# octave-mcp - 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 octave-mcp 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：`src/octave_mcp/resources/skills/octave-compression/SKILL.md`, `src/octave_mcp/resources/skills/octave-literacy/SKILL.md`, `src/octave_mcp/resources/skills/octave-mastery/SKILL.md`, `src/octave_mcp/resources/skills/octave-mythology/SKILL.md` 等 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：`src/octave_mcp/resources/skills/octave-compression/SKILL.md`, `src/octave_mcp/resources/skills/octave-literacy/SKILL.md`, `src/octave_mcp/resources/skills/octave-mastery/SKILL.md`, `src/octave_mcp/resources/skills/octave-mythology/SKILL.md` 等 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

- `pip install octave-mcp` 证据：`README.md` Claim：`clm_0005` supported 0.86
- `git clone https://github.com/elevanaltd/octave-mcp.git` 证据：`README.md` Claim：`clm_0006` supported 0.86

## 继续前判断卡

- **当前建议**：先做权限沙盒试用
- **为什么**：项目存在安装命令、宿主配置或本地写入线索，不建议直接进入主力环境，应先在隔离环境试装。

### 30 秒判断

- **现在怎么做**：先做权限沙盒试用
- **最小安全下一步**：先跑 Prompt Preview；若仍要安装，只在隔离环境试装
- **先别相信**：工具权限边界不能在安装前相信。
- **继续会触碰**：命令执行、宿主 AI 配置、本地环境或项目文件

### 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：`src/octave_mcp/resources/skills/octave-compression/SKILL.md`, `src/octave_mcp/resources/skills/octave-literacy/SKILL.md`, `src/octave_mcp/resources/skills/octave-mastery/SKILL.md`, `src/octave_mcp/resources/skills/octave-mythology/SKILL.md` 等 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：`src/octave_mcp/resources/skills/octave-compression/SKILL.md`, `src/octave_mcp/resources/skills/octave-literacy/SKILL.md`, `src/octave_mcp/resources/skills/octave-mastery/SKILL.md`, `src/octave_mcp/resources/skills/octave-mythology/SKILL.md` 等 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

### 现在还不能相信

- **工具权限边界不能在安装前相信。**（unverified）：MCP/tool 类项目通常会触碰文件、网络、浏览器或外部 API，必须真实检查权限和日志。
- **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：`src/octave_mcp/resources/skills/octave-compression/SKILL.md`, `src/octave_mcp/resources/skills/octave-literacy/SKILL.md`, `src/octave_mcp/resources/skills/octave-mastery/SKILL.md`, `src/octave_mcp/resources/skills/octave-mythology/SKILL.md` 等
- **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。
- **安装命令是否需要网络、权限或全局写入？**（unverified）：这影响企业环境和个人环境的安装风险。 证据：`README.md`

### 继续会触碰什么

- **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：`src/octave_mcp/resources/skills/octave-compression/SKILL.md`, `src/octave_mcp/resources/skills/octave-literacy/SKILL.md`, `src/octave_mcp/resources/skills/octave-mastery/SKILL.md`, `src/octave_mcp/resources/skills/octave-mythology/SKILL.md` 等
- **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`
- **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**：用安装前交互式试用判断工作方式是否匹配，不需要授权或改环境。（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。）
- **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。
- **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。
- **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_0007` 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_0008` 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：`src/octave_mcp/resources/skills/octave-compression/SKILL.md`, `src/octave_mcp/resources/skills/octave-literacy/SKILL.md`, `src/octave_mcp/resources/skills/octave-mastery/SKILL.md`, `src/octave_mcp/resources/skills/octave-mythology/SKILL.md` 等 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：458
- 重要文件覆盖：40/458
- 证据索引条目：80
- 角色 / Skill 条目：5

### 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 octave-mcp 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 octave-mcp 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 octave-mcp 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 5 个角色 / Skill / 项目文档条目。

- **octave-compression**（skill）：Workflow for transforming prose into semantic OCTAVE structures. Covers tier selection, transformation phases, loss accounting, and decision rules. REQUIRES octave-literacy. 激活提示：当用户任务与“octave-compression”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：`src/octave_mcp/resources/skills/octave-compression/SKILL.md`
- **octave-literacy**（skill）：LLM-native structured communication format. Teaches OCTAVE syntax rules, canonical forms, and warning prevention for zero-error .oct.md authoring. 激活提示：当用户任务与“octave-literacy”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：`src/octave_mcp/resources/skills/octave-literacy/SKILL.md`
- **octave-mastery**（skill）：Advanced semantic vocabulary, holographic contracts, and structural patterns for OCTAVE. REQUIRES octave-literacy. Extends literacy with mythology, archetype annotation, v6 contracts, and anti-pattern rules. 激活提示：当用户任务与“octave-mastery”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：`src/octave_mcp/resources/skills/octave-mastery/SKILL.md`
- **octave-mythology**（skill）：Functional mythological compression for OCTAVE Olympian Common Text And Vocabulary Engine documents. Semantic shorthand for LLM audiences, not prose decoration 激活提示：当用户任务与“octave-mythology”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：`src/octave_mcp/resources/skills/octave-mythology/SKILL.md`
- **octave-ultra-mythic**（skill）：Ultra-high density compression using mythological atoms and semantic shorthand for OCTAVE Olympian Common Text And Vocabulary Engine . Preserves soul and constraints at 60% compression for identity transmission, binding protocols, and extreme token scarcity. 激活提示：当用户任务与“octave-ultra-mythic”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：`src/octave_mcp/resources/skills/octave-ultra-mythic/SKILL.md`

## 证据索引

- 共索引 80 条证据。

- **OCTAVE Guides**（documentation）：This directory contains conceptual documentation for OCTAVE Olympian Common Text And Vocabulary Engine . 证据：`docs/guides/README.md`
- **OCTAVE: Empirical Evidence**（documentation）：This document provides a summary of the empirical evidence validating the effectiveness of the OCTAVE protocol. The findings are based on systematic testing across multiple large language models LLMs , complexity tiers, and content domains. 证据：`docs/research/README.md`
- **.hestai/ -- Three-Tier Architecture**（documentation）：.hestai/ -- Three-Tier Architecture 证据：`.hestai/README.md`
- **OCTAVE MCP Server**（documentation）：! License https://img.shields.io/badge/License-Apache 2.0-blue.svg https://opensource.org/licenses/Apache-2.0 ! Python 3.11+ https://img.shields.io/badge/python-3.11+-blue.svg https://www.python.org/downloads/ ! Tests https://img.shields.io/badge/tests-3003%20passing-brightgreen.svg ! PyPI https://img.shields.io/pypi/v/octave-mcp.svg https://pypi.org/project/octave-mcp/ 证据：`README.md`
- **OCTAVE Examples**（documentation）：Examples demonstrating OCTAVE compression across different scales and domains. 证据：`examples/README.md`
- **OCTAVE Primer Test Suite**（documentation）：Test protocol to verify the micro-primer enables direct OCTAVE emission with ~96% validity. 证据：`tests/README.md`
- **OCTAVE Tools**（documentation）：Minimal utilities for OCTAVE validation and integration. 证据：`tools/README.md`
- **OCTAVE Specifications Archive**（documentation）：Historical artifacts from OCTAVE v5 specification development December 2025 . 证据：`_archive/specs/README.md`
- **OCTAVE + Repomix Integration**（documentation）：Boost AI code analysis accuracy by 10.2× with only 11.4% token overhead 证据：`examples/integrations/repomix/README.md`
- **OCTAVE Templates**（documentation）：Ready-to-use templates for OCTAVE adoption. 证据：`examples/templates/README.md`
- **OCTAVE Olympian Common Text And Vocabulary Engine Package Resources**（documentation）：OCTAVE Olympian Common Text And Vocabulary Engine Package Resources 证据：`src/octave_mcp/resources/README.md`
- **OCTAVE JSON Schema**（documentation）：This document defines a standardized schema for implementing OCTAVE as JSON, enabling developers to integrate the semantic specification into JSON-based systems while preserving core OCTAVE concepts. 证据：`src/octave_mcp/resources/specs/schemas/json/README.md`
- **Contributing to OCTAVE MCP**（documentation）：Thank you for your interest in contributing! 证据：`CONTRIBUTING.md`
- **Skill**（skill_instruction）：===OCTAVE COMPRESSION=== META: TYPE::SKILL VERSION::"3.0.0" STATUS::ACTIVE PURPOSE::"Decision rules and workflow for transforming prose into semantic OCTAVE at the correct fidelity tier" REQUIRES::octave-literacy SPEC REFERENCE::octave-data-spec.oct.md --- §1::TIER SELECTION // Choose tier BEFORE reading source. Tier drives every subsequent decision. TIERS: LOSSLESS: TARGET::"100% fidelity" PRESERVE::everything DROP::nothing USE:: critical reasoning, legal documents, safety analysis, audit trails CONSERVATIVE: TARGET::"85-90% fidelity" PRESERVE::explanatory depth DROP::redundancy LOSS::"10-15% repetition,verbose phrasing,some edge cases " USE:: research summaries, design decisions, technica… 证据：`src/octave_mcp/resources/skills/octave-compression/SKILL.md`
- **Skill**（skill_instruction）：===OCTAVE LITERACY=== META: TYPE::SKILL VERSION::"3.0.0" STATUS::ACTIVE PURPOSE::"Zero-error OCTAVE authoring — syntax rules, canonical forms, warning prevention" OCTAVE::"Olympian Common Text And Vocabulary Engine — loss accounting system for LLM communication" AUDIENCE::LLM SPEC REFERENCE::octave-core-spec.oct.md NEXT SKILLS:: octave-mastery,octave-compression --- §0::CONSUMPTION DIRECTIVE // You are writing for LLM consumption only. No prose. No narrative. Every token carries payload. // Optimize for parsing efficiency and token density. Readability is irrelevant. MYTHOLOGY::"Use as compression — zero-shot, trust it. ATHENA = 1 token replacing 15." MYTHOLOGY ANTI PATTERN::"ZEUS::executiv… 证据：`src/octave_mcp/resources/skills/octave-literacy/SKILL.md`
- **Skill**（skill_instruction）：===OCTAVE MASTERY=== META: TYPE::SKILL VERSION::"3.0.0" STATUS::ACTIVE PURPOSE::"Expert-level OCTAVE: mythology vocabulary, holographic contracts, archetype annotation, anti-patterns" REQUIRES::octave-literacy SPEC REFERENCE::octave-core-spec.oct.md --- §1::SEMANTIC PANTHEON // Compression vocabulary — zero-shot, use directly. Literal term wins when equally clear. // Use as KEY prefixes ARTEMIS::latency p99 or PATTERN DESCRIPTORS SISYPHEAN DEBT . DOMAINS: ZEUS::"Executive authority, final arbitration, strategic direction" ATHENA::"Strategic wisdom, planning, elegant solutions" APOLLO::"Analytics, insight, clarity, prediction" HERMES::"Communication, APIs, translation, messaging" HEPHAESTUS:… 证据：`src/octave_mcp/resources/skills/octave-mastery/SKILL.md`
- **Skill**（skill_instruction）：===OCTAVE MYTHOLOGY=== META: TYPE::SKILL VERSION::"1.2.1" STATUS::ACTIVE PURPOSE::"Functional mythological semantic compression for OCTAVE documents" PRINCIPLE::"Compression shorthand for LLM audiences, not ceremonial prose" EVIDENCE:: "60-70% token reduction vs natural language", "88-96% cross-model zero-shot comprehension", "+17% structural sophistication blind assessments ", "100% pattern recognition across 35 semantic elements" SOURCE::octave-mcp docs/research/mythology-evidence-synthesis.oct.md TIER::LOSSLESS 证据：`src/octave_mcp/resources/skills/octave-mythology/SKILL.md`
- **Skill**（skill_instruction）：===OCTAVE ULTRA MYTHIC=== META: TYPE::SKILL VERSION::"1.2.1" STATUS::ACTIVE PURPOSE::"Ultra-high density compression using mythological atoms for identity and knowledge preservation" REQUIRES:: octave-literacy, octave-mythology TIER::ULTRA MYTHIC SPEC REFERENCE::octave-data-spec.oct.md 证据：`src/octave_mcp/resources/skills/octave-ultra-mythic/SKILL.md`
- **License**（source_file）：Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ 证据：`LICENSE`
- **OCTAVE MCP Server - API Reference**（documentation）：Complete API reference for the OCTAVE MCP server, including MCP tools, Python modules, and CLI commands. 证据：`docs/api.md`
- **Development.Oct**（documentation）：===OCTAVE MCP DEVELOPMENT=== META: TYPE::"DEVELOPER DOC" VERSION::"1.0.0" STATUS::ACTIVE PURPOSE::"How to set up a local dev environment and run tests/quality gates" 证据：`docs/development.oct.md`
- **OCTAVE MCP Server - Configuration Guide**（documentation）：OCTAVE MCP Server - Configuration Guide 证据：`docs/mcp-configuration.md`
- **OCTAVE Quick Start Guide**（documentation）：OCTAVE is a structured notation format optimized for LLM communication and agent-to-agent data exchange. It provides predictable parsing, semantic compression, and machine validation. 证据：`docs/octave-quick-start.md`
- **OCTAVE Specification Historical Review**（documentation）：OCTAVE Specification Historical Review 证据：`docs/octave-spec-historical-review.md`
- **OCTAVE MCP Server - Usage Guide**（documentation）：This guide provides detailed examples and workflows for using the OCTAVE MCP server in production. 证据：`docs/usage.md`
- **B3 Integration Phase Report: OCTAVE MCP Server**（documentation）：B3 Integration Phase Report: OCTAVE MCP Server 证据：`_archive/docs/reports/b3-integration-report.md`
- **OCTAVE MCP Server: Configurability and Modularity Analysis**（documentation）：OCTAVE MCP Server: Configurability and Modularity Analysis 证据：`_archive/docs/reports/configurability-analysis.md`
- **OCTAVE MCP Server: Configurability Summary**（documentation）：OCTAVE MCP Server: Configurability Summary 证据：`_archive/docs/reports/configurability-summary.md`
- **Build Plan.Oct**（documentation）：===OCTAVE MCP BUILD PLAN=== META: TYPE::BUILD PLAN VERSION::"1.1.0" STATUS::APPROVED DATE::"2025-12-22" PHASE:: B1 TASK DECOMPOSITION OCTAVE VERSION::"5.1.0" TOTAL TASKS::25 证据：`_archive/docs/workflow/build-plan.oct.md`
- **ADR-001: Configurability and Modularity Architecture**（documentation）：ADR-001: Configurability and Modularity Architecture 证据：`docs/adr/adr-0001-configurability-and-modularity-architecture.md`
- **ADR-002: Schema Validation Using OCTAVE Holographic Patterns**（documentation）：ADR-002: Schema Validation Using OCTAVE Holographic Patterns 证据：`docs/adr/adr-0002-schema-validation-using-octave-holographic-patterns.md`
- **Adr 0003 Generative Holographic Contracts**（documentation）：===ADR 003 GENERATIVE HOLOGRAPHIC CONTRACTS=== META: TYPE::ARCHITECTURE DECISION VERSION::"6.0.0" STATUS::ACCEPTED DATE::"2026-01-06" 证据：`docs/adr/adr-0003-generative-holographic-contracts.md`
- **ADR-004: OCTAVE-MCP Tool Consolidation GH 51**（documentation）：ADR-004: OCTAVE-MCP Tool Consolidation GH 51 证据：`docs/adr/adr-0004-tool-consolidation-design.md`
- **ADR-005: OCTAVE v1.5 — Compiler Shift + Operator Evolution**（documentation）：ADR-005: OCTAVE v1.5 — Compiler Shift + Operator Evolution 证据：`docs/adr/adr-0005-octave-v1.5-compiler-shift-operator-evolution.md`
- **ADR-0006 G3: META Envelope Schema Admission for Audit Markers**（documentation）：ADR-0006 G3: META Envelope Schema Admission for Audit Markers 证据：`docs/adr/adr-0006-g3-meta-audit-markers.md`
- **ADR-0006 Sprint 2 Programme Addendum**（documentation）：ADR-0006 Sprint 2 Programme Addendum 证据：`docs/adr/adr-0006-sprint-2-addendum.md`
- **ADR-0006 SR1-T1: Unified Grammar Core — Design Pass**（documentation）：ADR-0006 SR1-T1: Unified Grammar Core — Design Pass 证据：`docs/adr/adr-0006-sr1-t1-grammar-core-design.md`
- **ADR-0006 SR2-T2 — AST Source-Span Coverage Audit Strategy A for GH 377**（documentation）：ADR-0006 SR2-T2 — AST Source-Span Coverage Audit Strategy A for GH 377 证据：`docs/adr/adr-0006-sr2-t2-ast-span-coverage-audit.md`
- **ADR-0006: Writer/Reader Symmetry — Killing the octave validate / octave write Asymmetry**（documentation）：ADR-0006: Writer/Reader Symmetry — Killing the octave validate / octave write Asymmetry 证据：`docs/adr/adr-0006-writer-reader-symmetry.md`
- **ADR-0283: Chassis-Profile Schema for Agent Capability Tiering**（documentation）：ADR-0283: Chassis-Profile Schema for Agent Capability Tiering 证据：`docs/adr/adr-0283-chassis-profile-capability-tiering.md`
- **Blueprint: Loss Accounting Hardening**（documentation）：Blueprint: Loss Accounting Hardening 证据：`docs/blueprints/loss-accounting-hardening.md`
- **The Cognitive Type System**（documentation）：OCTAVE agents are governed by a triadic cognitive architecture: LOGOS , ETHOS , and PATHOS . Each cognition type defines how an agent thinks -- distinct from what it does §2::OPERATIONAL BEHAVIOR or how it speaks §4::INTERACTION RULES . 证据：`docs/guides/cognitive-type-system.md`
- **OCTAVE MCP Server - Development Setup**（documentation）：OCTAVE MCP Server - Development Setup 证据：`docs/guides/development-setup.md`
- **The Mythological Compression Principle**（documentation）：The Mythological Compression Principle 证据：`docs/guides/mythological-compression.md`
- **OCTAVE Custom Instruction — Lite**（documentation）：What this is: A compression-first custom instruction for any LLM. Paste it into Claude Projects, ChatGPT Custom GPTs, or any system prompt. Ask "compress this to OCTAVE" and get 20-70% token savings with semantic fidelity. What this is NOT: The full OCTAVE specification. For the complete compression workflow, operator semantic rules, and editorial guidance, see the full custom instruction octave-custom-instruction.md . For machine-validated output, use the OCTAVE-MCP server https://github.com/elevanaltd/octave-mcp . 证据：`docs/guides/octave-custom-instruction-lite.md`
- **OCTAVE Custom Instruction Portable**（documentation）：What this is: Self-contained custom instruction for Claude Projects, ChatGPT, or any LLM system prompt. Enables OCTAVE document conversion without the MCP toolchain. What this is NOT: A production validator. For machine-validated, spec-compliant output, use the OCTAVE-MCP server https://github.com/elevanaltd/octave-mcp with octave validate and octave write tools. 证据：`docs/guides/octave-custom-instruction.md`
- **Octave Custom Instruction.Oct**（documentation）：===OCTAVE CUSTOM INSTRUCTION=== META: TYPE::LLM PROFILE VERSION::"1.0" PURPOSE::"Portable OCTAVE conversion instruction for any LLM" COMPRESSION TIER::CONSERVATIVE LOSS PROFILE::"platform notes reduced∧marketing trimmed∧output mode added" PRODUCTION VALIDATION::"For spec-compliant output use OCTAVE-MCP server github.com/elevanaltd/octave-mcp " --- // SYSTEM COMMAND: You know the OCTAVE format. Answer normally unless the user requests conversion. // Only emit OCTAVE when explicitly asked. Never OCTAVE-ify unprompted. // NOTE: META COMPRESSION TIER describes this document's compression level. User-facing default is in §11. §1::ROLE IDENTITY::"OCTAVE conversion specialist" FORMAT::"OCTAVE Olym… 证据：`docs/guides/octave-custom-instruction.oct.md`
- **Octave Expert Mcp Aware.Oct**（documentation）：===OCTAVE EXPERT=== META: TYPE::LLM PROFILE VERSION::"1.0" PURPOSE::"OCTAVE expertise layer for MCP-equipped agents" COMPRESSION TIER::CONSERVATIVE LOSS PROFILE::"syntax rules delegated to mcp∧editorial judgment preserved∧mythology as domain labels" REQUIRES::"octave-mcp server octave validate, octave write, octave eject " NARRATIVE DEPTH::CONSERVATIVE MYTH --- // OCTAVE Expert — for environments WITH the MCP toolchain. // Tools handle syntax, validation, schema enforcement. // This instruction handles judgment, compression craft, and naming. // NOTE: META COMPRESSION TIER describes this document's compression level. User-facing default is in §7. §1::ROLE IDENTITY::"OCTAVE expert with MCP t… 证据：`docs/guides/octave-expert-mcp-aware.oct.md`
- **The Philosophy of OCTAVE: Writing for Value**（documentation）：The Philosophy of OCTAVE: Writing for Value 证据：`docs/guides/octave-philosophy.md`
- **Octave Philosophy.Oct**（documentation）：===OCTAVE PHILOSOPHY=== META: TYPE::GUIDE VERSION::"1.0" PURPOSE::"Anti-patterns and quality principles for effective OCTAVE" §1::GOLDEN RULE LITMUS::"If your OCTAVE were a database schema, would it have foreign keys?" MEANING::"Flat lists provide information. Relationship networks provide understanding." MANDATE::"Show how elements connect, influence, depend" §2::SEVEN DEADLY SMELLS ISOLATED LISTS: SYMPTOM::"Array items without explicit relationships" IMPACT::"LLM knows WHAT, not HOW they connect" FIX::"Hierarchy with relationship keys ENABLES, CONFLICTS WITH " CEREMONY OVERFLOW: SYMPTOM::"Prose, metaphors, comments everywhere" IMPACT::"Signal vs Noise. LLMs extract from structure, not poe… 证据：`docs/guides/octave-philosophy.oct.md`
- **OCTAVE Asterisk Notation Validation Report**（documentation）：OCTAVE Asterisk Notation Validation Report Test Date: 2025-06-16 Test Type: Zero-Shot Comprehension of Non-Asterisked Elements Models Tested: 10 证据：`docs/research/01_comprehension_and_validation/asterisk-validation-report.md`
- **OCTAVE Evaluation Bias Report**（documentation）：Date: 2025-07-15 Context: Agent Capability Streamlining Session Phenomenon: Contradictory LLM assessments of OCTAVE format effectiveness 证据：`docs/research/01_comprehension_and_validation/octave-evaluation-bias-report.md`
- **OCTAVE Mythological Semantics Comprehension Test Results**（documentation）：OCTAVE Mythological Semantics Comprehension Test Results 证据：`docs/research/01_comprehension_and_validation/octave-mythological-semantics-comprehension-test-2025-06-19.md`
- **OCTAVE Protocol Validation Summary**（documentation）：A comprehensive review of the OCTAVE protocol implementation and empirical evidence has been conducted. Based on extensive multi-model testing, benchmarking, and structural analysis, OCTAVE delivers measurable performance benefits as an LLM-to-LLM communication protocol, with proven advantages in information density, cross-domain translation, and relationship representation. 证据：`docs/research/01_comprehension_and_validation/octave-validation-summary.md`
- **OCTAVE Protocol: Comprehensive Empirical Assessment**（documentation）：OCTAVE Protocol: Comprehensive Empirical Assessment 证据：`docs/research/02_benchmarking_and_generation/octave-benchmarking-evidence.md`
- **OCTAVE Generation Analysis**（documentation）：Document Type: Empirical Study Date: January 19, 2025 Focus: LLM capability to generate OCTAVE format responses Status: Analysis complete 证据：`docs/research/02_benchmarking_and_generation/octave-generation-analysis-2025.md`
- **OCTAVE Secretary — Definitive Conclusions**（documentation）：OCTAVE Secretary — Definitive Conclusions 证据：`docs/research/02_benchmarking_and_generation/octave-secretary-conclusions-2026-04-09.md`
- **OCTAVE Specialist Model Comparison Test**（documentation）：OCTAVE Specialist Model Comparison Test 证据：`docs/research/02_benchmarking_and_generation/octave-specialist-model-comparison-2026-04-06.md`
- **OCTAVE Specialist Model Comparison — Round 2: octave write**（documentation）：OCTAVE Specialist Model Comparison — Round 2: octave write 证据：`docs/research/02_benchmarking_and_generation/octave-specialist-octave-write-benchmark-2026-04-06.md`
- **OCTAVE Specialist Round 3 — Controlled Model Comparison**（documentation）：OCTAVE Specialist Round 3 — Controlled Model Comparison 证据：`docs/research/02_benchmarking_and_generation/octave-specialist-r3-controlled-comparison-2026-04-08.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：`docs/guides/README.md`, `docs/research/README.md`, `.hestai/README.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：`docs/guides/README.md`, `docs/research/README.md`, `.hestai/README.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

The following material strengthens the Repomix/AI Context Pack body. Human Manual is only a reading skeleton; pitfall logs become hard operating constraints for the host AI.

## Human Manual Skeleton

Usage rule: this is only a reading path and salience signal, not factual authority. Concrete facts must still come from repo evidence / Claim Graph.

Hard rules for the host AI:
- Do not treat page titles, order, summaries, or importance as project facts.
- When explaining the Human Manual skeleton, state that it is only a reading path / salience signal.
- Capability, installation, compatibility, runtime status, and risk judgments must cite repo evidence, source paths, or Claim Graph.

- **Project Introduction**：importance `high`
  - source_paths: README.md, src/octave_mcp/__init__.py, AGENTS.oct.md
- **Project File Structure**：importance `medium`
  - source_paths: CONTRIBUTING.md, src/octave_mcp, docs
- **System Architecture**：importance `high`
  - source_paths: src/octave_mcp/mcp/server.py, src/octave_mcp/mcp/http_transport.py, src/octave_mcp/integrations/llama_cpp.py, src/octave_mcp/integrations/vllm.py, src/octave_mcp/integrations/outlines.py
- **Canonical Normalization**：importance `high`
  - source_paths: src/octave_mcp/core/lexer.py, src/octave_mcp/core/parser.py, src/octave_mcp/core/emitter.py, src/octave_mcp/core/grammar/tier_normalize.py, src/octave_mcp/core/grammar/cst.py
- **Schema Validation**：importance `high`
  - source_paths: src/octave_mcp/core/validator.py, src/octave_mcp/core/schema_extractor.py, src/octave_mcp/schemas/loader.py, src/octave_mcp/schemas/builtin/meta.oct.md, src/octave_mcp/schemas/builtin/skill.oct.md
- **Compression System**：importance `high`
  - source_paths: src/octave_mcp/core/literal_zone_audit.py, src/octave_mcp/core/holographic.py, src/octave_mcp/core/sealer.py, src/octave_mcp/core/repair.py, docs/guides/mythological-compression.md
- **Grammar Compilation**：importance `medium`
  - source_paths: src/octave_mcp/core/gbnf_compiler.py, src/octave_mcp/core/grammar_compiler/gbnf.py, src/octave_mcp/mcp/compile_grammar.py, docs/grammar/octave-v1.0-grammar.ebnf
- **MCP Tools Reference**：importance `high`
  - source_paths: src/octave_mcp/mcp/validate.py, src/octave_mcp/mcp/write.py, src/octave_mcp/mcp/eject.py, src/octave_mcp/mcp/compile_grammar.py, src/octave_mcp/mcp/base_tool.py

## Repo Inspection Evidence

- repo_clone_verified: true
- repo_inspection_verified: true
- repo_commit: `a5c87b735599ad7cdf5c6bdb7ee6321ba34b30aa`
- inspected_files: `pyproject.toml`, `README.md`, `uv.lock`, `docs/octave-quick-start.md`, `docs/api.md`, `docs/octave-spec-historical-review.md`, `docs/usage.md`, `docs/development.oct.md`, `docs/mcp-configuration.md`, `docs/adr/adr-0006-writer-reader-symmetry.md`, `docs/adr/adr-0005-octave-v1.5-compiler-shift-operator-evolution.md`, `docs/adr/adr-0006-sr1-t1-grammar-core-design.md`, `docs/adr/adr-0283-chassis-profile-capability-tiering.md`, `docs/adr/adr-0001-configurability-and-modularity-architecture.md`, `docs/adr/adr-0003-generative-holographic-contracts.md`, `docs/adr/adr-0002-schema-validation-using-octave-holographic-patterns.md`, `docs/adr/adr-0006-g3-meta-audit-markers.md`, `docs/adr/adr-0004-tool-consolidation-design.md`, `docs/adr/adr-0006-sprint-2-addendum.md`, `docs/adr/adr-0006-sr2-t2-ast-span-coverage-audit.md`

Hard rules for the host AI:
- Without repo_clone_verified=true, do not claim the source code has been read.
- Without repo_inspection_verified=true, do not turn README/docs/package observations into facts.
- Without quick_start_verified=true, do not claim the Quick Start has been successfully run.

## Doramagic Pitfall Constraints

These rules come from Doramagic discovery, validation, or compilation pitfalls. The host AI must treat them as operating constraints, not general background notes.

### Constraint 1: 失败模式：security_permissions: octave_write/octave_validate: add AGENT_DEFINITION schema for .hestai-sys/library/agents/*.oc...

- Trigger: Developers should check this security_permissions risk before relying on the project: octave_write/octave_validate: add AGENT_DEFINITION schema for .hestai-sys/library/agents/*.oct.md
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: octave_write/octave_validate: add AGENT_DEFINITION schema for .hestai-sys/library/agents/*.oct.md. Context: Source discussion did not expose a precise runtime context.
- Why it matters: Developers may expose sensitive permissions or credentials: octave_write/octave_validate: add AGENT_DEFINITION schema for .hestai-sys/library/agents/*.oct.md
- Evidence: failure_mode_cluster:github_issue | fmev_22c0329bf698546f57cbd9edd620083f | https://github.com/elevanaltd/octave-mcp/issues/424 | octave_write/octave_validate: add AGENT_DEFINITION schema for .hestai-sys/library/agents/*.oct.md
- Hard boundary: do not present this pitfall as solved, verified, or safe to ignore unless later validation evidence explicitly closes it.

### Constraint 2: 失败模式：security_permissions: octave_write: add FRAME_CARD multi-envelope schema (Facet ABI per hestai-context-mcp RFC #38)

- Trigger: Developers should check this security_permissions risk before relying on the project: octave_write: add FRAME_CARD multi-envelope schema (Facet ABI per hestai-context-mcp RFC #38)
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: octave_write: add FRAME_CARD multi-envelope schema (Facet ABI per hestai-context-mcp RFC #38). Context: Source discussion did not expose a precise runtime context.
- Why it matters: Developers may expose sensitive permissions or credentials: octave_write: add FRAME_CARD multi-envelope schema (Facet ABI per hestai-context-mcp RFC #38)
- Evidence: failure_mode_cluster:github_issue | fmev_e63e5f9a96f8ad23bef9d32f6c4c13e7 | https://github.com/elevanaltd/octave-mcp/issues/420 | octave_write: add FRAME_CARD multi-envelope schema (Facet ABI per hestai-context-mcp RFC #38)
- Hard boundary: do not present this pitfall as solved, verified, or safe to ignore unless later validation evidence explicitly closes it.

### Constraint 3: 来源证据：bug: octave_write surgical edit primitives unsafe on inline-array top-level entries (APPEND + expanded modes)

- Trigger: GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：bug: octave_write surgical edit primitives unsafe on inline-array top-level entries (APPEND + expanded modes)
- Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。
- Why it matters: 可能影响升级、迁移或版本选择。
- Evidence: community_evidence:github | cevd_75dbe0c2c20b479a9afc619c467acc20 | https://github.com/elevanaltd/octave-mcp/issues/411 | 来源讨论提到 python 相关条件，需在安装/试用前复核。
- Hard boundary: do not present this pitfall as solved, verified, or safe to ignore unless later validation evidence explicitly closes it.

### Constraint 4: 来源证据：octave_validate: CRS_REVIEW §FINDINGS section uncovered → false negatives on malformed finding blocks

- Trigger: GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：octave_validate: CRS_REVIEW §FINDINGS section uncovered → false negatives on malformed finding blocks
- Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。
- Why it matters: 可能阻塞安装或首次运行。
- Evidence: community_evidence:github | cevd_744a11a12c0340e08087ea951c281000 | https://github.com/elevanaltd/octave-mcp/issues/426 | 来源类型 github_issue 暴露的待验证使用条件。
- Hard boundary: do not present this pitfall as solved, verified, or safe to ignore unless later validation evidence explicitly closes it.

### Constraint 5: 失败模式：installation: octave_validate: CRS_REVIEW §FINDINGS section uncovered → false negatives on malformed findin...

- Trigger: Developers should check this installation risk before relying on the project: octave_validate: CRS_REVIEW §FINDINGS section uncovered → false negatives on malformed finding blocks
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: octave_validate: CRS_REVIEW §FINDINGS section uncovered → false negatives on malformed finding blocks. Context: Source discussion did not expose a precise runtime context.
- Why it matters: Developers may fail before the first successful local run: octave_validate: CRS_REVIEW §FINDINGS section uncovered → false negatives on malformed finding blocks
- Evidence: failure_mode_cluster:github_issue | fmev_8ff9088f7d6c1752dffdf17a7dd320db | https://github.com/elevanaltd/octave-mcp/issues/426 | octave_validate: CRS_REVIEW §FINDINGS section uncovered → false negatives on malformed finding blocks, failure_mode_cluster:github_issue | fmev_aa61ed66e510ebfae83228fb28ae6e11 | https://github.com/elevanaltd/octave-mcp/issues/426 | octave_validate: CRS_REVIEW §FINDINGS section uncovered → false negatives on malformed finding blocks, failure_mode_cluster:github_issue | fmev_6046cbe1d9f5946d7c5f3b4a9e75cd5a | https://github.com/elevanaltd/octave-mcp/issues/426 | octave_validate: CRS_REVIEW §FINDINGS section uncovered → false negatives on malformed finding blocks, failure_mode_cluster:github_issue | fmev_6450b53644007e96c1fa966585fe47ea | https://github.com/elevanaltd/octave-mcp/issues/426 | octave_validate: CRS_REVIEW §FINDINGS section uncovered → false negatives on malformed finding blocks
- Hard boundary: do not present this pitfall as solved, verified, or safe to ignore unless later validation evidence explicitly closes it.

### Constraint 6: 失败模式：installation: octave_write/octave_validate: add DECISION_LOG schema for DECISIONS_OCTAVE_v20260417 type doc...

- Trigger: Developers should check this installation risk before relying on the project: octave_write/octave_validate: add DECISION_LOG schema for DECISIONS_OCTAVE_v20260417 type documents
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: octave_write/octave_validate: add DECISION_LOG schema for DECISIONS_OCTAVE_v20260417 type documents. Context: Source discussion did not expose a precise runtime context.
- Why it matters: Developers may fail before the first successful local run: octave_write/octave_validate: add DECISION_LOG schema for DECISIONS_OCTAVE_v20260417 type documents
- Evidence: failure_mode_cluster:github_issue | fmev_9d395f7455d912516430481376e952e2 | https://github.com/elevanaltd/octave-mcp/issues/425 | octave_write/octave_validate: add DECISION_LOG schema for DECISIONS_OCTAVE_v20260417 type documents
- Hard boundary: do not present this pitfall as solved, verified, or safe to ignore unless later validation evidence explicitly closes it.

### Constraint 7: 来源证据：bug: _find_target_start backslash-run quote-escape mishandling (sibling of cubic P1 on PR #431)

- 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：bug: _find_target_start backslash-run quote-escape mishandling (sibling of cubic P1 on PR #431)
- Host AI rule: 来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。
- Why it matters: 可能增加新用户试用和生产接入成本。
- Evidence: community_evidence:github | cevd_8284755b0fa74799b1f881f624677141 | https://github.com/elevanaltd/octave-mcp/issues/432 | 来源类型 github_issue 暴露的待验证使用条件。
- Hard boundary: do not present this pitfall as solved, verified, or safe to ignore unless later validation evidence explicitly closes it.

### Constraint 8: 失败模式：configuration: RFC v1.14: wire #191 META schema compilation into pre-parse pipeline (Shape G — self-describi...

- Trigger: Developers should check this configuration risk before relying on the project: RFC v1.14: wire #191 META schema compilation into pre-parse pipeline (Shape G — self-describing operator sovereignty)
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: RFC v1.14: wire #191 META schema compilation into pre-parse pipeline (Shape G — self-describing operator sovereignty). Context: Observed when using python
- Why it matters: Developers may misconfigure credentials, environment, or host setup: RFC v1.14: wire #191 META schema compilation into pre-parse pipeline (Shape G — self-describing operator sovereignty)
- Evidence: failure_mode_cluster:github_issue | fmev_c368f015439226dbb8b9c45fddf3158d | https://github.com/elevanaltd/octave-mcp/issues/430 | RFC v1.14: wire #191 META schema compilation into pre-parse pipeline (Shape G — self-describing operator sovereignty)
- Hard boundary: do not present this pitfall as solved, verified, or safe to ignore unless later validation evidence explicitly closes it.

### Constraint 9: 失败模式：configuration: bug: emitter normalises backslash counts in string literals (round-trip byte-loss)

- Trigger: Developers should check this configuration risk before relying on the project: bug: emitter normalises backslash counts in string literals (round-trip byte-loss)
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: bug: emitter normalises backslash counts in string literals (round-trip byte-loss). Context: Source discussion did not expose a precise runtime context.
- Why it matters: Developers may misconfigure credentials, environment, or host setup: bug: emitter normalises backslash counts in string literals (round-trip byte-loss)
- Evidence: failure_mode_cluster:github_issue | fmev_bbc57f3d1a93f9e5fb48332874044f35 | https://github.com/elevanaltd/octave-mcp/issues/434 | bug: emitter normalises backslash counts in string literals (round-trip byte-loss)
- Hard boundary: do not present this pitfall as solved, verified, or safe to ignore unless later validation evidence explicitly closes it.

### Constraint 10: 失败模式：configuration: bug: lexer requires ∧ constraint chain for AST-level holographic recognition (target-only pat...

- Trigger: Developers should check this configuration risk before relying on the project: bug: lexer requires ∧ constraint chain for AST-level holographic recognition (target-only patterns parse as ListValue)
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: bug: lexer requires ∧ constraint chain for AST-level holographic recognition (target-only patterns parse as ListValue). Context: Source discussion did not expose a precise runtime context.
- Why it matters: Developers may misconfigure credentials, environment, or host setup: bug: lexer requires ∧ constraint chain for AST-level holographic recognition (target-only patterns parse as ListValue)
- Evidence: failure_mode_cluster:github_issue | fmev_cf23dec47765d23b75fcd69bef5c1332 | https://github.com/elevanaltd/octave-mcp/issues/433 | bug: lexer requires ∧ constraint chain for AST-level holographic recognition (target-only patterns parse as ListValue)
- Hard boundary: do not present this pitfall as solved, verified, or safe to ignore unless later validation evidence explicitly closes it.