Lay the prompt out so the endpoint can cache most of it

Prompt caching bills on a shared prefix: the endpoint reuses the request up
to the first byte that differs from last time and no further. The live
world-state block sat third from the top of the system message, so every turn
re-priced the instructions, the plot essentials and the whole story history
underneath it. The retrieved memories and the rewritten summary did it again.

Everything fixed is emitted first now, and everything that moves goes after
the history, ordered least-volatile first — which is also where recency serves
it best, the reasoning that already put the emit reminder last. The three tail
sections that are last for their own reasons stay last. The moved sections are
still charged to the token budget; only their position changed.

Two smaller halves of the same problem. OpenRouter serves a model from
whichever upstream is free and each upstream holds its own cache, so a
deepseek model now names deepseek as its preferred upstream — a preference,
not a restriction, so a turn still runs if that upstream is down. And the
endpoint's usage block is read back off the response and kept per attempt, so
the hit rate shows up in Insights and the debug log instead of being assumed.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DfMCsN1KBLsTqMkj5hSgrY

backend/app/attempts.py

@@ -40,9 +40,11 @@ from .context import lineage
 
 # The slices of a context snapshot that belong to one attempt rather than to
 # the turn: the world-state delta it proposed and what the referee did with it,
-# the script report, and the model's literal reply. Everything else in a
+# the script report, the model's literal reply, and the endpoint's token
+# accounting — each attempt is its own API call, and a retry is precisely the
+# call expected to read the prompt back out of cache. Everything else in a
 # snapshot is the prompt, which is assembled once per turn.
-ATTEMPT_KEYS = ("world_state", "script", "raw_output")
+ATTEMPT_KEYS = ("world_state", "script", "raw_output", "usage")
 
 
 # ------------------------------------------------------------------ reading