update ci to use uv, updated linting

.github/workflows/ci.yml

@@ -21,23 +21,19 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: '3.11'
-          cache: 'pip'
 
-      - name: Install dependencies
-        run: |
-          cd core
-          pip install -e .
-          pip install -r requirements-dev.txt
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
 
       - name: Ruff lint
         run: |
-          ruff check core/
-          ruff check tools/
+          uv run --project core ruff check core/
+          uv run --project tools ruff check tools/
 
       - name: Ruff format
         run: |
-          ruff format --check core/
-          ruff format --check tools/
+          uv run --project core ruff format --check core/
+          uv run --project tools ruff format --check tools/
 
   test:
     name: Test Python Framework
@@ -52,18 +48,15 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: '3.11'
-          cache: 'pip'
 
-      - name: Install dependencies
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+
+      - name: Install dependencies and run tests
         run: |
           cd core
-          pip install -e .
-          pip install -r requirements-dev.txt
-
-      - name: Run tests
-        run: |
-          cd core
-          pytest tests/ -v
+          uv sync
+          uv run pytest tests/ -v
 
   test-tools:
     name: Test Tools
@@ -97,13 +90,14 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: '3.11'
-          cache: 'pip'
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
 
       - name: Install dependencies
         run: |
           cd core
-          pip install -e .
-          pip install -r requirements-dev.txt
+          uv sync
 
       - name: Validate exported agents
         run: |
@@ -126,7 +120,7 @@ jobs:
           for agent_dir in "${agent_dirs[@]}"; do
             if [ -f "$agent_dir/agent.json" ]; then
               echo "Validating $agent_dir"
-              python -c "import json; json.load(open('$agent_dir/agent.json'))"
+              uv run python -c "import json; json.load(open('$agent_dir/agent.json'))"
               validated=$((validated + 1))
             fi
           done

.gitignore

@@ -54,7 +54,6 @@ __pycache__/
 *.egg-info/
 .eggs/
 *.egg
-uv.lock
 
 # Generated runtime data
 core/data/

core/framework/builder/workflow.py

@@ -15,7 +15,7 @@ You cannot skip steps or bypass validation.
 
 from collections.abc import Callable
 from datetime import datetime
-from enum import Enum
+from enum import StrEnum
 from pathlib import Path
 from typing import Any
 
@@ -26,7 +26,7 @@ from framework.graph.goal import Goal
 from framework.graph.node import NodeSpec
 
 
-class BuildPhase(str, Enum):
+class BuildPhase(StrEnum):
     """Current phase of the build process."""
 
     INIT = "init"  # Just started

core/framework/credentials/models.py

@@ -8,7 +8,7 @@ containing one or more keys (e.g., api_key, access_token, refresh_token).
 from __future__ import annotations
 
 from datetime import UTC, datetime
-from enum import Enum
+from enum import StrEnum
 from typing import Any
 
 from pydantic import BaseModel, Field, SecretStr
@@ -19,7 +19,7 @@ def _utc_now() -> datetime:
     return datetime.now(UTC)
 
 
-class CredentialType(str, Enum):
+class CredentialType(StrEnum):
     """Types of credentials the store can manage."""
 
     API_KEY = "api_key"

core/framework/credentials/oauth2/provider.py

@@ -11,11 +11,11 @@ from __future__ import annotations
 
 from dataclasses import dataclass, field
 from datetime import UTC, datetime, timedelta
-from enum import Enum
+from enum import StrEnum
 from typing import Any
 
 
-class TokenPlacement(str, Enum):
+class TokenPlacement(StrEnum):
     """Where to place the access token in HTTP requests."""
 
     HEADER_BEARER = "header_bearer"

core/framework/graph/edge.py

@@ -21,7 +21,7 @@ allowing the LLM to evaluate whether proceeding along an edge makes sense
 given the current goal, context, and execution state.
 """
 
-from enum import Enum
+from enum import StrEnum
 from typing import Any
 
 from pydantic import BaseModel, Field
@@ -29,7 +29,7 @@ from pydantic import BaseModel, Field
 from framework.graph.safe_eval import safe_eval
 
 
-class EdgeCondition(str, Enum):
+class EdgeCondition(StrEnum):
     """When an edge should be traversed."""
 
     ALWAYS = "always"  # Always after source completes

core/framework/graph/goal.py

@@ -12,13 +12,13 @@ Goals are:
 """
 
 from datetime import datetime
-from enum import Enum
+from enum import StrEnum
 from typing import Any
 
 from pydantic import BaseModel, Field
 
 
-class GoalStatus(str, Enum):
+class GoalStatus(StrEnum):
     """Lifecycle status of a goal."""
 
     DRAFT = "draft"  # Being defined

core/framework/graph/hitl.py

@@ -6,11 +6,11 @@ where agents need to gather input from humans.
 """
 
 from dataclasses import dataclass, field
-from enum import Enum
+from enum import StrEnum
 from typing import Any
 
 
-class HITLInputType(str, Enum):
+class HITLInputType(StrEnum):
     """Type of input expected from human."""
 
     FREE_TEXT = "free_text"  # Open-ended text response

core/framework/graph/plan.py

@@ -11,13 +11,13 @@ The Plan is the contract between the external planner and the executor:
 """
 
 from datetime import datetime
-from enum import Enum
+from enum import StrEnum
 from typing import Any
 
 from pydantic import BaseModel, Field
 
 
-class ActionType(str, Enum):
+class ActionType(StrEnum):
     """Types of actions a PlanStep can perform."""
 
     LLM_CALL = "llm_call"  # Call LLM for generation
@@ -27,7 +27,7 @@ class ActionType(str, Enum):
     CODE_EXECUTION = "code_execution"  # Execute dynamic code (sandboxed)
 
 
-class StepStatus(str, Enum):
+class StepStatus(StrEnum):
     """Status of a plan step."""
 
     PENDING = "pending"
@@ -56,7 +56,7 @@ class StepStatus(str, Enum):
         return self == StepStatus.COMPLETED
 
 
-class ApprovalDecision(str, Enum):
+class ApprovalDecision(StrEnum):
     """Human decision on a step requiring approval."""
 
     APPROVE = "approve"  # Execute as planned
@@ -91,7 +91,7 @@ class ApprovalResult(BaseModel):
     model_config = {"extra": "allow"}
 
 
-class JudgmentAction(str, Enum):
+class JudgmentAction(StrEnum):
     """Actions the judge can take after evaluating a step."""
 
     ACCEPT = "accept"  # Step completed successfully, continue
@@ -423,7 +423,7 @@ class Plan(BaseModel):
         }
 
 
-class ExecutionStatus(str, Enum):
+class ExecutionStatus(StrEnum):
     """Status of plan execution."""
 
     COMPLETED = "completed"

core/framework/runtime/event_bus.py

@@ -12,13 +12,13 @@ import logging
 from collections.abc import Awaitable, Callable
 from dataclasses import dataclass, field
 from datetime import datetime
-from enum import Enum
+from enum import StrEnum
 from typing import Any
 
 logger = logging.getLogger(__name__)
 
 
-class EventType(str, Enum):
+class EventType(StrEnum):
     """Types of events that can be published."""
 
     # Execution lifecycle

core/framework/runtime/shared_state.py

@@ -11,13 +11,13 @@ import asyncio
 import logging
 import time
 from dataclasses import dataclass, field
-from enum import Enum
+from enum import StrEnum
 from typing import Any
 
 logger = logging.getLogger(__name__)
 
 
-class IsolationLevel(str, Enum):
+class IsolationLevel(StrEnum):
     """State isolation level for concurrent executions."""
 
     ISOLATED = "isolated"  # Private state per execution
@@ -25,7 +25,7 @@ class IsolationLevel(str, Enum):
     SYNCHRONIZED = "synchronized"  # Shared with write locks (strong consistency)
 
 
-class StateScope(str, Enum):
+class StateScope(StrEnum):
     """Scope for state operations."""
 
     EXECUTION = "execution"  # Local to a single execution

core/framework/schemas/decision.py

@@ -10,13 +10,13 @@ This is MORE important than actions because:
 """
 
 from datetime import datetime
-from enum import Enum
+from enum import StrEnum
 from typing import Any
 
 from pydantic import BaseModel, Field, computed_field
 
 
-class DecisionType(str, Enum):
+class DecisionType(StrEnum):
     """Types of decisions an agent can make."""
 
     TOOL_SELECTION = "tool_selection"  # Which tool to use

core/framework/schemas/run.py

@@ -6,7 +6,7 @@ summaries and metrics that Builder needs to understand what happened.
 """
 
 from datetime import datetime
-from enum import Enum
+from enum import StrEnum
 from typing import Any
 
 from pydantic import BaseModel, Field, computed_field
@@ -14,7 +14,7 @@ from pydantic import BaseModel, Field, computed_field
 from framework.schemas.decision import Decision, Outcome
 
 
-class RunStatus(str, Enum):
+class RunStatus(StrEnum):
     """Status of a run."""
 
     RUNNING = "running"

core/framework/testing/approval_types.py

@@ -6,13 +6,13 @@ programmatic/MCP-based approval.
 """
 
 from datetime import datetime
-from enum import Enum
+from enum import StrEnum
 from typing import Any
 
 from pydantic import BaseModel, Field
 
 
-class ApprovalAction(str, Enum):
+class ApprovalAction(StrEnum):
     """Actions a user can take on a generated test."""
 
     APPROVE = "approve"  # Accept as-is

core/framework/testing/test_case.py

@@ -6,13 +6,13 @@ but require mandatory user approval before being stored.
 """
 
 from datetime import datetime
-from enum import Enum
+from enum import StrEnum
 from typing import Any
 
 from pydantic import BaseModel, Field
 
 
-class ApprovalStatus(str, Enum):
+class ApprovalStatus(StrEnum):
     """Status of user approval for a generated test."""
 
     PENDING = "pending"  # Awaiting user review
@@ -21,7 +21,7 @@ class ApprovalStatus(str, Enum):
     REJECTED = "rejected"  # User declined (with reason)
 
 
-class TestType(str, Enum):
+class TestType(StrEnum):
     """Type of test based on what it validates."""
 
     __test__ = False  # Not a pytest test class

core/framework/testing/test_result.py

@@ -6,13 +6,13 @@ categorization for guiding iteration strategy.
 """
 
 from datetime import datetime
-from enum import Enum
+from enum import StrEnum
 from typing import Any
 
 from pydantic import BaseModel, Field
 
 
-class ErrorCategory(str, Enum):
+class ErrorCategory(StrEnum):
     """
     Category of test failure for guiding iteration.