Add exec output-schema parameter (#4079)

Adds structured output to `exec` via the `--structured-output`
parameter.

codex-rs/core/tests/suite/json_result.rs

@@ -0,0 +1,97 @@
+#![cfg(not(target_os = "windows"))]
+
+use codex_core::protocol::AskForApproval;
+use codex_core::protocol::EventMsg;
+use codex_core::protocol::InputItem;
+use codex_core::protocol::Op;
+use codex_core::protocol::SandboxPolicy;
+use codex_protocol::config_types::ReasoningSummary;
+use core_test_support::non_sandbox_test;
+use core_test_support::responses;
+use core_test_support::test_codex::TestCodex;
+use core_test_support::test_codex::test_codex;
+use core_test_support::wait_for_event;
+use pretty_assertions::assert_eq;
+use responses::ev_assistant_message;
+use responses::ev_completed;
+use responses::sse;
+use responses::start_mock_server;
+
+const SCHEMA: &str = r#"
+{
+    "type": "object",
+    "properties": {
+        "explanation": { "type": "string" },
+        "final_answer": { "type": "string" }
+    },
+    "required": ["explanation", "final_answer"],
+    "additionalProperties": false
+}
+"#;
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn codex_returns_json_result() -> anyhow::Result<()> {
+    non_sandbox_test!(result);
+
+    let server = start_mock_server().await;
+
+    let sse1 = sse(vec![
+        ev_assistant_message(
+            "m2",
+            r#"{"explanation": "explanation", "final_answer": "final_answer"}"#,
+        ),
+        ev_completed("r1"),
+    ]);
+
+    let expected_schema: serde_json::Value = serde_json::from_str(SCHEMA)?;
+    let match_json_text_param = move |req: &wiremock::Request| {
+        let body: serde_json::Value = serde_json::from_slice(&req.body).unwrap_or_default();
+        let Some(text) = body.get("text") else {
+            return false;
+        };
+        let Some(format) = text.get("format") else {
+            return false;
+        };
+
+        format.get("name") == Some(&serde_json::Value::String("codex_output_schema".into()))
+            && format.get("type") == Some(&serde_json::Value::String("json_schema".into()))
+            && format.get("strict") == Some(&serde_json::Value::Bool(true))
+            && format.get("schema") == Some(&expected_schema)
+    };
+    responses::mount_sse_once(&server, match_json_text_param, sse1).await;
+
+    let TestCodex { codex, cwd, .. } = test_codex().build(&server).await?;
+
+    // 1) Normal user input – should hit server once.
+    codex
+        .submit(Op::UserTurn {
+            items: vec![InputItem::Text {
+                text: "hello world".into(),
+            }],
+            final_output_json_schema: Some(serde_json::from_str(SCHEMA)?),
+            cwd: cwd.path().to_path_buf(),
+            approval_policy: AskForApproval::Never,
+            sandbox_policy: SandboxPolicy::DangerFullAccess,
+            model: "gpt-5".to_string(),
+            effort: None,
+            summary: ReasoningSummary::Auto,
+        })
+        .await?;
+
+    let message = wait_for_event(&codex, |ev| matches!(ev, EventMsg::AgentMessage(_))).await;
+    if let EventMsg::AgentMessage(message) = message {
+        let json: serde_json::Value = serde_json::from_str(&message.message)?;
+        assert_eq!(
+            json.get("explanation"),
+            Some(&serde_json::Value::String("explanation".into()))
+        );
+        assert_eq!(
+            json.get("final_answer"),
+            Some(&serde_json::Value::String("final_answer".into()))
+        );
+    } else {
+        anyhow::bail!("expected agent message event");
+    }
+
+    Ok(())
+}

codex-rs/core/tests/suite/mod.rs

@@ -7,6 +7,7 @@ mod compact_resume_fork;
 mod exec;
 mod exec_stream_events;
 mod fork_conversation;
+mod json_result;
 mod live_cli;
 mod model_overrides;
 mod prompt_caching;

codex-rs/core/tests/suite/prompt_caching.rs

@@ -546,6 +546,7 @@ async fn per_turn_overrides_keep_cached_prefix_and_key_constant() {
             model: "o3".to_string(),
             effort: Some(ReasoningEffort::High),
             summary: ReasoningSummary::Detailed,
+            final_output_json_schema: None,
         })
         .await
         .unwrap();
@@ -655,6 +656,7 @@ async fn send_user_turn_with_no_changes_does_not_send_environment_context() {
             model: default_model.clone(),
             effort: default_effort,
             summary: default_summary,
+            final_output_json_schema: None,
         })
         .await
         .unwrap();
@@ -671,6 +673,7 @@ async fn send_user_turn_with_no_changes_does_not_send_environment_context() {
             model: default_model.clone(),
             effort: default_effort,
             summary: default_summary,
+            final_output_json_schema: None,
         })
         .await
         .unwrap();
@@ -766,6 +769,7 @@ async fn send_user_turn_with_changes_sends_environment_context() {
             model: default_model,
             effort: default_effort,
             summary: default_summary,
+            final_output_json_schema: None,
         })
         .await
         .unwrap();
@@ -782,6 +786,7 @@ async fn send_user_turn_with_changes_sends_environment_context() {
             model: "o3".to_string(),
             effort: Some(ReasoningEffort::High),
             summary: ReasoningSummary::Detailed,
+            final_output_json_schema: None,
         })
         .await
         .unwrap();