Widens #90327's line_input() to the whole bug class: all 46 bare input()
free-text prompt sites across the setup wizards (model_setup_flows, setup,
config, gateway, auth, auth_commands, plugins_cmd, skills_hub, bundles,
setup_whatsapp_cloud, main) now route through line_input(), and the shared
cli_output.prompt() / setup.prompt() helpers do too — so every CLI wizard
gets cursor editing, not just the custom model prompt.
Redirected stdin and missing prompt_toolkit keep builtin input() behavior.
E2E: real PTY with raw escape bytes through line_input, cli_output.prompt,
and setup.prompt (arrows + Ctrl+A/E edit correctly); redirected-stdin
fallback verified.
Worker sessions are deny-listed out of every conversation list, so a
profile grinding through a 30-minute kanban task read idle ('3 hr ago')
with no ACTIVE NOW entry the entire run.
- tui_gateway/methods_profiles.py: profiles.list rows gain worker_session
— the newest kanban/tool row (id, source, title, last_active). Workers
heartbeat last_activity_at every <=60s while running (#72016), so the
field stays fresh exactly while work is happening. last_session keeps
its deny-list contract; include_sessions:false omits the field; older
clients ignore it.
- hermes-bots plugin: workerActiveAt() (150s window, one missed heartbeat
of slack) feeds ACTIVE NOW, the row pulse dot ('Working on a task right
now'), and the row age label while a worker runs. Chat semantics are
untouched when no worker is live.
- Tests: 4 new pytest (real SessionDB on temp HERMES_HOME), 2 new node
behavior tests; sabotage-verified.
Session-list visibility of workers (the issue's first half) is left as-is
by design — auto-resume and shared lists must keep excluding workers; the
roster signal was the actionable gap.
test_progress_advances_while_the_orchestrator_blocks raced its subject on
both edges within one hour of PR CI (#90358):
- Run 1: sampled right after the shim URL printed, before the orchestrator
published its stage — caught the page boot default
('Hermes will open once done.' != 'Testing quiet update').
- Run 2 (rerun): with HOLD=4s on a slow runner, the second sample slid past
the hold and caught the cleared terminal state ('' != 'Testing quiet
update').
Fix: wait (<=10s) for the published stage to actually land before starting
the 1.5s stability window, and raise the hold to 10s so both samples land
inside it. Same assertions, same contract — just anchored to the event the
test is about instead of wall-clock luck.
The #89503/#70058/#74295/#87279 bug class kept regenerating because every
transport and provider profile hand-rolled its own effort translation map
(9 sites, 4 distinct policies). New agent/reasoning_effort.py is the single
source of truth:
- EFFORT_LADDER: canonical low->high ordering (superset check against
VALID_REASONING_EFFORTS pinned by test)
- clamp_effort(): one policy — supported passes verbatim, otherwise nearest
WEAKER supported level (never escalate, never invert the ladder), floor
when nothing weaker, 'none' never a degradation target, declared
vendor-documented overrides win, bespoke names pass through
- declared wire vocabularies as data: OpenAI-compat, Codex Responses,
xAI (4.6/legacy), Actual relays, Kimi K3/K2, TokenHub, GLM-5.2,
DeepSeek V4, Ollama Cloud, Meta, Solar
Converted sites (all behavior-preserving except noted):
- chat_completions chokepoint, Kimi + TokenHub paths
- codex transport (backend branches now pick a declared set)
- auxiliary_client Responses path
- hermes_cli.models clamp_reasoning_effort_to_supported -> thin wrapper
- plugins: kimi-coding, zai, opencode-zen, deepseek, ollama-cloud,
meta-ai, upstage, custom (copilot already routes via the wrapper)
Behavior fixes the shared policy surfaces:
- ollama-cloud/opencode-go 'minimal' now degrades to 'low' instead of
being dropped (drop left the server default = MORE thinking than asked)
New tests: ladder contract (every configurable level is clamped by every
declared wire set; monotonicity across the full ladder for every set).
Archived rows render from $archivedSessions (their own capped store —
they're excluded from $sessions by design), but removeSession only pruned
$sessions. Deleting from the Archived filter left the row in place; a
click on it resumed a hard-deleted id: resume 404 -> goneSessionVerdict
saw the row still listed -> 'retry' -> unrecoverable spinner.
removeSession now resolves the row from either store, evicts both
optimistically, restores the archived row on RPC failure, and forwards
the archived row's owning profile to deleteSession.
Community report (X @Cobalt_Peak): Reconnect and Restart gateway in the
statusbar gateway popover rendered the same RefreshCw icon side by side,
so users triggered full gateway restarts when they meant to reconnect.
- Restart now uses a Power icon with a destructive hover tint
- Moved restart to the end of the row, after the system-panel button,
behind a visual divider separating it from the benign actions
Both cron empty states used search-flavored copy unconditionally; a fresh
panel with zero jobs and no query told users 'Try a broader search
query'. Copy now follows the query state, reusing existing i18n keys.
The backend's session search wraps matched terms in sqlite snippet()
delimiters '>>>'/'<<<' (hermes_state_search.py). The sidebar rendered the
snippet as plain text via searchResultToSession(), so searching 'foo'
painted rows literally titled '>>>foo<<<'. Strip the markers before the
snippet becomes the row preview.
/api/model/options probed Copilot auth via `gh auth token` four separate
times per payload build. When gh has no credential store for the backend's
HOME (fresh profile, desktop-spawned backend, CI), each probe blocks its
full 5s subprocess timeout on keyring/D-Bus, so every open of the Desktop
Models or Providers settings page took 20s — past the renderer's 15s IPC
budget, painting 'Error invoking remote method hermes:api: Timed out'.
Fix: cache the gh-CLI probe result (hit or miss) for 5 minutes with an
invalidation hook, feed gh stdin=DEVNULL, and disable gh interactive
prompts/update notifier in the probe env.
Measured on the failing profile: 20.5s -> 5.3s cold (one bounded probe),
0.03s warm.
Threading timeoutMs/signal through requestForSessionProfile and
requestGatewayForProfile handed every session-scoped RPC a trailing
`undefined, undefined`. Only the plugin host bridge actually supplies those,
so the rest of the app's calls changed observed arity for no reason — and the
resume/activate paths assert on the exact call shape.
Forward the deadline args only when the caller set them; the plugin bridge
keeps the full four-argument route it needs.
Opening a plugin/Bot Mode session is navigation, not a workspace switch.
keepAllProfilesScope (default true) now dials the named backend without
moving $activeGatewayProfile or setApiRequestProfile. Session-owned RPCs
still route to the session owner. Pass false to switch chrome and collapse
the Sessions sidebar.
Bot Mode passed keepAllProfilesScope:false, which re-homed the sidebar
onto the bot profile. That profile forever-chat is hidden, so Sessions
and the roster looked empty. Opening a bot is navigation, not a workspace
switch. Also restore all-profiles when the bot backend is already live.
Related: #89789
A review of the previous commit found that retrying at the plugin layer
(openStoredBotChat catching and re-calling host.openSession) didn't fix
the reported bug: host.openSession's own catch block unconditionally
calls setResumeExhaustedSessionId on a hydration timeout before
rethrowing, and only an explicit resumeSession() (the manual Retry
button) clears that latch for the currently-routed session. A
plugin-side retry is a different code path that can hydrate the
transcript fine while the full-screen "Couldn't load this session"
overlay stays latched over it.
host.openSession now takes a retryHydrationTimeoutOnce option and
retries the open+hydration-wait internally, before the latch is ever
set, so a successful retry never arms the overlay. openStoredBotChat
just opts in via that option.
host.openSession awaited ensureGatewayProfile with no deadline. That await
gates waitForFocusedSessionHydration, which arms the only timer on the path,
so a profile dial that never settles left the open pending for the life of the
window: the pane froze with no error, no Retry and - the part that made this
hard to recognise - no timeout either. The gateway log signature is a bare
`ws accepted` with no matching `ws closed`.
Bound the activation with its own copy of the wake budget rather than folding
it into the hydration one. A cold profile backend can legitimately spend most
of the hydration budget painting a large transcript, and that race is already
tight enough to lose, so charging activation to the same clock would trade a
wedge for a regression. The timeout reuses the hydration message prefix on
purpose - openSession keys the core stranded-session surface off it - and the
[bot-wake] support log now names which phase expired, so a stuck dial is not
read as a slow transcript.
Scoped to callers that passed awaitHydration. A plain open never asked for a
deadline and has nowhere to render one, so its behaviour is unchanged.
Two existing tests counted microtask ticks between the call and the core open.
The bounded activation adds a tick, so they now flush a macrotask instead,
which asserts the same thing without depending on the await count.
Refs #89556
The exit chip floated over the composer in a 26px transparent strip reserved
for it (--hud-chip-strip), hidden until you hovered the bar. Under glass that
strip is bare untinted material across the top of the HUD — a band of chrome
above the surface, present in every state, holding a control you cannot see.
It rides the composer's controls row now, next to send. That costs no
reserved space and takes about 120 lines of CSS with it: the chip needed its
own placement, hover reveal, leave-hold, and an opaque card to stay legible
over an unknown desktop. None of that applies to a button on the bar, which
is already our surface — the problem was the placement, not the control.
Trade-off worth naming: the way out is now always visible in the HUD rather
than revealed on hover. It is one more permanent glyph on a Spotlight bar, in
exchange for an escape hatch that no longer depends on discovering it.
Dictation, spoken replies, the wake word and start-conversation were four
separate icon buttons in a Spotlight bar a few hundred pixels wide — most of
the row spent on toggles that are set once and rarely touched. In the HUD
they collapse into a single menu; the docked composer has the width and
keeps them inline, same controls and same state.
The trigger is not a static glyph. It reports the loudest live voice state —
recording, transcribing, listening for the wake word, speaking replies — and
lights while any is on, because a folded menu that looked idle with the mic
open would be a worse trade than the space it saves. The three toggles are
checkbox rows that hold the menu open on select, so the state you just
changed is the state you can see.
The shared control class names move to a module of their own so the row and
the menus it renders can wear them without importing each other, and the
pressed-toggle tint stops being written out at each of its four sites.
The band wore its own card tint at a hardcoded 80/92%, so a HUD beside the
docked window read as a lookalike rather than the same surface, and the Tint
slider moved one and not the other. It now paints --ui-bg-chrome at
--translucency-glass-keep: one painter, one token, one lever.
That needed the setting and the surface rewrite to stop being one flag.
data-hermes-glass means "this window's field surfaces may be rewritten" and
is deliberately false in the HUD, which owns its own backgrounds; the new
data-hermes-glass-on means "the user's Glass setting is live" and is
published everywhere, along with the tint number the band reads.
The 0.5rem side inset drops to zero while glass is on. It exists to keep an
opaque sheet clear of the bar's corner controls, but the frost is the whole
window — an inset sheet left a hairline of bare untinted material down both
sides.
An open completion drawer now drops the frost along with the band it belongs
to. The drawer takes the band to 25% and blurs it while the native material
stayed at full strength, which is the same bare slab in a different
disguise. It mounts without a focus change, so it is observed rather than
passed in, coalesced to a frame because the shell mutates with every
streamed token.
The HUD asked for vibrancy directly and always with the 'hud' material —
one of the two rungs the macOS census rejected, because it collapses into
under-window on blur and so changed the frost the moment another app took
focus. It also ignored the translucency setting entirely: Glass off still
frosted, and Windows got nothing at all.
hudFrostFor is the mapping for a transparent window, beside vibrancyFor in
the shared module both processes read. Two gates give it its answer: the
renderer's report that the band actually covers the window, and the user's
Glass setting. Off resolves to no material rather than a resting one, since
a transparent window has no opaque page to hide an unwanted frost behind.
Windows 11 rides setBackgroundMaterial through the same call, so the HUD
follows the frost ladder on both platforms. Main self-diffs and keys the
latch to the window, so a Settings change re-frosts a live HUD, a tint drag
touches nothing native, and a HUD respawned on another profile is not
mistaken for the window that already carried the material.
Composio eval traces showed Hermes wasting turns re-issuing identical tool
calls (same tool, same args, same result — 3x/4x in one run) and ending
turns by announcing an action it never took. Two conservative, config-gated
guards (agent.stall_guards, default true):
- Identical-call loop breaker: ToolCallGuardrailController.observe_identical_call
tracks the consecutive streak of (tool, canonical args, result-hash); on
the 3rd identical call a compact one-line notice is appended to that tool
RESULT at construction time (cache-safe — tool results are append-only).
Never blocks the call. Pollers (process, *_get_result, *_poll) are exempt
via STALL_GUARD_REPEATABLE_TOOLS. Streak resets on any different call,
changed result, or new turn. Observed on the raw result before the
tool-loop warning suffix so its changing count can't defeat matching.
- Said-continue-but-stopped recovery: trailing_continue_intent() detects a
short reply ENDING on an announced next action ('Let me now…', 'I will
now…', 'Next, I…'); the conversation loop feeds it into the EXISTING
intent-ack continuation path (same interim-assistant + user-nudge
mechanism, same codex_ack_continuations cap of 2), preserving message
alternation — no parallel recovery machinery.
Config: agent.stall_guards in DEFAULT_CONFIG; docs in configuration.md;
unit tests for streak/allowlist/reset/gate and detector pos/neg cases.
The persistent terminal is a position:fixed overlay that chases its slot's
rect, and the whole tracker — visibility included — was gated behind the
renderer pause. Switching tabs while the window is unfocused therefore left
the overlay parked over the zone at full opacity with pointerEvents:auto, so
the chat underneath was unreachable until something refocused the window.
Visibility is correctness rather than perf, so sample it on every wake even
while paused; the rect chase, which is the part that forces layout, stays
gated.
Composio-style MCP servers return un-paginated 22-47K-char payloads that
sail under the generic 100K per-result spillover threshold, bloating
context and ballooning per-turn reasoning time on long conversations.
Competitors cap harder (OpenCode/pi 50KB, Claude Code 30K, Codex ~10K
tokens). Three changes:
- mcp_* tools spill at a tighter 50K default (BudgetConfig.mcp_result_size,
config-overridable via tool_budget.mcp_result_size_chars; pinned and
per-tool overrides still win; capped by the context-scaled default).
- The persisted-output preview now teaches recovery: page the saved file
with read_file or process with execute_code instead of re-requesting the
same data from the remote API.
- Untrusted/MCP string results are scanned (bounded, first 64KB) for
provider-side elision markers ('...N more items', "has_more": true,
'saved to sandbox', data_preview) and get ONE cache-safe incompleteness
notice appended at result-construction time, before untrusted wrapping —
so the model stops treating provider-elided enumerations as complete.
- Hard 2M-char allocation cap in mcp_tool.py (text, error, and
structuredContent paths) so a pathological multi-MB server payload is
bounded before it propagates, while ordinary large results reach
spillover intact. Distilled from #56060/#56072/#56511 (issue #56059);
supersedes their 50K lossy truncation with spillover-friendly semantics.
Docs: configuration.md spillover-budget section + cli-config.yaml.example.
Co-authored-by: Stoltemberg <215755014+Stoltemberg@users.noreply.github.com>
Co-authored-by: AlexFucuson9 <295703459+AlexFucuson9@users.noreply.github.com>
Co-authored-by: Tranquil-Flow <66773372+Tranquil-Flow@users.noreply.github.com>
Unpinned zero-credential installs now pick Exa or Parallel by the
parity of the per-process random session id (stable within a process,
even split fleet-wide) instead of always favoring Parallel. An explicit
hermes tools selection (web.backend / per-capability keys) bypasses the
split entirely; the runner-up vendor stays in the walk as fallback.
Live E2E: 6 fresh processes split 3/3 between vendors, each performed
a real keyless search via its picked endpoint; explicit pin verified.
Un-fences OPENAI_MODEL_EXECUTION_GUIDANCE from the gpt/codex/grok substring
check and gives it its own injection gate, independent of
tool_use_enforcement, controlled by config.yaml `agent.execution_guidance`
(auto/true/false/list — same semantics as tool_use_enforcement). The "auto"
list (EXECUTION_GUIDANCE_MODELS) now also covers deepseek, kimi, qwen, glm,
minimax, mimo, and mistral.
Composio agentic-eval traces showed Hermes+DeepSeek/Kimi failing where
competitors passed: financial math done in prose, no read-back after
external writes, malformed identifiers "repaired", completeness claimed
despite count mismatches. The discipline block existed but those models
never received it.
The block is extended with compact clauses distilled from that analysis:
- external-write read-back (tool-call success is not task success; internal
file edits already confirmed by the tool are not re-verified)
- count reconciliation (declared totals/has_more are hard assertions)
- literal preservation (never normalize identifiers that fail a stated
format; lookup success does not validate a malformed token)
- retry-differently (empty/partial/suspiciously narrow results get a
broader retry before concluding)
- completion gated on verification (done = every named acceptance
criterion verified, never a plausible subset)
The todo tool description now encourages enumeration-as-checklist for
"all N items" tasks and gates completed status on verified work, never
intent.
Guidance is chosen once at session start keyed on model name, so the
system prompt stays byte-stable for the life of a conversation.
Supersedes/absorbs prior contributor proposals: #20588, #35087, #41874
(MiMo), #53847 (GLM tool-calls-as-text stall).
Co-authored-by: Mat-London <56627804+Mat-London@users.noreply.github.com>
Co-authored-by: intelac <8803887+intelac@users.noreply.github.com>
Co-authored-by: 6ylqq <51219463+6ylqq@users.noreply.github.com>
Co-authored-by: tauros1983 <267660491+tauros1983@users.noreply.github.com>
The SDK now returns the registry rows per its documented contract
(salvaged #89893), while desktops predating the SDK unwrap resolve the
raw registry envelope. The plugin normalize accepts both, so the picker
works across the transition; regression test updated to pin the
dual-shape normalize.
Update the sibling tests that pinned the old use_gateway-writing
contract: image/video selector and reconfigure rows now assert the
single provider string ('nous' managed / 'fal' BYOK) plus legacy-key
popping, the stt/video picker writes drop the use_gateway expectation,
the web_server managed-browser select asserts the persisted 'nous'
cloud_provider, and explicit-local STT pins no-cloud-fallback against
a stored raw-config selection.
Two real gaps the CI-red sibling tests exposed:
- read_selection() treated EVERY raw stt.provider: local as the legacy
DEFAULT_CONFIG seed and reported no-selection — but the seed never
reached config.yaml (save_config strips schema defaults), so a
picker- or hand-written local pick was silently discarded and the
autodetect ladder could route an explicit local user to cloud STT.
A raw 'local' is now a genuine selection; the merged-view ambiguity
note replaces the over-broad shim (mirror comment updated in
nous_subscription._selected_provider and _get_provider).
- _reconfigure_provider was half-migrated: the tts/stt/browser/web
branches and the managed-category fallthrough still wrote
use_gateway flags and vendor names for managed rows. They now write
the single provider string ('nous' for managed rows) and pop the
legacy key, matching _write_provider_config.
Teknium