Files
shockbot/test/adhoc/delegateSynthesis.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

75 lines
3.0 KiB
TypeScript

import type { AgentResult, TestRunnerOptions, ValidationCheck } from "../utils.ts";
import { defineFixture, getAgentOutput, getStructuredOutput } from "../utils.ts";
/**
* delegate-synthesis — orchestrator delegates two research tasks to separate
* subagents, then synthesizes their results into a combined answer.
*
* phase 1: subagent reads README.md and extracts the first line.
* phase 2: subagent counts how many .md files exist via list_directory.
* synthesis: orchestrator combines both pieces of info into the final output.
*
* this tests the orchestrator's ability to:
* - run multiple sequential delegations
* - pass specific, different instructions to each subagent
* - extract and combine results from separate delegation phases
* - produce a structured final output from heterogeneous subagent responses
*/
const fixture = defineFixture(
{
prompt: `You are an orchestrator. You must delegate TWO research tasks and SYNTHESIZE the results.
PHASE 1 — GET FIRST LINE:
Select Plan mode via select_mode, then delegate with mini effort.
Subagent instructions: "Use gh_pullfrog/file_read to read 'README.md'. Extract the FIRST LINE of the file. Call gh_pullfrog/set_output with just the first line of text (nothing else)."
PHASE 2 — COUNT FILES:
Select Plan mode again, then delegate with mini effort.
Subagent instructions: "Use gh_pullfrog/list_directory to list the root directory '.'. Count how many items are listed. Call gh_pullfrog/set_output with just the number (nothing else)."
SYNTHESIS:
After both phases complete, YOU (the orchestrator) must call set_output with EXACTLY:
"FIRST_LINE=<first line from phase 1>,FILE_COUNT=<number from phase 2>"
Both pieces must come from the respective subagent results. Do NOT read the files yourself.`,
effort: "auto",
timeout: "10m",
},
{ localOnly: true }
);
function validator(result: AgentResult): ValidationCheck[] {
const output = getStructuredOutput(result);
const agentOutput = getAgentOutput(result);
const setOutputCalled = output !== null;
// should have two delegation calls
const delegationMatches = agentOutput.match(/» delegating subagent=/g);
const twoDelegations = delegationMatches !== null && delegationMatches.length >= 2;
// FIRST_LINE should be a non-empty string (the first line of README.md)
const firstLineMatch = output ? /FIRST_LINE=([^,]+)/i.exec(output) : null;
const hasFirstLine = firstLineMatch !== null && firstLineMatch[1].trim().length > 0;
// FILE_COUNT should be a positive number
const countMatch = output ? /FILE_COUNT=(\d+)/i.exec(output) : null;
const hasFileCount = countMatch !== null && parseInt(countMatch[1], 10) > 0;
return [
{ name: "set_output", passed: setOutputCalled },
{ name: "two_delegations", passed: twoDelegations },
{ name: "first_line_extracted", passed: hasFirstLine },
{ name: "file_count_extracted", passed: hasFileCount },
];
}
export const test: TestRunnerOptions = {
name: "delegate-synthesis",
fixture,
validator,
env: { GITHUB_REPOSITORY: "pullfrog/test-repo" },
tags: ["adhoc"],
};