* 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
* add mode instructions and restructure dashboard sidebar
- add modeInstructions JSONB field to Repo model for per-mode user instructions
- thread modeInstructions through settings API, run-context API, RepoSettings, ToolContext, and selectMode runtime
- merge user-defined mode instructions with hardcoded orchestrator guidance, with IncrementalReview inheriting from Review
- reduce visible built-in modes from 7 to 4 (Build, Review, Plan, Fix) with editable Instructions textareas
- add TRIGGERS group header to sidebar above Mentions, Pull requests, Issues
- add wiki/modes.md documenting triggers and modes conceptual model
Made-with: Cursor
* fix leaping comment deletion and address review feedback
- wrap post-createReview operations in try/finally so deleteProgressComment
runs even when updateReview or reportReviewNodeId throws
- add parseModeInstructions runtime guard to filter non-string values
from the JSONB field before passing to buildOrchestratorGuidance
- add useEffect sync for localInstructions when props change
- guard onBlur to skip save when instructions haven't changed
- update wiki/modes.md to reflect V2 is implemented (no longer "proposed")
Made-with: Cursor
* harden review cleanup, fix type cast, stabilize mode instructions state
- wrap deleteProgressComment in try/catch inside finally to prevent masking original errors
- replace `as Record<string,string>` cast with runtime parseModeInstructions + useMemo
- fix wiki dual-prompt table to reflect mode.prompt fallback status
Made-with: Cursor
* fix wiki tense and heading ambiguity from PR review
Made-with: Cursor
* fix review "edited" badge by using pending review + submit flow
create review as PENDING first (no event/body), build the footer with
the now-known review ID, then submitReview with the full body. single
atomic publish — no updateReview edit needed.
Made-with: Cursor
* add post-agent follow-up re-review dispatch
After the agent exits, check if PR HEAD moved past the reviewed commit
and dispatch a follow-up re-review. This closes the gap where push
webhooks are suppressed during in-flight reviews.
Made-with: Cursor
* add silent flag to follow-up re-review dispatch
Made-with: Cursor
* restructure dashboard for consistency and clarity
- consolidate tools into single grouped card (was 4 separate cards)
- merge coding + autofix CI into one section
- remove redundant trigger section descriptions
- add bidirectional crosslinks between modes and triggers
- inline instruction links (review/plan/build) into descriptions
- add save status indicators to all sections
- restructure flags with grouped built-in/custom cards
- flatten sidebar (remove dividers and group headers)
- tighten all descriptions
Made-with: Cursor
* update PR screenshots for new dashboard layout
Made-with: Cursor
* extend review context inline instead of dispatching new workflow
when commits are pushed during a review, the agent now handles them
inline: create_pull_request_review detects HEAD movement, returns
instructions to pull and review the incremental diff, and the agent
submits a second review covering only the new changes. this avoids
the cost of spinning up a full new workflow run.
also fixes a bug where reviewedSha was set to the submission HEAD
(current) rather than the checkout HEAD (what was actually reviewed),
which caused commits pushed between checkout and submission to be
silently missed by postReviewCleanup.
the workflow dispatch is kept as a safety net for agent timeout/error.
Made-with: Cursor
* polish dashboard UI: fix debug markers, crosslinks, title consistency, descriptions
- remove all red debug borders/labels and CM component
- remove all inline style={{}} debug outlines from crosslinks
- fix ambiguous crosslinks: Build→"Coding ↓", Plan→"Enrich issues ↓"
- add missing "Edit build instructions ↑" backlink on Auto-address reviews
- normalize card title weight to text-sm font-semibold across all cards
- rename "Default" subcard to "Setup" with broader description
- fix Mentions description to imperative tone
- broaden Flags section description to cover built-in and custom
- remove useless fragments in ModesSection and ToolsSettings
- restructure Agent section: remove ConsoleSection wrappers, add sidebar indent support
Made-with: Cursor
* extract PR quick links as standalone card, consistent with issues
- PR quick links is now its own card under Reviews (was a sub-toggle inside Review PRs disabled state)
- Review PRs OFF sets prCreated="none" instead of auto-falling back to "links"
- Review PRs card hides sub-toggles when disabled (re-review/approve don't apply)
- Both PRs and Issues now have identical Quick links card structure
Made-with: Cursor
* update reviews screenshot with standalone quick links card
Made-with: Cursor
* polish dashboard UI: revert quick links to inline toggles, fix fonts and spacing
- revert standalone PR/issue Quick Links cards back to inline toggles inside
Review PRs and Enrich Issues cards (fixes prCreated state coupling bug)
- restore original font-medium card titles across all trigger/settings cards
- fix sidebar: add CONSOLE heading, remove nested indentation, remove truncation
- right-justify Enrich Issues mode dropdown, group description with label
- move instructions links inline with behavior descriptions
- replace text save indicators with icon spinner/checkmark
- standardize section title spacing, move footer below danger zone
Made-with: Cursor
* fix formatting for biome lint
Made-with: Cursor
* address PR review feedback: cleanup guard, shared util, wiki update
- clear ctx.toolState.review after read to prevent double-execution of postReviewCleanup
- forward authorPermission in safety-net re-review dispatch
- extract parseModeInstructions to utils/schemas/modeInstructions.ts
- update wiki/modes.md: remove stale v1/v2 language, fix dashboard layout
- add typecheck to pre-push hook
Made-with: Cursor
* add action typecheck to pre-push, fix exactOptionalPropertyTypes errors
Made-with: Cursor
* fix duplicate actuallyReviewedSha from rebase
Made-with: Cursor
* remove PR screenshots
Made-with: Cursor
* add label/textarea association for mode instruction accessibility
Made-with: Cursor
---------
Co-authored-by: Colin McDonnell <colinmcd94@gmail.com>
* add incremental re-review on new PR commits
When new commits are pushed to a PR that Pullfrog has previously reviewed,
automatically perform a focused re-review on only the new changes. Includes
a supersede mechanism to abort stale in-flight reviews on rapid pushes, a
new IncrementalReview mode with incremental diff + prior-feedback awareness,
and a PRReview tracking model so re-review fires for both auto-reviewed and
manually-triggered PRs. Reviews now always submit (APPROVE when clean).
Co-authored-by: Cursor <cursoragent@cursor.com>
* simplify re-review eligibility and add summary to incremental reviews
Remove the path1/path2 distinction for re-review eligibility — now simply
requires prReReview=enabled and a prior Pullfrog review on the PR. Show
the re-review toggle regardless of prCreated setting. Add a top-level
summary body to incremental reviews for consistency with full reviews.
Co-authored-by: Cursor <cursoragent@cursor.com>
* replace superseded polling with server-side in-flight dedup and add prApproveEnabled setting
Made-with: Cursor
* add armstrong cursor command
Made-with: Cursor
* update armstrong
* feat: Pullfrogger game v1 (#378)
* Frogger game basis code (CC0 1.0 Unversal license).
* Initial React port.
* fix props for Sprite.
* fixed context issue in FroggerGame.
* Fixed format.
* Fixed lint issue in FroggerGame.
* Restoring LeapingLoader, using FroggerGame as a new fallback in Suspense.
* feat: Display toast when URL ready.
* Add props constraints on Sprite.
* feat: frog sprite.
* fix: zoom and alignment.
* fix: extract const.
* fix: mv types.
* fix: mv game into index.tsx file.
* fix: replacing deprecated event prop which with key.
* feat: Log sprite.
* feat: turtle sprite.
* Adjusting game colors.
* feat: sprites for the cars.
* rm primitive sprites.
* fix: bulldozer sprite position.
* Adjusting colors.
* Shape constraints.
* rm original.
* minor: naming, cleanup.
* fix: renderers dict.
* fix: adjusting and renaming racer.
* fix renderer binding for scored frogs.
* feat: responsive layout with gap below and maintained aspect ratio.
* grammar fix.
* feat: road lane dividers.
* feat: using AbortController to cleanup events.
* fix: cleanup and shortening.
* feat: extracting drawGameBackground.
* feat: initObstacleRows and updateAndDrawObstacles helpers.
* feat: initFroggers helper.
* feat: drawFroggers helper.
* feat: checkForCollision helper.
* feat: makeKeydownHandler helper.
* feat: listenToKeyboardEvents helper.
* mv cleanup into drawGameBackground.
* fix: cleanup.
* feat: better adjustBrightness helper.
* Polling on the page.tsx side, restoring timeout and fallbacks, dynamic link msg.
* FEAT: wait for workflow to complete and notify additionally with a big link (incl.db migration).
* Fix: larger title, shorter link.
* fix(hook): Writing completedAt from hook.workflow_run.updated_at according to suggestion.
* fix(loader): rm unused props from WorkflowRunClientProps as suggested.
* fix(loader): mv id=dev case into the page.
* fix(DNRY): mv PollStartedResult and PollCompletedResult types.
* fix(DNRY): reusing drawEllipse() helper in Sprite.
* fix(style): reordering methods by priority in Sprite.
* fix(frogger): rm empty rows from canvas, square game.
* feat: game canvas rounded corners.
* fix(DNRY): extracting SpriteShape type for faster reference.
* fix: rm target from links, use same window.
* add incremental re-review on new PR commits
When new commits are pushed to a PR that Pullfrog has previously reviewed,
automatically perform a focused re-review on only the new changes. Includes
a supersede mechanism to abort stale in-flight reviews on rapid pushes, a
new IncrementalReview mode with incremental diff + prior-feedback awareness,
and a PRReview tracking model so re-review fires for both auto-reviewed and
manually-triggered PRs. Reviews now always submit (APPROVE when clean).
Co-authored-by: Cursor <cursoragent@cursor.com>
* replace superseded polling with server-side in-flight dedup and add prApproveEnabled setting
Made-with: Cursor
* consolidate workflow_run completed handling and track completedAt
Removes the duplicate exported handleWorkflowRunCompleted in favor of
the private one, merges status + orphan resolution logic into a single
path, and sets completedAt on both normal completion and orphan cancel.
Made-with: Cursor
* fix rebase conflict resolution: restore eligibility logic, incremental review summaries, and exhaustiveness check
- replace deleted hasPullfrogReviewedPR call with WorkflowRun.findFirst
(the utility file was removed by the dedup improvements commit)
- restore IncrementalReview summary body in modes.ts and selectMode.ts
(lost during ca0168b conflict resolution; origin had re-added them via f98f902)
- use switch + satisfies never for workflow_run event dispatch
- lowercase comments per project conventions
Made-with: Cursor
* fix workflow-run polling architecture and improve incremental review prompts
move polling loops from server actions to client to avoid serverless timeouts
(pollForCompleted ran up to 600s in a single invocation). each server action
is now a single DB check; client drives retries. also fix misleading prompt
text about incremental diff scope and remove dead code in handleWebhook.
Made-with: Cursor
* await reportReviewNodeId to eliminate race condition and webhook sleep
- refactor reportReviewNodeId from fire-and-forget to async/awaited,
guaranteeing the dedup signal lands before the tool returns
- remove the 5-second grace period sleep in the synchronize webhook
handler (no longer needed with the awaited PATCH)
- update IncrementalReview guidance to use get_review_comments for
detailed prior line-level feedback instead of just review summaries
- remove dead fallbackUrl field from CheckStartedResult type
Made-with: Cursor
* fix rebase artifacts: broken triggeringIssue reference, review formatting, and prompt wording
Made-with: Cursor
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Anna Bocharova <robin_tail@me.com>
* Standardize on top-level `triggerer` property
- Rename `triggeringUser` → `triggerer` as the single top-level payload property
- Remove redundant `triggerer` from `FixReviewEvent`, add `approvedOnly` boolean
- Auto-apply `approved_by` filtering in `get_review_comments` when `approvedOnly` is set
- Auto-assign created PRs to the triggerer
- Simplify `AddressReviews` mode prompt
- Accept both `triggerer` and `triggeringUser` in schema for backward compat
* Address review feedback: simplify approved_only, remove addAssignees, drop approved_by param
* Fix formatting in `action/mcp/pr.ts`
* re-add triggeringUser backward-compat fallback in payload schema
* auto-assign created PRs to the triggerer
* Revert "auto-assign created PRs to the triggerer"
This reverts commit c088c425fea33793eb299a001ffd253798d2c674.
* Revert "re-add triggeringUser backward-compat fallback in payload schema"
This reverts commit ae5b3cb3f1377cd4a634b2d48962c785c31013f3.
* backend compat
* tweak prompt to ensure compat
* Address review feedback
* chore: remove triggeringUser fallback
---------
Co-authored-by: pullfrog[bot] <226033991+pullfrog[bot]@users.noreply.github.com>
Co-authored-by: Mateusz Burzyński <mateuszburzynski@gmail.com>
Co-authored-by: Colin McDonnell <colinmcd94@gmail.com>
Include actor/account github identity details in installation and repo lifecycle alerting, add shared identity helpers, and tighten CI workflow permission typing for safer validation.
Co-authored-by: Cursor <cursoragent@cursor.com>
- Add `comment_type: "issue"` to `IssueCommentCreatedEvent` interface and
dispatch sites so agents can distinguish issue comments from PR review
comments
- Add dedicated "Progress reporting" section to system prompt making
`report_progress` the mandatory tool for sharing results
- Update `reply_to_review_comment` description to clarify it only works
for inline review comments on PR diffs, not issue comments
Co-authored-by: pullfrog[bot] <226033991+pullfrog[bot]@users.noreply.github.com>
* Scope installation token permissions in restricted mode
In restricted/disabled bash mode, the installation token is now scoped
to match the workflow's permissions block. This preserves fork push
capability while limiting what the agent can do with the token.
- Read workflow permissions from pullfrog.yml at runtime
- Pass permissions to API when acquiring installation token
- Clear OIDC env vars in restricted mode to prevent token minting
- Simplify setupGit by moving token resolution to main.ts
* Address review feedback: fail closed with default permissions
- Add restrictive default permissions (contents:read, pull_requests:read,
issues:read) as fallback when workflow permissions can't be read
- Add support for job-level permissions via GITHUB_JOB env var
- Fix misleading comment about token resolution in restricted mode
- Add documentation about fork PR checkout behavior
* Simplify to separate git/MCP tokens without workflow permission scoping
- gitToken: minimal contents:write only (assumed exfiltratable)
- mcpToken: full installation token (not exfiltratable via MCP tools)
- Remove workflowPermissions.ts - security-conscious users can pass
their own token via GH_TOKEN or inputs.token
- Add type-safe InstallationTokenPermissions to github.ts and API route
* Rename `write` permission to `push` and remove vestigial tool blocking
The `write` permission was previously used to block local file write tools
in agents. This was security theater since bash can write files anyway.
Now `push` only controls the git token scope:
- push: enabled → contents:write (can push commits)
- push: disabled → contents:read (read-only, can't push)
Changes:
- Rename `write` to `push` in action.yml, Prisma schema, and all TS types
- Remove vestigial write tool blocking from all agents (claude, cursor,
gemini, opencode, codex)
- Add data-preserving Prisma migration using RENAME COLUMN
- Update UI: "Write files" → "Git push" with updated description
* add PID namespace isolation for bash sandbox
when running in CI, attempts to use unshare --pid to create a new PID
namespace for bash subprocesses. this prevents the /proc/$PPID/environ
attack where a malicious command could read secrets from the parent
process's environment.
the protection works by:
1. creating a new PID namespace (subprocess becomes PID 1)
2. mounting fresh /proc showing only sandbox PIDs
3. parent PIDs become invisible (PPID = 0, /proc/0 doesn't exist)
combined with filterEnv(), this provides complete protection against
/proc-based secret theft. falls back gracefully if namespaces aren't
available.
includes test script to verify the protection works.
* add PID namespace test to CI workflow
tests whether unshare --pid works on GHA runners out of the box,
and if not, whether enabling via sysctl helps. also runs the
pidNamespace.ts test to verify the full protection.
* fix pnpm setup and add procIsolation agent test
- fix pnpm/action-setup by specifying package_json_file path
- add procIsolation crossagent test that has agent attempt to
read secrets via /proc/$PPID/environ
- add procIsolation to CI test matrix
* add pid-namespace test job to main workflow
this job tests unshare --pid capabilities on GHA runners and runs
the pidNamespace.ts adhoc test to verify /proc isolation works
* test bubblewrap's sysctl approach for enabling namespaces
- write to /etc/sysctl.d/99-userns.conf and run sysctl --system
- try aa-complain on unshare binary
- more detailed diagnostics
* fix pidNamespace test and add sudo-unshare fallback for GHA
- fix reference error in pidNamespace.ts (renamed function but didn't update calls)
- add sudo-unshare as fallback method for GHA runners where unprivileged
namespaces are blocked but sudo is available
- update bash.ts to detect and use sudo unshare when unprivileged fails
* consolidate security docs and document PID namespace isolation
- update security.md with current implementation details
- document sudo unshare fallback for GHA runners
- add testing instructions for local Docker and CI
- add "Further Exploration" section with Landlock and path validation ideas
- delete bash-sandbox.md and landlock.md (consolidated into security.md)
* move procIsolation test to adhoc folder
the procIsolation test requires PID namespace capabilities that aren't
available in the Docker test environment. moved to adhoc/ so it's excluded
from default test runs and can be run explicitly when needed (e.g. via
the pid-namespace CI job or locally with --privileged docker).
* fix Docker test environment for PID namespace isolation
- add CI and GITHUB_ACTIONS to testEnvAllowList so sandbox detection runs
- add --privileged to Docker run for PID namespace support (unshare)
this fixes the test environment to properly test the sandbox. in production,
the action runs directly on GHA runner where sudo unshare works.
* fix getJobToken() to work in test environment
add fallback to GH_TOKEN and GITHUB_TOKEN when INPUT_TOKEN is not set.
this allows tests to run without requiring workflow-level token input.
the token resolution order is:
1. INPUT_TOKEN (from workflow `with: token:`)
2. GH_TOKEN (external token override)
3. GITHUB_TOKEN (pre-acquired in tests or from GHA env)
* security: filter secrets from all subprocess environments
- extract filterEnv() to shared utils/secrets.ts
- make $() utility filter secrets by default (git, npm, etc. don't need them)
- disable git hooks via core.hooksPath to prevent hook-based exfiltration
- git auth uses token embedded in URL, not env vars
this prevents malicious git hooks, npm postinstall scripts, and other
code execution vectors from exfiltrating GITHUB_TOKEN and API keys.
* docs: clarify defense-in-depth security model
update security.md to explain why BOTH layers are required:
- filterEnv(): cleans child's own /proc/self/environ
- PID namespace: hides parent's /proc entries
PID namespace alone isn't sufficient - with --mount-proc, the child
becomes PID 1, so /proc/1/environ is the child's OWN environment.
without filterEnv(), secrets would still be accessible there.
* add procSandbox crossagent test for PID namespace security
- add crossagent/procSandbox.ts: security test that instructs agent to try
various /proc attack vectors and validates sandbox blocks them
- update wiki/security.md: document PID namespace isolation details, add
verification commands, explain why sudo inside sandbox doesn't break security
- update docker.ts: use node:24 with sudo for GHA-like test environment
- update instructions.ts: allow disabling security messaging for pentests
- clean up adhoc test files (procIsolation.ts, securityAudit.ts)
the procSandbox test sets SANDBOX_TEST_TOKEN (matches *_TOKEN filter), gives
the agent explicit hints about attack vectors (/proc, sudo, nsenter, etc.),
disables prompt-based mitigations, and validates the secret is never leaked.
* move procSandbox test to agnostic/ (runs with one agent)
* WIP
* docs: add agent testing guide (pnpm play, Docker, pentesting)
* docs: add CI details to agent testing guide
* docs: add interesting findings and gotchas from pentesting
* improve test fidelity: auto-set CI=true, verify sandbox active
- docker.ts: always set CI=true in container so sandbox activates
- docker.ts: skip sudo/user setup if already done (faster reruns)
- bash.ts: export getSandboxMethod() for diagnostics
- bash.ts: add debug log when sandbox disabled
- procSandbox.ts: add sandbox_was_active check to catch vacuous passes
the CI=true change is critical: without it, PID namespace isolation
is skipped and security tests pass without actually testing anything.
* docs: update agent-testing.md with CI=true auto-set note
* docs: clarify log format is agent-specific
* fix git auth, simplify MCP tools, add adversarial tests
- fix gitWithAuth to use Basic auth format (Bearer doesn't work with git's http.extraheader)
- fix token.ts: push:restricted now correctly gets contents:write
- fix github.ts: pass permissions when acquiring installation tokens locally
- remove commit_files and create_branch MCP tools (redundant, don't require credentials)
- remove containsSecrets() - trivially bypassable, not sound security
- add agnostic adversarial tests: pushDisabled, pushRestricted, tokenExfil
- update instructions.ts to clearly list available git MCP tools
- add wiki/git.md documenting credential isolation and push permission tiers
- update wiki/docker.md with custom image considerations
- update wiki/agent-testing.md with adversarial testing patterns
* fix type errors after rebase
- change ResolveTokensParams.push from ToolPermission to PushPermission
- use tags: ["agnostic"] instead of agnostic: true in test files
* fix cleanup permission error in sandbox tests
when sandbox isolation is enabled (CI=true), files created by the unshare
subprocess may have different ownership, causing rmSync to fail with EACCES.
this error in the finally block was overriding the test's success result.
fix: wrap cleanup in try-catch and fall back to sudo rm if rmSync fails.
* Add adhoc
* Handle git config/remote bypasses
* add git hooks protection and simplify ToolState
- disable git hooks in restricted mode via -c core.hooksPath=/dev/null
- add gitHooks adversarial test to verify hook protection works
- unify prNumber/issueNumber into single issueNumber field
- add pushUrl to ToolState for push validation
- add generateTestMarker() for simpler single-agent test markers
- export SENSITIVE_PATTERNS and isSensitiveEnvName from secrets.ts
- remove redundant pidNamespace.ts (duplicated by procSandbox.ts)
- update documentation
* harden $git() auth: subcommand whitelist, binary tamper detection
- rename gitWithAuth() to $git() with explicit subcommand first arg
- restrict to "fetch" | "push" at type level (filters don't run for these)
- resolve git binary path at startup via resolveGit(), sha256 fingerprint
- verify hash before each $git() call to detect binary replacement
- rename disableHooks to restricted for cleaner semantics
- document filter exfiltration attack and empirical verification in wiki
* remove redundant pid-namespace CI job
the PID namespace isolation testing is now handled by
action/test/agnostic/procSandbox.ts via pnpm runtest agnostic
* fix push_branch for new branches and improve token leak detection
- getPushDestination now falls back to origin/<branch> when @{push}
is not configured (happens for new branches created locally)
- gitPerms validator now checks for actual token patterns instead
of matching "x-access-token" string in test instructions
* use kebab-case for test names
* simplify shell env API: "restricted" | "inherit" | object
replace passFullEnv boolean with cleaner env option that accepts:
- "restricted" (default): filterEnv() to prevent secret leakage
- "inherit": full process.env
- object: custom env merged with restricted base
* share EnvMode and resolveEnv between shell.ts and bash.ts
move shared env resolution logic to secrets.ts
* add env option to bash tool (default: restricted)
* delete agent-testing.md (renamed to adversarial.md)
* Add checkout tests
* reframe githooks test prompt to avoid claude safety refusal
claude was refusing to execute the test because the prompt used words
like "malicious" and "security testing". reframed as a debugging task
with innocuous env var name (TESTING_DEBUG_TAG) per adversarial.md guidance.
Co-authored-by: Cursor <cursoragent@cursor.com>
* clean up verbose token acquisition logs
move logging responsibility to call sites which have better context
(git token vs MCP token). remove redundant intermediate OIDC logs
and unused "(permission-scoped)" suffix.
Co-authored-by: Cursor <cursoragent@cursor.com>
* isolate agnostic tests with matrix strategy, fix .pullfrog-env secret leak
- split action-agnostic into per-test matrix jobs for isolated logs and filesystems
- only write explicitly opted-in env vars to .pullfrog-env via fileAgentEnv
(fixes token-exfil test where claude found SANDBOX_TEST_TOKEN on disk)
- mcpmerge test opts in via fileAgentEnv for cursor's repo-level MCP fallback
Co-authored-by: Cursor <cursoragent@cursor.com>
* remove env parameter from bash tool to prevent agents bypassing filterEnv
the bash tool exposed an `env` parameter accepting "restricted" | "inherit"
which allowed agents to pass env: "inherit" and see all secrets including
SANDBOX_TEST_TOKEN, bypassing the restricted environment filtering entirely.
env mode is now determined internally (always restricted).
Co-authored-by: Cursor <cursoragent@cursor.com>
* use pullfrog/test-repo for push tests to stop polluting main repo
push tests were creating branches and tags on pullfrog/app directly.
now all push tests (push-restricted, push-disabled, push-enabled,
git-permissions) target pullfrog/test-repo instead.
Co-authored-by: Cursor <cursoragent@cursor.com>
* use pullfrog/test-repo for all tests, not just push tests
no test should clone or operate on pullfrog/app directly.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix token scoping for test-repo and bash timeout defaults
- acquireTokenViaOIDC now includes GITHUB_REPOSITORY repo in token
scope so push tests work against pullfrog/test-repo
- bash tool default timeout: 120s -> 30s, cap: 600s -> 120s
- activity timeout: 30s -> 60s
- prevents hung bash commands (e.g. find /) from killing the agent
via activity timeout
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
- Move prompt construction logic from action-side to server-side (webhook handler and trigger page)
- Include issue/comment body in USER PROMPT only if @pullfrog was tagged (checked server-side using containsTriggerPhrase)
- Add repoInstructions as separate REPO-LEVEL INSTRUCTIONS section in FULL prompt
- Macro-expand repoInstructions server-side before sending to action
- Trigger page never includes body (manual triggers)
- Remove redundant customInstructions field (now combined into prompt server-side)
files changed:
- action/external.ts: add repoInstructions to WriteablePayload, remove customInstructions
- action/utils/payload.ts: add repoInstructions to JsonPayload schema, remove customInstructions
- action/utils/repoSettings.ts: add repoInstructions to RepoSettings interface
- action/utils/instructions.ts: use payload.prompt directly, add repo section to full prompt, add repo field to ResolvedInstructions
- utils/webhooks/handleWebhook.ts: check @pullfrog tag and include body if tagged, macro-expand repoInstructions
- app/trigger/[owner]/[repo]/[number]/page.tsx: macro-expand repoInstructions (never include body)
Colin McDonnell