test: stabilize archivebox ci shards

archivebox/tests/test_api_v1_cli_workflow_add_search_update_remove.py

@@ -114,6 +114,7 @@ def test_cli_api_add_search_update_remove_over_server(tmp_path):
                 "filter_patterns": [target_url],
                 "batch_size": 1,
                 "continuous": False,
+                "index_only": True,
             },
             timeout=20,
         )

archivebox/tests/test_config_SAVE_TITLE.py

@@ -1,3 +1,5 @@
+import time
+
 from archivebox.tests.conftest import run_archivebox_cmd, cli_env
 
 import pytest
@@ -25,26 +27,36 @@ def _install_chrome(tmp_path, env):
     assert install_process.returncode == 0, install_process.stderr or install_process.stdout
 
 
-def test_title_is_extracted(tmp_path, initialized_archive):
+def _wait_for_snapshot_title(data_dir, *, timeout=30):
+    deadline = time.time() + timeout
+    title = None
+    while time.time() < deadline:
+        with use_archivebox_db(data_dir):
+            title = Snapshot.objects.values_list("title", flat=True).get()
+        if title:
+            return title
+        time.sleep(0.5)
+    return title
+
+
+def test_title_is_extracted(tmp_path, initialized_archive, recursive_test_site):
     """Test that title is extracted from the page."""
     env = cli_env(disable_extractors=True)
     env.update({"SAVE_TITLE": "true"})
     _install_chrome(tmp_path, env)
     add_process = run_archivebox_cmd(
-        ["add", "--plugins=chrome,wget,title", "https://example.com"],
+        ["add", "--plugins=chrome,wget,title", recursive_test_site["root_url"]],
         cwd=tmp_path,
         env=env,
     )
     assert add_process.returncode == 0, add_process.stderr or add_process.stdout
 
-    with use_archivebox_db(tmp_path):
-        title = Snapshot.objects.values_list("title", flat=True).get()
-
+    title = _wait_for_snapshot_title(tmp_path)
     assert title is not None
-    assert "Example" in title
+    assert "Root" in title
 
 
-def test_title_is_listed_by_search_alias(tmp_path, initialized_archive):
+def test_title_is_listed_by_search_alias(tmp_path, initialized_archive, recursive_test_site):
     """
     https://github.com/ArchiveBox/ArchiveBox/issues/330
     Unencoded content should not be rendered as it facilitates xss injections
@@ -54,7 +66,7 @@ def test_title_is_listed_by_search_alias(tmp_path, initialized_archive):
     env.update({"SAVE_TITLE": "true"})
     _install_chrome(tmp_path, env)
     add_process = run_archivebox_cmd(
-        ["add", "--plugins=chrome,wget,title", "https://example.com"],
+        ["add", "--plugins=chrome,wget,title", recursive_test_site["root_url"]],
         cwd=tmp_path,
         env=env,
     )
@@ -67,4 +79,4 @@ def test_title_is_listed_by_search_alias(tmp_path, initialized_archive):
     assert list_process.returncode == 0, list_process.stderr or list_process.stdout
 
     output = list_process.stdout
-    assert "https://example.com" in output
+    assert recursive_test_site["root_url"] in output

archivebox/tests/test_machine_service.py

@@ -41,6 +41,8 @@ def _runtime_env(data_dir: Path, bin_dir: Path) -> dict[str, str]:
         "LIB_BIN_DIR": str(data_dir / "lib" / "bin"),
         "ABXPKG_LIB_DIR": str(data_dir / "lib"),
         "LITEPARSE_ENABLED": "True",
+        "TIMEOUT": "180",
+        "ABXPKG_INSTALL_TIMEOUT": "180",
         "PATH": os.pathsep.join(entry for entry in path_entries if entry),
     }
 
@@ -55,7 +57,7 @@ def test_install_persists_machine_binary_config_and_recovers_stale_path(initiali
     _cmd_result = run_archivebox_cmd(
         ["install", "--binproviders=env", "liteparse"],
         cwd=initialized_archive,
-        timeout=120,
+        timeout=240,
         env=_runtime_env(initialized_archive, bootstrap_bin_dir),
     )
     stdout, stderr, returncode = _cmd_result.stdout, _cmd_result.stderr, _cmd_result.returncode