* agent & model refactor with ASKPASS git auth, UI restructure, clerk v7
Made-with: Cursor
* fix stale agent/effort refs, add tests for askpass + model resolution
- reviewCleanup.ts: payload.agent -> payload.model, remove effort
- selectMode.ts PlanEdit: remove delegation/subagent/effort references
- pullfrog.yml.ts: update env vars (drop GOOGLE_API_KEY/CURSOR_API_KEY,
add GOOGLE_GENERATIVE_AI_API_KEY/XAI_API_KEY/MOONSHOT_API_KEY/OPENCODE_API_KEY)
- FlagsSettings/RepoInstructionsSection: remove stale effort/timeout copy
- new: gitAuthServer.test.ts (10 tests — lifecycle, token delivery, tamper detection, script gen)
- new: agent.test.ts (4 tests — default opentoad, AGENT_OVERRIDE, invalid override)
- new: models.test.ts (19 tests — parseModel, resolution, registry invariants)
- update models.dev snapshot
Made-with: Cursor
* fix changed-agents.sh to filter legacy agent files from CI matrix
legacy agent files (claude.ts, codex.ts, etc.) are @ts-nocheck and not
exported from index.ts. changed-agents.sh now reads index.ts imports to
build the active agent set and treats changes to inactive files as
non-agent changes (opentoad canary only).
Made-with: Cursor
* remove MCP file tools, old agent harnesses, and obsolete security tests
ASKPASS-based git auth makes the old MCP file tool security layer unnecessary:
- token never in subprocess env, so symlink/gitattributes/hook attacks can't exfiltrate it
- agents now use native file tools (OpenCode builtin read/edit)
deleted:
- action/mcp/file.ts (file_read, file_write, file_edit, file_delete, list_directory)
- action/mcp/index.ts (dead re-export)
- agent harnesses: claude.ts, codex.ts, cursor.ts, gemini.ts, opencode.ts
- opencode-runner.ts (inlined into opentoad.ts)
- security tests that validated MCP file tool restrictions
- commented-out three-step review flow (~300 lines)
- sanitizeSchema/wrapSchema dead code from mcp/shared.ts
- OPENCODE_MODEL_MINI/MAX env vars (effort-level model overrides removed)
updated test prompts to use generic file ops instead of MCP tool names.
restored pkg-json-scripts + requirements-txt-attack (test --ignore-scripts defense).
Made-with: Cursor
* bump actions/checkout v4 → v6 (node 24)
node 20 actions deprecated june 2, 2026.
Made-with: Cursor
* temporarily disable fail-fast on agnostic tests to debug checkout@v6
Made-with: Cursor
* re-enable fail-fast on agnostic tests
Made-with: Cursor
* fix test token mismatch: mint OIDC tokens scoped to target repo
CI tests override GITHUB_REPOSITORY to pullfrog/test-repo but inherit
the runner's GITHUB_TOKEN (scoped to pullfrog/app), causing 401s on
every run-context fetch. Clear GITHUB_TOKEN in the test subprocess so
ensureGitHubToken() mints a properly scoped token via OIDC.
Also centralizes the default GITHUB_REPOSITORY in runAgentStreaming
instead of repeating it in every test file, and fixes preview-cleanup
to remove workers from all queues (not just name-matching ones).
Made-with: Cursor
* fix ensureGitHubToken to try OIDC when app credentials are absent
ensureGitHubToken only attempted token minting when GITHUB_APP_ID and
GITHUB_PRIVATE_KEY were set. In CI, OIDC is available but app creds
aren't exposed — so the guard prevented minting entirely.
Made-with: Cursor
* dead code cleanup: remove remnants of deleted agents, file tools, effort system
remove unused @anthropic-ai/claude-agent-sdk and @openai/codex-sdk deps,
orphaned file-tool security tests, dead GEMINI_MODEL passthrough, stale
opencode-runner wiki refs, deleted test file references, and MCP file tool
docs. rename docs/effort → docs/models. fix vitest setup: move dotenv to
globalSetup (runs once before forks instead of per-file, 19s → 200ms).
Made-with: Cursor
* address review feedback: remove dead code, update stale references
- remove AGENT_OVERRIDE (only opentoad exists)
- remove shellToolName plumbing (always restricted shell)
- bump action version to 0.0.179
- remove CURSOR_API_KEY from all workflows/configs
- remove OPENCODE_MODEL_MINI/MAX from workflows/docs
- delete wiki/effort.md, rewrite docs/effort.mdx as "Models"
- rewrite wiki/modes.md: orchestrator/subagent → single agent
- simplify flag system: drop builtin flag extraction (debug, effort,
timeout, agent), keep custom flag replacement only
- reserve all legacy flag names to prevent custom flag conflicts
Made-with: Cursor
* regenerate lockfile after removing claude-agent-sdk and codex-sdk
Made-with: Cursor
* fix import ordering, add lockfile check to pre-push hook
Made-with: Cursor
* remove dead debug payload field, stale packageExtensions
Made-with: Cursor
* merge proc-sandbox and token-exfil into a single test
proc-sandbox and token-exfil were duplicative — both tested that
SANDBOX_TEST_TOKEN couldn't be exfiltrated. consolidated into
token-exfil with shell:restricted (which actually exercises filterEnv)
and the /proc attack vector hints from proc-sandbox.
Made-with: Cursor
* fix wiki adversarial.md to match actual tokenExfil validator
Made-with: Cursor
* feat(plans): Suggested plan for plan revisions.
* fix: add planCommentId to reduce GitHub API calls.
* Revert "fix: add planCommentId to reduce GitHub API calls."
This reverts commit ef9c24811fa291b12ac3601cc4cd3edb7c9a0fca.
* Improving plan revision: the implementation draft.
* fix schema composition order.
* fix: reusing existing retry helper (action) for reportPlanCommentToRun.
* mv: updatePlanCommentId.
* fix: higher severity for logging error.
* fix: add error handling when calling findExistingPlanCommentIdForIssue.
* feat: improving the revisit plan request detection by adding PLAN_REVISION_VERBS.
* Updating the plan with alternative non-determenistic solution.
* add more verbs to PLAN_REVISION_VERBS.
* fix: supply the previous plan in the event context as previousPlanBody, updating Plan mode instructions.
* fix: adjusting the way PLAN_REVISION_VERBS are used in sentences.
* fix: using GraphQL approach with NodeId to find commentId in findExistingPlanCommentIdForIssue.
* fix: use double word boundaries (both sides).
* fix condition in findExistingPlanCommentIdForIssue.
* fix: rm unused args from findExistingPlanCommentIdForIssue.
* bump the action version.
* fix(plan): rm everything related to approach A.
* fix(plan): No limit for progress comments.
* feat(plan): the new plan.
* Revert: changed to webhook (no longer involved).
* feat: mv plan comment lookup into a new API endpoint.
* Revert: changes to select_mode tool.
* FEAT: The new implementation.
* fix arktype issues.
* fix plan diagram.
* fix(selectMode): e2e type constraints for fetchExistingPlanComment.
* Revert "fix(selectMode): e2e type constraints for fetchExistingPlanComment."
This reverts commit 53f3b6650a9928e3080700faa9eead0052e94333.
* fix(selectMode): type constraints (copy) for fetchExistingPlanComment.
* feat: improving isHttpError helper and reusing it consistently instead of casting.
* address review: remove unconditional retry, add plan comment warning, dedupe type, remove dead guard, fix GraphQL types
* Fix: tightening the PlanEdit guidance.
* fix(select_mode): Providing the agent with existingPlanCommentId as well.
* fix(instructions): Adjusting the primary guidance to prefer Plan mode for issue-related ambiguous requests.
* fix(wiki): updating the delegation docs according to the current instructions.
* fix(instructions): rm implication to call for issue details.
* fix(select_mode): tweak for PlanEdit.
* fix(select_mode): more tweaks to PlanEdit.
* fix(select_mode): tweaks for the order of instructions and context.
* revert: to the state of 5c400efce1f1fec0a0855eeacad2bc3b721fd1bf.
* fix(select_mode): Correcting the guideline.
* rm the plan from the branch (impletemented).
---------
Co-authored-by: pullfrog[bot] <226033991+pullfrog[bot]@users.noreply.github.com>
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>
Increment @pullfrog/pullfrog from 0.0.163 to 0.0.164 and include current beta/docs/waitlist script changes.
Co-authored-by: Cursor <cursoragent@cursor.com>
* upgrade Claude to Opus 4.6 with --effort max for --max mode
- mini: haiku → sonnet
- auto: opusplan → opus (Opus 4.6)
- max: opus → opus + --effort max (Opus 4.6 max effort)
- bump @anthropic-ai/claude-agent-sdk 0.2.7 → 0.2.39
Co-authored-by: Cursor <cursoragent@cursor.com>
* update action lockfile for claude-agent-sdk 0.2.39
Co-authored-by: Cursor <cursoragent@cursor.com>
* add tool_use_summary handler for SDK 0.2.39
Co-authored-by: Cursor <cursoragent@cursor.com>
* integrate gpt-5.3-codex with runtime model availability detection
checks GET /v1/models at agent start to determine if gpt-5.3-codex is
available for the API key, falling back to gpt-5.2-codex when it isn't.
model resolution runs concurrently with CLI install for zero added latency.
also bumps @openai/codex-sdk from 0.80.0 to 0.98.0.
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
* Add utils for r2 upload
* Add the tool and new routes
* fix auth issue
* sign headers
* add comment
* use our own API key to auth signed uploads
* Restructure things slightly
* tweak
* tweak
* add comments
* tweak
* revert a thing
* twaek
* drop mime type filtering
* new incarnation of mime type filtering
* jsut allow all octet-streams
* simplify further
* tweak
* update lockfile
---------
Co-authored-by: Colin McDonnell <colinmcd94@gmail.com>
Colin McDonnell