Files
PaperClipAI/server/src/services/native-runtime/native-provider-capacity-retry.ts
T
DottaandPaperclip f2715e02bb fix(native): surface model capacity errors and retry automatically (#15347)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - Native runs preserve provider events and results, then decide task
state.
> - Codex can fail a turn because the selected model is temporarily at
capacity.
> - Paperclip displayed a generic native-session failure and left the
task in recovery.
> - A known capacity failure needs a clear message and a durable delayed
retry.
> - This pull request uses committed terminal evidence, the
status-effect ledger, and existing dispatch gates.
> - The task can continue automatically without an unbounded retry loop
or a model switch.

## Linked Issues or Issue Description

Related: #13993 adds launcher capacity deferrals before provider
startup. This change handles a committed native Codex `serverOverloaded`
terminal after provider work has started.

**What happened?**
A native Codex turn ended with `codexErrorInfo: serverOverloaded` and
“Selected model is at capacity. Please try a different model.” Paperclip
saved the result, showed a generic failure, and required recovery
instead of waiting and retrying.

**Expected behavior**
Show the capacity error directly. Schedule bounded retries after a short
delay. Preserve saved work and honor current execution gates.

**Steps to reproduce**
1. Run a native Codex task.
2. Commit a `turn.failed` event with `serverOverloaded`, then accept a
failed result for the same turn.
3. Inspect the task error and its recovery state. The regression test
reproduces this without a paid provider call.

**Paperclip version or commit**
Reproduced against master `16b7db35ffa0f9a95913c8cbdeea3d595435691f`.

## What Changed

- Classify capacity failures from committed runner events and the pinned
execution identity. Preserve accepted results and display the specific
capacity error.
- Atomically persist one scheduled successor with the status decision.
Retry after one minute, then two minutes. Share the existing failure
budget and stop after two automatic retries.
- Reuse dispatch gates for ownership, task holds, dependencies, budget,
and locks. Wait for predecessor execution, finalization, and cleanup
before claiming a retry.
- Preserve pending reviewer authority and suppress retries after
reassignment or a successor claim.
- Consume the failed run's resume receipt and delivered wake input.
Rebuild ordinary continuation from the failed run so explicitly resumed
tasks can retry without borrowing one-run authorization.
- Label scheduled retries “Model at capacity.” Add a Storybook example
and avoid duplicate punctuation in the existing retry card.
- Add regression coverage and document the runtime contract.

## Verification

- Targeted recovery and UI suites: 125 tests passed. Additional final
cleanup and lock regressions passed.
- Latest-head continuation and authorization regressions: 57 tests
passed, including all four capacity integration tests against an
isolated PostgreSQL database.
- Rechecked all four capacity integration tests with the full runner's
isolated `PAPERCLIP_HOME`, config, temporary directory, and serial fork
settings: passed.
- `pnpm -r typecheck`: passed. Final server typecheck passed.
- `pnpm build`: passed.
- `pnpm check:token-gates`: passed.
- Browser: checked the real Storybook card. It shows the capacity
message, automatic retry time, and existing Retry now action.
- `pnpm test:run`: attempted and restarted after an interruption. The
resumed run started before the final review correction and was stopped
after recorded workspace/native test failures and the five-minute Git
streaming timeout already documented on master. Exit 130; no complete
local full-suite pass is claimed. Current-head isolated capacity tests
and the complete CI suite pass.
- A combined local recovery-suite attempt also hit PostgreSQL
initialization failures at this macOS host's global shared-memory limit
(32 slots). The focused recovery suites passed separately; final-head
capacity tests also pass with the full runner's isolated environment
settings.
- Latest-head GitHub checks: all 56 checks green, including general and
serialized test shards, browser E2E, typecheck, build, Runner
verification, and canary dry run. No merge conflicts.
- Greptile: 5/5 on `813a470b8c18c05aeb7e31e63e573c3a3a2f5cac`, with zero
unresolved findings after fixing the resumed-task continuation issue.

## Risks

- Capacity retries can repeat a task turn after partial work. They start
a fresh provider session with task history and wait for predecessor
cleanup. They do not resume the failed turn.
- Retries retain the configured model unless an operator changes
configuration. Persistent overload consumes the existing failure budget
and then needs an explicit retry or model change.
- Only run-bound native Codex `serverOverloaded` failures qualify.
Usage-limit exhaustion, model/account incompatibility, unbound text, and
unknown provider failures retain their current recovery behavior.
- No schema migration is required.

## Model Used

- OpenAI GPT-6 through Codex. The exact model ID and context-window size
are not exposed to this session. Used reasoning, repository tools, code
execution, and browser verification. No subagents.

## 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
- [ ] 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>
2026-10-06 10:59:18 -05:00

70 lines
3.7 KiB
TypeScript

import { randomUUID } from "node:crypto";
import { and, eq } from "drizzle-orm";
import { agentWakeupRequests, heartbeatRuns, type Db } from "@paperclipai/db";
import { accountingForScheduledRetry, executionFailureRetryCount } from "../execution-recovery-attempt.js";
import { NATIVE_PROVIDER_CAPACITY_MAX_RETRIES, NATIVE_PROVIDER_OVERLOADED_CODE, NATIVE_PROVIDER_OVERLOADED_MESSAGE } from "./native-provider-failure.js";
/** Called under the finalizer's issue/coordinator locks, in the status-effect transaction. */
export async function materializeNativeProviderCapacityRetry(input: {
tx: Db;
companyId: string;
issueId: string;
runId: string;
agentId: string;
}) {
const [run] = await input.tx.select().from(heartbeatRuns).where(and(
eq(heartbeatRuns.companyId, input.companyId), eq(heartbeatRuns.id, input.runId),
eq(heartbeatRuns.agentId, input.agentId), eq(heartbeatRuns.nativeIssueId, input.issueId),
)).for("update");
if (!run || run.runtimeMode !== "native") throw new Error("native_capacity_retry_run_binding_mismatch");
// Share the predecessor claim with every other failure-retry lane.
const [existing] = await input.tx.select().from(heartbeatRuns).where(and(
eq(heartbeatRuns.companyId, input.companyId), eq(heartbeatRuns.retryOfRunId, run.id),
)).limit(1);
if (existing) return existing.id;
const attempt = executionFailureRetryCount(run) + 1;
if (attempt > NATIVE_PROVIDER_CAPACITY_MAX_RETRIES) throw new Error("native_capacity_retry_exhausted");
const now = new Date();
const dueAt = new Date(now.getTime() + 60_000 * 2 ** (attempt - 1));
const retryId = randomUUID();
const predecessorContext = { ...run.contextSnapshot };
// Resume receipts and delivered wake input belong to the failed run. The
// new turn has ordinary task authority; history comes from retryOfRunId.
// Match the consumed-input boundary used by native safe replacements.
for (const key of [
"explicitUserContinuation", "wakeCommentId", "wakeCommentIds", "commentId",
"commentIds", "latestCommentId", "resumeIntent", "followUpRequested",
"paperclipWake", "paperclipWakeComment", "paperclipTaskMarkdown", "paperclipTaskMarkdownCompact",
"paperclipTaskMarkdownAssignment", "paperclipTaskMarkdownAssignmentCompact", "paperclipTurnContext",
]) delete predecessorContext[key];
const contextSnapshot = {
...predecessorContext,
issueId: input.issueId,
taskId: input.issueId,
forceFreshSession: true,
retryOfRunId: run.id,
retryReason: NATIVE_PROVIDER_OVERLOADED_CODE,
wakeReason: NATIVE_PROVIDER_OVERLOADED_CODE,
scheduledRetryAttempt: attempt,
scheduledRetryAt: dueAt.toISOString(),
executionRetryAccounting: accountingForScheduledRetry(run, NATIVE_PROVIDER_OVERLOADED_CODE, attempt),
};
const [wake] = await input.tx.insert(agentWakeupRequests).values({
companyId: run.companyId, agentId: run.agentId, source: "automation", triggerDetail: "system",
reason: NATIVE_PROVIDER_OVERLOADED_CODE, status: "queued", runId: retryId,
idempotencyKey: `native-capacity:${run.companyId}:${run.id}`,
requestedByActorType: "system", requestedByActorId: "native_finalizer",
payload: contextSnapshot,
}).returning({ id: agentWakeupRequests.id });
await input.tx.insert(heartbeatRuns).values({
id: retryId, companyId: run.companyId, agentId: run.agentId,
invocationSource: "automation", triggerDetail: "system", status: "scheduled_retry",
responsibleUserId: run.responsibleUserId, wakeupRequestId: wake.id,
retryOfRunId: run.id, scheduledRetryReason: NATIVE_PROVIDER_OVERLOADED_CODE,
scheduledRetryAttempt: attempt, scheduledRetryAt: dueAt,
error: NATIVE_PROVIDER_OVERLOADED_MESSAGE, errorCode: NATIVE_PROVIDER_OVERLOADED_CODE,
contextSnapshot,
});
return retryId;
}