349 lines
11 KiB
JavaScript
349 lines
11 KiB
JavaScript
const http = require("http");
|
|
const https = require("https");
|
|
|
|
const SYSTEM_PROMPT = `你是一个场景信息提取助手。根据场景目录的内容，提取 scene-id 和 scene-name。
|
|
|
|
scene-id 规则：
|
|
- 使用英文短横线连接，如 tq-lineloss-report
|
|
- 全小写，有业务含义
|
|
|
|
scene-name 规则：
|
|
- 使用中文，简短描述性名称
|
|
- 如 "台区线损报表"、"知乎热榜导出"
|
|
|
|
请以 JSON 格式返回：{"sceneId": "...", "sceneName": "..."}`;
|
|
|
|
const DEEP_SYSTEM_PROMPT = `你是一个场景代码分析专家。分析场景源码，提取关键业务信息。
|
|
|
|
## 分析目标
|
|
|
|
1. **多模式识别** (关键):
|
|
- 查找条件分支逻辑 (if/switch) 中基于 period_mode、reportType 等字段的分支
|
|
- 识别不同分支对应的 API 端点、列定义、请求格式
|
|
- 如果发现多模式，使用 modes 数组格式输出
|
|
|
|
2. **API 端点**: 识别所有 HTTP 请求地址 (URL, method, contentType, 用途)
|
|
- 从 \$.ajax/fetch 调用中提取 contentType
|
|
- 检测请求格式: application/json 或 application/x-www-form-urlencoded
|
|
|
|
3. **请求模板**: 识别请求参数结构
|
|
- 提取硬编码的分页参数 (rows, page, sidx, sord)
|
|
- 识别模板变量如 \${args.org_code}
|
|
|
|
4. **数据归一化**: 识别数据处理规则
|
|
- 查找数据渲染/表格填充逻辑
|
|
- 检测数据验证条件 (哪些字段不能为空)
|
|
|
|
5. **响应路径**: 识别数据在响应中的位置
|
|
- 如 response.content 或 response.data
|
|
|
|
## 输出格式
|
|
|
|
### 单模式场景 (无 modes 数组):
|
|
{
|
|
"sceneId": "string",
|
|
"sceneName": "string",
|
|
"sceneKind": "report_collection | monitoring",
|
|
"expectedDomain": "string",
|
|
"targetUrl": "string",
|
|
"apiEndpoints": [{"name": "", "url": "", "method": "POST"}],
|
|
"staticParams": {"key": "value"},
|
|
"columnDefs": [["fieldName", "中文列名"]]
|
|
}
|
|
|
|
### 多模式场景 (有 modes 数组):
|
|
{
|
|
"sceneId": "tq-lineloss-report",
|
|
"sceneName": "台区线损报表",
|
|
"sceneKind": "report_collection",
|
|
"modes": [
|
|
{
|
|
"name": "month",
|
|
"label": "月度报表",
|
|
"condition": {"field": "period_mode", "operator": "equals", "value": "month"},
|
|
"apiEndpoint": {
|
|
"name": "月度线损查询",
|
|
"url": "http://...",
|
|
"method": "POST",
|
|
"contentType": "application/x-www-form-urlencoded"
|
|
},
|
|
"columnDefs": [["ORG_NAME", "供电单位"], ...],
|
|
"requestTemplate": {"orgno": "\${args.org_code}", "rows": 1000, "page": 1},
|
|
"normalizeRules": {"type": "validate_all_columns", "filterNull": true},
|
|
"responsePath": "content"
|
|
},
|
|
{
|
|
"name": "week",
|
|
"label": "周报表",
|
|
"condition": {"field": "period_mode", "operator": "equals", "value": "week"},
|
|
"apiEndpoint": {...},
|
|
"columnDefs": [...],
|
|
...
|
|
}
|
|
],
|
|
"defaultMode": "month",
|
|
"modeSwitchField": "period_mode"
|
|
}
|
|
|
|
**重要**: 如果发现代码中有基于 period_mode 的 if/switch 分支，必须使用多模式格式输出！`;
|
|
|
|
function buildAnalyzePrompt(sourceDir, dirContents) {
|
|
const parts = [];
|
|
|
|
parts.push(`=== 目录结构 ===`);
|
|
parts.push(dirContents.tree || "(empty)");
|
|
|
|
if (dirContents["scene.toml"]) {
|
|
parts.push(`\n=== scene.toml ===`);
|
|
parts.push(dirContents["scene.toml"]);
|
|
}
|
|
|
|
if (dirContents["SKILL.toml"]) {
|
|
parts.push(`\n=== SKILL.toml ===`);
|
|
parts.push(dirContents["SKILL.toml"]);
|
|
}
|
|
|
|
if (dirContents["SKILL.md"]) {
|
|
parts.push(`\n=== SKILL.md ===`);
|
|
parts.push(dirContents["SKILL.md"]);
|
|
}
|
|
|
|
if (dirContents.scripts && Object.keys(dirContents.scripts).length > 0) {
|
|
parts.push(`\n=== 脚本文件 ===`);
|
|
for (const [name, content] of Object.entries(dirContents.scripts)) {
|
|
parts.push(`\n--- ${name} ---`);
|
|
const contentStr = typeof content === 'string' ? content : String(content || '');
|
|
parts.push(contentStr.substring(0, 2000));
|
|
}
|
|
}
|
|
|
|
return `以下是场景目录 "${sourceDir}" 的内容：\n\n${parts.join("\n")}\n\n请以 JSON 格式返回：{"sceneId": "...", "sceneName": "..."}`;
|
|
}
|
|
|
|
function buildDeepAnalyzePrompt(sourceDir, dirContents, indexHtmlContent) {
|
|
const parts = [];
|
|
|
|
parts.push(`=== 目录结构 ===`);
|
|
parts.push(dirContents.tree || "(empty)");
|
|
|
|
if (dirContents["scene.toml"]) {
|
|
parts.push(`\n=== scene.toml ===`);
|
|
parts.push(dirContents["scene.toml"]);
|
|
}
|
|
|
|
if (dirContents["SKILL.toml"]) {
|
|
parts.push(`\n=== SKILL.toml ===`);
|
|
parts.push(dirContents["SKILL.toml"]);
|
|
}
|
|
|
|
if (dirContents["SKILL.md"]) {
|
|
parts.push(`\n=== SKILL.md ===`);
|
|
parts.push(dirContents["SKILL.md"]);
|
|
}
|
|
|
|
// Include index.html content (key addition)
|
|
if (indexHtmlContent && typeof indexHtmlContent === 'string') {
|
|
parts.push(`\n=== index.html ===`);
|
|
// Limit to first 15000 chars to avoid token limits
|
|
parts.push(indexHtmlContent.substring(0, 15000));
|
|
}
|
|
|
|
if (dirContents.scripts && Object.keys(dirContents.scripts).length > 0) {
|
|
parts.push(`\n=== 脚本文件 ===`);
|
|
for (const [name, content] of Object.entries(dirContents.scripts)) {
|
|
parts.push(`\n--- ${name} ---`);
|
|
const contentStr = typeof content === 'string' ? content : String(content || '');
|
|
parts.push(contentStr.substring(0, 3000));
|
|
}
|
|
}
|
|
|
|
return `以下是场景目录 "${sourceDir}" 的内容：\n\n${parts.join("\n")}\n\n请分析以上代码，提取完整的场景信息。`;
|
|
}
|
|
|
|
function extractJsonFromResponse(text) {
|
|
const codeBlockMatch = text.match(/```(?:json)?\s*\n([\s\S]*?)\n```/);
|
|
if (codeBlockMatch) return JSON.parse(codeBlockMatch[1]);
|
|
|
|
const jsonMatch = text.match(
|
|
/\{[\s\S]*"sceneId"[\s\S]*"sceneName"[\s\S]*\}/
|
|
);
|
|
if (jsonMatch) return JSON.parse(jsonMatch[0]);
|
|
|
|
return JSON.parse(text);
|
|
}
|
|
|
|
function extractSceneInfo(text) {
|
|
// Try code block first
|
|
const codeBlockMatch = text.match(/```(?:json)?\s*\n([\s\S]*?)\n```/);
|
|
if (codeBlockMatch) {
|
|
try {
|
|
return JSON.parse(codeBlockMatch[1]);
|
|
} catch (e) {
|
|
// fall through
|
|
}
|
|
}
|
|
|
|
// Try to find JSON object with sceneId
|
|
const jsonMatch = text.match(/\{[\s\S]*"sceneId"[\s\S]*\}/);
|
|
if (jsonMatch) {
|
|
try {
|
|
return JSON.parse(jsonMatch[0]);
|
|
} catch (e) {
|
|
// fall through
|
|
}
|
|
}
|
|
|
|
// Last resort: parse entire text
|
|
try {
|
|
return JSON.parse(text);
|
|
} catch (e) {
|
|
throw new Error("Failed to extract valid SceneInfo JSON from LLM response");
|
|
}
|
|
}
|
|
|
|
function analyzeScene(sourceDir, dirContents, { apiKey, baseUrl, model }) {
|
|
const userPrompt = buildAnalyzePrompt(sourceDir, dirContents);
|
|
|
|
const requestBody = JSON.stringify({
|
|
model,
|
|
messages: [
|
|
{ role: "system", content: SYSTEM_PROMPT },
|
|
{ role: "user", content: userPrompt },
|
|
],
|
|
temperature: 0.1,
|
|
max_tokens: 256,
|
|
});
|
|
|
|
return new Promise((resolve, reject) => {
|
|
const url = new URL(baseUrl.replace(/\/v1\/?$/, "") + "/v1/chat/completions");
|
|
const options = {
|
|
hostname: url.hostname,
|
|
port: url.port || (url.protocol === "https:" ? 443 : 80),
|
|
path: url.pathname,
|
|
method: "POST",
|
|
headers: {
|
|
"Content-Type": "application/json",
|
|
Authorization: `Bearer ${apiKey}`,
|
|
"Content-Length": Buffer.byteLength(requestBody),
|
|
},
|
|
};
|
|
|
|
const req = https.request(options, (res) => {
|
|
let data = "";
|
|
res.on("data", (chunk) => (data += chunk));
|
|
res.on("end", () => {
|
|
if (res.statusCode !== 200) {
|
|
return reject(new Error(`LLM API error ${res.statusCode}: ${data}`));
|
|
}
|
|
|
|
try {
|
|
const parsed = JSON.parse(data);
|
|
const content = parsed.choices?.[0]?.message?.content;
|
|
if (!content) return reject(new Error("LLM returned empty response"));
|
|
const result = extractJsonFromResponse(content);
|
|
if (!result.sceneId || !result.sceneName) {
|
|
return reject(
|
|
new Error(`LLM response missing sceneId/sceneName: ${content}`)
|
|
);
|
|
}
|
|
resolve(result);
|
|
} catch (err) {
|
|
reject(new Error(`Failed to parse LLM response: ${err.message}`));
|
|
}
|
|
});
|
|
});
|
|
|
|
req.on("error", reject);
|
|
req.setTimeout(30000, () => {
|
|
req.destroy(new Error("LLM API request timed out"));
|
|
});
|
|
|
|
req.write(requestBody);
|
|
req.end();
|
|
});
|
|
}
|
|
|
|
function analyzeSceneDeep(sourceDir, dirContents, indexHtmlContent, { apiKey, baseUrl, model }) {
|
|
const userPrompt = buildDeepAnalyzePrompt(sourceDir, dirContents, indexHtmlContent);
|
|
|
|
const requestBody = JSON.stringify({
|
|
model,
|
|
messages: [
|
|
{ role: "system", content: DEEP_SYSTEM_PROMPT },
|
|
{ role: "user", content: userPrompt },
|
|
],
|
|
temperature: 0.1,
|
|
max_tokens: 2048, // Increased for detailed response
|
|
});
|
|
|
|
return new Promise((resolve, reject) => {
|
|
const url = new URL(baseUrl.replace(/\/v1\/?$/, "") + "/v1/chat/completions");
|
|
const options = {
|
|
hostname: url.hostname,
|
|
port: url.port || (url.protocol === "https:" ? 443 : 80),
|
|
path: url.pathname,
|
|
method: "POST",
|
|
headers: {
|
|
"Content-Type": "application/json",
|
|
Authorization: `Bearer ${apiKey}`,
|
|
"Content-Length": Buffer.byteLength(requestBody),
|
|
},
|
|
};
|
|
|
|
const httpModule = url.protocol === "https:" ? https : http;
|
|
const req = httpModule.request(options, (res) => {
|
|
let data = "";
|
|
res.on("data", (chunk) => (data += chunk));
|
|
res.on("end", () => {
|
|
if (res.statusCode !== 200) {
|
|
return reject(new Error(`LLM API error ${res.statusCode}: ${data}`));
|
|
}
|
|
|
|
try {
|
|
const parsed = JSON.parse(data);
|
|
const content = parsed.choices?.[0]?.message?.content;
|
|
if (!content) return reject(new Error("LLM returned empty response"));
|
|
const result = extractSceneInfo(content);
|
|
|
|
// Validate required fields
|
|
if (!result.sceneId || !result.sceneName) {
|
|
return reject(new Error(`LLM response missing sceneId/sceneName: ${content}`));
|
|
}
|
|
|
|
// Set defaults for optional fields
|
|
result.sceneKind = result.sceneKind || "report_collection";
|
|
result.apiEndpoints = result.apiEndpoints || [];
|
|
result.staticParams = result.staticParams || {};
|
|
result.columnDefs = result.columnDefs || [];
|
|
result.businessLogic = result.businessLogic || {};
|
|
result.modes = result.modes || [];
|
|
result.defaultMode = result.defaultMode || (result.modes.length > 0 ? result.modes[0].name : null);
|
|
result.modeSwitchField = result.modeSwitchField || "period_mode";
|
|
|
|
resolve(result);
|
|
} catch (err) {
|
|
reject(new Error(`Failed to parse LLM response: ${err.message}`));
|
|
}
|
|
});
|
|
});
|
|
|
|
req.on("error", reject);
|
|
req.setTimeout(60000, () => {
|
|
req.destroy(new Error("LLM API request timed out"));
|
|
});
|
|
|
|
req.write(requestBody);
|
|
req.end();
|
|
});
|
|
}
|
|
|
|
module.exports = {
|
|
buildAnalyzePrompt,
|
|
extractJsonFromResponse,
|
|
analyzeScene,
|
|
// New exports
|
|
buildDeepAnalyzePrompt,
|
|
extractSceneInfo,
|
|
analyzeSceneDeep,
|
|
};
|