S2: recover food-set and charity-beneficiary lists (P61 144/180) - #174
Merged
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Product
/recallrecovers beneficiary organization sets for who/which beneficiary questions. Frozen skip-ingest store already had John's raise-for objects (dog shelter, homeless, children's hospital); leftover covering was answering with the CS:GO tournament slogan.Skip-ingest 180 on this SHA: 144/180 vs P59 143/180. Unique CORRECT +1 (
conv-47-q22). Unique leftover losses none. MH 24/33, OD 4/11, SH 85/98, temporal 31/38.This is generic S2 enumerate, not leftover covering and not a LoCoMo gold dictionary. Food-set work on this branch did not flip the 180 (judge completeness + WRITE-missing gold); p60/p60b 143/180 are not pins.
90% on this 180 is 162/180. Public LoCoMo n=1540 is still 11.4%. Do not treat 144/180 as 90% or as beating Mem0. README published-% / 1×30 70% are not replaced.
Changes
looksBeneficiarySetQuery— who/which/what +beneficiaries/beneficiary.recoverBeneficiarySlots/beneficiaryObjectsFromContent— raise/for-cues; thin-stop charity/CS:GO/tournament; cap 6.leftoverCoveringKeepTypedAnswerkeeps a ≥2 affiliation join.Test plan
gofmton touched filesgo vet ./internal/memory/ ./cmd/api ./cmd/workergo test ./internal/memory/(23.5s, green)dog shelter, homeless, children's hospital(not CS:GO); P59/P60 holds (food q18, soda/candy, Audrey collars, James tricks, Maria dogs, Jolene snakes, dinner leftover)locomo-s0-diag-mh-135-p61-product-recall-s1-02435b144/180, unique +1/−0 vs P59origin/dev(notmain)Linear / tracking
Risk / follow-ups
conv-26-q39) and who-told (conv-49-q78) if gold is in the frozen store.main.