diff options
| -rw-r--r-- | packages/api/src/agent-manager.ts | 2 | ||||
| -rw-r--r-- | packages/core/src/tools/send-to-tab.ts | 32 | ||||
| -rw-r--r-- | packages/core/tests/tools/send-to-tab.test.ts | 16 |
3 files changed, 42 insertions, 8 deletions
diff --git a/packages/api/src/agent-manager.ts b/packages/api/src/agent-manager.ts index 36a26f8..4264884 100644 --- a/packages/api/src/agent-manager.ts +++ b/packages/api/src/agent-manager.ts @@ -84,7 +84,7 @@ const TOOL_DESCRIPTIONS: Record<string, string> = { youtube_transcribe: "Fetch the transcript/subtitles for a YouTube video. Set background=true to start in the background and get a job_id for later retrieval.", send_to_tab: - "Send a message to another tab (agent) by its short ID, as shown in the tab bar. Fire-and-forget: it queues/wakes the target and returns immediately without waiting for a reply. Use read_tab later to read the target's response.", + "Send a message to another tab (agent) by its short ID, as shown in the tab bar. Fire-and-forget: it queues/wakes the target and returns immediately without waiting for a reply. Do NOT sleep, poll, or run commands to wait — a reply arrives on its own in a later turn (or use read_tab in a future turn); if you are only waiting, end your turn.", read_tab: "Read another tab (agent)'s most recent completed response by its short ID. Returns a non-blocking snapshot; if the target is still running you get its previous completed turn. Use after send_to_tab to collect a reply.", }; diff --git a/packages/core/src/tools/send-to-tab.ts b/packages/core/src/tools/send-to-tab.ts index eb86b7e..84e5f25 100644 --- a/packages/core/src/tools/send-to-tab.ts +++ b/packages/core/src/tools/send-to-tab.ts @@ -64,9 +64,14 @@ export function createSendToTabTool(callbacks: SendToTabCallbacks): ToolDefiniti " - If the target tab is idle, your message WAKES it and starts a new turn.", "", "This is fire-and-forget: it returns immediately and does NOT wait for a reply.", - "Use the 'read_tab' tool with the same ID later to read the target's latest response.", + "Do NOT sleep, poll, or run shell commands to wait for a reply — that wastes turns and", + "money. If the target replies it arrives on its own as a new message in a later turn; you", + "can also call 'read_tab' with the same ID in a FUTURE turn to check. If you have other", + "work to do, keep going; if you are ONLY waiting for the reply, end your turn now.", "", - "Your tab ID is auto-added to the top of the message so the recipient can reply to you.", + "Your tab ID is auto-added to the top of the message so the recipient knows who to reply", + "to. The recipient must use this same 'send_to_tab' tool (addressed to your ID) to answer;", + "a plain text response reaches only their own user, not you.", "IDs are git-style prefixes: pass any length that uniquely identifies the target (min 4 chars).", "If the ID is ambiguous you'll be asked to add a character.", ].join("\n"), @@ -117,8 +122,18 @@ export function createSendToTabTool(callbacks: SendToTabCallbacks): ToolDefiniti } // Stamp provenance so the recipient (and the watching user) can see - // which tab the message came from and reply back via its handle. - const delivered = `[message from tab ${callbacks.self.handle}]\n\n${message}`; + // which tab the message came from and how to reply. The header makes + // clear this is a PEER AGENT, not the recipient's own user, and the + // footer states the reply contract: a reply (only if warranted) must + // go back through `send_to_tab`, since a plain text answer reaches + // only the recipient's own user — not this sender. + const delivered = [ + `[message from tab ${callbacks.self.handle} — this is another agent, NOT your user]`, + "", + message, + "", + `[To reply to tab ${callbacks.self.handle}, use the send_to_tab tool with tab_id "${callbacks.self.handle}". Only reply if this message asks you to, or your user tells you to — it may just be context or instructions. A plain text response goes to your own user, not to this agent.]`, + ].join("\n"); try { const result = await callbacks.deliver(target.id, delivered); @@ -138,7 +153,14 @@ export function createSendToTabTool(callbacks: SendToTabCallbacks): ToolDefiniti result.status === "queued" ? "queued (target is busy; it will be picked up next turn)" : "delivered (target was idle; a new turn has started)"; - return `Message ${verb}. Target tab: ${target.handle} (${target.title}). Use read_tab with "${target.handle}" to read its reply later.`; + return [ + `Message ${verb}. Target tab: ${target.handle} (${target.title}).`, + "", + "Do NOT sleep, poll, or run commands to wait for a reply. If the target replies it", + `arrives on its own as a new message later; you can also call read_tab with "${target.handle}"`, + "in a FUTURE turn to check. Keep working if you have other tasks; if you are ONLY", + "waiting for this reply, end your turn now.", + ].join("\n"); } catch (err) { return `Error delivering message: ${err instanceof Error ? err.message : String(err)}`; } 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 () => { |