chore(context): apply linter fixes and sort imports (#86)

Phase 8 of Context Management Engine - Final Cleanup:

- Sort __all__ exports alphabetically
- Sort imports per isort conventions
- Fix minor linting issues

Final test results:
- 311 context management tests passing
- 2507 total backend tests passing
- 85% code coverage

Context Management Engine is complete with all 8 phases:
1. Foundation: Types, Config, Exceptions
2. Token Budget Management
3. Context Scoring & Ranking
4. Context Assembly Pipeline
5. Model Adapters (Claude, OpenAI)
6. Caching Layer (Redis + in-memory)
7. Main Engine & Integration
8. Testing & Documentation

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

backend/app/services/context/__init__.py

@@ -35,12 +35,36 @@ Usage:
 """
 
 # Budget Management
+# Adapters
+from .adapters import (
+    ClaudeAdapter,
+    DefaultAdapter,
+    ModelAdapter,
+    OpenAIAdapter,
+    get_adapter,
+)
+
+# Assembly
+from .assembly import (
+    ContextPipeline,
+    PipelineMetrics,
+)
 from .budget import (
     BudgetAllocator,
     TokenBudget,
     TokenCalculator,
 )
 
+# Cache
+from .cache import ContextCache
+
+# Compression
+from .compression import (
+    ContextCompressor,
+    TruncationResult,
+    TruncationStrategy,
+)
+
 # Configuration
 from .config import (
     ContextSettings,
@@ -49,6 +73,9 @@ from .config import (
     reset_context_settings,
 )
 
+# Engine
+from .engine import ContextEngine, create_context_engine
+
 # Exceptions
 from .exceptions import (
     AssemblyTimeoutError,
@@ -63,34 +90,6 @@ from .exceptions import (
     TokenCountError,
 )
 
-# Assembly
-from .assembly import (
-    ContextPipeline,
-    PipelineMetrics,
-)
-
-# Compression
-from .compression import (
-    ContextCompressor,
-    TruncationResult,
-    TruncationStrategy,
-)
-
-# Adapters
-from .adapters import (
-    ClaudeAdapter,
-    DefaultAdapter,
-    get_adapter,
-    ModelAdapter,
-    OpenAIAdapter,
-)
-
-# Cache
-from .cache import ContextCache
-
-# Engine
-from .engine import ContextEngine, create_context_engine
-
 # Prioritization
 from .prioritization import (
     ContextRanker,

backend/app/services/context/adapters/__init__.py

@@ -29,7 +29,7 @@ def get_adapter(model: str) -> ModelAdapter:
 __all__ = [
     "ClaudeAdapter",
     "DefaultAdapter",
-    "get_adapter",
     "ModelAdapter",
     "OpenAIAdapter",
+    "get_adapter",
 ]

backend/app/services/context/engine.py

@@ -8,7 +8,6 @@ Provides a high-level API for assembling optimized context for LLM requests.
 import logging
 from typing import TYPE_CHECKING, Any
 
-from .adapters import get_adapter
 from .assembly import ContextPipeline
 from .budget import BudgetAllocator, TokenBudget, TokenCalculator
 from .cache import ContextCache

backend/app/services/context/prioritization/ranker.py

@@ -10,10 +10,10 @@ from typing import TYPE_CHECKING, Any
 
 from ..budget import TokenBudget, TokenCalculator
 from ..scoring.composite import CompositeScorer, ScoredContext
-from ..types import BaseContext, ContextType
+from ..types import BaseContext
 
 if TYPE_CHECKING:
-    from app.services.mcp.client_manager import MCPClientManager
+    pass
 
 logger = logging.getLogger(__name__)
 

backend/app/services/context/scoring/base.py

@@ -10,7 +10,7 @@ from typing import TYPE_CHECKING, Any, Protocol, runtime_checkable
 from ..types import BaseContext
 
 if TYPE_CHECKING:
-    from app.services.mcp.client_manager import MCPClientManager
+    pass
 
 
 @runtime_checkable

backend/app/services/context/scoring/composite.py

@@ -6,15 +6,14 @@ Combines multiple scoring strategies with configurable weights.
 
 import asyncio
 import logging
-from dataclasses import dataclass, field
+from dataclasses import dataclass
 from typing import TYPE_CHECKING, Any
 
-from .base import BaseScorer
+from ..config import ContextSettings, get_context_settings
+from ..types import BaseContext
 from .priority import PriorityScorer
 from .recency import RecencyScorer
 from .relevance import RelevanceScorer
-from ..config import ContextSettings, get_context_settings
-from ..types import BaseContext
 
 if TYPE_CHECKING:
     from app.services.mcp.client_manager import MCPClientManager

backend/app/services/context/scoring/priority.py

@@ -6,8 +6,8 @@ Scores context based on assigned priority levels.
 
 from typing import Any
 
+from ..types import BaseContext, ContextType
 from .base import BaseScorer
-from ..types import BaseContext, ContextPriority, ContextType
 
 
 class PriorityScorer(BaseScorer):

backend/app/services/context/scoring/recency.py

@@ -6,11 +6,11 @@ More recent content gets higher scores.
 """
 
 import math
-from datetime import UTC, datetime, timedelta
+from datetime import UTC, datetime
 from typing import Any
 
-from .base import BaseScorer
 from ..types import BaseContext, ContextType
+from .base import BaseScorer
 
 
 class RecencyScorer(BaseScorer):

backend/app/services/context/scoring/relevance.py

@@ -9,8 +9,8 @@ import logging
 import re
 from typing import TYPE_CHECKING, Any
 
+from ..types import BaseContext, KnowledgeContext
 from .base import BaseScorer
-from ..types import BaseContext, ContextType, KnowledgeContext
 
 if TYPE_CHECKING:
     from app.services.mcp.client_manager import MCPClientManager