Files
paperclip/server/src/services/issue-continuation-summary.ts
T
Dotta dbebf30c89 Add low-trust review containment (#7530)
## Thinking Path

> - Paperclip is a control plane for AI-agent companies, so execution
policy and trust boundaries are part of the product's safety contract.
> - Low-trust review work needs narrower authority than normal
same-company agents because hostile PRs, comments, attachments, and
generated output can carry prompt-injection payloads.
> - The current V1 shape gives trusted workers broad company context,
which is useful for normal execution but too permissive for a reviewer
assigned to hostile content.
> - This branch adds a `low_trust_review` preset, source-trust tagging,
route-level containment, and quarantine handling so low-trust output
does not automatically flow into higher-trust wake context.
> - The branch has been rebased onto current `origin/master`, and the
low-trust migration was renumbered to `0097_low_trust_source_trust.sql`
to avoid collisions with existing `0091` through `0096` migrations.
> - Greptile feedback was addressed by tightening low-trust detection,
preserving project-level trust policy checks, fixing issue-kind
promotion lookup, removing duplicate post-lease isolation assertion,
documenting fail-closed source-trust behavior, bounding ancestry checks,
enforcing runtime issue context for CEOs, awaiting accepted-plan monitor
authorization, and making low-trust issue source-trust tagging atomic.
> - The benefit is a first production slice of deny-by-default review
containment with regression coverage for the main control-plane pivot
surfaces.

Fixes #7531.

## What Changed

- Added shared trust-policy types and validators, plus
database/source-trust fields for issues, comments, documents, and work
products.
- Implemented server enforcement for low-trust issue scope, agent
self-view redaction, secret/plugin/runtime denial paths, promotion
checks, and quarantined continuation/wake context.
- Added focused low-trust regression tests for resolver behavior, source
trust, route authorization, heartbeat preflight ordering, runtime
containment, and quarantine redaction.
- Added board UI affordances for selecting/reviewing the low-trust
preset and surfacing source-trust badges in relevant issue views.
- Added `doc/LOW-TRUST-PRESETS.md`, updated
`doc/SPEC-implementation.md`, and committed the low-trust review
contract plan under `doc/plans/`.
- Rebasing note: the original `0097_low_trust_source_trust.sql`
migration was renamed to `0097_low_trust_source_trust.sql`; the SQL uses
`ADD COLUMN IF NOT EXISTS` so users who already applied the old-numbered
migration are not broken by the renumbered migration.

## Verification

- Rebased branch onto current `origin/master` and force-pushed with
lease to `origin/PAP-10211-low-trust-agent` at head `2719f31e3`.
- Confirmed the PR diff does not include `pnpm-lock.yaml` or
`.github/workflows` changes.
- Resolved upstream UI/comment conflicts by preserving deleted-comment
tombstone behavior and low-trust source-trust badges/metadata.
- Renumbered the low-trust source-trust migration to
`0097_low_trust_source_trust.sql`; the SQL uses `ADD COLUMN IF NOT
EXISTS` so users who already applied an old-numbered copy are not
broken.
- `pnpm exec vitest run ui/src/lib/issue-chat-messages.test.ts
server/src/__tests__/heartbeat-workspace-session.test.ts`
- `pnpm exec vitest run server/src/__tests__/source-trust.test.ts
server/src/__tests__/workspace-runtime-service-authz.test.ts
ui/src/lib/trust-policy-ui.test.ts
ui/src/components/TrustPresetSection.test.tsx`
- `pnpm run typecheck:build-gaps`
- `git diff --check`
- GitHub checks pass on head `2719f31e3`: build, typecheck/release
registry, general tests, serialized server suites, e2e, canary, verify,
policy/review, Socket, and Snyk.
- Greptile Review passes with Confidence Score 5/5 and zero unresolved
Greptile review threads.
- No design screenshots/images were added because the task explicitly
says not to add them unless they are specifically part of the work.

## Risks

- Medium risk: this touches shared trust-policy contracts, server
authorization paths, heartbeat context generation, migration metadata,
and UI preset controls.
- Low-trust containment is intentionally deny-by-default; legitimate
future review workflows may need explicit allowlisted exceptions.
- Plugin/runtime/security surfaces are broad, so regression tests cover
the current known routes but future integrations must route through the
same containment layer.
- The PR is ready for review; GitHub checks are green and Greptile is
5/5.

> 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 coding agent, tool-enabled shell and GitHub CLI
workflow.

## 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] UI changes are covered by focused tests; no screenshots were added
per task instruction not to add design images unless specifically
required
- [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>
2026-06-05 16:48:02 -05:00

285 lines
9.9 KiB
TypeScript

import { and, eq } from "drizzle-orm";
import type { Db } from "@paperclipai/db";
import { documents, issueDocuments, issues } from "@paperclipai/db";
import { ISSUE_CONTINUATION_SUMMARY_DOCUMENT_KEY, type SourceTrustMetadata } from "@paperclipai/shared";
import { documentService } from "./documents.js";
export { ISSUE_CONTINUATION_SUMMARY_DOCUMENT_KEY };
export const ISSUE_CONTINUATION_SUMMARY_TITLE = "Continuation Summary";
export const ISSUE_CONTINUATION_SUMMARY_MAX_BODY_CHARS = 8_000;
const SUMMARY_SECTION_MAX_CHARS = 1_200;
const PATH_CANDIDATE_RE = /(?:^|[\s`"'(])((?:server|ui|packages|doc|scripts|\.github)\/[A-Za-z0-9._/-]+)/g;
const WAITING_FOR_REVIEW_OR_APPROVAL_RE =
/\bwait(?:ing)? for\b.{0,160}\b(?:review(?:er)?(?: feedback)?|approval|board|human|user|operator)\b/i;
type IssueSummaryInput = {
id: string;
identifier: string | null;
title: string;
description: string | null;
status: string;
priority: string;
};
type RunSummaryInput = {
id: string;
status: string;
error: string | null;
errorCode?: string | null;
resultJson?: Record<string, unknown> | null;
stdoutExcerpt?: string | null;
stderrExcerpt?: string | null;
finishedAt?: Date | null;
};
type AgentSummaryInput = {
id: string;
name: string;
adapterType: string | null;
};
export type IssueContinuationSummaryDocument = {
key: typeof ISSUE_CONTINUATION_SUMMARY_DOCUMENT_KEY;
title: string | null;
body: string;
latestRevisionId: string | null;
latestRevisionNumber: number;
sourceTrust: SourceTrustMetadata | null;
updatedAt: Date;
};
function truncateText(value: string, maxChars: number) {
const trimmed = value.trim();
if (trimmed.length <= maxChars) return trimmed;
return `${trimmed.slice(0, Math.max(0, maxChars - 20)).trimEnd()}\n[truncated]`;
}
function asNonEmptyString(value: unknown) {
return typeof value === "string" && value.trim().length > 0 ? value.trim() : null;
}
function readResultSummary(resultJson: Record<string, unknown> | null | undefined) {
if (!resultJson || typeof resultJson !== "object" || Array.isArray(resultJson)) return null;
return (
asNonEmptyString(resultJson.summary) ??
asNonEmptyString(resultJson.result) ??
asNonEmptyString(resultJson.message) ??
asNonEmptyString(resultJson.error) ??
null
);
}
function extractMarkdownSection(markdown: string | null | undefined, heading: string) {
if (!markdown) return null;
const escaped = heading.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
const re = new RegExp(`^##\\s+${escaped}\\s*$([\\s\\S]*?)(?=^##\\s+|(?![\\s\\S]))`, "im");
const match = re.exec(markdown);
const section = match?.[1]?.trim();
return section ? truncateText(section, SUMMARY_SECTION_MAX_CHARS) : null;
}
function extractPathCandidates(...texts: Array<string | null | undefined>) {
const seen = new Set<string>();
for (const text of texts) {
if (!text) continue;
for (const match of text.matchAll(PATH_CANDIDATE_RE)) {
const path = match[1]?.replace(/[),.;:]+$/, "");
if (path) seen.add(path);
if (seen.size >= 12) break;
}
if (seen.size >= 12) break;
}
return [...seen];
}
function inferMode(issue: IssueSummaryInput, run: RunSummaryInput) {
if (issue.status === "done" || issue.status === "in_review") return "review";
if (run.status === "failed" || run.status === "timed_out" || run.status === "cancelled") return "implementation";
if (issue.status === "backlog" || issue.status === "todo") return "plan";
return "implementation";
}
function inferNextAction(issue: IssueSummaryInput, run: RunSummaryInput, previousNextAction: string | null) {
if (issue.status === "done") return "Review the completed issue output and close any remaining follow-up comments.";
if (issue.status === "in_review") return "Wait for reviewer feedback or approval before continuing executor work.";
if (run.status === "failed" || run.status === "timed_out") {
return "Inspect the failed run, fix the cause, and resume from the most recent concrete action above.";
}
if (run.status === "cancelled") return "Confirm the cancellation reason before starting another run.";
return previousNextAction ?? "Resume implementation from the acceptance criteria, latest comments, and this summary.";
}
function bulletList(items: string[], empty: string) {
if (items.length === 0) return `- ${empty}`;
return items.map((item) => `- ${item}`).join("\n");
}
function extractPreviousNextAction(previousBody: string | null | undefined) {
const section = extractMarkdownSection(previousBody, "Next Action");
if (!section) return null;
return section
.split(/\r?\n/)
.map((line) => line.replace(/^[-*]\s+/, "").trim())
.find(Boolean) ?? null;
}
export function extractContinuationSummaryNextAction(body: string | null | undefined) {
return extractPreviousNextAction(body);
}
export function continuationSummaryParksExecutor(body: string | null | undefined) {
const nextAction = extractContinuationSummaryNextAction(body);
if (!nextAction) return false;
return WAITING_FOR_REVIEW_OR_APPROVAL_RE.test(nextAction);
}
export function buildContinuationSummaryMarkdown(input: {
issue: IssueSummaryInput;
run: RunSummaryInput;
agent: AgentSummaryInput;
previousSummaryBody?: string | null;
}) {
const { issue, run, agent } = input;
const resultSummary = readResultSummary(run.resultJson);
const recentActions = [
`Run \`${run.id}\` finished with status \`${run.status}\`${run.finishedAt ? ` at ${run.finishedAt.toISOString()}` : ""}.`,
resultSummary ? truncateText(resultSummary, SUMMARY_SECTION_MAX_CHARS) : "No adapter-provided result summary was captured for this run.",
];
if (run.error) {
recentActions.push(`Latest run error${run.errorCode ? ` (${run.errorCode})` : ""}: ${truncateText(run.error, 500)}`);
}
const paths = extractPathCandidates(resultSummary, run.stdoutExcerpt, run.stderrExcerpt, input.previousSummaryBody);
const objective = extractMarkdownSection(issue.description, "Objective") ?? issue.description?.trim() ?? "No objective captured.";
const acceptanceCriteria = extractMarkdownSection(issue.description, "Acceptance Criteria") ?? "No explicit acceptance criteria captured.";
const mode = inferMode(issue, run);
const nextAction = inferNextAction(issue, run, extractPreviousNextAction(input.previousSummaryBody));
const body = [
"# Continuation Summary",
"",
`- Issue: ${issue.identifier ?? issue.id}${issue.title}`,
`- Status: ${issue.status}`,
`- Priority: ${issue.priority}`,
`- Current mode: ${mode}`,
`- Last updated by run: ${run.id}`,
`- Agent: ${agent.name} (${agent.adapterType ?? "unknown"})`,
"",
"## Objective",
"",
truncateText(objective, SUMMARY_SECTION_MAX_CHARS),
"",
"## Acceptance Criteria",
"",
acceptanceCriteria,
"",
"## Recent Concrete Actions",
"",
bulletList(recentActions, "No recent actions captured."),
"",
"## Files / Routes Touched",
"",
bulletList(paths.map((path) => `\`${path}\``), "No file or route paths were detected in the captured run summary."),
"",
"## Commands Run",
"",
bulletList(
[
`Heartbeat run \`${run.id}\` invoked adapter \`${agent.adapterType ?? "unknown"}\`.`,
"Detailed shell/tool commands remain in the run log and transcript.",
],
"No command metadata captured.",
),
"",
"## Blockers / Decisions",
"",
bulletList(
run.error
? [`Latest run ended with \`${run.status}\`; inspect the error before continuing.`]
: ["No new blocker was recorded by the latest run."],
"No blockers or decisions captured.",
),
"",
"## Next Action",
"",
`- ${nextAction}`,
].join("\n");
return truncateText(body, ISSUE_CONTINUATION_SUMMARY_MAX_BODY_CHARS);
}
export async function getIssueContinuationSummaryDocument(
db: Db,
issueId: string,
): Promise<IssueContinuationSummaryDocument | null> {
const row = await db
.select({
key: issueDocuments.key,
title: documents.title,
body: documents.latestBody,
latestRevisionId: documents.latestRevisionId,
latestRevisionNumber: documents.latestRevisionNumber,
sourceTrust: documents.sourceTrust,
updatedAt: documents.updatedAt,
})
.from(issueDocuments)
.innerJoin(documents, eq(issueDocuments.documentId, documents.id))
.where(and(eq(issueDocuments.issueId, issueId), eq(issueDocuments.key, ISSUE_CONTINUATION_SUMMARY_DOCUMENT_KEY)))
.then((rows) => rows[0] ?? null);
if (!row) return null;
return {
key: ISSUE_CONTINUATION_SUMMARY_DOCUMENT_KEY,
title: row.title,
body: row.body,
latestRevisionId: row.latestRevisionId,
latestRevisionNumber: row.latestRevisionNumber,
sourceTrust: row.sourceTrust ?? null,
updatedAt: row.updatedAt,
};
}
export async function refreshIssueContinuationSummary(input: {
db: Db;
issueId: string;
run: RunSummaryInput;
agent: AgentSummaryInput;
}) {
const { db, issueId, run, agent } = input;
const [issue, existing] = await Promise.all([
db
.select({
id: issues.id,
identifier: issues.identifier,
title: issues.title,
description: issues.description,
status: issues.status,
priority: issues.priority,
})
.from(issues)
.where(eq(issues.id, issueId))
.then((rows) => rows[0] ?? null),
getIssueContinuationSummaryDocument(db, issueId),
]);
if (!issue) return null;
const body = buildContinuationSummaryMarkdown({
issue,
run,
agent,
previousSummaryBody: existing?.body ?? null,
});
const result = await documentService(db).upsertIssueDocument({
issueId,
key: ISSUE_CONTINUATION_SUMMARY_DOCUMENT_KEY,
title: ISSUE_CONTINUATION_SUMMARY_TITLE,
format: "markdown",
body,
baseRevisionId: existing?.latestRevisionId ?? null,
changeSummary: `Refresh continuation summary after run ${run.id}`,
createdByAgentId: agent.id,
createdByRunId: run.id,
});
return result.document;
}