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.

tests/hermes_cli/test_env_load_cache.py

@@ -0,0 +1,193 @@
+"""Tests for the load_env() process-level cache.
+
+The cache exists to keep `hermes tools` → "All Platforms" fast: every
+`get_env_value()` lookup used to re-read and re-sanitise the entire
+.env file, racking up hundreds of ms across one menu render. The
+cache is keyed on (path, mtime, size); writers (save_env_value /
+remove_env_value / sanitise_env_file) call invalidate_env_cache().
+"""
+
+from __future__ import annotations
+
+import os
+import tempfile
+from pathlib import Path
+from unittest.mock import patch
+
+
+def _write_env(path: Path, contents: str) -> None:
+    path.write_text(contents, encoding="utf-8")
+
+
+def test_load_env_caches_on_repeat_calls():
+    """Repeated load_env() calls on the same file return the cached dict."""
+    from hermes_cli.config import invalidate_env_cache, load_env
+
+    invalidate_env_cache()
+
+    with tempfile.NamedTemporaryFile(
+        mode="w", suffix=".env", delete=False, encoding="utf-8"
+    ) as f:
+        f.write("OPENAI_API_KEY=sk-first\n")
+        env_path = Path(f.name)
+
+    try:
+        with patch("hermes_cli.config.get_env_path", return_value=env_path):
+            first = load_env()
+            # Even if a writer outside our cache mutates the file, an
+            # mtime/size match means the cache still wins. We simulate that
+            # by writing identical bytes back — sanity check that the cache
+            # is keyed structurally, not on a counter.
+            second = load_env()
+
+        assert first == second
+        assert first.get("OPENAI_API_KEY") == "sk-first"
+    finally:
+        env_path.unlink(missing_ok=True)
+        invalidate_env_cache()
+
+
+def test_load_env_invalidates_on_mtime_bump():
+    """Editing the file (mtime changes) invalidates the cache."""
+    from hermes_cli.config import invalidate_env_cache, load_env
+
+    invalidate_env_cache()
+
+    with tempfile.NamedTemporaryFile(
+        mode="w", suffix=".env", delete=False, encoding="utf-8"
+    ) as f:
+        f.write("OPENAI_API_KEY=sk-old\n")
+        env_path = Path(f.name)
+
+    try:
+        with patch("hermes_cli.config.get_env_path", return_value=env_path):
+            first = load_env()
+            assert first.get("OPENAI_API_KEY") == "sk-old"
+
+            # Rewrite file with new contents and bump mtime to make sure
+            # the FS records the change even on coarse-mtime filesystems.
+            _write_env(env_path, "OPENAI_API_KEY=sk-new\n")
+            future = env_path.stat().st_mtime + 5.0
+            os.utime(env_path, (future, future))
+
+            second = load_env()
+            assert second.get("OPENAI_API_KEY") == "sk-new", (
+                "load_env() returned stale value after file change"
+            )
+    finally:
+        env_path.unlink(missing_ok=True)
+        invalidate_env_cache()
+
+
+def test_invalidate_env_cache_forces_reread():
+    """invalidate_env_cache() forces the next load_env() to hit the disk.
+
+    This is the belt-and-braces knob for writers (save_env_value, etc.)
+    on filesystems where mtime resolution might miss a same-second write.
+    """
+    from hermes_cli.config import invalidate_env_cache, load_env
+
+    invalidate_env_cache()
+
+    with tempfile.NamedTemporaryFile(
+        mode="w", suffix=".env", delete=False, encoding="utf-8"
+    ) as f:
+        f.write("OPENAI_API_KEY=sk-old\n")
+        env_path = Path(f.name)
+
+    try:
+        with patch("hermes_cli.config.get_env_path", return_value=env_path):
+            assert load_env().get("OPENAI_API_KEY") == "sk-old"
+
+            # Rewrite WITHOUT bumping mtime — simulates same-second write.
+            mtime_before = env_path.stat().st_mtime
+            _write_env(env_path, "OPENAI_API_KEY=sk-new\n")
+            os.utime(env_path, (mtime_before, mtime_before))
+
+            # Without invalidation, cache hit might return stale.
+            invalidate_env_cache()
+
+            assert load_env().get("OPENAI_API_KEY") == "sk-new"
+    finally:
+        env_path.unlink(missing_ok=True)
+        invalidate_env_cache()
+
+
+def test_save_env_value_invalidates_cache(tmp_path, monkeypatch):
+    """save_env_value() invalidates the cache so subsequent reads see the update."""
+    from hermes_cli import config as config_mod
+    from hermes_cli.config import invalidate_env_cache, load_env, save_env_value
+
+    invalidate_env_cache()
+
+    env_path = tmp_path / ".env"
+    env_path.write_text("EXISTING_KEY=old\n", encoding="utf-8")
+
+    monkeypatch.setattr(config_mod, "get_env_path", lambda: env_path)
+    monkeypatch.setattr(config_mod, "ensure_hermes_home", lambda: None)
+    monkeypatch.setattr(config_mod, "_secure_file", lambda _p: None)
+    monkeypatch.setattr(config_mod, "is_managed", lambda: False)
+
+    try:
+        # Prime the cache.
+        first = load_env()
+        assert first.get("EXISTING_KEY") == "old"
+
+        save_env_value("NEW_KEY", "shiny")
+
+        # Same-second writes on coarse-mtime filesystems would normally
+        # let stale cache survive; invalidate_env_cache() inside the
+        # writer makes the next read see the new key.
+        result = load_env()
+        assert result.get("NEW_KEY") == "shiny"
+        assert result.get("EXISTING_KEY") == "old"
+    finally:
+        monkeypatch.delenv("NEW_KEY", raising=False)
+        invalidate_env_cache()
+
+
+def test_remove_env_value_invalidates_cache(tmp_path, monkeypatch):
+    """remove_env_value() invalidates the cache so the removed key disappears."""
+    from hermes_cli import config as config_mod
+    from hermes_cli.config import (
+        invalidate_env_cache,
+        load_env,
+        remove_env_value,
+        save_env_value,
+    )
+
+    invalidate_env_cache()
+
+    env_path = tmp_path / ".env"
+    monkeypatch.setattr(config_mod, "get_env_path", lambda: env_path)
+    monkeypatch.setattr(config_mod, "ensure_hermes_home", lambda: None)
+    monkeypatch.setattr(config_mod, "_secure_file", lambda _p: None)
+    monkeypatch.setattr(config_mod, "is_managed", lambda: False)
+
+    save_env_value("DOOMED_KEY", "value")
+    assert load_env().get("DOOMED_KEY") == "value"
+
+    try:
+        removed = remove_env_value("DOOMED_KEY")
+        assert removed is True
+        assert "DOOMED_KEY" not in load_env()
+    finally:
+        monkeypatch.delenv("DOOMED_KEY", raising=False)
+        invalidate_env_cache()
+
+
+def test_load_env_handles_missing_file():
+    """A nonexistent .env returns {} and caches the empty result."""
+    from hermes_cli.config import invalidate_env_cache, load_env
+
+    invalidate_env_cache()
+
+    nonexistent = Path(tempfile.gettempdir()) / "hermes-test-no-such-env-xyz123.env"
+    nonexistent.unlink(missing_ok=True)
+
+    try:
+        with patch("hermes_cli.config.get_env_path", return_value=nonexistent):
+            assert load_env() == {}
+            assert load_env() == {}  # cached
+    finally:
+        invalidate_env_cache()

tests/hermes_cli/test_nous_auth_status_cache.py

@@ -0,0 +1,144 @@
+"""Tests for the get_nous_auth_status() process-level cache.
+
+The cache avoids re-validating Nous credentials on every menu paint —
+`hermes tools` → "All Platforms" used to fire ~31 OAuth refresh POSTs
+against portal.nousresearch.com during one render. The cache is keyed
+on auth.json mtime so login/logout flows invalidate naturally; tests
+and other writers can also call invalidate_nous_auth_status_cache().
+"""
+
+from __future__ import annotations
+
+import json
+import os
+from unittest.mock import patch
+
+
+def _seed_auth_file(tmp_path):
+    """Drop a placeholder auth.json into the test HERMES_HOME.
+
+    The exact content doesn't matter for cache-key purposes — only that
+    the file exists and we can mutate it to bump mtime.
+    """
+    auth = tmp_path / "auth.json"
+    auth.write_text(json.dumps({"providers": {}}), encoding="utf-8")
+    return auth
+
+
+def test_get_nous_auth_status_caches_consecutive_calls(tmp_path, monkeypatch):
+    """A second call within the TTL skips re-computing the snapshot."""
+    monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+    _seed_auth_file(tmp_path)
+
+    from hermes_cli import auth as auth_mod
+
+    auth_mod.invalidate_nous_auth_status_cache()
+
+    call_count = {"n": 0}
+
+    def fake_compute():
+        call_count["n"] += 1
+        return {"logged_in": False, "source": "auth_store", "call": call_count["n"]}
+
+    with patch.object(auth_mod, "_compute_nous_auth_status", side_effect=fake_compute):
+        first = auth_mod.get_nous_auth_status()
+        second = auth_mod.get_nous_auth_status()
+        third = auth_mod.get_nous_auth_status()
+
+    assert call_count["n"] == 1, (
+        f"_compute_nous_auth_status was called {call_count['n']}× — "
+        "cache is not deduplicating within TTL."
+    )
+    # Each call returns a copy so callers can't mutate the cached dict.
+    assert first == second == third
+    first["mutated"] = True
+    assert "mutated" not in auth_mod.get_nous_auth_status()
+
+    auth_mod.invalidate_nous_auth_status_cache()
+
+
+def test_get_nous_auth_status_invalidates_on_auth_file_mtime(tmp_path, monkeypatch):
+    """Touching auth.json (login/logout) forces a re-compute."""
+    monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+    auth_path = _seed_auth_file(tmp_path)
+
+    from hermes_cli import auth as auth_mod
+
+    auth_mod.invalidate_nous_auth_status_cache()
+
+    call_count = {"n": 0}
+
+    def fake_compute():
+        call_count["n"] += 1
+        return {"logged_in": False, "source": "auth_store", "call": call_count["n"]}
+
+    with patch.object(auth_mod, "_compute_nous_auth_status", side_effect=fake_compute):
+        auth_mod.get_nous_auth_status()
+        # Bump mtime forward so coarse-resolution filesystems still record
+        # a change.
+        future = auth_path.stat().st_mtime + 5.0
+        os.utime(auth_path, (future, future))
+        auth_mod.get_nous_auth_status()
+
+    assert call_count["n"] == 2, (
+        "auth.json mtime change should invalidate the cache, but only "
+        f"{call_count['n']} compute call(s) happened."
+    )
+
+    auth_mod.invalidate_nous_auth_status_cache()
+
+
+def test_invalidate_nous_auth_status_cache_forces_recompute(tmp_path, monkeypatch):
+    """Explicit invalidate forces the next call to re-compute."""
+    monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+    _seed_auth_file(tmp_path)
+
+    from hermes_cli import auth as auth_mod
+
+    auth_mod.invalidate_nous_auth_status_cache()
+
+    call_count = {"n": 0}
+
+    def fake_compute():
+        call_count["n"] += 1
+        return {"logged_in": False, "source": "auth_store"}
+
+    with patch.object(auth_mod, "_compute_nous_auth_status", side_effect=fake_compute):
+        auth_mod.get_nous_auth_status()
+        auth_mod.invalidate_nous_auth_status_cache()
+        auth_mod.get_nous_auth_status()
+
+    assert call_count["n"] == 2
+
+    auth_mod.invalidate_nous_auth_status_cache()
+
+
+def test_get_nous_auth_status_caches_failure_path(tmp_path, monkeypatch):
+    """Logged-out snapshots are cached too — that's where the cost was.
+
+    Teknium's case: ~31 cache misses per `hermes tools` "All Platforms"
+    menu paint, all returning logged_in=False after a failed refresh POST.
+    The whole point of the cache is to memoise that failure path too.
+    """
+    monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+    _seed_auth_file(tmp_path)
+
+    from hermes_cli import auth as auth_mod
+
+    auth_mod.invalidate_nous_auth_status_cache()
+
+    call_count = {"n": 0}
+
+    def fake_compute():
+        call_count["n"] += 1
+        return {"logged_in": False, "source": "auth_store", "error": "refresh failed"}
+
+    with patch.object(auth_mod, "_compute_nous_auth_status", side_effect=fake_compute):
+        for _ in range(10):
+            auth_mod.get_nous_auth_status()
+
+    assert call_count["n"] == 1, (
+        f"Logged-out snapshots must cache; got {call_count['n']} computes for 10 calls."
+    )
+
+    auth_mod.invalidate_nous_auth_status_cache()