Skip to content

feat(cross-surface): stage tpch and tpcds gates, record CI budget - #2428

Merged
joeharris76 merged 8 commits into
developfrom
fix/df-parity-staged-tpch-tpcds
Oct 1, 2026
Merged

joeharris76 merged 8 commits into
developfrom
fix/df-parity-staged-tpch-tpcds

Conversation

@joeharris76

Copy link
Copy Markdown
Collaborator

Wire tpch and tpcds STAGED_GATES on the Q-prefix maps. tpch runs
unseeded-vs-unseeded at SF=0.01 (41/44 cells pass; fixed-stream needs
seeded DF overrides first). tpcds full-99 staged at SF=0.01 (~13s
wall); only Q38/Q88 pass, so the 10-15 blocking subset is deferred
to the promotion item. Module docstring states the staged status
and honest oracle limits. No GATES promotion, no CI wiring.

Wire tpch and tpcds STAGED_GATES on the Q-prefix maps. tpch runs
unseeded-vs-unseeded at SF=0.01 (41/44 cells pass; fixed-stream needs
seeded DF overrides first). tpcds full-99 staged at SF=0.01 (~13s
wall); only Q38/Q88 pass, so the 10-15 blocking subset is deferred
to the promotion item. Module docstring states the staged status
and honest oracle limits. No GATES promotion, no CI wiring.
@chatgpt-codex-connector

chatgpt-codex-connector Bot commented Sep 27, 2026 •

Copy link
Copy Markdown

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review Status Commit Review trigger
📝 Code Review ✅ Completed 2026-09-27T15:54:12.544342Z 0ccf5c4 PR opened
ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 0ccf5c47a3

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment thread benchbox/core/equivalence/cross_surface.py
Comment thread benchbox/core/equivalence/builders/nyctaxi.py Outdated
Comment thread benchbox/core/equivalence/builders/tpcds.py Outdated
Comment thread benchbox/core/equivalence/builders/tpch_skew.py
Comment thread benchbox/core/equivalence/cross_surface.py Outdated
Joe Harris and others added 3 commits September 27, 2026 13:25
Reuse _assemble_simple_duckdb_cell for the TPC-H, TPC-DS, and TPC-H
Skew builders so the duplicate-code delta gate stays flat. The
TPC-H unseeded-defaults rationale and scale seam stay in place.
Record the three thin per-benchmark delegations in the scoped
duplicate ignore list.
Port the expression Q15 relative-tolerance max filter and both-family
Q17 empty-set NULL preservation. The tpch staged gate now runs green
(44/44 cells, 0 divergent, 0 vacuous) at SF=0.01 unseeded.
Take the staged-small builder fixes (seeded SQL windows with DF
parse-back, active-table loading, TPC-H Skew scale seam) and keep the
TPC-H scale seam. Render the TPC-DS reference in the DuckDB dialect
so Q90's alias parses. Replace the work-item handoff comment with the
durable blocking-subset rationale. Regenerate the oracle coverage map.
@joeharris76

Copy link
Copy Markdown
Collaborator Author

Maintainer review: addressed all five threads in 3200d44. Adopted the staged-small builder fixes (seeded SQL windows with DF parse-back, active-table loading, skew scale seam) and kept the TPC-H Q11 scale seam; TPC-DS reference now renders with dialect=duckdb (Q90 alias parses); the gate comment states the durable blocking-subset rationale (only Q38/Q88 pass today); coverage map regenerated (tpch/tpcds staged). Threads resolved. CI re-running; enqueuing after green.

…y oracle

Staging tpch/tpcds gates exposed a generator blind spot: provenance
rendered only when cross-surface was primary, so tpch/tpcds rows showed
no provenance despite registered gates. Read the axis live from gate
metadata for every registered gate and pin the updated contract.
@joeharris76

Copy link
Copy Markdown
Collaborator Author

Status note (takeover sweep): the medium-test failure on this branch is a stale cross-surface applicability pin. This branch predates the staged tpch/tpcds gate registration landing via the current queue batch (2440 merged; 2427/2394/2441/2443 queued). After that batch drains, rebase this branch onto develop and run make cross-surface-applicability-report to refresh the artifact and pins, then re-push. No code fix needed.

Develop already stages the TPC-H, TPC-DS, NYC Taxi, TSBS, and TPC-H Skew gates
with their parameter and NULL fixes, so take its versions. The remaining
change discloses surface provenance for every registered gate and regenerates
the oracle coverage map.
@joeharris76
joeharris76 added this pull request to the merge queue Oct 1, 2026
Merged via the queue into develop with commit 1c0b148 Oct 1, 2026
40 checks passed
@joeharris76
joeharris76 deleted the fix/df-parity-staged-tpch-tpcds branch October 1, 2026 02:42
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant