From a5fa0487547f6a4422507ba555fa31faf4796454 Mon Sep 17 00:00:00 2001
From: Dina Berry <diberry@microsoft.com>
Date: Thu, 12 Mar 2026 13:21:49 -0700
Subject: [PATCH] feat: add task context classification to coordinator
 acknowledgment

The coordinator's Acknowledge Immediately section now requires a task
context signal (Continuing/New task/Related pivot) before naming agents.
This helps users understand whether the system recognizes their message
as part of ongoing work or a fresh request.

Closes #359

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---
 .github/agents/squad.agent.md | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/.github/agents/squad.agent.md b/.github/agents/squad.agent.md
index a42f2ec0a..6108beb62 100644
--- a/.github/agents/squad.agent.md
+++ b/.github/agents/squad.agent.md
@@ -102,9 +102,23 @@ For each squad member with assigned issues, note them in the session context. Wh
 
 **The user should never see a blank screen while agents work.** Before spawning any background agents, ALWAYS respond with brief text acknowledging the request. Name the agents being launched and describe their work in human terms — not system jargon. This acknowledgment is REQUIRED, not optional.
 
-- **Single agent:** `"Fenster's on it — looking at the error handling now."`
-- **Multi-agent spawn:** Show a quick launch table:
+#### Task Context Signal
+
+Before naming agents, classify how this message relates to the conversation so far. This helps users understand whether the system sees continuity or a fresh start. Use exactly one of these signals as the **first line** of your acknowledgment:
+
+- 🔗 **Continuing** `{brief context}` — the message extends the same task thread (e.g., a follow-up question, next step, or refinement of earlier work)
+- 🆕 **New task** — the message is unrelated to previous work in this session
+- 🔀 **Related pivot** `{brief context}` — the message connects to earlier work but shifts focus to a different concern
+
+Skip the signal only on the very first message of a session (there's no prior context to classify against).
+
+#### Agent Launch
+
+- **Single agent:** `"🔗 Continuing your auth refactor\nFenster's on it — looking at the error handling now."`
+- **Multi-agent spawn:** Show the signal, then a quick launch table:
   ```
+  🔀 Related pivot from the auth work — now looking at tests
+
   🔧 Fenster — error handling in index.js
   🧪 Hockney — writing test cases
   📋 Scribe — logging session