Shay
f87cd68f6b
Merge pull request #884 from AssetOverflow/feat/generalization-benchmark-manifests
2026-06-23 06:21:40 -07:00
Shay
67f9b63916
fix(evals): align benchmark manifests and gitignore with sealed-holdout policy
...
- Adds benchmark cache ignore rule to extend ADR-0119.7 discipline
- Removes sealed slice references from manifest smoke fixture lines
- Clarifies openbookqa and para_mawps license gates
2026-06-23 06:12:50 -07:00
Shay
34dc0d64c5
feat(evals): add generalization benchmark manifests + policy (PR-1 of 2)
...
Adds policy document and sealed manifest records for the first 8
external audit datasets. No data is vendored. Local cache paths are
gitignored. Fetch/verify scripts and smoke fixtures come in PR-2.
Datasets: GSM1K, ASDiv, SVAMP, PARA-MAWPS, ARC-Easy, ARC-Challenge,
OpenBookQA, CLUTRR
2026-06-23 05:59:36 -07:00
Shay
3fc080d3e2
Merge pull request #883 from AssetOverflow/codex/quantity-entity-binding-candidate-operator
2026-06-23 05:54:12 -07:00
Shay
28deb5664b
style(kernel): place quantity-entity builder before exports
2026-06-23 05:43:17 -07:00
Shay
cead96596c
feat: implement quantity_entity_binding_candidate.v1 operator
...
- Implement CandidateOperatorPolicy and cue dataclass for quantity entity binding
- Add build_quantity_entity_binding_candidate constructor with strict refusal checks
- Bump CANDIDATE_OPERATOR_SET_VERSION to candidate_operators.v2
- Update exact export and static table shape tests
- Reconcile stale static guards across binding replay adapters
- Provide full explicit determinism and failure mode test coverage
2026-06-23 05:37:08 -07:00
Shay
846fe468e2
Merge pull request #882 from AssetOverflow/codex/adr-0234-second-candidate-operator-selection
2026-06-23 01:02:57 -07:00
Shay
afbc5aef88
Merge branch 'main' into codex/adr-0234-second-candidate-operator-selection
2026-06-23 00:52:38 -07:00
Shay
038c8bc457
docs: select second candidate operator
2026-06-23 00:49:26 -07:00
Shay
7f50368540
Merge pull request #881 from AssetOverflow/reconcile-bound-evidence-guards
2026-06-23 00:37:08 -07:00
Shay
df72c71182
test(kernel): reconcile bound evidence spine static guards
2026-06-23 00:28:25 -07:00
Shay
ff1280ffa2
Merge pull request #880 from AssetOverflow/feat/bound-practice-episode-sealing
2026-06-23 00:20:31 -07:00
Shay
b9a6eb9676
fix(kernel): fail-closed bound trace structural validation
...
Return PracticeTraceRefusal before dereferencing bindings or operator
results when structural type/shape checks fail. Guard seal_bound zip
against binding_result_count_mismatch. Add five refusal-without-exception
tests for malformed bound inputs.
2026-06-23 00:11:14 -07:00
Shay
484e8ff9fe
docs+kernel: support bound practice episode sealing
...
Extends SealedPracticeTrace for externally bound candidate episodes per
ADR-0233. Adds candidate_attempt_binding_ids to trace identity, bound trace
input/seal entry points, and end-to-end bound episode tests without mutating
GeometricSearchRun.candidate_attempts.
2026-06-23 00:04:26 -07:00
Shay
5b30ec877f
Merge pull request #879 from AssetOverflow/feat/replay-bound-attempt-input
2026-06-22 23:49:33 -07:00
Shay
708237525c
test(kernel): cover bound replay adapter input
2026-06-22 23:39:41 -07:00
Shay
0e638039f4
feat(kernel): support bound attempts in replay adapter input
2026-06-22 23:38:51 -07:00
Shay
27e5bc105c
fix(kernel): remove bound replay adapter stub
2026-06-22 23:35:44 -07:00
Shay
c0307ae702
feat(kernel): add stub for bound replay adapter input
2026-06-22 23:31:50 -07:00
Shay
4ce2793c3c
Merge pull request #878 from AssetOverflow/feat/run-attempt-binding-shell
2026-06-22 23:26:22 -07:00
Shay
76bb756519
test(kernel): cover run-attempt binding shell
2026-06-22 23:16:02 -07:00
Shay
f8d496ff9e
feat(kernel): implement run-attempt binding shell
2026-06-22 23:12:16 -07:00
Shay
d0d7df3857
fix: add generate/run_attempt_binding.py + complete real tests (no placeholders, full coverage)
2026-06-22 23:05:42 -07:00
Shay
fbf9b18868
fix: replace placeholder with full ADR-0232 implementation of run_attempt_binding (generate/ + tests/)
2026-06-22 23:03:04 -07:00
Shay
65505e059d
feat(kernel): implement inert run-attempt binding shell per ADR-0232
2026-06-22 22:57:22 -07:00
Shay
32927611ff
Merge pull request #877 from AssetOverflow/docs/run-attempt-binding-boundary
2026-06-22 22:10:00 -07:00
Shay
fc78db7500
docs(kernel): define candidate-attempt run binding boundary
2026-06-22 19:50:20 -07:00
Shay
4bbc27a55a
Merge pull request #876 from AssetOverflow/feat/missing-role-candidate-operator
...
feat(kernel): implement missing-role candidate operator shell
2026-06-22 19:39:19 -07:00
Shay
1d9e40602c
feat(kernel): implement missing-role candidate operator shell
...
Implements ADR-0231's inert missing_role_candidate.v1 operator shell for
direction_unbound residuals under unary_delta_transition. Adds deterministic
operator-set identity, candidate reconstruction with split digests,
CandidateAttempt-compatible output, typed refusals, and isolation tests.
2026-06-22 19:27:41 -07:00
Shay
5bb7c62006
Merge pull request #875 from AssetOverflow/docs/first-candidate-operator-boundary
...
docs(kernel): define first candidate-operator boundary
2026-06-22 19:22:14 -07:00
Shay
7fa49c6099
docs(kernel): define first candidate-operator boundary
2026-06-22 19:11:05 -07:00
Shay
7da4b170a0
Merge pull request #874 from AssetOverflow/feat/sealed-practice-trace-shell
...
feat(kernel): implement inert SealedPracticeTrace shell
2026-06-22 18:54:49 -07:00
Shay
520e2c8237
fix(kernel): validate sealed trace replay record ids
2026-06-22 18:44:59 -07:00
Shay
d4379a6ece
Merge branch 'main' into feat/sealed-practice-trace-shell
2026-06-22 18:33:26 -07:00
Shay
a1de11e0e3
feat(kernel): implement inert SealedPracticeTrace shell
...
Adds immutable practice-trace input, sealed-trace, and trace-refusal
records with deterministic identity-chain validation after the Contract/
Proof Replay Adapter, as authorized by ADR-0230.
2026-06-22 18:20:52 -07:00
Shay
9f5871cf00
Merge pull request #873 from AssetOverflow/docs/sealed-practice-trace-boundary
...
docs(kernel): define sealed practice trace boundary
2026-06-22 17:31:04 -07:00
Shay
60a118c1a4
docs(kernel): define sealed practice trace boundary
...
Adds ADR-0230 defining the immutable SealedPracticeTrace evidence
envelope after the Contract/Proof Replay Adapter in the residual-gated
practice loop. Docs-only; authorizes the inert shell implementation PR.
2026-06-22 17:18:09 -07:00
Shay
e3defda7e0
Merge pull request #872 from AssetOverflow/feat/replay-adapter-shell
...
feat(kernel): implement diagnostic replay adapter shell
2026-06-22 15:42:49 -07:00
Shay
feb36cfdbb
feat(kernel): implement diagnostic replay adapter shell
...
Adds the ADR-0229-authorized Contract/Proof Replay Adapter diagnostic
boundary after GeometricSearchRun: deterministic input/result/refusal
records, candidate_organ/contract_replay_target binding via static
allowlist, strict run/attempt/candidate identity validation, ADR-aligned
replay_disposition on refusals, vacuous-proof closure only with explicit
schema declaration, and injection-based disposition classification
without candidate generation, search execution, repair, answer
production, or runtime mutation.
2026-06-22 15:18:22 -07:00
Shay
cc0e196106
Merge pull request #871 from AssetOverflow/docs/replay-adapter-boundary
...
docs(kernel): define contract/proof replay adapter boundary
2026-06-22 14:52:42 -07:00
Shay
6aa78f7039
docs(kernel): define contract/proof replay adapter boundary
2026-06-22 14:43:58 -07:00
Shay
5fcb21add2
Merge pull request #870 from AssetOverflow/feat/geometric-search-run-shell
...
feat(kernel): implement inert GeometricSearchRun trace shell
2026-06-22 14:19:24 -07:00
Shay
93ba988c1e
feat(kernel): implement inert GeometricSearchRun trace shell
2026-06-22 14:09:52 -07:00
Shay
6aab3db7aa
Merge pull request #869 from AssetOverflow/docs/geometric-search-run-envelope
...
docs(kernel): define inert GeometricSearchRun envelope
2026-06-22 13:50:13 -07:00
Shay
91c290a11a
docs(kernel): define inert GeometricSearchRun envelope
2026-06-22 13:39:13 -07:00
Shay
f19b5a044e
Merge pull request #868 from AssetOverflow/feat/compute-budget-decision
...
feat(kernel): implement diagnostic-only ComputeBudgetDecision
2026-06-22 13:23:45 -07:00
Shay
fcac436f7d
feat(kernel): implement diagnostic-only ComputeBudgetDecision
2026-06-22 13:13:49 -07:00
Shay
7e4ba10c7a
docs(kernel): ratify diagnostic ComputeBudgetPolicy envelope
...
Ratifies ADR-0227 and authorizes exactly one next implementation PR: diagnostic-only ComputeBudgetDecision.
No ComputeBudgetDecision implementation, GeometricSearchRun, search execution, candidate generation, repair, Workbench, runtime/serving behavior, teaching/proposal/report/eval mutation, answer production, or unreviewed artifact mutation is authorized.
2026-06-22 12:46:25 -07:00
Shay
f3dad63907
Merge pull request #866 from AssetOverflow/docs/compute-budget-policy-envelope
...
docs(kernel): define diagnostic ComputeBudgetPolicy envelope
2026-06-22 12:38:05 -07:00
Shay
94c474aee7
docs(kernel): define diagnostic ComputeBudgetPolicy envelope
2026-06-22 11:58:22 -07:00
