fix: improve cross-device evidence and exploration lifecycle

Align Responses cache affinity across execution and summary calls, preserve required checks and evidence uncertainty, and allow safe deletion of inactive explorations while retaining independent reruns.

Validation: backend suite passed except intentional prompt golden drift, then all 17 transcript tests passed after snapshot refresh; 268 frontend tests and production build passed; Ruff, quality ratchet and core type checks passed.

artemis/services/llm.py

@@ -23,14 +23,13 @@ from collections.abc import Awaitable, Callable, Coroutine
 from contextvars import ContextVar, Token
 from contextlib import aclosing
 import functools
-import hashlib
 import logging
 from pathlib import Path
 import re
 import sys
 import time
 from typing import Any, Literal, TypeVar, overload
-from uuid import UUID, uuid4
+from uuid import uuid4
 
 from langchain_core.language_models.chat_models import BaseChatModel
 from langchain_core.messages import AIMessage, BaseMessage, HumanMessage
@@ -48,6 +47,7 @@ from artemis.config import (
 from artemis.context import ArtemisContext
 from artemis.data_engine.trace import CURRENT_TRACE_ID, DataEngineCallbackHandler
 from artemis.llm.diagnostics import ACTIVE_ATTEMPT, RequestAttempt, error_text, input_images
+from artemis.llm.cache_affinity import cache_affinity_options
 from artemis.llm.reliability import (
     CircuitBreaker,
     FailureCategory,
@@ -637,16 +637,7 @@ class RobustChatModelWrapper:
 
     def _prepare_model_call(self, args: tuple, kwargs: dict) -> tuple[tuple, dict]:
         model_name = self.endpoint.model_name if self.endpoint else None
-        engine = getattr(self.ctx, "data_engine", None)
-        session = getattr(self.ctx, "exploration_id", None) or getattr(
-            engine, "current_session_id", None
-        )
-        if isinstance(session, (str, UUID)) and str(session):
-            identity = f"{session}:{self.role or 'model'}:{model_name}"
-            kwargs = {
-                "prompt_cache_key": "artemis:" + hashlib.sha256(identity.encode()).hexdigest()[:40],
-                **kwargs,
-            }
+        kwargs = cache_affinity_options(self.ctx, self.role, model_name, kwargs)
         if (
             args
             and isinstance(args[0], (list, tuple))