# mnemonic - Doramagic AI Context Pack

> 定位：安装前体验与判断资产。它帮助宿主 AI 有一个好的开始，但不代表已经安装、执行或验证目标项目。

## 充分原则

- **充分原则，不是压缩原则**：AI Context Pack 应该充分到让宿主 AI 在开工前理解项目价值、能力边界、使用入口、风险和证据来源；它可以分层组织，但不以最短摘要为目标。
- **压缩策略**：只压缩噪声和重复内容，不压缩会影响判断和开工质量的上下文。

## 给宿主 AI 的使用方式

你正在读取 Doramagic 为 mnemonic 编译的 AI Context Pack。请把它当作开工前上下文：帮助用户理解适合谁、能做什么、如何开始、哪些必须安装后验证、风险在哪里。不要声称你已经安装、运行或执行了目标项目。

## Claim 消费规则

- **事实来源**：Repo Evidence + Claim/Evidence Graph；Human Wiki 只提供显著性、术语和叙事结构。
- **事实最低状态**：`supported`
- `supported`：可以作为项目事实使用，但回答中必须引用 claim_id 和证据路径。
- `weak`：只能作为低置信度线索，必须要求用户继续核实。
- `inferred`：只能用于风险提示或待确认问题，不能包装成项目事实。
- `unverified`：不得作为事实使用，应明确说证据不足。
- `contradicted`：必须展示冲突来源，不得替用户强行选择一个版本。

## 它最适合谁

- **正在使用 Claude/Codex/Cursor/Gemini 等宿主 AI 的开发者**：README 或插件配置提到多个宿主 AI。 证据：`README.md` Claim：`clm_0003` supported 0.86
- **希望把专业流程带进宿主 AI 的用户**：仓库包含 Skill 文档。 证据：`.agents/skills/typescript-code-review/SKILL.md`, `skills/mnemonic-rpi-workflow/SKILL.md` Claim：`clm_0004` supported 0.86

## 它能做什么

- **AI Skill / Agent 指令资产库**（可做安装前预览）：项目包含可被宿主 AI 读取的 Skill 或 Agent 指令文件，可用于把专业流程带入 Claude、Codex、Cursor 等宿主。 证据：`.agents/skills/typescript-code-review/SKILL.md`, `skills/mnemonic-rpi-workflow/SKILL.md` Claim：`clm_0001` supported 0.86
- **命令行启动或安装流程**（需要安装后验证）：项目文档中存在可执行命令，真实使用需要在本地或宿主环境中运行这些命令。 证据：`README.md` Claim：`clm_0002` supported 0.86

## 怎么开始

- `npm install @danielmarbach/mnemonic-mcp` 证据：`README.md` Claim：`clm_0005` supported 0.86, `clm_0006` supported 0.86
- `npm install @danielmarbach/mnemonic-mcp@0.2.0` 证据：`README.md` Claim：`clm_0006` supported 0.86
- `npx mnemonic-install-skills --target all --mode copy` 证据：`README.md` Claim：`clm_0007` supported 0.86, `clm_0009` supported 0.86
- `npx -y -p @danielmarbach/mnemonic-mcp mnemonic-install-skills --target all --mode copy` 证据：`README.md` Claim：`clm_0008` supported 0.86
- `npx mnemonic-install-skills --target all --mode copy --update` 证据：`README.md` Claim：`clm_0009` supported 0.86
- `npx mnemonic-install-skills --target all --mode symlink --update` 证据：`README.md` Claim：`clm_0010` supported 0.86
- `git clone git@github.com:you/mnemonic-vault.git ~/mnemonic-vault` 证据：`README.md` Claim：`clm_0011` supported 0.86

## 继续前判断卡

- **当前建议**：需要管理员/安全审批
- **为什么**：继续前可能涉及密钥、账号、外部服务或敏感上下文，建议先经过管理员或安全审批。

### 30 秒判断

- **现在怎么做**：需要管理员/安全审批
- **最小安全下一步**：先跑 Prompt Preview；若涉及凭证或企业环境，先审批再试装
- **先别相信**：研究结论、引用和实验结果不能在安装前相信。
- **继续会触碰**：研究判断、命令执行、宿主 AI 配置

### 现在可以相信

- **适合人群线索：正在使用 Claude/Codex/Cursor/Gemini 等宿主 AI 的开发者**（supported）：有 supported claim 或项目证据支撑，但仍不等于真实安装效果。 证据：`README.md` Claim：`clm_0003` supported 0.86
- **适合人群线索：希望把专业流程带进宿主 AI 的用户**（supported）：有 supported claim 或项目证据支撑，但仍不等于真实安装效果。 证据：`.agents/skills/typescript-code-review/SKILL.md`, `skills/mnemonic-rpi-workflow/SKILL.md` Claim：`clm_0004` supported 0.86
- **能力存在：AI Skill / Agent 指令资产库**（supported）：可以相信项目包含这类能力线索；是否适合你的具体任务仍要试用或安装后验证。 证据：`.agents/skills/typescript-code-review/SKILL.md`, `skills/mnemonic-rpi-workflow/SKILL.md` Claim：`clm_0001` supported 0.86
- **能力存在：命令行启动或安装流程**（supported）：可以相信项目包含这类能力线索；是否适合你的具体任务仍要试用或安装后验证。 证据：`README.md` Claim：`clm_0002` supported 0.86
- **存在 Quick Start / 安装命令线索**（supported）：可以相信项目文档出现过启动或安装入口；不要因此直接在主力环境运行。 证据：`README.md` Claim：`clm_0005` supported 0.86, `clm_0006` supported 0.86

### 现在还不能相信

- **研究结论、引用和实验结果不能在安装前相信。**（unverified）：研究 Skill 可以组织问题和路径，但不能替代真实资料检索、论文核验和实验复现。
- **是否适合你的具体研究领域不能直接相信。**（unverified）：Skill 覆盖很多研究主题，不代表对你的领域、资料要求和可信度标准足够。
- **真实输出质量不能在安装前相信。**（unverified）：Prompt Preview 只能展示引导方式，不能证明真实项目中的结果质量。
- **宿主 AI 版本兼容性不能在安装前相信。**（unverified）：Claude、Cursor、Codex、Gemini 等宿主加载规则和版本差异必须在真实环境验证。
- **不会污染现有宿主 AI 行为，不能直接相信。**（inferred）：Skill、plugin、AGENTS/CLAUDE/GEMINI 指令可能改变宿主 AI 的默认行为。 证据：`.agents/skills/typescript-code-review/SKILL.md`, `CLAUDE.md`, `skills/mnemonic-rpi-workflow/SKILL.md`
- **可安全回滚不能默认相信。**（unverified）：除非项目明确提供卸载和恢复说明，否则必须先在隔离环境验证。
- **真实安装后是否与用户当前宿主 AI 版本兼容？**（unverified）：兼容性只能通过实际宿主环境验证。
- **项目输出质量是否满足用户具体任务？**（unverified）：安装前预览只能展示流程和边界，不能替代真实评测。

### 继续会触碰什么

- **研究判断**：问题拆解、资料路径、实验路径、结论结构和可信度判断。 原因：研究型 Skill 可能让输出看起来更专业，但不能替代真实证据核验。
- **命令执行**：包管理器、网络下载、本地插件目录、项目配置或用户主目录。 原因：运行第一条命令就可能产生环境改动；必须先判断是否值得跑。 证据：`README.md`
- **宿主 AI 配置**：Claude/Codex/Cursor/Gemini/OpenCode 等宿主的 plugin、Skill 或规则加载配置。 原因：宿主配置会改变 AI 后续工作方式，可能和用户已有规则冲突。 证据：`.agents/skills/typescript-code-review/SKILL.md`, `CLAUDE.md`, `skills/mnemonic-rpi-workflow/SKILL.md`
- **本地环境或项目文件**：安装结果、插件缓存、项目配置或本地依赖目录。 原因：安装前无法证明写入范围和回滚方式，需要隔离验证。 证据：`README.md`
- **环境变量 / API Key**：项目入口文档明确出现 API key、token、secret 或账号凭证配置。 原因：如果真实安装需要凭证，应先使用测试凭证并经过权限/合规判断。 证据：`.mnemonic/notes/multi-provider-embedding-support-plan-and-research-consolida-c1687672.md`, `README.md`
- **宿主 AI 上下文**：AI Context Pack、Prompt Preview、Skill 路由、风险规则和项目事实。 原因：导入上下文会影响宿主 AI 后续判断，必须避免把未验证项包装成事实。

### 最小安全下一步

- **先跑 Prompt Preview**：先验证它能否正确界定研究问题和证据边界，不要先相信研究输出。（适用：任何项目都适用，尤其是输出质量未知时。）
- **只在隔离目录或测试账号试装**：避免安装命令污染主力宿主 AI、真实项目或用户主目录。（适用：存在命令执行、插件配置或本地写入线索时。）
- **先备份宿主 AI 配置**：Skill、plugin、规则文件可能改变 Claude/Cursor/Codex 的默认行为。（适用：存在插件 manifest、Skill 或宿主规则入口时。）
- **不要使用真实生产凭证**：环境变量/API key 一旦进入宿主或工具链，可能产生账号和合规风险。（适用：出现 API、TOKEN、KEY、SECRET 等环境线索时。）
- **安装后只验证一个最小任务**：先验证加载、兼容、输出质量和回滚，再决定是否深用。（适用：准备从试用进入真实工作流时。）

### 退出方式

- **保留安装前状态**：记录原始宿主配置和项目状态，后续才能判断是否可恢复。
- **准备移除宿主 plugin / Skill / 规则入口**：如果试装后行为异常，可以把宿主 AI 恢复到试装前状态。
- **保留资料和结论核验清单**：如果后续发现引用或实验路径不可靠，可以回到证据边界阶段重新校验。
- **记录安装命令和写入路径**：没有明确卸载说明时，至少要知道哪些目录或配置需要手动清理。
- **准备撤销测试 API key 或 token**：测试凭证泄露或误用时，可以快速止损。
- **如果没有回滚路径，不进入主力环境**：不可回滚是继续前阻断项，不应靠信任或运气继续。

## 哪些只能预览

- 解释项目适合谁和能做什么
- 基于项目文档演示典型对话流程
- 帮助用户判断是否值得安装或继续研究

## 哪些必须安装后验证

- 真实安装 Skill、插件或 CLI
- 执行脚本、修改本地文件或访问外部服务
- 验证真实输出质量、性能和兼容性

## 边界与风险判断卡

- **把安装前预览误认为真实运行**：用户可能高估项目已经完成的配置、权限和兼容性验证。 处理方式：明确区分 prompt_preview_can_do 与 runtime_required。 Claim：`clm_0012` inferred 0.45
- **命令执行会修改本地环境**：安装命令可能写入用户主目录、宿主插件目录或项目配置。 处理方式：先在隔离环境或测试账号中运行。 证据：`README.md` Claim：`clm_0013` supported 0.86
- **待确认**：真实安装后是否与用户当前宿主 AI 版本兼容？。原因：兼容性只能通过实际宿主环境验证。
- **待确认**：项目输出质量是否满足用户具体任务？。原因：安装前预览只能展示流程和边界，不能替代真实评测。
- **待确认**：安装命令是否需要网络、权限或全局写入？。原因：这影响企业环境和个人环境的安装风险。

## 开工前工作上下文

### 加载顺序

- 先读取 how_to_use.host_ai_instruction，建立安装前判断资产的边界。
- 读取 claim_graph_summary，确认事实来自 Claim/Evidence Graph，而不是 Human Wiki 叙事。
- 再读取 intended_users、capabilities 和 quick_start_candidates，判断用户是否匹配。
- 需要执行具体任务时，优先查 role_skill_index，再查 evidence_index。
- 遇到真实安装、文件修改、网络访问、性能或兼容性问题时，转入 risk_card 和 boundaries.runtime_required。

### 任务路由

- **AI Skill / Agent 指令资产库**：先基于 role_skill_index / evidence_index 帮用户挑选可用角色、Skill 或工作流。 边界：可做安装前 Prompt 体验。 证据：`.agents/skills/typescript-code-review/SKILL.md`, `skills/mnemonic-rpi-workflow/SKILL.md` Claim：`clm_0001` supported 0.86
- **命令行启动或安装流程**：先说明这是安装后验证能力，再给出安装前检查清单。 边界：必须真实安装或运行后验证。 证据：`README.md` Claim：`clm_0002` supported 0.86

### 上下文规模

- 文件总数：230
- 重要文件覆盖：40/230
- 证据索引条目：80
- 角色 / Skill 条目：2

### 证据不足时的处理

- **missing_evidence**：说明证据不足，要求用户提供目标文件、README 段落或安装后验证记录；不要补全事实。
- **out_of_scope_request**：说明该任务超出当前 AI Context Pack 证据范围，并建议用户先查看 Human Manual 或真实安装后验证。
- **runtime_request**：给出安装前检查清单和命令来源，但不要替用户执行命令或声称已执行。
- **source_conflict**：同时展示冲突来源，标记为待核实，不要强行选择一个版本。

## Prompt Recipes

### 适配判断

- 目标：判断这个项目是否适合用户当前任务。
- 预期输出：适配结论、关键理由、证据引用、安装前可预览内容、必须安装后验证内容、下一步建议。

```text
请基于 mnemonic 的 AI Context Pack，先问我 3 个必要问题，然后判断它是否适合我的任务。回答必须包含：适合谁、能做什么、不能做什么、是否值得安装、证据来自哪里。所有项目事实必须引用 evidence_refs、source_paths 或 claim_id。
```

### 安装前体验

- 目标：让用户在安装前感受核心工作流，同时避免把预览包装成真实能力或营销承诺。
- 预期输出：一段带边界标签的体验剧本、安装后验证清单和谨慎建议；不含真实运行承诺或强营销表述。

```text
请把 mnemonic 当作安装前体验资产，而不是已安装工具或真实运行环境。

请严格输出四段：
1. 先问我 3 个必要问题。
2. 给出一段“体验剧本”：用 [安装前可预览]、[必须安装后验证]、[证据不足] 三种标签展示它可能如何引导工作流。
3. 给出安装后验证清单：列出哪些能力只有真实安装、真实宿主加载、真实项目运行后才能确认。
4. 给出谨慎建议：只能说“值得继续研究/试装”“先补充信息后再判断”或“不建议继续”，不得替项目背书。

硬性边界：
- 不要声称已经安装、运行、执行测试、修改文件或产生真实结果。
- 不要写“自动适配”“确保通过”“完美适配”“强烈建议安装”等承诺性表达。
- 如果描述安装后的工作方式，必须使用“如果安装成功且宿主正确加载 Skill，它可能会……”这种条件句。
- 体验剧本只能写成“示例台词/假设流程”：使用“可能会询问/可能会建议/可能会展示”，不要写“已写入、已生成、已通过、正在运行、正在生成”。
- Prompt Preview 不负责给安装命令；如用户准备试装，只能提示先阅读 Quick Start 和 Risk Card，并在隔离环境验证。
- 所有项目事实必须来自 supported claim、evidence_refs 或 source_paths；inferred/unverified 只能作风险或待确认项。

```

### 角色 / Skill 选择

- 目标：从项目里的角色或 Skill 中挑选最匹配的资产。
- 预期输出：候选角色或 Skill 列表，每项包含适用场景、证据路径、风险边界和是否需要安装后验证。

```text
请读取 role_skill_index，根据我的目标任务推荐 3-5 个最相关的角色或 Skill。每个推荐都要说明适用场景、可能输出、风险边界和 evidence_refs。
```

### 风险预检

- 目标：安装或引入前识别环境、权限、规则冲突和质量风险。
- 预期输出：环境、权限、依赖、许可、宿主冲突、质量风险和未知项的检查清单。

```text
请基于 risk_card、boundaries 和 quick_start_candidates，给我一份安装前风险预检清单。不要替我执行命令，只说明我应该检查什么、为什么检查、失败会有什么影响。
```

### 宿主 AI 开工指令

- 目标：把项目上下文转成一次对话开始前的宿主 AI 指令。
- 预期输出：一段边界明确、证据引用明确、适合复制给宿主 AI 的开工前指令。

```text
请基于 mnemonic 的 AI Context Pack，生成一段我可以粘贴给宿主 AI 的开工前指令。这段指令必须遵守 not_runtime=true，不能声称项目已经安装、运行或产生真实结果。
```

## 角色 / Skill 索引

- 共索引 2 个角色 / Skill / 项目文档条目。

- **typescript-code-review**（skill）：Review TypeScript for type safety, security, performance, maintainability. Makes invalid states unrepresentable via branded types, discriminated unions, template literals, satisfies, infer. Use for TypeScript review, type audits, antipatterns, type-level correctness. 激活提示：当用户任务与“typescript-code-review”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.agents/skills/typescript-code-review/SKILL.md`
- **mnemonic-rpi-workflow**（skill）：mnemonic RPIR research-plan-implement-review workflow. Use for multi-step feature/bugfix work, subagent handoffs, plan-heavy tasks, RPIR artifacts. Review phase: fresh-context subagent with adversarial posture for constraint violation hunting. 激活提示：当用户任务与“mnemonic-rpi-workflow”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/mnemonic-rpi-workflow/SKILL.md`

## 证据索引

- 共索引 80 条证据。

- **mnemonic**（documentation）：A local MCP memory server backed by plain markdown files, synced via git. No database. Project-scoped memory with hybrid semantic, exact-match, and relationship-aware recall. 证据：`README.md`
- **Package**（package_manifest）：{ "name": "@danielmarbach/mnemonic-mcp", "version": "0.36.0", "description": "A local MCP memory server backed by markdown + JSON files, synced via git", "type": "module", "repository": { "type": "git", "url": "git+https://github.com/danielmarbach/mnemonic.git" }, "publishConfig": { "registry": "https://registry.npmjs.org", "access": "public" }, "files": "build", "skills", "scripts/install-skills.mjs", "CHANGELOG.md", "README.md", "LICENSE" , "bin": { "mnemonic": "build/index.js", "mnemonic-install-skills": "scripts/install-skills.mjs" }, "scripts": { "build": "npm run typecheck && tsc && chmod 755 build/index.js", "build:clean": "tsc --build --clean && npm run build", "build:fast": "tsc &&… 证据：`package.json`
- **TypeScript Code Review**（skill_instruction）：Review TypeScript code with a focus on making invalid states unrepresentable . The type system is the most powerful correctness tool available — when types prevent invalid states at compile time, LLMs and humans alike produce fewer bugs because mistakes don't compile. 证据：`.agents/skills/typescript-code-review/SKILL.md`
- **RPIR Workflow: Research → Plan → Implement → Review**（skill_instruction）：RPIR Workflow: Research → Plan → Implement → Review 证据：`skills/mnemonic-rpi-workflow/SKILL.md`
- **RTK Rust Token Killer - Token-Optimized Commands**（documentation）：RTK Rust Token Killer - Token-Optimized Commands 证据：`CLAUDE.md`
- **Contributing to mnemonic**（documentation）：Thank you for contributing to mnemonic. This guide covers the conventions, workflows, and expectations for working on the project. 证据：`CONTRIBUTING.md`
- **License**（source_file）：Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ 证据：`LICENSE`
- **Architecture**（documentation）：mnemonic is a file-first MCP memory server. It stores notes as markdown, keeps embeddings as local JSON, routes reads and writes across a main vault and optional project vaults, and uses git as the synchronization and audit layer instead of a database. 证据：`ARCHITECTURE.md`
- **Config**（source_file）：import fs from "fs/promises"; import path from "path"; import { z } from "zod"; ⋮---- import { attempt, attemptSync, debugLog, getErrorMessage } from "./error-utils.js"; import { CONSOLIDATION MODES, PROJECT POLICY SCOPES, PROTECTED BRANCH BEHAVIORS, type ProjectMemoryPolicy, } from "./project-memory-policy.js"; import type { ProjectIdentityOverride } from "./project.js"; import type { ProjectAttachmentConfig } from "./vault.js"; import { attachmentSlug } from "./brands.js"; ⋮---- export type MutationPushMode = "all" "main-only" "none"; ⋮---- export interface MnemonicConfig { schemaVersion: string; reindexEmbedConcurrency: number; mutationPushMode: MutationPushMode; projectMemoryPolicies: R… 证据：`src/config.ts`
- **Consolidate**（source_file）：import type { Note, Relationship } from "./storage.js"; import type { ConsolidationMode } from "./project-memory-policy.js"; import type { ConsolidateClassification } from "./structured-content.js"; import { daysSince } from "./date-utils.js"; ⋮---- export type MergeRisk = typeof MERGE RISKS number ; ⋮---- export interface ConsolidateNoteEvidence { id: string; title: string; lifecycle: "temporary" "permanent"; role?: Note "role" ; ageDays: number; superseded: boolean; supersededBy?: string; supersededCount?: number; relatedCount: number; classification?: ConsolidateClassification; warnings?: string ; mergeRisk: MergeRisk; } ⋮---- function noteAgeDays updatedAt: string, now: Date = new Date… 证据：`src/consolidate.ts`
- **Embeddings**（source_file）：import type { EmbeddingCompatibilityKey, EmbeddingDimensions, EmbeddingMetric, EmbeddingModelId, EmbeddingProviderId, } from "./brands.js"; import { embeddingCompatibilityKey, embeddingDimensions, embeddingMetric, embeddingModelId, embeddingProviderId, } from "./brands.js"; import { EmbeddingConfigurationError, EmbeddingDimensionMismatchError, EmbeddingProviderError, OllamaUrlError, } from "./domain-errors.js"; import type { EmbeddingRecord } from "./storage.js"; import { z } from "zod"; ⋮---- export type EmbeddingProviderKind = typeof EMBEDDING PROVIDER IDS number ; ⋮---- export type EmbeddingMetricValue = typeof EMBEDDING METRICS number ; ⋮---- export interface EmbeddingIdentity { readonl… 证据：`src/embeddings.ts`
- **Index**（source_file）：import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; ⋮---- import { registerAllTools } from "./tools/index.js"; import { registerPrompts } from "./prompts.js"; import { createServerContext, readPackageVersion } from "./context.js"; import { startServer } from "./startup.js"; import { isCliCommand, showHelp, rejectUnknownCommand, runCliCommand } from "./cli/dispatch.js"; 证据：`src/index.ts`
- **Lexical**（source_file）：export function normalizeText text: string : string ⋮---- export function tokenize text: string : string ⋮---- export function jaccardSimilarity a: Set , b: Set : number ⋮---- export function bigramJaccardSimilarity a: string, b: string : number ⋮---- function bigrams text: string : string ⋮---- / Check if one string contains another as a substring case-insensitive . / export function containsSubstring haystack: string, needle: string : boolean ⋮---- / Compute a composite lexical score between a query and projection text. Returns a value in 0, 1 combining: - substring match bonus 0.4 weight — exact phrase containment - bigram Jaccard 0.35 weight — phrase-level overlap - unigram Jaccard 0.25… 证据：`src/lexical.ts`
- **Migration**（source_file）：import fs from "fs/promises"; import path from "path"; import matter from "gray-matter"; ⋮---- import { getErrorMessage, debugLog } from "./error-utils.js"; import { MigrationAlreadyRegisteredError, UnknownMigrationError, InvalidSchemaVersionError, } from "./domain-errors.js"; ⋮---- import type { Vault, VaultManager } from "./vault.js"; import type { Note } from "./storage.js"; import { readVaultSchemaVersion, writeVaultSchemaVersion } from "./config.js"; ⋮---- export interface MigrationResult { notesProcessed: number; notesModified: number; modifiedNoteIds: string ; errors: Array ; warnings: string ; } ⋮---- export interface Migration { name: string; description: string; minSchemaVersion?:… 证据：`src/migration.ts`
- **Project**（source_file）：import { execFile } from "child process"; import { promisify } from "util"; import path from "path"; import type { ProjectId } from "./brands.js"; import { projectId } from "./brands.js"; import { attempt } from "./error-utils.js"; ⋮---- export type ProjectSource = "git-remote" "git-remote-override" "git-folder" "folder"; ⋮---- export interface ProjectInfo { id: ProjectId; name: string; source: ProjectSource; remoteName?: string; } ⋮---- export interface ProjectIdentityOverride { remoteName: string; updatedAt: string; } ⋮---- export interface ProjectDetectionOptions { getProjectIdentityOverride?: projectId: string = Promise ; } ⋮---- export interface ProjectIdentityResolution { project: Pro… 证据：`src/project.ts`
- **Projections**（source_file）：import type { Note, NoteStorage } from "./storage.js"; import type { NoteProjection } from "./structured-content.js"; import { memoryId } from "./brands.js"; ⋮---- export function extractProjectionSummary note: Note : string ⋮---- // Strip leading heading lines Title, Title, etc. from the body ⋮---- // Step 2: first bullet list block converted to plain text ⋮---- // Step 3: first 200 chars of plain text body ⋮---- // ── Heading extraction ──────────────────────────────────────────────────────── ⋮---- / Extract headings from markdown content. Returns plain text, in order, deduplicated, max 8 headings. / export function extractHeadings markdown: string : string ⋮---- // ── Projection text ───… 证据：`src/projections.ts`
- **Recall**（source_file）：import type { Vault } from "./vault.js"; import type { EffectiveNoteMetadata } from "./role-suggestions.js"; import { computeLexicalScore, tokenize } from "./lexical.js"; import { MS PER DAY } from "./date-utils.js"; import { UnknownRelationshipTypeError } from "./domain-errors.js"; ⋮---- import type { Confidence } from "./structured-content.js"; import type { RelationshipType } from "./storage.js"; ⋮---- export interface TemporalQueryHint { windowDays: number; maxBoost: number; confidence: Confidence; filterWindowDays?: number; } ⋮---- export interface ScoredRecallCandidate { id: string; identityKey?: string; score: number; semanticScoreForPromotion?: number; semanticRank?: number; lexical… 证据：`src/recall.ts`
- **Relationships**（source_file）：import type { Note, Relationship } from "./storage.js"; import type { Vault } from "./vault.js"; import type { Confidence, RelatedNotePreview, RelationshipPreview } from "./structured-content.js"; import { classifyTheme } from "./project-introspection.js"; import { getEffectiveMetadata, type EffectiveNoteMetadata, type RoleSuggestionContext, } from "./role-suggestions.js"; import { daysSince } from "./date-utils.js"; import { attempt } from "./error-utils.js"; import { memoryId } from "./brands.js"; import { storageLabel } from "./helpers/vault.js"; ⋮---- export interface RelationshipExpansionOptions { activeProjectId?: string; limit?: number; includeGlobal?: boolean; sourceVaultPath?: stri… 证据：`src/relationships.ts`
- **Vault**（source_file）：import fs from "fs/promises"; import path from "path"; import { simpleGit } from "simple-git"; ⋮---- import { attempt, debugLog, getErrorMessage } from "./error-utils.js"; import { Storage, type Note, type NoteStorage } from "./storage.js"; import { memoryId, type AttachmentSlug } from "./brands.js"; import { GitOps } from "./git.js"; import { AttachedStorage } from "./attached-storage.js"; import { expandHomePath } from "./paths.js"; ⋮---- export type VaultProvenance = "main" "project-local" "project-attached"; ⋮---- export interface AttachmentRef { projectSlug: AttachmentSlug; projectName: string; localPath: string; branch: string; branchTipHash: string; writable?: boolean; pushBranch?: s… 证据：`src/vault.ts`
- **Dispatch**（source_file）：import { runMigrateCli } from "./migrate.js"; import { runImportCli } from "./import-claude-memory.js"; ⋮---- export type CliCommand = typeof CLI COMMANDS number "name" ; ⋮---- export function isCliCommand arg: string : arg is CliCommand ⋮---- export function showHelp : never ⋮---- export function rejectUnknownCommand command: string : never ⋮---- export async function runCliCommand command: CliCommand : Promise 证据：`src/cli/dispatch.ts`
- **Import Claude Memory**（source_file）：import { randomUUID } from "crypto"; import path from "path"; import { promises as fs } from "fs"; ⋮---- import type { MemoryId } from "../brands.js"; import { memoryId, isoDateString } from "../brands.js"; import { resolveUserPath, defaultVaultPath, defaultClaudeHome } from "../paths.js"; import { VaultManager } from "../vault.js"; import { parseMemorySections } from "../import.js"; import { MnemonicConfigStore } from "../config.js"; import { debugLog, getErrorMessage } from "../error-utils.js"; import type { Note } from "../storage.js"; ⋮---- export function makeImportNoteId title: string : MemoryId ⋮---- export async function runImportCli : Promise 证据：`src/cli/import-claude-memory.ts`
- **Migrate**（source_file）：import { resolveUserPath, defaultVaultPath } from "../paths.js"; import { VaultManager } from "../vault.js"; import { Migrator } from "../migration.js"; import { readVaultSchemaVersion } from "../config.js"; ⋮---- export async function runMigrateCli : Promise 证据：`src/cli/migrate.ts`
- **Index**（source_file）：import { randomUUID } from "crypto"; import type { Note, NoteLifecycle, NoteRole } from "../storage.js"; import type { MemoryId } from "../brands.js"; import { memoryId } from "../brands.js"; import type { RelationshipPreview, RetrievalEvidence } from "../structured-content.js"; ⋮---- export function slugify text: string : string ⋮---- export function makeId title: string : MemoryId ⋮---- export function describeLifecycle lifecycle: NoteLifecycle : string ⋮---- export function formatNote note: Note, score?: number, showRawRelated = true : string ⋮---- export function formatTemporalHistory history: Array , : string ⋮---- export function formatRelationshipPreview preview: RelationshipPreview… 证据：`src/helpers/index.ts`
- **Project**（source_file）：import { z } from "zod"; import path from "path"; import { simpleGit } from "simple-git"; import { detectProject, resolveProjectIdentity, type ProjectIdentityResolution, } from "../project.js"; import type { ServerContext } from "../server-context.js"; import type { ProjectRef } from "../structured-content.js"; import type { Vault } from "../vault.js"; import type { WriteScope } from "../project-memory-policy.js"; import { invalidateActiveProjectCache } from "../cache.js"; import { checkBranchChange } from "../branch-tracker.js"; import { backfillEmbeddingsAfterSync, removeStaleEmbeddings } from "./embed.js"; import { expandHomePath } from "../paths.js"; import { attempt as attemptFn, getEr… 证据：`src/helpers/project.ts`
- **Vault**（source_file）：import type { Note, NoteLifecycle, NoteRole } from "../storage.js"; import type { ServerContext } from "../server-context.js"; import type { Vault } from "../vault.js"; import type { PersistenceStatus } from "../structured-content.js"; import { getOrBuildVaultNoteList } from "../cache.js"; import { resolveProject } from "./project.js"; import { formatCommitBody, commitVaultWithProtection, checkVaultProtectedBranch, } from "./git-commit.js"; import { pushAfterMutation, buildMutationRetryContract, buildPersistenceStatus, } from "./persistence.js"; import { ProtectedBranchError } from "../domain-errors.js"; import { filterRelationships } from "../consolidate.js"; import { summarizePreview } fr… 证据：`src/helpers/vault.ts`
- **Consolidate**（source_file）：import { z } from "zod"; import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; import { ConsolidateResultSchema } from "../structured-content.js"; import { projectParam, resolveProject, ensureBranchSynced } from "../helpers/project.js"; import { collectVisibleNotes, projectNotFoundResponse } from "../helpers/vault.js"; import { CONSOLIDATION MODES, resolveConsolidationMode } from "../project-memory-policy.js"; import { invalidateActiveProjectCache } from "../cache.js"; import { detectDuplicates, findClusters, suggestMerges, executeMerge, pruneSuperseded, dryRunAll, } from "./consolidate-helpers.js"; export functi… 证据：`src/tools/consolidate.ts`
- **Detect Project**（source_file）：import { z } from "zod"; import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; import { resolveProjectIdentityForCwd as resolveProjectIdentityForCwdFromModule } from "../helpers/project.js"; import { projectNotFoundResponse, formatProjectPolicyLine as formatProjectPolicyLineFromModule, } from "../helpers/vault.js"; import type { ProjectIdentityResolution } from "../project.js"; import { ProjectIdentityResultSchema, type ProjectIdentityResult } from "../structured-content.js"; ⋮---- export function formatProjectIdentityText identity: ProjectIdentityResolution : string ⋮---- export function registerDetectProjectToo… 证据：`src/tools/detect-project.ts`
- **Forget**（source_file）：import { z } from "zod"; import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; import { NoteIdSchema, ForgetResultSchema, type ForgetResult, type MutationRetryContract, } from "../structured-content.js"; import { projectParam, resolveProject, noteProjectRef, ensureBranchSynced, } from "../helpers/project.js"; import { memoryId } from "../brands.js"; import { formatCommitBody, commitVaultWithProtection, checkVaultProtectedBranch, } from "../helpers/git-commit.js"; import { buildMutationRetryContract, formatRetrySummary, pushAfterMutation, } from "../helpers/persistence.js"; import { removeRelationshipsToNoteIds, a… 证据：`src/tools/forget.ts`
- **Get**（source_file）：import { z } from "zod"; import { performance } from "perf hooks"; import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; import type { Note } from "../storage.js"; import type { Vault } from "../vault.js"; import { GetResultSchema, NoteIdSchema, type GetResult, type RelationshipPreview, } from "../structured-content.js"; import { ensureBranchSynced, resolveProject, noteProjectRef, projectParam, } from "../helpers/project.js"; import { storageLabel } from "../helpers/vault.js"; import { formatRelationshipPreview } from "../helpers/index.js"; import { getSessionCachedNote, setSessionCachedNote, recordSessionNoteAcc… 证据：`src/tools/get.ts`
- **Index**（source_file）：import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; ⋮---- import { registerDetectProjectTool } from "./detect-project.js"; import { registerGetProjectIdentityTool } from "./get-project-identity.js"; import { registerSetProjectIdentityTool } from "./set-project-identity.js"; import { registerListMigrationsTool, registerExecuteMigrationTool } from "./migration.js"; import { registerSetProjectMemoryPolicyTool, registerGetProjectMemoryPolicyTool, } from "./policy.js"; import { registerRememberTool } from "./remember.js"; import { registerRecallTool } from "./recall.js"; import { registerUpdateTool } from "./update.… 证据：`src/tools/index.ts`
- **List Attachments**（source_file）：import { z } from "zod"; import path from "path"; import fs from "fs/promises"; import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; import { resolveProject as resolveProjectFromModule } from "../helpers/project.js"; import { projectNotFoundResponse } from "../helpers/vault.js"; import { ListAttachmentsResultSchema, type ListAttachmentsResult } from "../structured-content.js"; import { attempt } from "../error-utils.js"; import { expandHomePath } from "../paths.js"; ⋮---- export function registerListAttachmentsTool server: McpServer, ctx: ServerContext : void 证据：`src/tools/list-attachments.ts`
- **List**（source_file）：import { z } from "zod"; import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; import { ListResultSchema, type ListResult, type ProjectRef } from "../structured-content.js"; import type { Note, NoteLifecycle } from "../storage.js"; import { projectParam, ensureBranchSynced, noteProjectRef } from "../helpers/project.js"; import { collectVisibleNotes, formatListEntry, storageLabel } from "../helpers/vault.js"; ⋮---- export function registerListTool server: McpServer, ctx: ServerContext : void 证据：`src/tools/list.ts`
- **Memory Graph**（source_file）：import { z } from "zod"; import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; import { MemoryGraphResultSchema, type MemoryGraphResult } from "../structured-content.js"; import { projectParam, toProjectRef, ensureBranchSynced } from "../helpers/project.js"; import { type NoteEntry, collectVisibleNotes } from "../helpers/vault.js"; ⋮---- export function registerMemoryGraphTool server: McpServer, ctx: ServerContext : void 证据：`src/tools/memory-graph.ts`
- **Migration**（source_file）：import { z } from "zod"; import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; import { readVaultSchemaVersion } from "../config.js"; import { MigrationListResultSchema, type MigrationListResult, MigrationExecuteResultSchema, type MigrationExecuteResult, } from "../structured-content.js"; import { getErrorMessage, attempt } from "../error-utils.js"; import { ensureBranchSynced as ensureBranchSyncedFromModule, projectParam, } from "../helpers/project.js"; ⋮---- export function registerListMigrationsTool server: McpServer, ctx: ServerContext : void ⋮---- export function registerExecuteMigrationTool server: McpServe… 证据：`src/tools/migration.ts`
- **Project Memory Summary**（source_file）：import { z } from "zod"; import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; import { performance } from "perf hooks"; ⋮---- import { memoryId } from "../brands.js"; import { checkEmbeddingCompatibility, currentEmbeddingIdentity, safeCosineSimilarity, } from "../embeddings.js"; import { getNoteProvenance, computeConfidence, computeDecayInfo } from "../provenance.js"; import { getRelationshipPreview } from "../relationships.js"; import { formatRelationshipPreview } from "../helpers/index.js"; import { resolveProject, ensureBranchSynced } from "../helpers/project.js"; import { formatProjectPolicyLine, projectNotF… 证据：`src/tools/project-memory-summary.ts`
- **Recall Helpers**（source_file）：import type { Note, NoteLifecycle } from "../storage.js"; import type { Vault } from "../vault.js"; import { getEffectiveMetadata } from "../role-suggestions.js"; import { computeRecallMetadataBoost, recallCandidateIdentity, type ScoredRecallCandidate, type TemporalQueryHint, shouldApplyTemporalFiltering, computeTemporalRecencyBoost, isWithinTemporalFilterWindow, } from "../recall.js"; import { getOrBuildProjection } from "../projections.js"; import { attempt } from "../error-utils.js"; import { getSessionCachedProjection, setSessionCachedProjection, getSessionCachedProjectionTokens, setSessionCachedProjectionTokens, getOrBuildVaultNoteList, } from "../cache.js"; import { tokenize, computeL… 证据：`src/tools/recall-helpers.ts`
- **Recall**（source_file）：import { z } from "zod"; import { performance } from "perf hooks"; import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; import type { Vault } from "../vault.js"; import type { Note, NoteLifecycle, RelationshipType } from "../storage.js"; import { memoryId } from "../brands.js"; import { Confidence, RecallResult, RecallResultSchema, RetrievalEvidence, RelationshipPreview, ProjectRef, type RecallRetrievalCoverage, } from "../structured-content.js"; import { checkEmbeddingCompatibility, currentEmbeddingIdentity, embed, safeCosineSimilarity, } from "../embeddings.js"; import { detectTemporalQueryHint, shouldApplyTem… 证据：`src/tools/recall.ts`
- **Remember**（source_file）：import { z } from "zod"; import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; import { NOTE LIFECYCLES, NOTE ROLES, type Note } from "../storage.js"; import { isoDateString } from "../brands.js"; import { getErrorMessage, attempt } from "../error-utils.js"; import { embed, embeddingMetadata } from "../embeddings.js"; import { invalidateActiveProjectCache, getRecentSessionNoteAccesses, getSessionCachedNote, getRecentSessionAccessNote, } from "../cache.js"; import { suggestAutoRelationships } from "../auto-relate.js"; import { MarkdownLintError, cleanMarkdown } from "../markdown.js"; import { resolveWriteScope, WR… 证据：`src/tools/remember.ts`
- **Sync**（source_file）：import { z } from "zod"; import path from "path"; import { simpleGit } from "simple-git"; import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; import { SyncResultSchema, type SyncResult as StructuredSyncResult, } from "../structured-content.js"; import type { SyncResult } from "../git.js"; import { projectParam, resolveProject as resolveProjectFromModule } from "../helpers/project.js"; import { invalidateActiveProjectCache } from "../cache.js"; import { backfillEmbeddingsAfterSync, removeStaleEmbeddings } from "../helpers/embed.js"; import { attempt, getErrorMessage } from "../error-utils.js"; import { expandHom… 证据：`src/tools/sync.ts`
- **Update**（source_file）：import { z } from "zod"; import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; import { ensureBranchSynced, resolveProject, noteProjectRef, projectParam, } from "../helpers/project.js"; import { formatCommitBody, commitVaultWithProtection, checkVaultProtectedBranch, } from "../helpers/git-commit.js"; import { buildPersistenceStatus, buildMutationRetryContract, formatPersistenceSummary, pushAfterMutation, } from "../helpers/persistence.js"; import { embedTextForNote } from "../helpers/embed.js"; import { memoryId, isoDateString } from "../brands.js"; import { cleanMarkdown, MarkdownLintError } from "../markdown.js… 证据：`src/tools/update.ts`
- **mnemonic — Agent Context**（documentation）：⚠️ WHEN WORKING ON MNEMONIC: Always test changes with local MCP server first npm run mcp:local or scripts/mcp-local.sh 证据：`AGENT.md`
- **Changelog**（documentation）：All notable changes to mnemonic will be documented in this file. 证据：`CHANGELOG.md`
- **Contributor Covenant Code of Conduct**（documentation）：Contributor Covenant Code of Conduct 证据：`CODE_OF_CONDUCT.md`
- **Plan**（documentation）：✅ Data format robustness and migration strategy 证据：`PLAN.md`
- **Mnemonic Memory System**（documentation）：No system prompt required. Mnemonic's tools are self-describing — each tool includes "use when" / "do not use when" guidance, behavioral annotations, and typed schemas. 证据：`SYSTEM_PROMPT.md`
- **TypeScript Common Anti-Patterns**（documentation）：Mistakes and anti-patterns to avoid, with better alternatives. 证据：`.agents/skills/typescript-code-review/references/common-antipatterns.md`
- **Making Invalid States Unrepresentable**（documentation）：Making Invalid States Unrepresentable 证据：`.agents/skills/typescript-code-review/references/impossible-states.md`
- **TypeScript Performance Tips**（documentation）：Runtime and compilation performance strategies. Both matter — slow builds hurt developer experience, slow runtime hurts users. 证据：`.agents/skills/typescript-code-review/references/performance-tips.md`
- **TypeScript Security Checklist**（documentation）：Security considerations for TypeScript code reviews. Check these during every review. 证据：`.agents/skills/typescript-code-review/references/security-checklist.md`
- **Start**（documentation）：Orient on the current state of the mnemonic project before doing any work. 证据：`.claude/commands/start.md`
- **Design**（documentation）：Phase 5 adds a lightweight in-memory session cache src/cache.ts that eliminates redundant listNotes + listEmbeddings I/O across tool calls within a single MCP session. 证据：`.mnemonic/notes/active-session-project-cache-single-in-memory-vault-cache-pe-7463f124.md`
- **Apply Bounded Rrf Hybrid Recall Alignment 0175C033**（documentation）：Implements the endorsed one-shot plan plan-one-shot-bounded-rrf-hybrid-recall-alignment-7aa73aaa . 证据：`.mnemonic/notes/apply-bounded-rrf-hybrid-recall-alignment-0175c033.md`
- **Automatic Branch Change Detection And Sync 89F4Da23**（documentation）：Automatic branch change detection and sync now applies to cwd -aware memory operations plus migration execution, not literally every tool. 证据：`.mnemonic/notes/automatic-branch-change-detection-and-sync-89f4da23.md`
- **Bug fixed: update tool created empty commits and wasted embeddings on no-op changes**（documentation）：Bug fixed: update tool created empty commits and wasted embeddings on no-op changes 证据：`.mnemonic/notes/bug-fix-update-tool-no-op-detection-1031c864.md`
- **Priority P1 - Build and Documentation Enhancements**（documentation）：Priority P1 - Build and Documentation Enhancements 证据：`.mnemonic/notes/build-process-documentation-improvements-7cf12703.md`
- **Retrieval channels**（documentation）：Supersede fragmented RRF and hybrid-recall notes with the current implemented design and its product constraints. 证据：`.mnemonic/notes/canonical-design-bounded-rrf-hybrid-recall-172a96ab.md`
- **Centralized Mutation Guards for Multi-Vault Operations**（documentation）：Centralized Mutation Guards for Multi-Vault Operations 证据：`.mnemonic/notes/centralized-mutation-guards-for-multi-vault-operations-a35f27a2.md`
- **Changelog writing principles**（documentation）：Changelog is a curated, user-focused log of notable changes — not a raw commit log. 证据：`.mnemonic/notes/changelog-writing-principles-87cdbc5b.md`
- **Ci Create Release Checkout Fails Fetching Tag Ref Over Https 64Dbc3B8**（documentation）：The create-release job in .github/workflows/publish.yml fails when workflow dispatch is triggered targeting a tag ref e.g. v0.5.0 in the GitHub UI. 证据：`.mnemonic/notes/ci-create-release-checkout-fails-fetching-tag-ref-over-https-64dbc3b8.md`
- **Consolidated from:**（documentation）：Consolidated operational guidance for CI-safe MCP integration tests and artifact-first CI failure learning in mnemonic. 证据：`.mnemonic/notes/ci-safe-mcp-integration-and-failure-learning-workflow-91431beb.md`
- 其余 20 条证据见 `AI_CONTEXT_PACK.json` 或 `EVIDENCE_INDEX.json`。

## 宿主 AI 必须遵守的规则

- **把本资产当作开工前上下文，而不是运行环境。**：AI Context Pack 只包含证据化项目理解，不包含目标项目的可执行状态。 证据：`README.md`, `package.json`, `.agents/skills/typescript-code-review/SKILL.md`
- **回答用户时区分可预览内容与必须安装后才能验证的内容。**：安装前体验的消费者价值来自降低误装和误判，而不是伪装成真实运行。 证据：`README.md`, `package.json`, `.agents/skills/typescript-code-review/SKILL.md`

## 用户开工前应该回答的问题

- 你准备在哪个宿主 AI 或本地环境中使用它？
- 你只是想先体验工作流，还是准备真实安装？
- 你最在意的是安装成本、输出质量、还是和现有规则的冲突？

## 验收标准

- 所有能力声明都能回指到 evidence_refs 中的文件路径。
- AI_CONTEXT_PACK.md 没有把预览包装成真实运行。
- 用户能在 3 分钟内看懂适合谁、能做什么、如何开始和风险边界。

---

## Doramagic Context Augmentation

下面内容用于强化 Repomix/AI Context Pack 主体。Human Manual 只提供阅读骨架；踩坑日志会被转成宿主 AI 必须遵守的工作约束。

## Human Manual 骨架

使用规则：这里只是项目阅读路线和显著性信号，不是事实权威。具体事实仍必须回到 repo evidence / Claim Graph。

宿主 AI 硬性规则：
- 不得把页标题、章节顺序、摘要或 importance 当作项目事实证据。
- 解释 Human Manual 骨架时，必须明确说它只是阅读路线/显著性信号。
- 能力、安装、兼容性、运行状态和风险判断必须引用 repo evidence、source path 或 Claim Graph。

- **Project Overview and System Architecture**：importance `high`
  - source_paths: README.md, ARCHITECTURE.md, src/index.ts, src/vault.ts, src/project.ts
- **MCP Tools and Memory Operations**：importance `high`
  - source_paths: src/tools/index.ts, src/tools/remember.ts, src/tools/recall.ts, src/tools/get.ts, src/tools/list.ts
- **Recall Engine, Embeddings, and Memory Intelligence**：importance `high`
  - source_paths: src/recall.ts, src/tools/recall-helpers.ts, src/embeddings.ts, src/projections.ts, src/lexical.ts
- **Operations, Deployment, and Workflows**：importance `high`
  - source_paths: skills/mnemonic-rpi-workflow/SKILL.md, src/cli/dispatch.ts, src/cli/migrate.ts, src/cli/import-claude-memory.ts, src/migration.ts

## Repo Inspection Evidence / 源码检查证据

- repo_clone_verified: true
- repo_inspection_verified: true
- repo_commit: `ecb00a843ce28cb077157ac66d26b42e38df1c26`
- inspected_files: `Dockerfile`, `README.md`, `package.json`, `src/attached-storage.ts`, `src/auto-relate.ts`, `src/branch-tracker.ts`, `src/brands.ts`, `src/cache.ts`, `src/cli/dispatch.ts`, `src/cli/import-claude-memory.ts`, `src/cli/migrate.ts`, `src/config.ts`, `src/consolidate.ts`, `src/context.ts`, `src/date-utils.ts`, `src/domain-errors.ts`, `src/embeddings.ts`, `src/error-utils.ts`, `src/git-constants.ts`, `src/git.ts`

宿主 AI 硬性规则：
- 没有 repo_clone_verified=true 时，不得声称已经读过源码。
- 没有 repo_inspection_verified=true 时，不得把 README/docs/package 文件判断写成事实。
- 没有 quick_start_verified=true 时，不得声称 Quick Start 已跑通。

## Doramagic Pitfall Constraints / 踩坑约束

这些规则来自 Doramagic 发现、验证或编译过程中的项目专属坑点。宿主 AI 必须把它们当作工作约束，而不是普通说明文字。

### Constraint 1: 失败模式：installation: Dependency Dashboard

- Trigger: Developers should check this installation risk before relying on the project: Dependency Dashboard
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: Dependency Dashboard. Context: Observed when using node, docker
- Why it matters: Developers may fail before the first successful local run: Dependency Dashboard
- Evidence: failure_mode_cluster:github_issue | https://github.com/danielmarbach/mnemonic/issues/13 | Dependency Dashboard
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 2: 失败模式：installation: v0.33.0

- Trigger: Developers should check this installation risk before relying on the project: v0.33.0
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v0.33.0. Context: Observed when using node, docker
- Why it matters: Upgrade or migration may change expected behavior: v0.33.0
- Evidence: failure_mode_cluster:github_release | https://github.com/danielmarbach/mnemonic/releases/tag/v0.33.0 | v0.33.0
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 3: 来源证据：Dependency Dashboard

- Trigger: GitHub 社区证据显示该项目存在一个安装相关的待验证问题：Dependency Dashboard
- Why it matters: 可能增加新用户试用和生产接入成本。
- Evidence: community_evidence:github | https://github.com/danielmarbach/mnemonic/issues/13 | 来源讨论提到 node 相关条件，需在安装/试用前复核。
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 4: 失败模式：configuration: v0.32.0

- Trigger: Developers should check this configuration risk before relying on the project: v0.32.0
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v0.32.0. Context: Source discussion did not expose a precise runtime context.
- Why it matters: Upgrade or migration may change expected behavior: v0.32.0
- Evidence: failure_mode_cluster:github_release | https://github.com/danielmarbach/mnemonic/releases/tag/v0.32.0 | v0.32.0
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 5: 能力判断依赖假设

- Trigger: README/documentation is current enough for a first validation pass.
- Host AI rule: 将假设转成下游验证清单。
- Why it matters: 假设不成立时，用户拿不到承诺的能力。
- Evidence: capability.assumptions | https://github.com/danielmarbach/mnemonic | README/documentation is current enough for a first validation pass.
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 6: 运行可能依赖外部服务

- Trigger: 项目说明出现 external service/cloud/webhook/database 等运行依赖关键词。
- Host AI rule: 确认是否有离线 demo、mock 数据或可替代服务。
- Why it matters: 本地安装成功不等于能力可用，外部服务不可用会阻断体验。
- Evidence: packet_text.keyword_scan | https://github.com/danielmarbach/mnemonic | matched external service / cloud / webhook / database keyword
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 7: 维护活跃度未知

- Trigger: 未记录 last_activity_observed。
- Host AI rule: 补 GitHub 最近 commit、release、issue/PR 响应信号。
- Why it matters: 新项目、停更项目和活跃项目会被混在一起，推荐信任度下降。
- Evidence: evidence.maintainer_signals | https://github.com/danielmarbach/mnemonic | last_activity_observed missing
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

- Trigger: no_demo
- Evidence: downstream_validation.risk_items | https://github.com/danielmarbach/mnemonic | no_demo; severity=medium
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 9: 存在评分风险

- Trigger: no_demo
- Why it matters: 风险会影响是否适合普通用户安装。
- Evidence: risks.scoring_risks | https://github.com/danielmarbach/mnemonic | no_demo; severity=medium
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 10: 失败模式：performance: v0.30.1

- Trigger: Developers should check this performance risk before relying on the project: v0.30.1
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v0.30.1. Context: Source discussion did not expose a precise runtime context.
- Why it matters: Upgrade or migration may change expected behavior: v0.30.1
- Evidence: failure_mode_cluster:github_release | https://github.com/danielmarbach/mnemonic/releases/tag/v0.30.1 | v0.30.1
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。