From b7261c8e701ccc2e0af0ec5eb89aa1ccc973bf5a Mon Sep 17 00:00:00 2001
From: Nicolas Mowen <nickmowen213@gmail.com>
Date: Wed, 22 Apr 2026 09:55:54 -0600
Subject: [PATCH] GenAI Tweaks (#22968)

* Add debug logs

* refresh embeddings maintainer genai clients on config update

---------

Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
---
 frigate/embeddings/maintainer.py |  4 ++++
 frigate/genai/ollama.py          | 28 ++++++++++++++++++++++++++--
 frigate/genai/openai.py          | 18 +++++++++++++++++-
 3 files changed, 47 insertions(+), 3 deletions(-)

diff --git a/frigate/embeddings/maintainer.py b/frigate/embeddings/maintainer.py
index ea1c9a118..33bef38f2 100644
--- a/frigate/embeddings/maintainer.py
+++ b/frigate/embeddings/maintainer.py
@@ -310,6 +310,10 @@ class EmbeddingMaintainer(threading.Thread):
             self._handle_custom_classification_update(topic, payload)
             return
 
+        if topic == "config/genai":
+            self.config.genai = payload
+            self.genai_manager.update_config(self.config)
+
         # Broadcast to all processors — each decides if the topic is relevant
         for processor in self.realtime_processors:
             processor.update_config(topic, payload)
diff --git a/frigate/genai/ollama.py b/frigate/genai/ollama.py
index 7524d54e3..1c0e222d9 100644
--- a/frigate/genai/ollama.py
+++ b/frigate/genai/ollama.py
@@ -113,6 +113,15 @@ class OllamaClient(GenAIClient):
                 schema = response_format.get("json_schema", {}).get("schema")
                 if schema:
                     ollama_options["format"] = self._clean_schema_for_ollama(schema)
+            logger.debug(
+                "Ollama generate request: model=%s, prompt_len=%s, image_count=%s, "
+                "has_format=%s, options=%s",
+                self.genai_config.model,
+                len(prompt),
+                len(images) if images else 0,
+                "format" in ollama_options,
+                {k: v for k, v in ollama_options.items() if k != "format"},
+            )
             result = self.provider.generate(
                 self.genai_config.model,
                 prompt,
@@ -120,9 +129,24 @@ class OllamaClient(GenAIClient):
                 **ollama_options,
             )
             logger.debug(
-                f"Ollama tokens used: eval_count={result.get('eval_count')}, prompt_eval_count={result.get('prompt_eval_count')}"
+                "Ollama generate response: done=%s, done_reason=%s, eval_count=%s, "
+                "prompt_eval_count=%s, response_len=%s",
+                result.get("done"),
+                result.get("done_reason"),
+                result.get("eval_count"),
+                result.get("prompt_eval_count"),
+                len(result.get("response", "") or ""),
             )
-            return str(result["response"]).strip()
+            response_text = str(result["response"]).strip()
+            if not response_text:
+                logger.warning(
+                    "Ollama returned a blank response for model %s (done_reason=%s, "
+                    "eval_count=%s). Check model output, ensure thinking is disabled.",
+                    self.genai_config.model,
+                    result.get("done_reason"),
+                    result.get("eval_count"),
+                )
+            return response_text
         except (
             TimeoutException,
             ResponseError,
diff --git a/frigate/genai/openai.py b/frigate/genai/openai.py
index 88108e730..af94859de 100644
--- a/frigate/genai/openai.py
+++ b/frigate/genai/openai.py
@@ -80,7 +80,23 @@ class OpenAIClient(GenAIClient):
                 and hasattr(result, "choices")
                 and len(result.choices) > 0
             ):
-                return str(result.choices[0].message.content.strip())
+                message = result.choices[0].message
+                content = message.content
+
+                if not content:
+                    # When reasoning is enabled for some OpenAI backends the actual response
+                    # is incorrectly placed in reasoning_content instead of content.
+                    # This is buggy/incorrect behavior — reasoning should not be
+                    # enabled for these models.
+                    reasoning_content = getattr(message, "reasoning_content", None)
+                    if reasoning_content:
+                        logger.warning(
+                            "Response content was empty but reasoning_content was provided; "
+                            "reasoning appears to be enabled and should be disabled for this model."
+                        )
+                        content = reasoning_content
+
+                return str(content.strip()) if content else None
             return None
         except (TimeoutException, Exception) as e:
             logger.warning("OpenAI returned an error: %s", str(e))