Stability fixes batch — tech debt review 2026-04-29 ...

Critical:
- Concurrent WS run race guard (#1)
- Tool task cancellation on generator teardown (#2)
- StopAsyncIteration kills fallback chain (#3)
- Session loading race with _lastLoadId guard (#4)
- ContentCard .match() crash on non-string result (#5)
- Image data type guard in buildMessageList (#6)

High:
- Cap WS replay buffer at 500 events (#7)
- Deduplicate memory extraction task with asyncio.Lock (#9)
- TTL-based fallback blacklisting (5 min) (#10)
- Subagent tool exception isolation (#11)
- Inline image size/count validation on WS (#12)
- Clean up orphaned file on DB insert failure (#13)
- Deep watch streamingMsg for auto-scroll (#14)
- WS_SCHEME wss:// support for HTTPS (#15)
- Sending guard against duplicate message sends (#16)
- Global unhandledrejection listener in API layer (#17)

Medium:
- Cap planning_logs at 20 entries (#22)
- Store cleanup_loop task reference (#23)
- BaseException → Exception in _run_with_sentinel (#24)
- Propagate SystemExit in agent loop (#25)
- Configurable output_reserve_tokens (#26)
- Always reloadSession on session_sync (#30)
- FIFO queue for confirm dialogs (#31)
- Reset body.overflow on ImageLightbox unmount (#32)
- try/finally in fallback copy (#33)
- _isConnecting guard in WS send() (#34)

Low:
- Lazy-init deps.py singletons (#36)
- Replace __import__ with direct imports (#38)
- Preserve token count 0 in ollama.py (#39)
- Clear orphaned streamingMsg on reconnect reload (#43)
- Escape single quote in UserMessage (#44)
- Polyfill-free findLast replacement (#48)
- Match <table> tags with attributes in markdown (#49)
- Attach copy buttons only when msg.done (#50)
- Fix hasMeta falsy-0 bug (#53)

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

Fix system prompt leakage into chat history; polish content cards ...

Backend:
- websocket.py + agent.py: separate user-visible display_message from
  LLM user_message. System hints (image/file attachments) no longer leak
  into session.messages and appear after page reload.
- main.py: add ensure_tables() on startup so session_content table is
  created before first publish.
- profiles: add kimi-k2.6:cloud to all model lists as fallback.

Frontend:
- ContentCard.vue: remove border-radius, add scrollbar styles, fix
  metadata fallback parsing so cards survive page reload.
- content-viewers/*.html: add matching scrollbar styles.

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

Add content hosting system with inline viewers ...

Backend:
- Add navi/content/ directory for published files
- Add content_store.py with publish/list/delete/cleanup functions
- Add content_publish tool for publishing files as viewable content
- Add /content static file mount in main.py
- Add /content-viewers mount for viewer pages
- Extend ToolEvent with metadata field
- Forward metadata through websocket tool_call events
- Update Agent to include metadata in ToolEvent

Frontend:
- Add ContentCard.vue component for displaying published content
- Add viewer pages: stl.html (Three.js), svg.html, html.html, pdf.html
- Update AssistantMessage.vue to render ContentCard for content_publish
- Update chat store to preserve metadata in tool cards
- Update websocket protocol docs with metadata field

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

Add eval system Phase 1 — message feedback signal ...

Spec at docs/eval_system.md describes the full LLM-as-judge plan;
this commit lands only the in-app feedback layer:
- debug/eval/ Python package with EvalDB (asyncpg) and FastAPI router
  exposing /eval/feedback (set / clear / list)
- message_feedback postgres table keyed by (session_id, message_index)
- thumbs up / down on each completed assistant block in the webclient,
  optimistic update with rollback on failure

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Collapse thinking and plan cards by default ...

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Add discuss profile; responsive WelcomeScreen for 6+ profiles ...

- New 'discuss' profile: creative Q&A and idea discussion, temp=1.0,
  planning phase 3 only, tools: web_search/view, scratchpad, reflect,
  memory, image_view, todo
- WelcomeScreen mobile: 2-column grid for profile cards, compact logo
  (row layout with subtitle on second line), reduced padding/gaps

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

WelcomeScreen polish, root-path fix, docs update ...

- Move mobile sidebar button to top-left corner (no header bar backdrop)
- Show WelcomeScreen on / with no hash instead of auto-loading first session
- Docs: document Ollama multi-server fallback, model priority lists, OLLAMA_BACKENDS_FILE

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Fix WelcomeScreen: add with-icon, mobile sidebar toggle ...

- Add with-icon class to Start button
- Add mobile-only header with sidebar toggle (reuses chat-header +
  btn-sidebar-toggle styles, hidden on desktop via existing CSS)
- Wire toggle-sidebar event through App.vue

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Go to WelcomeScreen when active session is deleted ...

Previously deleting the active session would load the first session from
the list. Now it calls clearSession() which resets currentId to null,
and showWelcome now triggers on currentId === null (not just empty list).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Autonomous reasoning improvements: budget, anchoring, anti-stall, validation ...

- AgentProfile: per-profile thinking mechanics flags (think_enabled,
  iteration_budget_enabled, goal_anchoring, anti_stall, step_validation,
  planning_reflect, adaptive_replan) — all profiles updated in config.json
- Iteration budget: inject remaining iterations into context so model knows
  when to wrap up; urgency levels at ≤7 and ≤3 remaining
- Goal anchoring: inject original goal + todo state every N iterations to
  prevent drift on long tasks
- Anti-stall: two signals — no todo progress for N iterations, or identical
  tool calls repeated N times; warning injected into context
- Todo step validation: marking done requires a validation field describing
  how result was verified; failed gets a soft nudge with tip for re-planning
- stream_complete: add think param to base class, ollama and openai backends
- Summarizer: raise max_tokens 1024→3000, expand system prompt with
  user-preferences section and verbatim-value instructions
- Compression card: persist to session.messages (is_compression flag on
  Message), show expandable summary in webclient with markdown body
- ToolResult.to_message_content: always include output on failure so
  tracebacks and error details reach the model (fixes silent Error: None)
- Developer profile: fix subagent profile secretary→developer, add write_tool
  to subagent_tools, clarify write_tool vs filesystem in system prompt

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Route subagent planning events into spawn_agent card in the UI ...

Previously PlanningStatus/PlanReady had no is_subagent flag, so subagent
planning spinners and plan cards rendered as top-level Navi planning UI.

Backend:
- Add is_subagent field to PlanningStatus and PlanReady events
- _run_planning accepts is_subagent param, passes it through all yields
- run_ephemeral calls _run_planning with is_subagent=True
- websocket.py forwards is_subagent in planning_status and plan_ready messages

Frontend (chat.js):
- onPlanningStatus: if is_subagent, set planningLabel on the last spawn_agent
  card instead of msg.statusLabel
- onPlanReady: if is_subagent, push plan into spawn card steps and clear
  planningLabel; otherwise behave as before

Frontend (ToolCard.vue):
- Render subagent-planning-indicator (spinner + label) when planningLabel set
- Render plan cards inside subagent steps using the same plan-card pattern

Also includes leftover session changes: spawn_agent default 40 in description
and manual, updated manual content.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Planning phases, context compression, and tool improvements ...

Agent:
- Planning now a 3-phase async generator: Analysis → Execution plan → AIHelper critic
- Yield PlanningStatus events before each phase (UI progress labels)
- Phase 1 runs with think=True for deeper analysis
- Phase 2 includes available tool list so executor assignments are accurate
- Phase 3: independent critic pass validates and corrects TOOL: names against real tool list
- Planning converted from list return to async generator (fixes token accounting)

Backend:
- Context compression threshold: 80% → 70% to trigger earlier
- Compressor summary prompt: structured sections (goal, work state, key facts, outputs, errors)
- Terminal output capped at 5000 chars to prevent context flooding
- Web search: region=wt-wt for DDG, country=ALL for Brave, language=all for SearxNG
- Scratchpad: mandate writing a 'goal' section at start of multi-step tasks
- secretary max_iterations: 40→25, temperature: 0.7→0.5
- server_admin max_iterations: 40→20

Webclient:
- ThinkingCard strips <thought> XML tags leaked by Ollama
- planning_status WS event wired to chat.onPlanningStatus()

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Webclient UI improvements + backend fixes ...

Webclient:
- Draft persistence across page refreshes (localStorage, reactive watch)
- Image lightbox modal using UI kit classes on thumbnail click
- Copy button on user and assistant messages
- Selection reply toolbar: select assistant text → quote inserted into input
- User message rendering: proper HTML escaping, styled blockquote for > replies
- Markdown table fix: preprocessor to inject missing separator rows
- Planning status labels (rebuild dist)

Backend:
- Developer profile: enable subagent delegation, increase max_iterations to 35
- share_file: updated description + manual with absolute path requirement and URL sharing
- persona.txt: instructions for quote replies and GFM table format

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Persist context token count: return from API, restore on session load ...

- GET /sessions/{id} now returns context_token_count and max_context_tokens
  (max pulled from settings.ollama_num_ctx)
- loadSession() in chat store sets contextTokens/maxContextTokens from the
  response so ContextBar shows the last known fill level immediately on load,
  not only after the first new message
- Restore v-if guard on ContextBar (hides for brand-new sessions with 0 tokens)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Fix metrics: net token delta, subagent aggregation, ContextBar always visible ...

- run_stream: track _prev_tokens baseline before turn loop; compute net
  token cost as (context_tokens - prev) + subagent_tokens for per-message cost
- run_stream: intercept SubagentComplete in sink drain loop to accumulate
  subagent token and tool-call counts into the parent turn's totals
- run_ephemeral: already emitting SubagentComplete (from prior session)
- msg-meta-row: remove margin-left:auto from .msg-meta-time so time
  groups inline with elapsed/tools/tokens instead of floating right
- ContextBar: remove v-if guard so bar is always visible (not only after
  first LLM response with token data)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Add response metrics: elapsed time, tool calls, token count ...

Server:
- Message model: elapsed_seconds, tool_call_count, token_count fields
  (display-only, excluded from LLM context via exclude_none)
- StreamEnd event: carries same three fields
- agent.run_stream: tracks turn start time, counts ToolEvent completions,
  writes metrics onto the final assistant Message before saving to DB
- WebSocket: forwards metrics in stream_end payload

Client:
- chat.onStreamEnd: attaches elapsed_seconds, tool_call_count, token_count
  to the streaming message on completion
- buildMessageList: scans each assistant group for metrics from history
- AssistantMessage: renders .msg-meta-row below the response —
  timer icon + Xs · wrench icon + N tools · coins icon + Nk tokens · time
  (each item only shown if present; time pushed right via margin-left: auto)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

webclient: UI density improvements for session names and header ...

Sidebar:
- session-name: 12px → 13px (more prominent with real names)
- session-preview: 13px → 12px, clamp 2 → 3 lines (more content visible)
- session-actions buttons: 26×26px, gap 2px (narrower, more room for info)

Chat header (mobile):
- chat-header-info: column layout on mobile so title and profile badge
  stack vertically (flex-direction: column; align-items: flex-start)

ContextBar:
- Recomposed to single row: [track] [pct%]
- Track 100px → 60px, height 5px → 4px
- Full token counts moved to title attribute (hover tooltip)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

webclient: remove 'Planning' label from wait indicator; add scroll-to-bottom button ...

- Waiting indicator now shows only a spinner (text was misleading — model
  doesn't always plan before responding)
- Add floating scroll-to-bottom button that appears when scrolled >200px
  from bottom, disappears when near bottom; smooth fade+slide transition;
  positioned bottom-right (under thumb on mobile)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

webclient: fix history scroll by hiding content until positioned ...

Hide message-list-inner (opacity: 0) before scrolling to bottom,
then reveal it — so the user never sees the jump from top to bottom
on page reload or session switch. Content fades in already at the
correct scroll position.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

webclient: message timestamps, confirm dialog, layout and UX fixes ...

- Add useTime.js: relative time labels ("just now", "5m ago", HH:MM) with auto-refresh every 30s
- Show message timestamps below user bubbles and assistant replies
- Show session last_active time in sidebar below preview
- Add ConfirmDialog.vue + useConfirm.js: kit-styled modal confirm, wired to delete in SessionItem
- SessionList: switch RecycleScroller → DynamicScroller to support variable item heights
- SessionItem: remove fixed 74px height; show action buttons always on touch devices (hover: none)
- MessageList: constrain content to max-width 920px centered (message-list-inner, input-row)
- MessageList: replace TransitionGroup with plain v-for; animate only new messages via .msg-enter CSS class, history loads silently without scroll animation

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Fix scroll-to-bottom after page reload ...

Watch chat.loading instead of currentId for post-load scroll.
nextTick + rAF ensures browser layout is settled before scrolling.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

ThinkingCard: add chevron, open by default; plan loading indicator ...

- ThinkingCard: add ph-caret-down chevron (matches plan/tool card style),
  open by default (removed auto-close on thinking_end)
- AssistantMessage: show "Planning…" spinner when streaming but no content
  yet — gives feedback during the two-LLM-call planning phase
- app.scss: thinking-chevron styles, planning-indicator styles

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Migrate to Vue webclient; rename old client to old_webclient ...

- client/ → old_webclient/ (vanilla JS client preserved as reference)
- webclient/ — new Vue 3 + Pinia webclient (source + dist build)
- vite.config.js: outDir changed to webclient/dist/
- main.py: serve /assets and /images from webclient/dist/,
  index.html from webclient/dist/index.html
- .gitignore: exclude webclient/node_modules/, include webclient/dist/

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>