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).
83 lines
2.7 KiB
Python
83 lines
2.7 KiB
Python
"""Tests for agent.oneshot — shared one-off (stateless) LLM requests."""
|
|
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
import pytest
|
|
|
|
from agent.oneshot import (
|
|
PROMPT_TEMPLATES,
|
|
render_template,
|
|
run_oneshot,
|
|
_strip_code_fence,
|
|
_truncate,
|
|
)
|
|
|
|
|
|
class TestRenderTemplate:
|
|
|
|
|
|
def test_commit_message_includes_diff_and_recent(self):
|
|
instructions, user = render_template(
|
|
"commit_message",
|
|
{"diff": "diff --git a/x b/x\n+new", "recent_commits": "feat: a\nfix: b"},
|
|
)
|
|
# Instructions describe the contract (conventional commits), not a snapshot.
|
|
assert "Conventional Commits" in instructions
|
|
assert "diff --git a/x b/x" in user
|
|
assert "feat: a" in user
|
|
|
|
|
|
|
|
def test_commit_message_avoid_forces_new_message(self):
|
|
# Passing the previous message must instruct the model not to repeat it,
|
|
# so "regenerate" yields a different result even on greedy models.
|
|
_, plain = render_template("commit_message", {"diff": "d"})
|
|
_, regen = render_template("commit_message", {"diff": "d", "avoid": "feat: prior"})
|
|
assert "feat: prior" in regen
|
|
assert "do not repeat" in regen
|
|
assert "feat: prior" not in plain
|
|
|
|
|
|
class TestRunOneshot:
|
|
def _mock_response(self, content):
|
|
resp = MagicMock()
|
|
resp.choices = [MagicMock()]
|
|
resp.choices[0].message.content = content
|
|
resp.choices[0].message.reasoning = None
|
|
resp.choices[0].message.reasoning_content = None
|
|
resp.choices[0].message.reasoning_details = None
|
|
return resp
|
|
|
|
|
|
def test_explicit_instructions_path(self):
|
|
with patch(
|
|
"agent.oneshot.call_llm",
|
|
return_value=self._mock_response("hello"),
|
|
) as llm:
|
|
out = run_oneshot(instructions="be brief", user_input="say hi")
|
|
|
|
assert out == "hello"
|
|
messages = llm.call_args.kwargs["messages"]
|
|
assert messages[0]["content"] == "be brief"
|
|
assert messages[1]["content"] == "say hi"
|
|
|
|
|
|
def test_strips_wrapping_code_fence(self):
|
|
with patch(
|
|
"agent.oneshot.call_llm",
|
|
return_value=self._mock_response("```\nfix: bug\n```"),
|
|
):
|
|
assert run_oneshot(instructions="x", user_input="y") == "fix: bug"
|
|
|
|
|
|
class TestHelpers:
|
|
def test_truncate_under_limit_unchanged(self):
|
|
assert _truncate("short", 100) == "short"
|
|
|
|
def test_truncate_over_limit_marks_truncation(self):
|
|
out = _truncate("x" * 200, 50)
|
|
assert out.endswith("…(truncated)")
|
|
assert len(out) < 200
|
|
|
|
def test_strip_code_fence_without_fence_is_noop(self):
|
|
assert _strip_code_fence("plain text") == "plain text"
|