titan-agent 7.1.0 → 7.2.1

package/README.md

@@ -50,6 +50,27 @@
 
 <a id="whats-new"></a>
 
+## What's new in v7.2.0 "Conscience" — Honesty as an Enforced Invariant
+
+**TITAN stopped being able to bluff.** Two honesty organs turn any model — local
+or cloud — into one that *verifies before it claims* and *critiques before it
+speaks*. Flip one switch (`agent.reliabilityMode: true`) and your local model
+behaves with the reliability discipline of a frontier model, because reliability
+is enforced in the harness, not hoped for in the prompt.
+
+- 🛡️ **Verification wall (always on):** claim you sent/posted/deleted/deployed/
+  saved something with no tool that did it → TITAN appends a visible correction.
+- 🧠 **Self-critique (Reliability Mode):** the model reviews its own draft
+  adversarially and appends honest "on reflection" caveats. Live-proven: a local
+  model caught its own over-precise number and a definitional conflation,
+  unprompted.
+- ⚡ **Perf:** ~19MB/turn read deleted (tail-read trajectories); every timer
+  `.unref()`'d.
+
+See **[CHANGELOG.md](CHANGELOG.md)** for the full v7.2.0 entry.
+
+---
+
 ## What's new in v7.1.0 "Council" — Local-First Intelligence, Together
 
 **Agents advising agents, models sized to their machines, and benchmarks you can trust.**
@@ -65,6 +86,16 @@ TITAN now **learns each deployment's real context ceiling from live traffic** an
 
 **Proof, not vibes**: under the new `TITAN_BENCH=1` isolation mode, **Qwen3.6-35B-A3B NVFP4 on DGX-Spark-class hardware scores 85% through TITAN's harness — tying the RTX 5090's best local model.** Full corrected tables in [benchmarks/MODEL_COMPARISON.md](benchmarks/MODEL_COMPARISON.md).
 
+### 🛡️ Honesty as an enforced invariant (any model)
+TITAN won't let a model bluff. The **verification wall** appends a visible
+correction if a reply claims it *did* something (sent, posted, deleted,
+deployed, saved) with no tool that actually did it — deterministic, always on.
+Turn on **Reliability Mode** (`agent.reliabilityMode: true` — one switch) and TITAN
+also critiques its own draft before you see it, appending honest "on reflection"
+caveats for anything it didn't verify. This is how a local model reaches
+frontier *reliability* without frontier size — and it works on whatever brain
+you plug in.
+
 See **[CHANGELOG.md](CHANGELOG.md)** for the complete v7.1.0 entry.
 
 ---

package/dist/agent/agent.js

@@ -1243,6 +1243,15 @@ CRITICAL: Widgets are NOT files. Do NOT use write_file, edit_file, or any file t
     enrichedSystemPrompt += earlyPersona.systemPromptAppendix;
     logger.info(COMPONENT, `[Persona:${earlyPersona.id}] system prompt appendix injected`);
   }
+  try {
+    const relMode = config.agent.reliabilityMode === true;
+    if (relMode) {
+      const { buildDisciplinePrompt } = await import("./disciplinePrompt.js");
+      const frag = buildDisciplinePrompt(message, true);
+      if (frag) enrichedSystemPrompt += frag;
+    }
+  } catch {
+  }
   const messages = [
     { role: "system", content: enrichedSystemPrompt },
     ...historyMessages
@@ -1542,12 +1551,23 @@ ${buildSystemWidgetGate(sw)}` : buildSystemWidgetGate(sw);
       logger.info(COMPONENT, `[SystemWidgetShortcut] Deterministically emitted _____widget gate for ${sw.source}`);
     }
   }
+  try {
+    const agentCfg = config.agent;
+    const { resolveSelfCritique, runSelfCritique } = await import("./selfCritique.js");
+    const scCfg = resolveSelfCritique(agentCfg.selfCritique, agentCfg.reliabilityMode === true);
+    if (scCfg.enabled) {
+      const sc = await runSelfCritique(scCfg, message, finalContent, [...new Set(toolsUsed)], modelUsed);
+      if (sc.critiqued && sc.issues.length > 0) finalContent = sc.content;
+    }
+  } catch (e) {
+    logger.debug(COMPONENT, `Self-critique wrapper skipped: ${e.message}`);
+  }
   {
-    const claimsScheduled = /\b(i(?:'|’)?(?:ve| have)\s+(?:set|scheduled|created)|(?:reminder|schedule[d]?)\s+(?:is\s+)?(?:set|created|scheduled)|i(?:'|’)?ll remind you|scheduled a reminder)\b/i.test(finalContent);
-    const schedulingToolRan = toolsUsed.some((t) => /^(reminder|cron|schedule|event_trigger|workflows?|social_scheduler)/i.test(t));
-    if (claimsScheduled && !schedulingToolRan) {
-      finalContent += "\n\n\u26A0\uFE0F Correction: I described scheduling that, but I did not actually create a scheduled job this turn. Ask me again and I'll set it with the reminder tool properly.";
-      logger.warn(COMPONENT, "[HonestyGuard] Reply claimed scheduling without a scheduling tool \u2014 appended correction");
+    const { applyHonestyGuard } = await import("./honestyGuard.js");
+    const guarded = applyHonestyGuard(finalContent, toolsUsed);
+    if (guarded.flagged.length > 0) {
+      finalContent = guarded.content;
+      logger.warn(COMPONENT, `[HonestyGuard] Reply claimed ${guarded.flagged.join(", ")} without a capable tool \u2014 appended correction`);
     }
   }
   addMessage(session, "assistant", finalContent, {