mirror of
https://github.com/alkimake/paperclip.git
synced 2026-06-17 03:10:38 +09:00
Add SSH environment support (#4358)
## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - The environments subsystem already models execution environments, but before this branch there was no end-to-end SSH-backed runtime path for agents to actually run work against a remote box > - That meant agents could be configured around environment concepts without a reliable way to execute adapter sessions remotely, sync workspace state, and preserve run context across supported adapters > - We also need environment selection to participate in normal Paperclip control-plane behavior: agent defaults, project/issue selection, route validation, and environment probing > - Because this capability is still experimental, the UI surface should be easy to hide and easy to remove later without undoing the underlying implementation > - This pull request adds SSH environment execution support across the runtime, adapters, routes, schema, and tests, then puts the visible environment-management UI behind an experimental flag > - The benefit is that we can validate real SSH-backed agent execution now while keeping the user-facing controls safely gated until the feature is ready to come out of experimentation ## What Changed - Added SSH-backed execution target support in the shared adapter runtime, including remote workspace preparation, skill/runtime asset sync, remote session handling, and workspace restore behavior after runs. - Added SSH execution coverage for supported local adapters, plus remote execution tests across Claude, Codex, Cursor, Gemini, OpenCode, and Pi. - Added environment selection and environment-management backend support needed for SSH execution, including route/service work, validation, probing, and agent default environment persistence. - Added CLI support for SSH environment lab verification and updated related docs/tests. - Added the `enableEnvironments` experimental flag and gated the environment UI behind it on company settings, agent configuration, and project configuration surfaces. ## Verification - `pnpm exec vitest run packages/adapters/claude-local/src/server/execute.remote.test.ts packages/adapters/cursor-local/src/server/execute.remote.test.ts packages/adapters/gemini-local/src/server/execute.remote.test.ts packages/adapters/opencode-local/src/server/execute.remote.test.ts packages/adapters/pi-local/src/server/execute.remote.test.ts` - `pnpm exec vitest run server/src/__tests__/environment-routes.test.ts` - `pnpm exec vitest run server/src/__tests__/instance-settings-routes.test.ts` - `pnpm exec vitest run ui/src/lib/new-agent-hire-payload.test.ts ui/src/lib/new-agent-runtime-config.test.ts` - `pnpm -r typecheck` - `pnpm build` - Manual verification on a branch-local dev server: - enabled the experimental flag - created an SSH environment - created a Linux Claude agent using that environment - confirmed a run executed on the Linux box and synced workspace changes back ## Risks - Medium: this touches runtime execution flow across multiple adapters, so regressions would likely show up in remote session setup, workspace sync, or environment selection precedence. - The UI flag reduces exposure, but the underlying runtime and route changes are still substantial and rely on migration correctness. - The change set is broad across adapters, control-plane services, migrations, and UI gating, so review should pay close attention to environment-selection precedence and remote workspace lifecycle behavior. ## Model Used - OpenAI Codex via Paperclip's local Codex adapter, GPT-5-class coding model with tool use and code execution in the local repo workspace. The local adapter does not surface a more specific public model version string in this branch workflow. ## 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 - [ ] If this change affects the UI, I have included before/after screenshots - [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
GitHub
parent
f98c348e2b
commit
e4995bbb1c
95 changed files with 10162 additions and 315 deletions
|
|
@ -3,6 +3,20 @@ import path from "node:path";
|
|||
import { fileURLToPath } from "node:url";
|
||||
import type { AdapterExecutionContext, AdapterExecutionResult } from "@paperclipai/adapter-utils";
|
||||
import type { RunProcessResult } from "@paperclipai/adapter-utils/server-utils";
|
||||
import {
|
||||
adapterExecutionTargetIsRemote,
|
||||
adapterExecutionTargetPaperclipApiUrl,
|
||||
adapterExecutionTargetRemoteCwd,
|
||||
adapterExecutionTargetSessionIdentity,
|
||||
adapterExecutionTargetSessionMatches,
|
||||
adapterExecutionTargetUsesManagedHome,
|
||||
describeAdapterExecutionTarget,
|
||||
ensureAdapterExecutionTargetCommandResolvable,
|
||||
prepareAdapterExecutionTargetRuntime,
|
||||
readAdapterExecutionTarget,
|
||||
resolveAdapterExecutionTargetCommandForLogs,
|
||||
runAdapterExecutionTargetProcess,
|
||||
} from "@paperclipai/adapter-utils/execution-target";
|
||||
import {
|
||||
asString,
|
||||
asNumber,
|
||||
|
|
@ -15,14 +29,11 @@ import {
|
|||
joinPromptSections,
|
||||
buildInvocationEnvForLogs,
|
||||
ensureAbsoluteDirectory,
|
||||
ensureCommandResolvable,
|
||||
ensurePathInEnv,
|
||||
resolveCommandForLogs,
|
||||
renderTemplate,
|
||||
renderPaperclipWakePrompt,
|
||||
stringifyPaperclipWakePayload,
|
||||
DEFAULT_PAPERCLIP_AGENT_PROMPT_TEMPLATE,
|
||||
runChildProcess,
|
||||
} from "@paperclipai/adapter-utils/server-utils";
|
||||
import {
|
||||
parseClaudeStreamJson,
|
||||
|
|
@ -42,6 +53,7 @@ interface ClaudeExecutionInput {
|
|||
agent: AdapterExecutionContext["agent"];
|
||||
config: Record<string, unknown>;
|
||||
context: Record<string, unknown>;
|
||||
executionTarget?: ReturnType<typeof readAdapterExecutionTarget>;
|
||||
authToken?: string;
|
||||
}
|
||||
|
||||
|
|
@ -92,7 +104,7 @@ function resolveClaudeBillingType(env: Record<string, string>): "api" | "subscri
|
|||
}
|
||||
|
||||
async function buildClaudeRuntimeConfig(input: ClaudeExecutionInput): Promise<ClaudeRuntimeConfig> {
|
||||
const { runId, agent, config, context, authToken } = input;
|
||||
const { runId, agent, config, context, executionTarget, authToken } = input;
|
||||
|
||||
const command = asString(config.command, "claude");
|
||||
const workspaceContext = parseObject(context.paperclipWorkspace);
|
||||
|
|
@ -218,6 +230,10 @@ async function buildClaudeRuntimeConfig(input: ClaudeExecutionInput): Promise<Cl
|
|||
if (runtimePrimaryUrl) {
|
||||
env.PAPERCLIP_RUNTIME_PRIMARY_URL = runtimePrimaryUrl;
|
||||
}
|
||||
const targetPaperclipApiUrl = adapterExecutionTargetPaperclipApiUrl(executionTarget);
|
||||
if (targetPaperclipApiUrl) {
|
||||
env.PAPERCLIP_API_URL = targetPaperclipApiUrl;
|
||||
}
|
||||
|
||||
for (const [key, value] of Object.entries(envConfig)) {
|
||||
if (typeof value === "string") env[key] = value;
|
||||
|
|
@ -228,8 +244,8 @@ async function buildClaudeRuntimeConfig(input: ClaudeExecutionInput): Promise<Cl
|
|||
}
|
||||
|
||||
const runtimeEnv = ensurePathInEnv({ ...process.env, ...env });
|
||||
await ensureCommandResolvable(command, cwd, runtimeEnv);
|
||||
const resolvedCommand = await resolveCommandForLogs(command, cwd, runtimeEnv);
|
||||
await ensureAdapterExecutionTargetCommandResolvable(command, executionTarget, cwd, runtimeEnv);
|
||||
const resolvedCommand = await resolveAdapterExecutionTargetCommandForLogs(command, executionTarget, cwd, runtimeEnv);
|
||||
const loggedEnv = buildInvocationEnvForLogs(env, {
|
||||
runtimeEnv,
|
||||
includeRuntimeKeys: ["HOME", "CLAUDE_CONFIG_DIR"],
|
||||
|
|
@ -276,7 +292,7 @@ export async function runClaudeLogin(input: {
|
|||
authToken: input.authToken,
|
||||
});
|
||||
|
||||
const proc = await runChildProcess(input.runId, runtime.command, ["login"], {
|
||||
const proc = await runAdapterExecutionTargetProcess(input.runId, null, runtime.command, ["login"], {
|
||||
cwd: runtime.cwd,
|
||||
env: runtime.env,
|
||||
timeoutSec: runtime.timeoutSec,
|
||||
|
|
@ -298,6 +314,11 @@ export async function runClaudeLogin(input: {
|
|||
|
||||
export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExecutionResult> {
|
||||
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,
|
||||
|
|
@ -315,6 +336,7 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
|
|||
agent,
|
||||
config,
|
||||
context,
|
||||
executionTarget,
|
||||
authToken,
|
||||
});
|
||||
const {
|
||||
|
|
@ -330,6 +352,7 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
|
|||
graceSec,
|
||||
extraArgs,
|
||||
} = runtimeConfig;
|
||||
const effectiveExecutionCwd = adapterExecutionTargetRemoteCwd(executionTarget, cwd);
|
||||
const terminalResultCleanupGraceMs = Math.max(
|
||||
0,
|
||||
asNumber(config.terminalResultCleanupGraceMs, 5_000),
|
||||
|
|
@ -369,27 +392,74 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
|
|||
instructionsContents: combinedInstructionsContents,
|
||||
onLog,
|
||||
});
|
||||
const effectiveInstructionsFilePath = promptBundle.instructionsFilePath ?? undefined;
|
||||
const preparedExecutionTargetRuntime = executionTargetIsRemote
|
||||
? await (async () => {
|
||||
await onLog(
|
||||
"stdout",
|
||||
`[paperclip] Syncing workspace and Claude runtime assets to ${describeAdapterExecutionTarget(executionTarget)}.\n`,
|
||||
);
|
||||
return await prepareAdapterExecutionTargetRuntime({
|
||||
target: executionTarget,
|
||||
adapterKey: "claude",
|
||||
workspaceLocalDir: cwd,
|
||||
assets: [
|
||||
{
|
||||
key: "skills",
|
||||
localDir: promptBundle.addDir,
|
||||
followSymlinks: true,
|
||||
},
|
||||
],
|
||||
});
|
||||
})()
|
||||
: null;
|
||||
const restoreRemoteWorkspace = preparedExecutionTargetRuntime
|
||||
? () => preparedExecutionTargetRuntime.restoreWorkspace()
|
||||
: null;
|
||||
const effectivePromptBundleAddDir = executionTargetIsRemote
|
||||
? preparedExecutionTargetRuntime?.assetDirs.skills ??
|
||||
path.posix.join(effectiveExecutionCwd, ".paperclip-runtime", "claude", "skills")
|
||||
: promptBundle.addDir;
|
||||
const effectiveInstructionsFilePath = promptBundle.instructionsFilePath
|
||||
? executionTargetIsRemote
|
||||
? path.posix.join(effectivePromptBundleAddDir, path.basename(promptBundle.instructionsFilePath))
|
||||
: promptBundle.instructionsFilePath
|
||||
: undefined;
|
||||
|
||||
const runtimeSessionParams = parseObject(runtime.sessionParams);
|
||||
const runtimeSessionId = asString(runtimeSessionParams.sessionId, runtime.sessionId ?? "");
|
||||
const runtimeSessionCwd = asString(runtimeSessionParams.cwd, "");
|
||||
const runtimeRemoteExecution = parseObject(runtimeSessionParams.remoteExecution);
|
||||
const runtimePromptBundleKey = asString(runtimeSessionParams.promptBundleKey, "");
|
||||
const hasMatchingPromptBundle =
|
||||
runtimePromptBundleKey.length === 0 || runtimePromptBundleKey === promptBundle.bundleKey;
|
||||
const canResumeSession =
|
||||
runtimeSessionId.length > 0 &&
|
||||
hasMatchingPromptBundle &&
|
||||
(runtimeSessionCwd.length === 0 || path.resolve(runtimeSessionCwd) === path.resolve(cwd));
|
||||
(runtimeSessionCwd.length === 0 || path.resolve(runtimeSessionCwd) === path.resolve(effectiveExecutionCwd)) &&
|
||||
adapterExecutionTargetSessionMatches(runtimeRemoteExecution, executionTarget);
|
||||
const sessionId = canResumeSession ? runtimeSessionId : null;
|
||||
if (
|
||||
executionTargetIsRemote &&
|
||||
runtimeSessionId &&
|
||||
runtimeSessionCwd.length > 0 &&
|
||||
path.resolve(runtimeSessionCwd) !== path.resolve(cwd)
|
||||
!canResumeSession
|
||||
) {
|
||||
await onLog(
|
||||
"stdout",
|
||||
`[paperclip] Claude session "${runtimeSessionId}" was saved for cwd "${runtimeSessionCwd}" and will not be resumed in "${cwd}".\n`,
|
||||
`[paperclip] Claude 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 &&
|
||||
runtimeSessionCwd.length > 0 &&
|
||||
path.resolve(runtimeSessionCwd) !== path.resolve(effectiveExecutionCwd)
|
||||
) {
|
||||
await onLog(
|
||||
"stdout",
|
||||
`[paperclip] Claude 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] Claude session "${runtimeSessionId}" was saved for cwd "${runtimeSessionCwd}" and will not be resumed in "${effectiveExecutionCwd}".\n`,
|
||||
);
|
||||
}
|
||||
if (runtimeSessionId && runtimePromptBundleKey.length > 0 && runtimePromptBundleKey !== promptBundle.bundleKey) {
|
||||
|
|
@ -416,10 +486,12 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
|
|||
const shouldUseResumeDeltaPrompt = Boolean(sessionId) && wakePrompt.length > 0;
|
||||
const renderedPrompt = shouldUseResumeDeltaPrompt ? "" : renderTemplate(promptTemplate, templateData);
|
||||
const sessionHandoffNote = asString(context.paperclipSessionHandoffMarkdown, "").trim();
|
||||
const taskContextNote = asString(context.paperclipTaskMarkdown, "").trim();
|
||||
const prompt = joinPromptSections([
|
||||
renderedBootstrapPrompt,
|
||||
wakePrompt,
|
||||
sessionHandoffNote,
|
||||
taskContextNote,
|
||||
renderedPrompt,
|
||||
]);
|
||||
const promptMetrics = {
|
||||
|
|
@ -427,6 +499,7 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
|
|||
bootstrapPromptChars: renderedBootstrapPrompt.length,
|
||||
wakePromptChars: wakePrompt.length,
|
||||
sessionHandoffChars: sessionHandoffNote.length,
|
||||
taskContextChars: taskContextNote.length,
|
||||
heartbeatPromptChars: renderedPrompt.length,
|
||||
};
|
||||
|
||||
|
|
@ -452,7 +525,7 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
|
|||
if (attemptInstructionsFilePath && !resumeSessionId) {
|
||||
args.push("--append-system-prompt-file", attemptInstructionsFilePath);
|
||||
}
|
||||
args.push("--add-dir", promptBundle.addDir);
|
||||
args.push("--add-dir", effectivePromptBundleAddDir);
|
||||
if (extraArgs.length > 0) args.push(...extraArgs);
|
||||
return args;
|
||||
};
|
||||
|
|
@ -489,7 +562,7 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
|
|||
await onMeta({
|
||||
adapterType: "claude_local",
|
||||
command: resolvedCommand,
|
||||
cwd,
|
||||
cwd: effectiveExecutionCwd,
|
||||
commandArgs: args,
|
||||
commandNotes,
|
||||
env: loggedEnv,
|
||||
|
|
@ -499,7 +572,7 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
|
|||
});
|
||||
}
|
||||
|
||||
const proc = await runChildProcess(runId, command, args, {
|
||||
const proc = await runAdapterExecutionTargetProcess(runId, executionTarget, command, args, {
|
||||
cwd,
|
||||
env,
|
||||
stdin: prompt,
|
||||
|
|
@ -584,8 +657,13 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
|
|||
const resolvedSessionParams = resolvedSessionId
|
||||
? ({
|
||||
sessionId: resolvedSessionId,
|
||||
cwd,
|
||||
cwd: effectiveExecutionCwd,
|
||||
promptBundleKey: promptBundle.bundleKey,
|
||||
...(executionTargetIsRemote
|
||||
? {
|
||||
remoteExecution: adapterExecutionTargetSessionIdentity(executionTarget),
|
||||
}
|
||||
: {}),
|
||||
...(workspaceId ? { workspaceId } : {}),
|
||||
...(workspaceRepoUrl ? { repoUrl: workspaceRepoUrl } : {}),
|
||||
...(workspaceRepoRef ? { repoRef: workspaceRepoRef } : {}),
|
||||
|
|
@ -618,21 +696,31 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
|
|||
};
|
||||
};
|
||||
|
||||
const initial = await runAttempt(sessionId ?? null);
|
||||
if (
|
||||
sessionId &&
|
||||
!initial.proc.timedOut &&
|
||||
(initial.proc.exitCode ?? 0) !== 0 &&
|
||||
initial.parsed &&
|
||||
isClaudeUnknownSessionError(initial.parsed)
|
||||
) {
|
||||
await onLog(
|
||||
"stdout",
|
||||
`[paperclip] Claude resume session "${sessionId}" is unavailable; retrying with a fresh session.\n`,
|
||||
);
|
||||
const retry = await runAttempt(null);
|
||||
return toAdapterResult(retry, { fallbackSessionId: null, clearSessionOnMissingSession: true });
|
||||
}
|
||||
try {
|
||||
const initial = await runAttempt(sessionId ?? null);
|
||||
if (
|
||||
sessionId &&
|
||||
!initial.proc.timedOut &&
|
||||
(initial.proc.exitCode ?? 0) !== 0 &&
|
||||
initial.parsed &&
|
||||
isClaudeUnknownSessionError(initial.parsed)
|
||||
) {
|
||||
await onLog(
|
||||
"stdout",
|
||||
`[paperclip] Claude resume session "${sessionId}" is unavailable; retrying with a fresh session.\n`,
|
||||
);
|
||||
const retry = await runAttempt(null);
|
||||
return toAdapterResult(retry, { fallbackSessionId: null, clearSessionOnMissingSession: true });
|
||||
}
|
||||
|
||||
return toAdapterResult(initial, { fallbackSessionId: runtimeSessionId || runtime.sessionId });
|
||||
return toAdapterResult(initial, { fallbackSessionId: runtimeSessionId || runtime.sessionId });
|
||||
} finally {
|
||||
if (restoreRemoteWorkspace) {
|
||||
await onLog(
|
||||
"stdout",
|
||||
`[paperclip] Restoring workspace changes from ${describeAdapterExecutionTarget(executionTarget)}.\n`,
|
||||
);
|
||||
await restoreRemoteWorkspace();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue