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>
61 lines
2.5 KiB
TypeScript
61 lines
2.5 KiB
TypeScript
import { type } from "arktype";
|
|
import { Effort } 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 DelegateParams = type({
|
|
instructions: type.string.describe(
|
|
"the complete prompt for the subagent. the subagent receives ONLY this text — include all context it needs (file paths, constraints, conventions, tool usage instructions). craft a focused, self-contained task description."
|
|
),
|
|
"effort?": Effort.describe(
|
|
'effort level for the subagent: "mini" (low-effort and fast, only for simple tasks), "auto" (medium-effort, good for typical tasks that don\'t require significant reasoning), or "max" (high-effort, good for PR reviews and complex coding tasks)'
|
|
),
|
|
});
|
|
|
|
export function DelegateTool(ctx: ToolContext) {
|
|
return tool({
|
|
name: "delegate",
|
|
description:
|
|
"Delegate a task to a subagent. The subagent receives ONLY the instructions you provide — no other context is added. Use select_mode first to get guidance on how to craft the instructions for a given mode.",
|
|
parameters: DelegateParams,
|
|
execute: execute(async (params) => {
|
|
if (ctx.toolState.activeSubagentId) {
|
|
return {
|
|
error:
|
|
"delegation is not available inside a subagent. you are already running as a delegated subagent. complete the task directly using the available tools.",
|
|
};
|
|
}
|
|
|
|
const effort = params.effort ?? "auto";
|
|
const mode = ctx.toolState.selectedMode ?? "unknown";
|
|
if (!ctx.toolState.selectedMode) {
|
|
log.info(`» warning: delegating without calling select_mode first (mode=${mode})`);
|
|
}
|
|
const subagent = createSubagentState({ ctx, mode });
|
|
|
|
log.info(`» delegating subagent=${subagent.id} (mode=${mode}, effort=${effort})`);
|
|
const result = await runSubagent({
|
|
ctx,
|
|
subagent,
|
|
effort,
|
|
instructions: params.instructions,
|
|
});
|
|
log.info(`» delegation completed (mode=${mode}, success=${result.success})`);
|
|
|
|
return {
|
|
success: result.success,
|
|
mode,
|
|
effort,
|
|
summary:
|
|
subagent.output ??
|
|
result.error ??
|
|
"no output produced — the subagent may not have called set_output. check stdoutFile for full logs.",
|
|
stdoutFile: subagent.stdoutFilePath,
|
|
error: result.error,
|
|
};
|
|
}),
|
|
});
|
|
}
|