Remove dead code and wire the two-worker smoke script

scimesh/sdk/artifacts.py

@@ -8,7 +8,7 @@ from dataclasses import dataclass, field
 from datetime import datetime, timezone
 from enum import Enum
 from types import MappingProxyType
-from typing import Any, Mapping, Sequence
+from typing import Any, Mapping
 
 from ._validation import (
     canonical_json,

scimesh/sdk/batch.py

@@ -24,9 +24,7 @@ from typing import Any, Mapping, Sequence
 
 from .artifacts import (
     ArtifactCollection,
-    ArtifactItem,
     ArtifactRef,
-    ArtifactSchema,
     Cardinality,
     CollectionKind,
     OutputManifest,
@@ -295,8 +293,6 @@ class MapReduceWorkload:
             conformance_profiles=("core-batch-v1",),
         )
         self._exact_verifier = _EXACT_VERIFIER
-        self._resources = resources
-        self._execution = execution
         self._limits = limits
 
     # ------------------------------------------------------------------

scimesh/sdk/conformance.py

@@ -24,7 +24,7 @@ from .artifacts import (
     OutputManifest,
     Provenance,
 )
-from .identity import ComponentRef, SDK_API_VERSION, SchemaRef
+from .identity import ComponentRef, SDK_API_VERSION
 from .execution import NetworkPolicy, ProcessModel
 from .manifest import TrustMode, WorkloadManifest
 from .plans import JobRequest, TaskSpec
@@ -686,9 +686,6 @@ class CancellationFlag:
     def __init__(self) -> None:
         self._event = Event()
 
-    def cancel(self) -> None:
-        self._event.set()
-
     def cancelled(self) -> bool:
         return self._event.is_set()
 

scimesh/sdk/integrity.py

@@ -4,7 +4,6 @@ from __future__ import annotations
 
 import hashlib
 import importlib.util
-import os
 from importlib import metadata
 from pathlib import Path
 

scimesh/sdk/protocols.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 from pathlib import Path
-from typing import Mapping, Protocol, Sequence
+from typing import Mapping, Protocol
 
 from .artifacts import (
     ArtifactCollection,

scimesh/sdk/registry.py

@@ -26,7 +26,6 @@ from .manifest import WorkloadManifest
 from .plans import JobRequest, ValidatedJob, WorkflowPlan
 from .protocols import (
     Planner,
-    PlanningContext,
     PlanningResources,
     Reducer,
     Runner,

scimesh/sdk/resources.py

@@ -5,7 +5,6 @@ from __future__ import annotations
 from dataclasses import dataclass
 from enum import Enum
 from threading import Lock
-from types import MappingProxyType
 from typing import Mapping
 from uuid import uuid4
 

scimesh/sdk/runtime.py

@@ -10,7 +10,6 @@ from ._validation import (
     require_identifier,
     require_string,
     validate_version_range,
-    version_in_range,
 )
 from .identity import SDK_API_VERSION
 from .execution import NetworkPolicy, ProcessModel

scimesh/sdk/schema.py

@@ -5,7 +5,7 @@ from __future__ import annotations
 import math
 import re
 from fractions import Fraction
-from typing import Mapping, Sequence
+from typing import Mapping
 
 
 _ANNOTATIONS = {

scimesh/sdk/verification.py

@@ -20,7 +20,6 @@ from ._validation import (
     freeze_json_mapping,
     require_exact_keys,
     require_identifier,
-    require_nonnegative_int,
     require_positive_int,
     require_sha256,
     require_string,

scimesh/sdk/workflow.py

@@ -15,7 +15,6 @@ from ._validation import (
     require_nonnegative_int,
     require_positive_int,
     require_schema_version,
-    require_string,
 )
 from .artifacts import PortSpec
 from .execution import ExecutionProfile, NetworkPolicy, RetryPolicy

scimesh/worker/config.py

@@ -2,7 +2,6 @@
 
 from __future__ import annotations
 
-import json
 from dataclasses import dataclass
 from math import isfinite
 from pathlib import Path

scimesh/worker/daemon.py

@@ -5,7 +5,6 @@ from __future__ import annotations
 import logging
 from dataclasses import replace
 from dataclasses import dataclass
-from pathlib import Path
 import random
 import re
 import shutil

scimesh/worker/runners.py

@@ -24,7 +24,6 @@ from uuid import NAMESPACE_URL, uuid5
 
 from scimesh.sdk.artifacts import (
     ArtifactCollection,
-    ArtifactRef,
     OutputManifest,
     Provenance,
 )

scimesh/workloads/descriptors/__init__.py

@@ -9,11 +9,9 @@ from .core import (
     DESCRIPTOR_NAMES,
     DescriptorRow,
     compute_descriptor_batch,
-    concatenate_descriptor_shards,
     descriptor_calculator,
     validate_descriptor_names,
     write_descriptor_rows,
-    write_descriptor_shards,
 )
 from .definition import (
     MAP_ENTRY_POINT,
@@ -31,11 +29,9 @@ __all__ = [
     "DescriptorBatchWorkload",
     "DescriptorRow",
     "compute_descriptor_batch",
-    "concatenate_descriptor_shards",
     "descriptor_batch_sdk_definition",
     "descriptor_calculator",
     "validate_descriptor_names",
     "workload_definition",
     "write_descriptor_rows",
-    "write_descriptor_shards",
 ]

scimesh/workloads/descriptors/core.py

@@ -19,7 +19,7 @@ import csv
 from dataclasses import dataclass
 from functools import lru_cache
 from pathlib import Path
-from typing import Any, Iterator, Mapping, Sequence
+from typing import Iterator, Sequence
 
 from rdkit import Chem
 from rdkit.ML.Descriptors.MoleculeDescriptors import MolecularDescriptorCalculator
@@ -229,86 +229,3 @@ def compute_descriptor_batch(
     materialized = list(rows)
     write_descriptor_rows(output_path, materialized)
     return stats.as_metrics()
-
-
-def write_descriptor_shards(
-    input_path: Path,
-    workspace: Path,
-    shard_rows: int,
-) -> list[Path]:
-    """Split the input TSV into deterministic row-bounded shards with headers."""
-    if (
-        isinstance(shard_rows, bool)
-        or not isinstance(shard_rows, int)
-        or shard_rows < 1
-    ):
-        raise ValueError("shard_rows must be a positive integer")
-    paths: list[Path] = []
-    current: Path | None = None
-    destination = None
-    writer = None
-    rows_in_shard = 0
-    try:
-        with input_path.open("r", encoding="utf-8", newline="") as source:
-            reader = csv.DictReader(source, delimiter="\t")
-            fieldnames = tuple(reader.fieldnames or ())
-            if not {"chembl_id", "canonical_smiles"}.issubset(set(fieldnames)):
-                raise ValueError(
-                    "dataset is missing required columns: chembl_id, canonical_smiles"
-                )
-            for row in reader:
-                if destination is None or rows_in_shard == shard_rows:
-                    if destination is not None:
-                        destination.close()
-                    current = workspace / f"shard-{len(paths)}.tsv"
-                    destination = current.open("w", encoding="utf-8", newline="")
-                    writer = csv.DictWriter(
-                        destination,
-                        fieldnames=list(fieldnames),
-                        delimiter="\t",
-                        lineterminator="\n",
-                    )
-                    writer.writeheader()
-                    paths.append(current)
-                    rows_in_shard = 0
-                assert writer is not None
-                writer.writerow(row)
-                rows_in_shard += 1
-    finally:
-        if destination is not None:
-            destination.close()
-    if not paths:
-        raise ValueError("dataset has no data rows")
-    return paths
-
-
-def concatenate_descriptor_shards(
-    partial_paths: Sequence[Path],
-    output_path: Path,
-) -> dict[str, int]:
-    """Merge shard partial CSVs by shard index with exactly one header.
-
-    Every partial is a full CSV with the same header. The first partial is
-    copied verbatim; each later partial contributes only its data rows, so the
-    merged file is byte-identical to the single-process reference for the same
-    input rows.
-    """
-    if not partial_paths:
-        raise ValueError("descriptor reducer requires at least one partial")
-    output_path.parent.mkdir(parents=True, exist_ok=True)
-    rows_emitted = 0
-    with output_path.open("w", encoding="utf-8", newline="") as destination:
-        for index, partial in enumerate(partial_paths):
-            with partial.open("r", encoding="utf-8", newline="") as source:
-                for line_index, line in enumerate(source):
-                    if line_index == 0:
-                        if index > 0:
-                            continue
-                        if line.rstrip("\r\n") != ",".join(DESCRIPTOR_COLUMNS):
-                            raise ValueError(
-                                "partial descriptor CSV has an invalid header"
-                            )
-                    destination.write(line)
-                    if line_index > 0:
-                        rows_emitted += 1
-    return {"partial_count": len(partial_paths), "rows_emitted": rows_emitted}

scimesh/workloads/environment.py

@@ -8,7 +8,6 @@ workload definition packages (``search``, ``graph``, ``descriptors``) and the
 from __future__ import annotations
 
 import hashlib
-import os
 import platform
 import sys
 

scimesh/workloads/molwt_filter/core.py

@@ -10,7 +10,6 @@ from __future__ import annotations
 
 import csv
 from pathlib import Path
-from typing import Mapping
 
 from rdkit import Chem
 from rdkit.Chem import Descriptors

scimesh/workloads/similarity_graph.py

@@ -12,7 +12,7 @@ from typing import Any
 
 from rdkit import DataStructs
 
-from scimesh.chemistry.dataset import DatasetStats, MoleculeRecord, iter_valid_molecules
+from scimesh.chemistry.dataset import DatasetStats, iter_valid_molecules
 from scimesh.chemistry.fingerprints import fingerprint