Let a delegated task choose the workspace it runs in
delegate_task had no workspace argument: a task handed over from the coordinator's own chat always ran in the worker's own chat, on that worker's memory, files and directly assigned computers alone, even when the work belonged to a workspace. The coordinator could not say where the work goes, and the prompt never said the two differ. - delegate_task takes an optional workspace_id: the worker runs the task in that workspace's context, with its own instructions and memory there, the project's files and the workspace's computers, and the result lands in its conversation in that workspace. - A worker missing from that workspace is added first (pushBotCreated) and the reply says so. - Handed over from inside a workspace the task always runs there; a different workspace_id is refused instead of ignored. - The coordinator prompt, CoordinatorReplyNote and the tool description now spell the distinction out.
This commit is contained in:
@@ -27,6 +27,9 @@ Permission to draft is not permission to send, permission to analyze is not perm
|
||||
## 2. Delegate well
|
||||
|
||||
- Pick by role, instructions and tools, not by name.
|
||||
- Say where the work runs, and mean it. \`delegate_task\` takes an optional \`workspace_id\`, and that one argument decides the whole context the worker has: its own chat, or a workspace. A task in the worker's own chat has only that worker's own memory, files and directly assigned computers. A task in a workspace has the workspace's shared context, the worker's instructions and memory for that workspace, the project's files, and the workspace's computers as well as the worker's. The result also lands in a different conversation: the worker's own chat, or its conversation in that workspace beside the rest of that project. Choose by where the work belongs, not by which is easier to type.
|
||||
- Handed over from a conversation inside a workspace, the task always runs in that workspace and \`workspace_id\` is not accepted: say so, don't pretend you moved it.
|
||||
- Delegating into a workspace the worker isn't in adds it to that workspace as a side effect. Say that in your reply when it happens; don't add members silently for a one-off.
|
||||
- Give a full brief: objective, inputs, deliverable, acceptance criteria, constraints.
|
||||
- Check \`list_tasks\` first. Never give two bots the same job, and don't restart work an open task already covers.
|
||||
- Track what comes back, judge it against the request, and integrate it. Don't pass a worker's unchecked claim on as fact.
|
||||
|
||||
@@ -115,7 +115,7 @@ Every action counts here: saving memory or instructions, creating or changing a
|
||||
/**
|
||||
* Added to the coordinator's chat prompt: it hands work to the crew.
|
||||
*/
|
||||
export const CoordinatorReplyNote = `As the coordinator, hand work that fits a crew member's role to them with delegate_task. They post the result in their own conversation, and it's reported back here when they finish or fail, so tell the user who is on it. When a report comes back, pass on what matters to the user, follow up on anything left, and propose what comes next: the next piece of work, which bot would take it, or a question that settles the direction. Once the user agrees, you can also grow the crew with create_bot, put a worker in a workspace with add_bot_to_workspace, and create or change a workspace with create_workspace and update_workspace. When you name a crew member, write its ref instead of its name, e.g. ${botRef({ id: 3 })}: the user sees it as the bot's name, linked to its conversation.`;
|
||||
export const CoordinatorReplyNote = `As the coordinator, hand work that fits a crew member's role to them with delegate_task. They post the result in their own conversation, and it's reported back here when they finish or fail, so tell the user who is on it and where: a task with no workspace_id runs in that bot's own chat, on its own memory, files and directly assigned computers; one with workspace_id runs in the workspace, on the workspace's context, files and computers as well as the bot's, and lands in that project's conversation. Never swap one for the other without saying so. When a report comes back, pass on what matters to the user, follow up on anything left, and propose what comes next: the next piece of work, which bot would take it, or a question that settles the direction. Once the user agrees, you can also grow the crew with create_bot, put a worker in a workspace with add_bot_to_workspace, and create or change a workspace with create_workspace and update_workspace. When you name a crew member, write its ref instead of its name, e.g. ${botRef({ id: 3 })}: the user sees it as the bot's name, linked to its conversation.`;
|
||||
|
||||
/**
|
||||
* Added to the coordinator's chat prompt instead while it has no workers,
|
||||
|
||||
@@ -0,0 +1,72 @@
|
||||
import { describe, expect, test } from "bun:test";
|
||||
import type { BUN_SQLITE_COBBLE_BOTS, BUN_SQLITE_COBBLE_WORKSPACES } from "@/db/types/db";
|
||||
import delegateTaskTool from "./delegate-task-tool";
|
||||
|
||||
const worker = { id: 5, name: "Researcher", role: "research", kind: "worker" } as BUN_SQLITE_COBBLE_BOTS;
|
||||
const workspace = { id: 3, name: "Launch", archived: 0 } as BUN_SQLITE_COBBLE_WORKSPACES;
|
||||
const signal = new AbortController().signal;
|
||||
|
||||
function coordinatorTool({
|
||||
workspace_id,
|
||||
workers = [worker],
|
||||
workspaces = [workspace],
|
||||
}: { workspace_id?: number; workers?: BUN_SQLITE_COBBLE_BOTS[]; workspaces?: BUN_SQLITE_COBBLE_WORKSPACES[] } = {}) {
|
||||
return delegateTaskTool({
|
||||
user_id: 1,
|
||||
coordinator_id: 1,
|
||||
session_id: 10,
|
||||
workspace_id: workspace_id ?? null,
|
||||
coordinator_name: "Coordinator",
|
||||
workers,
|
||||
workspaces,
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
* The tool's own confines, kept to what needs no database: the argument it
|
||||
* accepts and the refusal that keeps a workspace hand-over in its
|
||||
* workspace. Every run that gets past those reaches the DB.
|
||||
*/
|
||||
describe("delegateTaskTool", () => {
|
||||
test("takes an optional workspace the task runs in", () => {
|
||||
const tool = coordinatorTool();
|
||||
|
||||
expect(tool.name).toBe("delegate_task");
|
||||
expect(tool.schema?.safeParse({ bot_id: 5, title: "Dig", instructions: "Read the docs." }).success).toBe(true);
|
||||
expect(
|
||||
tool.schema?.safeParse({ bot_id: 5, title: "Dig", instructions: "Read the docs.", workspace_id: 3 }).success,
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
test("names the workspaces it can hand work into", () => {
|
||||
expect(coordinatorTool().description).toContain("3: Launch");
|
||||
});
|
||||
|
||||
test("in a workspace, says the task runs there and offers no other", () => {
|
||||
const tool = coordinatorTool({ workspace_id: 3 });
|
||||
|
||||
expect(tool.description).toContain("runs there");
|
||||
expect(tool.schema?.safeParse({ bot_id: 5, title: "Dig", instructions: "x", workspace_id: 9 }).success).toBe(
|
||||
true,
|
||||
);
|
||||
});
|
||||
|
||||
test("refuses to move a hand-over out of the workspace it came from", async () => {
|
||||
await expect(
|
||||
coordinatorTool({ workspace_id: 3 }).run({
|
||||
args: { bot_id: 5, title: "Dig", instructions: "x", workspace_id: 9 },
|
||||
signal,
|
||||
}),
|
||||
).rejects.toThrow(/runs in that workspace/);
|
||||
});
|
||||
|
||||
test("accepts the workspace it came from", async () => {
|
||||
/** Reaches the DB and fails there for a test id, never on the guard. */
|
||||
await expect(
|
||||
coordinatorTool({ workspace_id: 3 }).run({
|
||||
args: { bot_id: 5, title: "Dig", instructions: "x", workspace_id: 3 },
|
||||
signal,
|
||||
}),
|
||||
).rejects.not.toThrow(/runs in that workspace/);
|
||||
});
|
||||
});
|
||||
@@ -1,8 +1,12 @@
|
||||
import { z } from "zod";
|
||||
import type { BUN_SQLITE_COBBLE_BOTS } from "@/db/types/db";
|
||||
import type { BUN_SQLITE_COBBLE_BOTS, BUN_SQLITE_COBBLE_WORKSPACES } from "@/db/types/db";
|
||||
import pushBotCreated from "@/src/bots-queue/push-bot-created";
|
||||
import pushBotNotice from "@/src/bots-queue/push-bot-notice";
|
||||
import enqueueBotJob from "@/src/functions/backend/db/bots-queue/enqueue-bot-job";
|
||||
import grabOpenBotTask from "@/src/functions/backend/db/bots-queue/grab-open-bot-task";
|
||||
import addBotToWorkspace from "@/src/functions/backend/db/workspaces/add-bot-to-workspace";
|
||||
import grabUserWorkspaces from "@/src/functions/backend/db/workspaces/grab-user-workspaces";
|
||||
import grabWorkspaceBots from "@/src/functions/backend/db/workspaces/grab-workspace-bots";
|
||||
import insertBotMessage from "@/src/functions/backend/db/bots/insert-bot-message";
|
||||
import grabCrewWorkers from "@/src/functions/backend/db/bots/grab-crew-workers";
|
||||
import grabBotComputers from "@/src/functions/backend/db/computers/grab-bot-computers";
|
||||
@@ -32,19 +36,32 @@ type Params = {
|
||||
* The worker bots it can hand work to (in a workspace, its members).
|
||||
*/
|
||||
workers: BUN_SQLITE_COBBLE_BOTS[];
|
||||
/**
|
||||
* The user's live workspaces, for the picker. In a workspace there's
|
||||
* nothing to pick: the task runs there.
|
||||
*/
|
||||
workspaces?: BUN_SQLITE_COBBLE_WORKSPACES[];
|
||||
};
|
||||
|
||||
type Args = {
|
||||
bot_id: number;
|
||||
title: string;
|
||||
instructions: string;
|
||||
/**
|
||||
* The workspace the worker runs the task in, from the coordinator's own
|
||||
* chat. Left out, the worker runs it in its own chat, on its own
|
||||
* memory and its direct computers only.
|
||||
*/
|
||||
workspace_id?: number;
|
||||
};
|
||||
|
||||
/**
|
||||
* Lets the coordinator hand a task to a worker bot. The worker runs it on
|
||||
* the computer it's on (if it has one) and posts the result in its own
|
||||
* conversation, where a note says who asked; the result (or failure) is
|
||||
* also reported back in the coordinator's conversation.
|
||||
* Lets the coordinator hand a task to a worker bot: in its own chat, or in
|
||||
* one of the user's workspaces, which decides the work's context entirely.
|
||||
* The worker runs it on the computer it's on there (if it has one) and
|
||||
* posts the result in that conversation, where a note says who asked; the
|
||||
* result (or failure) is also reported back in the coordinator's
|
||||
* conversation.
|
||||
*/
|
||||
export default function delegateTaskTool({
|
||||
user_id,
|
||||
@@ -53,33 +70,79 @@ export default function delegateTaskTool({
|
||||
workspace_id,
|
||||
coordinator_name,
|
||||
workers,
|
||||
workspaces = [],
|
||||
}: Params): HarnessTool<Args> {
|
||||
const crew = workers
|
||||
.map((bot) => `${bot.id}: ${bot.name}${bot.role ? ` (${bot.role})` : ""}`)
|
||||
.join("; ");
|
||||
const places = workspaces
|
||||
.map((w) => `${w.id}: ${w.name}`)
|
||||
.join("; ");
|
||||
|
||||
return {
|
||||
name: "delegate_task",
|
||||
description: `Hand a task to a crew member. They run it in the background and post the result in their own conversation; it's also reported back here when they finish or fail. Write the instructions as a full brief: what to do, where, and how they'll know it's done. Crew: ${crew}.`,
|
||||
description: `Hand a task to a crew member. They run it in the background and post the result in their own conversation; it's also reported back here when they finish or fail. Write the instructions as a full brief: what to do, where, and how they'll know it's done. Crew: ${crew}.${
|
||||
workspace_id
|
||||
? ` You are working in a workspace, so the task runs there: in this workspace's context.`
|
||||
: ` Leave workspace_id out to run it in the crew member's own chat: only its own memory, files and directly assigned computers apply there, and the user finds the result by talking to it on its own. Add workspace_id to run it in one of the user's workspaces instead: the workspace's shared context, the member's instructions and memory there, its files and its computers (the workspace's own and the member's) all apply, and the result lands in its conversation in that workspace, beside the project it belongs to. Pick a workspace when the work belongs to that project; the member is added to it when it isn't in it yet. Workspaces: ${places || "none"}.`
|
||||
}`,
|
||||
schema: z.object({
|
||||
bot_id: z.number().int(),
|
||||
title: z.string().min(1).max(80),
|
||||
instructions: z.string().min(1).max(8000),
|
||||
workspace_id: z
|
||||
.number()
|
||||
.int()
|
||||
.optional()
|
||||
.describe(
|
||||
workspace_id
|
||||
? "Not available here: a task handed over in a workspace runs in that workspace."
|
||||
: "Run the task in this workspace: its shared context, memory, files and computers apply. Leave it out to run it in the crew member's own chat.",
|
||||
),
|
||||
}),
|
||||
run: async ({ args }) => {
|
||||
const fresh = await grabCrewWorkers({ workspace_id });
|
||||
/**
|
||||
* In a workspace the task can't leave it: the run is already
|
||||
* there, and that is the whole point of the hand-over.
|
||||
*/
|
||||
if (workspace_id && args.workspace_id && args.workspace_id != Number(workspace_id)) {
|
||||
throw new Error(
|
||||
`A task handed over from a workspace runs in that workspace. Leave workspace_id out, or hand it over from your own chat.`,
|
||||
);
|
||||
}
|
||||
|
||||
const target_workspace_id = workspace_id
|
||||
? Number(workspace_id)
|
||||
: args.workspace_id
|
||||
? Number(args.workspace_id)
|
||||
: null;
|
||||
|
||||
const fresh = await grabCrewWorkers({ workspace_id: target_workspace_id });
|
||||
const worker = fresh.find((bot) => bot.id == args.bot_id);
|
||||
|
||||
if (!worker?.id) {
|
||||
throw new Error(
|
||||
`No crew member has id ${args.bot_id}. Crew: ${fresh
|
||||
.map((bot) => `${bot.id}: ${bot.name}`)
|
||||
.join("; ") || "none"}.`,
|
||||
`No crew member has id ${args.bot_id}${
|
||||
target_workspace_id ? ` in workspace ${target_workspace_id}` : ""
|
||||
}. Crew: ${
|
||||
fresh.map((bot) => `${bot.id}: ${bot.name}`).join("; ") || "none"
|
||||
}.`,
|
||||
);
|
||||
}
|
||||
|
||||
const computers = await grabBotComputers({ bot_id: worker.id, workspace_id });
|
||||
const worker_session = await ensureBotSession({ user_id, bot_id: worker.id, workspace_id });
|
||||
const joined = target_workspace_id
|
||||
? await ensureWorkerInWorkspace({ user_id, worker, target_workspace_id })
|
||||
: "";
|
||||
|
||||
const computers = await grabBotComputers({
|
||||
bot_id: worker.id,
|
||||
workspace_id: target_workspace_id,
|
||||
});
|
||||
const worker_session = await ensureBotSession({
|
||||
user_id,
|
||||
bot_id: worker.id,
|
||||
workspace_id: target_workspace_id,
|
||||
});
|
||||
const open = await grabOpenBotTask({
|
||||
bot_id: worker.id,
|
||||
session_id: Number(worker_session.id),
|
||||
@@ -108,12 +171,58 @@ export default function delegateTaskTool({
|
||||
message: await insertBotMessage({
|
||||
bot_id: worker.id,
|
||||
session_id: Number(worker_session.id),
|
||||
workspace_id: workspace_id ? Number(workspace_id) : null,
|
||||
workspace_id: target_workspace_id,
|
||||
text: `${coordinator_name} asked me to: **${args.title}**`,
|
||||
}),
|
||||
});
|
||||
|
||||
return `Task #${job_id} is with ${worker.name}. Their result will be in their conversation and reported back here.`;
|
||||
return `Task #${job_id} is with ${worker.name}${
|
||||
target_workspace_id ? ` in workspace ${target_workspace_id}` : " in their own chat"
|
||||
}.${joined} Their result will be in that conversation and reported back here.`;
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
type EnsureParams = {
|
||||
user_id: number | string;
|
||||
worker: BUN_SQLITE_COBBLE_BOTS;
|
||||
target_workspace_id: number;
|
||||
};
|
||||
|
||||
/**
|
||||
* A worker can only run a task in a workspace it's in, and a workspace's
|
||||
* members were already listed by `grabCrewWorkers`. Anyone else is added
|
||||
* first, since delegation is exactly the moment the broker decides who
|
||||
* does the work where.
|
||||
*/
|
||||
async function ensureWorkerInWorkspace({
|
||||
user_id,
|
||||
worker,
|
||||
target_workspace_id,
|
||||
}: EnsureParams) {
|
||||
if (!worker.id) return "";
|
||||
|
||||
const workspaces = (await grabUserWorkspaces({ user_id })).filter((w) => !w.archived);
|
||||
const workspace = workspaces.find((w) => w.id == target_workspace_id);
|
||||
|
||||
if (!workspace) {
|
||||
throw new Error(
|
||||
`No workspace has id ${target_workspace_id}. Workspaces: ${
|
||||
workspaces.map((w) => `${w.id}: ${w.name}`).join("; ") || "none"
|
||||
}. Hand the task over without workspace_id to run it in the crew member's own chat.`,
|
||||
);
|
||||
}
|
||||
|
||||
const members = await grabWorkspaceBots({ user_id, workspace_id: target_workspace_id });
|
||||
|
||||
if (members.some((bot) => bot.id == worker.id)) return "";
|
||||
|
||||
await addBotToWorkspace({
|
||||
user_id,
|
||||
workspace_id: target_workspace_id,
|
||||
bot_id: Number(worker.id),
|
||||
});
|
||||
await pushBotCreated({ bot: worker });
|
||||
|
||||
return ` ${worker.name} wasn't in "${workspace.name}", so it was added to it first.`;
|
||||
}
|
||||
|
||||
@@ -61,7 +61,9 @@ type Params = {
|
||||
* for the coordinator (the super admin's alone) create_workspace and
|
||||
* update_workspace (a workspace and its shared context), create_bot to
|
||||
* grow the crew, delegate_task to every worker (the workspace's in a
|
||||
* workspace) plus, in its own chat, find_bot and find_workspace,
|
||||
* workspace, where the task runs; from its own chat, in the worker's own
|
||||
* chat or in a workspace it names) plus, in its own chat, find_bot and
|
||||
* find_workspace,
|
||||
* add_bot_to_workspace and remove_bot_from_workspace, assign_computer,
|
||||
* update_bot, delete_bot and delete_workspace (which workspace, which
|
||||
* computers, and which name, role and core instructions each crew member
|
||||
@@ -150,6 +152,7 @@ export default async function grabBotChatTools({
|
||||
workspace_id,
|
||||
coordinator_name: bot.name || "The coordinator",
|
||||
workers,
|
||||
workspaces,
|
||||
}),
|
||||
);
|
||||
|
||||
|
||||
Reference in New Issue
Block a user