From a89d3a3b64e698f07a4c29d49211a253da8ace29 Mon Sep 17 00:00:00 2001
From: Golo Roden <golo.roden@thenativeweb.io>
Date: Sat, 1 Aug 2026 10:48:21 +0200
Subject: [PATCH] fix: pull the container image only once per process

Container.start() pulled the image from the registry on every single
call. Since each test gets its own container, a full test run made 77
registry round trips for an image that was already local -- 91 of 156
seconds, 58% of the total runtime.

That also made the suite flaky. Pull latency is normally ~1.1s, but
outliers of up to 15.5s showed up in two of four measured runs, and
pytest allows 30s for setup, test and teardown combined. Two runs failed
with a setup time of exactly 30.01s, hitting different tests each time.
Docker Hub allows 100 anonymous requests per hour and source IP, so a
single run already consumes 77% of that budget.

Remember which images were pulled in this process, so the first start
pulls and every later one reuses the local image. Runtime drops from
~156s to ~64s, and the slowest setup from 15.78s to 1.84s.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01F3ADPwk11GHQF7BBwQHaPz
---
 eventsourcingdb/container.py | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/eventsourcingdb/container.py b/eventsourcingdb/container.py
index 3be6b9b..484b9b9 100644
--- a/eventsourcingdb/container.py
+++ b/eventsourcingdb/container.py
@@ -3,6 +3,7 @@
 import tarfile
 import time
 from http import HTTPStatus
+from typing import ClassVar
 
 import docker
 import requests
@@ -16,6 +17,10 @@
 
 
 class Container:
+    # Images already pulled in this process. Every container start would
+    # otherwise hit the registry again, even though the image is local.
+    _pulled_images: ClassVar[set[str]] = set()
+
     def __init__(
         self,
     ) -> None:
@@ -191,11 +196,18 @@ def start(self) -> "Container":
         return self
 
     def _pull_or_get_image(self) -> None:
+        image = f"{self._image_name}:{self._image_tag}"
+
+        if image in Container._pulled_images:
+            return
+
         try:
             self._docker_client.images.pull(self._image_name, self._image_tag)
         except errors.APIError as e:
             self._handle_image_pull_error(e)
 
+        Container._pulled_images.add(image)
+
     def _handle_image_pull_error(self, error) -> None:
         image_name = f"{self._image_name}:{self._image_tag}"
         try: