Files
PaperClipAI/tests/runner-e2e/history.ts
T
DottaandPaperclip 11921075a4 Add first-task onboarding skill and Runner E2E coverage (#13517)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - The first task helps a new user define and approve useful work.
> - That workflow needs reusable instructions and tests against the
production experience.
> - Native Codex and Claude must load the assigned skill, including
after resume.
> - Maintainers need recorded conversations and precise failed checks to
judge regressions.
> - This pull request adds the first-task skill and a suite in the
shared Runner E2E harness.
> - It keeps behavior results separate from informational quality scores
and incomplete recordings.

## Linked Issues or Issue Description

**What existing behavior does this improve?**

The first onboarding task and the Runner E2E report used to review it.

**Current behavior**

Onboarding embeds its policy in a hidden brief. Native Codex drops the
skill-instructions setting at the Rust boundary. The shared E2E harness
has no onboarding suite or full conversation view.

**Proposed behavior**

Assign and invoke `/first-task` for the onboarding task. Send selected
Codex skills as structured protocol inputs. Run twelve scenarios across
legacy Codex, legacy Claude, native Codex, and native ACPX Claude.
Include all 48 cells in full campaigns. Show recorded chat, question and
approval cards, exact checks, instructions, and billing in the shared
dashboard.

**Reason and benefit**

Measure the real onboarding experience before changing prompts.
Distinguish infrastructure failures, behavior failures, and unexercised
journey steps.

**Breaking changes**

No database migration or production API change. First-task instructions
now live in an assigned skill. The user-edited persona is preserved; the
skill includes the maintainer-approved proposal-mode mapping and
saved-plan requirement.

Related: #11043 is earlier onboarding work. #13422 already fixes native
Claude model pinning, context delivery, and read permissions on master;
this branch includes those fixes through its base. The new Claude
recovery test supplements them.

## What Changed

- Extract and assign the first-task skill while retaining the production
greeting and opening question.
- Carry the Codex skill-instructions flag through thread start and
resume. Resolve explicit task skill references only against assigned
skills and send native skill inputs.
- Invoke an unambiguously selected assigned skill through Claude ACPX’s
native slash-command parser on initial and resumed turns, retaining the
entire task/wake envelope as its argument. Do not carry that invocation
into ordinary tasks.
- Restore the saved single-task proposal modes: confirmation card, or
saved plan with revision-targeted checkbox approval. Explicit plan
requests also require a saved plan.
- Add first-response and complete-journey cases with fixed user facts,
acceptance checkpoints, durable outcome checks, and accounting for child
runs.
- Fail the eval when choice questions have fewer than two real options.
Recognize planning documents without treating them as completed work.
- Add optional, bounded quality judging as explicit post-processing.
- Render full conversations and static interaction cards in the shared
report. Conversations start folded. Show original and regraded results
and incomplete journeys distinctly.
- Keep credential-persistence scanning outside the first-task behavioral
suite; retain public evidence redaction.
- Refresh generated capability references after the API-reference edits.
- Correct shared native question guidance and tool schemas: choices need
at least two meaningful options; open-ended questions use canonical text
fields with the required compatibility payload. Verify both formats
through real tool-authority persistence.
- Disable announcements automatically for every isolated Runner E2E
process and label the gallery environment/provider/target explicitly.
- Remove CI races in the GitHub connection browser test and native
session recovery test by waiting for the actual async work before
asserting its results.

## Verification

- `pnpm exec vitest run
server/src/services/onboarding-first-task-assets.test.ts
server/src/__tests__/issue-onboarding-first-task-routes.test.ts`: 19
passed.
- `pnpm --dir packages/paperclip-runner exec vitest run
src/drivers/acpx/runtime-host.test.ts
src/drivers/acpx/native-skill-prompt.test.ts
src/cli/acpx-runtime-sidecar.test.ts`: 70 passed. Native command
forwarding and the 1 MiB input boundary both failed before their fixes
and passed afterward. Coverage includes changed skills on reopen,
approval context, and an ordinary subsequent task.
- Runner E2E unit suite: 306 passed. Harness typecheck passed. The 64
first-task fixture and grader tests also pass.
- Full repository typecheck and build passed locally. Server typecheck
and Runner build passed again after the native-command change.
- Full GitHub Actions CI passed on `23e56447b`: all
server/workspace/browser shards, Runner verification, typecheck/release
registry, build, canary, policy, and Docker checks. Greptile reviewed
this exact head at 5/5 with no unresolved threads. The earlier broad
local run had database startup/timing failures that passed isolated
retries; the complete remote suite is green.
- Merge verification against current master: 312 harness tests and 13
native recovery tests passed. Regenerated semantic contracts and fixture
hashes pass their consistency check. Full local typecheck and build also
passed on the stacked queue branch. After merging the latest master and
preserving the GitHub setup timing regression in the split browser
suite, both focused GitHub browser tests passed. Three CI timing/startup
flakes passed local verification and one remote retry; all latest-head
checks are green.
- Real pinned Claude SDK and Claude ACP JSON-RPC probes against a local
mock API confirmed that `/skill-name` expands the assigned skill body
before the model request and retains the task arguments. A prose mention
does not. The probes made no paid model calls. The ACP probe used the
current first-task skill body and retained the wake arguments.
- [Full 48-case campaign and
report](https://pages.paperclip.ing/runner-e2e-first-task-35053063880/):
44 passed after three interrupted Codex cases completed in targeted
reruns. Original results, regrades, and all 51 executions remain in the
report provenance.
- [Claude campaign after the shared-question
fix](https://pages.paperclip.ing/runner-e2e-first-task-claude-35099525201/):
10/12 passed with zero single-option failures. All 12 recorded the
current assigned skill and corrected guidance. The failures exposed
skipped skill invocation and a missing saved plan. This PR adds native
command invocation and explicit saved-plan instructions; the subsequent
report below still shows behavior failures.
- [Fresh 12-case Claude
report](https://pages.paperclip.ing/runner-e2e-first-task-claude-35102737804/)
at `78452129e`: 10/12 pass after correcting two false proposal-matcher
failures. The recordings said “Here is the task I will create and
run/complete” in approval cards; the old matcher missed that word order.
Regression tests failed before the fix and pass after it. Original
results and offline regrade provenance remain linked. No agent rerun was
needed. Zero single-option-question failures; two behavior failures
remain: direct work before acceptance on a plain first message, and an
explicit plan request without a saved plan. Neither check was relaxed.
The follow-up `82087ac7e` fixes command-prefix size accounting;
`94aefb1f3` fixes only that proposal matcher.
- Report browser checks confirm folded conversations, rendered cards,
explicit Local/Daytona labels, and no page errors. The published-object
audit scanned 1,306 text files across 2,154 objects with no
credential-format findings or prohibited files. Image pixels and unknown
token formats are outside that scan.

## Risks

- Model behavior is nondeterministic. One campaign is evidence, not a
guarantee. The two remaining Claude behavior failures are visible in the
report and require further product work; this PR does not claim all
onboarding scenarios pass.
- The suite checks persisted Paperclip effects. It cannot prove the
absence of arbitrary external effects.
- Historical recordings can miss later journey steps. These remain
incomplete, never passes.
- Native profiles switch runtime after the production onboarding wizard
because it does not yet expose a native option.
- Quality scores are informational and cannot override behavioral
failures.

## Model Used

OpenAI Codex, GPT-6, with reasoning, repository tools, and code
execution. The exact deployed model identifier and context-window size
are not exposed in this session.

## 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] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

---------

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-09-16 14:24:32 -05:00

283 lines
9.1 KiB
TypeScript

import { isIncompleteFirstTaskResult } from "./case-outcome.js";
import { validateRetainedRunnerResult } from "./result-validation.js";
import {
discoverReportCatalog,
parseReportExecutionId,
type ReportExecution,
} from "./report-catalog.js";
import { runnerMatrix, runnerSuites } from "./catalog.js";
import {
aggregateCampaignBilling,
summarizeExecutionBilling,
} from "./billing.js";
import { resolveRunnerE2ESource } from "./source.js";
import type {
RunnerE2ECampaign,
RunnerE2EHistoryCampaign,
RunnerE2EHistoryIndex,
RunnerE2EResult,
} from "./types.js";
export function canonicalExecutionId(id: string) {
if (runnerMatrix.some((execution) => execution.id === id)) return id;
const coreId = `core-compatibility.${id}`;
return runnerMatrix.some((execution) => execution.id === coreId)
? coreId
: id;
}
export function upgradeRunnerResult(result: RunnerE2EResult): RunnerE2EResult {
validateRetainedRunnerResult(result);
const executionId = canonicalExecutionId(result.executionId);
const execution = runnerMatrix.find(
(candidate) => candidate.id === executionId,
);
if (!execution)
return {
...result,
executionId,
suiteId: result.suiteId ?? parseReportExecutionId(executionId).suiteId,
};
return {
...result,
executionId,
suiteId: result.suiteId ?? execution.suite.id,
suiteDefinitionHash:
result.suiteDefinitionHash ?? execution.suiteDefinitionHash,
...(result.schema === "paperclip.runner-e2e.result/v1"
? {
source: result.source ?? {
sha: null,
ref: null,
workflowRunUrl: null,
},
}
: {}),
};
}
export function buildRunnerCampaign(input: {
campaignId: string;
generatedAt: string;
expected: readonly string[];
results: readonly RunnerE2EResult[];
eventName?: string | null;
catalog?: readonly ReportExecution[];
}): RunnerE2ECampaign {
const expected = input.expected.map(canonicalExecutionId);
const results = input.results.map((result) => ({
...upgradeRunnerResult(result),
billing: result.billing ?? summarizeExecutionBilling(result),
}));
const knownCatalog = input.catalog ?? runnerMatrix;
const catalog = discoverReportCatalog({
catalog: knownCatalog,
expected,
results,
});
const discoveredSuites = [
...new Map(
catalog.map((execution) => [execution.suite.id, execution.suite]),
).values(),
];
const resultSource = results.find((result) => result.source)?.source;
const source = {
...resolveRunnerE2ESource(resultSource),
eventName: input.eventName ?? process.env.GITHUB_EVENT_NAME ?? null,
};
const suites = discoveredSuites
.map((suite) => {
const suiteExpected = expected.filter((id) =>
id.startsWith(`${suite.id}.`),
);
if (suiteExpected.length === 0) return null;
const suiteResults = results.filter(
(result) =>
expected.includes(result.executionId) &&
result.executionId.startsWith(`${suite.id}.`),
);
const passed = suiteResults.filter(
(result) => result.status === "passed" && result.cleanup === "passed",
).length;
const executed = suiteResults.filter(
(result) => result.attempt > 0,
).length;
return {
suiteId: suite.id,
suiteDefinitionHash:
suiteResults[0]?.suiteDefinitionHash ??
catalog.find((execution) => execution.suite.id === suite.id)!
.suiteDefinitionHash,
expected: suite.expectedMatrixSize,
selected: suiteExpected.length,
executed,
passed,
failed: suiteExpected.length - passed - suiteResults.filter(r => isIncompleteFirstTaskResult(r)).length,
incomplete: suiteResults.filter(r => isIncompleteFirstTaskResult(r)).length,
retries: suiteResults.reduce(
(total, result) => total + Math.max(0, result.attempt - 1),
0,
),
cleanupPassed: suiteResults.every(
(result) => result.cleanup === "passed",
),
complete:
suiteExpected.length === suite.expectedMatrixSize &&
knownCatalog.filter((execution) => execution.suite.id === suite.id)
.length === suiteExpected.length &&
knownCatalog
.filter((execution) => execution.suite.id === suite.id)
.every(
(execution) =>
suiteExpected.includes(execution.id) &&
suiteResults.every(
(result) =>
result.suiteDefinitionHash ===
execution.suiteDefinitionHash,
),
),
durationMs: suiteResults.reduce(
(total, result) => total + result.durationMs,
0,
),
billing: aggregateCampaignBilling(suiteResults),
};
})
.filter((suite): suite is NonNullable<typeof suite> => Boolean(suite));
const passed = results.filter(
(result) => result.status === "passed" && result.cleanup === "passed",
).length;
const rankingSnapshots = [
...new Map(
results.flatMap((result) =>
result.rankingSnapshot
? [
[
result.rankingSnapshot.snapshotId,
{
snapshotId: result.rankingSnapshot.snapshotId,
capturedAt: result.rankingSnapshot.capturedAt,
sourceUrl: result.rankingSnapshot.sourceUrl,
},
] as const,
]
: [],
),
).values(),
];
return {
schema: "paperclip.runner-e2e.campaign/v2",
campaignId: input.campaignId,
generatedAt: input.generatedAt,
source,
expected,
complete:
suites.length === runnerSuites.length &&
suites.every((suite) => suite.complete),
selected: expected.length,
executed: results.filter((result) => result.attempt > 0).length,
passed,
failed: expected.length - passed - results.filter(r => isIncompleteFirstTaskResult(r)).length,
incomplete: results.filter(r => isIncompleteFirstTaskResult(r)).length,
retries: results.reduce(
(total, result) => total + Math.max(0, result.attempt - 1),
0,
),
cleanupPassed: results.every((result) => result.cleanup === "passed"),
rankingSnapshots,
billing: aggregateCampaignBilling(results),
suites,
results,
};
}
export function campaignHistoryRecord(
campaign: RunnerE2ECampaign,
publicBaseUrl: string,
): RunnerE2EHistoryCampaign {
const publicUrl = `${publicBaseUrl.replace(/\/$/, "")}/campaigns/${encodeURIComponent(campaign.campaignId)}/`;
return {
campaignId: campaign.campaignId,
generatedAt: campaign.generatedAt,
source: campaign.source,
complete: campaign.complete,
selected: campaign.selected,
executed: campaign.executed,
passed: campaign.passed,
failed: campaign.failed,
incomplete: campaign.incomplete ?? 0,
retries: campaign.retries,
cleanupPassed: campaign.cleanupPassed,
publicUrl,
billing: campaign.billing,
suites: campaign.suites,
executions: campaign.results.map((result) => ({
executionId: result.executionId,
suiteId: result.suiteId ?? "core-compatibility",
profileId: result.profileId,
environmentId: result.environmentId,
caseId: result.caseId,
provider: result.provider,
model: result.model,
status: isIncompleteFirstTaskResult(result) ? "incomplete" : result.status,
durationMs: result.durationMs,
attempt: result.attempt,
cleanup: result.cleanup,
billing: result.billing ?? summarizeExecutionBilling(result),
})),
};
}
export function emptyRunnerHistory(): RunnerE2EHistoryIndex {
return {
schema: "paperclip.runner-e2e.history/v1",
updatedAt: new Date(0).toISOString(),
latestCampaignId: null,
latestGreenCampaignId: null,
latestBySuite: {},
latestGreenBySuite: {},
campaigns: [],
};
}
export function mergeRunnerHistory(
current: RunnerE2EHistoryIndex | null | undefined,
campaign: RunnerE2EHistoryCampaign,
): RunnerE2EHistoryIndex {
const base =
current?.schema === "paperclip.runner-e2e.history/v1"
? current
: emptyRunnerHistory();
const campaigns = [
campaign,
...base.campaigns.filter(
(candidate) => candidate.campaignId !== campaign.campaignId,
),
].sort(
(left, right) =>
Date.parse(right.generatedAt) - Date.parse(left.generatedAt),
);
const latestBySuite: Record<string, string> = {};
const latestGreenBySuite: Record<string, string> = {};
for (const candidate of campaigns) {
for (const suite of candidate.suites) {
latestBySuite[suite.suiteId] ??= candidate.campaignId;
if (suite.complete && suite.failed === 0 && (suite.incomplete ?? 0) === 0) {
latestGreenBySuite[suite.suiteId] ??= candidate.campaignId;
}
}
}
return {
schema: "paperclip.runner-e2e.history/v1",
updatedAt: new Date().toISOString(),
latestCampaignId: campaigns[0]?.campaignId ?? null,
latestGreenCampaignId:
campaigns.find(
(candidate) => candidate.complete && candidate.failed === 0 && (candidate.incomplete ?? 0) === 0,
)?.campaignId ?? null,
latestBySuite,
latestGreenBySuite,
campaigns,
};
}