Merge: per-mission runtime data (stop sharing the door token)

crates/cm-api/src/mission_runtime.rs

@@ -160,6 +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
@@ -257,6 +397,12 @@ 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());
+        // Per-mission copy of the seed data. See `seed_runtime_data`: sharing
+        // one directory meant sharing the door token and letting any mission
+        // poison every later one.
+        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 mounts = vec![
             // Mount just this mission's directory. Agents can navigate
             // its `/repo` subdir but never see other missions'.
@@ -267,14 +413,14 @@ impl MissionRuntimeProvisioner {
                 read_only: Some(false),
                 ..Default::default()
             },
-            // Share the shared-runtime data dir so this gateway inherits
+            // This mission's OWN copy of the seeded agent library
-            // the seeded agent library (`claw_*` templates). We then
+            // (`claw_*` templates). Copied rather than shared, so its
-            // mint a per-mission pairing code via /admin/paircode/new
+            // config.toml — which carries the door bearer token — and its
-            // below — the mint writes into the shared devices.db but
+            // sqlite files belong to this mission alone and are removed with
-            // the resulting token is unique to this mission.
+            // 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()
@@ -990,4 +1136,75 @@ 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");
+        }
+    }
 }