open-agents-ai 0.186.6 → 0.186.8

package/README.md

@@ -1072,6 +1072,67 @@ The identity kernel maintains a persistent self-model across sessions, the refle
 | L8 | Darwin Gödel Machine: Open-Ended Self-Improvement (2025) | [arxiv:2505.22954](https://arxiv.org/abs/2505.22954) |
 | L8 | i-MENTOR: Intrinsic Motivation Exploration (2025) | [arxiv:2505.17621](https://arxiv.org/abs/2505.17621) |
 
+## Agent Immune System — Constraint Enforcement & Pressure Resistance
+
+<div align="right"><a href="#top">back to top</a></div>
+
+Open Agents includes a behavioral immune system that prevents the agent from making pattern-matched mistakes under pressure. Inspired by biological immune systems: constraints are the antibodies, pressure detection is the inflammatory response, and memory injection is the recall mechanism.
+
+### Constraint Enforcement (`.oa/constraints.json`)
+
+Machine-readable rules checked **before every tool execution**:
+
+```json
+{
+  "constraints": [
+    {
+      "id": "no-reward-hack",
+      "trigger": "file_write|file_edit",
+      "pattern": "NEVER say|ALWAYS say",
+      "target_files": ["prompts/**/*.md"],
+      "action": "warn",
+      "message": "This looks like a reward-hacking directive. Fix the architecture, not the prompt."
+    }
+  ]
+}
+```
+
+| Action | Behavior |
+|--------|----------|
+| `block` | Prevents tool execution entirely, returns error to model |
+| `warn` | Executes tool but emits warning in agent's next turn context |
+| `log` | Silent recording to audit log, no interruption |
+
+Constraints are scoped: global (`~/.open-agents/constraints.json`), project (`.oa/constraints.json`), or session (ephemeral).
+
+### Pressure-Aware Decision Gate
+
+When the user is frustrated (detected via keyword matching), a brief `<reflection>` cue is injected into the agent's system prompt for ONE turn:
+
+```
+<reflection>The user is very frustrated. Pause. Check your constraints
+and past feedback before writing code. The fastest fix is often the wrong fix.</reflection>
+```
+
+This is NOT a block — it's a speed bump that prompts deliberation when the agent is most likely to cut corners. Zero overhead when no pressure is detected.
+
+| Pressure Level | Detection | Response |
+|---------------|-----------|----------|
+| **none** | Normal messages | No cue (zero tokens) |
+| **moderate** | Frustration signals | "Verify your change addresses the root cause" |
+| **high** | Strong frustration + urgency | "Pause. Check constraints before acting" |
+
+### How It Works Together
+
+```
+User (frustrated): "fix this broken shit"
+  → Pressure gate detects "high" → injects reflection cue
+  → Model proposes file_edit on prompts/system.md with "NEVER say..."
+  → Constraint checker matches "no-reward-hack" → emits warning
+  → Model sees warning on next turn → reconsiders approach
+  → Model fixes the architecture instead of adding a prompt hack
+```
+
 ## Context Compaction — Research-Backed Memory Management
 
 <div align="right"><a href="#top">back to top</a></div>

package/dist/index.js

@@ -26341,6 +26341,7 @@ TASK: ${task}` : task;
         let summary = "";
         let bruteForceCycle = 0;
         this._assistantTextEmitted = false;
+        let pendingConstraintWarnings = [];
         let consecutiveTextOnly = 0;
         const MAX_CONSECUTIVE_TEXT_ONLY = 3;
         let narratedToolCallCount = 0;
@@ -26358,6 +26359,11 @@ TASK: ${task}` : task;
             this.emit({ type: "error", content: "Task aborted by user", timestamp: (/* @__PURE__ */ new Date()).toISOString() });
             break;
           }
+          if (pendingConstraintWarnings.length > 0) {
+            const warningMsg = "<constraint-recall>\n" + pendingConstraintWarnings.join("\n") + "\n</constraint-recall>";
+            messages.push({ role: "system", content: warningMsg });
+            pendingConstraintWarnings = [];
+          }
           const now = Date.now();
           if (now > nextSelfEval) {
             selfEvalCount++;
@@ -26816,7 +26822,9 @@ If you're stuck, try a completely different approach. Do NOT repeat what failed
                 } else {
                   const warnViolations = violations.filter((v) => v.constraint.action === "warn");
                   if (warnViolations.length > 0) {
-                    this.emit({ type: "status", content: `\u26A0\uFE0F Constraint warning: ${warnViolations[0].constraint.message}`, timestamp: (/* @__PURE__ */ new Date()).toISOString() });
+                    const warning = formatViolationWarning(warnViolations);
+                    this.emit({ type: "status", content: `\u26A0\uFE0F ${warning}`, timestamp: (/* @__PURE__ */ new Date()).toISOString() });
+                    pendingConstraintWarnings.push(warning);
                   }
                   try {
                     result = await tool.execute(tc.arguments);
@@ -29313,6 +29321,13 @@ ${description}`
   }
 });
 
+// packages/orchestrator/dist/constraint-learner.js
+var init_constraint_learner = __esm({
+  "packages/orchestrator/dist/constraint-learner.js"() {
+    "use strict";
+  }
+});
+
 // packages/orchestrator/dist/nexusBackend.js
 import { existsSync as existsSync32, statSync as statSync10, openSync, readSync, closeSync, unlinkSync as unlinkSync5, writeFileSync as writeFileSync12 } from "node:fs";
 import { watch as fsWatch } from "node:fs";
@@ -30480,6 +30495,7 @@ var init_dist5 = __esm({
     init_retryController();
     init_agenticRunner();
     init_pressure_gate();
+    init_constraint_learner();
     init_nexusBackend();
     init_cascadeBackend();
     init_flowstatePrompt();

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "open-agents-ai",
-  "version": "0.186.6",
+  "version": "0.186.8",
   "description": "AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop",
   "type": "module",
   "main": "./dist/index.js",