diff --git a/docs/research/2026-05-19-indoor-walking-phase2-pickup-prompt.md b/docs/research/2026-05-19-indoor-walking-phase2-pickup-prompt.md
index 804a8c4..2b1eb8a 100644
--- a/docs/research/2026-05-19-indoor-walking-phase2-pickup-prompt.md
+++ b/docs/research/2026-05-19-indoor-walking-phase2-pickup-prompt.md
@@ -60,32 +60,52 @@ back outside through a door works.
    - #80: 2nd-floor goes very dark (pre-existing lighting issue, may be
      part of a broader Cluster B lighting phase)
 
-3. Per CLAUDE.md's work-order autonomy rule, YOU pick the next phase.
-   Candidates ranked by my best guess at priority:
+3. **The user has set a focused track: indoor walking issues, collision,
+   physics, and dungeons.** M2 (kill-a-drudge demo) is explicitly NOT
+   the next direction. Stay on the indoor-experience track until they
+   redirect.
 
-   A) Indoor lighting cluster (closes #79/#80/#81/#82) — completes the
-      "indoor feels right" visual story. The wall-blocking is done; the
-      visible darkness on upper floors and broken atmospheric lighting
-      indoors is the next thing the player notices. ~1-2 weeks.
+   Candidates within that scope, ranked by my best guess at priority:
 
-   B) Continue M2 critical path — F.2 (Inventory panel), F.3 (Combat
-      math + damage flow), F.5a (dev panels), L.1c (combat animation),
-      L.1b (command router). Kill-a-drudge demo. ~6-10 weeks total but
-      can be sliced per-phase.
+   A) **#83 — Walking up stairs broken**. Pure indoor/physics. The
+      retail step-up logic (`CPhysicsObj::step_up`) doesn't yet handle
+      indoor cell-BSP polys for stair geometry. Unblocks multi-floor
+      cottages (the 2nd-floor darkness #80 also depends on actually
+      reaching the 2nd floor) and dungeons (which are multi-level).
+      Natural follow-on to Phase 2. ~3-5 days.
 
-   C) #88 indoor vibration — quick to fix once diagnosed; pre-existing
-      annoyance. 1-3 commits depending on root cause.
+   B) **Dungeon stress test + adaptation**. Phase 2's portal traversal
+      was developed and verified at Holtburg cottage (a small one-room
+      building). Dungeons (Subway, Mite Burrow, Carved Stone) are
+      multi-cell indoor spaces with complex portal graphs. Walk a
+      character into a dungeon and see what breaks. Findings drive a
+      follow-up scope. ~1-3 days for the test + variable for fixes.
 
-   D) Triage docs/ISSUES.md to clear chronic-open items (#2 lightning,
-      #4 sky horizon-glow, #28 aurora, #29 cloud thinness, #37 humanoid
-      coat, #41 remote-motion blips). ~1 hour, surfaces what's actually
-      blocking M2 vs nice-to-have.
+   C) **#88 — Indoor object vibration** (bookshelves, open furnaces).
+      Quality bug noticed during Phase 2 testing. Likely a per-frame
+      transform recompute or EntityScriptActivator re-firing on cell
+      changes (less likely after Phase 2 stabilized cell tracking but
+      still possible). ~1-3 commits depending on root cause.
 
-   My recommendation: A. Indoor lighting closes the indoor-experience
-   loop. The user explicitly mentioned darkness as a noticeable issue
-   during Phase 2 testing, and the diagnostic infrastructure from
-   Phase 2 is still warm. But pick based on your read of the codebase
-   + recent commits.
+   D) **#89 — Port `BSPQuery.SphereIntersectsCellBsp`**. Retail-faithful
+      entry timing for outdoor→indoor. Phase 2 ships with the documented
+      ~0.5m late-entry approximation; this closes the gap. Pure physics
+      polish. ~2-3 days.
+
+   E) **Indoor lighting cluster** (closes #79/#80/#81/#82). Slightly
+      adjacent — "indoor experience" but not strictly walking/collision.
+      Worth considering once stairs (A) lands so you can actually reach
+      the dark 2nd floor to verify lighting fixes. ~1-2 weeks.
+
+   F) **#78 — Outdoor stabs visible through floor**. Visibility/stencil
+      issue. Render side. Indoor-adjacent. ~3-5 days.
+
+   My recommendation: **A (stairs)**. Reasons:
+   - Pure indoor physics/collision — squarely in the user's stated track.
+   - Unblocks both multi-floor cottages AND dungeons (B is gated on it).
+   - Continues the natural arc from Phase 1 (walls) → Phase 2 (cell
+     tracking) → Phase 3 (vertical movement / stairs).
+   - The Phase 2 diagnostic infrastructure is still warm; reuse it.
 
 4. CLAUDE.md rules apply:
    - No workarounds; fix root causes.
@@ -120,14 +140,27 @@ Key files for the next phase (whichever path A/B/C/D you pick):
 - **`docs/ISSUES.md`** — current OPEN items (note new #88 + #89 from Phase 2).
 - **`docs/plans/2026-04-11-roadmap.md`** — shipped table; Indoor walking Phase 2 row is most recent.
 
-If picking **Path A (indoor lighting)**:
+If picking **Path A (#83 stairs — recommended)**:
 
-- Start by re-reading the existing Cluster B sketches in the original Cluster A handoff:
-  `docs/research/2026-05-19-indoor-followup-handoff.md` — section "The 9 follow-up issues" lists #79/#80/#81/#82 as Cluster B.
-- Lighting code surfaces: `src/AcDream.App/Rendering/GameWindow.cs::UpdateSunFromSky` (indoor branch around line 8330+), `src/AcDream.App/Rendering/Shaders/mesh_modern.frag` (accumulateLights + indoor ambient), `src/AcDream.Core/Lighting/LightInfoLoader.cs`.
-- Probe surface: there is no `[lighting]` probe yet — adding one will likely be the first commit in the brainstorm.
+- Retail oracle: `docs/research/named-retail/acclient_2013_pseudo_c.txt` — grep `step_up`, `step_sphere_up`, `find_walkable` for the existing logic. Our `BSPQuery` ports these for outdoor terrain at lines 1278+; the indoor analog needs the same flow against `cellPhysics.Resolved` floor-and-stair polys.
+- Touchpoints likely: `src/AcDream.Core/Physics/TransitionTypes.cs` (where the new `TryFindIndoorWalkablePlane` lives — extend to handle step-up across vertical floor polys), `src/AcDream.Core/Physics/BSPQuery.cs::FindCollisions` Path 5/6 (which already handles outdoor step-up; needs indoor counterpart).
+- Probe surface: `[indoor-bsp]` already captures every cell-BSP query; new probe `[step-up]` may be helpful.
+
+If picking **Path B (dungeon stress test)**:
+
+- Pick a small dungeon. Subway (`@0x0102 ...`) or Mite Burrow are good first targets — both are small enough to walk through quickly but complex enough to exercise multi-cell portal traversal.
+- Run the launch with all indoor probes enabled (`ACDREAM_PROBE_INDOOR_BSP=1`, `ACDREAM_PROBE_CELL=1`, `ACDREAM_PROBE_CELL_CACHE=1`). Walk through every room. Note any wall-pass-through, stuck states, or cell-tracking failures.
+- Findings drive scope. Probably uncovers stair issues (→ Path A) or sphere-vs-cell timing issues (→ #89).
 
 If picking **Path C (#88 vibration)**:
 
 - Likely candidates from the bug report: `EntityScriptActivator.OnCreate/OnRemove` re-firing on rapid CellId promotion/demotion (now less likely after Phase 2 stabilized cell tracking, but worth investigating); per-frame transform recompute drift on cell-static `WorldEntity` instances; particle-emitter offset accumulation.
 - File this as a Phase rather than an issue if the root cause turns out to be the per-frame transform pipeline (multi-commit refactor).
+
+If picking **Path E (indoor lighting)**:
+
+- Start by re-reading the existing Cluster B sketches in the original Cluster A handoff:
+  `docs/research/2026-05-19-indoor-followup-handoff.md` — section "The 9 follow-up issues" lists #79/#80/#81/#82 as Cluster B.
+- Lighting code surfaces: `src/AcDream.App/Rendering/GameWindow.cs::UpdateSunFromSky` (indoor branch around line 8330+), `src/AcDream.App/Rendering/Shaders/mesh_modern.frag` (accumulateLights + indoor ambient), `src/AcDream.Core/Lighting/LightInfoLoader.cs`.
+- Probe surface: there is no `[lighting]` probe yet — adding one will likely be the first commit in the brainstorm.
+- **Note:** verify Path A (stairs) lands first or you can't reach the 2nd floor to test indoor lighting at altitude.