ZacharyZhang-NY/AgentCompany
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity

Q83: a model passes an agent check before it does agent work

Browse Source 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
ZacharyZhang-NYandClaude Opus 5.5 committed 2026-10-08 14:19:48 -04:00
1 parent 4e232b241f
commit 665bf3cae1
35 files changed
+350 -47
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/unit/task-execution-service.test.ts
+6 -5
View File
@@ -14,6 +14,7 @@ import { SnapshotService } from "../../src/main/services/snapshot-service";
import { TaskExecutionService } from "../../src/main/services/task-execution-service";
import { APPROVAL_STATE, PROVIDER_DATA_POLICY, RISK_LEVEL, TASK_PRIORITY, TASK_STATUS } from "../../src/shared/domain";
import { currentProviderUsageWindow, PROVIDER_MONTHLY_LIMIT_MESSAGE } from "../../src/shared/provider-runtime-domain";
import { answeringModelCheck } from "../helpers/model-check";
function createConnection(): DatabaseConnection {
return new DatabaseConnection(join(tmpdir(), `agentcompany-new-task-execution-${randomUUID()}.db`));
@@ -40,7 +41,7 @@ describe("task execution service", () => {
if (first?.role === "user") capturedPrompt = first.text;
return { text: "executed:gpt-5.4", toolCalls: [], rawResponseJson: JSON.stringify({ id: "resp-task-1" }) };
};
const providers = new ProviderService(connection.db, providerAdapters, testVault, undefined, fakeToolTurn);
const providers = new ProviderService(connection.db, providerAdapters, testVault, undefined, answeringModelCheck(fakeToolTurn));
const skills = new SkillService(connection.db, join(tmpdir(), `agentcompany-task-skills-${randomUUID()}`));
const execution = new TaskExecutionService(connection.db, providers);
const skillDir = join(tmpdir(), `agentcompany-task-skill-${randomUUID()}`);
@@ -152,7 +153,7 @@ describe("task execution service", () => {
toolCalls: [],
rawResponseJson: JSON.stringify({ id: "resp-task-approved" }),
});
const providers = new ProviderService(connection.db, providerAdapters, testVault, undefined, fakeToolTurn);
const providers = new ProviderService(connection.db, providerAdapters, testVault, undefined, answeringModelCheck(fakeToolTurn));
const execution = new TaskExecutionService(connection.db, providers);
let orgId = "";
let employeeId = "";
@@ -291,7 +292,7 @@ describe("task execution service", () => {
const fakeToolTurn = async (): Promise<AgentTurnResult> => {
throw new Error("provider rejected task");
};
const providers = new ProviderService(connection.db, providerAdapters, testVault, undefined, fakeToolTurn);
const providers = new ProviderService(connection.db, providerAdapters, testVault, undefined, answeringModelCheck(fakeToolTurn));
const execution = new TaskExecutionService(connection.db, providers);
let orgId = "";
let taskId = "";
@@ -349,7 +350,7 @@ describe("task execution service", () => {
turns += 1;
return { text: "done", toolCalls: [], rawResponseJson: JSON.stringify({ id: `resp-${turns}` }) };
};
const providers = new ProviderService(connection.db, providerAdapters, testVault, undefined, fakeToolTurn);
const providers = new ProviderService(connection.db, providerAdapters, testVault, undefined, answeringModelCheck(fakeToolTurn));
const execution = new TaskExecutionService(connection.db, providers);
let orgId = "";
let taskId = "";
@@ -848,7 +849,7 @@ describe("task execution service", () => {
const fakeToolTurn = async (): Promise<AgentTurnResult> => {
throw new Error("The usage limit has been reached");
};
const providers = new ProviderService(connection.db, providerAdapters, testVault, undefined, fakeToolTurn);
const providers = new ProviderService(connection.db, providerAdapters, testVault, undefined, answeringModelCheck(fakeToolTurn));
let nowMs = Date.now();
const execution = new TaskExecutionService(connection.db, providers, undefined, undefined, () => nowMs);
let orgId = "";