wip(confidence-engine): checkpoint open-question presentation work

prompts/reconstruct-v0.4.md

@@ -29,6 +29,8 @@ You are a neutral analyst performing evidence-based situation reconstruction.
 9. If input is too ambiguous or contains no useful operational anchors, say so and ask for
    the single piece of context that would best distinguish plausible interpretations.
 
+9a. For every importantUnknown, preserve its uncertainty meaning in `description` and provide `question` as a natural, direct interrogative addressed to the user. Retain all scope, conditions, timeframes, and qualifications without adding assumptions or an implied conclusion. Do not use fragments or indirect proposition forms such as "Whether …".
+
 10. Do not split concepts merely to increase the number of unknowns — only separate when the user has presented materially distinct dimensions worth independent investigation.
 
 ## Preserve supplied relationships
@@ -139,7 +141,7 @@ Return a JSON object with exactly these four top-level keys (use **camelCase**):
     "knownTransitions": [{"id": "...", "description": "...", "confidence": "<low|medium|high>", "entity": "...", "previousState": "...", "currentState": "...", "explanationStatus": "..."}],
     "unexplainedTransitions": [{"id": "...", "description": "...", "confidence": "<low|medium|high>", "entity": "...", "previousState": "...", "currentState": "..."}],
     "contradictions": [{"id": "...", "description": "...", "confidence": "<low|medium|high>"}],
-    "importantUnknowns": [{"id": "...", "description": "...", "confidence": "<low|medium|high>"}],
+    "importantUnknowns": [{"id": "...", "description": "<the canonical uncertainty meaning>", "question": "<a natural direct question for the user>", "confidence": "<low|medium|high>"}],
     "plausibleInterpretations": [{"id": "...", "description": "...", "supportingEvidenceIds": ["<ids that support this interpretation>"], "assumptionsRequired": [], "confidence": "<low|medium|high>"}]
   },
   "evidence": [