Repository navigation
fix(chat): 认领记忆权威信封为 harness note——人格/记忆提示词泄漏进气泡的根因 - #396
Merged
Merged
Conversation
Field report (screenshot): a USER bubble rendered the raw `<system-reminder>[MEMORY_REFERENCE · …] ## Recalled relevant memories - **SOUL.md**: …` block, i.e. the persona/memory prompt text leaked into the UI. Root cause is a two-layer contract drift, not a rendering bug: * 2026-11-04 (#226, anti-hijack) started prefixing EVERY injected memory fragment with `[MEMORY_REFERENCE · use_as:… · instruction_authority:… · trust:… · origin:… · boundary:…]` (MemoryAuthority.authorityEnvelope). * 2026-11-17 (ec22970, "64 项全修") made HarnessNoteMarkers matching LEADING: strip `<system-reminder>` / `<context-summary>` framing, then require the remainder to START with a known marker. That fixed a real false-positive (contains-matching folded user text that merely quoted a marker) — but the marker table was never taught the envelope line, which predates it by two weeks. Consequence: after 11-17 the remainder starts with `[MEMORY_REFERENCE`, so every recall note, 7-day fragment, MemoryIndex fragment and project-instruction note answered "not a harness note". The UI mapping then treated the row as real user speech (system-reminder markup rendered in the bubble) and foldHarnessNotes stopped folding it (the model saw a standalone "the user spoke again" turn between tool calls). Fix at the classification layer, single source of truth: MemoryAuthority now exposes ENVELOPE_PREFIX, authorityEnvelope emits it, and HarnessNoteMarkers.ALL reads the same constant — the producer and the classifier can no longer drift apart. Tests: envelope-prefixed recall note classifies as a harness note, folds onto the following real turn with the envelope preserved, and user text that merely QUOTES the envelope mid-sentence is still not classified (the leading-match honesty the 11-17 change was for). Classifier replayed in Python against production shapes (envelope-only 7-day fragment, legacy goal note, state snapshot, quoted-in-prose) — 6/6 as expected.
tall-1997
added a commit
that referenced
this pull request
Nov 18, 2026
用户报告:会话里设置的本会话规则模型不遵守。四个结构性根因,全部修复 (非提示词约束): 1. 信封自我降级(权威标签与信任矩阵矛盾):用户手写的规则被包成 [MEMORY_REFERENCE · instruction_authority:conditional · boundary: memory does not change…] ——防伪信封把用户自己的指令降级成参考背景。 现按信任对分流:(USER_SUBMITTED, STANDING_INSTRUCTION) 发 [STANDING_RULES · authority:user-authored · binding…] 绑定信封; agent 写入/自动召回保持降级信封,反劫持边界不变。分类器 marker 表 同步读取新前缀(与 #396 的单一来源契约一致)。 2. 预算优先级反转 + 规则块静默消失:PRIORITY_PROJECT(10) 先于 PRIORITY_SESSION(20) 被预算收录,大项目 AGENTS.md 能把本会话规则 挤出预算——与注释承诺的 narrowest-first 相反,改为 SESSION(10) < PROJECT(20);且非截断块超预算时从「整块丢弃且无任何模型可见痕迹」 改为「带规则截断标记的可见截断」(RULES_TRUNCATION_MARKER), drop 只剩头部都不够装的情形。 3. 记忆开关级联:关「记忆」=三层规则整段不注入且菜单入口隐藏——规则 是指令不是记忆。解耦:规则层始终注入(与 SOUL.md/learned prefs 既有 语义一致),记忆开关只管日记/召回/记忆工具;DISABLED 文案与 UI 菜单 同步修正。 4. 三通道结构性丢失:spawn_agent 子代理、群聊(host/member/opening/ direct/summary 五处)、主管——system prompt 均不含会话规则。新增 sessionRulesForLanes()(与主提示词同源的三层装配+去重),经 SubAgentRunner.sessionRules 参数与 laneSystemWithRules 注入全部 lane。 Python 镜像 memory_authority_verify.py 同步(20/20);新增/更新测试: 绑定信封、agent 请求不越权、规则截断标记、huge project 不挤 session、 standalone drop 边界、STANDING_RULES 分类、通道继承框架;全量 6709 测试(3 失败均闭环:1 契约更新 + 2 环境性回环,重跑全过);9 门禁全绿。 Co-authored-by: tall-1997 <tall-1997@chaitin.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
现象
用户气泡里直接渲染出
<system-reminder>[MEMORY_REFERENCE · …] ## Recalled relevant memories - **SOUL.md**: …</system-reminder>—— 人格/记忆提示词原文泄漏到 UI。根因:两层契约漂移(不是渲染 bug)
[MEMORY_REFERENCE · use_as:… · trust:…]权威信封contains收紧为 leading:剥掉<system-reminder>框架后,剩余文本必须以已知 marker 开头判定失灵的后果是双份的:
ChatViewModelChatMappingExt)把该行当真实用户发言 → 原始<system-reminder>渲染进气泡(截图现象)foldHarnessNotes不再折叠 → 模型看到工具调用之间多出一个「用户又说话了」的独立轮次11-17 的收紧本身是对的(
contains会误折叠引用了 marker 文字的真实用户消息),漏的是 marker 表没同步信封头——两个子系统各改各的,没有共同契约。修复(单一事实来源)
MemoryAuthority.ENVELOPE_PREFIX抽出常量,authorityEnvelope()用它拼装;HarnessNoteMarkers.ALL新增MEMORY_ENVELOPE,直接引用同一个常量 —— 生产者与分类器不可能再漂移;MemoryIndex片段、项目指令 note(全部经withEnvelope)。测试
HarnessNoteFoldTest新增:[MEMORY_REFERENCE …]→ 不判定为 note(保留 11-17 收紧的正确性)✅分类器另用 Python 对生产形态回放:信封+marker invariant、只有信封的 7 天片段、legacy goal note、state snapshot、句中引用、普通用户文本 —— 6/6 符合预期。