From 784febe1cf43419bc882fcba4b0d39c3cb903933 Mon Sep 17 00:00:00 2001
From: Teknium <127238744+teknium1@users.noreply.github.com>
Date: Tue, 19 May 2026 14:24:53 -0700
Subject: [PATCH] perf(cli): defer openai._base_client import via sys.meta_path
 finder (#28864)

`cli.py` was eager-importing `openai._base_client` at module-load time
purely to monkeypatch `AsyncHttpxClientWrapper.__del__` (defense against
"Press ENTER to continue..." errors when AsyncOpenAI clients are GC'd
against dead event loops). That import cost ~166ms / ~30MB on every
cold CLI start because openai's type tree (responses/*, graders/*) is huge.

Replace with a `sys.meta_path` finder that intercepts the first import
of `openai._base_client` from anywhere in the codebase, lets the normal
load run, then applies the `__del__ = lambda self: None` patch before
control returns to the caller. Same correctness guarantee (patch
applies before any AsyncOpenAI instance can be constructed), zero cost
until the SDK is actually needed.

Hot path: every hermes chat / gateway boot / cron tick / subagent spawn.

A/B benchmark, 10 runs each, fresh subprocess:
                     BEFORE  AFTER   delta
  import cli wall    0.86s   0.62s   -28% (median)
  import cli wall    0.85s   0.59s   -31% (min)
  import cli RSS     91.2MB  74.0MB  -19% (median)

The `neuter_async_httpx_del` function in agent/auxiliary_client.py is
unchanged; its tests still pass and any future callers can still invoke
it directly.

Verified:
- import cli no longer pulls openai into sys.modules
- first 'from openai._base_client import AsyncHttpxClientWrapper'
  triggers the patch; __del__.__name__ == '<lambda>'
- tests/run_agent/test_async_httpx_del_neuter.py: 9/9 pass
- tests/agent/test_auxiliary_client.py: 159/159 pass
- tests/cli/: 715/715 pass
---
 cli.py | 53 +++++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 51 insertions(+), 2 deletions(-)

diff --git a/cli.py b/cli.py
index 8fdfa6faad0..d9192020b64 100644
--- a/cli.py
+++ b/cli.py
@@ -655,9 +655,58 @@ except Exception:
 # which, during CLI idle time, finds prompt_toolkit's event loop and tries to
 # close TCP transports bound to dead worker loops — producing
 # "Event loop is closed" / "Press ENTER to continue..." errors.
+#
+# We install a sys.meta_path finder that defers the actual import + patch
+# until ``openai._base_client`` is first loaded by the rest of the codebase.
+# Eagerly importing it here (the old approach) cost ~166ms / ~30MB on every
+# cold CLI start because openai's type tree (responses/*, graders/*) is huge.
+# The finder approach pays nothing until the SDK is genuinely needed and
+# still guarantees the patch is applied before any AsyncOpenAI instance can
+# be constructed (the import-then-instantiate ordering is enforced by
+# Python's import system).
 try:
-    from agent.auxiliary_client import neuter_async_httpx_del
-    neuter_async_httpx_del()
+    import sys as _httpx_neuter_sys
+    import importlib.util as _httpx_neuter_imp_util
+
+    class _AsyncHttpxDelNeuter:
+        """Defer ``AsyncHttpxClientWrapper.__del__`` neutering until import.
+
+        Saves ~166ms on cold CLI start where openai is never used (e.g.
+        ``hermes --help`` paths inside the chat command flow).  See
+        ``agent.auxiliary_client.neuter_async_httpx_del`` for full rationale
+        on why ``__del__`` must be a no-op.
+        """
+
+        _armed = True
+
+        def find_spec(self, fullname, path=None, target=None):
+            if not self._armed or fullname != "openai._base_client":
+                return None
+            # Disarm before delegating so the recursive find_spec call
+            # below doesn't loop through us.
+            self._armed = False
+            try:
+                _httpx_neuter_sys.meta_path.remove(self)
+            except ValueError:
+                pass
+            spec = _httpx_neuter_imp_util.find_spec(fullname)
+            if spec is None or spec.loader is None:
+                return None
+            _orig_exec = spec.loader.exec_module
+
+            def _patched_exec(module):
+                _orig_exec(module)
+                try:
+                    cls = getattr(module, "AsyncHttpxClientWrapper", None)
+                    if cls is not None:
+                        cls.__del__ = lambda self: None  # type: ignore[assignment]
+                except Exception:
+                    pass
+
+            spec.loader.exec_module = _patched_exec  # type: ignore[method-assign]
+            return spec
+
+    _httpx_neuter_sys.meta_path.insert(0, _AsyncHttpxDelNeuter())
 except Exception:
     pass