test: speed up slow tests (backoff + subprocess + IMDS network) (#11797)

Cuts shard-3 local runtime in half by neutralizing real wall-clock
waits across three classes of slow test:

## 1. Retry backoff mocks

- tests/run_agent/conftest.py (NEW): autouse fixture mocks
  jittered_backoff to 0.0 so the `while time.time() < sleep_end`
  busy-loop exits immediately. No global time.sleep mock (would
  break threading tests).
- test_anthropic_error_handling, test_413_compression,
  test_run_agent_codex_responses, test_fallback_model: per-file
  fixtures mock time.sleep / asyncio.sleep for retry / compression
  paths.
- test_retaindb_plugin: cap the retaindb module's bound time.sleep
  to 0.05s via a per-test shim (background writer-thread retries
  sleep 2s after errors; tests don't care about exact duration).
  Plus replace arbitrary time.sleep(N) waits with short polling
  loops bounded by deadline.

## 2. Subprocess sleeps in production code

- test_update_gateway_restart: mock time.sleep. Production code
  does time.sleep(3) after `systemctl restart` to verify the
  service survived. Tests mock subprocess.run \u2014 nothing actually
  restarts \u2014 so the wait is dead time.

## 3. Network / IMDS timeouts (biggest single win)

- tests/conftest.py: add AWS_EC2_METADATA_DISABLED=true plus
  AWS_METADATA_SERVICE_TIMEOUT=1 and ATTEMPTS=1. boto3 falls back
  to IMDS (169.254.169.254) when no AWS creds are set. Any test
  hitting has_aws_credentials() / resolve_aws_auth_env_var() (e.g.
  test_status, test_setup_copilot_acp, anything that touches
  provider auto-detect) burned ~2-4s waiting for that to time out.
- test_exit_cleanup_interrupt: explicitly mock
  resolve_runtime_provider which was doing real network auto-detect
  (~4s). Tests don't care about provider resolution \u2014 the agent
  is already mocked.
- test_timezone: collapse the 3-test "TZ env in subprocess" suite
  into 2 tests by checking both injection AND no-leak in the same
  subprocess spawn (was 3 \u00d7 3.2s, now 2 \u00d7 4s).

## Validation

| Test | Before | After |
|---|---|---|
| test_anthropic_error_handling (8 tests) | ~80s | ~15s |
| test_413_compression (14 tests) | ~18s | 2.3s |
| test_retaindb_plugin (67 tests) | ~13s | 1.3s |
| test_status_includes_tavily_key | 4.0s | 0.05s |
| test_setup_copilot_acp_skips_same_provider_pool_step | 8.0s | 0.26s |
| test_update_gateway_restart (5 tests) | ~18s total | ~0.35s total |
| test_exit_cleanup_interrupt (2 tests) | 8s | 1.5s |
| **Matrix shard 3 local** | **108s** | **50s** |

No behavioral contract changed \u2014 tests still verify retry happens,
service restart logic runs, etc.; they just don't burn real seconds
waiting for it.

Supersedes PR #11779 (those changes are included here).

tests/conftest.py

@@ -229,6 +229,15 @@ def _hermetic_environment(tmp_path, monkeypatch):
     monkeypatch.setenv("LC_ALL", "C.UTF-8")
     monkeypatch.setenv("PYTHONHASHSEED", "0")
 
+    # 4b. Disable AWS IMDS lookups. Without this, any test that ends up
+    #     calling has_aws_credentials() / resolve_aws_auth_env_var()
+    #     (e.g. provider auto-detect, status command, cron run_job) burns
+    #     ~2s waiting for the metadata service at 169.254.169.254 to time
+    #     out. Tests don't run on EC2 — IMDS is always unreachable here.
+    monkeypatch.setenv("AWS_EC2_METADATA_DISABLED", "true")
+    monkeypatch.setenv("AWS_METADATA_SERVICE_TIMEOUT", "1")
+    monkeypatch.setenv("AWS_METADATA_SERVICE_NUM_ATTEMPTS", "1")
+
     # 5. Reset plugin singleton so tests don't leak plugins from
     #    ~/.hermes/plugins/ (which, per step 3, is now empty — but the
     #    singleton might still be cached from a previous test).

tests/hermes_cli/test_update_gateway_restart.py

@@ -13,9 +13,29 @@ from unittest.mock import patch, MagicMock
 import pytest
 
 import hermes_cli.gateway as gateway_cli
+import hermes_cli.main as cli_main
 from hermes_cli.main import cmd_update
 
 
+# ---------------------------------------------------------------------------
+# Skip the real-time sleeps inside cmd_update's restart-verification path
+# ---------------------------------------------------------------------------
+
+
+@pytest.fixture(autouse=True)
+def _no_restart_verify_sleep(monkeypatch):
+    """hermes_cli/main.py uses time.sleep(3) after systemctl restart to
+    verify the service survived. Tests mock subprocess.run — nothing
+    actually restarts — so the 3s wait is dead time.
+
+    main.py does ``import time as _time`` at both module level (line 167)
+    and inside functions (lines 3281, 4384, 4401). Patching the global
+    ``time.sleep`` affects only the duration of this test.
+    """
+    import time as _real_time
+    monkeypatch.setattr(_real_time, "sleep", lambda *_a, **_k: None)
+
+
 # ---------------------------------------------------------------------------
 # Helpers
 # ---------------------------------------------------------------------------

tests/plugins/test_retaindb_plugin.py

@@ -31,6 +31,31 @@ def _isolate_env(tmp_path, monkeypatch):
     monkeypatch.delenv("RETAINDB_PROJECT", raising=False)
 
 
+@pytest.fixture(autouse=True)
+def _cap_retaindb_sleeps(monkeypatch):
+    """Cap production-code sleeps so background-thread tests run fast.
+
+    The retaindb ``_WriteQueue._flush_row`` does ``time.sleep(2)`` after
+    errors. Across multiple tests that trigger the retry path, that adds
+    up. Cap the module's bound ``time.sleep`` to 0.05s — tests don't care
+    about the exact retry delay, only that it happens. The test file's
+    own ``time.sleep`` stays real since it uses a different reference.
+    """
+    try:
+        from plugins.memory import retaindb as _retaindb
+    except ImportError:
+        return
+
+    real_sleep = _retaindb.time.sleep
+
+    def _capped_sleep(seconds):
+        return real_sleep(min(float(seconds), 0.05))
+
+    import types as _types
+    fake_time = _types.SimpleNamespace(sleep=_capped_sleep, time=_retaindb.time.time)
+    monkeypatch.setattr(_retaindb, "time", fake_time)
+
+
 # We need the repo root on sys.path so the plugin can import agent.memory_provider
 import sys
 _repo_root = str(Path(__file__).resolve().parents[2])
@@ -130,16 +155,18 @@ class TestWriteQueue:
     def test_enqueue_creates_row(self, tmp_path):
         q, client, db_path = self._make_queue(tmp_path)
         q.enqueue("user1", "sess1", [{"role": "user", "content": "hi"}])
-        # Give the writer thread a moment to process
+        # shutdown() blocks until the writer thread drains the queue — no need
-        time.sleep(1)
+        # to pre-sleep (the old 1s sleep was a just-in-case wait, but shutdown
+        # does the right thing).
         q.shutdown()
         # If ingest succeeded, the row should be deleted
         client.ingest_session.assert_called_once()
 
     def test_enqueue_persists_to_sqlite(self, tmp_path):
         client = MagicMock()
-        # Make ingest hang so the row stays in SQLite
+        # Make ingest slow so the row is still in SQLite when we peek.
-        client.ingest_session = MagicMock(side_effect=lambda *a, **kw: time.sleep(5))
+        # 0.5s is plenty — the test just needs the flush to still be in-flight.
+        client.ingest_session = MagicMock(side_effect=lambda *a, **kw: time.sleep(0.5))
         db_path = tmp_path / "test_queue.db"
         q = _WriteQueue(client, db_path)
         q.enqueue("user1", "sess1", [{"role": "user", "content": "test"}])
@@ -154,8 +181,7 @@ class TestWriteQueue:
     def test_flush_deletes_row_on_success(self, tmp_path):
         q, client, db_path = self._make_queue(tmp_path)
         q.enqueue("user1", "sess1", [{"role": "user", "content": "hi"}])
-        time.sleep(1)
+        q.shutdown()  # blocks until drain
-        q.shutdown()
         # Row should be gone
         conn = sqlite3.connect(str(db_path))
         rows = conn.execute("SELECT COUNT(*) FROM pending").fetchone()[0]
@@ -168,14 +194,20 @@ class TestWriteQueue:
         db_path = tmp_path / "test_queue.db"
         q = _WriteQueue(client, db_path)
         q.enqueue("user1", "sess1", [{"role": "user", "content": "hi"}])
-        time.sleep(3)  # Allow retry + sleep(2) in _flush_row
+        # Poll for the error to be recorded (max 2s), instead of a fixed 3s wait.
-        q.shutdown()
+        deadline = time.time() + 2.0
-        # Row should still exist with error recorded
+        last_error = None
+        while time.time() < deadline:
             conn = sqlite3.connect(str(db_path))
             row = conn.execute("SELECT last_error FROM pending").fetchone()
             conn.close()
-        assert row is not None
+            if row and row[0]:
-        assert "API down" in row[0]
+                last_error = row[0]
+                break
+            time.sleep(0.05)
+        q.shutdown()
+        assert last_error is not None
+        assert "API down" in last_error
 
     def test_thread_local_connection_reuse(self, tmp_path):
         q, _, _ = self._make_queue(tmp_path)
@@ -193,14 +225,27 @@ class TestWriteQueue:
         client1.ingest_session = MagicMock(side_effect=RuntimeError("fail"))
         q1 = _WriteQueue(client1, db_path)
         q1.enqueue("user1", "sess1", [{"role": "user", "content": "lost turn"}])
-        time.sleep(3)
+        # Wait until the error is recorded (poll with short interval).
+        deadline = time.time() + 2.0
+        while time.time() < deadline:
+            conn = sqlite3.connect(str(db_path))
+            row = conn.execute("SELECT last_error FROM pending").fetchone()
+            conn.close()
+            if row and row[0]:
+                break
+            time.sleep(0.05)
         q1.shutdown()
 
         # Now create a new queue — it should replay the pending rows
         client2 = MagicMock()
         client2.ingest_session = MagicMock(return_value={"status": "ok"})
         q2 = _WriteQueue(client2, db_path)
-        time.sleep(2)
+        # Poll for the replay to happen.
+        deadline = time.time() + 2.0
+        while time.time() < deadline:
+            if client2.ingest_session.called:
+                break
+            time.sleep(0.05)
         q2.shutdown()
 
         # The replayed row should have been ingested via client2

tests/run_agent/conftest.py

@@ -0,0 +1,34 @@
+"""Fast-path fixtures shared across tests/run_agent/.
+
+Many tests in this directory exercise the retry/backoff paths in the
+agent loop. Production code uses ``jittered_backoff(base_delay=5.0)``
+with a ``while time.time() < sleep_end`` loop — a single retry test
+spends 5+ seconds of real wall-clock time on backoff waits.
+
+Mocking ``jittered_backoff`` to return 0.0 collapses the while-loop
+to a no-op (``time.time() < time.time() + 0`` is false immediately),
+which handles the most common case without touching ``time.sleep``.
+
+We deliberately DO NOT mock ``time.sleep`` here — some tests
+(test_interrupt_propagation, test_primary_runtime_restore, etc.) use
+the real ``time.sleep`` for threading coordination or assert that it
+was called with specific values. Tests that want to additionally
+fast-path direct ``time.sleep(N)`` calls in production code should
+monkeypatch ``run_agent.time.sleep`` locally (see
+``test_anthropic_error_handling.py`` for the pattern).
+"""
+
+from __future__ import annotations
+
+import pytest
+
+
+@pytest.fixture(autouse=True)
+def _fast_retry_backoff(monkeypatch):
+    """Short-circuit retry backoff for all tests in this directory."""
+    try:
+        import run_agent
+    except ImportError:
+        return
+
+    monkeypatch.setattr(run_agent, "jittered_backoff", lambda *a, **k: 0.0)

tests/run_agent/test_413_compression.py

@@ -19,6 +19,24 @@ import pytest
 
 from agent.context_compressor import SUMMARY_PREFIX
 from run_agent import AIAgent
+import run_agent
+
+
+# ---------------------------------------------------------------------------
+# Fast backoff for compression retry tests
+# ---------------------------------------------------------------------------
+
+
+@pytest.fixture(autouse=True)
+def _no_compression_sleep(monkeypatch):
+    """Short-circuit the 2s time.sleep between compression retries.
+
+    Production code has ``time.sleep(2)`` in multiple places after a 413/context
+    compression, for rate-limit smoothing. Tests assert behavior, not timing.
+    """
+    import time as _time
+    monkeypatch.setattr(_time, "sleep", lambda *_a, **_k: None)
+    monkeypatch.setattr(run_agent, "jittered_backoff", lambda *a, **k: 0.0)
 
 
 # ---------------------------------------------------------------------------

tests/run_agent/test_anthropic_error_handling.py

@@ -27,6 +27,39 @@ from gateway.config import Platform
 from gateway.session import SessionSource
 
 
+# ---------------------------------------------------------------------------
+# Fast backoff for tests that exercise the retry loop
+# ---------------------------------------------------------------------------
+
+
+@pytest.fixture(autouse=True)
+def _no_backoff_wait(monkeypatch):
+    """Short-circuit retry backoff so tests don't block on real wall-clock waits.
+
+    The production code uses jittered_backoff() with a 5s base delay plus a
+    tight time.sleep(0.2) loop. Without this patch, each 429/500/529 retry
+    test burns ~10s of real time on CI — across six tests that's ~60s for
+    behavior we're not asserting against timing.
+
+    Tests assert retry counts and final results, never wait durations.
+    """
+    import asyncio as _asyncio
+    import time as _time
+
+    monkeypatch.setattr(run_agent, "jittered_backoff", lambda *a, **k: 0.0)
+    monkeypatch.setattr(_time, "sleep", lambda *_a, **_k: None)
+
+    # Also fast-path asyncio.sleep — the gateway's _run_agent path has
+    # several await asyncio.sleep(...) calls that add real wall-clock time.
+    _real_asyncio_sleep = _asyncio.sleep
+
+    async def _fast_sleep(delay=0, *args, **kwargs):
+        # Yield to the event loop but skip the actual delay.
+        await _real_asyncio_sleep(0)
+
+    monkeypatch.setattr(_asyncio, "sleep", _fast_sleep)
+
+
 # ---------------------------------------------------------------------------
 # Helpers
 # ---------------------------------------------------------------------------

tests/run_agent/test_exit_cleanup_interrupt.py

@@ -13,6 +13,24 @@ from unittest.mock import MagicMock, patch, call
 import pytest
 
 
+@pytest.fixture(autouse=True)
+def _mock_runtime_provider(monkeypatch):
+    """run_job calls resolve_runtime_provider which can try real network
+    auto-detection (~4s of socket timeouts in hermetic CI). Mock it out
+    since these tests don't care about provider resolution — the agent
+    is mocked too."""
+    import hermes_cli.runtime_provider as rp
+    def _fake_resolve(*args, **kwargs):
+        return {
+            "provider": "openrouter",
+            "api_key": "test-key",
+            "base_url": "https://openrouter.ai/api/v1",
+            "model": "test/model",
+            "api_mode": "chat_completions",
+        }
+    monkeypatch.setattr(rp, "resolve_runtime_provider", _fake_resolve)
+
+
 class TestCronJobCleanup:
     """cron/scheduler.py — end_session + close in the finally block."""
 

tests/run_agent/test_fallback_model.py

@@ -11,6 +11,16 @@ from unittest.mock import MagicMock, patch
 import pytest
 
 from run_agent import AIAgent
+import run_agent
+
+
+@pytest.fixture(autouse=True)
+def _no_fallback_wait(monkeypatch):
+    """Short-circuit time.sleep in fallback/recovery paths so tests don't
+    block on the ``min(3 + retry_count, 8)`` wait before a primary retry."""
+    import time as _time
+    monkeypatch.setattr(_time, "sleep", lambda *_a, **_k: None)
+    monkeypatch.setattr(run_agent, "jittered_backoff", lambda *a, **k: 0.0)
 
 
 def _make_tool_defs(*names: str) -> list:

tests/run_agent/test_run_agent_codex_responses.py

@@ -12,6 +12,15 @@ sys.modules.setdefault("fal_client", types.SimpleNamespace())
 import run_agent
 
 
+@pytest.fixture(autouse=True)
+def _no_codex_backoff(monkeypatch):
+    """Short-circuit retry backoff so Codex retry tests don't block on real
+    wall-clock waits (5s jittered_backoff base delay + tight time.sleep loop)."""
+    import time as _time
+    monkeypatch.setattr(run_agent, "jittered_backoff", lambda *a, **k: 0.0)
+    monkeypatch.setattr(_time, "sleep", lambda *_a, **_k: None)
+
+
 def _patch_agent_bootstrap(monkeypatch):
     monkeypatch.setattr(
         run_agent,

tests/test_timezone.py

@@ -159,18 +159,34 @@ class TestCodeExecutionTZ:
         return _json.dumps({"error": f"unexpected tool call: {function_name}"})
 
     def test_tz_injected_when_configured(self):
-        """When HERMES_TIMEZONE is set, child process sees TZ env var."""
+        """When HERMES_TIMEZONE is set, child process sees TZ env var.
+
+        Verified alongside leak-prevention + empty-TZ handling in one
+        subprocess call so we don't pay 3x the subprocess startup cost
+        (each execute_code spawns a real Python subprocess ~3s).
+        """
         import json as _json
         os.environ["HERMES_TIMEZONE"] = "Asia/Kolkata"
 
+        # One subprocess, three things checked:
+        #   1) TZ is injected as "Asia/Kolkata"
+        #   2) HERMES_TIMEZONE itself does NOT leak into the child env
+        probe = (
+            'import os; '
+            'print("TZ=" + os.environ.get("TZ", "NOT_SET")); '
+            'print("HERMES_TIMEZONE=" + os.environ.get("HERMES_TIMEZONE", "NOT_SET"))'
+        )
         with patch("model_tools.handle_function_call", side_effect=self._mock_handle):
             result = _json.loads(self._execute_code(
-                code='import os; print(os.environ.get("TZ", "NOT_SET"))',
+                code=probe,
-                task_id="tz-test",
+                task_id="tz-combined-test",
                 enabled_tools=[],
             ))
         assert result["status"] == "success"
-        assert "Asia/Kolkata" in result["output"]
+        assert "TZ=Asia/Kolkata" in result["output"]
+        assert "HERMES_TIMEZONE=NOT_SET" in result["output"], (
+            "HERMES_TIMEZONE should not leak into child env (only TZ)"
+        )
 
     def test_tz_not_injected_when_empty(self):
         """When HERMES_TIMEZONE is not set, child process has no TZ."""
@@ -186,20 +202,6 @@ class TestCodeExecutionTZ:
         assert result["status"] == "success"
         assert "NOT_SET" in result["output"]
 
-    def test_hermes_timezone_not_leaked_to_child(self):
-        """HERMES_TIMEZONE itself must NOT appear in child env (only TZ)."""
-        import json as _json
-        os.environ["HERMES_TIMEZONE"] = "Asia/Kolkata"
-
-        with patch("model_tools.handle_function_call", side_effect=self._mock_handle):
-            result = _json.loads(self._execute_code(
-                code='import os; print(os.environ.get("HERMES_TIMEZONE", "NOT_SET"))',
-                task_id="tz-leak-test",
-                enabled_tools=[],
-            ))
-        assert result["status"] == "success"
-        assert "NOT_SET" in result["output"]
-
 
 # =========================================================================
 # Cron timezone-aware scheduling