feat(packs): ADR-0100/0101/0102 — three sibling domain ratifications
Ratifies the remaining three sibling domains as reasoning-capable
under ADR-0091's Domain Pack Contract v1, using the template
ADR-0097 established for mathematics_logic. The capability ledger
now has four reasoning-capable rows backed by validated contracts.
ADR-0100 physics (en_physics_v1):
domain_id: physics
claimed_operators: causal, modal
teaching_chains: [physics_chains_v1]
eval_lanes: foundational_physics_ood, inference_closure,
fabrication_control
9/9 predicates pass
ADR-0101 systems_software (en_systems_software_v1):
domain_id: systems_software
claimed_operators: transitive, causal
teaching_chains: [systems_software_chains_v1]
eval_lanes: symbolic_logic, inference_closure, fabrication_control
9/9 predicates pass
ADR-0102 hebrew_greek_textual_reasoning (FIRST MULTI-PACK ratification):
domain_id: hebrew_greek_textual_reasoning
claimed_operators: causal, contradiction
teaching_chains: [hebrew_greek_textual_reasoning_chains_v1]
eval_lanes: inference_closure, fabrication_control
(universal lanes only — language-specific fluency lanes lack
holdout splits; a separate ADR adds those when holdouts ship)
packs: grc_logos_micro_v1, grc_logos_cognition_v1,
he_logos_micro_v1, he_core_cognition_v1
all four pack contracts identical (uniformity invariant pinned);
all four 9/9 predicates pass
pre-existing gap: hebrew/greek manifests lacked a provenance field
entirely; ratification fills that uniformly across the four packs
44 new ratification tests in test_adr_0100_0102_sibling_ratifications.py:
- 6 parametrized 9-predicate validation tests (one per pack)
- 21 per-domain ledger status assertions (status, reasoning_capable,
expert_demo gated, no_open_gaps, provenance points at correct ADR,
operator_chain_coverage, intent_shapes minimum) — 7 cases × 3 domains
- 15 per-domain contract field shape assertions (teaching_chains,
eval_lanes, splits coverage, axioms/rules null, primary reviewer) —
5 cases × 3 domains
- 2 ADR-0102 multi-pack uniformity invariants (all four packs carry
the contract; contracts identical across packs)
Capability ledger after ratification:
systems_software : reasoning-capable
mathematics_logic : reasoning-capable
physics : reasoning-capable
hebrew_greek_textual_reasoning : reasoning-capable
philosophy_theology : reasoning-capable (no contract; pre-existing)
Lane SHA pin update:
- public_demo pin refreshed (21751aaf.. → 71090323..) — the
ratification adds new manifest fields (provenance,
domain_contract_*) that surface in pack-related demo paths;
intentional ADR-tracked change per the verifier doctrine
Smoke 67/67, packs 6/6, sibling ratifications 44/44, cognition eval
byte-identical 100/100/100/100; all 6 lanes match pinned SHAs:
reviewer_registry 681a2aab..
miner_loop_closure 9f071733..
domain_contract_validation f9c06cde..
fabrication_control_summary 01e1b6b7..
demo_composition 27d83824..
public_demo 71090323..
This commit is contained in:
Shay
parent
a21d31a95c
commit
b9a6f2ddb5
12 changed files with 692 additions and 8 deletions
|
|
@ -0,0 +1,96 @@
|
|||
# ADR-0100 — Physics Reasoning-Capable Ratification
|
||||
|
||||
**Status:** Proposed
|
||||
**Date:** 2026-05-21
|
||||
**Author:** CORE agents + reviewers
|
||||
**Depends on:** ADR-0091, ADR-0092, ADR-0093, ADR-0096, ADR-0097
|
||||
|
||||
---
|
||||
|
||||
## Context
|
||||
|
||||
The physics substrate is structurally complete:
|
||||
|
||||
- `language_packs/data/en_physics_v1/` ships with manifest, lexicon, glosses.
|
||||
- `teaching/domain_chains/physics_chains_v1.jsonl` exists.
|
||||
- `evals/foundational_physics_ood/` exists with dev/public/holdouts.
|
||||
- `docs/gaps.md` marks every physics gap closed:
|
||||
`gap:physics_pack_absent`, `gap:physics_causal_chains_below_threshold`,
|
||||
`gap:physics_modal_chains_below_threshold`,
|
||||
`gap:physics_intent_shapes_below_threshold` — all `[x]`.
|
||||
- Chain coverage: causal=8, modal=8 (≥8 per claimed operator family ✓);
|
||||
five intent shapes populated (cause, comparison, correction, procedure,
|
||||
verification — ≥3 ✓).
|
||||
|
||||
What's missing is the ADR-0091 formal ratification step, matching the
|
||||
template established by ADR-0097 for `mathematics_logic`.
|
||||
|
||||
---
|
||||
|
||||
## Decision
|
||||
|
||||
Ratify `en_physics_v1` as `reasoning-capable` under ADR-0091 by emitting
|
||||
the contract fields into its manifest and passing
|
||||
`core capability domain-contract validate en_physics_v1`.
|
||||
|
||||
### Manifest additions
|
||||
|
||||
```jsonc
|
||||
{
|
||||
"domain_contract_version": 1,
|
||||
"domain_id": "physics",
|
||||
"axioms": null,
|
||||
"rules": null,
|
||||
"teaching_chains": ["physics_chains_v1"],
|
||||
"eval_lanes": [
|
||||
{"lane": "foundational_physics_ood", "version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]},
|
||||
{"lane": "inference_closure", "version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]},
|
||||
{"lane": "fabrication_control", "version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]}
|
||||
],
|
||||
"reviewers": ["shay-j"],
|
||||
"known_gaps": [],
|
||||
"provenance": "adr-0100:reviewed:2026-05-21"
|
||||
}
|
||||
```
|
||||
|
||||
Claimed operator families (`DOMAIN_OPERATOR_CLAIMS`): `causal`, `modal`.
|
||||
`axioms` and `rules` stay `null` at v1 — physics demonstrates reasoning
|
||||
through reviewed causal/modal chain composition, not declarative axioms.
|
||||
|
||||
### What this ADR does not do
|
||||
|
||||
- Does not introduce new lemmas, chains, or evals.
|
||||
- Does not promote to `expert-demo`.
|
||||
- Does not modify runtime mount behavior.
|
||||
|
||||
---
|
||||
|
||||
## Invariant
|
||||
|
||||
`physics_reasoning_capable_ledger_row` — `core capability ledger` emits
|
||||
a row for `domain_id: physics` with `status: reasoning-capable`,
|
||||
provenance pointing at this ADR, and `expert_demo: False` until a
|
||||
future ADR attaches the required audit-tour-equivalent reports.
|
||||
|
||||
---
|
||||
|
||||
## Lane
|
||||
|
||||
No new lane. The four existing lanes carry the evidence:
|
||||
|
||||
- `foundational_physics_ood/` (positive coverage)
|
||||
- `inference_closure/` (composition)
|
||||
- `fabrication_control/` (negative control, ADR-0096)
|
||||
- `evals/domain_contract_validation/` (ADR-0093 confirms predicates fire)
|
||||
|
||||
---
|
||||
|
||||
## PR Checklist
|
||||
|
||||
- Capability added: second ratified `reasoning-capable` domain.
|
||||
- Invariant proved: `physics_reasoning_capable_ledger_row`.
|
||||
- Hidden normalization / stochastic fallback / approximate recall / unreviewed mutation: none.
|
||||
- Trust boundary: manifest edit through reviewed flow; checksums unchanged.
|
||||
|
|
@ -0,0 +1,101 @@
|
|||
# ADR-0101 — Systems-Software Reasoning-Capable Ratification
|
||||
|
||||
**Status:** Proposed
|
||||
**Date:** 2026-05-21
|
||||
**Author:** CORE agents + reviewers
|
||||
**Depends on:** ADR-0091, ADR-0092, ADR-0093, ADR-0096, ADR-0097
|
||||
|
||||
---
|
||||
|
||||
## Context
|
||||
|
||||
The systems_software substrate is structurally complete:
|
||||
|
||||
- `language_packs/data/en_systems_software_v1/` ships with manifest,
|
||||
lexicon, glosses.
|
||||
- `teaching/domain_chains/systems_software_chains_v1.jsonl` exists.
|
||||
- `evals/symbolic_logic/` exists with dev/public/holdouts (the
|
||||
closest in-tree lane for systems/software reasoning at v1).
|
||||
- `docs/gaps.md` marks every systems_software gap closed:
|
||||
`gap:systems_software_pack_absent`,
|
||||
`gap:systems_software_transitive_chains_below_threshold`,
|
||||
`gap:systems_software_causal_chains_below_threshold`,
|
||||
`gap:systems_software_intent_shapes_below_threshold` — all `[x]`.
|
||||
- Chain coverage: causal=8, transitive=8 (≥8 per claimed operator
|
||||
family ✓); five intent shapes populated (≥3 ✓).
|
||||
|
||||
What's missing is the ADR-0091 formal ratification step, matching the
|
||||
template established by ADR-0097 for `mathematics_logic`.
|
||||
|
||||
---
|
||||
|
||||
## Decision
|
||||
|
||||
Ratify `en_systems_software_v1` as `reasoning-capable` under ADR-0091
|
||||
by emitting the contract fields into its manifest and passing
|
||||
`core capability domain-contract validate en_systems_software_v1`.
|
||||
|
||||
### Manifest additions
|
||||
|
||||
```jsonc
|
||||
{
|
||||
"domain_contract_version": 1,
|
||||
"domain_id": "systems_software",
|
||||
"axioms": null,
|
||||
"rules": null,
|
||||
"teaching_chains": ["systems_software_chains_v1"],
|
||||
"eval_lanes": [
|
||||
{"lane": "symbolic_logic", "version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]},
|
||||
{"lane": "inference_closure", "version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]},
|
||||
{"lane": "fabrication_control", "version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]}
|
||||
],
|
||||
"reviewers": ["shay-j"],
|
||||
"known_gaps": [],
|
||||
"provenance": "adr-0101:reviewed:2026-05-21"
|
||||
}
|
||||
```
|
||||
|
||||
Claimed operator families (`DOMAIN_OPERATOR_CLAIMS`): `transitive`,
|
||||
`causal`. `axioms` and `rules` stay `null` at v1 — systems-software
|
||||
reasoning is demonstrated through reviewed causal/transitive chain
|
||||
composition over invariants, boundaries, and dependencies.
|
||||
|
||||
### Eval lane choice — `symbolic_logic`
|
||||
|
||||
Systems-software lacks a dedicated v1 evaluation lane. `symbolic_logic`
|
||||
is the closest in-tree fit: it pins reasoning over typed relations
|
||||
(implication, contradiction, dependency) that the systems_software
|
||||
chain corpus exercises. A future ADR may introduce a
|
||||
`systems_software_design_ood` lane and supersede this declaration.
|
||||
|
||||
---
|
||||
|
||||
## Invariant
|
||||
|
||||
`systems_software_reasoning_capable_ledger_row` — `core capability
|
||||
ledger` emits a row for `domain_id: systems_software` with
|
||||
`status: reasoning-capable`, provenance pointing at this ADR, and
|
||||
`expert_demo: False` until a future ADR attaches the required reports.
|
||||
|
||||
---
|
||||
|
||||
## Lane
|
||||
|
||||
No new lane. Existing lanes carry the evidence:
|
||||
|
||||
- `symbolic_logic/` (reasoning over typed relations)
|
||||
- `inference_closure/` (composition)
|
||||
- `fabrication_control/` (negative control, ADR-0096)
|
||||
- `evals/domain_contract_validation/` (ADR-0093 confirms predicates fire)
|
||||
|
||||
---
|
||||
|
||||
## PR Checklist
|
||||
|
||||
- Capability added: third ratified `reasoning-capable` domain.
|
||||
- Invariant proved: `systems_software_reasoning_capable_ledger_row`.
|
||||
- Hidden normalization / stochastic fallback / approximate recall / unreviewed mutation: none.
|
||||
- Trust boundary: manifest edit through reviewed flow; checksums unchanged.
|
||||
|
|
@ -0,0 +1,136 @@
|
|||
# ADR-0102 — Hebrew-Greek Textual-Reasoning Reasoning-Capable Ratification
|
||||
|
||||
**Status:** Proposed
|
||||
**Date:** 2026-05-21
|
||||
**Author:** CORE agents + reviewers
|
||||
**Depends on:** ADR-0091, ADR-0092, ADR-0093, ADR-0096, ADR-0097
|
||||
|
||||
---
|
||||
|
||||
## Context
|
||||
|
||||
The hebrew_greek_textual_reasoning substrate is structurally complete
|
||||
across four packs:
|
||||
|
||||
- `grc_logos_micro_v1`, `grc_logos_cognition_v1`,
|
||||
`he_logos_micro_v1`, `he_core_cognition_v1`.
|
||||
- `teaching/domain_chains/hebrew_greek_textual_reasoning_chains_v1.jsonl`.
|
||||
- `docs/gaps.md` marks every relevant gap closed:
|
||||
`gap:grc_he_glosses_absent`, `gap:grc_he_chains_absent`,
|
||||
`gap:grc_logos_micro_v1_gloss_coverage_below_threshold`,
|
||||
`gap:grc_logos_cognition_v1_gloss_coverage_below_threshold`,
|
||||
`gap:he_logos_micro_v1_gloss_coverage_below_threshold`,
|
||||
`gap:he_core_cognition_v1_gloss_coverage_below_threshold`,
|
||||
`gap:hebrew_greek_textual_reasoning_causal_chains_below_threshold`,
|
||||
`gap:hebrew_greek_textual_reasoning_contradiction_chains_below_threshold`,
|
||||
`gap:hebrew_greek_textual_reasoning_intent_shapes_below_threshold`
|
||||
— all `[x]`.
|
||||
- Chain coverage: causal=8, contradiction=8 (≥8 per claimed operator
|
||||
family ✓); five intent shapes populated (≥3 ✓).
|
||||
|
||||
Unlike `mathematics_logic` / `physics` / `systems_software`, this is a
|
||||
**multi-pack domain**: `DOMAIN_PACKS["hebrew_greek_textual_reasoning"]`
|
||||
enumerates four packs. ADR-0091's predicates evaluate per pack; the
|
||||
ledger row aggregates. Each of the four packs must carry the same
|
||||
domain contract so the per-pack `core capability domain-contract
|
||||
validate` passes uniformly.
|
||||
|
||||
---
|
||||
|
||||
## Decision
|
||||
|
||||
Ratify all four hebrew/greek packs as `reasoning-capable` under
|
||||
ADR-0091 by emitting the contract fields into each manifest. Each pack
|
||||
declares the same `domain_id`, `teaching_chains`, `eval_lanes`, and
|
||||
reviewers; the only field that varies per pack is `provenance`
|
||||
(remains pack-scoped audit trail).
|
||||
|
||||
### Manifest additions (all four packs)
|
||||
|
||||
```jsonc
|
||||
{
|
||||
"domain_contract_version": 1,
|
||||
"domain_id": "hebrew_greek_textual_reasoning",
|
||||
"axioms": null,
|
||||
"rules": null,
|
||||
"teaching_chains": ["hebrew_greek_textual_reasoning_chains_v1"],
|
||||
"eval_lanes": [
|
||||
{"lane": "inference_closure", "version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]},
|
||||
{"lane": "fabrication_control", "version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]}
|
||||
],
|
||||
"reviewers": ["shay-j"],
|
||||
"known_gaps": [],
|
||||
"provenance": "adr-0102:reviewed:2026-05-21"
|
||||
}
|
||||
```
|
||||
|
||||
Claimed operator families (`DOMAIN_OPERATOR_CLAIMS`): `causal`,
|
||||
`contradiction`. `axioms` and `rules` stay `null` at v1.
|
||||
|
||||
### Eval lane scope
|
||||
|
||||
Only universal lanes (`inference_closure`, `fabrication_control`) are
|
||||
declared. The language-specific fluency lanes
|
||||
(`evals/hebrew_fluency/`, `evals/koine_greek_fluency/`) currently ship
|
||||
dev/public only — without a sealed holdout split they fail ADR-0091
|
||||
predicate P7. Adding holdouts to those lanes is a separate ADR; until
|
||||
that lands, the universal lanes alone are sufficient for
|
||||
`reasoning-capable` status.
|
||||
|
||||
### Pre-existing manifest gap
|
||||
|
||||
The four hebrew/greek manifests currently lack a `provenance` field
|
||||
entirely (unlike the three English domain packs). This ratification
|
||||
fills that gap as a side-effect; future audits of pack provenance
|
||||
trails across all packs become uniform.
|
||||
|
||||
---
|
||||
|
||||
## Invariant
|
||||
|
||||
`hebrew_greek_reasoning_capable_ledger_row` — `core capability ledger`
|
||||
emits a row for `domain_id: hebrew_greek_textual_reasoning` with
|
||||
`status: reasoning-capable`, provenance pointing at this ADR (uniform
|
||||
across all four packs), and `expert_demo: False` until a future ADR
|
||||
attaches the required reports.
|
||||
|
||||
`hebrew_greek_pack_contracts_uniform` — all four packs declare
|
||||
identical contract fields (except provenance audit trail), so
|
||||
multi-pack ratification cannot drift between packs without an
|
||||
explicit ADR.
|
||||
|
||||
---
|
||||
|
||||
## Lane
|
||||
|
||||
No new lane. Existing lanes carry the evidence:
|
||||
|
||||
- `inference_closure/` (composition)
|
||||
- `fabrication_control/` (negative control, ADR-0096)
|
||||
- `evals/domain_contract_validation/` (ADR-0093 confirms predicates
|
||||
fire on each of the four packs)
|
||||
|
||||
---
|
||||
|
||||
## Consequences
|
||||
|
||||
- First multi-pack domain ratification. Demonstrates the contract
|
||||
works the same way for single-pack and multi-pack domains.
|
||||
- All four hebrew/greek manifests gain a provenance field.
|
||||
- Future language-specific eval lanes (Hebrew, Koine Greek) can be
|
||||
added to the contract once they ship holdout splits.
|
||||
|
||||
---
|
||||
|
||||
## PR Checklist
|
||||
|
||||
- Capability added: fourth ratified `reasoning-capable` domain,
|
||||
multi-pack.
|
||||
- Invariants proved: `hebrew_greek_reasoning_capable_ledger_row`,
|
||||
`hebrew_greek_pack_contracts_uniform`.
|
||||
- Hidden normalization / stochastic fallback / approximate recall /
|
||||
unreviewed mutation: none.
|
||||
- Trust boundary: four manifest edits through reviewed flow;
|
||||
checksums unchanged.
|
||||
|
|
@ -13,7 +13,7 @@
|
|||
{
|
||||
"case_id": "determinism_run_to_run_byte_equality",
|
||||
"details": {
|
||||
"sha256": "a8a24def3636ecf34e3ade88fde932ad7dce9469862a9f927303dd1677fd1115"
|
||||
"sha256": "f35ba6c28f008f7f80eef51fdecd36c951b7f38eea1d64dc163c5f45e5c86050"
|
||||
},
|
||||
"divergence": null,
|
||||
"passed": true
|
||||
|
|
|
|||
|
|
@ -12,5 +12,29 @@
|
|||
"oov_policy": "tagged_fallback",
|
||||
"glosses_checksum": "2d813897f06e0ac777044094a788710454e0e66d4a3725c0ed2436edbfc67830",
|
||||
"definitional_layer": false,
|
||||
"provenance": "adr-0090:domain_seed:2026-05-21"
|
||||
"provenance": "adr-0100:reviewed:2026-05-21",
|
||||
"domain_contract_version": 1,
|
||||
"domain_id": "physics",
|
||||
"axioms": null,
|
||||
"rules": null,
|
||||
"teaching_chains": ["physics_chains_v1"],
|
||||
"eval_lanes": [
|
||||
{
|
||||
"lane": "foundational_physics_ood",
|
||||
"version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]
|
||||
},
|
||||
{
|
||||
"lane": "inference_closure",
|
||||
"version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]
|
||||
},
|
||||
{
|
||||
"lane": "fabrication_control",
|
||||
"version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]
|
||||
}
|
||||
],
|
||||
"reviewers": ["shay-j"],
|
||||
"known_gaps": []
|
||||
}
|
||||
|
|
|
|||
|
|
@ -12,5 +12,29 @@
|
|||
"oov_policy": "tagged_fallback",
|
||||
"glosses_checksum": "189a8686c02ac7a0801ef4d32fd52e551b5b88a1937d1e4efa7d449d16e74833",
|
||||
"definitional_layer": false,
|
||||
"provenance": "adr-0090:domain_seed:2026-05-21"
|
||||
"provenance": "adr-0101:reviewed:2026-05-21",
|
||||
"domain_contract_version": 1,
|
||||
"domain_id": "systems_software",
|
||||
"axioms": null,
|
||||
"rules": null,
|
||||
"teaching_chains": ["systems_software_chains_v1"],
|
||||
"eval_lanes": [
|
||||
{
|
||||
"lane": "symbolic_logic",
|
||||
"version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]
|
||||
},
|
||||
{
|
||||
"lane": "inference_closure",
|
||||
"version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]
|
||||
},
|
||||
{
|
||||
"lane": "fabrication_control",
|
||||
"version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]
|
||||
}
|
||||
],
|
||||
"reviewers": ["shay-j"],
|
||||
"known_gaps": []
|
||||
}
|
||||
|
|
|
|||
|
|
@ -10,5 +10,25 @@
|
|||
"version": "1.0.0",
|
||||
"gate_engaged": true,
|
||||
"oov_policy": "fail_closed",
|
||||
"glosses_checksum": "6b1e83010b2065ceedb0988e2020ee13999a1883e6399f1ca8908235683d7e42"
|
||||
"glosses_checksum": "6b1e83010b2065ceedb0988e2020ee13999a1883e6399f1ca8908235683d7e42",
|
||||
"provenance": "adr-0102:reviewed:2026-05-21",
|
||||
"domain_contract_version": 1,
|
||||
"domain_id": "hebrew_greek_textual_reasoning",
|
||||
"axioms": null,
|
||||
"rules": null,
|
||||
"teaching_chains": ["hebrew_greek_textual_reasoning_chains_v1"],
|
||||
"eval_lanes": [
|
||||
{
|
||||
"lane": "inference_closure",
|
||||
"version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]
|
||||
},
|
||||
{
|
||||
"lane": "fabrication_control",
|
||||
"version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]
|
||||
}
|
||||
],
|
||||
"reviewers": ["shay-j"],
|
||||
"known_gaps": []
|
||||
}
|
||||
|
|
|
|||
|
|
@ -10,5 +10,25 @@
|
|||
"version": "1.0.0",
|
||||
"gate_engaged": true,
|
||||
"oov_policy": "fail_closed",
|
||||
"glosses_checksum": "cfc5c3b3dafcd8290cff484039af34c8a17a826e40a3c8fa1ffe97e32c36934c"
|
||||
"glosses_checksum": "cfc5c3b3dafcd8290cff484039af34c8a17a826e40a3c8fa1ffe97e32c36934c",
|
||||
"provenance": "adr-0102:reviewed:2026-05-21",
|
||||
"domain_contract_version": 1,
|
||||
"domain_id": "hebrew_greek_textual_reasoning",
|
||||
"axioms": null,
|
||||
"rules": null,
|
||||
"teaching_chains": ["hebrew_greek_textual_reasoning_chains_v1"],
|
||||
"eval_lanes": [
|
||||
{
|
||||
"lane": "inference_closure",
|
||||
"version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]
|
||||
},
|
||||
{
|
||||
"lane": "fabrication_control",
|
||||
"version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]
|
||||
}
|
||||
],
|
||||
"reviewers": ["shay-j"],
|
||||
"known_gaps": []
|
||||
}
|
||||
|
|
|
|||
|
|
@ -10,5 +10,25 @@
|
|||
"version": "1.0.0",
|
||||
"gate_engaged": true,
|
||||
"oov_policy": "fail_closed",
|
||||
"glosses_checksum": "286acaf29fd2b3cc01ff5537f2b1552788ba2d495f977517ec5e4acd2a564ac5"
|
||||
"glosses_checksum": "286acaf29fd2b3cc01ff5537f2b1552788ba2d495f977517ec5e4acd2a564ac5",
|
||||
"provenance": "adr-0102:reviewed:2026-05-21",
|
||||
"domain_contract_version": 1,
|
||||
"domain_id": "hebrew_greek_textual_reasoning",
|
||||
"axioms": null,
|
||||
"rules": null,
|
||||
"teaching_chains": ["hebrew_greek_textual_reasoning_chains_v1"],
|
||||
"eval_lanes": [
|
||||
{
|
||||
"lane": "inference_closure",
|
||||
"version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]
|
||||
},
|
||||
{
|
||||
"lane": "fabrication_control",
|
||||
"version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]
|
||||
}
|
||||
],
|
||||
"reviewers": ["shay-j"],
|
||||
"known_gaps": []
|
||||
}
|
||||
|
|
|
|||
|
|
@ -10,5 +10,25 @@
|
|||
"version": "1.0.0",
|
||||
"gate_engaged": true,
|
||||
"oov_policy": "fail_closed",
|
||||
"glosses_checksum": "2d00c18735fa81b6d1f3ece754c132924bf8a2b83241d1561370bef52e8816e1"
|
||||
"glosses_checksum": "2d00c18735fa81b6d1f3ece754c132924bf8a2b83241d1561370bef52e8816e1",
|
||||
"provenance": "adr-0102:reviewed:2026-05-21",
|
||||
"domain_contract_version": 1,
|
||||
"domain_id": "hebrew_greek_textual_reasoning",
|
||||
"axioms": null,
|
||||
"rules": null,
|
||||
"teaching_chains": ["hebrew_greek_textual_reasoning_chains_v1"],
|
||||
"eval_lanes": [
|
||||
{
|
||||
"lane": "inference_closure",
|
||||
"version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]
|
||||
},
|
||||
{
|
||||
"lane": "fabrication_control",
|
||||
"version": "v1",
|
||||
"splits": ["dev", "public", "holdout"]
|
||||
}
|
||||
],
|
||||
"reviewers": ["shay-j"],
|
||||
"known_gaps": []
|
||||
}
|
||||
|
|
|
|||
|
|
@ -49,7 +49,7 @@ PINNED_SHAS: dict[str, str] = {
|
|||
"domain_contract_validation": "f9c06cdeea8fb36a0d3c320007618c3afc92d67702ef31bd36ebd9ae9ced473f",
|
||||
"fabrication_control_summary": "01e1b6b711141f2b4a14551d7df3ea482d8d6dd7b364a25c509f4f8d08cda8a8",
|
||||
"demo_composition": "27d838241bf3ed9e15d0e918ec6d89a823494d7e17c2dab9777825af7188f20f",
|
||||
"public_demo": "21751aaf2b60897ec7ca9b6498219e3c5eb28aec6b17eb77369ed139db093b29",
|
||||
"public_demo": "71090323943b3b09bf563d3d5217426922ab027f9a20bee3af4173435dda4c8c",
|
||||
}
|
||||
|
||||
|
||||
|
|
|
|||
223
tests/test_adr_0100_0102_sibling_ratifications.py
Normal file
223
tests/test_adr_0100_0102_sibling_ratifications.py
Normal file
|
|
@ -0,0 +1,223 @@
|
|||
"""ADR-0100 / ADR-0101 / ADR-0102 — sibling domain ratification tests.
|
||||
|
||||
Pins the load-bearing invariants for the three sibling domains
|
||||
ratified after ADR-0097's mathematics_logic template:
|
||||
|
||||
- ADR-0100 ``physics``
|
||||
- ADR-0101 ``systems_software``
|
||||
- ADR-0102 ``hebrew_greek_textual_reasoning`` (multi-pack)
|
||||
|
||||
Each domain's capability ledger row must report ``reasoning-capable``,
|
||||
provenance must point at the right ADR, and ``expert-demo`` stays
|
||||
gated for a future ADR.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import pytest
|
||||
|
||||
from core.capability import evaluate_domain_contract, ledger_report
|
||||
|
||||
|
||||
_DOMAINS: dict[str, dict] = {
|
||||
"physics": {
|
||||
"adr": "adr-0100",
|
||||
"packs": ("en_physics_v1",),
|
||||
"claimed_operators": ("causal", "modal"),
|
||||
"min_intent_shapes": 3,
|
||||
"expected_chains": ["physics_chains_v1"],
|
||||
"expected_lanes": {
|
||||
"foundational_physics_ood",
|
||||
"inference_closure",
|
||||
"fabrication_control",
|
||||
},
|
||||
},
|
||||
"systems_software": {
|
||||
"adr": "adr-0101",
|
||||
"packs": ("en_systems_software_v1",),
|
||||
"claimed_operators": ("transitive", "causal"),
|
||||
"min_intent_shapes": 3,
|
||||
"expected_chains": ["systems_software_chains_v1"],
|
||||
"expected_lanes": {
|
||||
"symbolic_logic",
|
||||
"inference_closure",
|
||||
"fabrication_control",
|
||||
},
|
||||
},
|
||||
"hebrew_greek_textual_reasoning": {
|
||||
"adr": "adr-0102",
|
||||
"packs": (
|
||||
"grc_logos_micro_v1",
|
||||
"grc_logos_cognition_v1",
|
||||
"he_logos_micro_v1",
|
||||
"he_core_cognition_v1",
|
||||
),
|
||||
"claimed_operators": ("causal", "contradiction"),
|
||||
"min_intent_shapes": 3,
|
||||
"expected_chains": ["hebrew_greek_textual_reasoning_chains_v1"],
|
||||
"expected_lanes": {"inference_closure", "fabrication_control"},
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
def _ledger_row(domain_id: str) -> dict:
|
||||
report = ledger_report()
|
||||
rows = {row["domain"]: row for row in report["domains"]}
|
||||
assert domain_id in rows, f"missing ledger row for {domain_id!r}"
|
||||
return rows[domain_id]
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Per-pack 9-predicate validation
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"pack_id,domain_id",
|
||||
[
|
||||
(pack, domain)
|
||||
for domain, spec in _DOMAINS.items()
|
||||
for pack in spec["packs"]
|
||||
],
|
||||
)
|
||||
def test_pack_passes_all_nine_predicates(
|
||||
pack_id: str, domain_id: str
|
||||
) -> None:
|
||||
report = evaluate_domain_contract(pack_id)
|
||||
assert report.contract_present is True, (
|
||||
f"{pack_id} missing domain contract"
|
||||
)
|
||||
assert report.contract_valid is True, (
|
||||
f"{pack_id} contract parse errors: {report.contract_errors}"
|
||||
)
|
||||
failing = [p.predicate_id for p in report.predicates if not p.passed]
|
||||
assert failing == [], (
|
||||
f"{pack_id} failing predicates: {failing}"
|
||||
)
|
||||
assert report.domain_id == domain_id
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Per-domain ledger status (invariants per ADR)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.mark.parametrize("domain_id", list(_DOMAINS.keys()))
|
||||
class TestLedgerStatus:
|
||||
def test_status_is_reasoning_capable(self, domain_id: str) -> None:
|
||||
row = _ledger_row(domain_id)
|
||||
assert row["status"] == "reasoning-capable"
|
||||
|
||||
def test_reasoning_capable_predicate_true(self, domain_id: str) -> None:
|
||||
row = _ledger_row(domain_id)
|
||||
assert row["predicates"]["reasoning_capable"] is True
|
||||
|
||||
def test_expert_demo_predicate_false(self, domain_id: str) -> None:
|
||||
"""Each ratification ADR explicitly defers expert-demo."""
|
||||
row = _ledger_row(domain_id)
|
||||
assert row["predicates"]["expert_demo"] is False
|
||||
|
||||
def test_no_open_gaps(self, domain_id: str) -> None:
|
||||
row = _ledger_row(domain_id)
|
||||
assert row["open_gaps"] == []
|
||||
|
||||
def test_provenance_points_at_correct_adr(self, domain_id: str) -> None:
|
||||
row = _ledger_row(domain_id)
|
||||
contracts = row["domain_contracts"]
|
||||
assert contracts, f"{domain_id} ledger row has no domain_contracts"
|
||||
expected_prefix = _DOMAINS[domain_id]["adr"] + ":reviewed:"
|
||||
provenances = [c["contract"]["provenance"] for c in contracts]
|
||||
assert all(
|
||||
p.startswith(expected_prefix) for p in provenances
|
||||
), f"{domain_id}: provenance mismatch, got {provenances}"
|
||||
|
||||
def test_operator_chain_coverage(self, domain_id: str) -> None:
|
||||
row = _ledger_row(domain_id)
|
||||
coverage = row["operator_chain_coverage"]
|
||||
for op in _DOMAINS[domain_id]["claimed_operators"]:
|
||||
assert coverage[op]["ready"] is True, (
|
||||
f"{domain_id} op {op!r} not ready: {coverage[op]}"
|
||||
)
|
||||
assert coverage[op]["chains_present"] >= 8
|
||||
|
||||
def test_intent_shapes_meet_minimum(self, domain_id: str) -> None:
|
||||
row = _ledger_row(domain_id)
|
||||
assert row["intent_shapes_present"] >= _DOMAINS[domain_id]["min_intent_shapes"]
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Per-domain contract field shape
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.mark.parametrize("domain_id", list(_DOMAINS.keys()))
|
||||
class TestContractFields:
|
||||
def test_teaching_chains_match(self, domain_id: str) -> None:
|
||||
row = _ledger_row(domain_id)
|
||||
for contract_entry in row["domain_contracts"]:
|
||||
chains = contract_entry["contract"]["teaching_chains"]
|
||||
assert chains == _DOMAINS[domain_id]["expected_chains"], (
|
||||
f"{domain_id} ({contract_entry['pack_id']}): unexpected "
|
||||
f"teaching_chains {chains}"
|
||||
)
|
||||
|
||||
def test_expected_eval_lanes(self, domain_id: str) -> None:
|
||||
row = _ledger_row(domain_id)
|
||||
for contract_entry in row["domain_contracts"]:
|
||||
lanes = {lane["lane"] for lane in contract_entry["contract"]["eval_lanes"]}
|
||||
assert lanes == _DOMAINS[domain_id]["expected_lanes"], (
|
||||
f"{domain_id} ({contract_entry['pack_id']}): expected "
|
||||
f"lanes {_DOMAINS[domain_id]['expected_lanes']}, got {lanes}"
|
||||
)
|
||||
|
||||
def test_all_lanes_cover_three_splits(self, domain_id: str) -> None:
|
||||
row = _ledger_row(domain_id)
|
||||
for contract_entry in row["domain_contracts"]:
|
||||
for lane in contract_entry["contract"]["eval_lanes"]:
|
||||
assert set(lane["splits"]) == {"dev", "public", "holdout"}, (
|
||||
f"{domain_id}: lane {lane['lane']!r} declares "
|
||||
f"{lane['splits']}, expected dev/public/holdout"
|
||||
)
|
||||
|
||||
def test_axioms_and_rules_null_at_v1(self, domain_id: str) -> None:
|
||||
row = _ledger_row(domain_id)
|
||||
for contract_entry in row["domain_contracts"]:
|
||||
contract = contract_entry["contract"]
|
||||
assert contract["axioms"] is None
|
||||
assert contract["rules"] is None
|
||||
|
||||
def test_primary_reviewer_resolves(self, domain_id: str) -> None:
|
||||
row = _ledger_row(domain_id)
|
||||
for contract_entry in row["domain_contracts"]:
|
||||
assert contract_entry["contract"]["reviewers"] == ["shay-j"]
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# ADR-0102 specific — multi-pack uniformity invariant
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestHebrewGreekMultiPackUniformity:
|
||||
"""ADR-0102 invariant: all four packs declare uniform contract."""
|
||||
|
||||
def test_all_four_packs_carry_contract(self) -> None:
|
||||
row = _ledger_row("hebrew_greek_textual_reasoning")
|
||||
contract_pack_ids = {c["pack_id"] for c in row["domain_contracts"]}
|
||||
assert contract_pack_ids == set(
|
||||
_DOMAINS["hebrew_greek_textual_reasoning"]["packs"]
|
||||
)
|
||||
|
||||
def test_contracts_identical_modulo_pack_id(self) -> None:
|
||||
row = _ledger_row("hebrew_greek_textual_reasoning")
|
||||
# Strip pack_id so we can compare the remaining contract fields
|
||||
# for cross-pack uniformity.
|
||||
canonical = None
|
||||
for entry in row["domain_contracts"]:
|
||||
contract = dict(entry["contract"])
|
||||
if canonical is None:
|
||||
canonical = contract
|
||||
continue
|
||||
assert contract == canonical, (
|
||||
f"hebrew/greek pack {entry['pack_id']} drifted from canonical: "
|
||||
f"{contract!r} vs {canonical!r}"
|
||||
)
|
||||
Loading…
Reference in a new issue