experiment: diagnose structural-mutation prompt compliance

2026-08-11 13:15:27 +01:00
parent 6aea0bd90c
commit 0c477adea9
2 changed files with 262 additions and 1 deletions
@@ -700,4 +700,24 @@ This run did not test the v0.17 contract's core question because the model never

 **Key finding:** v0.17 successfully blocks the original failure (accepted semantic-only no-op) but does not establish a positive path for faithful meaning to produce graph progress. The open question remains: is there any valid pathway where faithful meaning translates to structural mutation, or does the MUST rule universally block it?

-Configured Ollama: qwen-claude:latest at http://192.168.1.111:11434. No production code changed. Harness restored. No-retry preserved. Dev server disturbed: NO.
+Configured Ollama: qwen-claude:latest at http://192.168.1.111:11434. No production code changed. Harness restored. No-retry preserved. Dev server disturbed: NO.
+### Experiment 57J.42 — Structural-Mutation MUST Rule Prompt Conflict Diagnosis
+
+**Objective:** Diagnose why the model produces faithful `userSupportedMeaning` with zero structural mutation despite the v0.17 MUST rule. Read-only prompt-contract analysis of assembled prompt + tests. No Ollama calls.
+
+**Method:** Inspected all prompt rules from `lib/graph/prompt-builder.js`, analyzed action-selection ambiguity, checked six conflict patterns (A–F), reviewed test adequacy in `tests/graph/prompt-builder.test.js`.
+
+**Relevant rule conflicts found:**
+- Rule #6 (MUST) vs Additional Guidance bullet B (PERMIT empty arrays if "answer does not justify a change"): direct MUST vs PERMIT conflict. Rule #7's restrictive enumeration + rules #4 ("genuinely new concepts") + #11 (no duplicates) help the model decide nothing justifies a change, triggering the escape hatch in Additional Guidance.
+- Additional Guidance bullet C: "Use answerMeaning to preserve the answer's direct meaning even when the graph change remains unresolved" explicitly encourages semantic-only output — the exact pattern v0.17 sought to eliminate.
+- Action-selection ambiguity under rule #6: four acceptable forms listed without decision criteria or fallback ordering.
+- Pattern D fidelity paralysis: high-traceability requirements make structural creation non-trivial for simple uncertainty about known topics.
+
+**Classification: C — PROMPT CONFLICT**
+
+Primary owner of 57J.41 failure: PROMPT CONFLICT (not MODEL)
+Provider-agnostic concern: YES — CONTRACT LEVEL
+
+Smallest correction boundary: Two Additional Guidance bullets (~10 words total) at lines ~132 of prompt-builder.js must be removed or conditioned on rule #6 not triggering. Text-preservation-only tests do not prove prompt coherence.
+
+Configured Ollama: none used. Production code changed: NO. Prompt changed: NO. Tests changed: NO. Dev server disturbed: NO.