⚡ Bolt: Optimize ordered deduplication with dict.fromkeys

configs/quality/runtime_uuid_seams.yaml

@@ -25,7 +25,7 @@ seams:
     owner: control-plane
     migration_policy: inject deterministic event_id_factory for replay-critical ledger fixtures or migrations.
   - path: src/bioetl/application/services/control_plane/manifest_service_scaffold.py
-    line: 26
+    line: 42
     kind: call
     symbol: uuid4
     layer: application
@@ -43,7 +43,7 @@ seams:
     owner: workflow-control-plane
     migration_policy: inject deterministic run_id_factory for replay-critical workflow execution tests.
   - path: src/bioetl/application/services/control_plane/workflow/ledger_service.py
-    line: 59
+    line: 67
     kind: call
     symbol: uuid4
     layer: application

scripts/engineering/qa/check_quality_exemptions.py

@@ -31,3 +31,13 @@ def _canonical_script() -> Path:
         sys.stderr.write(f"ERROR: canonical script not found: {script}\n")
         raise SystemExit(2)
     runpy.run_path(str(script), run_name="__main__")
+
+def main() -> int:
+    script = _canonical_script()
+    if not script.exists():
+        sys.stderr.write(f"ERROR: canonical script not found: {script}\n")
+        return 2
+    import runpy
+    sys.argv[0] = str(script)
+    runpy.run_path(str(script), run_name="__main__")
+    return 0

src/bioetl/application/services/control_plane/_run_manifest_diagnostics_composite.py

@@ -4,12 +4,12 @@
 
 from typing import Protocol
 
-from bioetl.application.services.control_plane.manifest.diagnostics.helpers import (
-    extract_diagnostic_context,
-)
 from bioetl.application.services.control_plane._run_manifest_diagnostics_replay_helpers import (
     _is_composite_execution_context,
 )
+from bioetl.application.services.control_plane.manifest.diagnostics.helpers import (
+    extract_diagnostic_context,
+)
 from bioetl.domain.control_plane import RunLedgerEntry, RunManifest
 
 

src/bioetl/application/services/control_plane/_run_manifest_diagnostics_replay_helpers.py

@@ -7,14 +7,14 @@
 
 from typing import Literal
 
+from bioetl.application.services.control_plane.manifest.diagnostics.nested_mapping import (
+    lookup_mapping_path,
+)
 from bioetl.application.services.control_plane.replay.historical_certification import (
     HISTORICAL_COMPOSITE_REPLAY_ENVELOPE_CERTIFIED,
     HISTORICAL_SOURCE_SNAPSHOT_CERTIFIED,
     LIVE_CAPTURE_SNAPSHOT_MATERIALIZED,
 )
-from bioetl.application.services.control_plane.manifest.diagnostics.nested_mapping import (
-    lookup_mapping_path,
-)
 from bioetl.application.services.control_plane.run_manifest_exact_replay_blockers import (
     append_mode_exact_replay_blockers as _append_mode_exact_replay_blockers,
 )

src/bioetl/application/services/control_plane/_run_manifest_diagnostics_summary.py

@@ -9,9 +9,6 @@
 from bioetl.application.services.control_plane._run_manifest_diagnostics_composite import (
     build_composite_dossier_projection,
 )
-from bioetl.application.services.control_plane.manifest.diagnostics.helpers import (
-    DQDetailsSummary,
-)
 from bioetl.application.services.control_plane._run_manifest_diagnostics_ledger import (
     _resolve_policy_value,
 )
@@ -23,14 +20,17 @@
 from bioetl.application.services.control_plane._run_manifest_diagnostics_replay_helpers import (
     _is_composite_execution_context,
 )
-from bioetl.application.services.control_plane.manifest.identity_graph_builder import (
-    RunManifestIdentityGraphAssembler,
-)
 from bioetl.application.services.control_plane.manifest.diagnostics.artifact_support import (
     apply_artifact_publication_closure_policy,
     build_produced_artifact_trace,
     sorted_text_items,
 )
+from bioetl.application.services.control_plane.manifest.diagnostics.helpers import (
+    DQDetailsSummary,
+)
+from bioetl.application.services.control_plane.manifest.identity_graph_builder import (
+    RunManifestIdentityGraphAssembler,
+)
 from bioetl.domain.control_plane import RunLedgerEntry, RunManifest
 
 

src/bioetl/application/services/control_plane/manifest/diagnostics/base.py

@@ -32,8 +32,8 @@
     _build_resume_contract,
 )
 from bioetl.application.services.control_plane.manifest.diagnostics.replay_projection import (
-    _build_replay_projection_context_kwargs,
     _build_replay_projection_bundle,
+    _build_replay_projection_context_kwargs,
 )
 from bioetl.application.services.control_plane.manifest.diagnostics.snapshot_support import (
     collect_input_snapshot_content_hashes as _collect_input_snapshot_content_hashes,
@@ -96,7 +96,11 @@ def _resolve_base_summary_replay_context(
         replay_family_contract=replay_family_contract,
     )
     replay_projection_context = _build_replay_projection_context_kwargs(
-        manifest, input_snapshots, requested_exact_replay, resume_requested, policy_assessment
+        manifest,
+        input_snapshots,
+        requested_exact_replay,
+        resume_requested,
+        policy_assessment,
     )
     replay_projection_bundle = _build_replay_projection_bundle(
         **replay_projection_context,

src/bioetl/application/services/control_plane/manifest/diagnostics/replay_projection.py

@@ -10,6 +10,11 @@
 from bioetl.application.services.control_plane.manifest.diagnostics.replay import (
     _resolve_manifest_replay_readiness_verdict,
 )
+from bioetl.application.services.control_plane.manifest.replay_taxonomy import (
+    build_replay_taxonomy_projection,
+    resolve_replay_next_action,
+    resolve_replay_resume_rebuild_verdict,
+)
 from bioetl.application.services.control_plane.run_manifest_diagnostics_support import (
     _build_replay_state_projection,
     _collect_append_mode_semantic_sinks,
@@ -22,11 +27,6 @@
     build_lineage_closure_boundary,
     build_replay_family_contract_payload,
 )
-from bioetl.application.services.control_plane.manifest.replay_taxonomy import (
-    build_replay_taxonomy_projection,
-    resolve_replay_next_action,
-    resolve_replay_resume_rebuild_verdict,
-)
 from bioetl.domain.control_plane import RunManifest
 from bioetl.domain.control_plane.reproducibility_policy import (
     ReproducibilityPolicyAssessment,
@@ -184,7 +184,11 @@ def _build_operator_replay_projection(
     """Return canonical operator-facing replay projection fields."""
     replay_family_contract = _resolve_replay_family_contract(manifest)
     replay_projection_context = _build_replay_projection_context_kwargs(
-        manifest, input_snapshots, requested_exact_replay, resume_requested, policy_assessment
+        manifest,
+        input_snapshots,
+        requested_exact_replay,
+        resume_requested,
+        policy_assessment,
     )
     replay_inputs = _build_operator_replay_projection_inputs(
         **replay_projection_context

src/bioetl/application/services/control_plane/manifest/diagnostics/snapshot_support.py

@@ -4,13 +4,13 @@
 
 from collections.abc import Mapping
 
+from bioetl.application.services.control_plane.manifest.diagnostics.nested_mapping import (
+    lookup_mapping_path,
+)
 from bioetl.application.services.control_plane.replay.historical_certification import (
     LIVE_CAPTURE_SNAPSHOT_MATERIALIZED,
     MIXED_POST_MANIFEST_SNAPSHOT_MATERIALIZATION,
 )
-from bioetl.application.services.control_plane.manifest.diagnostics.nested_mapping import (
-    lookup_mapping_path,
-)
 from bioetl.domain.control_plane import RunLedgerEntry, RunManifest
 from bioetl.domain.control_plane.run_ledger import INPUT_SNAPSHOT_PUBLISHED_EVENT
 from bioetl.domain.normalization import (

src/bioetl/application/services/control_plane/manifest/inspection_service.py

@@ -5,14 +5,14 @@
 from dataclasses import dataclass
 from typing import Protocol, cast
 
-from bioetl.application.services.control_plane.manifest.diagnostics import (
-    build_diagnostics_summary,
-)
 from bioetl.application.services.control_plane.manifest import inspection_models
 from bioetl.application.services.control_plane.manifest._inspection_support import (
     RunManifestInspectionDiffClassificationMixin,
     RunManifestInspectionIdentityGraphMixin,
 )
+from bioetl.application.services.control_plane.manifest.diagnostics import (
+    build_diagnostics_summary,
+)
 from bioetl.application.services.control_plane.manifest.inspection_models import (
     RunManifestDiffEntry,
     RunManifestDiffResult,

src/bioetl/application/services/control_plane/manifest/service.py

@@ -4,13 +4,13 @@
 
 from dataclasses import dataclass
 
-from bioetl.application.services.control_plane.manifest.models import (
-    RunManifestCreateSpec,
-)
 from bioetl.application.services.control_plane.manifest._service_support import (
     RunManifestHydrationMixin,
     RunManifestPayloadMixin,
 )
+from bioetl.application.services.control_plane.manifest.models import (
+    RunManifestCreateSpec,
+)
 from bioetl.application.services.control_plane.manifest_service_scaffold import (
     ManifestServiceScaffoldMixin,
 )

src/bioetl/application/services/control_plane/replay/_historical_record_payload.py

@@ -78,16 +78,16 @@ def build_historical_certified_identity_payload_from_record(
     """Build one historical replay row from a record exposing certification fields."""
     return build_historical_certified_identity_payload(
         record,
-        certification_status=str(getattr(record, "certification_status")),
-        replay_occurrence_kind=str(getattr(record, "replay_occurrence_kind")),
+        certification_status=str(record.certification_status),
+        replay_occurrence_kind=str(record.replay_occurrence_kind),
         blocking_reasons=tuple(getattr(record, "blocking_reasons", ())),
         **extra_fields,
     )
 
 
 __all__ = [
+    "build_historical_certification_payload",
     "build_historical_certified_identity_payload",
     "build_historical_certified_identity_payload_from_record",
-    "build_historical_certification_payload",
     "build_historical_run_identity_payload",
 ]

src/bioetl/application/services/control_plane/replay/historical_certification_service.py

@@ -4,15 +4,15 @@
 
 from dataclasses import dataclass
 
-from bioetl.application.services.control_plane.replay.historical_certification import (
-    HISTORICAL_COMPOSITE_REPLAY_ENVELOPE_CERTIFIED,
-    HISTORICAL_SOURCE_SNAPSHOT_CERTIFIED,
-)
 from bioetl.application.services.control_plane.replay._historical_certification_support import (
     HistoricalReplayCertificationResult,
     HistoricalReplayCertificationResultAssembler,
     HistoricalReplayCertificationValidator,
 )
+from bioetl.application.services.control_plane.replay.historical_certification import (
+    HISTORICAL_COMPOSITE_REPLAY_ENVELOPE_CERTIFIED,
+    HISTORICAL_SOURCE_SNAPSHOT_CERTIFIED,
+)
 from bioetl.domain.ports import RunLedgerPort, RunManifestPort
 from bioetl.domain.types import RunID
 

src/bioetl/application/services/control_plane/replay/historical_corpus_models.py

@@ -7,7 +7,9 @@
 from bioetl.application.services.control_plane.replay._historical_record_payload import (
     build_historical_certified_identity_payload_from_record,
 )
-from bioetl.application.services.control_plane.replay.historical_identity_models import HistoricalReplayRunIdentity
+from bioetl.application.services.control_plane.replay.historical_identity_models import (
+    HistoricalReplayRunIdentity,
+)
 
 
 @dataclass(frozen=True, slots=True)

src/bioetl/application/services/control_plane/replay/historical_corpus_service.py

@@ -7,11 +7,11 @@
 from bioetl.application.services.control_plane.manifest.diagnostics import (
     build_diagnostics_summary,
 )
+from bioetl.application.services.control_plane.replay import historical_corpus_models
 from bioetl.application.services.control_plane.replay.historical_certification_service import (
     HistoricalReplayCertificationResult,
     HistoricalReplayCertificationService,
 )
-from bioetl.application.services.control_plane.replay import historical_corpus_models
 from bioetl.application.services.control_plane.replay.historical_corpus_models import (
     HistoricalReplayBulkCertificationRecord,
     HistoricalReplayBulkCertificationResult,

src/bioetl/application/services/control_plane/replay/historical_identity_models.py

@@ -5,9 +5,9 @@
 from dataclasses import dataclass, fields
 
 __all__ = [
-    "build_historical_identity_core_payload",
     "HistoricalReplayRunIdentity",
     "HistoricalReplayRunIdentityRecord",
+    "build_historical_identity_core_payload",
 ]
 
 

src/bioetl/application/services/control_plane/run_manifest_inspection_helpers.py

@@ -5,12 +5,12 @@
 from collections.abc import Mapping
 from typing import cast
 
-from bioetl.application.services.control_plane.manifest.execution_identity_support import (
-    build_contract_identity_anchor_fields,
-)
 from bioetl.application.services.control_plane._run_manifest_inspection_artifact_refs import (
     build_artifact_ref_semantic_diff,
 )
+from bioetl.application.services.control_plane.manifest.execution_identity_support import (
+    build_contract_identity_anchor_fields,
+)
 from bioetl.domain.control_plane import RunManifest
 
 _AUTHORITATIVE_REPLAY_ARTIFACTS = [

src/bioetl/composition/runtime_builders/_manifest_publication_context_support.py

@@ -150,10 +150,10 @@ def resolve_manifest_publication_identity(
 
 
 __all__ = [
-    "build_manifest_publication_identity_kwargs",
     "ResolvedManifestPublicationContext",
+    "build_manifest_publication_identity_kwargs",
     "contract_identity_requires_strict_resolution",
     "ensure_manifest_publication_identity",
-    "resolve_manifest_publication_identity",
     "resolve_manifest_publication_context",
+    "resolve_manifest_publication_identity",
 ]

src/bioetl/composition/runtime_builders/_run_manifest_refs.py

@@ -6,22 +6,13 @@
 from dataclasses import dataclass
 from typing import TYPE_CHECKING, Protocol, cast
 
-from bioetl.composition.runtime_builders._run_manifest_data_roots import (
-    DataRootMode,
-    build_planned_artifacts,
-    control_plane_root,
-    is_explicit_data_root_configured,
-    resolve_data_root_mode,
-)
 from bioetl.composition.runtime_builders.run_manifest_contract_identity import (
     CONTRACT_IDENTITY_FIELD_NAMES,
 )
 from bioetl.domain.normalization import normalize_runtime_anchor_payload
 
 if TYPE_CHECKING:
-
     from bioetl.domain.context import PipelineRunContext
-    from bioetl.infrastructure.config.settings_api import Settings
 
 
 def legacy_config_hash_from_resolved_config_hash(

src/bioetl/domain/value_objects/__init__.py

@@ -86,12 +86,12 @@
         PolarSurfaceArea,
         RotatableBondCount,
     )
-    from bioetl.domain.value_objects.publications import DOI, PubMedId
     from bioetl.domain.value_objects.protein_class_hierarchy import (
         ProteinClassHierarchy,
-        ProteinClassLevel,
         ProteinClassificationResolutionError,
+        ProteinClassLevel,
     )
+    from bioetl.domain.value_objects.publications import DOI, PubMedId
     from bioetl.domain.value_objects.taxonomy_id import TaxonomyId, validate_taxonomy_id
 
 _MODULE_ACADEMIC_IDS = "bioetl.domain.value_objects.academic_ids"
@@ -104,9 +104,7 @@
 _MODULE_IDENTIFIERS = "bioetl.domain.value_objects.identifiers"
 _MODULE_MOLECULAR_DESCRIPTORS = "bioetl.domain.value_objects.molecular_descriptors"
 _MODULE_PUBLICATIONS = "bioetl.domain.value_objects.publications"
-_MODULE_PROTEIN_CLASS_HIERARCHY = (
-    "bioetl.domain.value_objects.protein_class_hierarchy"
-)
+_MODULE_PROTEIN_CLASS_HIERARCHY = "bioetl.domain.value_objects.protein_class_hierarchy"
 _MODULE_TAXONOMY_ID = "bioetl.domain.value_objects.taxonomy_id"
 
 _LAZY_ATTRIBUTE_EXPORTS: dict[str, tuple[str, str]] = {
@@ -229,12 +227,12 @@
     "OpenAlexId",
     "PChemblValue",
     "PolarSurfaceArea",
-    "PubChemCid",
-    "PubMedId",
-    "PublicationYear",
     "ProteinClassHierarchy",
     "ProteinClassLevel",
     "ProteinClassificationResolutionError",
+    "PubChemCid",
+    "PubMedId",
+    "PublicationYear",
     "RelationOperator",
     "RotatableBondCount",
     "SemanticScholarId",