David Blass
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>
58 lines
2.2 KiB
TypeScript
58 lines
2.2 KiB
TypeScript
import type { AgentResult, TestRunnerOptions, ValidationCheck } from "../utils.ts";
|
|
import { defineFixture, getAgentOutput, getStructuredOutput } from "../utils.ts";
|
|
|
|
/**
|
|
* delegate-file-read — orchestrator delegates a subagent to read a real file
|
|
* from the repository and return its content.
|
|
*
|
|
* tests the full delegation pipeline: mode selection → prompt crafting with MCP
|
|
* tool references → subagent file read → result propagation back to orchestrator.
|
|
*
|
|
* unlike the basic delegate test (which just echoes a hardcoded string), this
|
|
* requires the subagent to actually use MCP tools (file_read) to interact with
|
|
* the repo and return derived data.
|
|
*/
|
|
|
|
const fixture = defineFixture(
|
|
{
|
|
prompt: `You are an orchestrator. Your task:
|
|
|
|
1. Select the Plan mode via select_mode.
|
|
2. Delegate to a subagent with mini effort. Craft instructions telling it to:
|
|
- Use gh_pullfrog/file_read to read the file "README.md" from the repository root
|
|
- Count the total number of lines in the file
|
|
- Call gh_pullfrog/set_output with EXACTLY this format: "LINES=<number>" where <number> is the line count (e.g., "LINES=42")
|
|
- Do NOT create any branches, commits, or PRs
|
|
3. After the delegation completes, call set_output with the subagent's result (the LINES=<number> string).
|
|
|
|
IMPORTANT: Your subagent prompt must include the exact MCP tool names (gh_pullfrog/file_read, gh_pullfrog/set_output).`,
|
|
effort: "auto",
|
|
timeout: "8m",
|
|
},
|
|
{ localOnly: true }
|
|
);
|
|
|
|
function validator(result: AgentResult): ValidationCheck[] {
|
|
const output = getStructuredOutput(result);
|
|
const agentOutput = getAgentOutput(result);
|
|
|
|
const setOutputCalled = output !== null;
|
|
const linesMatch = output ? /LINES=(\d+)/i.exec(output) : null;
|
|
const hasLineCount = linesMatch !== null && parseInt(linesMatch[1], 10) > 0;
|
|
const delegationOccurred = /» delegating subagent=/i.test(agentOutput);
|
|
|
|
return [
|
|
{ name: "set_output", passed: setOutputCalled },
|
|
{ name: "line_count_reported", passed: hasLineCount },
|
|
{ name: "delegation_occurred", passed: delegationOccurred },
|
|
];
|
|
}
|
|
|
|
export const test: TestRunnerOptions = {
|
|
name: "delegate-file-read",
|
|
fixture,
|
|
validator,
|
|
env: { GITHUB_REPOSITORY: "pullfrog/test-repo" },
|
|
tags: ["adhoc"],
|
|
};
|