Duplicated values and sums

app/mcp/v1/tools/ch_reader.py

@@ -36,7 +36,7 @@ def get_health_summary_ch() -> dict[str, Any]:
     try:
         return get_health_summary_from_ch()
     except Exception as e:
-        return {"error": str(e)}
+        return {"error": f"Failed to get health summary: {str(e)}"}
 
 
 @ch_reader_router.tool
@@ -71,7 +71,7 @@ def search_health_records_ch(params: HealthRecordSearchParams) -> dict[str, Any]
     try:
         return search_health_records_from_ch(params)
     except Exception as e:
-        return {"error": str(e)}
+        return {"error": f"Failed to search health records: {str(e)}"}
 
 
 @ch_reader_router.tool
@@ -142,16 +142,26 @@ def get_trend_data_ch(
 
     Returns:
     - record_type: The analyzed record type
+    - device: The device on which the data was recorded
     - interval: The time interval used
     - trend_data: List of time buckets with statistics for each period:
       * date: The time period (ISO string)
+      * value_sum: Sum of values for the period
       * avg_value: Average value for the period
       * min_value: Minimum value for the period
       * max_value: Maximum value for the period
       * count: Number of records in the period
 
     Notes for LLMs:
     - Use this to analyze trends, patterns, and seasonal variations in health data
+    - Keep in mind that when there is data from multiple devices spanning the same
+      time period, there is a possibility of data being duplicated. Inform the user
+      of this possibility if you see multiple devices in the same time period.
+    - If a user asks you to sum up some values from their health records, DO NOT
+      search for records and write a script to sum them, instead, use this tool:
+      if they ask to sum data from a year, use this tool with date_from set as the
+      beginning of the year and date_to as the end of the year, with an interval
+      of 'year'
     - The function automatically handles date filtering if date_from/date_to are provided
     - IMPORTANT - interval must be one of: "day", "week", "month", or "year".
       Do not use other values.

app/mcp/v1/tools/duckdb_reader.py

@@ -36,7 +36,7 @@ def get_health_summary_duckdb() -> list[dict[str, Any]]:
     try:
         return get_health_summary_from_duckdb()
     except Exception as e:
-        return [{"error": str(e)}]
+        return [{"error": f"Failed to get health summary: {str(e)}"}]
 
 
 @duckdb_reader_router.tool
@@ -71,7 +71,7 @@ def search_health_records_duckdb(params: HealthRecordSearchParams) -> list[dict[
     try:
         return search_health_records_from_duckdb(params)
     except Exception as e:
-        return [{"error": str(e)}]
+        return [{"error": f"Failed to search health records: {str(e)}"}]
 
 
 @duckdb_reader_router.tool
@@ -142,16 +142,26 @@ def get_trend_data_duckdb(
 
     Returns:
     - record_type: The analyzed record type
+    - device: The device on which the data was recorded
     - interval: The time interval used
     - trend_data: List of time buckets with statistics for each period:
       * date: The time period (ISO string)
+      * value_sum: Sum of values for the period
       * avg_value: Average value for the period
       * min_value: Minimum value for the period
       * max_value: Maximum value for the period
       * count: Number of records in the period
 
     Notes for LLMs:
     - Use this to analyze trends, patterns, and seasonal variations in health data
+    - Keep in mind that when there is data from multiple devices spanning the same
+      time period, there is a possibility of data being duplicated. Inform the user
+      of this possibility if you see multiple devices in the same time period.
+    - If a user asks you to sum up some values from their health records, DO NOT
+      search for records and write a script to sum them, instead, use this tool:
+      if they ask to sum data from a year, use this tool with date_from set as the
+      beginning of the year and date_to as the end of the year, with an interval
+      of 'year'
     - The function automatically handles date filtering if date_from/date_to are provided
     - IMPORTANT - interval must be one of: "day", "week", "month", or "year".
       Do not use other values.
@@ -207,4 +217,4 @@ def search_values_duckdb(
     try:
         return search_values_from_duckdb(record_type, value, date_from, date_to)
     except Exception as e:
-        return [{"error": f"Failed to get trend data: {str(e)}"}]
+        return [{"error": f"Failed to search for values: {str(e)}"}]

app/mcp/v1/tools/es_reader.py

@@ -36,7 +36,7 @@ def get_health_summary_es() -> dict[str, Any]:
     try:
         return get_health_summary_from_es()
     except Exception as e:
-        return {"error": f"Failed to get health summary from ES: {str(e)}"}
+        return {"error": f"Failed to get health summary: {str(e)}"}
 
 
 @es_reader_router.tool
@@ -142,16 +142,26 @@ def get_trend_data_es(
 
     Returns:
     - record_type: The analyzed record type
+    - device: The device on which the data was recorded
     - interval: The time interval used
     - trend_data: List of time buckets with statistics for each period:
       * date: The time period (ISO string)
+      * value_sum: Sum of values for the period
       * avg_value: Average value for the period
       * min_value: Minimum value for the period
       * max_value: Maximum value for the period
       * count: Number of records in the period
 
     Notes for LLMs:
     - Use this to analyze trends, patterns, and seasonal variations in health data
+    - Keep in mind that when there is data from multiple devices spanning the same
+      time period, there is a possibility of data being duplicated. Inform the user
+      of this possibility if you see multiple devices in the same time period.
+    - If a user asks you to sum up some values from their health records, DO NOT
+      search for records and write a script to sum them, instead, use this tool:
+      if they ask to sum data from a year, use this tool with date_from set as the
+      beginning of the year and date_to as the end of the year, with an interval
+      of 'year'
     - The function automatically handles date filtering if date_from/date_to are provided
     - IMPORTANT - interval must be one of: "day", "week", "month", or "year".
       Do not use other values.
@@ -207,4 +217,4 @@ def search_values_es(
     try:
         return search_values_logic(record_type, value, date_from, date_to)
     except Exception as e:
-        return [{"error": f"Failed to get trend data: {str(e)}"}]
+        return [{"error": f"Failed to search for values: {str(e)}"}]

app/services/health/clickhouse.py

@@ -32,12 +32,13 @@ def get_trend_data_from_ch(
     date_to: str | None = None,
 ) -> dict[str, Any]:
     return ch.inquire(f"""
-        SELECT toStartOfInterval(startDate, INTERVAL 1 {interval}) AS interval,
-        AVG(value), MIN(value), MAX(value), COUNT(*) FROM {ch.db_name}.{ch.table_name}
+        SELECT device, toStartOfInterval(startDate, INTERVAL 1 {interval}) AS interval,
+        AVG(value) AS average, SUM(value) AS sum, MIN(value) AS min,
+        MAX(value) AS max, COUNT(*) AS count FROM {ch.db_name}.{ch.table_name}
         WHERE type = '{record_type}'
         {f"AND startDate >= '{date_from}'" if date_from else ""}
         {f"AND startDate <= '{date_to}'" if date_to else ""}
-        GROUP BY interval ORDER BY interval ASC
+        GROUP BY interval, device ORDER BY interval ASC
     """)
 
 

app/services/health/duckdb_queries.py

@@ -44,13 +44,14 @@ def get_trend_data_from_duckdb(
     date_to: str | None = None,
 ) -> list[dict[str, Any]]:
     result = duckdb.sql(f"""
-        SELECT time_bucket(INTERVAL '1 {interval}', startDate) AS interval,
-            AVG(value) AS average, MIN(value) AS min, MAX(value) AS max, COUNT(*) AS count
+        SELECT device, time_bucket(INTERVAL '1 {interval}', startDate) AS interval,
+        AVG(value) AS average, SUM(value) AS sum,
+        MIN(value) AS min, MAX(value) AS max, COUNT(*) AS count
         FROM read_parquet('{client.parquetpath}')
         WHERE type = '{record_type}'
-            {f"AND startDate >= '{date_from}'" if date_from else ""}
-            {f"AND startDate <= '{date_to}'" if date_to else ""}
-        GROUP BY interval ORDER BY interval ASC
+        {f"AND startDate >= '{date_from}'" if date_from else ""}
+        {f"AND startDate <= '{date_to}'" if date_to else ""}
+        GROUP BY interval, device ORDER BY interval ASC
     """)
     return client.format_response(result)
 

app/services/health/elasticsearch.py

@@ -106,6 +106,7 @@ def get_trend_data_logic(
                     "avg_value": {"avg": {"field": "value"}},
                     "min_value": {"min": {"field": "value"}},
                     "max_value": {"max": {"field": "value"}},
+                    "value_sum": {"sum": {"field": "value"}},
                     "count": {"value_count": {"field": "value"}},
                 },
             },
@@ -121,6 +122,7 @@ def get_trend_data_logic(
                 "avg_value": bucket["avg_value"]["value"],
                 "min_value": bucket["min_value"]["value"],
                 "max_value": bucket["max_value"]["value"],
+                "value_sum": bucket["value_sum"]["value"],
                 "count": bucket["count"]["value"],
             },
         )