fix(config): adjust story sweep rotation region and stage count

.claude/skills/deploy-gpu/SKILL.md

@@ -1,32 +1,36 @@
 ---
 name: deploy-gpu
-description: Sync this repo's working tree to nik-gpu, refresh the flat runtime paths via setup.sh, and optionally smoke-test one task against the live game. Use when the user asks to deploy, push, sync, or ship code to nik-gpu, or wants to try a task live after an edit.
+description: Sync this repo's working tree to nik-gpu, where it runs directly out of the git checkout, and optionally smoke-test one task against the live game. Use when the user asks to deploy, push, sync, or ship code to nik-gpu, or wants to try a task live after an edit.
 disable-model-invocation: true
 ---
 
 # /deploy-gpu
 
-Deploys the current working tree to `nik-gpu` and refreshes the runtime paths
-`~/ba_dailies.sh` actually executes from. See `README.md`'s "Deploying your
-changes" section and `CLAUDE.md`'s "Deployment model" for the source of truth
-this skill wraps — if either has changed, follow the doc over this file.
+Deploys the current working tree to `nik-gpu`. See `README.md`'s "Deploying
+your changes" section and `CLAUDE.md`'s "Deployment model" for the source of
+truth this skill wraps — if either has changed, follow the doc over this
+file.
 
 Optional task argument (smoke test): $ARGUMENTS
 
-## Why two steps, not just rsync
+## The checkout IS the runtime
 
-`rsync` only updates the git checkout at `nik-gpu:~/repo/ba-auto-daily/`. The
-launcher itself runs from separate flat paths (`~/ba_dailies.sh`,
-`~/ba_daily.py`, `~/ba_auto/`, `~/ba_assets/`) that only `setup.sh` copies
-into. Skipping the `setup.sh` step means nik-gpu keeps executing old code
-even though the rsync "succeeded".
+As of 2026-07-18, `ba_dailies.sh` runs directly out of the git checkout at
+`nik-gpu:~/repo/ba-auto-daily/` — there is no separate flat-path copy
+(`~/ba_dailies.sh`, `~/ba_daily.py`, `~/ba_auto/`, `~/ba_assets/`) for
+`setup.sh` to keep in sync. If those flat paths turn up on nik-gpu, they're
+stale leftovers from the pre-2026-07-18 model — don't assume anything reads
+from them.
+
+This means a plain rsync is normally enough on its own; `setup.sh` is no
+longer a required second step for an ordinary code change.
 
 ## Steps
 
 1. From the repo root, run:
 
    ```bash
-   rsync -av --delete \
+   rsync -av \
      --exclude='.git/' \
      --exclude='__pycache__/' \
      --exclude='*.pyc' \
@@ -37,7 +41,12 @@ even though the rsync "succeeded".
      ./ nik-gpu:~/repo/ba-auto-daily/
    ```
 
-2. Run:
+2. Only run `setup.sh` if this deploy also needs it — a fresh/empty checkout,
+   a new Python dependency, a new host-level tool requirement (e.g. a
+   tesseract language pack), or the venv otherwise needs
+   installing/reinstalling. It's idempotent and safe to re-run, but it no
+   longer copies any files anywhere, so don't run it out of habit expecting
+   it to "finish" the deploy — step 1's rsync already did:
 
    ```bash
    ssh nik-gpu "cd ~/repo/ba-auto-daily && ./setup.sh"
@@ -47,21 +56,24 @@ even though the rsync "succeeded".
    missing `tesseract`) rather than treating the deploy as done.
 
 3. **Only if a task name was given in `$ARGUMENTS`** (e.g. `/deploy-gpu
-   cafe`), run it live as a smoke test:
+   cafe`), run it live as a smoke test, from the checkout path directly:
 
    ```bash
-   ssh nik-gpu "~/ba_dailies.sh <task>"
+   ssh nik-gpu "~/repo/ba-auto-daily/ba_dailies.sh <task>"
    ```
 
    Do not invent a task to run if none was given — several tasks
-   (`story_sweep`, `shop_common`, `shop_tactical`, `lesson`) spend real AP,
-   credits, tactical coin, or lesson tickets, and running one without the
-   user asking for that specific task would be an unrequested spend.
+   (`story_sweep`, `story_sweep_hard`, `shop_common`, `shop_tactical`,
+   `lesson`, `arena`, `bounty`, `event_sweep`) spend real AP, credits,
+   tactical coin, lesson tickets, an arena ticket, or a bounty ticket, and
+   running one without the user asking for that specific task would be an
+   unrequested spend.
 
    Exit code 0 only means the script ran without a Python exception, not
    that the in-game action succeeded — surface the task's own log lines
    (e.g. `claiming all`, `nothing to claim`, `patted N sparkle(s)`) to the
    user, not just the exit code.
 
-4. Summarize what happened: deploy succeeded/failed, and if a task was
-   smoke-tested, what its log output actually said.
+4. Summarize what happened: deploy succeeded/failed, whether `setup.sh` was
+   needed/run, and if a task was smoke-tested, what its log output actually
+   said.

ba_auto/config.py

@@ -364,8 +364,8 @@ STORY_SWEEP_TARGETS = []
 # ordinal modulo, not the calendar day-of-year, so the cycle doesn't skip or
 # repeat around a year boundary. Set STORY_SWEEP_ROTATION_REGION to None to
 # disable this and only sweep STORY_SWEEP_TARGETS.
-STORY_SWEEP_ROTATION_REGION = 30
-STORY_SWEEP_ROTATION_STAGE_COUNT = 6
+STORY_SWEEP_ROTATION_REGION = 29
+STORY_SWEEP_ROTATION_STAGE_COUNT = 5
 STORY_SWEEP_ROTATION_COUNT = "max"
 
 # Hard story AP sweep (module/explore_tasks/sweep_task.py's sweep_hard_task).