Conversation
📝 WalkthroughWalkthroughA new dbt model Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Tip Issue Planner is now in beta. Read the docs and try it out! Share your feedback on Discord. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🧹 Nitpick comments (1)
dbt/models/marts/gold_user_engagement.sql (1)
10-10: Replace positionalGROUP BY 1with an explicit column reference.Ordinal references silently break if the
SELECTlist is reordered, making the model fragile for future edits.♻️ Proposed fix
-GROUP BY 1 +GROUP BY channel🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@dbt/models/marts/gold_user_engagement.sql` at line 10, The model uses a positional GROUP BY ("GROUP BY 1") which is fragile; open dbt/models/marts/gold_user_engagement.sql, identify the SELECT list first expression (the column or expression that the ordinal 1 refers to, e.g., user_id or event_date) and replace "GROUP BY 1" with an explicit "GROUP BY <that_column_or_expression>" (if multiple ordinals were intended, list each actual column name). Ensure you use the exact column identifier from the SELECT (including any alias) so the GROUP BY matches the SELECT output.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@dbt/models/marts/gold_user_engagement.sql`:
- Line 9: The WHERE clause using activity_date >= DATEADD(day, -7, CURRENT_DATE)
is off-by-one and yields 8 days (includes today); update the filter for the
intended 7-day window by either (a) adding an upper bound activity_date <
CURRENT_DATE to get 7 complete days excluding today, or (b) shifting the lower
bound to DATEADD(day, -6, CURRENT_DATE) to include today as the 7th day—modify
the WHERE clause referencing activity_date, DATEADD and CURRENT_DATE accordingly
to match the business requirement.
- Line 9: Replace the warehouse-specific DATEADD usage in the WHERE clause with
dbt's cross-warehouse macro: locate the WHERE filtering on activity_date that
currently uses DATEADD(day, -7, CURRENT_DATE) and call the dbt.dateadd macro
instead (keep the same datepart "day", interval -7, and CURRENT_DATE as the date
argument) so the compiled SQL will work across adapters; update the expression
that references activity_date and CURRENT_DATE accordingly.
- Around line 1-10: The model gold_user_engagement is missing a dbt config block
so it will default to the project-level materialization (likely view) instead of
the intended table; add a top-of-file {{ config(materialized='table') }} block
(before the SELECT) in the gold_user_engagement model to explicitly set
materialized: table, leaving the rest of the query (including
ref('stg_user_activity')) unchanged.
---
Nitpick comments:
In `@dbt/models/marts/gold_user_engagement.sql`:
- Line 10: The model uses a positional GROUP BY ("GROUP BY 1") which is fragile;
open dbt/models/marts/gold_user_engagement.sql, identify the SELECT list first
expression (the column or expression that the ordinal 1 refers to, e.g., user_id
or event_date) and replace "GROUP BY 1" with an explicit "GROUP BY
<that_column_or_expression>" (if multiple ordinals were intended, list each
actual column name). Ensure you use the exact column identifier from the SELECT
(including any alias) so the GROUP BY matches the SELECT output.
| -- Model: gold_user_engagement | ||
| -- User engagement metrics by channel for Marketing dashboard | ||
| SELECT | ||
| channel, | ||
| COUNT(DISTINCT user_id) AS active_users, | ||
| SUM(sessions) AS total_sessions, | ||
| AVG(session_duration_minutes) AS avg_session_duration | ||
| FROM {{ ref('stg_user_activity') }} | ||
| WHERE activity_date >= DATEADD(day, -7, CURRENT_DATE) | ||
| GROUP BY 1 |
There was a problem hiding this comment.
Missing {{ config() }} block — model will not materialize as a table.
The PR metadata specifies materialized: table, but there is no {{ config() }} block in the file. Without it, dbt uses the project-level default (typically view), silently mismatching the intended materialisation.
🔧 Proposed fix
+{{ config(materialized='table') }}
+
-- Model: gold_user_engagement
-- User engagement metrics by channel for Marketing dashboard🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@dbt/models/marts/gold_user_engagement.sql` around lines 1 - 10, The model
gold_user_engagement is missing a dbt config block so it will default to the
project-level materialization (likely view) instead of the intended table; add a
top-of-file {{ config(materialized='table') }} block (before the SELECT) in the
gold_user_engagement model to explicitly set materialized: table, leaving the
rest of the query (including ref('stg_user_activity')) unchanged.
| SUM(sessions) AS total_sessions, | ||
| AVG(session_duration_minutes) AS avg_session_duration | ||
| FROM {{ ref('stg_user_activity') }} | ||
| WHERE activity_date >= DATEADD(day, -7, CURRENT_DATE) |
There was a problem hiding this comment.
Off-by-one: >= DATEADD(day, -7, CURRENT_DATE) spans 8 days, not 7.
With today as the anchor, DATEADD(day, -7, CURRENT_DATE) resolves to 7 days ago. Using >= therefore includes that anchor day plus 7 subsequent days (including today) — a total of 8 days. Additionally, aggregating today's still-accumulating data skews the daily metrics for the Marketing dashboard.
For 7 complete days (exclusive of today):
WHERE activity_date >= DATEADD(day, -7, CURRENT_DATE)
AND activity_date < CURRENT_DATEOr, for a rolling 7-day window ending today inclusive but exactly 7 days:
WHERE activity_date >= DATEADD(day, -6, CURRENT_DATE)Choose whichever matches the business requirement.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@dbt/models/marts/gold_user_engagement.sql` at line 9, The WHERE clause using
activity_date >= DATEADD(day, -7, CURRENT_DATE) is off-by-one and yields 8 days
(includes today); update the filter for the intended 7-day window by either (a)
adding an upper bound activity_date < CURRENT_DATE to get 7 complete days
excluding today, or (b) shifting the lower bound to DATEADD(day, -6,
CURRENT_DATE) to include today as the 7th day—modify the WHERE clause
referencing activity_date, DATEADD and CURRENT_DATE accordingly to match the
business requirement.
🧩 Analysis chain
🌐 Web query:
dbt dateadd macro documentation
💡 Result:
dateadd is now documented as a dbt Core cross-database macro (namespace: dbt), not in dbt_utils (those cross-db macros were removed from dbt_utils starting in v1.0). [1] (docs.getdbt.com)
dbt dateadd macro (Core)
Signature
{{ dbt.dateadd(datepart="day", interval=1, from_date_or_timestamp="..." ) }}Args
datepart: a date/time part (database-specific)interval: integer (positive or negative)from_date_or_timestamp: a date/time expression [1] (docs.getdbt.com)
Examples
{{ dbt.dateadd(datepart="day", interval=1, from_date_or_timestamp="'2016-03-09'") }}
{{ dbt.dateadd(datepart="month", interval=-2, from_date_or_timestamp="'2016-03-09'") }}
``` [1] ([docs.getdbt.com](https://docs.getdbt.com/reference/dbt-jinja-functions/cross-database-macros))
### Sources
- [1] dbt Developer Hub — “Cross-database macros” (includes `dateadd`) ([docs.getdbt.com](https://docs.getdbt.com/reference/dbt-jinja-functions/cross-database-macros))
- [2] dbt-utils README note about cross-database macros moving to dbt Core ([github.com](https://github.com/dbt-labs/dbt-utils?utm_source=openai))
Citations:
- 1: https://docs.getdbt.com/reference/dbt-jinja-functions/cross-database-macros
- 2: https://docs.getdbt.com/reference/dbt-jinja-functions/cross-database-macros
- 3: https://docs.getdbt.com/reference/dbt-jinja-functions/cross-database-macros
- 4: https://docs.getdbt.com/reference/dbt-jinja-functions/cross-database-macros
- 5: https://github.com/dbt-labs/dbt-utils?utm_source=openai
---
🌐 Web query:
`DATEADD function Snowflake Redshift PostgreSQL BigQuery compatibility`
💡 Result:
### `DATEADD` compatibility overview (Snowflake vs Redshift vs PostgreSQL vs BigQuery)
| Engine | Has `DATEADD`? | Add *N* units to a date/time |
|---|---:|---|
| **Snowflake** | Yes | `DATEADD(part, value, expr)` (aliases: `TIMEADD`, `TIMESTAMPADD`) [1] |
| **Amazon Redshift** | Yes | `DATEADD(datepart, interval, expr)` [2] |
| **PostgreSQL** | **No** (built-in) | Use arithmetic: `timestamp + interval '1 day'`, `date + integer` (days), etc. [5] |
| **BigQuery (GoogleSQL)** | **No** (`DATEADD` name) | Use typed functions: `DATE_ADD(date, INTERVAL n part)`, `DATETIME_ADD(...)`, `TIMESTAMP_ADD(...)`, `TIME_ADD(...)` [3][4] |
---
## Syntax mappings
### Snowflake → Redshift (nearly 1:1)
Both accept the same 3-argument pattern: `(part, number, expression)` [1][2].
```sql
-- Snowflake / Redshift
DATEADD(day, 7, some_ts)Snowflake / Redshift → BigQuery
BigQuery uses *_ADD(expr, INTERVAL n PART) (note the INTERVAL clause and PART position) [3][4]. Google’s Snowflake migration guide summarizes this mapping as:
DATEADD(part, value, dateOrTime)→DATE_ADD(date, INTERVAL value part)[6]
-- BigQuery
DATE_ADD(some_date, INTERVAL 7 DAY)
TIMESTAMP_ADD(some_ts, INTERVAL 7 DAY)Snowflake / Redshift → PostgreSQL
PostgreSQL typically uses + interval (and for date, + integer adds days) [5].
-- PostgreSQL
some_ts + interval '7 day'
some_date + 7Key behavioral gotchas (portability)
-
Return type differences when input is
DATEand you add sub-day units- Snowflake: adding
hour/minute/secondto aDATEreturns a timestamp (TIMESTAMP_NTZ) starting at midnight [1]. - Redshift:
DATEADDreturnsTIMESTAMPfor date inputs (date becomes timestamp at00:00:00) [2].
- Snowflake: adding
-
Month/quarter/year end-of-month behavior
- BigQuery: for
MONTH/QUARTER/YEAR, if the target month is shorter, the result becomes the last day of that month [3]. - Snowflake: warns that
year/quarter/monthcan shift the day-of-month when the result month has fewer days [1]. - PostgreSQL interval math explicitly uses “last day of month” when needed while applying the months field of an interval [5].
- BigQuery: for
-
BigQuery
TIMESTAMP_ADDsupports only up toDAYTIMESTAMP_ADD(..., INTERVAL n DAY/HOUR/MINUTE/...)is supported, but notMONTH/QUARTER/YEARforTIMESTAMP_ADD[4]. (UseDATETIME_ADD, or convert toDATETIME/DATEwhere appropriate.)
Sources: Snowflake DATEADD [1], Redshift DATEADD [2], BigQuery DATE_ADD [3], BigQuery TIMESTAMP_ADD [4], PostgreSQL date/time operators & interval rules [5], BigQuery Snowflake translation guide [6].
Use the {{ dbt.dateadd() }} macro instead of DATEADD for cross-warehouse compatibility.
DATEADD(datepart, interval, date) is native to Snowflake and Redshift but PostgreSQL does not have a built-in DATEADD function, and BigQuery uses DATE_ADD/DATETIME_ADD/TIMESTAMP_ADD. dbt provides a cross-warehouse {{ dbt.dateadd() }} macro that compiles to the correct dialect for each adapter.
🔧 Proposed fix using dbt's built-in macro
-WHERE activity_date >= DATEADD(day, -7, CURRENT_DATE)
+WHERE activity_date >= {{ dbt.dateadd(datepart="day", interval=-7, from_date_or_timestamp=current_date) }}📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| WHERE activity_date >= DATEADD(day, -7, CURRENT_DATE) | |
| WHERE activity_date >= {{ dbt.dateadd(datepart="day", interval=-7, from_date_or_timestamp="CURRENT_DATE") }} |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@dbt/models/marts/gold_user_engagement.sql` at line 9, Replace the
warehouse-specific DATEADD usage in the WHERE clause with dbt's cross-warehouse
macro: locate the WHERE filtering on activity_date that currently uses
DATEADD(day, -7, CURRENT_DATE) and call the dbt.dateadd macro instead (keep the
same datepart "day", interval -7, and CURRENT_DATE as the date argument) so the
compiled SQL will work across adapters; update the expression that references
activity_date and CURRENT_DATE accordingly.
1 participant
Summary
AI-assisted pipeline: User engagement metrics by channel (7-day window) for Marketing dashboard. Includes active users, sessions, and avg session duration.
Tags:
engagement,marketingCriticality:
P1Models (1)
gold_user_engagementLineage
Data Quality Tests (2)
Generated by Data Portal
Summary by CodeRabbit