chore: sentry log grouping and file upload stats

letta/otel/metric_registry.py

@@ -58,7 +58,12 @@ class MetricRegistry:
     def tool_execution_counter(self) -> Counter:
         return self._get_or_create_metric(
             "count_tool_execution",
-            partial(self._meter.create_counter, name="count_tool_execution", description="Counts the number of tools executed.", unit="1"),
+            partial(
+                self._meter.create_counter,
+                name="count_tool_execution",
+                description="Counts the number of tools executed.",
+                unit="1",
+            ),
         )
 
     # project_id + model
@@ -66,7 +71,12 @@ class MetricRegistry:
     def ttft_ms_histogram(self) -> Histogram:
         return self._get_or_create_metric(
             "hist_ttft_ms",
-            partial(self._meter.create_histogram, name="hist_ttft_ms", description="Histogram for the Time to First Token (ms)", unit="ms"),
+            partial(
+                self._meter.create_histogram,
+                name="hist_ttft_ms",
+                description="Histogram for the Time to First Token (ms)",
+                unit="ms",
+            ),
         )
 
     # (includes model name)
@@ -158,3 +168,15 @@ class MetricRegistry:
                 unit="1",
             ),
         )
+
+    @property
+    def file_process_bytes_histogram(self) -> Histogram:
+        return self._get_or_create_metric(
+            "hist_file_process_bytes",
+            partial(
+                self._meter.create_histogram,
+                name="hist_file_process_bytes",
+                description="Histogram for file process in bytes",
+                unit="By",
+            ),
+        )

letta/schemas/tool.py

@@ -77,9 +77,8 @@ class Tool(BaseTool):
 
         if self.tool_type is ToolType.CUSTOM:
             if not self.source_code:
-                error_msg = f"Custom tool with id={self.id} is missing source_code field."
-                logger.error(error_msg)
-                raise ValueError(error_msg)
+                logger.error("Custom tool with id=%s is missing source_code field", self.id)
+                raise ValueError(f"Custom tool with id={self.id} is missing source_code field.")
 
             # Always derive json_schema for freshest possible json_schema
             if self.args_json_schema is not None:
@@ -96,8 +95,7 @@ class Tool(BaseTool):
                 try:
                     self.json_schema = derive_openai_json_schema(source_code=self.source_code)
                 except Exception as e:
-                    error_msg = f"Failed to derive json schema for tool with id={self.id} name={self.name}. Error: {str(e)}"
-                    logger.error(error_msg)
+                    logger.error("Failed to derive json schema for tool with id=%s name=%s: %s", self.id, self.name, e)
         elif self.tool_type in {ToolType.LETTA_CORE, ToolType.LETTA_MEMORY_CORE, ToolType.LETTA_SLEEPTIME_CORE}:
             # If it's letta core tool, we generate the json_schema on the fly here
             self.json_schema = get_json_schema_from_module(module_name=LETTA_CORE_TOOL_MODULE_NAME, function_name=self.name)
@@ -119,9 +117,8 @@ class Tool(BaseTool):
 
         # At this point, we need to validate that at least json_schema is populated
         if not self.json_schema:
-            error_msg = f"Tool with id={self.id} name={self.name} tool_type={self.tool_type} is missing a json_schema."
-            logger.error(error_msg)
-            raise ValueError(error_msg)
+            logger.error("Tool with id=%s name=%s tool_type=%s is missing a json_schema", self.id, self.name, self.tool_type)
+            raise ValueError(f"Tool with id={self.id} name={self.name} tool_type={self.tool_type} is missing a json_schema.")
 
         # Derive name from the JSON schema if not provided
         if not self.name:

letta/services/file_processor/file_processor.py

@@ -1,6 +1,7 @@
 from typing import List
 
 from letta.log import get_logger
+from letta.otel.context import get_ctx_attributes
 from letta.otel.tracing import log_event, trace_method
 from letta.schemas.agent import AgentState
 from letta.schemas.enums import FileProcessingStatus
@@ -122,6 +123,10 @@ class FileProcessor:
             if isinstance(content, str):
                 content = content.encode("utf-8")
 
+            from letta.otel.metric_registry import MetricRegistry
+
+            MetricRegistry().file_process_bytes_histogram.record(len(content), attributes=get_ctx_attributes())
+
             if len(content) > self.max_file_size:
                 log_event(
                     "file_processor.size_limit_exceeded",