docs: record the removal of Waggle Room tasks
- CHANGELOG "Removed" and the README's list of what is not in this edition name Waggle Room tasks for coding agents and say what the Tool Launcher still does. - AGENTS.md lists the removal under "Already removed". - The Room canvas no longer invites users to "launch a captured external task"; it shows Waggle agents, groups and launched tools.
This commit is contained in:
@@ -97,7 +97,11 @@ packages/shared/src/ # shared types, Zod schemas, MCP catalog
|
||||
Already removed: tiers and Stripe (P0.1); KVARK, enterprise packs, the compliance
|
||||
subsystem, self-learning and `packages/optimizer` (P1.4, P1.6, ADR-0004); the team and
|
||||
WaggleDance routes in the sidecar and `team-sync` in core, with the team server moved to
|
||||
`packages/team-server` (P1.1); the single-mind to multi-mind migration in core (P1.2).
|
||||
`packages/team-server` (P1.1); the single-mind to multi-mind migration in core (P1.2);
|
||||
Waggle Room tasks for external coding agents (`POST /api/tools/run`, the headless task contract
|
||||
in tool manifests, run tokens and the hook settings a launch used to set) and the router's
|
||||
external executors. The Tool Launcher keeps detect, launch, live output and stop; the Room canvas
|
||||
(`/room`) still shows Waggle agents, groups and launched tools.
|
||||
The install audit trail moved from core to the server (`packages/server/src/local/install-audit.ts`,
|
||||
P1.2); other packages write to it through `InstallAuditRecorder` from `@waggle/shared`.
|
||||
|
||||
|
||||
@@ -26,6 +26,11 @@ lists what changed for users compared with that product. The reasons are recorde
|
||||
- **Features of the old memory engine** (ADR-0002): the knowledge graph, the wiki, importing chat
|
||||
history from ChatGPT and Claude exports, memory consolidation, the memory server for
|
||||
external tools (MCP), and the memory hooks for Claude Code, Codex and other coding agents.
|
||||
- **Waggle Room tasks for coding agents** (ADR-0002): running Claude Code, Codex, Hermes or
|
||||
OpenClaw as a captured task or as a team in one Room, with results written to memory. The Tool
|
||||
Launcher still detects these tools, opens them in the active workspace, shows their live output
|
||||
and stops them. "Best fit" in chat now proposes Waggle personas only, so no workspace memories
|
||||
are sent to an external agent.
|
||||
- **`install.sh`** and `scripts/waggle-server.sh`, replaced by the server installer.
|
||||
- The automatic start of a LiteLLM proxy, which needed Python. It is now opt-in (see Changed).
|
||||
|
||||
|
||||
@@ -47,7 +47,7 @@ Neither way needs Python, Docker or a compiler. Details, updates and uninstallin
|
||||
|
||||
Not in this edition: billing and tiers, KVARK, compliance reports, self-learning, team mode, the
|
||||
knowledge graph, chat-history import, the wiki, memory hooks for external coding agents (Claude
|
||||
Code, Codex) and the memory server for external tools (MCP).
|
||||
Code, Codex), Waggle Room tasks for those agents and the memory server for external tools (MCP).
|
||||
[CHANGELOG.md](CHANGELOG.md) lists what changed from the commercial product.
|
||||
|
||||
## Run from source
|
||||
|
||||
@@ -178,7 +178,7 @@ describe('RoomApp', () => {
|
||||
render(<RoomApp />);
|
||||
// The empty-state body carries a distinctive explainer (the header counter
|
||||
// also says "no agents running", so we assert the body copy here).
|
||||
expect(screen.getByText(/spawn a Waggle agent.*captured external task/i)).toBeInTheDocument();
|
||||
expect(screen.getByText(/spawn a Waggle agent or run an agent group/i)).toBeInTheDocument();
|
||||
// No two-column stage/participants chrome when empty.
|
||||
expect(screen.queryByTestId('room-participants')).not.toBeInTheDocument();
|
||||
expect(screen.queryByTestId('room-stage')).not.toBeInTheDocument();
|
||||
@@ -199,7 +199,7 @@ describe('RoomApp', () => {
|
||||
// The error branch wins over the empty-state body (B2): no stage, no
|
||||
// "ask a complex question" explainer — just the connection error.
|
||||
expect(screen.queryByTestId('room-stage')).not.toBeInTheDocument();
|
||||
expect(screen.queryByText(/spawn a Waggle agent.*captured external task/i)).not.toBeInTheDocument();
|
||||
expect(screen.queryByText(/spawn a Waggle agent or run an agent group/i)).not.toBeInTheDocument();
|
||||
});
|
||||
|
||||
it('renders the two-column stage + participants panel once a roster exists', () => {
|
||||
|
||||
@@ -602,7 +602,7 @@ const RoomApp = ({ workspaceId, roomId, workspaceNames = {} }: RoomAppProps) =>
|
||||
<Users className="w-10 h-10 text-muted-foreground/30 mb-3" />
|
||||
<p className="text-sm font-display text-foreground">No agents running</p>
|
||||
<p className="text-[11px] text-muted-foreground mt-1 max-w-xs">
|
||||
Spawn a Waggle agent, run an agent group, or launch a captured external task to watch it work here.
|
||||
Spawn a Waggle agent or run an agent group to watch it work here.
|
||||
</p>
|
||||
</div>
|
||||
) : (
|
||||
@@ -725,7 +725,7 @@ const RoomApp = ({ workspaceId, roomId, workspaceNames = {} }: RoomAppProps) =>
|
||||
<p className="mt-4 text-[12px] text-muted-foreground leading-relaxed">
|
||||
{focusedRoom
|
||||
? 'Each agent works in its bound workspace. Full results return to that workspace mind, with a concise reference in your personal mind.'
|
||||
: 'Waggle agents, groups, and captured external tasks appear here across your workspaces.'}
|
||||
: 'Waggle agents, groups and launched tools appear here across your workspaces.'}
|
||||
</p>
|
||||
</aside>
|
||||
</div>
|
||||
|
||||
Reference in New Issue
Block a user