Repository navigation
Conversation
- query_db now accepts {"collection": ..., "pipeline": [...]} for MongoDB
and runs it via aggregate(); documented in the tool schema and prompt.
- Mongo find() no longer silently caps results at 5 documents, matching
SQL behaviour of returning every row.
- DAB_PERSISTENT_DBS env var skips reload/cleanup of Mongo and Postgres
databases that already exist, so repeated runs reuse loaded data.
Needed by the bank freshness datasets, whose Mongo-only variants rely on
aggregation queries.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SQhxfVKEX2459gdzzSfZEw
Three variants of the same 48 time-sensitive banking questions, each with its own db_config.yaml, db_description.txt, ground_truth.csv and validate.py per query: - query_bank_fresh_direct: six source systems (Postgres core banking, SQLite cards/payments, DuckDB lending/insurance, Mongo CRM) - query_bank_fresh_live: single Mongo collection (bank_live) - query_bank_fresh_warehouse: single Mongo collection plus _meta (bank_warehouse) Agent run logs are intentionally left out, as for the other datasets. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01SQhxfVKEX2459gdzzSfZEw
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds the bank freshness test: 48 time-sensitive banking questions, each shipped over three database layouts so the same questions can be run against different backends.
query_bank_fresh_direct: six source systems (Postgres core banking, SQLite cards/payments, DuckDB lending/insurance, Mongo CRM)query_bank_fresh_live: single Mongo collection (bank_live)query_bank_fresh_warehouse: single Mongo collection plus_meta(bank_warehouse)Each query directory has
query.json,ground_truth.csvandvalidate.py, matching the existing dataset layout. Binary datasets (.db,.sql,.bson) go through LFS per.gitattributes. Agent run logs are excluded, as for the other datasets.Scaffold changes
The Mongo-only variants rely on aggregation queries, so this also includes:
query_dbaccepts{"collection": ..., "pipeline": [...]}for MongoDB and runs it viaaggregate(); documented in the tool schema and prompt examples.find()no longer silently caps results at 5 documents, matching SQL behaviour.DAB_PERSISTENT_DBSenv var skips reload/cleanup of Mongo and Postgres databases that already exist, so repeated runs reuse loaded data.🤖 Generated with Claude Code
https://claude.ai/code/session_01SQhxfVKEX2459gdzzSfZEw