Eval catalog plan versus direct brief A/B scaffold - #58
Draft
myobie wants to merge 8 commits into
Draft
Conversation
# Conflicts: # AGENT-SPEC.md # CATALOG.md # README.md # bin/check-corpus.sh # evidence/harness-exclusions.tsv
myobie
marked this pull request as ready for review
August 3, 2026 16:20
Collaborator
Author
|
Moved this shared PR from draft to ready at the unchanged accepted head |
myobie
marked this pull request as draft
August 3, 2026 16:51
Collaborator
Author
|
Returning this shared PR to draft at unchanged head |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Outcome
This draft preserves the realistic model-free catalog-plan versus direct-brief comparison while adopting the accepted Resource-linked PR115 discovery contract.
mainnormally at merge commit17bc728; no force-push or history rewrite.resource "receipt-report" _tag="plan" uri="file:plans/receipt-report/plan.kdl".plan.kdlowns identity, owner, versions, parents, reasons, and either external Markdowncontentor inlineintent; the Agent Resource owns only its local role/link.st2 message sendoperations withinReplyTolineage, then recovers them throughmessage ls|read.plan-refand agent-owned inline plan truth are absent.Model-free comparison result
The conclusion remains
no-measured-advantagefor cold resume, intent recovery, or acceptance evidence. The plan adds static schema/graph validation and resolved-content provenance. Neither read-only plan inspection nor direct-message delivery reports worker acceptance.Plain copied folders remain sufficient and
casRequiredis false.Exact pairing
9fae14a192a1f11074de0ef2044e3235017bd4768a76b6e71355140e5b89cd9313fcfd88c82b5cad214e08874720bc546d4adf7d7977e614237baf7989cc09f6932cd991f497a7535c1d1425491c28cded9172ad63afaf1665ecfe22b61aeca76160c4cf98544682562b57cThe contract stores no content digest or historical record, so it cannot prove that an earlier declaration, parent link, or content file stayed unchanged. The repository-wide released runner remains
0fed14b; the experimental8a76b6eartifact is isolated to this cell.Validation
st2 eval ./cells/catalog-plan-vs-direct-brief/ --keep— 24 PASS / 0 FAIL / 24 gating judges.contentand inlineintentboth passvalidate|list|show|inspect, with catalog bytes unchanged.0fed14brunner:bin/check-corpus.sh— PASS, 60 maintained cells, 119 KDL files, 12 nested catalogs.git diff --check: pass.Honest limits
The reference implementation proves the frozen task and arm-neutral judges are valid; it is not substituted for two agent executions. Correctness, coordination messages/bytes, model input/output tokens, cost, and wall duration remain unresolved provider-backed endpoints. A live A/B requires separate authorization naming the model, effort, per-arm budgets, order/counterbalancing, spend ceiling, cleanup, and rollback.
This PR remains draft and unmerged pending Nathan review of the exact pair.