@clawpump/claw-agent 0.1.5 → 0.1.7

package/agent/hermes_cli/auth_commands.py

@@ -13,6 +13,7 @@ from agent.credential_pool import (
     AUTH_TYPE_OAUTH,
     CUSTOM_POOL_PREFIX,
     SOURCE_MANUAL,
+    SOURCE_MANUAL_DEVICE_CODE,
     STATUS_EXHAUSTED,
     STRATEGY_FILL_FIRST,
     STRATEGY_ROUND_ROBIN,
@@ -312,47 +313,62 @@ def auth_add_command(args) -> None:
             creds["tokens"]["access_token"],
             _oauth_default_label(provider, len(pool.entries()) + 1),
         )
-        auth_mod._save_codex_tokens(
-            creds["tokens"],
-            last_refresh=creds.get("last_refresh"),
-            label=label,
-        )
-        pool = load_pool(provider)
-        entry = next((item for item in pool.entries() if item.source == "device_code"), None)
-        shown_label = entry.label if entry is not None else label
-        print(f'Saved {provider} OAuth device-code credentials: "{shown_label}"')
-        return
-
-    if provider == "xai-oauth":
-        creds = auth_mod._xai_oauth_loopback_login(
-            timeout_seconds=getattr(args, "timeout", None) or 20.0,
-            open_browser=not getattr(args, "no_browser", False),
-            manual_paste=bool(getattr(args, "manual_paste", False)),
-        )
-        label = (getattr(args, "label", None) or "").strip() or label_from_token(
-            creds["tokens"]["access_token"],
-            _oauth_default_label(provider, len(pool.entries()) + 1),
-        )
+        # Add a distinct, self-contained pool entry per account (matching the
+        # xai-oauth / google-gemini-cli / qwen-oauth patterns) instead of
+        # routing through the singleton ``_save_codex_tokens`` save path.
+        # The singleton round-trip collapsed every added account into the
+        # latest login: a second ``hermes auth add openai-codex`` overwrote
+        # the first account's singleton-mirrored ``device_code`` entry rather
+        # than creating an independent one (#39236). ``manual:device_code``
+        # entries refresh from their own token pair, so they need no singleton
+        # shadow.
         entry = PooledCredential(
             provider=provider,
             id=uuid.uuid4().hex[:6],
             label=label,
             auth_type=AUTH_TYPE_OAUTH,
             priority=0,
-            source=f"{SOURCE_MANUAL}:xai_pkce",
+            source=SOURCE_MANUAL_DEVICE_CODE,
             access_token=creds["tokens"]["access_token"],
             refresh_token=creds["tokens"].get("refresh_token"),
             base_url=creds.get("base_url"),
             last_refresh=creds.get("last_refresh"),
         )
+        first_credential = not pool.entries()
         pool.add_entry(entry)
+        # Adding the first Codex credential should make it the active provider
+        # (the old singleton save path did this implicitly via
+        # _save_provider_state). Subsequent adds leave the active provider as-is.
+        if first_credential:
+            auth_mod.mark_provider_active_if_unset(provider)
         print(f'Added {provider} OAuth credential #{len(pool.entries())}: "{entry.label}"')
         return
 
+    if provider == "xai-oauth":
+        creds = auth_mod._xai_oauth_loopback_login(
+            timeout_seconds=getattr(args, "timeout", None) or 20.0,
+            open_browser=not getattr(args, "no_browser", False),
+            manual_paste=bool(getattr(args, "manual_paste", False)),
+        )
+        auth_mod._save_xai_oauth_tokens(
+            creds["tokens"],
+            discovery=creds.get("discovery"),
+            redirect_uri=creds.get("redirect_uri", ""),
+            last_refresh=creds.get("last_refresh"),
+        )
+        pool = load_pool(provider)
+        entry = next((e for e in pool.entries() if getattr(e, "source", "") == "loopback_pkce"), None)
+        shown_label = entry.label if entry is not None else label_from_token(
+            creds["tokens"]["access_token"], _oauth_default_label(provider, 1)
+        )
+        print(f'Saved {provider} OAuth credentials: "{shown_label}"')
+        return
+
     if provider == "google-gemini-cli":
         from agent.google_oauth import run_gemini_oauth_login_pure
 
         creds = run_gemini_oauth_login_pure()
+        auth_mod._mark_google_gemini_cli_active(creds)
         label = (getattr(args, "label", None) or "").strip() or (
             creds.get("email") or _oauth_default_label(provider, len(pool.entries()) + 1)
         )
@@ -372,6 +388,7 @@ def auth_add_command(args) -> None:
 
     if provider == "qwen-oauth":
         creds = auth_mod.resolve_qwen_runtime_credentials(refresh_if_expiring=False)
+        auth_mod._mark_qwen_oauth_active(creds)
         label = (getattr(args, "label", None) or "").strip() or label_from_token(
             creds["api_key"],
             _oauth_default_label(provider, len(pool.entries()) + 1),

package/agent/hermes_cli/backup.py

@@ -31,14 +31,41 @@ logger = logging.getLogger(__name__)
 # ---------------------------------------------------------------------------
 
 # Directory names to skip entirely (matched against each path component)
+# ``hermes-agent`` is special-cased to root level only in ``_should_exclude``
+# so that skill directories like ``skills/autonomous-ai-agents/hermes-agent/``
+# are not accidentally excluded.
+#
+# The dependency/cache entries below matter for more than tidiness: without
+# them a single plugin venv, MCP-server install, or pip/uv cache living under
+# HERMES_HOME gets walked file-by-file, ballooning a backup to hundreds of
+# thousands of entries that crawl for hours — the exact "backup stuck for
+# days / 426543 files" symptom users hit. The dependency/test-env names mostly
+# mirror ``agent.skill_utils.EXCLUDED_SKILL_DIRS`` (the project's canonical
+# "regeneratable dir" set); ``.cache`` is an additional backup-only entry, as
+# it names a broad regeneratable cache convention (pip/uv/etc.) that the skill
+# scanner doesn't need to prune but a backup walk does. We deliberately do NOT
+# exclude ``.archive`` here because the curator's ``skills/.archive/`` holds
+# restorable user skills that must survive a backup.
 _EXCLUDED_DIRS = {
     "hermes-agent",     # the codebase repo — re-clone instead
     "__pycache__",      # bytecode caches — regenerated on import
     ".git",             # nested git dirs (profiles shouldn't have these, but safety)
-    "node_modules",     # js deps if website/ somehow leaks in
+    "node_modules",     # js deps — reinstalled on demand
     "backups",          # prior auto-backups — don't nest backups exponentially
     "checkpoints",      # session-local trajectory caches — regenerated per-session,
                         # session-hash-keyed so they don't port to another machine anyway
+    # Python dependency trees (plugin / MCP-server venvs under HERMES_HOME) —
+    # regenerated by reinstalling; never irreplaceable state.
+    ".venv",
+    "venv",
+    "site-packages",
+    # Tool / build caches — all regeneratable.
+    ".cache",
+    ".tox",
+    ".nox",
+    ".pytest_cache",
+    ".mypy_cache",
+    ".ruff_cache",
 }
 
 # File-name suffixes to skip
@@ -61,6 +88,39 @@ _EXCLUDED_NAMES = {
     "cron.pid",
 }
 
+# File names that ``hermes import`` must never overwrite, matched by basename so
+# they're caught for the root profile (``gateway_state.json``) and for named
+# profiles alike (``profiles/<name>/gateway_state.json``).
+#
+# These hold *volatile gateway/process runtime state that is namespaced to the
+# machine or container the backup was taken on* — PIDs in a dead process
+# namespace, a runtime lock, the process registry, and the gateway's last
+# recorded run/desired state. Restoring them onto a different host (or a hosted
+# container) is at best meaningless and at worst actively harmful:
+#
+#   - ``gateway_state.json`` drives the container-boot reconciler
+#     (``container_boot._read_desired_state``), which only auto-starts a
+#     gateway whose recorded state is ``running``. A backup taken from a
+#     machine where the gateway was stopped (or carrying a stale/foreign
+#     value) overwrites the container's own state and leaves the gateway
+#     stuck "starting"/"cooking", disconnecting it from the Nous portal
+#     (NS-508 / the second half of NS-501).
+#   - ``gateway.pid`` / ``cron.pid`` / ``gateway.lock`` / ``processes.json``
+#     reference PIDs and locks in the *source* machine's process namespace; a
+#     numerically-equal PID in the new environment is a different process.
+#     These mirror exactly what ``container_boot._STALE_RUNTIME_FILES`` already
+#     sweeps on every container boot.
+#
+# Older backups predate the backup-side exclusions, so we filter on import too
+# rather than trusting the archive's contents.
+_IMPORT_SKIP_NAMES = {
+    "gateway_state.json",
+    "gateway.pid",
+    "cron.pid",
+    "gateway.lock",
+    "processes.json",
+}
+
 # zipfile.open() drops Unix mode bits on extract; restore tightens these to 0600.
 _SECRET_FILE_NAMES = {".env", "auth.json", "state.db"}
 
@@ -69,10 +129,15 @@ def _should_exclude(rel_path: Path) -> bool:
     """Return True if *rel_path* (relative to hermes root) should be skipped."""
     parts = rel_path.parts
 
-    # Any path component matches an excluded dir name
     for part in parts:
-        if part in _EXCLUDED_DIRS:
-            return True
+        if part not in _EXCLUDED_DIRS:
+            continue
+        # ``hermes-agent`` only matches at the root level (first component).
+        # Nested directories with the same name — e.g.
+        # ``skills/autonomous-ai-agents/hermes-agent/`` — must be preserved.
+        if part == "hermes-agent" and part != parts[0]:
+            continue
+        return True
 
     name = rel_path.name
 
@@ -177,10 +242,13 @@ def run_backup(args) -> None:
         rel_dir = dp.relative_to(hermes_root)
 
         # Prune excluded directories in-place so os.walk doesn't descend
+        # ``hermes-agent`` is only pruned at the root level; nested dirs
+        # with the same name (e.g. in skills/) must be preserved.
+        is_root = rel_dir == Path(".")
         orig_dirnames = dirnames[:]
         dirnames[:] = [
             d for d in dirnames
-            if d not in _EXCLUDED_DIRS
+            if d not in _EXCLUDED_DIRS or (d == "hermes-agent" and not is_root)
         ]
         for removed in set(orig_dirnames) - set(dirnames):
             skipped_dirs.add(str(rel_dir / removed))
@@ -211,7 +279,13 @@ def run_backup(args) -> None:
             try:
                 # Safe copy for SQLite databases (handles WAL mode)
                 if abs_path.suffix == ".db":
-                    with tempfile.NamedTemporaryFile(suffix=".db", delete=False) as tmp:
+                    # Stage the snapshot alongside the output zip so that the
+                    # temp file lives on the same filesystem.  The system
+                    # default (/tmp) may be a small tmpfs that cannot hold
+                    # large databases, causing silent backup incompleteness.
+                    with tempfile.NamedTemporaryFile(
+                        suffix=".db", delete=False, dir=str(out_path.parent)
+                    ) as tmp:
                         tmp_db = Path(tmp.name)
                     if _safe_copy_db(abs_path, tmp_db):
                         zf.write(tmp_db, arcname=str(rel_path))
@@ -368,6 +442,7 @@ def run_import(args) -> None:
 
         errors = []
         restored = 0
+        skipped_runtime: list[str] = []
         t0 = time.monotonic()
 
         for member in members:
@@ -380,6 +455,16 @@ def run_import(args) -> None:
             if not rel:
                 continue
 
+            # Never overwrite volatile gateway/process runtime state. These are
+            # namespaced to the machine/container the backup was taken on;
+            # clobbering them (especially gateway_state.json) breaks the gateway
+            # reconciler on the target and disconnects hosted instances from the
+            # Nous portal. Matched by basename so both the root profile and
+            # named profiles (profiles/<name>/gateway_state.json) are covered.
+            if Path(rel).name in _IMPORT_SKIP_NAMES:
+                skipped_runtime.append(rel)
+                continue
+
             target = hermes_root / rel
 
             # Security: reject absolute paths and traversals
@@ -416,6 +501,16 @@ def run_import(args) -> None:
             if len(errors) > 10:
                 print(f"  ... and {len(errors) - 10} more")
 
+        if skipped_runtime:
+            print(
+                f"\n  Preserved {len(skipped_runtime)} runtime state "
+                f"file(s) (kept this machine's, not the backup's):"
+            )
+            for rel in sorted(skipped_runtime)[:10]:
+                print(f"    {rel}")
+            if len(skipped_runtime) > 10:
+                print(f"    ... and {len(skipped_runtime) - 10} more")
+
         # Post-import: restore profile wrapper scripts
         profiles_dir = hermes_root / "profiles"
         restored_profiles = []
@@ -493,6 +588,7 @@ _QUICK_STATE_FILES = (
     "cron/jobs.json",
     "gateway_state.json",
     "channel_directory.json",
+    "channel_aliases.json",
     "processes.json",
     # Pairing stores (generic + per-platform JSONs outside state.db)
     "pairing",                          # legacy location (gateway/pairing.py)
@@ -853,7 +949,13 @@ def _write_full_zip_backup(out_path: Path, hermes_root: Path) -> Optional[Path]:
             for abs_path, rel_path in files_to_add:
                 try:
                     if abs_path.suffix == ".db":
-                        with tempfile.NamedTemporaryFile(suffix=".db", delete=False) as tmp:
+                        # Stage the snapshot alongside the output zip so that the
+                        # temp file lives on the same filesystem.  The system
+                        # default (/tmp) may be a small tmpfs that cannot hold
+                        # large databases, causing silent backup incompleteness.
+                        with tempfile.NamedTemporaryFile(
+                            suffix=".db", delete=False, dir=str(out_path.parent)
+                        ) as tmp:
                             tmp_db = Path(tmp.name)
                         try:
                             if _safe_copy_db(abs_path, tmp_db):

package/agent/hermes_cli/banner.py

@@ -11,6 +11,7 @@ import subprocess
 import threading
 import time
 from pathlib import Path
+from urllib.parse import urlparse
 from hermes_constants import get_hermes_home
 from typing import TYPE_CHECKING, Dict, List, Optional
 
@@ -133,6 +134,53 @@ try:
     from hermes_cli.distribution import UPDATE_REPO_URL as _UPSTREAM_REPO_URL
 except Exception:
     _UPSTREAM_REPO_URL = "https://github.com/NousResearch/hermes-agent.git"
+_OFFICIAL_REPO_CANONICAL = "github.com/nousresearch/hermes-agent"
+
+
+def _canonical_github_remote(url: str | None) -> str:
+    """Return ``host/owner/repo`` for common GitHub remote URL forms."""
+    if not url:
+        return ""
+    value = url.strip()
+    if value.startswith("git@github.com:"):
+        value = "github.com/" + value[len("git@github.com:"):]
+    elif value.startswith("ssh://git@github.com/"):
+        value = "github.com/" + value[len("ssh://git@github.com/"):]
+    else:
+        parsed = urlparse(value)
+        if parsed.netloc and parsed.path:
+            value = f"{parsed.netloc}{parsed.path}"
+    value = value.strip().rstrip("/")
+    if value.endswith(".git"):
+        value = value[:-4]
+    return value.lower()
+
+
+def _is_ssh_remote(url: str | None) -> bool:
+    if not url:
+        return False
+    value = url.strip().lower()
+    return value.startswith("git@") or value.startswith("ssh://")
+
+
+def _is_official_ssh_remote(url: str | None) -> bool:
+    return _is_ssh_remote(url) and _canonical_github_remote(url) == _OFFICIAL_REPO_CANONICAL
+
+
+def _git_stdout(args: list[str], *, cwd: Path, timeout: int = 5) -> Optional[str]:
+    try:
+        result = subprocess.run(
+            ["git", *args],
+            capture_output=True,
+            text=True,
+            timeout=timeout,
+            cwd=str(cwd),
+        )
+    except Exception:
+        return None
+    if result.returncode != 0:
+        return None
+    return (result.stdout or "").strip()
 
 
 def _check_via_rev(local_rev: str) -> Optional[int]:
@@ -158,6 +206,11 @@ def _check_via_rev(local_rev: str) -> Optional[int]:
 
 def _check_via_local_git(repo_dir: Path) -> Optional[int]:
     """Count commits behind origin/main in a local checkout."""
+    origin_url = _git_stdout(["remote", "get-url", "origin"], cwd=repo_dir)
+    if _is_official_ssh_remote(origin_url):
+        head_rev = _git_stdout(["rev-parse", "HEAD"], cwd=repo_dir)
+        return _check_via_rev(head_rev) if head_rev else None
+
     try:
         subprocess.run(
             ["git", "fetch", "origin", "--quiet"],
@@ -237,6 +290,25 @@ def check_for_updates() -> Optional[int]:
     cache_file = hermes_home / ".update_check"
     embedded_rev = os.environ.get("HERMES_REVISION") or None
 
+    # Docker images have no working tree to count commits against — the
+    # published image excludes `.git` (see .dockerignore) and sets no
+    # HERMES_REVISION (that's nix-only). Without this guard the checks below
+    # fall through to `check_via_pypi()`, whose PyPI-version mismatch flag (1)
+    # then gets rendered by the CLI banner and the TUI badge as a phantom
+    # "1 commit behind" — even though no git repo or commit math is involved,
+    # and `hermes update` correctly refuses to run in-place inside the
+    # container anyway. The dashboard's REST `/api/hermes/update/check`
+    # endpoint already short-circuits docker the same way (web_server.py);
+    # mirror that here so the banner/TUI surfaces agree. Returning None makes
+    # both the Rich banner (build_welcome_banner) and the Ink badge
+    # (branding.tsx, guarded on `typeof === 'number' && > 0`) show nothing.
+    try:
+        from hermes_cli.config import detect_install_method
+        if detect_install_method() == "docker":
+            return None
+    except Exception:
+        pass
+
     # Read cache — invalidate if the embedded rev OR installed version has
     # changed since the last check. The version guard matters for pip installs:
     # `check_via_pypi()` compares against VERSION, so a `pip install --upgrade`
@@ -640,11 +712,27 @@ def build_welcome_banner(console: "Console", model: str, cwd: str,
         right_lines.append("")
         right_lines.append(f"[bold {accent}]MCP Servers[/]")
         for srv in mcp_status:
+            status = srv.get("status")
             if srv["connected"]:
                 right_lines.append(
                     f"[dim {dim}]{srv['name']}[/] [{text}]({srv['transport']})[/] "
                     f"[dim {dim}]—[/] [{text}]{srv['tools']} tool(s)[/]"
                 )
+            elif srv.get("disabled") or status == "disabled":
+                right_lines.append(
+                    f"[dim {dim}]{srv['name']}[/] [dim]({srv['transport']})[/] "
+                    f"[dim {dim}]— disabled[/]"
+                )
+            elif status == "connecting":
+                right_lines.append(
+                    f"[dim {dim}]{srv['name']}[/] [dim]({srv['transport']})[/] "
+                    f"[yellow]— connecting[/]"
+                )
+            elif status == "configured":
+                right_lines.append(
+                    f"[dim {dim}]{srv['name']}[/] [dim]({srv['transport']})[/] "
+                    f"[dim {dim}]— configured[/]"
+                )
             else:
                 right_lines.append(
                     f"[red]{srv['name']}[/] [dim]({srv['transport']})[/] "