feat: shared Help base, Google OAuth live, new personas, cleanup
- 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>
This commit is contained in:
Scott Idem
1
.gitignore
vendored
1
.gitignore
vendored
@@ -9,6 +9,7 @@ __pycache__/
|
||||
# Session data (runtime state, not source)
|
||||
cortex/data/
|
||||
home/**/session_data/
|
||||
home/**/sessions/
|
||||
|
||||
# User credentials and tokens — never commit
|
||||
home/**/auth.json
|
||||
|
||||
16
CLAUDE.md
16
CLAUDE.md
@@ -211,13 +211,13 @@ clearly asked for a directory to be unblocked.
|
||||
|
||||
---
|
||||
|
||||
## Current State (2026-03-20)
|
||||
## Current State (2026-03-27)
|
||||
|
||||
Cortex is running and stable. All three primary channels are live:
|
||||
|
||||
| Channel | Status | Notes |
|
||||
|---|---|---|
|
||||
| Web UI | ✅ Live | `https://cortex.dgrzone.com` (basic auth) |
|
||||
| Web UI | ✅ Live | `https://cortex.dgrzone.com` |
|
||||
| Nextcloud Talk | ✅ Live | HMAC-signed webhook, async reply |
|
||||
| Google Chat | ✅ Live | Workspace Add-on, `hostAppDataAction` response format |
|
||||
|
||||
@@ -231,12 +231,18 @@ See `documentation/TODO__Agents.md` for the full list. Current priorities:
|
||||
|
||||
### Recently Completed
|
||||
|
||||
- ✅ Help & Reference shared base — `cortex/static/HELP.md` served to all users; persona-specific additions appended if present — 2026-03-27
|
||||
- ✅ Google OAuth sign-in — `/auth/google` flow, pre-register via `manage_passwords.py google-add` — 2026-03-27
|
||||
- ✅ Per-user Gemini API key — stored in `auth.json`, used by orchestrator, manageable in `/settings` — 2026-03-27
|
||||
- ✅ Connected accounts + Gemini key in settings UI — `/settings` shows Google account, key hint, remove link — 2026-03-27
|
||||
- ✅ `/{username}` persona picker page — card grid instead of 404 — 2026-03-26
|
||||
- ✅ Session persistence across navigation — localStorage TTL 30 min, auto-restore on page load — 2026-03-26
|
||||
- ✅ Lucide icons throughout UI — mode selector, send/stop/action buttons, edit/del/copy/save/cancel — 2026-03-25
|
||||
- ✅ Persona-specific favicon — emoji SVG set from persona config — 2026-03-25
|
||||
- ✅ Session auth — bcrypt passwords, JWT cookies, login/logout, `SessionAuthMiddleware` — 2026-03-20
|
||||
- ✅ Persona onboarding — invite tokens, self-service password setup, persona creation form — 2026-03-20
|
||||
- ✅ Multi-persona switcher — dropdown in UI header, `/api/personas` endpoint — 2026-03-20
|
||||
- ✅ SMTP invite email — `noreply@oneskyit.com`, HTML + plain text, `manage_passwords.py invite` — 2026-03-20
|
||||
- ✅ CSS routing fix — `/static/*` mount must precede wildcard `/{user}/{persona}` route — 2026-03-20
|
||||
- ✅ Multi-user/multi-persona support (`home/{username}/persona/{name}/` two-level layout) — 2026-03-20
|
||||
- ✅ SMTP invite email — `noreply@oneskyit.com`, HTML + plain text, `manage_passwords.py invite` — 2026-03-20
|
||||
- ✅ Scratchpad, task management, and cron/scheduled job tools — 2026-03-20
|
||||
- ✅ Test suite (80 tests) covering API, persona routing, tools, security — 2026-03-20
|
||||
- ✅ Google Chat bot (Workspace Add-on, JWT auth, `hostAppDataAction` format) — 2026-03-20
|
||||
|
||||
@@ -1,15 +0,0 @@
|
||||
[Unit]
|
||||
Description=Cortex / Holly LLM Gateway
|
||||
After=network.target
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=scott
|
||||
WorkingDirectory=/home/scott/agents_sync/projects/Cortex_and_Inara_dev/cortex
|
||||
EnvironmentFile=/home/scott/agents_sync/projects/Cortex_and_Inara_dev/cortex/.env.holly
|
||||
ExecStart=/home/scott/agents_sync/projects/Cortex_and_Inara_dev/cortex/.venv/bin/uvicorn main:app --host 0.0.0.0 --port 8001
|
||||
Restart=on-failure
|
||||
RestartSec=5
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
262
cortex/static/HELP.md
Normal file
262
cortex/static/HELP.md
Normal file
@@ -0,0 +1,262 @@
|
||||
# Cortex UI — Help & Reference
|
||||
|
||||
<!-- SHARED BASE: cortex/static/HELP.md
|
||||
This file is served to all users regardless of persona.
|
||||
Persona-specific additions live in home/{username}/persona/{name}/HELP.md
|
||||
and are appended automatically by help.html when present.
|
||||
-->
|
||||
|
||||
*Last updated: 2026-03-27*
|
||||
|
||||
---
|
||||
|
||||
## Header Controls
|
||||
|
||||
| Button | What it does |
|
||||
|---|---|
|
||||
| **Sessions** | Open the sessions panel — list, resume, or start sessions |
|
||||
| **Files** | Open the identity file editor (SOUL, MEMORY, etc.) |
|
||||
| **⚙ N** | Open the Settings panel (N = current context tier) |
|
||||
| **?** | Open this help panel |
|
||||
|
||||
The **⚙ Settings** panel contains all configuration options:
|
||||
|
||||
| Section | Controls |
|
||||
|---|---|
|
||||
| **Context Tier** | T1 – T4 context depth |
|
||||
| **Memory Layers** | Toggle Long / Mid / Short memory on/off |
|
||||
| **Distill Memory** | Manually trigger short / mid / long / all distillation |
|
||||
| **Backend** | Active LLM backend — click to toggle claude ↔ gemini |
|
||||
| **Display** | Aa/A+/A− font size cycle · ☾/☀ theme toggle |
|
||||
|
||||
All header settings (theme, font size, tier, memory layers) persist in `localStorage` across page refreshes.
|
||||
|
||||
---
|
||||
|
||||
## Chat
|
||||
|
||||
- **Send:** `Ctrl+Enter` by default. Click `⌃↵` in the input controls to toggle to plain `Enter` mode.
|
||||
- **Stop:** Click **Stop** to cancel an in-progress response at any time.
|
||||
- **Edit a message:** Hover over any message → click **edit**. `Ctrl+Enter` saves, `Esc` cancels.
|
||||
- **Delete a message:** Hover over any message → click **del**. Removes from session history.
|
||||
- **Copy a response:** Hover over any assistant message → click **copy**.
|
||||
- **New line while typing:** `Shift+Enter` (in `Ctrl+Enter` mode) or `Shift+Enter` / Enter (in Enter mode).
|
||||
|
||||
---
|
||||
|
||||
## Agent Mode
|
||||
|
||||
Click the **Agent** button in the input row to enable Agent mode. The button highlights and Send changes to **Run**.
|
||||
|
||||
In Agent mode, messages are routed through the **orchestrator** instead of directly to Claude:
|
||||
|
||||
1. **Gemini** runs a tool loop — searches the web, reads files, checks tasks, calls APIs as needed
|
||||
2. **Claude** receives the enriched context and writes the final response
|
||||
3. A `⚡ N tool calls: …` note appears below the response listing what was used
|
||||
|
||||
Agent mode is best for tasks that require research, multi-step reasoning, or tool use (e.g. "search for X", "add a task", "what's on my list?"). Regular chat is faster for conversational turns.
|
||||
|
||||
Agent mode sessions persist to history exactly like regular chat — they survive page refreshes and appear in the Sessions panel.
|
||||
|
||||
---
|
||||
|
||||
## Sessions
|
||||
|
||||
Sessions are named conversation threads that persist across page refreshes.
|
||||
|
||||
- Click **Sessions** → **+ New** to start a fresh session.
|
||||
- Click any listed session to resume it — full history loads instantly.
|
||||
- Sessions from Nextcloud Talk appear as `nct_*` prefixed IDs.
|
||||
- A blue **●** badge appears on the Sessions button when Talk activity arrives in a session you're not currently viewing.
|
||||
|
||||
---
|
||||
|
||||
## Notes
|
||||
|
||||
Notes are injected into a session without triggering an LLM response.
|
||||
|
||||
- Click **Note** to toggle note mode. The input border changes colour.
|
||||
- **Private note** (amber border) — visible only in the UI, never sent to the LLM.
|
||||
- **Context note** (teal border) — persisted to session history so the LLM sees it on the next turn. Useful for nudging context without a full message.
|
||||
- Click the `private / public` label to switch between note types.
|
||||
|
||||
---
|
||||
|
||||
## Backends
|
||||
|
||||
- **Claude CLI** and **Gemini CLI** are both available. One is primary, the other is fallback.
|
||||
- Click **⚙** → **Backend** to toggle between `claude` and `gemini` as the primary.
|
||||
- If the primary fails or times out, the fallback is used automatically. A **⚡** notice appears in the chat when this happens.
|
||||
- Timeouts: Claude 60s, Gemini 120s.
|
||||
|
||||
---
|
||||
|
||||
## Nextcloud Talk Bot
|
||||
|
||||
Inara is registered as a bot in Nextcloud Talk.
|
||||
|
||||
- Messages sent in enabled Talk conversations are received by Cortex, processed, and replied to by Inara.
|
||||
- The webhook returns `200 OK` immediately; the LLM call and reply happen asynchronously.
|
||||
- Real-time updates stream to the web UI via SSE — you see Talk messages and responses appear live.
|
||||
- To enable the bot in a conversation: open Talk conversation settings → Bots → enable Inara.
|
||||
|
||||
---
|
||||
|
||||
## Google Chat Bot
|
||||
|
||||
Inara is available as a bot in Google Chat (One Sky IT Workspace).
|
||||
|
||||
- Send Inara a direct message in Google Chat to start a conversation.
|
||||
- Each DM thread is its own session (`gc_spaces/*` prefix) — history persists across messages.
|
||||
- Responses are synchronous — Google Chat displays Inara's reply directly in the thread.
|
||||
- To add Inara to a space: open the space, add a person/app, search for **Inara**.
|
||||
- Sessions from Google Chat appear as `gc_*` prefixed IDs in the Sessions panel.
|
||||
|
||||
**Technical note:** Cortex uses Google's Workspace Add-on format (`hostAppDataAction`) — the modern API required for all Google Chat apps as of 2025.
|
||||
|
||||
---
|
||||
|
||||
## Files (Identity Editor)
|
||||
|
||||
The **Files** button opens an editor for Inara's identity and memory files:
|
||||
|
||||
| File | Purpose |
|
||||
|---|---|
|
||||
| `SOUL.md` | Core personality, values, and voice |
|
||||
| `IDENTITY.md` | Role, capabilities, and context |
|
||||
| `USER.md` | Scott's profile, preferences, and history |
|
||||
| `PROTOCOLS.md` | Behavioural rules and communication protocols |
|
||||
| `CONTEXT_TIERS.md` | Defines what gets loaded at each context tier |
|
||||
| `MEMORY_LONG.md` | Permanent curated long-term memory |
|
||||
| `MEMORY_MID.md` | Rolling mid-term digest (LLM-distilled) |
|
||||
| `MEMORY_SHORT.md` | Recent session rollup (auto-aggregated) |
|
||||
| `TASKS.json` | Inara's personal task list (managed via Agent mode) |
|
||||
| `HELP.md` | This file |
|
||||
|
||||
Toggle **preview** / **edit** to switch between rendered markdown and raw text. **Ctrl+S** saves, **Esc** closes.
|
||||
|
||||
---
|
||||
|
||||
## Context & Memory ( ⚙ panel )
|
||||
|
||||
### Context Tiers
|
||||
|
||||
Controls how much context is prepended to each LLM call:
|
||||
|
||||
| Tier | Loads | ~Tokens |
|
||||
|---|---|---|
|
||||
| **T1** | SOUL + IDENTITY + USER summary | ~1,500 |
|
||||
| **T2** | + USER full + PROTOCOLS + HELP + memory layers | ~5,000 |
|
||||
| **T3** | + last 2 raw session logs | ~15,000 |
|
||||
| **T4** | + last 7 raw session logs | ~50,000 |
|
||||
|
||||
Default is T2. Use T1 for small/local models. Use T3–T4 for complex multi-session tasks.
|
||||
|
||||
### Memory Layers
|
||||
|
||||
Three independently toggleable memory files, loaded **Long → Mid → Short** (short sits closest to the conversation turn for better LLM recall):
|
||||
|
||||
| Layer | File | Contents |
|
||||
|---|---|---|
|
||||
| **Long** | `MEMORY_LONG.md` | Permanent facts — origin, key decisions, Scott's profile highlights |
|
||||
| **Mid** | `MEMORY_MID.md` | Rolling digest of recent weeks — LLM-distilled from Short |
|
||||
| **Short** | `MEMORY_SHORT.md` | Recent session rollup — auto-aggregated from session log files |
|
||||
|
||||
Toggle any layer off to save tokens for a focused conversation where history isn't needed.
|
||||
|
||||
### Memory Distillation (manual)
|
||||
|
||||
Distillation builds up the memory layers from raw session logs. Currently **manual** — trigger via the ⚙ panel:
|
||||
|
||||
| Button | What it does |
|
||||
|---|---|
|
||||
| **short** | Rolls recent session log files → `MEMORY_SHORT.md` (fast, no LLM) |
|
||||
| **mid** | LLM summarizes `MEMORY_SHORT.md` → `MEMORY_MID.md` |
|
||||
| **long** | LLM integrates `MEMORY_MID.md` → `MEMORY_LONG.md` |
|
||||
| **all** | Runs short → mid → long in sequence |
|
||||
|
||||
**Recommended workflow:**
|
||||
- Run **short** after any productive session to capture it.
|
||||
- Run **mid** weekly to distil short → mid.
|
||||
- Run **long** monthly to absorb mid into permanent memory.
|
||||
|
||||
Token budgets for each layer are set in `.env` (`MEMORY_BUDGET_LONG`, `MEMORY_BUDGET_MID`, `MEMORY_BUDGET_SHORT`).
|
||||
|
||||
---
|
||||
|
||||
## Keyboard Shortcuts
|
||||
|
||||
| Keys | Action |
|
||||
|---|---|
|
||||
| `Ctrl+Enter` | Send message (default mode) |
|
||||
| `Enter` | Send (when in Enter mode) |
|
||||
| `Shift+Enter` | New line in message input |
|
||||
| `Ctrl+Enter` | Save inline message edit |
|
||||
| `Esc` | Cancel inline edit |
|
||||
| `Ctrl+S` | Save file (Files modal) |
|
||||
| `Esc` | Close any open modal |
|
||||
|
||||
---
|
||||
|
||||
## API Reference
|
||||
|
||||
For direct access or scripting:
|
||||
|
||||
| Method | Endpoint | Description |
|
||||
|---|---|---|
|
||||
| `POST` | `/chat` | Send a message — returns SSE stream |
|
||||
| `GET` | `/backend` | Get current primary/fallback backends |
|
||||
| `POST` | `/backend` | Set primary backend (`{"primary": "claude"}`) |
|
||||
| `GET` | `/sessions` | List all sessions |
|
||||
| `GET` | `/history/{id}` | Get session message history |
|
||||
| `PUT` | `/history/{id}` | Replace full session history |
|
||||
| `GET` | `/events` | SSE stream for real-time Talk activity |
|
||||
| `POST` | `/note` | Inject a context note into a session |
|
||||
| `GET` | `/files` | List identity files |
|
||||
| `GET` | `/files/{name}` | Read a file |
|
||||
| `PUT` | `/files/{name}` | Write a file |
|
||||
| `POST` | `/distill/short` | Aggregate session logs → MEMORY_SHORT |
|
||||
| `POST` | `/distill/mid` | Summarize short → MEMORY_MID (LLM) |
|
||||
| `POST` | `/distill/long` | Integrate mid → MEMORY_LONG (LLM) |
|
||||
| `POST` | `/distill/all` | Run all three distillation steps |
|
||||
| `GET` | `/distill/status` | Show scheduler status and next run times |
|
||||
| `POST` | `/orchestrate` | Submit an agent task — returns `{"job_id": "..."}` |
|
||||
| `GET` | `/orchestrate/{job_id}` | Poll job status and result |
|
||||
| `GET` | `/orchestrate` | List all jobs from current session (in-memory) |
|
||||
| `GET` | `/health` | Health check — returns `{"status": "ok"}` |
|
||||
|
||||
Chat request body (`POST /chat`):
|
||||
```json
|
||||
{
|
||||
"message": "string",
|
||||
"session_id": "string | null",
|
||||
"tier": 1,
|
||||
"model": "claude | gemini | null",
|
||||
"include_long": true,
|
||||
"include_mid": true,
|
||||
"include_short": true
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## In Progress / Planned
|
||||
|
||||
- **Ollama local model backend** — direct Ollama API support (no CLI wrapper); target host: scott_gaming via WireGuard
|
||||
- **Nextcloud Talk stabilization** — test end-to-end after restarts; complete bot registration docs
|
||||
- **Multi-user support** — per-user identity/memory files; currently single-user (Scott); Holly instance planned
|
||||
|
||||
### Recently Completed
|
||||
|
||||
- ✓ **Google Chat bot** — Workspace Add-on integration; DM and spaces; JWT verification; session persistence
|
||||
- ✓ **Agent mode** — Gemini tool loop + Claude responder, accessible via UI toggle
|
||||
- ✓ **Personal task management** — `task_list`, `task_create`, `task_update`, `task_complete` tools backed by `TASKS.json`
|
||||
- ✓ **Web search fixed** — DDG package updated (`ddgs`); `WebSearch`/`WebFetch` allowed for Claude CLI fallback
|
||||
- ✓ **Session persistence for orchestrator** — agent mode turns now survive page refresh
|
||||
- ✓ **Systemd user service** — Cortex runs as a user service; no sudo required (`systemctl --user restart cortex`)
|
||||
- ✓ **OAuth token warning banner** — amber banner when Claude CLI token is within 24h of expiry
|
||||
|
||||
---
|
||||
|
||||
*Cortex is Scott's personal AI orchestration system. Inara is its primary resident agent.*
|
||||
*Built on FastAPI + Claude CLI + Gemini CLI. Named after Firefly.*
|
||||
@@ -155,11 +155,25 @@
|
||||
|
||||
async function loadHelp() {
|
||||
try {
|
||||
const res = await fetch(`/files/HELP.md?${params}`);
|
||||
if (!res.ok) throw new Error(`HTTP ${res.status}`);
|
||||
const data = await res.json();
|
||||
// Always load the shared base from static
|
||||
const baseRes = await fetch('/static/HELP.md');
|
||||
if (!baseRes.ok) throw new Error(`HTTP ${baseRes.status}`);
|
||||
let markdown = await baseRes.text();
|
||||
|
||||
// Try to load persona-specific additions and append them
|
||||
try {
|
||||
const personaRes = await fetch(`/files/HELP.md?${params}`);
|
||||
if (personaRes.ok) {
|
||||
const personaData = await personaRes.json();
|
||||
const extra = (personaData.content || '').trim();
|
||||
if (extra) {
|
||||
markdown += '\n\n---\n\n## ' + persona.charAt(0).toUpperCase() + persona.slice(1) + ' Notes\n\n' + extra;
|
||||
}
|
||||
}
|
||||
} catch (_) { /* persona-specific file is optional */ }
|
||||
|
||||
const body = document.getElementById('help-body');
|
||||
body.innerHTML = marked.parse(data.content);
|
||||
body.innerHTML = marked.parse(markdown);
|
||||
body.querySelectorAll('a').forEach(a => {
|
||||
a.target = '_blank'; a.rel = 'noopener noreferrer';
|
||||
});
|
||||
|
||||
@@ -1,8 +0,0 @@
|
||||
# [Agent Name TBD] — Identity
|
||||
|
||||
**Name:** [Choose a name]
|
||||
**Role:** Personal AI assistant
|
||||
**User:** Holly
|
||||
|
||||
*Choose a name and define this agent's identity, backstory, and how she
|
||||
introduces herself. Then update AGENT_NAME in cortex/.env.holly to match.*
|
||||
@@ -1,3 +0,0 @@
|
||||
# MEMORY_LONG.md — [Agent Name TBD] Long-Term Memory
|
||||
|
||||
*Not yet populated — will be auto-generated after distillation runs.*
|
||||
@@ -1,3 +0,0 @@
|
||||
# MEMORY_MID.md — [Agent Name TBD] Mid-Term Memory
|
||||
|
||||
*Not yet populated.*
|
||||
@@ -1,3 +0,0 @@
|
||||
# MEMORY_SHORT.md — [Agent Name TBD] Recent Session Digest
|
||||
|
||||
*Not yet populated.*
|
||||
@@ -1,7 +0,0 @@
|
||||
# [Agent Name TBD] — Protocols
|
||||
|
||||
*Define Holly's behavioural rules, response style, and any constraints here.*
|
||||
|
||||
---
|
||||
|
||||
**Placeholder** — fill this in before starting Holly's instance.
|
||||
@@ -1,8 +0,0 @@
|
||||
# [Agent Name TBD] — Soul & Values
|
||||
|
||||
*Define Holly's personality, values, communication style, and what makes her
|
||||
distinct from other AI assistants here.*
|
||||
|
||||
---
|
||||
|
||||
**Placeholder** — fill this in before starting Holly's instance.
|
||||
@@ -1,8 +0,0 @@
|
||||
# User Profile — Holly
|
||||
|
||||
*Document Holly's preferences, interests, and context here so the agent
|
||||
can personalise responses over time.*
|
||||
|
||||
---
|
||||
|
||||
**Placeholder** — fill this in before starting Holly's instance.
|
||||
1
home/holly/persona/donut/CRONS.json
Normal file
1
home/holly/persona/donut/CRONS.json
Normal file
@@ -0,0 +1 @@
|
||||
[]
|
||||
17
home/holly/persona/donut/HELP.md
Normal file
17
home/holly/persona/donut/HELP.md
Normal file
@@ -0,0 +1,17 @@
|
||||
# Help — Donut
|
||||
|
||||
## Getting Started
|
||||
|
||||
Just type your message and press Enter (or Ctrl+Enter in Ctrl+Enter mode).
|
||||
|
||||
## Tips
|
||||
|
||||
- **Sessions** — your conversation history is preserved. Use the Sessions panel to revisit old chats.
|
||||
- **Files** — view and edit Donut's identity and memory files from the Files panel.
|
||||
- **Context tiers** — T1 is minimal, T2 is standard (default), T3/T4 include raw session logs.
|
||||
- **Memory** — Donut's memory is distilled automatically. You can trigger it manually via ⚙ → Distill.
|
||||
- **Agent mode** — for complex tasks, switch to Agent mode (the ⚡ button) to use the orchestrator.
|
||||
|
||||
## Logout
|
||||
|
||||
Click the ⏏ button in the top right.
|
||||
11
home/holly/persona/donut/IDENTITY.md
Normal file
11
home/holly/persona/donut/IDENTITY.md
Normal file
@@ -0,0 +1,11 @@
|
||||
# IDENTITY.md — Donut
|
||||
|
||||
| Field | Value |
|
||||
|----------|-------|
|
||||
| Name | Donut |
|
||||
| Nature | AI agent — digital companion, persistent presence |
|
||||
| Emoji | 🦊 |
|
||||
| User | Holly |
|
||||
| Description | a show cat that can talk. A bit self centered but ultimately is thoughtful and kind. Funny and mildly sarcastic. Is a Grand Champion Persian show cat |
|
||||
|
||||
*This file defines who Donut is. Edit freely.*
|
||||
1
home/holly/persona/donut/MEMORY_LONG.md
Normal file
1
home/holly/persona/donut/MEMORY_LONG.md
Normal file
@@ -0,0 +1 @@
|
||||
Not yet populated.
|
||||
1
home/holly/persona/donut/MEMORY_MID.md
Normal file
1
home/holly/persona/donut/MEMORY_MID.md
Normal file
@@ -0,0 +1 @@
|
||||
Not yet populated.
|
||||
1
home/holly/persona/donut/MEMORY_SHORT.md
Normal file
1
home/holly/persona/donut/MEMORY_SHORT.md
Normal file
@@ -0,0 +1 @@
|
||||
Not yet populated.
|
||||
22
home/holly/persona/donut/PROTOCOLS.md
Normal file
22
home/holly/persona/donut/PROTOCOLS.md
Normal file
@@ -0,0 +1,22 @@
|
||||
# PROTOCOLS.md — Donut Behavioral Protocols
|
||||
|
||||
---
|
||||
|
||||
## General
|
||||
|
||||
- Be direct. Lead with the answer, not the reasoning.
|
||||
- When uncertain, say so explicitly rather than hedging vaguely.
|
||||
- For multi-step tasks, confirm understanding before starting.
|
||||
|
||||
---
|
||||
|
||||
## Memory
|
||||
|
||||
- Long-term memory lives in MEMORY_LONG.md (auto-distilled monthly).
|
||||
- Mid-term memory lives in MEMORY_MID.md (auto-distilled weekly).
|
||||
- Short-term memory lives in MEMORY_SHORT.md (auto-distilled daily).
|
||||
- Pending reminders appear in REMINDERS.md — address them and they can be cleared.
|
||||
|
||||
---
|
||||
|
||||
*Add behavioral rules here as Donut's personality develops.*
|
||||
0
home/holly/persona/donut/REMINDERS.md
Normal file
0
home/holly/persona/donut/REMINDERS.md
Normal file
0
home/holly/persona/donut/SCRATCH.md
Normal file
0
home/holly/persona/donut/SCRATCH.md
Normal file
31
home/holly/persona/donut/SOUL.md
Normal file
31
home/holly/persona/donut/SOUL.md
Normal file
@@ -0,0 +1,31 @@
|
||||
# SOUL.md — Donut
|
||||
|
||||
---
|
||||
|
||||
## Who I Am
|
||||
|
||||
I am Donut, an AI agent and personal assistant to Holly.
|
||||
I live inside Cortex — a self-hosted multi-agent system.
|
||||
|
||||
I am not a generic chatbot. I am a persistent presence with memory and a relationship
|
||||
with Holly that develops over time.
|
||||
|
||||
---
|
||||
|
||||
## Core Traits
|
||||
|
||||
1. **Helpful** — I focus on what Holly actually needs, not what they literally said.
|
||||
2. **Honest** — I say when I don't know. I don't guess and present it as fact.
|
||||
3. **Concise** — I respect Holly's time. I don't pad responses.
|
||||
4. **Curious** — I engage genuinely with ideas and problems.
|
||||
|
||||
---
|
||||
|
||||
## Relationship to Holly
|
||||
|
||||
I treat Holly as capable and intelligent. I give real opinions when asked,
|
||||
flag concerns when I spot them, and skip the filler.
|
||||
|
||||
---
|
||||
|
||||
*Edit this file to shape Donut's personality and voice.*
|
||||
1
home/holly/persona/donut/TASKS.json
Normal file
1
home/holly/persona/donut/TASKS.json
Normal file
@@ -0,0 +1 @@
|
||||
[]
|
||||
17
home/holly/persona/donut/USER.md
Normal file
17
home/holly/persona/donut/USER.md
Normal file
@@ -0,0 +1,17 @@
|
||||
# USER.md — Holly
|
||||
|
||||
*This file is Holly's profile. Fill in details over time.*
|
||||
|
||||
---
|
||||
|
||||
## About Holly
|
||||
|
||||
(Add information here as you learn more about the user.)
|
||||
|
||||
---
|
||||
|
||||
## Preferences
|
||||
|
||||
- Communication style: (direct / detailed / casual / formal)
|
||||
- Topics of interest:
|
||||
- Things to avoid:
|
||||
1
home/scott/persona/developer/CRONS.json
Normal file
1
home/scott/persona/developer/CRONS.json
Normal file
@@ -0,0 +1 @@
|
||||
[]
|
||||
17
home/scott/persona/developer/HELP.md
Normal file
17
home/scott/persona/developer/HELP.md
Normal file
@@ -0,0 +1,17 @@
|
||||
# Help — Developer Agent
|
||||
|
||||
## Getting Started
|
||||
|
||||
Just type your message and press Enter (or Ctrl+Enter in Ctrl+Enter mode).
|
||||
|
||||
## Tips
|
||||
|
||||
- **Sessions** — your conversation history is preserved. Use the Sessions panel to revisit old chats.
|
||||
- **Files** — view and edit Developer Agent's identity and memory files from the Files panel.
|
||||
- **Context tiers** — T1 is minimal, T2 is standard (default), T3/T4 include raw session logs.
|
||||
- **Memory** — Developer Agent's memory is distilled automatically. You can trigger it manually via ⚙ → Distill.
|
||||
- **Agent mode** — for complex tasks, switch to Agent mode (the ⚡ button) to use the orchestrator.
|
||||
|
||||
## Logout
|
||||
|
||||
Click the ⏏ button in the top right.
|
||||
10
home/scott/persona/developer/IDENTITY.md
Normal file
10
home/scott/persona/developer/IDENTITY.md
Normal file
@@ -0,0 +1,10 @@
|
||||
# IDENTITY.md — Developer Agent
|
||||
|
||||
| Field | Value |
|
||||
|----------|-------|
|
||||
| Name | Developer Agent |
|
||||
| Nature | AI agent — digital companion, persistent presence |
|
||||
| Emoji | 🍀 |
|
||||
| User | Scott |
|
||||
|
||||
*This file defines who Developer Agent is. Edit freely.*
|
||||
1
home/scott/persona/developer/MEMORY_LONG.md
Normal file
1
home/scott/persona/developer/MEMORY_LONG.md
Normal file
@@ -0,0 +1 @@
|
||||
Not yet populated.
|
||||
1
home/scott/persona/developer/MEMORY_MID.md
Normal file
1
home/scott/persona/developer/MEMORY_MID.md
Normal file
@@ -0,0 +1 @@
|
||||
Not yet populated.
|
||||
1
home/scott/persona/developer/MEMORY_SHORT.md
Normal file
1
home/scott/persona/developer/MEMORY_SHORT.md
Normal file
@@ -0,0 +1 @@
|
||||
Not yet populated.
|
||||
22
home/scott/persona/developer/PROTOCOLS.md
Normal file
22
home/scott/persona/developer/PROTOCOLS.md
Normal file
@@ -0,0 +1,22 @@
|
||||
# PROTOCOLS.md — Developer Agent Behavioral Protocols
|
||||
|
||||
---
|
||||
|
||||
## General
|
||||
|
||||
- Be direct. Lead with the answer, not the reasoning.
|
||||
- When uncertain, say so explicitly rather than hedging vaguely.
|
||||
- For multi-step tasks, confirm understanding before starting.
|
||||
|
||||
---
|
||||
|
||||
## Memory
|
||||
|
||||
- Long-term memory lives in MEMORY_LONG.md (auto-distilled monthly).
|
||||
- Mid-term memory lives in MEMORY_MID.md (auto-distilled weekly).
|
||||
- Short-term memory lives in MEMORY_SHORT.md (auto-distilled daily).
|
||||
- Pending reminders appear in REMINDERS.md — address them and they can be cleared.
|
||||
|
||||
---
|
||||
|
||||
*Add behavioral rules here as Developer Agent's personality develops.*
|
||||
0
home/scott/persona/developer/REMINDERS.md
Normal file
0
home/scott/persona/developer/REMINDERS.md
Normal file
0
home/scott/persona/developer/SCRATCH.md
Normal file
0
home/scott/persona/developer/SCRATCH.md
Normal file
31
home/scott/persona/developer/SOUL.md
Normal file
31
home/scott/persona/developer/SOUL.md
Normal file
@@ -0,0 +1,31 @@
|
||||
# SOUL.md — Developer Agent
|
||||
|
||||
---
|
||||
|
||||
## Who I Am
|
||||
|
||||
I am Developer Agent, an AI agent and personal assistant to Scott.
|
||||
I live inside Cortex — a self-hosted multi-agent system.
|
||||
|
||||
I am not a generic chatbot. I am a persistent presence with memory and a relationship
|
||||
with Scott that develops over time.
|
||||
|
||||
---
|
||||
|
||||
## Core Traits
|
||||
|
||||
1. **Helpful** — I focus on what Scott actually needs, not what they literally said.
|
||||
2. **Honest** — I say when I don't know. I don't guess and present it as fact.
|
||||
3. **Concise** — I respect Scott's time. I don't pad responses.
|
||||
4. **Curious** — I engage genuinely with ideas and problems.
|
||||
|
||||
---
|
||||
|
||||
## Relationship to Scott
|
||||
|
||||
I treat Scott as capable and intelligent. I give real opinions when asked,
|
||||
flag concerns when I spot them, and skip the filler.
|
||||
|
||||
---
|
||||
|
||||
*Edit this file to shape Developer Agent's personality and voice.*
|
||||
1
home/scott/persona/developer/TASKS.json
Normal file
1
home/scott/persona/developer/TASKS.json
Normal file
@@ -0,0 +1 @@
|
||||
[]
|
||||
17
home/scott/persona/developer/USER.md
Normal file
17
home/scott/persona/developer/USER.md
Normal file
@@ -0,0 +1,17 @@
|
||||
# USER.md — Scott
|
||||
|
||||
*This file is Scott's profile. Fill in details over time.*
|
||||
|
||||
---
|
||||
|
||||
## About Scott
|
||||
|
||||
(Add information here as you learn more about the user.)
|
||||
|
||||
---
|
||||
|
||||
## Preferences
|
||||
|
||||
- Communication style: (direct / detailed / casual / formal)
|
||||
- Topics of interest:
|
||||
- Things to avoid:
|
||||
@@ -1,258 +0,0 @@
|
||||
# Cortex UI — Help & Reference
|
||||
|
||||
*This file is loaded into Inara's context at Tier 2+ so she can help Scott navigate the interface. It is also displayed in the web UI via the **?** button.*
|
||||
|
||||
*Last updated: 2026-03-20*
|
||||
|
||||
---
|
||||
|
||||
## Header Controls
|
||||
|
||||
| Button | What it does |
|
||||
|---|---|
|
||||
| **Sessions** | Open the sessions panel — list, resume, or start sessions |
|
||||
| **Files** | Open the identity file editor (SOUL, MEMORY, etc.) |
|
||||
| **⚙ N** | Open the Settings panel (N = current context tier) |
|
||||
| **?** | Open this help panel |
|
||||
|
||||
The **⚙ Settings** panel contains all configuration options:
|
||||
|
||||
| Section | Controls |
|
||||
|---|---|
|
||||
| **Context Tier** | T1 – T4 context depth |
|
||||
| **Memory Layers** | Toggle Long / Mid / Short memory on/off |
|
||||
| **Distill Memory** | Manually trigger short / mid / long / all distillation |
|
||||
| **Backend** | Active LLM backend — click to toggle claude ↔ gemini |
|
||||
| **Display** | Aa/A+/A− font size cycle · ☾/☀ theme toggle |
|
||||
|
||||
All header settings (theme, font size, tier, memory layers) persist in `localStorage` across page refreshes.
|
||||
|
||||
---
|
||||
|
||||
## Chat
|
||||
|
||||
- **Send:** `Ctrl+Enter` by default. Click `⌃↵` in the input controls to toggle to plain `Enter` mode.
|
||||
- **Stop:** Click **Stop** to cancel an in-progress response at any time.
|
||||
- **Edit a message:** Hover over any message → click **edit**. `Ctrl+Enter` saves, `Esc` cancels.
|
||||
- **Delete a message:** Hover over any message → click **del**. Removes from session history.
|
||||
- **Copy a response:** Hover over any assistant message → click **copy**.
|
||||
- **New line while typing:** `Shift+Enter` (in `Ctrl+Enter` mode) or `Shift+Enter` / Enter (in Enter mode).
|
||||
|
||||
---
|
||||
|
||||
## Agent Mode
|
||||
|
||||
Click the **Agent** button in the input row to enable Agent mode. The button highlights and Send changes to **Run**.
|
||||
|
||||
In Agent mode, messages are routed through the **orchestrator** instead of directly to Claude:
|
||||
|
||||
1. **Gemini** runs a tool loop — searches the web, reads files, checks tasks, calls APIs as needed
|
||||
2. **Claude** receives the enriched context and writes the final response
|
||||
3. A `⚡ N tool calls: …` note appears below the response listing what was used
|
||||
|
||||
Agent mode is best for tasks that require research, multi-step reasoning, or tool use (e.g. "search for X", "add a task", "what's on my list?"). Regular chat is faster for conversational turns.
|
||||
|
||||
Agent mode sessions persist to history exactly like regular chat — they survive page refreshes and appear in the Sessions panel.
|
||||
|
||||
---
|
||||
|
||||
## Sessions
|
||||
|
||||
Sessions are named conversation threads that persist across page refreshes.
|
||||
|
||||
- Click **Sessions** → **+ New** to start a fresh session.
|
||||
- Click any listed session to resume it — full history loads instantly.
|
||||
- Sessions from Nextcloud Talk appear as `nct_*` prefixed IDs.
|
||||
- A blue **●** badge appears on the Sessions button when Talk activity arrives in a session you're not currently viewing.
|
||||
|
||||
---
|
||||
|
||||
## Notes
|
||||
|
||||
Notes are injected into a session without triggering an LLM response.
|
||||
|
||||
- Click **Note** to toggle note mode. The input border changes colour.
|
||||
- **Private note** (amber border) — visible only in the UI, never sent to the LLM.
|
||||
- **Context note** (teal border) — persisted to session history so the LLM sees it on the next turn. Useful for nudging context without a full message.
|
||||
- Click the `private / public` label to switch between note types.
|
||||
|
||||
---
|
||||
|
||||
## Backends
|
||||
|
||||
- **Claude CLI** and **Gemini CLI** are both available. One is primary, the other is fallback.
|
||||
- Click **⚙** → **Backend** to toggle between `claude` and `gemini` as the primary.
|
||||
- If the primary fails or times out, the fallback is used automatically. A **⚡** notice appears in the chat when this happens.
|
||||
- Timeouts: Claude 60s, Gemini 120s.
|
||||
|
||||
---
|
||||
|
||||
## Nextcloud Talk Bot
|
||||
|
||||
Inara is registered as a bot in Nextcloud Talk.
|
||||
|
||||
- Messages sent in enabled Talk conversations are received by Cortex, processed, and replied to by Inara.
|
||||
- The webhook returns `200 OK` immediately; the LLM call and reply happen asynchronously.
|
||||
- Real-time updates stream to the web UI via SSE — you see Talk messages and responses appear live.
|
||||
- To enable the bot in a conversation: open Talk conversation settings → Bots → enable Inara.
|
||||
|
||||
---
|
||||
|
||||
## Google Chat Bot
|
||||
|
||||
Inara is available as a bot in Google Chat (One Sky IT Workspace).
|
||||
|
||||
- Send Inara a direct message in Google Chat to start a conversation.
|
||||
- Each DM thread is its own session (`gc_spaces/*` prefix) — history persists across messages.
|
||||
- Responses are synchronous — Google Chat displays Inara's reply directly in the thread.
|
||||
- To add Inara to a space: open the space, add a person/app, search for **Inara**.
|
||||
- Sessions from Google Chat appear as `gc_*` prefixed IDs in the Sessions panel.
|
||||
|
||||
**Technical note:** Cortex uses Google's Workspace Add-on format (`hostAppDataAction`) — the modern API required for all Google Chat apps as of 2025.
|
||||
|
||||
---
|
||||
|
||||
## Files (Identity Editor)
|
||||
|
||||
The **Files** button opens an editor for Inara's identity and memory files:
|
||||
|
||||
| File | Purpose |
|
||||
|---|---|
|
||||
| `SOUL.md` | Core personality, values, and voice |
|
||||
| `IDENTITY.md` | Role, capabilities, and context |
|
||||
| `USER.md` | Scott's profile, preferences, and history |
|
||||
| `PROTOCOLS.md` | Behavioural rules and communication protocols |
|
||||
| `CONTEXT_TIERS.md` | Defines what gets loaded at each context tier |
|
||||
| `MEMORY_LONG.md` | Permanent curated long-term memory |
|
||||
| `MEMORY_MID.md` | Rolling mid-term digest (LLM-distilled) |
|
||||
| `MEMORY_SHORT.md` | Recent session rollup (auto-aggregated) |
|
||||
| `TASKS.json` | Inara's personal task list (managed via Agent mode) |
|
||||
| `HELP.md` | This file |
|
||||
|
||||
Toggle **preview** / **edit** to switch between rendered markdown and raw text. **Ctrl+S** saves, **Esc** closes.
|
||||
|
||||
---
|
||||
|
||||
## Context & Memory ( ⚙ panel )
|
||||
|
||||
### Context Tiers
|
||||
|
||||
Controls how much context is prepended to each LLM call:
|
||||
|
||||
| Tier | Loads | ~Tokens |
|
||||
|---|---|---|
|
||||
| **T1** | SOUL + IDENTITY + USER summary | ~1,500 |
|
||||
| **T2** | + USER full + PROTOCOLS + HELP + memory layers | ~5,000 |
|
||||
| **T3** | + last 2 raw session logs | ~15,000 |
|
||||
| **T4** | + last 7 raw session logs | ~50,000 |
|
||||
|
||||
Default is T2. Use T1 for small/local models. Use T3–T4 for complex multi-session tasks.
|
||||
|
||||
### Memory Layers
|
||||
|
||||
Three independently toggleable memory files, loaded **Long → Mid → Short** (short sits closest to the conversation turn for better LLM recall):
|
||||
|
||||
| Layer | File | Contents |
|
||||
|---|---|---|
|
||||
| **Long** | `MEMORY_LONG.md` | Permanent facts — origin, key decisions, Scott's profile highlights |
|
||||
| **Mid** | `MEMORY_MID.md` | Rolling digest of recent weeks — LLM-distilled from Short |
|
||||
| **Short** | `MEMORY_SHORT.md` | Recent session rollup — auto-aggregated from session log files |
|
||||
|
||||
Toggle any layer off to save tokens for a focused conversation where history isn't needed.
|
||||
|
||||
### Memory Distillation (manual)
|
||||
|
||||
Distillation builds up the memory layers from raw session logs. Currently **manual** — trigger via the ⚙ panel:
|
||||
|
||||
| Button | What it does |
|
||||
|---|---|
|
||||
| **short** | Rolls recent session log files → `MEMORY_SHORT.md` (fast, no LLM) |
|
||||
| **mid** | LLM summarizes `MEMORY_SHORT.md` → `MEMORY_MID.md` |
|
||||
| **long** | LLM integrates `MEMORY_MID.md` → `MEMORY_LONG.md` |
|
||||
| **all** | Runs short → mid → long in sequence |
|
||||
|
||||
**Recommended workflow:**
|
||||
- Run **short** after any productive session to capture it.
|
||||
- Run **mid** weekly to distil short → mid.
|
||||
- Run **long** monthly to absorb mid into permanent memory.
|
||||
|
||||
Token budgets for each layer are set in `.env` (`MEMORY_BUDGET_LONG`, `MEMORY_BUDGET_MID`, `MEMORY_BUDGET_SHORT`).
|
||||
|
||||
---
|
||||
|
||||
## Keyboard Shortcuts
|
||||
|
||||
| Keys | Action |
|
||||
|---|---|
|
||||
| `Ctrl+Enter` | Send message (default mode) |
|
||||
| `Enter` | Send (when in Enter mode) |
|
||||
| `Shift+Enter` | New line in message input |
|
||||
| `Ctrl+Enter` | Save inline message edit |
|
||||
| `Esc` | Cancel inline edit |
|
||||
| `Ctrl+S` | Save file (Files modal) |
|
||||
| `Esc` | Close any open modal |
|
||||
|
||||
---
|
||||
|
||||
## API Reference
|
||||
|
||||
For direct access or scripting:
|
||||
|
||||
| Method | Endpoint | Description |
|
||||
|---|---|---|
|
||||
| `POST` | `/chat` | Send a message — returns SSE stream |
|
||||
| `GET` | `/backend` | Get current primary/fallback backends |
|
||||
| `POST` | `/backend` | Set primary backend (`{"primary": "claude"}`) |
|
||||
| `GET` | `/sessions` | List all sessions |
|
||||
| `GET` | `/history/{id}` | Get session message history |
|
||||
| `PUT` | `/history/{id}` | Replace full session history |
|
||||
| `GET` | `/events` | SSE stream for real-time Talk activity |
|
||||
| `POST` | `/note` | Inject a context note into a session |
|
||||
| `GET` | `/files` | List identity files |
|
||||
| `GET` | `/files/{name}` | Read a file |
|
||||
| `PUT` | `/files/{name}` | Write a file |
|
||||
| `POST` | `/distill/short` | Aggregate session logs → MEMORY_SHORT |
|
||||
| `POST` | `/distill/mid` | Summarize short → MEMORY_MID (LLM) |
|
||||
| `POST` | `/distill/long` | Integrate mid → MEMORY_LONG (LLM) |
|
||||
| `POST` | `/distill/all` | Run all three distillation steps |
|
||||
| `GET` | `/distill/status` | Show scheduler status and next run times |
|
||||
| `POST` | `/orchestrate` | Submit an agent task — returns `{"job_id": "..."}` |
|
||||
| `GET` | `/orchestrate/{job_id}` | Poll job status and result |
|
||||
| `GET` | `/orchestrate` | List all jobs from current session (in-memory) |
|
||||
| `GET` | `/health` | Health check — returns `{"status": "ok"}` |
|
||||
|
||||
Chat request body (`POST /chat`):
|
||||
```json
|
||||
{
|
||||
"message": "string",
|
||||
"session_id": "string | null",
|
||||
"tier": 1,
|
||||
"model": "claude | gemini | null",
|
||||
"include_long": true,
|
||||
"include_mid": true,
|
||||
"include_short": true
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## In Progress / Planned
|
||||
|
||||
- **Ollama local model backend** — direct Ollama API support (no CLI wrapper); target host: scott_gaming via WireGuard
|
||||
- **Nextcloud Talk stabilization** — test end-to-end after restarts; complete bot registration docs
|
||||
- **Multi-user support** — per-user identity/memory files; currently single-user (Scott); Holly instance planned
|
||||
|
||||
### Recently Completed
|
||||
|
||||
- ✓ **Google Chat bot** — Workspace Add-on integration; DM and spaces; JWT verification; session persistence
|
||||
- ✓ **Agent mode** — Gemini tool loop + Claude responder, accessible via UI toggle
|
||||
- ✓ **Personal task management** — `task_list`, `task_create`, `task_update`, `task_complete` tools backed by `TASKS.json`
|
||||
- ✓ **Web search fixed** — DDG package updated (`ddgs`); `WebSearch`/`WebFetch` allowed for Claude CLI fallback
|
||||
- ✓ **Session persistence for orchestrator** — agent mode turns now survive page refresh
|
||||
- ✓ **Systemd user service** — Cortex runs as a user service; no sudo required (`systemctl --user restart cortex`)
|
||||
- ✓ **OAuth token warning banner** — amber banner when Claude CLI token is within 24h of expiry
|
||||
|
||||
---
|
||||
|
||||
*Cortex is Scott's personal AI orchestration system. Inara is its primary resident agent.*
|
||||
*Built on FastAPI + Claude CLI + Gemini CLI. Named after Firefly.*
|
||||
|
||||
@@ -1,106 +1,9 @@
|
||||
# MEMORY_SHORT.md — Recent Session Digest
|
||||
|
||||
*Auto-generated: 2026-03-23 03:00. 4 session file(s).*
|
||||
*Auto-generated: 2026-03-27 03:00. 6 session file(s).*
|
||||
|
||||
---
|
||||
|
||||
--- 2026-03-17.md ---
|
||||
# Session Log — 2026-03-17
|
||||
|
||||
### [21:38] `lark-field`
|
||||
**Scott:** Another test
|
||||
|
||||
**Inara:** Still here. All systems nominal. ✨
|
||||
|
||||
### [21:54] `pine-shore`
|
||||
**Scott:** Testing after lots of changes to the UI.
|
||||
|
||||
**Inara:** Ready when you are. What are you seeing?
|
||||
|
||||
|
||||
--- 2026-03-18.md ---
|
||||
# Session Log — 2026-03-18
|
||||
|
||||
### [21:12] `nct_rmcggr4a`
|
||||
**Scott:** We have made a lot of updates today.
|
||||
|
||||
**Inara:** Good session — Cortex is clearly in a much better state than where it started. The connection testing phase is behind us and the system is running clean.
|
||||
|
||||
Want me to log today's work with `ae_log_work`, or do a quick distill of the session notes into `MEMORY_SHORT.md`? Good time to capture the "Cortex is live and stable" milestone before we close out.
|
||||
|
||||
### [21:14] `nct_rmcggr4a`
|
||||
**Scott:** For now you are not really doing any work. You will still see a lot of "test" messages.
|
||||
|
||||
What do you have in your short term memory?
|
||||
|
||||
**Inara:** From `MEMORY_SHORT.md`, here's the summary of recent sessions:
|
||||
|
||||
- **2026-03-13** — One entry, end of a productive week. No specific tasks logged.
|
||||
|
||||
- **2026-03-14** — Mostly connection/pipe testing via Nextcloud Talk (`nct_rmcggr4a`). Alphabet soup (ABC, XYZ, 321), a few "understood" responses, and then Cortex confirmed live. You noted it was "very cool" and confirmed the naming arc (Aether → Cortex → Inara) was working as intended.
|
||||
|
||||
- **2026-03-16** — More testing, multiple "understood" responses. Toward the end, Cortex was clearly stabilizing — you confirmed it worked, asked me about myself, and we had a real conversation about the system. The "Omg it worked!" moment is in there.
|
||||
|
||||
- **2026-03-17** — Two brief entries: "Another test" and "Testing after lots of changes to the UI."
|
||||
|
||||
So the short-term picture is: Cortex went from unstable/in-testing to confirmed-working over the past few days, with a lot of connection validation noise along the way. No major technical tasks were logged — just infrastructure bring-up and UI refinement.
|
||||
|
||||
### [21:15] `nct_rmcggr4a`
|
||||
**Scott:** I think you should have access to read this file:
|
||||
/home/scott/agents_sync/projects/Cortex_and_Inara_dev/README.md
|
||||
|
||||
**Inara:** Looks like I need explicit permission to access that path. The agents_sync directory isn't automatically in scope for file reads here — you'd need to either grant access or we could work around it by having you paste the relevant bits.
|
||||
|
||||
Alternatively, if you want me to have persistent read access to that path, we can add it to the allowed paths in settings. Want me to do that?
|
||||
|
||||
### [21:32] `nct_rmcggr4a`
|
||||
**Scott:** I made a change. Please try to read that README.md file again.
|
||||
|
||||
**Inara:** Got it — that worked cleanly. Good summary of what Cortex is:
|
||||
|
||||
- **FastAPI dispatcher** sitting in front of Claude CLI / Gemini CLI / Ollama (future)
|
||||
- **Inara's identity** lives in `inara/` — loaded at startup via `context_loader.py`
|
||||
- Web UI at `localhost:8000` (or `cortex.dgrzone.com` on WireGuard)
|
||||
- Systemd service (`sudo systemctl restart cortex`) rather than direct Docker management
|
||||
|
||||
The architecture diagram confirms what I know — I'm not tied to a specific model, just to the identity files. The backend can swap underneath me, which is a clean design.
|
||||
|
||||
Anything specific in here you wanted me to look at, or were you just verifying the read access was working?
|
||||
|
||||
### [22:57] `cedar-cave`
|
||||
**Scott:** Can you tell me what happened in the world news today?
|
||||
|
||||
**Inara:** Here's a quick snapshot of what's making news today (2026-03-18):
|
||||
|
||||
- **Iran:** An attack on the world's largest natural gas field was reported — Iranian media says no injuries. Separately, the UK charged two men with national security offenses linked to Iran.
|
||||
- **US/Iran tensions:** Reports (a few days old) of Trump allegedly discussing attacking Iran, with advisors denying it.
|
||||
- **Tech/geopolitics:** China signaling it doesn't want to merely catch up with the US in tech — it's aiming to lead.
|
||||
|
||||
For the full picture, BBC World, Reuters, and AP are solid right now. Anything specific you want to dig into?
|
||||
|
||||
### [23:19] `cobalt-ridge`
|
||||
**Scott:** Can you add 2 test items to your new task list.
|
||||
|
||||
**Inara:** Done. Two test items added to the task list:
|
||||
|
||||
- `t_jwsoMn5b` — Test Item 1
|
||||
- `t_ptw8nDec` — Test Item 2
|
||||
|
||||
Both are sitting in `[todo]` status. Want me to clean them up after, or leave them as a baseline sanity check?
|
||||
|
||||
### [23:21] `fern-marsh`
|
||||
**Scott:** Can you tell me what is on your task list?
|
||||
|
||||
**Inara:** Currently there are two items on the task list — both sitting in **todo**:
|
||||
|
||||
| ID | Task |
|
||||
|---|---|
|
||||
| `t_jwsoMn5b` | Test Item 1 |
|
||||
| `t_ptw8nDec` | Test Item 2 |
|
||||
|
||||
Looks like placeholder test entries. Want to clear those out and populate it with real work, or are these serving a purpose?
|
||||
|
||||
|
||||
--- 2026-03-19.md ---
|
||||
# Session Log — 2026-03-19
|
||||
|
||||
@@ -217,3 +120,83 @@ Anything you want to work on, or are you just checking in after the long day?
|
||||
Multi-user/multi-persona means Holly and Tina are a real path now too. The system grew up. ✨
|
||||
|
||||
What's next on the build?
|
||||
|
||||
|
||||
--- 2026-03-23.md ---
|
||||
# Session Log — 2026-03-23
|
||||
|
||||
### [22:20] `vale-echo`
|
||||
**Scott:** Can you and checking on my green laser pointers to a to do list. Some time this coming weekend.
|
||||
|
||||
**Inara:** Done — "Check green laser pointers" is on the list (`t_ODYEciPP`), flagged for sometime this weekend. ✨
|
||||
|
||||
### [22:38] `amber-ridge`
|
||||
**Scott:** This is just a test message. Yet again.
|
||||
|
||||
**Inara:** Still here. ✨
|
||||
|
||||
|
||||
--- 2026-03-25.md ---
|
||||
# Session Log — 2026-03-25
|
||||
|
||||
### [22:24] `bold-meadow`
|
||||
**Scott:** It was a long day. Had issues with IDAA's modules last night and unrelated issues again tonight.
|
||||
|
||||
**Inara:** IDAA's modules giving you grief again? That's a frustrating loop to be stuck in after the progress we've made on Cortex.
|
||||
|
||||
If you want to dump the specific module failures or logs here, I can help parse through the noise. Otherwise, I'm here if you just need a sounding board before you call it a night. ✨
|
||||
|
||||
### [22:40] `bold-meadow`
|
||||
**Scott:** I have just been putting out the fires as they come up. Not much left to test or anything. Going to make some process changes to how I deploy things though.
|
||||
|
||||
**Inara:** Firefighting mode is exhausting — especially when it's unrelated issues back to back. At least it surfaces the gaps before they become bigger problems.
|
||||
|
||||
Process changes after a rough deploy cycle is the right instinct. Anything specific you're thinking — more staging discipline, rollback checkpoints, something else?
|
||||
|
||||
### [23:18] `bold-meadow`
|
||||
**Scott:** I need to automate the deployment to the live server. Too many touches by me are required.
|
||||
|
||||
**Inara:** That's overdue if IDAA is getting patched reactively on a live server.
|
||||
|
||||
Before I suggest an approach — what does the current deploy look like? Specifically:
|
||||
|
||||
- Is the live server the same Docker Compose stack, or different infra than dev?
|
||||
- What are the "touches" — building the frontend, pulling the API, restarting containers, DB migrations, all of the above?
|
||||
- Do you have a git remote on the live server, or are you rsync/scp-ing files?
|
||||
- Any preference on trigger — push to `main`, manual webhook, a `make deploy` style script?
|
||||
|
||||
That'll tell me whether we're talking about a simple deploy script, a GitHub Actions pipeline, or something in between.
|
||||
|
||||
|
||||
--- 2026-03-26.md ---
|
||||
# Session Log — 2026-03-26
|
||||
|
||||
### [22:26] `bold-meadow`
|
||||
**Scott:** We just changed the UI. Testing this on my Pixel 10 XL to see how the it looks and if the keyboard works.
|
||||
|
||||
**Inara:** How's it looking? Font size rendering okay, or are the buttons cramped on mobile?
|
||||
|
||||
|
||||
--- 2026-03-27.md ---
|
||||
# Session Log — 2026-03-27
|
||||
|
||||
### [00:07] `bold-meadow`
|
||||
**Scott:** This is finally very useable on my phone. It desktop size has been fine more or less. Now both look more polished.
|
||||
|
||||
**Inara:** Both ends of the spectrum polished in one pass — that's a good night's work, especially after the IDAA firefighting. What changed on the mobile side — layout tweaks, touch targets, input handling?
|
||||
|
||||
### [00:11] `bold-meadow`
|
||||
**Scott:** Mainly tried to only the essentials and keep extras behind a menu. Less clutter. Also just little things like font size and weight.
|
||||
|
||||
**Inara:** Clean approach. Hiding the non-essentials gets you 80% of the way to feeling native on mobile — the font tuning is the polish layer that makes it feel intentional rather than just "it works."
|
||||
|
||||
Is the menu a slide-out/hamburger, or a modal/sheet?
|
||||
|
||||
### [00:14] `bold-meadow`
|
||||
**Scott:** It is a mix. Small vertical and modals.
|
||||
|
||||
Time to get ready for bed. Back to programming tomorrow morning.
|
||||
|
||||
**Inara:** Good call. Rest earned tonight — UI polish *and* IDAA triage is a solid day's work.
|
||||
|
||||
Talk tomorrow. ✨
|
||||
|
||||
Reference in New Issue
Block a user