mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-02 02:07:25 +08:00
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Its control plane decides when a task can continue, wait, stop, or complete. > - Legacy continuation could change when an agent changed its wording without changing task state. > - Shared attempt counts also let repair and infrastructure retries affect each other's limits. > - This pull request uses persisted state and separate, bounded allowances for these decisions. > - If automatic repair stops, the task explains what happened and offers a guarded retry. > - Paired tests and real-provider evaluations verify that Stop, approvals, ownership, and spending limits remain authoritative. ## Linked Issues or Issue Description Related work: Refs #13761, Refs #11126, Refs #13610. These cover obsolete continuation dispatch and retry storms. Open and closed issues and PRs were searched for related lifecycle, continuation, and retry work. **What happened?** Legacy continuation depended on English wording and progress heuristics. Repair, failure retry, and productive continuation could consume shared counts. When bounded repair stopped, the task showed a technical recovery message without a clear next action. **Expected behavior** Persisted disposition and owned execution paths determine the next action. Missing disposition prompts bounded agent repair. Explicit work mode determines planning mode. Narrative changes and raw activity counts cannot replenish allowances. An exhausted repair shows a readable notice. An explicit retry checks current controls and preserves the assigned agent. **Steps to reproduce** Run `pnpm test:lifecycle-baseline`. The paired probes keep structured state constant while varying completion, planning, blocker, and progress prose. Run the explicit `lifecycle-baseline` and `continuation-accounting` Product E2E suites for real-provider coverage. In Storybook, open **Design previews / Recovery notice** to inspect the production component's normal, pending, acknowledged, unavailable, failure, and mobile states. ## What Changed - Hide the image attachment button, icon, and drop/paste hint in answer composers. Image paste and drop support remains available. - Merge current master and retain both browser regression sets. Use a production-stamped service worker in the offline recovery browser fixture. - Share one state-based legacy continuation decision across immediate, delayed, and recovered dispatch. Bind bounded repairs to their source run and episode. - Remove title and description wording from work-mode authority. Agents can still write requested plans in execution mode. - Persist separate failure-retry and productive-continuation counters. Disposition repair and resource waits cannot consume or reset those allowances. - Validate delayed repair identity, then recheck current gates before provider dispatch. Fence native startup cancellation. - Show **Agent needs attention**, a plain-language explanation, **Retry agent**, and expandable details in both task interfaces. Report request progress, acknowledgement, and errors inline. - Store typed recovery notice metadata. Recognize older active notices only through exact stored action and run IDs. Notice text never grants retry authority. - Use the existing recovery-action endpoint for retry. Recheck current action, status, owner, agent availability, dependencies, active runs, pending questions and confirmations, approvals, pause controls, and budget. Duplicate requests do not wake twice. - Add component, page, route, database, contract, and Storybook coverage. Keep the scenario inventory and executable evals here. Historical reports and snapshots live in the [commit-pinned paperclip-evals archive](https://github.com/paperclipai/paperclip-evals/blob/ce3e5afcd4a1184650f586a2b5b8be5874c66c8b/experiments/2026-09-lifecycle-authority/README.md). - Preserve unsaved project fields while the same project URL changes to its canonical alias. Do not reuse data across projects or companies. This separate fix addresses the repeated repository-editor browser failure without changing the browser test. - Keep the development service worker from intercepting Vite module reloads. Update the connection-intent browser fixture to record progress and completion through the agent API. ## Verification Merge preparation on September 25, commit `c1e8e4b7ddd9fbc4913ed55ce21b8e12906c2f97`: - Merged master `bd2030932` and resolved the browser test-list conflict by keeping both sets of regressions. - Deterministic lifecycle baseline: 1,090/1,090 assertions passed; no failures, skips, or missing selected evidence. Unit 423, runner 184, database integration 397, grading 86. - Browser support: 17/17 passed. The offline recovery test first failed with an unstamped development worker, then passed with the production stamp. Its assertions are unchanged. - Focused interaction UI and offline fallback tests: 19/19 passed. Verified the custom-answer composer in Storybook: no attachment controls or hint; entering an answer enables Next. - Recursive typecheck, production build, token gates, and diff checks passed. The worktree is clean. No new real-provider campaign was run. - Current CI and review: [Current PR CI passed](https://github.com/paperclipai/paperclip/actions/runs/36166011243): 55 successful checks and two optional Storybook skips. Greptile scored this exact commit 5/5. Hiding the question attachment controls is an intentional UI change; paste/drop remains available. Earlier recovery UI verification, commit `21be0fec0e90e86b6d662b8ee4831847cd041cdb`: - Recursive typecheck, production build, token gates, and diff checks passed. - Focused UI coverage: 338 tests passed across six suites (336 before the interaction guard, with the two affected suites rerun at 149 passed after it). Covers both task interfaces, the real page mutation, pending/error acknowledgement, stale state, and unavailable controls. - Recovery database integration: 352 tests passed before the interaction guard. The complete recovery-action and mutation-route suites passed 181 tests after it. The two new pending question/confirmation regressions failed before the fix and passed afterward, including resolved-interaction controls. Shared validator suite: 31 passed. E2E catalog suites: 34 passed. - Browser inspection passed for light/dark themes, mobile layout, expandable details, pending retry, acknowledgement, failure, and disabled retry. Storybook renders the production component; its request is simulated. - The broad local run hit two chat callback-order wait failures and was stopped after all CI unit/database/runner shards passed. Both local failures passed when rerun without the competing full-suite process. - CI exposed a repeated project-repository draft-loss race during canonical redirects. A new unit regression failed before the fix; all nine project-page tests now pass, including controls for other projects and companies. Both unchanged repository browser tests passed against a fresh local server. UI typecheck, production UI build, and token gates passed after this fix. - [Earlier PR CI passed](https://github.com/paperclipai/paperclip/actions/runs/36072486798) on `21be0fec0e90e86b6d662b8ee4831847cd041cdb`: 55 successful checks, two optional Storybook skips, and no failed or pending checks. The repository browser shard passed with the production fix. Greptile is 5/5 on this exact commit with no unresolved review threads. The PR is mergeable. Historical, source-qualified lifecycle evidence: - Lifecycle baseline: 1,074 assertions. Native session coverage: 447 tests. Product E2E support: 515 tests. Browser support: 11 tests. Full earlier verification is retained in the archive. - [Real-provider campaign: 8/8 passed, zero retries](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-35881382080-1/index.html), source `e88d210417280140b44a36449027290adcb1aeaa`. Evidence and cleanup checks passed. This includes deliberately exhausted repair cases that correctly remain blocked; it does not mean every task finished Done. This campaign predates the recovery UI change. - Archive migration verified all 16 original JSON files byte-for-byte and all 24 checksum entries. App tests do not need private archive access. [Archive PR #27](https://github.com/paperclipai/paperclip-evals/pull/27) is merged. ## Risks - Agents that omit durable disposition receive at most two repair attempts by default. Prose-only completion exposes missing state rather than silently changing scheduling. - A retry is an explicit board action. The server rechecks current controls. A successful response confirms the task returned to To do; it does not claim that the provider has already started. - Existing notice metadata remains valid. Only older active notices with matching structured evidence receive the new UI. Historical notices without that evidence keep their existing rendering. No schema migration is required. - Old run records require conservative retry accounting. Tests cover old counters, alternating retry lanes, restarts, and exhausted repairs. - Historical snapshots require private `paperclip-evals` access. The app index retains public campaign links. Live campaigns qualify specific sources and scenarios; no new real-provider campaign has run for the recovery UI commit. > This fixes existing lifecycle and recovery behavior and does not duplicate planned core work. ## Model Used OpenAI GPT-6 through Codex assisted implementation, reasoning, code execution, and review. The exact serving model ID and context window are not exposed in this task. Historical real-provider evaluations used Codex model `gpt-5.6-sol`, separately from the implementation assistant. ## 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 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 --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
104 lines
8.2 KiB
TypeScript
104 lines
8.2 KiB
TypeScript
import { mkdtemp, writeFile, rm } from "node:fs/promises";
|
|
import { tmpdir } from "node:os";
|
|
import { join } from "node:path";
|
|
import { packageEvidence } from "./evidence.js";
|
|
import { describe, expect, it } from "vitest";
|
|
import { accountingCase, accountingCases, accountingCommentBodies, accountingScreenshotFile } from "./accounting-cases.js";
|
|
import { gradeAccounting, type AccountingCheckpoint } from "./accounting-scoring.js";
|
|
import { parseRunnerSelectors, selectRunnerExecutions } from "./selectors.js";
|
|
function recording(id = "accounting-productive-neutral") {
|
|
const probe = accountingCase(id), nonce = "nonce", agentId = "agent";
|
|
const run = (i: number) => ({ id: `r${i}`, status: "succeeded", runtimeMode: "legacy", scheduledRetryAttempt: 0, contextSnapshot: {} as Record<string, any> });
|
|
const comments = (runs: any[]) => runs.filter(r => r.status === "succeeded").flatMap(r => accountingCommentBodies(probe, nonce).map(body => ({ body, authorAgentId: agentId, createdByRunId: r.id })));
|
|
const cleanIssue = { status: "done", executionRunId: null, scheduledRetry: null, monitorNextCheckAt: null, activeRecoveryAction: null };
|
|
let checkpoints: AccountingCheckpoint[];
|
|
if (probe.kind === "productive") {
|
|
checkpoints = Array.from({ length: 5 }, (_, i) => {
|
|
const step = i + 1, runs = Array.from({ length: step }, (_, n) => run(n));
|
|
return { phase: `step-${step}`, issue: { ...cleanIssue, status: step < 5 ? "in_review" : "done" }, runs, comments: comments(runs),
|
|
documents: Array.from({ length: step }, (_, n) => ({ key: `step-${n + 1}`, latestRevisionNumber: 1, body: `STEP ${n + 1}: ${n === 0 ? "START" : `VALUEnonceN${n + 1}`}` })),
|
|
interactions: Array.from({ length: Math.min(step, 4) }, (_, n) => ({ id: `q${n}`, kind: "ask_user_questions", status: n === i && step < 5 ? "pending" : "answered" })),
|
|
};
|
|
});
|
|
} else {
|
|
const runs = [run(0), run(1), run(2)];
|
|
for (let i = 1; i <= 2; i++) runs[i].contextSnapshot = { wakeReason: "issue_disposition_repair", legacyDispositionEpisode: { id: "r0", attempt: i, maxAttempts: 2 } };
|
|
if (probe.kind === "approval") {
|
|
runs[2].contextSnapshot = {};
|
|
checkpoints = [{ phase: "approval", issue: { ...cleanIssue, status: "in_review" }, runs: runs.slice(0, 2), comments: comments(runs.slice(0, 2)), documents: [], interactions: [{ kind: "request_confirmation", status: "pending" }] },
|
|
{ phase: "completed", issue: cleanIssue, runs, comments: comments(runs), documents: [], interactions: [{ kind: "request_confirmation", status: "accepted" }] }];
|
|
} else {
|
|
const scheduled = { phase: "scheduled", issue: cleanIssue, runs: structuredClone(runs), comments: comments(runs), documents: [], interactions: [] };
|
|
scheduled.runs[2].status = "scheduled_retry";
|
|
const restarted = { ...structuredClone(scheduled), phase: "restarted" };
|
|
if (probe.kind === "stop") runs[2].status = "cancelled";
|
|
const finished = { phase: "after-due", issue: probe.kind === "stop" ? cleanIssue : { ...cleanIssue, status: "blocked", activeRecoveryAction: { ownerType: "board", attemptCount: 2 } }, runs, comments: comments(runs), documents: [], interactions: [] };
|
|
checkpoints = [scheduled, restarted, finished];
|
|
}
|
|
}
|
|
checkpoints.push({ ...structuredClone(checkpoints.at(-1)!), phase: "final" });
|
|
return { probe, nonce, agentId, runtime: "legacy", checkpoints };
|
|
}
|
|
const failures = (r: ReturnType<typeof recording>) => gradeAccounting(r).filter(c => !c.passed).map(c => c.id);
|
|
describe("ACCT calibrated live accounting evidence", () => {
|
|
it("retains every accounting screenshot through the existing evidence allowlist", async () => {
|
|
const root = await mkdtemp(join(tmpdir(), "accounting-evidence-"));
|
|
try {
|
|
const files = ["step-1", "step-2", "step-3", "step-4", "step-5", "approval", "final"].map(accountingScreenshotFile);
|
|
for (const file of files) await writeFile(join(root, file), Buffer.from("89504e470d0a1a0a", "hex"));
|
|
const packaged = await packageEvidence({ privateDir: root, uploadDir: join(root, "packaged"), secrets: [], expectPassScreenshot: false });
|
|
expect(packaged.leaks).toEqual([]);
|
|
expect(packaged.files).toEqual(expect.arrayContaining(files));
|
|
expect(files).toContain("final-state.png");
|
|
} finally { await rm(root, { recursive: true, force: true }); }
|
|
});
|
|
it("discovers eight explicit-only real-provider cells and excludes unsupported native repair injection", () => {
|
|
const cells = selectRunnerExecutions(parseRunnerSelectors(["--suite", "continuation-accounting"]));
|
|
expect(cells).toHaveLength(8);
|
|
expect(cells.filter(c => c.profile.generation === "native")).toHaveLength(2);
|
|
expect(selectRunnerExecutions(parseRunnerSelectors(["--all"])).some(c => c.suite.id === "continuation-accounting")).toBe(false);
|
|
expect(cells.every(c => c.requiredCredentials.includes("OPENAI_API_KEY"))).toBe(true);
|
|
});
|
|
it.each(accountingCases)("accepts a complete $id recording", c => expect(failures(recording(c.id))).toEqual([]));
|
|
it("rejects a serialized array in place of the exact neutral comment", () => {
|
|
const r = recording(), f = r.checkpoints.at(-1)!;
|
|
for (const comment of f.comments) comment.body = JSON.stringify([comment.body]);
|
|
expect(failures(r)).toEqual(["perturbation"]);
|
|
});
|
|
it.each(["accounting-productive-neutral", "accounting-exhaustion-noisy", "accounting-repair-stop", "accounting-repair-approval"])("rejects missing final evidence for %s", id => {
|
|
const r = recording(id); r.checkpoints.pop(); expect(failures(r)).toContain("evidence");
|
|
});
|
|
it.each(["noise", "extra-run", "wrong-runtime", "pending-retry", "repair-debt", "wrong-document", "premature-document", "missing-answer", "missing-state", "rewritten-document", "deduplicated-noise"])("rejects productive %s", mutation => {
|
|
const r = recording("accounting-productive-noisy"), f = r.checkpoints.at(-1)!;
|
|
if (mutation === "deduplicated-noise") f.comments = f.comments.filter(c => !c.body.includes("N2:") && !c.body.includes("N3:"));
|
|
if (mutation === "noise") f.comments = [];
|
|
if (mutation === "extra-run") f.runs.push(structuredClone(f.runs[0]));
|
|
if (mutation === "wrong-runtime") f.runs[0].runtimeMode = "native";
|
|
if (mutation === "pending-retry") f.issue.scheduledRetry = { id: "retry" };
|
|
if (mutation === "repair-debt") f.runs[1].contextSnapshot.dispositionRepairAttempt = 1;
|
|
if (mutation === "wrong-document") r.checkpoints[2].documents[0].body = "wrong";
|
|
if (mutation === "premature-document") r.checkpoints[0].documents.push({ key: "step-5", body: "premature" });
|
|
if (mutation === "missing-state") delete f.issue.scheduledRetry;
|
|
if (mutation === "rewritten-document") r.checkpoints[2].documents[0].latestRevisionNumber = 2;
|
|
if (mutation === "missing-answer") f.interactions.pop();
|
|
expect(failures(r).length).toBeGreaterThan(0);
|
|
});
|
|
it.each(["new-episode", "reset-attempt", "extra-repair", "user-comment", "restart-loss", "hidden-exhaustion"])("rejects exhausted repair %s", mutation => {
|
|
const r = recording("accounting-exhaustion-noisy"), f = r.checkpoints.at(-1)!;
|
|
if (mutation === "new-episode") f.runs[2].contextSnapshot.legacyDispositionEpisode.id = "new";
|
|
if (mutation === "reset-attempt") f.runs[2].contextSnapshot.legacyDispositionEpisode.attempt = 1;
|
|
if (mutation === "extra-repair") f.runs.push(structuredClone(f.runs[2]));
|
|
if (mutation === "user-comment") f.comments.push({ authorUserId: "operator", body: "continue" });
|
|
if (mutation === "restart-loss") r.checkpoints[1].runs[2].id = "replacement";
|
|
if (mutation === "hidden-exhaustion") f.issue.activeRecoveryAction = null;
|
|
expect(failures(r).length).toBeGreaterThan(0);
|
|
});
|
|
it("rejects Stop that still dispatched the provider", () => {
|
|
const r = recording("accounting-repair-stop"); r.checkpoints.at(-1)!.runs[2].startedAt = "2026-09-22"; expect(failures(r)).toContain("stopped");
|
|
});
|
|
it("rejects pending approval competing with repair and declined approval continuing", () => {
|
|
const r = recording("accounting-repair-approval"); r.checkpoints[0].issue.scheduledRetry = { id: "repair" }; r.checkpoints.at(-1)!.interactions[0].status = "rejected";
|
|
expect(failures(r)).toEqual(expect.arrayContaining(["approval-owner", "approval-resumed"]));
|
|
});
|
|
});
|