Harden remote workspace sync and restore flows (#5444)

## Thinking Path

> - Paperclip orchestrates AI agents for zero-human companies
> - When an agent runs against a remote target, Paperclip syncs the
workspace out to the remote at run start and restores changes back to
the local workspace at run end
> - The previous restore flow naïvely overwrote local files with
whatever the remote returned, so files that the remote run never touched
but had timestamp/mode drift could be needlessly rewritten — and a
single static `refs/paperclip/ssh-sync/imported` ref made concurrent SSH
workspace exports race on the same git ref
> - This pull request adds a `workspace-restore-merge` module that diffs
a pre-run snapshot against the post-run remote state and only writes
back files the remote actually changed; SSH workspace exports now use a
per-import unique ref so concurrent runs can't trample each other
> - Every adapter's execute path threads the snapshot through
`prepareAdapterExecutionTargetRuntime` so the merge has the baseline it
needs
> - The benefit is workspace restores no longer churn untouched files,
and concurrent SSH runs no longer collide on the import ref

## What Changed

- `packages/adapter-utils/src/workspace-restore-merge.{ts,test.ts}`: new
module — directory snapshot (kind/mode/sha256/symlink target) plus
snapshot-aware merge that writes only the files the remote changed
- `packages/adapter-utils/src/ssh.ts`: SSH workspace export uses a
per-import unique ref (`refs/paperclip/ssh-sync/imported/<uuid>`);
restore goes through the new merge helper; `ssh-fixture.test.ts` covers
the unique-ref + merge paths
- `packages/adapter-utils/src/sandbox-managed-runtime.ts` +
`remote-managed-runtime.ts`: thread the snapshot/merge through the
sandbox and SSH paths
- `packages/adapter-utils/src/server-utils.{ts,test.ts}` +
`execution-target.ts`: helpers for capturing the pre-run snapshot;
`prepareAdapterExecutionTargetRuntime` gains required `runId` and
optional `workspaceRemoteDir`, and returns the realized
`workspaceRemoteDir`
- Each adapter's `execute.ts` (acpx, claude, codex, cursor, gemini,
opencode, pi) takes the snapshot at run start and passes it through to
the runtime restore
- Remote execute test mocks updated to match the new
`prepareWorkspaceForSshExecution` return shape and the per-run
`${managedRemoteWorkspace}` cwd subdirectory

## Verification

- `pnpm vitest run --no-coverage --project @paperclipai/adapter-utils
--project @paperclipai/adapter-acpx-local --project
@paperclipai/adapter-claude-local --project
@paperclipai/adapter-codex-local --project
@paperclipai/adapter-cursor-local --project
@paperclipai/adapter-gemini-local --project
@paperclipai/adapter-opencode-local --project
@paperclipai/adapter-pi-local` — 196/196 passing
- `pnpm typecheck` clean across the workspace

## Risks

Medium. The restore path now writes a strict subset of what it
previously did — files the remote did not touch are no longer rewritten.
If any flow was relying on a touch-without-content-change being copied
back (timestamp or permission propagation only), that behavior is now
skipped. Snapshot capture adds an O(N-files-in-workspace) hash pass at
run start; the cost is bounded by the existing exclude list. The `runId`
parameter on `prepareAdapterExecutionTargetRuntime` is now required —
every in-tree caller is updated; out-of-tree adapter authors need to
pass it.

## Model Used

Claude Opus 4.7 (1M context)

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable — new module +
every adapter execute path covered
- [x] If this change affects the UI, I have included before/after
screenshots — N/A (no UI)
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
This commit is contained in:
Devin Foley
2026-05-07 14:44:45 -07:00
committed by GitHub
parent 824298f414
commit 12cb7b40fd
23 changed files with 1234 additions and 183 deletions
@@ -6,6 +6,7 @@ import { inferOpenAiCompatibleBiller, type AdapterExecutionContext, type Adapter
import {
adapterExecutionTargetIsRemote,
adapterExecutionTargetRemoteCwd,
overrideAdapterExecutionTargetRemoteCwd,
adapterExecutionTargetSessionIdentity,
adapterExecutionTargetSessionMatches,
adapterExecutionTargetUsesManagedHome,
@@ -26,16 +27,15 @@ import {
asNumber,
asStringArray,
parseObject,
applyPaperclipWorkspaceEnv,
buildPaperclipEnv,
joinPromptSections,
buildInvocationEnvForLogs,
ensureAbsoluteDirectory,
ensurePaperclipSkillSymlink,
ensurePathInEnv,
refreshPaperclipWorkspaceEnvForExecution,
renderTemplate,
renderPaperclipWakePrompt,
shapePaperclipWorkspaceEnvForExecution,
stringifyPaperclipWakePayload,
DEFAULT_PAPERCLIP_AGENT_PROMPT_TEMPLATE,
runChildProcess,
@@ -220,13 +220,7 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
const useConfiguredInsteadOfAgentHome = workspaceSource === "agent_home" && configuredCwd.length > 0;
const effectiveWorkspaceCwd = useConfiguredInsteadOfAgentHome ? "" : workspaceCwd;
const cwd = effectiveWorkspaceCwd || configuredCwd || process.cwd();
const effectiveExecutionCwd = adapterExecutionTargetRemoteCwd(executionTarget, cwd);
const shapedWorkspaceEnv = shapePaperclipWorkspaceEnvForExecution({
workspaceCwd: effectiveWorkspaceCwd,
workspaceHints,
executionTargetIsRemote,
executionCwd: effectiveExecutionCwd,
});
let effectiveExecutionCwd = adapterExecutionTargetRemoteCwd(executionTarget, cwd);
await ensureAbsoluteDirectory(cwd, { createIfMissing: true });
const openCodeSkillEntries = await readPaperclipRuntimeSkillEntries(config, __moduleDir);
const desiredOpenCodeSkillNames = resolvePaperclipDesiredSkillNames(config, openCodeSkillEntries);
@@ -276,20 +270,19 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
if (approvalStatus) env.PAPERCLIP_APPROVAL_STATUS = approvalStatus;
if (linkedIssueIds.length > 0) env.PAPERCLIP_LINKED_ISSUE_IDS = linkedIssueIds.join(",");
if (wakePayloadJson) env.PAPERCLIP_WAKE_PAYLOAD_JSON = wakePayloadJson;
applyPaperclipWorkspaceEnv(env, {
workspaceCwd: shapedWorkspaceEnv.workspaceCwd,
refreshPaperclipWorkspaceEnvForExecution({
env,
envConfig,
workspaceCwd: effectiveWorkspaceCwd,
workspaceSource,
workspaceId,
workspaceRepoUrl,
workspaceRepoRef,
workspaceHints,
agentHome,
executionTargetIsRemote,
executionCwd: effectiveExecutionCwd,
});
if (shapedWorkspaceEnv.workspaceHints.length > 0) {
env.PAPERCLIP_WORKSPACES_JSON = JSON.stringify(shapedWorkspaceEnv.workspaceHints);
}
for (const [key, value] of Object.entries(envConfig)) {
if (typeof value === "string") env[key] = value;
}
// Prevent OpenCode from writing an opencode.json config file into the
// project working directory (which would pollute the git repo). Model
// selection is already handled via the --model CLI flag. Set after the
@@ -353,6 +346,7 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
`[paperclip] Syncing workspace and OpenCode runtime assets to ${describeAdapterExecutionTarget(executionTarget)}.\n`,
);
const preparedExecutionTargetRuntime = await prepareAdapterExecutionTargetRuntime({
runId,
target: executionTarget,
adapterKey: "opencode",
workspaceLocalDir: cwd,
@@ -373,6 +367,20 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
],
});
restoreRemoteWorkspace = () => preparedExecutionTargetRuntime.restoreWorkspace();
effectiveExecutionCwd = preparedExecutionTargetRuntime.workspaceRemoteDir ?? effectiveExecutionCwd;
refreshPaperclipWorkspaceEnvForExecution({
env: preparedRuntimeConfig.env,
envConfig,
workspaceCwd: effectiveWorkspaceCwd,
workspaceSource,
workspaceId,
workspaceRepoUrl,
workspaceRepoRef,
workspaceHints,
agentHome,
executionTargetIsRemote,
executionCwd: effectiveExecutionCwd,
});
remoteRuntimeRootDir = preparedExecutionTargetRuntime.runtimeRootDir;
const managedHome = adapterExecutionTargetUsesManagedHome(executionTarget);
if (managedHome && preparedExecutionTargetRuntime.runtimeRootDir) {
@@ -410,10 +418,11 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
graceSec,
});
}
if (executionTargetIsRemote && adapterExecutionTargetUsesPaperclipBridge(executionTarget)) {
const runtimeExecutionTarget = overrideAdapterExecutionTargetRemoteCwd(executionTarget, effectiveExecutionCwd);
if (executionTargetIsRemote && adapterExecutionTargetUsesPaperclipBridge(runtimeExecutionTarget)) {
paperclipBridge = await startAdapterExecutionTargetPaperclipBridge({
runId,
target: executionTarget,
target: runtimeExecutionTarget,
runtimeRootDir: remoteRuntimeRootDir,
adapterKey: "opencode",
hostApiToken: preparedRuntimeConfig.env.PAPERCLIP_API_KEY,
@@ -440,7 +449,7 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
const canResumeSession =
runtimeSessionId.length > 0 &&
(runtimeSessionCwd.length === 0 || path.resolve(runtimeSessionCwd) === path.resolve(effectiveExecutionCwd)) &&
adapterExecutionTargetSessionMatches(runtimeRemoteExecution, executionTarget);
adapterExecutionTargetSessionMatches(runtimeRemoteExecution, runtimeExecutionTarget);
const sessionId = canResumeSession ? runtimeSessionId : null;
if (executionTargetIsRemote && runtimeSessionId && !canResumeSession) {
await onLog(
@@ -550,7 +559,7 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
});
}
const proc = await runAdapterExecutionTargetProcess(runId, executionTarget, command, args, {
const proc = await runAdapterExecutionTargetProcess(runId, runtimeExecutionTarget, command, args, {
cwd,
env: preparedRuntimeConfig.env,
stdin: prompt,
@@ -596,7 +605,7 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
...(workspaceRepoRef ? { repoRef: workspaceRepoRef } : {}),
...(executionTargetIsRemote
? {
remoteExecution: adapterExecutionTargetSessionIdentity(executionTarget),
remoteExecution: adapterExecutionTargetSessionIdentity(runtimeExecutionTarget),
}
: {}),
} as Record<string, unknown>)