fix: resolve import errors and add missing modules

- Fix siare/__init__.py exports (remove non-existent ExecutionTrace, RoleOutput)
- Fix siare/core/__init__.py exports to match available classes
- Add siare/services/__init__.py with proper service exports
- Add siare/services/selection/ module (factory.py, strategies.py)
- Add tests/mocks/ for test fixtures
- Add core unit tests (202 passing, 8 version format assertions)

Auto-applied linter fixes for import ordering.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <[email protected]>

Author: danielbentes

siare/__init__.py

@@ -15,30 +15,28 @@
     >>> improved_config = await director.mutate_sop(config, diagnosis)
 """
 
+from siare.core.hooks import (
+    EvaluationHooks,
+    EvolutionHooks,
+    ExecutionHooks,
+    HookContext,
+    HookRegistry,
+    HookRunner,
+    LLMHooks,
+    StorageHooks,
+)
 from siare.core.models import (
     Diagnosis,
     EvaluationVector,
-    ExecutionTrace,
     GraphEdge,
     MetricConfig,
     MutationType,
     ProcessConfig,
     PromptGenome,
     Role,
-    RoleOutput,
     SOPGene,
     Task,
 )
-from siare.core.hooks import (
-    EvaluationHooks,
-    EvolutionHooks,
-    ExecutionHooks,
-    HookContext,
-    HookRegistry,
-    HookRunner,
-    LLMHooks,
-    StorageHooks,
-)
 
 __version__ = "1.0.0"
 __author__ = "Daniel Bentes"
@@ -56,8 +54,6 @@
     "PromptGenome",
     "Task",
     "EvaluationVector",
-    "ExecutionTrace",
-    "RoleOutput",
     "Diagnosis",
     "MutationType",
     "MetricConfig",

siare/adapters/base.py

@@ -1,7 +1,7 @@
 """Base Tool Adapter - Plugin system for tools"""
 
 from abc import ABC, abstractmethod
-from typing import Any, Optional
+from typing import Any
 
 
 class ToolAdapter(ABC):
@@ -83,9 +83,9 @@ def __enter__(self):
 
     def __exit__(
         self,
-        exc_type: Optional[type[BaseException]],
-        exc_val: Optional[BaseException],
-        exc_tb: Optional[Any],
+        exc_type: type[BaseException] | None,
+        exc_val: BaseException | None,
+        exc_tb: Any | None,
     ) -> None:
         """Context manager exit"""
         self.cleanup()

siare/adapters/vector_search.py

@@ -2,14 +2,13 @@
 
 import logging
 import os
-from typing import Any, Optional
+from typing import Any
 
 import numpy as np
 import numpy.typing as npt
 
 from siare.adapters.base import ToolAdapter, register_adapter
 
-
 logger = logging.getLogger(__name__)
 
 
@@ -18,7 +17,7 @@
 # ============================================================================
 
 # Sentence-transformers model (lazy loaded) - lowercase to avoid constant redefinition errors
-_sentence_transformer_model: Optional[Any] = None
+_sentence_transformer_model: Any | None = None
 _sentence_transformer_name = "all-MiniLM-L6-v2"
 
 # Import flags (use lowercase to avoid constant redefinition errors)
@@ -40,7 +39,7 @@
     OpenAI = None  # type: ignore
 
 
-def _get_sentence_transformer_model() -> Optional[Any]:
+def _get_sentence_transformer_model() -> Any | None:
     """Lazy load sentence-transformer model"""
     global _sentence_transformer_model
     if _sentence_transformer_model is None and _sentence_transformers_available:
@@ -106,8 +105,8 @@ def __init__(self, config: dict[str, Any]):
         if self.max_memory_vectors <= 0:
             raise ValueError(f"max_memory_vectors must be positive, got {self.max_memory_vectors}")
 
-        self.client: Optional[Any] = None
-        self.index: Optional[Any] = None
+        self.client: Any | None = None
+        self.index: Any | None = None
 
         # In-memory storage for MVP
         self._memory_vectors: list[npt.NDArray[np.float64]] = []
@@ -389,7 +388,7 @@ def _validate_embedding_dimension(self) -> None:
                 self.dimension = expected_dim
 
     def _search_memory(
-        self, query_vector: list[float], top_k: int, filter_dict: Optional[dict[str, Any]] = None
+        self, query_vector: list[float], top_k: int, filter_dict: dict[str, Any] | None = None
     ) -> list[dict[str, Any]]:
         """Search in-memory vectors"""
 
@@ -429,7 +428,7 @@ def _search_memory(
         return results
 
     def _search_pinecone(
-        self, query_vector: list[float], top_k: int, filter_dict: Optional[dict[str, Any]] = None
+        self, query_vector: list[float], top_k: int, filter_dict: dict[str, Any] | None = None
     ) -> list[dict[str, Any]]:
         """Search Pinecone index"""
 
@@ -455,7 +454,7 @@ def _search_pinecone(
         return results
 
     def _search_chroma(
-        self, query_vector: list[float], top_k: int, filter_dict: Optional[dict[str, Any]] = None
+        self, query_vector: list[float], top_k: int, filter_dict: dict[str, Any] | None = None
     ) -> list[dict[str, Any]]:
         """Search ChromaDB collection"""
 
@@ -484,14 +483,14 @@ def _search_chroma(
         return results
 
     def _search_qdrant(
-        self, query_vector: list[float], top_k: int, filter_dict: Optional[dict[str, Any]] = None
+        self, query_vector: list[float], top_k: int, filter_dict: dict[str, Any] | None = None
     ) -> list[dict[str, Any]]:
         """Search Qdrant collection"""
 
         from qdrant_client.models import FieldCondition, Filter, MatchValue
 
         # Build filter
-        qd_filter: Optional[Filter] = None
+        qd_filter: Filter | None = None
         if filter_dict:
             conditions: list[FieldCondition] = [
                 FieldCondition(key=k, match=MatchValue(value=v)) for k, v in filter_dict.items()

siare/adapters/web_search.py

@@ -3,14 +3,13 @@
 import logging
 from collections import deque
 from time import sleep, time
-from typing import Any, Optional
+from typing import Any
 from urllib.parse import urlparse
 
 import requests
 
 from siare.adapters.base import ToolAdapter, register_adapter
 
-
 logger = logging.getLogger(__name__)
 
 
@@ -51,7 +50,7 @@ def __init__(self, config: dict[str, Any]):
         self.rate_limit = config.get("rate_limit", 10)
         self.provider_config = config.get("provider_config", {})
 
-        self.session: Optional[requests.Session] = None
+        self.session: requests.Session | None = None
         self.request_times: deque[float] = deque(maxlen=self.rate_limit)
 
     def initialize(self) -> None:
@@ -199,12 +198,12 @@ def _validate_url(self, url: str) -> bool:
         try:
             result = urlparse(url)
             return all([result.scheme, result.netloc])
-        except Exception as e:  # noqa: BLE001 - Catch-all with logging for URL validation
+        except Exception as e:
             logger.debug(f"URL validation failed: {e}")
             return False
 
     def _search_google(
-        self, query: str, max_results: int, filter_date: Optional[str], safe_search: bool
+        self, query: str, max_results: int, filter_date: str | None, safe_search: bool
     ) -> list[dict[str, Any]]:
         """Search using Google Custom Search API"""
 
@@ -254,7 +253,7 @@ def _search_google(
         return results
 
     def _search_bing(
-        self, query: str, max_results: int, filter_date: Optional[str], safe_search: bool
+        self, query: str, max_results: int, filter_date: str | None, safe_search: bool
     ) -> list[dict[str, Any]]:
         """Search using Bing Search API"""
 
@@ -299,7 +298,9 @@ def _search_duckduckgo(self, query: str, max_results: int) -> list[dict[str, Any
 
         try:
             from duckduckgo_search import DDGS  # type: ignore[import-untyped]
-            from duckduckgo_search.exceptions import DuckDuckGoSearchException  # type: ignore[import-untyped]
+            from duckduckgo_search.exceptions import (
+                DuckDuckGoSearchException,  # type: ignore[import-untyped]
+            )
 
             # Retry with exponential backoff for rate limits
             max_retries = 3
@@ -341,7 +342,7 @@ def _search_duckduckgo(self, query: str, max_results: int) -> list[dict[str, Any
             raise ImportError("DuckDuckGo search requires: pip install duckduckgo-search")
 
     def _search_serper(
-        self, query: str, max_results: int, filter_date: Optional[str]
+        self, query: str, max_results: int, filter_date: str | None
     ) -> list[dict[str, Any]]:
         """Search using Serper.dev (Google Search API)"""
 

siare/adapters/wikipedia_search.py

@@ -11,7 +11,6 @@
 
 from siare.adapters.base import ToolAdapter, register_adapter
 
-
 logger = logging.getLogger(__name__)
 
 

siare/benchmarks/__init__.py

@@ -46,21 +46,6 @@
     GenerationHistoryEntry,
     StatisticalComparison,
 )
-from siare.benchmarks.self_improvement_benchmark import (
-    GenerationSnapshot,
-    SelfImprovementBenchmark,
-    SelfImprovementConfig,
-    SelfImprovementResult,
-)
-from siare.benchmarks.tracking import (
-    ChangeSummary,
-    ConvergenceInfo,
-    LearningCurvePoint,
-    LearningCurveTracker,
-    PromptDiff,
-    PromptDiffTracker,
-    PromptSnapshot,
-)
 from siare.benchmarks.hotpotqa import HotpotQADataset
 from siare.benchmarks.metrics import (
     STANDARD_K_VALUES,
@@ -104,6 +89,12 @@
 from siare.benchmarks.reporter import BenchmarkReporter
 from siare.benchmarks.reproducibility import EnvironmentSnapshot, ReproducibilityTracker
 from siare.benchmarks.runner import BenchmarkResults, BenchmarkRunner, SampleResult
+from siare.benchmarks.self_improvement_benchmark import (
+    GenerationSnapshot,
+    SelfImprovementBenchmark,
+    SelfImprovementConfig,
+    SelfImprovementResult,
+)
 from siare.benchmarks.sops import (
     create_benchmark_genome,
     create_benchmark_sop,
@@ -112,7 +103,15 @@
     create_rag_genome,
     create_rag_sop,
 )
-
+from siare.benchmarks.tracking import (
+    ChangeSummary,
+    ConvergenceInfo,
+    LearningCurvePoint,
+    LearningCurveTracker,
+    PromptDiff,
+    PromptDiffTracker,
+    PromptSnapshot,
+)
 
 __all__ = [
     # Constants

siare/benchmarks/adapters.py

@@ -1,6 +1,5 @@
 """Adapters for converting benchmark datasets to evolution formats."""
 from datetime import datetime, timezone
-from typing import Optional
 
 from siare.benchmarks.base import BenchmarkDataset
 from siare.core.models import TaskSet
@@ -9,8 +8,8 @@
 def benchmark_to_taskset(
     dataset: BenchmarkDataset,
     version: str = "1.0.0",
-    domain: Optional[str] = None,
-    description: Optional[str] = None,
+    domain: str | None = None,
+    description: str | None = None,
 ) -> TaskSet:
     """Convert a BenchmarkDataset to a TaskSet for evolution.
 

siare/benchmarks/base.py

@@ -2,8 +2,7 @@
 from abc import ABC, abstractmethod
 from collections.abc import Iterator
 from dataclasses import dataclass, field
-from typing import TYPE_CHECKING, Any, Optional
-
+from typing import TYPE_CHECKING, Any
 
 if TYPE_CHECKING:
     from siare.core.models import Task
@@ -108,7 +107,7 @@ class BenchmarkDataset(ABC):
     def __init__(
         self,
         split: str = "test",
-        max_samples: Optional[int] = None,
+        max_samples: int | None = None,
     ) -> None:
         """Initialize the benchmark dataset.
 

siare/benchmarks/comparison/__init__.py

@@ -1,19 +1,19 @@
 """Baseline comparison framework for benchmark evaluation."""
 
 from siare.benchmarks.comparison.baselines import (
+    STATIC_BASELINE_CONFIGS,
     BaselineComparison,
     BaselineResult,
     RandomSearchBaseline,
-    STATIC_BASELINE_CONFIGS,
     create_no_retrieval_baseline,
     create_static_baseline,
 )
 
 __all__ = [
+    "STATIC_BASELINE_CONFIGS",
     "BaselineComparison",
     "BaselineResult",
     "RandomSearchBaseline",
-    "STATIC_BASELINE_CONFIGS",
     "create_no_retrieval_baseline",
     "create_static_baseline",
 ]

siare/benchmarks/comparison/baselines.py

@@ -11,7 +11,7 @@
 
 import random
 from dataclasses import dataclass
-from typing import Any, Optional
+from typing import Any
 
 from siare.benchmarks.sops.evolvable_rag import (
     EVOLVABLE_PARAM_BOUNDS,
@@ -24,7 +24,6 @@
 )
 from siare.core.models import ProcessConfig, PromptGenome
 
-
 # Static baseline configurations
 STATIC_BASELINE_CONFIGS: dict[str, dict[str, Any]] = {
     "poor": {
@@ -117,8 +116,8 @@ class RandomSearchBaseline:
     def __init__(
         self,
         n_samples: int = 20,
-        seed: Optional[int] = None,
-        param_bounds: Optional[dict[str, dict[str, Any]]] = None,
+        seed: int | None = None,
+        param_bounds: dict[str, dict[str, Any]] | None = None,
     ) -> None:
         """Initialize random search baseline.