chore: testing on freeform apply_patch (openai#5952)

## Summary
Duplicates the tests in `apply_patch_cli.rs`, but tests the freeform
apply_patch tool as opposed to the function call path. The good news is
that all the tests pass with zero logical tests, with the exception of
the heredoc, which doesn't really make sense in the freeform tool
context anyway.

@jif-oai since you wrote the original tests in openai#5557, I'd love your
opinion on the right way to DRY these test cases between the two. Happy
to set up a more sophisticated harness, but didn't want to go down the
rabbit hole until we agreed on the right pattern

## Testing
- [x] These are tests

Author: dylan-hurd-oai

codex-rs/core/tests/common/test_codex.rs

@@ -240,6 +240,30 @@ impl TestCodexHarness {
             .expect("output string")
             .to_string()
     }
+
+    pub async fn custom_tool_call_output(&self, call_id: &str) -> String {
+        let bodies = self.request_bodies().await;
+        custom_tool_call_output(&bodies, call_id)
+            .get("output")
+            .and_then(Value::as_str)
+            .expect("output string")
+            .to_string()
+    }
+}
+
+fn custom_tool_call_output<'a>(bodies: &'a [Value], call_id: &str) -> &'a Value {
+    for body in bodies {
+        if let Some(items) = body.get("input").and_then(Value::as_array) {
+            for item in items {
+                if item.get("type").and_then(Value::as_str) == Some("custom_tool_call_output")
+                    && item.get("call_id").and_then(Value::as_str) == Some(call_id)
+                {
+                    return item;
+                }
+            }
+        }
+    }
+    panic!("custom_tool_call_output {call_id} not found");
 }
 
 fn function_call_output<'a>(bodies: &'a [Value], call_id: &str) -> &'a Value {