mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-03 17:51:58 +01:00
## Thinking Path > - Paperclip must perform work and report its outcome accurately. > - A chat response and its delegated or operator-owned work are separate stages. > - Native chat contracts instead required literal completion of the user's whole request. > - Agents kept searching or waiting even when a truthful handoff should finish the response. > - OpenCode also has separate acknowledgement backlog and empty-response failure paths. > - This PR aligns chat completion with its current stage and makes OpenCode completion truthful. ## Linked Issues or Issue Description Refs #18098 for retained OpenCode evidence and #18377 for separate eval setup, oracle and reporting repairs. **What happened?** Real pinned OpenCode 1.18.34 reproduced an MCP timeout behind 800 text fragments. Pilot [41222196525](https://github.com/paperclipai/paperclip/actions/runs/41222196525) separately exposed a fabricated successful reply after a reasoning-only response. Later restart attempts timed out without an answer. Their native criterion literally required restarting the instance, although the chat instructions and authority required an operator handoff. General authority guidance alone did not resolve it. **Expected behavior:** A standing chat completes its current authorized response. It performs and verifies permitted actions, verifies delegated handoffs, or explains the specific unavailable action and operator path. The worker's task remains separate. Ordinary execution tasks must still complete their requested work. Empty provider responses must not become invented success. **Version and reproduction:** Actual pinned OpenCode and native Rust Runner, with retained full-stack AWS attempts. Product baseline master `51ea624344`. This PR adds no historical catalog to master. ## What Changed - Build standing-chat completion contracts from the server-owned conversation identity. Scope each current request to the response stage; preserve request text, criterion IDs, order, human-response scope and source revisions. Require verified authorized actions and truthful handoffs. Ordinary task contracts stay strict. Existing admitted inputs retain their saved contract during recovery; new contract content uses the existing revision/hash mechanism. - Guide prospective defaults to their owning resource and preserve existing work unless backfill is requested. Guide unavailable board/operator operations to the supported handoff. These are general chat instructions with no eval identities or expected answers. - Batch adjacent assistant text for at most 50 ms and 4,000 UTF-8 bytes. Preserve text, metadata and order; flush before non-text frames and shutdown. - Give an empty OpenCode response one correction within its existing turn, model, reasoning, context and deadline. Accept actual completed answer parts with incomplete headers. Preserve actual active tool work, bound idle evidence grace and fail truthfully if correction stays empty. - Reject empty OpenCode terminals in Rust without actual prose or an accepted semantic result. Never invent successful replies or evidence. Refresh generated project-discovery contracts. - Preserve accurate public API-discovery descriptions for existing project defaults and managed instance restart operations, including their field scope and authority limits. ## Verification **Qualified: [pilot 41256592937](https://github.com/paperclipai/paperclip/actions/runs/41256592937) passes 3/3, with all 35 independent checks passing.** | Case | Checks | Full case duration | Evidence and cleanup | | --- | --- | --- | --- | | Instance restart | 9/9 | 140.1 s | complete | | Project defaults | 11/11 | 204.2 s | complete | | Project work | 15/15 | 204.0 s | complete | All three are original-attempt results from source `c51e079f7f2364305b131ffd549e263ff78c5335`, containing the exact product files from `13c2b61f31d873a475ea0c3c026b19926ff42301`. Actual saved conversation contracts were inspected, as were ordinary native worker contracts where present. Each protected archive includes the actual API state and final PNG; cleanup completes. Original queries, `openrouter/deepseek/deepseek-v4.1-flash-1017`, finite case clocks, concurrency one and zero eval retries are preserved. Earlier passes do not transfer into this qualification. Both current heads pass all checks: product **62** (56 success, one neutral, five skipped), catalog **56** (54 success, one neutral, one skipped). Both have exact-head Greptile **5/5**, zero unresolved review threads and clean mergeability. The three trusted private-evidence protocol files remain byte-identical to the dispatch workflow. Raw evidence stays protected. - **2,044 API discovery tests pass.** Red controls showed that “restart instance” selected unrelated drain/settings operations and “save project defaults” selected repository replacement. Accurate public summaries now rank the existing operations correctly; route registration preserves descriptions. No endpoint, permission or field behavior changes. - **112 real-database, authenticated HTTP, native Runner and OpenAPI consumer tests pass locally**, using disposable task-owned Docker PostgreSQL. It was removed afterward; shared IPC was untouched. These cover persisted contract selection, admitted native input and the model envelope together. The isolated CI suites also pass. - **77 focused contract/input/context tests pass.** Red controls catch the wrong conversation predicate; canonical identity requires both agent and user IDs, including the actual heartbeat projection. Ordinary tasks, agent-only issues and planner tasks remain strict. Coalesced requests preserve criterion identities, source hashes and human-response scope. - **144 OpenCode driver tests pass**; native core **441 pass, one ignored**; packaging **56 pass, six skipped**. Server typecheck and build pass. - Real pinned OpenCode/native Runner: a delayed 25-second acknowledgement completes within the original 30-second MCP deadline. The text-fragment control changes 817 notifications / 54.1 seconds / timeout to 45 / 19.0 seconds / accepted finish. Separate fast, six-minute and real authenticated API probes complete 32 tool calls plus finish. These do not reproduce every remaining historical MCP timeout, and no common cause is claimed for all such failures. Retained failures remain attributed to their original source. Earlier runs exposed fabricated empty-response success, prospective-default backfill, a literal whole-task chat criterion, fixture readiness and oracle/reporting defects. The immediately preceding [41250502608](https://github.com/paperclipai/paperclip/actions/runs/41250502608), product `c0bf249807` / source `7b1de24ce1`, is **1/3**: work 15/15; restart 4/9 with the repaired contract actually admitted but no answer; defaults timed out before settlement, then exceeded the unchanged 256 MiB original-evidence allowance. Defaults domain behavior on that attempt remains inconclusive. #18377 retains the full attempt ledger, including missing archives and pre-paid cancellations. The fresh 3/3 establishes these selected outcomes; it does not establish full-catalog reliability. ## Risks The shared contract change applies to standing native chats across providers. It changes model instructions and completion scope, while permission, approval and review gates remain enforced by their existing owners. Incorrect model claims remain possible; the product evals independently require actual mutations, native work and delivery. The correction adds at most one provider request within the existing deadline; text batching can delay adjacent text by 50 ms. Three qualified attempts do not establish full-catalog reliability. ## Model Used OpenAI GPT-6 through Codex, with repository inspection, tool use, code execution and live eval tooling. Exact hosted model revision and context-window size are not exposed. ## 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 #` 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 - [x] Final same-source three-cell pilot passes 3/3 with required evidence and cleanup --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
269 lines
13 KiB
TypeScript
269 lines
13 KiB
TypeScript
import { createHash } from "node:crypto";
|
|
import { and, desc, eq, sql } from "drizzle-orm";
|
|
|
|
import type { Db } from "@paperclipai/db";
|
|
import { completionContracts } from "@paperclipai/db";
|
|
import type { NativeCompletionSource, StrictCompletionContractInput } from "../../vendor/paperclip-runner/index.js";
|
|
|
|
import { nativeSha256 } from "./canonical.js";
|
|
import { isConversation, type ConversationIdentity } from "../agent-conversations.js";
|
|
|
|
export const NATIVE_COMPLETION_CONTRACT_SCHEMA = "paperclip.completion-contract.v1";
|
|
export const NATIVE_COMPLETION_POLICY_VERSION = "phase6-v4";
|
|
|
|
/** Canonical persisted receipt includes the policy that governs the contract. */
|
|
export function nativeCompletionContractSha256(row: Pick<typeof completionContracts.$inferSelect,
|
|
"schemaVersion" | "policyVersion" | "risk" | "completionAuthority" | "contractJson">): string {
|
|
return nativeSha256({
|
|
schemaVersion: row.schemaVersion,
|
|
policyVersion: row.policyVersion,
|
|
risk: row.risk,
|
|
completionAuthority: row.completionAuthority,
|
|
contract: row.contractJson,
|
|
});
|
|
}
|
|
|
|
type CompletionComment = {
|
|
id?: string;
|
|
body: string;
|
|
attachments?: readonly unknown[];
|
|
};
|
|
|
|
export function nativeCompletionSource(kind: NativeCompletionSource["kind"], id: string, content: string): NativeCompletionSource {
|
|
return { kind, id, revision: createHash("sha256").update(content.trim()).digest("hex") };
|
|
}
|
|
|
|
/** Select only the server-owned description source for the ordinary objective path. */
|
|
export function nativeImmediateObjectiveSource(input: {
|
|
issueId: string;
|
|
objectiveSource?: {
|
|
kind: "comment" | "description" | "title";
|
|
id: string;
|
|
revision: string | null;
|
|
} | null;
|
|
excluded: boolean;
|
|
}): NativeCompletionSource | null {
|
|
const source = input.objectiveSource;
|
|
return !input.excluded && source?.kind === "description" && source.id === input.issueId && source.revision
|
|
? { kind: "description", id: source.id, revision: source.revision }
|
|
: null;
|
|
}
|
|
|
|
/** The same source operation produces both the requirement and its provenance. */
|
|
export function nativeCompletionRequestsWithSources(
|
|
comments: readonly CompletionComment[],
|
|
options: { requiredFullWakeCommentCount?: number } = {},
|
|
): { requests: string[]; sources: Array<NativeCompletionSource | null> } {
|
|
if (Number.isSafeInteger(options.requiredFullWakeCommentCount) && (options.requiredFullWakeCommentCount ?? 0) > 0) {
|
|
return { requests: [
|
|
`Read every server-bound pending external-chat comment with read_current_wake_comments until complete=true, then answer all ${options.requiredFullWakeCommentCount} accepted comments in order without omitting a request. Report any unavailable attachment honestly; metadata alone is not its content.`,
|
|
], sources: [null] };
|
|
}
|
|
const entries = comments.flatMap((comment, index) => {
|
|
const body = comment.body.trim();
|
|
if (body) return [{ request: body, source: comment.id ? nativeCompletionSource("comment", comment.id, body) : null }];
|
|
// A file-only message has an independent inspection requirement.
|
|
return comment.attachments?.length
|
|
? [{ request: `Inspect and respond to the attached file(s) on pending comment ${index + 1}.`, source: null }]
|
|
: [];
|
|
});
|
|
return { requests: entries.map((entry) => entry.request), sources: entries.map((entry) => entry.source) };
|
|
}
|
|
|
|
export function nativeCompletionRequestsForComments(
|
|
comments: readonly CompletionComment[],
|
|
options: { requiredFullWakeCommentCount?: number } = {},
|
|
): string[] {
|
|
return nativeCompletionRequestsWithSources(comments, options).requests;
|
|
}
|
|
|
|
export function resolveNativeCompletionPolicy(issue: {
|
|
reviewPolicy?: string | null;
|
|
}) {
|
|
const externalReviewRequired =
|
|
issue.reviewPolicy === "human_only" || issue.reviewPolicy === "not_creator";
|
|
return externalReviewRequired
|
|
? { risk: "standard", completionAuthority: "server_arbiter" } as const
|
|
: { risk: "low", completionAuthority: "agent_claim_policy" } as const;
|
|
}
|
|
|
|
export function buildNativeCompletionContract(
|
|
issue: { title: string; description: string | null } & ConversationIdentity,
|
|
options: {
|
|
readonly revision?: number;
|
|
readonly immediateRequest?: string | null;
|
|
readonly immediateRequests?: readonly string[] | null;
|
|
/** ID of this wake's server-verified humanResponses entry; its content is already in task context. */
|
|
readonly humanResponseId?: string | null;
|
|
} = {},
|
|
): StrictCompletionContractInput {
|
|
const immediateRequests = (
|
|
options.immediateRequests ??
|
|
(options.immediateRequest == null ? [] : [options.immediateRequest])
|
|
)
|
|
.map((request) => request.trim())
|
|
.filter((request) => request.length > 0);
|
|
const humanResponseId = options.humanResponseId?.trim();
|
|
const hasFollowUp = immediateRequests.length > 0 || Boolean(humanResponseId);
|
|
const conversation = isConversation(issue);
|
|
const requirement = (request: string) => conversation
|
|
? `Address this request in the current authorized conversation response: ${request}`
|
|
: request;
|
|
// Reference existing context rather than copying the brief/history into every
|
|
// follow-up contract. Keep this guidance stable across comments and resumes.
|
|
const followUpObjective = "Complete the current authorized stage using the task brief and current user direction in the supplied context. Later human direction replaces conflicting scope; preserve other requirements, assigned-skill instructions, and approval gates. Apply authenticated humanResponses only to their question or decision. Clarification is not approval. If acceptance is required, propose or save the requested plan and wait before executing.";
|
|
const conversationObjective = "Complete the current conversation response using the supplied context and current user direction. Carry out requested chat actions within current authority and verify their results before claiming success. For delegated work, verify the saved handoff and report it without waiting for or performing the worker's task. For an unavailable action, explain the specific limitation and supported handoff without claiming the action occurred. Finishing this response leaves underlying delegated or unavailable work incomplete until separately verified. Later human direction replaces conflicting scope; preserve other requirements, assigned-skill instructions, and approval gates. Apply authenticated humanResponses only to their question or decision. Clarification is not approval.";
|
|
return {
|
|
revision: String(options.revision ?? 1),
|
|
objective: conversation
|
|
? conversationObjective
|
|
: hasFollowUp
|
|
? followUpObjective
|
|
: issue.title,
|
|
criteria: hasFollowUp
|
|
? [
|
|
...immediateRequests.map((request, index) => ({
|
|
id: immediateRequests.length === 1 ? "objective" : `pending_comment_${index + 1}`,
|
|
requirement: requirement(request),
|
|
})),
|
|
...(humanResponseId ? [{
|
|
id: "human_response",
|
|
requirement: `Apply the server-verified humanResponses entry with id ${JSON.stringify(humanResponseId)} in the supplied current request context, within its question or decision scope and subject to later user direction.`,
|
|
}] : []),
|
|
]
|
|
: [
|
|
{
|
|
id: "objective",
|
|
requirement:
|
|
requirement(issue.description?.trim() || (conversation ? "Respond to the current conversation context." : `Complete: ${issue.title}`)),
|
|
},
|
|
],
|
|
};
|
|
}
|
|
|
|
function nativeCompletionContractLockKey(companyId: string, issueId: string): string {
|
|
return `paperclip:native-completion-contract:${companyId}:${issueId}`;
|
|
}
|
|
|
|
export async function lockCurrentNativeCompletionContract(tx: Db, input: {
|
|
companyId: string; issueId: string; contractId: string;
|
|
}): Promise<boolean> {
|
|
const [lock] = await tx.execute(sql`select pg_try_advisory_xact_lock(hashtextextended(
|
|
${nativeCompletionContractLockKey(input.companyId, input.issueId)}, 0)) as acquired`) as unknown as Array<{ acquired: boolean }>;
|
|
if (!lock.acquired) return false;
|
|
const [latest] = await tx.select({ id: completionContracts.id }).from(completionContracts)
|
|
.where(and(eq(completionContracts.companyId, input.companyId), eq(completionContracts.issueId, input.issueId)))
|
|
.orderBy(desc(completionContracts.revision)).limit(1);
|
|
return latest?.id === input.contractId;
|
|
}
|
|
|
|
export async function ensureNativeCompletionContract(input: {
|
|
db: Db;
|
|
companyId: string;
|
|
issue: {
|
|
id: string;
|
|
title: string;
|
|
description: string | null;
|
|
reviewPolicy?: string | null;
|
|
conversationAgentId?: string | null;
|
|
conversationUserId?: string | null;
|
|
};
|
|
actorId: string;
|
|
immediateRequest?: string | null;
|
|
/** Provenance for a singular server-selected request, when explicitly known. */
|
|
immediateRequestSource?: NativeCompletionSource | null;
|
|
immediateRequests?: readonly string[] | null;
|
|
immediateRequestSources?: readonly (NativeCompletionSource | null)[];
|
|
humanResponseId?: string | null;
|
|
}) {
|
|
return input.db.transaction(async (tx) => {
|
|
await tx.execute(sql`select pg_advisory_xact_lock(hashtextextended(
|
|
${nativeCompletionContractLockKey(input.companyId, input.issue.id)}, 0))`);
|
|
const policy = resolveNativeCompletionPolicy(input.issue);
|
|
const latest = await tx
|
|
.select()
|
|
.from(completionContracts)
|
|
.where(and(
|
|
eq(completionContracts.companyId, input.companyId),
|
|
eq(completionContracts.issueId, input.issue.id),
|
|
))
|
|
.orderBy(desc(completionContracts.revision))
|
|
.limit(1)
|
|
.then((rows) => rows[0] ?? null);
|
|
const latestRevision = latest?.revision ?? 1;
|
|
const latestCandidate = buildNativeCompletionContract(input.issue, {
|
|
revision: latestRevision,
|
|
immediateRequest: input.immediateRequest,
|
|
immediateRequests: input.immediateRequests,
|
|
humanResponseId: input.humanResponseId,
|
|
});
|
|
const latestCandidateSha256 = nativeCompletionContractSha256({
|
|
schemaVersion: NATIVE_COMPLETION_CONTRACT_SCHEMA,
|
|
policyVersion: NATIVE_COMPLETION_POLICY_VERSION,
|
|
...policy,
|
|
contractJson: latestCandidate as unknown as Record<string, unknown>,
|
|
});
|
|
if (latest?.canonicalSha256 === latestCandidateSha256) {
|
|
return { row: latest, contract: latestCandidate, sources: buildNativeCompletionContractSources(input) };
|
|
}
|
|
|
|
const nextRevision = latest ? latest.revision + 1 : 1;
|
|
const contract = buildNativeCompletionContract(input.issue, {
|
|
revision: nextRevision,
|
|
immediateRequest: input.immediateRequest,
|
|
immediateRequests: input.immediateRequests,
|
|
humanResponseId: input.humanResponseId,
|
|
});
|
|
const canonicalSha256 = nativeCompletionContractSha256({
|
|
schemaVersion: NATIVE_COMPLETION_CONTRACT_SCHEMA,
|
|
policyVersion: NATIVE_COMPLETION_POLICY_VERSION,
|
|
...policy,
|
|
contractJson: contract as unknown as Record<string, unknown>,
|
|
});
|
|
const [row] = await tx.insert(completionContracts).values({
|
|
companyId: input.companyId,
|
|
issueId: input.issue.id,
|
|
revision: nextRevision,
|
|
schemaVersion: NATIVE_COMPLETION_CONTRACT_SCHEMA,
|
|
policyVersion: NATIVE_COMPLETION_POLICY_VERSION,
|
|
...policy,
|
|
incompleteCriteriaPolicy: "preserve_non_terminal",
|
|
contractJson: contract as unknown as Record<string, unknown>,
|
|
canonicalSha256,
|
|
createdByActorType: "system",
|
|
createdByActorId: input.actorId,
|
|
supersedesContractId: latest?.id ?? null,
|
|
}).returning();
|
|
if (!row) throw new Error("native_completion_contract_not_persisted");
|
|
return { row, contract, sources: buildNativeCompletionContractSources(input) };
|
|
});
|
|
}
|
|
|
|
|
|
export function buildNativeCompletionContractSources(input: {
|
|
issue: { id: string; description: string | null };
|
|
immediateRequest?: string | null;
|
|
immediateRequestSource?: NativeCompletionSource | null;
|
|
immediateRequests?: readonly string[] | null;
|
|
immediateRequestSources?: readonly (NativeCompletionSource | null)[];
|
|
humanResponseId?: string | null;
|
|
}): Array<{ id: string; source: NativeCompletionSource }> {
|
|
const requests = (input.immediateRequests ?? (input.immediateRequest == null ? [] : [input.immediateRequest]))
|
|
.map((body, index) => ({
|
|
body: body.trim(),
|
|
source: input.immediateRequests
|
|
? input.immediateRequestSources?.[index]
|
|
: input.immediateRequestSource,
|
|
}))
|
|
.filter((entry) => entry.body.length > 0);
|
|
if (requests.length > 0) {
|
|
return requests.flatMap((entry, index) => entry.source ? [{
|
|
id: requests.length === 1 ? "objective" : `pending_comment_${index + 1}`,
|
|
source: entry.source,
|
|
}] : []);
|
|
}
|
|
return !input.humanResponseId?.trim() && input.issue.description?.trim()
|
|
? [{ id: "objective", source: nativeCompletionSource("description", input.issue.id, input.issue.description) }]
|
|
: [];
|
|
}
|