mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
6b81590c55
Systematic prune per AGENTS.md test policy, one pass over every major test tree (gateway, hermes_cli, tools, agent, run_agent, plugins, cli, cron, tui_gateway, honcho/openviking, root-level): - DELETE: source-reading tests (read_text/getsource on prod files), change-detector tests (exact catalog counts, model-name snapshots, config version literals), mock-echo tests (assert a mock returns what it was told), assertion-free/trivial tests, near-duplicate parametrizations (boundaries + one representative kept), async/sync twin duplicates, cosmetic within-file variations. - KEEP (mandatory): security/redaction/approval guards, message-role alternation invariants, prompt-caching/deterministic-call-id invariants, issue-number regression tests (deduped), E2E tests. - 6 test files deleted outright (script-style/no-assert or fully redundant); conftest.py, fakes/, fixtures/ untouched. - tests/acp/conftest.py added: autouse fixture stubs the live models.dev/GitHub/Copilot/Anthropic inventory fetches that ACP server tests performed on every session create — test_server.py 147s → 3.4s, and the tests are now genuinely hermetic. - Sleep-based slowness shrunk where safe (codex_ttfb_watchdog, compression_concurrent_fork, etc.); no wall-clock assertion tightened. Verification: full hermetic suite via scripts/run_tests.sh — 2439 files, 31,130 tests passed, 0 failed, 0 flaky retries, 315s wall (baseline: 583s wall, 13,564s subprocess CPU).
122 lines
3.7 KiB
Python
122 lines
3.7 KiB
Python
"""Tests for scripts/ci/live_comment.py — classify_jobs().
|
|
|
|
The poller's core logic is a pure function: take raw GitHub API job dicts
|
|
and split them into (completed, pending). The API wrapper + polling loop
|
|
are tested via E2E in CI, not here.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import importlib.util
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
_PATH = Path(__file__).resolve().parents[2] / "scripts" / "ci" / "live_comment.py"
|
|
_spec = importlib.util.spec_from_file_location("live_comment", _PATH)
|
|
if _spec is None or _spec.loader is None:
|
|
raise ImportError("Failed to load live_comment.py")
|
|
_mod = importlib.util.module_from_spec(_spec)
|
|
sys.modules["live_comment"] = _mod
|
|
_spec.loader.exec_module(_mod)
|
|
|
|
|
|
def _job(name: str, status: str, conclusion: str | None = None, workflow: str = "") -> dict:
|
|
"""Build a raw API job dict."""
|
|
j = {"name": name, "status": status, "conclusion": conclusion}
|
|
if workflow:
|
|
j["_workflow_name"] = workflow
|
|
return j
|
|
|
|
|
|
|
|
|
|
def test_classify_success():
|
|
jobs = [_job("Python tests", "completed", "success")]
|
|
completed, pending, job_urls = _mod.classify_jobs(jobs)
|
|
assert completed == {"Python tests": "success"}
|
|
assert pending == []
|
|
|
|
|
|
def test_classify_failure():
|
|
jobs = [_job("Python tests", "completed", "failure")]
|
|
completed, pending, job_urls = _mod.classify_jobs(jobs)
|
|
assert completed == {"Python tests": "failure"}
|
|
assert pending == []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_classify_queued():
|
|
jobs = [_job("Python tests", "queued", None)]
|
|
completed, pending, job_urls = _mod.classify_jobs(jobs)
|
|
assert completed == {}
|
|
assert pending == ["Python tests"]
|
|
|
|
|
|
|
|
|
|
def test_classify_mixed():
|
|
jobs = [
|
|
_job("Python tests", "completed", "success"),
|
|
_job("Python lints", "completed", "failure"),
|
|
_job("JS & TS checks", "in_progress", None),
|
|
_job("Desktop E2E", "queued", None),
|
|
]
|
|
completed, pending, job_urls = _mod.classify_jobs(jobs)
|
|
assert completed == {"Python tests": "success", "Python lints": "failure"}
|
|
assert set(pending) == {"JS & TS checks", "Desktop E2E"}
|
|
|
|
|
|
|
|
|
|
def test_classify_sub_workflow_jobs_prefixed():
|
|
"""Sub-workflow jobs get 'Workflow / job' display names."""
|
|
jobs = [
|
|
_job("test", "completed", "success", workflow="Tests"),
|
|
_job("check", "in_progress", None, workflow="JS Tests"),
|
|
]
|
|
completed, pending, job_urls = _mod.classify_jobs(jobs)
|
|
assert "Tests / test" in completed
|
|
assert completed["Tests / test"] == "success"
|
|
assert "JS Tests / check" in pending
|
|
|
|
|
|
def test_classify_captures_html_url():
|
|
"""The poller captures html_url per job for per-job log links."""
|
|
jobs = [
|
|
{**_job("Python tests", "completed", "failure"),
|
|
"html_url": "https://github.com/repo/actions/runs/1/job/2"},
|
|
_job("Python lints", "completed", "success"),
|
|
]
|
|
completed, pending, job_urls = _mod.classify_jobs(jobs)
|
|
assert job_urls["Python tests"] == "https://github.com/repo/actions/runs/1/job/2"
|
|
# Jobs without html_url are simply absent from the dict
|
|
assert "Python lints" not in job_urls
|
|
|
|
|
|
|
|
|
|
def test_classify_timed_out_treated_as_failure():
|
|
jobs = [_job("Python tests", "completed", "timed_out")]
|
|
completed, pending, job_urls = _mod.classify_jobs(jobs)
|
|
assert completed == {"Python tests": "failure"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_commit_info_uses_present_tense_while_jobs_are_pending():
|
|
info = "<sub>running on [abc1234](https://commit-url) — fix: thing</sub>"
|
|
assert _mod._commit_info_for_state(info, ["Python tests"]) == info
|
|
|
|
|
|
def test_commit_info_uses_past_tense_after_jobs_complete():
|
|
info = "<sub>running on [abc1234](https://commit-url) — fix: thing</sub>"
|
|
assert _mod._commit_info_for_state(info, []) == (
|
|
"<sub>ran on [abc1234](https://commit-url) — fix: thing</sub>"
|
|
)
|