Files
paperclip/packages/adapters/codex-local/src/server/execute.ts
T
Devin Foley 07e98d2b2c feat(adapter-utils): add observable sandbox sync progress (#8395)
## Thinking Path

> - Paperclip is the control plane for running AI-agent companies, so
long-running remote work needs to stay observable to human operators.
> - Cloud / sandbox agents are an active roadmap area, and their
workspace sync path is part of the runtime substrate every remote coding
run depends on.
> - In the sandbox and SSH execution-target flows, Paperclip logged that
sync had started, then often went silent for the full transfer window.
> - That made large remote syncs feel stalled and also hid a real
performance problem in the command-managed sandbox upload path.
> - The first part of this pull request threads a throttled
progress-reporting surface through the adapter execution-target stack so
sync and restore work can emit meaningful updates.
> - The second part fixes the command-managed sandbox transport itself:
it removes the old serial 32KB append bottleneck, but also falls back
away from the single-stream path when a provider-backed sandbox runner
cannot surface mid-flight stdin progress.
> - The result is that sandbox and SSH transfers are both faster and
more observable, including the live Daytona-style sandbox case that
previously only emitted `0%` and `100%`.

## Linked Issues or Issue Description

No public GitHub issue exists for this bug, so it is described inline
below following the bug report template.

### What happened

- Remote sandbox and SSH workspace syncs could spend a long time
transferring data while only logging a start line (`Syncing workspace
and runtime assets to sandbox environment`) and, at best, a terminal
line.
- In the command-managed sandbox path, the original upload
implementation also paid a large performance cost by appending base64
data in many small sequential remote writes (thousands of serial 32KB
round-trips on a large workspace).
- After the initial transport rewrite, live provider-backed sandbox runs
still only emitted `0%` and `100%` because the single-stream stdin RPC
buffered progress until completion.

### Expected behavior

- Long-running sandbox and SSH syncs should periodically report how much
of the transfer is complete (a percentage and/or MB transferred) so an
operator can tell the run is healthy and making progress rather than
stuck.
- The main sandbox upload path should not be artificially slow.
- A transfer that fails partway should leave an explicit failure marker
in the log rather than a dangling intermediate percentage.

### Steps to reproduce

1. Run an agent against a sandbox (command-managed) or SSH
(remote-managed) execution target with a non-trivial workspace.
2. Watch the run log during the workspace/runtime asset sync phase.
3. Observe that the log shows the sync start line and then stays silent
for the full transfer (live provider-backed sandbox runs only show `0%`
then `100%`).

### Paperclip version or commit

- Branch `PAPA-825-provide-status-updates-when-syncing-sandboxes` off
`master`.

### Deployment mode

- Self-hosted / local instance using sandbox (command-managed) and SSH
(remote-managed) execution targets, including provider-backed sandbox
runners.

## What Changed

- Added shared throttled runtime progress reporting and threaded
`onProgress` through the adapter execution-target surface and adapter
`execute.ts` entrypoints.
- Added sync and restore progress reporting for the command-managed
sandbox path and the SSH/remote-managed path, including git
import/export progress where totals are known.
- Reworked command-managed sandbox transfer behavior so uploads use the
faster single-stream path when appropriate, but fall back to chunked
progress-emitting writes when the runner cannot expose mid-stream stdin
progress.
- Marked provider-backed environment sandbox runners as not supporting
single-stream stdin progress so live sandbox runs emit meaningful
intermediate updates instead of only `0%` and `100%`.
- Emit an explicit terminal failure marker (`failed at NN% (x/y MB)`)
when an SSH/tar transfer rejects, so a failed sync no longer leaves a
dangling intermediate percentage in the log.
- Run the SSH sync/restore size estimate (local directory walk / remote
`du` probe) concurrently with the transfer instead of awaiting it before
opening the pipe, so progress instrumentation no longer adds startup
latency proportional to workspace file count.
- Added and extended focused regression coverage for runtime progress
throttling and the new failure marker, command-managed sandbox
transfers, sandbox orchestration, SSH transfer progress, and environment
execution-target wiring.

## Verification

- `pnpm exec vitest run
packages/adapter-utils/src/runtime-progress.test.ts
packages/adapter-utils/src/ssh-fixture.test.ts
packages/adapter-utils/src/command-managed-runtime.test.ts
packages/adapter-utils/src/sandbox-managed-runtime.test.ts`
- `pnpm exec vitest run
packages/adapter-utils/src/command-managed-runtime.test.ts
server/src/__tests__/environment-execution-target.test.ts`
- `npx tsc --noEmit` for `packages/adapter-utils`

## Risks

- The provider-backed sandbox fallback now prefers chunked
command-managed writes when progress hooks are active, so
small-to-medium uploads may trade some raw throughput for observable
intermediate progress on runtimes that cannot surface true mid-stream
stdin progress.
- Progress percentages on tar-based transfers still depend on estimates
in some cases, so operators may briefly see MB-only lines before the
estimate resolves, then near-final clamping before the terminal `100%`
line.
- This PR changes shared execution-target behavior used by multiple
adapters, so regressions would most likely appear in remote runtime
setup/teardown flows rather than in a single adapter.

## Model Used

- Initial implementation: OpenAI GPT-5.4 via Codex local agent
(`codex_local`), high reasoning mode.
- Observability follow-ups (failure marker, concurrent size estimate,
added tests): Claude Opus 4.8 via Claude Code (`claude_local`).

## 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 searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [ ] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [ ] I will address all Greptile and reviewer comments before
requesting merge

---------

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-06-20 13:03:42 -07:00

891 lines
35 KiB
TypeScript

import fs from "node:fs/promises";
import path from "node:path";
import { fileURLToPath } from "node:url";
import { inferOpenAiCompatibleBiller, type AdapterExecutionContext, type AdapterExecutionResult } from "@paperclipai/adapter-utils";
import {
adapterExecutionTargetIsRemote,
adapterExecutionTargetRemoteCwd,
overrideAdapterExecutionTargetRemoteCwd,
adapterExecutionTargetSessionIdentity,
adapterExecutionTargetSessionMatches,
adapterExecutionTargetUsesPaperclipBridge,
describeAdapterExecutionTarget,
ensureAdapterExecutionTargetCommandResolvable,
ensureAdapterExecutionTargetRuntimeCommandInstalled,
prepareAdapterExecutionTargetRuntime,
readAdapterExecutionTarget,
resolveAdapterExecutionTargetTimeoutSec,
resolveAdapterExecutionTargetCommandForLogs,
runAdapterExecutionTargetProcess,
startAdapterExecutionTargetPaperclipBridge,
} from "@paperclipai/adapter-utils/execution-target";
import {
asString,
asNumber,
parseObject,
buildPaperclipEnv,
buildInvocationEnvForLogs,
ensureAbsoluteDirectory,
ensurePaperclipSkillSymlink,
ensurePathInEnv,
refreshPaperclipWorkspaceEnvForExecution,
readPaperclipRuntimeSkillEntries,
readPaperclipIssueWorkModeFromContext,
resolvePaperclipDesiredSkillNames,
renderTemplate,
renderPaperclipWakePrompt,
stringifyPaperclipWakePayload,
DEFAULT_PAPERCLIP_AGENT_PROMPT_TEMPLATE,
joinPromptSections,
} from "@paperclipai/adapter-utils/server-utils";
import {
parseCodexJsonl,
extractCodexRetryNotBefore,
isCodexTransientUpstreamError,
isCodexUnknownSessionError,
} from "./parse.js";
import { pathExists, prepareManagedCodexHome, resolveManagedCodexHomeDir, resolveSharedCodexHomeDir } from "./codex-home.js";
import { prepareCodexRuntimeConfig } from "./runtime-config.js";
import { resolveCodexDesiredSkillNames } from "./skills.js";
import { buildCodexExecArgs } from "./codex-args.js";
import { SANDBOX_INSTALL_COMMAND } from "../index.js";
const __moduleDir = path.dirname(fileURLToPath(import.meta.url));
const CODEX_ROLLOUT_NOISE_RE =
/^\d{4}-\d{2}-\d{2}T[^\s]+\s+ERROR\s+codex_core::rollout::list:\s+state db missing rollout path for thread\s+[a-z0-9-]+$/i;
function stripCodexRolloutNoise(text: string): string {
const parts = text.split(/\r?\n/);
const kept: string[] = [];
for (const part of parts) {
const trimmed = part.trim();
if (!trimmed) {
kept.push(part);
continue;
}
if (CODEX_ROLLOUT_NOISE_RE.test(trimmed)) continue;
kept.push(part);
}
return kept.join("\n");
}
function firstNonEmptyLine(text: string): string {
return (
text
.split(/\r?\n/)
.map((line) => line.trim())
.find(Boolean) ?? ""
);
}
function hasNonEmptyEnvValue(env: Record<string, string>, key: string): boolean {
const raw = env[key];
return typeof raw === "string" && raw.trim().length > 0;
}
function resolveCodexBillingType(env: Record<string, string>): "api" | "subscription" {
// Codex uses API-key auth when OPENAI_API_KEY is present; otherwise rely on local login/session auth.
return hasNonEmptyEnvValue(env, "OPENAI_API_KEY") ? "api" : "subscription";
}
function resolveCodexBiller(env: Record<string, string>, billingType: "api" | "subscription"): string {
const openAiCompatibleBiller = inferOpenAiCompatibleBiller(env, "openai");
if (openAiCompatibleBiller === "openrouter") return "openrouter";
return billingType === "subscription" ? "chatgpt" : openAiCompatibleBiller ?? "openai";
}
async function isLikelyPaperclipRepoRoot(candidate: string): Promise<boolean> {
const [hasWorkspace, hasPackageJson, hasServerDir, hasAdapterUtilsDir] = await Promise.all([
pathExists(path.join(candidate, "pnpm-workspace.yaml")),
pathExists(path.join(candidate, "package.json")),
pathExists(path.join(candidate, "server")),
pathExists(path.join(candidate, "packages", "adapter-utils")),
]);
return hasWorkspace && hasPackageJson && hasServerDir && hasAdapterUtilsDir;
}
async function isLikelyPaperclipRuntimeSkillPath(
candidate: string,
skillName: string,
options: { requireSkillMarkdown?: boolean } = {},
): Promise<boolean> {
if (path.basename(candidate) !== skillName) return false;
const skillsRoot = path.dirname(candidate);
if (path.basename(skillsRoot) !== "skills") return false;
if (options.requireSkillMarkdown !== false && !(await pathExists(path.join(candidate, "SKILL.md")))) {
return false;
}
let cursor = path.dirname(skillsRoot);
for (let depth = 0; depth < 6; depth += 1) {
if (await isLikelyPaperclipRepoRoot(cursor)) return true;
const parent = path.dirname(cursor);
if (parent === cursor) break;
cursor = parent;
}
return false;
}
async function pruneBrokenUnavailablePaperclipSkillSymlinks(
skillsHome: string,
allowedSkillNames: Iterable<string>,
onLog: AdapterExecutionContext["onLog"],
) {
const allowed = new Set(Array.from(allowedSkillNames));
const entries = await fs.readdir(skillsHome, { withFileTypes: true }).catch(() => []);
for (const entry of entries) {
if (allowed.has(entry.name) || !entry.isSymbolicLink()) continue;
const target = path.join(skillsHome, entry.name);
const linkedPath = await fs.readlink(target).catch(() => null);
if (!linkedPath) continue;
const resolvedLinkedPath = path.resolve(path.dirname(target), linkedPath);
if (await pathExists(resolvedLinkedPath)) continue;
if (
!(await isLikelyPaperclipRuntimeSkillPath(resolvedLinkedPath, entry.name, {
requireSkillMarkdown: false,
}))
) {
continue;
}
await fs.unlink(target).catch(() => {});
await onLog(
"stdout",
`[paperclip] Removed stale Codex skill "${entry.name}" from ${skillsHome}\n`,
);
}
}
function resolveCodexSkillsDir(codexHome: string): string {
return path.join(codexHome, "skills");
}
type EnsureCodexSkillsInjectedOptions = {
skillsHome?: string;
skillsEntries?: Array<{ key: string; runtimeName: string; source: string }>;
desiredSkillNames?: string[];
linkSkill?: (source: string, target: string) => Promise<void>;
};
type CodexTransientFallbackMode =
| "same_session"
| "safer_invocation"
| "fresh_session"
| "fresh_session_safer_invocation";
function readCodexTransientFallbackMode(context: Record<string, unknown>): CodexTransientFallbackMode | null {
const value = asString(context.codexTransientFallbackMode, "").trim();
switch (value) {
case "same_session":
case "safer_invocation":
case "fresh_session":
case "fresh_session_safer_invocation":
return value;
default:
return null;
}
}
function fallbackModeUsesSaferInvocation(mode: CodexTransientFallbackMode | null): boolean {
return mode === "safer_invocation" || mode === "fresh_session_safer_invocation";
}
function fallbackModeUsesFreshSession(mode: CodexTransientFallbackMode | null): boolean {
return mode === "fresh_session" || mode === "fresh_session_safer_invocation";
}
function buildCodexTransientHandoffNote(input: {
previousSessionId: string | null;
fallbackMode: CodexTransientFallbackMode;
continuationSummaryBody: string | null;
}): string {
return [
"Paperclip session handoff:",
input.previousSessionId ? `- Previous session: ${input.previousSessionId}` : "",
"- Rotation reason: repeated Codex transient remote-compaction failures",
`- Fallback mode: ${input.fallbackMode}`,
input.continuationSummaryBody
? `- Issue continuation summary: ${input.continuationSummaryBody.slice(0, 1_500)}`
: "",
"Continue from the current task state. Rebuild only the minimum context you need.",
]
.filter(Boolean)
.join("\n");
}
export async function ensureCodexSkillsInjected(
onLog: AdapterExecutionContext["onLog"],
options: EnsureCodexSkillsInjectedOptions = {},
) {
const allSkillsEntries = options.skillsEntries ?? await readPaperclipRuntimeSkillEntries({}, __moduleDir);
const desiredSkillNames =
options.desiredSkillNames ?? allSkillsEntries.map((entry) => entry.key);
const desiredSet = new Set(desiredSkillNames);
const skillsEntries = allSkillsEntries.filter((entry) => desiredSet.has(entry.key));
if (skillsEntries.length === 0) return;
const skillsHome = options.skillsHome ?? resolveCodexSkillsDir(resolveSharedCodexHomeDir());
await fs.mkdir(skillsHome, { recursive: true });
const linkSkill = options.linkSkill;
for (const entry of skillsEntries) {
const target = path.join(skillsHome, entry.runtimeName);
try {
const existing = await fs.lstat(target).catch(() => null);
if (existing?.isSymbolicLink()) {
const linkedPath = await fs.readlink(target).catch(() => null);
const resolvedLinkedPath = linkedPath
? path.resolve(path.dirname(target), linkedPath)
: null;
if (
resolvedLinkedPath &&
resolvedLinkedPath !== entry.source &&
(await isLikelyPaperclipRuntimeSkillPath(resolvedLinkedPath, entry.runtimeName))
) {
await fs.unlink(target);
if (linkSkill) {
await linkSkill(entry.source, target);
} else {
await fs.symlink(entry.source, target);
}
await onLog(
"stdout",
`[paperclip] Repaired Codex skill "${entry.runtimeName}" into ${skillsHome}\n`,
);
continue;
}
}
const result = await ensurePaperclipSkillSymlink(entry.source, target, linkSkill);
if (result === "skipped") continue;
await onLog(
"stdout",
`[paperclip] ${result === "repaired" ? "Repaired" : "Injected"} Codex skill "${entry.runtimeName}" into ${skillsHome}\n`,
);
} catch (err) {
await onLog(
"stderr",
`[paperclip] Failed to inject Codex skill "${entry.key}" into ${skillsHome}: ${err instanceof Error ? err.message : String(err)}\n`,
);
}
}
await pruneBrokenUnavailablePaperclipSkillSymlinks(
skillsHome,
skillsEntries.map((entry) => entry.runtimeName),
onLog,
);
}
export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExecutionResult> {
const { runId, agent, runtime, config, context, onLog, onMeta, onSpawn, authToken } = ctx;
const promptTemplate = asString(
config.promptTemplate,
DEFAULT_PAPERCLIP_AGENT_PROMPT_TEMPLATE,
);
const command = asString(config.command, "codex");
const model = asString(config.model, "");
const workspaceContext = parseObject(context.paperclipWorkspace);
const workspaceCwd = asString(workspaceContext.cwd, "");
const workspaceSource = asString(workspaceContext.source, "");
const workspaceStrategy = asString(workspaceContext.strategy, "");
const workspaceId = asString(workspaceContext.workspaceId, "");
const workspaceRepoUrl = asString(workspaceContext.repoUrl, "");
const workspaceRepoRef = asString(workspaceContext.repoRef, "");
const workspaceBranch = asString(workspaceContext.branchName, "");
const workspaceWorktreePath = asString(workspaceContext.worktreePath, "");
const agentHome = asString(workspaceContext.agentHome, "");
const workspaceHints = Array.isArray(context.paperclipWorkspaces)
? context.paperclipWorkspaces.filter(
(value): value is Record<string, unknown> => typeof value === "object" && value !== null,
)
: [];
const runtimeServiceIntents = Array.isArray(context.paperclipRuntimeServiceIntents)
? context.paperclipRuntimeServiceIntents.filter(
(value): value is Record<string, unknown> => typeof value === "object" && value !== null,
)
: [];
const runtimeServices = Array.isArray(context.paperclipRuntimeServices)
? context.paperclipRuntimeServices.filter(
(value): value is Record<string, unknown> => typeof value === "object" && value !== null,
)
: [];
const runtimePrimaryUrl = asString(context.paperclipRuntimePrimaryUrl, "");
const configuredCwd = asString(config.cwd, "");
const useConfiguredInsteadOfAgentHome = workspaceSource === "agent_home" && configuredCwd.length > 0;
const effectiveWorkspaceCwd = useConfiguredInsteadOfAgentHome ? "" : workspaceCwd;
const cwd = effectiveWorkspaceCwd || configuredCwd || process.cwd();
const envConfig = parseObject(config.env);
const executionTarget = readAdapterExecutionTarget({
executionTarget: ctx.executionTarget,
legacyRemoteExecution: ctx.executionTransport?.remoteExecution,
});
const executionTargetIsRemote = adapterExecutionTargetIsRemote(executionTarget);
const configuredCodexHome =
typeof envConfig.CODEX_HOME === "string" && envConfig.CODEX_HOME.trim().length > 0
? path.resolve(envConfig.CODEX_HOME.trim())
: null;
const codexSkillEntries = await readPaperclipRuntimeSkillEntries(config, __moduleDir);
const desiredSkillNames = resolveCodexDesiredSkillNames(config, codexSkillEntries);
await ensureAbsoluteDirectory(cwd, { createIfMissing: true });
const configuredOpenAiApiKey =
typeof envConfig.OPENAI_API_KEY === "string" && envConfig.OPENAI_API_KEY.trim().length > 0
? envConfig.OPENAI_API_KEY.trim()
: null;
const preparedManagedCodexHome =
configuredCodexHome
? null
: await prepareManagedCodexHome(process.env, onLog, agent.companyId, {
apiKey: configuredOpenAiApiKey,
});
const defaultCodexHome = resolveManagedCodexHomeDir(process.env, agent.companyId);
const effectiveCodexHome = configuredCodexHome ?? preparedManagedCodexHome ?? defaultCodexHome;
await fs.mkdir(effectiveCodexHome, { recursive: true });
// Merge custom model providers (PAPERCLIP_CODEX_PROVIDERS) into the managed
// CODEX_HOME's config.toml BEFORE the home is shipped to a remote execution
// target, so both local and sandboxed Codex processes pick up the routing.
// An explicit env.CODEX_HOME override is treated as user-managed and skipped.
const envConfigStrings = Object.fromEntries(
Object.entries(envConfig).filter(
(entry): entry is [string, string] => typeof entry[1] === "string",
),
);
const preparedRuntimeConfig = await prepareCodexRuntimeConfig({
env: envConfigStrings,
codexHome: configuredCodexHome ? null : effectiveCodexHome,
});
try {
for (const note of preparedRuntimeConfig.notes) {
await onLog("stdout", `[paperclip] ${note}\n`);
}
// Inject skills into the same CODEX_HOME that Codex will actually run with
// (managed home in the default case, or an explicit override from adapter config).
const codexSkillsDir = resolveCodexSkillsDir(effectiveCodexHome);
await ensureCodexSkillsInjected(
onLog,
{
skillsHome: codexSkillsDir,
skillsEntries: codexSkillEntries,
desiredSkillNames,
},
);
const timeoutSec = resolveAdapterExecutionTargetTimeoutSec(
executionTarget,
asNumber(config.timeoutSec, 0),
);
const graceSec = asNumber(config.graceSec, 20);
let effectiveExecutionCwd = adapterExecutionTargetRemoteCwd(executionTarget, cwd);
const preparedExecutionTargetRuntime = executionTargetIsRemote
? await (async () => {
await onLog(
"stdout",
`[paperclip] Syncing workspace and CODEX_HOME to ${describeAdapterExecutionTarget(executionTarget)}.\n`,
);
return await prepareAdapterExecutionTargetRuntime({
runId,
target: executionTarget,
adapterKey: "codex",
timeoutSec,
workspaceLocalDir: cwd,
installCommand: SANDBOX_INSTALL_COMMAND,
detectCommand: command,
onProgress: (line) => onLog("stdout", line),
assets: [
{
key: "home",
localDir: effectiveCodexHome,
followSymlinks: true,
},
],
});
})()
: null;
if (preparedExecutionTargetRuntime?.workspaceRemoteDir) {
effectiveExecutionCwd = preparedExecutionTargetRuntime.workspaceRemoteDir;
}
const runtimeExecutionTarget = overrideAdapterExecutionTargetRemoteCwd(executionTarget, effectiveExecutionCwd);
const executionTargetIsSandbox =
runtimeExecutionTarget?.kind === "remote" && runtimeExecutionTarget.transport === "sandbox";
const restoreRemoteWorkspace = preparedExecutionTargetRuntime
? () => preparedExecutionTargetRuntime.restoreWorkspace((line) => onLog("stdout", line))
: null;
let paperclipBridge: Awaited<ReturnType<typeof startAdapterExecutionTargetPaperclipBridge>> = null;
const remoteCodexHome = executionTargetIsRemote
? preparedExecutionTargetRuntime?.assetDirs.home ??
path.posix.join(effectiveExecutionCwd, ".paperclip-runtime", "codex", "home")
: null;
const hasExplicitApiKey =
typeof envConfig.PAPERCLIP_API_KEY === "string" && envConfig.PAPERCLIP_API_KEY.trim().length > 0;
const env: Record<string, string> = { ...buildPaperclipEnv(agent) };
env.PAPERCLIP_RUN_ID = runId;
const wakeTaskId =
(typeof context.taskId === "string" && context.taskId.trim().length > 0 && context.taskId.trim()) ||
(typeof context.issueId === "string" && context.issueId.trim().length > 0 && context.issueId.trim()) ||
null;
const wakeReason =
typeof context.wakeReason === "string" && context.wakeReason.trim().length > 0
? context.wakeReason.trim()
: null;
const wakeCommentId =
(typeof context.wakeCommentId === "string" && context.wakeCommentId.trim().length > 0 && context.wakeCommentId.trim()) ||
(typeof context.commentId === "string" && context.commentId.trim().length > 0 && context.commentId.trim()) ||
null;
const approvalId =
typeof context.approvalId === "string" && context.approvalId.trim().length > 0
? context.approvalId.trim()
: null;
const approvalStatus =
typeof context.approvalStatus === "string" && context.approvalStatus.trim().length > 0
? context.approvalStatus.trim()
: null;
const linkedIssueIds = Array.isArray(context.issueIds)
? context.issueIds.filter((value): value is string => typeof value === "string" && value.trim().length > 0)
: [];
const wakePayloadJson = stringifyPaperclipWakePayload(context.paperclipWake);
const issueWorkMode = readPaperclipIssueWorkModeFromContext(context);
if (wakeTaskId) {
env.PAPERCLIP_TASK_ID = wakeTaskId;
}
if (issueWorkMode) {
env.PAPERCLIP_ISSUE_WORK_MODE = issueWorkMode;
}
if (wakeReason) {
env.PAPERCLIP_WAKE_REASON = wakeReason;
}
if (wakeCommentId) {
env.PAPERCLIP_WAKE_COMMENT_ID = wakeCommentId;
}
if (approvalId) {
env.PAPERCLIP_APPROVAL_ID = approvalId;
}
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;
}
refreshPaperclipWorkspaceEnvForExecution({
env,
envConfig,
workspaceCwd: effectiveWorkspaceCwd,
workspaceSource,
workspaceStrategy,
workspaceId,
workspaceRepoUrl,
workspaceRepoRef,
workspaceBranch,
workspaceWorktreePath,
workspaceHints,
agentHome,
executionTargetIsRemote,
executionCwd: effectiveExecutionCwd,
});
if (runtimeServiceIntents.length > 0) {
env.PAPERCLIP_RUNTIME_SERVICE_INTENTS_JSON = JSON.stringify(runtimeServiceIntents);
}
if (runtimeServices.length > 0) {
env.PAPERCLIP_RUNTIME_SERVICES_JSON = JSON.stringify(runtimeServices);
}
if (runtimePrimaryUrl) {
env.PAPERCLIP_RUNTIME_PRIMARY_URL = runtimePrimaryUrl;
}
env.CODEX_HOME = remoteCodexHome ?? effectiveCodexHome;
if (!hasExplicitApiKey && authToken) {
env.PAPERCLIP_API_KEY = authToken;
}
if (executionTargetIsRemote && adapterExecutionTargetUsesPaperclipBridge(runtimeExecutionTarget)) {
paperclipBridge = await startAdapterExecutionTargetPaperclipBridge({
runId,
target: runtimeExecutionTarget,
runtimeRootDir: preparedExecutionTargetRuntime?.runtimeRootDir,
adapterKey: "codex",
timeoutSec,
hostApiToken: env.PAPERCLIP_API_KEY,
onLog,
});
if (paperclipBridge) {
Object.assign(env, paperclipBridge.env);
}
}
const effectiveEnv = Object.fromEntries(
Object.entries({ ...process.env, ...env }).filter(
(entry): entry is [string, string] => typeof entry[1] === "string",
),
);
const billingType = resolveCodexBillingType(effectiveEnv);
const runtimeEnv = Object.fromEntries(
Object.entries(ensurePathInEnv(effectiveEnv)).filter(
(entry): entry is [string, string] => typeof entry[1] === "string",
),
);
await ensureAdapterExecutionTargetRuntimeCommandInstalled({
runId,
target: executionTarget,
installCommand: ctx.runtimeCommandSpec?.installCommand,
detectCommand: ctx.runtimeCommandSpec?.detectCommand,
cwd,
env: runtimeEnv,
timeoutSec,
graceSec,
onLog,
});
await ensureAdapterExecutionTargetCommandResolvable(command, executionTarget, cwd, runtimeEnv);
const resolvedCommand = await resolveAdapterExecutionTargetCommandForLogs(command, executionTarget, cwd, runtimeEnv);
const loggedEnv = buildInvocationEnvForLogs(env, {
runtimeEnv,
includeRuntimeKeys: ["HOME"],
resolvedCommand,
});
const runtimeSessionParams = parseObject(runtime.sessionParams);
const runtimeSessionId = asString(runtimeSessionParams.sessionId, runtime.sessionId ?? "");
const runtimeSessionCwd = asString(runtimeSessionParams.cwd, "");
const runtimeRemoteExecution = parseObject(runtimeSessionParams.remoteExecution);
const canResumeSession =
runtimeSessionId.length > 0 &&
(runtimeSessionCwd.length === 0 || path.resolve(runtimeSessionCwd) === path.resolve(effectiveExecutionCwd)) &&
adapterExecutionTargetSessionMatches(runtimeRemoteExecution, runtimeExecutionTarget);
const codexTransientFallbackMode = readCodexTransientFallbackMode(context);
const forceSaferInvocation = fallbackModeUsesSaferInvocation(codexTransientFallbackMode);
const forceFreshSession = fallbackModeUsesFreshSession(codexTransientFallbackMode);
const sessionId = canResumeSession && !forceFreshSession ? runtimeSessionId : null;
if (executionTargetIsRemote && runtimeSessionId && !canResumeSession) {
await onLog(
"stdout",
`[paperclip] Codex session "${runtimeSessionId}" does not match the current remote execution identity and will not be resumed in "${effectiveExecutionCwd}". Starting a fresh remote session.\n`,
);
} else if (runtimeSessionId && !canResumeSession) {
await onLog(
"stdout",
`[paperclip] Codex session "${runtimeSessionId}" was saved for cwd "${runtimeSessionCwd}" and will not be resumed in "${effectiveExecutionCwd}".\n`,
);
}
const instructionsFilePath = asString(config.instructionsFilePath, "").trim();
const instructionsDir = instructionsFilePath ? `${path.dirname(instructionsFilePath)}/` : "";
let instructionsPrefix = "";
let instructionsChars = 0;
if (instructionsFilePath) {
try {
const instructionsContents = await fs.readFile(instructionsFilePath, "utf8");
instructionsPrefix =
`${instructionsContents}\n\n` +
`The above agent instructions were loaded from ${instructionsFilePath}. ` +
`Resolve any relative file references from ${instructionsDir}.\n\n`;
instructionsChars = instructionsPrefix.length;
} catch (err) {
const reason = err instanceof Error ? err.message : String(err);
await onLog(
"stdout",
`[paperclip] Warning: could not read agent instructions file "${instructionsFilePath}": ${reason}\n`,
);
}
}
const repoAgentsNote =
"Codex exec automatically applies repo-scoped AGENTS.md instructions from the current workspace; Paperclip does not currently suppress that discovery.";
const bootstrapPromptTemplate = asString(config.bootstrapPromptTemplate, "");
const templateData = {
agentId: agent.id,
companyId: agent.companyId,
runId,
company: { id: agent.companyId },
agent,
run: { id: runId, source: "on_demand" },
context,
};
const renderedBootstrapPrompt =
!sessionId && bootstrapPromptTemplate.trim().length > 0
? renderTemplate(bootstrapPromptTemplate, templateData).trim()
: "";
const wakePrompt = renderPaperclipWakePrompt(context.paperclipWake, { resumedSession: Boolean(sessionId) });
const shouldUseResumeDeltaPrompt = Boolean(sessionId) && wakePrompt.length > 0;
const promptInstructionsPrefix = shouldUseResumeDeltaPrompt ? "" : instructionsPrefix;
instructionsChars = promptInstructionsPrefix.length;
const continuationSummary = parseObject(context.paperclipContinuationSummary);
const continuationSummaryBody = asString(continuationSummary.body, "").trim() || null;
const codexFallbackHandoffNote =
forceFreshSession
? buildCodexTransientHandoffNote({
previousSessionId: runtimeSessionId || runtime.sessionId || null,
fallbackMode: codexTransientFallbackMode ?? "fresh_session",
continuationSummaryBody,
})
: "";
const commandNotes = (() => {
if (!instructionsFilePath) {
const notes = [repoAgentsNote];
if (forceSaferInvocation) {
notes.push("Codex transient fallback requested safer invocation settings for this retry.");
}
if (forceFreshSession) {
notes.push("Codex transient fallback forced a fresh session with a continuation handoff.");
}
return notes;
}
if (instructionsPrefix.length > 0) {
if (shouldUseResumeDeltaPrompt) {
const notes = [
`Loaded agent instructions from ${instructionsFilePath}`,
"Skipped stdin instruction reinjection because an existing Codex session is being resumed with a wake delta.",
repoAgentsNote,
];
if (forceSaferInvocation) {
notes.push("Codex transient fallback requested safer invocation settings for this retry.");
}
if (forceFreshSession) {
notes.push("Codex transient fallback forced a fresh session with a continuation handoff.");
}
return notes;
}
const notes = [
`Loaded agent instructions from ${instructionsFilePath}`,
`Prepended instructions + path directive to stdin prompt (relative references from ${instructionsDir}).`,
repoAgentsNote,
];
if (forceSaferInvocation) {
notes.push("Codex transient fallback requested safer invocation settings for this retry.");
}
if (forceFreshSession) {
notes.push("Codex transient fallback forced a fresh session with a continuation handoff.");
}
return notes;
}
const notes = [
`Configured instructionsFilePath ${instructionsFilePath}, but file could not be read; continuing without injected instructions.`,
repoAgentsNote,
];
if (forceSaferInvocation) {
notes.push("Codex transient fallback requested safer invocation settings for this retry.");
}
if (forceFreshSession) {
notes.push("Codex transient fallback forced a fresh session with a continuation handoff.");
}
return notes;
})();
if (executionTargetIsSandbox) {
commandNotes.push(
"Added --skip-git-repo-check for sandbox execution because Codex requires an explicit trust bypass in headless remote workspaces.",
);
}
if (preparedRuntimeConfig.notes.length > 0) {
commandNotes.unshift(...preparedRuntimeConfig.notes);
}
const renderedPrompt = shouldUseResumeDeltaPrompt ? "" : renderTemplate(promptTemplate, templateData);
const sessionHandoffNote = asString(context.paperclipSessionHandoffMarkdown, "").trim();
const prompt = joinPromptSections([
promptInstructionsPrefix,
renderedBootstrapPrompt,
wakePrompt,
codexFallbackHandoffNote,
sessionHandoffNote,
renderedPrompt,
]);
const promptMetrics = {
promptChars: prompt.length,
instructionsChars,
bootstrapPromptChars: renderedBootstrapPrompt.length,
wakePromptChars: wakePrompt.length,
sessionHandoffChars: sessionHandoffNote.length,
heartbeatPromptChars: renderedPrompt.length,
};
const runAttempt = async (resumeSessionId: string | null) => {
const execArgs = buildCodexExecArgs(
forceSaferInvocation ? { ...config, fastMode: false } : config,
{
resumeSessionId,
skipGitRepoCheck: executionTargetIsSandbox,
},
);
const args = execArgs.args;
const commandNotesWithFastMode =
execArgs.fastModeIgnoredReason == null
? commandNotes
: [...commandNotes, execArgs.fastModeIgnoredReason];
if (onMeta) {
await onMeta({
adapterType: "codex_local",
command: resolvedCommand,
cwd: effectiveExecutionCwd,
commandNotes: commandNotesWithFastMode,
commandArgs: args.map((value, idx) => {
if (idx === args.length - 1 && value !== "-") return `<prompt ${prompt.length} chars>`;
return value;
}),
env: loggedEnv,
prompt,
promptMetrics,
context,
});
}
const proc = await runAdapterExecutionTargetProcess(runId, runtimeExecutionTarget, command, args, {
cwd,
env,
stdin: prompt,
timeoutSec,
graceSec,
onSpawn,
onLog: async (stream, chunk) => {
if (stream !== "stderr") {
await onLog(stream, chunk);
return;
}
const cleaned = stripCodexRolloutNoise(chunk);
if (!cleaned.trim()) return;
await onLog(stream, cleaned);
},
});
const cleanedStderr = stripCodexRolloutNoise(proc.stderr);
return {
proc: {
...proc,
stderr: cleanedStderr,
},
rawStderr: proc.stderr,
parsed: parseCodexJsonl(proc.stdout),
};
};
const toResult = (
attempt: { proc: { exitCode: number | null; signal: string | null; timedOut: boolean; stdout: string; stderr: string }; rawStderr: string; parsed: ReturnType<typeof parseCodexJsonl> },
clearSessionOnMissingSession = false,
isRetry = false,
): AdapterExecutionResult => {
if (attempt.proc.timedOut) {
return {
exitCode: attempt.proc.exitCode,
signal: attempt.proc.signal,
timedOut: true,
errorMessage: `Timed out after ${timeoutSec}s`,
clearSession: clearSessionOnMissingSession,
};
}
const canFallbackToRuntimeSession = !isRetry && !forceFreshSession;
const resolvedSessionId =
attempt.parsed.sessionId ??
(canFallbackToRuntimeSession ? (runtimeSessionId ?? runtime.sessionId ?? null) : null);
const resolvedSessionParams = resolvedSessionId
? ({
sessionId: resolvedSessionId,
cwd: effectiveExecutionCwd,
...(executionTargetIsRemote
? {
remoteExecution: adapterExecutionTargetSessionIdentity(runtimeExecutionTarget),
}
: {}),
...(workspaceId ? { workspaceId } : {}),
...(workspaceRepoUrl ? { repoUrl: workspaceRepoUrl } : {}),
...(workspaceRepoRef ? { repoRef: workspaceRepoRef } : {}),
} as Record<string, unknown>)
: null;
const parsedError = typeof attempt.parsed.errorMessage === "string" ? attempt.parsed.errorMessage.trim() : "";
const stderrLine = firstNonEmptyLine(attempt.proc.stderr);
const fallbackErrorMessage =
parsedError ||
stderrLine ||
`Codex exited with code ${attempt.proc.exitCode ?? -1}`;
const transientRetryNotBefore =
(attempt.proc.exitCode ?? 0) !== 0
? extractCodexRetryNotBefore({
stdout: attempt.proc.stdout,
stderr: attempt.proc.stderr,
errorMessage: fallbackErrorMessage,
})
: null;
const transientUpstream =
(attempt.proc.exitCode ?? 0) !== 0 &&
isCodexTransientUpstreamError({
stdout: attempt.proc.stdout,
stderr: attempt.proc.stderr,
errorMessage: fallbackErrorMessage,
});
return {
exitCode: attempt.proc.exitCode,
signal: attempt.proc.signal,
timedOut: false,
errorMessage:
(attempt.proc.exitCode ?? 0) === 0
? null
: fallbackErrorMessage,
errorCode:
transientUpstream
? "codex_transient_upstream"
: null,
errorFamily: transientUpstream ? "transient_upstream" : null,
retryNotBefore: transientRetryNotBefore ? transientRetryNotBefore.toISOString() : null,
usage: attempt.parsed.usage,
sessionId: resolvedSessionId,
sessionParams: resolvedSessionParams,
sessionDisplayId: resolvedSessionId,
provider: "openai",
biller: resolveCodexBiller(effectiveEnv, billingType),
model,
billingType,
costUsd: null,
resultJson: {
stdout: attempt.proc.stdout,
stderr: attempt.proc.stderr,
...(transientUpstream ? { errorFamily: "transient_upstream" } : {}),
...(transientRetryNotBefore ? { retryNotBefore: transientRetryNotBefore.toISOString() } : {}),
...(transientRetryNotBefore ? { transientRetryNotBefore: transientRetryNotBefore.toISOString() } : {}),
},
summary: attempt.parsed.summary,
clearSession: Boolean((clearSessionOnMissingSession || forceFreshSession) && !resolvedSessionId),
};
};
try {
const initial = await runAttempt(sessionId);
if (
sessionId &&
!initial.proc.timedOut &&
(initial.proc.exitCode ?? 0) !== 0 &&
isCodexUnknownSessionError(initial.proc.stdout, initial.rawStderr)
) {
await onLog(
"stdout",
`[paperclip] Codex resume session "${sessionId}" is unavailable; retrying with a fresh session.\n`,
);
const retry = await runAttempt(null);
return toResult(retry, true, true);
}
return toResult(initial, false, false);
} finally {
if (paperclipBridge) {
await paperclipBridge.stop();
}
if (restoreRemoteWorkspace) {
await onLog(
"stdout",
`[paperclip] Restoring workspace changes from ${describeAdapterExecutionTarget(executionTarget)}.\n`,
);
await restoreRemoteWorkspace();
}
}
} finally {
// Restore the managed config.toml so PAPERCLIP_CODEX_PROVIDERS changes
// (or removal) between runs never leave stale provider routing behind. This
// finally starts the moment prepareCodexRuntimeConfig returns, so a throw
// anywhere in the remaining setup (skill injection, remote runtime
// preparation, command building) restores the original config.toml too.
// If the process dies before reaching this, the next
// prepareCodexRuntimeConfig restores the original from the pre-run backup
// written at prepare time.
await preparedRuntimeConfig.cleanup();
}
}