summaryrefslogtreecommitdiffhomepage
path: root/packages/core/tests
diff options
context:
space:
mode:
authorAdam Malczewski <[email protected]>2026-06-02 15:42:00 +0900
committerAdam Malczewski <[email protected]>2026-06-02 15:42:00 +0900
commite475e527cd768dc05368a0881a07a84ea140e13e (patch)
tree0d59596468eb0d734eef712b52dca94476f89842 /packages/core/tests
parent9c89ec9db22d0a7226c36b62640addc00918029b (diff)
downloaddispatch-e475e527cd768dc05368a0881a07a84ea140e13e.tar.gz
dispatch-e475e527cd768dc05368a0881a07a84ea140e13e.zip
fix(tabs): clearer send_to_tab context to stop busy-wait + wrong-recipient replies
Two behavioral problems observed once the tools were usable: 1. The SENDER busy-waited for a reply (ran 'sleep 20' / polled) instead of ending its turn. Tool description, the delivery result text, and the system-prompt one-liner now say plainly: do not sleep/poll/run commands to wait; a reply arrives on its own in a later turn (or via read_tab in a future turn); keep working if there's other work, else end your turn. 2. The RECIPIENT replied to its OWN user in plain text instead of routing the answer back through send_to_tab. The provenance wrapper now states the message is from another AGENT (not your user), and that to reply you must use send_to_tab addressed to the sender's handle — and only if asked, since it may just be context. A plain text answer reaches only your own user. Tests updated for the new wording.
Diffstat (limited to 'packages/core/tests')
-rw-r--r--packages/core/tests/tools/send-to-tab.test.ts16
1 files changed, 14 insertions, 2 deletions
diff --git a/packages/core/tests/tools/send-to-tab.test.ts b/packages/core/tests/tools/send-to-tab.test.ts
index 4450fc5..68f8fa0 100644
--- a/packages/core/tests/tools/send-to-tab.test.ts
+++ b/packages/core/tests/tools/send-to-tab.test.ts
@@ -24,6 +24,9 @@ describe("createSendToTabTool — schema & description", () => {
expect(tool.name).toBe("send_to_tab");
expect(tool.description).toContain("fire-and-forget");
expect(tool.description.toLowerCase()).toContain("queued");
+ // Description must steer the model away from busy-waiting for a reply.
+ expect(tool.description.toLowerCase()).toContain("do not sleep");
+ expect(tool.description.toLowerCase()).toContain("end your turn");
});
});
@@ -35,11 +38,20 @@ describe("createSendToTabTool — execute()", () => {
expect(deliver).toHaveBeenCalledTimes(1);
const [targetId, delivered] = deliver.mock.calls[0] ?? [];
expect(targetId).toBe("target-id");
- // Provenance prefix names the sending tab's handle.
- expect(delivered).toContain("[message from tab self]");
+ // Provenance header names the sending tab's handle and marks it as a
+ // peer agent (not the recipient's own user).
+ expect(delivered).toContain("[message from tab self");
+ expect(delivered).toContain("another agent");
expect(delivered).toContain("hello there");
+ // Reply contract: the recipient must answer via send_to_tab back to the
+ // sender's handle, not as a plain text reply to its own user.
+ expect(delivered).toContain('send_to_tab tool with tab_id "self"');
+ expect(delivered.toLowerCase()).toContain("only reply if");
expect(out).toContain("idle");
expect(out).toContain("targ");
+ // Sender is steered away from busy-waiting and told to end its turn.
+ expect(out.toLowerCase()).toContain("do not sleep");
+ expect(out.toLowerCase()).toContain("end your turn");
});
it("reports the queued status when the target is busy", async () => {