Run the CEO agent autonomously with a real tool-use loop

The new app reached a real LLM but never ran an agent: the kickoff task_run
sat queued forever and runTask was a single text completion with no tools.

This adds the missing runtime:
- provider-tool-turn: OpenAI Responses + Anthropic Messages tool-use turns
- agent-tools + deliverable-writer: hire_agent, create_task,
  update_task_status, write_deliverable (workspace-scoped, traversal-safe)
- agent-run-loop: real tool-use loop, capped iterations
- task-queue-worker: claims queued runs in a transaction and executes them

task-execution now drives the loop; a background worker auto-runs the
bootstrap CEO run so it hires its team, delegates tasks, and writes the first
deliverable into the bound workspace. Autonomy is gated by AGENTCOMPANY_NEW_AUTORUN
(tests run with it off to stay hermetic).
This commit is contained in:
ZacharyZhang-NY committed 2026-05-29 21:08:04 -04:00
1 parent 1c7b81830e
commit 0575712e02
15 files changed
+1008 -74

No files matched your search

+6
View File
@@ -5,6 +5,7 @@ import { DatabaseConnection } from "./database/connection";
import { createMainWindow } from "./app/create-window";
import { registerIpcHandlers } from "./app/ipc-handlers";
import { startProviderBackgroundWorker } from "./app/provider-background-worker";
import { startTaskQueueWorker } from "./app/task-queue-worker";
const __dirname = dirname(fileURLToPath(import.meta.url));
const hasSingleInstanceLock = app.requestSingleInstanceLock();
@@ -31,6 +32,10 @@ app.whenReady().then(() => {
db: connection.db,
mainWindow: win,
});
const autonomousExecution = process.env.AGENTCOMPANY_NEW_AUTORUN !== "0";
const stopTaskQueueWorker = autonomousExecution
? startTaskQueueWorker({ connection, mainWindow: win })
: () => {};
app.on("second-instance", () => {
if (win.isMinimized()) win.restore();
@@ -39,6 +44,7 @@ app.whenReady().then(() => {
app.on("before-quit", () => {
stopProviderBackgroundWorker();
stopTaskQueueWorker();
connection.close();
});
});