Merge pull request #1645 from DeusData/fix/product-runtime-dir-override

fix(daemon): let a shipped build relocate the rendezvous via CBM_RUNTIME_DIR

docs/CONFIGURATION.md

@@ -121,8 +121,46 @@ These environment variables affect runtime behavior:
 | `CBM_DIAGNOSTICS` | `false` | Enable periodic `snapshot.json` and retained `trajectory.ndjson` below a fresh owner-private directory in the system temp directory. The daemon records the randomized paths in the `diagnostics.start` discovery record (a single JSON line) in `${CBM_CACHE_DIR}/logs/cbm-daemon.log`; that one record is emitted even when `CBM_LOG_LEVEL` suppresses ordinary logging, so the paths always remain discoverable. |
 | `CBM_DOWNLOAD_URL` | GitHub releases | Override the update download URL. |
 | `CBM_LOG_LEVEL` | `info` | Set the log level to `debug`, `info`, `warn`, `error`, or `none` (or `0`-`4`). Thin-frontend messages use that session's stderr; detached daemon events use `${CBM_CACHE_DIR}/logs/cbm-daemon.log`. |
+| `CBM_RUNTIME_DIR` | `%LOCALAPPDATA%` (Windows), `/private/tmp` (macOS), `/tmp` (other) | Parent directory for the daemon/CLI rendezvous directory, which CBM creates inside it as `cbm-daemon-<uid>` (`cbm-daemon-<key>` on Windows). Set it when the default ancestry cannot pass the private-directory check — see below. `CBM_CACHE_DIR` does **not** move the rendezvous. |
 | `CBM_WORKERS` | auto-detected | Override the indexing worker count. |
 
+### Relocating the daemon rendezvous directory
+
+Before it is used, the rendezvous directory and every ancestor of it are checked:
+each ancestor must be owned by you or by root, must not be world-writable (unless
+it is the standard root-owned sticky directory such as `/tmp`), and must carry no
+allow-ACL — on Windows, no ACE granting mutation rights to another identity. The
+rendezvous directory itself is then forced to owner-only (`0700`, no extended ACL
+/ an owner-only DACL).
+
+That ancestry is not always acceptable in the default location. A Windows profile
+that has acquired a capability-SID ACE with `WRITE_DAC` / `WRITE_OWNER` / `DELETE`
+on `%LOCALAPPDATA%` — something an installed packaged app can add — fails the walk,
+and so can an unusual `/tmp` or home directory on POSIX. When that happens *every*
+command fails, `config list` included, so the settings surface cannot be reached
+either:
+
+```text
+codebase-memory-mcp: secure daemon endpoint could not be created
+```
+
+`CBM_RUNTIME_DIR` points the rendezvous at an ancestry you choose:
+
+```bash
+export CBM_RUNTIME_DIR="$HOME/cbm-runtime"   # any directory you own
+```
+
+```powershell
+$env:CBM_RUNTIME_DIR = "D:\cbm-runtime"
+```
+
+The check is not relaxed for the directory you name: it goes through exactly the
+same validation as the default, and a value that fails it is refused rather than
+silently ignored. Because the rendezvous is how sessions find each other, every
+process that should share one daemon must see the same value — set it in the
+environment of your MCP client and your shell alike, or a CLI invocation without
+it will coordinate through the default location instead.
+
 Environment used by daemon-owned components—such as diagnostics, daemon logging, and process-wide indexing resource limits—is captured from the first daemon-backed session that starts the daemon. Later sessions join the existing process and cannot replace those values. To change them, close every daemon-backed session, update the relevant agent configurations consistently, and restart a session. `CBM_ALLOWED_ROOT` remains session-specific, a conflicting `CBM_CACHE_DIR` is rejected, and one-shot CLI commands use their own current environment without starting the daemon.
 
 

src/daemon/bootstrap.c

@@ -208,12 +208,43 @@ bool cbm_daemon_process_role_requires_client(cbm_daemon_process_role_t role) {
     return role == CBM_DAEMON_PROCESS_MCP_CLIENT || role == CBM_DAEMON_PROCESS_HOOK_CLIENT;
 }
 
+/* #1574/#1621: the rendezvous directory is created under %LOCALAPPDATA%
+ * (Windows) or /tmp — /private/tmp on macOS — and that ancestry is not always
+ * acceptable to the private-directory walk. A profile that carries a
+ * mutation-granting ACE for an untrusted identity (an AppContainer capability
+ * SID, for instance) fails it, and the binary then cannot start at all: every
+ * command needs this endpoint, `config list` included, so the operator cannot
+ * even reconfigure their way out. The only relocation hook was
+ * CBM_TEST_DAEMON_RUNTIME_PARENT, compiled out unless CBM_ENABLE_TEST_SEAMS is
+ * defined, so a test build started while the shipped build did not. CBM_CACHE_DIR
+ * does not help either — it moves the cache, never the rendezvous.
+ *
+ * CBM_RUNTIME_DIR does NOT relax the check. The directory it names goes through
+ * exactly the same validation as the default; the operator only chooses an
+ * ancestry that passes, and a value that fails is refused rather than ignored.
+ * cbm_safe_getenv never truncates: a value too long for the buffer is reported
+ * as absent, so no half a path can ever become a runtime parent. */
+static const char *bootstrap_runtime_parent_override(char *buffer, size_t capacity) {
+    const char *value = cbm_safe_getenv("CBM_RUNTIME_DIR", buffer, capacity, NULL);
+    return value && value[0] != '\0' ? value : NULL;
+}
+
 cbm_daemon_ipc_endpoint_t *cbm_daemon_bootstrap_endpoint_new(const char *runtime_parent) {
     char key[CBM_DAEMON_KEY_SIZE];
     if (!cbm_daemon_rendezvous_key(key)) {
         return NULL;
     }
-    return cbm_daemon_ipc_endpoint_new(key, runtime_parent);
+    /* An explicit parent keeps precedence: it carries the compile-time test
+     * seam and the lifecycle guards' isolated namespace. The override is
+     * resolved HERE, the one function every product endpoint goes through
+     * (daemon, MCP client, local CLI, index worker, activation), so no call
+     * site can silently keep the default. */
+    char override_parent[BOOTSTRAP_PATH_CAP];
+    const char *parent =
+        runtime_parent
+            ? runtime_parent
+            : bootstrap_runtime_parent_override(override_parent, sizeof(override_parent));
+    return cbm_daemon_ipc_endpoint_new(key, parent);
 }
 
 bool cbm_daemon_bootstrap_launch_spec_init(const char *executable_path,

tests/test_daemon_bootstrap.c

@@ -89,6 +89,15 @@ static bool bootstrap_endpoint_fixture_start(bootstrap_endpoint_fixture_t *fixtu
     return written > 0 && written < (int)sizeof(fixture->runtime_dir);
 }
 
+/* Compare against canonical parents only: the endpoint canonicalizes its parent
+ * before building the runtime path (/var/folders/... becomes /private/var/... on
+ * macOS), so a raw prefix compare would miss a correct relocation. */
+static bool bootstrap_path_has_parent(const char *path, const char *parent) {
+    size_t length = parent ? strlen(parent) : 0;
+    return path && length > 0 && strncmp(path, parent, length) == 0 &&
+           (path[length] == '/' || path[length] == '\\');
+}
+
 static void bootstrap_endpoint_fixture_finish(bootstrap_endpoint_fixture_t *fixture) {
     cbm_daemon_ipc_endpoint_free(fixture->endpoint);
     if (fixture->runtime_dir[0] != '\0') {
@@ -220,8 +229,7 @@ static bool bootstrap_fake_spawn(void *opaque, const cbm_daemon_bootstrap_launch
     bootstrap_fake_ops_t *fake = opaque;
     /* Client bootstrap must only ever spawn the EPHEMERAL two-argument
      * shape; the permanent shape belongs exclusively to `daemon start`. */
-    bool exact = spec && spec->argc == 2U && spec->argv[0] &&
-                 spec->argv[1] && !spec->argv[2] &&
+    bool exact = spec && spec->argc == 2U && spec->argv[0] && spec->argv[1] && !spec->argv[2] &&
                  strcmp(spec->argv[1], CBM_DAEMON_INTERNAL_ARG) == 0 && spec->detached &&
                  !spec->inherit_standard_handles && !spec->use_shell &&
                  atomic_load(&fake->handoff_count) > 0 && atomic_load(&fake->lock_held) == 1;
@@ -365,6 +373,81 @@ TEST(daemon_bootstrap_uses_one_stable_per_account_endpoint) {
     PASS();
 }
 
+/* #1574/#1621: the shipped build must be able to relocate the rendezvous when
+ * the default ancestry (%LOCALAPPDATA%, /private/tmp) cannot pass the
+ * private-directory walk — otherwise every command fails, `config list`
+ * included, and the operator cannot reconfigure their way out. CBM_RUNTIME_DIR
+ * moves WHERE the rendezvous lives; it never relaxes HOW it is checked, so a
+ * value that cannot be a private runtime parent must be refused rather than
+ * silently replaced by the default. An explicit parent — the compile-time test
+ * seam, the lifecycle guards' isolated namespace — keeps precedence over it. */
+TEST(daemon_bootstrap_runtime_dir_env_relocates_rendezvous) {
+    char override_parent[BOOTSTRAP_TEST_PATH_CAP] = {0};
+    char canonical_override[BOOTSTRAP_TEST_PATH_CAP] = {0};
+    char canonical_explicit[BOOTSTRAP_TEST_PATH_CAP] = {0};
+    char relocated_runtime[BOOTSTRAP_TEST_PATH_CAP] = {0};
+    char explicit_runtime[BOOTSTRAP_TEST_PATH_CAP] = {0};
+    char unusable[BOOTSTRAP_TEST_PATH_CAP] = {0};
+    int written = snprintf(override_parent, sizeof(override_parent),
+                           "%s/cbm-bootstrap-runtime-env-XXXXXX", cbm_tmpdir());
+    if (written <= 0 || written >= (int)sizeof(override_parent) || !cbm_mkdtemp(override_parent)) {
+        FAIL("could not create the override runtime parent");
+    }
+    written = snprintf(unusable, sizeof(unusable), "%s/absent/nested", override_parent);
+    bool prepared =
+        written > 0 && written < (int)sizeof(unusable) &&
+        cbm_canonical_path(override_parent, canonical_override, sizeof(canonical_override)) != 0 &&
+        cbm_setenv("CBM_RUNTIME_DIR", override_parent, 1) == 0;
+
+    /* NULL parent == every product call site: daemon, MCP client, local CLI,
+     * index worker, activation. */
+    cbm_daemon_ipc_endpoint_t *relocated =
+        prepared ? cbm_daemon_bootstrap_endpoint_new(NULL) : NULL;
+    const char *relocated_dir = relocated ? cbm_daemon_ipc_endpoint_runtime_dir(relocated) : NULL;
+    if (relocated_dir) {
+        (void)snprintf(relocated_runtime, sizeof(relocated_runtime), "%s", relocated_dir);
+    }
+
+    /* Same environment, explicit parent: the caller still wins. */
+    bootstrap_endpoint_fixture_t fixture = {0};
+    bool explicit_started = prepared && bootstrap_endpoint_fixture_start(&fixture, "runtime-env");
+    bool explicit_canonical =
+        explicit_started &&
+        cbm_canonical_path(fixture.parent, canonical_explicit, sizeof(canonical_explicit)) != 0;
+    if (explicit_started) {
+        (void)snprintf(explicit_runtime, sizeof(explicit_runtime), "%s", fixture.runtime_dir);
+    }
+
+    /* A named parent that cannot pass validation is refused, never ignored. */
+    bool unusable_set = prepared && cbm_setenv("CBM_RUNTIME_DIR", unusable, 1) == 0;
+    cbm_daemon_ipc_endpoint_t *refused =
+        unusable_set ? cbm_daemon_bootstrap_endpoint_new(NULL) : NULL;
+
+    /* Restore before asserting: a failed assertion returns immediately, and a
+     * leaked CBM_RUNTIME_DIR would follow every later suite in this process. */
+    (void)cbm_unsetenv("CBM_RUNTIME_DIR");
+    cbm_daemon_ipc_endpoint_free(refused);
+    cbm_daemon_ipc_endpoint_free(relocated);
+    if (relocated_runtime[0] != '\0') {
+        (void)cbm_rmdir(relocated_runtime);
+    }
+    if (explicit_started) {
+        bootstrap_endpoint_fixture_finish(&fixture);
+    }
+    (void)cbm_rmdir(override_parent);
+
+    ASSERT_TRUE(prepared);
+    ASSERT_TRUE(explicit_started);
+    ASSERT_TRUE(explicit_canonical);
+    ASSERT_TRUE(unusable_set);
+    ASSERT_NOT_NULL(relocated);
+    ASSERT_TRUE(bootstrap_path_has_parent(relocated_runtime, canonical_override));
+    ASSERT_TRUE(bootstrap_path_has_parent(explicit_runtime, canonical_explicit));
+    ASSERT_FALSE(bootstrap_path_has_parent(explicit_runtime, canonical_override));
+    ASSERT_NULL(refused);
+    PASS();
+}
+
 TEST(daemon_bootstrap_launches_only_exact_detached_hidden_role) {
     cbm_daemon_bootstrap_launch_spec_t spec;
     ASSERT_TRUE(cbm_daemon_bootstrap_launch_spec_init("/tmp/cbm exact", &spec));
@@ -774,6 +857,7 @@ SUITE(daemon_bootstrap) {
     RUN_TEST(daemon_bootstrap_internal_roles_never_take_client_leases);
     RUN_TEST(daemon_bootstrap_rejects_ambiguous_internal_daemon_argv);
     RUN_TEST(daemon_bootstrap_uses_one_stable_per_account_endpoint);
+    RUN_TEST(daemon_bootstrap_runtime_dir_env_relocates_rendezvous);
     RUN_TEST(daemon_bootstrap_launches_only_exact_detached_hidden_role);
     RUN_TEST(daemon_bootstrap_permanent_daemon_argv_is_byte_exact);
     RUN_TEST(daemon_bootstrap_daemon_ctl_token_routes_after_cli);