fix: prevent truncated Ollama answers

backend/README.md

@@ -1100,6 +1100,7 @@ OLLAMA_BASE_URL=http://host.docker.internal:11434
 OLLAMA_DEFAULT_MODEL=qwen3.5:9b
 OLLAMA_TIMEOUT_SECONDS=120
 OLLAMA_MAX_OUTPUT_TOKENS=700
+OLLAMA_CONTEXT_TOKENS=16384
 ```
 
 The Unraid deployment adds `host.docker.internal:host-gateway` automatically.
@@ -1107,7 +1108,9 @@ Verify the connection with `GET /api/v1/assistant/status`, inspect installed
 models with `GET /api/v1/assistant/models` and ask a grounded question through
 `POST /api/v1/projects/{project_id}/assistant/query`. A requested model must be
 present in Ollama `/api/tags`. Missing water depth/bathymetry remains explicit;
-the assistant cannot turn 2D water geometry into volume.
+the assistant cannot turn 2D water geometry into volume. GeoIntel rejects an
+answer when Ollama reports `done_reason=length`, so a visibly truncated sentence
+is never presented as a complete result.
 
 ## Helpful repository scripts
 

backend/app/core/config.py

@@ -51,6 +51,7 @@ class Settings(BaseSettings):
     ollama_default_model: str = Field(default="qwen3.5:9b", validation_alias="OLLAMA_DEFAULT_MODEL")
     ollama_timeout_seconds: int = Field(default=120, ge=5, le=600, validation_alias="OLLAMA_TIMEOUT_SECONDS")
     ollama_max_output_tokens: int = Field(default=700, ge=100, le=4_000, validation_alias="OLLAMA_MAX_OUTPUT_TOKENS")
+    ollama_context_tokens: int = Field(default=16_384, ge=4_096, le=131_072, validation_alias="OLLAMA_CONTEXT_TOKENS")
     cors_origins: list[str] | str = Field(
         default=["http://localhost:5173", "http://127.0.0.1:5173"],
         validation_alias="CORS_ORIGINS",

backend/app/services/geo_assistant_service.py

@@ -367,9 +367,23 @@ class GeoAssistantService:
                 "stream": False,
                 "think": False,
                 "keep_alive": "10m",
-                "options": {"temperature": 0.1, "num_predict": self.settings.ollama_max_output_tokens},
+                "options": {
+                    "temperature": 0.1,
+                    "num_ctx": self.settings.ollama_context_tokens,
+                    "num_predict": self.settings.ollama_max_output_tokens,
+                },
             },
         )
+        if response.get("done_reason") == "length":
+            raise AppError(
+                code="OLLAMA_RESPONSE_TRUNCATED",
+                message="Ollama kon geen volledig antwoord binnen de ingestelde contextlimiet genereren.",
+                details={
+                    "context_tokens": self.settings.ollama_context_tokens,
+                    "max_output_tokens": self.settings.ollama_max_output_tokens,
+                },
+                status_code=502,
+            )
         message = response.get("message") if isinstance(response.get("message"), dict) else {}
         answer = str(message.get("content") or "").strip()
         if not answer:

backend/tests/test_sprint202_temporal_metrics_and_ollama.py

@@ -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": [