Merge pull request #1224 from MemPalace/feat/privacy-warn-external-llm

feat(privacy): warn when LLM tier sends content to external API
2026-04-26 19:18:13 -03:00
parent 414aa3e20b 4400734867
commit 4d33f14988
4 changed files with 248 additions and 0 deletions
@@ -1629,3 +1629,115 @@ def test_merge_tier_fields_no_llm_provider_returns_heuristic_only():
    assert res["agent_persona_names"] == []
    assert res["user_name"] is None
    assert res["primary_platform"] is None
+
+
+# ─────────────────────────────────────────────────────────────────────────
+# External-API privacy warning (issue #24).
+#
+# When mempalace init resolves an LLM provider whose endpoint will send
+# user content off the local machine/network, init MUST print a clear
+# warning naming the provider, stating that MemPalace doesn't control
+# how the provider logs/retains/uses the data, and pointing at --no-llm.
+# Local providers (Ollama on localhost, LM Studio on LAN, etc.) MUST NOT
+# trigger the warning.
+# ─────────────────────────────────────────────────────────────────────────
+
+
+def test_init_prints_privacy_warning_when_provider_is_external(
+    ai_dialogue_corpus: Path, tmp_path: Path, capsys
+):
+    """When cmd_init successfully acquires a provider whose
+    is_external_service is True, output must contain the privacy
+    warning text including the EXTERNAL marker.
+    """
+    from mempalace.cli import cmd_init
+
+    palace = tmp_path / "palace"
+    args = _init_args(ai_dialogue_corpus)  # default = LLM ON
+
+    fake_provider = MagicMock()
+    fake_provider.check_available.return_value = (True, "ok")
+    fake_provider.is_external_service = True
+    fake_provider.classify.return_value = MagicMock(text='{"classifications": []}')
+
+    with (
+        patch("mempalace.cli.MempalaceConfig", return_value=_stub_cfg(palace)),
+        patch("mempalace.cli.get_provider", return_value=fake_provider),
+        patch("mempalace.cli._maybe_run_mine_after_init"),
+        patch("mempalace.room_detector_local.detect_rooms_local"),
+    ):
+        cmd_init(args)
+
+    out = capsys.readouterr().out
+    assert "EXTERNAL API" in out, (
+        f"Privacy warning must mention 'EXTERNAL API' when provider is external. " f"Got: {out!r}"
+    )
+    assert (
+        "--no-llm" in out
+    ), f"Privacy warning must point users at --no-llm to opt out. Got: {out!r}"
+    # The warning should also tell users MemPalace isn't responsible
+    # for downstream provider behavior.
+    assert (
+        "does not control" in out.lower()
+        or "not responsible" in out.lower()
+        or "logs" in out.lower()
+        or "retains" in out.lower()
+    ), (
+        f"Privacy warning must clarify MemPalace doesn't control how the "
+        f"provider handles the data. Got: {out!r}"
+    )
+
+
+def test_init_no_privacy_warning_when_provider_is_local(
+    ai_dialogue_corpus: Path, tmp_path: Path, capsys
+):
+    """When cmd_init successfully acquires a LOCAL provider (e.g. Ollama
+    on localhost, LM Studio on LAN), the privacy warning MUST NOT fire —
+    nothing is leaving the user's machine/network.
+    """
+    from mempalace.cli import cmd_init
+
+    palace = tmp_path / "palace"
+    args = _init_args(ai_dialogue_corpus)  # default = LLM ON
+
+    fake_provider = MagicMock()
+    fake_provider.check_available.return_value = (True, "ok")
+    fake_provider.is_external_service = False  # Local provider — no warning
+    fake_provider.classify.return_value = MagicMock(text='{"classifications": []}')
+
+    with (
+        patch("mempalace.cli.MempalaceConfig", return_value=_stub_cfg(palace)),
+        patch("mempalace.cli.get_provider", return_value=fake_provider),
+        patch("mempalace.cli._maybe_run_mine_after_init"),
+        patch("mempalace.room_detector_local.detect_rooms_local"),
+    ):
+        cmd_init(args)
+
+    out = capsys.readouterr().out
+    assert "EXTERNAL API" not in out, (
+        f"Privacy warning fired for a LOCAL provider — should not have. " f"Got: {out!r}"
+    )
+
+
+def test_init_no_privacy_warning_with_no_llm_flag(ai_dialogue_corpus: Path, tmp_path: Path, capsys):
+    """With --no-llm, no provider is acquired at all, so the privacy
+    warning has nothing to fire on. Output must not contain it.
+    """
+    from mempalace.cli import cmd_init
+
+    palace = tmp_path / "palace"
+    args = _init_args(ai_dialogue_corpus, no_llm=True)
+
+    with (
+        patch("mempalace.cli.MempalaceConfig", return_value=_stub_cfg(palace)),
+        patch("mempalace.cli.get_provider") as mock_get,
+        patch("mempalace.cli._maybe_run_mine_after_init"),
+        patch("mempalace.room_detector_local.detect_rooms_local"),
+    ):
+        cmd_init(args)
+
+    mock_get.assert_not_called(), "--no-llm must short-circuit before provider acquisition"
+    out = capsys.readouterr().out
+    assert (
+        "EXTERNAL API" not in out
+    ), f"Privacy warning fired on --no-llm path — should not have. Got: {out!r}"
@@ -325,3 +325,56 @@ def test_anthropic_no_key_raises_on_classify(monkeypatch):
    p = AnthropicProvider(model="claude-haiku")
    with pytest.raises(LLMError, match="requires ANTHROPIC_API_KEY"):
        p.classify("s", "u")
+
+
+# ── is_external_service property (issue #24 — privacy warning support) ──
+#
+# `is_external_service` is True when this provider's endpoint sends data
+# off the user's machine/network. Used by mempalace init to print a
+# privacy warning before first run when an external API will receive
+# folder content. URL-based heuristic: localhost, 127.x, ::1, .local,
+# RFC1918 (10/8, 192.168/16, 172.16-31/12), and IPv6 ULA (fc/fd::) are
+# all treated as local. Everything else is treated as external.
+
+
+def test_ollama_provider_default_endpoint_is_local():
+    """OllamaProvider's default endpoint is http://localhost:11434, which
+    must be classified as local — no privacy warning fires for the
+    typical user running Ollama on their own machine."""
+    p = OllamaProvider(model="gemma4:e4b")
+    assert p.is_external_service is False, (
+        f"Default OllamaProvider endpoint must be local; got "
+        f"is_external_service={p.is_external_service} for endpoint={p.endpoint}"
+    )
+
+
+def test_openai_compat_provider_localhost_endpoint_is_local():
+    """LM Studio / llama.cpp server / vLLM commonly bind to localhost.
+    Those setups must NOT trigger the external-API warning."""
+    p = OpenAICompatProvider(model="any", endpoint="http://localhost:1234")
+    assert p.is_external_service is False
+    p_127 = OpenAICompatProvider(model="any", endpoint="http://127.0.0.1:8000")
+    assert p_127.is_external_service is False
+    p_lan = OpenAICompatProvider(model="any", endpoint="http://192.168.1.50:1234")
+    assert p_lan.is_external_service is False, "LAN (RFC1918) endpoints must be local"
+
+
+def test_openai_compat_provider_cloud_endpoint_is_external():
+    """A user pointing openai-compat at OpenAI's hosted API or any other
+    non-local endpoint MUST trigger the external warning."""
+    p = OpenAICompatProvider(model="gpt-4o", endpoint="https://api.openai.com")
+    assert p.is_external_service is True, (
+        f"https://api.openai.com must be classified external; got "
+        f"is_external_service={p.is_external_service}"
+    )
+
+
+def test_anthropic_provider_default_endpoint_is_external():
+    """AnthropicProvider's default endpoint is https://api.anthropic.com,
+    which is always external by definition. The privacy warning MUST
+    fire by default for users who pass --llm-provider anthropic."""
+    p = AnthropicProvider(model="claude-haiku-4-5", api_key="sk-test")
+    assert p.is_external_service is True, (
+        f"Default AnthropicProvider endpoint must be external; got "
+        f"is_external_service={p.is_external_service} for endpoint={p.endpoint}"
+    )