Files
shockbot/mcp/shared.ts
T
David Blass cfd38d82fc refactor delegation system, add PR summary comments, and improve code quality (#334)
* refactor delegation system and add PR summary comments

Delegation system:
- replace mode-based delegation with select_mode → delegate two-step flow
- orchestrator crafts self-contained subagent prompts (clean context — no system/repo/event instructions leak)
- add role-based tool filtering via FastMCP authenticate hook (?role=subagent hides orchestrator-only tools)
- add select_mode tool for orchestrator guidance per mode
- add ask_question tool for lightweight research subagents
- extract shared subagent lifecycle into subagent.ts (create, complete, stdout, instructions)
- route set_output to per-subagent state when activeSubagentId is set
- track per-subagent state (SubagentState Map) replacing boolean delegationActive flag
- capture and aggregate AgentUsage across all agents (claude, codex, gemini, opencode)
- write usage summary table to GitHub job summary
- block built-in subagent spawning (Task for Claude, Task(*) for Cursor)
- increase activity timeout from 60s to 300s (subagent thinking phases)
- fix gh CLI misguidance in system prompt — explicitly forbid usage

PR summary comments:
- add prSummaryComment trigger (DB schema + migrations + Zod + UI toggle)
- dispatch mini-effort summary job alongside PR review on pr.created
- add update_pull_request_body MCP tool
- add defaultEffort option to webhook dispatch

Hardening:
- rewrite delegate/selectMode tests with simulated state management
- add toolFiltering.test.ts for role extraction, canAccess, set_output routing
- remove non-null assertions for PULLFROG_TEMP_DIR (proper error throws)
- use fetchWithRetry for direct tarball downloads
- DRY fix for rate limit check in test runner

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix: add type keyword to Effort import in handleWebhook.ts

Co-authored-by: Cursor <cursoragent@cursor.com>

* clean up delegation system, improve code quality across the codebase

- simplify delegate tool to instructions + effort params with subagent lifecycle in subagent.ts
- add select_mode and ask_question orchestrator-only tools with canAccess filtering
- replace delegate.test.ts/selectMode.test.ts with toolFiltering.test.ts (live MCP integration)
- add set_output routing for subagent context and AgentUsage tracking across all agents
- add PR summary comment trigger (schema, UI, webhook dispatch with silent flag)
- add update_pull_request_body MCP tool
- fix changed-agents.sh to always include claude canary for non-agent action changes
- fix cursor pagination bug in getSelectedInstallationReposPage
- remove destructuring patterns, inline type definitions, and unsafe type casts
- replace non-null assertions with explicit checks in install.ts
- convert multi-param functions to single param objects (postCleanup, runActionLocal, etc.)
- use isHttpError helper in API routes instead of catch-any patterns
- add adhoc test fixtures for delegation scenarios (context isolation, error handling, synthesis, etc.)

Co-authored-by: Cursor <cursoragent@cursor.com>

* no subagent mutation, one mcp per subagent

* address review feedback: parallel-safe usage tracking, subagent isolation, minor improvements

* fix subagent state isolation: replace Object.freeze with shallow copy

Object.freeze throws TypeErrors when subagent tools (checkout_pr,
report_progress) write scalar properties to toolState. A shallow copy
achieves the same isolation for scalar fields while allowing tools to
work normally. Shared references (subagents Map, usageEntries array)
remain shared for coordination.

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: pullfrog[bot] <226033991+pullfrog[bot]@users.noreply.github.com>
2026-02-22 14:12:43 +00:00

196 lines
5.7 KiB
TypeScript

import type { StandardSchemaV1 } from "@standard-schema/spec";
import { encode as toonEncode } from "@toon-format/toon";
import type { FastMCP, Tool } from "fastmcp";
import { formatJsonValue, log } from "../utils/cli.ts";
import type { ToolContext } from "./server.ts";
export const tool = <const params>(
toolDef: Tool<any, StandardSchemaV1<params>>
): Tool<any, StandardSchemaV1<params>> => toolDef;
export interface ToolResult {
content: {
type: "text";
text: string;
}[];
isError?: boolean;
}
export const handleToolSuccess = (data: Record<string, any> | string): ToolResult => {
const text = typeof data === "string" ? data : toonEncode(data);
return {
content: [{ type: "text", text }],
};
};
export const handleToolError = (error: unknown): ToolResult => {
const errorMessage = error instanceof Error ? error.message : String(error);
return {
content: [
{
type: "text",
text: `Error: ${errorMessage}`,
},
],
isError: true,
};
};
/**
* Helper to wrap a tool execute function with error handling.
* Captures ctx in closure so tools don't need to handle try/catch.
* @param fn - the function to execute
* @param toolName - optional tool name for error logging
*/
export const execute = <T, R extends Record<string, any> | string>(
fn: (params: T) => Promise<R>,
toolName?: string
) => {
const _fn = async (params: T): Promise<ToolResult> => {
try {
const result = await fn(params);
return handleToolSuccess(result);
} catch (error) {
const errorMessage = error instanceof Error ? error.message : String(error);
const prefix = toolName ? `[${toolName}]` : "tool";
log.info(`${prefix} error: ${errorMessage}`);
log.debug(`${prefix} params: ${formatJsonValue(params)}`);
return handleToolError(error);
}
};
return _fn;
};
/**
* Sanitize JSON schema to remove problematic fields that Gemini CLI/API can't handle
* - Removes $schema field (causes "no schema with key or ref" errors)
* - Converts $defs to definitions (draft-07 compatibility)
* - Removes any draft-2020-12 specific features
* - Converts any_of with enum values to direct STRING enum (Google API requirement)
*/
function sanitizeSchema(schema: any): any {
if (!schema || typeof schema !== "object") {
return schema;
}
if (Array.isArray(schema)) {
return schema.map(sanitizeSchema);
}
// handle any_of with enum values - convert to direct STRING enum for Google API
// Google API requires: {type: "string", enum: [...]} not {anyOf: [{enum: [...]}, {enum: [...]}]}
if (schema.anyOf && Array.isArray(schema.anyOf) && schema.anyOf.length > 0) {
const enumValues: string[] = [];
let allAreEnumObjects = true;
for (const item of schema.anyOf) {
if (item && typeof item === "object" && Array.isArray(item.enum)) {
// collect enum values (only strings)
const stringEnums = item.enum.filter((v: any) => typeof v === "string");
if (stringEnums.length > 0) {
enumValues.push(...stringEnums);
} else {
allAreEnumObjects = false;
break;
}
} else {
allAreEnumObjects = false;
break;
}
}
// if all any_of items are enum objects with string values, convert to direct STRING enum
if (allAreEnumObjects && enumValues.length > 0) {
const uniqueEnums = [...new Set(enumValues)];
// preserve other properties from the original schema (like description)
const result: any = {
type: "string",
enum: uniqueEnums,
};
if (schema.description) {
result.description = schema.description;
}
return result;
}
}
const sanitized: any = {};
for (const [key, value] of Object.entries(schema)) {
// skip $schema field entirely
if (key === "$schema") {
continue;
}
// skip any_of if we already converted it above
if (key === "anyOf" && schema.anyOf) {
continue;
}
// convert $defs to definitions for draft-07 compatibility
if (key === "$defs") {
sanitized.definitions = sanitizeSchema(value);
continue;
}
// recursively sanitize nested objects
sanitized[key] = sanitizeSchema(value);
}
return sanitized;
}
/**
* Wrap a StandardSchemaV1 to intercept toJsonSchema() calls and sanitize the output
*/
function wrapSchema(schema: StandardSchemaV1<any>): StandardSchemaV1<any> {
const originalToJsonSchema = (schema as any).toJsonSchema?.bind(schema);
if (!originalToJsonSchema) {
return schema;
}
// create a proxy that intercepts toJsonSchema calls
return new Proxy(schema, {
get(target, prop) {
if (prop === "toJsonSchema") {
return () => {
const originalSchema = originalToJsonSchema();
return sanitizeSchema(originalSchema);
};
}
return (target as any)[prop];
},
}) as StandardSchemaV1<any>;
}
/**
* Transform tool to sanitize its parameter schema for Gemini CLI compatibility
*/
function sanitizeTool<T extends Tool<any, any>>(tool: T): T {
if (!tool.parameters) {
return tool;
}
// wrap the schema object to intercept toJsonSchema() calls
const wrappedSchema = wrapSchema(tool.parameters);
// create a new tool with wrapped schema
return {
...tool,
parameters: wrappedSchema,
} as T;
}
export const addTools = (ctx: ToolContext, server: FastMCP<any>, tools: Tool<any, any>[]) => {
// sanitize schemas for gemini agent and opencode (when using Google API)
// both have issues with draft-2020-12 schemas and any_of enum constructs
const shouldSanitize = ctx.agent.name === "gemini" || ctx.agent.name === "opencode";
for (const tool of tools) {
const processedTool = shouldSanitize ? sanitizeTool(tool) : tool;
server.addTool(processedTool);
}
return server;
};