Revert tool-choice forcing — the Codex regression was strict:null

The GPT-account (Codex) path supports tool calls and worked before; my
forced tool_choice broke it and was the wrong fix. The real regression was
strict:null in the rebuild's tool definitions, which made the endpoint drop
the tool list so the model had nothing to call — a "Done" run that hired no
one. Forcing then turned that silent failure into a red one.

Restore the original "auto" loop (no forced tool_choice, no finish tool) and
keep only the one-line strict:null omission. Codex now receives valid tools
on the working "auto" choice, as in the version that worked.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

AgentCompany-New/tests/unit/task-execution-service.test.ts

@@ -37,11 +37,7 @@ describe("task execution service", () => {
     const fakeToolTurn = async (input: ProviderToolTurnInput): Promise<AgentTurnResult> => {
       const first = input.messages[0];
       if (first?.role === "user") capturedPrompt = first.text;
-      const acted = input.messages.some((message) => message.role === "tool");
-      const toolCall = acted
-        ? { id: `call_${randomUUID()}`, name: "finish", arguments: {} }
-        : { id: `call_${randomUUID()}`, name: "create_document", arguments: { title: "Run note", doc_type: "memo", content: "Executed." } };
-      return { text: "executed:gpt-5.4", toolCalls: [toolCall], rawResponseJson: JSON.stringify({ id: "resp-task-1" }) };
+      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 skills = new SkillService(connection.db, join(tmpdir(), `agentcompany-task-skills-${randomUUID()}`));
@@ -145,13 +141,11 @@ describe("task execution service", () => {
     const organization = new OrganizationService(connection.db);
     const approvals = new ApprovalService(connection.db);
     const snapshot = new SnapshotService(connection.db);
-    const fakeToolTurn = async (input: ProviderToolTurnInput): Promise<AgentTurnResult> => {
-      const acted = input.messages.some((message) => message.role === "tool");
-      const toolCall = acted
-        ? { id: `call_${randomUUID()}`, name: "finish", arguments: {} }
-        : { id: `call_${randomUUID()}`, name: "create_document", arguments: { title: "Run note", doc_type: "memo", content: "Executed." } };
-      return { text: "executed:gpt-5.4", toolCalls: [toolCall], rawResponseJson: JSON.stringify({ id: "resp-task-approved" }) };
-    };
+    const fakeToolTurn = async (): Promise<AgentTurnResult> => ({
+      text: "executed:gpt-5.4",
+      toolCalls: [],
+      rawResponseJson: JSON.stringify({ id: "resp-task-approved" }),
+    });
     const providers = new ProviderService(connection.db, providerAdapters, testVault, undefined, fakeToolTurn);
     const execution = new TaskExecutionService(connection.db, providers);
     let orgId = "";