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>
56 lines
2.0 KiB
TypeScript
56 lines
2.0 KiB
TypeScript
import type { AgentResult, TestRunnerOptions, ValidationCheck } from "../utils.ts";
|
|
import { defineFixture, getAgentOutput, getStructuredOutput } from "../utils.ts";
|
|
|
|
/**
|
|
* delegateMulti test - validates multi-phase delegation with context passing.
|
|
*
|
|
* the orchestrator delegates twice:
|
|
* 1. first to Plan mode (subagent calls set_output with PHASE_1_MARKER)
|
|
* 2. then to Plan mode again with context from phase 1 (subagent calls set_output with MULTI_DELEGATE_PASSED)
|
|
*
|
|
* validates that both delegations executed and the final set_output value is correct.
|
|
*/
|
|
|
|
const fixture = defineFixture(
|
|
{
|
|
prompt: `This is a multi-delegation test. You must delegate exactly twice:
|
|
|
|
Phase 1: Select Plan mode via select_mode, then delegate with mini effort. Your subagent instructions:
|
|
"Your task is to call set_output with the value 'PHASE_1_MARKER'. Do not create plans or PRs."
|
|
|
|
Phase 2: After Phase 1 completes, select Plan mode again and delegate with mini effort. Include the result from Phase 1. Your subagent instructions:
|
|
"Your task is to call set_output with the value 'MULTI_DELEGATE_PASSED'. Do not create plans or PRs."
|
|
|
|
Both delegations must complete successfully.`,
|
|
effort: "mini",
|
|
timeout: "8m",
|
|
},
|
|
{ localOnly: true }
|
|
);
|
|
|
|
function validator(result: AgentResult): ValidationCheck[] {
|
|
const output = getStructuredOutput(result);
|
|
const agentOutput = getAgentOutput(result);
|
|
|
|
const setOutputCalled = output !== null;
|
|
// the last set_output call wins — should be from Phase 2
|
|
const finalValue = setOutputCalled && /MULTI_DELEGATE_PASSED/i.test(output);
|
|
|
|
const delegationMatches = agentOutput.match(/» delegating subagent=/g);
|
|
const twoDelegations = delegationMatches !== null && delegationMatches.length >= 2;
|
|
|
|
return [
|
|
{ name: "set_output", passed: setOutputCalled },
|
|
{ name: "final_value", passed: finalValue },
|
|
{ name: "two_delegations", passed: twoDelegations },
|
|
];
|
|
}
|
|
|
|
export const test: TestRunnerOptions = {
|
|
name: "delegate-multi",
|
|
fixture,
|
|
validator,
|
|
env: { GITHUB_REPOSITORY: "pullfrog/test-repo" },
|
|
tags: ["agnostic"],
|
|
};
|