Cortex-Inara/documentation/TODO__Agents.md

Cortex / Inara — Agent Task List

Read this file before starting any work on this project. Status: Active development — ongoing.

---

🔴 High Priority

[UX] User onboarding — guided model setup

New users complete password + persona setup and land directly in the chat with no working AI model configured. This closes that gap with a guided Step 3 and a fallback for existing users who skipped it or were onboarded before this existed.

Design spec: documentation/ARCH__SYSTEM.md § Onboarding Flow

• Setup Step 3 page — new /setup/model GET/POST in onboarding.py — 2026-05-06
  • Recommends OpenRouter: "one API key, access to Claude, Gemini, and dozens of other models"
  • API key field + curated model dropdown (claude-3-5-haiku, claude-3-7-sonnet, gemini-2.0-flash, llama-3.3-70b)
  • On submit: save_host() (OpenRouter) + save_model() + set_role(chat, primary, model_id) in model_registry.py
  • Skip: POST /setup/model/skip reads cx_setup_persona cookie, redirects to chat; JS fetch on skip-link click
  • Step labels updated: setup.html "1 of 3" / "2 of 3" / "3 of 3" (was "1 of 2" / "2 of 2")
  • Standalone: /setup/model works without step labels (no cx_setup_persona cookie → no label)
  • Persona creation now redirects to /setup/model instead of directly to chat
• Existing user banner — displayed in chat if no role has a model assigned — 2026-05-06
  • Checks GET /backend on load (uses available_roles — already does role-resolution)
  • Dismissable amber callout strip above chat: "No AI model configured — Set up OpenRouter →"
  • Dismissed via localStorage key cx_no_model_banner_dismissed; auto-removed when a model is added
• Settings quick-link — amber card in settings Model Registry section — 2026-05-06
  • Checks GET /backend on page load; shown if available_roles is empty
  • Links to /setup/model
• Update cortex/static/HELP.md — Getting Started section + model registry quick-connect note — 2026-05-06
• Update CLAUDE.md — documented /setup/model endpoint, setup flow description, docs philosophy — 2026-05-06

[Local] Local orchestrator — reach full parity with Gemini orchestrator

openai_orchestrator.py is partially built and wired into POST /orchestrate. When the orchestrator role resolves to a local_openai model it routes there automatically. Remaining work is quality/reliability parity, not ground-up design.

• Tool schema conversion — Gemini FunctionDeclaration → OpenAI tools format
• Context budget: _context_budget() uses context_k * 1000 * 0.75, min 16k — 2026-05-06
• Context compaction: _compact_messages() trims old tool results before each round and before the confirmation-gate call — 2026-05-06
• Error handling: malformed tool args caught + logged; tool execution errors returned as strings
• Retry logic on transient API errors (connection timeout, 429, 503) — 2026-05-09
  • _chat_with_retry() helper in openai_orchestrator.py; 3 attempts, exponential backoff (1s, 2s)
  • Retries on APIConnectionError and APIStatusError with status 429/500/502/503/504
• Test end-to-end with Gemma 4 E4B and 26B A4B on scott_gaming
• Review ARCH__FUTURE.md agent architecture ideas before finalising design
• Reference: docs/OPEN_WEBUI_API.md, documentation/ARCH__FUTURE.md §1

---

🟡 Medium Priority

[UI] Progressive Web App (PWA) ✅ — 2026-04-29

• manifest.json, sw.js, icon-192/512.png, SW registration in app.js
• /manifest.json and /sw.js served at root; added to _PUBLIC in auth_middleware
• Tested: install prompt confirmed working in Chromium

[Tools] Orchestrator tool expansions — Round 1 ✅

• cortex_restart — detached subprocess, 5s delay, admin-only, confirm-required — 2026-04-29
• cortex_logs — journalctl --user -u cortex -n N, admin-only — 2026-04-29
• http_fetch — direct URL fetch via httpx, 8192 char cap — 2026-04-29
• file_list — directory listing with size, dirs first, 200 entry cap, admin-only — 2026-04-29
• file_write — overwrite/append to home_root paths, admin-only, confirm-required — 2026-04-29
• nc_talk_send — outbound NC Talk message via notification.py, admin-only — 2026-04-29
• email_send — SMTP via email_utils, per-user regex allowlist in home/{user}/email_allowlist.json, managed via Settings UI textarea + Files panel raw editor — 2026-04-29
• web_push — VAPID push via pywebpush; subscriptions in home/{user}/push_subscriptions.json; "Enable notifications" toggle in ☰ menu; sw.js push+notificationclick handlers — 2026-05-05

[Tools] Orchestrator tool expansions — Round 2

Next additions identified 2026-05-08. See ARCH__FUTURE.md §2 for design notes.

Note: datetime_now is NOT needed — current date/time is already injected into every system prompt by context_loader.py at all tiers.

• session_search — expose existing session search to the orchestrator — 2026-05-08
  • Wraps session log grep as a tool callable in tools/files.py
  • Params: query: str, limit: int = 5 (max 20)
  • Returns: excerpts with session date, newest first; own sessions only via ContextVars
  • User-level (no TOOL_ROLES entry needed)
• reminders due-date support — make reminders time-aware — 2026-05-08
  • Optional due: YYYY-MM-DD on reminders_add; stored as due: date first line of body
  • context_loader.py calls load_due_reminders() — future-dated sections suppressed until due
  • reminders_list shows [OVERDUE], [due TODAY], or [due: YYYY-MM-DD] per entry
  • Backward compatible — existing undated reminders always surface as before
• spawn_agent — spawn a synchronous sub-agent using any role's model + tools — 2026-05-08
  • cortex/tools/agents.py — spawn_agent(task, role, tier, timeout, max_rounds)
  • Per-host asyncio semaphore keyed by host_id (or model type for cloud); max_concurrent field in host schema
  • Supports local_openai and gemini_api model types; returns error string for others
  • Admin-only tool (powerful — can spawn arbitrarily long sub-tasks)
  • Host UI: "Max parallel" number input in host edit/add forms
• http_post — POST to external URLs — 2026-05-09
  • Params: url: str, body: str, headers: dict | None, max_chars: int
  • Per-user URL prefix allowlist in home/{user}/http_allowlist.json (JSON array of prefixes)
  • Default: blocked if no allowlist or URL doesn't match any prefix
  • Admin-only, confirm-required
• nc_talk_history — read recent Talk messages — 2026-05-09
  • Params: conversation_token: str (optional, defaults to notification_room), limit: int = 20
  • Returns last N messages with sender + timestamp, chronological order
  • Admin-only; requires nc_username and nc_app_password in channels.json under nextcloud
• task_list priority filter — add priority param alongside existing status
• http_fetch max_chars — optional param, default 8192, cap at 32768 — 2026-05-09
• web_read(url, max_chars=16000) — clean article extraction via trafilatura; strips ads/nav/boilerplate, returns markdown — 2026-05-09
• session_read(date) — read a full session log by YYYY-MM-DD date; lists available dates if not found — 2026-05-09

[Channel] Proactive notifications ✅ — 2026-05-08

Inara reaches out on her own initiative via NC Talk, Google Chat, email, or browser push.

• notification.py — notify(username, message, channel=None) routes to NCT / email / Google Chat / web_push
• web_push added as a routable channel in notification.py (was tool-only before)
• scheduler.py — _run_reminder_check() daily at 09:00: reads due reminders per persona, fires notify() with a summary
• cron_runner.py — already calls notify() on job completion (was already wired)
• scheduler.py — distill_mid and distill_long already call notify() on completion
• Settings UI — "Browser Push Notification" option added to Notification Channel selector
• notification_channel accepts "web_push" in routers/settings.py
• GET /settings/notifications — dedicated Notifications page (channel form + test buttons); Settings page now shows a link card
• POST /api/push/test + POST /api/push/reminders/check — on-demand test endpoints
• push_utils.py — fixed pywebpush 2.x key deserialisation (use Vapid.from_pem() instead of passing PEM string)

[Channel] Home Assistant integration — design & tools

Inara can already receive HA events via POST /webhook/ha/{username}/{webhook_id} and respond via web push. Next steps are deciding what events to send and giving Inara the ability to act on HA via the REST API.

• Event design — decide which HA events are worth routing to Inara (security, climate thresholds, low battery, unexpected device state). Avoid flooding with high-frequency sensor polling. Per-automation "tools": true/false to choose notify-only vs. agentic response.
• Richer payload template — update rest_command in HA to include trigger.to_state.attributes, area_name, and previous_state so Inara gets full device context automatically.
• HA API tools — add dedicated orchestrator tools in cortex/tools/homeassistant.py: - ha_get_state(entity_id) — current state + attributes of any entity - ha_call_service(domain, service, data) — turn on lights, set HVAC, lock doors, etc. - ha_get_states(area=None, domain=None) — list states with optional filter - Auth via Long-Lived Access Token stored in channels.json under homeassistant.token - HA URL from channels.json under homeassistant.url
• Store HA config in channels.json — add url and token fields alongside webhook_id so tools can reach the HA REST API (https://ha.dgrzone.com)
• ha_call_service confirm-required — destructive actions (locks, alarms) should go through the confirmation gate

[UX] Session delete confirmation

The session delete button in the sidebar needs a confirmation step before firing — currently it deletes immediately on click with no undo. A simple confirm() dialog or an inline "Are you sure? [Delete] [Cancel]" reveal would prevent accidental data loss.

• Add confirm step to session delete button click handler in app.js
• Consider: also confirm for message-level delete (Edit/Delete hover controls)

[UI] File attachments in chat

Upload an image or document inline and have it flow into context. Natural workflow ("here's this PDF, summarize it"); local backend already supports multimodal via Open WebUI.

• Add attachment button to input area (paperclip icon, hidden file input)
• Client: encode file as base64 or multipart; send alongside message text
• Server: accept file in POST /chat; route to appropriate backend
  • Claude: content array with image blocks (base64 or URL)
  • Gemini: parts array with inline_data
  • Local (Open WebUI): content array with image_url items
• UI: show thumbnail/filename above the sent message

[Auth] Encrypted sessions

Allow users to opt-in to per-session encryption so session logs on disk cannot be read without the user's key.

• Design key derivation: password-based (PBKDF2/Argon2) or separate passphrase
• Encrypt session_logger.py output before writing to sessions/*.md
• Decrypt on read in session_store.py (history reload, file browser)
• UI toggle in Settings to enable/disable encrypted sessions per persona
• Decide: encrypt at rest only, or also in-memory session store?
• Consider: how distillation and session search interact with encrypted files

[Models] Model Registry V2 — Unified Provider System

See DESIGN__Model_Registry_V2.md for full design.

• Phase 1 — V2 schema with providers (Anthropic/Google), multi-account Gemini, auto migration, orchestrator uses account API key — 2026-04-27
• Phase 2 — Cloud provider UI: Anthropic + Google sections in /settings/models, account management, model entry creation for cloud models
• Phase 3 — Unified roles + toggle redesign: standalone role assignments, chat toggle cycles role slots (Primary/Backup 1/Backup 2) showing model label
• Phase 4 — Polish: Claude API key, OpenRouter as named provider, catalog sync from API

[Intelligence] Knowledge consolidation — Phase 1

See ARCH__Intelligence_Layer.md for full design.

• Tool: ae_journal_list — list all journals for the account — 2026-04-28
• Tool: ae_journal_search — search before creating to avoid duplicates
• Tool: ae_journal_entry_create — write a new entry with source metadata
• Tool: ae_journal_entry_update — PATCH any fields on an existing entry — 2026-04-28
• Tool: ae_journal_entry_disable — soft-delete via enable=false — 2026-04-28
• Tool: ae_journal_entry_append — read→append timestamped section→write (running logs) — 2026-04-28
• Tool: ae_journal_entry_prepend — read→prepend timestamped section→write (newest-first logs) — 2026-04-28
• Import script: walk a markdown directory, chunk by H2 section, create entries — 2026-05-05
• Target: markdown files from ~/DgrZone_Nextcloud/ and ~/OSIT_Nextcloud/ — 2026-05-05
• Tag strategy: source path, topic tags from path components — 2026-05-05

---

🟢 Lower Priority / Future

[Research] Agent architecture patterns — review before building dev agent pipeline

The Claude Code system prompt was leaked April 2026. Two reimplementation repos have useful design ideas directly applicable to the local orchestrator and dev agent work. Read before finalising either design.

• Review https://github.com/HarnessLab/claw-code-agent (Python, targets local models)
• Review https://github.com/ultraworkers/claw-code (community port, interesting source)
• Key ideas to evaluate for Cortex:
  • Tiered permission model (read-only / write / shell / unsafe) — relevant once dev agent is writing and executing code
  • Agent lineage tracking — which agent spawned which sub-agent; essential for the orchestrator → specialist → supervisor chain
  • Hard token/cost budgets per operation — local models have fixed context ceilings
  • Context compaction mid-session — trim stale tool results before hitting limit
  • Nested agent delegation with dependency-aware batching
  • Plugin/manifest-based tool registration — worth considering before tool suite grows

[Backend] API usage / cost tracking

Multi-user setup with real Gemini/Claude API costs. Track per-user token consumption so Scott can see who's spending what.

• Count input + output tokens — local backend (OpenAI usage field) + Gemini API (usage_metadata) — 2026-05-05
• Append to home/{user}/usage.json — daily buckets, per-model breakdown — 2026-05-05
• Expose via /api/usage + /api/usage/summary + /api/usage/all (admin); usage table in Settings — 2026-05-06
• Optional: soft spending limit with a warning toast when exceeded

[Security] Tool call audit log — 2026-05-05

Every orchestrator tool invocation logged to home/{user}/tool_audit/YYYY-MM-DD.jsonl.

• tool_audit.py — JSONL writer with asyncio locks; ContextVars for engine/model set by each orchestrator at run start
• Hook in call_tool() — fire-and-forget asyncio.create_task; captures status ok/error/denied, 300-char result snippet, args (truncated at 500 chars)
• GET /api/audit/files — lists available dates for current user (self-service)
• GET /api/audit/day?date= — returns entries for one date (self-service)
• GET /api/audit/recent + /stats — cross-user aggregation (admin only)
• "Audit Log" group in Files panel sidebar (collapsed by default) — read-only table with time/tool/status/model/args/result columns; colour-coded status

[Intelligence] Dev agent pipeline

See ARCH__Intelligence_Layer.md. Full design not yet started.

• Specialist agent: frontend (SvelteKit) code changes
• Specialist agent: backend (FastAPI) code changes
• Supervisor agent: diff review, syntax check, test runner
• Gitea webhook integration: trigger on push/PR, report back
• Human approval gate before commit

[Intelligence] Supervisor agent

• Runs py_compile, svelte-check, unit tests after specialist agent work
• Reports pass/fail back to orchestrator
• Only commits on explicit approval

[Channel] Gitea webhooks

• Receive push/PR/issue events → route to appropriate agent
• cortex/routers/ already has pattern; add gitea.py
• Gitea Actions (CI) for "run tests on push" — simpler than custom runner

[Local] RAG via Open WebUI

Open WebUI has a full RAG pipeline (file upload → embed → knowledge collections → reference in chat). Could feed Nextcloud docs or session logs into a local knowledge base accessible to local models. Endpoints documented in docs/OPEN_WEBUI_API.md.

• /api/v1/files/ upload + /api/v1/retrieval/process/web for URLs
• Reference in chat via "files": [{"type": "collection", "id": "..."}]

[Backend] Intelligent model routing — automatic task-type dispatch

Model Registry V2 (2026-04-27) added role-based routing and manual role toggle — that's the foundation. What remains is removing the need to toggle manually.

• Classify incoming messages by task type (heuristic or lightweight classifier)
• Map task type → role → model automatically:
  • User conversation → chat role → Claude (quality prose, persona fidelity)
  • Tool/research tasks → orchestrator role → Gemini API or local
  • Private/sensitive → local role → Ollama (no data leaves network)
  • Long context (>50k tokens) → Gemini 2.0 (1M ctx window)
  • Fast/cheap queries → local E4B (25 t/s, no API cost)
• Routing logic in llm_client.py or new router.py; expose override in UI

[Future] Cortex Mesh — multi-instance fleet coordination

Each fleet device runs its own Cortex instance. Instances delegate tasks to each other based on resources and specialisation. No central coordinator required.

• Concept only — no design yet. Resolve these questions before building:
  • Auth between instances (shared JWT secret vs. per-instance API keys)
  • Capability advertisement (model registry over HTTP? shared Syncthing file?)
  • Whether ae_send_message / the inbox system is the right coordination layer
  • Session continuity — does a conversation stay on one node or migrate?
• Natural foundation already in place: Syncthing-synced home/ and shared model_registry.json mean instances share persona memory without a central DB

---

✅ Completed

[Tools] email_send tool + per-user email allowlist — 2026-04-29

• email_send(to, subject, body) in cortex/tools/notify.py — SMTP via email_utils.py
• Per-user regex allowlist at home/{user}/email_allowlist.json (JSON array of patterns)
• re.fullmatch(..., re.IGNORECASE) — supports wildcards like .*@oneskyit\\.com
• Blocked by default (no allowlist = no sends); non-matching addresses silently blocked
• Registered as admin-only tool in TOOL_ROLES
• Settings UI: POST /settings/email-allowlist — textarea in Account Settings, one pattern per line
• Files panel: email_allowlist.json added to USER_FILES in files.py; served from home/{user}/; appears in new "Settings" group in sidebar

[Models] Edit existing model entries — 2026-04-29

• Inline edit form per model row in local_llm.html (.model-row-header + hidden .model-edit-form)
• "Edit" toggle shows pre-populated form; "Cancel" collapses it
• "Fetch models" button in edit form — same live-fetch flow as Add Model
• POST /settings/local/models/{model_id}/edit route in local_llm.py dispatches to save_model / save_cloud_model (upsert via model_id)
• Works for both local_openai and cloud model types

[Sessions] Cross-session search — 2026-04-29

• GET /sessions/search?q=&user=&persona=&limit= in files.py — full-text grep across sessions/*.md, newest first
• Returns up to limit matches with 120-char excerpt and date; total_files_searched count
• UI: search input + results panel below Files sidebar; Ctrl+F / search icon shortcut; marked.parse highlights matches

[Tools] Role-based access control + confirmation gate — 2026-04-29

• TOOL_ROLES dict maps tool names to minimum required role (admin/user)
• CONFIRM_REQUIRED set blocks destructive tools; orchestrator injects confirmation prompt instead
• get_tools_for_role(role) filters both Gemini declarations and callables
• get_user_role(username) added to auth_utils.py; passed through both orchestrators
• manage_passwords.py role <username> admin|user — shell-only admin promotion
• Admin-only tools: shell_exec, claude_allow_dir, cortex_restart, cortex_logs, file_read, file_list, file_write, ae_task_list, nc_talk_send
• Confirm-required tools: cortex_restart, file_write, shell_exec, cron_remove, reminders_clear

[UI] Admin role badge in Account settings — 2026-04-29

• GET /settings now injects user_role from auth.json into settings page
• Role shown as a styled pill badge (purple ADMIN, muted USER) below username field

[Local] Unsloth Gemma 4 variants — resolved 2026-04-29

• Ollama update resolved the 500: unable to load model issue
• Unsloth Dynamic 2.0 Q4_K_M GGUFs loading correctly

[Distill] Distill quality review — resolved 2026-04-29

• Short/mid/long output reviewed and quality confirmed acceptable
• No prompt tuning needed at this time

[UI] Progressive Web App (PWA) — 2026-04-29

• manifest.json, sw.js, PNG icons (192/512) generated via rsvg-convert
• /manifest.json and /sw.js served at root via ui.py; exempted in auth_middleware
• Theme-color meta tag updated dynamically on light/dark toggle
• Install prompt confirmed working in Chromium desktop; apple-touch-icon for iOS

[UI] CodeMirror markdown editor for identity/memory files — 2026-04-28

• Replaced textarea in Files panel with CodeMirror 5 (markdown mode, CDN)
• Syntax highlighting, line wrapping, Ctrl+S to save, per-file undo history

[UI] Input area polish — 2026-04-28

• Single cycling S/M/L button replaces 3 separate height buttons (same UX as font size)
• S size collapses mode-select to a row (compact); M/L keep vertical column layout
• Input height minimum derived from setting so empty textarea reflects selected size
• Context & Memory panel and Settings dropdown are mutually exclusive (closeAllPanels fix)
• Both panels now use consistent shadow (var(--shadow)) and z-index (200)

[Tools] Tools toggle — decoupled from Role/Backend — 2026-04-28

• Removed "Agent" mode from the mode selector; replaced with independent ⚡ toggle
• toolsEnabled persists in localStorage; routes to orchestrator regardless of active mode
• Layout: column (M/L) or row (S) driven by data-size attribute set by JS
• chat_role flows from UI → OrchestrateRequest → orchestrator_engine.run(response_role=...)

[Tools] shell_exec tool — 2026-04-28

• shell_exec(command, working_dir, timeout) in cortex/tools/system.py
• Runs any shell command on the Cortex host; timeout clamped 1–120s
• Use for system diagnostics: df -h, ps aux, journalctl, free -h, etc.

[Tools] Aether Journals full toolkit — 2026-04-28

• ae_journal_list — list all journals + ids for the account
• ae_journal_entry_update — PATCH any fields (title, content, summary, tags, enable)
• ae_journal_entry_disable — soft-delete via enable=false
• ae_journal_entry_append — read→append timestamped section→write (running/data logs)
• ae_journal_entry_prepend — read→prepend timestamped section→write (newest-first)
• Shared _get_entry / _patch_entry helpers; OpenAI JSON Schema auto-derived from Gemini declarations

[Local] Per-user multi-model local LLM settings — 2026-04-01

• home/{username}/local_llm.json — hosts[] + models[] + active_model_id structure
• cortex/user_settings.py — CRUD functions: save_host, add_model, remove_model, set_active_model, get_active_local_model
• cortex/routers/local_llm.py + cortex/static/local_llm.html — dedicated /settings/local page
• "Fetch models from host" button — proxied via /api/local-llm/fetch-models, populates dropdown
• Active model shown in UI near backend toggle button (amber hint text)
• Migrates old flat .env-style config automatically on first use

[UI] Copy button for user (sent) messages — 2026-04-01

• Added matching copy-on-hover button to user messages (same pattern as assistant messages)
• div.dataset.raw set on send; makeCopyBtn(div) appended inline

[Backend] Local model backend (Open WebUI / Ollama) — 2026-04-01

• OpenAI-compatible API via httpx — no CLI wrapper needed
• Configured via LOCAL_API_URL / LOCAL_API_KEY / LOCAL_MODEL in .env
• Backend toggle cycles claude → gemini → local (amber color in UI)
• /auth/status includes local reachability check (GET /api/models)
• Tested end-to-end: test-agent-simple (Qwen3-8B) on scott-lt-i7-rtx:3000, full persona context flowing correctly

[Testing] Gitea SSH port 2222 — 2026-03-29

• pfSense WAN → 192.168.32.7:2222 port forward confirmed working
• ssh -p 2222 git@git.dgrzone.com reaches Gitea (returns "Invalid repository path" — expected, confirms connectivity)
• Clone/push via SSH: git clone ssh://git@git.dgrzone.com:2222/<user>/<repo>.git

[Multi-user] Brian onboarding — 2026-03-29

• Invite sent to memedrift@gmail.com
• Brian completed onboarding, created wintermute persona
• Google OAuth registered (google-add brian memedrift@gmail.com)

[Tools] Reminders tools — 2026-03-29

• reminders_add, reminders_list, reminders_clear added to orchestrator tool suite
• Tools live in cortex/tools/reminders.py
• All persona PROTOCOLS.md updated with Tools & Modes reference (direct chat vs Agent mode)
• persona_template.py updated so new personas get the protocol automatically

[Auth] Token expiry — no restart needed — 2026-03-27

• llm_client._fresh_claude_token() reads live from ~/.claude/.credentials.json on every call
• systemd service is a user unit (no sudo) — systemctl --user restart cortex is sufficient
• No manual token sync required after claude auth login

[Multi-user] Per-user channel config — 2026-03-27

• Google Chat and NC Talk secrets/config moved from .env to home/{username}/channels.json
• New endpoints: POST /channels/google-chat/{username} and POST /webhook/nextcloud/{username}
• No channel access by default — each user configures their own channels.json
• Setup guides: docs/GOOGLE_CHAT_BOT.md and docs/NEXTCLOUD_TALK_BOT.md

[Auth] Google OAuth sign-in — 2026-03-27

• GET /auth/google → Google consent → GET /auth/google/callback flow
• Users pre-registered via manage_passwords.py google-add <user> <email>
• Google sign-in button on /login; auth.json stores google_sub + google_email
• Active users: scott (scott.idem@oneskyit.com), holly (holly.danner@gmail.com), brian (memedrift@gmail.com)

[Settings] Per-user Gemini API key — 2026-03-27

• Stored in home/{username}/auth.json as gemini_api_key
• Orchestrator uses user key if set, falls back to server-level GEMINI_API_KEY
• Manageable via /settings UI (add, remove, masked hint)

[UI] Session persistence across navigation — 2026-03-26

• localStorage keyed to cx_sid_{user}_{persona} with 30-min inactivity TTL
• Auto-restored silently on page load; cleared on "New session" or session delete

[UI] Persona picker page — 2026-03-26

• GET /{username} shows a card grid of available personas instead of 404
• Each card links directly to /{username}/{persona}

[UI] Lucide icons — 2026-03-25

• Icons throughout: mode selector, send/stop buttons, edit/del/copy, save/cancel
• Loaded via UMD CDN; icon_html() + render_icons() helpers in app.js

[UI] Persona-specific favicon — 2026-03-25

• Emoji SVG favicon generated from persona config at load time

[Multi-user] Holly onboarding — 2026-03-20

• Holly's invite sent; onboarding completed via /setup/{token}
• home/holly/persona/tina/ created from template
• Google OAuth registered (holly.danner@gmail.com)

[Channel] Nextcloud Talk integration ✅ — 2026-03-20, updated 2026-03-27

• HMAC verification: incoming uses random + raw_body; outgoing reply uses random + message_text
• Per-user routing added 2026-03-27 (endpoint: /webhook/nextcloud/{username})
• Docs: docs/NEXTCLOUD_TALK_BOT.md

[Channel] Google Chat integration ✅ — 2026-03-20, updated 2026-03-27

• JWT verification via authorizationEventObject.systemIdToken
• Workspace Add-on format: hostAppDataAction.chatDataAction.createMessageAction
• Per-user routing added 2026-03-27 (endpoint: /channels/google-chat/{username})
• Docs: docs/GOOGLE_CHAT_BOT.md

[Intelligence] Orchestrator service — Phase 1 — 2026-03-18

• Gemini API (google-genai SDK) tool loop → Claude final response
• POST /orchestrate (async job), GET /orchestrate/{job_id} (poll)
• Tools: web search, AE API, file read, task list, scratch, reminders, cron
• Default model: gemini-2.5-flash

[Auth] Session auth + persona onboarding — 2026-03-20

• bcrypt passwords in home/{username}/auth.json
• JWT session cookies (HS256, 30-day expiry)
• Invite tokens (72h, one-time-use) — manage_passwords.py invite <user> [email]
• Self-service onboarding: /setup/{token} → /setup/persona
• SMTP invite email via noreply@oneskyit.com

[UI] Mobile-friendly header — 2026-03

• Backend toggle, font size, theme buttons moved into ⚙ settings panel
• Header reduced to core buttons

[UI] Help & Reference — 2026-03-27

• Shared base at cortex/static/HELP.md (served to all users)
• Persona-specific additions appended from home/{username}/persona/{name}/HELP.md if present
• Collapsible H2 sections via <details> elements

[Backend] Gemini CLI backend — 2026-03

• gemini -p subprocess, streaming output; auth check at /auth/status

[Backend] Memory distiller — 2026-03

• APScheduler: distill_short (daily 03:00), distill_mid (weekly Sun 03:30), distill_long (monthly 1st 04:00)
• Writes to MEMORY_SHORT.md, MEMORY_MID.md, MEMORY_LONG.md per persona

[Backend] Session logging + file browser — 2026-03

• Sessions saved to home/{user}/persona/{name}/sessions/
• Files panel in UI browses persona directory

[Backend] Dispatcher core — 2026-03-04

• FastAPI service with streaming SSE response
• Claude CLI and Gemini CLI subprocess backends
• Session context management (rolling window, MAX_HISTORY_MESSAGES)