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

.github/workflows

Avoid using --ignore-workspace (#353 )

2026-02-19 14:41:21 +00:00

.husky

Avoid using --ignore-workspace (#353 )

2026-02-19 14:41:21 +00:00

agents

refactor delegation system, add PR summary comments, and improve code quality (#334 )

2026-02-22 14:12:43 +00:00

fixtures

add per-agent smoke tests (#100 )

2026-01-16 08:00:16 +00:00

get-installation-token

Audit core.warning/core.error usage (#269 )

2026-02-19 23:11:47 +00:00

internal

Avoid using --ignore-workspace (#353 )

2026-02-19 14:41:21 +00:00

lint

add agent and debug macros, improve activity timeouts, migrate claude and codex to cli (#224 )

2026-02-04 22:29:45 +00:00

mcp

refactor delegation system, add PR summary comments, and improve code quality (#334 )

2026-02-22 14:12:43 +00:00

prep

Replace Date.now() with performance.now() for duration measurements (#258 )

2026-02-12 15:26:28 +00:00

scripts

Avoid using --ignore-workspace (#353 )

2026-02-19 14:41:21 +00:00

test

refactor delegation system, add PR summary comments, and improve code quality (#334 )

2026-02-22 14:12:43 +00:00

utils

refactor delegation system, add PR summary comments, and improve code quality (#334 )

2026-02-22 14:12:43 +00:00

.cursorignore

Create JS action

2025-08-27 16:53:48 -07:00

.gitignore

Fixing CI (#119 )

2026-01-19 08:41:56 +00:00

.node-version

Use await using for installation token cleanup

2026-01-07 19:25:24 +01:00

action.yml

feat(action): Update "Leaping" comment when workflow failed or cancelled early (#230 )

2026-02-06 18:10:08 +00:00

entry

refactor delegation system, add PR summary comments, and improve code quality (#334 )

2026-02-22 14:12:43 +00:00

entry.ts

fix: replace domain-specific exit handler with generic signal handler registry (#299 )

2026-02-20 10:23:56 +00:00

esbuild.config.js

Base Cloudflare integration with the codebase (#261 )

2026-02-13 19:17:27 +00:00

external.ts

Request reviews from the PR's human initiator (#340 )

2026-02-19 14:00:57 +00:00

index.ts

Add upload tool and related APIs (#187 )

2026-01-28 05:34:58 +00:00

LICENSE

Correct copyright holder name in LICENSE file (#368 )

2026-02-20 12:39:11 +00:00

lifecycle.ts

feat: Lifecycle hooks (#219 )

2026-02-06 07:16:14 +00:00

main.ts

refactor delegation system, add PR summary comments, and improve code quality (#334 )

2026-02-22 14:12:43 +00:00

modes.ts

improve review mode: no compliments, no unrelated nitpicks

2026-02-20 19:19:09 +00:00

package.json

refactor delegation system, add PR summary comments, and improve code quality (#334 )

2026-02-22 14:12:43 +00:00

play.ts

run post action cleanup in play.ts (#344 )

2026-02-18 18:32:24 +00:00

pnpm-lock.yaml

refactor delegation system, add PR summary comments, and improve code quality (#334 )

2026-02-22 14:12:43 +00:00

pnpm-workspace.yaml

Avoid using --ignore-workspace (#353 )

2026-02-19 14:41:21 +00:00

post

refactor delegation system, add PR summary comments, and improve code quality (#334 )

2026-02-22 14:12:43 +00:00

post.ts

run post action cleanup in play.ts (#344 )

2026-02-18 18:32:24 +00:00

README.md

Deployment protection bypass (#298 )

2026-02-13 20:01:48 +00:00

test.txt

test: trivial change to test preview system (#179 )

2026-01-25 08:18:49 +00:00

tsconfig.json

Establishing unit tests using vitest.

2026-01-12 15:05:30 +01:00

vitest.config.ts

tests and better diffs (#163 )

2026-01-23 06:28:22 +00:00

vitest.setup.ts

switch local dev to dedicated GitHub App + Clerk project (#347 )

2026-02-19 04:37:35 +00:00

README.md

Pullfrog

Bring your favorite coding agent into GitHub

🚀 Pullfrog is in beta! We're onboarding users in waves. Get on the waitlist →

What is Pullfrog?

Pullfrog is a GitHub bot that brings the full power of your favorite coding agents into GitHub. It's open source and powered by GitHub Actions.

Tag @pullfrog — Tag @pullfrog in a comment anywhere in your repo. It will pull in any relevant context using the action's internal MCP server and perform the appropriate task.
Prompt from the web — Trigger arbitrary tasks from the Pullfrog dashboard
Automated triggers — Configure Pullfrog to trigger agent runs in response to specific events. Each of these triggers can be associated with custom prompt instructions.
- issue created
- issue labeled
- PR created
- PR review created
- PR review requested
- and more...

Pullfrog is the bridge between your preferred coding agents and GitHub. Use it for:

🤖 Coding tasks — Tell @pullfrog to implement something and it'll spin up a PR. If CI fails, it'll read the logs and attempt a fix automatically. It'll automatically address any PR reviews too.
🔍 PR review — Coding agents are great at reviewing PRs. Using the "PR created" trigger, you can configure Pullfrog to auto-review new PRs.
🤙 Issue management — Via the "issue created" trigger, Pullfrog can automatically respond to common questions, create implementation plans, and link to related issues/PRs. Or (if you're feeling lucky) you can prompt it to immediately attempt a PR addressing new issues.
Literally whatever — Want to have the agent automatically add docs to all new PRs? Cut a new release with agent-written notes on every commit to main? Pullfrog lets you do it.