Each assistant message in the session JSON now carries:
backend, backend_label, host (platform.node())
These fields are shown as model tags in the UI — on live responses and
when loading session history. Session log entries (sessions/YYYY-MM-DD.md)
include the backend label and host in the turn header.
The local (OpenAI-compat) backend strips non-standard fields before
sending messages to the API so extra fields don't leak upstream.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- openai_orchestrator.py — new ReAct tool loop engine for any
OpenAI-compatible endpoint (OpenRouter, Open WebUI, Ollama, LiteLLM);
model handles both tool loop and final response, no Claude handoff needed
- tools/__init__.py — auto-derive OpenAI JSON Schema from existing Gemini
FunctionDeclarations so tool definitions have a single source of truth
- routers/orchestrator.py — route to openai_orchestrator when model registry
"orchestrator" role resolves to a local_openai type host
- routers/chat.py — pass role to _backend_label(); fix fallback_used logic
(only meaningful for explicit backend overrides, not auto-routing)
- static/app.js — add null/"auto" to backend cycle; fetch local model hint
without overriding the auto default on page load
- model_registry.py — _normalize() back-fills host_type on old registry files
- requirements.txt — add openai>=1.0.0
- ARCH__BACKENDS.md — document OpenAI-compat backend and routing logic
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds host_type ("openwebui" | "openai") to the host schema so Cortex can
talk to both Open WebUI/Ollama and OpenRouter/standard-OpenAI endpoints.
Path differences per type:
openwebui (default): /api/chat/completions, /api/models
openai: /chat/completions, /models
model_registry.py:
- host_type added to host schema (default "openwebui", backward compat)
- save_host() accepts host_type parameter
- _resolve_model() passes host_type through with the merged host fields
llm_client._local():
- Reads host_type from resolved model_cfg
- Selects correct chat completions path accordingly
routers/local_llm.py:
- save_host route accepts host_type form field
- fetch-models uses /models for openai type, /api/models for openwebui
- Existing host rows show type selector pre-filled from stored value
local_llm.html:
- "Add host" form includes type selector
To use OpenRouter:
- Add host: URL = https://openrouter.ai/api/v1, Type = OpenAI-compatible
- API key from openrouter.ai (store in .env or model_registry.json only)
- Fetch models or add manually (e.g. anthropic/claude-sonnet-4-5-20251022)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Fixes:
- app.js was tracking primaryBackend locally but never included
model: primaryBackend in the /chat POST body, so the server always
used settings.primary_backend regardless of what the user clicked.
Now model: primaryBackend is sent on every chat request.
- Responses were only annotated when fallback occurred. Now every
assistant message shows a small model tag at the bottom right.
chat.py:
- _backend_label() resolves human-readable name:
claude → "Claude", gemini → "Gemini",
local → registry label (e.g. "Gemma 4 E4B") or model_name
- SSE payload now includes backend_label field
app.js:
- model: primaryBackend added to /chat fetch body
- After every response, appends .model-tag div with backend_label
- Fallback shows "⚡ fallback → <label>" in amber; normal is muted
- Removed separate system message for fallback (tag covers it)
style.css:
- .model-tag: small muted text, right-aligned, separated by thin line
- .model-tag.fallback: amber (#f59e0b)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Replaces the single-host local model settings page with a full model
registry interface at /settings/local.
Hosts section:
- List existing hosts with inline edit + save + remove
- Collapsible "Add host" form
- Per-host "Fetch models" button
Models section:
- List all models with label, model name, host, context_k badge, tags
- Remove button
Add Model section:
- Host dropdown, label, model name, context_k, tags (comma-separated)
- "Fetch models from host" with auto-fill picker
Role Assignments section:
- One row per defined role (chat, orchestrator, distill, coder, research)
- Primary + backup_1 + backup_2 dropdowns per role
- Dropdowns pre-filled from registry on load
- AJAX save on change (POST /api/models/role) with toast confirmation
- Built-in models (claude_cli, gemini_cli, gemini_api) always available in dropdowns
Backend:
- All user_settings references replaced with model_registry
- host/{id}/remove route added
- fetch-models now accepts host_id query param
- POST /api/models/role for AJAX role assignment
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Replaces the lone "← Back to Cortex" link with a consistent page-nav
on both pages: ← Chat | Help | Settings | Sign out
Active page is highlighted purple; others are muted gray.
Settings page gets a {{ help_href }} template var from settings.py.
Help page builds nav links from the existing cfg JS object.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- cortex/static/HELP.md: shared Help & Reference base served to all users
- help.html: loads shared base + appends persona-specific HELP.md if present
- inara/HELP.md: cleared (content moved to shared base)
- Google OAuth: registered scott.idem@oneskyit.com; flow now working end-to-end
- .gitignore: exclude home/**/sessions/ (runtime logs)
- New personas tracked: home/holly/persona/donut/, home/scott/persona/developer/
- Removed orphans: holly/, personas/, cortex-holly.service
- CLAUDE.md: updated current state and recently completed list to 2026-03-27
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Change type="password" to type="text" — the main signal password
managers use. Also add autocomplete="off", data-lpignore, data-1p-ignore
for broader coverage across Bitwarden, 1Password, LastPass.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Settings page gains two new sections:
- Connected Accounts: shows linked Google email (read-only)
- Gemini API Key: paste personal key from aistudio.google.com,
shows masked hint of saved key, remove link to revert to server key
POST /settings/gemini-key saves/clears gemini_api_key in auth.json.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Users with Google accounts can now sign in without a password.
Auth flow:
- GET /auth/google → Google consent page (CSRF state cookie)
- GET /auth/google/callback → exchange code, lookup user, set JWT
- auth.json gains google_sub + google_email fields
- set_password() no longer overwrites unrelated auth.json fields
Admin setup:
python manage_passwords.py google-add <username> <email>
# add GOOGLE_CLIENT_ID + GOOGLE_CLIENT_SECRET to .env
Per-user Gemini key:
- get_user_gemini_key() reads gemini_api_key from auth.json
- orchestrator_engine.run() accepts gemini_api_key param
- orchestrator router passes user's key, falls back to server key
login.html: "Sign in with Google" button above the password form.
manage_passwords.py list: now shows auth method columns (pw / google).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
app.js updates the <link rel="icon"> to the active persona's emoji on
load (CORTEX_EMOJI is already injected server-side). /favicon.ico route
added as a fallback for login/settings/help pages that don't have
persona context.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
beforeunload closes the EventSource explicitly so the browser doesn't
log "connection interrupted while page was loading". onerror handler
suppresses auto-reconnect noise if the connection temporarily drops.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Session ID is stored in localStorage keyed to user+persona. On page load
it's silently restored if within 30 min of last activity. Timestamp
updates on every sent message. New session / delete session clears the
stored ID so the TTL logic stays consistent.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
pencil → edit, trash-2 → del, copy → copy, check → copied feedback,
check → Save, x → Cancel. All small action buttons get inline-flex
alignment for consistent icon+label layout.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Pass ?persona= query param on the help link so the server knows which
persona to return to. Previously always defaulted to personas[0], causing
navigation back to the wrong persona.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Sync preload script font sizes to match app.js (21/25/17px)
- Send button variants now show icons: ↑ Send, 📝 Note, ⚡ Run
- Remove fixed width on send-col; add white-space:nowrap + padding
so "📝 Note" never wraps regardless of font size
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Load Inter variable font from Google Fonts on all 5 HTML pages
- font-weight: 450 on body (between regular and medium — fixes thin feel)
- -webkit-font-smoothing: antialiased for cleaner screen rendering
- Base font size: normal 16→17px, large 18→19px, small 14→15px
- Applies consistently to main UI, login, setup, settings, and help pages
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Header:
- Sessions, ⚙ context panel, ≡ settings dropdown (Files, Account,
Sign Out), and ❓ help — down from 6+ individual buttons
- Responsive: flex-row on desktop, wraps on mobile with labels hidden
Footer (input area):
- 4-way mode select replaces the button row — shows only the active
mode as [icon] [label] ▲; click opens an upward dropdown
- Options sorted by MRU: most recently used floats to the bottom
(closest to the trigger button) for quick re-selection
- Current mode marked with ✓
- Note mode shows a small prv/pub sub-toggle below the select button
- Mobile: textarea on top (full width), mode select + send on one row
Mode state consolidated from 3 booleans into a single current_mode
variable with localStorage persistence and MRU tracking.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds a third input mode toggle alongside Note and Agent. When active:
- Textarea gets a subtle purple tint with dashed border
- OTR button highlights purple
- Placeholder reads "Off the record — not logged or distilled…"
- off_record=True is sent to /chat; session_logger is skipped
- In-memory session context is preserved within the session
Switching to Note or Agent mode deactivates OTR, and vice versa.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Hardcoded 'Inara' replaced with CORTEX_PERSONA in all placeholder
strings (chat mode and agent task mode).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Fix 'undefined' in auth banner: read access_token_hours_remaining (not hours_remaining)
- Fix false-positive warning on fresh tokens: when refresh token present, only warn
within 1 hour of expiry (not 24h) since the CLI should auto-rotate but sometimes misses
- Emit claude_auth_expired SSE event on 401 so UI shows inline red banner immediately
- app.js: handle claude_auth_expired SSE event with persistent top banner + dismiss button
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Session name field: PATCH /sessions/{id} endpoint, inline rename button in UI
- Persona rename: inline ✏ toggle form in settings, POST /settings/persona/rename
- Username rename: inline form in settings, POST /settings/username (renames home dir, forces re-login)
- Help page: dedicated /help route replacing modal, collapsible sections
- Per-persona isolation: files.py and session_store.py now scope to correct user/persona
- Contrast/visibility: muted text bumped to slate-400+, session rename btn at 0.4 opacity
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add /settings page with password change form and personas list
- Add /help dedicated page (replaces help modal); renders HELP.md with
collapsible sections, dark theme, back link to active persona
- Add 👤 account button and convert ? button to link in header
- Remove help modal HTML and ~55 lines of modal JS from main app
- Register settings and help routers in main.py
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- session_store: store sessions under home/{user}/persona/{name}/session_data/
instead of the shared cortex/data/sessions/ bucket
- chat endpoints: add user/persona query params to /sessions, /history/*,
/sessions/*, /note so they resolve the correct persona context
- files router: add user/persona query params to /files and /files/{name}
so the file browser loads the right persona's files
- app.js: pass user/persona on all session, history, and file fetches;
move _fileParams to top-level scope so it is available everywhere
- onboarding: fix FastAPI route ordering — register /persona before /{token}
so the literal path wins and does not get captured as a token value
- ui.py: read Emoji field from IDENTITY.md and inject into CORTEX_CONFIG
so the header icon reflects each persona's chosen emoji
- .gitignore: exclude home/**/session_data/ (runtime state)
- migrate scott/inara sessions from cortex/data/sessions/ to session_data/
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
New user flow:
1. Admin: python manage_passwords.py invite <username> → generates URL
2. User visits /setup/<token> → sets own password → logged in
3. User redirected to /setup/persona → fills name/emoji/description
4. persona_template.py generates all starter files → lands at /{user}/{persona}
Multiple personas:
- Header persona name is now a clickable dropdown listing all personas
- "New persona" link at bottom → /setup/persona (available to logged-in users)
- /api/personas endpoint returns persona list for current session user
New files:
- persona_template.py: generates IDENTITY/SOUL/PROTOCOLS/USER/HELP.md + data files
- routers/onboarding.py: /setup/{token}, /setup/persona GET+POST
- static/setup.html: two-step form (password → persona), emoji picker, mobile-friendly
Updated:
- auth_utils.py: create_invite(), validate_invite(), consume_invite()
- manage_passwords.py: invite command with URL output
- auth_middleware.py: /setup/* prefix is public (invite tokens need no auth)
- routers/ui.py: /api/personas endpoint; post-login redirect if no personas
- static/app.js: persona switcher dropdown with navigation + Add persona link
- static/style.css: .persona-switcher, .persona-dropdown, mobile adjustments
Mobile: login/setup pages are card-centered with responsive padding;
dropdown avoids edge-clipping on narrow screens; logout button stays visible.
All 80 tests pass.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Orchestrator now saves turns to session store so history survives page refresh
- UI session_id updated from job result; history controls attached to agent turns
- Cortex migrated from system service to systemd user service (no more sudo)
- Update README.md and CLAUDE.md with correct service commands
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add Agent mode toggle to web UI input row — routes through POST /orchestrate
instead of /chat; polls for result with live tool-call count in thinking bubble
- Add cortex/tools/system.py with claude_allow_dir tool; registers in tool registry
- Fix web search: duckduckgo_search renamed to ddgs, update import + requirements.txt
- Allow WebSearch and WebFetch in ~/.claude/settings.json for Claude CLI fallback
- Add claude-allow-dir script docs and security note to CLAUDE.md
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Session delete:
- DELETE /sessions/{session_id} endpoint (chat.py + session_store.py)
- × button on each session item in the panel (hover-reveal on desktop)
- Clears UI if the active session is deleted
Touch accessibility:
- @media (hover: none) rule makes msg-actions always visible on touch devices
- msg-act-btn tap targets enlarged to 36px min-height, readable font size
- session-delete-btn also always visible and finger-sized on touch
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Stack textarea above button row on mobile (flex-direction: column)
- font-size: 16px on textarea prevents iOS Safari auto-zoom on focus
- body height: 100dvh adjusts dynamically as soft keyboard opens/closes
- Right col goes horizontal (row) with full width on mobile
- Hide height-row and enter-toggle (desktop-only concepts)
- Larger touch targets for Send/Stop/Note
- Hide session-id to reclaim vertical space
Desktop layout unchanged.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
/auth/status now returns per-backend status: Claude warns on <24h expiry,
Gemini warns only when oauth_creds.json is missing or has no refresh_token
(access token rotates automatically so expiry_date is not a useful signal).
Banner shows warnings for both backends when needed, and the hint text
names the specific CLI commands to run.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Fetches /distill/status when the ⚙ panel opens and renders next run
times below the distill buttons (monospace, muted). Shows "today",
"tomorrow", or "Mar 18" format depending on how far away.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Banner now shows a second line explaining how to fix it: SSH to the
Cortex host, run `claude`, follow the login prompt, restart Cortex.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
New GET /auth/status endpoint reads ~/.claude/.credentials.json and
returns hours remaining + warning flag. UI shows a dismissible amber
banner when < 24h remain, turning red if expired. Checked on page load
and every 30 minutes.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Header trimmed to 4 buttons (Sessions, Files, ⚙, ?). Backend toggle,
font size, and theme moved into the ⚙ settings panel under new Backend
and Display sections. Panels use responsive widths to avoid overflow on
small screens. Mobile breakpoints tighten padding and hide subtitle.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- static/index.html: reduced to 127-line HTML shell
- static/style.css: all styles extracted (~900 lines) + help modal styles
+ shared markdown rendering for file-preview and help-modal-body
including tables (previously missing)
- static/app.js: all JS extracted (~900 lines) + help modal fetch/render
- index.html: adds ? help button + help modal HTML
- inara/HELP.md: comprehensive reference doc covering all features,
keyboard shortcuts, API endpoints, memory system, planned items
- routers/files.py: HELP.md added to ALLOWED set
- context_loader.py: HELP.md loaded at tier 2+ (after PROTOCOLS.md)
so Inara can reference it when helping Scott with the interface
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Cycles normal (16px) → large (18px) → small (14px) on the root element
so all rem-based text scales together. Persisted in localStorage, applied
before first paint to avoid flash. Also include today's session log.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Edit/delete individual messages from session context with inline editing
(Ctrl+Enter saves, Escape cancels); changes sync to backend via PUT /history
- PUT /history/{session_id} endpoint to replace full message list
- Named sessions: readable slugs (e.g. quiet-spring) instead of UUID fragments
- Scroll no longer snaps to bottom when user has scrolled up to read history
- cortex.service: systemd unit for auto-start and restart-on-failure
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Cortex: FastAPI backend serving Inara via Claude/Gemini CLI backends.
Includes SSE streaming chat, session persistence, Google Chat webhook
handler, and Docker support.
Inara: Identity files (persona, soul, protocols, memory, context tiers)
mounted read-only into the container at runtime.
Features in initial cut:
- /chat endpoint with SSE keepalive + LLM fallback
- Session store with rolling history window
- Markdown rendering, copy-to-clipboard, links open in new tab
- Stacked right-column input controls (height selector, enter toggle,
note mode with public/private) — semi-hidden until textarea grows
- /note endpoint for injecting public context into session history
- Docker Compose config (local dev runs natively; Docker for server)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
