fix: prevent truncated Ollama answers

2026-07-15 07:39:03 +02:00
parent 5be8f628ef
commit 56f823f02a
13 changed files with 89 additions and 4 deletions
@@ -155,11 +155,57 @@ def test_geo_assistant_sends_grounded_context_without_thinking_trace(monkeypatch
    assert captured["path"] == "/api/chat"
    assert captured["payload"]["stream"] is False
    assert captured["payload"]["think"] is False
+    assert captured["payload"]["options"]["num_ctx"] == 16_384
    assert "Gebruik uitsluitend feiten en cijfers uit CONTEXT_JSON" in captured["payload"]["messages"][0]["content"]
    assert "scope.label is het exact geanalyseerde gebied" in captured["payload"]["messages"][0]["content"]
    assert "water_volume_available" in captured["payload"]["messages"][0]["content"]


+def test_geo_assistant_rejects_truncated_ollama_answer(monkeypatch) -> None:
+    service = GeoAssistantService(ollama_settings())
+    monkeypatch.setattr(service, "list_models", lambda: [AssistantModelRead(name="qwen3.5:9b")])
+    monkeypatch.setattr(
+        service,
+        "_build_context",
+        lambda *args, **kwargs: (
+            {"scope": {"label": "Gemeente Mol"}},
+            [],
+            [],
+            [],
+            [],
+            "Gemeente Mol",
+        ),
+    )
+    monkeypatch.setattr(
+        service,
+        "_request_json",
+        lambda path, payload=None: {
+            "done": True,
+            "done_reason": "length",
+            "message": {"role": "assistant", "content": "Een onvolledige zin"},
+        },
+    )
+
+    with pytest.raises(AppError) as exc_info:
+        service.query(
+            object(),
+            project_id=uuid4(),
+            payload=AssistantQueryRequest(question="Hoe evolueerde Mol?"),
+        )
+
+    assert exc_info.value.code == "OLLAMA_RESPONSE_TRUNCATED"
+
+
+def test_unraid_ollama_context_window_is_configurable() -> None:
+    compose = (ROOT / "docker-compose.unraid.yml").read_text(encoding="utf-8")
+    template = (ROOT / "deploy/unraid/geointel-unraid-template.xml").read_text(encoding="utf-8")
+    env_example = (ROOT / "deploy/unraid/geointel.env.example").read_text(encoding="utf-8")
+
+    assert "OLLAMA_CONTEXT_TOKENS: ${OLLAMA_CONTEXT_TOKENS:-16384}" in compose
+    assert 'Target="OLLAMA_CONTEXT_TOKENS"' in template
+    assert "OLLAMA_CONTEXT_TOKENS=16384" in env_example
+
+
 def test_temporal_comparison_preserves_all_compatible_semantic_metrics() -> None:
    earlier = {
        "metrics": [