Add navi_ui form component with client-side validation ...

- Add Form UI component schema in navi/mcp/ui_server/components/form.py
- Support text, textarea, number, email, url, select, multiselect, checkbox, date fields
- Implement hidden user message mode for form submissions (is_display=False, is_context=True)
- Add WebSocket form_submit handling and _start_agent_run helper
- Render forms client-side with real-time JS validation in webclient
- Submit once guard via localStorage and replace form with read-only summary
- Provide wsSend via Vue provide/inject in ChatArea
- Add tests for backend form component, websocket form_submit, and frontend Form.vue
- Update docs/tools.md and docs/websocket.md
- Build production webclient dist

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

Add internal navi_ui MCP server for structured UI components ...

- Add navi/mcp/ui_server.py: FastMCP streamable_http server on port 8001
  exposing render_component(component_name, payload, session_id).
- Start server in main lifespan before container creation so McpManager can
  connect; wire orchestrator once container is ready; clean up on shutdown.
- Add env settings NAVI_UI_MCP_ENABLED/HOST/PORT.
- Add mcp_servers.d/navi_ui.json config with the 'ui' tool group.
- Frontend: dispatch ui_component websocket event, store in chat.js, render
  placeholder UiComponentCard inside AssistantMessage.vue.
- Unit tests for ui_server tool and chat.onUiComponent.

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

Add terminals tab to ArtifactsPanel with live output ...

- New "Terminals" tab in ArtifactsPanel showing active terminal sessions
- List view: name, description, status badge (busy/idle/closed)
- Detail view on click: PID, command, CWD, uptime, background flag, live output
- chat.js: capture terminal metadata from tool_start and tool_call events
- Merge terminal metadata (open/status/list/close) into reactive terminals store
- Vue reactivity: immutable updates for terminals map
- Build webclient and verify all backend tests pass

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

Fix terminal review issues: security, lifecycle, reactivity ...

- TerminalManager.open now accepts exec_tokens to use create_subprocess_exec
  for restricted commands instead of always using shell
- Fix kill/terminate order: SIGTERM first, SIGKILL fallback
- Pop closed sessions from _sessions dict to prevent memory leak
- Add terminal_manager.shutdown() to AppContainer.shutdown()
- Wait for reader tasks in foreground open before returning output
- Add _MAX_TERMINALS_PER_SESSION limit (10)
- Wrap cleanup_idle tasks in _close_one_safe with error logging
- send_input catches BrokenPipeError/ConnectionResetError specifically
- Foreground terminals auto-close after gathering output
- Vue reactivity: replace terminals object immutably instead of mutating
- onTerminalClosed marks matching tool card as no longer pending
- Update tests for new behavior (foreground auto-close, max limit)

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

Add persistent multi-session terminal tool with background support ...

- New TerminalManager module: named subprocess sessions per Navi session,
  background readers, event-sink streaming, idle auto-cleanup
- Refactor terminal tool to multi-action: run, open, close, list,
  status, send_input
- Add TerminalOutputDelta and TerminalClosed events for streaming
- Wire TerminalManager into AppContainer, orchestrator, and registry
- Persist session_metadata in Session model and pg_session_store
- Close all session terminals on session delete
- Webclient: handle terminal_output/terminal_closed WS events,
  display live terminal output in tool cards
- Update unit tests for new terminal actions

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

Fix reloadSession race that orphans streamingMsg ...

reloadSession checked streaming.value at entry but api.getSession is
async. While awaiting, onStreamStart could set streaming=true and push
the assistant message into messages.value. When reloadSession resumed it
replaced messages.value with the stale server snapshot, evicting the live
streaming message. All subsequent deltas and tool cards went to the orphan
and were invisible.

Fix: re-check streaming.value after the await before mutating messages.

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

Fix delta loss during thinking-to-text transition and streaming orphaning ...

Backend:
- agent.py _consume_stream: replace elif with if so a single chunk can
  carry both the final thinking fragment AND the first text delta.
  Fixes the 'first token lost after tools' bug.

Frontend:
- chat.js reloadSession: bail out early when streaming.value is true.
  Replacing messages.value mid-stream orphans streamingMsg, breaking
  Vue reactivity for all subsequent deltas and tool cards.
- useWebSocket.js session_sync handler: add !chat.streaming guard
  before calling reloadSession.

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

Fix streaming message orphaning and duplicate message keys ...

chat.js:
- reloadSession: during an active stream, replace the last built assistant
  message with the live streamingMsg instead of discarding it on text match.
  This fixes the root cause of invisible first messages and flickering tool
  cards when session_sync arrives mid-stream.
- buildMessageList: remove assistantCounter and use firstIdx as the message id
  to avoid duplicate Vue keys (e.g. user h_0 and assistant h_0).

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>

Fix MCP tool spinner bug: match tool_started → tool_call by tool_call_id ...

- Add tool_call_id field to ToolStarted and ToolEvent dataclasses
- Pass tc.id as tool_call_id from agent.py, subagent_runner.py, and tool_executor.py
- Update frontend chat.js onToolStarted/onToolCall to match cards by toolCallId
  with fallback to name-matching for backward compatibility

Closes spinner issue where LLM short name ("search_docs") didn't match
resolved MCP name ("mcp__gnexus_book__search_docs").

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>

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>

Add session search across messages with backend + frontend ...

Backend:
- GET /sessions now accepts `search` query param
- _session_summary computes match_indices and match_preview from messages
- pg_session_store: messages ILIKE added to search_list and count_all
- In-memory store: search_list also filters by message content

Frontend:
- AppSidebar: search toggle icon + debounced input, Ctrl+K shortcut
- SessionItem: highlight matching text, show match_preview from search
- SessionList: pass searchQuery to SessionItem
- SessionsStore: searchQuery/searchActive state, setSearch/clearSearch
- API layer: getSessions accepts search param
- MessageList: scroll to target message + brightness flash animation
- ChatStore: loadSession accepts targetMessageIndex, scrollToMessageIndex ref
- CSS: msg-flash keyframe animation in app.scss
- Tests updated for new getSessions signature

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

Persist uploaded files in messages, live file tree updates, and UI polish ...

Backend:
- Add `files` field to `Message` model so uploaded file metadata survives page refresh
- Pass `files` through websocket handler → `agent.run_stream` / `agent.run`
- `list_tools`: make `profile_id` required; return error instead of all-tools fallback

Webclient:
- Call `fetchFiles()` after successful file upload for immediate Files tab update
- Live refresh file tree on filesystem (write/edit/append/mkdir/rm/cp/mv), terminal, and code_exec tool calls
- Add manual refresh button (desktop) and pull-to-refresh (mobile) to Files tab
- Fix live link updates: move regex creation inside per-message loop to avoid lastIndex state leak
- Restore full profile name text next to avatar in ChatHeader; hide avatar in header
- Fix mobile ArtifactsPanel: collapse tab text labels so close button fits with 3 tabs

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

Add session file directory listing endpoint and Files tab in ArtifactsPanel ...

Backend:
- New GET /sessions/{session_id}/files endpoint (recursive, max depth 10)
- Includes hidden files, returns {path, size, is_dir, modified_at}
- Path traversal protection via resolve() + relative_to(base)
- list_session_files() helper in session_files.py

Webclient:
- Third "Files" tab in ArtifactsPanel alongside Artifacts and Links
- Tree display with depth-based indentation
- File type icons by extension (image, video, code, etc.)
- Download and inline-open actions per file
- Fetch on session load/reload via chatStore.fetchFiles()

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

Add deterministic line-based file editing (edit_lines), rating UI fix, and session refresh ...

- filesystem.py: add edit_lines action (deterministic line ops via operations array)
           + numbered param for read (1-based line numbers in output)
           + clarify four editing modes in tool description
- chat.js: fix rating IDs for streaming messages (assign h_ ID on stream_end)
- SessionList.vue: mobile pull-to-refresh with PTR_THRESHOLD=80
- AppSidebar.vue: desktop refresh button next to Conversations header
- planning.py: knowledge source assessment in Phase 1
- debug panel: MCP servers tab + resolved tools per profile
- NAVI.md: reposition as neutral quick-reference

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

Remove erroneous vue-router from webclient ...

vue-router was accidentally left over from an earlier attempt to embed
admin features in the main client. It broke hash-based session routing
and rendered app-main empty. Revert to direct component rendering in
App.vue with native hashchange handling.

- Remove vue-router dependency and src/router/index.js
- Revert main.js to createApp without router
- App.vue: render WelcomeScreen/ChatArea directly, restore hashchange handler
- chat.js: revert hash format to raw session id
- api/index.js: keep 401 → authStore.user = null (login overlay fix)

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

Fix blank session rendering and 401 auth handling ...

- Install missing vue-router dependency (was imported but not in node_modules,
  causing app init failure and empty app-main)
- Add :sessionId? route param and HomeView watcher for hash-based session routing
- Update hash format to '#/' for Vue Router compatibility
- Add 401 handling in api/index.js to invalidate auth and show login overlay
- Add error handling in loadSession and WelcomeScreen start to prevent stuck UI

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

Refine 3D modeler workflow

Improve content publishing UX

Add webclient unit tests (Vitest) — 47 tests ...

- Vitest + @vue/test-utils + happy-dom setup
- api/index.test.js: 8 tests for fetch wrapper, verbs, errors, FormData
- stores/chat.test.js: 23 tests for buildMessageList, WS handlers, load/clear
- stores/sessions.test.js: 6 tests for fetch, create, delete, pin, preview
- stores/profiles.test.js: 3 tests for fetch, auto-select, lookup
- composables/useWebSocket.test.js: 7 tests with MockWebSocket
- Export buildMessageList from chat store so tests can verify message parsing
- Update docs/testing.md with webclient stack, layout, and commands

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

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>

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>

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>

Fix session switch race: connect WS after REST fetch completes ...

loadSession was setting currentId before the REST fetch, which triggered
ws.connect() immediately. If WS replay arrived before the REST response,
onStreamStart() would push a streaming message, then the REST response
would overwrite messages.value entirely — leaving streamingMsg pointing
to an orphaned object no longer in the array.

Fix: move currentId and location.hash assignment to after the REST fetch
so the WS connection is established only once messages are populated.

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

WebSocket event replay buffer for disconnect resilience ...

On reconnect to an active agent run the server now replays all events
emitted since the turn started, then switches to live forwarding.
This eliminates the gap where tool cards, thinking blocks and stream
deltas were permanently lost after a network blip.

Server (_AgentRun):
- events: list[dict] buffers every serialised agent event
- broadcast() serialises and appends before putting in subscriber queues
- reconnect flow: subscribe → replay_count snapshot → stream_start →
  replay events[0:replay_count] → live _stream_to_client

Client:
- onStreamStart() removes the frozen ghost message instead of marking
  done=true, so replay cleanly rebuilds the message from scratch
- replayMode flag suppresses animations during replay
- onReplayStart/onReplayEnd handlers set/clear the flag and restore
  animate on the message once live events resume

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>

Planning debug panel, todo auto-populate, scratchpad/persona improvements ...

- Planning debug panel: new Planning tab in debug/index.html shows raw
  phase 1/2 outputs and token counts per planning run, stored in
  session.planning_logs (new column in both SQLite and PostgreSQL)
- New GET /sessions/{id}/planning API endpoint
- PlanningDebugData internal event wires _run_planning() output into
  session storage; never forwarded to WebSocket clients
- Phase 3 (plan critic) disabled — to be reworked with reflect integration
- Todo tool: auto-populated from plan steps after phase 2; model only
  needs to call update/view, not set
- Scratchpad: clarified description and persona instructions; removed
  context_transfer from user-facing docs (internal mechanism only)
- web_search: switched to ddgs package, SearXNG as primary backend,
  DDG html-only fallback; added find_up action to filesystem tool
- Persona: added SCRATCHPAD and TODO sections with clear usage rules;
  added NAVI.md project context instructions
- chat.js: fixed subagent planning event fallthrough into parent UI;
  statusLabel cleared on first stream delta

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