feat(tool-search): expand dynamic group activation

This commit is contained in:
云服务部-叶林立
2026-08-28 12:05:11 +08:00
parent bf874455db
commit 2dcec0207c
15 changed files with 897 additions and 119 deletions
+94 -15
View File
@@ -334,6 +334,17 @@ export function writeCachedCatalog(cachePath: string, catalog: ToolCatalog): voi
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) ?? []);
@@ -343,24 +354,92 @@ function queryTerms(value: string): Set<string> {
return terms;
}
export function rankGroups(catalog: ToolCatalog, query: string): Array<{ group: GroupCard; score: number }> {
const querySet = queryTerms(query);
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 searchable = [
group.id,
group.title,
group.summary,
...group.useWhen,
...group.avoidWhen,
...cards.flatMap((tool) => [tool.name, tool.summary, ...tool.useWhen, ...tool.keywords]),
].join(" ");
const terms = queryTerms(searchable);
let score = 0;
for (const term of querySet) if (terms.has(term)) score += term.length > 1 ? 3 : 1;
if (group.id === query.trim().toLowerCase()) score += 100;
return { group, score };
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;
}
+41 -7
View File
@@ -1,17 +1,35 @@
import { mkdirSync, readFileSync, renameSync, writeFileSync } from "node:fs";
import {
chmodSync,
closeSync,
fsyncSync,
mkdirSync,
openSync,
readFileSync,
renameSync,
rmSync,
writeFileSync,
} from "node:fs";
import { dirname, join } from "node:path";
export type ToolSearchDefaultResult = "updated" | "unchanged" | "skipped-invalid";
export const BUNDLE_TOOL_SEARCH_DEFAULTS = {
alwaysEnabled: ["codegraph_explore", "lsp_diagnostics"],
alwaysEnabled: [
"codegraph_explore",
"lsp_diagnostics",
"ctx_execute",
"ctx_execute_file",
"ctx_batch_execute",
],
showToolSearchFooterStatus: false,
maxActiveGroups: 3,
maxActiveGroups: 5,
maxToolsPerGroup: 8,
maxDynamicTools: 20,
maxDynamicTools: 28,
groupOverrides: {},
} as const;
export const BUNDLE_TOOL_SEARCH_DEFAULTS_VERSION = 2;
export interface ToolSearchConfig {
alwaysEnabled: string[];
showToolSearchFooterStatus: boolean;
@@ -100,12 +118,28 @@ export function ensureToolSearchDefaults(agentDir: string): ToolSearchDefaultRes
toolSearch[key] = Array.isArray(value) ? [...value] : isObject(value) ? { ...value } : value;
changed = true;
}
if (existing === undefined) {
toolSearch.bundleDefaultsVersion = BUNDLE_TOOL_SEARCH_DEFAULTS_VERSION;
changed = true;
}
if (!changed) return "unchanged";
settings.toolSearch = toolSearch;
mkdirSync(dirname(targetPath), { recursive: true });
const temporaryPath = `${targetPath}.my-pi.tmp`;
writeFileSync(temporaryPath, `${JSON.stringify(settings, null, 2)}\n`, "utf8");
renameSync(temporaryPath, targetPath);
const temporaryPath = `${targetPath}.my-pi-${process.pid}-${Math.random().toString(16).slice(2)}.tmp`;
let descriptor: number | undefined;
try {
descriptor = openSync(temporaryPath, "wx", 0o600);
writeFileSync(descriptor, `${JSON.stringify(settings, null, 2)}\n`, "utf8");
fsyncSync(descriptor);
closeSync(descriptor);
descriptor = undefined;
renameSync(temporaryPath, targetPath);
chmodSync(targetPath, 0o600);
} catch (error) {
if (descriptor !== undefined) closeSync(descriptor);
rmSync(temporaryPath, { force: true });
throw error;
}
return "updated";
}
+153 -40
View File
@@ -18,6 +18,7 @@ import {
parseGeneratedCatalog,
rankGroups,
readCachedCatalog,
selectConfidentGroup,
writeCachedCatalog,
type CatalogConstraints,
type GroupCard,
@@ -32,6 +33,7 @@ import { ensureToolSearchDefaults, readToolSearchConfig } from "./config.ts";
const TOOL_SEARCH_NAME = "tool_search";
const POWERSHELL_TOOL_NAME = "powershell";
const MAX_BATCH_GROUPS = 5;
const CORE_TOOLS = ["read", "write", "edit", "bash", "grep", "find"];
type CatalogSource = "bundle" | "cache" | "fallback" | "hybrid" | "model";
@@ -102,7 +104,7 @@ function groupDescription(catalog: ToolCatalog, source: CatalogSource): string {
})
.join("\n");
return [
"Activate a complete tool group for the current task. Prefer an exact group id from this catalog; use query only when no id clearly matches.",
"Activate one or more complete tool groups for the current task. Prefer exact group ids from this catalog; use query only when no id clearly matches.",
`Catalog source: ${sourceLabel}.`,
"Available groups:",
groups || " (no hidden tool groups)",
@@ -131,6 +133,7 @@ export default function toolSearchExtension(pi: ExtensionAPI): void {
const activeGroups = new Map<string, number>();
const pinnedTools = new Set<string>();
let bundleState: BundleCatalogResult = { catalog, coveredNames: new Set(), unknownTools: [] };
let lastEviction = "none";
function constraints(): CatalogConstraints {
return {
@@ -171,12 +174,32 @@ export default function toolSearchExtension(pi: ExtensionAPI): void {
return catalog.groups.find((group) => group.id === id);
}
function dynamicToolCount(): number {
return unique([...activeGroups.keys()].flatMap((id) => groupById(id)?.tools ?? [])).length;
function dynamicToolCount(groupIds: Iterable<string> = activeGroups.keys()): number {
return unique([...groupIds].flatMap((id) => groupById(id)?.tools ?? [])).length;
}
function leastRecentlyUsedGroup(): string | undefined {
return [...activeGroups].sort((left, right) => left[1] - right[1] || left[0].localeCompare(right[0]))[0]?.[0];
function leastRecentlyUsedGroup(
groups: Map<string, number> = activeGroups,
protectedGroups: ReadonlySet<string> = new Set(),
): string | undefined {
return [...groups]
.filter(([id]) => !protectedGroups.has(id))
.sort((left, right) => left[1] - right[1] || left[0].localeCompare(right[0]))[0]?.[0];
}
function currentStatusText(): string {
const lru = [...activeGroups]
.sort((left, right) => left[1] - right[1] || left[0].localeCompare(right[0]))
.map(([id]) => id);
return [
"Tool Search status",
`Catalog: ${catalogSource}`,
`Pinned tools: ${pinnedTools.size}`,
`Dynamic groups: ${activeGroups.size}/${config.maxActiveGroups}`,
`Dynamic tools: ${dynamicToolCount()}/${config.maxDynamicTools}`,
`LRU oldest → newest: ${lru.join(" → ") || "none"}`,
`Last eviction: ${lastEviction}`,
].join("\n");
}
function applyActiveTools(): void {
@@ -189,7 +212,7 @@ export default function toolSearchExtension(pi: ExtensionAPI): void {
ctx.ui.setStatus(
"tool-search",
config.showToolSearchFooterStatus
? `${activeToolCount} / ${tools.length + 1} tools · ${activeGroups.size} / ${config.maxActiveGroups} groups`
? `${activeToolCount} / ${tools.length + pinnedTools.size + 1} tools · ${activeGroups.size} / ${config.maxActiveGroups} groups`
: undefined,
);
}
@@ -199,71 +222,147 @@ export default function toolSearchExtension(pi: ExtensionAPI): void {
name: TOOL_SEARCH_NAME,
label: "Tool Search",
description: groupDescription(catalog, catalogSource),
promptSnippet: `Activate relevant tool groups on demand; at most ${config.maxActiveGroups} dynamic groups remain active`,
promptSnippet: `Activate relevant tool groups on demand; up to ${config.maxActiveGroups} dynamic groups can remain active. Use groups for workflows that need several groups together`,
parameters: Type.Object({
group: Type.Optional(Type.String({ description: "Exact group id from the tool_search catalog" })),
groups: Type.Optional(
Type.Array(Type.String({ description: "Exact group id from the tool_search catalog" }), {
description: `Exact group ids to activate atomically (maximum ${MAX_BATCH_GROUPS})`,
minItems: 1,
maxItems: MAX_BATCH_GROUPS,
}),
),
query: Type.Optional(Type.String({ description: "Natural-language task used to rank groups when an exact id is unclear" })),
}),
async execute(_toolCallId, params, signal, _onUpdate, ctx) {
const requestedId = params.group?.trim().toLowerCase();
let selected = requestedId ? groupById(requestedId) : undefined;
const generation: CatalogGenerationResult = selected
? {}
: await ensureModelCatalog(ctx, signal);
const singleGroup = typeof params.group === "string" ? params.group.trim() : "";
const batchGroups = Array.isArray(params.groups) ? params.groups : [];
const query = typeof params.query === "string" ? params.query.trim() : "";
const hasSingle = singleGroup.length > 0;
const hasBatch = batchGroups.length > 0;
const hasQuery = query.length > 0;
const modes = Number(hasSingle) + Number(hasBatch) + Number(hasQuery);
const lines: string[] = [];
const emptyDetails = (candidates: Array<{ id: string; score: number }> = []) => ({
loadedGroup: undefined,
loadedGroups: [] as string[],
evictedGroups: [] as string[],
activeGroups: [...activeGroups.keys()],
candidates,
catalogSource,
});
if (modes !== 1) {
lines.push("Provide exactly one of group, groups, or query.");
return { content: [{ type: "text", text: lines.join("\n") }], details: emptyDetails() };
}
if (batchGroups.length > MAX_BATCH_GROUPS) {
lines.push(`groups accepts at most ${MAX_BATCH_GROUPS} group ids.`);
return { content: [{ type: "text", text: lines.join("\n") }], details: emptyDetails() };
}
const requestedIds = unique(
(hasBatch ? batchGroups : hasSingle ? [singleGroup] : [])
.map((id) => id.trim().toLowerCase())
.filter(Boolean),
);
let selectedGroups = requestedIds.map(groupById).filter((group): group is GroupCard => group !== undefined);
const needsCatalog = hasQuery || selectedGroups.length !== requestedIds.length;
const generation: CatalogGenerationResult = needsCatalog ? await ensureModelCatalog(ctx, signal) : {};
if (generation.notice) lines.push(generation.notice);
if (!selected && requestedId) selected = groupById(requestedId);
const ranked = params.query ? rankGroups(catalog, params.query).slice(0, 3) : [];
if (!selected && params.query && (ranked[0]?.score ?? 0) > 0) selected = ranked[0]?.group;
selectedGroups = requestedIds.map(groupById).filter((group): group is GroupCard => group !== undefined);
const ranked = hasQuery ? rankGroups(catalog, query).slice(0, 3) : [];
if (hasQuery) {
const selected = selectConfidentGroup(ranked, query);
if (selected) selectedGroups = [selected];
}
if (!selected) {
const missingIds = requestedIds.filter((id) => !groupById(id));
if (selectedGroups.length === 0 || missingIds.length > 0) {
const candidates = ranked.length > 0 ? ranked : catalog.groups.slice(0, 5).map((group) => ({ group, score: 0 }));
lines.push(
params.group ? `Unknown group: ${params.group}` : "No group was activated. Provide an exact group id from the catalog.",
missingIds.length > 0
? `Unknown groups: ${missingIds.join(", ")}`
: hasQuery
? "No group was activated because the query match was weak or ambiguous. Use an exact group id from the candidates."
: "No group was activated. Provide an exact group id from the catalog.",
`Candidates: ${candidates.map(({ group }) => group.id).join(", ") || "none"}`,
);
return {
content: [{ type: "text", text: lines.join("\n") }],
details: { loadedGroup: undefined, evictedGroups: [], activeGroups: [...activeGroups.keys()], candidates: candidates.map(({ group, score }) => ({ id: group.id, score })), catalogSource },
details: emptyDetails(candidates.map(({ group, score }) => ({ id: group.id, score }))),
...(generation.usage ? { usage: generation.usage } : {}),
};
}
const groupTools = unique(selected.tools);
if (groupTools.length > config.maxDynamicTools) {
lines.push(`Group ${selected.id} has ${groupTools.length} tools, exceeding maxDynamicTools=${config.maxDynamicTools}.`);
const selectedIds = selectedGroups.map((group) => group.id);
const selectedTools = unique(selectedGroups.flatMap((group) => group.tools));
if (selectedIds.length > config.maxActiveGroups || selectedTools.length > config.maxDynamicTools) {
lines.push(
`Requested workflow needs ${selectedIds.length} groups and ${selectedTools.length} tools, exceeding the configured limits of ${config.maxActiveGroups} groups and ${config.maxDynamicTools} tools.`,
);
return {
content: [{ type: "text", text: lines.join("\n") }],
details: { loadedGroup: undefined, evictedGroups: [], activeGroups: [...activeGroups.keys()], candidates: [], catalogSource },
details: emptyDetails(),
...(generation.usage ? { usage: generation.usage } : {}),
};
}
const requestedSet = new Set(selectedIds);
const nextActive = new Map(activeGroups);
for (const id of selectedIds) if (!nextActive.has(id)) nextActive.set(id, Number.MAX_SAFE_INTEGER);
const evictedGroups: string[] = [];
if (!activeGroups.has(selected.id)) {
while (
activeGroups.size >= config.maxActiveGroups ||
(activeGroups.size > 0 && dynamicToolCount() + groupTools.length > config.maxDynamicTools)
) {
const evicted = leastRecentlyUsedGroup();
if (!evicted) break;
activeGroups.delete(evicted);
evictedGroups.push(evicted);
}
const evictionReasons = new Set<string>();
while (nextActive.size > config.maxActiveGroups || dynamicToolCount(nextActive.keys()) > config.maxDynamicTools) {
if (nextActive.size > config.maxActiveGroups) evictionReasons.add(`group cap ${config.maxActiveGroups}`);
if (dynamicToolCount(nextActive.keys()) > config.maxDynamicTools) evictionReasons.add(`tool cap ${config.maxDynamicTools}`);
const evicted = leastRecentlyUsedGroup(nextActive, requestedSet);
if (!evicted) break;
nextActive.delete(evicted);
evictedGroups.push(evicted);
}
activeGroups.set(selected.id, ++clock);
applyActiveTools();
registerToolSearch();
updateStatus(ctx);
lines.push(`Loaded group: ${selected.id} (${groupTools.join(", ")})`);
const previousActive = new Map(activeGroups);
const previousClock = clock;
const previousLastEviction = lastEviction;
activeGroups.clear();
for (const [id, recency] of nextActive) activeGroups.set(id, recency);
for (const id of selectedIds) activeGroups.set(id, ++clock);
if (evictedGroups.length > 0) {
lastEviction = `${evictedGroups.join(", ")} (${[...evictionReasons].join("; ")})`;
}
try {
applyActiveTools();
registerToolSearch();
updateStatus(ctx);
} catch (error) {
activeGroups.clear();
for (const [id, recency] of previousActive) activeGroups.set(id, recency);
clock = previousClock;
lastEviction = previousLastEviction;
try {
applyActiveTools();
registerToolSearch();
updateStatus(ctx);
} catch {
// Preserve the original host activation failure while retaining rolled-back internal state.
}
throw error;
}
if (selectedGroups.length === 1) {
lines.push(`Loaded group: ${selectedGroups[0]?.id} (${selectedTools.join(", ")})`);
} else {
lines.push(`Loaded groups: ${selectedIds.join(", ")} (${selectedTools.length} unique tools)`);
}
if (evictedGroups.length > 0) lines.push(`Evicted least-recently-used: ${evictedGroups.join(", ")}`);
lines.push(`Active groups: ${[...activeGroups.keys()].join(", ")}`);
return {
content: [{ type: "text", text: lines.join("\n") }],
details: {
loadedGroup: selected.id,
loadedGroup: selectedIds.at(-1),
loadedGroups: selectedIds,
evictedGroups,
activeGroups: [...activeGroups.keys()],
candidates: ranked.map(({ group, score }) => ({ id: group.id, score })),
@@ -379,17 +478,23 @@ export default function toolSearchExtension(pi: ExtensionAPI): void {
if (catalogChanged) {
activeGroups.clear();
clock = 0;
lastEviction = "none";
attemptedGenerationHash = undefined;
installBaseCatalog(true);
}
let capacityChanged = false;
const refreshEvictions: string[] = [];
const refreshReasons = new Set<string>();
while (activeGroups.size > config.maxActiveGroups || dynamicToolCount() > config.maxDynamicTools) {
if (activeGroups.size > config.maxActiveGroups) refreshReasons.add(`group cap ${config.maxActiveGroups}`);
if (dynamicToolCount() > config.maxDynamicTools) refreshReasons.add(`tool cap ${config.maxDynamicTools}`);
const evicted = leastRecentlyUsedGroup();
if (!evicted) break;
activeGroups.delete(evicted);
capacityChanged = true;
refreshEvictions.push(evicted);
}
const capacityChanged = refreshEvictions.length > 0;
if (capacityChanged) lastEviction = `${refreshEvictions.join(", ")} (${[...refreshReasons].join("; ")}; settings refresh)`;
if (catalogChanged || policyChanged || capacityChanged) {
registerToolSearch();
applyActiveTools();
@@ -397,6 +502,13 @@ export default function toolSearchExtension(pi: ExtensionAPI): void {
updateStatus(ctx);
}
pi.registerCommand("tool-search-status", {
description: "Show Tool Search catalog, capacity, active-group LRU order, and the latest eviction reason",
handler: async (_args, ctx) => {
if (ctx.hasUI) ctx.ui.notify(currentStatusText(), "info");
},
});
pi.registerCommand("tool-search-rebuild", {
description: "Invalidate the generated tool-group catalog; rebuild lazily on the next tool_search call",
handler: async (_args, ctx) => {
@@ -407,6 +519,7 @@ export default function toolSearchExtension(pi: ExtensionAPI): void {
}
activeGroups.clear();
attemptedGenerationHash = undefined;
lastEviction = "none";
installBaseCatalog(false);
registerToolSearch();
applyActiveTools();