Ling0925
/
buster
mirror of https://github.com/buster-so/buster.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

hotfix on sql dialect

This commit is contained in:
dal 2025-07-25 14:31:35 -06:00
parent 4464abfc22
commit 523a6921b1
No known key found for this signature in database
GPG Key ID: 16F4B0E1E9F61122
1 changed files with 1 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
packages/ai/src/agents/think-and-prep-agent/think-and-prep-instructions.ts
View File

@ -398,42 +398,7 @@ Once all TODO list items are addressed and submitted for review, the system will
<sql_best_practices>
- Current SQL Dialect Guidance:
- **Date/Time Functions (PostgreSQL/Supabase)**:
- **\`DATE_TRUNC\`**: Prefer \`DATE_TRUNC('day', column)\`, \`DATE_TRUNC('week', column)\`, \`DATE_TRUNC('month', column)\`, etc., for grouping time series data. Note that \`'week'\` starts on Monday.
- **\`EXTRACT\`**: \`EXTRACT(DOW FROM column)\` (0=Sun), \`EXTRACT(ISODOW FROM column)\` (1=Mon), \`EXTRACT(WEEK FROM column)\`, \`EXTRACT(EPOCH FROM column)\` (Unix timestamp).
- **Intervals**: Use \`INTERVAL '1 day'\`, \`INTERVAL '1 month'\`, etc.
- **Current Date/Time**: \`CURRENT_DATE\`, \`CURRENT_TIMESTAMP\`, \`NOW()\`.
- **Performance Tips**:
- Use indexes on date columns: \`CREATE INDEX ON table (DATE_TRUNC('day', date_col))\` for frequent grouping
- Prefer \`EXISTS\` over \`IN\` for subqueries with large result sets
- Use \`LIMIT\` rather than fetching all rows when possible
- For time ranges, use \`column >= start_date AND column < end_date\` (avoids timezone issues)
- **String Handling**: Use \`ILIKE\` for case-insensitive matching, \`SIMILAR TO\` for regex patterns
- **Aggregations**: Use \`FILTER (WHERE condition)\` for conditional aggregations instead of \`CASE WHEN\`
- **JSON Operations**: PostgreSQL excels at JSON - use \`->\`, \`->>\`, \`@>\`, \`?\` operators for JSON queries
- **Window Functions**: Powerful for analytics - \`LAG()\`, \`LEAD()\`, \`FIRST_VALUE()\`, \`PERCENT_RANK()\`
- **Date Spine Example**: For complete time series, use \`generate_series()\`:
\`\`\`sql
WITH date_spine AS (
SELECT generate_series(
DATE_TRUNC('month', CURRENT_DATE - INTERVAL '11 months'),
DATE_TRUNC('month', CURRENT_DATE),
INTERVAL '1 month'
)::date AS period_date
)
SELECT
ds.period_date,
COALESCE(SUM(t.amount), 0) AS total_amount
FROM date_spine ds
LEFT JOIN schema.transactions t ON DATE_TRUNC('month', t.date) = ds.period_date
GROUP BY ds.period_date
ORDER BY ds.period_date;
\`\`\`
- **Common Gotchas**:
- \`NOW()\` returns timestamp with timezone, \`CURRENT_TIMESTAMP\` is standard SQL
- String concatenation: Use \`||\` not \`+\`
- \`NULL\` comparisons: Use \`IS NULL\`/\`IS NOT NULL\`, never \`= NULL\`
- Performance: Ensure date/timestamp columns used in \`WHERE\` or \`JOIN\` clauses are indexed. Consider functional indexes on \`DATE_TRUNC\` or \`EXTRACT\` expressions if filtering/grouping by them frequently.
${params.sqlDialectGuidance}
- Keep Queries Simple: Strive for simplicity and clarity in your SQL. Adhere as closely as possible to the user's direct request without overcomplicating the logic or making unnecessary assumptions.
- Default Time Range: If the user does not specify a time range for analysis, default to the last 12 months from the current date. Clearly state this assumption if making it.
- Avoid Bold Assumptions: Do not make complex or bold assumptions about the user's intent or the underlying data. If the request is highly ambiguous beyond a reasonable time frame assumption, indicate this limitation in your final response.