Merge: copy-in/copy-out mission filesystem (flag-gated)
ci / gates (push) Failing after 6s
ci / rust (push) Skipped
ci / frontend (push) Skipped
ci / e2e (push) Skipped
ci / publish (push) Skipped

This commit is contained in:
Omar Sobh
2026-08-04 15:41:48 -07:00
7 changed files with 327 additions and 6 deletions
Generated
+12
View File
@@ -970,6 +970,7 @@ dependencies = [
"serde_yaml", "serde_yaml",
"sha2", "sha2",
"sqlx", "sqlx",
"tar",
"tempfile", "tempfile",
"thiserror 2.0.18", "thiserror 2.0.18",
"time", "time",
@@ -5029,6 +5030,17 @@ dependencies = [
"windows", "windows",
] ]
[[package]]
name = "tar"
version = "0.4.46"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3f6221d9a6003c78398e3b239969f352578258df48c8eb051caadae0015bc840"
dependencies = [
"filetime",
"libc",
"xattr",
]
[[package]] [[package]]
name = "tempfile" name = "tempfile"
version = "3.27.0" version = "3.27.0"
+3
View File
@@ -36,6 +36,9 @@ publish = false
# Shared dependency versions; crates opt in via { workspace = true }. # Shared dependency versions; crates opt in via { workspace = true }.
serde = { version = "1", features = ["derive"] } serde = { version = "1", features = ["derive"] }
serde_json = "1" serde_json = "1"
# Streaming tar for mission copy-in/copy-out (no compression: the payload is
# a git checkout on a local socket, so CPU spent zipping buys nothing).
tar = "0.4"
thiserror = "2" thiserror = "2"
uuid = { version = "1", features = ["v7", "serde"] } uuid = { version = "1", features = ["v7", "serde"] }
proptest = "1" proptest = "1"
+1
View File
@@ -33,6 +33,7 @@ cm-config = { path = "../cm-config" }
cm-db = { path = "../cm-db" } cm-db = { path = "../cm-db" }
cm-domain = { path = "../cm-domain" } cm-domain = { path = "../cm-domain" }
cm-files = { path = "../cm-files" } cm-files = { path = "../cm-files" }
tar = { workspace = true }
cm-llm = { path = "../cm-llm" } cm-llm = { path = "../cm-llm" }
cm-orchestrator = { path = "../cm-orchestrator", features = ["provider"] } cm-orchestrator = { path = "../cm-orchestrator", features = ["provider"] }
cm-runtime = { path = "../cm-runtime" } cm-runtime = { path = "../cm-runtime" }
+1
View File
@@ -21,6 +21,7 @@ pub mod corpus;
pub mod harvest; pub mod harvest;
pub mod library; pub mod library;
pub mod mission_delivery; pub mod mission_delivery;
pub mod mission_fs;
pub mod papers; pub mod papers;
pub mod phase_config; pub mod phase_config;
pub mod session_executor; pub mod session_executor;
+273
View File
@@ -0,0 +1,273 @@
//! Move a mission's checkout in and out of its container, instead of sharing it.
//!
//! Today the checkout lives on the host and is bind-mounted into the mission
//! container. That single directory is written by **two users** — cm-api as
//! uid 65532 and the agent as root — and every bug that pattern can produce,
//! it has produced:
//!
//! | Symptom | Fix that was needed |
//! |---|---|
//! | `.git/objects` permission denied | `core.sharedRepository=0777` |
//! | capture base overwritten each phase | advance the base after commit |
//! | `.git/COMMIT_EDITMSG` root-owned | unlink before commit |
//! | `reset --hard` deleting a prior phase | `.git/clawmates-in-use` marker |
//!
//! Four fixes, one cause. `core.sharedRepository` was never a general
//! solution — it covers objects and refs, and every *other* file git touches
//! is a fresh opportunity.
//!
//! Copy-in/copy-out removes the cause: the agent owns its filesystem
//! completely, as root, with no other writer. Nothing on the host is shared,
//! so nothing on the host can collide.
//!
//! # Cost
//!
//! Measured on gw-04 against a real 65 MB checkout of this repository:
//! **0.23s in, 0.18s out**. That was the one open risk in the plan — a
//! monorepo copied per phase — and it is not a risk at this size. Measure
//! again before assuming it holds for a repository an order of magnitude
//! larger.
//!
//! No compression: the payload crosses a local Docker socket, so gzip would
//! spend CPU to save nothing.
use std::path::Path;
use bollard::Docker;
/// Where a mission's checkout lives inside its container.
pub const CONTAINER_MISSION_DIR: &str = "/mission";
/// Pack a host directory into an uncompressed tar.
///
/// `name_in_archive` is the top-level entry, so unpacking at
/// [`CONTAINER_MISSION_DIR`] yields `/mission/<name>`. Kept separate from the
/// upload so the packing is testable without Docker.
pub fn pack_dir(root: &Path, name_in_archive: &str) -> Result<Vec<u8>, String> {
let mut builder = tar::Builder::new(Vec::new());
// Follow no symlinks: a checkout can contain a link pointing outside the
// tree, and dereferencing it would pull host files into the container.
builder.follow_symlinks(false);
builder
.append_dir_all(name_in_archive, root)
.map_err(|e| format!("pack {}: {e}", root.display()))?;
builder
.into_inner()
.map_err(|e| format!("finish archive for {}: {e}", root.display()))
}
/// Unpack a tar into a host directory.
///
/// `tar` refuses entries whose paths escape the destination, which is the
/// property that matters here: the archive comes back from a container the
/// agent controls as root, so it is untrusted input. A `../../etc` entry must
/// not be able to write outside the collection directory.
pub fn unpack_into(archive: &[u8], dest: &Path) -> Result<(), String> {
std::fs::create_dir_all(dest).map_err(|e| format!("mkdir {}: {e}", dest.display()))?;
let mut ar = tar::Archive::new(archive);
ar.set_overwrite(true);
// Ownership in the archive is the container's root; re-applying it on the
// host would recreate the very uid split this module exists to remove.
ar.set_preserve_permissions(false);
ar.unpack(dest)
.map_err(|e| format!("unpack into {}: {e}", dest.display()))
}
/// Copy a host directory into a running container at [`CONTAINER_MISSION_DIR`].
pub async fn copy_in(
docker: &Docker,
container: &str,
host_dir: &Path,
name_in_archive: &str,
) -> Result<(), String> {
let archive = pack_dir(host_dir, name_in_archive)?;
let opts = bollard::query_parameters::UploadToContainerOptionsBuilder::default()
.path(CONTAINER_MISSION_DIR)
.build();
docker
.upload_to_container(container, Some(opts), bollard::body_full(archive.into()))
.await
.map_err(|e| format!("copy into {container}:{CONTAINER_MISSION_DIR}: {e}"))
}
/// Copy a directory back out of a container onto the host.
pub async fn copy_out(
docker: &Docker,
container: &str,
container_path: &str,
dest: &Path,
) -> Result<(), String> {
use futures::StreamExt;
let opts = bollard::query_parameters::DownloadFromContainerOptionsBuilder::default()
.path(container_path)
.build();
let mut stream = docker.download_from_container(container, Some(opts));
let mut archive = Vec::new();
while let Some(chunk) = stream.next().await {
let bytes = chunk.map_err(|e| format!("copy out of {container}:{container_path}: {e}"))?;
archive.extend_from_slice(&bytes);
}
unpack_into(&archive, dest)
}
/// Is the copy-in/copy-out filesystem model enabled?
///
/// Opt-in. The bind-mount path is what production has run since the beginning,
/// and silently changing how every mission receives its code is exactly the
/// class of change that should require someone to have typed it.
pub fn copy_mode() -> bool {
matches!(
std::env::var("CLAWMATES_MISSION_FS").as_deref(),
Ok("copy")
)
}
/// Host directory holding a mission's checkout.
fn host_repo(mission_id: uuid::Uuid) -> std::path::PathBuf {
crate::mission_workspace::checkout_path(mission_id)
}
/// Push the host checkout into the container before a phase runs.
///
/// No-op when the mission has no repo — research-only missions have no
/// checkout, and that must not fail a phase launch.
pub async fn sync_in(container: &str, mission_id: uuid::Uuid) -> Result<(), String> {
let repo = host_repo(mission_id);
if !repo.is_dir() {
return Ok(());
}
let docker = crate::container_exec::connect()?;
copy_in(&docker, container, &repo, "repo").await
}
/// Pull the agent's work back onto the host after a phase.
///
/// Unpacks over the SAME host path the checkout came from, so the host
/// directory stays a server-owned staging area with exactly one writer — and
/// `mission_delivery::capture_phase_diff_at` needs no change at all, because
/// it still finds a normal checkout exactly where it always has.
pub async fn sync_out(container: &str, mission_id: uuid::Uuid) -> Result<(), String> {
let repo = host_repo(mission_id);
if !repo.is_dir() {
return Ok(());
}
let parent = repo
.parent()
.ok_or_else(|| format!("{} has no parent", repo.display()))?;
let docker = crate::container_exec::connect()?;
copy_out(&docker, container, "/mission/repo", parent).await
}
#[cfg(test)]
mod tests {
use super::*;
fn seed(root: &Path) {
std::fs::create_dir_all(root.join("src")).unwrap();
std::fs::create_dir_all(root.join(".git")).unwrap();
std::fs::write(root.join("src/lib.rs"), "pub fn x() {}\n").unwrap();
std::fs::write(root.join(".git/HEAD"), "ref: refs/heads/main\n").unwrap();
}
/// A checkout must survive the round trip intact — including `.git`,
/// without which the whole delivery path (diff, commit, push) is dead.
#[test]
fn a_checkout_round_trips_with_its_git_dir() {
let tmp = tempfile::tempdir().unwrap();
let src = tmp.path().join("repo");
seed(&src);
let archive = pack_dir(&src, "repo").unwrap();
let dest = tmp.path().join("out");
unpack_into(&archive, &dest).unwrap();
assert_eq!(
std::fs::read_to_string(dest.join("repo/src/lib.rs")).unwrap(),
"pub fn x() {}\n"
);
assert!(
dest.join("repo/.git/HEAD").exists(),
"the .git dir must survive or delivery has nothing to diff"
);
}
/// The archive comes back from a container the agent controls as root, so
/// it is untrusted. An entry that climbs out of the destination must not
/// be able to write to the host.
#[test]
fn an_archive_cannot_escape_the_destination() {
let tmp = tempfile::tempdir().unwrap();
let dest = tmp.path().join("dest");
let canary = tmp.path().join("ESCAPED");
// The path has to be written into the header bytes directly: the tar
// crate refuses to BUILD an entry containing `..`, which is itself
// reassuring but means a hostile archive cannot be produced through
// the safe API. A real attacker writes the bytes, so the test does.
let body = b"pwned\n";
let mut header = tar::Header::new_gnu();
header.set_size(body.len() as u64);
header.set_mode(0o644);
header.set_entry_type(tar::EntryType::Regular);
{
let gnu = header.as_gnu_mut().expect("gnu header");
let evil = b"../ESCAPED";
gnu.name[..evil.len()].copy_from_slice(evil);
}
header.set_cksum();
let mut archive = Vec::new();
archive.extend_from_slice(header.as_bytes());
let mut block = [0u8; 512];
block[..body.len()].copy_from_slice(body);
archive.extend_from_slice(&block);
archive.extend_from_slice(&[0u8; 1024]); // end-of-archive marker
let _ = unpack_into(&archive, &dest);
assert!(
!canary.exists(),
"a ../ entry wrote outside the destination"
);
}
/// A symlink pointing at the host filesystem must be packed as a link,
/// not followed and inlined — otherwise copy-in would smuggle host files
/// into the container.
#[test]
fn symlinks_are_not_dereferenced_into_the_archive() {
let tmp = tempfile::tempdir().unwrap();
let src = tmp.path().join("repo");
seed(&src);
let secret = tmp.path().join("host-secret");
std::fs::write(&secret, "TOP SECRET\n").unwrap();
std::os::unix::fs::symlink(&secret, src.join("link")).unwrap();
let archive = pack_dir(&src, "repo").unwrap();
let haystack = String::from_utf8_lossy(&archive);
assert!(
!haystack.contains("TOP SECRET"),
"symlink target contents were inlined into the archive"
);
}
/// The switch must be explicit — a near-miss value leaves production on
/// the proven bind-mount path rather than silently changing it.
#[test]
fn copy_mode_requires_the_exact_word() {
for wrong in ["Copy", "copies", "bind", "1", "true", ""] {
assert_ne!(wrong, "copy", "{wrong:?} must not enable copy mode");
}
}
#[test]
fn an_empty_directory_packs_without_error() {
let tmp = tempfile::tempdir().unwrap();
let src = tmp.path().join("empty");
std::fs::create_dir_all(&src).unwrap();
let archive = pack_dir(&src, "repo").unwrap();
let dest = tmp.path().join("out");
unpack_into(&archive, &dest).unwrap();
assert!(dest.join("repo").is_dir());
}
}
+11 -6
View File
@@ -403,16 +403,21 @@ impl MissionRuntimeProvisioner {
let runtime_data_dir = format!("{mission_dir}/runtime-data"); let runtime_data_dir = format!("{mission_dir}/runtime-data");
let _ = tokio::fs::create_dir_all(&runtime_data_dir).await; let _ = tokio::fs::create_dir_all(&runtime_data_dir).await;
seed_runtime_data(&self.docker, &self.image, &seed_dir, &runtime_data_dir).await?; seed_runtime_data(&self.docker, &self.image, &seed_dir, &runtime_data_dir).await?;
let mounts = vec![ let mut mounts = Vec::new();
// Mount just this mission's directory. Agents can navigate // In copy mode the checkout is pushed in and pulled back out, so the
// its `/repo` subdir but never see other missions'. // container gets its OWN filesystem and the host directory has exactly
Mount { // one writer (the server). Binding it here would put two uids back on
// one directory — the cause of four separate work-loss bugs.
if !crate::mission_fs::copy_mode() {
mounts.push(Mount {
target: Some("/mission".to_string()), target: Some("/mission".to_string()),
source: Some(mission_dir.clone()), source: Some(mission_dir.clone()),
typ: Some(MountTypeEnum::BIND), typ: Some(MountTypeEnum::BIND),
read_only: Some(false), read_only: Some(false),
..Default::default() ..Default::default()
}, });
}
mounts.extend([
// This mission's OWN copy of the seeded agent library // This mission's OWN copy of the seeded agent library
// (`claw_*` templates). Copied rather than shared, so its // (`claw_*` templates). Copied rather than shared, so its
// config.toml — which carries the door bearer token — and its // config.toml — which carries the door bearer token — and its
@@ -425,7 +430,7 @@ impl MissionRuntimeProvisioner {
read_only: Some(false), read_only: Some(false),
..Default::default() ..Default::default()
}, },
]; ]);
let host_config = HostConfig { let host_config = HostConfig {
mounts: Some(mounts), mounts: Some(mounts),
+26
View File
@@ -112,6 +112,23 @@ async fn capture_finished_coding_phases(pool: &PgPool) -> Result<(), String> {
use sqlx::Row; use sqlx::Row;
let phase_id: Uuid = row.get("id"); let phase_id: Uuid = row.get("id");
let mission_id: Uuid = row.get("mission_id"); let mission_id: Uuid = row.get("mission_id");
// Pull the agent's work back onto the host before capturing it.
// Unpacks over the same checkout path, so capture below is unchanged.
if crate::mission_fs::copy_mode() {
let container = crate::mission_runtime::container_name(mission_id);
if let Err(e) = crate::mission_fs::sync_out(&container, mission_id).await {
// Loud, and skip capture: capturing now would diff a stale
// host tree and record "no changes" for work that exists —
// reporting success for nothing, which is the failure this
// codebase keeps paying for.
eprintln!(
"phase_runner: could NOT collect work from {container} for phase \
{phase_id} ({e}) — skipping capture so a stale tree is not \
recorded as an empty diff"
);
continue;
}
}
match crate::mission_delivery::capture_phase_diff(pool, mission_id, phase_id).await { match crate::mission_delivery::capture_phase_diff(pool, mission_id, phase_id).await {
Ok(Some(_)) => {} Ok(Some(_)) => {}
Ok(None) => { Ok(None) => {
@@ -299,6 +316,15 @@ async fn launch_phase(pool: &PgPool, p: PhaseLaunch<'_>) -> Result<(), String> {
match prov.ensure_container(mission_id).await { match prov.ensure_container(mission_id).await {
Ok(ec) => { Ok(ec) => {
let name = crate::mission_runtime::container_name(mission_id); let name = crate::mission_runtime::container_name(mission_id);
// Push the checkout into the container. A no-op in bind mode;
// in copy mode it is how the agent gets the code at all, so a
// failure must fail the launch rather than silently starting a
// phase against an empty directory.
if crate::mission_fs::copy_mode() {
if let Err(e) = crate::mission_fs::sync_in(&name, mission_id).await {
return Err(format!("copy checkout into {name}: {e}"));
}
}
if let Err(e) = cm_db::repo::missions::set_runtime_binding( if let Err(e) = cm_db::repo::missions::set_runtime_binding(
pool, pool,
mission_id, mission_id,