chore: Coderabbit Nitpicks

.env.template

@@ -10,8 +10,8 @@
 LOG_LEVEL=INFO
 # SESSION_OBSERVERS_LIMIT=10
 # GET_CONTEXT_MAX_TOKENS=100000
-# MAX_FILE_SIZE=5242880
-# MAX_MESSAGE_SIZE=25000
+# MAX_FILE_SIZE=5242880 # Bytes
+# MAX_MESSAGE_SIZE=25000 # Characters
 
 # Embedding settings
 # EMBED_MESSAGES=true
@@ -133,4 +133,4 @@ LLM_ANTHROPIC_API_KEY=your-anthropic-api-key-here
 # SENTRY_RELEASE=your-release-semver
 # SENTRY_ENVIRONMENT=development
 # SENTRY_TRACES_SAMPLE_RATE=0.1
-# SENTRY_PROFILES_SAMPLE_RATE=0.1
+# SENTRY_PROFILES_SAMPLE_RATE=0.1

config.toml.example

@@ -9,7 +9,7 @@ LOG_LEVEL = "INFO"
 SESSION_OBSERVERS_LIMIT = 10
 GET_CONTEXT_MAX_TOKENS = 100000
 MAX_FILE_SIZE = 5242880  # 5MB
-MAX_MESSAGE_SIZE = 25000
+MAX_MESSAGE_SIZE = 25000 # Characters
 EMBED_MESSAGES = true
 MAX_EMBEDDING_TOKENS = 8192
 MAX_EMBEDDING_TOKENS_PER_REQUEST = 300000

src/deriver/consumer.py

@@ -33,7 +33,7 @@ async def process_items(task_type: str, queue_payloads: list[dict[str, Any]]) ->
     task type to Pydantic model. After validation, routes the request to
     the correct processor without repeating type checks elsewhere.
     """
-    if not queue_payloads:
+    if not queue_payloads or not queue_payloads[0]:
         logger.debug("process_items received no payloads for task type %s", task_type)
         return
 

src/deriver/deriver.py

@@ -109,7 +109,7 @@ async def process_representation_tasks_batch(
     """
     Process a batch of representation tasks by extracting insights and updating working representations.
     """
-    if not payloads:
+    if not payloads or len(payloads) == 0:
         return
 
     payloads.sort(key=lambda x: x.message_id)