f54e2a46ae
yolo auto-approves every tool call, so a real-time search query could in principle trigger write/shell tools. Default approval mode still auto-runs the CLI's read-only web search in headless mode but never silently approves destructive tools. Verified end-to-end: a grounded query returns a current answer in ~23s with the account OAuth login. Test asserts yolo is absent; specs and docs/llm_contexts.md updated. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
96 lines
3.6 KiB
Python
96 lines
3.6 KiB
Python
"""Behaviour tests for the Gemini CLI (OAuth login) real-time search backend.
|
|
|
|
These verify the observable contract of ``gemini_cli_search``:
|
|
- a fenced answer when the CLI returns a JSON ``response``,
|
|
- fail-open (``None``) when the CLI is missing, times out, errors, or returns
|
|
empty/garbage output,
|
|
- the child process never inherits ``GEMINI_API_KEY`` / ``GOOGLE_API_KEY`` so
|
|
the CLI uses the account OAuth login rather than API-key auth.
|
|
"""
|
|
|
|
import subprocess
|
|
import types
|
|
|
|
import jarvis.tools.builtin.realtime_search as rs
|
|
|
|
|
|
def _fake_proc(stdout: str) -> types.SimpleNamespace:
|
|
return types.SimpleNamespace(stdout=stdout, stderr="", returncode=0)
|
|
|
|
|
|
def test_returns_fenced_answer_on_success(monkeypatch):
|
|
monkeypatch.setattr(rs, "_gemini_bin", lambda: "/usr/bin/gemini")
|
|
monkeypatch.setattr(
|
|
rs.subprocess,
|
|
"run",
|
|
lambda *a, **k: _fake_proc('{"response": "Seoul is sunny, 21C.", "stats": {}}'),
|
|
)
|
|
|
|
out = rs.gemini_cli_search("weather in Seoul")
|
|
|
|
assert out is not None
|
|
assert "Seoul is sunny, 21C." in out
|
|
assert "UNTRUSTED WEB EXTRACT" in out # untrusted-data fence preserved
|
|
|
|
|
|
def test_none_when_cli_not_installed(monkeypatch):
|
|
monkeypatch.setattr(rs, "_gemini_bin", lambda: None)
|
|
# subprocess.run must not even be reached
|
|
monkeypatch.setattr(rs.subprocess, "run", lambda *a, **k: (_ for _ in ()).throw(AssertionError("should not run")))
|
|
|
|
assert rs.gemini_cli_search("anything") is None
|
|
|
|
|
|
def test_none_on_empty_query(monkeypatch):
|
|
monkeypatch.setattr(rs, "_gemini_bin", lambda: "/usr/bin/gemini")
|
|
assert rs.gemini_cli_search("") is None
|
|
|
|
|
|
def test_none_on_empty_response(monkeypatch):
|
|
monkeypatch.setattr(rs, "_gemini_bin", lambda: "/usr/bin/gemini")
|
|
monkeypatch.setattr(rs.subprocess, "run", lambda *a, **k: _fake_proc('{"response": "", "stats": {}}'))
|
|
assert rs.gemini_cli_search("q") is None
|
|
|
|
|
|
def test_none_on_garbage_output(monkeypatch):
|
|
monkeypatch.setattr(rs, "_gemini_bin", lambda: "/usr/bin/gemini")
|
|
monkeypatch.setattr(rs.subprocess, "run", lambda *a, **k: _fake_proc("not json at all"))
|
|
assert rs.gemini_cli_search("q") is None
|
|
|
|
|
|
def test_none_on_timeout(monkeypatch):
|
|
monkeypatch.setattr(rs, "_gemini_bin", lambda: "/usr/bin/gemini")
|
|
|
|
def _boom(*a, **k):
|
|
raise subprocess.TimeoutExpired(cmd="gemini", timeout=30)
|
|
|
|
monkeypatch.setattr(rs.subprocess, "run", _boom)
|
|
assert rs.gemini_cli_search("q") is None
|
|
|
|
|
|
def test_api_key_stripped_from_child_env(monkeypatch):
|
|
monkeypatch.setattr(rs, "_gemini_bin", lambda: "/usr/bin/gemini")
|
|
monkeypatch.setenv("GEMINI_API_KEY", "AIza-secret")
|
|
monkeypatch.setenv("GOOGLE_API_KEY", "another-secret")
|
|
captured = {}
|
|
|
|
def _capture(*a, **k):
|
|
captured["env"] = k.get("env", {})
|
|
captured["cmd"] = a[0] if a else k.get("args")
|
|
return _fake_proc('{"response": "ok"}')
|
|
|
|
monkeypatch.setattr(rs.subprocess, "run", _capture)
|
|
rs.gemini_cli_search("q")
|
|
|
|
assert "GEMINI_API_KEY" not in captured["env"]
|
|
assert "GOOGLE_API_KEY" not in captured["env"]
|
|
# Google-account (OAuth) auth method is selected explicitly so a missing
|
|
# login fails fast non-interactively instead of erroring on "no auth method".
|
|
assert captured["env"].get("GOOGLE_GENAI_USE_GCA") == "true"
|
|
# invoked headless with JSON output
|
|
assert "-p" in captured["cmd"] and "-o" in captured["cmd"] and "json" in captured["cmd"]
|
|
# never auto-approve all tools: a search query must not be able to trigger
|
|
# write/shell tool execution.
|
|
assert "yolo" not in captured["cmd"]
|
|
assert "--yolo" not in captured["cmd"]
|