forked from farhoodlabs/paperclip
Polish board settings and skills workflow (#4863)
## Thinking Path > - Paperclip's board UI and bundled skills are the operator layer for configuring agents, routines, issue workflows, and local troubleshooting loops. > - The prior rollup mixed this operator polish with database backups, backend reliability, thread scale, and cost/workflow primitives. > - This pull request isolates the remaining board QoL, settings, issue-detail integration, adapter config cleanup, and skills smoke tooling. > - It includes some integration-level overlap with the thread and workflow slices so this branch can run from `origin/master` while still preserving the full original work. > - Preferred merge order is the narrower primitives first, then this integration PR last. > - The benefit is that reviewers can inspect the user-facing board/settings/skills layer separately from backend infrastructure changes. ## What Changed - Added board/settings polish for agents, routines, company settings, project workspace detail, and issue detail controls. - Added agent/routine UI regression tests and New Issue dialog coverage. - Integrated issue-detail activity/cost/interaction surfaces and leaf work pause/resume controls. - Cleaned bundled adapter UI config defaults and onboarding copy. - Added terminal-bench loop and work-stoppage diagnosis skills plus a smoke test script. - Updated attachment type handling and Paperclip skill/API guidance. ## Verification - `pnpm install --frozen-lockfile` - `pnpm exec vitest run ui/src/pages/Agents.test.tsx ui/src/pages/Routines.test.tsx ui/src/components/NewIssueDialog.test.tsx ui/src/pages/IssueDetail.test.tsx server/src/__tests__/costs-service.test.ts server/src/__tests__/issue-thread-interaction-routes.test.ts server/src/__tests__/issue-thread-interactions-service.test.ts` - Result: 7 test files passed, 54 tests passed. - `pnpm run smoke:terminal-bench-loop-skill` - Result: JSON output included `"ok": true` and `"cleanup": true`. - UI screenshots not included because verification is focused component/page coverage for the changed board surfaces. ## Risks - This is the integration-heavy PR in the split and intentionally overlaps some component/API primitives with the issue-thread and workflow PRs so it can run from `origin/master`. - Preferred merge order: #4859, #4860, #4861, #4862, then this PR last. If earlier branches merge first, this PR may need a straightforward conflict refresh in shared UI files. - The terminal-bench smoke script creates temporary mock issues and relies on cleanup; the verified run returned `cleanup: true`. > For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and discuss it in `#dev` before opening the PR. Feature PRs that overlap with planned core work may need to be redirected — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used - OpenAI Codex, GPT-5.5, code execution and GitHub CLI tool use, medium reasoning effort. ## 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 - [x] 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 --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
This commit is contained in:
Dotta
+357
@@ -0,0 +1,357 @@
|
||||
#!/usr/bin/env node
|
||||
|
||||
import { readFile } from "node:fs/promises";
|
||||
import { join } from "node:path";
|
||||
import { fileURLToPath } from "node:url";
|
||||
|
||||
const repoRoot = join(fileURLToPath(new URL(".", import.meta.url)), "..", "..");
|
||||
|
||||
function parseArgs(argv) {
|
||||
const parsed = {
|
||||
keep: false,
|
||||
sourceIssueId: process.env.PAPERCLIP_TASK_ID ?? null,
|
||||
projectId: process.env.PAPERCLIP_PROJECT_ID ?? null,
|
||||
goalId: process.env.PAPERCLIP_GOAL_ID ?? null,
|
||||
runKey: null,
|
||||
};
|
||||
|
||||
for (let index = 0; index < argv.length; index += 1) {
|
||||
const arg = argv[index];
|
||||
if (arg === "--keep") {
|
||||
parsed.keep = true;
|
||||
continue;
|
||||
}
|
||||
if (arg === "--source-issue-id") {
|
||||
parsed.sourceIssueId = argv[++index] ?? null;
|
||||
continue;
|
||||
}
|
||||
if (arg === "--project-id") {
|
||||
parsed.projectId = argv[++index] ?? null;
|
||||
continue;
|
||||
}
|
||||
if (arg === "--goal-id") {
|
||||
parsed.goalId = argv[++index] ?? null;
|
||||
continue;
|
||||
}
|
||||
if (arg === "--run-key") {
|
||||
parsed.runKey = argv[++index] ?? null;
|
||||
continue;
|
||||
}
|
||||
if (arg === "--help" || arg === "-h") {
|
||||
printUsage();
|
||||
process.exit(0);
|
||||
}
|
||||
throw new Error(`Unknown argument: ${arg}`);
|
||||
}
|
||||
|
||||
return parsed;
|
||||
}
|
||||
|
||||
function printUsage() {
|
||||
console.log(`
|
||||
Usage:
|
||||
PAPERCLIP_API_URL=http://localhost:3100 \\
|
||||
PAPERCLIP_API_KEY=... \\
|
||||
PAPERCLIP_COMPANY_ID=... \\
|
||||
pnpm smoke:terminal-bench-loop-skill
|
||||
|
||||
Options:
|
||||
--source-issue-id <uuid> Attach smoke issues under an existing Paperclip issue.
|
||||
--project-id <uuid> Override inferred project id.
|
||||
--goal-id <uuid> Override inferred goal id.
|
||||
--run-key <string> Stable key used in smoke titles and mocked artifact paths.
|
||||
--keep Leave smoke issues in their verified blocked/in_review posture.
|
||||
`);
|
||||
}
|
||||
|
||||
function requireEnv(name) {
|
||||
const value = process.env[name];
|
||||
if (!value) {
|
||||
throw new Error(`${name} is required. Run against a local Paperclip server with an agent or board API token.`);
|
||||
}
|
||||
return value;
|
||||
}
|
||||
|
||||
function slugify(value) {
|
||||
return value.replace(/[^a-zA-Z0-9_.-]+/g, "-").replace(/^-+|-+$/g, "").slice(0, 80);
|
||||
}
|
||||
|
||||
function assert(condition, message) {
|
||||
if (!condition) {
|
||||
throw new Error(message);
|
||||
}
|
||||
}
|
||||
|
||||
async function assertLocalSkillPackage() {
|
||||
const skillPath = join(repoRoot, "skills", "terminal-bench-loop", "SKILL.md");
|
||||
const markdown = await readFile(skillPath, "utf8");
|
||||
for (const expected of [
|
||||
"name: terminal-bench-loop",
|
||||
"request_confirmation",
|
||||
"diagnosis",
|
||||
"blockedByIssueIds",
|
||||
"PAPERCLIPAI_CMD",
|
||||
]) {
|
||||
assert(markdown.includes(expected), `Skill smoke expected ${skillPath} to mention ${expected}`);
|
||||
}
|
||||
}
|
||||
|
||||
function createApiClient({ apiUrl, apiKey, runId }) {
|
||||
const baseUrl = apiUrl.replace(/\/+$/, "");
|
||||
|
||||
return async function api(method, path, { body, ok } = {}) {
|
||||
const expectedStatuses = ok ?? (method === "POST" || method === "PUT" ? [200, 201] : [200]);
|
||||
const headers = {
|
||||
Authorization: `Bearer ${apiKey}`,
|
||||
Accept: "application/json",
|
||||
};
|
||||
if (body !== undefined) {
|
||||
headers["Content-Type"] = "application/json";
|
||||
}
|
||||
if (runId && method !== "GET") {
|
||||
headers["X-Paperclip-Run-Id"] = runId;
|
||||
}
|
||||
|
||||
const response = await fetch(`${baseUrl}${path}`, {
|
||||
method,
|
||||
headers,
|
||||
body: body === undefined ? undefined : JSON.stringify(body),
|
||||
});
|
||||
const text = await response.text();
|
||||
const data = text ? JSON.parse(text) : null;
|
||||
if (!expectedStatuses.includes(response.status)) {
|
||||
throw new Error(`${method} ${path} returned ${response.status}: ${text}`);
|
||||
}
|
||||
return data;
|
||||
};
|
||||
}
|
||||
|
||||
async function main() {
|
||||
const args = parseArgs(process.argv.slice(2));
|
||||
const apiUrl = requireEnv("PAPERCLIP_API_URL");
|
||||
const apiKey = requireEnv("PAPERCLIP_API_KEY");
|
||||
const companyId = requireEnv("PAPERCLIP_COMPANY_ID");
|
||||
const runId = process.env.PAPERCLIP_RUN_ID ?? null;
|
||||
const api = createApiClient({ apiUrl, apiKey, runId });
|
||||
|
||||
await assertLocalSkillPackage();
|
||||
|
||||
const sourceIssue = args.sourceIssueId
|
||||
? await api("GET", `/api/issues/${args.sourceIssueId}`)
|
||||
: null;
|
||||
const projectId = args.projectId ?? sourceIssue?.projectId ?? null;
|
||||
const goalId = args.goalId ?? sourceIssue?.goalId ?? null;
|
||||
const runKey = slugify(args.runKey ?? runId ?? `local-${new Date().toISOString()}`);
|
||||
const artifactRoot = `mock://terminal-bench-loop-smoke/${runKey}`;
|
||||
const titlePrefix = `[smoke:${runKey}]`;
|
||||
const commonIssueFields = {
|
||||
...(projectId ? { projectId } : {}),
|
||||
...(goalId ? { goalId } : {}),
|
||||
priority: "low",
|
||||
};
|
||||
|
||||
const loop = await api("POST", `/api/companies/${companyId}/issues`, {
|
||||
body: {
|
||||
...commonIssueFields,
|
||||
...(sourceIssue ? { parentId: sourceIssue.id } : {}),
|
||||
title: `${titlePrefix} Terminal-Bench loop skill smoke`,
|
||||
status: "todo",
|
||||
description: [
|
||||
"Deterministic smoke for the /terminal-bench-loop skill.",
|
||||
"",
|
||||
"- Task: terminal-bench/fix-git",
|
||||
"- Iteration budget: 1",
|
||||
"- Benchmark command: mocked; no Terminal-Bench, Harbor, model, or provider process is started.",
|
||||
`- Artifact root: ${artifactRoot}`,
|
||||
].join("\n"),
|
||||
},
|
||||
});
|
||||
|
||||
const iteration = await api("POST", `/api/companies/${companyId}/issues`, {
|
||||
body: {
|
||||
...commonIssueFields,
|
||||
parentId: loop.id,
|
||||
title: `${titlePrefix} Iteration 1: terminal-bench/fix-git`,
|
||||
status: "todo",
|
||||
description: [
|
||||
"Smoke iteration child created by the deterministic terminal-bench-loop skill smoke.",
|
||||
"",
|
||||
"This issue records mocked run artifacts, diagnosis, and the pending confirmation path.",
|
||||
].join("\n"),
|
||||
},
|
||||
});
|
||||
|
||||
const runDocument = await api("PUT", `/api/issues/${iteration.id}/documents/run`, {
|
||||
body: {
|
||||
title: "Mocked benchmark run",
|
||||
format: "markdown",
|
||||
body: [
|
||||
"# Mocked benchmark run",
|
||||
"",
|
||||
"- Label: smoke / non-comparable",
|
||||
"- Terminal-Bench task: terminal-bench/fix-git",
|
||||
"- Stop reason: verifier_failed",
|
||||
`- Manifest: ${artifactRoot}/manifest.json`,
|
||||
`- Results JSONL: ${artifactRoot}/results.jsonl`,
|
||||
`- Harbor raw job folder: ${artifactRoot}/harbor/raw-job`,
|
||||
"",
|
||||
"No benchmark process, Harbor job, model call, or provider call was started.",
|
||||
].join("\n"),
|
||||
changeSummary: "Record deterministic mocked benchmark artifact paths.",
|
||||
},
|
||||
});
|
||||
|
||||
const diagnosisDocument = await api("PUT", `/api/issues/${iteration.id}/documents/diagnosis`, {
|
||||
body: {
|
||||
title: "Smoke diagnosis",
|
||||
format: "markdown",
|
||||
body: [
|
||||
"# Smoke diagnosis",
|
||||
"",
|
||||
`Exact stop point: ${iteration.identifier ?? iteration.id} is waiting on a product-fix confirmation after a mocked verifier failure.`,
|
||||
"",
|
||||
"Next-action owner: board/user must accept or reject the confirmation before implementation subtasks exist.",
|
||||
"",
|
||||
"Failure taxonomy: Paperclip product gap, mocked for smoke coverage.",
|
||||
"",
|
||||
"Invariant check:",
|
||||
"",
|
||||
"- Productive work continues: acceptance wakes the assignee and would create the implementation path.",
|
||||
"- Only real blockers stop work: the loop parent is blocked by this iteration child while the confirmation is pending.",
|
||||
"- No infinite loops: iteration budget is 1 and the smoke does not start a rerun.",
|
||||
].join("\n"),
|
||||
changeSummary: "Record exact stop point and next-action owner.",
|
||||
},
|
||||
});
|
||||
|
||||
const planDocument = await api("PUT", `/api/issues/${iteration.id}/documents/plan`, {
|
||||
body: {
|
||||
title: "Smoke fix proposal",
|
||||
format: "markdown",
|
||||
body: [
|
||||
"# Smoke fix proposal",
|
||||
"",
|
||||
"Proposed product rule: a Terminal-Bench loop iteration that identifies a product gap must create a request_confirmation interaction before implementation subtasks exist.",
|
||||
"",
|
||||
`Evidence: mocked run document ${runDocument.id}; diagnosis document ${diagnosisDocument.id}.`,
|
||||
].join("\n"),
|
||||
changeSummary: "Record smoke proposal for confirmation target.",
|
||||
},
|
||||
});
|
||||
|
||||
const confirmation = await api("POST", `/api/issues/${iteration.id}/interactions`, {
|
||||
body: {
|
||||
kind: "request_confirmation",
|
||||
idempotencyKey: `confirmation:${iteration.id}:plan:${planDocument.latestRevisionId}`,
|
||||
title: "Smoke plan confirmation",
|
||||
continuationPolicy: "wake_assignee",
|
||||
payload: {
|
||||
version: 1,
|
||||
prompt: "Accept the mocked terminal-bench-loop product-fix proposal?",
|
||||
acceptLabel: "Accept smoke plan",
|
||||
rejectLabel: "Reject smoke plan",
|
||||
rejectRequiresReason: true,
|
||||
rejectReasonLabel: "What should change?",
|
||||
detailsMarkdown: "This deterministic smoke verifies the waiting path only; do not treat it as a real benchmark result.",
|
||||
supersedeOnUserComment: true,
|
||||
target: {
|
||||
type: "issue_document",
|
||||
issueId: iteration.id,
|
||||
documentId: planDocument.id,
|
||||
key: "plan",
|
||||
revisionId: planDocument.latestRevisionId,
|
||||
revisionNumber: planDocument.latestRevisionNumber,
|
||||
label: "Smoke fix proposal",
|
||||
},
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
await api("PATCH", `/api/issues/${iteration.id}`, {
|
||||
body: {
|
||||
status: "in_review",
|
||||
comment: [
|
||||
"Smoke waiting path opened.",
|
||||
"",
|
||||
`Pending confirmation: ${confirmation.id}`,
|
||||
"Next-action owner: board/user accepts or rejects the mocked proposal.",
|
||||
].join("\n"),
|
||||
},
|
||||
});
|
||||
|
||||
await api("PATCH", `/api/issues/${loop.id}`, {
|
||||
body: {
|
||||
status: "blocked",
|
||||
blockedByIssueIds: [iteration.id],
|
||||
comment: [
|
||||
"Smoke loop parent is blocked by its iteration child while the typed confirmation is pending.",
|
||||
"",
|
||||
`Blocking iteration: ${iteration.identifier ?? iteration.id}`,
|
||||
].join("\n"),
|
||||
},
|
||||
});
|
||||
|
||||
const [verifiedLoop, verifiedIteration, verifiedRunDoc, verifiedDiagnosisDoc, interactions] = await Promise.all([
|
||||
api("GET", `/api/issues/${loop.id}`),
|
||||
api("GET", `/api/issues/${iteration.id}`),
|
||||
api("GET", `/api/issues/${iteration.id}/documents/run`),
|
||||
api("GET", `/api/issues/${iteration.id}/documents/diagnosis`),
|
||||
api("GET", `/api/issues/${iteration.id}/interactions`),
|
||||
]);
|
||||
|
||||
assert(verifiedLoop.status === "blocked", `Expected loop issue to be blocked, got ${verifiedLoop.status}`);
|
||||
assert(
|
||||
Array.isArray(verifiedLoop.blockedBy) && verifiedLoop.blockedBy.some((blocker) => blocker.id === iteration.id),
|
||||
"Expected loop issue to be blocked by the iteration child",
|
||||
);
|
||||
assert(
|
||||
verifiedIteration.status === "in_review",
|
||||
`Expected iteration issue to be in_review, got ${verifiedIteration.status}`,
|
||||
);
|
||||
assert(verifiedRunDoc.body.includes(`${artifactRoot}/results.jsonl`), "Expected run doc to include mocked results path");
|
||||
assert(
|
||||
verifiedDiagnosisDoc.body.includes("Exact stop point") && verifiedDiagnosisDoc.body.includes("Next-action owner"),
|
||||
"Expected diagnosis doc to include exact stop point and next-action owner",
|
||||
);
|
||||
assert(
|
||||
interactions.some((interaction) =>
|
||||
interaction.id === confirmation.id
|
||||
&& interaction.kind === "request_confirmation"
|
||||
&& interaction.status === "pending"
|
||||
&& interaction.continuationPolicy === "wake_assignee"
|
||||
),
|
||||
"Expected a pending request_confirmation interaction with wake_assignee continuation",
|
||||
);
|
||||
|
||||
if (!args.keep) {
|
||||
await api("PATCH", `/api/issues/${loop.id}`, {
|
||||
body: {
|
||||
status: "cancelled",
|
||||
blockedByIssueIds: [],
|
||||
comment: "Smoke cleanup: verified topology and cancelled the short-lived loop parent.",
|
||||
},
|
||||
});
|
||||
await api("PATCH", `/api/issues/${iteration.id}`, {
|
||||
body: {
|
||||
status: "cancelled",
|
||||
comment: "Smoke cleanup: verified confirmation/waiting posture and cancelled the short-lived iteration child.",
|
||||
},
|
||||
});
|
||||
}
|
||||
|
||||
console.log(JSON.stringify({
|
||||
ok: true,
|
||||
cleanup: !args.keep,
|
||||
loopIssue: { id: loop.id, identifier: loop.identifier ?? null },
|
||||
iterationIssue: { id: iteration.id, identifier: iteration.identifier ?? null },
|
||||
runDocument: runDocument.id,
|
||||
diagnosisDocument: diagnosisDocument.id,
|
||||
confirmation: confirmation.id,
|
||||
artifactRoot,
|
||||
}, null, 2));
|
||||
}
|
||||
|
||||
main().catch((error) => {
|
||||
console.error(`terminal-bench-loop skill smoke failed: ${error.message}`);
|
||||
process.exit(1);
|
||||
});
|
||||
Reference in New Issue
Block a user