57bd10d6dd
* fix(#15): precompute diff anchors in checkout_pr TOC * test(#15): update TOC snapshot for precomputed diff anchors * chore(tests): skip codex-mini-latest models.dev check + refresh latest-by-provider snapshot * fix(#22): add commitCount and commitLog to checkout_pr return * fix(#21): include PR body in checkout_pr return * fix(#5): force-fetch PR refspec to overwrite stale local branch * fix(#31): rename git tool parameter from subcommand to command * fix(#11): soft-fail post-checkout hook, bump timeout to 10min * fix(#16): strengthen diff file usage guidance Agent was bypassing diffPath and running `git diff` instead. Tighten instructions in `checkout_pr` result and remove the mixed-signal "log, diff" listing in the global Git guidance. `git log` and `git diff --stat` remain allowed for commit-range overview. * fix(#20): drop invalid inline review comments instead of failing review Previously, a single inline comment anchored outside a diff hunk would 422 the entire review submission. Pre-validate comments against the PR file patches via listFiles, drop the invalid ones, and append a note to the review body listing what was skipped. Include the dropped list in the tool response so the agent can retry targeted fixes. * fix(#12): stop MCP server on inner activity kill + filter reconnect noise Inner-activity-kill zombies were burning multi-hour runner time because mcp-proxy's SSE reconnect and provider-error retry lines kept the outer activity timer alive long after the agent subprocess was killed. - Filter [mcp-proxy] / "provider error detected" chunks so they don't count as outer-timer activity. - Add onActivityTimeout callback to spawn + thread through agent runs. - main.ts wires that callback to stop the MCP HTTP server (so reconnects finally fail instead of looping) and arms a 5min safety-net timer that force-rejects the outer timer if the agent promise is still pending. * audit: harden #12 lifecycle + cover #20/#12 with unit tests Bugs found during Ralph audit of the prior run-issues fixes: - main.ts's 5min safety-net setTimeout was never cleared on the happy path; also activityTimeout.stop() didn't null the internal rejectFn, so a late forceReject from the safety-net could still reject a long-resolved promise. Timer now cleared in finally; stop() now disarms forceReject. - mcp server disposal was non-idempotent, so the inner-kill path ran server.stop() twice once the outer `await using` block exited. Made the returned disposer idempotent. Tests: - action/mcp/review.test.ts: 14 tests for commentableLinesForFile (multi-hunk, no-count hunks, no-newline marker, empty) and validateInlineComments (file not in diff, wrong side, out-of-range line and start_line, partitioning batches, default side). - action/utils/activity.test.ts: 6 tests for isActivityNoise covering mcp-proxy lines, provider-error lines, mixed chunks, Buffer input. * audit(#22): cap commitLog at 200 + scope git-diff restriction to PR review - cap git log --oneline at 200 entries so a PR with thousands of commits cannot blow up the MCP tool response; expose commitLogTruncated so callers can warn the agent when the log was clipped - tighten instruction wording so `git diff` / `git diff --cached` remain available for inspecting an agent's own uncommitted changes, while PR review content must still come from diffPath Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit(#11,#22,#31): surface hook/commit warnings in instructions + polish git tool - append hookWarning + commitLogTruncated advisories to checkout_pr instructions so the agent actually sees the warning inline, not just as a field it may skip - fix stale 'subcommand' wording in git tool redirect for `pull` and in the `command` parameter description; the MCP parameter is named `command` now, and that's what the agent binds to Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * fix(#20): reassign params.comments even when all inline comments dropped if every inline comment fails pre-validation, the earlier guard skipped reassigning params.comments, so the submission still carried the bad comments and GitHub 422'd on the whole review. always reassign to validation.valid so the downstream 'nothing left to post' skip fires and an otherwise-empty review is no-oped cleanly. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit(#22): degrade gracefully when base ref isn't resolvable checkout_pr used to assume \`origin/<base>\` is always reachable, but it isn't guaranteed after a shallow fetch that only pulled down the PR head. Failing the whole checkout over metadata we added for ergonomics would be a regression, so wrap the rev-list / log in a try/catch and return empty commit metadata instead. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit(#12): anchor noise patterns to line start to avoid false positives before this, a line like "agent said: [mcp-proxy] was there" or "context: provider error detected in log" in real agent output would have been treated as noise and failed to reset the outer activity timer. both patterns now anchor at the start of the (optionally debug-timestamped) line, matching only lines mcp-proxy or our own log.info actually emit. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit(#20): export and unit-test formatDroppedCommentsNote covers single-line `path:N`, multi-line `path:start-end`, and startLine==line fallback so changes to the dropped-comments note format surface in test diffs instead of only in GitHub UI. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit(#20): cap dropped-comment note to stay under GitHub body limit a pathological run (agent emits hundreds of invalid inline comments on a huge PR and they all get dropped) would push the review body past GitHub's ~65KB limit and fail the whole submission with a body-too-long 422 — the exact all-or-nothing failure #20 was meant to prevent. cap the detail list at 50 entries with a "…and N more" line so the note stays bounded. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit(#20): distinguish binary/no-patch files in dropped-comment reason previously a comment on a binary file (or pure rename / mode-only change) was dropped with "line X is not inside a diff hunk", which misleads the agent into retrying with different line numbers. call out the no-textual-diff case explicitly so the agent knows to move that feedback to the review body instead. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit(#11): replace lifecycle timeout string-match with typed sentinel spawn() now rejects with SpawnTimeoutError (code === SPAWN_TIMEOUT_CODE or SPAWN_ACTIVITY_TIMEOUT_CODE) instead of a plain Error. executeLifecycleHook now branches on that code so rewording the error message in subprocess.ts can no longer silently misroute timeouts into the "transient — retry" warning. * audit(#12): route agent hung-vs-failed via typed SpawnTimeoutError claude.ts and opentoad.ts decide between "hung" and "failed" log wording based on the subprocess error. move them off the literal "activity timeout" substring match onto the same SPAWN_ACTIVITY_TIMEOUT_CODE sentinel used by lifecycle.ts so all three call sites agree on the source of truth. * audit(#20): delete leftover pending review when submit fails Why: `createAndSubmitWithFooter` creates a PENDING review first so we can mint Fix-links with the review ID, then submits. If submitReview fails (e.g. 422 from a race where the diff moved between pre-validation and submission), the draft was left on the PR. GitHub only allows one pending review per user, so the agent's retry would then fail with "already has a pending review" — an error the agent has no tools to clean up from. Best-effort cleanup: delete the pending draft on submit failure before re-throwing the original error, so retries start from a clean slate. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit(#31): point agent to concrete alternative when rebase/bisect blocked Why: in disabled-shell mode, `git rebase` and `git bisect` are blocked as arbitrary-code-execution escape hatches. Previous error messages explained *why* but left the agent without a next step — especially painful right after the `pull` redirect, which suggested "merge or rebase locally." The agent would follow that advice, hit the rebase block, and loop without knowing what to try next. Now: rebase block explicitly says "use 'merge' instead"; bisect block notes that manual bisect is also unavailable through this tool; pull redirect no longer recommends rebase in shell-disabled contexts. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit: import security tables into security.test to prevent drift Why: the security tests re-declared AUTH_REQUIRED_REDIRECT, NOSHELL_BLOCKED_SUBCOMMANDS, and NOSHELL_BLOCKED_ARGS inline with hand-copied message strings. When the runtime messages in git.ts were tightened (recent rebase/bisect guidance updates), the test copies drifted and tests validated a stale version of the logic while passing clean. A missing or mistyped entry in git.ts could therefore slip through. Now: export the tables from git.ts and import them into the test file. If a runtime message changes, the tests exercise the new string automatically; if an entry is added or removed, tests covering that command see the change without manual sync. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit: widen pending-review cleanup to cover pre-submit throws getApiUrl() (invoked in footer build) can throw if API_URL is misconfigured, which would leak a pending draft between createReview and the previous submitReview try/catch. Move the try/catch to wrap the entire post-create body so any throw routes through deletePendingReview cleanup. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit: reject leading-dash refs/branch names to block flag injection git's parseopt accepts options intermixed with positional args, so a ref like "--upload-pack=evil" passed to git_fetch could be parsed as a flag rather than a refspec. Add a narrow rejectIfLeadingDash helper to git_fetch (ref), delete_branch (branchName), and push_branch (branchName). HTTPS remotes ignore --upload-pack server-side, but the hygiene matters for defense in depth (ssh remotes, future code paths). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit: validate the resolved branch in push_branch too When branchName is omitted, rev-parse surfaces the current branch name, which could start with '-' if git state was tampered with. Move the leading-dash check to after the branch is resolved so both the explicit and derived paths go through validation. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit: cache commentable-lines snapshot at checkout to match review anchor Review comments are anchored to checkoutSha (commit_id), but validation was hitting pulls.listFiles at review time — latest HEAD, not the SHA the agent actually reviewed. If the PR was updated mid-run, valid comments could be silently dropped (or invalid ones admitted). Snapshot the commentable lines during checkout_pr so review-time validation matches the anchor exactly. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit(#12): route activity monitor's own debug output around the write wrap startProcessOutputMonitor monkey-patches process.stdout.write to mark activity, then called log.debug(...) every 5s to report idle time — which landed right back in its own wrapper, failed isActivityNoise, and called markActivity. with ACTIONS_STEP_DEBUG=true (common on reruns) the idle counter reset every interval and the timeout could never fire, re-creating the #12 zombie-run bug for any debug-enabled run. Fix: capture the original stdout.write and use it directly for the monitor's own diagnostics so they bypass the feedback loop. Added a tight-timeout regression test that asserts the timeout still rejects in debug mode. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit(#12): noise-filter subprocess.ts monitor logs so outer timer survives debug activity.ts's own monitor output already bypasses the wrap (c35cd3fb), but subprocess.ts's spawn activity timer uses log.debug — which goes straight through process.stdout.write and would still mark activity on every interval when debug logging is enabled. Pattern-filter those '(spawn|process) activity (check|timer|monitor)' lines in both local ([DEBUG] ...) and GH-runner (::debug::...) formats so they don't reset the outer agent-hang timer. Kept scoped to those specific monitor messages — a blanket [DEBUG] filter would silently classify any coincidentally-debug-prefixed agent output as idle, which is a worse failure mode than the one we're fixing. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit(#11): surface spawn ENOENT-style errors in stderr buffer spawn() resolved with exitCode=1 and an empty stderr when the command itself couldn't start (missing binary, bad permissions). lifecycle.ts then reported 'output: (empty)' to the user, who was explicitly told 'retry if the failure looks flaky' — so every run hit the same wall with no diagnostic trail. Append the '[spawn] <cmd>: <node error>' line to stderrBuffer before resolving so the real cause (ENOENT, EACCES, …) flows through to the hook-warning message. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit(#11,#12): cover executeLifecycleHook typed-timeout routing the typed SpawnTimeoutError + sentinel-code branching introduced in d7ee7fd2 / ea8dd2c4 classifies hung vs failed lifecycle hooks — critical for whether agents retry — but had no unit coverage. add tests for all four branches (no script, exit 0, non-zero exit with retry-if-flaky guidance, timeout with do-NOT-retry guidance, transient spawn failure). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit: re-verify clean tree after prepush hook the pre-prepush check guarantees we enter the hook with a clean tree, but if the hook writes tracked files (formatter, type generator, build artifacts), the push still only sends the pre-hook commit — the hook's edits silently disappear from the upstream branch while the tool reports "successfully pushed". add a post-hook status check so the agent sees the dropped mutations and can commit or discard them before retrying. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit: reject push_tags refspec injection via ':' in tag name without tag validation, a tag like "foo:refs/heads/main" concatenated into "refs/tags/${tag}" becomes a valid <src>:<dst> refspec — git pushes the local refs/tags/foo's commit to remote main, bypassing push_branch's default-branch guard. same shape blocks leading '-' (flag injection) and other refspec metacharacters (~ ^ ? * [ \) via an allow-list regex. only reachable in push=enabled today, so this is defense-in-depth, but hardens the tool in case push_tags is ever exposed in restricted mode. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit: stop pointing agents at an internal constant they can't change the lifecycle-hook timeout warning told agents to "bump LIFECYCLE_HOOK_TIMEOUT_MS" — but that's a hard-coded constant in the action, not something the agent or repo owner can tune. the agent would plausibly loop hunting for where to change it. redirect to the actual lever they control: ask the repo owner to simplify the hook. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit: drop inverted inline-comment ranges locally with precise reason validateInlineComments only checked that both line and start_line anchor inside a hunk, not that start_line <= line. an inverted range (e.g. start=44, line=42) would pass local validation and GitHub would 422 with "invalid line numbers" — opaque to the agent and unfixable without reading docs. reject locally with a reason that names the constraint. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit: don't let usage-summary write error mask main's outcome writeGitHubUsageSummaryToFile is called in main's finally block. it can throw on ENOSPC / EACCES / missing parent dir. a throw here propagates past the try's successful return or the catch's error return, hiding the actual run outcome behind an I/O failure on a purely informational file. swallow the write error (debug-logged) — the summary is nice-to-have, not load-bearing. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit: don't mislabel agent handler errors as JSON parse failures the onStdout event loop wrapped both JSON.parse and the handler call in one try/catch that logged every caught error as 'non-JSON stdout line'. if a handler threw (e.g. todowrite state shape drift), the error was silently classified as a parse error, making diagnosis impossible. split the try blocks so JSON errors and handler errors get distinct, identifying log lines. * audit: reject leading-dash PR refs before they reach git commands PR head/base refs come from GitHub and are attacker-controlled on fork PRs (the PR author picks headRef freely). they flow straight into `git fetch origin <ref>`, `git checkout -B <ref>`, and config writes. without a leading-dash check, a ref named like '-upload-pack=evil' could be parsed as a flag instead of a refspec. validate both refs at the top of checkoutPrBranch (before any async work) and cover the two attack shapes with unit tests. * audit: cover ActivityTimeout.stop()'s forceReject disarming main.ts's safety-net-timer path depends on ActivityTimeout.stop() nulling out rejectFn so a late safety-net fire after a successful agent run is a no-op. that behavior had no direct coverage — removing the \`rejectFn = null\` in stop() would silently break the happy path (unhandled rejection / spurious failure) without failing any test. add three tests covering: forceReject rejects with the reason, stop() disarms forceReject, and forceReject after timer rejection is an idempotent no-op. * audit: stabilize activity-timeout idleSec against late stdout race * audit: reject 0ms timeout parses to avoid insta-fail from '0m' * audit: surface raw GitHub error on review 422 instead of assuming anchor cause * audit: key commentable-lines cache by PR number to prevent cross-PR drift * audit: enumerate concrete 422 causes and name checkout_pr in review error * audit: stop shipping ralph-loop runtime state in PR history .claude/ralph-loop.local.md and .claude/ralph-loop-prompt.md were accidentally staged in an earlier audit commit. the .local.md suffix is conventional for gitignored runtime state, and the prompt file is per-run harness config — neither should merge to main. ignore the pattern and untrack the existing entries (files remain on disk so the active loop keeps working). * audit: pin commentable-lines cache to checkoutSha, not just PR number a second checkout_pr(N) call advances toolState.checkoutSha at line 305 or 334, then runs fetchAndFormatPrDiff + cache population at line 549. any throw between those two points (rate limit, 5xx, network blip) left the old snapshot keyed to (pullNumber=N) while checkoutSha now points at a different sha. review_pr(N) would reuse the stale snapshot, silently validating comments against the wrong anchor — the original failure this cache was meant to prevent. track commentableLinesCheckoutSha alongside the pull number and require both to match before returning the cache. if either has moved, fall back to listFiles like any other miss. * audit: auto-clear leftover pending review from killed prior runs a workflow timeout or OOM between createReview PENDING and submitReview leaves GitHub holding a pending draft. the next run hits GitHub's one-pending-per-user-per-PR limit and 422s at pending-create, with no way to recover short of a human cleaning up manually. catch 422 at pending-create, list the PR's reviews (GitHub only exposes our own pending to us, so the filter is safe), delete the leftover, and retry once. 404/422 on the cleanup are treated as no-ops (race with another concurrent cleanup or the draft was submitted); any other cleanup error rethrows so the real cause reaches the caller. * audit: extract + unit-test stranded-pending-review cleanup the recovery branch inside createAndSubmitWithFooter had no direct test coverage. a regression in any of its guards (status check, message match, listReviews filter, 404/422 tolerance, non-retryable rethrow) would silently cause either destructive deletes of unrelated reviews or the old failure mode where a stranded pending draft blocks every retry. extract to clearStrandedPendingReview so the cases can be exercised with a mocked octokit, and add tests for each branch — including the load-bearing negative cases (non-422 passthrough, non-pending-review 422 passthrough, no-leftover-found passthrough, non-retryable cleanup error passthrough). no behavior change at the call site. * audit: document concurrent-run race in clearStrandedPendingReview two runs on the same PR using the same GitHub App installation token would both see each other's PENDING draft via listReviews (GitHub exposes PENDING only to the author, and both runs share authorship). the loser's recovery path would delete the winner's active draft, causing the winner's submitReview to 404. no reliable in-request signal distinguishes a genuinely-stranded prior-run draft from an active peer's draft — PENDING reviews have no created_at, and the user field is the same bot in both cases. the correct fix is workflow-level concurrency (a per-PR concurrency key), not a heuristic here. document the limitation so future readers don't try to bolt on a broken heuristic. * audit: report signal-killed subprocesses as failures, not exit code 0 node's close event delivers (code=null, signal=<name>) when a child is killed by signal (OOM killer, segfault, external SIGTERM). the close handler captured only exitCode and coerced null to 0 via `exitCode || 0`, so lifecycle hooks killed by signal were silently reported as successful — lifecycle.ts's `if (result.exitCode !== 0)` check skipped the warning and callers proceeded as if setup/post-checkout/prepush had completed. now capture signal, append "killed by signal <name>" to stderr, and resolve with exitCode=1 when code is null but signal is set. adds a regression test that spawns `kill -KILL \$\$` and asserts a non-zero exit plus the signal-kill marker in stderr. * audit: untrack RUN_ISSUES*.md ralph-loop working docs same pattern called out in 4f14dbf1: these files are per-run harness state and analysis scratch, not merge-to-main deliverables. the TODO literally opens with "Ralph loop instructions:", so it's unambiguously in the same category as .claude/ralph-loop-prompt.md was. files stay on disk so the active loop keeps working. * audit: block refs/... + symbolic-ref bypass of default-branch guard push_branch's restricted-mode guard compared the resolved remoteBranch against defaultBranch with exact-string equality. an agent passing branchName "refs/heads/main" flowed through: rejectIfLeadingDash passed, getPushDestination's fallback preserved the refs/heads/main string as remoteBranch, so "refs/heads/main" !== "main" and the block was skipped, yet git push happily resolved refs/heads/main to the local main commit and pushed to the remote main branch. symbolic refs (HEAD / FETCH_HEAD / ORIG_HEAD / MERGE_HEAD) are the same class of bypass — they resolve to whatever commit they point at, unconstrained by the name-based guard. add rejectSpecialRef to enforce bare branch names at the tool entry, use it in push_branch and delete_branch. checkout_pr only ever assigns pr-<number> as the local branch, so nothing legitimate relied on the refs/... form here. * audit: keep original 422 visible when listReviews fails during pending-review cleanup if listReviews threw (e.g. transient 502, rate limit) during the stranded pending-review recovery path, the listing failure replaced the original 422 "pending review" error when it propagated up through the tool's outer catch. agents then saw a generic server error with no mention of the real blocker and stopped retrying the cleanup. now the listing failure is logged at debug but does not mask the original 422. the caller's retry re-attempts cleanup, which succeeds if the listing failure was transient. * audit: block default-branch deletion even under push: enabled delete_branch required push: enabled, but within that mode the agent could delete the default branch with no local guard. GitHub branch protection usually catches this at the remote, but not every repo has protection configured — and even when it does, relying on remote config for local safety is wrong. pushing to main is reversible (revert, force-push old HEAD); deleting main is not (reflog recovery only, 30-day window). block deletion of the resolved default_branch in DeleteBranchTool regardless of push permission. push: enabled authorizes pushes, not wholesale removal of the repository's primary branch. * audit: attach no-op catch to agentPromise so a late rejection can't crash cleanup agentPromise raced against activityTimeout.promise (and the --timeout timeoutPromise), both of which had .catch(() => {}) handlers. agentPromise did not. if a timeout won the race, agentPromise became stranded and its subsequent rejection was an unhandled rejection — under node 15+'s default unhandled-rejection policy that terminates the process, which would kill main() mid-cleanup and lose the error-reporting and usage-summary work queued in the catch/finally blocks. the race still sees the rejection (the original promise is shared); this catch only prevents node from treating a post-race rejection as unobserved. * audit: close push_branch refspec-injection via ':' / '+' in branchName rejectSpecialRef only forbade leading-dash, `refs/` prefix, and symbolic refs. git push accepts `[+]src[:dst]` refspec syntax, so an agent under push:restricted could smuggle a full refspec through branchName and bypass the downstream exact-string default-branch guard: "evil:refs/heads/main" → push local 'evil' to remote main ":refs/heads/main" → delete remote main ":other" → delete arbitrary branches (outside grant) "+main" → force-push refspec prefix reject ':', '+', '^', '~', '?', '*', '[', '\\', and whitespace — git's own check-ref-format forbids all of them in branch names, so the allow-list cannot false-positive against a legitimate branch. add regression tests. * audit: stop suggesting blocked 'rebase' in push_rejected advice under shell=disabled Why: when push fails with non-fast-forward, the advice told the agent to run 'git rebase origin/...'. In shell=disabled mode the git MCP tool blocks rebase (as an arbitrary-code-execution escape hatch), so the agent's only path forward was to hit the block, read the fallback message, and try merge — one wasted round trip. Now: under shell=disabled we directly suggest 'git merge origin/...', which always works. Under other modes the advice keeps the rebase/merge choice but leads with merge so the example is copy-pastable either way. * audit: harden includeIf cleanup against shell-injection via subsection names setupGit read `includeif.*` keys via `git config --get-regexp`, split on the first space, and fed the result into `execSync(\`git config --unset "${key}"\`)`. git config subsection values preserve arbitrary characters, so a crafted `[includeIf "gitdir:$(touch${IFS}/tmp/pwn)safe"]` entry round-trips through `--get-regexp` with its `$(...)` command substitution intact, survives the split-on-space filter (IFS-bypass leaves the payload space-free), and gets evaluated when interpolated into the shell command. Confirmed reachable as an RCE sink in local repro. Switch to `--get-regexp -z` (null-terminated, no ambiguity on whitespace) and call `$("git", ["config", "--unset-all", key])` which uses spawn-array and never hands the key to a shell. Extract the logic into `removeIncludeIfEntries` and add regression tests covering the injection payload, whitespace-in-subsection keys, benign entries, and the no-op case. * audit: clear SIGKILL escalator on clean SIGTERM exit the overall-timeout path scheduled a 5s SIGKILL follow-up without capturing the timer id. if the child cooperated with SIGTERM and `close` fired promptly, the escalator stayed pending in the event loop for up to 5s — delaying any subsequent clean shutdown (e.g. the main action exiting after an agent timeout) by that long. capture sigkillEscalatorId alongside timeoutId and clear it in both close and error handlers. regression test asserts the active-timer count does not grow past the pre-spawn baseline after a timed-out child exits on SIGTERM. * audit: correct rebase-availability hints to reflect shell=restricted the MCP git tool only blocks rebase when shell=disabled (NOSHELL_BLOCKED_SUBCOMMANDS check in GitTool). under shell=restricted, git({command: "rebase"}) works fine through the tool — NOSHELL_BLOCKED_SUBCOMMANDS doesn't apply. but two agent-facing messages implied rebase is only available with shell=enabled: - AUTH_REQUIRED_REDIRECT["pull"] said "rebase is only available when shell is enabled" - push-rejected integrateStep (non-disabled branch) said "(or 'rebase' if shell is enabled)" under shell=restricted, agents reading these would wrongly think they had to pick merge — pushing them toward merge commits when rebase would have been cleaner. the push-rejected branch is already ternary-gated on shell !== "disabled", so the qualifier there was just redundant noise. * audit: block difftool/mergetool under shell=disabled git difftool -x <cmd> is the short form of --extcmd. the args blocklist only matches --extcmd / --extcmd=*, so -x slipped through and let an agent run arbitrary commands even when shell=disabled. globally blocking -x would false-positive on git cherry-pick -x, which only appends metadata, so block difftool (and mergetool, same shape via mergetool.<name>.cmd) at the subcommand level instead. agents have no legitimate need for either — diffs go through diff/show and merges are resolved by file edits. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * audit: recover stranded PENDING drafts on no-body createReview too The body path already clears a stranded PENDING draft from a prior crashed run via createAndSubmitWithFooter's own try/catch. The no-body path (approve-with-no-feedback or comments-only) called createReview directly — so a PR whose previous body-path run crashed between createReview(PENDING) and submitReview would permanently 422 any subsequent no-body review with "already has a pending review" until a body-path run happened to clear it. Factored out createReviewWithStrandedRecovery so both paths get the same recovery treatment, and added regression tests covering the no-stranded / stranded-and-retry / non-stranded-422-no-retry cases. * audit: reject timeouts past node's setTimeout ceiling a user-supplied timeout like "999h" parses fine (parseTimeString has no upper cap) but falls off the 2^31-1 ms limit setTimeout clamps to 1ms. the agent run would reject with "timed out after 999h" in a single tick. extract a resolveTimeoutMs helper that centralizes the zero/overflow/ unparseable checks (previously scattered behind inline boolean logic in main.ts) and cover the behavior with unit tests including the boundary value. * fix(#22): replace parameter property in SpawnTimeoutError node --experimental-strip-types rejects readonly/public/private param properties in constructors. tests run via node directly (no tsc), so CI was hitting ERR_UNSUPPORTED_TYPESCRIPT_SYNTAX on every action-agents / action-agnostic job before any test code ran. declare the field and assign in the body instead. * audit: tighten git tool description and delete_branch refspec - `git` tool description previously implied `pull` had a dedicated MCP tool alongside `push_branch`/`git_fetch`. it doesn't — the redirect sends the agent back to the same git tool with `command: "merge"` (or `rebase`). update the description to teach this directly instead of letting agents discover it through the redirect error. - `delete_branch` now passes `refs/heads/${branchName}` to `git push --delete` so a same-named tag can't be silently deleted when both exist on the remote. `rejectSpecialRef` already guarantees the bare-name invariant, so the template construction stays injection-safe. Made-with: Cursor * audit: polish review.ts per anneal findings - drop `as "LEFT" | "RIGHT"` cast in `validateInlineComments` — octokit types `side?: string` at the createReview endpoint, so narrow via `c.side === "LEFT" ? "LEFT" : "RIGHT"`. no cast, no redundant annotation — TS infers the literal union from the ternary. - consolidate `clearStrandedPendingReview` from 3 params to 2 by folding `originalErr` into `params`, per AGENTS.md "max 2 parameters" rule. updates both call sites (`createReviewWithStrandedRecovery`, `createAndSubmitWithFooter`) and all 7 test paths. - upgrade `listReviews`-during-cleanup failure log from `log.debug` to `log.info` so operators not running at debug still see that recovery was attempted before the original 422 bubbles up. message now reads "surfacing original 422" to make the intent unambiguous. Made-with: Cursor * audit: signal partial commit metadata in checkout_pr previously a rev-list/log failure (e.g. shallow fetch where `origin/<base>` isn't reachable) silently returned `commitCount: 0, commitLog: ""` — indistinguishable from "this PR has no commits past base", which could mislead review reasoning about scope. add a `commitLogUnavailable: boolean` field to `CheckoutPrResult`, set when the rev-list/log calls throw. instructions footer now tells the agent to treat the values as "unknown" rather than "no commits" in that case. message phrased to cover the rare case where rev-list succeeds but git log throws (partial, not strictly zero) metadata. Made-with: Cursor * audit: fix parseDiffTocEntries to match production ' · diff-<sha>' TOC suffix the regex required $ right after the line range, but formatFilesWithLineNumbers in checkout.ts appends ` · diff-<sha256>` so agents have the GitHub "Files Changed" anchor precomputed. result: tocEntries was always empty on real PR reviews, breakdown.files was empty, and runDiffCoveragePreflight never fired its one-time "read the diff" nudge. add an optional suffix to the regex and a regression test that uses the exact production TOC shape. Made-with: Cursor * audit(#20): skip empty downgraded-APPROVE reviews before they 422 GitHub rejects `event: "COMMENT"` reviews with no body and no inline comments (HTTP 422 "Unprocessable Entity", verified empirically on repos/pullfrog/preview-546-run-issues-fixes/pulls/1). the runtime `prApproveEnabled` downgrade folds approved=true into event=COMMENT when the repo flag is off, so an agent asking to APPROVE a PR with no other feedback produces exactly that rejected shape — but the existing empty-review skip only fired for !approved cases, so the tool POSTed the doomed COMMENT, octokit returned what looked like a success-with- no-persisted-review shape, and agents reported a phantom reviewId that 404s on any subsequent GET. extract the skip decision into `reviewSkipDecision` and add a second branch for approved + !prApproveEnabled + empty. the function returns null when the review should be submitted, so a real bare APPROVE (approved + prApproveEnabled + empty) still goes through unchanged — GitHub accepts empty APPROVE reviews because the stamp itself is the content. surfaced in the PR #546 preview e2e run 24678139563 (reviewId 4141786854 reported by the agent but absent from every reviews listing). TC13 run 24680349445 re-ran the same scenario with prApproveEnabled=enabled and the review persisted correctly, isolating the cause to the downgrade + empty interaction. * audit(#31): drop misleading rebase mention from pull redirect AUTH_REQUIRED_REDIRECT["pull"] and the git tool's top-level description both said "use git_fetch then this tool with command 'merge' (or 'rebase' unless shell is disabled)". the "(or 'rebase' unless shell is disabled)" qualifier is active misinformation when the agent is already running under shell=disabled: rebase is blocked there by NOSHELL_BLOCKED_SUBCOMMANDS, so the suggestion sends the agent into a second block on the next tool call. 3b83ee97 already fixed this pattern for the push-rejected advice at line 248, but the pull redirect at line 280 and the tool description at line 351 were missed. the right copy isn't a conditional qualifier that agents have to parse against their own shell mode — it's just naming the one alternative that works everywhere (merge). agents under shell=restricted/enabled who want rebase can invoke it directly; the redirect doesn't need to advertise it. verified in preview e2e run 24679728733 (TC8 probe 6) where the agent correctly captured the verbatim redirect message under shell=disabled and explicitly flagged the "(or 'rebase' unless shell is disabled)" clause as confusing — the new test in security.test.ts asserts the message names merge and never rebase in every shell mode. * audit: drop vestigial entry/post references + add preview-546 settings util followup to d79860c6 "refactor: flatten action entrypoints" (Apr 10), which moved action.yml from built `entry`/`post` files to source `entry.ts`/`post.ts` but left three stale references lying around: - .gitignore: `action/run/entry` / `action/dispatch/entry` paths no longer exist anywhere in the build. - .github/workflows/pull-from-action.yml: agent instruction told the upstream sync agent to "Ignore `entry` files (they are built artifacts and .gitignored in this repo)". there are no built entry artifacts anymore — entry.ts is source. - .cursor/settings.json: search.exclude pattern "**/entry" excluded the old built files that no longer exist. none of these were load-bearing on their own, but the same drift had already broken preview e2e end-to-end: the pullfrog/template workflow's three-file copy step (cp .../entry, cp .../post) silently failed with cp: no such file on every preview PR since Apr 10. that template fix went to pullfrog/template@7ec7c8d and the preview-546 mirror at @17ab585, which is what unblocked this PR's full e2e validation. also adds scripts/preview-546-settings.ts, the helper used during the e2e validation to show/set/reset DB-level repo settings on the Neon preview branch (push, shell, prApproveEnabled, hook scripts). scoped to this preview repo ID so it can't accidentally mutate prod. * audit(#11): scope removeIncludeIfEntries to repoDir under inherited GIT_* the function takes `repoDir` as the target, but plain execSync / $(...) inherit GIT_DIR, GIT_WORK_TREE, and GIT_INDEX_FILE from the parent process — and `git config --local` honors GIT_DIR over cwd. when this runs as a child of another git invocation (notably the pre-push hook, but also any future caller embedded inside a git subcommand), the cleanup silently targets the outer repo instead of repoDir. latent today because the real caller is ASKPASS setup, which runs before any git-subcommand ancestor exists, but the function's contract still promised the wrong thing — and the test suite hit exactly this bug when invoked through `git push`. - envScopedToRepo() strips GIT_* before both the get-regexp and unset calls, so cwd wins. - swap the $(...) shell helper for execFileSync on the unset call. $() would merge our scoped env with a "restricted" base that's tuned for hook execution (no tokens) — overkill here and it re-introduces the shell-vs-argv distinction this function was explicitly hardened against in a9aa3b2b. execFileSync with argv is the right tool for a call where the key can contain arbitrary characters. - setup.test.ts also strips GIT_* in its own execSync harness so the suite passes identically under `pnpm vitest run`, `pnpm -r test`, and `git push`'s pre-push hook. --------- Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com> Co-authored-by: Colin McDonnell <colinmcd94@gmail.com>
513 lines
23 KiB
TypeScript
513 lines
23 KiB
TypeScript
import { regex } from "arkregex";
|
|
import { type } from "arktype";
|
|
import { log } from "../utils/cli.ts";
|
|
import { $git } from "../utils/gitAuth.ts";
|
|
import { executeLifecycleHook } from "../utils/lifecycle.ts";
|
|
import { $ } from "../utils/shell.ts";
|
|
import type { StoredPushDest, ToolContext } from "./server.ts";
|
|
import { execute, tool } from "./shared.ts";
|
|
|
|
type PushDestination = {
|
|
remoteName: string;
|
|
remoteBranch: string;
|
|
url: string;
|
|
};
|
|
|
|
/**
|
|
* get where git would actually push this branch.
|
|
* prefers the stored destination from toolState (set by checkout_pr) when it
|
|
* matches the current branch, because git config reads can silently fail in
|
|
* certain environments causing pushes to the wrong remote branch.
|
|
*
|
|
* falls back to reading branch.X.pushRemote and branch.X.merge from git config,
|
|
* and finally to origin/<branch> for branches created without checkout_pr.
|
|
*/
|
|
function getPushDestination(
|
|
branch: string,
|
|
storedDest: StoredPushDest | undefined
|
|
): PushDestination {
|
|
// prefer stored destination from checkout_pr when it matches the current branch
|
|
if (storedDest && storedDest.localBranch === branch) {
|
|
log.debug(`using stored push destination: ${storedDest.remoteName}/${storedDest.remoteBranch}`);
|
|
const url = $("git", ["remote", "get-url", "--push", storedDest.remoteName], {
|
|
log: false,
|
|
}).trim();
|
|
return { remoteName: storedDest.remoteName, remoteBranch: storedDest.remoteBranch, url };
|
|
}
|
|
|
|
// fall back to git config (for branches not created by checkout_pr)
|
|
try {
|
|
const pushRemote = $("git", ["config", `branch.${branch}.pushRemote`], { log: false }).trim();
|
|
const merge = $("git", ["config", `branch.${branch}.merge`], { log: false }).trim();
|
|
const remoteBranch = merge.replace(/^refs\/heads\//, "");
|
|
const url = $("git", ["remote", "get-url", "--push", pushRemote], { log: false }).trim();
|
|
return { remoteName: pushRemote, remoteBranch, url };
|
|
} catch {
|
|
// no push config - branch was created locally without checkout_pr
|
|
log.debug(`no push config for ${branch}, falling back to origin/${branch}`);
|
|
const url = $("git", ["remote", "get-url", "--push", "origin"], { log: false }).trim();
|
|
return { remoteName: "origin", remoteBranch: branch, url };
|
|
}
|
|
}
|
|
|
|
/**
|
|
* normalize URL for comparison (handle .git suffix, case)
|
|
*/
|
|
function normalizeUrl(url: string): string {
|
|
return url.replace(/\.git$/, "").toLowerCase();
|
|
}
|
|
|
|
// SECURITY: reject refs/branch names that begin with "-". git's parseopt
|
|
// accepts options intermixed with positional args, so a ref like
|
|
// "--upload-pack=evil" could be interpreted as a flag rather than a refspec.
|
|
export function rejectIfLeadingDash(value: string, kind: string): void {
|
|
if (value.startsWith("-")) {
|
|
throw new Error(`Blocked: ${kind} '${value}' starts with '-' — git could parse it as a flag.`);
|
|
}
|
|
}
|
|
|
|
// SECURITY: branch inputs to push/delete must be bare branch names. a branch
|
|
// name like "refs/heads/main" bypasses the restricted-mode default-branch
|
|
// check below (which does exact-string compare against "main"), and symbolic
|
|
// refs (HEAD / FETCH_HEAD / ORIG_HEAD / MERGE_HEAD) would resolve to
|
|
// whatever commit those refs point at — both routes let an agent push to
|
|
// protected branches even under push: restricted. checkout_pr only ever
|
|
// stores bare names like "pr-123", so nothing legitimate relies on the
|
|
// refs/... form here.
|
|
const SYMBOLIC_REFS = new Set(["HEAD", "FETCH_HEAD", "ORIG_HEAD", "MERGE_HEAD"]);
|
|
export function rejectSpecialRef(value: string, kind: string): void {
|
|
rejectIfLeadingDash(value, kind);
|
|
if (value.startsWith("refs/")) {
|
|
throw new Error(
|
|
`Blocked: ${kind} '${value}' is a fully-qualified ref path. Use a bare branch name (e.g. 'feature/foo' or 'main'), not a 'refs/heads/...' form.`
|
|
);
|
|
}
|
|
if (SYMBOLIC_REFS.has(value)) {
|
|
throw new Error(
|
|
`Blocked: ${kind} '${value}' is a git symbolic ref, not a branch name. Pass the resolved branch name (e.g. 'main'), or omit branchName to push the current branch.`
|
|
);
|
|
}
|
|
// SECURITY: git interprets ':' and leading '+' as refspec syntax, not as
|
|
// part of a branch name. without this check, an agent under push:restricted
|
|
// can smuggle a full refspec through branchName:
|
|
// - "evil:refs/heads/main" → pushes local 'evil' to remote main
|
|
// - ":refs/heads/main" → deletes remote main
|
|
// - ":other" → deletes remote 'other' under push:restricted
|
|
// - "+main" → force-push refspec
|
|
// the default-branch guard downstream is an exact-string compare, so any
|
|
// character that lets git parse the value as <src>:<dst> (or as a force
|
|
// prefix) bypasses it. git's own check-ref-format forbids ':', '+', '^',
|
|
// '~', '?', '*', '[', '\\', and whitespace in branch names, so rejecting
|
|
// them here cannot false-positive against a legitimate branch name.
|
|
const BAD = /[:+^~?*[\\\s]/;
|
|
const badMatch = value.match(BAD);
|
|
if (badMatch) {
|
|
throw new Error(
|
|
`Blocked: ${kind} '${value}' contains '${badMatch[0]}', which git interprets as refspec/revision syntax, not as part of a branch name.`
|
|
);
|
|
}
|
|
}
|
|
|
|
// SECURITY: validate tag names so the push_tags refspec can't be split into
|
|
// a <src>:<dst> refspec that targets a non-tag ref. without this, a tag like
|
|
// "foo:refs/heads/main" becomes "refs/tags/foo:refs/heads/main" and git
|
|
// pushes the local tag's commit to remote main — a back door around the
|
|
// branch-push rules in push_branch. keep the allow-list conservative (git's
|
|
// own check-ref-format forbids far more, but we only need enough to block
|
|
// refspec injection).
|
|
export function validateTagName(tag: string): void {
|
|
rejectIfLeadingDash(tag, "tag");
|
|
if (!/^[A-Za-z0-9._/-]+$/.test(tag)) {
|
|
throw new Error(
|
|
`Blocked: tag '${tag}' contains characters that could be parsed as a refspec or flag. Tags must match [A-Za-z0-9._/-]+.`
|
|
);
|
|
}
|
|
}
|
|
|
|
/**
|
|
* validate that the push destination matches expected URL.
|
|
* pushUrl is set by setupGit (base repo) and updated by checkout_pr (fork repo).
|
|
*/
|
|
function validatePushDestination(ctx: ToolContext, branch: string): PushDestination {
|
|
const pushUrl = ctx.toolState.pushUrl;
|
|
if (!pushUrl) throw new Error("pushUrl not set - setupGit must run before push_branch");
|
|
|
|
const dest = getPushDestination(branch, ctx.toolState.pushDest);
|
|
|
|
if (normalizeUrl(dest.url) !== normalizeUrl(pushUrl)) {
|
|
throw new Error(
|
|
`Push blocked: destination does not match expected repository.\n` +
|
|
`Expected: ${pushUrl}\n` +
|
|
`Actual: ${dest.url}\n` +
|
|
`Git configuration may have been tampered with.`
|
|
);
|
|
}
|
|
|
|
return dest;
|
|
}
|
|
|
|
export const PushBranch = type({
|
|
branchName: type.string
|
|
.describe("The branch name to push (defaults to current branch)")
|
|
.optional(),
|
|
force: type.boolean.describe("Force push (use with caution)").default(false),
|
|
});
|
|
|
|
export function PushBranchTool(ctx: ToolContext) {
|
|
const defaultBranch = ctx.repo.data.default_branch || "main";
|
|
const pushPermission = ctx.payload.push;
|
|
|
|
return tool({
|
|
name: "push_branch",
|
|
description:
|
|
"Push the current branch to the remote repository. Omit branchName to push the current branch (recommended). " +
|
|
"If specifying branchName, use the LOCAL branch name (e.g., 'pr-1'), not the remote branch name. " +
|
|
"The correct remote and remote branch are determined automatically from branch config set by checkout_pr. " +
|
|
"Requires a clean working tree. Runs the repository prepush hook (if configured) before the network push — hook failure means tests/lint or similar in that script failed, not necessarily a Pullfrog timeout. " +
|
|
"Never force push unless explicitly requested. Pushes to the default branch are blocked in restricted mode.",
|
|
parameters: PushBranch,
|
|
execute: execute(async ({ branchName, force }) => {
|
|
// permission check
|
|
if (pushPermission === "disabled") {
|
|
throw new Error("Push is disabled. This repository is configured for read-only access.");
|
|
}
|
|
|
|
const branch = branchName || $("git", ["rev-parse", "--abbrev-ref", "HEAD"], { log: false });
|
|
// check the resolved branch too — rev-parse could surface a weird current
|
|
// branch name that would otherwise bypass the user-facing check. use
|
|
// rejectSpecialRef so "refs/heads/main" and symbolic refs like HEAD
|
|
// can't slip past the default-branch guard below.
|
|
rejectSpecialRef(branch, "branch");
|
|
|
|
// reject push if working tree is dirty — forces agent to commit or discard before pushing
|
|
const status = $("git", ["status", "--porcelain"], { log: false });
|
|
if (status) {
|
|
throw new Error(
|
|
`push blocked: working tree is not clean (tracked changes and/or untracked files). commit, discard, or remove stray artifacts before pushing.\n\n` +
|
|
`git status:\n${status}`
|
|
);
|
|
}
|
|
|
|
// validate push destination matches expected URL
|
|
const pushDest = validatePushDestination(ctx, branch);
|
|
|
|
// block pushes to default branch in restricted mode
|
|
if (pushPermission === "restricted" && pushDest.remoteBranch === defaultBranch) {
|
|
throw new Error(
|
|
`Push blocked: cannot push directly to default branch '${pushDest.remoteBranch}'. ` +
|
|
`Create a feature branch and open a PR instead.`
|
|
);
|
|
}
|
|
|
|
// use refspec when local and remote branch names differ
|
|
const refspec =
|
|
branch === pushDest.remoteBranch ? branch : `${branch}:${pushDest.remoteBranch}`;
|
|
const pushArgs = force
|
|
? ["--force", "-u", pushDest.remoteName, refspec]
|
|
: ["-u", pushDest.remoteName, refspec];
|
|
|
|
// prepush failure should block the push — a passing hook is the gate
|
|
// that protects main from bad pushes.
|
|
const prepushHook = await executeLifecycleHook({
|
|
event: "prepush",
|
|
script: ctx.prepushScript,
|
|
});
|
|
if (prepushHook.warning) {
|
|
throw new Error(prepushHook.warning);
|
|
}
|
|
|
|
// re-verify clean working tree after prepush. a hook that writes tracked
|
|
// files (formatter, type generator, build artifacts) would leave those
|
|
// changes uncommitted — pushing now would silently drop them, and the
|
|
// agent would report a "successful push" of code the hook had expected
|
|
// to be included.
|
|
const postHookStatus = $("git", ["status", "--porcelain"], { log: false });
|
|
if (postHookStatus) {
|
|
throw new Error(
|
|
`push blocked: the prepush hook modified the working tree. those changes are not included in the push. commit or discard them (or change the hook to not mutate tracked files) before retrying.\n\n` +
|
|
`git status:\n${postHookStatus}`
|
|
);
|
|
}
|
|
|
|
log.debug(`pushing ${branch} to ${pushDest.remoteName}/${pushDest.remoteBranch}`);
|
|
if (force) {
|
|
log.warning(`force pushing - this will overwrite remote history`);
|
|
}
|
|
|
|
try {
|
|
await $git("push", pushArgs, {
|
|
token: ctx.gitToken,
|
|
});
|
|
} catch (err) {
|
|
const msg = err instanceof Error ? err.message : String(err);
|
|
if (msg.includes("fetch first") || msg.includes("non-fast-forward")) {
|
|
// git rebase is blocked through the MCP tool when shell is disabled
|
|
// (rebase --exec can execute arbitrary code). merge always works and
|
|
// integrates remote changes cleanly, so suggest it as the default.
|
|
const integrateStep =
|
|
ctx.payload.shell === "disabled"
|
|
? `2. use the git tool to merge the remote branch into yours: git({ command: "merge", args: ["origin/${pushDest.remoteBranch}"] })`
|
|
: `2. use the git tool to rebase or merge your changes on top: git({ command: "merge", args: ["origin/${pushDest.remoteBranch}"] }) (or 'rebase')`;
|
|
throw new Error(
|
|
`push rejected: the remote branch '${pushDest.remoteBranch}' has new commits you don't have locally.\n\n` +
|
|
`to resolve this:\n` +
|
|
`1. use git_fetch to fetch the remote branch: git_fetch({ ref: "${pushDest.remoteBranch}" })\n` +
|
|
`${integrateStep}\n` +
|
|
`3. resolve any merge conflicts if needed\n` +
|
|
`4. retry push_branch`
|
|
);
|
|
}
|
|
throw err;
|
|
}
|
|
|
|
return {
|
|
success: true,
|
|
branch,
|
|
remoteBranch: pushDest.remoteBranch,
|
|
remote: pushDest.remoteName,
|
|
force,
|
|
message: `successfully pushed ${branch} to ${pushDest.remoteName}/${pushDest.remoteBranch}`,
|
|
};
|
|
}),
|
|
});
|
|
}
|
|
|
|
// commands that require authentication - redirect to dedicated tools.
|
|
// exported so tests can exercise the same table the runtime uses.
|
|
//
|
|
// note: the `pull` redirect intentionally does not mention `rebase` — under
|
|
// shell=disabled rebase is itself blocked by NOSHELL_BLOCKED_SUBCOMMANDS, so
|
|
// advertising it here would just send the agent into a second block. agents
|
|
// under shell=restricted/enabled who prefer rebase can invoke it directly;
|
|
// the redirect's job is to name the canonical alternative (merge), which
|
|
// works in all modes.
|
|
export const AUTH_REQUIRED_REDIRECT: Record<string, string> = {
|
|
push: "use the push_branch tool instead — it handles authentication and permission checks.",
|
|
fetch: "use the git_fetch tool instead — it handles authentication.",
|
|
pull: "use git_fetch to fetch the remote ref, then call this git tool with command 'merge' locally.",
|
|
clone: "the repository is already cloned. use checkout_pr for PR branches.",
|
|
};
|
|
|
|
// SECURITY: subcommands blocked when shell is disabled.
|
|
// in disabled mode the agent has no shell access, so these subcommands are the
|
|
// primary escape vectors for arbitrary code execution. in restricted mode the
|
|
// agent already has shell in a stripped sandbox, so blocking these is redundant.
|
|
// exported so tests stay in sync with the runtime table.
|
|
export const NOSHELL_BLOCKED_SUBCOMMANDS: Record<string, string> = {
|
|
config: "Blocked: git config can set up filter drivers or hooks that execute arbitrary code.",
|
|
submodule:
|
|
"Blocked: git submodule can reference malicious repositories and execute code on update.",
|
|
"update-index":
|
|
"Blocked: git update-index can modify index entries in ways that bypass file protections.",
|
|
"filter-branch": "Blocked: git filter-branch executes arbitrary code on repository history.",
|
|
replace: "Blocked: git replace can redirect object lookups.",
|
|
// subcommands that accept --exec or similar flags for arbitrary code execution
|
|
rebase:
|
|
"Blocked: git rebase --exec can execute arbitrary shell commands. Use 'merge' instead to integrate remote changes.",
|
|
bisect:
|
|
"Blocked: git bisect run can execute arbitrary shell commands. Bisect by hand (bisect start/good/bad/reset) is not available through this tool either — ask the user to run the bisect if needed.",
|
|
// difftool/mergetool exist to shell out to external diff/merge programs.
|
|
// both accept `--extcmd` / `-x` (difftool) or configured tool commands
|
|
// (mergetool) that run arbitrary code. NOSHELL_BLOCKED_ARGS catches the
|
|
// long `--extcmd` form, but not the `-x` short form — and globally blocking
|
|
// `-x` would false-positive on `git cherry-pick -x`. block the subcommands
|
|
// wholesale instead; neither has a meaningful use in an automated agent
|
|
// workflow (agents use `git diff` / `git show` for diffs and resolve
|
|
// conflicts via file edits, not a TUI merge tool).
|
|
difftool:
|
|
"Blocked: git difftool runs an external diff program via --extcmd/-x or configured tool and can execute arbitrary shell commands. Use 'diff' (or 'show' for single commits) to inspect changes — those output directly and don't invoke an external tool.",
|
|
mergetool:
|
|
"Blocked: git mergetool runs an external merge program configured via mergetool.<name>.cmd and can execute arbitrary shell commands. Resolve conflicts by editing the files directly (conflict markers are written into the working tree) and then commit.",
|
|
};
|
|
|
|
// SECURITY: subcommand-specific arg flags that execute code.
|
|
// only blocked when shell is disabled — in restricted mode the agent already
|
|
// has shell access in a stripped sandbox, so these provide no additional security.
|
|
//
|
|
// NOTE: global git flags like -c and --config-env are NOT included here
|
|
// because they only work before the subcommand. in the MCP tool, the
|
|
// subcommand is always first, so -c in args is parsed as a subcommand flag
|
|
// (e.g., git log -c = combined diff format), not config injection.
|
|
// the subcommand check (rejecting "-" prefix) already blocks that attack.
|
|
//
|
|
// matched as: arg === flag OR arg starts with flag + "="
|
|
// (avoids false positives like --exclude matching --exec).
|
|
// exported so tests stay in sync with the runtime flag set.
|
|
export const NOSHELL_BLOCKED_ARGS = ["--exec", "--extcmd", "--upload-pack", "--receive-pack"];
|
|
|
|
const COLLAPSE_THRESHOLD = 200;
|
|
|
|
// SECURITY: subcommand must match [a-z][a-z0-9-]* to reject flags passed as the subcommand.
|
|
// this blocks injection of global git options like -c, -C, --exec-path, --config-env, etc.
|
|
//
|
|
// critical attack: git -c "alias.x=!evil-command" x
|
|
// -> sets alias "x" to a shell command via -c config injection, then runs it
|
|
// -> achieves arbitrary code execution even with shell=disabled
|
|
const subcommandPattern = regex("^[a-z][a-z0-9-]*$");
|
|
|
|
const Git = type({
|
|
command: type(subcommandPattern).describe("Git command (e.g., 'status', 'log', 'diff')"),
|
|
args: type.string.array().describe("Additional arguments for the git command").optional(),
|
|
});
|
|
|
|
export function GitTool(ctx: ToolContext) {
|
|
return tool({
|
|
name: "git",
|
|
description:
|
|
"Run git commands. For push/fetch, use the dedicated MCP tools (push_branch, git_fetch). " +
|
|
"git pull is not available — use git_fetch then this tool with command 'merge'.",
|
|
parameters: Git,
|
|
execute: execute(async (params) => {
|
|
const command = params.command;
|
|
const args = params.args ?? [];
|
|
|
|
const redirect = AUTH_REQUIRED_REDIRECT[command];
|
|
if (redirect) {
|
|
throw new Error(`git ${command} is not available through this tool — ${redirect}`);
|
|
}
|
|
|
|
// SECURITY: block dangerous subcommands when shell is disabled.
|
|
// in restricted mode the agent has shell in a stripped sandbox, so blocking
|
|
// these through the MCP tool is redundant (agent can do it via shell).
|
|
if (ctx.payload.shell === "disabled") {
|
|
const blocked = NOSHELL_BLOCKED_SUBCOMMANDS[command];
|
|
if (blocked) {
|
|
throw new Error(blocked);
|
|
}
|
|
|
|
// block subcommand-specific flags that execute arbitrary code
|
|
for (const arg of args) {
|
|
const isBlocked = NOSHELL_BLOCKED_ARGS.some(
|
|
(flag) => arg === flag || arg.startsWith(flag + "=")
|
|
);
|
|
if (isBlocked) {
|
|
throw new Error(
|
|
`Blocked: '${arg}' flag can execute arbitrary code and is not allowed.`
|
|
);
|
|
}
|
|
}
|
|
}
|
|
|
|
const output = $("git", [command, ...args], { log: false });
|
|
const lineCount = output.split("\n").length;
|
|
if (lineCount > COLLAPSE_THRESHOLD) {
|
|
log.group(`git ${command} output (${lineCount} lines)`, () => {
|
|
log.info(output);
|
|
});
|
|
} else if (output) {
|
|
log.info(output);
|
|
}
|
|
|
|
return { success: true, output };
|
|
}),
|
|
});
|
|
}
|
|
|
|
const GitFetch = type({
|
|
ref: type.string.describe("Ref to fetch: branch name, tag, or 'pull/N/head' for PRs"),
|
|
depth: type.number.describe("Fetch depth (for shallow clones)").optional(),
|
|
});
|
|
|
|
export function GitFetchTool(ctx: ToolContext) {
|
|
return tool({
|
|
name: "git_fetch",
|
|
description: "Fetch refs from remote repository. Use this instead of git fetch directly.",
|
|
parameters: GitFetch,
|
|
execute: execute(async (params) => {
|
|
rejectIfLeadingDash(params.ref, "ref");
|
|
const fetchArgs = ["--no-tags", "origin", params.ref];
|
|
if (params.depth !== undefined) {
|
|
fetchArgs.push(`--depth=${params.depth}`);
|
|
}
|
|
await $git("fetch", fetchArgs, {
|
|
token: ctx.gitToken,
|
|
});
|
|
return { success: true, ref: params.ref };
|
|
}),
|
|
});
|
|
}
|
|
|
|
const DeleteBranch = type({
|
|
branchName: type.string.describe("Remote branch to delete"),
|
|
});
|
|
|
|
export function DeleteBranchTool(ctx: ToolContext) {
|
|
const pushPermission = ctx.payload.push;
|
|
const defaultBranch = ctx.repo.data.default_branch || "main";
|
|
|
|
return tool({
|
|
name: "delete_branch",
|
|
description:
|
|
"Delete a remote branch. Requires push: enabled permission. " +
|
|
"Deletion of the repository's default branch is always blocked regardless of permission mode.",
|
|
parameters: DeleteBranch,
|
|
execute: execute(async (params) => {
|
|
if (pushPermission !== "enabled") {
|
|
throw new Error(
|
|
"Branch deletion requires push: enabled permission. " +
|
|
"Current mode only allows pushing to non-protected branches."
|
|
);
|
|
}
|
|
|
|
// delete_branch is already gated on push: enabled, but also block the
|
|
// refs/heads/... and symbolic-ref forms so this tool can't be tricked
|
|
// into deleting a protected ref that wouldn't match a bare-name check.
|
|
rejectSpecialRef(params.branchName, "branchName");
|
|
|
|
// defense-in-depth: deleting the default branch is catastrophic and
|
|
// unlike pushing to main it has no easy revert path (GitHub retains
|
|
// refs for 30 days but restoring requires the reflog or a direct SHA).
|
|
// push: enabled authorizes pushes, not wholesale removal of the
|
|
// repository's primary branch. block it locally even if GitHub branch
|
|
// protection would also reject — some repos disable protection on
|
|
// default branches and we should not rely on that config for safety.
|
|
if (params.branchName === defaultBranch) {
|
|
throw new Error(
|
|
`Blocked: cannot delete the default branch '${defaultBranch}'. ` +
|
|
`If you really need to delete or rename it, do it manually via the repository settings.`
|
|
);
|
|
}
|
|
|
|
// use refs/heads/<name> explicitly so a same-named tag can't be deleted
|
|
// by accident. `push --delete <bare-name>` resolves against both remote
|
|
// branches and tags; a tag-only match would silently remove the tag.
|
|
// rejectSpecialRef guarantees branchName is a bare name, so the
|
|
// branchName construction here can't collide with user-supplied refs.
|
|
await $git("push", ["origin", "--delete", `refs/heads/${params.branchName}`], {
|
|
token: ctx.gitToken,
|
|
});
|
|
return { success: true, deleted: params.branchName };
|
|
}),
|
|
});
|
|
}
|
|
|
|
const PushTags = type({
|
|
tag: type.string.describe("Tag name to push"),
|
|
force: type.boolean.describe("Force push the tag").default(false),
|
|
});
|
|
|
|
export function PushTagsTool(ctx: ToolContext) {
|
|
const pushPermission = ctx.payload.push;
|
|
|
|
return tool({
|
|
name: "push_tags",
|
|
description: "Push a tag to remote. Requires push: enabled permission.",
|
|
parameters: PushTags,
|
|
execute: execute(async (params) => {
|
|
if (pushPermission !== "enabled") {
|
|
throw new Error(
|
|
"Tag pushing requires push: enabled permission. " +
|
|
"Current mode only allows pushing branches."
|
|
);
|
|
}
|
|
|
|
validateTagName(params.tag);
|
|
const pushArgs = [...(params.force ? ["-f"] : []), "origin", `refs/tags/${params.tag}`];
|
|
await $git("push", pushArgs, {
|
|
token: ctx.gitToken,
|
|
});
|
|
return { success: true, tag: params.tag };
|
|
}),
|
|
});
|
|
}
|