profiles: restricted profiles for ordinary users, and a role gate that holds ...

`is_admin_only` was checked in one place out of nine and was not read from
config.json at all, so all seven profiles were reachable by every account with
role `user`. The flag now lives in config.json — the file is the baseline, a
`profile_overrides` row still wins on top of it — and one predicate,
`admin_only_blocked`, is the single place the rule is expressed. The nine
surfaces that list, switch to, spawn or resolve a profile all consult it:
`POST /sessions`, the WebSocket, switch_profile, list_profiles, the system
prompt's "Available profiles" block, spawn_agent and the Synapse reaction
runner. The prompt cache is now keyed by (profile, role), so a user's prompt
can never be served an admin's profile list.

The seven existing profiles (developer, discuss, dispatcher, modeler_3d,
navi_code, secretary, server_admin) are marked admin-only. Three new ones take
their place for ordinary users: assistant, designer_3d and coder. They share one
native tool set — ssh_exec, peer, reload_tools, create_mcp_server, test_mcp_tool,
image_view and gmail are withheld — and differ only in system prompt, model and
MCP groups. navi-web's raw `request` group, and the whole of gnexus-creds and
tgclient, are withheld too.

MCP per-user keys gain the missing half of the rule: a server that declares a
`user_key` slot is refused to anyone but an admin who has no personal key, and
is left out of their tool list entirely, instead of quietly falling back to the
owner's credential and appearing as a tool that cannot work. The refusal names
the server and points at Settings.

Also closes `GET /agents/prompts`, which served every profile's system prompt to
anyone, with no user dependency at all.

The accepted residual risk is written down in docs/profiles.md: the working
directory is a convention, not a sandbox.

docs: mcp.md (per-user MCP keys BYOK), /mcp-keys endpoints, user_key config

docs: synapse integration guide, special sessions filter, new endpoints ...

- docs/synapse.md: full guide — gateway, reaction runner pipeline,
  notify tool, per-user settings, service sessions in the UI
- index/tools/config/api: entry point + built-in tools + env vars +
  GET /sessions special param + synapse REST/webhook endpoints

agent parallelism: background tools, bg spawn_agent, parallel tool batches, message queue ...

- backgroundable tools (terminal/ssh_exec/peer/spawn_agent/code_exec) detach
  via TaskManager with per-session/global/spawn caps, rate limit and TTL
- completion delivery both ways: task_update event (out-of-band) + pending
  notes injected into the next turn; tasks tool (list/check/wait/cancel)
- parallel tool-call batches (profile-level gate, off by default) with
  ToolStarted up-front, tagged event mux, call-order results, one save,
  plus dangling tool_call repair on session load
- user message queue instead of busy error: message_queued frame,
  back-to-back drain on the same socket, headless fallback on disconnect
- pin mcp<2 (v2 renames FastMCP with breaking API changes)
- docs: tasks.md (new), websocket/api/agent/config updates, tasks manual,
  spawn_agent background param, persona contract section

PWA: installable webclient, offline shell, web push ...

Installability:
- public/manifest.webmanifest (standalone, theme #16161E) + PNG icons
  generated from logo.svg (regular + maskable, served via /images mount)
- index.html: manifest link, theme-color, apple-touch-icon

Offline shell:
- hand-rolled sw.js (no workbox): navigation = network-first (3s race)
  with cached-shell fallback + background refresh (a stale cached shell
  would 404 on entry chunks after a deploy); /assets/* cache-first
  (content-hashed); /images/* cache-first capped; /api,/ws,/auth,/push,
  /content pass-through
- vite closeBundle plugin stamps __NAVI_BUILD_VERSION__ (digest of
  index.html + asset names) into dist/sw.js; sw.js served no-store so
  every deploy reactivates the SW and activation evicts old caches
- SW registration in main.js, PROD only (dev HMR untouched)
- OfflineBanner (useOnline composable) over the app shell

Web push (VAPID, pywebpush):
- navi/push/ package: push_subscriptions table (postgres, boot-time DDL),
  PushSubscriptionStore, PushService (async fan-out, to_thread sends,
  404/410 prunes dead endpoints, per-session cooldown)
- routes: GET /push/vapid-key, POST/DELETE /push/subscribe (auth-gated)
- trigger in orchestrator run_agent + run_recall: push on StreamEnd when
  no WebSocket client watches the session; fire-and-forget, never
  disturbs the run; anonymous fallback only when auth is off
- client: usePush composable + Notifications settings panel (enable/
  disable via PushManager.subscribe with the server VAPID key)
- notification click focuses the app at /#<session_id> (hash routing
  opens the right chat); payload body is a markdown-stripped <=140-char
  preview

NAVIVAPID keys empty = push fully disabled (graceful, like other optional
integrations). dist/ artifacts committed per repo convention.

Tests: pytest push store/service/routes/trigger (+23), vitest usePush
(83 webclient tests green). Full suite 1143 passed.

swarm stage 1: instance identity, PSK, hive registry, announce loop ...

- navi/identity.py: adjective-animal names + uuid in instance.json
  (generated at install, renameable by hand)
- navi/swarm.py: HiveAnnouncer - periodic POST /announce to the hive
  with non-blocking reachability tracking (transitional logs, /health
  export, hive_status context provider reports outages to the agent)
- hive/: standalone FastAPI address book (SQLite, port 8087, PSK via
  X-Swarm-Key with .swarm-key.previous rotation window, TTL online
  status, host from client IP, port from payload). Not installed or
  started by default - run manually on the main server.
- ports moved to 8099 (API) / 8098 (UI MCP)
- install.sh: PYTHONIOENCODING=utf-8 in the systemd unit, generates
  instance.json and .swarm-key on fresh installs

port: 8000/8001 -> 8099/8098 everywhere ...

navi runs on shared servers where 8000/8001 are usually taken. New
defaults: API 8099, navi_ui MCP 8098. Touched: config defaults
(navi_port, navi_ui_mcp_port, public_url, gnauth_redirect_uri),
navi-server launcher docs, env.template/.env.example, install.sh
health-check fallback, terminal client base_url, webclient dev configs
(useWebSocket, contentLinks, vite proxy), android url hint, docs.
Also made the navi_ui FastMCP constructor port settings-driven instead
of a hardcoded 8001 (it was overridden at start anyway).

deploy: one-command server bundle (dockerized postgres + systemd) ...

deploy/install.sh — everything in one command: prerequisite checks,
.env provisioning from env.template (generated DB password), dockerized
PostgreSQL (pgvector image, restart: always, bound to 127.0.0.1, vector
+ pg_trgm extensions), venv + pip install, a systemd unit with
Restart=always (the server lives from installation, per the roadmap
where these modules become each other's subagents), health check, and
navi-code/navi-server symlinks into PATH. Idempotent — safe to re-run.

Default deployed shape: web UI off, auth off, terminal client only.
Re-enabling the web panel later is editing .env + restart — nothing is
removed from the tree.

The deploy branch (next commit set) differs from master only by a
filled-in .env.

permissions: remove broken client-side gate; add backend design doc ...

The terminal-TUI permission gate was a race: _execute_tools_with_sink
emits ToolStarted and starts the tool on the backend immediately, so by
the time the client dialog appeared the destructive action had already
run -- 'deny' could only stop the session, not un-execute the tool. It
also existed only in the terminal TUI (webclient/android had nothing),
and the system-prompt 'Strict Confirmation' nudge was an unreliable
duplicate.

Remove the broken machinery for a clean slate and plan the real
replacement from zero:

- delete clients/terminal/tui/permissions.py, screens/permission_dialog.py
  and their tests
- strip tui_app.py (engine, _deny_tool, _show_permission_dialog,
  _confirm_shell_command, _stop_session_worker, on_permission_request,
  tool_started gate) and the PermissionRequest TUI event; !cmd now runs
  directly (user-typed, no agent gate)
- drop the 'Strict Confirmation' prompt rule from navi_code/developer/
  tool_developer
- add docs/permissions.md: authoritative backend gate design (engine +
  registry + event + endpoint + agent gate + postgres policy + global
  rules config, sub-agents gated) -- design only, not yet implemented
- update docs/index.md, navi_code_cli.md, profiles.md, testing.md

Until Phase 1 lands there is no destructive-action confirmation -- a
conscious period without the false security of the old race-gate.

docs: index, profiles, tools, api actualization + archive historical docs ...

index.md: expand the file map to reference navi_code, navi_code_cli, store,
context_providers, eval_system, android-client, testing; point at archive/
for historical notes.

profiles.md: add the Compression section (compression_keep_recent /
compression_max_tokens / compression_prompt_file overrides), the
subagent_system_prompt field, and a note that AgentProfile allows unknown
keys (model_config extra=allow).

tools.md: rewrite the user-tools self-extension section — write_tool is
deprecated and removed; write the file via filesystem/code_exec and call
reload_tools instead.

api.md: add missing REST endpoints (GET /sessions/{id}/todos, GET
/sessions/{id}/files list, GET /sessions/{id}/messages/archive, POST
/sessions/{id}/stop) and the admin MCP management block (config CRUD,
reconnect, status, test, profile-mcp mapping, admin recalls); fix the
WS client→server table (type: message|compact, image limits 8/50MB);
add model_info / todo_updated / compression_started events; fix
recall_update action (add skipped), session_sync payload, context_compressed
threshold (70%).

Archive: move plan_01_god_object_agent.md, tech_debt_review_2026-04-29.md,
architecture_weak_spots.md, future_headless_nodes.md into docs/archive/
(historical design notes, no inbound links).

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

docs: update docs for tools.agent/tools.subagent and Navi Code TUI ...

- profiles.md: document tools.agent/tools.subagent structure, deprecate enabled_tools
- tools.md: move web tools to MCP section, fix mcp__navi-web__* names, add create_mcp_server/test_mcp_tool/mcp_status/recall tools
- api.md: update /agents/profiles and /admin/profiles/{id} response schemas, fix MCP examples
- navi_code.md: correct navi_code tool list (MCP disabled)
- navi_code_cli.md: add /thinking, /compact, correct TUI layout
- index.md: add navi_code, terminal client, pydantic-settings
- testing.md: refresh test directory layout, replace stale coverage roadmap
- agent.md: mention tools.agent/tools.subagent in loop

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

Add NAVI_AUTH_ENABLED switch for optional auth ...

- Add navi_auth_enabled setting (default true) to navi/config.py and .env.example
- When disabled, treat every request as anonymous admin user (id='anonymous')
- Create/update fixed anonymous navi_users row on startup
- Bypass OAuth/cookie/API-token resolution in navi/auth/deps.py
- Update /auth/status to return {enabled, configured}
- Log security warning on startup when auth is disabled
- Update webclient: skip fetchMe/login screen, show Local mode footer,
  expose /admin link, warn in API keys panel
- Rebuild webclient production bundle
- Add unit and integration tests for no-auth mode
- Update docs: auth.md, config.md, api.md, api_tokens.md, sessions.md,
  websocket.md, mechanics.md, index.md

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

Fix settings route switching and document API token system ...

- App.vue: make route reactive via ref + getRouteFromHash() so
  #settings toggles work without page reload
- docs/api_tokens.md: new comprehensive API token auth doc
- docs/api.md: add /api-tokens REST endpoints
- docs/auth.md: add token flow architecture diagram and resolution order
- docs/websocket.md: add auth section with cookie vs query-param token
- docs/architecture.md: update to AgentSessionOrchestrator + ToolContext
- docs/tools.md: add gnexus-creds MCP tools
- docs/index.md: link to api_tokens.md
- Rebuild webclient dist

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

Add comprehensive mechanics catalog (docs/mechanics.md) ...

Master catalog of all mechanisms in the Navi project:
- 80+ mechanics catalogued across all subsystems
- Each with description, config flags, source files, documentation status
- 50 undocumented mechanics explicitly listed
- Cross-reference index for feature planning
- Updated docs/index.md to link the catalog

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

docs: document scheduled recall system ...

- Add docs/recall.md with full architecture, data model, tools, loop behavior
- Update docs/api.md with recall endpoints (GET/DELETE/POST recall) and recall_update WS event
- Update docs/websocket.md with recall_update frame and session_sync case #3
- Update docs/tools.md: add ScheduleRecallTool and ManageRecallTool
- Update docs/sessions.md: add is_recall message flag
- Update docs/index.md: link recall.md in file map

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

Document multi-user auth system ...

- New docs/auth.md — comprehensive auth guide: OAuth flow, roles/permissions,
  webhooks, env vars, setup instructions, API reference, WebSocket auth,
  testing with mocked auth
- Update docs/config.md — add gnexus-auth OAuth env vars table
- Update docs/api.md — add /auth/*, /admin/*, /webhooks/gnexus-auth endpoints
- Update docs/index.md — add auth.md to file map
- Update docs/sessions.md — document user_id column and list_all filtering
- Update docs/memory.md — document user_id scoping in facts and summaries

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

Clean up SQLite references in docs and prompts after removal ...

- docs/index.md: PostgreSQL via asyncpg
- docs/memory.md: drop aiosqlite fallback mention
- docs/sessions.md: replace SqliteSessionStore with PgSessionStore docs
- webclient/docs/architecture.md: PostgreSQL only
- navi/profiles/tool_developer/system_prompt.txt: remove aiosqlite from available imports
- .gitignore: add .codex and *.db
- No remaining sqlite/aiosqlite/db_path references in codebase

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

Use gemma4 cloud model by default

Comprehensive documentation update ...

- websocket.md: add heartbeat, session_sync, replay_start/end, planning_status,
  plan_ready (with is_subagent), stream_end extra fields, context_compressed summary,
  updated _AgentRun.events replay buffer, corrected reconnect section
- sessions.md: add name, planning_logs fields; message flags (is_plan, is_compression,
  is_summary, thinking); set_name store op; debug endpoints section
- api.md: full rewrite — add generate-name, planning, file download endpoints;
  all missing WS events; correct message field table with is_plan/is_compression
- tools.md: update user tools list with all current tools
- index.md: fix profiles list (smart_home → developer)
- CLAUDE.md: add Documentation section with table of all docs files
- NAVI.md: add architecture.md entry, improve websocket description

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

Add backend documentation ...

10 markdown files covering all backend subsystems: architecture,
agent loop, tool system, sessions, WebSocket protocol, profiles,
memory, config, and API reference. Structured for AI readability
with a single entry point (docs/index.md) and cross-references.

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