webclient: drop the separate queue counter, mute the queued badge ...

The input area carried a chip with the queue's own count next to the
per-message "queued" mark. Two views of one queue disagreed more than they
helped, and the count said nothing the transcript did not: the chip, its
i18n keys and the store state behind it (queuedMessages, queuedCount) are
gone. message_queued still lands in the store — it drops the "sending" hint —
but nothing is counted.

The badge on a queued message took --gn-color-accent (#FF9E64). On the user's
blue bubble, already faded to 0.75 while queued, that measured ~1.9:1 and read
as a warning sign. It is now the palette's grey (#414868): muted, legible on
that blue, and clearly secondary to the message text — the darker neutrals
look like the message itself.

webclient: a recall you can inspect, skip and cancel ...

Clicking the banner opens a dialog with the call's kind, when it was created,
a live countdown to the next fire, the repeat interval and the system message
the agent wrote for itself; skip and cancel live there too.

The cancel button in the banner and the sidebar never worked: ph-clock-slash
is not a Phosphor icon, so the glyph was empty and the button collapsed to
8x4px. It is ph-x-circle now, with a larger hit area.

/recall payloads carry created_at, and the countdown picks days or hours
instead of counting out "43230 min".

sessions: the info dialog shows a pending recall ...

GET /sessions/{id}/info now carries the session's pending recall, and
GET /sessions/{id}/recall answers in one shape ({"recall": {...} | null})
instead of a flat object when found and a wrapper when not. The lookup is a
single indexed row rather than the newest 50 recalls filtered in Python.

webclient: a dialog that answers which model is serving, and from where ...

The header only named a model when the route had fallen back, so "what is
running this session, on which host, with how much context" had no answer
in the UI. The context percentage doubles as the second way in: a session
bar is a fair place to ask what the bar measures.

GET /sessions/{id}/info reads in-process state only — the active route
entry, the health chain, the profile's effective window, run and client
counts — and the dialog polls it while open. /meta and the session head
now report the route's window instead of the global ollama_num_ctx, which
had been wrong for every cloud-backed profile.

llm: routes that name a host, a backup and a window, and a profile that reads them ...

`llm.json` replaces `OLLAMA_BACKENDS_FILE`. It has targets (host and key
environment variable) and routes, where a route is an ordered chain of
`model @ target` entries, each with its own `context_window` and options. The
`default` route now starts on `glm-5.3-flash:cloud` and backs it with
`qwen3.6:35b-128k` on the home host, both at 131072 tokens, so a failover no
longer changes the budget the compressor and `num_ctx` are accounted against.
Embeddings get their own `embedding` route instead of a pinned host.

The engine classifies a failure (network, quota, auth, server, missing model),
cools that entry and moves the call down the chain; a background probe watches
only degraded targets and lets the next turn return to the primary once it is
healthy — it never interrupts a running turn. A profile joins a route with
`llm_route`, and the loader now actually reads it: `llm_route` and
`context_window` were declared on `AgentProfile` and written into every
`config.json` while the loader skipped both, the same silent no-op that
`is_admin_only` used to be, so every profile ran the legacy model list at the
global window. The writer emits them too, or an admin edit would erase the
route from disk.

The turn's resolved entry travels to the UI: the first chunk is stamped with
model and target, `model_info` carries `fallback` when a backup answered, and
the chat header shows a chip only then. `serving_primary` compares the target
as well as the model name, because a route may run one model on two hosts.
`/health` gains an `llm` block with the active entry, target states and missing
models.

`deploy/ollama/` keeps the local model's definition honest: MTP off (slower at
every context on this host), `presence_penalty 0` (the base model's 1.5 breaks
agentic tool calls), and `num_gpu 40` — Ollama's automatic fit claims a 128k
f16 slot fits and then dies mid-prefill with CUDA OOM; 40 of 42 layers leaves
~400 MiB and decodes at ~77 tok/s, 38 layers collapses to 48, and 39 OOMs.
q8_0 KV measured 37 tok/s against 70 on f16 here, so the cache stays f16.

webclient: a viewer for every content type, and a message sent mid-turn waits its course ...

The lightbox is now one dialog for every file the artifacts panel and the
content cards can show: audio and video players on the kit's own controls, a
text/source view with highlight.js, and a three.js viewer that replaced the
standalone stl.html frame with a model one. highlight.js emits .hljs-* classes
and ships no theme, so until now every highlighted block rendered in one flat
colour — app.scss now carries the palette.

While a turn runs, the send button no longer turns into Stop and vanishes the
draft with it: the message goes into the socket and is marked "queued" until
the stream_start of the turn that consumes it, the write-now-run-next model
navi-code uses. Send and Stop sit side by side, and the queue chip takes the
larger of the local and the server's counts.

The socket keeps its own liveness: a ping every 20 s, a watchdog that reopens a
socket silent for 45 s or stuck in CONNECTING, and a reconnect on resume from
background, network return or bfcache. On reopen it drops a half-written
message left by the dead socket, so the session_sync that follows is not hidden
behind a stream that will never finish.

webclient: a deliberate pull upwards outranks the autoscroll ...

While the agent streamed, the pin to the bottom was re-applied between deltas, so
a small wheel-up was yanked back before the "user scrolled up" flag had a chance
to be set — the view only came loose after a large fling. The flag itself was
written by the scroll handler from distance-from-bottom alone, which needs a
100px move to trip, well past the point the user has already been overruled.

Direction is now read from the gesture. A wheel tick or a finger drag that goes
up sets the flag at once and drops any landing loop still re-clamping, and the
pin stands down for 250ms after real input, in flight outranking it. A wheel on a
list that fits entirely is not treated as a request to leave the bottom — the
view never moves there and the flag would stick with the stream no longer
following. The scroll handler keeps the dragged-scrollbar fallback: entering
"scrolled up" still takes a clear move, while leaving it takes almost nothing, so
the pin re-arms as soon as the user is back at the bottom.

dist rebuilt and committed with the source.

synapse: a reaction continues its conversation, and the request becomes a record ...

Every Synapse event used to open its own service session, so two messages of
one Telegram chat landed in two unrelated chats. The dispatcher now returns a
`session_key` — derived from the payload according to the user's routing
document — and a later event carrying the same key joins the session that
opened it, within `reaction_session_ttl_minutes` of idle time (0 restores the
old always-fresh behaviour). A session that is still running is never joined:
`create_run` overwrites `state.run`, so a second run would orphan the first
one's subscribers — a busy thread gets a fresh session instead. When the
dispatcher names a different profile for the event, the session's profile is
switched through `set_profile`, never through `save()`, which does not rewrite
`name` or `profile_id`: the thread keeps its name and its history.

What the user reads in the transcript is now only the request. The event
record is a system message (`metadata.source == "synapse_event"`) drawn by a
new SynapseEventNotice.vue in the visual language of the recall badge, and the
framing plus the JSON envelope become a hidden user turn written once, on the
first event of a thread — not on every one. The instructions from Settings
reach the model through a new `current_reaction_instructions` ContextVar and
the `[Reaction session]` block of the system prompt, so they appear in no
transcript at all. The stored system record still has to reach the model, so
ContextBuilder's allowlist becomes `_LLM_SYSTEM_SOURCES = {task_note,
synapse_event}`.

The dispatcher gets a document of its own — how to route, rather than what to
do — stored beside the reaction instructions, versioned separately, and edited
in its own field in the settings panel. `synapse_instruction_versions` gains a
`doc` discriminator, so existing rows keep `'reaction'` and their history
verbatim. The new columns are added by `_MIGRATE`, and the index over `doc`
lives there too: `_DDL` runs first, so an index over a column the migration has
not added yet kills the whole batch on an existing database — which is what
the prod database is. A guard test keeps it that way.

Tests: 1776 passed, 1 skipped (backend), 242 passed (webclient, 28 files).

webclient: the chat area in en, uk and ru ...

The fifth area of the interface translation. The chat screen now builds its
text through t(): the header (the rename tooltip, the sidebar toggle, the
artifacts toggle, and the recall banner with its Cancel and Skip next
buttons), the list around it (the connection-lost banner and its Retry, and —
unreachable for now — the empty state), the input bar (the sending notice, the
paperclip, the placeholder, Send and Stop generation), the attachment strip
(its alt text and its remove button), the message list (Loading older
messages… and the scroll-to-bottom tooltip) and the queued-messages chip. Also
four toasts the WebSocket composable raises — background task started /
finished, MCP server connected / disconnected — and the compression notice's
own pending text.

26 new slugs in all three dictionaries:

- 20 in chat.* — the header and recall banner, the input bar, the attachment
  strip, the queued chip and the empty state;
- 4 in toast.* — the two background-task and the two MCP toasts;
- 2 in common.* — task and toolsCount.

Four details worth knowing:

- The recall banner used to read the server's call_type enum out loud
  ("Scheduled once recall at …"). The word is now a slug
  (chat.recallOnce / chat.recallRecurring / chat.recallImmediate), so it agrees
  with the sentence around it — Russian and Ukrainian both change the
  adjective's gender and the preposition, which a bare enum cannot.
- The banner's time was formatted with the browser's locale; it now formats
  against locale.value, so the date follows the interface language rather than
  the machine.
- The queued chip counted with `count === 1 ? '' : 's'`. It is now a dictionary
  plural driven by {n}, which is what Russian and Ukrainian need — "1
  сообщение", "2 сообщения", "5 сообщений".
- toolsCount moved from messages.* to common.*: the tool-count badge in the
  assistant message and the MCP-connected toast both render it, so the same
  word lives in the vocabulary area instead of twice under two areas.
  docs/i18n.md records the move.

The English values are verbatim the literals the code hard-coded, so the
English interface is unchanged and no test needed editing.

Checked live in Chromium against the built bundle on the dev backend, all
three languages: the header title, the input placeholder, both input-row
buttons, the recall banner and its buttons, twelve message rows and the
attachment's alt and remove — read fresh for each language by picking it in
Settings first — with a scan of the page's text, titles, aria-labels, alt texts
and placeholders for a slug that leaked into the interface as the pass
condition.

Two states a saved session cannot be put into are covered by a throwaway mount
instead, and the file was removed again: the streaming input bar (Sending…,
Stop generation) and the queued chip, plus the recall words and the toast
titles, printed in Russian — "1 сообщение в очереди" / "2 сообщения" /
"5 сообщений".

The connection-lost banner never appears in this harness: with no socket token
the server refuses the socket and the client never exhausts its retries inside
the test's window, on the current build and on HEAD's alike. It is covered by
the existing tests/unit/composables/useWebSocket.test.js and by reading
ChatArea.vue; the same goes for chat.nothingOpen / chat.startConversation,
which App.vue's WelcomeScreen shadows before ChatArea can render its own empty
state — the branch is dead today and keeps its slugs for when it is not.

webclient: hold the chat at the bottom when a stream ends ...

The list was pinned per streaming delta, but the last things to land arrive
after that final pin: the stats/rating footer, which renders only once
msg.done is set, and the copy buttons attached to code blocks after render.
Nothing re-clamped afterwards — the length watcher never fires (the message
stays in the array) and the landing loop only runs when a session opens — so
the view was left short of the bottom, looking like it had scrolled up.

Re-clamp through the same settle window the landing uses when streaming goes
true -> false, unless the user has scrolled up or a session is loading.
This addresses the late-layout half of the problem; the row is still remounted
when msg.id becomes h_<n>, which is the other source of a jump.

webclient: remove session list dividers, 42px sidebar logo, truncate long file names in preview pill

webclient: tool-count badge, kit-styled content card, thinking corner gap, chat top gap, drop duplicate reconnect notice

webclient + navi: session title click-to-rename; empty rename regenerates via LLM

webclient: polish batch — caps off, kit badge/chip in header+input, search clear closes, mobile full-bleed input, settings centered ...

- chat-header-title and sidebar logo span: remove forced uppercase
- profile badge -> GnBadge (variant per profile: secretary secondary,
  server_admin warning, developer info); custom box styles dropped
- pending file pill -> GnChip (icon + removable); image thumb stays
  app-owned (no kit image-preview component) but on kit surface look
- sidebar search clear button now also closes the field
- input-row: no yellow focus ring; on mobile full-screen width, no
  borders, inner padding carries the breathing room
- sidebar footer: without-hover removed from gear/admin/logout buttons
  — kit hover returns
- settings: header and body centered, max-width 1200px

webclient: replace vue-virtual-scroller with plain content-visibility rendering ...

The virtual scroller's measurement states duplicated item views (parked
copies at translateY(-9999) alongside working ones), which made tool/plan/
thinking cards unclickable and the chat flicker. Both chat messages and
the session sidebar are now plain v-for lists; off-screen rows skip
render/paint via content-visibility: auto, keeping long sessions cheap
without the scroller engine. Library removed from dependencies.

webclient: reconnect banner -> GnAlert (kit warning styling)

webclient: W4 — chat empty state -> GnEmptyState, card modal -> GnModal ...

- ChatArea: .empty-chat custom icon+text -> GnEmptyState card
  (keep .empty-chat wrapper only for centering)
- CardGrid: inline Teleport modal (overlay/close/scroll bespoke chrome
  removed) -> GnModal; .card-modal/.card-modal-title class names kept
  inside the new DOM (test contract); kit header slot renders the title
- WelcomeScreen: typography aligned to kit (30px h1, 14px base),
  profile cards get -radius-md, dead .profile-icon style dropped
- CardGrid test: mount with the kit plugin (GnModal resolves),
  two nextTicks for the post-flush open watcher

Verified: vitest 111 passed, build OK, welcome screenshot unchanged
(modal/empty-state visually checked after final build)

webclient: W3 — migrate settings/sidebar/chip surfaces onto kit components ...

- AppSidebar: hand-styled <select> -> GnSelect (options computed from the
  profiles store); the ~60-line bespoke select styling in app.scss is now
  three compact overrides collapsing GnSelect's form chrome for the slim
  sidebar row
- ApiKeysPanel: bespoke grid-table -> GnTable with cell slots (monospace
  key prefix, formatted dates, revoke GnIconButton in actions); loading
  state -> GnLoader; no-auth callout -> GnAlert(variant=warning)
- NotificationSettingsPanel: unsupported-browser callout -> GnAlert(info)
- SettingsView: header -> GnPageHeader (compact) with sidebar toggle in
  #actions
- ShowTokenModal: token field -> GnInputGroup + GnCopyButton (drops the
  bespoke copy/useCopy wiring)
- QueuedMessagesChip: .task-chip div -> GnChip (icon prop)

Verified: vitest 111 passed, build OK, screenshots of / and #settings

webclient: retokenize styles onto gn-ui-kit v1.0 CSS variables ...

All ~165 legacy var() usages (--color-*, --surface*, --accent*, --border,
--text*) with hex fallbacks and ~150 raw hex literals across app.scss and
24 scoped style blocks are swapped to the kit's --gn-* tokens per the
intent of the old fallback values:

- accent/primary/teal (#7aa2f7/#4ec9b0) -> --gn-color-secondary
- amber/orange highlights -> --gn-color-accent
- text greys -> --gn-color-text-{light,medium,dark}
- panels -> --gn-surface-panel; elevated tints -> color-mix over panel
- translucent overlays -> color-mix(in srgb, ..., transparent)

Deliberately literal: terminal deep bg #0f0f14 (darker than any token)
and the content-card image badge teal #89dceb (kit has no teal). File
type badges keep a categorical palette via nearest kit tokens.

Dead "UI kit overrides" block halved: kit 1.0 dropped hover icon
rotation, so only the app-owned chevron open-state flip remains.

Verified: vitest 111 passed, build OK, dev render matches W1 baseline

webclient: Backgrounds tab in artifacts panel + task toasts ...

- new Backgrounds tab: task list (running first, badges, per-tool icons)
  with a detail view (status, timestamps, sub-agent tokens, result/progress)
- GET /sessions/{id}/tasks snapshot endpoint: task_update events are not
  replayed on reconnect, so the client fetches the task list on session
  load/reload; live task_update entries are merged on top (chat.fetchTasks)
- terminal task_update no longer removes the entry — it marks it finished
  so the tab shows recent completions; _terminalTaskIds still blocks
  resurrection by a late running update
- toasts for background task start / finish (info / success / error) in
  the WS dispatch; silent for other sessions and unknown terminal ids
- persistent background-tasks chip removed (replaced by the tab); only
  the queued-messages chip stays
- fix invisible status text in terminal detail rows: filled .status-*
  backgrounds now scope to .terminal-status-badge only

webclient: virtualized message list (DynamicScroller) ...

- MessageList rewritten on vue-virtual-scroller DynamicScroller; only rows
  near the viewport mount (session switch 650-730ms longtask / DOM 31645 ->
  110-165ms / DOM 1-2.5k, zero freezes)
- scroller is keyed by session id: message ids repeat across sessions, so
  teardown drops the measured-size cache on switch
- convergeToBottom watches the bottom hold for a bounded window after
  landing (lazy row measurements nudge scrollHeight late); yields to wheel/
  pointer/touch input instead of scroll-position heuristics, which the
  scroller's own adjustments would trip
- renderMarkdown gets a byte-capped LRU memo so markdown remount cost is
  amortized while virtualized rows recycle
- removed dead .message-list/.message-list-inner styles

webclient: loading indicators where the UI looked frozen ...

- session open: centered spinner in MessageList while chat.loading
- image paste/drop: imagesProcessing counter (chat store, shared);
  FilePreviewStrip shows spinner placeholder tiles where the resized
  previews will land
- file upload: indeterminate sliding bar instead of the fake static 60%
- send → run start gap: "Sending…" hint with spinner, cleared on
  stream_start / message_queued / stream end / error / session switch
- content-card images: skeleton with spinner until @load (reset on src
  change); wrapper keeps min-height while the img is empty

vitest 96 passed.

webclient: background task chip, id-first tool matching, queued badge ...

- toolIndex (tool_call_id → card): exact matching for parallel batches and
  late events after stream_end; legacy name+pending fallback kept
- bare tool_call synthesizes a card so results are never lost
- task_update: backgroundTasks chip above composer + steps appended to the
  spawning tool card (parent_tool_call_id binding)
- message_queued badge, terminal_opened dispatch
- new BackgroundTasksChip component, task_update step rendering in ToolCard

Fix 19 issues found in full codebase review ...

Backend:
- Stop session auth bypass: require auth for owned sessions, reject anonymous with 401
- upload_file: stream chunks directly to disk instead of buffering in RAM
- MCP config: validate name against path traversal regex
- auth deps: cleanup stale refresh locks periodically
- auth routes: expire mobile auth states after 10 min to prevent unbounded growth
- compressor: meta-summarize existing summaries before compression; preserve assistant content when tool_calls present; rewrite hard_truncate to keep whole turns
- orchestrator: configurable WS replay buffer size; async cleanup/remove_websocket/clear_busy; fix run_recall ContextVar order to avoid deadlock on _build_agent failure; await cleanup in finally
- agent: persist image_msg in session.messages; remove archived messages from session after archive; remove duplicate StreamStopped yield on tool stop
- websocket: try/except around create_task with cleanup on failure; await remove_websocket

Frontend:
- App.vue: hashchange listener lifecycle in onMounted/onUnmounted
- MessageList.vue: passive scroll, flash timeout cleanup, archive scroll snapshot
- InputBar.vue: 300 ms debounce on draft save to localStorage
- SessionList.vue: remove :key from DynamicScroller to avoid remount jitter

Tests: 422 passed, 1 skipped

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Add archive message pagination, configurable WS replay buffer ...

Backend:
- Add archive_threshold to Session model and getSession response
- Add next_before_seq to archive endpoint for cursor pagination
- Make WS replay buffer size configurable via WS_REPLAY_BUFFER_SIZE

Webclient:
- Add getArchivedMessages API function
- Add archive pagination state and loadArchivedMessages to chat store
- MessageList: auto-load older messages on scroll-to-top with scroll
  position preservation and loading spinner

Docs: update config.md with new env vars

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Extract ContextCompressor, fix STL viewer, expand test suite, add architecture audit docs ...

- Extract ContextCompressor from agent.py (Step 1 of god-object refactor)
- Add retry + hard-truncate fallback logic to ContextCompressor
- Add unit tests: agent loop (14), compressor (18), KV store (8),
  auth encrypt (3), auth deps (13), todo/scratchpad/image_view/memory
- Fix WebGL STL viewer: allow-same-origin sandbox + graceful fallback
- Add CompressionStarted event and client-side compression notice
- Add docs/architecture_weak_spots.md and plan_01_god_object_agent.md
- Update test_events.py and test_agent_context_size.py for new logic

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

fix(recall): stabilize scheduled callback system and improve UX ...

Backend fixes:
- stop_session now stops headless recall runs via _busy_sessions dict
- _fire_recall sets user ContextVars so tools work correctly
- MaxIterationsReached treated as success, not failure
- skip_next_recall uses GREATEST(trigger_at, now) for overdue recalls
- schedule_recall rejects past trigger times
- timezone offset double-adjustment fixed for aware datetimes
- _fire_recall registers _AgentRun for reconnect/replay support
- session_sync race with stream_start fixed

Frontend improvements:
- Recall banner moved to ChatHeader with live Cancel/Skip buttons
- Recall messages styled with is_recall flag and badge
- Real-time recall updates via WebSocket (recall_update events)
- Recall filter moved to sessions-header as toggle button
- Session list shows clock icon for sessions with pending recall
- Empty state messages for empty/filtered session lists
- Fixed missing api import in ChatHeader.vue

Tests:
- Updated scheduler_loop tests for _busy_sessions dict change

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Add self-recall (scheduled callback) system ...

Core features:
- schedule_recall tool: once/recurring/immediate callbacks
- manage_recall tool: cancel/skip/list scheduled recalls
- Natural-language time parser (ISO, relative, "tomorrow at 09:00")
- PostgreSQL-backed RecallScheduler with lazy pool init
- Background recall_scheduler_loop with asyncio.Semaphore(3)
- _busy_sessions guard prevents user messages during headless runs
- Agent.run() preserves thinking field for session history visibility
- API endpoints: GET/DELETE/POST for session recall, admin list
- Frontend: recall badge, filter, cancel/skip in sidebar and chat header
- Tests: parser, scheduler CRUD, tools, API, scheduler loop (53 tests)
- Manuals: schedule_recall.md and manage_recall.md

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Fix search flash for assistant messages, move spinner, hide highlights ...

- MessageList: pass isFlashing prop to UserMessage/AssistantMessage instead
  of applying msg-flash on wrapper div. scrollToMessage now uses rawIndices
  to map backend match_index to grouped message index.
- UserMessage: add isFlashing prop, apply msg-flash to msg-user-bubble
- AssistantMessage: add isFlashing prop, apply msg-flash to msg-assistant-content
- ChatStore: add rawIndices to built messages (user, summary, assistant)
- AppSidebar: move spinner into sessions-label, remove from search field
- SessionList: accept searchOpen prop, pass empty searchQuery when closed
  so highlights disappear after selecting a session
- Tests pass (51/51)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Polish session search UX: GnSearchField, spinner, flash timing ...

- AppSidebar: use GnSearchField from gnexus-ui-kit, spinner during search,
  search toggle button always visible in sessions-header, hide search on select
- MessageList: fix msg-flash timing — make content visible before scrolling,
  extend flash duration to 2.5s with background + brightness
- CSS: enhance msg-flash keyframe animation
- Tests pass (51/51)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>