cfd38d82fc
* 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>
55 lines
2.1 KiB
TypeScript
55 lines
2.1 KiB
TypeScript
import { type } from "arktype";
|
|
import { ghPullfrogMcpName } from "../external.ts";
|
|
import { log } from "../utils/cli.ts";
|
|
import type { ToolContext } from "./server.ts";
|
|
import { execute, tool } from "./shared.ts";
|
|
import { createSubagentState, runSubagent } from "./subagent.ts";
|
|
|
|
export const AskQuestionParams = type({
|
|
question: type.string.describe(
|
|
"the question to answer about the codebase, architecture, or implementation details"
|
|
),
|
|
});
|
|
|
|
function buildQuestionPrompt(question: string): string {
|
|
return `You are a focused research subagent. Answer the following question by exploring the codebase using the available MCP tools (${ghPullfrogMcpName}/file_read, ${ghPullfrogMcpName}/list_directory, etc.).
|
|
|
|
Be thorough in your investigation but concise in your answer. When done, call ${ghPullfrogMcpName}/set_output with a maximally concise answer — key facts only, no filler, no preamble.
|
|
|
|
Question: ${question}`;
|
|
}
|
|
|
|
export function AskQuestionTool(ctx: ToolContext) {
|
|
return tool({
|
|
name: "ask_question",
|
|
description:
|
|
"Ask a question about the codebase and get a concise answer from a lightweight research subagent. The intermediate exploration context stays in the subagent — only the concise answer returns to you.",
|
|
parameters: AskQuestionParams,
|
|
execute: execute(async (params) => {
|
|
if (ctx.toolState.activeSubagentId) {
|
|
return { error: "cannot ask questions while a subagent is already running" };
|
|
}
|
|
|
|
const subagent = createSubagentState({ ctx, mode: "ask_question" });
|
|
log.info(`» ask_question subagent=${subagent.id}: ${params.question.slice(0, 100)}`);
|
|
|
|
const result = await runSubagent({
|
|
ctx,
|
|
subagent,
|
|
effort: "mini",
|
|
instructions: buildQuestionPrompt(params.question),
|
|
});
|
|
log.info(`» ask_question completed (success=${result.success})`);
|
|
|
|
return {
|
|
success: result.success,
|
|
answer:
|
|
subagent.output ??
|
|
result.error ??
|
|
"no answer produced — the subagent may not have called set_output. check stdoutFile for details.",
|
|
stdoutFile: subagent.stdoutFilePath,
|
|
};
|
|
}),
|
|
});
|
|
}
|