mirror of
https://github.com/alkimake/paperclip.git
synced 2026-06-14 18:10:39 +09:00
## 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
101 lines
2.9 KiB
TypeScript
101 lines
2.9 KiB
TypeScript
import { asNumber, asString, parseJson, parseObject } from "@paperclipai/adapter-utils/server-utils";
|
|
|
|
function errorText(value: unknown): string {
|
|
if (typeof value === "string") return value;
|
|
const rec = parseObject(value);
|
|
const message = asString(rec.message, "").trim();
|
|
if (message) return message;
|
|
const data = parseObject(rec.data);
|
|
const nestedMessage = asString(data.message, "").trim();
|
|
if (nestedMessage) return nestedMessage;
|
|
const name = asString(rec.name, "").trim();
|
|
if (name) return name;
|
|
const code = asString(rec.code, "").trim();
|
|
if (code) return code;
|
|
try {
|
|
return JSON.stringify(rec);
|
|
} catch {
|
|
return "";
|
|
}
|
|
}
|
|
|
|
export function parseOpenCodeJsonl(stdout: string) {
|
|
let sessionId: string | null = null;
|
|
const messages: string[] = [];
|
|
const errors: string[] = [];
|
|
const toolErrors: string[] = [];
|
|
const usage = {
|
|
inputTokens: 0,
|
|
cachedInputTokens: 0,
|
|
outputTokens: 0,
|
|
};
|
|
let costUsd = 0;
|
|
|
|
for (const rawLine of stdout.split(/\r?\n/)) {
|
|
const line = rawLine.trim();
|
|
if (!line) continue;
|
|
|
|
const event = parseJson(line);
|
|
if (!event) continue;
|
|
|
|
const currentSessionId = asString(event.sessionID, "").trim();
|
|
if (currentSessionId) sessionId = currentSessionId;
|
|
|
|
const type = asString(event.type, "");
|
|
|
|
if (type === "text") {
|
|
const part = parseObject(event.part);
|
|
const text = asString(part.text, "").trim();
|
|
if (text) messages.push(text);
|
|
continue;
|
|
}
|
|
|
|
if (type === "step_finish") {
|
|
const part = parseObject(event.part);
|
|
const tokens = parseObject(part.tokens);
|
|
const cache = parseObject(tokens.cache);
|
|
usage.inputTokens += asNumber(tokens.input, 0);
|
|
usage.cachedInputTokens += asNumber(cache.read, 0);
|
|
usage.outputTokens += asNumber(tokens.output, 0) + asNumber(tokens.reasoning, 0);
|
|
costUsd += asNumber(part.cost, 0);
|
|
continue;
|
|
}
|
|
|
|
if (type === "tool_use") {
|
|
const part = parseObject(event.part);
|
|
const state = parseObject(part.state);
|
|
if (asString(state.status, "") === "error") {
|
|
const text = asString(state.error, "").trim();
|
|
if (text) toolErrors.push(text);
|
|
}
|
|
continue;
|
|
}
|
|
|
|
if (type === "error") {
|
|
const text = errorText(event.error ?? event.message).trim();
|
|
if (text) errors.push(text);
|
|
continue;
|
|
}
|
|
}
|
|
|
|
return {
|
|
sessionId,
|
|
summary: messages.join("\n\n").trim(),
|
|
usage,
|
|
costUsd,
|
|
errorMessage: errors.length > 0 ? errors.join("\n") : null,
|
|
toolErrors,
|
|
};
|
|
}
|
|
|
|
export function isOpenCodeUnknownSessionError(stdout: string, stderr: string): boolean {
|
|
const haystack = `${stdout}\n${stderr}`
|
|
.split(/\r?\n/)
|
|
.map((line) => line.trim())
|
|
.filter(Boolean)
|
|
.join("\n");
|
|
|
|
return /unknown\s+session|session\b.*\bnot\s+found|resource\s+not\s+found:.*[\\/]session[\\/].*\.json|notfounderror|no session/i.test(
|
|
haystack,
|
|
);
|
|
}
|