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
@@ -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",
@@ -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: