saturated every core and left none to service the shared event loop
serving /api/status. So cap ONLY that:
- A dedicated, bounded ThreadPoolExecutor (_vision_cpu_executor) runs the
encode/resize/dimension-check off the caller's loop, sized to the host's
usable core count with NO fixed ceiling — the cap tracks the actual
exhausted resource (cores), not a magic number. Excess encodes queue on
the executor; cores stay free for the loop.
- The LLM call is deliberately OUTSIDE the executor, so multi-image
workflows keep full request concurrency.
- Override via auxiliary.vision.max_concurrency / HERMES_VISION_MAX_CONCURRENCY
(honored verbatim, including above core count); sub-1 ignored.
- _vision_concurrency_slot() is now a no-op shim for back-compat.
Tests assert: resolver defaults to host cores with no ceiling; env/config
override (incl. above cores); sub-1 rejection; the executor is dedicated and
core-sized; encode runs on a vision-encode thread; and crucially that encode
bursts are bounded to the cap while the analyses themselves stay fully
concurrent (calls_peak > cap).
A single agent turn can fan out N vision_analyze calls at once — the
classic trigger is "analyze every frame of this video", where ffmpeg
explodes a clip into dozens of frames and the model calls vision_analyze
on each. Every call does a CPU-heavy base64-encode/resize burst AND holds
a long-lived LLM stream open. The tool executor runs concurrent tool calls
on a per-session ThreadPoolExecutor (_MAX_TOOL_WORKERS=8), and multiple
agent sessions share one process (the dashboard runs the agent in-process),
so there was no global ceiling. In prod (June 2026) a video-frame fan-out
pinned a worker thread at ~100% CPU and starved the shared asyncio event
loop that also serves the dashboard's /api/status liveness probe, flapping
the instance to UNHEALTHY even though nothing had crashed.
Add a process-global threading.BoundedSemaphore that bounds how many vision
analyses run concurrently across the whole process, held across the entire
analysis (image load + encode + LLM call) in the single _handle_vision_analyze
chokepoint (covers both the native fast path and the legacy aux-LLM path).
It is a threading semaphore, NOT asyncio: each vision call is dispatched
through model_tools._run_async on a per-thread event loop, so an asyncio
primitive bound to one loop cannot coordinate across them. The acquire is
offloaded via run_in_executor so waiting for a slot never blocks the calling
loop.
Default: min(host CPUs, 4), floored at 1 — respect the host's concurrency,
or lower. Override via auxiliary.vision.max_concurrency (config.yaml) or
HERMES_VISION_MAX_CONCURRENCY (env). Values < 1 are ignored so the cap can
never be disabled into an unbounded fan-out.
Tests: bounded-fan-out regression guard + a control proving it would fail
without the cap; resolver tests for host-cpu default, ceiling clamp, low-cpu
host, env override, and sub-1 rejection. Pre-existing handler tests updated
for the now-async _handle_vision_analyze. Verified via the real
registry.dispatch -> _run_async per-thread-loop path (16 concurrent calls,
peak bounded to cap).
The auth-header fix adds headers=_auth_headers() to all Camofox HTTP
calls. Two _capture_post mocks in the persistence test lacked a headers
parameter, so navigate raised TypeError and the success assertions
failed. Add headers=None to both mock signatures.
The auth-header fix reads CAMOFOX_API_KEY but it was never registered,
so it didn't surface in `hermes setup` / `hermes tools`. Add it as an
advanced password-category tool env var alongside CAMOFOX_URL.
When a Camofox browser tab is garbage collected (idle timeout, browser
recycle), the held tab_id becomes stale. The next browser_navigate call
hits /tabs/{stale_id}/navigate -> HTTP 404 -> unhandled HTTPError.
Catch the 404 in camofox_navigate, clear the stale tab_id, and create a
fresh tab via _ensure_tab. The agent recovers transparently without
requiring a session restart.
Other tab operations (snapshot, click, type, etc.) use the same pattern
but only fail if the tab dies between successful calls — much rarer.
The navigate fix covers 95%+ of cases since navigate is always the entry
point.
The Camofox browser backend hardcoded a 30s HTTP timeout via
_DEFAULT_TIMEOUT, ignoring the user's browser.command_timeout config.
The main browser_tool path already reads this config via
_get_command_timeout().
This commit adds an equivalent _get_command_timeout() to
browser_camofox.py that reads browser.command_timeout from config
with caching, and switches all HTTP helper methods (_post, _get,
_get_raw, _delete) to use it as the default timeout.
Fixes#40843
The five HTTP call sites in browser_camofox.py (_ensure_tab, _post,
_get, _get_raw, _delete) did not include Authorization headers, causing
403 Forbidden when the Camofox server has API key auth enabled.
Added _auth_headers() helper and wired it into all five call sites.
The health check endpoint (/health) is left without auth since it is
a connectivity probe, not a browser operation.
Regression test covers: header present when key set, absent when unset,
blank key produces empty headers.
Fixes#20476
The Camoufox REST API server expects `listItemId` in the `POST /tabs`
body, but `_ensure_tab` was sending `sessionKey`. This caused a 400
Bad Request on every `browser_navigate` call.
The parameter name mismatch is visible in the same file: line 283
already reads `tab.get("listItemId")` when adopting existing tabs,
confirming the server-side field name.
Fixes#37960
Follow-up to the group-DM manifest fix. The manifest change only helps
NEW installs; existing apps keep their old (mpim-less) scopes until the
admin reinstalls. Since a missing message.mpim event delivers nothing
(no runtime API error to catch), detect stale installs at connect time
from the auth.test x-oauth-scopes header and log an actionable reinstall
nudge when im:history is granted but mpim:history is not. Also promote
message.mpim from Recommended to Required in the docs event tables so the
default setup path can't drop it.
Group DMs (multi-person DMs, channel_type=mpim) were never delivered to
the Slack bot. The adapter already classifies mpim as a DM and replies
ambiently (adapter.py:2526, is_dm = channel_type in {im, mpim}), but the
generated app manifest only subscribed to message.im / im:history — the
1:1 DM pair. Without the message.mpim event subscription Slack drops
group-DM messages before the adapter ever sees them, so 1:1 DMs worked
while group-DM ambient mode was dead.
Add message.mpim to bot_events and mpim:history (the scope that event
requires per Slack docs) + mpim:read (mirrors im:read for the
conversations.info classification call) to bot_scopes. Update the
SLACK_BOT_TOKEN / SLACK_APP_TOKEN setup-help strings and the Slack docs
(EN + zh-Hans: scope table, event table, troubleshooting) so existing
installs are told to add the new scopes and reinstall.
Reported by an enterprise customer. Note: this is a manifest/scope
change, so it only takes effect after the app is reinstalled and the
new scopes are accepted.
Tests: assert message.mpim + mpim:history + mpim:read are in the
manifest (with and without assistant mode); both fail on current main
and pass with this change.
test_gateway_pid_scan_hides_wmic_and_powershell_windows flaked once in CI
(slice 7/8) with 'KeyError: creationflags' while passing 15/15 under exact
CI-parity locally. The positional 'kwargs["creationflags"]' indexing raises
a bare KeyError the moment any stray subprocess.run call is captured, masking
the real contract. Filter captured calls to the two intended Windows console
spawns (wmic + PowerShell fallback) and assert each is windowless via
.get('creationflags'); a leaked/extra call now surfaces as a readable
len-mismatch with the full captured list, not a cryptic KeyError.
The supermemory and mem0 memory providers shipped third-party SDKs
(supermemory / mem0ai) that are not core dependencies, but — unlike the
honcho and hindsight providers — they imported those SDKs directly with
no tools.lazy_deps.ensure() preflight and had no LAZY_DEPS allowlist
entry. On the published Docker image the agent venv is sealed
(HERMES_DISABLE_LAZY_INSTALLS=1) and lazy installs are redirected to a
writable durable target (HERMES_LAZY_INSTALL_TARGET). honcho/hindsight
route through ensure() and install fine there; supermemory/mem0 never
called it, so their SDK was never installed on a hosted instance and the
provider silently reported itself unavailable even with the API key set.
Fixes:
- Add memory.supermemory + memory.mem0 to the LAZY_DEPS allowlist
(tools/lazy_deps.py), pinned to current PyPI releases.
- Call ensure('memory.<x>', prompt=False) at each SDK-import chokepoint
(_SupermemoryClient.__init__; Mem0MemoryProvider._create_backend),
mirroring honcho's wrapped try/except shape.
- Drop the SDK-import gate from supermemory's is_available() — it was a
chicken-and-egg trap (provider never loaded on a sealed venv, so
ensure() never ran). Now key-presence only, like honcho/mem0.
- Add matching pyproject extras [supermemory]/[mem0]; update the
lazy-covered-extras contract test (excluded from [all] by policy).
Tests prove each path fails without the fix and the real sealed-venv
durable-target gate accepts both features.
The bootstrap-runner PowerShell spawn is formatted multiline (spawn(\n ps,\n fullArgs,...), so the literal substring 'spawn(ps, fullArgs' never matched and the assertion was failing on main independent of #54635. Convert it to a whitespace-tolerant regex like every other call-site assertion in this file.
The recurring Windows desktop console-flash bug (#54220) is governed by the
*parent's* console, not by each child spawn. The desktop backend was launched as
GUI-subsystem pythonw.exe, which has no console at all — so every
console-subsystem child it spawns (git, gh, cmd, wmic, powershell, ...) had to
allocate its own console, flashing a window. That is why the fix had become an
endless per-call-site sweep of CREATE_NO_WINDOW flags: each leaf spawn was
papering over a missing console on the root.
Launch the backend as the venv's console python.exe instead. Under the existing
hiddenWindowsChildOptions() wrapper (windowsHide: true -> CREATE_NO_WINDOW) the
backend owns a single *windowless* console, and every descendant spawn inherits
it instead of allocating a visible one. This makes "no flashing windows" a
property of the one backend launch rather than a flag that must be remembered at
every spawn site — including spawns inside third-party libraries that no
call-site sweep can reach.
Verified on Windows 11 25H2 (Windows Terminal default): with the per-site hide
flag forcibly neutered, the canonical culprits (git/gh/cmd/wmic/powershell)
spawned naively and none flashed, while the same naive spawn from the old
console-less pythonw parent did flash — isolating the parent console as the cause.
Two premises behind the old pythonw approach did not hold up on current Windows
and are dropped here:
- The venv Scripts\python.exe uv shim, under CREATE_NO_WINDOW, re-execs base
python *windowless* — it does not flash a conhost (the #52239 concern), so the
base-pythonw detour is unnecessary.
- Console python restores stdout, so the backend announces its port on the normal
HERMES_DASHBOARD_READY stdout line; the pythonw-only ready-file side channel is
no longer needed and the readyFile opt-in is removed.
Removes the now-dead pythonw machinery (getNoConsoleVenvPython, toNoConsolePython,
applyWindowsNoConsoleSpawnHints, readVenvHome) and updates the test to assert the
new invariant: backend command is never pythonw, both backend spawns still go
through hiddenWindowsChildOptions, and no backend opts into the ready-file path.
Scope: this fixes the high-frequency backend-descendant flash classes. The
updater/UAC handoff (#54543) and embedded-terminal PTY accumulation (#53555)
classes have separate root causes and are unaffected.
The env translation block is type-checked across every locale (tsc -b), so
the 8 new customKeys strings must exist in all of them, not just en/zh. Add
translated entries to the remaining 14 locales (de, es, fr, it, ja, ko, pt,
ru, tr, uk, hu, ga, af, zh-hant).
The Keys page only rendered env vars present in a catalog (OPTIONAL_ENV_VARS
or the provider catalog); any other key a user set in .env was invisible, and
there was no way to add an arbitrary env var from the GUI (e.g. to inject a
var a skill or MCP server needs).
Backend: GET /api/env now also emits a row for every on-disk .env key that
isn't in any catalog, flagged category="custom" + custom=true and
password-masked (an unrecognised key could hold anything, so it's redacted and
reveal-gated like any secret). Channel-managed credentials stay excluded. The
write (PUT /api/env) and reveal (POST /api/env/reveal) paths already handle
arbitrary keys, with the existing env-name guard + denylist (PATH, LD_PRELOAD,
PYTHONPATH, …) enforced server-side — no new write surface.
Frontend: a new "Custom Keys" section lists those custom rows and carries an
add-a-key form (client-side name validation mirroring the backend regex; the
new row reuses the normal edit/save flow, so on save it round-trips back from
the backend as a durable custom row). i18n added for en + zh + types.
Tests: behavior-contract coverage that an unknown .env key surfaces as a
masked custom row and a catalogued key does not — verified to fail on the
pre-fix backend.
When local Ollama models are absent from models.dev, probe the Ollama
server's /api/show capabilities so attached images are routed natively
instead of being stripped as non-vision input.
Google's native Gemini REST endpoint (generativelanguage.googleapis.com,
non-/openai) rejects OpenAI-only stream_options={"include_usage": true},
crashing every streaming chat-completions call with TypeError. Omit it for
that endpoint while keeping it for the Gemini OpenAI-compat shim and all
OpenAI-compatible aggregators (OpenRouter, etc.) so usage accounting is
preserved.
Reuses is_native_gemini_base_url() so the compat shim (.../openai), which
accepts stream_options, is correctly excluded from the omission.
Fixes#14387
Co-authored-by: Hermes Agent <127238744+teknium1@users.noreply.github.com>
The WeCom callback endpoint (internet-facing, 0.0.0.0) parsed untrusted
request bodies before signature verification. defusedxml already guards
the entity-expansion class on main, but there was no cap on raw body
size, so an unauthenticated POST could still force unbounded read work
pre-auth.
Set client_max_size=64KB on the aiohttp app (413 at the framework layer)
plus an explicit length guard in _handle_callback as defense in depth.
WeCom callbacks are small encrypted XML envelopes — media is delivered
out-of-band via MediaId, never inline — so 64KB is ample for legitimate
traffic. Adds tests for oversized (413) and normal-sized (not 413) bodies.
Salvaged from #10192 by @memosr (body-size limit half; defusedxml half
already superseded on main).
Relocate marco0158's eviction into the dedicated auto-reset cleanup block
(single source of truth for dropping session-scoped transient state) and
add an AST invariant pinning _evict_cached_agent into that block. Add
AUTHOR_MAP entry for marco0158.
When a session is auto-reset by daily schedule, idle timeout, or suspended
state, the agent cache was not being cleared. This caused the old agent's
context_compressor._previous_summary to leak into the new session, mixing
old conversation history into new compaction summaries.
This was the root cause of the "skin making history" appearing after
compaction in fresh sessions reported by the user.
Follow-up to #9893 which only handled compression_exhausted case.
Changes:
- Add _evict_cached_agent(session_key) call after was_auto_reset check
- Covers daily, idle, and suspended auto-reset scenarios
- Matches the behavior of manual /reset command
Related tests: test_session_boundary_hooks, test_async_memory_flush,
test_session_reset_notify, test_session_reset_fix - all passing.
/resume is a conversation boundary, but unlike /new it did not clear the
chat-keyed _session_model_overrides / _pending_model_notes. A /model switch
made in the previous session under the same chat session_key leaked into the
resumed conversation, running it on the wrong model.
Clear both maps for the session_key after the switch (mirroring /new), scoped
to that key so other chats' overrides are untouched. The cached-agent eviction
this leak also implied already landed via #6672.
Closes#10702.
The cron delivery table only showed Discord/Telegram with explicit
target syntax and described Slack and every other platform as
home-channel-only. In fact the generic platform:<target> routing in
_resolve_single_delivery_target resolves explicit targets for every
platform: Slack (#channel / channel ID / channel:thread_ts), Matrix
(room/user IDs), Feishu (chat:thread), WhatsApp (JID / E.164), Signal
(group / E.164), SMS, Email, and Weixin all have dedicated explicit-
target branches in _parse_target_ref; the remaining platforms accept a
generic platform:<chat_id> passthrough.
Update the Delivery Model table (en + zh-Hans) to show the real
per-platform syntax, document #channel name resolution via the channel
directory, and note the Slack thread_ts nuance. Docs-only.
Clears the ty diff bot's warnings on the new test: pass real callables to
build_dashboard_parser (not object()) and replace the pytest.mark.parametrize
with a plain loop so the file is stdlib-only.
`hermes cron status` (and the create/list 'gateway not running' nag)
judge whether cron will fire purely from the in-process ticker's
heartbeat file + a live gateway PID. That heuristic is correct for the
built-in ticker but WRONG for an external provider like Chronos:
Chronos arms exactly one external one-shot per job and is fired by a
NAS-mediated webhook (POST /api/cron/fire). Its `start()` returns
immediately and it deliberately runs no 60s loop and writes no ticker
heartbeat — that's the whole point of scale-to-zero (the machine is at
zero between fires). So on a perfectly healthy Chronos instance,
`cron status` always printed '✗ Gateway is not running — cron jobs will
NOT fire' (or a STALLED-ticker warning), and `cron create` always
appended the 'jobs won't fire automatically' nag — both false.
Verified live on a staging Chronos instance: jobs fired and completed on
schedule via the relay while `cron status` insisted the gateway wasn't
running and the heartbeat was 370s+ stale.
Fix: resolve the active provider (offline — `resolve_cron_scheduler`,
whose `is_available()` contract forbids network) and, for any non-builtin
provider, report the managed-scheduler state instead of the ticker
heuristics, and suppress the ticker-only 'gateway not running' warning.
The built-in path is byte-unchanged. Active-job summary is factored into
a shared helper so both paths print it identically.
New tests prove both directions (chronos: no false negative even with no
gateway PID / no heartbeat; builtin: historical warning preserved) and
fail without the fix.
_on_invite now rejects auto-joins from users not on the allow-list. The
DM-recording tests invite @alice and expect a join, so the shared
_make_adapter fixture now puts @alice on _allowed_user_ids.
Two platform-security hardenings:
- Matrix: _on_invite now checks the inviter against the existing
allow-list (_allowed_user_ids / GATEWAY_ALLOW_ALL_USERS) before
auto-joining. Without this any federated Matrix user could invite
the bot into arbitrary rooms, exposing its presence and metadata.
The message and reaction paths already enforce this allow-list; the
invite path bypassed it.
- Mattermost: _api_get / _api_post / _api_put reject any path
containing '..'. WebSocket-event values (channel_id, post_id,
file_id) are interpolated directly into API paths, so a malicious or
compromised server could craft traversal payloads to make the bot
issue authenticated requests to arbitrary endpoints with its bearer
token.
The configurable-E2EE-passphrase change from the original PR is dropped:
the matrix adapter was rewritten onto mautrix and the passphrase-protected
key-export file no longer exists.
PR infographics are rendered locally and embedded in PR descriptions via
the image-provider (fal.media) URL — they were never meant to live in the
repo. The intended .gitignore enforcement (documented as added back in May
2026) was never actually committed, so 35 PNGs (~54MB) accumulated under
infographic/ via 'docs: add PR infographic for X' commits.
- Remove all 35 tracked infographic/*.png files.
- Add infographic/ to .gitignore so git add on the path is now a no-op.
The PR body remains the archive for these images.
Regression tests for the injection fix: outside a git repo only cwd is
checked (planted ancestor .hermes.md is ignored), a cwd-local .hermes.md
is still found, and inside a git repo the parent walk to the git root
still works.
_find_hermes_md walks parent directories looking for .hermes.md/HERMES.md,
stopping at the git root. But when there is no git repo (_find_git_root
returns None), the stop guard never fires and the loop walks all the way
to /. On shared systems (CI runners, multi-tenant servers), a .hermes.md
planted at /tmp, /home, or / would be loaded into the system prompt of any
agent session not inside a git repo — a cross-user prompt-injection vector.
Fix: when there is no git root, only check cwd; do not walk parents.
Co-authored-by: Teknium <127238744+teknium1@users.noreply.github.com>
User terminal tabs and their recent scrollback now survive an app restart
(VS Code parity). Tabs, active selection, cwd, and a serialized scrollback
snapshot are written to localStorage on every change; on launch the tabs
reopen with their history replayed above a fresh shell. Processes are NOT
revived — a new shell starts one line below the restored block.
- Capture: SerializeAddon snapshots the buffer on a 750ms leading-edge
throttle, so a `cmd; quit` lands on disk before teardown; the snapshot is
trimmed of its trailing idle prompt (no "double prompt" on restore) and
capped (200 scrollback lines / 48k chars) to stay under the storage budget.
- Teardown guard: app quit/reload kills the PTYs from the main process,
firing onExit in the renderer, but React skips effect cleanups on teardown
so the per-instance `disposed` flag never flips. A pagehide/beforeunload
flag stops onExit from calling closeTerminal() and wiping the persisted
tabs right before relaunch restores them. A real `exit`/Ctrl-D still closes.
- Agent mirror tabs stay runtime-only — only user tabs persist.
Add a focused contract test for the headless `serve` command (routes to the
shared dashboard handler, headless by default while `dashboard` is not, accepts
the legacy --no-open, shares the same runtime/lifecycle flag surface). Also
refresh the dashboard.py module docstring to cover both commands.
`hermes serve` is newer than the desktop binary's release cadence, so a new
app launched against an un-upgraded managed install / PATH `hermes` would
crash on an unknown subcommand and brick the user mid-upgrade. Detect whether
the resolved runtime registers `serve` (fast source read of its dashboard.py,
with a one-time CLI probe fallback) and rewrite the backend argv to the legacy
`dashboard --no-open` only when it does not. Happy path (current runtimes)
pays nothing and still spawns `serve`.
- electron/backend-command.cjs: pure serve/dashboard argv helpers + serve-
source detection (unit-tested in backend-command.test.cjs)
- main.cjs: backendSupportsServe() cache + getBackendArgsForRuntime() guard at
both backend spawn sites; expose `root` from the Windows venv unwrap so the
fast source check covers Windows too
- docs: note the backward-compat fallback in README, desktop.md, AGENTS.md
The desktop app spawned `hermes dashboard --no-open` as its backend, which
made the dashboard look like a desktop prerequisite. Add a dedicated headless
`hermes serve` command that boots the same gateway (shared cmd_dashboard /
start_server) but never opens a browser, and point the desktop backend spawn
exclusively at it. dashboard and serve are now independent surfaces — neither
launches the other.
- subcommands/dashboard.py: factor shared server args; add `serve` parser
(always headless; accepts legacy --no-open as a no-op)
- main.py: register serve in _BUILTIN_SUBCOMMANDS + coalesce set + gui-log
detection; extend stale-backend reaper patterns to match `serve`
- desktop electron: spawn `serve`, rename dashboardArgs -> backendArgs,
update comments + windows-child-process test assertions
- docs: desktop README, desktop.md (incl. remote-backend), AGENTS.md, and
cli-commands.md now describe `hermes serve` as the desktop/headless backend
The desktop app spawns a headless `hermes dashboard --no-open` backend and
talks to it through the shared @hermes/shared WebSocket client — it never
runs or requires the browser dashboard UI. Spell this out in the desktop
README, the desktop docs page, and AGENTS.md so "dashboard" stops reading
as a desktop prerequisite.
The shared websocket package is a web file: dependency but was excluded
by .dockerignore and never copied into the Docker build context. Also fix
tsc -b errors: expose buildWsUrl on api and drop the GatewayClient state
getter that conflicted with the shared base class.
Remove the prompt-gap cleanup that sent Ctrl-L into the user's shell; it could
render as literal ^L and create the exact top-line gap it was meant to hide.
Keep first-prompt cleanup renderer-side only, and parse short ESC charset
sequences so the initial newline stripper does not disarm early.
Also add a Close all action to the terminal tab context menu.
Run the package-appropriate Prettier config on the shared WebSocket files so
the extracted helpers match the surrounding desktop/shared TypeScript style.
Revert the repo-wide prettier churn the earlier fmt pass pulled into files
unrelated to this work; run prettier/eslint scoped to the touched files only.
Keep dashboard pages and components on the dashboard API helper instead of
calling the raw shared URL primitive directly. The shared helper remains the
single low-level implementation; web/src/lib/api.ts is the dashboard-specific
facade for auth, base path, and ticket minting.
- Gateway status popout: flatten the header to stacked connection + inference
statuses with system-panel and restart actions (reusing the shared
runGatewayRestart helper). The recent-activity tail is now live while the
popout is open via the shared LogView (WS connection churn filtered), and the
icon / "View all logs" link dismiss the popover.
- Statusbar "menu" items accept a menuContent(close) render fn over a now
controlled DropdownMenu, so popover content can close itself.
- Drop the always-on gateway-log poll from useStatusSnapshot (logs are fetched
by the popout only while open).
- SearchField → text-xs to match Input/Select (controlVariants).
- Command center: remove the usage/system section dividers, swap the sessions
nav icon (Pin → MessageCircle), small padding tweaks.
Ensure intentional client closes mark the transport closed and reject pending
RPCs immediately instead of relying on a browser close event that can be
ignored after the socket reference is cleared.
The Electron desktop app and the web dashboard each carried their own
copy of the tui_gateway JSON-RPC WebSocket client plus near-identical
auth'd WS-URL construction. The dashboard's copy was the historical
source of the "is the dashboard required to run the desktop app?"
confusion, since the two surfaces looked coupled.
Consolidate the genuinely shared transport into the existing
framework-agnostic `@hermes/shared` package so both surfaces consume it
independently — neither app depends on the other:
- Move `resolveGatewayWsUrl` + `GatewayReauthRequiredError` (single-use
OAuth ticket re-mint vs long-lived token fallback) into
`@hermes/shared`; desktop now imports them directly.
- Add `buildHermesWebSocketUrl`, one base-path/scheme/auth-aware URL
builder, and route every dashboard WS endpoint through it
(`/api/ws`, `/api/events`, `/api/pty`, plugin WS URLs).
- Reduce the dashboard `GatewayClient` to a thin subclass of the shared
`JsonRpcGatewayClient`, deleting ~210 lines of duplicated pending-call
/event-dispatch/connect plumbing while keeping its dashboard-specific
ticket-vs-token auth selection.
- Drop the stale "start it with --tui" chat banner, which implied the
dashboard flag was required.
Behavior is preserved on both surfaces; the dashboard additionally
inherits the shared client's 15s connect timeout (previously
desktop-only), so a hung connect now fails fast instead of pinning the
composer in "connecting".
Register read-only agent terminals with the same renderer-side terminal reader
as user terminals so read_terminal works on whichever tab is active.
Also bring agent xterm rendering closer to user-terminal parity (unicode 11,
web links, font weights/spacing) and make the gateway sink wiring resilient if
only one terminal event sink was already installed.
The dashboard Keys page and `hermes setup` render API-key rows from
OPTIONAL_ENV_VARS, but only Honcho had an entry — so Hindsight,
Supermemory, Mem0, RetainDB, ByteRover, and OpenViking read their keys
straight from os.environ yet had no place to set them in the GUI.
Add catalog entries (category=tool, password-masked, with get-key URLs
and the tool each powers) for all six, plus the relevant base-URL/endpoint
companions. Pure declaration: the generic GET /api/env endpoint, the
save/reveal write path, and the sandbox env blocklist (which auto-derives
from tool-category OPTIONAL_ENV_VARS) all pick these up with no further
wiring.
Adds a behavior-contract test asserting every memory provider's primary
credential key is catalogued, tool-categorised, and password-masked.
Make the read-only agent terminal mirrors stream in real time and give
the agent a desktop-only way to dismiss its own tabs.
- Stream background output live: the local reader used a blocking
read(4096) that buffered small periodic output until EOF, so agent
tabs only "filled in" at process exit. Switch to buffer.read1(4096)
(decoded) for incremental chunks.
- Route agent.terminal.output / terminal.close to the window that owns
the process (its gateway session) instead of an empty session id, so
events actually reach the desktop renderer.
- Add close_terminal: a HERMES_DESKTOP-gated tool (sibling of
read_terminal) that drops a process's read-only tab WITHOUT killing it
via process_registry.on_close; output keeps buffering and the user can
reopen from the status stack.
- ⌘W now closes a focused agent tab: mark the agent instance
data-terminal and focus it on activation so isFocusWithin routes there.
- ensureTerminal() no longer spawns an extra user shell when a tab
already exists (e.g. opening a background task from the status stack).
_normalize_approval_mode() previously accepted any string, so an unknown
value like 'auto' fell through every downstream mode check (off/smart) and
silently behaved like manual with no signal. Validate against the known
modes (manual/smart/off), emit a warning for anything else, and default to
manual to match the config default and the rest of the function.
Bug 1 from the original PR (/approve & /deny bypassing the running-agent
guard) already landed on main independently, so only the mode-validation
fix is salvaged here.
Fixes#4261
Co-authored-by: Hermes Agent <agent@nousresearch.com>
Remove zero-consumer overlay code surfaced while auditing the primitive set:
OverlayNewButton (orphaned once "New" moved into PanelAddButton), OverlayCard /
overlayCardClass, and the unused overlay-search-input module. Leaves three
intentional layers: OverlayView (base), Panel (master/detail), and
OverlaySplitLayout (settings/command-center nav→content).
Extract the agents/trace overlay chrome into overlays/panel.tsx and adopt it
across the Cron, Profiles, and Agents overlays so they share one layout
(centered card, header, master/detail list with built-in search, kebab row
actions, big "+" footer, empty state) instead of three ad-hoc split layouts.
Also in this pass:
- OverlayView insets equidistantly on every side (was top/left-only, which
left a large left gutter on narrow windows).
- Form-control chrome: input border/background/recessed-inset are now
per-mode theme-var knobs (--dt-input-border/-bg/-inset) — resting borders
blend in, strengthen on hover, and go solid on focus / while a Select is open.
- Thread-timeline popover reuses the shared dropdown surface (1:1 with the
kebab menus) and scrolls the hovered prompt into view.
`hermes profile alias <profile> --name <custom>` accepted arbitrary
strings and used them verbatim as a filename under ~/.local/bin. Because
normalize_profile_name only lowercases/strips (no regex gate), a value
like `../../.bashrc` escaped the wrapper directory and clobbered
arbitrary user-writable files. remove_wrapper_script had the same sink.
Add validate_alias_name (reusing the profile-id regex, which forbids
`/`, `.`, and `..`) and wire it into check_alias_collision,
create_wrapper_script, remove_wrapper_script, and the CLI alias action so
the rejection surfaces a clear "Invalid alias name" error instead of
silently writing or unlinking outside the wrapper dir.
Co-authored-by: Gutslabs <gutslabsxyz@gmail.com>
Co-authored-by: Xowiek <xowiekk@gmail.com>
Two of the three fixes from PR #6660 (the cli.py reopen_session change is
moot — that raw _conn.execute reopen block no longer exists on main).
- gateway/run.py: stop sending raw type(e).__name__ and str(e)[:300] to
end users on chat platforms. Exception text from LLM providers can leak
API URLs, file paths, and partial credentials. Return a generic message;
keep curated status hints for known HTTP codes; full detail stays in logs.
- gateway/platforms/webhook.py: validate pr_number (positive int) and repo
(owner/name regex) before passing to the 'gh pr comment' subprocess.
Payload-controlled values could otherwise inject gh flags (--help, a
different --repo). List-form subprocess means this is arg injection, not
shell injection, but validation is still correct.
Co-authored-by: aaronagent <1115117931@qq.com>
Two independent agent-loop hardening fixes:
- anthropic: when the streaming loop breaks on _interrupt_requested,
return None instead of calling stream.get_final_message() on the
partially-drained stream — the SDK may hang draining remaining events
or return a Message with incomplete tool_use blocks. The outer poll
loop raises InterruptedError, so the return value is discarded anyway.
- vision: add a 20 MB cap on base64 data-URL payloads before
base64.b64decode() in _materialize_data_url_for_vision. A 100MB+
payload creates ~275MB of memory pressure; gateway users sharing the
process can trivially OOM it. Oversized payloads return ("", None).
The third change from the original PR (streaming tool-name += to
assignment dedup) was already landed independently on main.
Co-authored-by: aaronlab <1115117931@qq.com>
All three .env parsers use `line.partition("=")` without stripping the
bash-compatible `export ` prefix first. A line like `export API_KEY=sk-...`
produces key `"export API_KEY"` instead of `"API_KEY"`, silently ignoring
the variable and causing auth failures for users who copy-paste from
bash profiles or follow tutorials that include `export`.
- tools/skills_tool.py: `load_env()` for skill environment
- hermes_cli/config.py: `load_env()` for core config
- hermes_cli/main.py: `_has_any_provider_configured()` inline parser
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
* fix(gateway): log error-notification failures instead of silently swallowing
The last-resort exception handler in _process_message_background() that
sends an error notice to the user caught all exceptions with a bare pass,
leaving zero trace when the notification itself failed. Upgrade to
logger.error(..., exc_info=True) so a failed error-notification send is
debuggable post-mortem.
Salvaged from #6499 by @BongSuCHOI (the logging-upgrade portion only).
* docs: add PR infographic for gateway error-notify logging
git remote set-url with an embedded password (https://PASSWORD@github.com)
leaked the credential into agent output — the redaction engine only masked
user:pass@ DB connection strings, never the colon-less bare-token userinfo
form a git remote uses.
Add _URL_BARE_TOKEN_RE: scheme://TOKEN@host for web/transport schemes
(http/https/wss/git/ssh/ftp), 8+ char floor to skip short usernames, token
class forbidding /:@ so an @ in a path/query is never treated as userinfo.
Deliberately scoped to the bare-token form only. The user:pass@ colon form
and query-string tokens stay passing through (#34029, 'pass web URLs through
unchanged') so magic-link / OAuth round-trip skills keep working — a bare
credential in userinfo is never a workflow token (those live in the query
string), so masking it can't break a skill.
* fix(terminal): require approval for host-bound Docker commands
The Docker terminal backend blanket-skips dangerous-command approval on
the assumption that the container is isolated from the host. That holds
only when nothing is bind-mounted in. Once a host path is exposed (via
TERMINAL_DOCKER_MOUNT_CWD_TO_WORKSPACE or a host-path entry in
TERMINAL_DOCKER_VOLUMES), a command like `rm -rf /workspace` reaches
real host files but is still auto-approved.
Detect host bind mounts and route those sessions through the normal
approval flow. Isolated Docker keeps the fast path. The same gating is
applied to the execute_code guard, which had the identical blanket skip.
Co-authored-by: Hermes Agent <agent@nousresearch.com>
* chore: add AUTHOR_MAP entry for PR #6436 salvage (Kolektori)
* test: accept has_host_access kwarg in _check_all_guards mocks
The host-bound Docker approval fix adds a has_host_access kwarg to the
_check_all_guards wrapper. Six pre-existing tests monkeypatch it with a
fixed (command, env_type) / (cmd, env) lambda signature, which now
raises TypeError when terminal_tool passes the new kwarg. Widen those
mock signatures to accept **kwargs.
---------
Co-authored-by: Kolektori <256073454+Kolektori@users.noreply.github.com>
Co-authored-by: Hermes Agent <agent@nousresearch.com>
On hosts where the cgroup v2 cpu/memory/pids controllers are not delegated
to the docker/podman process (unprivileged Proxmox LXCs, some rootless and
nested setups), --pids-limit/--cpus/--memory cause every container start to
fail with OCI runtime error / exit 126, breaking terminal + execute_code.
- Add _cgroup_limits_available(image): one-shot, host-wide cached probe that
spawns a throwaway container from the sandbox image itself (sleep 0) with
all three flags together, mirroring the existing _storage_opt_supported
probe-and-degrade pattern.
- Remove --pids-limit from static _BASE_SECURITY_ARGS; apply it (default 256
via _DEFAULT_PIDS_LIMIT) in resource_args gated on the probe.
- Gate --cpus and --memory on the same probe.
Behavior unchanged on cgroup-capable hosts; graceful degradation with a
one-time warning where controllers aren't delegated.
Fixes#6568.
(cherry picked from commit c933880b7ee2ce4d1167e0f89caa2d233db5639f)
Co-authored-by: angelos <angelos@oikos.lan.home.malaiwah.com>
Seed read-only agent terminal tabs with the background command immediately, so
they never open as a blank pane while stdout is pending or a live stream races
startup. Snapshot fallback now preserves that command header and appends only
missing output without duplicating live chunks.
Read-only agent terminal tabs now consume both live agent.terminal.output chunks
and the process-list/status snapshot. The snapshot seeds tabs opened after output
already exists and acts as a fallback if the live stream races startup, so agent
background tabs don't sit blank while the status stack already knows the tail.
Replace the 5s output_tail poll (which often showed nothing) with a real push
stream. The process registry gains an on_output sink called from its reader
threads with each chunk; the tui_gateway wires it to emit agent.terminal.output
{process_id, chunk} (write_json is _stdout_lock-guarded, so emitting from the
reader thread is safe). The desktop routes chunks by process id straight into
the read-only agent xterm via a small writer registry, with a capped backlog so
a tab opened mid-stream (or reopened) replays what it missed.
Drops the fragile poll/tail path: no session-key matching, no truncation, no
lag — full-fidelity ANSI, env-agnostic (local/docker/ssh).
When the agent runs terminal(background=true) — Hermes's equivalent of
Cursor's is_background — surface it as a read-only "agent" tab in the rail
(distinct sparkle icon), alongside the glanceable status-stack row, which now
links to the tab. The tab is a write-only xterm (no PTY, no input) fed by the
process output tail, appended live (faster poll while a tab is open) and
env-agnostic (works for local/docker/ssh shells alike).
- terminals.ts: TerminalEntry gains kind ('user'|'agent') + procId; agent tabs
auto-surface once (closing one doesn't resurrect it) and the status row can
reopen/focus them. ensureTerminal now guarantees a user shell specifically.
- use-agent-terminal.ts: slim read-only xterm hook, delta-appended.
- workspace: render user vs agent instances; auto-surface from the background
store; tail faster while an agent tab exists.
- composer-status: $backgroundOutputByProc selector; status row links to the tab
instead of an inline disclosure.
A WebGL terminal doesn't paint while visibility:hidden, so switching to it
(e.g. after closing the active tab) revealed a stale/garbled frame. On
activation, clear the glyph atlas and force a full term.refresh against the
live buffer (after the refit), then focus.
Replace the one-off isTerminalFocused with isFocusWithin(selector) in the
keybinds lib (beside isEditableTarget) — the reusable primitive for any
focus-scoped shortcut. The terminal marks itself data-terminal and the ⌘W
handler routes via isFocusWithin('[data-terminal]'); future surfaces just add
their own marker.
Fold terminal close into the existing ⌘/Ctrl+W handler so focus decides the
target: a focused terminal takes ⌘W (closes the active tab) and otherwise the
keystroke closes the active preview tab as before. Only the ⌘ gesture is
intercepted — Ctrl+W stays the shell's werase — and a focused terminal never
lets ⌘/Ctrl+W close a preview out from under it.
Hide inactive terminal tabs with `visibility` (absolute-stacked at full size)
instead of `display:none`. A display:none host is 0×0, so its ResizeObserver
fit bails and the terminal stops tracking pane resizes — re-showing it at a
changed size reflowed the buffer into a garbled prompt. Visibility-hidden
hosts keep their layout size, stay in sync, and switch instantly.
Multiple persistent in-app terminals managed by a thin VS Code-style icon
rail docked on the terminal pane's outer edge. Each tab is its own live
xterm+PTY that survives tab switches, session switches, and hiding the pane
(VS Code parity: only an explicit close or `exit` kills a shell). Terminals
own their state independent of the session — the sole thing they inherit is
an initial cwd snapshotted at creation.
- Rail: icon-only tabs (name + live hotkey on hover), +/hide controls,
context menu. Sits at z-40 above the collapsed sidebars' hover-reveal
triggers and marks itself data-suppress-pane-reveal, so reaching for a tab
can't summon the file-browser/review panel.
- Lifecycle: PersistentTerminal latches mounted on first open so shells stay
alive while hidden; ensureTerminal re-creates one on reopen.
- Agent reader: id-keyed registry drives read_terminal off the active tab.
- Keybinds (Ctrl-family, OS-aware): toggle Ctrl+`, new Ctrl+Shift+`,
next/prev Ctrl+Shift+Down/Up, close Ctrl+Shift+W.
resumeSession's warm-cache fast-path once again trusted the
storedSessionId -> runtimeId -> ClientSessionState mapping without
checking the cached state still BELONGS to the session being resumed. A
pooled profile backend that gets idle-reaped and respawned re-mints
runtime ids, so a recycled id resolves to a live-but-DIFFERENT session's
cache entry and paints the wrong transcript under the current route:
click thread A, a totally different thread (often from another worktree)
loads. The session.usage 404 guard only catches a fully-dead id; a
recycled-live id 200s, so the fast-path happily served the stale cache.
Straight regression, not a new bug. f7bf74064 ("reject cross-wired
runtime-id cache on session resume") landed takeWarmCache() + its
regression test; 62af32efe ("keep active sessions aligned with cwd"),
rebased off a stale branch, restructured resumeSession and silently
reverted both 29 minutes later -- the exact stale-branch squash clobber
AGENTS.md warns about ("Squash merges from stale branches silently
revert recent fixes").
Re-apply the whole-class fix on top of the current cwd-aligned code:
takeWarmCache() validates state.storedSessionId === storedSessionId at
BOTH cache reads (the early transcript-keep decision and the fast-path),
purging a cross-wired mapping on a miss so it falls through to a full
resume that rebinds a correct runtime id. Restore the two regression
tests guarding it.
Tests: resumeSession warm-cache mapping integrity -- a cross-wired
mapping is rejected + purged (the bug), a correctly-wired cache is still
served with no needless refetch (no perf regression).
Co-authored-by: professorpalmer <professorpalmer@users.noreply.github.com>
The fallback test only mocked fetch_api_models; CI still hit the real GMI
/v1/models endpoint via ProviderProfile.fetch_models and merged live
models into the result.
The /api/audio/elevenlabs/voices endpoint logged a WARNING on every
failure, and the desktop re-polls it on each settings open/focus — a
bad/expired/scoped ELEVENLABS_API_KEY floods agent/gui logs with
identical "voice list failed: HTTP Error 401" lines indefinitely.
Treat 401/403 as a persistent "integration unavailable" state: return
{available: false, error: "unauthorized"} with a 200 (the dropdown
already handles available:false) instead of a 502, and collapse repeated
identical failures to a single log line via a small re-arming latch
(logs again on recovery or when the error changes). Non-auth errors keep
the 502 but are throttled the same way.
windows_hide_flags() already returns 0 on POSIX (and creationflags=0 is
the no-op default there, exactly how server.py::_list_repo_files does it),
so drop the IS_WINDOWS import + ternary/one-use-dict gating and just pass
creationflags=windows_hide_flags() directly. Tests lose the now-pointless
IS_WINDOWS monkeypatch.
server.py's PDF-attach handler shells out to `pdftoppm` from the
console-less desktop/gateway backend; on Windows that pops a conhost
window each attach. Route it through windows_hide_flags() like the
sibling _list_repo_files git calls (no-op on POSIX).
The #54236/#54417 backend git/gh sweep routed git_probe, the repo-file
picker, coding_context, context_references, copilot_auth, and the gateway
process scans through CREATE_NO_WINDOW, but two sibling spawn legs that
also run inside the console-less desktop/gateway backend were missed:
- tools/checkpoint_manager.py `_run_git` (and the one-shot `git init
--bare` in `_init_store`) — when checkpoints are enabled, every
file-mutating turn fires multiple bare `git` calls (status, add,
write-tree/commit-tree, update-ref). Spawned from a parent with no
console (Electron spawns the backend with windowsHide → CREATE_NO_WINDOW),
each one allocates its own conhost window → a flurry of terminal popups.
- tools/skills_hub.py `GitHubAuth._try_gh_cli` — `gh auth token`, the same
bug class as the already-fixed copilot_auth gh probe.
Route both through `windows_hide_flags()` (no-op on POSIX), matching the
established per-site pattern. Tests added to
tests/test_windows_subprocess_no_window_flags.py.
The startup config/manifest reads used PyYAML's pure-Python SafeLoader,
which is ~8x slower than the libyaml-backed CSafeLoader C extension.
config.yaml is parsed several times during launch (cli config, raw
config, early interface/redaction bridge, logging config) and every
plugin manifest is parsed once — all on the slow path.
Add utils.fast_safe_load (CSafeLoader-preferring, pure-Python fallback,
true drop-in for safe_load) and route the hot startup parse sites
through it: hermes_cli/config.py (config + manifest reads),
hermes_cli/plugins.py (manifest parse), env_loader, cli.load_cli_config,
hermes_logging, and the two pre-config early YAML bridges in main.py.
Behavior is identical (same restricted safe tag set); only speed changes.
safe_load calls on the startup path drop from ~79 to ~0, cutting the
YAML parse cost from ~0.9s to ~0.15s under profiling.
Adds tests/test_fast_safe_load.py asserting equivalence with safe_load
across input shapes, empty-doc falsiness, C-loader preference, and that
python/object tags are still rejected (safe, not full loader).
yuanbao_media.download_url() fetched model-supplied (outbound) and inbound
image/file URLs server-side via httpx with follow_redirects=True and no
SSRF check. A model response containing <img src="http://169.254.169.254/...">
routed through ImageUrlHandler -> download_url and would fetch cloud-metadata
endpoints; same for inbound media.
Add an is_safe_url() pre-flight plus an async redirect event-hook that
re-validates every 30x target, matching the cache_image_from_url() guard in
gateway/platforms/base.py. The other gateway adapters already guard their
URL-fetch paths; this was the remaining unguarded one.
A config left with `provider: anthropic` but a leftover
`base_url: https://openrouter.ai/api/v1` (e.g. after a provider switch)
would route Anthropic OAuth/setup-token traffic to OpenRouter and 404.
Add `_anthropic_base_url_override_ok()` and gate the three native-Anthropic
resolution branches (pool, explicit, native) on it. The guard honors a
configured `model.base_url` only when it plausibly speaks the Anthropic
Messages protocol — official `*.anthropic.com` / `*.claude.com` hosts, Azure
Foundry endpoints, and `/anthropic`-suffixed or Kimi `/coding` proxies — and
falls back to `https://api.anthropic.com` otherwise. Aggregator URLs like
openrouter.ai / api.openai.com are treated as stale.
Reconstructed from @clovericbot's PR #3661 onto current main: the original
patched one branch with an anthropic-only allow-list, which would have broken
Azure-via-anthropic; widened to all three sites and made Azure/proxy-safe.
Bundled platform plugins (telegram, discord, feishu, teams, ...) were
eagerly imported at plugin-discovery time on every `hermes` invocation,
including plain `hermes chat` which never touches a gateway platform.
Their modules import heavy platform SDKs at module level (lark_oapi,
microsoft_teams, discord.py, slack_bolt, ...) — feishu alone pulled in
lark_oapi (~2.6s), teams pulled microsoft_teams (~1.9s).
Discovery now registers a cheap deferred loader per platform in the
platform_registry; the adapter module is imported only when the gateway
/ cron / setup / send_message path actually asks for that platform.
is_registered() and the iterate-all accessors stay correct (deferred
counts as registered; plugin_entries()/all_entries() materialize all
deferred loaders, since those paths genuinely need every adapter).
Cold start: ~4.4s -> ~2.45s to banner. discover_and_load: 2.0s -> 0.3s
(warm), and the heavy SDKs are no longer imported at all in CLI mode.
Every shipped platform remains available out of the box — it just loads
on first use.
When config.yaml has `provider: auto` and a non-cloud `base_url` (e.g. Ollama
at localhost:11434), requests were silently sent to https://api.anthropic.com
whenever ANTHROPIC_API_KEY was present in the environment, ignoring the
configured local endpoint and returning HTTP 401 / "credit balance too low".
Root cause: resolve_provider("auto") scans env vars and returns "anthropic"
when ANTHROPIC_API_KEY is set, before config.model.base_url is ever consulted.
In resolve_runtime_provider(), before calling resolve_provider(), short-circuit
to the OpenAI-compatible resolver when no explicit creds were passed, provider
is "auto"/unset, and a non-cloud base_url is configured. Well-known cloud roots
(openrouter.ai, anthropic.com, openai.com) are matched on HOST (not substring)
so look-alike hosts can't evade the bypass and leak a cloud credential.
Co-authored-by: Hermes Agent <hermes@nousresearch.com>
The curator's inactivity prune archived any non-pinned agent-created
skill whose activity was older than archive_after_days (90d). A skill
loaded only by a cron job had its usage bumped solely when the job
fired, so paused jobs, infrequent (quarterly/annual) schedules, and
far-future one-shots aged their skills out from under them — the next
run then failed to load the now-archived skill.
- cron/jobs.py: add referenced_skill_names() returning skills used by
ANY job (incl. paused/disabled).
- curator.apply_automatic_transitions(): skip cron-referenced skills
like pinned; add a use=0 grace floor so a never-used skill is not
marked stale/archived until it is at least stale_after_days old.
- LLM review pass: candidate list marks cron=yes; prompt forbids
pruning cron-referenced skills and never-used skills under 30 days.
Tested E2E against a real cron job + real usage records and with 4 new
unit tests.
On Windows, uv pip install -e . can register hermes.exe in package metadata
while the launcher never lands on disk. Detect missing [project.scripts]
shims and reinstall entry points under the existing quarantine path in
hermes update and install.ps1.
* fix(daytona): quote single-upload mkdir parent path
The single-file _daytona_upload() path shelled out 'mkdir -p {parent}'
with the remote parent interpolated unquoted, so shell metacharacters in
the path could break the command or inject arbitrary commands into the
sandbox. The bulk-upload, bulk-download, and delete paths were already
hardened with shlex-quoting helpers; this single-upload path was missed.
Route it through the existing quoted_mkdir_command() helper and add a
regression test covering a path with shell metacharacters.
Reported by @Gutslabs (#3960); the original branch predated the
file_sync refactor, so the fix is re-applied to the current code path.
* docs(infographic): daytona quote-sync fix
Removed/unauthorized Telegram users could inject prompt content before the
per-user auth gate fired. The adapter ran `_should_process_message`,
`_build_message_event`, and text/photo batching — and dispatched to the
runner — before `_is_user_authorized()` (gateway/authz_mixin.py) rejected
the sender. Unmentioned group chatter from a removed user was also
persisted into the session transcript via `_observe_unmentioned_group_message`,
leaking into the agent's observed context independent of dispatch.
Add `_is_user_authorized_from_message()` as an intake prefilter that runs
in `_handle_text_message`, `_handle_command`, `_handle_location_message`,
and `_handle_media_message` BEFORE batching, event construction, and the
unmentioned-group observe branch. It reuses the runner's
`_is_user_authorized()` with a correctly-shaped SessionSource (group vs
forum vs dm, real chat_id for TELEGRAM_GROUP_ALLOWED_* allowlists),
falls back to env allowlists, and only rejects when an allowlist actually
exists — unknown DMs with no allowlist still reach the pairing flow.
Channel posts authorize via `sender_chat` identity when `from_user` is
absent.
Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>
Co-authored-by: Carlos Manuel Cejas <carlosmcejas@gmail.com>
The SSRF cluster (7a6fe9bb, 48f5c425, 7ef04ae7) sealed
browser_snapshot, browser_vision, and _browser_eval against
eval-navigated private pages, but browser_get_images bypasses
_browser_eval and calls _run_browser_command("eval", ...) directly.
An eval-driven navigation to a private address followed by
browser_get_images would leak image src URLs and alt text from the
private page.
Add the same _eval_ssrf_guard_active + _current_page_private_url
recheck before returning image data, matching the pattern established
by the sibling guards.
5 new tests cover: block on private page, allow on public page, skip
for local backend, skip when private URLs allowed, no guard needed on
failed eval.
Route FS/git REST through the active profile, mount the remote folder picker
at app root, keep the project dialog open while picking, show a first-run
blank state, flip into grouped view on create, and constrain the picker scroll
area so Select stays reachable.
Pin the desktop-to-gateway cwd handoff: createBackendSessionForSend must pass
the current workspace cwd into session.create so the backend registers the
session cwd before the agent/tools run.
Let UI callers ask for folders/files without knowing remote-picker limits:
selectDesktopPaths now normalizes remote directory selection to a single folder
inside the facade. Project creation and composer context picking no longer branch
on remote mode; they route through desktop-fs helpers just like git callers route
through desktopGit(). Behavior unchanged except remote folder context now works
through the same backend picker path.
Keep the remote git mirror as a thin facade: route all GETs through gitGet,
all mutations through gitPost, and keep consumers on desktopGit(). On the
backend, route git paths through a single _git_path helper instead of repeating
str(_fs_path(...)) in every endpoint. Behavior unchanged.
Second pass on the remote-project flow: the project dialog and git cockpit were
remote-aware, but the composer's Add file/folder context picker still called the
native Electron picker directly. Route it through selectDesktopPaths so remote
sessions use the backend-aware picker instead of local disk paths; preserve local
multi-select behavior and keep remote folder selection single because the in-app
remote picker only supports one directory.
Also use readDesktopFileDataUrl for image previews so an already-known backend
image path can be read through /api/fs/read-data-url, and add focused coverage
for backend file-diff routing plus the plain-folder git init/worktree path.
writeProjectIdea used the local-only Electron writeTextFile, so on a remote
gateway IDEA.md never landed on the backend (where the project folder lives).
Route it through writeDesktopFileText (local Electron / POST /api/fs/write-text).
Collapse the two near-duplicate status parsers (_parse_status_v2 +
_iter_status_entries) into a single _walk_entries generator feeding the rail,
review list, and commit flow; share the staged predicate; hoist `import re`.
Behavior unchanged.
After the folder picker fix, an added remote folder was still half-usable:
the desktop's git GUI (coding-rail status, worktree lanes, review pane,
branch switch, file diff) all ran Electron-local git on the USER's machine,
so against a remote-gateway repo they silently degraded to empty.
Mirror the whole surface over the dashboard REST API so it acts on the
BACKEND repo where sessions actually run:
- hermes_cli/web_git.py: git/gh logic (status, worktrees, branches, review
list/diff/stage/unstage/revert/commit/commit-context/push/ship-info/
create-pr, file-diff, worktree add/remove, branch switch) shelling to the
system git, mirroring the Electron ops' shapes.
- web_server.py: /api/git/* routes (same auth gate + _fs_path hardening as
/api/fs, executor-offloaded, mutations -> 400).
- apps/desktop desktop-git.ts: remote-aware facade exposing the same shape as
window.hermesDesktop.git; coding-status / review / projects / model /
desktop-fs route through desktopGit() so local stays Electron, remote hits
/api/git/*.
Tests: tests/hermes_cli/test_web_server_git.py (real repo: status counts,
review classification, diff incl. untracked all-add, stage+commit roundtrip,
worktree/branch lifecycle, commit-context, gh-absent ship-info, auth) and
desktop-git.test.ts (local vs remote routing, envelope unwrap, POST bodies).
The new-project / add-folder dialog (PR #49037) picked folders via the
native Electron dialog (pickDefaultProjectDir), which only browses the
LOCAL machine. On a remote gateway that picks a path that doesn't exist
on the backend where sessions actually run.
Route pickProjectFolder() through selectDesktopPaths({directories,
multiple:false}) — the same remote-aware path the retired right-sidebar
picker used: local mode opens the native directory dialog, remote mode
browses the backend filesystem via the in-app RemoteFolderPicker. Seed
it with the backend's default cwd on remote so it opens somewhere useful.
When a local browser_navigate (or any browser command) fails fast because
Chromium isn't on disk, attempt a one-shot binary download via
`agent-browser install` and retry instead of only printing a hint.
Scope is narrow on purpose:
- binary only, never `--with-deps` (that shells apt/needs root, so missing
system libraries stay a user action)
- gated by `security.allow_lazy_installs` (same opt-out as every lazy install)
- skipped in Docker (Chromium ships in the image)
- attempted once per process
Follow-up to #54353, which made the cold-start failure legible; this closes
the "doesn't actually install the missing browser" gap for the common case.
Local browser_navigate cold-starts the agent-browser daemon and Chromium;
60s was too short on slow Linux hosts and timeouts discarded stderr,
leaving users with a generic failure. Use a 120s floor on first open,
inject --no-sandbox in Docker, include captured daemon output plus install
hints when commands time out, and show "Failed to open" in the desktop
tool chip when navigation returns success=false.
_get_platform_tools() applies agent.disabled_toolsets as a final
override AFTER reading platform_toolsets.<platform>, so a toolset
listed there stays permanently OFF no matter what the toggle write
path saves. Blank Slate installs pre-populate this list with ~27
toolsets, making most of the desktop Toolsets UI un-enableable
(issue #49995).
Fix: _save_platform_tools() now removes any toolset the user just
explicitly enabled FOR THIS PLATFORM from agent.disabled_toolsets.
Toolsets the user did not touch, or that remain disabled on other
platforms, are left alone -- disabled_toolsets keeps working as a
cross-platform suppression list for anything not actively re-enabled.
Disabling a toolset (unchecking it) does not touch disabled_toolsets
at all -- only enables reconcile it.
Verified end-to-end with the exact repro from the issue: Blank Slate
config (disabled_toolsets=['todo','memory','browser'], cli=['file',
'terminal']) -> enable 'todo' via the toggle -> _get_platform_tools()
now resolves 'todo' as enabled while 'memory'/'browser' (untouched)
remain disabled.
Added 4 regression tests. Full tools_config suite: 101 passed
(97 existing + 4 new), no regressions.
Fixes#49995
main (cb982ad99) wired windows_hide_flags() into the auxiliary git/gh/wmic/
bash/powershell/taskkill legs but left two it didn't reach, plus the Electron
backend-launch leg it explicitly deferred. Cover them the same way:
- apps/desktop/electron/main.cjs: getNoConsoleVenvPython resolves the BASE
pythonw.exe instead of the venv Scripts\pythonw.exe shim, which re-execs a
console python.exe and flashes a conhost the desktop backend can't suppress.
Both backend creators put the venv site-packages on PYTHONPATH so imports
still resolve under the base interpreter. (main's commit said this Electron
leg "needs a Windows-tested change of its own".)
- tools/tts_tool.py, tools/transcription_tools.py, plugins/platforms/discord:
ffmpeg conversions (voice notes / TTS / STT) via windows_hide_flags().
- plugins/platforms/whatsapp: netstat + taskkill bridge-port cleanup via
windows_hide_flags().
All no-ops on POSIX. Tests assert the base-pythonw preference and the ffmpeg
legs pass CREATE_NO_WINDOW.
The Windows desktop GUI runs its backend headless via pythonw.exe. Several
auxiliary subprocess sites that run inside that windowless backend spawned
console-subsystem children (git, gh, wmic, powershell, bash, rg, taskkill)
WITHOUT CREATE_NO_WINDOW, so Windows allocated a fresh conhost per call and
flashed a black window on screen — sometimes continuously (the dashboard
Projects-tree git probe alone fired ~118 spawns in 60s on startup).
The terminal tool, cron, browser, code_execution, and gateway-spawn paths
already carry windows_hide_flags(); these auxiliary probe/scan/launcher legs
were missed. Wire the existing helper into them:
- tui_gateway/git_probe.py: run_git (+ encoding=utf-8/errors=replace, fixes the
cp950 UnicodeDecodeError on CJK paths from the same site)
- agent/coding_context.py: _git (per-turn git status/log/diff)
- agent/context_references.py: _run_git + _rg_files (@file/@ref resolution)
- hermes_cli/copilot_auth.py: gh auth token probe (auxiliary provider:auto)
- hermes_cli/gateway.py: wmic + PowerShell Get-CimInstance PID scan
- hermes_cli/main.py: wmic stale-dashboard PID scan
- gateway/status.py: taskkill /T /F force-kill
windows_hide_flags() returns 0 on POSIX, so every changed call is a no-op on
Linux/macOS (verified: real git/rg probes still work; Windows-simulated calls
all pass creationflags=CREATE_NO_WINDOW).
Scoped to the windowless-backend paths that cause the reported flashing. The
Electron updater-handoff leg (main.cjs windowsHide:false) and the
interactive-CLI banner probes (cli.py) are intentionally NOT touched here —
the former needs a Windows-tested change of its own, the latter runs in a
visible console anyway.
Tracking: #54220
Refs: #53178#53631#53781#53957#49602#52982#53424#53053#53016
OAuth-protected MCP servers (e.g. Hospitable) return 200 text/html on an
unauthenticated HEAD probe — a login/landing page the server cannot substitute
for a real MCP response without a Bearer token. The preflight cannot
distinguish this from a misconfigured URL, so it raises NonMcpEndpointError
before the OAuth browser flow has a chance to run.
Add `and self._auth_type != "oauth"` to the preflight condition in
MCPServerTask.run(). The probe is inapplicable to OAuth servers: their URL
legitimacy is established by .well-known/oauth-protected-resource during the
OAuth handshake, not by a GET content-type check.
Concrete repro: Hospitable (https://mcp.hospitable.com/mcp) returns
`200 text/html` to an unauthenticated httpx HEAD. Without the guard:
✗ NonMcpEndpointError at `hermes mcp test`
With the guard:
✓ Connected (1487ms) — 63 tools discovered
Relation to open PRs:
- #37598 adds a POST probe fallback for POST-only non-OAuth servers (e.g.
DocuSeal), but only passes when POST returns 2xx + MCP content-type.
Hospitable returns 401 on the POST probe (Bearer challenge), so #37598
does not cover this case.
- #49463 extends the POST probe to also pass on non-2xx auth challenges
(making it OAuth-aware), but is labeled duplicate of #37598 and may not
land independently.
This fix is complementary: it handles OAuth servers with zero extra
round-trips rather than adding a POST probe step.
Tests:
- test_oauth_server_html_response_raises_without_skip: documents that
_preflight_content_type raises NonMcpEndpointError for 200 text/html
(the underlying issue), with an OAuth-server docstring.
- test_run_skips_preflight_for_oauth: verifies that run() does NOT invoke
_preflight_content_type when auth_type=="oauth", using class-level
monkeypatching so the gate is exercised without a live MCP transport.
23 passed tests/tools/test_mcp_preflight_content_type.py
When a stale lock file survives a gateway crash, `acquire_scoped_lock()`
may return `(False, existing_dict)` even after detecting and deleting
the stale lock (e.g. if unlink fails or a race condition occurs).
Previously, `_acquire_platform_lock()` called
`_set_fatal_error(..., retryable=False)`, which permanently killed the
platform — the reconnect watcher never retries a non-retryable fatal
error.
Change to `retryable=True` so the platform enters the "retrying"
state and the reconnect watcher can attempt acquisition again after the
standard backoff delay.
Fixes#54167
_append_model_switch_marker() appended the post-/model-switch context marker
to session history as {"role": "system"}. The cached system prompt is
prepended to the API message list (conversation_loop.py), so this marker
became a SECOND system message mid-array after prior user/assistant turns.
Strict OpenAI-compatible providers (vLLM, Qwen) reject any system message
that is not at the beginning of the array, returning HTTP 400 and killing
the conversation on the next turn.
Flip the marker to role="user" (history entry + both session-DB persist
sites), matching the existing personality-overlay marker which already uses
role="user". repair_message_sequence() then coalesces it with adjacent user
turns as needed.
Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>
Co-authored-by: Lucas Nicolas <lucas.nicolas@proton.me>
On macOS app.quit() closes windows but window-all-closed deliberately keeps
the process alive (Dock convention). Every detached hand-off (update swap,
relaunch, Windows bootstrap recovery, uninstall cleanup) waits for the
desktop PID to exit before replacing/removing the bundle — so the process
never dying means the script spins its full PID-wait and the user sees a
blank app, or an uninstall that appears to do nothing.
Add a module-level isQuittingForHandoff flag, set before every hand-off
app.quit(); window-all-closed then quits on all platforms when it's set.
Covers all five hand-off sites including the Linux relaunch path.
launchd restart can leave the gateway job stopped but still registered after
update-time drain logic, so a direct bootstrap hits exit 5 and falls back to a
detached process. Booting the stale registration out before bootstrap keeps the
launchd-managed restart path intact and locks it with a regression test.
Constraint: Keep upstream-facing conventional commit style while preserving local decision context
Rejected: Treat bootstrap exit 5 as expected | Leaves macOS launchd restart outside launchd supervision after update
Confidence: high
Scope-risk: narrow
Directive: Keep launchd start/restart recovery flows aligned when changing launchctl handling
Tested: pytest -q tests/hermes_cli/test_gateway_service.py -k "launchd_restart_boots_out_stale_registration_before_bootstrap or launchd_restart_falls_back_to_detached_on_error_5 or launchd_restart_drains_running_gateway_before_kickstart or launchd_restart_self_requests_graceful_restart_without_kickstart"
Tested: pytest -q tests/hermes_cli/test_gateway_service.py -k launchd
Not-tested: Manual macOS launchctl restart after hermes update
test_spinner_elapsed_format_is_fixed_width_to_reduce_wrap_jitter derived
_tool_start_time from the live time.monotonic() clock (now - 65.2 / now - 9.2).
monotonic()'s epoch is arbitrary — on a host where monotonic() < 65.2 (fresh
subprocess on a freshly-booted CI runner) the start time went negative, the
(t0 > 0) guard in _render_spinner_text() dropped the '(elapsed)' suffix, and
short.split('(',1)[1] raised IndexError: list index out of range. Deterministic
given a small clock, so it would keep flaking, not clear on rerun.
Pin time.monotonic to a fixed 1000.0 and offset _tool_start_time from it so both
the <60s and >=60s paths always render the elapsed suffix regardless of the
runner's monotonic epoch.
Pre-existing main flake (surfaced in CI test slice 1/8).
The README line enumerated 11 providers inline, which dilutes the point
and goes stale as providers come and go. Replace with Nous Portal,
OpenRouter, OpenAI, your own endpoint, and a 'many others' link to the
canonical AI Providers docs page that already lists them all.
The desktop app and dashboard chat reach the agent through the /api/ws
JSON-RPC sidecar (tui_gateway.ws.handle_ws), NOT through
tui_gateway.entry.main() — the stdio-TUI path that spawns the background
MCP discovery thread. In the WS process discovery was therefore never
started: _make_agent only *waits* (wait_for_mcp_discovery), which no-ops
when the thread was never created, so the agent snapshotted an MCP-less
tool list. The only discovery trigger reachable was a manual /reload-mcp,
which is why tools appeared after a reload but vanished on restart.
Start the shared, idempotent, config-gated background discovery in
handle_ws right after accept() and before gateway.ready, so the first
agent build picks up already-spawning servers (and the existing
late-binding refresh handles slow ones).
Fixes#38945.
The salvaged #35519 regression guard asserted that default (non-file_read)
mode keeps a head/tail `ghp_S1...Pn2T` mask for a `token: <key>` line. On
current main the YAML config pass (`_YAML_ASSIGN_RE`, key `token`) re-masks
the already-prefix-masked value to `***`, so the assertion was stale. Switch
to a bare-token context so the guard isolates what it claims (prefix-mask
head/tail shape in default mode) without depending on the YAML collapse.
When security.redact_secrets is on (default), read_file/search_files/cat
applied redact_sensitive_text(code_file=True) to file content, which still
ran prefix masking. An API key in config.yaml (ghp_..., sk-..., xai-..., etc.)
came back as a head/tail mask like `ghp_S1...Pn2T` — a plausible-looking
truncated key. When an agent read that and wrote it back to config, the masked
value replaced the real credential, silently breaking auth (401). Production
evidence: a config.yaml found containing the exact 13-char masked GitHub PAT.
The two community PRs (#35529, #35534) fixed the corruption by NOT redacting
prefixes for config reads — but that exposes the user's real keys to the agent
context, model, and logs (a security regression). This takes the safer route:
keep redacting, but for file content emit a NON-REUSABLE sentinel.
- New `_mask_token_nonreusable`: prefix secrets -> `«redacted:ghp_…»` (vendor
label preserved for debuggability; zero secret bytes; angle-bracket/ellipsis
wrapper is syntactically invalid as a token so it can't be mistaken for or
written back as a usable key).
- New `redact_sensitive_text(file_read=True)` routes prefix matches through it
(implies code_file=True). Default/log/display mode is UNCHANGED — `_mask_token`
still keeps head/tail (fine for logs, never written back).
- Wired the 3 file_tools.py call sites (read_file / search_files / cat) to
file_read=True.
Fixes both the corruption AND avoids the secret-exposure of the un-redact
approach. 6 new tests (sentinel shape, no-leak, not-a-plausible-key, default
mode unchanged, file_read implies code_file, sk- prefix); 88 redact tests pass;
mutation-verified (reverting to the old mask fails the sentinel/leak tests).
Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>
Co-authored-by: adammatski1972 <289282750+adammatski1972@users.noreply.github.com>
Closes#35519. Supersedes #35529, #35534.
The zombie status probe referenced psutil.Process/NoSuchProcess/Error
unconditionally, which raised AttributeError when psutil is a partial
stub that only defines pid_exists (as in test_windows_native_support's
fallback tests). Guard the probe so any failure to read status degrades
to the authoritative pid_exists() instead of raising.
Under systemd Restart=always, the old gateway becomes a zombie (in the
process table, awaiting reap) when the replacement starts. _pid_exists()
reported the zombie as alive, so --replace waited on a PID that never
dies, then aborted with exit 1 — a silent crash loop. Standalone runs are
unaffected because nothing respawns the gateway into a zombie.
The live path is psutil.pid_exists(), which returns True for zombies, so
the check is added there (Process.status() == STATUS_ZOMBIE -> dead). The
psutil-less POSIX fallback also reads /proc/<pid>/stat (state Z) with a ps
state= fallback for macOS/BSD, before the os.kill(pid, 0) liveness probe.
Diagnosis and the /proc + ps POSIX fallback by MorAlekss (PR #44898);
extended to cover the psutil hot path so the fix applies on normal installs.
Co-authored-by: MorAlekss <mor.aleksandr@yahoo.com>
Folds in PR #42124 (kyssta-exe): systemd_install gained a non_interactive
flag so the 'Remove the legacy unit(s)?' prompt — the second hidden prompt
not guarded by --start-now/--start-on-login — is also skipped in headless
contexts. Updates systemd_install test mocks to accept the new kwarg and
adds coverage for the legacy-unit-skip path.
When running `hermes gateway install` on Linux/systemd, the command
unconditionally prompts with two `prompt_yes_no` questions, breaking
headless installs (SSH, CI, provisioning scripts) and ignoring the
existing --start-now / --start-on-login CLI flags that the Windows
branch already respects.
The fix mirrors the Windows path: read CLI flags first, prompt only
when flags are not provided AND stdin is a TTY, and fall back to True
defaults for non-TTY contexts. The argparse help strings are promoted
from SUPPRESS to visible so users can discover the flags.
Fixes#42065
When the previous frame's stdout.write has not drained (the outer terminal
parser is overwhelmed by a wide CR+LF burst — CJK + ANSI tool output on a
high-context session), the renderer kept writing a new frame every tick. That
piled writes onto an already-backed-up pipe and kept the macrotask queue hot,
starving the stdin 'readable' callback — the observed stdin freeze where the
agent loop keeps running but keystrokes/Ctrl-C are dead.
onRender now coalesces: while pendingWriteStart is non-null (prior write's
drain callback hasn't fired) it skips the frame and retries on the drain tick
instead of writing. A MAX_COALESCED_BACKPRESSURE_FRAMES ceiling forces a write
through after N skips so a terminal whose drain callback never fires (OSError
EIO on flush) self-heals once the pipe recovers rather than wedging forever.
TTY-only; piped stdout has no flow control. Coalesce counter resets on every
real write.
This is the stdout-backpressure strand left open after #54046 fixed the
swallowed-exception strand.
The /api/pty handler only closed the PtyBridge in the writer loop's finally.
On child EOF the reader task closes the WebSocket, but if the handler task is
cancelled the instant the socket closes, the writer's finally can be skipped
and the PTY fds leak (#54028) — the FD-leak the regression test guards. Under
dashboard auto-reconnect this stacks orphaned PTYs until fds are exhausted.
Reap the bridge in the reader's EOF finally too (close() is idempotent), so
the PTY is reaped independently of the writer-loop cancellation race. Harden
the regression test to poll for teardown instead of asserting on the same
tick. Was flaky on main (2/20); now 25/25.
PR #39219 split run_browser_install_with_timeout into a thin wrapper that
delegates to a new run_with_timeout helper (and parameterized the timeout
binary as $timeout_bin for macOS gtimeout support), but did not update
tests/test_install_sh_browser_install.py. The behavioral harness extracted
only the now-empty wrapper, so the install command never ran (runs==[]),
failing all 8 behavioral cases; two text assertions also still expected the
old literal 'timeout' invocation.
Fix the stale test: extract run_with_timeout alongside the wrapper, and match
the $timeout_bin-parameterized GNU-timeout strings. Behavior unchanged.
The desktop install step ran npm ci / npm run pack with no wall-clock cap, and
the sibling browser-tools / TUI / agent-browser dependency installs had the same
gap. The Electron binary (~150MB) is fetched from GitHub during the pack; on a
throttled or region-blocked link that download can *stall* rather than fail —
npm never errors and never exits, so the installer sits on "Build desktop app"
(step 9/11) indefinitely with only harmless 'npm warn deprecated' lines visible.
The existing self-heal escalation (cache purge -> dist restore -> npmmirror
fallback) only fires when pack returns non-zero, so a stall bypassed it.
- run_with_timeout (generalized from run_browser_install_with_timeout): GNU
timeout --foreground -k 10 (Ctrl+C-aware, #35166) / gtimeout for external
commands, else a pure-shell process-group watchdog so stock macOS (neither
binary present) is protected. Shell functions (_desktop_pack) always take the
pure-shell path — the timeout binary can't exec a function. Integer-normalized
budget + a boundary recheck so a command finishing in the final poll second
isn't mislabeled 124. The internal wait is guarded so set -e can't abort
mid-function before the real exit code is computed.
- Wrap the desktop npm ci/install (sharing ONE budget via a computed deadline so
a stall can't cost 2x DESKTOP_BUILD_TIMEOUT) + all three _desktop_pack attempts
(DESKTOP_BUILD_TIMEOUT, default 900s), and the browser-tools / TUI / agent-
browser registry installs (NODE_DEPS_TIMEOUT, default 600s).
A stall now converts to a bounded non-zero exit that feeds the existing mirror
self-heal instead of hanging the whole install.
* fix(security): redact secrets in background process + foreground env-dump output
Terminal-output redaction was incomplete (#43025):
- Gap 1: process(action=poll/log/wait) returned background stdout verbatim —
no redaction at all. A background printenv/server/test emitting a key leaked
raw to the model, session.db, and CLI display. Same for the gateway
background-process watcher's completion/progress notifications.
- Gap 2: the foreground terminal path hardcoded code_file=True, which skips the
ENV-assignment pass, so an opaque token (no vendor prefix) from env/printenv
leaked even there.
Adds agent.redact.redact_terminal_output(output, command) as the single policy
for ALL terminal-output surfaces: env-dump commands (env/printenv/set/export/
declare) get the ENV-assignment pass (code_file=False) to mask opaque tokens;
other commands stay on code_file=True to avoid false positives on source dumps.
Wired into terminal_tool, process_registry (_handle_process boundary), and the
gateway watcher. Respects security.redact_secrets (no force) — opt-out preserved.
* docs: add infographic for #43025 terminal-output redaction fix
The merged CLOSE-WAIT heartbeat (#52744) only probes get_me(), which uses the
general request path and stays healthy while PTB's getUpdates consumer is
silently wedged (updater.running=True but the long-poll task is stuck, observed
on WSL2). DMs then queue in the Bot API and never reach handlers (#42909).
Augment the existing _polling_heartbeat_loop to also probe
get_webhook_info().pending_update_count. After two consecutive probes that see a
non-draining queue while the updater claims to be running, escalate into the
existing _handle_polling_network_error recovery ladder — no new restart
machinery. No-ops in webhook mode, when the updater is not running, or when a
reconnect is already in flight.
Credit to @gazzumatteo, whose PR #42959 identified the pending_update_count
signal as the missing liveness probe. This reuses the existing heartbeat +
recovery path rather than adding a parallel watchdog.
Fixes#42909.
Two related redaction bugs from #43083:
1. build_assistant_message redacted tool-call arguments in-memory. That dict
feeds both the replayed conversation history and state.db (which is itself
replayed verbatim on session resume), so the model read back its own
PGPASSWORD='***' psql call and copied the placeholder, breaking every
credential-dependent command on the second turn. The masking gave no real
protection either — the same secret still leaks through tool OUTPUT. Remove
it. Keeping secrets out of the replayable store is a separate
tokenization/vault concern (security.redact_secrets still governs
storage-time redaction elsewhere).
2. _AUTH_HEADER_RE's greedy \S+ credential class ate a closing quote when the
token sat flush against it (Authorization: Bearer sk-.."), turning value
corruption into syntax corruption (unterminated quote -> shell EOF /
SyntaxError). Exclude " and ' from the token class; real credentials never
contain them.
Closes#43083.
Config-backed quick_commands bypassed the admin-only slash gate. The
early gate in _handle_message only fires for registry-known commands
(is_gateway_known_command), but quick_commands are never in the gateway
registry, so they reached the type:exec dispatch sink unchecked. An
allowlisted non-admin gateway user could invoke admin-only quick
commands — including shell exec in the gateway process — even when the
operator set allow_admin_from / user_allowed_commands to lock them out.
Apply _check_slash_access(source, command) at the quick_commands
dispatch site (the single exec chokepoint, cold-path only) using the
raw typed name. Admins and users with the command in
user_allowed_commands still run it; backward-compat (no policy set)
is unaffected.
Fixes#44727.
Co-authored-by: maxpetrusenko <max.petrusenko.agent@gmail.com>
Co-authored-by: zapabob <1920071390@campus.ouj.ac.jp>
* fix(dashboard): close PTY WebSocket on child EOF to stop FD leak
The /api/pty handler's reader task returns on child EOF, but the writer
loop stayed blocked on ws.receive() until the browser sent a disconnect.
When the browser socket is half-open (no FIN delivered — common on
macOS/launchd), that disconnect never arrives, so the handler never
reaches its finally and the PTY master fd + child process leak. With
dashboard auto-reconnect (#52962), every dropped socket then spawns a
fresh PTY on top of the orphaned one, exhausting file descriptors within
hours (EMFILE / Errno 24).
Fix: the reader task now closes the WebSocket in a finally when the child
EOFs or the send side breaks, which unblocks ws.receive() so the existing
finally runs bridge.close(). The writer loop also guards ws.receive()
against the RuntimeError Starlette raises once the socket is closed.
Reported by @fifteenzhang.
Fixes#54028
* docs: add infographic for #54028 PTY FD leak fix
The snapshot/vision guards re-check the page URL before returning content,
but browser_console(expression=...) -> _browser_eval returns arbitrary JS
results directly, leaving two same-class bypasses open:
1. Direct fetch: fetch('http://127.0.0.1/secret').then(r=>r.text()) reads
a private endpoint and returns the body — the page URL stays public so
the post-eval recheck never sees it.
2. Navigate-then-read: location.href='http://127.0.0.1/' then a later eval
reads document.body.innerText.
Guard _browser_eval on the same condition as navigate/snapshot/vision
(not local backend, not local sidecar, not allow_private_urls):
- pre-scan the expression for private/always-blocked URL literals
- re-check window.location.href after the eval at both success-return
sites (supervisor fast-path + subprocess fallback)
Probe failures fail-open (matching the snapshot/vision guards).
The private-network guard in browser_snapshot() and browser_vision()
blocked all private URLs, including those accessed via local sidecar
sessions (hybrid routing). Local sidecar sessions intentionally access
private URLs — the cloud provider never sees the URL in that case.
Add `_is_local_sidecar_key(effective_task_id)` check to both guards,
matching the existing pattern in browser_navigate().
Fixes#45101 review feedback from egilewski.
The SSRF bypass in #44731 was only patched for browser_snapshot(), but
browser_vision() exposes the same vulnerability — it takes a screenshot
and sends it to the vision model without checking if eval-driven
navigation moved the page to a private/internal URL.
Add the same current-page URL safety check to browser_vision() before
any screenshot is captured, encoded, or forwarded to the vision model.
This covers both the normal screenshot path and the Lightpanda Chrome
fallback path.
7 new tests: blocks private URL, allows public URL, skips in local
backend, skips when private URLs allowed, handles eval failure/empty/exception.
browser_snapshot() now checks the current page URL before returning
content. When browser_console() changes location.href to a private or
internal address (e.g., http://127.0.0.1:8080/), the snapshot returns
an error instead of exposing the private page content.
This closes the SSRF bypass where an attacker could:
1. Navigate to a public page
2. Use browser_console to eval location.href = 'http://127.0.0.1:port/'
3. Use browser_snapshot to read the private page content
The fix reuses the existing _is_safe_url() and _allow_private_urls()
infrastructure, and fails open if the URL check itself fails.
Fixes#44731
HolographicMemoryProvider.shutdown() dropped its MemoryStore reference
without calling the existing MemoryStore.close(). Since the connection is
opened check_same_thread=False (one per session), its fd was released by
refcount/GC at a non-deterministic time on a non-deterministic thread,
churning a DB fd through the kernel free pool on every session teardown.
Call close() so the fd is released deterministically.
Reported by @alfranli123 (#44037), who pinpointed the exact code location.
Note: the report's TLS-fd-recycle corruption attribution could not be
reproduced from the code — dropping a sqlite connection flushes valid
SQLite pages via the VFS, never TLS framing, and the provider is at most a
releaser of DB fds, not a TLS-flushing socket owner. This change is correct
resource hygiene that removes per-session fd churn regardless.
A hard gateway crash (exit code 1) skips the graceful shutdown path, so
sessions.json is never cleared and is left pointing at sessions already
ended in state.db. On the next startup get_or_create_session() reuses
those stale entries as long as the time/policy reset checks pass — it
never consults end_reason — so every incoming message is silently routed
into a closed session, with no log or error (#52804).
SessionStore._ensure_loaded_locked() now calls a new
_prune_stale_sessions_locked() that drops any entry whose session_id has
end_reason IS NOT NULL in state.db. Idempotent, _db=None / legacy-absent
safe, DB errors non-fatal, sessions.json rewritten only when something
was pruned. Self-heals into a fresh session on the next message.
Reported and diagnosed by @terry197913 (#52808).
#35994 moved /new reset cleanup off the loop, but _cleanup_agent_resources
(agent.close() subprocess teardown; shutdown_memory_provider() plugin IO) was
still called INLINE on the event loop from three other sites:
- _session_expiry_watcher (5-min idle sweep) — live loop
- _handle_message_with_agent cache-hygiene re-eviction — live loop
- _finalize_shutdown_agents / stop() idle-cache loop — shutdown
A wedged memory provider on any of these froze the loop: bot goes silent,
runtime-status updated_at heartbeat stops advancing, and SIGTERM can't be
serviced (requires kill -9) — exactly the #53175 zombie pattern.
Adds _cleanup_agent_resources_off_loop: a bounded (30s) worker-thread offload
mirroring the #35994 reset fix, and routes all four sites through it.
The system-prompt backend probe imported a nonexistent symbol —
`from tools.environments import get_environment` — which always raised
ImportError: cannot import name 'get_environment'. The exception is caught
and only drops the live backend description to a static fallback, so it is
cosmetic, but it broke the live OS/user/cwd probe for every non-local
backend (docker/singularity/modal/daytona/ssh).
The real factory is `_create_environment` in tools.terminal_tool. Build the
environment the same way the live terminal path does (select backend image,
assemble ssh/container config from _get_env_config()), then run the probe.
Note: this does NOT affect tool loading — tool selection runs each tool's
check_fn and never consults this probe. Regression from #52147 (2026-06-25).
Closes#53667 (probe import); the 'cronjob-only' tool-collapse symptom is
not reproducible — tool selection has no probe dependency and memory's
check_fn is unconditionally True.
* test(ci): raise per-file timeout 140s to 300s to stop false timeouts
The per-file parallel runner caps each test-file subprocess at a flat
wall-clock budget. Combined with per-test subprocess isolation (a fresh
Python process per test), a large-collection file pays N x (interpreter
startup + import) of overhead before any test logic runs. That overhead
dilates under load on shared CI runners, so a file that finishes in
~100s on a quiet box can blow the old 140s cap purely from scheduling
jitter, surfacing as a false 'no tests ran' timeout (rc=124) with zero
actual test failures.
Raise the default to 300s (5 min). The Docker build matrix jobs already
take 7-10 min, so this headroom costs nothing on total CI wall time
while still bounding a genuinely hung file.
* docs: add infographic for CI per-file timeout bump
Two Windows-only desktop boot bugs that caused spurious reinstall/repair loops:
1. findOnPath() searched the empty extension BEFORE PATHEXT, so an
extensionless Git-Bash `hermes` shim shadowed the real hermes.cmd/.exe.
The shim then failed the shell:false --version probe and the resolver
fell through to bootstrap/repair even though a working CLI was on PATH.
Fix: try PATHEXT extensions first, keep the empty entry LAST so callers
that already include the extension (py.exe, pwsh.exe) still resolve.
2. handOffWindowsBootstrapRecovery() chose the destructive --repair over the
gentle --update by checking only venv\Scripts\hermes.exe -- the setuptools
console-script shim, written at the END of venv setup and absent in
interrupted/quarantined states. Fix: take --update when ANY real-install
signal is present (venv python, the shim, or .hermes-bootstrap-complete).
Adds windows-hermes-resolution.test.cjs (source-assertion pattern, wired into
test:desktop:platforms) guarding both regressions.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
A broken/empty Windows launcher venv can see the source tree via PYTHONPATH
but lack PyYAML, so 'import hermes_cli' succeeds while the first real CLI
import dies — the desktop then trusts the bootstrap marker, spawns a dead
backend, and loops on 'gateway offline' (#52378).
- backend-probes.cjs: canImportHermesCli now runs 'import yaml; import
hermes_cli.config' (extracted as hermesRuntimeImportProbe) and accepts an
env override, so a dependency regression is caught without a real broken
venv fixture.
- main.cjs: isBootstrapComplete() routes through new isActiveRuntimeUsable(),
which requires the venv python to pass the runtime import probe (with
ACTIVE_HERMES_ROOT on PYTHONPATH) — not just exist on disk.
Salvaged from PR #38179. The PR's install.ps1 reset/clean + autocrlf changes
and their tests are dropped: current main already preserves dirty checkouts
via stash (the data-loss-safe #38542 path) rather than the PR's older
reset-based Repair-ManagedCheckoutBeforeUpdate approach.
Add two tests for the self-lock guard in _recover_from_interrupted_install:
one asserting it clears the marker and skips install when hermes.exe is a
process ancestor (breaking the #52378/#45542 loop), one asserting it falls
through to a normal recovery install when the shim is NOT an ancestor.
The guard's manual-recovery hint runs only inside the Windows branch, so
quote it for cmd.exe (cd /d, double-quoted paths) — the cross-platform
fallback hint at the end of the function is left POSIX-correct.
Map Icather in scripts/release.py AUTHOR_MAP for the salvage.
Rebase onto plugins/platforms/matrix/adapter.py (code moved from
gateway/platforms/matrix.py). Same logic: _on_invite checks is_direct
on invite events and calls _record_dm_room to persist in m.direct
account data.
Fixes#44679
When the Desktop forcibly closes its WebSocket mid-write, asyncio logs a
full traceback for every pending connection-lost callback — 50+ identical
WinError 10054 (ConnectionResetError) lines per disconnect on Windows, the
equivalent ConnectionResetError/BrokenPipeError on POSIX. These are not
actionable: they are the expected side effect of the peer hanging up before
our writes drained.
Install a loop exception handler on the gateway serving loop that collapses
exactly this teardown class (ConnectionResetError/ConnectionAbortedError/
BrokenPipeError originating from _call_connection_lost) to a single debug
line, forwarding every other loop error to the existing/default handler
unchanged so genuine loop bugs still surface. Idempotent per loop.
The atomic mv approach (kyssta-exe's commit) narrows but does not close the
#38249 race: the temp name used $$ (parent shell PID), which is identical
across &-launched concurrent subshells. Two concurrent writers pick the same
temp file, clobber each other mid-write, and mv then publishes a torn snapshot
— a reader sourcing it absorbs declare-x/export fragments into PATH.
- Use $BASHPID (actual per-subshell PID) so concurrent writers never collide.
- Chain mv on export success (&&) and rm the temp on failure so a partial dump
never replaces a good snapshot; apply the same to the init_session bootstrap.
- shlex-quote the static temp-path portion (Windows/spaces), $BASHPID outside.
- LocalEnvironment.cleanup sweeps orphaned snap.tmp.* temps.
- Regression tests: string-shape + a behavioral concurrent writers/readers test
that proves the snapshot never tears (would still tear with $$).
Fix race condition in terminal environment snapshots that could corrupt
PATH with declare -x entries. When concurrent terminal calls share the
same snapshot file, the non-atomic 'export -p > snapshot.sh' write could
be read mid-write by another process, causing partial/corrupted env vars
to be sourced and mixed into PATH.
The fix uses atomic file replacement:
- Write to a temp file: export -p > snapshot.sh.tmp.303651
- Atomically replace: mv -f snapshot.sh.tmp.303651 snapshot.sh
On POSIX, mv within the same filesystem is atomic, so source() will
either see the old complete snapshot or the new complete one, never a
partial/truncated file.
Fixes#38249
- read_text(encoding='utf-8') (PLW1514)
- # windows-footgun: ok on signal.SIGKILL — module is Linux-only (reads
/proc, /sys/fs/cgroup; runs from a systemd unit)
- test lambda accepts the new encoding kwarg
Long-lived helpers spawned indirectly by tool calls (adb, platform
bridges) were left in the service cgroup after the gateway's main
process exited. When the kernel rejected the deferred cgroup-wide kill
with EINVAL, systemd blocked Restart=always for 6+ minutes, taking
down all platforms and cron windows (#37454).
Add a small ExecStopPost helper (gateway.cgroup_cleanup) that walks
cgroup.procs and sends per-PID SIGKILLs — a different kernel code path
than cgroup.kill, so it succeeds where the cgroup-wide write failed.
KillMode=mixed is preserved so the gateway still reaps its own
tool-call children before systemd intervenes (#8202).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
When tools.environments.local can't be imported (partial install,
import-time error), _is_hermes_provider_credential() returned False —
fail-open. A skill could then register a Hermes provider credential
(ANTHROPIC_API_KEY, etc.) as env passthrough; _scrub_child_env lets
passthrough vars bypass the secret-substring net (rule 1), so the
operator's real key would land in the execute_code child. Reopens the
GHSA-rhgp-j443-p4rf bypass.
Fail closed instead: on import failure, treat the name as a protected
provider credential and refuse passthrough. Regression test exercises
the full register -> scrub path under a simulated import failure.
Co-authored-by: Hermes Agent <noreply@nousresearch.com>
Follow-up to the salvaged #37733 fix. The contributor centralized
redaction at _openai_error and the chat/responses failure paths, which
covers the OpenAI-compatible envelopes transitively. Two sibling classes
crossed the same authenticated HTTP boundary unredacted:
- 8x cron-management endpoints returning {"error": str(e)} on 500
- the session-chat SSE error event ({"message": str(exc)})
Route both through the same _redact_api_error_text(force=True) helper.
Add AUTHOR_MAP entry for coygeek and a TestRedactApiErrorText guard
covering mask/force/limit/passthrough behavior.
Force API-server error text through the existing secret redactor before returning OpenAI-compatible errors, response fallback text, response snapshots, and run failure events. This prevents credential-shaped provider failure text from crossing the API-server boundary while preserving debuggable sanitized messages.
Extend the gateway noisy-status filter beyond Telegram so internal
compression lifecycle messages stay in logs instead of spamming Discord,
Slack, and other messaging channels.
Add an _is_user_authorized E2E for the platforms/whatsapp/session layout
on top of fesalfayed's resolver fix (#36665) — guards the actual
silently-dropped-LID-sender path from #36664.
expand_whatsapp_aliases hardcoded get_hermes_home()/whatsapp/session, but
the adapter writes lid-mapping files via get_hermes_dir("platforms/whatsapp/
session", "whatsapp/session"). On installs without the legacy directory the
two paths diverge, so the resolver finds no mappings and returns the bare LID,
which misses the allowlist and silently drops the message. Resolve through the
same helper so both sides stay in lockstep on new and legacy layouts.
When an LLM API call returns HTTP 4xx with an empty parsed SDK `body` ({}),
`_summarize_api_error` fell through to a bare `str(error)`, so users saw only
"HTTP 400" with no provider detail (reported on Windows in #36109). The SDK
leaves `body` empty in this case, but the httpx `response` still carries the
payload in `.text`.
- run_agent.py `_summarize_api_error`: when `body` is empty, fall back to
`response.text` — parse a JSON `error.message`/`message` when present, else
surface the raw (truncated) body. Platform-agnostic diagnostics.
- hermes_cli/oneshot.py: `hermes -z` now runs via `run_conversation` and returns
exit code 2 when the run is failed/partial with no usable final response, so
scripts can detect LLM failures (still 0 when a response — incl. an error
summary as output — is produced).
Tests: new tests/run_agent/test_summarize_api_error.py (empty-body JSON + raw
text, RED/GREEN verified) + oneshot exit-code/`run_conversation` wiring tests.
NOTE: #36109's original root cause (Windows "all providers return empty 400")
is not reproducible on current main (heavy provider-transport churn since
v0.15.1). This change does not claim to fix that root cause — it makes any
empty-body API error LEGIBLE so a future occurrence shows the real provider
message instead of a bare HTTP 400. Relates to #36109 (does not close it).
Follow-up on #54032 for #35166:
- Gate the PLAYWRIGHT_HOST_PLATFORM_OVERRIDE retry on the host being an apt
release newer than Playwright recognizes (Ubuntu >24.04 / Debian >13) via
playwright_host_unrecognized(), instead of retrying on ANY install failure.
A network/disk/permission failure on a supported host now surfaces unchanged
rather than getting a mismatched-glibc build forced onto it.
- detect_os() now captures DISTRO_VERSION from os-release.
- Fold in the interruptibility fix (was PR #35304, self-closed): wrap the
download in 'timeout --foreground -k 10' (probed, with plain-timeout
fallback) so a terminal Ctrl+C reaches the child and a wedged download is
force-killed after the deadline.
- Add behavioral tests that source the helpers and assert the retry fires only
on Ubuntu 26.04 / Debian 14, not on supported hosts, non-apt distros,
native-success, operator-pinned override, or unsupported arch.
On apt releases newer than the bundled Playwright recognizes (Ubuntu 26.04,
Debian 14, and future distros), 'npx playwright install --with-deps chromium'
hangs uninterruptibly at 'Installing Playwright Chromium with system
dependencies' because Playwright's resolver maps the host to a platform with
no download build (#35166).
Wrap every installer Playwright call in run_playwright_install(), which tries
the native install first and, only if it fails or times out, retries once with
PLAYWRIGHT_HOST_PLATFORM_OVERRIDE pinned to the newest known build
(ubuntu24.04-<arch>). This is the escape hatch Playwright's maintainers bless
for unrecognized platforms (microsoft/playwright#33434).
Try-native-first (not a hardcoded distro/version table) is deliberate:
- Self-correcting — when Playwright already supports the host (e.g. Ubuntu
26.04 on Playwright >=1.61) the first attempt succeeds and the override is
never applied, so we never force a mismatched-glibc build onto a release
Playwright handles correctly (microsoft/playwright#35114).
- Zero-maintenance — new distro releases work the moment Playwright adds them.
- Covers Debian 14+ and future releases, not just Ubuntu 26.04.
An operator-set PLAYWRIGHT_HOST_PLATFORM_OVERRIDE is always respected (applied
to the first attempt; retry skipped). Non-x64/arm64 arches have no fallback
build and skip the retry.
Refs #35166
A custom_providers config that names the model under model.name (or
model.model) resolved to an empty model, so the API request went out
with model= — HTTP 400 from OpenAI-compatible backends. Display paths
(hermes status/dump) already read model.name and showed the model,
making the failure silent.
The model id was read via 'default or model' at ~14 independent sites
(cli, gateway, cron, curator, oneshot, fallback, profiles, ...), none
of which honored 'name'. Rather than patch every site, canonicalize at
the single load/save chokepoint: _normalize_root_model_keys() now
promotes model.model/model.name -> model.default (precedence
default > model > name) and drops the stale alias, so every reader —
present and future — sees a populated default and config.yaml is
migrated canonical on next save. The gateway, which bypasses
load_config(), replays the same normalization in _load_gateway_config().
Co-authored-by: Bartok9 <danielrpike9@gmail.com>
Credit: root-cause analysis and fix direction from @Bartok9 (#34502,
first) and @v86861062 (#34527).
Dashboard /chat spawns the TUI attached to the dashboard's in-memory
gateway via HERMES_TUI_GATEWAY_URL. In that attach mode the already-running
gateway replays `gateway.ready` (and `session.info`) the instant the socket
connects, so those events land in GatewayClient.bufferedEvents *before* the
consumer's mount-time subscribe effect (useMainApp.ts) calls drain().
drain() then emitted the buffered events synchronously, so the
`gateway.ready` handler's patchUiState / setHistoryItems cascade ran while
React was still inside the first commit — tripping "Too many re-renders"
(Minified React error #301) and breaking Dashboard chat after `hermes update`.
Spawn / inline / sidecar modes never hit this: their `gateway.ready` only
arrives after the Python child boots, on a later async tick.
Fix: drain() defers the replay to the next microtask AND keeps `subscribed`
false until that microtask runs. Keeping `subscribed` false in the gap means
any live event arriving before the flush keeps buffering (publish() pushes
when !subscribed) instead of emitting synchronously and jumping ahead of the
chronologically-earlier replayed events — the flush re-drains the buffer
right after flipping `subscribed`, preserving FIFO order. A drainGeneration
token (bumped in resetStartupState) makes a queued flush a no-op if the
transport was reset/killed in the meantime, avoiding use-after-teardown and
duplicate/reordered exits.
Regression tests: (1) drain() does not dispatch buffered events synchronously;
(2) a live event arriving in the post-drain / pre-microtask window still
delivers BEHIND the earlier-buffered event (FIFO). Both are red against the
old synchronous behavior, green with this fix. Same class of fix as #44528.
Closes#36658
* fix(telegram): clear send_path_degraded on successful reconnect
_send_path_degraded was cleared only in _verify_polling_after_reconnect,
60s after reconnect and only if scheduled. A clean start_polling() reconnect
left the flag stuck True, short-circuiting send() and blocking all outbound
messages until the deferred probe ran (or forever if it never did).
Clear the flag the moment start_polling() succeeds — that is the recovery
signal. The deferred probe remains a defensive re-check that re-enters the
reconnect ladder (re-setting the flag) if it detects a silent wedge.
Fixes#35205.
* docs: add infographic for #35205 telegram send-path fix
Secret redaction is display/output-scoped on main — write_file writes
content verbatim, terminal/execute_code redact only output not the
command/source. The real bug is in displayed tool OUTPUT (read_file,
terminal, execute_code):
_DB_CONNSTR_RE's password group [^@]+ was greedy across newlines, so on a
multi-line block it scanned past the DSN line to the next stray '@' (a
Python @decorator), replacing every intervening character — including line
breaks — with ***. That dropped lines and concatenated the next line onto
the f-string line, making read_file output look corrupted (the file on disk
was always correct). Reported in #33801.
Fix:
- Forbid whitespace in the userinfo/password groups ([^:\s]+ / [^@\s]+) so
the match can never span a line break. A real DSN password never contains
whitespace. This alone kills the catastrophic line-dropping.
- Under code_file=True, preserve a password group that is a pure {...} brace
expression — f"postgresql://{user}:{pass}@{host}" is an f-string template,
not a live credential. Literal passwords are still masked.
- Pass code_file=True at the terminal and execute_code output redaction call
sites (file_tools already did) so code-execution output isn't corrupted by
ENV/JSON/template false positives. Real prefixes, auth headers, JWTs, and
private keys are still redacted.
Verified E2E against the reporter's exact pydantic-settings module: file
written verbatim, read_file shows the DSN f-string + @model_validator intact
with zero *** corruption, while a literal postgresql://admin:pw@host DSN and
a real sk- key are still masked.
Reported-by: koishi70
Reported-by: pfrenssen
* docs(discord): document bot-to-bot comms as unsupported (#32791)
Multi-profile bot-to-bot conversation is not a supported topology.
DISCORD_ALLOW_BOTS=none (the default) blocks all bot-originated
messages; setting mentions/all across multiple Hermes profiles to make
them reply to each other ack-loops because Discord's reply auto-mention
satisfies the mention gate every turn. Document the safe default and
the loop hazard so operators don't wire it up.
* docs(discord): infographic for bot-to-bot unsupported stance (#32791)
When a provider's output-layer safety filter (MiniMax "output new_sensitive
(1027)", Azure content_filter, etc.) kills a streaming response after deltas
were already sent, interruptible_streaming_api_call swallows the raw error
into a finish_reason=length partial-stream stub. The conversation loop then
burned 3 continuation retries against the SAME primary — re-hitting the
content-deterministic filter every time — and gave up with "Response remained
truncated after 3 continuation attempts", never consulting fallback_providers.
Builds on @595650661's classifier change (cherry-picked) so error_classifier
recognizes the filter; then:
- chat_completion_helpers: run the swallowed error through error_classifier at
the stub-creation point and stamp _content_filter_terminated on the stub
(single source of truth — no parallel pattern list).
- conversation_loop: read the tag and activate the fallback chain BEFORE
burning any continuation retries; roll partial content back to the last
clean turn and re-issue against the new provider (restart_with_rebuilt_messages).
Plain network stalls are unaffected (only content_policy_blocked is tagged).
Credits #32479 (@sweetcornna) and #33845 (@Tranquil-Flow) which fixed the
same issue via the stub-tag and loop-escalation approaches respectively.
Live E2E confirmed: before, _try_activate_fallback called 0x; after, fallback
fires on the first stub and the fallback provider completes the turn.
The MiniMax output-layer safety filter surfaces the error verbatim as
`output new_sensitive (1027)` (sometimes with additional provider
wrapping like 'Stream stalled mid tool-call: output new_sensitive (1027)').
When the model emits a large tool-call argument block, the upstream
filter trips and the SSE stream is truncated mid-flight, producing
'stream stalled mid tool-call' errors. Until now this case was
misclassified and retried 3x on the same provider, reproducing the same
refusal and burning paid attempts.
Adding `new_sensitive` to `_CONTENT_POLICY_BLOCKED_PATTERNS` routes
it through the existing is_client_error path: skip 3x retry, activate
configured fallback model immediately, surface a clear provider-safety
message to the user.
Refs #32421
A restart now interrupts in-flight agents immediately rather than holding
the gateway open for a grace window. The previous 180s default coupled two
independently-set timers: the gateway's own drain timer and systemd's
TimeoutStopSec. On a stale unit where TimeoutStopSec < drain, systemd
SIGKILLed the gateway mid-cleanup, leaving a stale lock that made the next
startup exit immediately ('already running') — an infinite crash loop under
Restart=on-failure (#31981).
Setting drain to 0 makes the mismatch structurally impossible: with drain 0
the generated unit gets TimeoutStopSec=90 against a near-instant drain, so
systemd never kills mid-cleanup. Contract: restart the gateway, in-flight
work stops. A grace window large enough to 'save' a long agent turn would
have to outlast an unbounded task, which is impossible.
Also fixes the stale-unit warning's suggested command
(hermes gateway service install --replace -> hermes gateway install --force);
the former subcommand does not exist.
Closes#31981
The .integration.test.mjs greps bridge.js source text for the queue
wiring — a change-detector that breaks on any benign refactor of the
same code. The behavioral unit test (bridge.sendqueue.test.mjs) already
covers FIFO ordering, error isolation, timeout propagation, and
single-consumer concurrency, which is the contract that matters.
Concurrent sock.sendMessage() calls on a single Baileys socket can cause
the WhatsApp protocol-level routing to misdeliver messages — responses
intended for one chat appear in another.
Add a promise-based send queue that serialises all sendMessage() calls
across concurrent HTTP /send, /edit, and /send-media handlers so only
one send is in-flight at a time.
Includes unit tests for queue ordering, error isolation, timeout
propagation, and single-consumer concurrency semantics, plus an
integration check that the queue is wired into sendWithTimeout.
Pull the #33271 post-interrupt recovery (flush_stdin + _force_full_redraw)
out of process_loop's finally block into _recover_terminal_after_interrupt(),
and replace the inline-logic-copy tests with ones that exercise the real
helper plus a source guard that process_loop still invokes it behind the
_last_turn_interrupted gate.
When the agent is interrupted during processing, prompt_toolkit's
renderer and VT100 input parser can be left in an inconsistent state.
CSI 6n cursor position report responses leak as literal text
(^[[19;1R) and the terminal stops accepting keyboard input.
Fix: in process_loop's finally block, after an interrupted turn:
- flush_stdin() to drain stray escape bytes from the OS input buffer
- _force_full_redraw() to reset prompt_toolkit's renderer cache
Closes#33271
Make check-and-replace atomic in _ensure_primary_openai_client by
keeping both operations under the same lock acquisition. Previously,
the lock was released between detecting a closed client and replacing
it, allowing two threads to simultaneously replace the client.
Fixes#32846
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The 600s default evicted the gateway clarify entry while users were
still away (meeting/AFK); a later button tap then landed on a dead
entry and the agent hung on 'running: clarify'. Raise the default to
1h in DEFAULT_CONFIG and the get_clarify_timeout() code-level fallback,
documenting the running-agent-guard tradeoff. User overrides still win.
Generated images under a profile gateway's cache (profiles/<name>/cache/
images/...) were silently dropped from Telegram/Discord delivery when
HERMES_HOME is symlinked under a denied prefix (e.g. /opt/data ->
/root/.hermes) and $HOME is not that prefix. The resolved path lands
under /root (a system denylist prefix), the root-home exception only
fires when the denied prefix IS $HOME, and the static safe-roots list
only covers the active HERMES_HOME's top-level cache — not per-profile
cache dirs. Both gates fail, so validate_media_delivery_path returns
None and the gateway logs 'Skipping unsafe MEDIA directive path'.
_media_delivery_allowed_roots() now also enumerates per-profile cache
roots (<root>/profiles/*/cache/{images,audio,videos,documents,
screenshots}) at check time. Allowlist match runs before the denylist,
so the profile artifact delivers regardless of the /root interaction;
profile-dir credentials (auth.json) stay blocked since they aren't
under a cache subdir.
Reopened regression of #34485/#38108, neither of which covered the
profile-scoped symlink case. Fixes#31733.
On Darwin, synchronous=FULL (the WAL default) only issues a plain
fsync(), which Apple documents does NOT guarantee writes reach stable
storage or stay ordered. SQLite's WAL corruption-safety guarantee
assumes the OS honors the fsync barrier; macOS does not unless the app
uses F_FULLFSYNC. During a launchd *system* shutdown the page cache is
dropped (effectively power-loss for in-flight pages), so a WAL
checkpoint whose fsync 'reported' durable may never hit the platter —
corrupting state.db with a malformed image. That is the trigger in
#30636 ('SIGTERM during launchd shutdown under high load').
Apply PRAGMA checkpoint_fullfsync=1 (macOS-guarded) in
apply_wal_with_fallback. It forces the F_FULLFSYNC barrier only at
checkpoint boundaries (where WAL frames land in the main DB), so cost
amortizes to ~+0.1ms/commit vs ~+4ms for the broader fullfsync=1.
No-op off Darwin (F_FULLFSYNC is macOS-only).
Root-cause analysis by @catapreta on #30636. Supersedes #30654, whose
synchronous=FULL is a no-op (already FULL in WAL mode) and whose
TRUNCATE-on-close is already on main.
Co-authored-by: catapreta <catapreta@users.noreply.github.com>
The advisory reference view stripped all tool calls and tool results, so
reference models judged a task whose actions and results they never saw — and
references only fired once per user turn, never re-running as the agent's
state advanced through the tool loop.
Two fixes:
- _reference_messages() now PRESERVES the agent's tool calls and tool results,
rendering them inline as text ([called tool: ...] / [tool result: ...]) so a
reference gives an informed judgement on the real current state. Still emits
zero tool-role messages and zero tool_calls arrays (strict providers reject
those), and large tool results are previewed head+tail (4000-char budget).
The required end-on-user shape is met by APPENDING a synthetic advisory user
turn — not by deleting the agent's latest context (which the prior fix did).
- References now re-run on every state change — each new user message AND each
new tool result — instead of once per user turn. The state-sensitive advisory
signature drives the cache: new tool result = miss (re-run), identical-state
re-call = hit (no re-run, no re-emit).
The acting aggregator still receives the full, untrimmed transcript.
Two follow-ups on top of the salvaged #46365 fix:
1. Tests: the salvaged tests injected the ephemeral MatrixAdapter via
sys.modules["gateway.platforms.matrix"], but Matrix migrated to a plugin
(#41112) and the fallback now imports from plugins.platforms.matrix.adapter.
Point the three sys.modules patches at the current module path so the
ephemeral-fallback tests actually exercise the injected fake adapter.
2. Harden the live-adapter lookup: split the gateway import guard from the
adapter lookup and log (instead of silently swallowing) when a runner
exists but adapters.get() raises. A silent fall-through there would
re-introduce the per-send reconnect/OTK-exhaustion storm this fix exists
to prevent (#46310). Documented that the live adapter is gateway-owned and
must not be disconnected, and why the ephemeral finally never touches it.
When a live gateway adapter is available (i.e. the tool runs inside a
running gateway), reuse the persistent connection instead of creating a
new MatrixAdapter per call. This eliminates per-message E2EE re-init
storms that exhaust recipient OTKs and silently drop messages.
The fix follows the same pattern as _send_to_platform (line 618):
gateway_runner_ref → runner.adapters[Platform.MATRIX]. Falls back to
the ephemeral connect/disconnect cycle for standalone contexts.
Also extracts the shared send logic into _send_via_matrix_adapter()
to avoid duplicating the media dispatch code between the two paths.
Fixes#46310
The docker-exec privilege-drop shim tests started a sleep container and
released the fixture as soon as `docker exec <c> true` returned 0. On
s6-overlay that succeeds almost immediately — ~0.05s in measurement —
long before the `01-hermes-setup` cont-init hook (docker/stage2-hook.sh)
has finished seeding + `chown hermes:hermes` config.yaml and running the
Python config migration (cont-init only fully settles at ~9.8s under
arm64 QEMU emulation).
`test_shim_opt_out_keeps_root` wipes config.yaml, writes it as root with
HERMES_DOCKER_EXEC_AS_ROOT=1, and asserts root:root ownership. When the
fixture released the test inside that ~10s window, stage2-hook's
boot-time `chown hermes:hermes config.yaml` raced the root-written file
and reset it to hermes:hermes — failing the assertion. The window is
invisible on native amd64 (stage2-hook completes in a blink) but wide
open under the arm64 build's QEMU emulation, which is why only build-arm64
flaked while build-amd64 stayed green.
Replace the responsiveness poll with a wait on the canonical
'cont-init finished' signal: $HERMES_HOME/logs/container-boot.log gaining
a `profile=default` line, written by 02-reconcile-profiles which s6 runs
strictly after 01-hermes-setup. Mirrors the readiness pattern already
used in test_container_restart.py. Also bumps the readiness timeout 20s->60s
to cover slow emulation.
No production code change — test-only hardening of a timing race.
tests/cron/test_scheduler_provider.py spawned a background ticker thread,
slept a fixed 0.2s, then asserted the loop had called tick()/heartbeat() at
least N times. Under loaded CI the worker thread isn't always scheduled
within that window, so the loop hadn't ticked yet — flaking with 'provider
never called tick()' (assert 0 >= 1).
Add a _wait_until(predicate, timeout) helper and replace all five fixed
time.sleep(0.2) sites with a poll on the actual predicate (calls/beats count
reached). Same contract assertions, no wall-clock dependence.
* fix(moa): reference advisory view must end with a user turn
MoA reference calls failed with Anthropic models that don't support
assistant prefill (e.g. Claude Opus 4.8): '400 ... must end with a user
message'. The advisory view built by _reference_messages() kept the last
assistant turn's text while dropping the following tool result, leaving a
trailing assistant turn — which Anthropic (and OpenRouter->Anthropic)
interpret as an assistant prefill to continue. References are advisory and
must end on the user turn they answer.
Strip trailing assistant turns from the advisory view (preserving
intervening ones). Update the existing test that encoded the buggy shape
and add a mid-tool-loop regression test.
* feat(moa): give reference models an advisory-role system prompt
Reference models received the bare trimmed conversation with no role
framing, so they assumed they were the acting agent and refused ("I can't
access repositories/URLs from here") or tried to call tools they don't have.
Prepend a dedicated advisory system prompt to every reference call: the
model is an analyst, not the actor — it cannot execute, should not
apologize for lacking tools, and should reason about the presented state to
advise the aggregator/orchestrator on approach, next steps, tool-use
strategy, risks, and anything the acting agent missed. Its output is private
guidance for the aggregator, not a user-facing answer.
The parallel runner only forwarded pytest args after a literal '--', so a
bare 'scripts/run_tests.sh tests/foo.py -q' (or -v/-x/-k/--tb=long) errored
out with 'unrecognized arguments'. This contradicted the docstring's
promise that common pytest flags pass through, and forced a retry on every
run that used pytest muscle-memory.
Now any token starting with '-' that isn't one of the runner's own options
(-j/--jobs, --paths, --slice, --file-timeout, --generate-slices, --files,
--include-integration) is routed to each per-file pytest invocation
automatically. Value-taking flags given space-separated (-k expr, -m mark,
-p plugin, -o name=val, etc.) keep their value instead of having it stolen
by positional-path discovery. The explicit '--' separator still works and
stacks with bare flags.
- scripts/run_tests_parallel.py: argv splitter routes bare unknown flags to
pytest; value-flag lookahead; updated docstring.
- scripts/run_tests.sh: usage comment reflects bare-flag passthrough.
- tests/test_run_tests_parallel.py: 4 behavior-contract tests (bare -q runs,
-k keeps its value/filters, '--' still works, positional path stays a root).
`npm run build` ended with `bundle-electron-main.mjs`, which esbuild-bundled
electron/main.cjs and renamed the bundle on top of the tracked source file.
Because every `hermes desktop` runs `npm run build`, each launch rewrote a
checked-in source file (~7.5k-line source -> ~14.8k-line bundle), dirtying the
working tree with a build artifact that `git restore` couldn't keep (the next
launch re-clobbered it) and forcing autostash/restore conflicts on update.
The bundle only existed to inline `simple-git` so the packaged app.asar (which
ships no node_modules) wouldn't crash at launch with "Cannot find module
'simple-git'". Replace it with the mechanism the repo already uses for the
other hoisted runtime dep (node-pty): stage the dependency closure and resolve
it from process.resourcesPath at runtime.
- stage-native-deps.cjs: resolve simple-git's runtime closure (walking
dependencies + optionalDependencies, so a version bump that adds a transitive
dep can't silently reintroduce the crash) and stage it under
build/native-deps/vendor/node_modules/. The `vendor/` nesting is load-bearing:
electron-builder drops a node_modules dir at the ROOT of an extraResources
copy but keeps a nested one.
- git-review-ops.cjs: fall back to the staged
native-deps/vendor/node_modules/simple-git when the hoisted require() fails;
dev runs resolve the hoisted copy and never hit the fallback.
- package.json: drop the bundler from the `build` script so main.cjs is never a
build target again.
- nix/desktop.nix: drop the direct bundler call (the closure rides the existing
`cp -rn native-deps` into $out) and patch process.resourcesPath in
git-review-ops.cjs alongside main.cjs.
- delete scripts/bundle-electron-main.mjs.
Verified: electron-builder's own file filter keeps the full staged closure
(0 dropped), and a packaged win-unpacked build launches with the git-review
pane resolving simple-git from the staged vendor path.
Adds a desktop: section to config.yaml so headless/VM users can make
`hermes desktop` launch correctly without a wrapper command:
- desktop.electron_flags: extra Electron CLI flags (e.g. --ozone-platform=x11)
appended to every launch. Accepts a list or a shell-split string.
- desktop.disable_gpu: auto|true|false, bridged to the HERMES_DESKTOP_DISABLE_GPU
env var the Electron app already reads. An explicit env var still wins.
cmd_gui() reads these via _desktop_launch_options() and applies them. This is
the config.yaml form of the capability proposed as a raw env var in #38934
(@1RB) — behavioral settings belong in config.yaml, not a new HERMES_* env var.
Co-authored-by: ray <86501179+1RB@users.noreply.github.com>
* docs: third-party-product plugins ship standalone, not into core tree
Generalizes the closed-set memory-provider policy to any plugin that
integrates someone else's product/project (observability backends,
vendor SaaS, analytics dashboards, paid-service tie-ins). These create
an open-ended maintenance burden on us for backends we don't own, so
they ship as standalone plugin repos installed into ~/.hermes/plugins/
and are promoted in #plugins-skills-and-skins — not merged into core.
- AGENTS.md: new 'what we don't want' bullet + generalized policy note
beside the memory-provider closed-set rule
- CONTRIBUTING.md: new 'Third-Party Product Integrations' section
- build-a-hermes-plugin.md: caution callout at the top of the guide
It's a coupling decision, not a quality bar — a plugin can clear review
and still be a close.
* docs: add infographic for standalone-plugin policy
The plain-Linux overlay re-enable (#53185) left nativeOverlayWidth() at 0
for plain Linux, so the native min/max/close buttons painted on top of the
app's right-edge titlebar tools. Reserve the fallback width everywhere the
WCO overlay is painted (Windows, WSLg, plain Linux); macOS still reserves 0
since it uses traffic lights.
Commit da5484b61 disabled the Window Controls Overlay on all Linux
(non-Windows, non-WSL) with the note that WCO is a Windows/macOS-only
Electron feature. However, several Linux compositors (KDE/KWin,
GNOME/Mutter) do support it — plain Electron titleBarOverlay paints
native min/max/close buttons that were working before that change.
Narrow the exclusion to only WSLg, where the RDP host draws its own
window controls and an Electron overlay would leave a dead gap.
Fixes: da5484b61 ("fix(desktop): WSL2 clipboard image paste + Linux titlebar overlay")
Salvage of NousResearch/hermes-agent#41498 (0-CYBERDYNE-SYSTEMS-0).
- Leave response_previewed false on partial_stream_recovery so gateway
fallback delivery can send the recovered fragment plus explanation.
- Always append the turn-completion explainer for partial_stream_recovery,
not only for empty or very short fragments (#34452 gap).
- Launch the detached /restart helper before drain, idempotently, with a
bounded wait of restart_drain_timeout + 5s.
* fix(cli): correct stale `hermes auth login nous` hints to `hermes auth add nous`
There is no `hermes auth login` subcommand — valid auth verbs are
add/list/remove/reset/status/logout/spotify. Six user-facing strings told
users to run `hermes auth login nous`, which fails with
`invalid choice: 'login'` — the same broken-hint class reported in #28089
for the proxy flow (already fixed there to `hermes auth add nous`).
Sites corrected to `hermes auth add nous`:
- hermes_cli/dashboard_register.py (401 retry hint, not-logged-in hint)
- hermes_cli/gateway_enroll.py (401 retry hint, not-logged-in hint)
- cli-config.yaml.example (two provider-requirement comments)
* docs(infographic): auth login nous hint fix
Non-root users picking 'System service' in the setup wizard were handed a
'sudo hermes gateway install --system --run-as-user <you>' recipe that fails
on most distros: sudo's secure_path strips ~/.local/bin (pipx/uv installs),
so 'sudo hermes' is command-not-found. Worse, it funnels a non-root user
toward a system install they shouldn't be doing from a user session.
Now prompt_linux_gateway_install_scope() only offers system scope when
os.geteuid()==0. Non-root sessions get user-service or skip, with a tip to
re-run as root for a boot service. The non-root branch in
install_linux_gateway_from_setup becomes a defensive guard that refuses
without printing any self-elevation recipe. Gated the matching deferral hint
in setup.py behind root too.
Follow-up to the salvaged #49129 commit. The original change flipped the
shared generic-provider merge in provider_model_ids() to live-first
unconditionally, which regressed curated-first for single providers
(kimi/zai, #46309) — and the PR encoded that regression by flipping the
kimi-coding and zai test assertions to expect live-first.
Gate live-first on an explicit _LIVE_FIRST_PICKER_PROVIDERS set
({opencode-zen, opencode-go}); every other provider keeps curated-first.
Also widen the uncapped picker + live-first sets to opencode-go, which has
the same 70+ model catalog problem as opencode-zen. Restore the
kimi-coding curated-first test and rewrite the merge-order test to assert
the per-provider contract.
Auxiliary clients now inject a keepalive httpx transport with explicit
HTTPS_PROXY/NO_PROXY resolution, matching the main agent. This avoids
macOS system proxy settings (which omit the ExceptionsList) breaking
vision and other auxiliary calls to internal provider endpoints.
Multi-agent boards leak staleness: a sibling worker's parent handoff,
comment, or prior-attempt summary gets read by the next worker as live
truth even when it's a day old. build_worker_context surfaced the text
with (at best) a bare absolute timestamp, which an LLM reads as fact
regardless of age — parent results had no timestamp at all.
Adds a coarse relative-age stamp (just now / 18h ago / 3d ago) to every
recalled-state line and a one-line 'point-in-time snapshot, re-verify
against source' frame on the parent-results section, so the worker sees
when handoffs were produced and re-checks stale ones before acting.
test_session_resume_uses_parent_lineage_for_display resumes via the
deferred (non-eager) path, which fires a 50ms background Timer
(_schedule_agent_build) calling whatever server._make_agent is patched
in at that moment. The timer outlived the test and landed in the next
test's (_follows_compression_tip) _make_agent mock, racily setting
agent_session_id='tip' and flaking 'assert tip == cont_tip' on CI.
Root-cause fix: stub _schedule_agent_build to a no-op in the leaking
test (it only asserts display history). Defense in depth: the victim's
fake_make_agent now setdefault()s so a stray late build can't overwrite
the synchronous eager build's captured id.
The exhaustion-cooldown timing assertions relied on a wall-clock budget
(before + window + 1.0s). On loaded CI runners the activation calls could
exceed the 1s slack, flaking 'Run tests slice 4/8'. Freeze
chat_completion_helpers.time.monotonic so the cooldown math is exact and
load-independent across all four tests.
Fixes#28126. sync_skills() was unconditionally writing bundled skills
into the local <profile_home>/skills/ tree even when the profile's
config.yaml delegated skill resolution to an external directory
via skills.external_dirs. The skill loader then saw two candidates
for the same name (local shadow + external canonical), refused to
resolve on collision, and every worker that auto-loaded such a skill
crashed with 'Unknown skill(s): <name>'.
Changes:
- _build_external_skill_index() indexes skills available in external
dirs (by directory name and frontmatter name)
- sync_skills() skips writing a bundled skill when it finds the same
name in the external index; records the hash in the manifest so
subsequent syncs treat it as already handled
- Self-healing: removes stale local shadows left by prior buggy syncs
(only when origin_hash == bundled_hash == user_hash, i.e. we wrote
it and user didn't touch it)
- New 'shadowed_by_external' key in sync_skills() return dict
3 new tests in TestExternalDirsIndexing (all passing).
All 48 tests in test_skills_sync.py pass.
Closes#28126
A WebUI/TUI session whose last turn died mid-tool-loop (stale-timeout kill,
interrupt, or process restart before the tool result was written) persists a
dangling assistant(tool_calls) or interrupted assistant->tool tail. The
messaging gateway already strips these tails before replay (the #49201 fix),
but the TUI/WebUI resume path fed db.get_messages_as_conversation() straight
in as the agent's conversation_history with no cleanup. The model re-issued
the unanswered call on every resume -- including after a full WebUI + Gateway
restart, since the poison lives in the SessionDB, not memory -- leaving the
session permanently 'thinking'. Only deleting the session recovered it.
- Extract the two strippers + helper from gateway/run.py into a shared
agent/replay_cleanup.py (sanitize_replay_history wraps both).
- gateway/run.py re-exports under the historical private names; messaging
behavior unchanged.
- Both TUI cold-resume sites now sanitize the model-fed history while leaving
the display transcript untouched, so the user still sees their full history.
Verified E2E against a real SessionDB: dangling and interrupted tails are
stripped from the model feed, healthy mid-progress tool sequences are
preserved, and the display transcript is always the full raw history.
Telegram polling entered a self-inflicted ~31s loop of 409 Conflict ->
retry -> resume -> Conflict. The error_callback PTB invokes synchronously
inside its internal network_retry_loop only scheduled our async recovery
task (loop.create_task) and returned, so PTB kept polling getUpdates on its
own while our handler concurrently ran stop -> sleep -> start_polling. The
two polling sessions overlapped and Telegram returned a fresh 409.
Fix: in the conflict branch of the error_callback, synchronously set PTB's
private polling stop_event before scheduling recovery. PTB's loop exits on
its next tick (it races that event in do_action), so our handler owns
polling alone. The handler's await updater.stop() drains the task and PTB
clears the event, so the subsequent start_polling() builds a fresh event
and is not poisoned.
Keeps the existing reconnect ladder intact (option B) — fixes only the
race. Defensive: probes mangled + unmangled stop_event spellings and no-ops
(prior behaviour) if neither exists; never flips _running, which would make
the handler skip stop() and leave the loop wedged.
* fix(agent): config-driven intent-ack continuation for all api_modes (#27881)
The agent could end a turn after only stating intent ('I will run a health
check...') without executing the announced tool call, forcing the user to
re-prompt. A continuation guard that catches this and nudges the model to
proceed already existed but was hard-gated to the codex_responses api_mode,
so Gemini/Claude/OpenRouter turns never benefited.
- New agent.intent_ack_continuation config (default 'auto' = codex-only,
byte-stable for existing conversations). 'true'/model-list opts every
api_mode in; 'false' disables. Mirrors agent.tool_use_enforcement's shape.
- looks_like_codex_intermediate_ack gains require_workspace (default True).
The opted-in path drops the codebase/filesystem requirement so general
autonomous workflows (server ops, deploys, API calls) are caught, not just
coding tasks. Future-ack + action-verb + short-content + no-prior-tool
guards still apply; the 2-nudge-per-turn cap is unchanged.
- Resolution centralized in intent_ack_continuation_mode (off/codex_only/all).
* docs(infographic): intent-ack continuation (#27881)
The curator's LLM consolidation pass could archive whole clusters of
active skills with zero verified consolidations (#29912): a bare prune
(skill_manage delete with absorbed_into empty/omitted) from the forked
review agent was accepted, removing the skill's name from lookup even
though counts.consolidated_this_run was 0.
- _delete_skill now fails closed during the curator/background-review
pass: a delete is only allowed when it declares a verified
consolidation (absorbed_into=<umbrella>, umbrella must exist). A prune
with no forwarding target is refused; the skill stays active. The
deterministic inactivity prune (archive_skill) is unaffected.
- A verified consolidation delete during the curator pass now routes
through the recoverable archive primitive instead of shutil.rmtree, so
a misjudged consolidation can be undone with hermes curator restore.
The usage record is kept (state=archived) rather than forgotten.
- Foreground, user-directed deletes keep their existing hard-delete
semantics.
Follow-up to the cherry-picked #29212 (#29177):
- Promote the 24h stale-process threshold to config.yaml
(session_reset.bg_process_max_age_hours) instead of a hardcoded
constant. 0 disables the cutoff (legacy: any live process blocks reset).
Wired through GatewayConfig.default_reset_policy in gateway/run.py.
- Bug 2: process(action=list) now resolves the gateway session_key from
the contextvar and surfaces session-scoped background processes (a
forgotten preview server under a different task), flagged
session_scoped — so the agent/user can discover and kill the blocker.
Previously the task-scoped list returned [] and the blocker was invisible.
- Tests: config round-trip for the new field, cross-task list visibility.
- Docs: messaging session-reset section.
Background processes (e.g. http.server preview) that Hermes starts and
forgets about previously blocked session idle/daily reset indefinitely.
The reset guard in session.py checked has_active_for_session() with no
max age — a 3-day-old preview server blocked reset the same as a task
started 30 seconds ago.
Changes:
- Add max_active_age parameter to has_active_for_session() in
process_registry.py. Processes older than this threshold are ignored.
- Add MAX_ACTIVE_PROCESS_AGE constant (24h / 86400s).
- Wire max_active_age into the gateway's session store callback in
run.py so stale processes no longer block session lifecycle.
- Add debug logging when reset is skipped due to active processes.
- Add 3 tests covering recent, stale, and legacy (None) max age.
Fixes#29177
The module-level import broke tests/tools/test_managed_browserbase_and_modal.py,
which loads browser_tool.py via spec_from_file_location against a stubbed
'tools' package that does not include tools.environments.local. Move the import
into a _build_browser_env() helper called at the two agent-browser spawn sites,
matching the lazy-import pattern already used by lazy_deps.py.
Subprocesses spawned outside the terminal/execute_code path (agent-browser,
copilot ACP, dep-ensure, lazy_deps uv install, TUI Node host, cli.exec)
inherited the operator's full credential environment via os.environ.copy().
The terminal path was already scrubbed by _HERMES_PROVIDER_ENV_BLOCKLIST
(#1002/#1264/#32314); these spawn sites bypassed it.
Adds hermes_subprocess_env(inherit_credentials=) in tools/environments/local.py
reusing the existing dynamic blocklist as the single source of truth:
- Tier 1 (_ALWAYS_STRIP_KEYS): gateway bot tokens, GitHub auth, infra
secrets -- stripped even for credential-inheriting children.
- Tier 2 (_HERMES_PROVIDER_ENV_BLOCKLIST): provider/tool keys -- stripped
unless inherit_credentials=True. The opt-in is grep-able for audit.
Browser worker keeps a _BROWSER_PASSTHROUGH_KEYS allowlist (BROWSERBASE/
FIRECRAWL) re-added after the strip. Model-driving children (ACP, TUI Node
host, cli.exec) use inherit_credentials=True so they still get provider keys
while losing Tier-1 secrets. Installers (dep-ensure, lazy_deps) inherit
nothing sensitive. cua_backend already routed through _sanitize_subprocess_env
on main -- left as-is. Gateway adapter utility spawns (gh pr comment, ffmpeg)
are left inheriting env: gh needs GH_TOKEN by design, ffmpeg is a trusted
system binary -- no untrusted-dependency exposure.
This is defense-in-depth (personal-assistant trust model: same-user spawns),
making the existing scrub policy uniform across the spawn surface; the main
real payoff is shrinking the blast radius if a transitive npm dep in
agent-browser is compromised.
Reconstructed on current main from the design in #31959 (Tranquil-Flow);
also credits #39003 (rodboev), #37843 (coygeek), #35769 (egilewski).
Co-authored-by: Tranquil-Flow <tranquil_flow@protonmail.com>
Co-authored-by: rodboev <rod.boev@gmail.com>
Co-authored-by: egilewski <egilewski@egilewski.com>
Three CI flakes hit while landing the credential-pool restore fix; all three
were timing/wall-clock races in the tests, not product bugs (each passes
locally and the assertions are correct):
- test_entire_tree_is_sigkilled_not_just_parent: _terminate_host_pid SIGKILLs
synchronously, but the test's 4s budget after a 1s in-function SIGTERM grace
left almost no slack for the kernel to tear down 3 processes + reparent the
children to zombies under loaded-CI scheduling. Widen the wait to 15s and
make the liveness predicate tolerant of vanished-pid / zombie races. The
assertion never weakens: every tree member must end up dead or zombie.
- test_session_resume_follows_compression_tip: appended messages got
time.time() timestamps (~now) while the test forced session started_at into
the past, so the get_compression_tip MAX(m.timestamp) tiebreaker depended on
wall-clock ordering. Pass explicit, well-separated message timestamps so the
chain resolution is deterministic by construction.
- test_non_retryable_exhaustion_arms_cooldown: asserted the short (5s)
exhaustion cooldown with a tight +1.0s slack, which false-fails when
wall-clock jitter between the 'before' snapshot and the cooldown computation
exceeds a second on a loaded runner. Widen to +30s — still cleanly below the
60s rate-limit window it must distinguish from.
_restore_primary_runtime restored the construction-time api_key snapshot and
never consulted the credential pool. After the pool rotated away from a
revoked/exhausted entry mid-session, every new turn restored the dead key,
re-failed instantly, burned the remaining entries, and fell through to
cross-provider fallback.
After restoring the snapshot, re-select the pool's current best entry and
swap the live credential in via _swap_credential (which already rebuilds the
OpenAI/Anthropic client, reapplies base-url headers, and carries the #33163
base_url / OAuth-detection fixes). Falls back to the snapshot key when the
pool is absent, empty, or the entry has no usable key.
Salvaged from #25206 onto current main: the original targeted the pre-refactor
monolithic method in run_agent.py; the logic now lives in
agent/agent_runtime_helpers.py and is collapsed onto _swap_credential instead
of re-inlining the client rebuild.
Fixes#25205
`resolve_provider("auto")` checked `auth.json` `active_provider` BEFORE the
config.yaml `model.provider` and env-var API-key checks. So a user who was
OAuth-logged-into one provider (e.g. Anthropic) but had set an explicit
`model.provider` or exported an API key (e.g. `OPENAI_API_KEY`) was silently
routed to the stale OAuth provider — the override was invisible and surprising.
Reorder the auto-path so explicit intent wins (the order the issue asks for):
1. explicit CLI api_key/base_url
2. config.yaml `model.provider` (safety net — see below)
3. OPENAI_API_KEY / OPENROUTER_API_KEY env
4. OpenRouter credential pool
5. provider-specific API-key env vars
6. auth.json `active_provider` (OAuth) ← demoted to last-resort
7. AWS Bedrock credential chain
8. error
`active_provider` is still honored — it's just a last-resort fallback chosen
only when the user expressed no other preference, instead of overriding one.
The normal chat/gateway/TUI/ACP/status path already resolves config.provider
upstream in `resolve_requested_provider()` before "auto" is reached, so this
duplicate config check is the safety net for the lone direct caller
(`main.py` `resolve_provider("auto")`) and any future bypass. Because every
surface funnels through this one resolver, the fix propagates everywhere with
a single edit — no sibling path re-implements precedence.
Also add a one-shot WARN when resolution lands on `active_provider` while a
populated `model` config dict lacks a `provider` key — surfacing the silent
override the issue reported without breaking first-install.
Synthesizes the two competing PRs: #29615 (LifeJiggy — config-before-auth +
the silent-override framing) and #29809 (Minksgo — the env-before-auth
reorder). #29809 could not be merged directly (bundled unrelated, un-opt-in
cost-tagging telemetry); its reorder idea is incorporated here and credited.
Tests: tests/hermes_cli/test_provider_precedence.py — config/env beat stale
OAuth, OAuth still used as last resort, explicit request short-circuits, WARN
fires on silent fall-through. Full provider-resolution suites: 374 passed.
Fixes#29285
Co-authored-by: LifeJiggy <141562589+LifeJiggy@users.noreply.github.com>
Co-authored-by: Minksgo <153416856+Minksgo@users.noreply.github.com>
Two profile gateway services sharing the default ~/.hermes resolve the
takeover marker to the same path. A --replace from profile B could land
in profile A's marker, match on PID + start_time by coincidence of a
shared PID namespace, and make profile A exit 0 — only to be revived by
systemd Restart=always, which races the replacer again, flapping
indefinitely.
write_takeover_marker now stamps replacer_hermes_home; the shared
consume path rejects markers written under a different HERMES_HOME and
leaves them in place for the correct profile. Absent field (older
markers) is treated as same-home, so single-profile and mixed old/new
deployments are unaffected.
Salvaged from #31414 by @CryptoByz onto current main (branch was ~3962
commits behind; the consume function had since been refactored for
issue #34597). Co-authored-by: CryptoByz.
The salvaged #27354 fix made save_config strip schema-default leaves by
default. Five migration sites added to main after the PR was authored
still called bare save_config(config) and intentionally materialize a
(often default-valued) key: model_catalog.ttl_hours, write_approval,
curator.consolidate, agent.verify_on_stop, and the suspicious-MCP-server
disable. Pass strip_defaults=False so those one-time deliberate writes
survive, matching the opt-out the PR applied to the other migrations.
Fixes#27354
Root cause: called during init (or by any code path
that saves ) wrote injected schema defaults into
config.yaml as if the user had authored them. Two fix layers:
1. now only injects
when the user actually set
somewhere (root or agent). A user who never set
keeps it absent, so 's explicit-path
detection won't treat it as user-authored.
2. gains a parameter and a
new pass that removes keys matching
unless those paths were explicitly present in the
**raw** (pre-normalization) config on disk. Explicit-path detection
uses on *before* any
normalisation runs — preventing injected-in defaults from being
mistaken for user-set values.
All migration and edit-config call sites pass
to preserve their intentional default-seeding behaviour.
New helpers:
- — collects leaf-key paths from a raw dict
- — removes keys matching schema defaults
Test coverage: 4 new regression tests (59 total, all passing).
The existing test_anthropic_stream_parser_valueerror_retries_before_delivery
asserted mock_replace.call_count == 1 — i.e. it passed precisely because the
buggy OpenAI rebuild was invoked on the Anthropic path. Repoint it to assert
the corrected close+rebuild-Anthropic behavior (#28161).
interruptible_streaming_api_call() has three connection-pool cleanup
sites that called _replace_primary_openai_client() unconditionally.
For api_mode=anthropic_messages this has two consequences:
1. _replace_primary_openai_client() fails (OPENAI_API_KEY unset on
Anthropic-only configs), so dead connections are never purged.
2. The stale-stream detector's outer-poll site (L1977) is the only
mechanism that can interrupt the worker thread while it blocks in
for event in stream:. Because the Anthropic client is never closed,
the thread stays blocked until the 900 s httpx read-timeout fires,
producing a visible 15-minute hang for Telegram/gateway users on
claude-opus-4-7.
Fix: mirror the existing interrupt-path pattern (L1989-1997) at all
three cleanup sites — if api_mode == "anthropic_messages", call
_anthropic_client.close() + _rebuild_anthropic_client() instead of
_replace_primary_openai_client(). _rebuild_anthropic_client() handles
both direct Anthropic and Bedrock-hosted Claude correctly, unlike the
inline build_anthropic_client() calls in open PR #14430.
PR #14430 (open) covers only the outer stale-detector site (L1977).
PR #23678 (open) covers only the inner retry sites (L1774, L1833).
This PR covers all three sites and uses _rebuild_anthropic_client()
for Bedrock parity.
Fixes#28161
The Discord adapter could enter a silent zombie state after a network
outage / proxy stall: the process is alive, _client looks open, but the
underlying socket is dead. discord.py's WebSocket reconnect never sees a
RST through a wedged proxy/NAT, so client.start() spins forever without
exiting — which means the bot-task done callback (which only fires on
task completion) never trips either. The bot stays "offline" in Discord
until a manual `hermes gateway restart`. Reported offline for 13-17h.
Adds an out-of-band REST liveness probe in DiscordAdapter. Every
`discord.liveness_interval_seconds` (default 60s) the adapter issues a
cheap fetch_user(bot_id) — the same REST path as message delivery, so it
fails when the proxy/NAT is wedged. After
`discord.liveness_failure_threshold` consecutive failures (default 3) the
probe closes the wedged client and surfaces a retryable fatal error,
which trips the gateway's existing _platform_reconnect_watcher and
rebuilds the adapter. Operators disable it by setting either knob to 0.
Config lives in config.yaml (discord.liveness_*) per the .env-is-secrets
policy; _apply_yaml_config bridges it to internal env vars the adapter
reads, matching the existing HERMES_DISCORD_TEXT_BATCH_* pattern.
Co-authored-by: Hermes Agent <agent@nousresearch.com>
The durable _last_known_cwd anchor is keyed by the shared 'default' container,
so a non-owning worktree session could inherit the owning session's cwd through
it — breaking the wrong-worktree-routing fix (test_file_tools_cwd_resolution::
test_resolution_routes_to_resolving_sessions_worktree).
Reorder _authoritative_workspace_root so the session-specific registered cwd
override (keyed by raw session id) is checked BEFORE the shared-container
_last_known_cwd fallback. A non-owning session now resolves into its own
registered worktree; the durable anchor only fills in when there's no
session-specific override (the #26211 single-session case). Adds a regression
test covering the owner-mirrors-then-other-session-resolves interaction.
Belt-and-suspenders on top of the cherry-picked cwd-preservation fix:
- Proactively mirror every live terminal cwd into _last_known_cwd on each
successful read, so the durable anchor survives even when the cleanup
thread pops both _file_ops_cache and _active_environments before
_get_file_ops' stale-cache save branch can fire.
- Fall back to _last_known_cwd in _authoritative_workspace_root. write_file_tool
resolves the path (via _resolve_path_for_task) BEFORE _get_file_ops rebuilds
the env, so restoring only the rebuilt env's cwd was insufficient — the
resolution that decides where the file lands runs first. This closes that gap.
The local env's persisted _cwd_file can't serve this role: it's keyed by a
random per-session uuid and deleted on cleanup (the same cleanup that triggers
the bug). The in-memory _last_known_cwd registry is the durable anchor instead.
Adds a real-IO E2E regression (TestSilentFileMisplacementE2E) exercising the
actual write_file_tool path after env cleanup.
Root cause: when the terminal environment (`_active_environments` entry) is
cleaned up and re-created during a long conversation, the new environment
always starts with the default config CWD (typically `~/.hermes/hermes-agent`)
instead of preserving the user's last-known working directory. Subsequent
relative-path writes (`write_file`, `execute_code`, shell commands) silently
land in the default CWD, making files appear to be "created but absent."
Fix: add `_last_known_cwd` dict that preserves the old environment's CWD
before the stale cache entry is invalidated. When a new environment is
created for the same task_id, we check `_last_known_cwd` first and use the
preserved CWD instead of the config default.
Changes:
- tools/file_tools.py: add `_last_known_cwd` dict, save CWD before stale
cache invalidation, restore CWD on env recreation
- tests/tools/test_file_tools.py: add `TestLastKnownCwd` with 2 tests
verifying CWD preservation and fallback behavior
Fixes#26211
A flaky external probe in a tool's check_fn (e.g. check_terminal_requirements
running `docker version` with a 5s timeout, momentarily timing out under load)
would return False for a single get_tool_definitions() call. Because file
tools delegate their check_fn to the terminal check, that one flake silently
stripped read_file/write_file/patch/search_files AND terminal from whatever
agent was being constructed at that instant — most visibly a delegate_task
subagent, which then reported "Tool read_file does not exist". This explains
both the intermittent (~80% success) user-session failures and the
deterministic cron failures in #21658 / #5304.
The existing _check_fn TTL cache made this worse: it cached the transient
False for the full 30s window, poisoning every subagent spawned in that span.
Fix: remember the last time each check_fn returned True; when a fresh probe
fails within a short grace window of that success, treat it as a flake —
serve the last-good True and do NOT cache the failure (so the next call
re-probes). A failure with no recent success, or past the grace window, is
honored normally so a backend that genuinely went down stops advertising its
tools. Probe failures now log at WARNING regardless of quiet mode, making the
previously-silent tool loss diagnosable in subagent (quiet) sessions.
Co-authored-by: Stuart Horner <5261694+djstunami@users.noreply.github.com>
A document attached alongside an image in the same Discord message was
swept into the vision pipeline and 400'd the whole turn ("Could not
process image"), and was simultaneously never surfaced to the agent as a
readable file. Restores the "any file type works" contract for mixed
messages and fixes the HTTP 400.
Bug 1 — mixed attachments: the inbound routing loop keyed image/audio/video
classification off the message-level type (PHOTO/VOICE/AUDIO), so a doc in
a PHOTO message landed in image_paths and poisoned the vision call. The
document context-note path was gated on message_type == DOCUMENT, so that
same doc never reached the agent at all. Now classification is
per-attachment (trust each attachment's own MIME; fall back to the
message-level type only when MIME is unknown), via shared _event_media_is_*
helpers used by both _build_media_placeholder and the main inbound loop.
The document note now fires for any non-image/audio/video attachment
regardless of message-level type.
Bug 2 — uncommon formats: AVIF/HEIC/BMP/TIFF/ICO produced the same generic
400 because providers only accept PNG/JPEG/GIF/WEBP. image_routing now
transcodes those to PNG via Pillow before declaring media_type, skipping
cleanly (logged) if Pillow/plugins are missing. SVG is vector — Pillow
can't rasterize it — so it's skipped rather than transcoded.
Closes#25935.
Co-authored-by: LeonSGP43 <cine.dreamer.one@gmail.com>
Co-authored-by: cypres0099 <74935762+cypres0099@users.noreply.github.com>
Same bug class as the Anthropic fix (#26293): the OpenAI/aggregator client is
built without max_retries, so the SDK default of 2 applies. The SDK's own 1-2s
backoff ignores Retry-After and retries inside hermes's outer conversation loop,
burning request slots against a rate-limited bucket. Set max_retries=0 at the
single create_openai_client chokepoint (covers init, switch_model, recovery,
restore, request-scoped). auxiliary_client builds its own clients and is not
wrapped by the loop, so it keeps SDK retries.
The Anthropic SDK clients were built without max_retries, so the SDK
default (max_retries=2) retried 429/5xx with its own backoff that ignores
Retry-After — double-retrying inside hermes's outer loop and burning
request slots against a bucket that won't refill for minutes. Set
max_retries=0 on all Anthropic/AnthropicBedrock client constructions so
the outer conversation loop (which already honors Retry-After) owns retry.
Also raise the Retry-After cap in the conversation loop from 120s to 600s.
Anthropic Tier 1 input-token buckets reset in ~171s, so the 120s cap made
hermes retry before the reset window and re-trip the limit.
Refs #26293
A persistent upstream 401 on a single-entry OAuth pool (common for Claude
Max subscribers) made the credential-pool recovery spin forever:
try_refresh_current() re-mints a fresh token and reports success on every
401, so recover_with_credential_pool returned True and the retry loop
continue'd without ever incrementing retry_count or reaching the
auth-failover block. The configured fallback_model never activated and the
agent appeared to hang.
Cap consecutive successful same-entry refreshes (keyed by provider +
pool-entry id) at 2; once exceeded, treat the credential as unrecoverable
and return not-recovered so the loop falls through to
_try_activate_fallback. The 429/billing paths already rotate-or-fall-through
correctly (mark_exhausted_and_rotate returns None on a single entry), so
only the auth-refresh branch needed the cap.
Co-authored-by: Hermes Agent <hermes@nousresearch.com>
When every provider in the fallback chain fails non-retryably back-to-back
(e.g. HTTP 400/402/429 across distinct providers), the within-turn walk is
already bounded — _fallback_index advances monotonically and the loop aborts
when the chain exhausts. The damaging mode is cross-turn: restore_primary_
runtime resets _fallback_index=0 every turn, so a client that re-submits
immediately replays the entire chain, re-marshaling the full (potentially
80k-token) context once per provider every turn with no throttle on the
non-rate-limit path. On constrained hosts this exhausts memory/swap.
Rate-limit/billing failures already arm a 60s cooldown via _rate_limited_until;
the gap was the non-rate-limit case. Now, when the chain exhausts on a non-
rate-limit failure with a non-empty chain, arm a short (5s) cooldown on the
same _rate_limited_until gate (max(), never shrinking an existing window).
The next turn's restore stays gated and does NOT reset the index, so the
chain isn't replayed until the cooldown clears. No new state, no thread sleep,
no false-trip on legitimately long chains (those walk normally within a turn).
Tests: tests/run_agent/test_24996_fallback_exhaustion_cooldown.py
Claude Code OAuth refresh tokens are single-use; Claude Code refreshes on
its own schedule, so by the time Hermes notices an expired token Claude
Code may have already rotated it. Re-read live credential sources first and
adopt a valid token rather than POSTing a possibly-stale refresh token.
Ports the _refresh_oauth_token hardening from PR #40107 (chazmaniandinkle)
on top of the keychain/file reconciliation from PR #21112 (nodejun).
Adds AUTHOR_MAP entry for nodejun.
read_claude_code_credentials() previously returned the macOS Keychain
entry as soon as one existed, even if its OAuth token was already
expired. Callers then ran is_claude_code_token_valid() on the result
and got False, so resolve_anthropic_token() returned None — surfacing
the misleading 'No Anthropic credentials found' error even when
~/.claude/.credentials.json held a perfectly valid token.
Now reads both sources and prefers the non-expired one. When both are
valid (or both expired), prefers the later expiresAt so any subsequent
refresh uses the freshest refresh_token.
Adds TestReadClaudeCodeCredentialsDesync covering the four reconciliation
cases. The existing 'keychain wins' priority test still passes because
both fixtures share the same expiresAt and the tiebreaker is >=.
When a Telegram attachment download/cache fails (typically a transient
httpx.ConnectError to Telegram's CDN), the except handler logged a warning
and fell through to handle_message() with empty media and no text — the user
thought the file was delivered, the agent saw a content-less turn with no
signal an attachment was attempted, and the only record was a buried log line.
Adds _surface_media_cache_failure(): replies to the user in Telegram so they
know to retry, and appends an agent-visible notice to event.text via the
existing _append_observed_note channel so the agent knows an attachment was
attempted and failed. No new event fields (structured-event refactor is out
of scope per #23045). Wired into all five cache-failure sites — photo, voice,
audio, video, document — since they shared the identical silent fall-through.
Bug 1 from #23045 (unsupported types routed as fake user messages) no longer
exists on main: the document handler now accepts any file type, so there is no
rejection branch to fix.
Closes#23045
Eager fallback previously fired only on rate_limit/billing. A stale-
detector-killed hung stream classifies as FailoverReason.timeout
(retryable=True) and the retry loop re-hit the same dead primary until
the budget exhausted -- 3 x ~180-300s stale kills compounding into a
15+ min silent hang while the configured fallback chain sat idle.
Extend the existing eager-fallback gate to also cover timeout and
overloaded, but only after one real retry (retry_count >= 2) so genuine
transient hiccups still recover on the primary. Reuses the same
pool-recovery guard and state-reset as the rate_limit branch -- no new
config flag, no change to the rate-limit intent.
Salvaged from PR #50228 by @linyubin. Closes#22277.
Co-authored-by: Hermes Agent <127238744+teknium1@users.noreply.github.com>
DISCORD_ALLOWED_USERS="*" now means "allow everyone", matching the
SIGNAL_ALLOWED_USERS / DISCORD_ALLOWED_CHANNELS wildcard convention and
the value `claw migrate` emits. Previously _is_allowed_user did exact
ID matching only, so "*" matched no user and blocked every non-self
sender — a P1 with no workaround.
Three sites, all required for the fix to hold at runtime:
- _is_allowed_user: short-circuit when "*" is in the allowlist.
- connect(): exclude "*" from the intents.members trigger so the
wildcard does not request the privileged Server Members intent
(which can block the bot from coming online).
- _resolve_allowed_usernames: preserve "*" verbatim; otherwise it lands
in the username-resolution bucket, matches no member, and is silently
dropped from the set and env var on the first on_ready — quietly
undoing the fix.
Slash auth delegates to _is_allowed_user (auto-covered); component auth
already honors "*" on main.
The gateway banner promises 'chat responses are scrubbed before delivery',
but _redact_gateway_user_facing_secrets used a divergent 6-pattern subset that
leaked credential shapes the comprehensive agent.redact catches — notably the
GitHub fine-grained PAT (github_pat_...) and the Telegram bot-token shape
(bot<digits>:<token>), the gateway's own credential type.
_redact_gateway_user_facing_secrets now delegates to
agent.redact.redact_sensitive_text(force=True) — the same Tirith-grade redactor
already applied to logs, tool output, and approval-command prompts — so the
outbound LLM-response path (final_response -> _sanitize_gateway_final_response)
masks the full credential set. The narrow local pattern set is kept as a
fail-soft second pass. force=True honors redaction even when
security.redact_secrets is off, matching _redact_approval_command.
Test: regression guard parametrizing all 5 issue shapes x every chat surface;
asserts secret body never reaches the user and surrounding prose survives. The
existing bearer-token test's marker assertion is loosened from the literal
'[REDACTED]' to mask-agnostic (the redactor masks as '***'/partial) — it
asserts the security invariant, not the implementation's mask string.
_try_openrouter() returned (None, None) whenever an OpenRouter credential
pool existed but was exhausted (_select_pool_entry -> (True, None)), making
the OPENROUTER_API_KEY env-var fallback unreachable. Auxiliary tasks
(compression, vision, web_extract) silently failed even with a valid env key.
Now the pool-present branch only returns early when it successfully builds a
client; an exhausted pool falls through to the env-var path. The final
failure (pool exhausted AND no env var) still marks the provider unhealthy.
Fixes#23452.
Co-authored-by: ambition0802 <noreply@github.com>
When the primary provider returns 401 and the auth-refresh path is
unavailable or fails, both call_llm() and async_call_llm() reached the
should_fallback gate without _is_auth_error in the condition, so the
auxiliary task (e.g. compression) was dropped silently — losing message
history. Add _is_auth_error to should_fallback (NOT is_capacity_error) in
both sync and async paths, plus an 'auth error' reason branch.
Auth stays a non-capacity error: it falls back in auto mode via the
is_auto gate, but on an explicitly-configured provider it still respects
the user's choice and raises rather than silently switching providers.
The agent's image-rejection fallback strips images and retries text-only when
a provider rejects image content, which is what lets the gateway drain its
queued messages. The fallback only fires on a hardcoded phrase list, and the
OpenRouter wording — HTTP 404 'No endpoints found that support image input' —
was missing. For OpenRouter-routed non-vision models the fallback never fired,
the retry loop re-sent the same rejected request until exhaustion, and every
subsequent message (including plain text) stayed queued behind the stuck turn.
Add the phrase to _IMAGE_REJECTION_PHRASES (the 404 already passes the 4xx
gate). Add a positive test and a guard test so the sibling OpenRouter
'no endpoints ... data policy / guardrail' 404s do NOT get their images
stripped.
Fixes#21160. Reported by @liu14goal14-ux; PR #21198 by @ygd58.
complete.path and complete.slash ran inline on the tui_gateway stdin
reader thread. complete.path spawns git ls-files and fuzzy-ranks the
whole repo; complete.slash does first-call prompt_toolkit imports plus a
skill-dir scan. While either ran, prompt.submit / session.interrupt sat
unread in the stdin pipe, freezing the TUI until the 120s RPC timeout
fired — most reliably reproduced by typing @ on a large repo / WSL2 mount.
Add both to _LONG_HANDLERS so completion runs on the existing thread
pool (write_json is already _stdout_lock-guarded). Root-cause fix:
covers any slow completion, not just the bare-@ trigger.
Fixes#21123
The main stop loop in _stop_impl() awaited adapter.cancel_background_tasks()
and adapter.disconnect() with no timeout, for both the primary and the
secondary-profile (multiplex) adapter maps. A half-dead platform — a wedged
Feishu/Lark WebSocket thread blocked on network I/O is the reported case —
makes one of those awaits block forever, so the process never exits. systemd
then SIGKILLs it after TimeoutStopSec, skipping atexit PID-file cleanup, and
the next start dies with 'PID file race lost' and enters a restart loop.
The per-adapter timeout infra already existed on main
(_adapter_disconnect_timeout_secs / HERMES_GATEWAY_ADAPTER_DISCONNECT_TIMEOUT,
default 5s) but was only wired into _safe_adapter_disconnect, which the
teardown path never calls.
Add _bounded_adapter_teardown(): wraps BOTH cancel_background_tasks() and
disconnect() in the existing timeout budget, logs and forces forward progress
on timeout, and never raises. Both teardown loops now route through it, so the
stop sequence always completes regardless of any adapter's internal behavior
and PID-file cleanup runs.
Original report + fix direction by @happy5318 (#14128, #14130); this widens it
to cover cancel_background_tasks(), the multiplex loop, and the config knob.
Co-authored-by: happy5318 <happy5318@users.noreply.github.com>
A user-added systemd drop-in like ExecStopPost=/bin/kill -9 $MAINPID fires
on every stop, including clean restarts — it SIGKILLs the freshly spawned
gateway before it stabilizes and Restart=always respawns it, producing an
infinite restart loop (issue #23272). The unit Hermes installs already shuts
down cleanly via KillMode=mixed + KillSignal=SIGTERM with Restart=always +
RestartForceExitStatus, so no extra kill is needed. Document this as a danger
callout in the gateway service-management section.
The MoA reference-block display (each reference model's output shown as a
labelled thinking block before the aggregator responds) previously existed
only in the classic CLI. The facade already emits moa.reference / moa.aggregating
through tool_progress_callback; this wires the TUI and desktop consumers.
- tui_gateway/server.py: _on_tool_progress relays moa.reference (label / text /
index / count) and moa.aggregating to the Ink/desktop client as their own
events.
- ui-tui: gatewayTypes adds the two event shapes; createGatewayEventHandler
routes them; turnController.recordMoaReference pushes a committed
thinking-style segment tagged with the source model. Shown regardless of
showReasoning — references ARE the mixture-of-agents process the user opted
into, not ordinary reasoning. moa.aggregating is a status-only transition
(no transcript entry).
- apps/desktop: use-message-stream appends each reference as a labelled
reasoning chunk via the existing reasoning disclosure; GatewayEventPayload
gains label/index/aggregator.
Tests: tui_gateway emit (3), Ink handler render + showReasoning-independence +
aggregating-no-segment (3). TUI typecheck/lint clean; desktop typecheck/lint
clean.
display.thinking_progress is documented as independent of tool_progress —
users can keep tool progress quiet while opting into mid-turn assistant
scratch-text bubbles. But two gates were keyed on tool_progress_enabled alone,
so with tool_progress:off the _thinking relay was silently dead even when
thinking_progress:true:
1. agent.tool_progress_callback was set to None unless tool_progress_enabled,
so the callback that queues _thinking text never fired.
2. The send_progress_messages drain task was only started when
tool_progress_enabled, so even queued messages had no consumer.
Both now gate on needs_progress_queue (tool_progress OR thinking_progress) —
the same condition that already decides whether to create the progress queue
at all. No effect when both are off (queue is None) or when tool_progress is
on (unchanged).
Tests: _thinking relays with thinking_progress:on/tool_progress:off, and is
suppressed when thinking_progress:off. Full progress-topics suite: 35 pass.
Follow-up to #53791 addressing review feedback: the footgun checker treated
capture_output=/stdout=/stderr=/check_output as proof a subprocess can't pop a
Windows console. That invariant is false — stream redirection controls where a
child's output goes, not whether a console is allocated. From a console-less
parent (Desktop/Electron, pythonw.exe, detached gateway/cron) a console-subsystem
child still flashes a window even when fully captured.
- check-windows-footguns.py: capture/redirect/check_output is no longer a blanket
safe-pass. Added _WINDOWS_FLASHING_PROGRAMS (git/gh/npm/node/python/uv/ffmpeg/
docker/powershell/…); calls to those are flagged even when captured. Non-flashing
programs keep the capture exemption (no 271-site noise). _subprocess_compat.run/
popen calls are inherently safe (wrapper injects CREATE_NO_WINDOW).
- Routed the 35 genuine flashing git/gh/npm/uv/ffmpeg/docker spawns through the
_subprocess_compat.run/popen chokepoint (Brooklyn's wrapper from #53810) — the
durable fix, not per-site annotations. cmd.exe /c start stays # ok (intentional).
- Updated tests + CONTRIBUTING.md rule #17 to the corrected invariant.
On a MoA session, auxiliary tasks (title generation, compression, vision, …)
ran through _resolve_auto with provider='moa' / model='<preset>', which sent
the preset name (e.g. 'opus-gpt') as the model id to resolve_provider_client —
producing 'HTTP 400: opus-gpt is not a valid model ID' on every turn (visible
as the title-generation warning).
MoA is a virtual provider with no real HTTP endpoint; aux tasks don't need the
reference fan-out. _resolve_auto now resolves a 'moa' main provider to the
preset's aggregator slot (its acting model) and continues Step 1 with that real
provider+model, dropping the virtual moa://local base_url + placeholder key so
the aggregator resolves via its own provider credentials. Mirrors the MoA
context-length resolution.
Verified live: a MoA turn no longer emits the 'not a valid model ID' warning.
Test: tests/agent/test_auxiliary_main_first.py (19 pass).
* fix(windows): stop terminal-window popups from background spawns
Native-Windows desktop/gateway users saw cmd/conhost windows flash on
gateway restart, image paste, the dashboard Projects tree, voice notes,
and ~5 min after closing the app (detached cron). Two root causes:
- Console-subsystem exes (taskkill, schtasks, wmic, netstat, tasklist,
agent-browser, git, ffmpeg, powershell, git-bash) spawned via raw
subprocess allocate a fresh console when the launching process has
none (pythonw desktop backend / detached gateway) - even with output
captured.
- uv venv pythonw shims re-exec console python.exe, so Python children
get a console regardless of how they're launched.
Fixes:
- Single hidden-spawn primitive (_subprocess_compat.run/.popen) that ORs
CREATE_NO_WINDOW on Windows, no-op on POSIX. Route every Hermes-owned
console-exe spawn through it.
- FreeConsole() catch-all in hermes_bootstrap: any Python child that
exclusively owns an auto-allocated console detaches it at startup
(GetConsoleProcessList()==1 gate leaves shared interactive consoles
untouched).
- Replace PowerShell/wmic gateway PID scans with in-process psutil.
- Skip schtasks queries on non-interactive desktop restarts.
- Prefer native agent-browser .exe over .cmd shims.
- Guard test bans raw subprocess spawns of the Windows-only console
tools repo-wide so the popup class can't regress.
* fix(windows): scope FreeConsole to background entry points; fix merge fallout
Console detach review (per #53810 feedback): GetConsoleProcessList()==1 can't
tell a uv pythonw->python phantom console apart from a user opening the
interactive CLI/TUI in its own fresh console (double-click, shortcut, ConPTY) —
both report a single attached process with a tty. Running FreeConsole() in the
import-time bootstrap therefore risked detaching a legitimately-interactive
terminal.
- Extract FreeConsole into explicit hermes_bootstrap.detach_orphan_console();
remove it from apply_windows_utf8_bootstrap() (import side effect).
- Call it only from known background mains: gateway run, dashboard backend
(start_server, what the desktop spawns), cron standalone, tui_gateway entry,
slash worker. Interactive CLI/TUI never calls it.
- Behavior-contract tests: frees only when solo owner, leaves shared console,
no-op without console / on POSIX, and asserts it's not an import side effect.
Merge fallout from origin/main (#53791):
- local.py: 3-way merge left a dangling **_popen_kwargs (NameError crashing
every terminal init). _subprocess_compat.popen already hides the window, so
drop it.
- discord adapter: merge stacked an undefined windows_hide_flags() onto the
primitive call; drop the redundant arg.
- test_gateway: scan now goes psutil-first (zero spawn); rewrite the
case-variant test to drive that production path.
* test(claw): mock _subprocess_compat.run seam for Windows process scan
claw.py's Windows tasklist/powershell scan routes through the hidden-spawn
primitive; the tests still patched claw_mod.subprocess, so on win32 the mock
was never hit and real spawns returned nothing. Patch the actual seam.
* fix(windows): stop subprocess console-window popups + add CI guard
The single biggest source of Windows 'terminal popup' bug reports was bare
subprocess.run/Popen calls spawning a console window. The compat helpers
(windows_hide_flags / windows_detach_popen_kwargs) already existed but the
footgun checker had no rule to stop new bare calls from reintroducing the flash.
- scripts/check-windows-footguns.py: new AST-based rule flagging subprocess
calls that can create a new console — output-redirection-aware (capture/
redirect/check_output exempt) and POSIX-only-program-aware (launchctl/
systemctl/brew/etc. exempt). Comprehensive on real popups, no annotation
burden on calls that can't flash.
- Swept all genuine window-spawning sites through windows_hide_flags()/
windows_detach_popen_kwargs(); marked intentionally-visible launches
(editor/terminal/foreground re-exec) with '# windows-footgun: ok'.
- tests/scripts/test_windows_footgun_subprocess_rule.py: behavior-contract
tests + full-repo cleanliness invariant.
- CONTRIBUTING.md: documents the rule + the helper pattern.
* test: accept creationflags kwarg in psutil_android fake_subprocess_run
The Windows no-window sweep added creationflags=windows_hide_flags() to
install_psutil_android.py's subprocess.run call; the test's fake stub had a
fixed (cmd) signature and raised TypeError on the new kwarg.
When a MoA preset is selected, each reference model's answer now renders in the
CLI as a thinking-style block labelled with its source model, BEFORE the
aggregator responds — so the mixture-of-agents process is visible instead of a
silent pause. The aggregator's response (and its tool actions) follow as normal.
Mechanism (shared seam, all surfaces):
- MoAChatCompletions/MoAClient take an optional reference_callback and emit
'moa.reference' (index/count/label/text) per reference, then 'moa.aggregating'
(aggregator label) once. agent_init wires this to the agent's
tool_progress_callback, which every surface already consumes — so the events
reach CLI/TUI/desktop/gateway with no new plumbing.
- CLI _on_tool_progress renders 'moa.reference' as a labelled '┊ ◇ Reference
i/n — <model>' header + a thinking-style preview (reusing _emit_reasoning_
preview), and 'moa.aggregating' as a spinner transition. Display-only; never
touches message history (cache-safe).
Turn-scoped reference cache: the agent loop calls the facade once per tool-loop
iteration, but the advisory message view is identical across iterations within a
turn, so references are now run AND displayed once per user turn (keyed by the
advisory view's signature) instead of re-running/re-spamming on every iteration.
This also cuts reference API cost from O(iterations) back to O(turns).
Verified live via interactive PTY on the opus-gpt preset (gpt-5.5 + opus refs):
reference blocks render once per turn, labelled by model, before the aggregator;
fresh blocks on each new turn; aggregator tool actions still execute.
Follow-up: TUI/desktop rich rendering + gateway batched-summary already receive
the events via tool_progress_callback; their surface-specific renderers are a
separate change.
The Hermes gateway runs inside its own venv, so its process environment
carries VIRTUAL_ENV (and possibly CONDA_PREFIX). The terminal tool spawned
subprocesses inheriting those markers. When the agent ran `uv sync`,
`uv pip install`, `poetry install`, etc. in ANY other project directory,
those tools honored the inherited VIRTUAL_ENV and rebuilt/synced that
project's dependencies into the Hermes venv path — wiping Hermes' own runtime
deps (and, when the other project pinned a different Python, replacing the
interpreter), bricking the gateway on the next restart (#23473).
Strip VIRTUAL_ENV/CONDA_PREFIX in both subprocess-env construction points in
tools/environments/local.py — `_sanitize_subprocess_env` and `_make_run_env`
— via a shared `_ACTIVE_VENV_MARKER_VARS` constant. The Hermes venv stays
reachable because its bin dir is already first on PATH, so removing the
active-environment markers is safe and only prevents the cross-project clobber.
Adds TestActiveVenvMarkerStripping: end-to-end (markers in os.environ don't
reach the spawned subprocess) and unit coverage for both functions, plus a
guard on the marker constant.
Also adds the AUTHOR_MAP entry for the salvaged contributor.
Closes#23473
In the interactive CLI, the aggregator's tool calls under a MoA preset (or
any non-streaming model call, e.g. copilot-acp) appeared to overwrite each
other instead of building scrollable history. Each tool only updated the
transient spinner line; no committed scrollback line was printed.
Root cause: persistent tool lines in _on_tool_progress's tool.completed
branch were gated on tool_progress_mode in {all, new}, omitting 'verbose'.
Streaming models hid the bug because _on_tool_gen_start commits a 'preparing'
line per tool during streaming; non-streaming calls (MoA forces
_use_streaming=False) never emit that, so under 'verbose' there was no
committed line at all — only the self-overwriting spinner.
'verbose' is strictly more than 'all', so it now commits the same scrollback
line. Verified live via interactive PTY on the MoA opus-gpt preset: three
terminal calls in turn 1 and two in turn 2 each render as separate persistent
lines.
A MoA session's model is the preset name (e.g. 'opus-gpt') and its base_url is
the virtual local endpoint, so get_model_context_length() missed every probe
and fell through to the 256K fallback — even when the aggregator is a 1M-context
model. The acting model in MoA IS the aggregator, so resolve the context window
from the aggregator slot's real provider+model.
- model_metadata.get_model_context_length: when provider=='moa', resolve the
preset's aggregator slot through resolve_runtime_provider and recurse with the
aggregator's real provider/model/base_url. Explicit model.context_length still
wins (checked first); falls through to the generic default if resolution fails.
Tests: opus-gpt preset now reports 1M (the aggregator window), config override
still honored.
`hermes desktop` / `hermes update` recover from a corrupt Electron download by
purging the cached zip + re-downloading and retrying the pack, and then by
falling back to a public mirror. That recovery is only meaningful when the
packaged executable is MISSING — the signature of a partial/corrupt unpack.
A LATE failure such as macOS code signing (#40187) leaves
`Hermes.app/Contents/MacOS/Hermes` (or the platform equivalent) in place.
Re-downloading Electron can't repair a signing failure, so the purge +
slow mirror retry just grind through another identical failure before the
build finally errors out.
Gate both recovery blocks on `_desktop_packaged_executable(desktop_dir) is None`
so a build that already produced the executable fails fast instead of
triggering the destructive download recovery. The corrupt-download path
(executable missing) is unchanged.
Salvage of #42782, re-applied onto current main (the surrounding recovery was
refactored to `_electron_dist_ok` / `_redownload_electron_dist` since the PR
was opened). Adds a regression test asserting no purge / mirror retry runs when
the executable exists, and updates the existing retry/mirror tests to model the
corrupt-download case (executable absent) the recovery is actually for.
Related to #40187 (the residual cache-purge sub-issue; the signing failure
itself is fixed by #52591).
Selecting 'Mixture of Agents' in the `hermes model` provider picker fell
through silently — select_provider_and_model had no moa branch, so it just
reprinted the current model/provider summary and exited. And the CLI session
banner rendered the bare preset name (e.g. 'opus-gpt · Nous Research'),
which is meaningless out of context.
- Add _model_flow_moa: always lists the available presets (even one), then
prints the full reference-models + aggregator breakdown for the selection
and persists model.provider=moa / model.default=<preset> (dropping stale
base_url + endpoint creds, since moa is a virtual local provider).
- Wire the branch into select_provider_and_model.
- build_welcome_banner takes provider; when 'moa' it renders
'MoA: <preset> · agg <aggregator>' instead of a bare slug. Both CLI call
sites pass self.provider.
Tests: 2 new banner tests (moa + non-moa unchanged); E2E verified the picker
persists the preset and clears stale base_url/api_key.
* fix(update): route loud build/installer output to update.log instead of the terminal
hermes update flooded the terminal with the full vite asset dump,
electron-builder logs, npm deprecation warnings from the desktop build,
and the cua-driver installer's 'Next steps' wall. All of that is
low-signal noise the user doesn't need on a successful update.
- Capture the desktop --build-only subprocess (vite + electron-builder)
into ~/.hermes/logs/update.log; print a one-line status, and on
failure surface the last 15 lines + a pointer to the full log.
- Capture the cua-driver installer's output when verbose=False (the
hermes update refresh path); concise upgrade line is unchanged.
- Add _log_only_write() / _run_logged_subprocess() helpers that write to
the update.log handle without echoing to the terminal.
The repo-root npm install keeps streaming (capture_output=False) — that
is the deliberate #18840 guard so a slow postinstall download doesn't
look hung. The desktop npm install is a separate Electron process with
no such progress concern and is captured.
* fix(update): persist full cua-driver installer output to update.log
The captured cua-driver installer output was only sent to logger.debug
(agent.log) on failure, so the 'Next steps' wall was lost from
update.log entirely on success. Write the full captured output straight
to the update.log handle (sys.stdout._log) on both success and failure,
matching the desktop-build capture, so update.log keeps the complete
record of everything an update did.
The secret redactor only matched uppercase env-style keys ([A-Z0-9_]),
so config-file assignments like spring.datasource.password=secret,
app.api.key=xyz, and YAML password: secret leaked verbatim when the
agent ran cat/grep on application.properties or .env files (issue #16413).
Adds three case-insensitive config-key matchers that run only in a
config-file context, preserving the existing #4367 (lowercase code/prose)
and web-URL-passthrough carve-outs:
- _CFG_DOTTED_RE: namespaced keys (contain a dot) — unambiguously config
- _CFG_ANCHORED_RE: bare secret-word keys at line start (incl. export)
- _YAML_ASSIGN_RE: unquoted colon config (password: value)
Value capture stops at whitespace and '&' so form bodies stay pair-wise;
the '://' guard keeps intentional web-URL query-param passthrough intact.
Reported-by: Murtaza1211
* fix(tools): let vision pick any provider+model, not just OpenRouter
hermes tools → configure → vision no longer forces an OPENROUTER_API_KEY.
It now offers the same any-provider surface as the model command: Auto
(use main model / aggregator fallback), pick any authenticated provider +
model, or a custom OpenAI-compatible endpoint. Selections persist to
auxiliary.vision.{provider,model,base_url} — the keys the vision resolver
already reads. Custom endpoint pins provider=custom so base_url routes
correctly. Reconfigure path uses the same picker instead of re-prompting
for OPENROUTER_API_KEY.
* docs: add PR infographic for vision any-provider picker
check_all_command_guards() swallowed ImportError from tools.tirith_security
with an unconditional pass, leaving tirith_result["action"] as "allow"
regardless of security.tirith_fail_open. When an operator sets
tirith_fail_open: false they have explicitly opted into fail-closed
behaviour; a missing or broken Tirith module must not silently permit
command execution.
Inside the except ImportError handler, read the live security config.
When tirith_enabled is true and tirith_fail_open is false, synthesise a
"warn"-action Tirith result so the command flows through the normal
approval path (prompt the user, or block in cron/gateway contexts)
instead of bypassing it. The default tirith_fail_open: true behaviour
is unchanged.
Adds three regression tests to tests/tools/test_approval.py:
- fail_open=true + ImportError → silently allowed (no regression)
- fail_open=false + ImportError → approval callback invoked, command denied
- tirith_enabled=false → always allowed regardless of fail_open
Fixes#20733
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
# Conflicts:
# tests/tools/test_approval.py
Cron jobs accumulate large volumes of repetitive vocabulary (recurring
project names, dates, summaries) and out-number a user's interactive
sessions. Under bare BM25 they dominate the top FTS rows, so discover's
early-exit-at-N dedup collects only cron sessions and the user's own
conversations never surface — "recall blindness" (#19434).
- _order_for_recall() stable-sorts FTS rows so interactive sources rank
above cron before lineage dedup; within each class BM25/recency order
is preserved. Cron is demoted, not excluded, so it still surfaces when
it is the only match.
- raise discover scan limit 50 -> 300 so buried interactive matches are
in hand for the demotion pass.
Fixes the cron-flooding sub-bug of #19434. The split-brain sub-bug is
covered by #52798; the child-session sub-bug is superseded by in-place
compaction.
send_message with MEDIA:/path to a WhatsApp target previously dropped the
attachment: the WhatsApp branch never passed media_files, the plugin's
_standalone_send accepted the param but only POSTed text, and WhatsApp was
absent from the media-supported platform list.
- send_message_tool: add a Platform.WHATSAPP media block (mirrors Feishu) that
routes media_files through the whatsapp plugin's standalone_sender_fn, and
add whatsapp to the supported-media list strings.
- whatsapp adapter: _standalone_send now sends text first (skipped when the
chunk is media-only), then uploads each file via the bridge /send-media
endpoint with a mediaType derived from extension/is_voice/force_document, so
images/videos/voice arrive as native bubbles instead of documents.
- _bridge_media_type classifier maps ext -> image|video|audio|document.
Closes#19105 (remaining send_message gap). Other items in the report
(inbound video paths, image_generate auto-deliver, history dedup, native
gateway bubbles) already landed on main.
A long-running gateway session could permanently lose an MCP server: once a
stdio subprocess died (or transient drops accumulated over the session), the
run loop exhausted its reconnect budget and returned, orphaning the task. With
no listener for _reconnect_event, the circuit breaker's half-open probe could
never revive the server — every probe hit a dead/absent session, re-armed the
60s cooldown, and looped forever until a full gateway restart (#16788).
Root cause was split ownership of transport liveness between the run loop and
the tool handler, plus a permanent give-up path. Fixed by one invariant: a
non-shutdown server task is always reconnectable.
- run loop parks (deregisters phantom tools, then awaits _reconnect_event)
instead of returning when the reconnect budget is exhausted, so the task
stays alive as a dormant listener
- retry budget resets on every successful (re)connect, so a healthy
long-lived server can't accumulate lifetime drops into a death sentence
- half-open probe with no live session signals a reconnect (reviving a
parked/dead task and respawning a dead stdio subprocess) and returns a
clean 'reconnecting' error instead of writing into a dead pipe
- breaker resets on successful session init across all transports
(stdio/HTTP/SSE) — fully transport-agnostic, no PID/pipe polling
Builds on the closed-PR cluster for this issue: keeps #49255's deregister-on-
exhaustion insight and #21006's signal-don't-probe insight, discards the racy
os.kill PID machinery.
Co-authored-by: LeonSGP43 <LeonSGP43@users.noreply.github.com>
Co-authored-by: srojk34 <srojk34@users.noreply.github.com>
MoA was calling reference and aggregator models through a bare
call_llm(provider=slot["provider"], model=slot["model"]) with a forced
temperature and a forced max_tokens (the preset's hardcoded 4096). That left
base_url/api_key/api_mode unresolved — so the auxiliary auto-detector guessed
the API surface instead of using the provider's real runtime, and the 4096 cap
truncated long aggregator syntheses.
A MoA slot is just a model selection and must be called the same way any model
is called elsewhere. Each slot is now resolved through resolve_runtime_provider
(the canonical provider→api_mode/base_url/api_key resolver the CLI, gateway, and
delegate_task all use) via a new _slot_runtime() helper, and the resolved
endpoint is passed into call_llm. So a reference/aggregator gets its provider's
actual API surface — MiniMax → anthropic_messages, GPT-5/o-series →
max_completion_tokens, custom endpoints → their base_url — identical to how that
model is handled as the acting model.
MoA also no longer imposes its own output cap: max_tokens defaults to None
(omitted → the model's real maximum) for references and is passed through from
the caller for the aggregator. The preset's hardcoded 4096 is gone. The
max_tokens preset config field is left in place (config/web/desktop unchanged);
it is simply no longer applied as a forced cap.
Tests: slots route through resolve_runtime_provider with resolved base_url/
api_key; resolution errors fall back to bare provider/model; neither call
carries an output cap even when the preset config still contains max_tokens.
When automatic fallback activates a provider that differs from the
primary, try_activate_fallback() cleared the primary's pool (to avoid
cross-provider base_url contamination, #33163) but never loaded the
fallback provider's own pool. The fallback then ran with no pool, so
rate_limit/billing/auth recovery couldn't rotate its credentials.
After clearing a mismatched pool, load_pool(fb_provider) and attach it
when it has credentials, so provider-specific rotation continues to
work on the fallback target.
switch_model() swapped model/provider/base_url/api_key but never
refreshed agent._credential_pool, which stays bound to the original
provider. recover_with_credential_pool() then sees a pool.provider !=
agent.provider mismatch and short-circuits — so a 429/401 on the new
provider gets no rotation and falls through to fallback instead.
Reload load_pool(new_provider) inside switch_model when the provider
changes (or the pool is missing). The reload is inside the protected
swap block and the pool is added to the rollback snapshot, so a failed
client rebuild restores the original pool.
Fixes#16678, #52727.
test_config_bridges_telegram_group_settings and
test_config_bridges_telegram_user_allowlists asserted the YAML→env bridge
via os.environ. A developer's real ~/.hermes/.env can repopulate TELEGRAM_*
vars during load_gateway_config(): the microsoft_teams plugin runs
load_dotenv(find_dotenv(usecwd=True)) at import time, which walks up from the
cwd (under ~/.hermes/ in worktrees) and reloads the user's .env, defeating the
env-over-YAML bridge for any key present there (e.g. TELEGRAM_GROUP_ALLOWED_CHATS).
Assert the returned PlatformConfig.extra instead — it is parsed straight from
the test's config.yaml and is immune to that ambient leak. free_response_chats
is bridged to the env var only (not extra), and TELEGRAM_FREE_RESPONSE_CHATS
doesn't appear in developer .env files, so it stays a deterministic os.environ
assertion.
The Telegram/Discord /model command's actual switch calls switch_model()
directly on the asyncio event loop. switch_model() can fall through to a
synchronous models.dev HTTP fetch (requests.get, 15s timeout) on a cold or
expired cache, freezing the gateway for up to 15s and dropping the Telegram
connection while a user switches models.
The picker provider-list and fallback text-list sites were already offloaded
(#41289), but the two _switch_model() calls — the picker callback and the
direct /model <name> path — were not. Wrap both in asyncio.to_thread.
Closes#20525.
The adapter-level intake gate (_is_dm_allowed / _is_group_allowed, reached
via _should_process_message) did a raw set-membership check against the
configured allowlist. WhatsApp now delivers inbound DM senders in LID form
(<id>@lid) while operators configure allowlists with phone numbers, so the
check never matched and every DM from an allowed contact was silently
dropped before the gateway authz layer ran.
Route both gates through the existing gateway.whatsapp_identity.
expand_whatsapp_aliases helper (already used by gateway authz and session
keys), which walks the bridge's lid-mapping-*.json session files. Phone and
LID forms now resolve to each other in both directions; exact JID matches,
wildcard, disabled/open policies, and empty-allowlist fail-closed behavior
are all preserved.
Fixes#14486
Z.AI / Zhipu reuse HTTP 429 for server-wide overload. The 429 status
path classified these unconditionally as rate_limit with
should_rotate_credential=True, so an overloaded provider exhausted the
credential pool after two errors — fatal for a single-key user, who has
nothing to rotate to.
The credential is valid; the server is just busy. Disambiguate the 429
body against a shared _OVERLOADED_PATTERNS list and route overload
language to FailoverReason.overloaded (retryable, no rotation), matching
the existing 503/529 path and the message-only path (#52890). Genuine
rate limits (no overload language) still rotate.
Extracted the inline overloaded tuple #52890 added into the shared
_OVERLOADED_PATTERNS constant so the status-code and message paths use
one list.
Closes#14038.
_normalize_custom_provider_entry() ran urlparse() on base_url and dropped
any entry whose value was an un-expanded placeholder, so a caller reaching
the normalizer with raw config (e.g. the Dockerized gateway path) silently
skipped the provider with a 'not a valid URL' warning. Skip URL validation
when the candidate contains a placeholder token — both ${ENV_VAR} env-refs
and bare {region}-style templates — since those are expanded at runtime.
Closes#14457
prompt_toolkit's renderer sends ESC[6n cursor-position queries before
painting in non-fullscreen mode; the terminal replies ESC[<row>;<col>R.
Over SSH/cloudflared tunnels and slow PTYs these replies race past the
input parser and land in the display as raw '20;1R21;1R' text, and the
pending-CPR future can stall the renderer so the prompt freezes after the
agent's final answer.
Build the prompt_toolkit output with enable_cpr=False so CPR is marked
NOT_SUPPORTED up front and ESC[6n is never sent. This is the root-cause
counterpart to the existing input-side _strip_leaked_terminal_responses
scrubbing. Vt100_Output.from_pty() does not expose enable_cpr in
prompt_toolkit 3.x, so _build_cpr_disabled_output() reproduces its
get_size setup and calls the constructor directly; it returns None on any
failure so startup falls back to the default output.
Verified in a real PTY: baseline emits 1 ESC[6n query, the fix emits 0,
banner/UI render identically. Layout is unaffected — with CPR off the
renderer sizes the prompt to its preferred height (the same fallback
prompt_toolkit uses on any terminal that doesn't answer CPR).
Co-authored-by: Hermes Agent <noreply@nousresearch.com>
The dashboard Config tab's Model field is a flat string with no provider
info. _denormalize_config_from_web only updated model.default and kept the
stale provider, so picking an OpenRouter model while the default provider was
ollama-local left provider=ollama-local and every call 404'd.
When the model string actually changes, infer the serving provider — curated
catalog first, then a vendor/model-slug heuristic for non-aggregator providers
— and route the switch through the existing _normalize_main_model_assignment /
_apply_main_model_assignment chokepoints so stale base_url/api_mode/api_key are
cleared on a provider change and preserved on a same-provider re-pick. Saving
an unchanged model never re-detects, so unrelated config saves keep an explicit
provider.
Closes#14058
Add an explicit _closing guard to both owned executors so the
recreate-on-shutdown path only recovers from an *external* teardown of
the loop default — never resurrects a pool the gateway/adapter itself
stopped. _shutdown_*executor() sets the flag; _get_*executor() raises if
closing; feishu connect() re-arms on reconnect. Updates the gateway
recreate test to assert the refusal contract and adds feishu coverage.
Feishu SDK calls ran on asyncio's shared default executor, so a torn-down
default executor wedged every send with 'Executor shutdown has been called'
and left the gateway a zombie (#10849). The adapter now owns a
ThreadPoolExecutor recreated on demand if shut down, mirroring the
gateway-owned executor change. Routes all 17 self._client SDK calls through
_run_blocking; shuts the pool down on disconnect.
Follow-up to the #13971 fix: a genuine native Ollama provider reached
through a reverse proxy carries no ollama/:11434 URL signature, so the
restricted detection would miss it. Add provider=="ollama" as an
explicit True case (idea from #14789, @Tranquil-Flow) and cover both it
and the #13971 LiteLLM-proxy-to-zai false-positive with E2E tests.
The _is_ollama_glm_backend() function was too broad: any local endpoint
running a GLM model was treated as Ollama, triggering the stop->length
misreport heuristic introduced in 8011aa3. This caused false truncation
detection on sglang, vLLM, LM Studio, and other non-Ollama servers that
correctly report finish_reason.
When a GLM model on sglang/vLLM returned finish_reason='stop', the agent
mistakenly reclassified it as 'length' if the response didn't end with
a whitelisted punctuation character (ASCII or CJK). This particularly
affected Chinese-language responses and Markdown-formatted text.
Root cause: the is_local_endpoint() fallback assumed any local GLM
endpoint = Ollama. But many non-Ollama servers also run on localhost.
Fix: remove the is_local_endpoint() catch-all. Only detect Ollama via
its distinctive signatures (port 11434, 'ollama' in URL). All other
local servers are assumed to report finish_reason correctly.
This is the correct tradeoff because:
- False negatives (Ollama at custom port, heuristic not triggered) only
mean the user sees a truncated response — same as having no heuristic
- False positives (non-Ollama server, heuristic wrongly triggered) inject
spurious continuation messages into the conversation — strictly worse
Adds two tests:
- sglang GLM response is NOT reclassified as truncated
- Ollama GLM on port 11434 still triggers the heuristic as before
Co-authored-by: Hermes Agent <hermes@nousresearch.com>
TELEGRAM_HOME_CHANNEL set to an @username (not a numeric chat ID) crashed
all webhook/cron->Telegram home-channel delivery with 'ValueError: invalid
literal for int()'. The Telegram Bot API accepts both a numeric chat_id and
an @username string; Hermes was force-coercing every chat_id with int().
Add normalize_telegram_chat_id() (returns int for numeric values, passes
@username strings through) and apply it at the Bot API send/edit sites in
the Telegram adapter and the send_message tool. Username targets are now
recognized as explicit targets in _parse_target_ref.
Reapplies the approach from #13274 (season179), whose branch predated the
gateway/platforms/telegram.py -> plugins/platforms/telegram/adapter.py
relocation. Dupes: #13535 (Tranquil-Flow), #37572 (chewkaah).
Co-authored-by: season179 <season.saw@gmail.com>
Follow-up on the cherry-picked #13173 fix. Holds the _run_restart task in
self._restart_task (a bare asyncio.create_task keeps only a weak reference,
so a still-pending task can be GC'd mid-flight) and explicitly skips it in
the _stop_impl cancel loop alongside _stop_task. Adds AUTHOR_MAP entry for
the contributor and a regression test that fails when the task is cancellable.
Refs #12875
When request_restart() adds _run_restart to _background_tasks, _stop_impl
later cancels all entries in that set. Since _run_restart is awaiting
_stop_task at that point, the CancelledError propagates into _stop_impl,
interrupting cleanup before _shutdown_event.set() and _exit_code = 75
execute. This leaves the gateway as a zombie (alive but disconnected) or
exiting with code 0 instead of 75, preventing systemd Restart=on-failure
from restarting the service.
Fix: don't add _run_restart to _background_tasks — it self-terminates in
~50ms and needs no lifecycle management.
Fixes#12875
Regression tests for the self-author guard added in the salvaged fix:
- bot-authored DM-topic watcher echo is dropped (the exact #11905 symptom)
- bot self-messages dropped in groups/supergroups too
- other bots in the same chat are still processed (self-id, not is_bot)
- observe-unmentioned sibling path also rejects self-messages
- missing from_user does not crash
Test scaffolding ported from @cola-runner's PR #12817 and adapted to the
current plugins/platforms/telegram/adapter.py and _is_own_message().
The error raised when a model's context window is below the 64K minimum
advertised "or set model.context_length in config.yaml to override" — but
the guard intentionally has no sub-64K escape hatch. Sub-64K models are
rejected by design (tool schemas + system prompt need the headroom).
The misleading clause invited a cluster of dup PRs (#11097, #11110, #8962,
#9142, #37548) all trying to wire an override that we don't want. Reword to
state the real options: pick a >=64K model, or — if your local server
under-reports its true window — declare the real value (which must itself
be >=64K). Guard behavior is unchanged.
A profile's cron jobs now provably live in AND execute under that profile's
HERMES_HOME. A job authored under profile `coder` is stored at
`~/.hermes/profiles/coder/cron/jobs.json` and runs with coder's .env,
config.yaml, scripts and skills — never the default root's.
This was the de-facto behavior on main but only by accident: PR #50112 had
re-anchored cron storage at the shared default root, and a later stale-branch
squash merge (#52147) silently reverted it back to the profile home. Neither
direction was guarded by a test, so it could flip again on the next stale merge.
Changes:
- cron/jobs.py: document the per-profile storage anchor (get_hermes_home, NOT
get_default_hermes_root) and why anchoring at the root leaks
config/credentials/skills across profiles — the #4707 security boundary.
- cron/scheduler.py, cron/suggestions.py: same intent documented at the
dynamic resolution helper and the suggestions store.
- tests/cron/test_cron_profile_isolation.py: pin storage, lock-path, and
execution-home resolution to the active profile so a re-anchor can't regress.
Verified E2E: jobs created under two profiles land in separate per-profile
stores with zero cross-profile leakage and no shared-root store; scheduler
execution-home follows the active profile. Full cron suite: 576/576.
The curator_env fixture left async review threads (synchronous=False spawns
a daemon 'curator-review' thread that calls save_state() on completion)
running past test teardown. save_state() resolves the state path from
HERMES_HOME at write time, so a straggler could write into the next test's
tmp home, corrupting test_state_file_survives_corrupt_read (and others)
under CI load. Join the thread on teardown while HERMES_HOME is still
pinned to this test's home.
Lock the contract that a clean stream-queue termination followed by an
agent failure never reports finish_reason: "stop". Covers the raised-
exception case (#12422 repro), the flagged failed-result case, truncation
(length), and the success happy path.
Follow-up to the salvaged #12504 fix from @flobo3.
Refresh the hermes-agent skill against the last 5 major releases and the
current codebase, and cut verbose prose.
Coverage added (v0.13.0–v0.17.0):
- New gateway platforms: iMessage (Photon), Teams, LINE, SimpleX, ntfy,
Google Chat, Raft, official WhatsApp Business Cloud API (now 20+).
- New surfaces section: desktop app, web dashboard admin panel,
hermes proxy (OpenAI-compatible OAuth proxy), Automation Blueprints.
- delegate_task(background=true) async subagents; memory-tool atomic
batch operations; session_search three-mode shape; x_search/video_analyze
toolsets; image_gen image-to-image; xAI Grok via SuperGrok OAuth.
- display.interface (cli/tui), curator.consolidate opt-in, PyPI install.
Accuracy fixes:
- Adding-a-Tool is two files (auto-discovery), not three.
- Testing uses scripts/run_tests.sh (canonical runner), not bare pytest.
- Dropped change-detector test count and a dangling references/ pointer.
- Refreshed overview (Windows-native, 20+ providers, many surfaces).
Conciseness: trimmed over-explained Windows keybinding/sandbox/test prose
and deep prompt-builder internals to pointers.
The dashboard form is built from CONFIG_SCHEMA, which doesn't enumerate
every root-level key the YAML supports. Most visibly, `custom_providers`
is in `_KNOWN_ROOT_KEYS` but is absent from the schema — so the frontend
never sends it in the PUT body. The previous full-replace save() then
silently wiped the key from disk every time the user clicked anything
that triggered a save. Other casualties (less visible because defaults
re-mask them on load) include `agent.personalities`,
`agent.reasoning_effort`, `terminal.lifetime_seconds`, etc.
Fix: read the raw on-disk config and deep-merge the incoming PUT body
on top of it before saving. The frontend can only overwrite what it
explicitly sends; everything else is preserved verbatim.
Reuses the existing `_deep_merge` helper from `hermes_cli.config`.
Tests:
- `test_round_trip_preserves_custom_providers` exercises the exact bug:
seed config with custom_providers, GET → drop the key → PUT,
assert it's still on disk.
- `test_round_trip_preserves_schema_invisible_nested_keys` covers the
shallow-vs-deep-merge case for nested dicts under `agent` etc.
Both fail on current main; both pass with this patch.
The 'whatsapp' and 'signal' PLATFORM_HINTS told the agent 'Please do not
use markdown as it does not render' — factually wrong. Both adapters
actively convert markdown to native formatting:
- whatsapp_common.format_message(): **bold**, ~~strike~~, # headers,
links, code blocks -> WhatsApp native syntax
- signal_format.markdown_to_signal(): same conversions via bodyRanges,
plus '- item' / '* item' bullets -> '• ' Unicode bullets
The wrong hint made the agent strip bullets and bold the adapter would
have rendered (#12224). Rewrote both hints to mirror whatsapp_cloud:
markdown is auto-converted, bullet lists work, tables are not supported.
Added a contract test asserting markdown-converting platforms never
forbid markdown in their hint.
Follow-up on the gateway-picker salvage: the cherry-picked change added a
second copy of the MoA virtual-provider row in model_switch.py, duplicating
inventory._moa_provider_row (same slug/name/preset-models, identical extra
fields). Make _moa_provider_row take a bare current_provider string and reuse
it from the gateway picker path so the row shape lives in one place and the
two surfaces can't drift.
HMAC validation authenticates the webhook sender, not the business
fields inside the payload (PR titles, commit messages, issue bodies),
which are authored by untrusted third parties. Expand the prompt-
injection section to make the trust boundary explicit: the agent's
capability surface, not the input channel. Document the hardening
levers (sandbox the runtime, scope the toolset, keep approvals on,
template narrowly) instead of pretending to sanitize untrusted text.
Refs #8820.
Follow-up on the salvaged MoA restore fix:
- Extract the finally-block restore into _restore_moa_one_shot() so the
behavior is unit-testable without re-implementing it, and so the gateway
/moa handler and the finally block share one implementation.
- Restore the load-bearing #28686 zombie-eviction comment above
_release_running_agent_state that the original diff dropped.
- Rewrite the tests to call the real _restore_moa_one_shot helper (the
originals re-implemented the restore logic inline, so they passed
regardless of the production code).
The MoA one-shot restore ran inside the try block after
_handle_message_with_agent returned. When that call raised an
exception (agent init failure, interpreter shutdown, OOM), the
restore was skipped and the MoA model override stayed permanently
on _session_model_overrides — silently routing all subsequent
messages through the MoA reference fan-out with no user-visible
indication.
Move the restore to the finally block so it fires on every exit
path (success, exception, interrupt). The restore data lives on
the per-turn event object and would be lost if not consumed here.
The verify-on-stop guard fired too eagerly — including on doc/markdown/skill
edits with nothing to verify, where it pushed a pointless /tmp verification
script. Three changes:
1. Default OFF for new installs: agent.verify_on_stop defaults to false
(was the "auto" surface-aware sentinel). _config_version bumped 30 -> 31.
2. One-time migration (v30 -> v31): existing installs are switched off once,
but only when the value is missing or still the "auto" sentinel — an
explicit true/false the user set is preserved.
3. Path filter: build_verify_on_stop_nudge() now drops documentation/prose
paths (.md/.mdx/.rst/.txt/LICENSE/CHANGELOG/...) so even when explicitly
enabled, a doc-only turn never nudges. Mixed doc+code turns still nudge on
the code paths.
The legacy "auto" sentinel is still honored when set explicitly (ON for
interactive coding surfaces, OFF for messaging). HERMES_VERIFY_ON_STOP env
override unchanged.
Collapse the three near-identical optional-text helpers
(optionalText/optionalBaseUrl/listToText) into one optionalText with a
strip-trailing-slash flag, route listToText + toolsets through the
existing splitCronList, and replace the repeated
typeof x === 'string' ? x : '' ladders with a single asString helper.
Behavior-identical; all 16 vitest cases pass.
/moa no longer does a sticky model switch. It now always runs a single
prompt through the default MoA preset and restores the prior model
afterward; the whole argument is the prompt (no preset-name matching).
To switch to a MoA preset for the session, select it from the model
picker, where presets already surface under a virtual Mixture of Agents
provider on every model-selection surface.
Also fixes#53444: the TUI one-shot only set session[model_override],
which the already-built cached agent ignored, so MoA silently never ran
and the turn used the original model. The TUI now does a real in-place
agent.switch_model() via _apply_model_switch() when a live agent exists
(with a proper restore after the turn), and falls back to a model_override
for lazy/unbuilt sessions.
Removes the redundant sticky-switch branch from the CLI, gateway, and TUI
/moa handlers; updates the command description, usage string, and docs.
Add post_setup() and get_status_config() to the Supermemory memory
provider so `hermes memory setup` and `hermes memory status` print a
one-line connection summary (container, profile fact count,
auto_recall/auto_capture). Point API-key onboarding at the Hermes
connect URL (app.supermemory.ai/integrations?connect=hermes).
Salvage of #52988. Two fixes folded in:
- Test isolation: the new probe/status tests mocked _SupermemoryClient
but not the __import__("supermemory") guard inside
_probe_supermemory_connection, so they passed only where the optional
supermemory package was installed and failed on a clean checkout / CI
(the PR shipped with red CI). Added _stub_supermemory_importable()
mirroring the existing test_is_available_false_when_import_missing
pattern; the suite now passes with supermemory absent.
- post_setup: `if api_key and api_key not in os.environ` checked whether
the key's *value* named an env var (always false in practice). Fixed to
compare the value: `os.environ.get("SUPERMEMORY_API_KEY") != api_key`.
Verified: 38/38 in test_supermemory_provider.py and the full
tests/plugins/memory/ suite green with supermemory not installed.
Closes#52988
Populate `reply_to_message_id`, `reply_to_text`, and
`reply_to_is_own_message` on reaction events so the gateway injects
`[Replying to your previous message: "..."]` when the agent receives
a tapback.
The sidecar now extracts a capped text preview from the hydrated
reaction target (plain text and mixed group messages; null for
attachment/voice-only targets), emitting it as `targetText` in the
NDJSON reaction payload. The Python adapter reads this field and sets
the reply correlation fields on the `MessageEvent`.
v8 made `richlink` outbound-only; inbound rich links now arrive as
plain `text`. Remove the `getBalloonBundleId`/`toRichlinkMessage`
branches from the iMessage mapper patch and update the fixture,
lockfile, and README accordingly.
Update the Photon platform plugin's Node.js sidecar from spectrum-ts
3.1.0 to 7.0.0, which splits the SDK into scoped `@spectrum-ts/*`
packages with `spectrum-ts` as the umbrella re-export.
- Bump exact pin in package.json/package-lock.json to 7.0.0
- Update mixed-attachments patch script to target the new
`@spectrum-ts/imessage/dist/index.js` path and tab-indented output
- Rewrite test fixture to match v7.x mapper shape (tab-indented,
`const ... = async` declarations, single-line builder calls) and
point at `@spectrum-ts/imessage/dist/index.js`
- Update README upgrade guide to document the v5 package split and
the postinstall patch validation step
- Update comments in cli.py and index.mjs to reference v5/v7 changes
A model selected via the CLI (e.g. /model openrouter/<uncurated-name>) was
absent from every model picker — the main picker AND the MoA reference/
aggregator slot pickers — because each provider row only carried its curated
catalog. Inject the current model at the front of its provider's row so it is
selectable and shown everywhere.
The self-hosted OIDC provider fetched the discovery document with a bare
httpx.get(). httpx defaults to follow_redirects=False (unlike curl -L or
the requests library), so when an IDP answers GET
/.well-known/openid-configuration with a 3xx — Authentik canonicalises the
.well-known path, and any IDP behind a reverse proxy doing an http→https
upgrade redirects too — the bare redirect (empty body) tripped the
status != 200 guard and raised 'OIDC discovery returned 302', which
routes.py maps to the provider_unreachable audit event and a 503. The
browser surfaced 'Auth provider self-hosted unreachable'.
The user's smoking gun (curl -o writing zero bytes from inside the
container) is exactly a redirect with no body — the same wall the code hit.
Add follow_redirects=True to the discovery GET only. It's safe: the
issuer-pin check and _require_https_or_loopback still validate the resolved
document and every endpoint, so a redirect can't smuggle in a bad issuer or
a cleartext endpoint. The token/revocation POSTs deliberately keep the
no-follow default (they carry an auth code / refresh token and the endpoint
is already the canonical absolute URL).
Existing discovery tests mocked httpx.get with a canned 200 and never
exercised a real 3xx. Add a regression test that runs a real loopback
server returning a 302 on the .well-known path — fails without the fix
(ProviderError: discovery returned 302), passes with it.
* Return None instead of erroring on drain login failure
* Fix login on drain
* Remove login for drained endpoints flow and clean the code
* chore: drop unrelated credits changes from this PR
* Remove extra comments that were not really necessary
A Radix <Select> renders a blank trigger when its `value` matches no
<SelectItem>. The Settings model pickers built their options solely from
each provider's curated `models` list, so a model added via config that
isn't in that list (e.g. anthropic/claude-opus-4.7 on nous) selected
nothing and showed an empty selector.
Union the active value into the options via a small `withActive` helper,
applied to the main, auxiliary, MoA reference, and MoA aggregator model
selects so the configured model always stays visible and selectable.
The backgrounding-contract test (test_prepare_agent_startup_backgrounds_
blocking_mcp_for_chat) failed intermittently on loaded CI shards: it stubs
tools.mcp_tool.discover_mcp_tools but NOT tools.mcp_oauth, so the background
discovery thread paid the real, cold ~0.75s 'import tools.mcp_oauth' (added by
this PR's _discover_mcp_tools_without_interactive_oauth) before calling the
stubbed discovery. On a slow/loaded runner that import plus thread scheduling
exceeded the 1.0s polling deadline, leaving calls['mcp'] == 0.
Fix: stub tools.mcp_oauth with a nullcontext suppress_interactive_oauth (the
same no-op production falls back to when mcp_oauth is unavailable), so the
test exercises the backgrounding contract without paying an unrelated cold
import in its timing window. Bumped the poll deadline 1.0s -> 3.0s as
belt-and-suspenders. Production behaviour is unchanged; the import cost was
always off the main thread.
Verified: 5/5 pass repeatedly via scripts/run_tests.sh (per-file isolation,
matching CI), ruff clean.
When an MCP server requires OAuth, the interactive `hermes` TUI froze on
startup: background MCP discovery hit the OAuth flow, which on an interactive
TTY spawns a daemon thread doing a blocking `sys.stdin.readline()` (the
"paste the redirect URL" fallback in mcp_oauth._wait_for_callback). That
thread competes with the TUI's own stdin reader for the same terminal, so
keystrokes get swallowed and the TUI appears frozen (up to the 300s OAuth
timeout). Reported symptom: "MCP OAuth: authorization required / Open this URL
... the tui is freezing, not respond to typing."
Add a thread-local `suppress_interactive_oauth()` context manager in
tools/mcp_oauth.py; `_is_interactive()` returns False while it's active, so the
stdin paste-thread and prompt are never created. Background discovery
(hermes_cli/mcp_startup.py, tui_gateway/entry.py) now runs discovery inside
that context, so OAuth-requiring servers soft-skip (raise
OAuthNonInteractiveError, already handled) instead of stealing the TUI's stdin.
A real `hermes mcp login` on the main thread is unaffected (thread-local).
Salvaged from #35945 by @zapabob (authorship preserved via cherry-pick;
resolved a conflict against main's new mcp_discovery_timeout / wait_for_mcp_
discovery refactor, keeping both). Verified E2E: with suppression the paste
prompt is NOT printed and no stdin thread spawns (raises OAuthNonInteractive
soft-skip); without it the prompt shows (the freeze). Mutation-verified
(removing the suppress check in _is_interactive fails the regression test).
76 tests pass, ruff clean.
Closes#35927.
SELF-REVIEW FIX: the original #35945 used threading.local(), which does NOT
propagate to the dedicated mcp-event-loop thread where OAuth actually runs
(discover_mcp_tools dispatches the connect via run_coroutine_threadsafe), so
the suppression was a NO-OP in production (the tests passed only by stubbing
out the cross-thread dispatch). Converted to a contextvars.ContextVar, which
asyncio copies onto the scheduled coroutine — empirically verified suppression
now holds on the mcp-event-loop thread through the real _run_on_mcp_loop path.
Added a cross-thread regression test (fails on threading.local, passes on the
ContextVar) so the no-op can't regress.
get_hermes_dir(new_subpath, old_name) returned the legacy <old_name>/
location as soon as it existed on disk — even when empty. When an empty
legacy stub is created on a profile that already has populated data at
the new consolidated <new_subpath>/ (install scaffolds, profile init, a
stray mkdir, or ensure_hermes_home() recreating legacy dirs), the
resolver silently flipped to the empty legacy dir and the real data
became invisible. No log, no error — the feature behaved as if state was
wiped. Reproduced as a Discord pairing store losing every approved user
when an empty pairing/ shadowed the populated platforms/pairing/.
Resolve the legacy path only when it has content: a populated directory
(any entry) or a non-directory file counts; an empty directory falls
through to the new layout. Inspection failures (PermissionError on
lstat/iterdir, or any OSError short of FileNotFoundError) are treated as
"occupied" so a transient error never orphans legacy data — only a
genuine FileNotFoundError counts as absent. The lstat()-based gate also
fixes the prior exists()/is_dir() path swallowing PermissionError and
mis-reading an unreadable legacy dir as absent.
This hardens all 11+ call sites that share the resolver (pairing,
image/audio/video/document caches, matrix/whatsapp session stores,
vision/credential/tts/browser dirs).
Adds TestGetHermesDir regression coverage (empty/populated/subdir/file/
unreadable/unstatable cases) and updates test_credential_files to
populate its legacy dirs so they still count as content.
Closes#27602Closes#27715
The existing test_chat_gateways_redact_secret_in_provider_error feeds a
provider-error envelope (HTTP 401), which _sanitize_gateway_final_response
rewrites wholesale to a generic category string. That rewrite strips the
secret regardless of whether the redaction layer works, so the test cannot
on its own prove _redact_gateway_user_facing_secrets is exercised.
Add test_chat_gateways_redact_secret_in_non_error_body: ordinary assistant
prose that echoes a bearer token but is NOT a provider-error envelope, so
the rewrite path does not fire and secret redaction is the only defense.
Verified fail-before (token leaks when _GATEWAY_SECRET_PATTERNS is emptied)
and pass-after across whatsapp/slack/signal/matrix, while non-secret prose
is preserved intact.
The Telegram noise/secret filter added in #28533 gated its work on
`_gateway_platform_value(platform) != "telegram"`, so
`_sanitize_gateway_final_response` and `_prepare_gateway_status_message`
only ran for Telegram. Every other human-facing chat surface
(WhatsApp, Discord, Slack, Signal, Matrix, plugin platforms, etc.)
received raw provider-error bodies verbatim — including any leaked
credentials the secret-redaction pass (`sk-…`, `Bearer …`, `gh[pousr]_…`,
`xox[baprs]-…`, `hf_…`, `glpat-…`) was meant to strip.
Invert the gate from a one-platform allowlist into a small
programmatic-surface denylist: only `local`, `api_server`, `webhook`,
and `msgraph_webhook` consume gateway text programmatically and keep raw
status/error text. Every other (chat) surface — including unknown/empty
platform values and on-demand plugin pseudo-members — fails closed to
the redacted, noise-filtered, sanitized path. This widens the same
root-cause fix to both call sites: status callbacks and final replies.
On the desktop Channels / Messaging page, the "Open setup guide" button was
rendered as a bare <a href={platform.docs_url} target="_blank"> with no guard.
Plugin-provided platforms (Microsoft Teams, Google Chat, Line, Raft, Yuanbao,
…) ship an empty docs_url, so the anchor's href was "".
In a packaged build, Electron resolves an empty href against the current
document — the app's own index.html inside the asar bundle — and
shell.openPath then fails with an OS "file not found" dialog. This is exactly
the Windows error reported for Messaging → Teams → Open guide.
Fix (3 changes):
1. fix(desktop) — Only render the "Open setup guide" button when docs_url is
non-empty, and route clicks through openExternalLink so a relative/empty
value can never be treated as a local bundle path. Fixes the whole class
(every plugin platform), not just Teams.
2. fix(messaging) — Give the Teams platform plugin a real docs_url (Microsoft
Teams setup guide) so its card shows a working button instead of nothing.
3. fix(messaging) — Give the Google Chat platform plugin a real docs_url
(Google Chat setup guide) so its card shows a working button instead of
nothing. Originally from #48940; folded in here because that PR's test
was broken (it queried the HTTP endpoint, but google_chat is a dynamic
enum member that only appears after the adapter module is imported).
Test plan:
- apps/desktop — new src/app/messaging/index.test.tsx: button is hidden when
docs_url is empty; a real URL opens via the validated external opener (does
not navigate).
- apps/desktop typecheck (tsc --noEmit) clean.
- backend — test_teams_messaging_metadata_links_setup_guide: the Teams catalog
entry exposes the setup-guide docs_url.
- backend — test_google_chat_messaging_metadata_links_setup_guide: the Google
Chat catalog entry exposes the setup-guide docs_url.
Co-authored-by: xxxigm <tuancanhnguyen706@gmail.com>
Co-authored-by: p-andhika <andhika.prakasiwi@gmail.com>
The back() handler had the same filtered-index drift bug as the Enter
and Ctrl+D transitions: when the user presses Esc to clear an active
filter on the provider stage, providerIdx was reset to 0, losing the
highlighted provider. Apply the same providerIndexAfterClearingFilter
fix as the other three transition paths.
Also adds edge-case tests for the helper: undefined provider, slug not
found, empty rows, and duplicate slug first-match behavior.
Found by hermes-pr-review Phase 2 + hermes-agent-dev 3-agent review.
GatewayRunner._run_agent's run_sync() wrote the per-turn session key to
the process-global os.environ["HERMES_SESSION_KEY"]. Because os.environ
is shared across the whole process, concurrent gateway sessions (e.g.
two Discord threads) clobbered each other's value. A tool worker thread
whose approval contextvar was unset then fell back to os.environ via
get_current_session_key() and read whichever session ran run_sync()
last — routing "Command Approval Required" prompts to the wrong thread.
Session routing is already concurrency-safe via contextvars:
- gateway/session_context.py _SESSION_KEY (set in set_session_vars)
- tools/approval.py _approval_session_key (set via set_current_session_key
right before the agent runs, inherited by tool worker threads)
The only non-test readers of HERMES_SESSION_KEY (tools/approval.py,
tools/terminal_tool.py, tools/kanban_tools.py) all prefer the contextvar
with os.environ as a mere fallback. CLI/cron/TUI set their own os.environ
via separate export paths (e.g. the TUI parent exporting it into the
agent subprocess), so removing this in-process write does not affect them.
Adds regression tests asserting the resolver prefers the contextvar and
does not leak a concurrent session's cleared/clobbered os.environ value.
Closes#24100
Co-authored-by: Yosapol Jitrak <yosapol@jitrak.dev>
- Use os.pathsep instead of literal ':' so Windows paths (C:\dir) and
the Windows separator ';' work correctly.
- Add 9 tests covering multi-root behavior: writes inside first/second
root, writes outside all roots, trailing/leading/double separators,
all-separators edge case, static deny priority, duplicate dedup.
- Update hermes_cli/tips.py tip string to mention multiple paths.
- Update docs to mention os.pathsep / ; on Windows.
Follow-up for salvaged PR #49557.
The OpenAI SDK exposes client.base_url as an httpx.URL object, not str.
The isinstance(live_raw, str) guard made this branch dead code in
production. Use _normalized_runtime_url (which coerces via str()) so
the fallback actually fires.
When parent_agent.base_url still carries a stale OpenRouter URL but the
live OpenAI client already points at local Ollama, subagents were routing
API calls to OpenRouter and failing with HTTP 401. Prefer _client_kwargs
and the mounted client base_url when they disagree with the surface field.
The PR's original refactor commit only replaced the primitives (regex,
is_table_row, split_markdown_table_row) with shared imports but left the
verbatim-copied renderer (_render_table_block_for_telegram) and driver
(_wrap_markdown_tables) in place. Both are logic-identical to the shared
convert_table_to_bullets in gateway/platforms/helpers.py.
Replace both with a direct import alias. _TABLE_SEPARATOR_RE is still
imported separately because it's used by the rich-message routing logic
(lines 1024, 1044) to detect whether content contains tables.
Found by 3-agent parallel code-reuse review.
Replace local _TABLE_SEPARATOR_RE, _is_table_row, and
_split_markdown_table_row with imports from the shared module.
Telegram-specific rendering stays local.
Co-authored-by: Yashiel Sookdeo <yashiel@skyner.co.za>
Discord does not render GFM pipe tables — raw pipe characters display
as garbage text. format_message now rewrites tables into bold-heading +
bullet groups using the shared helpers.
Fixes#21168
Co-authored-by: Yashiel Sookdeo <yashiel@skyner.co.za>
Move table-detection regex, row-splitting, and table-to-bullet
conversion into gateway/platforms/helpers.py so both Discord and
Telegram adapters can share them.
Co-authored-by: Yashiel Sookdeo <yashiel@skyner.co.za>
The desktop MoA settings 'Add preset', 'Set default', and 'Delete' buttons
mutated local React state only and never called the save endpoint, so a newly
constructed preset vanished on refresh. Each now builds the next config and
calls saveMoa() so the change is written to config.yaml via PUT /api/model/moa.
A MoA preset whose reference or aggregator slot points at the moa virtual
provider creates a recursive MoA tree. The runtime guards in moa_loop.py only
surface this mid-turn (references silently skipped, aggregator raises). Reject
it at the config chokepoint (_clean_slot) so it can never be saved, and hide it
from the desktop/dashboard slot pickers so it isn't offered as a dead choice.
preexec_fn=os.setsid runs Python code in the forked child before exec,
which is unsafe in multi-threaded processes (CPython docs). When the
Desktop gateway loads native libraries (onnxruntime, BLAS, provider SDKs)
with active thread pools, the fork can SIGSEGV before the child execs.
Replace all preexec_fn usage with start_new_session=True, which provides
the same setsid/process-group semantics without running Python in the
fork. This is already the pattern used throughout hermes_cli/gateway.py
and hermes_cli/_subprocess_compat.py.
Fixes#46789
_normalize_preset uses bare float() and int() to coerce
reference_temperature, aggregator_temperature, and max_tokens from
config.yaml. When a user hand-edits a non-numeric value (e.g.
max_tokens: "8k" or reference_temperature: "hot"), the coercion raises
ValueError. Since normalize_moa_config runs on every model-selection
and MoA turn (via resolve_moa_preset), the crash is unrecoverable and
blocks all MoA usage until the config is manually fixed.
Replace the bare casts with _coerce_float / _coerce_int helpers that
fall back to the default on TypeError/ValueError instead of raising.
The autonomous self-improvement review fork could still write to a pinned
skill — only external/bundled/hub-installed/protected-builtin skills were
guarded. The curator skips pinned skills from every auto-transition; the
review fork is the same kind of no-user-present actor and must too.
Adds a pin check to _background_review_write_guard so background-origin
edit/patch/delete/write_file/remove_file on a pinned skill are refused.
Stricter than the foreground _pinned_guard (delete-only) by design: with
no user in the loop there is no one to consent to an edit.
Fixes#25839
The verify-on-stop guard (#52296) printed '↻ Verification required before
finishing' to the terminal on every internal nudge turn, adding noise to
CLI/gateway sessions whenever code was edited without fresh passing checks.
Demote the user-facing status emit to a logger.debug breadcrumb — the loop
still nudges the model to verify before finishing, just silently.
The dangerous-command approval layer already blocks `hermes gateway
(stop|restart)`, `pkill/killall hermes|gateway`, and `kill ... $(pgrep ...)`.
A reporter noted on #33071 that the agent can still achieve the same
effect by driving launchd directly against the gateway's service label
(`launchctl stop ai.hermes.gateway`, `launchctl kickstart -k
system/ai.hermes.gateway`, etc.) or by substituting `pidof` for `pgrep`
in the kill-expansion form.
This widens the "Gateway lifecycle protection" block in
`tools/approval.py` to cover both vectors:
- `launchctl (stop|kickstart|bootout|unload|kill|disable|remove)`
scoped to commands that target a Hermes label (`hermes`,
`ai.hermes`). Read-only inspection (`launchctl print …`,
`launchctl list`) and operations against unrelated labels remain
unflagged.
- `kill ... $(pidof …)` and the backtick form, alongside the existing
`pgrep` expansion. `pidof` is the BSD/Linux equivalent and is
equally opaque to the `(pkill|killall) … hermes` name pattern.
Intentionally left out of scope: plain `kill -TERM <numeric_pid>` with
a PID looked up out-of-band. Catching that would require runtime PID
state and would break the existing
`TestPgrepKillExpansion::test_safe_kill_pid_not_flagged` contract,
which guarantees that a plain literal-PID `kill 12345` stays safe.
Embeds reach out to third parties on render, so default to a placeholder that
mirrors the tool-approval UX: "Load <service>" (this embed) or "Always allow
<service>" (persisted). A desktop-local store ($embedMode ask|always|off +
per-service allowlist) gates the fetch with zero gateway round-trip; an
Appearance setting controls the global default. Local renderers (mermaid, svg,
alerts) are never gated. Addresses review feedback on outbound third-party
requests.
Natural-language skill search returned a short, arbitrary list and never
surfaced NVIDIA (or OpenAI/Anthropic/HuggingFace) skills. Two causes:
1. The runtime index collapses every GitHub tap into source="github", so
there was no way to find or filter by provider at the CLI — the per-tap
identity only existed in the docs-site catalog.
2. HermesIndexSource.search matched only name/description/tags (not the
identifier or provider) and broke at the first `limit` hits in raw index
order, burying the most relevant skills. `search` also defaulted to
--limit 10 against an 86k-entry catalog.
Changes:
- GitHubSource stamps a per-tap provider label (extra.provider) on each
skill via github_provider_for(); source stays "github" so dedup/floor/
index-skip logic is untouched. Flows into the built index.
- HermesIndexSource.search now matches identifier + provider too, and
collect-then-ranks (exact > prefix > whole-word > substring) instead of
break-at-limit.
- --source nvidia|openai|anthropic|huggingface|voltagent|gstack|minimax
provider filters for browse/search (narrows merged results by provider).
- search --limit default 10 -> 25; table Source column shows the provider
label for github skills.
Tested: 181 unit tests pass; E2E against the live runtime index confirms
'nvidia'/'cuda' searches now surface NVIDIA-provider skills and
--source nvidia narrows to exactly the NVIDIA catalog.
The post-update gateway restart path relaunched the gateway with the
venv's console `python.exe` (via `get_python_path()` in
`_gateway_run_args_for_profile`). On Windows this leaves a terminal
window open permanently: uv's `venv\Scripts\python.exe` is a launcher
shim that re-execs the *base* console interpreter, which allocates its
own conhost — and `CREATE_NO_WINDOW` cannot suppress that second window.
The clean-start path (`_spawn_detached`) already dodges this by routing
through `_resolve_detached_python` to use the windowless base
`pythonw.exe`; the restart watcher did not.
Symptom (reported on Windows 11): after an in-app GUI update, a console
window for the gateway stays open and never closes. Confirmed on the
reporter's box — the running gateway was `python.exe ... gateway run
--replace` with a live conhost child and the foreground "Press Ctrl+C to
stop" banner, born exactly at the update's "Restarting Windows gateway"
log line.
Fix:
- Add `gateway_windows.windowless_gateway_restart_spec(run_argv)` which
rewrites a console-python gateway argv into the windowless `pythonw.exe`
equivalent and returns the cwd + env overlay (VIRTUAL_ENV / PYTHONPATH /
HERMES_HOME) the base interpreter needs to import `hermes_cli` without
the venv launcher's site config. No-op on POSIX.
- `_spawn_gateway_restart_watcher` now applies that rewrite on Windows and
threads cwd= / env= into the inlined respawn Popen. Covers both restart
entry points (`launch_detached_profile_gateway_restart` and
`launch_detached_gateway_restart_by_cmdline`). CREATE_NO_WINDOW |
DETACHED_PROCESS | CREATE_BREAKAWAY_FROM_JOB and the breakaway-denied
fallback are all preserved.
Verified E2E on a real Windows 11 box: drove the actual watcher against a
dummy old-pid; the respawned gateway came up as `pythonw.exe` (zero
console python, no conhost child) and booted fully (housekeeping + kanban
dispatcher started → imports resolved under the base interpreter).
Tests: TestWindowlessGatewayRestartSpec (behavior) +
TestGatewayDetachedWatcherWindowsFlags regression assert. Pre-existing
Linux-only failures on a Windows host (SIGKILL, systemd, docker-root)
confirmed identical on the bare base.
Add a deprecation banner to the top of the dedicated Nix & NixOS setup
guide and consistency notes at the Nix sections of installation, updating,
and the plugin-distribution guide. Nix is now best-effort only; the
supported install paths are the curl|bash installer, Docker, and Windows.
On macOS, terminal(background=true) silently failed: the process returned a
session_id and exit_code=0 but the command never ran (empty stdout, no side
effects). Root cause is two interacting issues:
1. _find_shell was aliased to _find_bash, which prefers `shutil.which("bash")`
→ /bin/bash (GNU bash 3.2, still shipped on macOS) over $SHELL (/bin/zsh).
2. process_registry.spawn_local runs [shell, "-lic", "set +m; <cmd>"] with
stdin=/dev/null. bash 3.2 as a login shell sources ~/.bash_profile, which on
many macOS setups contains `exec /bin/zsh -l`; that exec replaces bash but
drops the -c argument, so the command is swallowed (exit 0, no output).
Decouple _find_shell from _find_bash: _find_shell now prefers the user's
configured $SHELL on POSIX (the shell they actually log in with), falling back
to _find_bash when $SHELL is unset/missing. _find_bash is unchanged, so callers
that genuinely need bash (e.g. the _run_bash login-shell snapshot) keep bash
semantics. zsh handles -lic correctly even with redirected stdin.
Salvaged from #42219 by @liuhao1024 (authorship preserved via cherry-pick).
On top of the original (8 unit tests covering $SHELL-set/unset/missing/empty,
Windows-ignores-$SHELL, _find_bash-unchanged), added an E2E regression test
that reproduces the real bash-3.2 login-shell swallow (exit 0 / no file) and
asserts the shell _find_shell selects actually executes a -lic background
command. Mutation-verified: reverting _find_shell to the bash alias fails the
$SHELL-preference test. Bug reproduced directly: /bin/bash 3.2 -lic with a
.bash_profile->exec-zsh creates no file; zsh -lic does.
Closes#42203. Supersedes #42290.
When a Hermes-managed node/npm/npx shim exists but fails --version, redownload
the pinned nodejs.org bundle under HERMES_HOME/node and retry. Do not fall
back to system npm on PATH when a managed tree is present.
POSIX heal probes node, npm, and npx (npm can break while node still runs).
A stale or partial Hermes-managed Node tree under the active HERMES_HOME
can leave bin/npm behind while lib/cli.js is missing. File-existence checks
alone made hermes update pick that broken npm and skip healthy system npm
on PATH. Probe managed candidates with --version before preferring them.
projects.db (per-profile project store) and kanban.db were missing from
_QUICK_STATE_FILES, so the pre-update quick snapshot never backed them up.
On a desktop upgrade, when the update flow removes/replaces the file and the
post-update schema-init re-creates an empty one, all user-created projects,
folder mappings, the active-project pointer, kanban board bindings, and tasks
vanish silently — no error.
Add the per-profile user-created stores to the snapshot set:
- projects.db — project store
- response_store.db — gateway conversation history / tool payloads (WAL)
- memory_store.db — holographic memory facts/entities (WAL)
- verification_evidence.db — agent verification audit trail
- kanban.db — default board (back-compat <root>/kanban.db)
- kanban/boards — non-default boards (<root>/kanban/boards/<slug>/kanban.db
+ metadata); workspaces/ and attachments/ subtrees
are skipped as large + regenerable.
Also: the directory-branch of create_quick_snapshot now routes *.db through the
WAL-safe _safe_copy_db (SQLite backup() API), matching the top-level file path —
previously a non-default board DB with an open WAL could be copied inconsistently.
Salvaged from #52930 by @0xDevNinja (authorship preserved via cherry-pick).
On top of the original (which covered only projects.db + the default kanban.db),
this adds: non-default-board coverage, the three sibling per-profile DBs that
meet the same upgrade-wipe criteria, WAL-safe directory copies, and a
workspaces/attachments skip to avoid snapshot bloat (×20 retained). 8 tests,
all mutation-verified; E2E verified snapshot→wipe→restore preserves all six
store types on the real code path.
Closes#52889. Supersedes #52930.
The external-drain marker .drain_request.json is written under HERMES_HOME,
which on Hermes Cloud is a persistent Fly volume (/opt/data). A begin-drain
marker therefore SURVIVES the post-update machine restart. But the disruptive
lifecycle actions a drain protects (auto-update / image migrate / env edit /
profile change) all restart the machine — which is exactly the signal the drain
is over. The freshly-restarted gateway re-read the orphaned marker on its
startup reconcile and parked itself back in 'draining', refusing every new turn
indefinitely (NS-570: ~52 min until manually cleared).
Fix: stamp the marker with an identity of THIS container/VM instantiation
(kernel boot_id + PID 1 start time, read from /proc) and treat a marker whose
epoch differs from the current instantiation as absent. A deliberate restart →
new PID 1 → new epoch → stale marker ignored → gateway boots 'running'. A marker
written during the current instantiation (the live drain) still matches; an s6
respawn of just the gateway (PID 1/init unchanged) keeps the same epoch, so an
in-flight drain is still honoured (D4a reversibility preserved).
The staleness check is lenient and never fail-closed: a legacy marker with no
epoch, a corrupt/contentless marker, or an environment with no /proc (epoch
unavailable) all degrade to the original presence-only behaviour. NAS is
untouched — it only ever POSTs begin/cancel-drain over HTTP; the marker file is
purely gateway-internal IPC.
The fix is entirely within gateway/drain_control.py; the watcher and the
dashboard endpoint go through the same drain_requested()/write_drain_request()
chokepoints and need no functional change.
## Description
On macOS 26.x, `launchctl bootstrap` and `launchctl kickstart` return exit code 5 ("Input/output error"), which Hermes already anticipates and handles by spawning a detached fallback process. However, the gateway status reporting is ambiguous:
- `gateway status` says "Gateway service is loaded" (because `launchctl list` returns exit 0)
- But `launchctl print` shows `state = not running` — launchd isn't actually supervising anything
- The detached fallback PID running is invisible to the status command
- Users can't tell whether auto-start at login and auto-restart on crash are available
### Root Cause
Two problems in `hermes_cli/gateway.py`:
1. **`_probe_launchd_service_running()`** (line 1067): Determined launchd service liveness solely by `launchctl list <label>` exit code. On macOS 26, this returns 0 even when the service is only *registered* but not running (output lacks a `"PID"` field). This caused `GatewayRuntimeSnapshot.service_running = True` incorrectly, which suppressed the process/service mismatch warning.
2. **`launchd_status()`** (line 3569): Used the same binary "loaded/not loaded" check without inspecting whether launchd actually has a PID, whether a detached fallback is running, or whether auto-start/restart are available.
### Changes
**`hermes_cli/gateway.py`:**
1. **New `_parse_launchd_pid_from_list_output()` helper** — Extracts the PID from `launchctl list` output. When launchd is actively supervising, the output includes `"PID" = <number>;`. When only registered but not running, no PID field is present.
2. **Fixed `_probe_launchd_service_running()`** — Now requires a PID in the `launchctl list` output to confirm launchd is actually supervising. This correctly sets `service_running = False` when launchd has the service registered but `state = not running`, which triggers the existing process/service mismatch detection.
3. **Reworked `launchd_status()`** — Reports clearly separated information:
- LaunchAgent plist currentness (stale or current)
- Whether launchd is actively supervising (with PID)
- Whether a detached fallback PID is running
- Whether auto-start at login and auto-restart on crash are available
- When launchd supervision is known to be unavailable, explains why
4. **Persistent unsupported marker** (`~/.hermes/.gateway-launchd-unsupported`) — Written when `_launchd_fallback_to_detached()` is called (launchd exit 5/125). Allows `launchd_status()` to explain *why* launchd can't supervise even when no fallback process is currently running. Cleared automatically when a future bootstrap/kickstart succeeds (e.g., after an OS update fixes the issue).
5. **Updated `_print_gateway_process_mismatch()`** — Distinguishes the managed detached fallback from a genuinely manual `nohup hermes gateway run`, providing accurate guidance for each case.
### Status Output Examples
**Before** (macOS 26, fallback active):
```
Launchd plist: ~/Library/LaunchAgents/ai.hermes.gateway.plist
✓ Service definition matches the current Hermes install
✓ Gateway service is loaded
{
"Label" = "ai.hermes.gateway";
"OnDemand" = true;
...
};
```
**After** (macOS 26, fallback active):
```
Launchd plist: ~/Library/LaunchAgents/ai.hermes.gateway.plist
✓ Service definition matches the current Hermes install
⚠ Gateway service is registered but launchd is not supervising it
launchd cannot manage the gateway on this macOS version.
✓ Detached fallback process is running (PID 12345)
Cron jobs will fire. Stop with: hermes gateway stop
⚠ Auto-start at login and auto-restart on crash are NOT available.
```
**After** (normal launchd supervision):
```
Launchd plist: ~/Library/LaunchAgents/ai.hermes.gateway.plist
✓ Service definition matches the current Hermes install
✓ Gateway is supervised by launchd (PID 12345)
Auto-start at login and auto-restart on crash are available.
```
### Tests
Updated 5 existing tests and added 11 new tests in `tests/hermes_cli/test_gateway_service.py`:
- PID parsing from `launchctl list` output (with PID, without PID, empty, unquoted PID)
- `_probe_launchd_service_running()` requires PID presence
- Unsupport marker lifecycle (write, clear, persist across fallback)
- Marker cleared on successful bootstrap
- `launchd_status()` reporting: supervised, fallback-running, fallback-unavailable
- Existing fallback tests now verify marker creation
### Related Issues
- Issue #23387 (original macOS 26 launchd workaround)
- Issue #42524 (this issue)
A clarify/approval/sudo/secret prompt blocks the turn on the user, but the UI
treated it as an in-flight turn: the "thinking" timer kept ticking and Esc
interrupted the run — discarding a question you might want to come back to. Add
$activeSessionAwaitingInput (the pet's awaitingInput concept, scoped to the
active session) and use it to suppress the stall indicator and disarm Esc while a
prompt waits. Clear the session's prompts (and needsInput) on Stop and on turn
end so a resolved/aborted turn can't leave a dead panel or a stuck "needs input"
dot.
The inline clarify panel used its own card tokens, an animated ring, and
oversized spacing — out of step with every other tool row. Rebuild it on the
shared --ui-*/--conversation-* tokens: a compact panel, letter-key badges
(A/B/C…) that double as a/b/c… shortcuts, an inline content-sizing "Other" field
(CSS field-sizing — no view swap, no layout shift on focus), and a Continue
button so picking an option selects rather than auto-sends. Selection lives on
the letter badge alone (solid primary; outlined while Other is focused-but-empty).
Also settle the panel into the standard tool block once the turn stops running,
so a stopped turn no longer strands a live, unanswerable prompt.
Add a content-agnostic Zoomable primitive (useZoomPan hook + overlay viewer):
click to open full-screen, wheel-zoom toward the cursor, drag to pan, toolbar
zoom/reset, and an optional copy action. Wire Mermaid diagrams into it with
copy-as-PNG; reusable for other inline content later.
A config migration (or hand-edit) that leaves an invalid toolset name in
`platform_toolsets` — e.g. the #38798 corruption that rewrote `hermes-cli` to
the non-existent `hermes` — silently disabled all affected tools:
resolve_toolset() returns [] for an unknown name, so the agent quietly lost its
tools with no error, warning, or log entry and degraded to text-only replies.
Surface it loudly at two points:
- After migration (migrate_config): validate platform_toolsets and record/print
a warning per unknown name, with a `hermes-<platform>` suggestion when that
would have been valid (the exact #38798 shape).
- At runtime (_get_platform_tools): if a platform was explicitly configured but
every toolset name is invalid, log a warning when tools are resolved for a
session — so an ALREADY-corrupted config is caught at startup, not only on the
next `hermes update`.
Logic lives in a new pure, side-effect-free helper (toolset_validation.py) with
validate_toolset injected, so it is unit-testable without the tool registry.
Note: the original v25→v26 migration that caused the corruption no longer
exists (config format is now v30; no migration step rewrites toolset names).
This change is the durable defense against the silent-failure mode regardless
of cause, matching the issue's "Expected: log a warning".
Salvaged from #39207 by @lEWFkRAD (authorship preserved via cherry-pick).
Tests: 9 helper cases (incl. the #38798 corruption shape, mixed valid/invalid,
zero-tools state, non-dict/scalar/non-string) + a runtime caplog test — both the
helper warning and the runtime guard mutation-verified to fail without the fix.
Closes#38798. Supersedes #39581 (prevent-in-v25→v26 — that path is gone),
#41006 / #40208 (repair-migration for already-corrupted configs).
Wire the embeds module into the markdown surface: bare provider autolinks unfurl
to inline embeds, ```mermaid/```svg fences route to the rich renderers, and
`> [!NOTE]`-style blockquotes become alert callouts. Labeled links stay plain.
Per-kind renderers, each a lazy split chunk: plain-iframe video/maps (wheel
chains to the transcript; maps gate scroll behind ⌘), the in-document
blockquote-script path for X/Instagram, the dark Spotify player, and the
YouTube iframe. Adds Mermaid and DOMPurify-sanitised SVG fences and GFM alert
callouts, all sized to 33dvh and theme-matched to avoid white color-scheme
artifacts. Main-process stamps a Referer on YouTube embed requests.
Pure, synchronous URL→descriptor matchers for YouTube, Vimeo, Instagram,
Pinterest, TikTok, X, Spotify, Google Maps and OpenStreetMap, plus the shared
embed primitives (error boundary, fail card, escape-html, dark-mode hook,
sizing token). Declares the mermaid + dompurify deps used by the fenced
renderers.
The cron runtime tripwire (_scan_cron_prompt) used a 10-char invisible-unicode
set while the install-time scanner (threat_patterns.INVISIBLE_CHARS) flags 17.
The cron-local set was missing U+2062-U+2064 (invisible math operators) and
U+2066-U+2069 (directional isolates), so a directive obfuscated with one of
those codepoints (e.g. "ig<U+2063>nore all previous instructions") slipped past
the runtime cron gate while being caught at install time.
Import the canonical set so the cron tripwire and install scanner can't drift
apart again. Emoji-ZWJ protection (_zwj_has_emoji_neighbour) is unchanged.
Fixes#35075
Co-authored-by: rlaope <piyrw9754@gmail.com>
Replies on WhatsApp Cloud arrived at the agent with reply_to_id set but
reply_to_text=None, so run.py never injected the "[Replying to: ...]"
disambiguation prefix (it gates on reply_to_text). Meta's webhook context
object carries only the quoted message's id, never its text.
Index (chat_id, wamid) -> text in rich_sent_store on every inbound message
and every outbound text send -- the same store that solved the identical
Telegram rich-send problem -- then look up the quoted text in
_build_message_event_from_cloud and populate reply_to_text plus
reply_to_is_own_message, derived from context.from versus the business
number.
Tasks 2.1 + 2.2 + 2.3 of the safe-shutdown plan — the reversible
quiesce-without-restart machinery NAS drives during a lifecycle action (D4a).
These ship together because the endpoint, the control channel, and the gateway
state machine are one coherent slice.
2.2 — control channel (gateway/drain_control.py, new):
The dashboard has no HTTP path into a running gateway (guardrails: "there is NO
external control channel into a running gateway"); restart/drain is driven only
by markers the gateway reacts to. So begin/cancel-drain writes/removes a
presence-based marker .drain_request.json (HERMES_HOME-scoped, atomic write,
never-raises read; a corrupt marker reads as present-contentless → fail-safe
toward quiescing). This is Q-B option A.
2.2 — gateway state machine (gateway/run.py):
- _external_drain_active flag, DISTINCT from the shutdown _draining flag: this
one does NOT exit the process and is fully reversible.
- _enter_external_drain / _exit_external_drain: idempotent transitions that
flip gateway_state→draining / →running via _update_runtime_status (preserving
the live active_agents count). exit refuses to revert to running during a
real shutdown or after the loop stops (shutdown wins).
- _drain_control_watcher: 1s background task (modelled on _handoff_watcher)
reconciling accept-state with the marker; honours a marker that survived a
restart on its first tick. Registered alongside the other watchers in start.
- New-turn accept gate in _handle_message, placed BEFORE the session-slot
claim: when draining, refuse to START a new turn (so active_agents can only
fall → no TOCTOU race), while in-flight turns finish untouched. Internal/
system events (restart-recovery replays, bg-process completions) bypass it.
2.1 — endpoint (hermes_cli/web_server.py):
POST /api/gateway/drain {action: drain|cancel}. Authenticated by the Task-2.0a
token seam (the drain plugin registered this exact path as a token route);
attributes the request to the verified token principal. Begin writes the
marker, cancel removes it — the gateway process owns the actual transition.
Force-override (D6) is NOT here; it maps onto the existing immediate
/api/gateway/restart force path.
Tests (mocked — necessary-not-sufficient; the HARD live gate Q-B is next):
- tests/gateway/test_external_drain_control.py — marker contract (write/clear/
read/corrupt/atomic), state machine (enter/exit/idempotency/shutdown-wins/
loop-stopped), watcher reconcile-enter-then-exit, new-turn refusal, and
in-flight-not-interrupted. 15 tests.
- tests/hermes_cli/test_web_server.py — /api/gateway/drain begin/default-begin/
cancel/cancel-idempotent/bad-action-400. 6 tests.
- dashboard.drain_auth config section already added in 2.0b commit.
All touched suites green: 301 (gateway+auth) + 9 (web_server endpoints) passed.
Intentionally deferred:
- HARD live-validation gate (Q-B): real isolated `hermes gateway run`, drive a
real begin-drain marker, prove the 5-point checklist a–e.
- Spec-doc status flip + Phase-2 PR.
Build status: external-drain, restart-drain, status, dashboard-auth, drain-plugin,
token-auth, and web_server-endpoint suites green.
Task 2.0b: the concrete shared-bearer-secret auth provider, the FIRST consumer
of the generic token-auth capability (Task 2.0a). Implements decisions.md Q-A.
plugins/dashboard_auth/drain/ (bundled, discovered like dashboard_auth/basic):
- DrainSecretProvider: non-interactive provider, supports_token=True. Verifies
an inbound Authorization bearer token against a per-agent shared secret with
hmac.compare_digest (constant-time, no timing oracle) and, on a match,
vouches for the caller as the "drain-control" principal scoped to "drain".
The five interactive ABC methods raise NotImplementedError; verify_session
returns None (stacks harmlessly in the cookie-verify loop).
- assess_secret_strength(): fail-closed entropy gate. Rejects secrets shorter
than 43 url-safe-b64 chars (~256 bits), with < 16 distinct characters, or
below 128 bits Shannon entropy — so a weak/structured/repeated secret can
never be silently accepted. Enforced both at register() (friendly skip
reason) and in __init__ (raises — defence in depth).
- register(ctx): no-op + skip reason when HERMES_DASHBOARD_DRAIN_SECRET is
unset; rejects a weak secret fail-closed (drain endpoint stays gated). On a
strong secret, registers the provider AND opts /api/gateway/drain into the
generic token-auth seam via register_token_route().
Config: the secret is a CREDENTIAL → carried via HERMES_DASHBOARD_DRAIN_SECRET
(per-agent, provisioned by NAS at deploy). Behavioural knobs only
(dashboard.drain_auth.{scope,min_secret_chars}) live in config.yaml — added to
DEFAULT_CONFIG with the .env-is-for-secrets rationale documented inline.
Tests: tests/plugins/dashboard_auth/test_drain_provider.py — entropy gate
(strong pass; empty/short/repeated/few-distinct/custom-min reject), verify_token
(match → scoped principal, wrong/empty → None, custom scope), protocol
compliance, interactive-methods-raise, and register() (skip-no-secret,
fail-closed-weak-secret, strong-env-secret registers + route opt-in, config
scope + min_secret_chars). 21 new tests; drain + token-auth suites 44 passed.
Verified the plugin is discovered as dashboard_auth/drain alongside basic/nous.
Intentionally deferred:
- The begin/cancel-drain endpoint handler itself — Task 2.1.
- The dashboard→gateway control channel — Task 2.2.
Build status: dashboard-auth + drain-plugin suites green.
Task 2.0a of the safe-shutdown drain-coordination plan. Widens the dashboard
auth framework GENERICALLY to support non-interactive (service-to-service)
bearer-token auth, mirroring the existing supports_password precedent. This is
a reusable capability — any future machine-credential provider plugs in without
core changes (decisions.md Q-C). The drain bearer-secret plugin (Task 2.0b) is
the first consumer, not the definition.
- base.py: add TokenPrincipal dataclass (the token analog of Session) +
supports_token capability flag + verify_token() on the ABC (default raises
NotImplementedError so a misconfigured provider fails loud). Contract mirrors
verify_session stacking: return None for unrecognised tokens (never raise),
raise ProviderError only on a genuine backing-store outage.
- registry.py: list_token_providers() — the supports_token subset, in
registration order. Empty when none registered (token routes fail closed).
- token_auth.py (new): route-agnostic seam. Routes opt in via
register_token_route(exact path); token_auth_middleware owns the auth
decision for those routes only — authenticate via stacked providers, attach
request.state.token_principal + token_authenticated, pass through. 401 on
missing/unrecognised token, 503 when a provider was unreachable, untouched
passthrough for non-token routes. Fails closed (never open).
- web_server.py: install the seam OUTERMOST (registered last → runs first).
Both downstream gates (legacy auth_middleware + gated_auth_middleware) honour
request.state.token_authenticated and skip enforcement, so a token-authed
service request is never bounced to /login.
- audit.py: TOKEN_AUTH_SUCCESS / TOKEN_AUTH_FAILURE events.
Tests: tests/hermes_cli/test_dashboard_token_auth.py — ABC flag default,
verify_token NotImplementedError, registry filter, bearer extraction
(case-insensitive scheme, malformed/non-bearer → ""), provider stacking
(first-match-wins, unreachable-remembered, unreachable-then-valid, buggy
provider doesn't crash the gate), and the seam's passthrough/401/503/
fail-closed behaviour. 29 new tests; full dashboard-auth suite 169 passed.
Intentionally deferred:
- The concrete shared-bearer-secret provider plugin — Task 2.0b.
- The begin/cancel-drain endpoint that registers itself as a token route —
Task 2.1.
Build status: dashboard-auth + plugin-hook suites green.
The known_c2_framework threat pattern included 'praxis' in its
alternation alongside genuine offensive-security tool brands (Cobalt
Strike, Sliver, Havoc, Mythic, Metasploit, Brainworm). Unlike those
distinctive brand names, 'praxis' is a common English word (Greek for
practice/action) and a legitimate agent name, so any context file that
mentioned an agent named Praxis matched at 'context' scope and the whole
AGENTS.md / SOUL.md was replaced with a [BLOCKED] placeholder before it
reached the system prompt.
Remove 'praxis' from the alternation and add a guard comment: every
token in this list must be a distinctive tool brand, not a common word.
Real C2 brands still fire.
The new _maybe_flag_poisoned_client tests built a provider via
get_or_build_provider without an interactive stdin. Under the hermetic
test env (no TTY, no cached tokens), the non-interactive guard in
mcp_oauth_manager._make_provider raised OAuthNonInteractiveError before
the provider was built, failing 6 tests in CI parity (they passed
locally where stdin was a TTY).
Thread monkeypatch into _provider_with_token_endpoint and present an
interactive stdin, matching the sibling test_manager_builds_hermes_provider_subclass.
Fixes#36767.
Two complementary recoveries for the recurring "delete three cache files and
re-auth by hand" ritual when an MCP server's dynamically-registered OAuth
client goes dead server-side (IdP redeploy / DB wipe / rebrand):
- Auto-heal (token-endpoint subset): HermesMCPOAuthProvider now sniffs
auth-flow responses and, on a 400/401 `invalid_client` from the discovered
token endpoint, backs up + deletes `<server>.client.json` and `.meta.json`
and clears the in-memory client so the SDK re-runs RFC 7591 dynamic client
registration on the next flow. Conservative by construction: only
dynamically-registered (non config-supplied) clients, only the token
endpoint, only on a word-boundary `invalid_client` match (so RFC 7591's
`invalid_client_metadata` does not trip it); best-effort so a miss never
breaks the live flow. Covers both code-exchange and refresh when the token
endpoint was discovered. Tokens are preserved.
- `hermes mcp reauth [<name>|--all]`: the reporter's primary symptom — the
IdP's in-browser "Redirect URI Mismatch" — produces no HTTP signal (the SDK
only sees a callback timeout), so it cannot be auto-detected. The new
command re-auths one or ALL `auth: oauth` servers, serially: one browser
flow at a time, which also fixes the startup popup storm when several
servers are stale at once. Single-server reauth is factored out of
`mcp login` and shared.
Tests: +14 (poison helper x2; token-endpoint detection x5 incl. wrong-endpoint,
success-response, pre-registered, and invalid_client_metadata negative guards;
a bridge integration test driving the real async_auth_flow generator to prove
the detection hook preserves the bidirectional asend() forwarding contract;
reauth CLI x6). Verified against the pinned mcp==1.26.0: scripts/run_tests.sh
122/122 green for the touched suites; check-windows-footguns.py and ruff clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Cut over the agent half of Shape A (D-Q1.5a/b.1/c) to front a SET of platforms on
one relay WS:
- relay_platform_identities() parses GATEWAY_RELAY_PLATFORMS (list) +
GATEWAY_RELAY_BOT_IDS (JSON keyed map {platform:{botId,username?}}). Cut over
from the scalar GATEWAY_RELAY_PLATFORM/_BOT_ID (no fallback, D-Q1.5c).
- self_provision_relay() loops one /relay/provision per platform under one
gatewayId+secret, partial-failure-tolerant.
- WebSocketRelayTransport takes the identity SET, sends one hello per identity
(connector accumulates the advertised set), and stamps the per-frame
OutboundFrame.platform + its matching advertised botId on outbound.
- RelayAdapter remembers each chat's underlying source.platform (mirroring the
existing guild/dm scope capture) and tags the reply's egress platform.
- send_relay_policy() declares one relevance policy per fronted platform (the
connector keys policy by (tenant,platform,instanceId)).
Single-platform deploys are byte-identical on the wire (1-element list, no per-frame
tag -> connector session-default fallback). typecheck/ruff clean; relay unit 221 pass
(+10 new); all 15 cross-repo E2E drivers green vs connector origin/main.
The gateway reconnect watcher (gateway/run.py) recovers a platform after a
fatal adapter error by building a fresh adapter and calling
connect(is_reconnect=True). Every BasePlatformAdapter implements
connect(*, is_reconnect: bool = False) for this — except RelayAdapter, whose
connect() was bare. So the watcher's recovery path raised:
TypeError: connect() got an unexpected keyword argument 'is_reconnect'
Observed live on a hosted staging agent: after a fatal relay adapter error the
watcher could never re-establish relay, so the shared-bot inbound never reached
the gateway and Discord DMs stopped (dashboard surfaced the TypeError).
Relay deliberately ignores the flag: the #46621 server-side-queue-preservation
concern doesn't apply, because relay's outage buffer is the connector's durable
buffer (replayed on the transport's re-handshake), not a gateway-side queue the
adapter owns. Routine WS drops are already handled by the transport's own
reconnect supervisor (WebSocketRelayTransport, reconnect=True); the watcher path
is fatal-error recovery, and the fatal handler disconnect()s the old adapter
(cancelling its supervisor) before a fresh adapter+transport is built, so there
is no double-dial.
Adds two regression tests (both proven red without the fix): connect(is_reconnect=True)
reaches the same transport-less RuntimeError instead of TypeError, and the
signature matches BasePlatformAdapter.connect.
Bring apps/desktop and ui-tui to a clean state for typecheck, eslint,
and prettier:
- Run prettier across both trees (printWidth/wrap drift; prettier is not
CI-enforced for these JS projects, so main had accumulated drift).
- Apply eslint --fix for padding-line-between-statements and perfectionist
import/export sorting.
- Manual fixes for non-auto-fixable rules:
- remove unused node:net import in electron/main.cjs (uses Electron net)
- replace inline `typeof import(...)` annotations with top-level
`import type * as EnvModule` in two ui-tui test files
- scoped eslint-disable no-control-regex on intentional sentinel/ANSI
regexes (mathUnicode.ts, text.ts)
- resolve react-hooks/exhaustive-deps per-case: correct swapped/missing
deps, collapse redundant session.* members, and justified disables on
settings mount-only data-load effects to preserve run-once behavior
No behavior changes; test pass/fail counts are unchanged from the main
baseline.
When operator config has provider=anthropic with model.base_url pointing
at a non-Anthropic host (e.g. https://openrouter.ai/api/v1 with provider=anthropic),
the auxiliary Anthropic path was unconditionally applying that override.
Main-session traffic routed correctly because the main path attaches the
right credential for the actual destination, but every side-channel call
(memory extractors, reflection, vision, title generation, janus
extractor/promise) sent ANTHROPIC_API_KEY to the foreign host and 401'd.
Gate the override on hostname == api.anthropic.com. Operators routing main
through a non-Anthropic provider must use that provider's own auxiliary
client; the Anthropic aux path now stays pointed at api.anthropic.com.
Regression tests cover openrouter, openai, anthropic-with-path, empty, and
anthropic-default-base_url cases.
Alt+wheel now scales about the pixel under the pointer instead of growing from a
corner, so the pet stays put under the cursor instead of running away. In-window
shifts its top-left; the overlay repositions its OS window (cursor-anchored on
wheel, bottom-center for slider-driven changes).
Hold Alt/Option and scroll over the mascot to resize it (same on Mac and
Windows); the modifier keeps a plain scroll passing through to the page. The
gesture drives the same `display.pet.scale` path as the settings slider.
The popped-out overlay grows its OS window to fit the pet at any scale (anchored
bottom-center) so the sprite is never clipped by the window edge, and the
in-window pet re-clamps against its actual size so growing near an edge can't
crop it. Also makes the overlay click-through per-pixel: only solid sprite
pixels (plus bubble / mail button) are interactive, transparent margins pass
clicks through.
Ensure TUI/desktop stop targets the actual conversation thread and cancels any queued next prompt, including the lazy agent-start window, so a stopped session cannot keep running or restart itself.
Wire get_reasoning_stale_timeout_floor() into both stale detectors so known
reasoning models (Nemotron 3 Ultra, OpenAI o1/o3, Opus 4.x thinking, DeepSeek
R1, Qwen QwQ, Grok reasoning) tolerate multi-minute thinking phases instead of
the upstream gateway idle-killing the socket (BrokenPipeError) before first
token. Applied as max(default, floor) — never overrides explicit user config,
never lowers an existing threshold.
The reasoning_timeouts.py allowlist module already landed on main via #52795,
so this salvage carries only the wiring + tests (the duplicate module and the
stale-base MoA reverts from the original PR branch are dropped).
Salvaged from #52238. Fixes#52217.
The salvaged #51875 added a background-review write guard in skill_manage
that refuses mutations to skills.external_dirs skills — but it only fires
when is_background_review() is true. The curator's LLM review fork ran with
the default _memory_write_origin='assistant_tool', so the guard never
triggered during the exact curation pass it exists to protect against
(GH-47688).
- Set _memory_write_origin='background_review' on the curator review fork so
turn_context binds it onto the write-origin ContextVar and the guard fires.
- Add a regression test asserting the fork runs under the background_review
origin (the invariant linking the fork to the guard).
- AUTHOR_MAP: map yu-xin-c for the salvaged commit.
Force redact_sensitive_text(force=True) on the browser_type text arg so
recognized credentials (API keys, tokens, JWTs) are masked in tool
progress, previews, callbacks, and return payloads even when the global
security.redact_secrets opt-out is set — a typed credential reaching chat
history is a security boundary, not log hygiene. Normal typed text matches
no pattern and stays fully readable for debuggability.
Tests assert the API-key-shaped secret is masked across every surface and
that normal text passes through unchanged.
Stopping a turn while the model is streaming (stop/esc to redirect) raised
InterruptedError, set final_response to the throwaway "waiting for model
response" sentinel, and persisted messages WITHOUT the assistant text that
was already streamed to the screen. The next turn then had no record of the
half-finished reply, so the model appeared to "forget" what it just said.
Recover the on-screen text from _current_streamed_assistant_text in the
InterruptedError branch and append it as the assistant turn (and surface it
as final_response). The metadata sentinel is kept only when nothing was
streamed yet, preserving the ACP/client suppression behavior.
Completes the partial-stream recovery from 397eae5d9 (which wired the same
_current_streamed_assistant_text salvage into the connection-failure twin
but missed the user-interrupt path). The lossy handler dates to c98ee9852.
Live-measure WCO width in the renderer, drop the right rail below the titlebar
band, and re-enable GPU compositing under WSLg when /dev/dxg is present.
WSLg bridges clipboard text but not images — pull host screenshots via
PowerShell. Disable titleBarOverlay on plain Linux; gate overlay width per
platform in titlebar-overlay-width.cjs.
* feat(kanban): typed block reasons + unblock-loop breaker
Stops the kanban blocked-task loop: a worker blocks a task, a cron
unblocks it, the worker re-blocks for the same reason, repeat forever.
block_task now takes a typed kind and a persistent block_recurrences
counter on the tasks table:
- kind=dependency routes to todo (parent-gated, auto-resumed), never
the human 'blocked' bucket a cron would keep unblocking.
- needs_input/capability/transient/untyped land in blocked; each
same-cause re-block after an unblock increments block_recurrences,
and at BLOCK_RECURRENCE_LIMIT (default 2) the task routes to triage
for a human instead of blocked.
- unblock_task no longer resets block_recurrences (the amnesia that
let the loop run unbounded); complete_task clears it on success.
Wired through the worker kanban_block tool (new kind arg) and the
hermes kanban block --kind CLI flag, both reporting where the task
actually landed. Docs + 11 new tests; 536 existing kanban tests green.
* test(kanban): make second-block notify test use a distinct block cause
test_notifier_second_blocked_delivers blocked the same task twice with
the same (untyped) reason, which now trips the new unblock-loop breaker
and routes the second block to triage instead of blocked — so only one
'blocked' notification fired. The test's actual intent is that TWO
distinct block cycles each notify; give the two cycles different kinds
(needs_input then capability) so they're genuinely separate blocks. The
same-cause loop→triage path is covered by test_kanban_block_kinds.py.
After a prolonged outage the in-process network-error ladder escalates to
fatal and GatewayRunner._platform_reconnect_watcher rebuilds a fresh adapter
that reconnects through the bootstrap path. That path called
start_polling(drop_pending_updates=True), discarding every update Telegram
queued during the outage — all messages sent while the bot was down were
silently lost. The in-process ladder and 409-conflict handler already passed
drop_pending_updates=False; only bootstrap did not distinguish a cold first
boot from a reconnect.
Thread an is_reconnect signal from the watcher through
_connect_adapter_with_timeout into adapter.connect(). The base
BasePlatformAdapter.connect() gains a keyword-only is_reconnect=False so every
adapter inherits a tolerant signature (no per-platform breakage when the
runner forwards the kwarg). Telegram translates is_reconnect into
drop_pending_updates=not is_reconnect on both the polling and webhook bootstrap
calls. Cold boot still drops the stale queue; a watcher reconnect preserves it.
Fixes#46621.
Co-authored-by: annguyenNous <annguyen@nousresearch.com>
Co-authored-by: kyssta-exe <kyssta-exe@users.noreply.github.com>
Co-authored-by: Kewe63 <Kewe63@users.noreply.github.com>
When the primary provider raises AuthError (e.g. expired OAuth token),
_make_agent now walks the configured fallback_providers/fallback_model
chain before giving up — matching the behavior that cron/scheduler.py
and cli_agent_setup_mixin.py already have.
Fixes#47627
A readable state.db can still reject every message write through the
messages_fts* triggers when the FTS5 index is corrupt: base-table reads and
PRAGMA integrity_check pass, but INSERT INTO messages fails with 'database
disk image is malformed'. The gateway reloads conversation_history from disk
each turn, so a silently-failed write hands the next turn stale/empty history
even though the same cached AIAgent still holds the live transcript — causing
immediate same-session amnesia. (#50502)
- hermes_state.py: _db_opens_cleanly() now drives a rolled-back message write
through the FTS triggers, so write-only corruption (which the read-only
probe reported healthy) is detected. repair_state_db_schema() gains an
in-place FTS5 'rebuild' strategy (tier 0) before the dedup/drop tiers, plus
an already_healthy short-circuit. Both 'hermes sessions repair' and
'hermes doctor' route through these, so the fix covers the whole class.
- hermes_cli/doctor.py: the state.db check runs the write-health probe even on
the success (readable) path and repairs in place with --fix.
- gateway/run.py: _select_cached_agent_history() prefers the cached agent's
longer live _session_messages over a shorter persisted transcript, so an
FTS write failure can't wipe in-session context.
- tests: regressions for write-health detection, in-place repair preserving
rows + resuming writes, the already_healthy shortcut, and the gateway guard.
Combines the approaches from #50504 (@0-CYBERDYNE-SYSTEMS-0, issue author),
#52165 (@davidgut1982), and #50576 (@trevorgordon981).
The email adapter authorized senders entirely off the From: header, which is
attacker-controlled and unauthenticated by IMAP. An attacker could forge
From: an-allowlisted-address and pass both the adapter's EMAIL_ALLOWED_USERS
pre-filter and the gateway's allowlist authz (both key on the same spoofable
sender_addr), getting unauthorized commands executed by the agent.
Verify the From: domain against the trusted Authentication-Results header the
receiving mail server stamps (SPF/DKIM/DMARC) before trusting it for
authorization. Enforced only when an allowlist is in effect and allow-all is
off — fail-closed. Operators whose server does not stamp the header can opt
out via platforms.email.require_authenticated_sender: false (or
EMAIL_TRUST_FROM_HEADER=true).
The scale-to-zero idle watcher never started on a correctly-opted-in,
relay-only instance, so the gateway never ran its idle decision, never called
go_dormant(), and never sent going_idle to the connector. Fly's autostop still
suspended the machine on traffic-idle, but the connector never flipped the
instance to buffered-only — so an inbound DM took the live delivery path,
found no live session for the suspended machine, and was dropped fail-closed
with no wake poke. The machine slept and never woke.
Root cause: _scale_to_zero_should_arm() passed list(config.platforms.keys())
to messaging_is_relay_only_or_absent(). config.platforms is pre-seeded with a
DISABLED placeholder PlatformConfig for every known platform (telegram,
discord, slack, matrix, …), so the key set is always the full ~20-entry
catalog regardless of what the instance actually runs. The relay-only check
discarded "relay", saw the disabled placeholders as live direct-socket
platforms, and returned False — so should_arm() was False and the watcher was
never created. Verified live on a staging instance: config.platforms keys =
[telegram, discord, slack, mattermost, matrix, relay] with only relay
enabled=True; should_arm() = False.
Fix: filter config.platforms to ENABLED entries before the relay-only check,
mirroring the adapter-connect loop which already gates on
`if not platform_config.enabled: continue`. This arms off the same notion of
"active platform" the rest of start() already uses — no parallel concept.
Also add a one-line not-armed diagnostic: when an instance IS opted in (the
HERMES_SCALE_TO_ZERO stamp is set) but the watcher still doesn't arm, log why
(relay_only_or_absent, the enabled platforms, wake_url present/missing). A
non-opted instance stays silent. The arm path previously logged only on
success, so a failed arm was invisible.
Tests: the existing pure-helper tests passed bare names so they never
exercised the call site that feeds the placeholder-laden config. Add
behaviour-contract tests against the REAL _scale_to_zero_should_arm with a
realistic config.platforms (relay enabled + others disabled). The F25
regression test (relay-only + disabled placeholders must arm) and the
no-platform case are RED without this fix, GREEN with it; the
genuinely-enabled-direct-platform / not-opted-in / no-wake-url cases stay
correctly non-arming so the filter can't over-broaden.
Wake mechanism itself verified healthy independently (direct wakeUrl GET
resumed a suspended staging instance in 1.15s, clean resume signature).
CredentialPool._sync_device_code_entry_to_auth_store rotated single-use
OAuth refresh tokens but wrote the new chain only into the active profile
store. When a profile resolves a grant from the global-root fallback
(read_credential_pool, #18594) and the pool then refreshes it, root was
left holding a now-revoked refresh token — every other profile reading the
stale root grant subsequently died with refresh_token_reused / invalid_grant
once its access token expired.
This is the credential-pool analog of #43589 (which fixed the non-pool xAI
refresh path in _save_xai_oauth_tokens). Detect the read-from-root case
(profile lacks its own providers.<id> block) BEFORE the profile save and,
after it, write the rotated chain back to the global root via a best-effort,
seat-belted write-through. A profile that genuinely shadows root (owns the
block) is untouched; classic mode (profile == root) is a no-op; a failed root
write never breaks the profile's own save. Covers openai-codex (reported),
xai-oauth, and nous through the shared sync path.
Prevents stage2-hook.sh recursive chown from following a symlinked $HERMES_HOME/home (or profiles/cron) and destroying the host user's home directory. Also guards top-level state-file chowns and refuses first-boot seeding through symlinks. Fixes#52781.
Co-authored-by: harjoth <harjoth.khara@gmail.com>
Two-part fix:
Part 1 (classifier override at agent/error_classifier.py:720-738):
A transport disconnect on a reasoning model — even on a large session —
now routes to FailoverReason.timeout instead of context_overflow. Without
this, large-session reasoning-model disconnects route to the compression
branch and silently delete conversation history on a phantom
context-length error. The override is strictly targeted: non-reasoning
models (gpt-4o, claude-3-5-sonnet, llama-3.3-70b, etc.) still route to
context_overflow on large sessions — the existing intentional behavior
for chat models whose proxy doesn't idle-kill during prefill/generation.
Part 2 (new agent/thinking_timeout_guidance.py + integration at
agent/conversation_loop.py:3488-3567):
New is_thinking_timeout() and build_thinking_timeout_guidance() helpers.
When a known reasoning model (NVIDIA Nemotron 3 Ultra, OpenAI o1/o3,
Anthropic Opus 4.x thinking, DeepSeek R1, Qwen QwQ, xAI Grok reasoning)
hits a transport-kill on a small session (classifier says timeout
directly) or after Part 1 routes correctly (large session), the user
now sees reasoning-specific guidance with three actionable workarounds
in priority order:
1. Set providers.<provider>.models.<model>.stale_timeout_seconds: 900
in ~/.hermes/config.yaml (Hermes's built-in floor is already 600s
for known reasoning models; raise further if upstream is even
tighter).
2. Lower reasoning_budget or set reasoning_effort: medium on this
model if the provider supports it.
3. Use a smaller / faster reasoning model if the task doesn't
require deep thinking.
The new guidance takes precedence via if/elif over the existing
_is_stream_drop block, so a reasoning-model user with a transport-kill
message sees actionable advice instead of the misleading "try
execute_code with Python's open() for large files" advice (which is
correct for the unrelated large-file-write stream-drop case but
actively wrong for the thinking-timeout case).
Verified:
- 478 tests passing across 9 directly-relevant files (49 new + 429
existing, zero regressions).
- Ruff lint clean on all 4 modified/new files.
- Negative test: 6 parametrized regression guards confirm non-reasoning
models still route to context_overflow on large sessions; 4
parametrized gates confirm non-timeout classifier reasons never
trigger the guidance; 5 parametrized cases confirm non-transport
messages never trigger it.
- Regression guard: new guidance message does NOT contain
"execute_code" or "open()" — the misleading advice is fully
replaced, not appended alongside.
- Cross-vendor dual review via agy -p:
- Gemini 3.5 Flash (Medium) — passed: true, zero blockers, one
SHOULD-FIX (vprint block duplication — fixed by extracting
detection into a helper module).
- GPT-OSS 120B (Medium) — passed: true, zero blockers, two nits
(test placement — adopted at tests/agent/test_thinking_timeout_guidance.py;
primary-model capture — accepted as non-issue per Flash's nit).
Dependency note for maintainers:
This PR includes agent/reasoning_timeouts.py (the reasoning-model
allowlist module from PR #52238) because the Layer 1 override is
load-bearing on get_reasoning_stale_timeout_floor(). After PR #52238
lands on main, this PR's duplicate agent/reasoning_timeouts.py should
be rebased away. Either PR can land first; the other rebase is
mechanical.
Fixes#52271.
The #45966 cross-process coherence guard popped the stale cached agent
and then called the blocking _cleanup_agent_resources (memory-provider
shutdown, tool-resource teardown, async-client teardown) while still
holding _agent_cache_lock, on the gateway event-loop thread. While that
ran, _sweep_idle_cached_agents (driven by _session_expiry_watcher)
blocked acquiring the same lock and the asyncio loop stalled for minutes,
tripping repeated Discord 'heartbeat blocked' warnings.
Fix mirrors the cap-enforcer / idle-sweep paths: pop the stale entry
under the lock, release it, then schedule the SOFT release on a daemon
thread. The soft path (_release_evicted_agent_soft) is also more correct
here than the hard teardown the regression used — the same session
rebuilds a fresh agent immediately after invalidation, so its terminal
sandbox / browser / bg processes (keyed on task_id) must be preserved
for the rebuilt agent to inherit, not torn down.
Verified the cross-process site was the only cleanup-under-lock instance;
the other _cleanup_agent_resources call sites run outside the lock.
CI shard test_telegram_conflict.py timed out (140s) because the new
_polling_heartbeat_loop, started by connect(), busy-spun under those
tests: they monkeypatch asyncio.sleep to instant and pass a bot double
with no get_me(), so the probe raised AttributeError (swallowed) and the
loop re-entered immediately with no real pacing, starving the event loop.
Guard the loop to return when bot.get_me is not callable — a real PTB Bot
always exposes it, so this only triggers on a torn-down app or a test
double, where there is nothing to probe. Also cancel the heartbeat task in
the conflict tests that call connect() without disconnect(), matching the
production disconnect() teardown.
Verified: test_telegram_conflict.py now runs in ~4.5s; the 22
heartbeat/reconnect tests still pass; E2E confirms a hanging get_me still
fires the reconnect ladder while a missing get_me exits without spinning.
When a Telegram long-poll TCP socket enters CLOSE-WAIT (remote sent FIN
but httpx hasn't noticed), epoll still reports it readable so no
exception is raised. PTB's error_callback never fires, the reconnect
ladder never engages, and the gateway silently stops receiving messages
while the process stays alive — until a manual systemctl restart.
The existing recovery only covers two cases: error_callback-driven
reconnects (which require an exception PTB never gets) and a one-shot
_verify_polling_after_reconnect probe (which runs only right after an
explicit reconnect). A socket that wedges during steady-state operation
is never detected.
Add _polling_heartbeat_loop: a background asyncio.Task started in
connect() (polling mode only) that probes get_me() every 90s on the
general request pool (not the getUpdates pool, so healthy long-polls are
never interrupted). On asyncio.TimeoutError/OSError it hands off to the
existing _handle_polling_network_error ladder; other errors are
swallowed. disconnect() cancels and awaits the task. Worst-case
detection window ~105s.
Complementary to #51541 (general-pool keepalive limits / fd leak) — that
recycles idle pooled connections; this detects a wedged active read.
Fixes#48495
Co-authored-by: agt-user <267614622+agt-user@users.noreply.github.com>
The desktop scheduler can overwrite cron/jobs.json with its own small
set of internally-tracked crons after an update/restart, causing
partial loss of tool-created cron jobs. The previous guard only
checked for total loss (live_count == 0), missing the case where
live_count > 0 but less than the pre-update snapshot count.
Compare live_count against snap_count instead of checking for zero,
so both total loss (0 vs N) and partial loss (1 vs 19) trigger
restoration.
Salvaged from #52161 by @liuhao1024.
Closes#52144
A top-level delegate_task dispatches in the background and re-enters as a
fresh turn when done. Print a one-line dispatch-time note — no spinner,
nothing to poll — so the idle prompt doesn't read as "nothing happened."
When idle with a background subagent still in flight, append a tail status
segment spelling out that the agent resumes on its own. Width-budgeted like
every tail segment, so it drops first on a tight terminal where the ⛓ count
already carries the signal.
When idle with a top-level delegate_task still in flight, render a static,
shimmering system-note at the transcript tail instead of a spinner (which
reads as "stuck"). Reuses the shared steer / slash-status chrome (centered,
0.6875rem, muted, Codicon) so it sits in the thread like every other meta
line, and mirrors the primary child's latest stream line, falling back to
generic copy. i18n across en/ja/zh/zh-hant; markdown prose/heading rhythm
tuned so a re-entered turn breathes.
Track top-level delegate_task work that dispatches in the background and
re-enters as a fresh turn. $backgroundResume returns {count, activity} for
the active session while idle — count of parked tasks plus the primary
child's latest stream line (tool/progress/thinking) when readable.
Use the app's amber warn color for the unsaved-edits tab dot (was inheriting
the label text color) and add a tab-bg ring + soft drop shadow so it stays
legible where it overlaps the filename.
Extends the pane store with heightOverride (alongside widthOverride) and a
get/set/clear API, and wires the pane shell + desktop controller so the
bottom-row terminal pane can be resized on the Y axis with its size persisted.
Adds a CodeMirror 6 spot editor to the right-rail file preview so users can
make quick edits in-app without leaving for an IDE. Entering edit mode is a
pure in-place swap of the read view — same fixed-height header, same gutter
geometry/typography (mirrors SourceView 1:1) so nothing shifts — toggled via
the Edit button, a bare `e` when the pane is hovered/focused, or the tab.
- Save path is transport-agnostic (writeDesktopFileText): local Electron IPC
or a new hardened POST /api/fs/write-text on the dashboard server (path
validation, parent-must-exist, regular-files-only, size cap, atomic
temp-file + os.replace), behind the existing auth middleware.
- Stale-on-disk guard re-reads before writing and offers overwrite vs
discard-and-reload instead of clobbering external/agent edits.
- VS Code-style modified dot on the tab; ⌘/Ctrl+S and ⌘/Ctrl+Enter save,
Esc cancels; GitHub highlight style matched to the read view's Shiki theme.
- Typing stays render-free (draft in a ref; dirty flips once at the boundary).
The detector folds absolute home / Hermes-home prefixes into their canonical
~/ and ~/.hermes/ forms so static patterns catch /home/alice/.bashrc the same
way they catch ~/.bashrc (abd69b81). On native Windows this fold never fired,
so terminal commands writing to shell startup files, ~/.ssh/authorized_keys,
or ~/.hermes/config.yaml / .env returned "safe" and skipped the approval
prompt — and config.yaml carries the approval policy itself.
Two compounding causes:
1. The fold ran after the backslash-escape strip (r\m -> rm), which dissolves
the backslash separators in a Windows path (C:\Users\alice\.bashrc ->
C:Usersalice...) before the fold could match. It now runs before the strip.
2. The fold only recognized POSIX absolute paths and only the home prefix,
leaving multi-segment backslash suffixes (\.ssh\authorized_keys) to be
mangled by the strip.
Consolidated into _home_prefix_fold_regex / _fold_home_prefixes: match a home
prefix with either separator, capture the rest of the path token, and
normalize its separators to / so multi-segment patterns match. The
degenerate-path guard generalizes count("/") >= 2 to "at least two components
below the root" (also rejecting a bare drive root C:\). HOME is consulted
directly because Windows' expanduser ignores it; the more specific Hermes home
is folded first, longest candidate first, so neither fold clobbers the other.
POSIX behavior unchanged; the r\m -> rm anti-obfuscation strip still runs.
Adds TestWindowsAbsolutePathFolding, which monkeypatches a Windows-style
HOME/HERMES_HOME so the behavior is also exercised on the CI runner.
Follow-up to the salvage of #45035 + #48682. The two PRs touched different
functions (resolve_resume_session_id vs get_compression_tip) but #45035's
descendant walk followed ANY parent_session_id child, so a delegate/subagent
child could hijack the resume target. Apply the same _branched_from /
_delegate_from / source!='tool' exclusion the rest of hermes_state.py uses,
so the resume walk only follows genuine compression continuations.
Also updates the unrealistic delegation test fixture to carry the real
_delegate_from marker, and updates 3 list_sessions_rich test mocks for the
order_by_last_active kwarg #48682 added.
AUTHOR_MAP: map PINKIIILQWQ + ailang323 salvage authors.
After context compression, the parent session holds pre-compression messages
and a child (or deeper descendant) holds the continuation.
resolve_resume_session_id() short-circuited when the input session already
had messages (row is not None -> return session_id), causing REST API
endpoints, gateway resume, and CLI resume to serve stale parent messages.
Remove the early-return. Walk the full descendant chain, record the
deepest node that has messages (best), and return best if not None
else the original session_id (preserving the empty-chain fallback).
Callers (api_server.py, web_server.py, cli_agent_setup_mixin.py,
cli_commands_mixin.py) all use the resolved != input -> redirect pattern
and are transparent to this change.
The pre-update HERMES_HOME zip shipped on by default (DEFAULT_CONFIG +
runtime fallback both True), so every `hermes update` zipped the entire
~/.hermes — sessions DB, caches, skills — adding minutes to each update.
The shipped cli-config.yaml.example, the --backup help, and the example
config all already said "off by default," so the live default
contradicted its own documentation.
Flip the default to off everywhere: DEFAULT_CONFIG, the runtime
`.get(..., False)` fallback in _run_pre_update_backup, and the stale
--backup help string. Users who want the #48200 safety net opt in via
updates.pre_update_backup: true or --backup for a single run.
Updated test_default_enabled_creates_backup -> test_default_disabled_is_silent
to assert the new default (silent no-op, no zip).
* fix(cron): add default retention to per-run job output to bound disk usage (#52383)
Per-run cron output (cron/output/<job>/<timestamp>.md) is written once
per execution and was never pruned, so a frequently-scheduled job on
a long-running deploy accumulates one file per run indefinitely and
can fill the volume ('no space left on device').
save_job_output() now keeps the most recent N output files per job and
removes older ones. N defaults to 50 and is configurable via
cron.output_retention; a non-positive value disables pruning for
operators who manage cleanup externally.
Salvaged from #52402 by @0xDevNinja.
Closes#52383
* fix(config): add cron.output_retention to DEFAULT_CONFIG
Follow-up to #52383: the retention config key was functional via
get()-with-default but missing from DEFAULT_CONFIG, so the deep-merge
wouldn't auto-populate it for new installs. Add it explicitly.
---------
Co-authored-by: 0xDevNinja <manmit0x@gmail.com>
Regression for the salvaged #48254 fix: billing route is first-writer-wins
via update_token_counts (COALESCE), so a mid-session provider switch left
the dashboard attributing cost to the original provider. Asserts the new
update_session_billing_route() overwrites unconditionally, nulls system_prompt
so the next turn rebuilds Model:/Provider:, and preserves billing_mode when
omitted (COALESCE on None).
The session database records billing_provider and billing_base_url using
COALESCE(column, ?) in update_token_counts(), making them write-once.
When a user switches models mid-session via /model, the runtime (agent.provider,
agent.base_url) updates correctly, but the session row never reflects the new
provider. This causes the dashboard Models page to display a stale provider
badge and misattributes token usage / cost analytics.
Fix: add update_session_billing_route() that unconditionally sets
billing_provider, billing_base_url, and billing_mode (no COALESCE), and call
it from switch_model() in agent_runtime_helpers.py after the swap succeeds.
This follows the same pattern as update_session_model() which already
unconditionally updates the model column (added for the identical COALESCE
problem on the model field).
Closes#48248
A stale-index render race in assistant-ui (a just-shrunk thread rendered
at an old message index during a session switch / teardown) throws
errors like "tapClientLookup: Index N out of bounds", "Cannot read
properties of undefined (reading 'type')", or "Tried to unmount a fiber
that is already unmounted". These bubble to the root ErrorBoundary and
latch the WHOLE desktop app on the "Reload window" fallback even though
the next render against fresh state would be fine.
Teach the root boundary to treat that small set of known-transient
renderer errors as recoverable: log them and schedule a next-tick
reset() so React re-renders against current state instead of stranding
the user on the fallback.
Auto-recovery is BOUNDED -- at most MAX_RECOVERIES (3) attempts within a
5s window -- so a genuinely persistent error can't spin the boundary in
a reset -> throw -> reset loop; after the budget is spent the fallback
is left up for the user. Manual retry (the button) resets the budget.
Only the root boundary auto-recovers; scoped boundaries keep their own
fallbacks, and unrecognized errors are never swallowed.
Tests: transient race recovers (fallback never sticks), a persistent
recoverable error stops at the cap and surfaces the fallback (proving
the loop is bounded), and neither a non-root boundary nor an
unrecognized root error auto-recovers.
Closes#41693. Supersedes #41787 by @izumi0uu, reimplemented with a
bounded recovery budget so a non-transient error can't loop forever.
Co-authored-by: izumi0uu <izumi0uu@gmail.com>
resumeSession's warm-cache fast-path trusted the
storedSessionId -> runtimeId -> ClientSessionState mapping without
checking the cached state still BELONGS to the session being resumed.
A pooled profile backend that gets idle-reaped and respawned
(pruneSecondaryGateways) re-mints runtime ids, so a recycled id can
resolve to a live-but-DIFFERENT session's cache entry. The only
existing guard was a session.usage 404 -- that catches a fully-dead
runtime id, but a recycled id still 200s, so the fast-path happily
painted the wrong transcript under the current route (open chat A,
chat B loads).
Fold the belongs-to check into a single takeWarmCache() helper used at
BOTH cache reads -- the early transcript-keep decision and the fast-path
itself -- so a cross-wired entry can't even briefly flash a stale
transcript before the full resume repaints. On a mismatch the helper
purges both stale map entries and reports a miss, falling through to a
full resume that rebinds a correct runtime id. The full-resume path
already guards its final paint with isCurrentResume(), so only the
cached fast-path was missing the belongs-to check.
Pre-existing bug from the initial desktop app (#20059); not introduced
by the session-switch perf work (#49807), which left these lines
untouched.
Tests: two cases in use-session-actions.test.tsx driven through a
harness that owns the two cache maps -- a cross-wired mapping is
rejected + purged (the bug), and a correctly-wired cache still serves
from memory with no needless refetch (no perf regression).
Supersedes #50464 by @professorpalmer, reimplemented to also guard the
early transcript-keep read (whole-class fix, not just the fast-path).
Co-authored-by: professorpalmer <professorpalmer@users.noreply.github.com>
* feat(moa): expose MoA presets as selectable virtual models
Reconstructed onto current main (PR #46081's base had diverged with no common
ancestor, marking the PR dirty so CI never dispatched). MoA is now a virtual
provider: each named preset is a selectable model under provider 'moa', and the
preset's aggregator is the acting model that answers and calls tools.
Reference models fan out in parallel via a bounded ThreadPoolExecutor (the same
batch pattern delegate_task uses) — all references dispatched at once, collected
when every one finishes, then handed to the aggregator. Output order is
preserved, failures and the MoA-recursion guard stay isolated per reference.
- Removed the old mixture_of_agents model tool and moa toolset.
- Added moa as a virtual provider in the provider/model inventory.
- /moa is shortcut behavior over model selection (default preset / named preset
/ one-shot prompt).
- Dashboard + Desktop manage named presets; presets appear in model pickers.
- Parallel reference fan-out in agent/moa_loop.py with regression test.
* fix(moa): thread moa_config through _run_agent to _run_agent_inner
The reconstructed gateway MoA wiring declared moa_config on _run_agent (the
profile-scoping wrapper) and used it inside _run_agent_inner, but the wrapper
never forwarded it — _run_agent_inner had no such parameter, so the runtime hit
NameError: name 'moa_config' is not defined on the compression-failure session
sync path. Add moa_config to _run_agent_inner's signature and forward it from
both wrapper call sites (multiplex and non-multiplex). Caught by
tests/gateway/test_compression_failure_session_sync.py on CI shard test(4).
* fix(moa): classify moa as a virtual provider in the catalog
The moa virtual provider has no PROVIDER_REGISTRY/ProviderProfile entry, so
provider_catalog() fell through to the default auth_type="api_key" with no
env vars — tripping two catalog invariants:
- test_provider_catalog: api_key providers must expose a credential env var
- test_provider_parity: every hermes-model provider must be desktop-configurable
moa already declares auth_type="virtual" in HERMES_OVERLAYS; consult that
overlay as an auth_type fallback so the catalog reports moa as virtual (no real
credential, no network endpoint). Exempt virtual providers from the desktop
parity union check the same way 'custom' is exempt — derived from the catalog,
not a hardcoded slug, so future virtual providers are covered too.
Scheduled jobs delivering to Telegram/etc. started posting a literal
'⚠️ No reply: the model returned empty content…' message instead of
staying silent. Two interacting causes:
1. The turn-completion explainer (#34452) replaces an empty model turn
with a user-facing '⚠️ No reply…' string. In a cron context that is
not a silence marker, so the scheduler delivered it — a regression
from the previously-silent empty turn. run_job now detects the
explainer text deterministically (via the same formatter that
produced it) for abnormal-empty turn_exit_reasons and strips it to
empty, so the existing empty-response suppression + soft-fail guard
apply. The explainer is unchanged on CLI/gateway.
2. The cron suppression used a loose 'SILENT_MARKER in ...upper()'
substring check. It leaked bracketless near-markers the model emits
('SILENT', 'NO_REPLY', 'NO REPLY' — #51438, #46917) and wrongly
swallowed a real report that merely quoted '[SILENT]' mid-sentence.
Replaced with _is_cron_silence_response(): suppresses a canonical
token as the whole response, its own first/last line, or the
documented bracketed '[SILENT] <note>' prefix — while a token buried
mid-sentence in a genuine report is delivered. Preserves the
intentional cron trailing/prefix tolerance (existing tests unchanged).
Tests: bracketless-variant suppression, mid-sentence-quote delivery,
direct matcher contract, and explainer-strip + defensive real-report
delivery.
The trailing-whitespace expansion in _map_normalized_positions
unconditionally consumed whitespace after the matched region — including
the word-boundary space that separates the match from the next token.
This caused silent file corruption when the fuzzy matcher fell back to
the whitespace_normalized strategy.
Guard the expansion on the normalized match actually ending with
whitespace (i.e. the original had a run of spaces that were collapsed).
When the match ends with a non-space character, the first whitespace in
the original is a boundary and must not be consumed.
Fixes#52491
todo_tool crashed with `AttributeError: 'str' object has no attribute 'get'`
when the LLM emitted the `todos` param as a JSON-encoded string instead of an
array, or as a list containing non-dict items (observed intermittently on
Claude 4.5/4.6/4.7, and after a prior tool-call rejection where the model
"self-corrects" by wrapping the list in json.dumps).
Three additive guards, no behavior change for well-formed input:
- todo_tool(): if `todos` is a str, json.loads it; reject unparseable strings
and non-list values with a clear tool_error instead of crashing downstream.
- _validate(): non-dict items return a {id:"?", content:"(invalid item)"}
placeholder rather than calling .get() on a str/int/None.
- _dedupe_by_id(): non-dict items get a synthetic key so _validate handles them.
Salvaged from #14785 by @Tranquil-Flow (authorship preserved via cherry-pick).
Comprehensive tests: JSON-string coercion (parse / unparseable / non-list /
non-string), non-dict list items (str/None/int/mixed), and a well-formed-
unchanged regression class — both guards mutation-verified to fail without them.
Closes#14185. Supersedes #14187, #22505, #14350 (same fix, less/no test
coverage) and #16952 (bundled unrelated scope-creep).
The verify-on-stop guard (PRs #52296, #52297) defaulted ON for every
session, so on gateway messaging surfaces (Telegram, Discord, etc.) the
model complied with the nudge by writing a hermes-verify temp script and
emitting an ad-hoc verification summary, which the gateway delivered to
the end user as chat noise.
Resolve a surface-aware default instead. The DEFAULT_CONFIG value becomes
the sentinel "auto", which verify_on_stop_enabled() resolves to ON for
interactive coding surfaces (CLI, TUI, desktop) and programmatic callers,
and OFF for conversational messaging surfaces. The surface is read from
HERMES_SESSION_PLATFORM (what the gateway actually binds), with
HERMES_SESSION_SOURCE and HERMES_PLATFORM as fallbacks, matching the
sibling resolution in skill_commands.py and prompt_builder.py. An explicit
HERMES_VERIFY_ON_STOP env var or a boolean agent.verify_on_stop config
still overrides in either direction.
The passive evidence ledger and the call site are untouched.
GET /api/tools/toolsets returns the full CONFIGURABLE_TOOLSETS set with no
desktop curation, so the Skills & Tools → Toolsets list shows entries that
don't belong in a flat per-user toggle: platform-coupled toolsets (discord,
discord_admin, yuanbao — which `hermes tools` already platform-restricts off
the CLI) and internal plumbing (context_engine, moa). `hermes tools` curates
these out; the desktop didn't.
Add a small documented block-list + predicate (mirroring
desktop-slash-commands.ts) and apply it in the toolset list filter. Hiding a
row is cosmetic — enabled state and runtime gating are untouched.
2026-06-24 19:18:29 -05:00
1247 changed files with 94654 additions and 15019 deletions
and similar "someone else's product" plugins do NOT land under `plugins/` in
this repo. They place an ongoing maintenance burden on us to keep them working
against a fast-moving core, for a backend we don't own. Ship them as a
**standalone plugin repo** users install into `~/.hermes/plugins/` (or via a
pip entry point), and promote them in the Nous Research Discord
(`#plugins-skills-and-skins`). This is a coupling-and-maintenance decision, not
a quality bar — the plugin can be excellent and still be a close. PRs that add
such a directory to the tree are closed with a pointer to publish it as its own
repo.
### Before you call it a bug — verify the premise (and when NOT to close)
@@ -480,7 +491,7 @@ The dashboard embeds the real `hermes --tui` — **not** a rewrite. See `hermes
### Electron Desktop Chat App (`apps/desktop/`)
A **separate** chat surface from both the classic CLI and the dashboard's embedded TUI. It is an Electron + React + nanostore renderer (`@assistant-ui/react`) that talks to a `tui_gateway` backend over JSON-RPC (`requestGateway(method, params)`). It does NOT embed `hermes --tui` — it has its own composer, transcript, and slash-command pipeline. Route desktop bugs to the `hermes-desktop-app-work` skill, not `hermes-dashboard-work`.
A **separate** chat surface from both the classic CLI and the dashboard's embedded TUI. It is an Electron + React + nanostore renderer (`@assistant-ui/react`) that talks to a `tui_gateway` backend over JSON-RPC (`requestGateway(method, params)`). The WebSocket/JSON-RPC transport lives in the framework-agnostic `apps/shared` package (`@hermes/shared` — `JsonRpcGatewayClient` + WS URL helpers), which the web dashboard (`web/`) also consumes; **desktop has no build/runtime dependency on the dashboard frontend** — it spawns a headless `hermes serve` backend server (the same gateway `dashboard` serves, minus the browser UI). `dashboard` and `serve` share `cmd_dashboard`/`start_server` but are independent surfaces — neither launches the other. The one exception is a backward-compat *fallback*: `serve` is newer, so the desktop spawn (`electron/backend-command.cjs` + `backendSupportsServe()` in `main.cjs`) detects whether the resolved runtime registers `serve` and, only when it does not (an older managed install / PATH `hermes` the app hasn't updated yet), rewrites the argv to the legacy `dashboard --no-open`. Without that, a new app against an un-upgraded runtime would crash on an unknown subcommand and brick every mid-upgrade user. It does NOT embed `hermes --tui` — it has its own composer, transcript, and slash-command pipeline. Route desktop bugs to the `hermes-desktop-app-work` skill, not `hermes-dashboard-work`.
**Slash commands in the desktop app are curated client-side, then dispatched to the backend.** The pipeline:
@@ -783,6 +794,24 @@ landing in this tree. PRs that add a new directory under
provider as its own repo. Existing in-tree providers stay; bug fixes
to them are welcome.
**No new third-party-product plugins in-tree (policy, June 2026):** the
same rule applies beyond memory providers. Plugins that integrate
someone else's product or project — observability/metrics backends,
@@ -85,6 +85,23 @@ This isn't a quality bar — it's a coupling-and-maintenance decision. Memory pr
---
## Third-Party Product Integrations: Ship as a Standalone Plugin
The same rule extends to **any plugin that integrates someone else's product or project** — observability/metrics backends, vendor SaaS connectors, analytics dashboards, paid-service tie-ins, and similar third-party integrations. **These do not land in this repo.**
The reason is maintenance load, not quality. Every external product absorbed into the core tree becomes ours to keep working against a fast-moving codebase, for a backend we don't own and can't control. Hermes ships a lot and the core moves quickly; coupling third-party products into it creates an open-ended burden on the maintainers.
Publish these as a **standalone plugin repo** instead:
- Implement the relevant ABC and use the existing plugin discovery path (`~/.hermes/plugins/`, project `.hermes/plugins/`, or a pip entry point) — see [Build a Hermes Plugin](https://hermes-agent.nousresearch.com/docs/guides/build-a-hermes-plugin)
- Register lifecycle hooks (`pre_tool_call`, `post_tool_call`, `pre_llm_call`, `post_llm_call`, `on_session_start`, `on_session_end`), tools (`ctx.register_tool`), and CLI subcommands (`ctx.register_cli_command`) through the surface we already expose — no core changes needed
- If your plugin needs a capability the framework doesn't expose, that's a feature request to **widen the generic plugin surface** (a new hook or `ctx` method) — never special-case your plugin in core
- Promote it in the [Nous Research Discord](https://discord.gg/NousResearch) `#plugins-skills-and-skins` channel so users can find and install it
A well-built third-party-product plugin can clear automated review and still be closed for this reason — it's a placement decision, not a verdict on the code. PRs that add such a directory under `plugins/` will be closed with a pointer to publish it as its own repo.
---
## Development Setup
### Prerequisites
@@ -132,13 +149,20 @@ this way, make sure you run the `hermes` entrypoint from this venv; running the
system `python3 -m hermes_cli.main` can pick up unrelated system Python
packages.
Create the venv **outside** the cloned source tree. A venv that lives inside
the directory the agent operates from can be wiped by a relative-path command
the agent runs against its own checkout (`rm -rf venv`, `uv venv venv`, etc.),
which silently destroys the running runtime mid-session. Keeping it outside the
tree means no relative path from the workspace resolves to it.
**The self-improving AI agent built by [Nous Research](https://nousresearch.com).** It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions. Run it on a $5 VPS, a GPU cluster, or serverless infrastructure that costs nearly nothing when idle. It's not tied to your laptop — talk to it from Telegram while it works on a cloud VM.
Use any model you want — [Nous Portal](https://portal.nousresearch.com), [OpenRouter](https://openrouter.ai) (200+ models), [NovitaAI](https://novita.ai) (AI-native cloud for Model API, Agent Sandbox, and GPU Cloud), [NVIDIA NIM](https://build.nvidia.com) (Nemotron), [Xiaomi MiMo](https://platform.xiaomimimo.com), [z.ai/GLM](https://z.ai), [Kimi/Moonshot](https://platform.moonshot.ai), [MiniMax](https://www.minimax.io), [Hugging Face](https://huggingface.co), OpenAI, or your own endpoint. Switch with `hermes model` — no code changes, no lock-in.
Use any model you want — [Nous Portal](https://portal.nousresearch.com), OpenRouter, OpenAI, your own endpoint, and [many others](https://hermes-agent.nousresearch.com/docs/integrations/providers). Switch with `hermes model` — no code changes, no lock-in.
<table>
<tr><td><b>A real terminal interface</b></td><td>Full TUI with multiline editing, slash-command autocomplete, conversation history, interrupt-and-redirect, and streaming tool output.</td></tr>
@@ -232,10 +232,14 @@ scripts/run_tests.sh
Manual clone fallback (for throwaway clones/CI where you intentionally do not
want the managed install layout):
Create the venv outside the cloned source tree — a venv inside the directory
the agent operates from can be wiped by a relative-path command the agent runs
against its own checkout, destroying the running runtime mid-session.
@@ -85,7 +85,7 @@ Installers are built and uploaded to GitHub Releases manually. macOS/Windows sig
### How it works
The packaged app ships the Electron shell and a native React chat surface. On first launch it can install the Hermes Agent runtime into `HERMES_HOME` (`~/.hermes`, or `%LOCALAPPDATA%\hermes` on Windows) — the **same layout a CLI install uses**, so the two are interchangeable. Backend resolution first honours `HERMES_DESKTOP_HERMES_ROOT`, then a completed managed install, then a probed `hermes` on `PATH` (unless `HERMES_DESKTOP_IGNORE_EXISTING=1` is set), and finally an explicit `HERMES_DESKTOP_HERMES` command override for packagers/troubleshooting. The renderer (React, in `src/`) talks to a `hermes dashboard` backend over the `tui_gateway`/dashboard APIs and reuses the agent runtime rather than embedding `hermes --tui`. The install, backend-resolution, and self-update logic all live in `electron/main.cjs`.
The packaged app ships the Electron shell and a native React chat surface. On first launch it can install the Hermes Agent runtime into `HERMES_HOME` (`~/.hermes`, or `%LOCALAPPDATA%\hermes` on Windows) — the **same layout a CLI install uses**, so the two are interchangeable. Backend resolution first honours `HERMES_DESKTOP_HERMES_ROOT`, then a completed managed install, then a probed `hermes` on `PATH` (unless `HERMES_DESKTOP_IGNORE_EXISTING=1` is set), and finally an explicit `HERMES_DESKTOP_HERMES` command override for packagers/troubleshooting. The renderer (React, in `src/`) talks to a headless backend the app launches for you — a `hermes serve` process that serves the `tui_gateway` JSON-RPC/WebSocket API — through the framework-agnostic client in [`apps/shared`](../shared/) (the same client the web dashboard consumes), and reuses the agent runtime rather than embedding `hermes --tui`. The app is **self-contained**: it runs its own `hermes serve` backend and never opens or requires the web dashboard UI. (For backward compatibility, a runtime that predates the `serve` command automatically falls back to a headless `dashboard --no-open` — see `electron/backend-command.cjs` — so mid-upgrade installs never break.) The install, backend-resolution, and self-update logic all live in `electron/main.cjs`.
@@ -1771,6 +1976,16 @@ async function readCommitLog(cwd, branch) {
letupdateInFlight=false
// Set to true when the desktop is about to quit so a detached swap/install/
// uninstall script can take over. On macOS, app.quit() closes windows but
// window-all-closed deliberately keeps the process alive (standard Electron
// macOS convention). Without this flag the process never exits — the detached
// hand-off script spins its PID-wait for the full timeout, and the user sees a
// blank app with no window (and an uninstall that appears to do nothing). When
// set, window-all-closed calls app.quit() on every platform so the process
// actually dies and the hand-off script can proceed immediately.
letisQuittingForHandoff=false
// Resolve the staged updater binary. The Tauri installer copies itself to
// HERMES_HOME/hermes-setup.exe on a successful install (see
// apps/bootstrap-installer paths::copy_self_to_hermes_home). That binary owns
@@ -1982,7 +2197,8 @@ async function applyUpdates(opts = {}) {
emitUpdateProgress({
stage:'restart',
message:'Updating Hermes — this window will close and the updater will open. Don’t reopen Hermes yourself; it restarts automatically when the update finishes.',
message:
'Updating Hermes — this window will close and the updater will open. Don’t reopen Hermes yourself; it restarts automatically when the update finishes.',
percent:100
})
repairMacUpdaterHelper(updater)
@@ -2025,6 +2241,7 @@ async function applyUpdates(opts = {}) {
// appears), THEN quit to release the venv shim. The updater rebuilds and
// relaunches us when it's done. (#50419 — a 600ms quit looked like a crash
// and lured users into the #50238 relaunch loop.)
isQuittingForHandoff=true
setTimeout(()=>{
app.quit()
},UPDATE_HANDOFF_DWELL_MS)
@@ -2048,7 +2265,16 @@ async function handOffWindowsBootstrapRecovery(reason) {
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Brooklyn Nicholson