Add prompt route smoke checks

docs/prompt-architecture-improvement-plan.md

@@ -209,7 +209,8 @@ Improve later:
 Near-term:
 
 - Add final row hygiene already done through `prompt_hygiene.py`.
-- Add a metadata invariant checker for rows before return.
+- Add a metadata smoke checker for representative rows through
+  `tools/prompt_smoke.py`.
 - Normalize every row with one function before JSON serialization.
 
 Medium-term:
@@ -224,6 +225,8 @@ Near-term:
 - Normalize pair metadata with one helper.
 - Confirm pair prompts, captions, and soft/hard rows carry the same sanitized
   scene/camera/clothing fields.
+- Keep same-room pair continuity synchronized in both assembled prompt text and
+  `hardcore_row.scene_text`; `tools/prompt_smoke.py` covers this drift case.
 
 Medium-term:
 
@@ -236,8 +239,10 @@ Medium-term:
 Near-term:
 
 - Add final prose hygiene already done through `prompt_hygiene.py`.
-- Add tests for close foreplay, POV oral, POV penetration, aftercare, manual
-  stimulation, and camera-scene preservation.
+- Add smoke coverage through `tools/prompt_smoke.py` for metadata-driven Krea2
+  formatting across built-in rows, hardcore rows, same-cast pairs, and POV
+  pairs. Expand it next for close foreplay, POV penetration, and camera-scene
+  preservation.
 
 Medium-term:
 
@@ -249,7 +254,8 @@ Medium-term:
 Near-term:
 
 - Add final tag hygiene already done through `prompt_hygiene.py`.
-- Add smoke tests for trigger preservation and duplicate tag removal.
+- Add smoke tests for trigger preservation and duplicate tag removal through
+  `tools/prompt_smoke.py`.
 
 Medium-term:
 
@@ -260,7 +266,8 @@ Medium-term:
 Near-term:
 
 - Add final prose hygiene already done through `prompt_hygiene.py`.
-- Verify training captions keep trigger exactly once.
+- Verify training captions keep trigger exactly once through
+  `tools/prompt_smoke.py`.
 
 Medium-term:
 
@@ -293,7 +300,8 @@ Medium-term:
 
 ## Recommended Next Passes
 
-1. Add metadata invariant checks and small smoke fixtures.
+1. Expand `tools/prompt_smoke.py` with camera-scene, explicit nude, and
+   different-camera pair fixtures.
 2. Split Krea action/POV/clothing helpers into separate modules.
 3. Add category JSON pool reference validation to `tools/prompt_map_audit.py`.
 4. Extract scene-camera adapters from `prompt_builder.py`.

docs/prompt-pool-routing-map.md

@@ -655,6 +655,28 @@ The script does not import ComfyUI. It parses the repo and prints:
 Use its output to spot doc drift after adding a new node or pool. If a new node
 or pool appears there but not in this map, update the relevant route table.
 
+## Behavioral Smoke Helper
+
+Route behavior should be checked when changing prompt generation, pair assembly,
+formatter metadata parsing, trigger handling, expression disabling, or scene
+continuity. Run:
+
+```bash
+python tools/prompt_smoke.py
+```
+
+The script does not import ComfyUI. It builds representative metadata rows and
+pair metadata through the core Python APIs, then verifies:
+
+- generated rows keep prompt, negative prompt, scene, composition, action item,
+  and role graph metadata populated;
+- Krea2, SDXL, and natural caption routes use metadata instead of text fallback;
+- SDXL and caption trigger handling keeps one trigger;
+- negative prompts do not duplicate comma-list items;
+- same-room Insta/OF continuity keeps prompt text and `hardcore_row.scene_text`
+  synchronized;
+- expression-disabled rows do not fall back to generated expression text.
+
 ## Editing Cheatsheet
 
 | Symptom | First file/function to inspect |