Commit Graph

11 Commits

Author SHA1 Message Date
Colin McDonnell 52ec35790a fix review reply trigger: treat replies to Pullfrog threads as implicit triggers, only add eyes reaction when dispatching
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-24 19:28:08 +00:00
Colin McDonnell cd1ea5267c fix node24 PATH propagation and improve action logging (#381)
Add node24 binary directory to PATH in action entry point so spawned
processes (pnpm, npm, etc.) resolve to the correct node version instead
of the runner's default v20. Improve delegate task result logging with
success/failure status and summaries. Use collapsible log groups for
dependency install output instead of raw streaming.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-24 15:32:32 +00:00
Colin McDonnell e2d8dfeebf Clarify shell guidance and delegation checklists
Standardize orchestrator/subagent instructions on the MCP shell tool and format mode guidance as explicit checklists to make delegation flows easier to follow. Bump the action package version to 0.0.171 for this release.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-24 01:28:50 +00:00
Colin McDonnell 2017922780 Improve delegate (#377)
* Improve delegate

* fix stale log regexes in delegate tests and add test-coupling comments

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-23 23:41:27 +00:00
Colin McDonnell b8a0d799ee Update instructions. Bump. 2026-02-23 17:44:24 +00:00
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
pullfrog[bot] 70f1c47a28 Audit core.warning/core.error usage (#269)
* Stop using command-based logs for warnings and errors

Co-authored-by: Cursor <cursoragent@cursor.com>

* revert

* tweak

* de-noise

* Remove redundant ts() timestamp prefix from log calls

* Restore timestamped logging and refine debug output routing.

Bring back timestamp prefixes for standard logs and make log.debug emit via core.debug when runner debug is enabled, while still surfacing debug lines for --debug runs.

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Mateusz Burzyński <mateuszburzynski@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: pullfrog[bot] <226033991+pullfrog[bot]@users.noreply.github.com>
Co-authored-by: Colin McDonnell <colinmcd94@gmail.com>
2026-02-19 23:11:47 +00:00
Colin McDonnell b6658ddbc1 improve agent CI matrix, token permissions, and waitlist follower backfill (#313)
* add workflows permission to git token and waitlist improvements

- add `workflows` to `InstallationTokenPermissions` type in both action and API token routes
- include `workflows: write` in the git token so agents can push workflow file changes
- add `githubFollowers` field to WaitlistSignup schema with migration
- add script to populate waitlist followers from GitHub API
- add frog-green-square-border logo asset

Co-authored-by: Cursor <cursoragent@cursor.com>

* improve CI, agent logging, token permissions, and delegation guardrails

- add format check and build step to root CI job
- standardize agent model/effort log lines across all agents
- fix GitHub App permissions types to match OpenAPI schema (workflows is write-only)
- improve delegation error message to prevent subagent recursion
- demote noisy OpenCode stderr to debug level
- add subagent delegation rules to resolved instructions

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix graphql partial error handling, update delegation message, add workflow_run fixtures

Co-authored-by: Cursor <cursoragent@cursor.com>

* remove module-level env var throws that break CI build

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix logging bug and type hole from PR review

- use batch-local notFound counter so per-batch log doesn't undercount
- add workflows to WorkflowTokenPermissions so wire type matches what action sends

Co-authored-by: Cursor <cursoragent@cursor.com>

* lazy-init appOctokit to fix next build without env vars

Co-authored-by: Cursor <cursoragent@cursor.com>

* drop pnpm build from CI test workflow

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix delegate-effort test regex to match actual log format, disable fail-fast for agnostic tests

the test was matching `running \w+ with effort=auto` but the actual log
line from shared.ts is `» effort:  auto`. also temporarily set
fail-fast: false on action-agnostic so all failures surface at once.

Co-authored-by: Cursor <cursoragent@cursor.com>

* disable fail-fast in action workflow too, relax ci.test.ts to match

both workflow files now use fail-fast: false for agnostic tests so all
matrix jobs run to completion. the ci consistency test now checks that
the two workflows agree rather than requiring true.

Co-authored-by: Cursor <cursoragent@cursor.com>

* restore fail-fast: true now that all agnostic tests pass

Co-authored-by: Cursor <cursoragent@cursor.com>

* skip agent tests in CI when agent harness file didn't change

adds action/test/changed-agents.sh which reads the PR diff (via
dorny/paths-filter) and outputs only agents whose harness file was
modified. the action-agents matrix now uses this dynamic list instead
of a hardcoded array, so e.g. a PR touching only cursor.ts runs 6
jobs instead of 30.

Co-authored-by: Cursor <cursoragent@cursor.com>

* update ci.test.ts to validate dynamic agent matrix

the test now checks that the matrix references the changes job output
and that changed-agents.sh correctly discovers all agents.

Co-authored-by: Cursor <cursoragent@cursor.com>

* parallelize action jobs and use claude canary fallback for shared changes

runs action-agents in parallel with action-agnostic after root/changes, and updates changed-agents logic so shared or non-harness action runtime changes run only claude while harness-specific edits run only those changed agents.

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-16 22:36:29 +00:00
Colin McDonnell 97937f46f7 console UI improvements and cleanup (#311)
* console UI improvements and cleanup

- add verify workflow button and API endpoint for manual installation check
- move env var check into PromptBox as blocking overlay (hoisted to RepoConsole)
- extract FlagsCheatSheet modal, replace verbose flag hints everywhere
- add info popovers for repo setup / post-checkout script descriptions
- remove unused prAutoFixCiFailures schema fields and migration
- default mentionAllowNonCollaborator to disabled for safety on public repos
- update docs for triggers and getting started

Co-authored-by: Cursor <cursoragent@cursor.com>

* add diagnostic logging for push_branch bug investigation

temporary [push-debug] logs to trace why getPushDestination falls back
to origin/<localBranch> instead of using the correct remote branch name
for same-repo PRs.

Co-authored-by: Cursor <cursoragent@cursor.com>

* add git config diagnostic to verify original bug cause

Co-authored-by: Cursor <cursoragent@cursor.com>

* temporarily disable StoredPushDest to test git config path

Co-authored-by: Cursor <cursoragent@cursor.com>

* remove diagnostic logging for push_branch investigation

verified that StoredPushDest fix works correctly on preview repo.
both the stored dest path and the git config fallback resolve to the
correct remote branch in the GitHub Actions environment.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix formatting in AgentSettings and TriggersSettings

Co-authored-by: Cursor <cursoragent@cursor.com>

* pass derived env var state to PromptBox instead of raw secrets data

eliminates duplicated derivation logic between RepoConsole and PromptBox
by passing envVarMissing, envVarChecking, and agentKeyNames as props.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix: prevent duplicate comment after PR review deletes progress comment

progressCommentId now uses three states: undefined (no comment yet),
number (active), null (deliberately deleted). After create_pull_request_review
deletes the progress comment, subsequent report_progress calls skip instead
of creating a new comment.

Co-authored-by: Cursor <cursoragent@cursor.com>

* effort descriptions, test ordering, husky, docs images, typo fix

- rewrote delegation effort level descriptions to per-level breakdown
- action-agents now waits for action-agnostic; action-agnostic waits for root
- added husky + lint-staged (biome check --write on staged files)
- updated triggers docs images and triggers.mdx content
- fixed "figured" → "figures" typo on landing page
- updated pnpm-lock.yaml

Co-authored-by: Cursor <cursoragent@cursor.com>

* Commit

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-16 04:41:04 +00:00
David Blass a8dde34531 fix delegate timeout (#284)
* pin all CLI installations to explicit versions and use pro models by default

- codex: pin @openai/codex to 0.101.0 (was "latest")
- opencode: pin opencode-ai to 1.1.56 (was "latest")
- gemini: pin gemini-cli to v0.28.2 via new tag param on installFromGithub
- cursor: pin to 2026.01.28-fd13201 via direct tarball download (replaces curl install script)
- add installFromDirectTarball to install.ts for versioned tarball URLs
- gemini auto effort now uses pro-preview instead of flash-preview
- test runner model overrides updated to use pro-preview consistently

Co-authored-by: Cursor <cursoragent@cursor.com>

* increase activity timeout

* fix delegation timeout

* fix delegate timeouts

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-12 23:46:28 +00:00
David Blass 9071c0ae6c refactor mode selection into delegate tool that spawns subagents (#265) 2026-02-12 19:34:47 +00:00