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/integration/agent-reply.test.ts

@@ -37,7 +37,7 @@ function scriptedTeam(): (input: ProviderToolTurnInput) => Promise<AgentTurnResu
       call("create_task", { title: "Build the booking API", description: "Ship the booking API.", assignee_agent_name: "Dana Lee" }),
       call("send_message", { channel: "engineering", body: `@${handle} you own the booking API — kicking off here.` }),
     ] },
-    { text: "Kickoff complete.", toolCalls: [call("finish", {})] },
+    { text: "Kickoff complete.", toolCalls: [] },
   ];
   return async (input: ProviderToolTurnInput): Promise<AgentTurnResult> => {
     if ((input.instructions ?? "").includes("Dana Lee")) {
@@ -46,11 +46,11 @@ function scriptedTeam(): (input: ProviderToolTurnInput) => Promise<AgentTurnResu
       const threadId = firstUser ? /thread_id="([^"]+)"/.exec(firstUser.text)?.[1] : undefined;
       const turn = dana === 0
         ? { text: "On it.", toolCalls: [call("send_message", { channel: "engineering", body: "On it — booking API design starting now.", ...(threadId ? { thread_id: threadId } : {}) })] }
-        : { text: "Replied.", toolCalls: [call("finish", {})] };
+        : { text: "Replied.", toolCalls: [] };
       dana += 1;
       return { text: turn.text, toolCalls: turn.toolCalls, rawResponseJson: "{}" };
     }
-    const turn = ceoScript[ceo] ?? { text: "done", toolCalls: [call("finish", {})] };
+    const turn = ceoScript[ceo] ?? { text: "done", toolCalls: [] };
     ceo += 1;
     return { text: turn.text, toolCalls: turn.toolCalls, rawResponseJson: "{}" };
   };

AgentCompany-New/tests/integration/autonomous-run.test.ts

@@ -36,7 +36,7 @@ function scriptedCeo(): (input: ProviderToolTurnInput) => Promise<AgentTurnResul
       call("write_deliverable", { path: "plan/operating-plan.md", content: "# OrbitOps Operating Plan\n\n- Validate demand\n- Launch booking site\n" }),
     ] },
     { text: "Handing off the plan.", toolCalls: [] },
-    { text: "Team staffed, work delegated, plan written.", toolCalls: [call("finish", {})] },
+    { text: "Team staffed, work delegated, plan written.", toolCalls: [] },
   ];
   let index = 0;
   return async (input) => {
@@ -55,7 +55,7 @@ function scriptedCeo(): (input: ProviderToolTurnInput) => Promise<AgentTurnResul
         rawResponseJson: JSON.stringify({ id: `resp_${index}` }),
       };
     }
-    const turn = script[index] ?? { text: "done", toolCalls: [call("finish", {})] };
+    const turn = script[index] ?? { text: "done", toolCalls: [] };
     index += 1;
     return { text: turn.text, toolCalls: turn.toolCalls, rawResponseJson: JSON.stringify({ id: `resp_${index}` }) };
   };
@@ -166,17 +166,11 @@ describe("autonomous bootstrap run", () => {
 
   test("a goal created after onboarding reaches the CEO and runs autonomously", async () => {
     const connection = new DatabaseConnection(join(tmpdir(), `ac-goal-${randomUUID()}.db`));
-    // The forced opening turn means each run must take a concrete action; it
-    // posts to the company channel, then stops on the next (free) turn.
-    const providers = new ProviderService(connection.db, providerAdapters, testVault, undefined, async (input) => {
-      const acted = input.messages.some((message) => message.role === "tool");
-      if (acted) return { text: "Done.", toolCalls: [call("finish", {})], rawResponseJson: JSON.stringify({ id: "resp_goal_done" }) };
-      return {
-        text: "Reviewing the goal.",
-        toolCalls: [call("send_message", { channel: "general", body: "Reviewed the goal and posting the operating plan." })],
-        rawResponseJson: JSON.stringify({ id: "resp_goal_act" }),
-      };
-    });
+    const providers = new ProviderService(connection.db, providerAdapters, testVault, undefined, async () => ({
+      text: "Reviewed the goal and posted the operating plan.",
+      toolCalls: [],
+      rawResponseJson: JSON.stringify({ id: "resp_goal" }),
+    }));
     const onboarding = new OnboardingService({ db: connection.db, saveProviderCredential: (input) => providers.saveCredential(input) });
     const organization = new OrganizationService(connection.db);
     const taskExecution = new TaskExecutionService(connection.db, providers);