Skip to content

armgit / codex

Public Imported from GitHub
0

Lightweight coding agent that runs in your terminal

Rust

Balance Windows Bazel test shards using duration estimates (#49103)

jgershen-oai7e049b3eaa17
diff --git a/.github/scripts/select_windows_bazel_targets.py b/.github/scripts/select_windows_bazel_targets.py
new file mode 100644
index 0000000000..226bd70402
--- /dev/null
+++ b/.github/scripts/select_windows_bazel_targets.py
@@ -0,0 +1,103 @@
+#!/usr/bin/env python3
+
+"""Assign Windows Bazel test targets using checked-in duration estimates."""
+
+import argparse
+import sys
+from pathlib import Path
+
+
+DEFAULT_DURATION_SECONDS = 1
+DURATIONS_PATH = Path(__file__).with_name("windows_bazel_test_durations.tsv")
+
+
+def read_durations(path: Path) -> dict[str, int]:
+ durations = {}
+ for line_number, line in enumerate(
+ path.read_text(encoding="utf-8").splitlines(), 1
+ ):
+ if not line.strip() or line.lstrip().startswith("#"):
+ continue
+ fields = line.split("\t")
+ if len(fields) != 2 or not fields[0] or not fields[1].isdecimal():
+ raise ValueError(
+ f"{path}:{line_number}: expected target<TAB>positive integer"
+ )
+ target, duration_text = fields
+ duration = int(duration_text)
+ if duration < 1:
+ raise ValueError(f"{path}:{line_number}: duration must be positive")
+ if target in durations:
+ raise ValueError(f"{path}:{line_number}: duplicate target {target}")
+ durations[target] = duration
+ return durations
+
+
+def assign_targets(
+ targets: list[str], durations: dict[str, int], shard_count: int
+) -> tuple[list[list[str]], list[int]]:
+ if shard_count < 1:
+ raise ValueError("shard count must be positive")
+ if not targets:
+ raise ValueError("no Bazel test targets were provided")
+ if any(not target.strip() for target in targets):
+ raise ValueError("Bazel test target labels must not be empty")
+ if len(targets) != len(set(targets)):
+ raise ValueError("duplicate Bazel test target labels were provided")
+
+ assignments: list[list[str]] = [[] for _ in range(shard_count)]
+ loads = [0] * shard_count
+ # Place the longest targets first, breaking ties by label and shard number.
+ for target in sorted(
+ targets,
+ key=lambda target: (-durations.get(target, DEFAULT_DURATION_SECONDS), target),
+ ):
+ shard = min(range(shard_count), key=lambda shard: (loads[shard], shard))
+ assignments[shard].append(target)
+ loads[shard] += durations.get(target, DEFAULT_DURATION_SECONDS)
+ for assignment in assignments:
+ assignment.sort()
+ return assignments, loads
+
+
+def main() -> None:
+ parser = argparse.ArgumentParser(description=__doc__)
+ parser.add_argument("--shard", required=True, type=int)
+ parser.add_argument("--shard-count", required=True, type=int)
+ parser.add_argument(
+ "--durations",
+ type=Path,
+ default=DURATIONS_PATH,
+ help="use this timing file instead of the checked-in default",
+ )
+ args = parser.parse_args()
+ if not 1 <= args.shard <= args.shard_count:
+ parser.error("shard must be between 1 and shard count")
+
+ try:
+ durations = read_durations(args.durations)
+ targets = sys.stdin.read().splitlines()
+ assignments, loads = assign_targets(targets, durations, args.shard_count)
+ except (OSError, ValueError) as error:
+ parser.error(str(error))
+
+ selected_targets = assignments[args.shard - 1]
+ if not selected_targets:
+ parser.error(
+ f"no Bazel test targets selected for shard {args.shard}/{args.shard_count}"
+ )
+
+ target_set = set(targets)
+ print(
+ f"Windows Bazel shards: targets={[len(assignment) for assignment in assignments]}, "
+ f"estimated test-seconds={loads}, default weights={len(target_set - durations.keys())}, "
+ f"unused weights={len(durations.keys() - target_set)}. "
+ f"Selected shard {args.shard}/{args.shard_count}.",
+ file=sys.stderr,
+ )
+ # Keep LF delimiters when native Windows Python feeds Git Bash mapfile.
+ sys.stdout.buffer.write(("\n".join(selected_targets) + "\n").encode("utf-8"))
+
+
+if __name__ == "__main__":
+ main()
diff --git a/.github/scripts/test_select_windows_bazel_targets.py b/.github/scripts/test_select_windows_bazel_targets.py
new file mode 100644
index 0000000000..0c708ba4c5
--- /dev/null
+++ b/.github/scripts/test_select_windows_bazel_targets.py
@@ -0,0 +1,147 @@
+import subprocess
+import sys
+import tempfile
+import unittest
+from pathlib import Path
+
+from select_windows_bazel_targets import DURATIONS_PATH
+from select_windows_bazel_targets import assign_targets
+from select_windows_bazel_targets import read_durations
+
+
+class SelectWindowsBazelTargetsTest(unittest.TestCase):
+ def test_balances_targets_with_complete_deterministic_coverage(self) -> None:
+ durations = {
+ f"//test:{name}": duration
+ for name, duration in zip("abcdefgh", range(8, 0, -1))
+ }
+ targets = list(durations)
+
+ assignments, loads = assign_targets(targets, durations, 4)
+
+ self.assertEqual(loads, [9, 9, 9, 9])
+ self.assertEqual(
+ sorted(target for shard in assignments for target in shard), sorted(targets)
+ )
+ self.assertEqual(
+ assign_targets(list(reversed(targets)), durations, 4), (assignments, loads)
+ )
+ self.assertTrue(all(shard == sorted(shard) for shard in assignments))
+
+ def test_missing_weights_use_one_and_unused_weights_do_not_create_targets(
+ self,
+ ) -> None:
+ targets = ["//test:c", "//test:a", "//test:b"]
+
+ assignments, loads = assign_targets(targets, {"//test:stale": 100}, 2)
+
+ self.assertEqual(assignments, [["//test:a", "//test:c"], ["//test:b"]])
+ self.assertEqual(loads, [2, 1])
+
+ def test_rejects_empty_or_duplicate_target_input(self) -> None:
+ for targets in ([], [""], ["//test:a", "//test:a"]):
+ with self.subTest(targets=targets), self.assertRaises(ValueError):
+ assign_targets(targets, {}, 4)
+
+ def test_reads_duration_file_and_rejects_invalid_weights(self) -> None:
+ with tempfile.TemporaryDirectory() as temp_dir:
+ path = Path(temp_dir) / "durations.tsv"
+ path.write_text(
+ "# comment\n\n//test:a\t12\n//test:b\t1\n", encoding="utf-8"
+ )
+ self.assertEqual(read_durations(path), {"//test:a": 12, "//test:b": 1})
+
+ for contents in (
+ "//test:a 12\n",
+ "//test:a\t0\n",
+ "//test:a\t-1\n",
+ "//test:a\t1.5\n",
+ "//test:a\t1\n//test:a\t2\n",
+ ):
+ with self.subTest(contents=contents), self.assertRaises(ValueError):
+ path.write_text(contents, encoding="utf-8")
+ read_durations(path)
+
+ def test_cli_uses_checked_in_weights_and_writes_only_lf_delimited_targets(
+ self,
+ ) -> None:
+ durations = read_durations(DURATIONS_PATH)
+ known = sorted(durations, key=lambda target: (-durations[target], target))[:4]
+ self.assertEqual(len(known), 4)
+ targets = [*known, "//test:new-target"]
+ expected, _ = assign_targets(targets, durations, 4)
+ script = DURATIONS_PATH.with_name("select_windows_bazel_targets.py")
+
+ for shard, assignment in enumerate(expected, 1):
+ command = [
+ sys.executable,
+ str(script),
+ "--shard",
+ str(shard),
+ "--shard-count",
+ "4",
+ ]
+ for ordered_targets in (targets, list(reversed(targets))):
+ with self.subTest(shard=shard, ordered_targets=ordered_targets):
+ result = subprocess.run(
+ command,
+ input=("\r\n".join(ordered_targets) + "\r\n").encode(),
+ capture_output=True,
+ check=True,
+ )
+ self.assertEqual(
+ result.stdout, ("\n".join(assignment) + "\n").encode()
+ )
+ self.assertIn(b"default weights=1", result.stderr)
+
+ def test_cli_uses_only_the_requested_duration_file(self) -> None:
+ script = DURATIONS_PATH.with_name("select_windows_bazel_targets.py").resolve()
+ with tempfile.TemporaryDirectory() as temp_dir:
+ path = Path(temp_dir) / "durations.tsv"
+ path.write_text("//test:a\t1\n//test:b\t9\n", encoding="utf-8")
+ command = [sys.executable, str(script), "--shard-count", "2"]
+ for shard, expected in ((1, b"//test:b\n"), (2, b"//test:a\n//test:c\n")):
+ with self.subTest(shard=shard):
+ result = subprocess.run(
+ [*command, "--shard", str(shard), "--durations", path.name],
+ input=b"//test:a\n//test:b\n//test:c\n",
+ cwd=temp_dir,
+ capture_output=True,
+ check=True,
+ )
+ self.assertEqual(result.stdout, expected)
+ self.assertIn(b"estimated test-seconds=[9, 2]", result.stderr)
+ self.assertIn(b"unused weights=0", result.stderr)
+
+ result = subprocess.run(
+ [*command, "--shard", "1", "--durations", "missing.tsv"],
+ input=b"//test:a\n",
+ cwd=temp_dir,
+ capture_output=True,
+ check=False,
+ )
+ self.assertNotEqual(result.returncode, 0)
+ self.assertEqual(result.stdout, b"")
+ self.assertIn(b"missing.tsv", result.stderr)
+
+ def test_cli_rejects_bad_or_empty_selection_without_partial_output(self) -> None:
+ script = DURATIONS_PATH.with_name("select_windows_bazel_targets.py")
+ for targets, error in (
+ (b"", b"no Bazel test targets were provided"),
+ (b"//test:a\n//test:a\n", b"duplicate Bazel test target labels"),
+ (b"//test:a\n", b"no Bazel test targets selected for shard 2/2"),
+ ):
+ with self.subTest(targets=targets):
+ result = subprocess.run(
+ [sys.executable, str(script), "--shard", "2", "--shard-count", "2"],
+ input=targets,
+ capture_output=True,
+ check=False,
+ )
+ self.assertNotEqual(result.returncode, 0)
+ self.assertEqual(result.stdout, b"")
+ self.assertIn(error, result.stderr)
+
+
+if __name__ == "__main__":
+ unittest.main()
diff --git a/.github/scripts/windows_bazel_test_durations.tsv b/.github/scripts/windows_bazel_test_durations.tsv
new file mode 100644
index 0000000000..32bcc24783
--- /dev/null
+++ b/.github/scripts/windows_bazel_test_durations.tsv
@@ -0,0 +1,253 @@
+# Windows Bazel duration weights; columns: target<TAB>seconds.
+# Seeded from 24 successful public openai/codex Windows job logs across six main
+# runs, September 21-23, 2026. Public GitHub Actions run IDs:
+# 35638529858, 35665540272, 35694732932, 35912411800, 35919297566, 35924169500.
+# To refresh, take the median summed inner-run time (N * average) from clean,
+# uncached PASSED summaries, excluding partial cache hits and FLAKY results.
+# Round up to positive integer seconds. These weights exclude build/download time.
+# Every queried target is assigned; missing weights default to 1 and stale entries are ignored.
+//codex-rs/agent-graph-store:agent-graph-store-unit-tests 76
+//codex-rs/agent-identity:agent-identity-unit-tests 66
+//codex-rs/agent-roles:agent-roles-unit-tests 48
+//codex-rs/analytics:analytics-unit-tests 29
+//codex-rs/app-server-client:app-server-client-unit-tests 51
+//codex-rs/app-server-daemon:app-server-daemon-unit-tests 4
+//codex-rs/app-server-protocol:app-server-protocol-unit-tests 19
+//codex-rs/app-server-test-client:app-server-test-client-unit-tests 25
+//codex-rs/app-server-test-client:codex-app-server-test-client-bin-unit-tests 1
+//codex-rs/app-server-transport:app-server-transport-unit-tests 65
+//codex-rs/app-server/tests/common:common-unit-tests 26
+//codex-rs/app-server:app-server-all-test-windows-cross 2835
+//codex-rs/app-server:app-server-unit-tests 399
+//codex-rs/app-server:codex-app-server-bin-unit-tests 48
+//codex-rs/app-server:codex-app-server-test-notify-capture-bin-unit-tests 1
+//codex-rs/app-server:exec-server-bin-unit-tests 1
+//codex-rs/app-server:test_notify_capture-bin-unit-tests 1
+//codex-rs/apply-patch:apply-patch-all-test-windows-cross 50
+//codex-rs/apply-patch:apply-patch-unit-tests 48
+//codex-rs/apply-patch:apply_patch-bin-unit-tests 24
+//codex-rs/arg0:arg0-unit-tests 24
+//codex-rs/backend-client:backend-client-unit-tests 41
+//codex-rs/chatgpt:chatgpt-all-test-windows-cross 26
+//codex-rs/chatgpt:chatgpt-unit-tests 27
+//codex-rs/cli:cli-app_server-test-windows-cross 3
+//codex-rs/cli:cli-app_server_daemon-test-windows-cross 1
+//codex-rs/cli:cli-cloud_auth-test-windows-cross 47
+//codex-rs/cli:cli-cloud_config-test-windows-cross 3
+//codex-rs/cli:cli-daemon_startup-test-windows-cross 4
+//codex-rs/cli:cli-daemon_telemetry-test-windows-cross 1
+//codex-rs/cli:cli-debug_clear_memories-test-windows-cross 4
+//codex-rs/cli:cli-debug_models-test-windows-cross 2
+//codex-rs/cli:cli-delete-test-windows-cross 2
+//codex-rs/cli:cli-doctor_enterprise_network-test-windows-cross 3
+//codex-rs/cli:cli-doctor_path_safety-test-windows-cross 47
+//codex-rs/cli:cli-exec_server-test-windows-cross 39
+//codex-rs/cli:cli-exec_server_websocket_auth-test-windows-cross 4
+//codex-rs/cli:cli-execpolicy-test-windows-cross 2
+//codex-rs/cli:cli-features-test-windows-cross 3
+//codex-rs/cli:cli-login-test-windows-cross 4
+//codex-rs/cli:cli-marketplace_add-test-windows-cross 2
+//codex-rs/cli:cli-marketplace_remove-test-windows-cross 1
+//codex-rs/cli:cli-marketplace_upgrade-test-windows-cross 2
+//codex-rs/cli:cli-mcp_add_remove-test-windows-cross 3
+//codex-rs/cli:cli-mcp_list-test-windows-cross 2
+//codex-rs/cli:cli-mcp_login-test-windows-cross 2
+//codex-rs/cli:cli-plugin_cli-test-windows-cross 7
+//codex-rs/cli:cli-queue-test-windows-cross 1
+//codex-rs/cli:cli-sandbox_cloud_config-test-windows-cross 48
+//codex-rs/cli:cli-sandbox_network_proxy-test-windows-cross 1
+//codex-rs/cli:cli-sandbox_tty-test-windows-cross 1
+//codex-rs/cli:cli-unit-tests 2
+//codex-rs/cli:cli-update-test-windows-cross 47
+//codex-rs/cli:cli-worktree-test-windows-cross 12
+//codex-rs/cli:codex-bin-unit-tests 60
+//codex-rs/cli:logs_client-bin-unit-tests 1
+//codex-rs/cloud-config:cloud-config-unit-tests 47
+//codex-rs/cloud-tasks-client:cloud-tasks-client-unit-tests 35
+//codex-rs/cloud-tasks-mock-client:cloud-tasks-mock-client-unit-tests 59
+//codex-rs/cloud-tasks:cloud-tasks-env_filter-test-windows-cross 1
+//codex-rs/cloud-tasks:cloud-tasks-unit-tests 1
+//codex-rs/code-mode-host:code-mode-host-grpc-test-windows-cross 28
+//codex-rs/code-mode-host:code-mode-host-grpc_notifications-test-windows-cross 25
+//codex-rs/code-mode-host:code-mode-host-grpc_tcp-test-windows-cross 1
+//codex-rs/code-mode-host:code-mode-host-grpc_timing-test-windows-cross 7
+//codex-rs/code-mode-host:code-mode-host-stdio-test-windows-cross 11
+//codex-rs/code-mode-host:code-mode-host-unit-tests 2
+//codex-rs/code-mode-host:codex-code-mode-host-bin-unit-tests 1
+//codex-rs/code-mode-protocol:code-mode-protocol-unit-tests 62
+//codex-rs/code-mode-runtime:code-mode-runtime-array_sort-test-windows-cross 24
+//codex-rs/code-mode-runtime:code-mode-runtime-jit-test-windows-cross 1
+//codex-rs/code-mode-runtime:code-mode-runtime-unit-tests 7
+//codex-rs/code-mode:code-mode-unit-tests 49
+//codex-rs/codex-api:codex-api-clients-test-windows-cross 75
+//codex-rs/codex-api:codex-api-models_integration-test-windows-cross 66
+//codex-rs/codex-api:codex-api-realtime_websocket_e2e-test-windows-cross 63
+//codex-rs/codex-api:codex-api-realtime_websocket_tls-test-windows-cross 66
+//codex-rs/codex-api:codex-api-sse_end_to_end-test-windows-cross 48
+//codex-rs/codex-api:codex-api-unit-tests 60
+//codex-rs/codex-home:codex-home-unit-tests 13
+//codex-rs/codex-mcp:codex-mcp-unit-tests 61
+//codex-rs/config-schema:codex-write-config-schema-bin-unit-tests 48
+//codex-rs/config:config-unit-tests 75
+//codex-rs/connectors:connectors-unit-tests 39
+//codex-rs/context-fragments:context-fragments-unit-tests 59
+//codex-rs/core-api:core-api-unit-tests 1
+//codex-rs/core-plugins:core-plugins-unit-tests 20
+//codex-rs/core/tests/common:common-unit-tests 48
+//codex-rs/core:core-all-test-windows-cross 3162
+//codex-rs/core:core-mcp_trace_propagation-test-windows-cross 2
+//codex-rs/core:core-responses_headers-test-windows-cross 5
+//codex-rs/core:core-unit-tests 251
+//codex-rs/exec-server-protocol:exec-server-protocol-unit-tests 48
+//codex-rs/exec-server/tests/support:support-unit-tests 48
+//codex-rs/exec-server:exec-server-accepted_websocket-test-windows-cross 1
+//codex-rs/exec-server:exec-server-capability_discovery-test-windows-cross 1
+//codex-rs/exec-server:exec-server-chatgpt_cloudflare_affinity-test-windows-cross 1
+//codex-rs/exec-server:exec-server-deferred_environment-test-windows-cross 1
+//codex-rs/exec-server:exec-server-environment-test-windows-cross 10
+//codex-rs/exec-server:exec-server-environment_config-test-windows-cross 1
+//codex-rs/exec-server:exec-server-exec_process-test-windows-cross 1
+//codex-rs/exec-server:exec-server-file_stream-test-windows-cross 1
+//codex-rs/exec-server:exec-server-file_system_unix-test-windows-cross 1
+//codex-rs/exec-server:exec-server-file_system_windows-test-windows-cross 11
+//codex-rs/exec-server:exec-server-forward-test-windows-cross 10
+//codex-rs/exec-server:exec-server-health-test-windows-cross 1
+//codex-rs/exec-server:exec-server-http_client-test-windows-cross 2
+//codex-rs/exec-server:exec-server-http_request-test-windows-cross 1
+//codex-rs/exec-server:exec-server-http_request_logging-test-windows-cross 3
+//codex-rs/exec-server:exec-server-initialize-test-windows-cross 1
+//codex-rs/exec-server:exec-server-macos_fs_spawn-test-windows-cross 1
+//codex-rs/exec-server:exec-server-process-test-windows-cross 4
+//codex-rs/exec-server:exec-server-relay-test-windows-cross 8
+//codex-rs/exec-server:exec-server-selected_capability_roots-test-windows-cross 1
+//codex-rs/exec-server:exec-server-unit-tests 116
+//codex-rs/exec-server:exec-server-websocket-test-windows-cross 1
+//codex-rs/exec:codex-exec-bin-unit-tests 1
+//codex-rs/exec:exec-all-test-windows-cross 331
+//codex-rs/exec:exec-event_processor_with_json_output-test-windows-cross 1
+//codex-rs/exec:exec-unit-tests 47
+//codex-rs/ext/agent-message-board:agent-message-board-local_board-test-windows-cross 46
+//codex-rs/ext/agent-message-board:agent-message-board-unit-tests 30
+//codex-rs/ext/agent:agent-agent_service-test-windows-cross 3
+//codex-rs/ext/agent:agent-unit-tests 1
+//codex-rs/ext/connectors:connectors-unit-tests 47
+//codex-rs/ext/extension-api:extension-api-capabilities-test-windows-cross 14
+//codex-rs/ext/extension-api:extension-api-registry-test-windows-cross 31
+//codex-rs/ext/extension-api:extension-api-state-test-windows-cross 57
+//codex-rs/ext/extension-api:extension-api-unit-tests 35
+//codex-rs/ext/git-attribution:git-attribution-unit-tests 30
+//codex-rs/ext/goal:goal-accounting-test-windows-cross 1
+//codex-rs/ext/goal:goal-goal_extension_backend-test-windows-cross 9
+//codex-rs/ext/goal:goal-steering-test-windows-cross 1
+//codex-rs/ext/goal:goal-unit-tests 47
+//codex-rs/ext/guardian-reviewer:guardian-reviewer-unit-tests 36
+//codex-rs/ext/guardian-v2:guardian-v2-unit-tests 50
+//codex-rs/ext/history-notes:history-notes-history_notes_extension-test-windows-cross 1
+//codex-rs/ext/history-notes:history-notes-image_model_input-test-windows-cross 2
+//codex-rs/ext/history-notes:history-notes-unit-tests 1
+//codex-rs/ext/image-generation:image-generation-unit-tests 47
+//codex-rs/ext/mcp:mcp-hosted_apps_mcp-test-windows-cross 26
+//codex-rs/ext/mcp:mcp-plugin_mcp-test-windows-cross 5
+//codex-rs/ext/mcp:mcp-unit-tests 48
+//codex-rs/ext/memories:memories-unit-tests 28
+//codex-rs/ext/queue:queue-queue_service-test-windows-cross 9
+//codex-rs/ext/queue:queue-unit-tests 25
+//codex-rs/ext/skills:skills-executor_file_system_authority-test-windows-cross 36
+//codex-rs/ext/skills:skills-skills_extension-test-windows-cross 7
+//codex-rs/ext/skills:skills-unit-tests 8
+//codex-rs/ext/web-search:web-search-unit-tests 1
+//codex-rs/external-agent-migration:external-agent-migration-unit-tests 4
+//codex-rs/features:features-unit-tests 47
+//codex-rs/feedback:feedback-unit-tests 77
+//codex-rs/file-system:file-system-unit-tests 48
+//codex-rs/git-utils:git-utils-unit-tests 83
+//codex-rs/guardian-context:guardian-context-cache_prefix-test-windows-cross 66
+//codex-rs/guardian-context:guardian-context-unit-tests 67
+//codex-rs/history:history-unit-tests 59
+//codex-rs/hooks:hooks-unit-tests 16
+//codex-rs/hooks:write_hooks_schema_fixtures-bin-unit-tests 48
+//codex-rs/lmstudio:lmstudio-unit-tests 1
+//codex-rs/login:login-all-test-windows-cross 5
+//codex-rs/login:login-unit-tests 320
+//codex-rs/memories/read:read-unit-tests 62
+//codex-rs/memories/write:write-unit-tests 20
+//codex-rs/message-history:message-history-unit-tests 74
+//codex-rs/model-provider-info:model-provider-info-unit-tests 63
+//codex-rs/model-provider:model-provider-unit-tests 64
+//codex-rs/models-manager:models-manager-unit-tests 35
+//codex-rs/mxc-sandbox:mxc-sandbox-unit-tests 36
+//codex-rs/network-proxy:codex-network-proxy-bin-unit-tests 48
+//codex-rs/network-proxy:network-proxy-unit-tests 85
+//codex-rs/network-proxy:network-proxy-windows_stable_ingress-test-windows-cross 37
+//codex-rs/ollama:ollama-unit-tests 1
+//codex-rs/otel:otel-tests-test-windows-cross 17
+//codex-rs/otel:otel-unit-tests 48
+//codex-rs/plugin:plugin-unit-tests 74
+//codex-rs/prompts:prompts-unit-tests 62
+//codex-rs/protocol:protocol-unit-tests 67
+//codex-rs/response-debug-context:response-debug-context-unit-tests 66
+//codex-rs/rmcp-client:rmcp-client-foreign_stdio_cwd-test-windows-cross 48
+//codex-rs/rmcp-client:rmcp-client-mcp_2026_discovery-test-windows-cross 4
+//codex-rs/rmcp-client:rmcp-client-mcp_2026_message_limits-test-windows-cross 4
+//codex-rs/rmcp-client:rmcp-client-mcp_2026_mrtr-test-windows-cross 2
+//codex-rs/rmcp-client:rmcp-client-mcp_2026_oauth_discovery-test-windows-cross 1
+//codex-rs/rmcp-client:rmcp-client-mcp_2026_sse_discovery-test-windows-cross 1
+//codex-rs/rmcp-client:rmcp-client-mcp_2026_stdio-test-windows-cross 39
+//codex-rs/rmcp-client:rmcp-client-mcp_2026_stdio_discovery-test-windows-cross 2
+//codex-rs/rmcp-client:rmcp-client-mcp_events-test-windows-cross 2
+//codex-rs/rmcp-client:rmcp-client-process_group_cleanup-test-windows-cross 1
+//codex-rs/rmcp-client:rmcp-client-resources-test-windows-cross 1
+//codex-rs/rmcp-client:rmcp-client-stdio_descriptor_boundary-test-windows-cross 1
+//codex-rs/rmcp-client:rmcp-client-stdio_message_limits-test-windows-cross 3
+//codex-rs/rmcp-client:rmcp-client-stdio_stderr_cleanup-test-windows-cross 1
+//codex-rs/rmcp-client:rmcp-client-streamable_http_oauth_startup-test-windows-cross 6
+//codex-rs/rmcp-client:rmcp-client-streamable_http_oauth_store_pinning-test-windows-cross 38
+//codex-rs/rmcp-client:rmcp-client-streamable_http_oauth_tool_call-test-windows-cross 2
+//codex-rs/rmcp-client:rmcp-client-streamable_http_recovery-test-windows-cross 51
+//codex-rs/rmcp-client:rmcp-client-streamable_http_remote-test-windows-cross 3
+//codex-rs/rmcp-client:rmcp-client-streamable_http_test_support-test-windows-cross 1
+//codex-rs/rmcp-client:rmcp-client-streamable_http_user_agent-test-windows-cross 1
+//codex-rs/rmcp-client:rmcp-client-unit-tests 50
+//codex-rs/rmcp-client:rmcp_test_server-bin-unit-tests 39
+//codex-rs/rmcp-client:test_mcp_2026_discovery_stdio_server-bin-unit-tests 43
+//codex-rs/rmcp-client:test_mcp_2026_stdio_server-bin-unit-tests 25
+//codex-rs/rmcp-client:test_stdio_server-bin-unit-tests 41
+//codex-rs/rmcp-client:test_streamable_http_server-bin-unit-tests 40
+//codex-rs/rollout-trace:rollout-trace-unit-tests 76
+//codex-rs/rollout:rollout-unit-tests 56
+//codex-rs/sandboxing:sandboxing-unit-tests 74
+//codex-rs/secrets:secrets-unit-tests 57
+//codex-rs/shell-command:shell-command-unit-tests 60
+//codex-rs/shell-escalation:codex-execve-wrapper-bin-unit-tests 62
+//codex-rs/shell-escalation:shell-escalation-unit-tests 60
+//codex-rs/skills:skills-unit-tests 59
+//codex-rs/state:state-unit-tests 242
+//codex-rs/test-binary-support:test-binary-support-unit-tests 48
+//codex-rs/thread-manager-sample:codex-thread-manager-sample-bin-unit-tests 47
+//codex-rs/thread-store:thread-store-unit-tests 95
+//codex-rs/tools:tools-json_schema_policy_fixtures-test-windows-cross 34
+//codex-rs/tools:tools-unit-tests 37
+//codex-rs/tui:codex-tui-bin-unit-tests 2
+//codex-rs/tui:md-events-bin-unit-tests 1
+//codex-rs/tui:tui-all-test-windows-cross 36
+//codex-rs/tui:tui-manager_dependency_regression-test-windows-cross 2
+//codex-rs/tui:tui-test_backend-test-windows-cross 25
+//codex-rs/tui:tui-unit-tests 1003
+//codex-rs/utils/approval-presets:approval-presets-unit-tests 66
+//codex-rs/utils/audio:audio-unit-tests 76
+//codex-rs/utils/cli:cli-unit-tests 64
+//codex-rs/utils/git-discovery:git-discovery-unit-tests 59
+//codex-rs/utils/oss:oss-unit-tests 1
+//codex-rs/utils/output-truncation:output-truncation-unit-tests 60
+//codex-rs/utils/plugins:plugins-unit-tests 36
+//codex-rs/utils/sandbox-summary:sandbox-summary-unit-tests 66
+//codex-rs/windows-sandbox-rs:codex-command-runner-bin-unit-tests 1
+//codex-rs/windows-sandbox-rs:codex-windows-managed-deny-probe-bin-unit-tests 1
+//codex-rs/windows-sandbox-rs:codex-windows-sandbox-setup-bin-unit-tests 1
+//codex-rs/windows-sandbox-rs:windows-sandbox-rs-helper_manifest-test-windows-cross 1
+//codex-rs/windows-sandbox-rs:windows-sandbox-rs-unit-tests 23
+//codex-rs/windows-sandbox-service:codex-windows-sandbox-service-bin-unit-tests 46
+//codex-rs/windows-sandbox-service:windows-sandbox-service-unit-tests 12
+//codex-rs/worktree:worktree-settings-test-windows-cross 59
+//codex-rs/worktree:worktree-unit-tests 76
+//codex-rs/worktree:worktree-worktree-test-windows-cross 92
diff --git a/.github/workflows/bazel.yml b/.github/workflows/bazel.yml
index 568086a93d..ede5a7f070 100644
--- a/.github/workflows/bazel.yml
+++ b/.github/workflows/bazel.yml
@@ -160,6 +160,11 @@ jobs:
shell: pwsh
run: python .github/scripts/test_run_bazel_with_buildbuddy.py
+ - name: Test Windows Bazel target selector
+ if: matrix.shard == 1
+ shell: pwsh
+ run: python -m unittest discover -s .github/scripts -p test_select_windows_bazel_targets.py
+
- name: Prepare Bazel CI
id: prepare_bazel
uses: ./.github/actions/prepare-bazel-ci
@@ -180,29 +185,19 @@ jobs:
set -euo pipefail
bazel_test_query='tests(//...) except tests(//third_party/v8:all) except attr(tags, "manual", tests(//...))'
- mapfile -t bazel_targets < <(
- ./.github/scripts/run-bazel-query-ci.sh --output=label -- "${bazel_test_query}" \
- | LC_ALL=C sort
- )
-
- selected_targets=()
- for bazel_target in "${bazel_targets[@]}"; do
- target_bucket="$(
- printf '%s\n' "${bazel_target}" \
- | cksum \
- | awk -v shard_count="${BAZEL_TEST_SHARD_COUNT}" '{ print ($1 % shard_count) + 1 }'
- )"
- if [[ "${target_bucket}" == "${BAZEL_TEST_SHARD}" ]]; then
- selected_targets+=("${bazel_target}")
- fi
- done
-
- if [[ ${#selected_targets[@]} -eq 0 ]]; then
- echo "No Bazel test targets selected for Windows shard ${BAZEL_TEST_SHARD}/${BAZEL_TEST_SHARD_COUNT}." >&2
- exit 1
- fi
-
- echo "Selected ${#selected_targets[@]} of ${#bazel_targets[@]} Bazel test targets for Windows shard ${BAZEL_TEST_SHARD}/${BAZEL_TEST_SHARD_COUNT}."
+ bazel_targets_file="$(mktemp)"
+ selected_targets_file="$(mktemp)"
+ trap 'rm -f "${bazel_targets_file}" "${selected_targets_file}"' EXIT
+
+ # Keep query and selection in the foreground so failures cannot leave
+ # different jobs assigning different partial target lists.
+ ./.github/scripts/run-bazel-query-ci.sh --output=label -- "${bazel_test_query}" \
+ | LC_ALL=C sort > "${bazel_targets_file}"
+ python .github/scripts/select_windows_bazel_targets.py \
+ --shard "${BAZEL_TEST_SHARD}" \
+ --shard-count "${BAZEL_TEST_SHARD_COUNT}" \
+ < "${bazel_targets_file}" > "${selected_targets_file}"
+ mapfile -t selected_targets < "${selected_targets_file}"
bazel_test_args=(
test