Rename MCP tools to mcp:server:tool format and restore human-readable names ...

- Core naming: mcp_server_tool → mcp:server:tool (colon-delimited)
- navi-web tools: search/view/request → web_search/web_view/http_request
- navi-3d tools: compile_scad/render_stl/lint_scad (unchanged names)
- Updated all profile configs, system prompts, docs, manuals, tests
- Added new lint_scad.md manual
- Fixed modeler_3d prompt stale references (scad_lint, model_3d, render_3d)
- All 240 tests pass

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

Clean up remaining web_search / web_view / http_request references ...

- Deleted stale source files: navi/tools/web_search.py, web_view.py,
  http_request.py (no longer imported or registered).
- Updated system_prompt.txt in all profiles (secretary, server_admin,
  discuss, modeler_3d subagent) to reference mcp_navi-web_* tool names.
- Updated key_tools in developer, secretary, server_admin config.json.
- Updated docs (tools.md, profiles.md, api.md) to reflect MCP migration.

Tests: 240 passed.

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

Rename navi-web MCP tools and compact search output ...

- web_search → search, web_view → view, http_request → request
  This removes the redundant 'web' prefix from tool names in the
  navi-web MCP server, making them cleaner: mcp_navi-web_search etc.

- Compact search output: output string now contains only
  [Source] + [N] Title — URL, without duplicating the body snippet.
  Full results with body/description remain in metadata for
  programmatic use.

- Updated mcp_servers.json groups and all profile configs.

Tests: 240 passed.

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

Migrate web tools (web_search, web_view, http_request) to navi-web MCP server ...

New MCP server: mcp-servers/navi-web/
- app/search.py    — SearXNG primary, DDG fallback, Brave tertiary
- app/browse.py    — Playwright headless browser page extraction
- app/request.py   — httpx raw HTTP requests
- app/mcp_server.py — FastMCP entry point with stdio transport
- pyproject.toml   — deps: mcp, httpx, ddgs, playwright, pydantic

Changes:
- Added "navi-web" block to mcp_servers.json (stdio transport)
- Removed web_search, web_view, http_request from built-in registry
- Removed them from navi/tools/__init__.py
- Removed them from enabled_tools / subagent_tools in all profiles
- Added "navi-web": ["search", "browse", "request"] to mcp_servers
  in all profiles (developer, secretary, server_admin, tool_developer,
  modeler_3d, discuss)

Tests: 240 passed.

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

Migrate 3D modeling tools to standalone MCP server navi-3d ...

Phase 0 — Fix MCP error propagation:
- McpClient.call_tool now returns (output, is_error) tuple
- McpTool.execute sets success=False when MCP reports isError=True
- Fixes silent failures where MCP errors looked like success

Phase 1 — Create mcp-server-navi-3d:
- New standalone MCP server in mcp-servers/navi-3d/
- Tools: compile_scad, render_stl, lint_scad
- Session-scoped path resolution via SESSION_FILES_DIR env
- Anti-escape validation for security
- Includes tests/unit/test_scad_analyze.py

Phase 2 — Remove from Navi core:
- Deleted navi/tools/{model_3d,render_3d,scad_lint}.py
- Removed from registry.py builtins and navi/tools/__init__.py
- Updated pyproject.toml testpaths to exclude mcp-servers/

Phase 3 — Wire into Navi config:
- Added navi-3d block to mcp_servers.json (SSE on :8002)
- Updated modeler_3d profile: mcp_servers + updated system_prompt
- All old tool names replaced with mcp_navi-3d_* equivalents

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

Increase max_iterations across all profiles ...

- developer: 45 → 100
- discuss: 12 → 30
- modeler_3d: 50 → 70
- secretary: 35 → 70
- server_admin: 40 → 100
- tool_developer: 35 → 100

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

Add auto-reconnect to MCP client on call_tool/list_tools ...

- McpClient._ensure_connected() reconnects if session is dead
- list_tools() and call_tool() try reconnect + one retry on failure
- Fixes crash when MCP server restarts between calls

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

Wire MCP manager into sub-agent (spawn_agent) so MCP tools are available to sub-agents ...

- SpawnAgentTool: add mcp_manager parameter and pass it to Agent
- main.py: patch _mcp_manager into spawn_agent after MCP connect

Fixes: tool 'mcp_gnexus-book_*' not found in sub-agent sessions.

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

Handle MCP tool aliases robustly

Clarify knowledge persistence prompts

Integrate proactive knowledge capture into planning and persona ...

- Phase 1 planning: add KNOWLEDGE CAPTURE section to prompt
- Phase 3 planning: add knowledge persistence rule with target selection
- Persona: add "search before save" deduplication instruction
- MCP gnexus-book: add persistence guidance for discovered facts

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

Auto-inject relevant memory facts into LLM context on every user turn. ...

Semantic search against the vector memory store runs in parallel with
context provider collection. Number of injected facts scales with
message length (1–3) to reduce noise on short queries. Guardrails:
min length gate, per-turn deduplication, and structured logging at
info level for observability.

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

Remove dead LLMBackend.stream() method ...

The method was defined on all backends (Ollama, FallbackOllama, OpenAI)
and in the base LLMBackend interface, but was never called by agent.py
or messages.py. stream_complete() covers all streaming use cases.

- navi/llm/base.py: remove abstract stream() method
- navi/llm/ollama.py: remove OllamaBackend.stream()
- navi/llm/fallback.py: remove FallbackOllamaBackend.stream()
- navi/llm/openai_backend.py: remove OpenAIBackend.stream()
- docs/tech_debt_review: mark item 54 as fixed

236 tests passing.

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

Fix ollama_backends / FallbackOllamaBackend issues ...

- registry.py: always use FallbackOllamaBackend (unified backend).
  Enables model priority lists in all deployments, not just multi-server.
- agent.py: add missing think=profile.think_enabled to run() (REST endpoint).
- compressor.py: fix model param type (str → list[str] | str | None).
- fallback.py: harden load_servers_from_file against missing/bad JSON files
  and entries without host. Add clear_blacklists() for manual reset.
- admin.py: add POST /admin/ollama/clear-blacklists endpoint.
- tech_debt_review: document dead stream() methods.
- tests: add tests for single-server fallback, bad file handling,
  missing host skipping, and blacklist clearing.

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>

Fix graceful MCP disconnect during server shutdown ...

- McpClient.disconnect(): catch CancelledError / RuntimeError from
  anyio SSE transport teardown
- McpManager.disconnect_all(): shield gather from CancelledError
- main.py _on_shutdown(): catch CancelledError and RuntimeError
  explicitly (BaseException, not Exception)

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

Inject MCP server instructions into system prompt ...

- McpClient: collect instructions from MCP initialize handshake
- McpServerConfig: add 'instructions' field for Navi-side overlay
- McpManager.get_instructions(): merge server + config instructions
- ContextBuilder: new _mcp_context_msg() injects MCP server
  descriptions into every LLM context as a system message
- Agent passes mcp_manager to ContextBuilder
- mcp_servers.json: add overlay instructions for gnexus-book

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

Fix MCP tool lookup in websocket handler and tests ...

- websocket.py: pass mcp_manager to Agent(), with graceful fallback
  if MCP connection fails
- conftest.py: mock get_mcp_manager() in tests to prevent SSE
  connection attempts against real servers

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

Refactor MCP integration: server groups in profiles ...

- mcp_servers.json: add 'groups' (read/write/admin) for gnexus-book
- AgentProfile: new 'mcp_servers' field (server_name -> group list)
- Profile loader: parse and persist 'mcp_servers' in config.json
- Agent._tool_list(): expands mcp_servers into concrete tool names
  via McpManager.resolve_group(), wildcard '*' supported
- /agents/profiles API: includes 'mcp_servers' in response
- Profiles no longer list individual mcp_ tools in 'enabled_tools'
- discuss: gnexus-book read group
- server_admin: gnexus-book read+write+admin groups

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

Connect gnexus-book MCP server and enable in profiles ...

- mcp_servers.json: SSE transport to 192.168.1.170:8001
- server_admin profile: all 16 gnexus-book tools
- discuss profile: read-only gnexus-book tools (docs + inventory)

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

Add MCP server support and fix memory tools user isolation ...

MCP integration:
- New navi/mcp/ package: client, manager, config, tools
- ToolRegistry learns register_external() for MCP tools
- reload_tools reconnects MCP servers on hot reload
- New built-in mcp_status tool
- Startup/shutdown wiring for MCP connections
- 12 new tests (unit + integration with real stdio server)

Memory tools fix:
- memory, memory_save, memory_search, memory_forget now read
  current_user_id from tool context and pass it to MemoryStore
- Fixes invisible facts for authenticated users

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

Add profile editing to admin panel ...

Backend:
- navi/profiles/loader.py: add save_profile_to_dir() to write config.json
  and system_prompt.txt back to disk
- navi/core/registry.py: add ProfileRegistry.update() for in-memory updates
- navi/api/routes/admin.py: new endpoints GET /admin/profiles/{id} and
  PUT /admin/profiles/{id} for reading and saving full profile config

Admin panel:
- Profiles table: add Edit button per row
- Drawer form with sections: Basic, Model & Generation, Thinking,
  Planning, Sub-agent, Tools, System Prompt
- All fields editable inline (text inputs, checkboxes, textareas for lists)
- Save via PUT request, updates both disk and in-memory registry without
  server restart

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

Style OAuth bridge page with gnexus UI kit design system ...

Redesigned /auth/mobile-done to match the Navi webclient visual
language (Tokyo Night cyberpunk palette):
- Dark background (#16161E), muted panel with green success accent
- Squared corners, uppercase headings, wide letter-spacing
- Spinner during auto-redirect, fallback button with left accent border
- Full hover states matching .btn-success from the kit

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

Detect Android OAuth client via User-Agent header ...

WebView always sends NaviAndroid/1.0 in the HTTP User-Agent, while
navigator.userAgent in JS is unreliable. Backend now detects the
Android platform from the UA header when the ?platform query param is
absent, ensuring the bridge-page flow works regardless of webclient
version.

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

Improve OAuth bridge page with Chrome Intent URL + fallback button ...

/auth/mobile-done now tries Chrome Intent URL for automatic app
opening, and falls back to a styled button if the browser blocks
automatic navigation to custom schemes.

- Auto-redirect: intent://...#Intent;scheme=navi;package=com.navi.client;end
- Fallback UI: card with \"Open Navi App\" button after 1.5s timeout
- Works in both Chrome (auto) and DuckDuckGo (manual tap)

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

Add Android deep-link OAuth bridge for WebView auth ...

Problem: Android WebView opens OAuth in external browser (Chrome).
After successful login, cookie stays in Chrome and WebView remains
unauthenticated because cookies are not shared between apps.

Solution: bridge page flow that avoids cookies entirely for mobile.

Backend:
- /auth/login accepts ?platform=android and ?return_to params
- /auth/callback detects android via state metadata, skips cookie,
  redirects to /auth/mobile-done?sid=<session_id>
- /auth/mobile-done renders HTML that deep-links to navi://auth/callback

Webclient:
- login() detects NaviAndroid UA and adds ?platform=android

Android:
- MainActivity: handle incoming navi:// intent in onCreate and onNewIntent,
  set cookie via CookieManager, reload WebView
- AndroidManifest: add intent-filter for navi://auth/callback and
  singleTask launchMode

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

Add per-user sessions and memory filters in admin panel ...

Backend:
- GET /admin/memory now accepts user_id query param to filter facts
  for a specific user instead of returning the global view.

Frontend:
- Users table now has "Sessions" and "Memory" buttons per row.
- Clicking "Sessions" switches to Sessions tab and pre-fills search
  with the user id.
- Clicking "Memory" switches to Memory tab and passes user_id to the
  API, showing only that user's facts.
- Manual tab clicks reset filters (search / userId) so the view
  returns to unfiltered state.

Docs:
- docs/api.md updated with user_id param for GET /admin/memory.

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

Fix admin memory showing 0 facts; add pagination/search/sort ...

Bug fix:
- get_all_facts(user_id=None) was filtering for user_id IS NULL only,
  so admin panel showed 0 facts when facts had user_ids set.
- Added all_users parameter to get_all_facts and fact_count.
- Admin endpoint now passes all_users=True to return all facts.

Memory pagination:
- Extended get_all_facts with offset, search, sort_by, sort_order params.
- Extended fact_count with search and all_users params.
- /admin/memory endpoint now accepts limit, offset, search, sort_by,
  sort_order and returns {total, limit, offset, items}.

Admin panel frontend:
- Added server-side search with debounce for memory facts.
- Added sortable column headers (category, key, source, confidence, updated).
- Added pagination controls (prev/next, page size selector).
- Switched memory display from grouped tables to flat sortable table.

Tests:
- Added unit tests for get_all_facts(all_users=True) and
  fact_count(all_users=True).
- All 219 tests pass.

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

Add pagination, search, and sorting to admin sessions ...

Backend:
- Add count_all and search_list abstract methods to SessionStore
- Implement count_all and search_list in PgSessionStore (SQL with ILIKE)
- Implement count_all and search_list in InMemorySessionStore
- Update /admin/sessions to accept limit, offset, search, sort_by, sort_order
- Return {total, limit, offset, items} from /admin/sessions

Frontend:
- Add search input for sessions in admin panel
- Add clickable sortable column headers with asc/desc toggle
- Add pagination controls (prev/next, page size selector, item count)
- Debounce search input (300ms)

Tests:
- Add integration tests for pagination, offset, search, and sorting
- All 217 tests pass

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

Fix memory system bugs: deterministic summary id, skip legacy extraction ...

- _summary.py: replace non-deterministic hash() with zlib.crc32 so
  summary id stays stable across server restarts, preventing duplicate
  summary rows.
- extractor.py: skip memory extraction for legacy sessions (user_id=None)
  — ON CONFLICT(user_id, category, key) does not catch NULL duplicates
  in PostgreSQL (NULL != NULL).
- sessions.py: _process_stale_sessions skips legacy sessions.
- _facts.py: remove dead code (user_clause/user_param variables).
- test_extractor.py: add user_id to test sessions + new test for
  legacy session skip.

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