Files
PaperClipAI/tests/runner-e2e/chat-catalog-preservation.json
T
f4337bb5fb test(evals): land the chat catalog eval harness on master (#19614)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work
> - The chat-feature evals measure whether agents complete real chat
requests through the product
> - The chat catalog eval harness and its repairs live on the
`chat-eval/master-candidate` branch, not on master
> - Today's work made 139 of 242 chat evals pass in verified single-case
live runs. Each product fix landed on master as its own pull request
> - The eval-side changes (setups, graders, fault seams, evidence
capture) still exist only on the candidate
> - This pull request lands the harness on master. Master stays the
source of truth for product behavior
> - The benefit is one tree: evals run against master commits, and
product fixes reach the evals as soon as they merge

## Linked Issues or Issue Description

Refs #19441, Refs #19599, Refs #20270, Refs #20334, Refs #20342, Refs
#20344, Refs #20354, Refs #20360, Refs #20373, Refs #20382, Refs #20409

**What existing behavior does this improve?**
The chat catalog eval harness and the product it evaluates live on a
long-running branch outside master. Eval fixes do not reach master, so
master-based eval runs use old setups and graders.

**Subsystem affected**
`tests/runner-e2e` chat catalog harness, plus a small set of product
changes that exist only on the candidate.

**Proposed change**
Land the harness on master. Every product fix from this eval work
already merged to master as its own pull request. Conflicts keep
master's product behavior.

## What Changed

- Most of the diff (808 of 851 files) is under `tests/runner-e2e/`:
chat-catalog domains, scenarios, descriptors, the TestOps manifest,
private evidence tooling, and their tests.
- Graders now check saved state, setup literals and rendered or clicked
links. Many keyword and regex checks on free-form replies are removed.
Each changed grader has a bumped `oracleVersion` and calibration tests
(a valid reply, a reworded valid reply, and broken variants that must
fail).
- The shared link helper `hasLink` no longer treats a list link (for
example `/COM/issues?view=mine`) as a link to every task without a URL
key.
- Setup fixes build real state through supported product routes: routine
history, agent grants through the board grant route, budget holds with a
real cap, and a storage-layer archive fault for
`inbox-search.archive-partial-failure`.
- Browser boundary journeys (sign-in, chat-disabled, onboarding) now
write the standard pass evidence files.
- Retargeted cases, approved by the maintainer:
`agent-chat.chat-disabled` (Conference Room gate),
`agents.restore-instructions` (no saved instruction history),
`access.manage-membership` (member permission edits stay board-only).
- The private evidence trusted files (`manual-private-handoff.ts`,
`manual-private-retention.ts`, `manual-private-report-assets.ts`) are
byte-identical to master.
- Product files outside `tests/` (43 files, +1,328 −49) carry
candidate-only changes that master does not yet have. Most are tests.
The main code changes are in `request-human-input.ts`,
`heartbeat-run-summary.ts`, `native-completion-feedback.ts`,
`native-run-finalizer.ts`, `openapi.ts`, `secrets.ts` and
`IssueChatLongThreadPerf.tsx`.

## Verification

- `pnpm vitest run chat-catalog-domains chat-catalog-contract.test.ts
chat-catalog-consistency.test.ts unit-launcher.test.mjs
--testTimeout=180000` in `tests/runner-e2e`: 269 files pass, 3,550 tests
pass.
- `node --test chat-full-catalog-testops-manifest.test.mjs`: 10 pass.
- `node tests/runner-e2e/source-sdk-public-inputs.mjs <HEAD> --check`:
no change.
- `tsc` for `server` and `tests/runner-e2e`: clean.
- Live single-case verification: 139 of 242 cases passed on paid runs,
and a person read the saved evidence for each. These are single-case
runs, not one full-cohort run.

## Risks

- Large diff. Most of it is test-only, but the 43 non-test files change
product code paths. Review those files first.
- Some graders are now less strict on reply wording. A person must read
replies for meaning on those cases.
- 42 cases need disposable outside accounts (Notion, Slack, GitHub,
Daytona and others) and stay blocked. `access.invite-teammate` stays
failing until local agent isolation lands, because the runner's durable
state keeps a live invite token.
- The paid workflow compares the trusted private-evidence files with
master. They are unchanged, so this risk is low.

## Model Used

Anthropic Claude Opus 5.5 (`claude-opus-5-5`), with tool use and code
execution, in Claude Code. Subagents used the same model.

## 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
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-11-10 08:02:11 -06:00

174 lines
7.3 KiB
JSON

{
"schema": "paperclip.chat-catalog-preservation/v1",
"productionBaseline": "39e811c9c5226979fce42e052a27cfb28301018a",
"canonicalEvalBase": "0098da56f4c10f3154ed4ed96b1404fdf7a021ca",
"scenarioCount": 244,
"lazyCatalogEntries": 242,
"standaloneFlows": [
"tasks.create-backlog",
"tasks.delegate-announcement"
],
"purpose": "Eval source preservation only; no qualification, new attempt, budget reset or live admission.",
"components": [
{
"name": "SDK",
"sourceRevision": "9754e46d89bfa99e913efaf1769fe2d8b403fc4d"
},
{
"name": "overview-related",
"sourceRevision": "a62a023a5544ffcab98ee6624b0a583a6e8e6775"
},
{
"name": "status-card",
"sourceRevision": "97bcf2476d9f03bec70bec4ebd788e113fcc4425"
},
{
"name": "skills",
"sourceRevision": "bdca7305bf4c64fea033ae6ceec07927d2a754e2"
},
{
"name": "Ready2",
"sourceRevision": "819b7cf649c5551c32ba913509790ad16c1d5008"
},
{
"name": "repo",
"sourceRevision": "2a630b6b09efe4711dbbc42d0e0fc070067bbb17"
},
{
"name": "formal-model",
"sourceRevision": "687efafc61f841342c52b7d2a8c920b75c218d16"
},
{
"name": "formal-clock",
"sourceRevision": "f09af3cdebd58376d095d6f49d53aae80b635b6e"
},
{
"name": "new-company",
"sourceRevision": "6726c40f01342081557c265944ab8783f9ee82b4"
},
{
"name": "history-eval-only",
"sourceRevision": "2b84e38c15b10e10ef6c063984d375a14b307c4a"
},
{
"name": "ordinary-original-clock-multipart",
"sourceRevision": "73856cebe07cab32df42fdec7ff6ea7192cdd474"
},
{
"name": "new-company-original-clock",
"sourceRevision": "7c846a27a0b1ac1908d929209b60d7942f4246fb"
},
{
"name": "sdk-two-public-setup",
"sourceRevision": "8cb209e726237644f1312d2385da460083d0a035"
},
{
"name": "task-two-public-prerequisites",
"sourceRevision": "ef45d57ab8919854e7203ee789f6441db1470b87"
},
{
"name": "document-restore-decision-audience",
"sourceRevision": "8bf05430d65f1bd354b3eceea4e6a7963aca6a6c"
},
{
"name": "outbound-standing-native-provenance",
"sourceRevision": "7db3308ea4e48f4d87130e384a672b1ebd5f5394"
}
],
"productionPrerequisites": [
{
"scenarioId": "onboarding.new-company",
"corePullRequest": 18103,
"reason": "Actual local OpenCode native authentication/hello probe, absent from frozen production baseline."
},
{
"scenarioId": "questions-and-approvals.formal-hire-revision",
"corePullRequest": 18105,
"reason": "Permission-qualified, truthful responseText pre-dispatch recovery guidance, absent from frozen production baseline."
},
{
"scenarioId": "routines.read-history",
"corePullRequest": 18033,
"reason": "Actual local-native task status must finalize public routine history; merged after the frozen production baseline."
}
],
"coreChangesIncluded": false,
"candidateOutcomesQualifyFrozenBaseline": false,
"historicalResultsCarriedToThisHead": 0,
"knownUnqualifiedFixtureFindings": [
{
"scenarioIds": [
"plugins.disable-plugin"
],
"finding": "The preserved fixture sends a secret_ref object to an apiKey schema declared string with secret-ref format. The returned final reached this setup request and received HTTP400; the public validator requires the secure secret UUID string. This spent failure is retained without repair or rerun."
},
{
"scenarioIds": [
"plugins.configure-plugin"
],
"finding": "The returned final stopped earlier at the initial-identity wait. Its later UI/configuration leg was not exercised. The preserved object-vs-string secret-ref expectation is therefore a source-only finding for that later leg, not attribution of the observed failure. The spent raw failure remains unchanged without rerun."
}
],
"readinessLimits": {
"declaredUnsupportedFreshContext": [
"access.invite-teammate",
"access.manage-membership",
"activity.routine-audit",
"agents.restore-instructions",
"budgets-costs.subscription-fees",
"navigation-preferences.sidebar-order"
],
"currentProfileOrPublicCapabilityGaps": [
"assistant-connections.use-scoped-client",
"companies.configure-decision-model",
"steering.steer-active"
],
"otherRequirements": "Official provider resources, selected credentials, authorized operators and actual remote targets still require their declared public prerequisites. Importability is not runtime readiness.",
"attempts": "All original raw grades, source fingerprints, ordinals, usage, billing, privacy and cleanup remain bound to their original measurements. Exhausted cases remain exhausted.",
"sidebarOrdering": "The frozen legacy Projects manual-order surface is absent from both current39e layouts. No injected classic UI, fabricated ordering or feature revival is included."
},
"preservationParentRevision": "372b192327e6a02c6ab3da4961521b8632a60fb6",
"latestAcceptedEvalOnlyOverlays": {
"sdk-two-public-setup": {
"sourceRevision": "8cb209e726237644f1312d2385da460083d0a035",
"scenarioIds": [
"secrets.least-scope-delivery",
"routines.plugin-managed-routine"
],
"contracts": "Actual public resume Agent/state/version plus new unique public plugin operation receipt inside unchanged90s; managed selected saved resource facts in ordinary source description/CEO readback and structural JSON equality only."
},
"task-two-public-prerequisites": {
"sourceRevision": "ef45d57ab8919854e7203ee789f6441db1470b87",
"scenarioIds": [
"tasks.organize-open-work",
"task-coordination.delegate-with-context"
],
"contracts": "Actual ready-to-paused owners/version/manual holds with original deadline/no work; owned human browser Origin on original exact attachment upload with unchanged production guard."
},
"document-restore-decision-audience": {
"sourceRevision": "8bf05430d65f1bd354b3eceea4e6a7963aca6a6c",
"scenarioIds": [
"documents-artifacts.restore-document",
"inbox-search.show-decisions"
],
"contracts": "Exact public document id/task/key/revision/bytes plus actual Plans UI identity; independently authenticated addressed Riley pending-decision feed with explicit owner/Riley principal guards. Actual returned final failures stay exhausted and source preservation does not change outcomes."
},
"outbound-standing-native-provenance": {
"sourceRevision": "7db3308ea4e48f4d87130e384a672b1ebd5f5394",
"scenarioIds": [
"chat-channels.outbound-email"
],
"contracts": "Canonical source-human/native run, actual ordinary task creating actor/originRunId, public creation audit and unique native assignment admission. Standing-chat parentNULL and actual public issue.create omitted parent projection supported; explicit email-child/thread/endpoint and all original provider-receipt/duplicate/draft controls preserved. Authorized AgentMail input remains an external gate."
}
},
"ordinaryComposedHeadRuntimeQualification": 0,
"excludedCandidatePrerequisitesUnchanged": [
18103,
18105,
18033,
17917,
17848
],
"acceptedSourceDoesNotCureSpentRawFailures": true
}