docs: sync all documentation to current state (2026-04-28)
HELP.md: - Replace stale "Agent Mode" section with accurate "Tools (⚡)" section including full tool table (27 tools across 9 categories) - Fix header controls table: distinguish Context & Memory panel (sliders) from Settings dropdown (☰) - Update Settings panel section: "Backend" → "Role", add S/M/L and ⌃↵ to Display controls list - Update Backends section to match Role toggle terminology TODO__Agents.md: - Mark 5 new journal tools as complete (ae_journal_list, entry_update, entry_disable, entry_append, entry_prepend) - Add completed sections for: shell_exec tool, Tools toggle decoupling, UI input area polish (2026-04-28) MASTER.md: - Date: 2026-04-27 → 2026-04-28 - Orchestrator row: "Agent mode in UI" → "⚡ Tools toggle in UI (27 tools)" CLAUDE.md: - Date: 2026-04-03 → 2026-04-28 - Add orchestrator row to Current State table - Add full 27-tool list for quick reference Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Scott Idem
11
CLAUDE.md
11
CLAUDE.md
@@ -212,9 +212,9 @@ clearly asked for a directory to be unblocked.
|
||||
|
||||
---
|
||||
|
||||
## Current State (2026-04-03)
|
||||
## Current State (2026-04-28)
|
||||
|
||||
Cortex is running and stable. All three primary channels are live:
|
||||
Cortex is running and stable. All channels are live:
|
||||
|
||||
| Channel | Status | Notes |
|
||||
|---|---|---|
|
||||
@@ -222,9 +222,16 @@ Cortex is running and stable. All three primary channels are live:
|
||||
| Nextcloud Talk | ✅ Live | HMAC-signed webhook, async reply |
|
||||
| Google Chat | ✅ Live | Workspace Add-on, `hostAppDataAction` response format |
|
||||
| Local backend | ✅ Live | Open WebUI/Ollama, per-user multi-model config |
|
||||
| Orchestrator | ✅ Live | Gemini API tool loop → Claude response; ⚡ toggle in UI |
|
||||
|
||||
Active users: scott (inara, developer), holly (tina), brian (wintermute)
|
||||
|
||||
**27 orchestrator tools:** web_search, file_read, shell_exec, claude_allow_dir,
|
||||
task_list/create/update/complete, cron_list/add/remove/toggle,
|
||||
reminders_add/list/clear, scratch_read/write/append/clear,
|
||||
ae_journal_list/search/entry_create/entry_update/entry_disable/entry_append/entry_prepend,
|
||||
ae_task_list.
|
||||
|
||||
See `documentation/TODO__Agents.md` for the active task list.
|
||||
See `documentation/ROADMAP.md` for phases and what's next.
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
and are appended automatically by help.html when present.
|
||||
-->
|
||||
|
||||
*Last updated: 2026-04-27*
|
||||
*Last updated: 2026-04-28*
|
||||
|
||||
---
|
||||
|
||||
@@ -15,21 +15,21 @@
|
||||
| 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) |
|
||||
| **N** (sliders icon) | Open the Context & Memory panel (N = current context tier) |
|
||||
| **☰** | Settings menu — Files, Account, Sign Out |
|
||||
| **?** | Open this help panel |
|
||||
|
||||
The **⚙ Settings** panel contains all configuration options:
|
||||
The **Context & Memory** panel (sliders icon with tier number) 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 cycle: claude → gemini → local → auto |
|
||||
| **Display** | Aa/A+/A− font size cycle · ☾/☀ theme toggle |
|
||||
| **Distill Memory** | Manually trigger Short / Mid / Long / All distillation |
|
||||
| **Role** | Active LLM role — click to cycle through configured role assignments |
|
||||
| **Display** | **Aa** cycles font size · **☾** toggles theme · **S/M/L** cycles input area height · **⌃↵** toggles send shortcut |
|
||||
|
||||
All header settings (theme, font size, tier, memory layers) persist in `localStorage` across page refreshes.
|
||||
All settings persist in `localStorage` across page refreshes.
|
||||
|
||||
---
|
||||
|
||||
@@ -46,22 +46,36 @@ Each assistant response shows a small **model tag** in the bottom-right corner i
|
||||
|
||||
---
|
||||
|
||||
## Agent Mode
|
||||
## Tools (⚡)
|
||||
|
||||
Click the **Agent** button in the input row to enable Agent mode. The button highlights and Send changes to **Run**.
|
||||
Click the **⚡** button in the input row to enable the Tools toggle. When lit (amber), **Send** changes to **Run** and messages are routed through the **orchestrator** instead of directly to the chat model.
|
||||
|
||||
In Agent mode, messages are routed through the **orchestrator** instead of directly to the chat model:
|
||||
The orchestrator runs a multi-step tool loop:
|
||||
|
||||
1. The **orchestrator model** runs a tool loop — searches the web, reads files, checks tasks, calls APIs as needed
|
||||
1. The **orchestrator model** reasons about the request and calls tools as needed — web search, file reads, task management, shell commands, Aether Journals, and more
|
||||
2. It produces an enriched summary of what it found
|
||||
3. The **responder model** receives that context and writes the final user-facing reply
|
||||
3. The **responder model** (set by the active Role) receives that context and writes the final user-facing reply
|
||||
4. A `⚡ N tool calls: …` note appears below the response listing what was used
|
||||
|
||||
Which model acts as orchestrator is set in **Settings → Models → Role Assignments → Orchestrator**. By default this is Gemini API; a capable local model can be assigned instead.
|
||||
The ⚡ toggle is **independent of the Role selector** — you can use any role (chat, coder, research, etc.) with or without tools. The orchestrator model is configured in **Account → Model Registry → Role Assignments → Orchestrator**. By default this is Gemini API.
|
||||
|
||||
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.
|
||||
**Available tools:**
|
||||
|
||||
Agent mode sessions persist to history exactly like regular chat.
|
||||
| Category | Tools |
|
||||
|---|---|
|
||||
| Web | `web_search` |
|
||||
| Files | `file_read` |
|
||||
| Shell | `shell_exec`, `claude_allow_dir` |
|
||||
| Tasks | `task_list`, `task_create`, `task_update`, `task_complete` |
|
||||
| Cron | `cron_list`, `cron_add`, `cron_remove`, `cron_toggle` |
|
||||
| Reminders | `reminders_add`, `reminders_list`, `reminders_clear` |
|
||||
| Scratchpad | `scratch_read`, `scratch_write`, `scratch_append`, `scratch_clear` |
|
||||
| Aether Journals | `ae_journal_list`, `ae_journal_search`, `ae_journal_entry_create`, `ae_journal_entry_update`, `ae_journal_entry_disable`, `ae_journal_entry_append`, `ae_journal_entry_prepend` |
|
||||
| Aether Tasks | `ae_task_list` |
|
||||
|
||||
Tools mode is best for tasks requiring research, multi-step reasoning, or side effects (e.g. "search for X", "add a task", "what's on my list?", "append this to my journal"). Regular chat is faster for conversational turns.
|
||||
|
||||
Orchestrated sessions persist to history exactly like regular chat.
|
||||
|
||||
---
|
||||
|
||||
@@ -97,11 +111,11 @@ Three backends are available:
|
||||
| **Gemini** | Google Gemini via the Gemini CLI |
|
||||
| **Local** | Any OpenAI-compatible endpoint (Open WebUI, Ollama, OpenRouter, etc.) |
|
||||
|
||||
The **⚙ Backend** toggle cycles: **auto → claude → gemini → local → auto**
|
||||
The **Role** toggle in the Context & Memory panel cycles through configured role assignments. Each role maps to a Primary / Backup 1 / Backup 2 model chain set in the Model Registry.
|
||||
|
||||
- **auto** uses the model assigned to the `chat` role in your Model Registry (recommended)
|
||||
- Selecting a specific backend forces that backend for all messages, regardless of role assignments
|
||||
- The active model label appears below the toggle button when a specific backend is active
|
||||
- The active model label appears below the toggle button
|
||||
- `auto` (default) uses the model assigned to the `chat` role in your Model Registry
|
||||
- Forcing a specific backend overrides the role assignment for that session
|
||||
|
||||
If the active backend fails, a fallback is tried automatically. A **⚡** badge appears on the response when this happens.
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
# Cortex / Inara — Master Index
|
||||
|
||||
> Start here. This document is a map, not a manual.
|
||||
> Last updated: 2026-04-27
|
||||
> Last updated: 2026-04-28
|
||||
|
||||
---
|
||||
|
||||
@@ -23,7 +23,7 @@ Cortex is a self-hosted personal AI platform. It routes messages from any input
|
||||
| Claude backend | ✅ Live | Primary — via Claude Code CLI |
|
||||
| Gemini backend | ✅ Live | Fallback — via Gemini CLI |
|
||||
| Local backend | ✅ Live | Third option — Open WebUI/Ollama on scott_gaming |
|
||||
| Gemini orchestrator | ✅ Live | Tool loop → Claude response, Agent mode in UI |
|
||||
| Gemini orchestrator | ✅ Live | Tool loop → Claude response, ⚡ Tools toggle in UI (27 tools) |
|
||||
| Model registry V2 | ✅ Live | Providers (Anthropic/Google/Local), multi-account Gemini |
|
||||
| Memory distillation | ✅ Live | Short (daily) / Mid (weekly) / Long (monthly) |
|
||||
| Multi-user | ✅ Live | Scott, Holly, Brian — each with own personas |
|
||||
|
||||
@@ -36,8 +36,13 @@ See `DESIGN__Model_Registry_V2.md` for full design.
|
||||
|
||||
### [Intelligence] Knowledge consolidation — Phase 1
|
||||
See `ARCH__Intelligence_Layer.md` for full design.
|
||||
- [x] Tool: `ae_journal_list` — list all journals for the account — 2026-04-28
|
||||
- [x] Tool: `ae_journal_search` — search before creating to avoid duplicates
|
||||
- [x] Tool: `ae_journal_entry_create` — write a new entry with source metadata
|
||||
- [x] Tool: `ae_journal_entry_update` — PATCH any fields on an existing entry — 2026-04-28
|
||||
- [x] Tool: `ae_journal_entry_disable` — soft-delete via enable=false — 2026-04-28
|
||||
- [x] Tool: `ae_journal_entry_append` — read→append timestamped section→write (running logs) — 2026-04-28
|
||||
- [x] 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
|
||||
- [ ] Target: markdown files from `~/DgrZone_Nextcloud/` and `~/OSIT_Nextcloud/`
|
||||
- [ ] Tag strategy: source path, date, topic tags from frontmatter or filename
|
||||
@@ -99,6 +104,32 @@ base accessible to local models. Endpoints documented in `docs/OPEN_WEBUI_API.md
|
||||
|
||||
## ✅ Completed
|
||||
|
||||
### [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
|
||||
|
||||
Reference in New Issue
Block a user