[apply_patch] freeform apply_patch tool (#2576)

## Summary
GPT-5 introduced the concept of [custom
tools](https://platform.openai.com/docs/guides/function-calling#custom-tools),
which allow the model to send a raw string result back, simplifying
json-escape issues. We are migrating gpt-5 to use this by default.

However, gpt-oss models do not support custom tools, only normal
functions. So we keep both tool definitions, and provide whichever one
the model family supports.

## Testing
- [x] Tested locally with various models
- [x] Unit tests pass

codex-rs/core/src/config.rs

@@ -646,7 +646,7 @@ impl Config {
                 needs_special_apply_patch_instructions: false,
                 supports_reasoning_summaries,
                 uses_local_shell_tool: false,
-                uses_apply_patch_tool: false,
+                apply_patch_tool_type: None,
             }
         });
 
@@ -673,9 +673,6 @@ impl Config {
             Self::get_base_instructions(experimental_instructions_path, &resolved_cwd)?;
         let base_instructions = base_instructions.or(file_base_instructions);
 
-        let include_apply_patch_tool_val =
-            include_apply_patch_tool.unwrap_or(model_family.uses_apply_patch_tool);
-
         let responses_originator_header: String = cfg
             .responses_originator_header_internal_override
             .unwrap_or(DEFAULT_RESPONSES_ORIGINATOR_HEADER.to_owned());
@@ -732,7 +729,7 @@ impl Config {
 
             experimental_resume,
             include_plan_tool: include_plan_tool.unwrap_or(false),
-            include_apply_patch_tool: include_apply_patch_tool_val,
+            include_apply_patch_tool: include_apply_patch_tool.unwrap_or(false),
             responses_originator_header,
             preferred_auth_method: cfg.preferred_auth_method.unwrap_or(AuthMode::ChatGPT),
         };