open/llm-ingestion-okf
1
0
Fork 0
Code Issues Releases 4 Activity

test(gates): retire the K2 track; re-measure the retrieval gate's premises for BM25

Browse source 
Operator decision 2026-09-21: the test track built on material tied to the
operator's employer (K2) is retired -- not re-measured, not frozen. Public
tests and gates run on invented material.

Retrieval gate:
- The four FUSION_PREMISE xfails are gone and pass through their INPUTS: the
  synthetic MISS, LOOKUP and QUOTA bundles were re-measured for BM25 (the
  miss fasit no longer shares the rare word `maa`; lookup and quota decoys
  carry the question's words so each partition and the quota decide their
  own fixture). SPECS_SHA256 moved with them. Rows 2 and 3 green again.
- Row 7's mutants M04, M06, M07, M08, M10 now patch `bm25`, the code the
  default runs. Three survive with 0 ranks moved (passage body, title
  weight, bm25.RRF_K), each with its mechanism printed. M07 was not forced:
  every synthetic body carries its title as a heading.
- Row 9 (K2) removed; row 8 requires `wiki-20` alone, the `r761` and
  `vegnormal` adapters are gone. Chose the broad reading of "K2" because the
  operator decision defines it as employer-tied material and the order's
  grep includes `vegnormal`.

Also removed: tests/test_default_bundle_pin.py, the K2 arms of
test_okf_consume, the four real-arm tests of test_quality, the R761 soft
hyphen test, the N101/N200 delivery tests and okf_accounting_gate's default
real corpus (and H5's guard, which only existed for those defaults). Two
fixtures carrying road-standard identifiers are rewritten with invented ones.

Gate after: 1 10/10, 2 7/7, 3 5/5, 4 6/6, 5 0/1, 6 10/10, 7 11/14,
8 NOT RUN -> GATE RED: rows 5, 7, 8. Suite 2423 passed, 1 skipped,
0 xfailed.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
Kjell Tore Guttormsen 2026-09-21 10:05:43 +02:00
commit 3d149f955a
12 changed files with 288 additions and 1096 deletions
Download patch file Download diff file Expand all files Collapse all files

29
CLAUDE.md
View file

@ -376,8 +376,9 @@ concept byte-identical**. The same run found something this work did NOT cause:
the pinned artifact `K2-bundle-default-20260912` was written **2026-09-09
21:38**, two days before `ed0418f` (K3-22) changed `title:` quoting, so it
differs from what HEAD produces on **42 concept files** -- and
`tests/test_default_bundle_pin.py` stays green because it pins the count and
the hit@8 ranks, not the bytes. Re-pinning it is the OPERATOR's. Report:
`tests/test_default_bundle_pin.py` stayed green because it pinned the count and
the hit@8 ranks, not the bytes. (That pin was REMOVED 2026-09-21 with the
retired K2 test track, v1.1 K; the artifact is no longer read by anything.) Report:
`docs/2026-09-15-f1-f2-gaten-og-kodefencen.md`.
**Boundary rule (non-negotiable, zero overlap):** `llm-ingestion-guard`
@ -721,8 +722,8 @@ and fixtures, never code.
xargs shasum -a 256 | shasum -a 256` from inside the bundle, under which the
previous default is `862116da16e422f6...`. The pinned artifact lives at
`~/corpora/okf-telling-20260829/K2-bundle-default-20260910` and
`tests/test_default_bundle_pin.py` holds its concept count AND its per-row
hit@8 ranks -- the count alone survived a configuration that lost a rank,
`tests/test_default_bundle_pin.py` (removed 2026-09-21, v1.1 K) held its
concept count AND its per-row hit@8 ranks -- the count alone survived a configuration that lost a rank,
which is how a previous round's regression hid. Since 2026-09-10 it also
holds the KNOWN-NEGATIVE on the same bytes: read with
`--no-tie-shared-rank`, the shipped default bundle reproduces the very fall
@ -1315,7 +1316,7 @@ and fixtures, never code.
- **Judge the RETRIEVAL: `python3 tools/okf_retrieval_gate.py` (2026-09-19).**
A separate question from `okf quality` and a separate command: quality asks
what a bundle looks like, this asks whether the payload for a question
carries the fasit. **Written RED, no capability**: nine rows, exit 0 only
carries the fasit. **Written RED, no capability**: eight rows, exit 0 only
when all are green, 1 otherwise, 2 on wrong input, `--json`. Rows 1-4, 6, 7
run against a synthetic corpus this repo GENERATES and six sets it ships
pinned by sha256 -- no network, no private corpus, no clock; a set whose
@ -1323,10 +1324,20 @@ and fixtures, never code.
an INPUT and never a constant here** (`okf_consume_measure.py`'s rule, and
this repo is public). **THE CORPUS IS PINNED THE SAME WAY** since
2026-09-19 (`SPECS_SHA256`). Today (measured on the default run
2026-09-20): **1 (10/10) - 2 (7/7) - 3 (5/5) - 4 (6/6) - 5 (0/1) -
6 (10/10) - 7 (12/14) - 8 (0 of 3 sets, NOT RUN without `--real`; 44 of 64
questions the day all three were given to it, 2026-09-19) - 9 (0/6)**,
`GATE RED: rows 5, 7, 8, 9`.
2026-09-21, v1.1 K): **1 (10/10) - 2 (7/7) - 3 (5/5) - 4 (6/6) - 5 (0/1) -
6 (10/10) - 7 (11/14) - 8 (0 of 1 set, NOT RUN without `--real`)**,
`GATE RED: rows 5, 7, 8`.
**THE K2 TEST TRACK IS RETIRED (operator 2026-09-21, v1.1 K)**: material
tied to the operator's employer is not re-measured and not frozen, and
public tests and gates run on invented material. Row 9 (K2) and the `r761`
and `vegnormal` adapters of row 8 are gone (row 8 requires `wiki-20` alone),
and so are the tests that read the K2 bundles, the road-standard builds or
the R761/N101/N200 deliveries; `okf_accounting_gate.py` has no default real
corpus. The synthetic corpus was re-measured for BM25 (`MISS`, `LOOKUP`,
`QUOTA`), so rows 2 and 3 are green through their own fixtures again, and
row 7's mutants patch `bm25` where the default runs there; three survive
(passage body, field title weight, `bm25.RRF_K`) with 0 ranks moved. What
the text below says about rows 8/9, K2 and the three sets is history.
**FOUR OF EIGHT CHEATING ATTACKS WENT THROUGH IT AND ARE CLOSED
(2026-09-19).** PM's checkpoint on `2c8296b` found rows 3, 5, 7 and 8 could
go GREEN without one label becoming true or one concept ranking better, and