Files
PaperClipAI/server/src/services/native-runtime/evidence-classifier.test.ts
T
DottaandDev Agent 25cf079ec5 feat(runner): add Codex-native application integration (#12591)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - The runner package is useful only when the application can start,
observe, and recover a native Codex run safely.
> - Existing direct adapters must keep their current execution and
finalization paths.
> - The application boundary therefore needs additive persistence,
authorization, coordination, and recovery behind an explicit
experimental adapter.
> - This pull request adds that Codex-only boundary without activating
generalized providers, remote environments, or the later task/SDK
surfaces.

## Linked Issues or Issue Description

**Subsystem affected**

Shared contracts, database persistence, adapter utilities, server
native-runtime services, and the experimental Paperclip Runner adapter.

**Problem or motivation**

The already-landed runner package has a qualified Codex path, but the
application needs durable native-run state, guarded runtime selection,
authenticated coordination, tool security, finalization, and recovery
before the experimental adapter can be exercised safely.

**Proposed solution**

Add a Codex-only `paperclip_runner` application path behind the existing
default-off native-runner setting. Bind native state and coordination to
company/run identity, preserve persisted-run recovery, and leave every
direct adapter on its existing legacy execution path.

**Alternatives considered**

The earlier stack boundary introduced a generalized executor and
remote-environment lifecycle here. That made this PR depend on
implementations in higher PRs and changed reusable sandbox behavior
globally. Those pieces are now deferred together to #12592.

**Roadmap alignment**

ROADMAP.md does not list a conflicting native-runner integration
project. This change adds the application boundary for the existing
Runner architecture.

## What Changed

- Added native run/result/finalization/provider-trace persistence,
shared validators, and idempotent migration/replay coverage.
- Added guarded Codex-only runtime selection, authenticated PRP
coordination, recovery, finalization, and interaction services.
- Added run/company-bound tool-gateway authorization, credential
redaction, SSRF protections, and replay-safe behavior.
- Added the explicit `paperclip_runner` adapter behind the default-off
rollout setting.
- Preserved legacy answered-question wake projection and direct-adapter
execution/finalization paths.
- Hardened cancellation so only owned in-memory child processes are
signaled; persisted recycled PIDs/process groups are never trusted.
- Retained the narrow Claude ACPX isolated-context security follow-up
discovered after #12590.
- Deferred the generalized executor, provider ingress, remote lifecycle,
SDK/lab/eval work, release-process changes, and lockfile.

## Verification

- Changed-file delta against `master`: 133 files.
- GitHub Actions is the authoritative verification environment for this
PR.
- Full CI, security, and Greptile review will run on this lowest
unmerged stack PR.
- Local tests/build/typecheck were not run because this checkout is
resource constrained.
- Static diff/reference checks pass, and `pnpm-lock.yaml` is unchanged.

## Risks

- This touches central heartbeat and agent-route code, so legacy
compatibility is the primary risk.
- Runtime selection remains Codex-only and explicit; direct Codex,
Claude, OpenCode, process, HTTP, and plugin adapters remain on their
existing paths.
- Fresh native starts fail closed while the rollout flag is off;
persisted native records remain readable and recoverable.
- Cancellation, company/run binding, tool calls, status decisions, and
completion writes are guarded or replay-safe.

> 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.

## Model Used

OpenAI Codex, GPT-5.6, with repository tools, code execution, and
parallel agent review.

## 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 linked existing issues or described the issue in-PR
following the relevant issue template
- [x] I have not referenced internal or instance-local Paperclip issues
or links
- [x] My branch name describes the change and contains no internal
Paperclip ticket id
- [ ] I have run tests locally and they pass — GitHub Actions is
authoritative for this resource-constrained checkout
- [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 risks above
- [ ] All Paperclip CI and security gates are green
- [ ] Greptile is 5/5 with no open actionable findings
- [x] I will address all Greptile and reviewer comments before merge

## Stack

- Position: 3 of 5 overall; lowest of 3 currently unmerged
- Base: `master`
- Previous:
[#12590](https://github.com/paperclipai/paperclip/pull/12590), qualified
Claude ACPX runtime — merged
- Next: [#12592](https://github.com/paperclipai/paperclip/pull/12592),
generalized Codex executor, task experience, and developer SDKs

---------

Co-authored-by: Dev Agent <dev@paperclip.ing>
2026-08-31 14:38:38 -05:00

135 lines
4.4 KiB
TypeScript

import { describe, expect, it } from "vitest";
import type { Db } from "@paperclipai/db";
import { classifyNativeEvidence } from "./evidence-classifier.js";
const workProductId = "00000000-0000-4000-8000-000000000001";
const evidenceRef = `work_product:${workProductId}`;
function evidenceDb(row: Record<string, unknown> = {
id: workProductId,
status: "approved",
reviewState: "approved",
}): Db {
return {
select: () => ({
from: () => ({
where: () => ({
limit: () => Promise.resolve([row]),
}),
}),
}),
} as unknown as Db;
}
function result(status: "satisfied" | "not_satisfied", objectiveSatisfied: boolean) {
return {
reportedWorkDisposition: "done",
summary: "Classified",
completionClaim: {
contractRevision: "1",
objectiveSatisfied,
criteria: [{ criterionId: "objective", status, evidenceRefs: [evidenceRef] }],
remainingWork: [],
},
verification: [{ commandOrCheck: "test", status: "passed", artifactRef: evidenceRef }],
};
}
const input = {
db: evidenceDb(),
companyId: "company",
issueId: "issue",
runId: "run",
contract: {
revision: "1",
objective: "Classify evidence",
criteria: [{ id: "objective", requirement: "Use accepted durable evidence" }],
},
};
describe("classifyNativeEvidence", () => {
it("accepts a satisfied claim backed by an approved durable work product", async () => {
await expect(classifyNativeEvidence({
...input,
result: result("satisfied", true),
})).resolves.toEqual(expect.objectContaining({
objectiveSatisfied: true,
allCriteriaSatisfied: true,
verificationPassed: true,
acceptedEvidenceRefs: [evidenceRef],
}));
});
it("does not turn durable evidence into completion when the claim says the criterion is unsatisfied", async () => {
const assessment = await classifyNativeEvidence({
...input,
result: result("not_satisfied", false),
});
expect(assessment).toEqual(expect.objectContaining({
objectiveSatisfied: false,
allCriteriaSatisfied: false,
verificationPassed: true,
}));
expect(assessment.criterionAssessments).toEqual([
expect.objectContaining({ outcome: "rejected", reasonCode: "criterion_reported_not_satisfied" }),
]);
});
it("normalizes DOT-29-style environment attention into a non-blocking verification caveat", async () => {
const assessment = await classifyNativeEvidence({
...input,
result: {
...result("satisfied", true),
verification: [{ commandOrCheck: "Run npm test", status: "not_run" }],
attentionRequests: [{
kind: "environment_constraint",
summary: "Node and npm are unavailable in this sandbox.",
}],
},
});
expect(assessment.objectiveClaimSatisfied).toBe(true);
expect(assessment.hasFailedVerification).toBe(false);
expect(assessment.attentionRequests).toEqual([]);
expect(assessment.verificationCaveats).toEqual([{
commandOrCheck: "Run npm test",
reasonCode: "tool_unavailable",
detail: "Node and npm are unavailable in this sandbox.",
}]);
expect(assessment.ignoredAttentionRequests).toEqual([
expect.objectContaining({
sourceKind: "environment_constraint",
disposition: "verification_caveat",
}),
]);
});
it("accepts an annotated interaction UUID without sending the annotation to Postgres", async () => {
const interactionId = "00000000-0000-4000-8000-000000000029";
const annotatedRef = `interaction:${interactionId} (request_confirmation, status accepted)`;
const assessment = await classifyNativeEvidence({
...input,
db: evidenceDb({ id: interactionId, status: "accepted", result: { outcome: "accepted" } }),
result: {
reportedWorkDisposition: "done",
summary: "Plan accepted",
completionClaim: {
contractRevision: "1",
objectiveSatisfied: true,
criteria: [{ criterionId: "objective", status: "satisfied", evidenceRefs: [annotatedRef] }],
remainingWork: [],
},
verification: [],
},
});
expect(assessment.objectiveSatisfied).toBe(true);
expect(assessment.acceptedEvidenceRefs).toEqual([annotatedRef]);
expect(assessment.criterionAssessments[0]?.evidenceRefs[0]).toMatchObject({
durableRecordId: interactionId,
outcome: "accepted",
reasonCode: "interaction_resolved",
});
});
});