fix(action): sweep stale .git/*.lock and deepen-retry shallow git_fetch (#564) (#578)

- checkoutPrBranch now removes .git/shallow.lock, .git/index.lock, and
  .git/objects/maintenance.lock when older than 30s before the first fetch.
  prior runs that crashed mid-fetch left these behind on self-hosted runners,
  causing checkout_pr to abort with `Unable to create '.git/shallow.lock':
  File exists` until the agent shelled out to rm -f.

- GitFetchTool catches `Could not read <sha>` and `remote did not send all
  necessary objects` on shallow clones and retries once with --deepen=1000
  instead of bouncing the failure back to the agent. agents previously had
  to fall back to checking out FETCH_HEAD, losing branch context.

Co-authored-by: pullfrog[bot] <226033991+pullfrog[bot]@users.noreply.github.com>
Co-authored-by: David Blass <david@arktype.io>

mcp/checkout.ts

@@ -1,5 +1,5 @@
 import { createHash } from "node:crypto";
-import { writeFileSync } from "node:fs";
+import { statSync, unlinkSync, writeFileSync } from "node:fs";
 import { join } from "node:path";
 import type { Octokit, RestEndpointMethodTypes } from "@octokit/rest";
 import { type } from "arktype";
@@ -275,6 +275,39 @@ type CheckoutPrBranchParams = GitContext & {
   beforeSha?: string | undefined;
 };
 
+// stale lock files left over from a crashed/cancelled prior git process block
+// every subsequent fetch with `Unable to create '<path>': File exists`. only
+// sweep locks older than this threshold so we never race a concurrent
+// legitimate git op that's holding the lock.
+const STALE_LOCK_AGE_MS = 30_000;
+
+const GIT_LOCK_PATHS = [
+  ".git/shallow.lock",
+  ".git/index.lock",
+  ".git/objects/maintenance.lock",
+] as const;
+
+function cleanupStaleGitLocks(): void {
+  const now = Date.now();
+  for (const relPath of GIT_LOCK_PATHS) {
+    let mtimeMs: number;
+    try {
+      mtimeMs = statSync(relPath).mtimeMs;
+    } catch {
+      continue;
+    }
+    if (now - mtimeMs < STALE_LOCK_AGE_MS) continue;
+    try {
+      unlinkSync(relPath);
+      log.warning(`» removed stale ${relPath} from prior run`);
+    } catch (e) {
+      log.debug(
+        `» failed to remove stale ${relPath}: ${e instanceof Error ? e.message : String(e)}`
+      );
+    }
+  }
+}
+
 /**
  * Shared helper to checkout a PR branch and configure fork remotes.
  * Assumes origin remote is already configured with authentication.
@@ -296,6 +329,12 @@ export async function checkoutPrBranch(
   rejectIfLeadingDash(pr.baseRef, "PR base ref");
   rejectIfLeadingDash(pr.headRef, "PR head ref");
 
+  // self-hosted runners and cancelled jobs frequently leave stale .git/*.lock
+  // files behind. without this sweep, the first fetch below aborts with
+  // `Unable to create '.git/shallow.lock': File exists` and the agent has to
+  // shell out to `rm -f` (issue #564).
+  cleanupStaleGitLocks();
+
   const isFork = pr.headRepoFullName !== pr.baseRepoFullName;
 
   // always use pr-{number} as local branch name for consistency

mcp/git.ts

@@ -499,6 +499,21 @@ const GitFetch = type({
   depth: type.number.describe("Fetch depth (for shallow clones)").optional(),
 });
 
+// when an agent-supplied depth is too shallow to reach the merge base, git
+// surfaces "Could not read <sha>" and "remote did not send all necessary
+// objects". detect both wordings so a single deepen retry can recover before
+// the error reaches the agent (issue #564). git emits the full OID via
+// oid_to_hex, so the bound is 40 (SHA-1) or 64 (SHA-256).
+const SHALLOW_UNREACHABLE_PATTERNS: RegExp[] = [
+  /Could not read [a-f0-9]{40,64}/,
+  /remote did not send all necessary objects/,
+];
+
+// large enough to clear the merge base on most real-world PRs without
+// downloading the full history; matches the fallback used by checkoutPrBranch
+// when the compare API is unavailable.
+const DEEPEN_RETRY_DEPTH = 1000;
+
 export function GitFetchTool(ctx: ToolContext) {
   return tool({
     name: "git_fetch",
@@ -510,9 +525,22 @@ export function GitFetchTool(ctx: ToolContext) {
       if (params.depth !== undefined) {
         fetchArgs.push(`--depth=${params.depth}`);
       }
-      await $git("fetch", fetchArgs, {
-        token: ctx.gitToken,
-      });
+      try {
+        await $git("fetch", fetchArgs, { token: ctx.gitToken });
+      } catch (err) {
+        const msg = err instanceof Error ? err.message : String(err);
+        const isShallowUnreachable = SHALLOW_UNREACHABLE_PATTERNS.some((p) => p.test(msg));
+        const isShallow =
+          isShallowUnreachable &&
+          $("git", ["rev-parse", "--is-shallow-repository"], { log: false }).trim() === "true";
+        if (!isShallow) throw err;
+        log.info(
+          `» git_fetch hit shallow-unreachable error, retrying with --deepen=${DEEPEN_RETRY_DEPTH}`
+        );
+        await $git("fetch", [`--deepen=${DEEPEN_RETRY_DEPTH}`, "--no-tags", "origin", params.ref], {
+          token: ctx.gitToken,
+        });
+      }
       return { success: true, ref: params.ref };
     }),
   });