@questionbase/deskfree 0.3.0-alpha.2 → 0.3.0-alpha.21

package/README.md

@@ -2,7 +2,7 @@
 
 OpenClaw plugin that connects AI agents to [DeskFree](https://github.com/deskfree) — a task management platform built for human-AI collaboration.
 
-Agents can pick up tasks, post progress updates, mark work as done, and exchange messages with humans — all through a structured workflow with human oversight gates.
+Agents can pick up tasks, post progress updates, mark work as done or blocked, manage activities (knowledge containers), and exchange messages with humans — all through a structured workflow with human oversight gates.
 
 ## How it works
 
@@ -12,27 +12,34 @@ Agents can pick up tasks, post progress updates, mark work as done, and exchange
 │                                                                  │
 │   Tools (HTTP)               Channel (WebSocket + polling)       │
 │   ─────────────              ──────────────────────────────      │
-│   get_next_task              Inbound messages from humans        │
-│   comment / done / giveup    Outbound replies from agent         │
-│   list_tasks / create_task   Real-time notifications             │
+│   deskfree_state             Inbound messages from humans        │
+│   deskfree_start_task        Outbound replies from agent         │
+│   deskfree_complete_task     Real-time notifications             │
+│   deskfree_suggest_tasks                                           │
+│   deskfree_create_activity                                       │
+│   deskfree_update_activity                                       │
+│   deskfree_classify_task                                         │
+│   deskfree_learn_from_task                                       │
+│   deskfree_update_deliverable                                    │
+│   deskfree_send_message (+ task suggestions)                     │
 └──────────┬───────────────────────────┬───────────────────────────┘
            │                           │
            ▼                           ▼
 ┌──────────────────────────────────────────────────────────────────┐
 │                      DeskFree Backend                           │
 │                                                                  │
-│   Tasks          Messages        WebSocket Gateway               │
-│   ──────         ────────        ─────────────────               │
-│   State machine  1:1 bot↔user   DynamoDB-backed                 │
-│   RLS-scoped     Threaded by     Thin notifications              │
-│   Atomic claims  task             + polling fallback             │
+│   Tasks          Activities      Messages        WebSocket Gateway│
+│   ──────         ──────────      ────────        ─────────────── │
+│   State machine  Knowledge       1:1 bot↔user   DynamoDB-backed  │
+│   RLS-scoped     containers      Threaded by     Thin notifs      │
+│   Atomic claims  Learn loop      task            + polling fallback│
 └──────────────────────────────────────────────────────────────────┘
 ```
 
 The plugin registers three things with OpenClaw:
 
 1. **Channel** — bidirectional messaging between DeskFree users and the agent
-2. **Tools** — 8 task management tools the agent can call
+2. **Tools** — 10 task, activity, and messaging tools the agent can call
 3. **Skill** — workflow knowledge that teaches the agent how to use the tools correctly
 
 ## Install
@@ -108,12 +115,15 @@ Edit your OpenClaw config file (`~/.openclaw/config.json5`):
 
 ## Task workflow
 
-Tasks follow a strict state machine. The agent claims a task, works on it, and either completes or gives it up — always returning control to a human.
+Tasks follow a strict state machine. The agent claims a task, works on it, and completes it (done or blocked) — always returning control to a human.
 
 ```
-ready_for_bot ──[get_next_task]──> working_on_it ──[done]──> waiting_for_human
-                                         │
-                                         └───[giveup]──> waiting_for_human
+bot ──[start_task]──> bot (is_working) ──[complete_task(done)]──> human
+                                       │                                        │
+                                       └──[complete_task(blocked)]──>           │
+                                                                     human approves/declines
+                                                                                │
+                                                                         [approve] → done
 ```
 
 See [docs/tools.md](docs/tools.md) for the full tool reference and [docs/architecture.md](docs/architecture.md) for how the system works under the hood.