Dev - #687
Merged
Merged
Conversation
feat: add authored evidence requirements
feat: add behavior specifications to SDL
Add a pull_request workflow (.github/workflows/pr-title-lint.yml) that rejects agent-branded PR title prefixes ([codex], [claude], [openai], [chatgpt]) and enforces the conventional <type>(<optional-scope>): <subject> shape with a lowercase-leading subject, on every target branch including dev. The workflow runs the trusted base-ref copy of tools/check_pr_title.py so a PR cannot weaken its own required check; the same stdlib validator is shared by the test suite so the policy cannot drift between CI and local enforcement.
ci: add repo-side pr title guard against agent-branded titles
added: expose ACT-607 authority scope runtime metadata
docs(experiment-core): define replication and replay claims
Resolve the 7 new-code smells the SonarCloud PR gate flagged: - decompose _aptl_from_export (backend runs) and _validate_backend_runs (validation) so cyclomatic/cognitive complexity is back under threshold; - reduce build_aptl_backend_run to <=3 returns; - replace the bare-Any _get helper with typed _mapping/_sequence navigators (no bare Any annotations). Behavior-preserving: the committed corpus and its drift test are unaffected.
…cenario The backend-neutral live provisioning probe (issue #606) assumed every backend could realize a hard-coded vm/linux scenario, wrongly failing fixed-topology emulation and bounded simulation backends that legitimately cannot realize an arbitrary scenario. run_target_conformance now accepts an optional reference_scenario (default unchanged); a backend supplies a scenario it declares it can realize, and the #606 full-realization guard still applies to whichever scenario is selected. No schema/manifest/profile change. Temporary runner-parameter bridge for #663; superseded by the realizability-envelope design (#667) and the scenario/envelope subsumption relation (#668).
…ility fixed: parameterize target-conformance probe with a backend-supplied reference scenario
feat(corpus): add paper demonstration corpus with cross-backend invariant ledger
docs: document realization envelope semantics
Behavior-preserving rename across the #598/#614/#615/#600 surfaces so the OSS repo names reusable capabilities by function, not by 'paper': - scenario -> enterprise-participant-evidence-loop (file + internal SDL ids) - aces_operations.libvirt_evidence_run -> aces.libvirt.scenario-evidence-run/v1 - aces_operations.cross_backend_corpus -> aces.cross-backend-evidence-corpus/v1 - CLI: aces libvirt evidence validate (was: aces libvirt paper validate-evidence) - module-boundary allowlist updated to the new module names Relocate the research result out of ACES: remove the committed demonstration corpus (examples/corpus/paper-demonstration/); ACES keeps the producer, and the canonical published corpus now lives in the public Brad-Edwards/research repo. The drift test becomes a build-determinism smoke test. No published contracts and no historical decision-note filenames changed.
refactor(corpus): rename paper-* identifiers to functional names and relocate the corpus
Add the reusable-asset-trust-policy-v1 contract, ADR-071, and a normative spec declaring, per reusable asset family, the required integrity/authenticity/ provenance/governance evidence classes referencing existing ACES mechanisms. Invariants are enforced in the model, the published JSON Schema, and negative conformance fixtures.
Extract the reusable-asset family-policy checks into helpers so the model validator's cyclomatic complexity drops below the threshold. Behavior-preserving; the published schema is unchanged.
security: publish reusable-asset trust and integrity policy (GOV-913)
fixed: validate SDL variable substitution
docs: add validation admission profile design
Examine whether the OCR-inherited SDL scoring pipeline (metrics/evaluations/tlos/goals) and the CybORG agents.reward_calculator label belong in ACES, against the experiment-vs-data-use boundary already drawn by ADR-055/064/069. Recommend (proposed) treating these surfaces as vestigial in the SDL, keeping objectives+conditions, narrowing objective success to observable state, and routing graded scoring to the experiment/evaluator plane. Add scoring-scope research notes (docs/research/scoring-scope/) and a SEM-206 assessment-semantics compatibility guardrail. Decision deferred to review. Refs #671. ADR-073. SEM-206.
docs: add proposed ADR-073 on scoring/reward language scope
…omaly docs(security): record 2026-07-01 commit authorship anomaly
|
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
1 participant
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
Related Issues
Requirement Context
aces-sdlChanges
Test Plan
uvx nox -s verifypasses, or the unchecked sessions are listed belowuvx nox -s docs)Checklist
docs/explain/reference/coding-standards.md)changelog.d/, or not neededNotes for Review