mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-13 15:55:46 +01:00
## 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>
150 lines
6.2 KiB
TypeScript
150 lines
6.2 KiB
TypeScript
import { validateRetainedRunnerResult } from "./result-validation.js";
|
|
import { createHash } from "node:crypto";
|
|
import type { MatrixExecution, RunnerE2EResult } from "./types.js";
|
|
|
|
/** Presentation aliases only; retained execution identities never change. */
|
|
export const retainedSuiteLabels: Readonly<Record<string, string>> = { "qa-basics": "Basic app journeys" };
|
|
|
|
/** Display-only metadata: never load or reconstruct executable branch fixtures. */
|
|
export interface ReportExecution {
|
|
id: string;
|
|
suiteDefinitionHash: string;
|
|
suite: Pick<
|
|
MatrixExecution["suite"],
|
|
"id" | "label" | "description" | "expectedMatrixSize"
|
|
>;
|
|
profile: { id: string; label: string; generation: "legacy" | "native" | "none"; provider: string | null; model: string | null; expectedRuntimeMode: "legacy" | "native" | "none" };
|
|
environment: Pick<
|
|
MatrixExecution["environment"],
|
|
"id" | "label" | "provider" | "expectedExecutionTarget"
|
|
>;
|
|
task: Pick<MatrixExecution["task"], "id" | "label">;
|
|
}
|
|
|
|
export function parseReportExecutionId(id: string) {
|
|
// These identities also become evidence paths. Reject path traversal and any
|
|
// syntax other than catalog identities, even in imported JSON. Deployment
|
|
// journeys add one explicit target segment; all historical IDs stay intact.
|
|
if (typeof id !== "string")
|
|
throw new Error("Report execution identity must be a string");
|
|
const journey = /^(product-journeys)\.([a-z0-9][a-z0-9_-]*)\.([a-z0-9][a-z0-9_-]*)\.(local|daytona)\.([a-z0-9][a-z0-9_-]*)$/.exec(id);
|
|
if (journey && id.length <= 512) return { suiteId: journey[1]!, targetId: journey[2]!, profileId: journey[3]!, environmentId: journey[4]! as "local" | "daytona", caseId: journey[5]! };
|
|
// Only the chat catalog has a two-part area.case task identity.
|
|
const chat = /^(chat-features)\.([a-z0-9][a-z0-9_-]*)\.(local|daytona)\.([a-z0-9][a-z0-9_-]*\.[a-z0-9][a-z0-9_-]*)$/.exec(id);
|
|
if (chat && id.length <= 512) return { suiteId: chat[1]!, profileId: chat[2]!, environmentId: chat[3]! as "local" | "daytona", caseId: chat[4]!, targetId: undefined };
|
|
const match =
|
|
/^([a-z0-9][a-z0-9_-]*)\.([a-z0-9][a-z0-9_-]*)\.(local|daytona)\.([a-z0-9][a-z0-9_-]*)$/.exec(
|
|
id,
|
|
);
|
|
if (!match || id.length > 512)
|
|
throw new Error(
|
|
`Invalid report execution identity: ${String(id).slice(0, 512)}`,
|
|
);
|
|
return {
|
|
suiteId: match[1]!,
|
|
profileId: match[2]!,
|
|
environmentId: match[3]! as "local" | "daytona",
|
|
caseId: match[4]!,
|
|
targetId: undefined,
|
|
};
|
|
}
|
|
|
|
export function validateReportResultIdentity(result: RunnerE2EResult) {
|
|
validateRetainedRunnerResult(result);
|
|
const identity = parseReportExecutionId(result.executionId);
|
|
if (
|
|
(result.suiteId !== undefined && result.suiteId !== identity.suiteId) ||
|
|
result.profileId !== identity.profileId ||
|
|
result.environmentId !== identity.environmentId ||
|
|
result.caseId !== identity.caseId
|
|
|| identity.targetId !== undefined && result.productJourney?.targetId !== identity.targetId
|
|
) {
|
|
throw new Error(
|
|
`Result identity does not match execution ID: ${result.executionId}`,
|
|
);
|
|
}
|
|
return identity;
|
|
}
|
|
|
|
export function discoverReportCatalog(input: {
|
|
catalog: readonly ReportExecution[];
|
|
expected: readonly string[];
|
|
results: readonly RunnerE2EResult[];
|
|
}): ReportExecution[] {
|
|
const expected = new Set(input.expected);
|
|
if (expected.size !== input.expected.length)
|
|
throw new Error("Report expected identities must be unique");
|
|
const identities = new Map(
|
|
input.expected.map((id) => [id, parseReportExecutionId(id)]),
|
|
);
|
|
const results = new Map<string, RunnerE2EResult>();
|
|
for (const result of input.results) {
|
|
validateReportResultIdentity(result);
|
|
if (expected.has(result.executionId))
|
|
results.set(result.executionId, result);
|
|
}
|
|
const catalog = [...input.catalog];
|
|
const knownIds = new Set(catalog.map((execution) => execution.id));
|
|
const knownSuites = new Map(
|
|
catalog.map((execution) => [execution.suite.id, execution.suite]),
|
|
);
|
|
for (const [id, identity] of identities) {
|
|
if (knownIds.has(id)) continue;
|
|
const result = results.get(id);
|
|
const suiteIds = input.expected
|
|
.filter(
|
|
(candidate) => identities.get(candidate)?.suiteId === identity.suiteId,
|
|
)
|
|
.sort();
|
|
const suite = knownSuites.get(identity.suiteId) ?? {
|
|
id: identity.suiteId,
|
|
label: retainedSuiteLabels[identity.suiteId] ?? identity.suiteId,
|
|
description:
|
|
"Suite discovered from retained campaign identities; full suite size is not known to this publisher.",
|
|
expectedMatrixSize: suiteIds.length,
|
|
};
|
|
const knownProfile = input.catalog.find(
|
|
(execution) => execution.suite.id === identity.suiteId && execution.profile.id === identity.profileId,
|
|
)?.profile ?? input.catalog.find(
|
|
(execution) => execution.profile.id === identity.profileId &&
|
|
(!result || execution.profile.provider === result.provider && execution.profile.model === result.model),
|
|
)?.profile;
|
|
const knownEnvironment = input.catalog.find(
|
|
(execution) => execution.environment.id === identity.environmentId,
|
|
)?.environment;
|
|
const runtimeMode = result?.runtimeMode ?? "native";
|
|
catalog.push({
|
|
id,
|
|
suite,
|
|
suiteDefinitionHash:
|
|
result?.suiteDefinitionHash ??
|
|
`selection-${createHash("sha256").update(JSON.stringify(suiteIds)).digest("hex")}`,
|
|
profile: knownProfile ? result ? {
|
|
...knownProfile,
|
|
generation: runtimeMode,
|
|
expectedRuntimeMode: runtimeMode,
|
|
provider: result.provider,
|
|
model: result.model,
|
|
} : knownProfile : {
|
|
id: identity.profileId,
|
|
label: identity.profileId,
|
|
generation: runtimeMode,
|
|
expectedRuntimeMode: runtimeMode,
|
|
provider:
|
|
result?.runtimeMode === "none" ? null : result?.provider ?? "unknown",
|
|
model: result?.runtimeMode === "none" ? null : result?.model ?? "unknown",
|
|
},
|
|
environment: knownEnvironment ?? {
|
|
id: identity.environmentId,
|
|
label: identity.environmentId,
|
|
provider: identity.environmentId,
|
|
expectedExecutionTarget: {
|
|
kind: identity.environmentId === "local" ? "local" : "remote",
|
|
},
|
|
},
|
|
task: { id: identity.caseId, label: identity.caseId },
|
|
});
|
|
}
|
|
return catalog;
|
|
}
|