Merge branch 'pr-1578' into integration/validation-batch

# Conflicts:
#	plugin/scripts/context-generator.cjs
#	plugin/scripts/worker-service.cjs
#	src/utils/tag-stripping.ts
This commit is contained in:
Alex Newman
2026-04-06 14:21:45 -07:00
7 changed files with 283 additions and 220 deletions
+13 -3
View File
@@ -8,6 +8,8 @@
* (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)
* 4. <system-reminder> - Claude Code-injected system reminders
* (CLAUDE.md contents, deferred tool lists, etc. — should not be persisted)
*
* EDGE PROCESSING PATTERN: Filter at hook layer before sending to worker/storage.
* This keeps the worker service simple and follows one-way data stream.
@@ -15,6 +17,12 @@
import { logger } from './logger.js';
/**
* Regex to match <system-reminder> tags and their content.
* Exported for use by transcript parsers that strip system-reminder at read-time.
*/
export const SYSTEM_REMINDER_REGEX = /<system-reminder>[\s\S]*?<\/system-reminder>/g;
/**
* Maximum number of tags allowed in a single content block
* This protects against ReDoS (Regular Expression Denial of Service) attacks
@@ -31,8 +39,9 @@ function countTags(content: string): number {
const contextCount = (content.match(/<claude-mem-context>/g) || []).length;
const systemInstructionCount = (content.match(/<system_instruction>/g) || []).length;
const systemInstructionHyphenCount = (content.match(/<system-instruction>/g) || []).length;
const persistedOutputCount = (content.match(/<persisted-output>/g) || []).length;
return privateCount + contextCount + systemInstructionCount + systemInstructionHyphenCount + persistedOutputCount;
const persistedOutputCount = (content.match(/<persisted-output>/g) || []).length;
const systemReminderCount = (content.match(/<system-reminder>/g) || []).length;
return privateCount + contextCount + systemInstructionCount + systemInstructionHyphenCount + persistedOutputCount + systemReminderCount;
}
/**
@@ -56,7 +65,8 @@ function stripTagsInternal(content: string): string {
.replace(/<private>[\s\S]*?<\/private>/g, '')
.replace(/<system_instruction>[\s\S]*?<\/system_instruction>/g, '')
.replace(/<system-instruction>[\s\S]*?<\/system-instruction>/g, '')
.replace(/<persisted-output>[\s\S]*?<\/persisted-output>/g, '')
.replace(/<persisted-output>[\s\S]*?<\/persisted-output>/g, '')
.replace(SYSTEM_REMINDER_REGEX, '')
.trim();
}
+2 -1
View File
@@ -5,6 +5,7 @@
import { readFileSync } from 'fs';
import { logger } from './logger.js';
import { SYSTEM_REMINDER_REGEX } from './tag-stripping.js';
import type {
TranscriptEntry,
UserTranscriptEntry,
@@ -163,7 +164,7 @@ export class TranscriptParser {
if (filterSystemReminders) {
// Filter out system-reminder tags and their content
text = text.replace(/<system-reminder>[\s\S]*?<\/system-reminder>/g, '');
text = text.replace(SYSTEM_REMINDER_REGEX, '');
// Clean up excessive whitespace
text = text.replace(/\n{3,}/g, '\n\n').trim();
}