Files

446 lines
16 KiB
TypeScript

import { createHash } from "node:crypto";
import { chmodSync, mkdirSync, readFileSync, renameSync, writeFileSync } from "node:fs";
import { dirname } from "node:path";
import type { ToolInfo } from "@earendil-works/pi-coding-agent";
export const CATALOG_VERSION = 1;
export interface ToolCard {
name: string;
summary: string;
useWhen: string[];
avoidWhen: string[];
keywords: string[];
primaryGroup: string;
}
export interface GroupCard {
id: string;
title: string;
summary: string;
useWhen: string[];
avoidWhen: string[];
tools: string[];
}
export interface ToolCatalog {
version: number;
manifestHash: string;
generatedAt: string;
generatedBy?: string;
groups: GroupCard[];
tools: ToolCard[];
}
export interface CatalogConstraints {
maxToolsPerGroup: number;
groupOverrides: Record<string, string[]>;
}
interface StoredCatalog {
version: number;
catalog: ToolCatalog;
}
function compactText(value: unknown, maxLength: number): string {
if (typeof value !== "string") return "";
return value.replace(/\s+/gu, " ").trim().slice(0, maxLength);
}
function compactStrings(value: unknown, maxItems: number, maxLength: number): string[] {
if (!Array.isArray(value)) return [];
return value
.filter((item): item is string => typeof item === "string")
.map((item) => compactText(item, maxLength))
.filter(Boolean)
.slice(0, maxItems);
}
function normalizeGroupId(value: string): string {
return value
.trim()
.toLowerCase()
.replace(/[^a-z0-9]+/gu, "-")
.replace(/^-+|-+$/gu, "")
.slice(0, 64);
}
function stableValue(value: unknown, seen = new WeakSet<object>()): unknown {
if (value === null || typeof value === "string" || typeof value === "number" || typeof value === "boolean") {
return value;
}
if (Array.isArray(value)) return value.map((item) => stableValue(item, seen));
if (typeof value !== "object") return undefined;
if (seen.has(value)) return "[Circular]";
seen.add(value);
const output: Record<string, unknown> = {};
for (const key of Object.keys(value as Record<string, unknown>).sort()) {
const child = stableValue((value as Record<string, unknown>)[key], seen);
if (child !== undefined) output[key] = child;
}
seen.delete(value);
return output;
}
export function buildManifestHash(tools: ToolInfo[], constraints: CatalogConstraints): string {
const manifest = tools
.map((tool) => ({
name: tool.name,
description: tool.description,
parameters: stableValue(tool.parameters),
promptGuidelines: tool.promptGuidelines,
sourceInfo: stableValue(tool.sourceInfo),
}))
.sort((left, right) => left.name.localeCompare(right.name));
const payload = stableValue({ manifest, constraints });
return createHash("sha256").update(JSON.stringify(payload)).digest("hex");
}
export function buildCatalogModelInput(tools: ToolInfo[]): string {
const input = tools
.map((tool) => ({
name: tool.name,
description: tool.description,
parameters: stableValue(tool.parameters),
promptGuidelines: tool.promptGuidelines,
sourceInfo: stableValue(tool.sourceInfo),
}))
.sort((left, right) => left.name.localeCompare(right.name));
return JSON.stringify(input);
}
function fallbackGroupKey(tool: ToolInfo): string {
const prefix = tool.name.includes("_") ? tool.name.split("_", 1)[0] : "";
if (prefix && prefix.length > 1) return normalizeGroupId(prefix);
const source = stableValue(tool.sourceInfo);
if (source && typeof source === "object") {
const record = source as Record<string, unknown>;
for (const key of ["package", "name", "path", "source"]) {
const candidate = record[key];
if (typeof candidate !== "string") continue;
const parts = candidate.split(/[\\/]/u);
const normalized = normalizeGroupId(parts.at(-1)?.replace(/\.[^.]+$/u, "") ?? candidate);
if (normalized) return normalized;
}
}
return "other-tools";
}
export function applyCatalogOverrides(
groups: GroupCard[],
toolCards: ToolCard[],
overrides: Record<string, string[]>,
): { groups: GroupCard[]; tools: ToolCard[] } {
const knownNames = new Set(toolCards.map((tool) => tool.name));
const overridden = new Map<string, string>();
for (const [rawId, names] of Object.entries(overrides)) {
const id = normalizeGroupId(rawId);
if (!id) continue;
for (const name of names) {
if (knownNames.has(name)) overridden.set(name, id);
}
}
if (overridden.size === 0) return { groups, tools: toolCards };
const byId = new Map<string, GroupCard>();
for (const group of groups) {
const remaining = group.tools.filter((name) => !overridden.has(name));
if (remaining.length > 0) byId.set(group.id, { ...group, tools: remaining });
}
for (const [name, id] of overridden) {
const existing = byId.get(id);
if (existing) existing.tools.push(name);
else {
byId.set(id, {
id,
title: id.replace(/-/gu, " "),
summary: `Configured tool group for ${id.replace(/-/gu, " ")}.`,
useWhen: [],
avoidWhen: [],
tools: [name],
});
}
}
const updatedTools = toolCards.map((tool) => ({
...tool,
primaryGroup: overridden.get(tool.name) ?? tool.primaryGroup,
}));
return { groups: [...byId.values()], tools: updatedTools };
}
export function createFallbackCatalog(
tools: ToolInfo[],
manifestHash: string,
constraints: CatalogConstraints,
): ToolCatalog {
const cards = tools.map<ToolCard>((tool) => ({
name: tool.name,
summary: compactText(tool.description, 240) || `Use the ${tool.name} tool.`,
useWhen: [],
avoidWhen: [],
keywords: tool.name.split(/[_-]/u).filter(Boolean),
primaryGroup: fallbackGroupKey(tool),
}));
const buckets = new Map<string, ToolCard[]>();
for (const card of cards) {
const bucket = buckets.get(card.primaryGroup) ?? [];
bucket.push(card);
buckets.set(card.primaryGroup, bucket);
}
const groups: GroupCard[] = [];
for (const [baseId, bucket] of [...buckets].sort(([left], [right]) => left.localeCompare(right))) {
for (let index = 0; index < bucket.length; index += constraints.maxToolsPerGroup) {
const chunk = bucket.slice(index, index + constraints.maxToolsPerGroup);
const suffix = index === 0 ? "" : `-${Math.floor(index / constraints.maxToolsPerGroup) + 1}`;
const id = `${baseId}${suffix}`;
for (const card of chunk) card.primaryGroup = id;
groups.push({
id,
title: id.replace(/-/gu, " "),
summary: compactText(chunk.map((tool) => tool.summary).join("; "), 280),
useWhen: [],
avoidWhen: [],
tools: chunk.map((tool) => tool.name),
});
}
}
const overridden = applyCatalogOverrides(groups, cards, constraints.groupOverrides);
return {
version: CATALOG_VERSION,
manifestHash,
generatedAt: new Date().toISOString(),
groups: overridden.groups,
tools: overridden.tools,
};
}
function parseJsonObject(text: string): unknown {
const unfenced = text.replace(/^\s*```(?:json)?\s*/iu, "").replace(/\s*```\s*$/u, "");
const start = unfenced.indexOf("{");
const end = unfenced.lastIndexOf("}");
if (start < 0 || end <= start) throw new Error("catalog response did not contain a JSON object");
return JSON.parse(unfenced.slice(start, end + 1));
}
function isRecord(value: unknown): value is Record<string, unknown> {
return value !== null && typeof value === "object" && !Array.isArray(value);
}
export function parseGeneratedCatalog(
text: string,
tools: ToolInfo[],
manifestHash: string,
constraints: CatalogConstraints,
generatedBy: string,
): ToolCatalog {
const parsed = parseJsonObject(text);
if (!isRecord(parsed) || !Array.isArray(parsed.groups) || !Array.isArray(parsed.tools)) {
throw new Error("catalog response must contain groups and tools arrays");
}
const expectedNames = new Set(tools.map((tool) => tool.name));
const cards: ToolCard[] = [];
const cardNames = new Set<string>();
for (const value of parsed.tools) {
if (!isRecord(value) || typeof value.name !== "string" || typeof value.summary !== "string" || typeof value.primaryGroup !== "string") {
throw new Error("every generated tool card needs name, summary, and primaryGroup");
}
if (!expectedNames.has(value.name) || cardNames.has(value.name)) throw new Error(`invalid or duplicate tool card: ${value.name}`);
const primaryGroup = normalizeGroupId(value.primaryGroup);
if (!primaryGroup) throw new Error(`invalid primary group for ${value.name}`);
cardNames.add(value.name);
cards.push({
name: value.name,
summary: compactText(value.summary, 240),
useWhen: compactStrings(value.useWhen, 5, 160),
avoidWhen: compactStrings(value.avoidWhen, 5, 160),
keywords: compactStrings(value.keywords, 16, 60),
primaryGroup,
});
}
if (cardNames.size !== expectedNames.size) throw new Error("generated tool cards omitted one or more tools");
const groups: GroupCard[] = [];
const groupIds = new Set<string>();
const assignedNames = new Set<string>();
for (const value of parsed.groups) {
if (!isRecord(value) || typeof value.id !== "string" || typeof value.title !== "string" || typeof value.summary !== "string" || !Array.isArray(value.tools)) {
throw new Error("every generated group needs id, title, summary, and tools");
}
const id = normalizeGroupId(value.id);
if (!id || groupIds.has(id)) throw new Error(`invalid or duplicate group: ${value.id}`);
const names = value.tools.filter((name): name is string => typeof name === "string");
if (names.length === 0 || names.length > constraints.maxToolsPerGroup) throw new Error(`group ${id} has an invalid size`);
for (const name of names) {
if (!expectedNames.has(name) || assignedNames.has(name)) throw new Error(`invalid or duplicate group assignment: ${name}`);
assignedNames.add(name);
}
groupIds.add(id);
groups.push({
id,
title: compactText(value.title, 80),
summary: compactText(value.summary, 280),
useWhen: compactStrings(value.useWhen, 5, 160),
avoidWhen: compactStrings(value.avoidWhen, 5, 160),
tools: names,
});
}
if (assignedNames.size !== expectedNames.size) throw new Error("generated groups omitted one or more tools");
for (const card of cards) {
const group = groups.find((candidate) => candidate.id === card.primaryGroup);
if (!group?.tools.includes(card.name)) throw new Error(`tool card/group mismatch for ${card.name}`);
}
const overridden = applyCatalogOverrides(groups, cards, constraints.groupOverrides);
return {
version: CATALOG_VERSION,
manifestHash,
generatedAt: new Date().toISOString(),
generatedBy,
groups: overridden.groups,
tools: overridden.tools,
};
}
export function readCachedCatalog(
cachePath: string,
tools: ToolInfo[],
manifestHash: string,
constraints: CatalogConstraints,
): ToolCatalog | undefined {
try {
const stored: unknown = JSON.parse(readFileSync(cachePath, "utf8"));
if (!isRecord(stored) || stored.version !== CATALOG_VERSION || !isRecord(stored.catalog)) return undefined;
const catalog = stored.catalog as unknown as ToolCatalog;
if (catalog.manifestHash !== manifestHash) return undefined;
return parseGeneratedCatalog(JSON.stringify(catalog), tools, manifestHash, constraints, catalog.generatedBy ?? "cached model");
} catch {
return undefined;
}
}
export function writeCachedCatalog(cachePath: string, catalog: ToolCatalog): void {
mkdirSync(dirname(cachePath), { recursive: true, mode: 0o700 });
const temporaryPath = `${cachePath}.${process.pid}.tmp`;
const stored: StoredCatalog = { version: CATALOG_VERSION, catalog };
writeFileSync(temporaryPath, `${JSON.stringify(stored, null, 2)}\n`, { encoding: "utf8", mode: 0o600 });
chmodSync(temporaryPath, 0o600);
renameSync(temporaryPath, cachePath);
}
const GROUP_QUERY_ALIASES: Record<string, string[]> = {
"context-execution": ["context mode", "run command", "test build logs", "执行命令", "运行测试", "分析日志"],
"ssh-connection": ["ssh connect", "remote server connection", "连接服务器", "远程连接"],
"ssh-remote-shell": ["ssh shell", "remote command", "remote terminal", "远程命令", "远程终端"],
"ssh-remote-files": ["ssh file", "remote read write edit", "远程文件", "远程读写"],
"ssh-remote-search": ["ssh search", "remote find grep", "远程搜索", "远程查找"],
"chrome-navigation": ["chrome browser navigation", "browser tabs pages", "浏览器导航", "网页导航"],
"chrome-interaction": ["chrome browser interaction", "click type form", "浏览器交互", "点击输入"],
"chrome-debugging": ["chrome browser debugging", "console network screenshot", "浏览器调试", "控制台网络"],
};
function queryTerms(value: string): Set<string> {
const normalized = value.toLowerCase();
const terms = new Set(normalized.match(/[\p{L}\p{N}]+/gu) ?? []);
const cjk = [...normalized].filter((character) => /[\p{Script=Han}\p{Script=Hiragana}\p{Script=Katakana}]/u.test(character));
for (const character of cjk) terms.add(character);
for (let index = 0; index + 1 < cjk.length; index += 1) terms.add(`${cjk[index]}${cjk[index + 1]}`);
return terms;
}
const GENERIC_QUERY_TERMS = new Set([
"edit",
"execute",
"fetch",
"file",
"files",
"find",
"get",
"list",
"read",
"run",
"search",
"show",
"tool",
"tools",
"web",
"write",
"列出",
"写入",
"工具",
"执行",
"搜索",
"文件",
"显示",
"查找",
"获取",
"编辑",
"网页",
"读取",
"运行",
]);
function addTermWeights(target: Map<string, number>, querySet: Set<string>, value: string, weight: number): void {
const terms = queryTerms(value);
for (const term of querySet) {
if (terms.has(term)) target.set(term, Math.max(target.get(term) ?? 0, weight));
}
}
export interface RankedGroup {
group: GroupCard;
score: number;
matchedTerms: string[];
}
export function rankGroups(catalog: ToolCatalog, query: string): RankedGroup[] {
const normalizedQuery = query.trim().toLowerCase();
const querySet = queryTerms(normalizedQuery);
return catalog.groups
.map((group) => {
const cards = catalog.tools.filter((tool) => tool.primaryGroup === group.id);
const aliases = GROUP_QUERY_ALIASES[group.id] ?? [];
const termWeights = new Map<string, number>();
addTermWeights(termWeights, querySet, group.id, 8);
addTermWeights(termWeights, querySet, group.title, 6);
addTermWeights(termWeights, querySet, group.summary, 2);
addTermWeights(termWeights, querySet, group.useWhen.join(" "), 3);
addTermWeights(termWeights, querySet, group.avoidWhen.join(" "), 1);
addTermWeights(termWeights, querySet, aliases.join(" "), 5);
for (const card of cards) {
addTermWeights(termWeights, querySet, card.name, 10);
addTermWeights(termWeights, querySet, card.summary, 2);
addTermWeights(termWeights, querySet, card.useWhen.join(" "), 3);
addTermWeights(termWeights, querySet, card.keywords.join(" "), 5);
}
let score = [...termWeights].reduce(
(total, [term, weight]) => total + (term.length > 1 ? 3 : 1) * weight,
0,
);
if (cards.some((card) => normalizedQuery === card.name.toLowerCase())) score += 800;
if (group.id === normalizedQuery) score += 1_000;
if (aliases.some((alias) => alias.toLowerCase() === normalizedQuery)) score += 500;
return { group, score, matchedTerms: [...termWeights.keys()] };
})
.sort((left, right) => right.score - left.score || left.group.id.localeCompare(right.group.id));
}
/** Avoid auto-activating a generic, weak, or ambiguous natural-language match. */
export function selectConfidentGroup(ranked: RankedGroup[], _query: string): GroupCard | undefined {
const [first, second] = ranked;
if (!first || first.score < 24) return undefined;
if (first.score >= 500) return first.group;
const informativeTerms = first.matchedTerms.filter(
(term) => term.length > 1 && !GENERIC_QUERY_TERMS.has(term),
);
if (informativeTerms.length === 0) return undefined;
if (second && first.score - second.score < 12) return undefined;
return first.group;
}