Merge main into thedotmack/file-read-timeline-inject

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

src/utils/tag-stripping.ts

@@ -1,11 +1,13 @@
 /**
  * Tag Stripping Utilities
  *
- * Implements the dual-tag system for meta-observation control:
+ * Implements the tag system for meta-observation control:
  * 1. <claude-mem-context> - System-level tag for auto-injected observations
  *    (prevents recursive storage when context injection is active)
  * 2. <private> - User-level tag for manual privacy control
  *    (allows users to mark content they don't want persisted)
+ * 3. <system_instruction> / <system-instruction> - Conductor-injected system instructions
+ *    (should not be persisted to memory)
  *
  * EDGE PROCESSING PATTERN: Filter at hook layer before sending to worker/storage.
  * This keeps the worker service simple and follows one-way data stream.
@@ -27,7 +29,9 @@ const MAX_TAG_COUNT = 100;
 function countTags(content: string): number {
   const privateCount = (content.match(/<private>/g) || []).length;
   const contextCount = (content.match(/<claude-mem-context>/g) || []).length;
-  return privateCount + contextCount;
+  const systemInstructionCount = (content.match(/<system_instruction>/g) || []).length;
+  const systemInstructionHyphenCount = (content.match(/<system-instruction>/g) || []).length;
+  return privateCount + contextCount + systemInstructionCount + systemInstructionHyphenCount;
 }
 
 /**
@@ -49,6 +53,8 @@ function stripTagsInternal(content: string): string {
   return content
     .replace(/<claude-mem-context>[\s\S]*?<\/claude-mem-context>/g, '')
     .replace(/<private>[\s\S]*?<\/private>/g, '')
+    .replace(/<system_instruction>[\s\S]*?<\/system_instruction>/g, '')
+    .replace(/<system-instruction>[\s\S]*?<\/system-instruction>/g, '')
     .trim();
 }
 

tests/utils/tag-stripping.test.ts

@@ -1,7 +1,7 @@
 /**
  * Tag Stripping Utility Tests
  *
- * Tests the dual-tag privacy system for <private> and <claude-mem-context> tags.
+ * Tests the tag privacy system for <private>, <claude-mem-context>, and <system_instruction> tags.
  * These tags enable users and the system to exclude content from memory storage.
  *
  * Sources:
@@ -257,6 +257,74 @@ finish`;
     });
   });
 
+  describe('system_instruction tag stripping', () => {
+    describe('basic system_instruction removal', () => {
+      it('should strip single <system_instruction> tag from prompt', () => {
+        const input = 'user content <system_instruction>injected instructions</system_instruction> more content';
+        const result = stripMemoryTagsFromPrompt(input);
+        expect(result).toBe('user content  more content');
+      });
+
+      it('should strip <system_instruction> mixed with <private> tags', () => {
+        const input = '<system_instruction>instructions</system_instruction> public <private>secret</private> end';
+        const result = stripMemoryTagsFromPrompt(input);
+        expect(result).toBe('public  end');
+      });
+
+      it('should return empty string for entirely <system_instruction> content', () => {
+        const input = '<system_instruction>entire prompt is system instructions</system_instruction>';
+        const result = stripMemoryTagsFromPrompt(input);
+        expect(result).toBe('');
+      });
+
+      it('should strip <system_instruction> tags from JSON content', () => {
+        const jsonContent = JSON.stringify({
+          data: '<system_instruction>injected</system_instruction> real data'
+        });
+        const result = stripMemoryTagsFromJson(jsonContent);
+        const parsed = JSON.parse(result);
+        expect(parsed.data).toBe(' real data');
+      });
+
+      it('should strip multiline content within <system_instruction> tags', () => {
+        const input = `before
+<system_instruction>
+line one
+line two
+line three
+</system_instruction>
+after`;
+        const result = stripMemoryTagsFromPrompt(input);
+        expect(result).toBe('before\n\nafter');
+      });
+    });
+  });
+
+  describe('system-instruction (hyphen variant) tag stripping', () => {
+    it('should strip single <system-instruction> tag from prompt', () => {
+      const input = 'user content <system-instruction>injected instructions</system-instruction> more content';
+      const result = stripMemoryTagsFromPrompt(input);
+      expect(result).toBe('user content  more content');
+    });
+
+    it('should strip both underscore and hyphen variants in same prompt', () => {
+      const input = '<system_instruction>underscore</system_instruction> middle <system-instruction>hyphen</system-instruction> end';
+      const result = stripMemoryTagsFromPrompt(input);
+      expect(result).toBe('middle  end');
+    });
+
+    it('should strip multiline <system-instruction> content', () => {
+      const input = `before
+<system-instruction>
+line one
+line two
+</system-instruction>
+after`;
+      const result = stripMemoryTagsFromPrompt(input);
+      expect(result).toBe('before\n\nafter');
+    });
+  });
+
   describe('privacy enforcement integration', () => {
     it('should allow empty result to trigger privacy skip', () => {
       // Simulates what SessionRoutes does with private-only prompts