Files
PaperClipAI/packages/adapters/opencode-local/src/server/execute.ts
T
DottaandPaperclip 992f720262 fix: make runner task context ownership explicit (#13753)
<!-- Write all pull request text in Simplified Technical English
(ASD-STE100). -->

## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - Task descriptions, comments, continuation data, skills, and
execution rules enter several agent adapters.
> - The same source can be rendered by more than one automatic input
carrier.
> - Failed resumes can also rebuild input from stale or compact context.
> - This pull request gives each Paperclip-owned source one delivery
owner and preserves the required transport boundaries.
> - It adds deterministic adapter, interaction, runner, and browser
tests for these boundaries.
> - The benefit is more predictable context delivery with explicit
evidence for later live qualification.

## Linked Issues or Issue Description

Related: #13144 removes a duplicate environment payload and bounds wake
lists. Related: #11360 addresses Hermes resume behavior. This pull
request preserves compatible active-session formats while repairing
context ownership and stale question creation.

**What happened?**

Task descriptions and comments could enter more than one automatic
context block. Native transports could wrap a complete model input in a
second task envelope. Some legacy and gateway adapters could omit the
owned assignment on ordinary tasks or rebuild a failed resume with stale
compact context. A continuation could also request a question after
newer human comments had arrived.

**Expected behavior**

Each task or comment source has one automatic model-facing owner.
Distinct comment IDs and repeated wording remain distinct. Fresh
fallback attempts rebuild the required full context. A question request
is rejected when newer queued human direction makes it stale. Harness
access policy remains owned by execution configuration.

**Steps to reproduce**

1. Build a task with a description and current comments.
2. Capture the actual adapter or runner input.
3. Compare source ownership and task-envelope nesting.
4. Queue a human comment before a continuation requests a question.
5. Trigger a failed resume and inspect the fresh retry input.
6. Run the focused adapter, interaction, runner, and browser checks.

## What Changed

- Add shared prompt-section selection at the provider-attempt boundary.
- Deliver owned assignment context through native, legacy CLI, ACP,
gateway, cloud, Pi, Kimi, Grok, Gemini, OpenCode, Cursor, OpenClaw, and
Hermes paths.
- Rebuild full or compact context after resume recovery changes the
attempt. Add native and Claude ACP tests of actual recovery requests.
- Preserve custom templates, loaded instruction files, execution
policies, and older active-session formats.
- Record continuation source metadata and reject stale question creation
under the issue-row lock.
- Add explicit Product E2E context-integrity profiles, prerequisite
gates, credential-isolation checks, and report fixtures.
- Bypass service-worker forwarding for same-origin Vite development
modules. A real Chromium test fails with resource exhaustion before the
repair and passes after it. Production asset caching keeps its existing
policy.
- Add browser diagnostics and service-worker module-loading regressions.
- Add an explicit zero-retry eval option. The default retry behavior
remains unchanged. Each campaign records its effective policy.
- Remove the model-facing working-directory sentence from four prompt
builders. Existing workspace, sandbox, permission, and custom-template
configuration remains unchanged.
- Align the everyday workflow assertion with the current 47-entry
catalog.

Compared with current upstream master, the branch carries the
context-ownership implementation and its tests, the explicit
context-integrity catalog and evidence harness, and the focused browser
regression checks.

## Verification

**Merge assessment:** focused regression evidence supports merge. This
is not full completion of the original broad qualification matrix. The
maintainer has authorized merge after fresh verification of the master
integration.

- Current head: `bbd52f82114eabf09bc7b1a7e97d54a5b43bbc00`. This
integrates current master `2f585ef26a1814fa209715242d1ca791b63e4c4e`.
All 14 conflicts are resolved. Cancellation checks, workspace
finalization, native Grok support, and both sets of tests are retained.
- Current-head Greptile: **5/5**, with no blocking findings. The review
names this exact commit. All **59 reported checks are terminal: 55
successful, 4 skipped, zero pending or failing**. This includes the full
root general and serialized suites, separate runner checks, typecheck,
build, canary, browser E2E, Docker, and security checks. The successful
legacy security status is included in that total.
- After integration: workspace typecheck and full build passed. Separate
runner checks passed: **2,160 TypeScript tests (10 skipped), 582 Rust
tests, and 39 preparation checks**. Other passing checks include 621
Product E2E harness units, 376 focused shared/adapter tests, 160
real-database/API tests, 86 Hermes tests, 18 browser-support checks, and
Product E2E typechecking. The complete root suite passed in CI. The
duplicate local monolithic root run was stopped after that CI result; it
is not counted as a completed local pass.
- New native recovery coverage retains full assignment, completion
contract, and explicit skill selection after safe replacement, for old
and prepared input formats. Full native session test file: **136/136
passed**.
- New Claude ACP coverage captures actual fresh, resumed, and
missing-session fallback requests. It verifies one assignment copy,
comment order, identical text under distinct comment IDs, and full
fallback context. Full file: **33/33 passed**. Both affected TypeScript
checks passed.
- Existing deterministic tests cover source revisions, approval and
trust boundaries, completion validation, custom templates, compatible
sessions, standalone driver wrapping, and maintained adapter transport
requests.
- Provider-free browser support: **17/17 passed** after the master
merge. Service-worker unit tests: **33/33 passed**. The module-overload
regression failed before the repair and passed after it in real
Chromium.

### Fresh live comparisons

The new batch ran exactly four Product E2E attempts. **All four passed
on the first attempt; no retries.** Each has six terminal matchers plus
the existing browser lifecycle and invariant checks.

| Exact case ID | Control | Candidate |
|---|---|---|
| `core-compatibility.runner-codex.local.plan-revise-accept` | Passed |
Passed |
|
`local-session-integrity.runner-acpx-claude.local.structured-question-restart-resume`
| Passed | Passed |

The plan case checks a revised canonical plan and revision-bound
approval before completion. The question case restarts the server before
submitting the answer, then verifies the continuation completes.

Control source is `dfa4e1bda8d50a1a01746603251a9128dbe9d0d6`. Candidate
source is `79fcdb5dece501d28064ea9da306603881b46f0c`. They use identical
frozen definitions and provider versions: Codex `0.156.0` with
`gpt-5.6-sol`; ACPX `0.13.1` / Claude ACP `0.73.0` with
`claude-sonnet-5`. The September 24 head added master browser recovery
and test-only changes. The September 28 head also integrates newer
master changes, including cancellation, workspace finalization, and
native Grok. These are frozen-source live results, not exact-head live
runs.

The candidate received one description copy where the control initially
received three. The submitted initial plan envelopes were 7,969 versus
19,097 characters. Question envelopes were 7,592 versus 18,919. These
are structural measurements, not whole-provider token or dollar savings.

### Earlier evidence and failed attempts

- The preceding fresh batch has four effective passing pairs: OpenCode
comment continuation and assigned skill, native Codex comment
continuation, and native Claude comment continuation. It retains **11
attempts: eight passed and three failed**.
- Original failures remain recorded: missing local PostgreSQL library
links before task creation; host-sleep cleanup after task/page checks
passed; and a Claude **control** session-open rejection before a model
turn. Setup was repaired identically on both worktrees. The permitted
unchanged infrastructure retries passed. The underlying Claude provider
startup error was not retained and remains unknown.
- Older R2 retains **17 passes and one failure** across 18 attempts,
including eight both-pass native/legacy Codex/Claude pairs. Its OpenCode
blank-page failure led to the service-worker repair. R2 is historical
evidence: master changed the native fixed prompt and removed duplicate
wake environment data afterward.
- The September 24 CI run initially failed one unrelated preview
readiness test (`ECONNREFUSED` on its local fixture). Its test and
production code match master. Isolated local verification passed **28
tests, 3 skipped**. One unchanged CI retry passed the full shard: **831
passed, 1 skipped**, including all **31 preview-exposure tests**. The
aggregate CI gate passed afterward. The precise startup cause remains
unknown; a port race is a hypothesis, not a proved cause.

### Limits

The original wider profile/workflow matrix, repeated trials, and remote
Daytona qualification are incomplete. These results support a focused
merge recommendation, not statistical equivalence or universal harness
qualification. Some usage receipts are missing in both variants, so no
token or dollar savings are claimed. The $500 ceiling was preserved
using conservative allowances; failed attempts and unknown charges
remain in the ledger.

Reproduce the focused additions with `pnpm exec vitest run
packages/adapters/claude-local/src/server/acp.test.ts` and `pnpm
--filter @paperclipai/paperclip-runner exec vitest run
src/native-session-runtime.test.ts`. Full checks use `pnpm -r
typecheck`, `pnpm test:run`, `pnpm build`, and the separate runner
checks. Paid evals require the frozen definitions, profiles, and
credentials; do not use `--all` as a substitute for the selected cases.

## Risks

- Context placement changes can affect model behavior. Deterministic
checks cover the selected paths, but live qualification remains
incomplete.
- The stale-question guard can reject a request when queued human
comments arrived during the run. This is intended.
- New stored inputs and model envelopes retain compatibility readers for
older active sessions.
- Custom templates may intentionally repeat content.
- Removing a model-facing working-directory sentence does not change
filesystem, command, sandbox, or permission configuration.
- The worker bypass applies only to same-origin development module
paths. Cache-policy tests preserve private-response handling and
production asset caching. Mounted HTTP fixture changes remain test-only.
- This PR does not claim measured token savings or statistical
equivalence across every harness.

## Model Used

OpenAI Codex, exact model gpt-6-astra, with repository tools and code
execution. Bounded supporting work used gpt-5.6-luna and gpt-6-luna. The
serving context-window size is not exposed in this task.

## 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 described the issue in-PR using the required issue fields
- [x] I have not referenced internal/instance-local Paperclip issues or
links
- [x] My branch name describes the change and contains no internal
ticket id
- [x] I have run the focused local checks and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect these changes
- [x] I have considered and documented risks above
- [x] All current-head Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
for the current head
- [x] I will address all Greptile and reviewer comments before
requesting merge

---------

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-09-28 14:49:14 -05:00

776 lines
31 KiB
TypeScript

import { createProviderStoppedBoundary } from "@paperclipai/adapter-utils/provider-stopped-boundary";
import fs from "node:fs/promises";
import os from "node:os";
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,
adapterExecutionTargetUsesManagedHome,
adapterExecutionTargetUsesPaperclipBridge,
describeAdapterExecutionTarget,
ensureAdapterExecutionTargetCommandResolvable,
ensureAdapterExecutionTargetRuntimeCommandInstalled,
prepareAdapterExecutionTargetRuntime,
adapterExecutionTargetDuplexObservabilityRecorder,
adapterExecutionTargetEnablesSandboxDuplexBridge,
readAdapterExecutionTarget,
readAdapterExecutionTargetHomeDir,
resolveAdapterExecutionTargetTimeoutSec,
resolveAdapterExecutionTargetCommandForLogs,
runAdapterExecutionTargetProcess,
runAdapterExecutionTargetShellCommand,
startAdapterExecutionTargetPaperclipBridge,
} from "@paperclipai/adapter-utils/execution-target";
import {
asString,
asNumber,
asStringArray,
parseObject,
buildPaperclipEnv,
buildRuntimeToolsEnv,
joinPromptSections,
buildInvocationEnvForLogs,
ensureAbsoluteDirectory,
ensurePaperclipSkillSymlink,
ensurePathInEnv,
refreshPaperclipWorkspaceEnvForExecution,
renderTemplate,
selectPaperclipPromptSections,
selectInitialCommunicationGuidance,
isPaperclipRecoveryWakePayload,
DEFAULT_PAPERCLIP_AGENT_PROMPT_TEMPLATE,
DEFAULT_PAPERCLIP_CONVERSATION_PROMPT_TEMPLATE,
runChildProcess,
isPaperclipSkillSourceMissing,
readPaperclipRuntimeSkillEntries,
readPaperclipIssueWorkModeFromContext,
resolveLegacyPaperclipDesiredSkillNames,
} from "@paperclipai/adapter-utils/server-utils";
import { isOpenCodeUnknownSessionError, parseOpenCodeJsonl } from "./parse.js";
import {
ensureOpenCodeModelConfiguredAndAvailable,
isTruthyEnvFlag,
parseOpenCodeModelsOutput,
requireOpenCodeModelId,
} from "./models.js";
import { removeMaintainerOnlySkillSymlinks } from "@paperclipai/adapter-utils/server-utils";
import { prepareOpenCodeRuntimeConfig, prepareManagedOpenCodeRemoteHomes } from "./runtime-config.js";
import { SANDBOX_INSTALL_COMMAND } from "../index.js";
import { resolveOpenCodeSkillsHome } from "./skills.js";
const __moduleDir = path.dirname(fileURLToPath(import.meta.url));
function firstNonEmptyLine(text: string): string {
return (
text
.split(/\r?\n/)
.map((line) => line.trim())
.find(Boolean) ?? ""
);
}
function parseModelProvider(model: string | null): string | null {
if (!model) return null;
const trimmed = model.trim();
if (!trimmed.includes("/")) return null;
return trimmed.slice(0, trimmed.indexOf("/")).trim() || null;
}
function resolveOpenCodeBiller(env: Record<string, string>, provider: string | null): string {
return inferOpenAiCompatibleBiller(env, null) ?? provider ?? "unknown";
}
const REMOTE_OPENCODE_MODELS_PROBE_DEFAULT_TIMEOUT_SEC = 20;
const REMOTE_OPENCODE_MODELS_PROBE_SANDBOX_TIMEOUT_SEC = 120;
export async function ensureRemoteOpenCodeModelConfiguredAndAvailable(input: {
runId: string;
executionTarget: NonNullable<AdapterExecutionContext["executionTarget"]>;
command: string;
model: string;
cwd: string;
env: Record<string, string>;
timeoutSec: number;
graceSec: number;
}) {
const model = requireOpenCodeModelId(input.model);
// When the caller opts into OPENCODE_ALLOW_ALL_MODELS, OpenCode accepts any
// provider/model at run time (e.g. gateway-routed models that never appear in
// `opencode models` output). Honour that on the REMOTE path too by skipping the
// remote availability probe; we still enforce the provider/model format above.
// Mirrors the local ensureOpenCodeModelConfiguredAndAvailable bypass. Prefer the
// explicit run env, then the process env.
if (isTruthyEnvFlag(input.env.OPENCODE_ALLOW_ALL_MODELS ?? process.env.OPENCODE_ALLOW_ALL_MODELS)) {
return;
}
const defaultProbeTimeoutSec =
input.executionTarget.kind === "remote" && input.executionTarget.transport === "sandbox"
? REMOTE_OPENCODE_MODELS_PROBE_SANDBOX_TIMEOUT_SEC
: REMOTE_OPENCODE_MODELS_PROBE_DEFAULT_TIMEOUT_SEC;
const probeTimeoutSec = input.timeoutSec > 0
? Math.min(input.timeoutSec, defaultProbeTimeoutSec)
: defaultProbeTimeoutSec;
const probe = await runAdapterExecutionTargetProcess(
input.runId,
input.executionTarget,
input.command,
["models"],
{
cwd: input.cwd,
env: input.env,
timeoutSec: probeTimeoutSec,
graceSec: input.graceSec,
onLog: async () => {},
},
);
// The remote availability probe is a best-effort pre-flight guard, not a gate.
// If `opencode models` itself cannot run on the target — timeout, transient CLI
// error, provider hiccup — do NOT abort the run. The real invocation is
// authoritative, so a probe that can't execute must never be fatal. (Previously
// these threw and crashed runs mid-flight, losing the agent's work + disposition.)
if (probe.timedOut) {
console.warn(
`[opencode-local] Remote model availability probe for "${model}" timed out after ${probeTimeoutSec}s; proceeding with the configured model.`,
);
return;
}
if ((probe.exitCode ?? 1) !== 0) {
const detail = firstNonEmptyLine(probe.stderr) || firstNonEmptyLine(probe.stdout);
console.warn(
`[opencode-local] Remote \`opencode models\` could not run for "${model}"${
detail ? ` (${detail})` : ""
}; proceeding with the configured model.`,
);
return;
}
const models = parseOpenCodeModelsOutput(probe.stdout);
if (models.length === 0) {
console.warn(
`[opencode-local] Remote \`opencode models\` returned no models; proceeding with the configured model "${model}".`,
);
return;
}
if (!models.some((entry) => entry.id === model)) {
const sample = models.slice(0, 12).map((entry) => entry.id).join(", ");
throw new Error(
`Configured OpenCode model is unavailable on the remote execution target: ${model}. Available models: ${sample}${models.length > 12 ? ", ..." : ""}`,
);
}
}
async function ensureOpenCodeSkillsInjected(
onLog: AdapterExecutionContext["onLog"],
skillsEntries: Array<{ key: string; runtimeName: string; source: string }>,
desiredSkillNames?: string[],
skillsHome = resolveOpenCodeSkillsHome({}),
) {
await fs.mkdir(skillsHome, { recursive: true });
const desiredSet = new Set(desiredSkillNames ?? skillsEntries.map((entry) => entry.key));
const selectedEntries = skillsEntries.filter((entry) => desiredSet.has(entry.key));
const removedSkills = await removeMaintainerOnlySkillSymlinks(
skillsHome,
selectedEntries.map((entry) => entry.runtimeName),
);
for (const skillName of removedSkills) {
await onLog(
"stderr",
`[paperclip] Removed maintainer-only OpenCode skill "${skillName}" from ${skillsHome}\n`,
);
}
for (const entry of selectedEntries) {
const target = path.join(skillsHome, entry.runtimeName);
try {
const result = await ensurePaperclipSkillSymlink(entry.source, target);
if (result === "skipped") continue;
await onLog(
"stderr",
`[paperclip] ${result === "repaired" ? "Repaired" : "Injected"} OpenCode skill "${entry.key}" into ${skillsHome}\n`,
);
} catch (err) {
await onLog(
"stderr",
`[paperclip] Failed to inject OpenCode skill "${entry.key}" into ${skillsHome}: ${err instanceof Error ? err.message : String(err)}\n`,
);
}
}
}
async function buildOpenCodeSkillsDir(config: Record<string, unknown>): Promise<string> {
const tmp = await fs.mkdtemp(path.join(os.tmpdir(), "paperclip-opencode-skills-"));
const target = path.join(tmp, "skills");
await fs.mkdir(target, { recursive: true });
const availableEntries = await readPaperclipRuntimeSkillEntries(config, __moduleDir);
const desiredNames = new Set(resolveLegacyPaperclipDesiredSkillNames(config, availableEntries));
for (const entry of availableEntries) {
if (!desiredNames.has(entry.key)) continue;
if (isPaperclipSkillSourceMissing(entry)) continue;
await fs.symlink(entry.source, path.join(target, entry.runtimeName));
}
return target;
}
export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExecutionResult> {
const providerStop = createProviderStoppedBoundary(ctx.onProviderStopped);
const { runId, agent, runtime, config, context, onLog, onMeta, onSpawn, authToken } = ctx;
const executionTarget = readAdapterExecutionTarget({
executionTarget: ctx.executionTarget,
legacyRemoteExecution: ctx.executionTransport?.remoteExecution,
});
const executionTargetIsRemote = adapterExecutionTargetIsRemote(executionTarget);
const promptTemplate = asString(
config.promptTemplate,
context.conversationMode === true
? DEFAULT_PAPERCLIP_CONVERSATION_PROMPT_TEMPLATE
: DEFAULT_PAPERCLIP_AGENT_PROMPT_TEMPLATE,
);
const command = asString(config.command, "opencode");
const model = asString(config.model, "").trim();
const variant = asString(config.variant, "").trim();
const workspaceContext = parseObject(context.paperclipWorkspace);
const workspaceCwd = asString(workspaceContext.cwd, "");
const workspaceSource = asString(workspaceContext.source, "");
const workspaceId = asString(workspaceContext.workspaceId, "");
const workspaceRepoUrl = asString(workspaceContext.repoUrl, "");
const workspaceRepoRef = asString(workspaceContext.repoRef, "");
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 configuredCwd = asString(config.cwd, "");
const useConfiguredInsteadOfAgentHome = workspaceSource === "agent_home" && configuredCwd.length > 0;
const effectiveWorkspaceCwd = useConfiguredInsteadOfAgentHome ? "" : workspaceCwd;
const cwd = effectiveWorkspaceCwd || configuredCwd || process.cwd();
let effectiveExecutionCwd = adapterExecutionTargetRemoteCwd(executionTarget, cwd);
await ensureAbsoluteDirectory(cwd, { createIfMissing: true });
const openCodeSkillEntries = await readPaperclipRuntimeSkillEntries(config, __moduleDir);
const desiredOpenCodeSkillNames = resolveLegacyPaperclipDesiredSkillNames(config, openCodeSkillEntries);
if (!executionTargetIsRemote) {
await ensureOpenCodeSkillsInjected(
onLog,
openCodeSkillEntries,
desiredOpenCodeSkillNames,
resolveOpenCodeSkillsHome(config),
);
}
const envConfig = parseObject(config.env);
const env: Record<string, string> = {
...buildPaperclipEnv(agent),
...buildRuntimeToolsEnv(ctx.runtimeTools),
};
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 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(",");
refreshPaperclipWorkspaceEnvForExecution({
env,
envConfig,
workspaceCwd: effectiveWorkspaceCwd,
workspaceSource,
workspaceId,
workspaceRepoUrl,
workspaceRepoRef,
workspaceHints,
agentHome,
executionTargetIsRemote,
executionCwd: effectiveExecutionCwd,
});
// 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
// envConfig loop so user overrides cannot disable this guard.
env.OPENCODE_DISABLE_PROJECT_CONFIG = "true";
if (authToken) {
env.PAPERCLIP_API_KEY = authToken;
}
const preparedRuntimeConfig = await prepareOpenCodeRuntimeConfig({ env, config });
const localRuntimeConfigHome =
preparedRuntimeConfig.notes.length > 0 ? preparedRuntimeConfig.env.XDG_CONFIG_HOME : "";
try {
const runtimeEnv = Object.fromEntries(
Object.entries(ensurePathInEnv({ ...process.env, ...preparedRuntimeConfig.env })).filter(
(entry): entry is [string, string] => typeof entry[1] === "string",
),
);
const timeoutSec = resolveAdapterExecutionTargetTimeoutSec(
executionTarget,
asNumber(config.timeoutSec, 0),
);
const graceSec = asNumber(config.graceSec, 20);
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, {
installCommand: SANDBOX_INSTALL_COMMAND,
timeoutSec,
});
const resolvedCommand = await resolveAdapterExecutionTargetCommandForLogs(command, executionTarget, cwd, runtimeEnv);
let loggedEnv = buildInvocationEnvForLogs(preparedRuntimeConfig.env, {
runtimeEnv,
includeRuntimeKeys: ["HOME"],
resolvedCommand,
});
if (!executionTargetIsRemote) {
await ensureOpenCodeModelConfiguredAndAvailable({
model,
command,
cwd,
env: runtimeEnv,
});
}
const extraArgs = (() => {
const fromExtraArgs = asStringArray(config.extraArgs);
if (fromExtraArgs.length > 0) return fromExtraArgs;
return asStringArray(config.args);
})();
let restoreRemoteWorkspace: (() => Promise<void>) | null = null;
let localSkillsDir: string | null = null;
let remoteRuntimeRootDir: string | null = null;
let paperclipBridge: Awaited<ReturnType<typeof startAdapterExecutionTargetPaperclipBridge>> = null;
if (executionTarget?.kind === "remote") {
localSkillsDir = await buildOpenCodeSkillsDir(config);
await onLog(
"stdout",
`[paperclip] Syncing workspace and OpenCode runtime assets to ${describeAdapterExecutionTarget(executionTarget)}.\n`,
);
const preparedExecutionTargetRuntime = await prepareAdapterExecutionTargetRuntime({
runId,
target: executionTarget,
adapterKey: "opencode",
timeoutSec,
workspaceLocalDir: cwd,
installCommand: SANDBOX_INSTALL_COMMAND,
detectCommand: command,
onProgress: (line) => onLog("stdout", line),
onRuntimeProgress: ctx.onRuntimeProgress,
assets: [
{
key: "skills",
localDir: localSkillsDir,
followSymlinks: true,
},
...(localRuntimeConfigHome
? [{
key: "xdgConfig",
localDir: localRuntimeConfigHome,
}]
: []),
],
});
restoreRemoteWorkspace = () =>
preparedExecutionTargetRuntime.restoreWorkspace((line) => onLog("stdout", line));
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) {
preparedRuntimeConfig.env.HOME = preparedExecutionTargetRuntime.runtimeRootDir;
}
if (localRuntimeConfigHome && preparedExecutionTargetRuntime.assetDirs.xdgConfig) {
preparedRuntimeConfig.env.XDG_CONFIG_HOME = preparedExecutionTargetRuntime.assetDirs.xdgConfig;
}
prepareManagedOpenCodeRemoteHomes({
env: preparedRuntimeConfig.env,
config,
runtimeRootDir: preparedExecutionTargetRuntime.runtimeRootDir,
runId,
configDir: preparedExecutionTargetRuntime.assetDirs.xdgConfig,
});
const remoteHomeDir = config.managedAiConnection
? preparedRuntimeConfig.env.HOME
: managedHome && preparedExecutionTargetRuntime.runtimeRootDir
? preparedExecutionTargetRuntime.runtimeRootDir
: await readAdapterExecutionTargetHomeDir(runId, executionTarget, {
cwd,
env: preparedRuntimeConfig.env,
timeoutSec,
graceSec,
onLog,
});
if (remoteHomeDir && preparedExecutionTargetRuntime.assetDirs.skills) {
const remoteSkillsDir = path.posix.join(remoteHomeDir, ".claude", "skills");
await runAdapterExecutionTargetShellCommand(
runId,
executionTarget,
`mkdir -p ${JSON.stringify(path.posix.dirname(remoteSkillsDir))} && rm -rf ${JSON.stringify(remoteSkillsDir)} && cp -a ${JSON.stringify(preparedExecutionTargetRuntime.assetDirs.skills)} ${JSON.stringify(remoteSkillsDir)}`,
{ cwd, env: preparedRuntimeConfig.env, timeoutSec, graceSec, onLog },
);
}
await ensureRemoteOpenCodeModelConfiguredAndAvailable({
runId,
executionTarget,
command,
model,
cwd,
env: preparedRuntimeConfig.env,
timeoutSec,
graceSec,
});
}
const runtimeExecutionTarget = overrideAdapterExecutionTargetRemoteCwd(executionTarget, effectiveExecutionCwd);
if (executionTargetIsRemote && adapterExecutionTargetUsesPaperclipBridge(runtimeExecutionTarget)) {
paperclipBridge = await startAdapterExecutionTargetPaperclipBridge({
runId,
target: runtimeExecutionTarget,
enableSandboxDuplexBridge: adapterExecutionTargetEnablesSandboxDuplexBridge(runtimeExecutionTarget),
duplexObservabilityRecorder: adapterExecutionTargetDuplexObservabilityRecorder(runtimeExecutionTarget),
runtimeRootDir: remoteRuntimeRootDir,
adapterKey: "opencode",
timeoutSec,
hostApiToken: preparedRuntimeConfig.env.PAPERCLIP_API_KEY,
onLog,
});
if (paperclipBridge) {
Object.assign(preparedRuntimeConfig.env, paperclipBridge.env);
loggedEnv = buildInvocationEnvForLogs(preparedRuntimeConfig.env, {
runtimeEnv: Object.fromEntries(
Object.entries(ensurePathInEnv({ ...process.env, ...preparedRuntimeConfig.env })).filter(
(entry): entry is [string, string] => typeof entry[1] === "string",
),
),
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 sessionId = canResumeSession ? runtimeSessionId : null;
if (executionTargetIsRemote && runtimeSessionId && !canResumeSession) {
await onLog(
"stdout",
`[paperclip] OpenCode session "${runtimeSessionId}" does not match the current remote execution identity and will not be resumed in "${effectiveExecutionCwd}". Starting a fresh remote session.\n`,
);
} else if (runtimeSessionId && !canResumeSession) {
await onLog(
"stdout",
`[paperclip] OpenCode session "${runtimeSessionId}" was saved for cwd "${runtimeSessionCwd}" and will not be resumed in "${effectiveExecutionCwd}".\n`,
);
}
const instructionsFilePath = asString(config.instructionsFilePath, "").trim();
const resolvedInstructionsFilePath = instructionsFilePath
? path.resolve(cwd, instructionsFilePath)
: "";
const instructionsDir = resolvedInstructionsFilePath ? `${path.dirname(resolvedInstructionsFilePath)}/` : "";
let instructionsPrefix = "";
if (resolvedInstructionsFilePath) {
try {
const instructionsContents = await fs.readFile(resolvedInstructionsFilePath, "utf8");
instructionsPrefix =
`${instructionsContents}\n\n` +
`The above agent instructions were loaded from ${resolvedInstructionsFilePath}. ` +
`Resolve any relative file references from ${instructionsDir}.\n\n`;
} catch (err) {
const reason = err instanceof Error ? err.message : String(err);
await onLog(
"stdout",
`[paperclip] Warning: could not read agent instructions file "${resolvedInstructionsFilePath}": ${reason}\n`,
);
}
}
const commandNotes = (() => {
const notes = [...preparedRuntimeConfig.notes];
if (!resolvedInstructionsFilePath) return notes;
if (instructionsPrefix.length > 0) {
notes.push(`Loaded agent instructions from ${resolvedInstructionsFilePath}`);
notes.push(
`Prepended instructions + path directive to stdin prompt (relative references from ${instructionsDir}).`,
);
return notes;
}
notes.push(
`Configured instructionsFilePath ${resolvedInstructionsFilePath}, but file could not be read; continuing without injected instructions.`,
);
return notes;
})();
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 buildPrompt = (resumedSession: boolean) => {
const renderedBootstrapPrompt =
!resumedSession && bootstrapPromptTemplate.trim().length > 0
? renderTemplate(bootstrapPromptTemplate, templateData).trim()
: "";
const { taskContextNote, wakePrompt } = selectPaperclipPromptSections(context, {
resumedSession,
includeCommunicationGuidance: false,
});
const shouldUseResumeDeltaPrompt = resumedSession && wakePrompt.length > 0;
const renderedPrompt = shouldUseResumeDeltaPrompt || isPaperclipRecoveryWakePayload(context.paperclipWake)
? ""
: renderTemplate(promptTemplate, templateData);
const sessionHandoffNote = asString(context.paperclipSessionHandoffMarkdown, "").trim();
const basePrompt = joinPromptSections([
instructionsPrefix,
renderedBootstrapPrompt,
wakePrompt,
taskContextNote,
sessionHandoffNote,
renderedPrompt,
]);
return {
basePrompt,
promptMetrics: {
promptChars: basePrompt.length,
instructionsChars: instructionsPrefix.length,
bootstrapPromptChars: renderedBootstrapPrompt.length,
wakePromptChars: wakePrompt.length,
taskContextChars: taskContextNote.length,
sessionHandoffChars: sessionHandoffNote.length,
heartbeatPromptChars: renderedPrompt.length,
},
};
};
// Optional diagnostic: surface OpenCode's own logs on stderr (captured into the
// run result) so failures that OpenCode otherwise wraps as an opaque
// "Unexpected server error" can be diagnosed in remote/sandbox runs where the
// log file is unreachable. Toggle via PAPERCLIP_OPENCODE_PRINT_LOGS (run env,
// then process env).
const printLogs = isTruthyEnvFlag(
env.PAPERCLIP_OPENCODE_PRINT_LOGS ?? process.env.PAPERCLIP_OPENCODE_PRINT_LOGS,
);
const buildArgs = (resumeSessionId: string | null) => {
const args = ["run", "--format", "json"];
if (printLogs) args.push("--print-logs");
if (resumeSessionId) args.push("--session", resumeSessionId);
if (model) args.push("--model", model);
if (variant) args.push("--variant", variant);
if (extraArgs.length > 0) args.push(...extraArgs);
return args;
};
const runAttempt = async (resumeSessionId: string | null) => {
const { basePrompt, promptMetrics } = buildPrompt(Boolean(resumeSessionId));
const prompt = joinPromptSections([
selectInitialCommunicationGuidance(context, { resumedSession: Boolean(resumeSessionId) }),
basePrompt,
]);
const args = buildArgs(resumeSessionId);
if (onMeta) {
await onMeta({
adapterType: "opencode_local",
command: resolvedCommand,
cwd: effectiveExecutionCwd,
commandNotes,
commandArgs: [...args, `<stdin prompt ${prompt.length} chars>`],
env: loggedEnv,
prompt,
promptMetrics: { ...promptMetrics, promptChars: prompt.length },
context,
});
}
const proc = await runAdapterExecutionTargetProcess(runId, runtimeExecutionTarget, command, args, {
onProcessStopped: providerStop.beginInvocation(),
cwd,
env: preparedRuntimeConfig.env,
stdin: prompt,
timeoutSec,
graceSec,
onSpawn,
onRuntimeProgress: ctx.onRuntimeProgress,
onLog,
runLogTail: paperclipBridge?.runLogTail,
settleRunDisposition: paperclipBridge?.settleRunDisposition,
});
return {
proc,
rawStderr: proc.stderr,
parsed: parseOpenCodeJsonl(proc.stdout),
};
};
const toResult = (
attempt: {
proc: { exitCode: number | null; signal: string | null; timedOut: boolean; stdout: string; stderr: string; errorCode?: string | null };
rawStderr: string;
parsed: ReturnType<typeof parseOpenCodeJsonl>;
},
clearSessionOnMissingSession = 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 resolvedSessionId =
attempt.parsed.sessionId ??
(clearSessionOnMissingSession ? null : runtimeSessionId ?? runtime.sessionId ?? null);
const resolvedSessionParams = resolvedSessionId
? ({
sessionId: resolvedSessionId,
cwd: effectiveExecutionCwd,
...(workspaceId ? { workspaceId } : {}),
...(workspaceRepoUrl ? { repoUrl: workspaceRepoUrl } : {}),
...(workspaceRepoRef ? { repoRef: workspaceRepoRef } : {}),
...(executionTargetIsRemote
? {
remoteExecution: adapterExecutionTargetSessionIdentity(runtimeExecutionTarget),
}
: {}),
} as Record<string, unknown>)
: null;
const parsedError = typeof attempt.parsed.errorMessage === "string" ? attempt.parsed.errorMessage.trim() : "";
const stderrLine = firstNonEmptyLine(attempt.proc.stderr);
const rawExitCode = attempt.proc.exitCode;
const synthesizedExitCode = parsedError && (rawExitCode ?? 0) === 0 ? 1 : rawExitCode;
const fallbackErrorMessage =
parsedError ||
stderrLine ||
`OpenCode exited with code ${synthesizedExitCode ?? -1}`;
const modelId = model || null;
return {
exitCode: synthesizedExitCode,
signal: attempt.proc.signal,
timedOut: false,
errorMessage: (synthesizedExitCode ?? 0) === 0 ? null : fallbackErrorMessage,
// Forward the transport-level error code from the run-disposition seam.
// A lost duplex control channel surfaces the typed `duplex_channel_lost`
// code; every other result carries no code here.
errorCode: attempt.proc.errorCode ?? null,
usage: {
inputTokens: attempt.parsed.usage.inputTokens,
outputTokens: attempt.parsed.usage.outputTokens,
cachedInputTokens: attempt.parsed.usage.cachedInputTokens,
},
sessionId: resolvedSessionId,
sessionParams: resolvedSessionParams,
sessionDisplayId: resolvedSessionId,
provider: parseModelProvider(modelId),
biller: resolveOpenCodeBiller(runtimeEnv, parseModelProvider(modelId)),
model: modelId,
billingType: "unknown",
costUsd: attempt.parsed.costUsd,
resultJson: {
stdout: attempt.proc.stdout,
stderr: attempt.proc.stderr,
},
summary: attempt.parsed.summary,
clearSession: Boolean(clearSessionOnMissingSession && !attempt.parsed.sessionId),
};
};
try {
const initial = await runAttempt(sessionId);
const initialFailed =
!initial.proc.timedOut && ((initial.proc.exitCode ?? 0) !== 0 || Boolean(initial.parsed.errorMessage));
if (
sessionId &&
initialFailed &&
isOpenCodeUnknownSessionError(initial.proc.stdout, initial.rawStderr)
) {
await onLog(
"stdout",
`[paperclip] OpenCode session "${sessionId}" is unavailable; retrying with a fresh session.\n`,
);
const retry = await runAttempt(null);
return toResult(retry, true);
}
return toResult(initial);
} finally {
try {
await providerStop.collectBeforeRestore();
} finally {
await Promise.all([
paperclipBridge?.stop(),
restoreRemoteWorkspace?.(),
localSkillsDir ? fs.rm(path.dirname(localSkillsDir), { recursive: true, force: true }).catch(() => undefined) : Promise.resolve(),
]);
}
}
} finally {
await preparedRuntimeConfig.cleanup();
}
}