@polycode-projects/the-mechanical-code-talker 2.9.5 → 2.10.0

package/README.md

@@ -200,7 +200,7 @@ under a guard that proves the protected spans came through byte-for-byte.
 
 A frozen regression suite plays out full multi-turn dialogues built from these
 phrasings, from a single question up to a messy, typo-ridden real user.
-Tier-by-tier detail is in `HANDOVER.md`.
+Tier-by-tier detail is in `NEXT.md`.
 
 ## How it guides you
 
@@ -1082,7 +1082,7 @@ The full tables, judge scores, and transcripts are in the linked write-ups.
 | Groundedness | Every answer carries a source, and an empty graph reports itself empty. Judge-scored mean 1.809/2 over 138 cases, 5 hard fails, 136/138 tier-1. | Judged (`claude-haiku-4-5-20251001`, `judge-prompt-v2`) at N=1. The judge prompt moved v1→v2 since 2.6.0, so this is a measurement, not a clean lever comparison against the prior cycle. The judge runs in the offline eval harness, never in the product. | `BENCHMARK_CEFR_ENGLISH_2.7.12.md` |
 | Abstention (the honest miss) | 0% fabrication across 479 inference rows (379 chat + 100 kernel) and 0% hallucination across 272 agent rows | Structural, not a tuned threshold. tmct abstains because nothing matched, so the rows test a property of a no-model design rather than a score. | `BENCHMARK_INFERENCE_2.7.12.md`, `BENCHMARK_AGENT_2.7.12.md` |
 | Determinism | Byte-identical on rerun — a 379-case `--replay` clean across 2 runs, no LLM, no network, $0 per turn | A property of the no-model pipeline. | `BENCHMARK_INFERENCE_2.7.12.md` |
-| Dialogue robustness (persona sweep) | A 6-persona sweep (textbook logician, casual newcomer, new developer, adversarial sceptic, returning user, planning user) fixed 25 of the prior cycle's 29 routed findings (21 clean, 4 with a residual noted); 4 remain broken, 2 in a shape distinct from the original complaint | Free exploration across all six personas surfaced roughly 60 fresh findings beyond the ratchet check — the single highest-signal pattern: tmct's own suggested repair text was itself frequently broken when followed verbatim (since fixed, see `HANDOVER.md`). | `BENCHMARK_CONVERSATION_2.7.11.md` |
+| Dialogue robustness (persona sweep) | A 6-persona sweep (textbook logician, casual newcomer, new developer, adversarial sceptic, returning user, planning user) fixed 25 of the prior cycle's 29 routed findings (21 clean, 4 with a residual noted); 4 remain broken, 2 in a shape distinct from the original complaint | Free exploration across all six personas surfaced roughly 60 fresh findings beyond the ratchet check — the single highest-signal pattern: tmct's own suggested repair text was itself frequently broken when followed verbatim (since fixed, see `NEXT.md`). | `BENCHMARK_CONVERSATION_2.7.11.md` |
 
 Three offline benchmark rigs live in a clone (they are not in the npm
 package). Each replays a committed case set through the real product and

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@polycode-projects/the-mechanical-code-talker",
-  "version": "2.9.5",
+  "version": "2.10.0",
   "private": false,
   "type": "module",
   "description": "The Mechanical Code Talker (tmct) — a tolerant, offline, $0 chat surface that guides you toward precision queries about a software repository. ELIZA/PARRY-style but domain-obsessed with code. No model calls; no codebase index of its own.",

package/src/services/ledger-viz.mjs

@@ -515,10 +515,15 @@ export function renderLedgerHtml({ rows, terms, edges, focus, contradictions, wo
   // the query-only wording even when the live bundle is offered — the dock's
   // own script swaps it for a teach-aware placeholder the moment it confirms
   // tmctLedger actually loaded (never claimed ahead of that confirmation).
+  // The example term skips anything under 3 characters — the SAME floor the
+  // dock's own miss-tips apply below — so a graph whose highest-degree term
+  // is a short stopword-shaped fragment (init:large corpora carry plenty:
+  // "os", "ip", "s3") never becomes the one example a visitor sees.
   const termSet = new Set((terms || []).map((t) => t.term));
+  const exampleTerm = (terms || []).find((t) => t && t.term && t.term.length >= 3);
   const placeholder = termSet.has("ishmael")
     ? "who is the grandfather of ishmael"
-    : (terms && terms.length ? `ask the graph… e.g. what is ${terms[0].term}` : "ask the graph…");
+    : (exampleTerm ? `ask the graph… e.g. what is ${exampleTerm.term}` : "ask the graph…");
   const dockHtml = hasMemChat
     ? `<div class="chat">
         <div class="chatlog" id="chatlog" aria-live="polite"></div>