hermes-agent/tests/agent/test_oneshot.py
brooklyn! 211ba9c7d3
feat(agent): one-shot LLM helper + llm.oneshot gateway RPC (#51261)
A "one-shot" is a single stateless model call that runs OUTSIDE any conversation:
it never touches session history, never breaks prompt caching, and returns plain
text. UI surfaces need this for small generative chores — a commit message from a
diff, a rename suggestion, a summary — where an agent turn would pollute the
thread and hand-rolling an LLM call at every call site would be worse.

- `agent/oneshot.py`: `run_oneshot(...)` over the existing auxiliary-client
  plumbing (same path as title generation). Two call shapes: explicit
  instructions/input, or a registered `template` + `variables` (templates own the
  prompt engineering so it stays consistent across CLI/TUI/desktop). Ships a
  `commit_message` template. Model selection inherits the live session via
  `main_runtime`, else the configured aux `task` backend.
- `tui_gateway/server.py`: `llm.oneshot` RPC (long-handler) inheriting the
  session's model when `session_id` resolves.

Stateless by construction — no session mutation, cache untouched.
2026-06-23 08:01:50 +00:00

110 lines
3.9 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_unknown_template_raises(self):
with pytest.raises(KeyError):
render_template("does-not-exist", {})
def test_commit_message_template_is_registered(self):
assert "commit_message" in PROMPT_TEMPLATES
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_diff_with_braces_passes_through(self):
# Templates must not use str.format — code payloads carry literal { }.
_, user = render_template("commit_message", {"diff": "x = {a: 1}"})
assert "x = {a: 1}" in user
def test_commit_message_handles_missing_variables(self):
instructions, user = render_template("commit_message", {})
assert instructions
assert "no textual diff available" 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_template_path_calls_llm_with_rendered_prompt(self):
with patch(
"agent.oneshot.call_llm",
return_value=self._mock_response("feat: add thing"),
) as llm:
out = run_oneshot(template="commit_message", variables={"diff": "d"})
assert out == "feat: add thing"
messages = llm.call_args.kwargs["messages"]
assert messages[0]["role"] == "system"
assert messages[1]["role"] == "user"
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_requires_template_or_prompt(self):
with pytest.raises(ValueError):
run_oneshot()
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"