docs: update HELP.md for agent mode, tasks, and 2026-03-18 changes

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

inara/HELP.md

@@ -2,7 +2,7 @@
 
 *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: 2026-03-17*
+*Last updated: 2026-03-18*
 
 ---
 
@@ -40,6 +40,22 @@ All header settings (theme, font size, tier, memory layers) persist in `localSto
 
 ---
 
+## 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.
@@ -96,6 +112,7 @@ The **Files** button opens an editor for Inara's identity and memory files:
 | `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.
@@ -185,6 +202,9 @@ For direct access or scripting:
 | `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`):
@@ -204,10 +224,18 @@ Chat request body (`POST /chat`):
 
 ## In Progress / Planned
 
-- **Auto memory distillation (long)** — short and mid run automatically; long-term integration is off by default (set `AUTO_DISTILL_LONG=true` in `.env` to enable)
-- **Ollama local model backend** — direct Ollama API support (no CLI wrapper)
-- **OAuth token auto-refresh notifications** — ✓ implemented: amber banner shown when Claude CLI token is within 24h of expiry (check `GET /auth/status`)
-- **Multi-user support** — per-user identity/memory files; currently single-user (Scott)
+- **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
+
+- ✓ **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
 
 ---