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.

tests/unit/agents/test_operator_transcript.py

@@ -54,8 +54,8 @@ from artemis.memory.transcript import (
 
 # SHA-256 snapshots of the legacy system message with the fixed inputs below.
 # Update these when an intentional template change alters the rendered prompt.
-GOLDEN_EMPTY_PLAN = "d715128625911aec46c83138e15aabfa967b385ab4c878509fe36ab4304fae2a"
-GOLDEN_SENTINEL_PLAN = "e2cf4ede75ffd9e283159f70dcd5c94a169c18e9f6dd4d1e7aacf460e956eaf3"
+GOLDEN_EMPTY_PLAN = "58bf034527b2d782f7746d8e379cb0decc44a05dfa18cb73153d49cd8265002b"
+GOLDEN_SENTINEL_PLAN = "b328052390a0a815c096b8ec4c5286421be487e7b6cd3bec55d6bc62a1f2518f"
 
 SCREENSHOT_B64 = base64.b64encode(b"fake-jpeg-bytes").decode("utf-8")