# agentic-swmm-workflow - 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 agentic-swmm-workflow 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

- **AI 研究者或研究型 Agent 构建者**：README 明确围绕研究、实验或论文工作流展开。 证据：`README.md` Claim：`clm_0003` supported 0.86
- **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_0004` 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：`skills/skill-author/SKILL.md`, `skills/swmm-anywhere/SKILL.md`, `skills/swmm-builder/SKILL.md`, `skills/swmm-calibration/SKILL.md` 等 Claim：`clm_0005` 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：`skills/skill-author/SKILL.md`, `skills/swmm-anywhere/SKILL.md`, `skills/swmm-builder/SKILL.md`, `skills/swmm-calibration/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`, `docs/swmm-anywhere-quickstart.md` Claim：`clm_0002` supported 0.86

## 怎么开始

- `curl -fsSL https://aiswmm.com/install.sh | bash` 证据：`README.md` Claim：`clm_0006` supported 0.86
- `npx skills add Zhonghao1995/agentic-swmm-workflow` 证据：`README.md` Claim：`clm_0007` supported 0.86
- `pip install "aiswmm[anywhere]"` 证据：`docs/swmm-anywhere-quickstart.md` Claim：`clm_0008` 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：AI 研究者或研究型 Agent 构建者**（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：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_0004` 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：`skills/skill-author/SKILL.md`, `skills/swmm-anywhere/SKILL.md`, `skills/swmm-builder/SKILL.md`, `skills/swmm-calibration/SKILL.md` 等 Claim：`clm_0005` 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：`skills/skill-author/SKILL.md`, `skills/swmm-anywhere/SKILL.md`, `skills/swmm-builder/SKILL.md`, `skills/swmm-calibration/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`, `docs/swmm-anywhere-quickstart.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_0006` 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：`skills/skill-author/SKILL.md`, `skills/swmm-anywhere/SKILL.md`, `skills/swmm-builder/SKILL.md`, `skills/swmm-calibration/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`, `docs/swmm-anywhere-quickstart.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：`skills/skill-author/SKILL.md`, `skills/swmm-anywhere/SKILL.md`, `skills/swmm-builder/SKILL.md`, `skills/swmm-calibration/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`, `docs/swmm-anywhere-quickstart.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_0009` 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`, `docs/swmm-anywhere-quickstart.md` Claim：`clm_0010` supported 0.86
- **源文档冲突：skill_count**：项目文档中存在数量表述不一致，AI Context Pack 必须提示用户不要把单一数字当作已验证事实。 处理方式：在 Human Manual 和 AI Context Pack 中共同标记为待核实，而不是强行选择一个数字。 证据：`docs/agent-nl-swmm-evidence-20260514.md`, `docs/agent-nl-swmm-gpt55-evidence-20260515.md`, `CHANGELOG.md` Claim：`clm_0011` supported 0.86, `clm_0012` contradicted 0.20
- **源文件冲突 skill_count**：发现多个值 `14, 18`，应在真实使用前核实。
- **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：`skills/skill-author/SKILL.md`, `skills/swmm-anywhere/SKILL.md`, `skills/swmm-builder/SKILL.md`, `skills/swmm-calibration/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`, `docs/swmm-anywhere-quickstart.md` Claim：`clm_0002` supported 0.86

### 上下文规模

- 文件总数：510
- 重要文件覆盖：40/510
- 证据索引条目：80
- 角色 / Skill 条目：18

### 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 agentic-swmm-workflow 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 agentic-swmm-workflow 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 agentic-swmm-workflow 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 18 个角色 / Skill / 项目文档条目。

- **skill-author**（skill）：Draft a well-formed new skill a SKILL.md scaffold, optionally with scripts/references from a described recurring need, for human review and approval. Use whenever a repeated workflow gap has no existing skill covering it, when someone wants to propose or create a new skill or capability, or when an agentic system detects a recurring problem that warrants a brand-new skill rather than editing an existing one. Domain-… 激活提示：当用户任务与“skill-author”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/skill-author/SKILL.md`
- **swmm-anywhere**（skill）：Synthesize a plausible SWMM drainage network from public data OSM streets + DEM when NO real pipe-network data exists — input is just a bbox. Use ONLY when the user has no pipe shapefile/CAD/GIS data, or to establish a baseline before real data arrives; if real pipe data exists, route to swmm-network or swmm-gis instead. 激活提示：当用户任务与“swmm-anywhere”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/swmm-anywhere/SKILL.md`
- **swmm-builder**（skill）：Assemble a runnable SWMM INP deterministically from subcatchment geometry/attributes, merged parameter JSON, network JSON, and climate references. Use when creating auditable INP + manifest artifacts for downstream swmm-runner/calibration. 激活提示：当用户任务与“swmm-builder”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/swmm-builder/SKILL.md`
- **swmm-calibration**（skill）：Calibration and validation scaffold for EPA SWMM. Use when an agent needs to 1 compare simulated vs observed flow, 2 evaluate candidate parameter sets, 3 rank explicit candidates by an objective, 4 run a bounded random / LHS / adaptive search for the best-fitting parameters, 5 run a publication-grade SCE-UA calibration with KGE as the primary objective and r, alpha, beta decomposition reported, or 6 run a DREAM-ZS B… 激活提示：当用户任务与“swmm-calibration”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/swmm-calibration/SKILL.md`
- **swmm-climate**（skill）：Deterministic rainfall/climate formatting for SWMM. Use when converting timestamped rainfall CSV files into SWMM-ready TIMESERIES lines and RAINGAGES helper snippets for swmm-builder. 激活提示：当用户任务与“swmm-climate”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/swmm-climate/SKILL.md`
- **swmm-design-review**（skill）： 激活提示：当用户任务与“swmm-design-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：`skills/swmm-design-review/SKILL.md`
- **swmm-end-to-end**（skill）：Top-level orchestration skill for agentic SWMM modelling. Use when an agent needs one entrypoint that decides which module tools to run, in what order, and when to stop, for example to build, run, QA, and optionally calibrate a SWMM case from prepared or partially prepared inputs. 激活提示：当用户任务与“swmm-end-to-end”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/swmm-end-to-end/SKILL.md`
- **swmm-experiment-audit**（skill）：Consolidate Agentic SWMM run artifacts into auditable provenance, comparison records, and local Obsidian audit notes. Use after any SWMM build/run/QA attempt, successful or failed, when an agent or CLI workflow needs a traceable record of inputs, commands, artifacts, metrics, QA checks, run-to-run differences, and first-user-friendly Obsidian visualization. 激活提示：当用户任务与“swmm-experiment-audit”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/swmm-experiment-audit/SKILL.md`
- **swmm-gis**（skill）：GIS/DEM preprocessing for SWMM experiments using the user's own QGIS/GRASS layers. Use when the user asks to 1 delineate subcatchments through QGIS/GRASS standard or entropy-guided , 2 preprocess QGIS-derived subcatchment polygons into builder-ready CSV, 3 identify high-entropy hotspot subcatchments, or 4 expose QGIS/GRASS-backed preprocessing as MCP tools for reproducible workflows. For bbox-only inputs WITHOUT rea… 激活提示：当用户任务与“swmm-gis”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/swmm-gis/SKILL.md`
- **swmm-modeling-memory**（skill）：Read historical Agentic SWMM experiment audit artifacts and summarize repeated assumptions, QA issues, failures, missing evidence, run-to-run differences, lessons learned, and controlled skill update proposals. Use downstream of swmm-experiment-audit when multiple audited runs exist or when a user asks for modeling memory, failure-pattern extraction, lessons learned, or human-reviewed skill refinement proposals. 激活提示：当用户任务与“swmm-modeling-memory”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/swmm-modeling-memory/SKILL.md`
- **swmm-network**（skill）：Build, validate, and route SWMM pipe-network models for urban drainage from raw municipal shapefiles or structured GIS/CAD exports. Use when handling junctions, conduits, outfalls, xsections, network field-mapping configs, or wiring subcatchments to upstream nodes. Requires real pipe data as SHP / GeoJSON / CSV — native CAD DXF/DWG is not parsed and must first be exported to one of these. For data-scarce areas where… 激活提示：当用户任务与“swmm-network”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/swmm-network/SKILL.md`
- **swmm-params**（skill）：Deterministic mapping from land use and soil texture to SWMM runoff/subarea and Green-Ampt infiltration parameters. Use when generating first-pass subcatchment parameter tables for swmm-builder. 激活提示：当用户任务与“swmm-params”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/swmm-params/SKILL.md`
- **swmm-plot**（skill）：Publication-grade plotting for SWMM rainfall–runoff time-series figures. Use when an agent needs to produce a paired rainfall top, inverted + node flow bottom figure from a SWMM .inp + .out, with strict style rules SI units, Arial, ticks inward, no title , optionally cropped to an event window or focus day. 激活提示：当用户任务与“swmm-plot”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/swmm-plot/SKILL.md`
- **swmm-rag-memory**（skill）：Retrieve relevant Agentic SWMM modeling memory from audited runs, modeling-memory summaries, and Obsidian-compatible notes at query time. Use when a user asks for RAG, similar past runs, evidence-linked memory retrieval, historical QA/failure patterns, or memory-grounded answers. 激活提示：当用户任务与“swmm-rag-memory”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/swmm-rag-memory/SKILL.md`
- **swmm-report**（skill）： 激活提示：当用户任务与“swmm-report”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/swmm-report/SKILL.md`
- **swmm-runner**（skill）：Run EPA SWMM swmm5 simulations reproducibly and extract key metrics from the report file. Use when an agent needs to 1 run a .inp via swmm5 CLI, 2 generate a run directory with rpt/out + manifest, 3 extract peak flow/time for a node/outfall, 4 parse SWMM continuity Runoff Quantity / Flow Routing errors from .rpt, or 5 compare two .rpt files e.g. GUI vs CLI for equivalence. 激活提示：当用户任务与“swmm-runner”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/swmm-runner/SKILL.md`
- **swmm-uncertainty**（skill）：Parameter and forcing uncertainty propagation and sensitivity analysis for EPA SWMM. Use when an agent needs to 1 propagate parameter uncertainty through SWMM fuzzy alpha-cut or Monte Carlo , 2 quantify hydrograph envelopes or output entropy without treating the run as calibration, 3 screen which parameters matter using OAT / Morris elementary-effects / Sobol' indices, 4 generate a rainfall ensemble observed-series… 激活提示：当用户任务与“swmm-uncertainty”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/swmm-uncertainty/SKILL.md`
- **swmm-water-quality**（skill）： 激活提示：当用户任务与“swmm-water-quality”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/swmm-water-quality/SKILL.md`

## 证据索引

- 共索引 80 条证据。

- **Saanich E2E with B7 — pipe network actually used 2026-05-13**（documentation）：Saanich E2E with B7 — pipe network actually used 2026-05-13 证据：`docs/framework-validation/saanich-b7-network-routed-20260513/README.md`
- **Saanich E2E with B8 — water finally reaches OUT1 2026-05-13**（documentation）：Saanich E2E with B8 — water finally reaches OUT1 2026-05-13 证据：`docs/framework-validation/saanich-b8-end-to-end-out1-flowing-20260513/README.md`
- **Cold-start agent validation — Saanich Cecelia Ravine 2026-05-13**（documentation）：Cold-start agent validation — Saanich Cecelia Ravine 2026-05-13 证据：`docs/framework-validation/saanich-cold-start-cecelia-20260513/README.md`
- **Saanich end-to-end with new MCP tools — 2026-05-13 lock-in**（documentation）：Saanich end-to-end with new MCP tools — 2026-05-13 lock-in 证据：`docs/framework-validation/saanich-e2e-new-tools-20260513/README.md`
- **Saanich MCP-first framework smoke — 2026-05-13 lock-in**（documentation）：Saanich MCP-first framework smoke — 2026-05-13 lock-in 证据：`docs/framework-validation/saanich-smoke-20260513/README.md`
- **Agentic SWMM Workflow**（documentation）：Pre-1.0 · stable v0.7.4 · pip install aiswmm==0.7.4 · CHANGELOG CHANGELOG.md 🚧 In active development: SWMMCanada https://github.com/Zhonghao1995/SWMMCanada , a SWMM INP generator built from Canadian open data: draw anywhere in Canada and run, with real municipal storm networks for 7 cities or synthesized everywhere else. 证据：`README.md`
- **Agentic SWMM Integrations**（documentation）：This directory contains runtime integration guidance for agent systems that use Agentic SWMM outside the direct CLI path. 证据：`integrations/README.md`
- **Local run outputs**（documentation）：runs/ is for local generated outputs. Do not commit run artifacts from this folder. 证据：`runs/README.md`
- **Agentic SWMM Website Installers**（documentation）：These files are meant to be hosted at the root of the public website: 证据：`web/README.md`
- **Agentic SWMM Public Agent Memory Layer**（documentation）：Agentic SWMM Public Agent Memory Layer 证据：`agent/memory/README.md`
- **Calibration example MVP**（documentation）：This folder contains a minimal example configuration for the public calibration scaffold. 证据：`examples/calibration/README.md`
- **Tecnopolo Prepared-Input Benchmark**（documentation）：This example is a compact external benchmark for the Agentic SWMM prepared-input workflow. It is derived from the public Zenodo Tecnopolo SWMM dataset and trimmed to January 1994 so it can be committed and rerun quickly. 证据：`examples/tecnopolo/README.md`
- **TUFLOW SWMM Module 03 Raw GeoPackage Benchmark**（documentation）：TUFLOW SWMM Module 03 Raw GeoPackage Benchmark 证据：`examples/tuflow-swmm-module03/README.md`
- **MCP Runtime Integration**（documentation）：This folder makes the Agentic SWMM module MCP servers easier to attach to Codex, Hermes, OpenClaw, or any other stdio MCP client. 证据：`integrations/mcp/README.md`
- **Skill Installation**（documentation）：Agentic SWMM ships its orchestration knowledge as repository skills under skills/ . 证据：`integrations/skills/README.md`
- **SWMM Modeling Memory Example**（documentation）：Run modeling-memory summarization after one or more run directories have been audited by swmm-experiment-audit . 证据：`skills/swmm-modeling-memory/examples/README.md`
- **City Dual-System Structured Network Benchmark**（documentation）：City Dual-System Structured Network Benchmark 证据：`skills/swmm-network/examples/city-dual-system/README.md`
- **mapping.json templates for import city network**（documentation）：mapping.json templates for import city network 证据：`skills/swmm-network/templates/README.md`
- **Skill author**（skill_instruction）：Turn a description of a recurring need into a draft skill that a human can review and approve. This skill writes proposals; it never installs, activates, or edits skills on its own — a freshly drafted skill is a proposal, not a verified capability. 证据：`skills/skill-author/SKILL.md`
- **swmm-anywhere**（skill_instruction）：Synthesize a plausible SWMM drainage network from public data OSM streets + DEM when no real pipe-network data exists. 证据：`skills/swmm-anywhere/SKILL.md`
- **SWMM Builder INP assembly layer**（skill_instruction）：Part of Agentic SWMM https://github.com/Zhonghao1995/agentic-swmm-workflow — install the project first for the executable toolchain aiswmm CLI, SWMM solver, MCP servers . 证据：`skills/swmm-builder/SKILL.md`
- **SWMM Calibration / Validation**（skill_instruction）：Part of Agentic SWMM https://github.com/Zhonghao1995/agentic-swmm-workflow — install the project first for the executable toolchain aiswmm CLI, SWMM solver, MCP servers . 证据：`skills/swmm-calibration/SKILL.md`
- **SWMM Climate MVP rainfall layer**（skill_instruction）：Part of Agentic SWMM https://github.com/Zhonghao1995/agentic-swmm-workflow — install the project first for the executable toolchain aiswmm CLI, SWMM solver, MCP servers . 证据：`skills/swmm-climate/SKILL.md`
- **swmm-design-review — Design Review / Code-Compliance Checker**（skill_instruction）：swmm-design-review — Design Review / Code-Compliance Checker 证据：`skills/swmm-design-review/SKILL.md`
- **SWMM End-to-End Orchestration**（skill_instruction）：Part of Agentic SWMM https://github.com/Zhonghao1995/agentic-swmm-workflow — install the project first for the executable toolchain aiswmm CLI, SWMM solver, MCP servers . 证据：`skills/swmm-end-to-end/SKILL.md`
- **SWMM Experiment Audit**（skill_instruction）：Part of Agentic SWMM https://github.com/Zhonghao1995/agentic-swmm-workflow — install the project first for the executable toolchain aiswmm CLI, SWMM solver, MCP servers . 证据：`skills/swmm-experiment-audit/SKILL.md`
- **SWMM GIS / Preprocess**（skill_instruction）：Part of Agentic SWMM https://github.com/Zhonghao1995/agentic-swmm-workflow — install the project first for the executable toolchain aiswmm CLI, SWMM solver, MCP servers . 证据：`skills/swmm-gis/SKILL.md`
- **SWMM Modeling Memory**（skill_instruction）：Part of Agentic SWMM https://github.com/Zhonghao1995/agentic-swmm-workflow — install the project first for the executable toolchain aiswmm CLI, SWMM solver, MCP servers . 证据：`skills/swmm-modeling-memory/SKILL.md`
- **SWMM Network pipe-system layer**（skill_instruction）：Part of Agentic SWMM https://github.com/Zhonghao1995/agentic-swmm-workflow — install the project first for the executable toolchain aiswmm CLI, SWMM solver, MCP servers . 证据：`skills/swmm-network/SKILL.md`
- **SWMM Params MVP mapping layer**（skill_instruction）：Part of Agentic SWMM https://github.com/Zhonghao1995/agentic-swmm-workflow — install the project first for the executable toolchain aiswmm CLI, SWMM solver, MCP servers . 证据：`skills/swmm-params/SKILL.md`
- **SWMM Plot publication spec**（skill_instruction）：Part of Agentic SWMM https://github.com/Zhonghao1995/agentic-swmm-workflow — install the project first for the executable toolchain aiswmm CLI, SWMM solver, MCP servers . 证据：`skills/swmm-plot/SKILL.md`
- **SWMM RAG Memory**（skill_instruction）：- Query-time retrieval over Agentic SWMM audited run memory. - A lightweight keyword/tag retriever that works without embeddings or a vector database. - A local hybrid retriever that combines keyword matches, deterministic SWMM tags, metadata weighting, and hashed token/character n-gram embeddings. - RAG context packs that can be passed to Codex, OpenClaw, Hermes, or another LLM. - Source citations for each retrieved memory item, including run id, project key, source file, failure patterns, diagnostics, and matched terms. - Retrieval-grounded failure advice.{json,md} for failed or warning runs, without modifying model files. - Explicit resolution memory.json for human-reviewed and benchmark… 证据：`skills/swmm-rag-memory/SKILL.md`
- **SWMM Report Export Skill**（skill_instruction）：Assemble a reproducible, client-deliverable Word .docx report from the artifacts produced by swmm-experiment-audit and swmm-plot . The script reads only existing files; it never re-runs SWMM or modifies the run directory. 证据：`skills/swmm-report/SKILL.md`
- **SWMM Runner CLI-first**（skill_instruction）：Part of Agentic SWMM https://github.com/Zhonghao1995/agentic-swmm-workflow — install the project first for the executable toolchain aiswmm CLI, SWMM solver, MCP servers . 证据：`skills/swmm-runner/SKILL.md`
- **SWMM Uncertainty**（skill_instruction）：Part of Agentic SWMM https://github.com/Zhonghao1995/agentic-swmm-workflow — install the project first for the executable toolchain aiswmm CLI, SWMM solver, MCP servers . 证据：`skills/swmm-uncertainty/SKILL.md`
- **SWMM Water Quality Skill**（skill_instruction）：Complete SWMM engine coverage for pollutant buildup/washoff simulation and load reporting. This skill provides: 证据：`skills/swmm-water-quality/SKILL.md`
- **Modeling Memory and Controlled Skill Evolution**（documentation）：Modeling Memory and Controlled Skill Evolution 证据：`docs/modeling-memory-and-skill-evolution.md`
- **Repository Map**（documentation）：This repository is the Agentic SWMM workflow layer: a compact set of skills, scripts, examples, benchmarks, audit records, and modeling-memory artifacts for reproducible SWMM work. 证据：`docs/repo-map.md`
- **Package**（package_manifest）：{ "name": "swmm-builder-mcp", "version": "0.1.0", "type": "module", "main": "server.js", "scripts": { "start": "node server.js" }, "dependencies": { "@modelcontextprotocol/sdk": "^1.27.1", "zod": "^4.3.6" } } 证据：`mcp/swmm-builder/package.json`
- **Package**（package_manifest）：{ "name": "swmm-calibration-mcp", "version": "0.1.0", "private": true, "type": "module", "dependencies": { "@modelcontextprotocol/sdk": "^1.17.5", "zod": "^3.24.1" }, "scripts": { "start": "node server.js" } } 证据：`mcp/swmm-calibration/package.json`
- **Package**（package_manifest）：{ "name": "swmm-climate-mcp", "version": "0.1.0", "type": "module", "main": "server.js", "scripts": { "start": "node server.js" }, "dependencies": { "@modelcontextprotocol/sdk": "^1.27.1", "zod": "^4.3.6" } } 证据：`mcp/swmm-climate/package.json`
- **Package**（package_manifest）：{ "name": "swmm-experiment-audit-mcp", "version": "0.1.0", "type": "module", "main": "server.js", "scripts": { "start": "node server.js" }, "dependencies": { "@modelcontextprotocol/sdk": "^1.27.1", "zod": "^4.3.6" } } 证据：`mcp/swmm-experiment-audit/package.json`
- **Package**（package_manifest）：{ "name": "swmm-gis-mcp", "version": "0.1.0", "type": "module", "main": "server.js", "scripts": { "start": "node server.js" }, "dependencies": { "@modelcontextprotocol/sdk": "^1.27.1", "zod": "^4.3.6" } } 证据：`mcp/swmm-gis/package.json`
- **Package**（package_manifest）：{ "name": "swmm-modeling-memory-mcp", "version": "0.1.0", "type": "module", "main": "server.js", "scripts": { "start": "node server.js" }, "dependencies": { "@modelcontextprotocol/sdk": "^1.27.1", "zod": "^4.3.6" } } 证据：`mcp/swmm-modeling-memory/package.json`
- **Package**（package_manifest）：{ "name": "swmm-network-mcp", "version": "0.1.0", "type": "module", "main": "server.js", "scripts": { "start": "node server.js" }, "dependencies": { "@modelcontextprotocol/sdk": "^1.27.1", "zod": "^4.3.6" } } 证据：`mcp/swmm-network/package.json`
- **Package**（package_manifest）：{ "name": "swmm-params-mcp", "version": "0.1.0", "type": "module", "main": "server.js", "scripts": { "start": "node server.js" }, "dependencies": { "@modelcontextprotocol/sdk": "^1.27.1", "zod": "^4.3.6" } } 证据：`mcp/swmm-params/package.json`
- **Package**（package_manifest）：{ "name": "swmm-plot-mcp", "version": "0.1.0", "type": "module", "main": "server.js", "scripts": { "start": "node server.js" }, "dependencies": { "@modelcontextprotocol/sdk": "^1.27.1", "zod": "^4.3.6" } } 证据：`mcp/swmm-plot/package.json`
- **Package**（package_manifest）：{ "name": "swmm-runner-mcp", "version": "0.1.0", "type": "module", "main": "server.js", "scripts": { "start": "node server.js" }, "dependencies": { "@modelcontextprotocol/sdk": "^1.27.1", "zod": "^4.3.6" } } 证据：`mcp/swmm-runner/package.json`
- **Package**（package_manifest）：{ "name": "swmm-uncertainty-mcp", "version": "0.1.0", "private": true, "type": "module", "dependencies": { "@modelcontextprotocol/sdk": "^1.17.5", "zod": "^3.24.1" }, "scripts": { "start": "node server.js" } } 证据：`mcp/swmm-uncertainty/package.json`
- **License**（source_file）：Copyright c 2026 Zhonghao Zhang & Caterina Valeo 证据：`LICENSE`
- **Changelog**（documentation）：All notable changes to Agentic SWMM Workflow are documented here. 证据：`CHANGELOG.md`
- **Agent NL → SWMM End-to-End Evidence 2026-05-14**（documentation）：Agent NL → SWMM End-to-End Evidence 2026-05-14 证据：`docs/agent-nl-swmm-evidence-20260514.md`
- **Agent NL - SWMM End-to-End Evidence with gpt-5.5 2026-05-15**（documentation）：Agent NL - SWMM End-to-End Evidence with gpt-5.5 2026-05-15 证据：`docs/agent-nl-swmm-gpt55-evidence-20260515.md`
- **Agentic SWMM — NL→SWMM evidence LLM-engaged path, gpt-5.5-2026-04-23**（documentation）：Agentic SWMM — NL→SWMM evidence LLM-engaged path, gpt-5.5-2026-04-23 证据：`docs/agent-nl-swmm-gpt55-llm-engaged-evidence-20260515.md`
- **NL - SWMM + Plot E2E Evidence gpt-5.5, auto-router disabled - 2026-05-15**（documentation）：NL - SWMM + Plot E2E Evidence gpt-5.5, auto-router disabled - 2026-05-15 证据：`docs/agent-nl-swmm-gpt55-plot-evidence-20260515.md`
- **Agentic Runtime UX PRD**（documentation）：The current aiswmm runtime can run prepared INP workflows, audit runs, inspect plot options, cache MCP schemas, and route common intents. Even so, the user experience still feels weak when the agent is used as an interactive modelling assistant. 证据：`docs/agentic-runtime-ux-prd.md`
- **API Key Configuration**（documentation）：Agentic SWMM plans the interactive aiswmm runtime with one of two API-key providers : openai the default; OPENAI API KEY and anthropic opt-in; ANTHROPIC API KEY . Configure the relevant key during installation or in your shell environment before starting the runtime. For how to switch providers and which models each uses, see llm providers.md llm providers.md . 证据：`docs/api-key-configuration.md`
- **Byte-identical SWMM reproducibility across environments Tecnopolo**（documentation）：Byte-identical SWMM reproducibility across environments Tecnopolo 证据：`docs/byte-identical-reproducibility.md`
- **Codex Runtime Path**（documentation）：This document explains how to use Codex as the primary local development runtime for Agentic SWMM. 证据：`docs/codex-runtime.md`
- **Experiment Audit Framework**（documentation）：This document defines the audit layer for Agentic SWMM. 证据：`docs/experiment-audit-framework.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/framework-validation/saanich-b7-network-routed-20260513/README.md`, `docs/framework-validation/saanich-b8-end-to-end-out1-flowing-20260513/README.md`, `docs/framework-validation/saanich-cold-start-cecelia-20260513/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/framework-validation/saanich-b7-network-routed-20260513/README.md`, `docs/framework-validation/saanich-b8-end-to-end-out1-flowing-20260513/README.md`, `docs/framework-validation/saanich-cold-start-cecelia-20260513/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

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。

- **项目概览与设计理念**：importance `high`
  - source_paths: README.md, CHANGELOG.md, CITATION.cff, LICENSE
- **系统总体架构与目录结构**：importance `high`
  - source_paths: agentic_swmm/__init__.py, agentic_swmm/cli.py, agentic_swmm/runtime/registry.py, agentic_swmm/config.py, docs/repo-map.md
- **核心特性与运行产物**：importance `high`
  - source_paths: README.md, agentic_swmm/agent/single_shot.py, agentic_swmm/audit/run_folder_layout.py, docs/modeling-memory-and-skill-evolution.md
- **数据流、案例与制品管理**：importance `high`
  - source_paths: agentic_swmm/case/case_registry.py, agentic_swmm/case/case_defaults.py, agentic_swmm/case/case_id.py, cases/tecnopolo/case_meta.yaml, cases/todcreek/case_meta.yaml
- **CLI、REPL 与用户界面**：importance `high`
  - source_paths: agentic_swmm/cli.py, agentic_swmm/agent/repl.py, agentic_swmm/agent/ui.py, agentic_swmm/agent/welcome.py, agentic_swmm/agent/warm_intro.py
- **MCP 服务器矩阵**：importance `high`
  - source_paths: mcp/swmm-builder/server.js, mcp/swmm-runner/server.js, mcp/swmm-calibration/server.js, mcp/swmm-network/server.js, integrations/mcp/README.md
- **Skill 层体系**：importance `high`
  - source_paths: skills/swmm-end-to-end/SKILL.md, skills/swmm-builder/SKILL.md, skills/swmm-calibration/SKILL.md, skills/swmm-climate/SKILL.md, skills/swmm-network/SKILL.md
- **LLM 提供商与 Agent 编排**：importance `high`
  - source_paths: agentic_swmm/providers/factory.py, agentic_swmm/providers/openai_api.py, agentic_swmm/providers/anthropic_api.py, agentic_swmm/agent/planner.py, agentic_swmm/agent/intent_classifier.py

## Repo Inspection Evidence / 源码检查证据

- repo_clone_verified: true
- repo_inspection_verified: true
- repo_commit: `33306a9fee7fc4c8b0a773c7cd184a247ee5c9c8`
- inspected_files: `Dockerfile`, `README.md`, `pyproject.toml`, `requirements.txt`, `docs/agent-nl-swmm-evidence-20260514.md`, `docs/agent-nl-swmm-gpt55-evidence-20260515.md`, `docs/agent-nl-swmm-gpt55-llm-engaged-evidence-20260515.md`, `docs/agent-nl-swmm-gpt55-plot-evidence-20260515.md`, `docs/agentic-runtime-ux-prd.md`, `docs/api-key-configuration.md`, `docs/byte-identical-reproducibility.md`, `docs/codex-runtime.md`, `docs/experiment-audit-framework.md`, `docs/framework-validation/BACKLOG.md`, `docs/framework-validation/saanich-b7-network-routed-20260513/README.md`, `docs/framework-validation/saanich-b7-network-routed-20260513/network.json`, `docs/framework-validation/saanich-b7-network-routed-20260513/runner_manifest.json`, `docs/framework-validation/saanich-b8-end-to-end-out1-flowing-20260513/README.md`, `docs/framework-validation/saanich-b8-end-to-end-out1-flowing-20260513/network.json`, `docs/framework-validation/saanich-b8-end-to-end-out1-flowing-20260513/runner_manifest.json`

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: 依赖 Docker 环境

- Trigger: 安装/运行入口包含 Docker 命令：docker run --rm -v "$PWD/runs:/app/runs" ghcr.io/zhonghao1995/agentic-swmm-workflow:v0.7.4 acceptance
- Host AI rule: 标注 Docker 前置条件，并提供非 Docker 路径或失败提示。
- Why it matters: 非工程用户可能没有 Docker，启动成本明显增加。
- Evidence: identity.distribution | https://github.com/Zhonghao1995/agentic-swmm-workflow | docker run --rm -v "$PWD/runs:/app/runs" ghcr.io/zhonghao1995/agentic-swmm-workflow:v0.7.4 acceptance
- 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: 可能修改宿主 AI 配置

- Trigger: 项目面向 Claude/Cursor/Codex/Gemini/OpenCode 等宿主，或安装命令涉及用户配置目录。
- Host AI rule: 列出会写入的配置文件、目录和卸载/回滚步骤。
- Why it matters: 安装可能改变本机 AI 工具行为，用户需要知道写入位置和回滚方法。
- Evidence: capability.host_targets | https://github.com/Zhonghao1995/agentic-swmm-workflow | host_targets=openclaw, mcp_host, claude_code, claude, hermes, chatgpt
- 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: 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/Zhonghao1995/agentic-swmm-workflow | 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 4: 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/Zhonghao1995/agentic-swmm-workflow | 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/Zhonghao1995/agentic-swmm-workflow | 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 6: 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/Zhonghao1995/agentic-swmm-workflow | 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 7: issue/PR 响应质量未知

- Trigger: issue_or_pr_quality=unknown。
- Host AI rule: 抽样最近 issue/PR，判断是否长期无人处理。
- Why it matters: 用户无法判断遇到问题后是否有人维护。
- Evidence: evidence.maintainer_signals | https://github.com/Zhonghao1995/agentic-swmm-workflow | issue_or_pr_quality=unknown
- 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 8: 发布节奏不明确

- Trigger: release_recency=unknown。
- Host AI rule: 确认最近 release/tag 和 README 安装命令是否一致。
- Why it matters: 安装命令和文档可能落后于代码，用户踩坑概率升高。
- Evidence: evidence.maintainer_signals | https://github.com/Zhonghao1995/agentic-swmm-workflow | release_recency=unknown
- 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。