ba-auto-daily/plan.md

ba-auto-daily implementation plan

Personal Blue Archive JP daily-automation script. Controls the game via xdotool over a remote X11 session (Steam+Proton on nik-gpu), using OpenCV template/color matching for detection. No OCR is set up yet (see Prerequisites).

Feature list and priority ordering below is derived from studying ~/repo/baas-reference (pur1fying/blue_archive_auto_script, GPL-3.0, read-only reference — not copied from, reimplemented fresh in our own style). Its own default scheduler priority, complexity, and JP-relevance were used to rank the backlog. See "Reference" under each feature for the baas file(s) that describe the mechanic, for research purposes only.

Status snapshot

Feature	Status
Mailbox claim	✅ Done (do_mailbox)
Cafe (pats + income)	✅ Done (do_cafe)
Everything else below	Not started

Prerequisites (cross-cutting, unblock multiple tiers)

• OCR. Not set up. Needed for currency/ticket-count readouts, region/tab name search, and a few other read-a-number moments. When we get there, evaluate Tesseract vs PaddleOCR in the existing ~/.venvs/ba-auto-daily venv. Until then, stick to features that are pure color-check / template-match.
• Auto-fight primitive. A shared "start fight → max speed + auto-mode → detect win/lose" routine that Arena, and any future story/raid automation, all need. Build once, early, before Tier 3 combat features. Reference: module/main_story.py (auto_fight/enter_battle).

---

Tier 1 — High priority, no OCR needed

Stamina/AP sweep (free + task-menu power)

Claim the daily free 10 AP purchase and the daily task-menu AP/pyroxene rewards. Pure color-check state detection, fixed clicks. High value: AP is capped and this is free currency/materials left on the table every day. Reference: module/collect_daily_free_power.py, module/collect_daily_task_power.py.

Club/Group AP claim

Claim 10 AP from the club/dorm menu. Trivial fixed click + color check. Reference: module/group.py (29 lines).

Momo Talk (chat app conversations)

Auto-complete unread chat conversations, including relationship-rank-up story beats, claim pyroxene. No OCR — pure pixel-column scanning state machine (reply bubble / "enter story" prompt detection by color). Runs on its own ~3h cadence like cafe. Moderate build effort but no new dependencies. Reference: module/momo_talk.py (183 lines, getConversationState).

---

Tier 2 — Medium priority, sweep-style AP consumption

These three share the same shape: buy tickets (optional), sweep N times per sub-area, detected mostly by color (a multi-pixel "sss/star-rank" signature, not OCR). Minor OCR only for optional coin-balance readouts — can hardcode/skip that part initially and just sweep until out of stamina/tickets.

Commissions ("Special Task" / 委託)

Two sub-dungeons (Base Defense = EXP, Item Retrieval = credits). Reference: module/clear_special_task_power.py (148 lines).

Scrimmage (学院交流会)

Three academies, ticket purchase available on JP. Reference: module/scrimmage.py (166 lines).

Bounty ("Rewarded Task" / 悬赏通缉)

Three sub-areas, ticket purchase (0–12). Needs a little OCR for bounty-coin balance if we want auto-refresh; otherwise skippable. Reference: module/rewarded_task.py (204 lines).

Normal/Hard story AP sweep (re-clear already-cleared stages)

Sweep already-cleared main-story stages by region/mission count to burn AP. Needs OCR for current-region-number + a fuzzy swipe-search over mission buttons — more OCR-dependent than the three above, so ranked after them. Reference: module/explore_tasks/sweep_task.py, module/explore_tasks/task_utils.py.

---

Tier 3 — Needs real OCR investment

Do these once OCR is actually set up.

Battle Pass claim (JP-only feature upstream — relevant to us)

Claim pass mission points + tier rewards. Simple template claim-flow; OCR only needed for the optional level/points stat readout (can stub that part). Reference: module/collect_pass_reward.py (146 lines).

Common Shop + Tactical (Arena) Shop

Auto-buy configured items, auto-refresh when affordable. OCR needed for currency balances and shop-tab name search. Reference: module/shop/common_shop.py, module/shop/tactical_challenge_shop.py, module/shop/shop_utils.py.

Arena (PvP ladder)

Fight until out of tickets or rank 1, claim season + daily rewards. Needs the Tier-1-prerequisite auto-fight primitive, plus OCR for ticket count and self/opponent level. High value (decays twice daily, at 06:00/20:00 reset) but gated on OCR + auto-fight both being ready. Reference: module/arena.py (173 lines).

---

Tier 4 — Heavy investment, lower ROI (defer)

Lesson / Schedule (affection farming via classes)

Structurally the most complex non-crafting feature: fuzzy OCR region-name matching, per-region student-portrait templates, multi-page swipe search, and a bespoke isometric-grid pixel-sampling helper for locating a specific favorite student. A stripped-down "just pick the highest-affection lesson in a fixed region" version would be much cheaper than full favorite-student targeting — consider that subset first if we ever pick this up. Reference: module/lesson.py (615 lines).

Crafting (自动制造)

The single most complex feature in the reference project (1000+ lines): 3-phase material selection, priority-list + rarity-tier config, quantity-stepper OCR, filter/sort UI manipulation. Large one-time build cost for recurring but non-urgent value (crafting mats don't decay the way AP/tickets do). Reference: module/create.py (1028 lines).

Main story / Normal-Hard story "push" (auto-clear next uncleared stage)

Distinct from the Tier-1/2 "sweep already-cleared stages" — this is unlocking new content. baas ships ~920KB of hand-authored per-stage click/formation-swap JSON scripts for "grid mode"; "simple mode" (plain auto-fight, no positioning) is far cheaper but doesn't work on every stage. Only worth building incrementally, per-stage, on demand — not a batch feature. Reference: module/main_story.py, module/explore_tasks/explore_task.py.

Group Story / Mini Story (side-plot cleanup)

OCR-detect a "NEW" badge across a paged grid, clear each unread plot. Pure convenience, optional. Reference: module/group_story.py, module/mini_story.py.

Event content (Activities: story/mission/challenge push)

Shape mirrors Tier-2 sweep work, but the content is 100% ephemeral — a new JSON/script per event, expires when the event ends. Recommendation: only build the generic "event AP sweep" (reuses Tier-1/2 sweep logic almost as-is) as a standing capability; don't try to pre-build specific named events. Note also that per baas's own docs, current JP/Global events have mostly moved away from grid-walking challenges, so "challenge push" content increasingly needs manual play anyway — low automation ROI there specifically. Reference: module/activities/activity_utils.py, module/sweep_activity.py.

---

Skip list (not relevant to this project)

Feature	Why skip
Total Assault (raid)	Stubbed/dead code upstream too (return True before any real logic) and disabled by default; low value to chase.
Joint Firing Drill (综合战术测试)	Hard-disabled for JP server in baas's own code (if self.server == "JP": return True) despite being in their README — it's a no-op on JP regardless.
De-clothes localization toggle	CN-only.
Restart / refresh-uiautomator2	Android/ADB housekeeping for baas's mobile control backend; not applicable to our PC/Steam/Proton setup.
Auto-unfriend	Disabled by default upstream too; low value, mildly risky (deletes friends).
Daily minigame dispatcher	Event-specific and changes every campaign — not a stable feature to pre-build. Handle ad hoc if/when a specific live minigame is worth automating.

---

Notes on cadence

Several features are time-decaying rather than "any time" farmable, which should inform how often the script runs (cron/scheduler), not just build order:

• Cafe income + Momo Talk: effectively continuous, ~3h internal cadence.
• Arena: resets twice daily (06:00, 20:00 UTC).
• Everything else: once-daily, JP/Global reset at 20:00 UTC (03:00 UTC+8).