fix: harden DGR-017 contract continuity
This commit is contained in:
@@ -161,13 +161,13 @@ seeing a result. Each of those moves now has a test that names it:
|
||||
- admit the dense fallback → `test_admitting_the_dense_attention_fallback_after_the_fact_is_rejected`
|
||||
- shrink the reserve → `test_relaxing_the_per_node_reserve_after_the_fact_is_rejected`
|
||||
|
||||
**Be precise about what the seal does.** `contract_sha256` is tamper-*evidence*, not
|
||||
tamper-proofing. Nothing checked into a repo can stop an agent that rewrites the
|
||||
threshold *and* re-seals the digest — `test_resealing_a_mutated_contract_changes_its_digest`
|
||||
asserts that path openly. What the seal removes is the *silent* mutation: the digest
|
||||
moves, and the change becomes a visible diff on a file whose entire purpose is to not
|
||||
change, still claiming `contract_id: glm-5.2-max-alpha/v1`. Reviewers, not hashes, are
|
||||
the enforcement; the hash makes sure there is something to review.
|
||||
**Contract continuity is fail-closed.** The document’s `contract_sha256` detects
|
||||
accidental edits, and the approved v1 digest is pinned independently in code. A caller
|
||||
that changes a threshold and re-seals it under `glm-5.2-max-alpha/v1` is rejected by
|
||||
`test_resealing_a_mutated_v1_contract_is_rejected`; amendments require a new supported
|
||||
contract identity under human review. Parsed nested state is recursively immutable,
|
||||
so thresholds cannot change between validation and use; `to_dict()` returns an isolated
|
||||
copy rather than exposing the validated object.
|
||||
|
||||
## 6. Upstream status — the gating risk for DGR-004/DGR-018
|
||||
|
||||
|
||||
@@ -98,3 +98,18 @@ $VP -m pytest -q tests/test_tracker_routing.py::test_tracker_dashboard_can_cance
|
||||
-> 1 passed, repeated 5/5 in isolation
|
||||
$VP -m pytest -q # integrated rerun
|
||||
-> 852 passed, 13 skipped in 253.30s (0:04:13)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# 7. Late independent-review repair (2026-07-14)
|
||||
# ---------------------------------------------------------------------------
|
||||
PYTHONPATH=packages/node $VP -m pytest -q tests/test_glm_alpha_target.py
|
||||
-> 99 passed in 0.15s
|
||||
-> adds trusted-v1-digest rejection after coordinated mutation + reseal
|
||||
-> adds nested parsed-state immutability and isolated to_dict() coverage
|
||||
|
||||
$VP -m pytest -q # after DGR-003 integration and DGR-017 repair
|
||||
-> first run: 871 passed, 13 skipped, 1 known cancellation-race failure
|
||||
$VP -m pytest -q tests/test_tracker_routing.py::test_tracker_dashboard_can_cancel_inflight_proxy
|
||||
-> 5/5 passed in isolation
|
||||
$VP -m pytest -q # integrated rerun
|
||||
-> 872 passed, 13 skipped in 253.46s (0:04:13)
|
||||
|
||||
@@ -6,16 +6,15 @@ the fact: *what would have counted as success?*
|
||||
Its thresholds are locked before the target ever runs (DGR-017), and DGR-020 reads
|
||||
them back to publish an ``alpha`` or ``stop`` verdict. The whole point is that the
|
||||
gap between those two moments is where a threshold quietly becomes "0.1 tokens/sec
|
||||
was always the goal". So the document carries ``contract_sha256`` over its own
|
||||
canonical content, and :func:`load_alpha_contract` recomputes it on every load. An
|
||||
agent that edits a threshold and forgets the digest is rejected; an agent that
|
||||
edits both has left a diff on a file whose whole purpose is to not change.
|
||||
was always the goal". So the document carries ``contract_sha256`` over its canonical content, while the
|
||||
approved v1 digest is pinned independently in code. :func:`load_alpha_contract`
|
||||
recomputes the self-digest and then requires that trusted pre-execution digest.
|
||||
Changing a threshold and re-sealing under the same identity is rejected; an
|
||||
amendment requires a new supported contract identity under human review.
|
||||
|
||||
This is a tamper-*evidence* mechanism, not tamper-proofing. It cannot stop a
|
||||
determined rewrite of the file and the digest together — nothing in-repo can. What
|
||||
it does is remove the possibility of a silent one, which is the failure mode that
|
||||
actually happens: a number nudged mid-run, with no reviewer ever seeing that it
|
||||
moved.
|
||||
The parsed contract recursively freezes nested mappings and sequences. Thresholds
|
||||
therefore cannot change between verification and use, and :meth:`AlphaContract.to_dict`
|
||||
returns an isolated mutable copy for diagnostics and tests.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -25,6 +24,7 @@ import re
|
||||
from dataclasses import dataclass
|
||||
from importlib.resources import files
|
||||
from pathlib import Path
|
||||
from types import MappingProxyType
|
||||
from typing import Any, Mapping
|
||||
|
||||
from .manifest import (
|
||||
@@ -39,6 +39,7 @@ from .manifest import (
|
||||
ALPHA_CONTRACT_SCHEMA_VERSION = 1
|
||||
ALPHA_CONTRACT_VERSION = 1
|
||||
ALPHA_CONTRACT_ID = "glm-5.2-max-alpha/v1"
|
||||
ALPHA_CONTRACT_V1_SHA256 = "aab23220280c053a3c14ff559df3cb5c9e1bf7f0f7188c6519e2e9d9ad036ed9"
|
||||
|
||||
_CONTRACT_RESOURCE = "alpha-contract.json"
|
||||
|
||||
@@ -72,7 +73,23 @@ def contract_signing_payload(document: Mapping[str, Any]) -> dict:
|
||||
|
||||
def compute_contract_digest(document: Mapping[str, Any]) -> str:
|
||||
"""SHA-256 over the canonical contract content."""
|
||||
return canonical_sha256(contract_signing_payload(document))
|
||||
return canonical_sha256(contract_signing_payload(_thaw_json(document)))
|
||||
|
||||
|
||||
def _freeze_json(value: Any) -> Any:
|
||||
if isinstance(value, Mapping):
|
||||
return MappingProxyType({str(key): _freeze_json(item) for key, item in value.items()})
|
||||
if isinstance(value, list):
|
||||
return tuple(_freeze_json(item) for item in value)
|
||||
return value
|
||||
|
||||
|
||||
def _thaw_json(value: Any) -> Any:
|
||||
if isinstance(value, Mapping):
|
||||
return {str(key): _thaw_json(item) for key, item in value.items()}
|
||||
if isinstance(value, tuple):
|
||||
return [_thaw_json(item) for item in value]
|
||||
return value
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
@@ -107,7 +124,7 @@ class AlphaContract:
|
||||
return block[key]
|
||||
|
||||
def to_dict(self) -> dict:
|
||||
return dict(self.raw)
|
||||
return _thaw_json(self.raw)
|
||||
|
||||
|
||||
def parse_alpha_contract(data: Any, source: str = "<memory>") -> AlphaContract:
|
||||
@@ -229,18 +246,28 @@ def parse_alpha_contract(data: Any, source: str = "<memory>") -> AlphaContract:
|
||||
if not isinstance(amendment_policy, str) or not amendment_policy.strip():
|
||||
raise AlphaContractError(f"{source} must state its amendment policy")
|
||||
|
||||
if declared != ALPHA_CONTRACT_V1_SHA256:
|
||||
raise AlphaContractError(
|
||||
f"{source} is a re-sealed mutation of {ALPHA_CONTRACT_ID}: digest "
|
||||
f"{declared} does not match the trusted pre-execution digest "
|
||||
f"{ALPHA_CONTRACT_V1_SHA256}. An amendment requires a new supported "
|
||||
"contract identity under human review."
|
||||
)
|
||||
|
||||
frozen = _freeze_json(data)
|
||||
|
||||
return AlphaContract(
|
||||
schema_version=schema_version,
|
||||
contract_version=contract_version,
|
||||
contract_id=contract_id,
|
||||
locked_at=str(data["locked_at"]),
|
||||
locked_by=str(data["locked_by"]),
|
||||
target=target,
|
||||
sections={name: data[name] for name in REQUIRED_SECTIONS},
|
||||
target=frozen["target"],
|
||||
sections=MappingProxyType({name: frozen[name] for name in REQUIRED_SECTIONS}),
|
||||
verdicts=tuple(verdicts),
|
||||
amendment_policy=amendment_policy,
|
||||
digest=declared,
|
||||
raw=data,
|
||||
raw=frozen,
|
||||
source=source,
|
||||
)
|
||||
|
||||
|
||||
@@ -80,7 +80,7 @@ def snapshot_doc(snapshot):
|
||||
|
||||
@pytest.fixture
|
||||
def contract_doc(contract):
|
||||
return copy.deepcopy(dict(contract.raw))
|
||||
return contract.to_dict()
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------
|
||||
@@ -746,7 +746,7 @@ def test_the_contract_locks_the_roadmap_thresholds(contract):
|
||||
assert contract.threshold("performance", "quality_pass_with_speed_fail_verdict") == "stop"
|
||||
|
||||
assert contract.threshold("reliability", "synthetic_workers_satisfy_alpha") is False
|
||||
assert contract.threshold("storage", "forbidden_path_prefixes") == ["/home"]
|
||||
assert contract.threshold("storage", "forbidden_path_prefixes") == ("/home",)
|
||||
|
||||
|
||||
def test_the_contract_offers_only_alpha_or_stop(contract):
|
||||
@@ -820,17 +820,26 @@ def test_a_dropped_acceptance_section_is_rejected(contract_doc):
|
||||
parse_alpha_contract(contract_doc)
|
||||
|
||||
|
||||
def test_resealing_a_mutated_contract_changes_its_digest(contract, contract_doc):
|
||||
"""Tamper-evidence, not tamper-proofing: a rewrite is legal but never silent."""
|
||||
def test_resealing_a_mutated_v1_contract_is_rejected(contract, contract_doc):
|
||||
contract_doc["performance"]["min_median_decode_tokens_per_second"] = 0.05
|
||||
resealed = seal_contract(contract_doc)
|
||||
|
||||
# It parses — nothing in-repo can stop a determined rewrite of file plus digest.
|
||||
reparsed = parse_alpha_contract(resealed)
|
||||
with pytest.raises(AlphaContractError, match="trusted pre-execution digest"):
|
||||
parse_alpha_contract(resealed)
|
||||
assert resealed["contract_sha256"] != contract.digest
|
||||
|
||||
# But the digest moved, so the change is a visible diff on a file whose entire
|
||||
# purpose is to not change, and the contract_id still claims to be v1.
|
||||
assert reparsed.digest != contract.digest
|
||||
|
||||
def test_parsed_contract_nested_state_is_immutable(contract):
|
||||
with pytest.raises(TypeError):
|
||||
contract.raw["performance"]["min_median_decode_tokens_per_second"] = 0.05
|
||||
with pytest.raises(TypeError):
|
||||
contract.target["reasoning_effort"] = "high"
|
||||
|
||||
|
||||
def test_contract_to_dict_returns_an_isolated_mutable_copy(contract):
|
||||
copied = contract.to_dict()
|
||||
copied["performance"]["min_median_decode_tokens_per_second"] = 0.05
|
||||
assert contract.threshold("performance", "min_median_decode_tokens_per_second") == 0.5
|
||||
|
||||
|
||||
def test_an_unknown_threshold_cannot_be_invented_at_read_time(contract):
|
||||
|
||||
Reference in New Issue
Block a user