Files
PaperClipAI/server/src/services/native-runtime/native-provider-failure-evidence.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

53 lines
3.0 KiB
TypeScript

import { and, desc, eq, sql } from "drizzle-orm";
import { heartbeatRunEvents, heartbeatRuns, type Db } from "@paperclipai/db";
import { parseNativeExecutionInput, validatePrpEvent, type PrpTerminalState } from "../../vendor/paperclip-runner/index.js";
import { nativeSha256 } from "./canonical.js";
import { createNativeProviderFailureObservation } from "./native-provider-failure.js";
function record(value: unknown): Record<string, unknown> {
return value !== null && typeof value === "object" && !Array.isArray(value)
? value as Record<string, unknown> : {};
}
/** Re-derive authority from immutable run-bound evidence, including after restart. */
export async function readPersistedNativeProviderFailure(
db: Db,
run: typeof heartbeatRuns.$inferSelect,
turnId: string | null,
terminal: PrpTerminalState,
) {
if (run.runtimeMode !== "native" || !turnId || !run.nativeSessionId || !run.runnerInstanceId ||
terminal.turnTerminalState !== "failed" || terminal.runTerminalState !== "failed") return null;
let execution;
try { execution = parseNativeExecutionInput(record(run.runnerProfileJson).nativeExecutionInput); } catch { return null; }
if (execution.provider.kind !== "codex" ||
execution.binding.runId !== run.id || execution.binding.companyId !== run.companyId ||
execution.binding.agentId !== run.agentId || execution.binding.issueId !== run.nativeIssueId ||
execution.session.normalizedSessionId !== run.nativeSessionId ||
execution.completionContract.id !== run.completionContractId ||
execution.completionContract.sha256 !== run.completionContractSha256) return null;
const [row] = await db.select().from(heartbeatRunEvents).where(and(
eq(heartbeatRunEvents.companyId, run.companyId), eq(heartbeatRunEvents.runId, run.id),
eq(heartbeatRunEvents.sourceInstanceId, run.runnerInstanceId), eq(heartbeatRunEvents.eventType, "turn.failed"),
sql`${heartbeatRunEvents.payload}->'prpEvent'->>'turnId' = ${turnId}`,
)).orderBy(desc(heartbeatRunEvents.seq)).limit(1);
if (!row) return null;
const parsed = validatePrpEvent(record(row.payload).prpEvent);
if (!parsed.ok || parsed.event.runId !== run.id || parsed.event.normalizedSessionId !== run.nativeSessionId ||
parsed.event.sourceKind !== "runner" || parsed.event.sourceInstanceId !== run.runnerInstanceId ||
parsed.event.sourceEventId !== row.sourceEventId || parsed.event.sourceSeq !== row.sourceSeq ||
parsed.event.eventType !== row.eventType || parsed.event.turnId !== turnId ||
row.sourcePayloadSha256 !== nativeSha256(parsed.event)) return null;
const observed = createNativeProviderFailureObservation(execution.provider);
observed.observe(parsed.event);
return observed.forTerminal(turnId, terminal);
}
export async function readPersistedNativeModelRejection(
...args: Parameters<typeof readPersistedNativeProviderFailure>
) {
const failure = await readPersistedNativeProviderFailure(...args);
return failure?.errorCode === "native_provider_model_rejected" ? failure : null;
}