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>
This commit is contained in:
David Blass
2026-02-22 14:12:43 +00:00
committed by pullfrog[bot]
parent a90743e9fe
commit cfd38d82fc
43 changed files with 3293 additions and 2158 deletions
+34 -5
View File
@@ -24,31 +24,60 @@ function buildPrBodyWithFooter(ctx: ToolContext, body: string): string {
return `${bodyWithoutFooter}${footer}`;
}
export const UpdatePullRequestBody = type({
pull_number: type.number.describe("the pull request number to update"),
body: type.string.describe("the new body content for the pull request"),
});
export function UpdatePullRequestBodyTool(ctx: ToolContext) {
return tool({
name: "update_pull_request_body",
description: "Update the body/description of an existing pull request",
parameters: UpdatePullRequestBody,
execute: execute(async (params) => {
const bodyWithFooter = buildPrBodyWithFooter(ctx, params.body);
const result = await ctx.octokit.rest.pulls.update({
owner: ctx.repo.owner,
repo: ctx.repo.name,
pull_number: params.pull_number,
body: bodyWithFooter,
});
return {
success: true,
number: result.data.number,
url: result.data.html_url,
};
}),
});
}
export function CreatePullRequestTool(ctx: ToolContext) {
return tool({
name: "create_pull_request",
description: "Create a pull request from the current branch",
parameters: PullRequest,
execute: execute(async ({ title, body, base }) => {
execute: execute(async (params) => {
const currentBranch = $("git", ["rev-parse", "--abbrev-ref", "HEAD"], { log: false });
log.debug(`Current branch: ${currentBranch}`);
const bodyWithFooter = buildPrBodyWithFooter(ctx, body);
const bodyWithFooter = buildPrBodyWithFooter(ctx, params.body);
const result = await ctx.octokit.rest.pulls.create({
owner: ctx.repo.owner,
repo: ctx.repo.name,
title: title,
title: params.title,
body: bodyWithFooter,
head: currentBranch,
base: base,
base: params.base,
});
// best-effort: request review from the user who triggered the workflow
const reviewer = ctx.payload.triggeringUser;
if (reviewer) {
try {
log.debug(`Requesting review from ${reviewer} on PR #${result.data.number}`);
log.debug(`requesting review from ${reviewer} on PR #${result.data.number}`);
await ctx.octokit.rest.pulls.requestReviewers({
owner: ctx.repo.owner,
repo: ctx.repo.name,