From 57ee874d6e42a91035bd71e33f044b223c614d81 Mon Sep 17 00:00:00 2001
From: Nick Sweeting <git@sweeting.me>
Date: Thu, 3 Sep 2026 00:59:06 -0700
Subject: [PATCH] Trust ready OpenCode processes

---
 archivebox/opencode/views.py            | 28 ++++++------------
 archivebox/tests/test_opencode_agent.py | 38 ++++---------------------
 2 files changed, 14 insertions(+), 52 deletions(-)

diff --git a/archivebox/opencode/views.py b/archivebox/opencode/views.py
index 14876093..461141d7 100644
--- a/archivebox/opencode/views.py
+++ b/archivebox/opencode/views.py
@@ -38,7 +38,6 @@ _PROCESS_READY: subprocess.Popen | None = None
 _PROCESS_LOCK = threading.Lock()
 _SESSION_LOCK = threading.Lock()
 _LOGGER = logging.getLogger(__name__)
-_PROCESS_HEALTH_GRACE = 5
 _PROXY_PREFIX = "/admin/agent/opencode"
 _PROXY_PREFIX_REGEX = _PROXY_PREFIX.replace("/", r"\/")
 _PROXY_PREFIX_NO_SLASH_REGEX = _PROXY_PREFIX.lstrip("/").replace("/", r"\/")
@@ -383,11 +382,11 @@ def _owned_process_ready() -> bool:
     return process is not None and process is _PROCESS and process.poll() is None
 
 
-def _health(settings: dict, timeout: float = 2) -> bool:
+def _health(settings: dict) -> bool:
     try:
         response = requests.get(
             f"{settings['origin']}/global/health",
-            timeout=timeout,
+            timeout=2,
         )
         return response.status_code == 200
     except requests.RequestException:
@@ -413,23 +412,14 @@ def _ensure_opencode(settings: dict) -> tuple[bool, str]:
     workdir = settings["workdir"].resolve()
 
     with _PROCESS_LOCK:
-        if _owned_process_running():
-            deadline = time.monotonic() + min(_PROCESS_HEALTH_GRACE, settings["timeout"])
-            while _owned_process_running():
-                remaining = deadline - time.monotonic()
-                if remaining <= 0:
-                    break
-                if _health(settings, timeout=min(2, remaining)):
-                    if time.monotonic() <= deadline:
-                        _PROCESS_READY = _PROCESS
-                        return True, ""
-                    break
-                remaining = deadline - time.monotonic()
-                if remaining > 0:
-                    time.sleep(min(0.25, remaining))
-            _stop_owned_process(_PROCESS)
-        elif _health(settings):
+        if _owned_process_ready():
             return True, ""
+        if _health(settings):
+            if _owned_process_running():
+                _PROCESS_READY = _PROCESS
+            return True, ""
+        if _owned_process_running():
+            _stop_owned_process(_PROCESS)
 
         try:
             binary, git_binary, binary_env = _resolve_binary(
diff --git a/archivebox/tests/test_opencode_agent.py b/archivebox/tests/test_opencode_agent.py
index 65c21b27..0d81c15d 100644
--- a/archivebox/tests/test_opencode_agent.py
+++ b/archivebox/tests/test_opencode_agent.py
@@ -3,7 +3,6 @@ import os
 import signal
 import socket
 import subprocess
-import time
 from concurrent.futures import ThreadPoolExecutor
 from pathlib import Path
 from types import SimpleNamespace
@@ -128,13 +127,14 @@ def test_opencode_disabled_route_does_not_start_server(client, initialized_archi
     assert views._PROCESS is None or views._PROCESS.poll() is not None
 
 
-def test_stop_owned_process_falls_back_when_process_has_no_dedicated_group():
+def test_stop_owned_process_falls_back_for_stopped_process_without_dedicated_group():
     from archivebox.opencode import views
 
     process = subprocess.Popen(["sleep", "60"])
     try:
+        process.send_signal(signal.SIGSTOP)
         views._stop_owned_process(process)
-        assert process.poll() is not None
+        assert process.returncode == -signal.SIGTERM
     finally:
         if process.poll() is None:
             process.kill()
@@ -287,47 +287,19 @@ def test_concurrent_opencode_startup_waits_until_server_is_ready(live_opencode):
     assert views._health(live_opencode.settings)
 
 
-def test_opencode_restarts_an_unhealthy_owned_process(live_opencode):
+def test_opencode_does_not_probe_or_replace_a_ready_owned_process(live_opencode):
     from archivebox.opencode import views
 
-    old_process = views._PROCESS
+    process = views._PROCESS
     settings = {**live_opencode.settings, "port": _free_port()}
     settings["origin"] = f"http://{settings['host']}:{settings['port']}"
 
     ok, error = views._ensure_opencode(settings)
 
     assert ok, error
-    assert old_process is not None
-    assert old_process.poll() is not None
-    assert views._PROCESS is not old_process
-    assert views._health(settings)
-
-
-def test_opencode_preserves_a_transiently_unhealthy_owned_process(live_opencode):
-    from archivebox.opencode import views
-
-    process = views._PROCESS
     assert process is not None
-    views._signal_owned_process(process, signal.SIGSTOP)
-
-    def resume_process():
-        time.sleep(1.5)
-        views._signal_owned_process(process, signal.SIGCONT)
-
-    try:
-        with ThreadPoolExecutor(max_workers=1) as executor:
-            resumed = executor.submit(resume_process)
-            started_at = time.monotonic()
-            ok, error = views._ensure_opencode(live_opencode.settings)
-            elapsed = time.monotonic() - started_at
-            resumed.result()
-    finally:
-        views._signal_owned_process(process, signal.SIGCONT)
-
-    assert ok, error
     assert views._PROCESS is process
     assert process.poll() is None
-    assert elapsed < views._PROCESS_HEALTH_GRACE
 
 
 def test_opencode_proxy_does_not_wait_for_recovery_lock(admin_client, live_opencode):