fix: provide tolerance for apply_patch tool (#993)

As explained in detail in the doc comment for `ParseMode::Lenient`, we
have observed that GPT-4.1 does not always generate a valid invocation
of `apply_patch`. Fortunately, the error is predictable, so we introduce
some new logic to the `codex-apply-patch` crate to recover from this
error.

Because we would like to avoid this becoming a de facto standard (as it
would be incompatible if `apply_patch` were provided as an actual
executable, unless we also introduced the lenient behavior in the
executable, as well), we require passing `ParseMode::Lenient` to
`parse_patch_text()` to make it clear that the caller is opting into
supporting this special case.

Note the analogous change to the TypeScript CLI was
https://github.com/openai/codex/pull/930. In addition to changing the
accepted input to `apply_patch`, it also introduced additional
instructions for the model, which we include in this PR.

Note that `apply-patch` does not depend on either `regex` or
`regex-lite`, so some of the checks are slightly more verbose to avoid
introducing this dependency.

That said, this PR does not leverage the existing
`extract_heredoc_body_from_apply_patch_command()`, which depends on
`tree-sitter` and `tree-sitter-bash`:


5a5aa89914/codex-rs/apply-patch/src/lib.rs (L191-L246)

though perhaps it should.

codex-rs/core/src/client.rs

@@ -106,7 +106,7 @@ impl ModelClient {
             return stream_from_fixture(path).await;
         }
 
-        let full_instructions = prompt.get_full_instructions();
+        let full_instructions = prompt.get_full_instructions(&self.model);
         let tools_json = create_tools_json_for_responses_api(prompt, &self.model)?;
         let reasoning = create_reasoning_param_for_request(&self.model, self.effort, self.summary);
         let payload = ResponsesApiRequest {