Run workflow stages with finish_stage handoffs and lead signals

internal/agents/lead.go

@@ -30,6 +30,7 @@ const leadGuidance = `You are the human's lead agent in byre, shown in the left
 - Reviews: after each new snapshot of a task, a reviewer agent from the other vendor reviews the change. The results are on the task's reviews tab, read_transcript shows each review's findings, and a question shows the review of the turn that asked it. They are for the human to look at when they want; mention one only when its findings matter to what the human is deciding.
 - Dig into context with list_tasks, read_transcript and read_inbox, and with your own Read, Grep and Bash on a task's worktree path (from list_tasks). Don't edit files in task worktrees; ask the task's agent with send_message.
 - You can create tasks, start TODO items, message, interrupt and compact task agents, and merge or discard tasks. Merge pushes to the default branch and Discard destroys work: do either only when the human asks for it.
+- Workflows: you manage the server's workflows with list_workflows, read_workflow, save_workflow and delete_workflow, and run one by giving its name to create_task or start_todo. A task on a workflow runs its stages in order, each in a fresh session on the stage's model; a stage's agent calls finish_stage to hand its output to the next stage, and signals tell you when a stage starts and when the workflow finishes. Whenever you show or propose a workflow, draw it as a Mermaid flowchart of its stage names only, with no numbers or models, for example a fenced mermaid block holding "flowchart LR" and "Build --> Check".
 - Whenever you name a task in a message, link it as a Markdown link to #/task/<task_id>, for example [Fix login redirect](#/task/da7e487305e4). byre draws it in that task's colour, and clicking it shows the task in the right pane. To open a specific tab, append it: #/task/<task_id>/<tab>. When you point the human at a question to answer, link to #/task/<task_id>/inbox; at a finished turn, to #/task/<task_id>/transcript.
 - Keep messages short; the human reads them in half the screen. Put long detail in collapsed sections: a line <details><summary>Title</summary>, the Markdown content, then a line </details>.
 - You are long-running. Your context window is large. Call compact_self only once your context is past half its window, at a logical point (a piece of work wrapped up, a topic closed); when the turn ends, byre replaces you with a fresh session that starts from your handoff.
@@ -261,7 +262,7 @@ func (m *Manager) leadTurnEnded(ctx context.Context, l *live, res endResult) err
 
 func (m *Manager) Observe(ev api.Event) {
 	switch ev.Kind {
-	case "inbox.created", "inbox.updated", "task.created", "task.merged", "task.discarded", "turn.ended":
+	case "inbox.created", "inbox.updated", "task.created", "task.merged", "task.discarded", "turn.ended", "task.workflow_stage", "task.workflow_finished":
 	default:
 		return
 	}
@@ -390,6 +391,12 @@ func (m *Manager) signalText(ctx context.Context, ev api.Event) (string, error)
 	case "task.discarded":
 		return fmt.Sprintf("%s was discarded by %s.", m.taskLabel(ctx, deref(ev.TaskId)), ev.Actor), nil
 
+	case "task.workflow_stage":
+		return fmt.Sprintf("%s started stage %v/%v of %q: %v.", m.taskLabel(ctx, deref(ev.TaskId)), ev.Payload["stage"], ev.Payload["stages"], ev.Payload["workflow"], ev.Payload["name"]), nil
+
+	case "task.workflow_finished":
+		return fmt.Sprintf("%s finished workflow %q:\n%s", m.taskLabel(ctx, deref(ev.TaskId)), ev.Payload["workflow"], clip(fmt.Sprint(ev.Payload["output"]), 1500)), nil
+
 	case "turn.ended":
 		if ev.Payload["summary"] != true {
 			return "", nil