[codex] exec-server: stream files in chunks (#28354)

## Why

`fs/readFile` buffers the entire file in one response, which makes large
remote reads expensive and prevents callers from applying backpressure.
We need an opt-in streaming path with bounded block sizes while
preserving the existing single-call API for small and sandboxed reads.

## What changed

- Add `ExecServerClient::stream`, returning a named `FileReadStream`
that implements `futures::Stream` and yields immutable 1 MiB byte
blocks.
- Add internal `fs/open`, `fs/readBlock`, and `fs/close` RPCs.
`fs/readBlock` accepts an explicit offset and length.
- Keep unsandboxed files open between block reads, cap open handles per
connection, and clean them up on EOF, error, stream drop, explicit
close, or connection shutdown.
- Reject platform-sandboxed streaming opens instead of turning the
one-shot sandbox helper into a persistent server. Existing `fs/readFile`
behavior is unchanged.

## Testing

- `just test -p codex-exec-server`
- Integration coverage for 1 MiB chunking, exact block-boundary EOF,
sandbox rejection, and continued reads from the opened file after path
replacement.
- Handle-manager coverage for non-sequential offsets, variable block
lengths, the 128-handle limit, and capacity release after close.
This commit is contained in:
pakrym-oai
2026-06-16 09:50:55 -07:00
committed by GitHub
parent 76135cbe7e
commit a4711b88dd
25 changed files with 1229 additions and 36 deletions
@@ -9,16 +9,23 @@ use crate::CreateDirectoryOptions;
use crate::ExecServerRuntimePaths;
use crate::ExecutorFileSystem;
use crate::RemoveOptions;
use crate::file_read::FileReadHandleManager;
use crate::local_file_system::LocalFileSystem;
use crate::protocol::FS_WRITE_FILE_METHOD;
use crate::protocol::FsCanonicalizeParams;
use crate::protocol::FsCanonicalizeResponse;
use crate::protocol::FsCloseParams;
use crate::protocol::FsCloseResponse;
use crate::protocol::FsCopyParams;
use crate::protocol::FsCopyResponse;
use crate::protocol::FsCreateDirectoryParams;
use crate::protocol::FsCreateDirectoryResponse;
use crate::protocol::FsGetMetadataParams;
use crate::protocol::FsGetMetadataResponse;
use crate::protocol::FsOpenParams;
use crate::protocol::FsOpenResponse;
use crate::protocol::FsReadBlockParams;
use crate::protocol::FsReadBlockResponse;
use crate::protocol::FsReadDirectoryEntry;
use crate::protocol::FsReadDirectoryParams;
use crate::protocol::FsReadDirectoryResponse;
@@ -32,18 +39,69 @@ use crate::rpc::internal_error;
use crate::rpc::invalid_request;
use crate::rpc::not_found;
const MAX_FILE_READ_HANDLE_ID_BYTES: usize = 32;
#[derive(Clone)]
pub(crate) struct FileSystemHandler {
file_system: LocalFileSystem,
file_reads: FileReadHandleManager,
}
impl FileSystemHandler {
pub(crate) fn new(runtime_paths: ExecServerRuntimePaths) -> Self {
Self {
file_system: LocalFileSystem::with_runtime_paths(runtime_paths),
file_reads: FileReadHandleManager::default(),
}
}
pub(crate) async fn shutdown(&self) {
self.file_reads.close_all().await;
}
pub(crate) async fn open(
&self,
params: FsOpenParams,
) -> Result<FsOpenResponse, JSONRPCErrorError> {
validate_file_read_handle_id(&params.handle_id)?;
let file = self
.file_system
.open_file_for_read(&params.path, params.sandbox.as_ref())
.await
.map_err(map_fs_error)?;
let handle_id = self
.file_reads
.open(params.handle_id, file)
.await
.map_err(map_fs_error)?;
Ok(FsOpenResponse { handle_id })
}
pub(crate) async fn read_block(
&self,
params: FsReadBlockParams,
) -> Result<FsReadBlockResponse, JSONRPCErrorError> {
validate_file_read_handle_id(&params.handle_id)?;
let block = self
.file_reads
.read_block(&params.handle_id, params.offset, params.len)
.await
.map_err(map_fs_error)?;
Ok(FsReadBlockResponse {
chunk: block.bytes.into(),
eof: block.eof,
})
}
pub(crate) async fn close(
&self,
params: FsCloseParams,
) -> Result<FsCloseResponse, JSONRPCErrorError> {
validate_file_read_handle_id(&params.handle_id)?;
self.file_reads.close(&params.handle_id).await;
Ok(FsCloseResponse {})
}
pub(crate) async fn read_file(
&self,
params: FsReadFileParams,
@@ -176,6 +234,15 @@ impl FileSystemHandler {
}
}
fn validate_file_read_handle_id(handle_id: &str) -> Result<(), JSONRPCErrorError> {
if handle_id.len() > MAX_FILE_READ_HANDLE_ID_BYTES {
return Err(invalid_request(format!(
"file read handle ID must not exceed {MAX_FILE_READ_HANDLE_ID_BYTES} bytes"
)));
}
Ok(())
}
fn map_fs_error(err: io::Error) -> JSONRPCErrorError {
match err.kind() {
io::ErrorKind::NotFound => not_found(err.to_string()),
@@ -19,12 +19,18 @@ use crate::protocol::ExecParams;
use crate::protocol::ExecResponse;
use crate::protocol::FsCanonicalizeParams;
use crate::protocol::FsCanonicalizeResponse;
use crate::protocol::FsCloseParams;
use crate::protocol::FsCloseResponse;
use crate::protocol::FsCopyParams;
use crate::protocol::FsCopyResponse;
use crate::protocol::FsCreateDirectoryParams;
use crate::protocol::FsCreateDirectoryResponse;
use crate::protocol::FsGetMetadataParams;
use crate::protocol::FsGetMetadataResponse;
use crate::protocol::FsOpenParams;
use crate::protocol::FsOpenResponse;
use crate::protocol::FsReadBlockParams;
use crate::protocol::FsReadBlockResponse;
use crate::protocol::FsReadDirectoryParams;
use crate::protocol::FsReadDirectoryResponse;
use crate::protocol::FsReadFileParams;
@@ -87,6 +93,7 @@ impl ExecServerHandler {
self.background_task_shutdown.cancel();
self.background_tasks.close();
self.background_tasks.wait().await;
self.file_system.shutdown().await;
if let Some(session) = self.session() {
session.detach().await;
}
@@ -234,6 +241,30 @@ impl ExecServerHandler {
self.file_system.read_file(params).await
}
pub(crate) async fn fs_open(
&self,
params: FsOpenParams,
) -> Result<FsOpenResponse, JSONRPCErrorError> {
self.require_initialized_for("filesystem")?;
self.file_system.open(params).await
}
pub(crate) async fn fs_read_block(
&self,
params: FsReadBlockParams,
) -> Result<FsReadBlockResponse, JSONRPCErrorError> {
self.require_initialized_for("filesystem")?;
self.file_system.read_block(params).await
}
pub(crate) async fn fs_close(
&self,
params: FsCloseParams,
) -> Result<FsCloseResponse, JSONRPCErrorError> {
self.require_initialized_for("filesystem")?;
self.file_system.close(params).await
}
pub(crate) async fn fs_write_file(
&self,
params: FsWriteFileParams,
@@ -8,17 +8,23 @@ use crate::protocol::EXEC_TERMINATE_METHOD;
use crate::protocol::EXEC_WRITE_METHOD;
use crate::protocol::ExecParams;
use crate::protocol::FS_CANONICALIZE_METHOD;
use crate::protocol::FS_CLOSE_METHOD;
use crate::protocol::FS_COPY_METHOD;
use crate::protocol::FS_CREATE_DIRECTORY_METHOD;
use crate::protocol::FS_GET_METADATA_METHOD;
use crate::protocol::FS_OPEN_METHOD;
use crate::protocol::FS_READ_BLOCK_METHOD;
use crate::protocol::FS_READ_DIRECTORY_METHOD;
use crate::protocol::FS_READ_FILE_METHOD;
use crate::protocol::FS_REMOVE_METHOD;
use crate::protocol::FS_WRITE_FILE_METHOD;
use crate::protocol::FsCanonicalizeParams;
use crate::protocol::FsCloseParams;
use crate::protocol::FsCopyParams;
use crate::protocol::FsCreateDirectoryParams;
use crate::protocol::FsGetMetadataParams;
use crate::protocol::FsOpenParams;
use crate::protocol::FsReadBlockParams;
use crate::protocol::FsReadDirectoryParams;
use crate::protocol::FsReadFileParams;
use crate::protocol::FsRemoveParams;
@@ -93,6 +99,24 @@ pub(crate) fn build_router() -> RpcRouter<ExecServerHandler> {
handler.fs_read_file(params).await
},
);
router.request(
FS_OPEN_METHOD,
|handler: Arc<ExecServerHandler>, params: FsOpenParams| async move {
handler.fs_open(params).await
},
);
router.request(
FS_READ_BLOCK_METHOD,
|handler: Arc<ExecServerHandler>, params: FsReadBlockParams| async move {
handler.fs_read_block(params).await
},
);
router.request(
FS_CLOSE_METHOD,
|handler: Arc<ExecServerHandler>, params: FsCloseParams| async move {
handler.fs_close(params).await
},
);
router.request(
FS_WRITE_FILE_METHOD,
|handler: Arc<ExecServerHandler>, params: FsWriteFileParams| async move {