sync: update from private repo (ddadfd71)

2026-07-08 23:35:00 +00:00
parent b1292e34b2
commit 77ee3bc426
187 changed files with 19918 additions and 10938 deletions
@@ -14,16 +14,20 @@ It works standalone as long as you have an OpenAI-compatible LLM endpoint ([Olla

 ## Screenshots

-The three-pane workspace — task list on the left, the live conversation and rendered output in the center, and a structured side panel (status, mission brief, files, trace) on the right:
+The workspace — a rail of your workspaces on the left, the chats inside the selected one next to it, and the live conversation with the agent's rendered output filling the rest. Overview, progress, files, and the full trace are one tab away:

-![Task workspace](docs/screenshots/workspace.png)
+![Workspace](docs/screenshots/workspace.png)

 <details>
-<summary>More screenshots — task list and settings</summary>
+<summary>More screenshots — workspaces, chat list, and settings</summary>

-Task list with at-a-glance status (running / waiting / done) and quick filters:
+Your personal workspace and each project workspace sit side by side; the same agent runs in every one:

-![Task list](docs/screenshots/task-list.png)
+![Workspaces](docs/screenshots/spaces.png)
+
+Chats with at-a-glance status (running / waiting / done) and quick filters:
+
+![Chat list](docs/screenshots/task-list.png)

 Settings: every `config.yaml` section as a form — LLM workers, sandbox, auth, tools, and more:

@@ -54,7 +58,7 @@ docker compose up -d          # builds on first run, then starts

 No `.env` or `config.yaml` is needed to start: a fresh `docker compose up` opens a setup wizard in the UI where you point MAESTRO at your LLM. To preset it instead, `cp .env.example .env` and set `OLLAMA_BASE_URL` / `OLLAMA_MODEL`.

-For safety, Compose exposes only `127.0.0.1:9876`. Before making it reachable from another host, configure OAuth authentication and place a TLS-enabled reverse proxy in front. Specify the LLM endpoint in `.env` / `config.yaml`.
+Compose publishes `9876` on all interfaces, so a Docker host is reachable from your LAN out of the box — and unauthenticated until you configure it. Before leaving it on a shared network, enable authentication, `safety.bash_sandbox: always`, and TLS (native `server.tls` or a reverse proxy); pin the mapping to `127.0.0.1:9876:9876` to keep it local-only. Specify the LLM endpoint in `.env` / `config.yaml`.

 Full Docker guide (Linux networking, data persistence, the sandbox, troubleshooting): **[docs/docker.md](docs/docker.md)**.