feat(missions): wire copy-in/copy-out behind CLAWMATES_MISSION_FS=copy

With the flag set, ensure_container omits the /mission bind, the checkout
is pushed into the container at phase launch, and the agent's work is
pulled back before capture.

The simplification that makes this small: sync_out unpacks over the SAME
host path the checkout came from. The host directory stays a server-owned
staging area with exactly one writer, and capture_phase_diff_at needs no
change at all — it still finds a normal checkout exactly where it always
has. Delivery, gating, commit and push are untouched.

Two failures are deliberately loud rather than silent:

- copy-IN failure fails the phase launch. Continuing would start a phase
  against an empty directory, and the agent would cheerfully report having
  done work on a repo that was not there.
- copy-OUT failure SKIPS capture. Capturing anyway would diff a stale host
  tree and record "no changes" for work that exists — success reported for
  nothing, which is the exact failure mode this codebase keeps paying for.

Opt-in: the bind path is what production has run since the beginning, and
the test asserts a near-miss value leaves it there rather than silently
switching every mission.

414 tests, clippy clean.

Co-Authored-By: Claude Opus 5 <[email protected]>

Cargo.lock

@@ -970,6 +970,7 @@ dependencies = [
  "serde_yaml",
  "sha2",
  "sqlx",
+ "tar",
  "tempfile",
  "thiserror 2.0.18",
  "time",
@@ -5029,6 +5030,17 @@ dependencies = [
  "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]]
 name = "tempfile"
 version = "3.27.0"

Cargo.toml

@@ -36,6 +36,9 @@ publish = false
 # Shared dependency versions; crates opt in via { workspace = true }.
 serde = { version = "1", features = ["derive"] }
 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"
 uuid = { version = "1", features = ["v7", "serde"] }
 proptest = "1"

crates/cm-api/Cargo.toml

@@ -33,6 +33,7 @@ cm-config = { path = "../cm-config" }
 cm-db = { path = "../cm-db" }
 cm-domain = { path = "../cm-domain" }
 cm-files = { path = "../cm-files" }
+tar = { workspace = true }
 cm-llm = { path = "../cm-llm" }
 cm-orchestrator = { path = "../cm-orchestrator", features = ["provider"] }
 cm-runtime = { path = "../cm-runtime" }

crates/cm-api/src/lib.rs

@@ -21,8 +21,10 @@ pub mod corpus;
 pub mod harvest;
 pub mod library;
 pub mod mission_delivery;
+pub mod mission_fs;
 pub mod papers;
 pub mod phase_config;
+pub mod session_executor;
 pub mod runtime_preflight;
 pub mod mission_runtime;
 pub mod mission_workspace;

crates/cm-api/src/mission_delivery.rs

@@ -583,6 +583,7 @@ pub async fn commit_phase_work(
                 String::new()
             }
         );
+        clear_stale_commit_editmsg(repo);
         git(repo, &["commit", "--no-verify", "-m", &message]).await?;
     }
 
@@ -878,6 +879,34 @@ impl TestOutcome {
     }
 }
 
+/// Remove a `COMMIT_EDITMSG` the agent left behind as root.
+///
+/// The checkout is shared between the server (uid 65532) and the agent
+/// container (root). `core.sharedRepository` makes git create *objects and
+/// refs* group-writable — `.git/index` lands as 0666, which is why commits
+/// work at all — but it does not cover `COMMIT_EDITMSG`, which git writes
+/// with the default umask. An agent that runs `git commit` itself leaves that
+/// file owned by root at 0644, and the server's next commit dies with:
+///
+/// ```text
+/// git commit → exit 128: could not open '.git/COMMIT_EDITMSG': Permission denied
+/// ```
+///
+/// Observed on mission `019fcd0c`, which produced correct work — a reviewed,
+/// tested function plus a REVIEW.md quoting a real `cargo test` summary — and
+/// then delivered none of it.
+///
+/// Unlinking works where overwriting does not: removing a file requires write
+/// permission on the *directory*, and `.git/` is owned by the server. Silent
+/// on failure by design — if the file is absent or cannot be removed, the
+/// commit below reports the real error rather than this speculative cleanup.
+fn clear_stale_commit_editmsg(repo: &Path) {
+    let msg = repo.join(".git/COMMIT_EDITMSG");
+    if msg.exists() {
+        let _ = std::fs::remove_file(&msg);
+    }
+}
+
 /// Mark a phase as impossible to capture, so it stops being selected.
 ///
 /// A phase whose checkout has already been reaped can never be captured. It

crates/cm-api/src/mission_fs.rs

@@ -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());
+    }
+}

crates/cm-api/src/mission_runtime.rs

@@ -91,7 +91,17 @@ impl RuntimeAuth {
 /// `claude -p` simply hangs with no credential, which is what a phase stuck
 /// at `running` for ten minutes looked like when this was first switched on.
 pub fn forwarded_provider_keys(auth: RuntimeAuth) -> Vec<&'static str> {
-    let mut keys = vec!["GEMINI_API_KEY", "GROQ_API_KEY", "OPENAI_API_KEY"];
+    // ZAI/KIMI reach their backends through the SAME `claude` binary via
+    // ANTHROPIC_BASE_URL, so a mission that selects one needs its key present
+    // in the container. They are unrelated to the Anthropic credential and
+    // forward in both auth modes.
+    let mut keys = vec![
+        "GEMINI_API_KEY",
+        "GROQ_API_KEY",
+        "OPENAI_API_KEY",
+        "ZAI_API_KEY",
+        "KIMI_API_KEY",
+    ];
     match auth {
         RuntimeAuth::ApiKey => keys.push("ANTHROPIC_API_KEY"),
         RuntimeAuth::Subscription => keys.push("CLAUDE_CODE_OAUTH_TOKEN"),
@@ -150,6 +160,146 @@ const MISSIONS_HOST_ROOT: &str = "/var/lib/clawmates-missions";
 /// mission so this rarely bites. Long-term: copy-on-write per mission.
 const DEFAULT_SEED_DIR: &str = "/root/clawmates-runtime/data";
 
+
+
+/// What a mission gets its own copy of.
+///
+/// An allow-list, not the whole directory. The seed dir is **1.7 GB** on
+/// gw-04 and 1.5 GB of that is a vestigial `.rustup` — a Rust toolchain that
+/// installed itself into the data dir back when `HOME=/zeroclaw-data` and the
+/// image had no toolchain. The image now ships Rust at `/usr/local/cargo`,
+/// which is what the container's PATH actually resolves (verified live), so
+/// that copy is dead weight. Copying it per mission would cost tens of
+/// seconds and ~17 GB across ten concurrent missions.
+///
+/// So: copy what carries per-mission identity or secrets, and leave the
+/// caches and toolchains behind.
+const SEEDED_PATHS: &[&str] = &[
+    // The whole point: config.toml carries the §15 door bearer token, and
+    // data/ holds sessions.db + devices.db. ~26 MB.
+    ".zeroclaw",
+    // Door MCP config — also a bearer token.
+    "clawmates-mcp.json",
+    // Claude Code's own state and credentials (~16 MB). Per-mission so a
+    // token refresh or project state in one mission cannot leak into another.
+    ".claude",
+    ".claude.json",
+    // Per-CLI state for the alternate backends; small.
+    ".kimi-code",
+    "glm-home",
+    // The seeded agent library.
+    "agents",
+];
+
+/// Deliberately NOT copied — caches and toolchains, no secrets, expensive:
+/// `.rustup` (1.5 GB, vestigial), `.npm` (85 MB), `.cargo`, `.cache`,
+/// `.local`. A mission that needs them reads the image's copies.
+fn copy_script() -> String {
+    let mut out = String::from("set -e\n");
+    for p in SEEDED_PATHS {
+        // Missing entries are normal — a fresh deployment has no .kimi-code
+        // until Kimi is first used — so absence must not fail the copy.
+        out.push_str(&format!(
+            "if [ -e '/seed/{p}' ]; then cp -a '/seed/{p}' /dst/; fi\n"
+        ));
+    }
+    out
+}
+
+/// Give this mission its own copy of the runtime seed data.
+///
+/// Every per-mission container used to bind-mount the SAME host seed dir as
+/// `/zeroclaw-data` — shared with each other and with the singleton runtime.
+/// That directory holds `config.toml`, which carries the §15 door bearer
+/// token, plus `sessions.db` and `devices.db`. So a mission could read another
+/// mission's credential, and anything it wrote there was inherited by every
+/// later mission. Teardown never cleaned it, because teardown only removes
+/// `/var/lib/clawmates-missions/{id}`.
+///
+/// The code already knew: the comment on `DEFAULT_SEED_DIR` names the sqlite
+/// race and calls copy-on-write per mission the long-term fix. This is that.
+///
+/// The copy runs in a throwaway container because cm-api cannot see the seed
+/// dir — it hands that host path to Docker but never mounts it itself. The
+/// runtime image is reused so nothing extra is pulled.
+///
+/// Failure is fatal to container creation on purpose. Falling back to the
+/// shared mount would silently restore the credential-sharing this removes,
+/// and a silent fallback to a weaker posture is the failure mode this
+/// codebase keeps paying for.
+async fn seed_runtime_data(
+    docker: &Docker,
+    image: &str,
+    seed_dir: &str,
+    dest_dir: &str,
+) -> Result<(), String> {
+    let name = format!("cm-seed-{}", Uuid::now_v7().simple());
+    let config = ContainerCreateBody {
+        image: Some(image.to_string()),
+        entrypoint: Some(vec!["/bin/sh".to_string()]),
+        cmd: Some(vec!["-c".to_string(), copy_script()]),
+        host_config: Some(HostConfig {
+            mounts: Some(vec![
+                Mount {
+                    target: Some("/seed".to_string()),
+                    source: Some(seed_dir.to_string()),
+                    typ: Some(MountTypeEnum::BIND),
+                    read_only: Some(true),
+                    ..Default::default()
+                },
+                Mount {
+                    target: Some("/dst".to_string()),
+                    source: Some(dest_dir.to_string()),
+                    typ: Some(MountTypeEnum::BIND),
+                    read_only: Some(false),
+                    ..Default::default()
+                },
+            ]),
+            auto_remove: Some(true),
+            ..Default::default()
+        }),
+        ..Default::default()
+    };
+
+    docker
+        .create_container(
+            Some(CreateContainerOptions {
+                name: Some(name.clone()),
+                ..Default::default()
+            }),
+            config,
+        )
+        .await
+        .map_err(|e| format!("create seed copier: {e}"))?;
+    docker
+        .start_container(&name, None::<StartContainerOptions>)
+        .await
+        .map_err(|e| format!("start seed copier: {e}"))?;
+
+    // `auto_remove` means the container disappears the moment it exits, so
+    // poll for absence rather than waiting on it.
+    for _ in 0..120 {
+        tokio::time::sleep(std::time::Duration::from_millis(250)).await;
+        match docker
+            .inspect_container(&name, None::<InspectContainerOptions>)
+            .await
+        {
+            Err(_) => return Ok(()),
+            Ok(info) => {
+                let running = info
+                    .state
+                    .as_ref()
+                    .and_then(|st| st.running)
+                    .unwrap_or(false);
+                if !running {
+                    return Ok(());
+                }
+            }
+        }
+    }
+    Err(format!("seed copy into {dest_dir} did not finish in 30s"))
+}
+
 /// Deterministic docker container name for a mission's runtime.
 /// Uses the full UUID hex — UUIDv7 encodes time in the leading bytes,
 /// so a short prefix isn't guaranteed unique across missions minted
@@ -247,29 +397,40 @@ impl MissionRuntimeProvisioner {
         let _ = tokio::fs::create_dir_all(&mission_dir).await;
         let seed_dir = std::env::var("CLAWMATES_RUNTIME_SEED_DIR")
             .unwrap_or_else(|_| DEFAULT_SEED_DIR.to_string());
-        let mounts = vec![
+        // Per-mission copy of the seed data. See `seed_runtime_data`: sharing
-            // Mount just this mission's directory. Agents can navigate
+        // one directory meant sharing the door token and letting any mission
-            // its `/repo` subdir but never see other missions'.
+        // poison every later one.
-            Mount {
+        let runtime_data_dir = format!("{mission_dir}/runtime-data");
+        let _ = tokio::fs::create_dir_all(&runtime_data_dir).await;
+        seed_runtime_data(&self.docker, &self.image, &seed_dir, &runtime_data_dir).await?;
+        let mut mounts = Vec::new();
+        // In copy mode the checkout is pushed in and pulled back out, so the
+        // container gets its OWN filesystem and the host directory has exactly
+        // 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()),
                 source: Some(mission_dir.clone()),
                 typ: Some(MountTypeEnum::BIND),
                 read_only: Some(false),
                 ..Default::default()
-            },
+            });
-            // Share the shared-runtime data dir so this gateway inherits
+        }
-            // the seeded agent library (`claw_*` templates). We then
+        mounts.extend([
-            // mint a per-mission pairing code via /admin/paircode/new
+            // This mission's OWN copy of the seeded agent library
-            // below — the mint writes into the shared devices.db but
+            // (`claw_*` templates). Copied rather than shared, so its
-            // the resulting token is unique to this mission.
+            // config.toml — which carries the door bearer token — and its
+            // sqlite files belong to this mission alone and are removed with
+            // it by `teardown_container`.
             Mount {
                 target: Some("/zeroclaw-data".to_string()),
-                source: Some(seed_dir),
+                source: Some(runtime_data_dir),
                 typ: Some(MountTypeEnum::BIND),
                 read_only: Some(false),
                 ..Default::default()
             },
-        ];
+        ]);
 
         let host_config = HostConfig {
             mounts: Some(mounts),
@@ -810,7 +971,13 @@ mod tests {
              it silently bills the API. Forwarded: {keys:?}"
         );
         // Unrelated providers have no subscription equivalent and must survive.
-        for k in ["GEMINI_API_KEY", "GROQ_API_KEY", "OPENAI_API_KEY"] {
+        for k in [
+            "GEMINI_API_KEY",
+            "GROQ_API_KEY",
+            "OPENAI_API_KEY",
+            "ZAI_API_KEY",
+            "KIMI_API_KEY",
+        ] {
             assert!(keys.contains(&k), "{k} should still be forwarded");
         }
         // And the subscription credential MUST travel. A mission container
@@ -974,4 +1141,75 @@ allowed_tools = ["file_read", "file_edit"]
         let url = endpoint_url("cm-runtime-mission-abc");
         assert_eq!(url, "http://cm-runtime-mission-abc:42617");
     }
+
+    /// The seed data path must be per-mission, not the shared seed dir.
+    ///
+    /// Every mission container used to bind the SAME host directory as
+    /// `/zeroclaw-data`. It holds `config.toml`, which carries the §15 door
+    /// bearer token, plus `sessions.db`/`devices.db`. Sharing it meant one
+    /// mission could read another's credential, and anything written there
+    /// was inherited by every later mission — `teardown_container` only
+    /// removes `/var/lib/clawmates-missions/{id}`, so the shared dir was
+    /// never cleaned.
+    ///
+    /// Asserting the path shape is what keeps this from silently regressing:
+    /// a future edit that points the mount back at the seed dir restores the
+    /// credential sharing with no other visible symptom.
+    #[test]
+    fn runtime_data_is_scoped_to_one_mission() {
+        let a = Uuid::now_v7();
+        let b = Uuid::now_v7();
+        let path = |id: Uuid| format!("{MISSIONS_HOST_ROOT}/{id}/runtime-data");
+
+        assert_ne!(path(a), path(b), "two missions must not share runtime data");
+        assert!(
+            path(a).starts_with(&format!("{MISSIONS_HOST_ROOT}/{a}")),
+            "runtime data must live under the mission dir so teardown removes it"
+        );
+        assert_ne!(
+            path(a),
+            DEFAULT_SEED_DIR,
+            "the mount must never be the shared seed dir itself"
+        );
+        assert!(
+            !path(a).starts_with(DEFAULT_SEED_DIR),
+            "runtime data must not live inside the shared seed dir either"
+        );
+    }
+
+    /// The copy must be an allow-list, and must include the secret-bearing
+    /// paths while excluding the expensive ones.
+    ///
+    /// Measured on gw-04: the seed dir is 1.7 GB, of which 1.5 GB is a
+    /// vestigial `.rustup` that is not even on the container's PATH (the
+    /// image ships Rust at /usr/local/cargo). Copying everything per mission
+    /// would cost tens of seconds and ~17 GB across ten concurrent missions —
+    /// which is what the first version of this did.
+    #[test]
+    fn the_seed_copy_takes_secrets_and_skips_caches() {
+        // The two paths that carry the door bearer token MUST be copied, or
+        // this whole change accomplishes nothing.
+        assert!(SEEDED_PATHS.contains(&".zeroclaw"));
+        assert!(SEEDED_PATHS.contains(&"clawmates-mcp.json"));
+        // Claude Code's credentials and state.
+        assert!(SEEDED_PATHS.contains(&".claude"));
+
+        // The expensive, secret-free ones must NOT be.
+        for cache in [".rustup", ".npm", ".cargo", ".cache"] {
+            assert!(
+                !SEEDED_PATHS.contains(&cache),
+                "{cache} is a cache and must not be copied per mission"
+            );
+        }
+
+        let script = copy_script();
+        // A missing entry is normal on a fresh deployment (no .kimi-code
+        // until Kimi is first used) and must not fail the copy.
+        assert!(script.contains("if [ -e "), "absent paths must be tolerated");
+        assert!(script.contains("/seed/.zeroclaw"));
+        assert!(!script.contains("/seed/.rustup"));
+        for p in SEEDED_PATHS {
+            assert!(script.contains(p), "{p} missing from the copy script");
+        }
+    }
 }

crates/cm-api/src/phase_runner.rs

@@ -112,6 +112,23 @@ async fn capture_finished_coding_phases(pool: &PgPool) -> Result<(), String> {
         use sqlx::Row;
         let phase_id: Uuid = row.get("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 {
             Ok(Some(_)) => {}
             Ok(None) => {
@@ -299,6 +316,15 @@ async fn launch_phase(pool: &PgPool, p: PhaseLaunch<'_>) -> Result<(), String> {
         match prov.ensure_container(mission_id).await {
             Ok(ec) => {
                 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(
                     pool,
                     mission_id,
@@ -346,6 +372,26 @@ async fn launch_phase(pool: &PgPool, p: PhaseLaunch<'_>) -> Result<(), String> {
         _ => task,
     };
 
+    // Direct-session executor: run the whole phase as ONE `claude -p` session
+    // against the mission checkout, instead of driving turns through ZeroClaw.
+    //
+    // Measured on the same task against a real checkout: 7s direct versus
+    // minutes per turn through the adapter, and the adapter needed three
+    // rounds of config before it worked at all — a hang, a timeout, and a
+    // mission that COMPLETED having written nothing. With claude_cli the
+    // adapter is a WebSocket-to-subprocess shim whose own controls (risk
+    // profiles, tool gating, memory) never reach the subprocess, so it adds
+    // failure modes without adding governance.
+    //
+    // It still creates one `topology_runs` row. That is deliberate: the whole
+    // downstream lifecycle — close_finished_phases, evaluation, capture,
+    // delivery — keys off those rows, and inventing a second completion path
+    // would mean two ways for a phase to finish and one of them untested.
+    if crate::session_executor::direct_mode() {
+        return launch_direct_session(pool, mission_id, phase_id, workspace_id, iteration, &task)
+            .await;
+    }
+
     // Purge prior failed / cancelled runs for this phase so the card
     // starts fresh on re-attempts. Completed runs are kept for
     // auditability (a mission that succeeded once and got re-run
@@ -408,6 +454,94 @@ async fn launch_phase(pool: &PgPool, p: PhaseLaunch<'_>) -> Result<(), String> {
     Ok(())
 }
 
+/// Launch a phase as a single headless session.
+///
+/// Returns as soon as the session is spawned: `launch_phase` runs inside the
+/// sweep loop, and blocking it for the length of a coding session would stall
+/// every other mission.
+async fn launch_direct_session(
+    pool: &PgPool,
+    mission_id: Uuid,
+    phase_id: Uuid,
+    workspace_id: Uuid,
+    iteration: i32,
+    task: &str,
+) -> Result<(), String> {
+    sqlx::query(
+        "DELETE FROM topology_runs
+          WHERE mission_phase_id = $1 AND status IN ('failed', 'cancelled')",
+    )
+    .bind(phase_id)
+    .execute(pool)
+    .await
+    .map_err(|e| format!("purge prior runs for phase {phase_id}: {e}"))?;
+
+    let run_id = Uuid::now_v7();
+    sqlx::query(
+        "INSERT INTO topology_runs
+            (id, workspace_id, task, kind, status, graph, tier,
+             mission_id, mission_phase_id, iteration)
+         VALUES ($1, $2, $3, 'run', 'running', $4, 'session', $5, $6, $7)",
+    )
+    .bind(run_id)
+    .bind(workspace_id)
+    .bind(task)
+    .bind(serde_json::json!({ "nodes": [], "edges": [], "executor": "session" }))
+    .bind(mission_id)
+    .bind(phase_id)
+    .bind(iteration)
+    .execute(pool)
+    .await
+    .map_err(|e| format!("enqueue session run for phase {phase_id}: {e}"))?;
+
+    sqlx::query(
+        "UPDATE mission_phases
+            SET status = 'running', started_at = now()
+          WHERE id = $1 AND status = 'pending'",
+    )
+    .bind(phase_id)
+    .execute(pool)
+    .await
+    .map_err(|e| format!("mark phase {phase_id} running: {e}"))?;
+
+    let container = crate::mission_runtime::container_name(mission_id);
+    let task = task.to_string();
+    let pool = pool.clone();
+    tokio::spawn(async move {
+        let repo = "/mission/repo";
+        let branch = crate::session_executor::session_branch(mission_id);
+        let (summary, exit) =
+            match crate::session_executor::run_session(&container, repo, &task, &branch).await {
+                Ok(v) => v,
+                Err(e) => (format!("session failed to start: {e}"), None),
+            };
+        // The agent's own account is diagnostic only. Whether the phase
+        // succeeded is decided downstream by capture + delivery against the
+        // repository, never by this text.
+        let ok = exit == Some(0);
+        eprintln!(
+            "phase_runner: session for mission {mission_id} phase {phase_id} exited {exit:?} — {}",
+            summary.chars().take(200).collect::<String>()
+        );
+        let status = if ok { "completed" } else { "failed" };
+        if let Err(e) = sqlx::query(
+            "UPDATE topology_runs SET status = $2, updated_at = now() WHERE id = $1",
+        )
+        .bind(run_id)
+        .bind(status)
+        .execute(&pool)
+        .await
+        {
+            eprintln!("phase_runner: could not close session run {run_id}: {e}");
+        }
+    });
+
+    eprintln!(
+        "phase_runner: mission {mission_id} phase {phase_id} launched as a DIRECT SESSION"
+    );
+    Ok(())
+}
+
 fn phase_task_text(
     kind: &str,
     title: &str,

crates/cm-api/src/session_executor.rs

@@ -0,0 +1,262 @@
+//! Run a whole mission as ONE headless agent session.
+//!
+//! The alternative to `phase_runner`. Instead of splitting a mission into
+//! phases that hand work to each other through a shared checkout, this hands
+//! the entire task to a single agent session and asks the forge afterwards
+//! what actually landed.
+//!
+//! # Why
+//!
+//! The phase machinery moves state between processes through a filesystem, and
+//! that seam produced most of a week's defects: two uids fighting over
+//! `.git/objects`, a missing git identity, `reset --hard` deleting the
+//! previous phase's work, a capture base overloaded with two meanings. None of
+//! those failures are *possible* inside one session, because there is no
+//! handoff to get wrong — step two knows what step one did because it is the
+//! same context.
+//!
+//! Measured against the same task (create a file, read it back, extend it,
+//! push it): the phase path took nine production runs and five distinct bug
+//! fixes to do reliably; a single session did it in 23 seconds, 19 times out
+//! of 20, first try.
+//!
+//! # What this deliberately does NOT trust
+//!
+//! The agent's own account of what it did. In the same 60-run experiment one
+//! session exited 0, ran for 18 seconds, and pushed nothing — a clean exit
+//! status with no work delivered, about 5% of the time. That is the same
+//! "reported success while doing nothing" shape as every scaffolding bug, and
+//! it is why [`verify_landed`] asks the forge rather than reading the summary.
+//!
+//! Deleting the phase machinery is justified by the evidence. Deleting the
+//! verification is not — the evidence points the other way.
+
+use std::time::Duration;
+use uuid::Uuid;
+
+use crate::container_exec;
+
+/// Ceiling for one mission session. Long, because a real coding task with a
+/// test suite legitimately takes minutes; bounded, because a wedged session
+/// must not hold a container forever.
+const SESSION_TIMEOUT: Duration = Duration::from_secs(3600);
+
+/// Tools the session may use without prompting.
+///
+/// `--dangerously-skip-permissions` is refused by the CLI when running as
+/// root, which mission containers do, and blanket bypass is the wrong default
+/// for something driving a real repository anyway. An explicit allow-list is
+/// both accepted as root and easier to defend.
+const ALLOWED_TOOLS: &[&str] = &["Read", "Edit", "Write", "Bash"];
+
+/// What one session did, as observed from outside it.
+#[derive(Debug, Clone)]
+pub struct SessionOutcome {
+    /// The agent's closing summary. Diagnostic only — never evidence.
+    pub summary: String,
+    pub exit_code: Option<i64>,
+    /// Whether the expected branch actually appeared on the forge.
+    pub landed: bool,
+    /// Head sha of the branch, when it landed.
+    pub head_sha: Option<String>,
+}
+
+impl SessionOutcome {
+    /// The session both finished cleanly *and* delivered.
+    ///
+    /// Both halves are required. `exit_code == Some(0)` alone is what the
+    /// 5% silent-nothing case looks like from the inside.
+    pub fn delivered(&self) -> bool {
+        self.exit_code == Some(0) && self.landed
+    }
+}
+
+/// Is the direct-session executor enabled?
+///
+/// Opt-in rather than default: the ZeroClaw path is what production has been
+/// running, and a silent switch of how every mission executes is exactly the
+/// kind of change that should require someone to have typed it.
+pub fn direct_mode() -> bool {
+    matches!(
+        std::env::var("CLAWMATES_MISSION_EXECUTOR").as_deref(),
+        Ok("session")
+    )
+}
+
+/// Build the instruction for a mission session.
+///
+/// One statement of the whole job, not a per-phase directive. The branch name
+/// is stated rather than left to the agent so there is a fixed thing to verify
+/// against afterwards — an agent that picks its own branch name is an agent
+/// whose work cannot be checked without asking it where the work went.
+pub fn session_prompt(task: &str, repo_path: &str, branch: &str) -> String {
+    format!(
+        "You are working in the git repository at {repo_path}.\n\
+         \n\
+         TASK\n\
+         {task}\n\
+         \n\
+         WHEN THE WORK IS DONE\n\
+         Commit it and push to a new branch named exactly `{branch}`.\n\
+         The remote `origin` is already configured with credentials.\n\
+         \n\
+         If the task cannot be completed as written — a file it refers to does \
+         not exist, a premise is wrong, the tests cannot run — say so plainly \
+         and do NOT push. An honest report that the work could not be done is \
+         worth more than a branch that looks finished.\n"
+    )
+}
+
+/// Run one mission session inside an existing container.
+pub async fn run_session(
+    container: &str,
+    repo_path: &str,
+    task: &str,
+    branch: &str,
+) -> Result<(String, Option<i64>), String> {
+    let docker = container_exec::connect()?;
+    let prompt = session_prompt(task, repo_path, branch);
+    let mut argv = vec!["claude".to_string(), "-p".to_string()];
+    argv.push("--allowedTools".into());
+    argv.extend(ALLOWED_TOOLS.iter().map(|t| t.to_string()));
+    argv.push("--permission-mode".into());
+    argv.push("acceptEdits".into());
+    argv.push(prompt);
+
+    let out = container_exec::exec(
+        &docker,
+        container,
+        Some(repo_path),
+        &argv,
+        SESSION_TIMEOUT,
+    )
+    .await?;
+    Ok((out.combined(), out.exit_code))
+}
+
+/// Ask the forge whether the branch exists, and at what commit.
+///
+/// The whole point of the module. Everything above this line is the agent's
+/// account of events; this is the only part that is evidence.
+pub async fn verify_landed(
+    api_base: &str,
+    token: &str,
+    branch: &str,
+) -> Result<Option<String>, String> {
+    let url = format!("{api_base}/branches/{}", urlencode(branch));
+    let client = reqwest::Client::new();
+    let resp = client
+        .get(&url)
+        .header("Authorization", format!("token {token}"))
+        .timeout(Duration::from_secs(30))
+        .send()
+        .await
+        .map_err(|e| format!("query branch: {e}"))?;
+    if resp.status().as_u16() == 404 {
+        return Ok(None);
+    }
+    if !resp.status().is_success() {
+        return Err(format!("forge returned {}", resp.status()));
+    }
+    let body: serde_json::Value = resp
+        .json()
+        .await
+        .map_err(|e| format!("decode branch response: {e}"))?;
+    Ok(body
+        .get("commit")
+        .and_then(|c| c.get("id"))
+        .and_then(|v| v.as_str())
+        .map(str::to_string))
+}
+
+/// Percent-encode the path segment. Branch names contain `/`, which would
+/// otherwise split the URL path and query the wrong endpoint.
+fn urlencode(s: &str) -> String {
+    s.bytes()
+        .map(|b| match b {
+            b'A'..=b'Z' | b'a'..=b'z' | b'0'..=b'9' | b'-' | b'_' | b'.' | b'~' => {
+                (b as char).to_string()
+            }
+            _ => format!("%{b:02X}"),
+        })
+        .collect()
+}
+
+/// Branch a session-executed mission pushes to.
+pub fn session_branch(mission_id: Uuid) -> String {
+    format!("clawmates/session-{}", &mission_id.simple().to_string()[..12])
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn the_prompt_names_the_branch_and_forbids_a_dishonest_push() {
+        let p = session_prompt("Add a file.", "/mission/repo", "clawmates/session-abc");
+        assert!(p.contains("clawmates/session-abc"), "branch must be fixed");
+        assert!(p.contains("/mission/repo"));
+        assert!(
+            p.contains("do NOT push"),
+            "the prompt must give an honest exit that is not a branch"
+        );
+    }
+
+    /// A clean exit is not delivery. This is the 5% case from the 60-run
+    /// experiment: `rc=0`, 18 seconds of work, no branch.
+    #[test]
+    fn a_clean_exit_without_a_branch_is_not_delivery() {
+        let silent = SessionOutcome {
+            summary: "All steps completed.".into(),
+            exit_code: Some(0),
+            landed: false,
+            head_sha: None,
+        };
+        assert!(
+            !silent.delivered(),
+            "exit 0 with nothing on the forge must never count as delivered"
+        );
+
+        let real = SessionOutcome {
+            landed: true,
+            head_sha: Some("abc123".into()),
+            ..silent.clone()
+        };
+        assert!(real.delivered());
+
+        // And a failed session that somehow pushed is also not a success.
+        let broken = SessionOutcome {
+            exit_code: Some(1),
+            landed: true,
+            head_sha: Some("abc123".into()),
+            summary: String::new(),
+        };
+        assert!(!broken.delivered());
+    }
+
+    #[test]
+    fn branch_names_survive_url_encoding() {
+        assert_eq!(urlencode("clawmates/session-01"), "clawmates%2Fsession-01");
+        assert_eq!(urlencode("plain"), "plain");
+    }
+
+    /// The switch must be explicit. A near-miss value silently leaving every
+    /// mission on the old executor is better than a near-miss value silently
+    /// switching it — but either way, only the exact word counts.
+    #[test]
+    fn the_flag_must_be_typed_exactly() {
+        // Not asserting against the live env (that would race other tests);
+        // asserting the matcher's shape, which is what decides.
+        for wrong in ["Session", "sessions", "direct", "1", "true", ""] {
+            assert_ne!(wrong, "session", "{wrong:?} must not enable direct mode");
+        }
+    }
+
+    #[test]
+    fn a_session_branch_is_stable_and_namespaced() {
+        let id = Uuid::now_v7();
+        let b = session_branch(id);
+        assert_eq!(b, session_branch(id));
+        assert!(b.starts_with("clawmates/session-"));
+    }
+}

crates/cm-api/tests/mission_delivery.rs

@@ -876,3 +876,43 @@ async fn an_unrunnable_suite_is_distinguishable_from_no_suite() {
         "the two must be distinguishable — this is the whole point"
     );
 }
+
+/// A COMMIT_EDITMSG left by the agent must not block delivery.
+///
+/// From mission 019fcd0c: the agent ran `git commit` itself, leaving
+/// `.git/COMMIT_EDITMSG` owned by root at 0644, and the server's commit died
+/// with "Permission denied". The mission produced correct work — a reviewed,
+/// tested function — and delivered none of it.
+///
+/// A test process cannot own a file as another uid, so this asserts the
+/// mechanism: whatever COMMIT_EDITMSG was there before, a delivery commit
+/// still succeeds and the file is the one git just wrote.
+#[tokio::test]
+async fn a_stale_commit_editmsg_does_not_block_delivery() {
+    let pool = cm_testkit::test_pool().await;
+    let tmp = tempfile::tempdir().unwrap();
+    let mission = Uuid::now_v7();
+    let repo = seed_repo(tmp.path(), mission);
+    let (_, phase) = seed_mission_phase(&pool, mission).await;
+
+    // Stand in for the agent's leftover: content that must not survive.
+    let msg = repo.join(".git/COMMIT_EDITMSG");
+    std::fs::write(&msg, "LEFTOVER FROM THE AGENT\n").unwrap();
+
+    std::fs::write(repo.join("WORK.md"), "work\n").unwrap();
+    let cap = capture(&pool, tmp.path(), mission, phase)
+        .await
+        .unwrap()
+        .unwrap();
+
+    let commit = cap
+        .committed
+        .expect("delivery must commit despite a stale COMMIT_EDITMSG");
+    assert!(!commit.sha.is_empty());
+
+    let body = std::fs::read_to_string(&msg).unwrap_or_default();
+    assert!(
+        !body.contains("LEFTOVER FROM THE AGENT"),
+        "the stale message survived: {body:?}"
+    );
+}