perf(tools): cache get_nous_auth_status() and load_env() to fix slow hermes tools menus (#25341)

`hermes tools` -> "All Platforms" took ~14s to render the checklist
because building the toolset labels called `get_nous_auth_status()` ~31x
transitively (`_toolset_has_keys` -> `_visible_providers` ->
`get_nous_subscription_features` -> `managed_nous_tools_enabled`).
Each call did a synchronous OAuth refresh POST to
portal.nousresearch.com (~350ms even on the failure path), so one menu
paint burned >13s of HTTP and 31 single-use Nous refresh tokens.

Secondary hot spot: every `get_env_value()` re-read and re-sanitised
the entire .env file. 116 reads with O(lines x known-keys) scanning
added ~300ms of CPU per render.

Fix is two process-level caches, both mtime-keyed so login/logout/edit
invalidate naturally:

* `hermes_cli/auth.py`: memoise `get_nous_auth_status()` for 15s keyed
  on auth.json mtime. Splits `_compute_nous_auth_status()` as the
  uncached impl. Adds `invalidate_nous_auth_status_cache()`.
* `hermes_cli/config.py`: memoise `load_env()` keyed on .env
  (path, mtime, size). Adds `invalidate_env_cache()`, wired into
  `save_env_value`, `remove_env_value`, and the sanitize-on-load
  writer so writers don't return stale dicts on same-second writes.

Before/after on Teknium's box (real HERMES_HOME, no Nous login):

* "All Platforms" cold path: ~13,874ms -> ~691ms label-build
* Warm re-open within the same process: ~122ms -> ~17ms

Side benefit: stops burning a Nous refresh token on every menu paint,
which was risking the portal's reuse-detection revocation logic.

hermes_cli/auth.py

@@ -35,7 +35,7 @@ from dataclasses import dataclass, field
 from datetime import datetime, timezone
 from http.server import BaseHTTPRequestHandler, HTTPServer
 from pathlib import Path
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, List, Optional, Tuple
 from urllib.parse import parse_qs, urlencode, urlparse
 
 import httpx
@@ -3870,6 +3870,39 @@ def _snapshot_nous_pool_status() -> Dict[str, Any]:
         return _empty_nous_auth_status()
 
 
+# ── Process-level memo for get_nous_auth_status() ──
+# get_nous_auth_status() validates state by calling resolve_nous_runtime_credentials(),
+# which does a synchronous OAuth refresh POST to portal.nousresearch.com. That can take
+# ~350ms even on the failure path, and read-only UI surfaces (`hermes tools`, status panels,
+# subscription-feature checks) call it many times per render — `hermes tools` → "All Platforms"
+# was firing the refresh ~31× during one menu paint, racking up >13s of HTTP and burning
+# single-use refresh tokens. Cache the snapshot for a few seconds, keyed on the auth.json
+# mtime so that `hermes auth login/logout/add/remove` invalidate naturally on the next call.
+_NOUS_AUTH_STATUS_CACHE_TTL = 15.0  # seconds
+_nous_auth_status_cache: Optional[Tuple[float, Optional[float], Dict[str, Any]]] = None
+
+
+def _auth_file_mtime() -> Optional[float]:
+    try:
+        return _auth_file_path().stat().st_mtime
+    except FileNotFoundError:
+        return None
+    except Exception:
+        return None
+
+
+def invalidate_nous_auth_status_cache() -> None:
+    """Clear the get_nous_auth_status() process-level memo.
+
+    Call this from any code path that mutates Nous auth state without going
+    through resolve_nous_runtime_credentials() (e.g. tests). Login/logout
+    flows touch auth.json, so the mtime check below invalidates them
+    automatically — explicit invalidation is the belt-and-braces option.
+    """
+    global _nous_auth_status_cache
+    _nous_auth_status_cache = None
+
+
 def get_nous_auth_status() -> Dict[str, Any]:
     """Status snapshot for Nous auth.
 
@@ -3878,7 +3911,32 @@ def get_nous_auth_status() -> Dict[str, Any]:
     by resolving runtime credentials so revoked refresh sessions do not show up
     as a healthy login. If provider state is absent, fall back to the credential
     pool for the just-logged-in / not-yet-promoted case.
+
+    The returned snapshot is memoised for ~15s keyed on the auth.json mtime,
+    so menu/status surfaces that ask repeatedly don't trigger one refresh POST
+    per call. Login/logout flows write to auth.json and therefore invalidate
+    the cache automatically; tests can also call
+    ``invalidate_nous_auth_status_cache()`` explicitly.
     """
+    global _nous_auth_status_cache
+    now = time.monotonic()
+    mtime = _auth_file_mtime()
+    cached = _nous_auth_status_cache
+    if cached is not None:
+        cached_at, cached_mtime, cached_status = cached
+        if (
+            cached_mtime == mtime
+            and (now - cached_at) < _NOUS_AUTH_STATUS_CACHE_TTL
+        ):
+            return dict(cached_status)
+
+    status = _compute_nous_auth_status()
+    _nous_auth_status_cache = (now, mtime, dict(status))
+    return status
+
+
+def _compute_nous_auth_status() -> Dict[str, Any]:
+    """Uncached implementation of get_nous_auth_status(). See that function."""
     state = get_provider_auth_state("nous")
     if state:
         base_status = {

hermes_cli/config.py

@@ -4319,10 +4319,34 @@ def load_env() -> Dict[str, str]:
     concatenated KEY=VALUE pairs on a single line) are handled
     gracefully instead of producing mangled values such as duplicated
     bot tokens.  See #8908.
+
+    The parsed dict is memoised keyed on the .env file mtime, because
+    ``get_env_value()`` is called dozens-to-hundreds of times per
+    interactive menu render (`hermes tools`, `hermes setup`, status
+    panels). Sanitisation is O(lines × known-keys), so re-parsing the
+    same file on every call was burning ~300ms of CPU per `hermes tools`
+    menu paint on top of the OAuth-refresh slowness. The mtime check
+    invalidates the cache when the user edits .env mid-process.
     """
+    global _env_cache
     env_path = get_env_path()
-    env_vars = {}
-    
+
+    try:
+        mtime = env_path.stat().st_mtime
+        size = env_path.stat().st_size
+        cache_key = (str(env_path), mtime, size)
+    except FileNotFoundError:
+        cache_key = (str(env_path), None, None)
+    except Exception:
+        cache_key = None
+
+    if cache_key is not None and _env_cache is not None:
+        cached_key, cached_vars = _env_cache
+        if cached_key == cache_key:
+            return dict(cached_vars)
+
+    env_vars: Dict[str, str] = {}
+
     if env_path.exists():
         # On Windows, open() defaults to the system locale (cp1252) which can
         # fail on UTF-8 .env files. Always use explicit UTF-8; tolerate BOM
@@ -4338,10 +4362,33 @@ def load_env() -> Dict[str, str]:
             if line and not line.startswith('#') and '=' in line:
                 key, _, value = line.partition('=')
                 env_vars[key.strip()] = value.strip().strip('"\'')
-    
+
+    if cache_key is not None:
+        _env_cache = (cache_key, dict(env_vars))
+
     return env_vars
 
 
+# Module-level memo for load_env(), keyed on (path, mtime, size).
+# Editing .env bumps mtime → next load_env() rebuilds. invalidate_env_cache()
+# is the explicit knob for writers that update .env via this module
+# (set_env_value, save_env, etc.) without relying on filesystem mtime
+# resolution.
+_env_cache: Optional[Tuple[Tuple[str, Optional[float], Optional[int]], Dict[str, str]]] = None
+
+
+def invalidate_env_cache() -> None:
+    """Clear the load_env() process-level memo.
+
+    Writers that mutate .env (set_env_value, save_env, etc.) call this
+    to guarantee the next load_env() sees their change even on
+    filesystems with coarse mtime resolution. Reads invalidate naturally
+    via the mtime/size check.
+    """
+    global _env_cache
+    _env_cache = None
+
+
 def _sanitize_env_lines(lines: list) -> list:
     """Fix corrupted .env lines before reading or writing.
 
@@ -4444,6 +4491,7 @@ def sanitize_env_file() -> int:
             pass
         raise
     _secure_file(env_path)
+    invalidate_env_cache()
     return fixes
 
 
@@ -4555,6 +4603,7 @@ def save_env_value(key: str, value: str):
     _secure_file(env_path)
 
     os.environ[key] = value
+    invalidate_env_cache()
 
 
 def remove_env_value(key: str) -> bool:
@@ -4610,6 +4659,7 @@ def remove_env_value(key: str) -> bool:
         _secure_file(env_path)
 
     os.environ.pop(key, None)
+    invalidate_env_cache()
     return found