mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-23 00:53:38 +02:00
## 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>
87 lines
5.3 KiB
TypeScript
87 lines
5.3 KiB
TypeScript
import { describe, expect, it } from "vitest";
|
|
import type { PrpEvent, PrpTerminalState } from "../../vendor/paperclip-runner/index.js";
|
|
import { createNativeProviderFailureObservation, NATIVE_MODEL_REJECTION_DIAGNOSTIC, NATIVE_MODEL_REJECTION_MESSAGE, NATIVE_PROVIDER_OVERLOADED_MESSAGE } from "./native-provider-failure.js";
|
|
|
|
const model = "test-model";
|
|
const response = {
|
|
type: "error", status: 400,
|
|
error: { type: "invalid_request_error", message: `The '${model}' model is not supported when using Codex with a ChatGPT account.` },
|
|
};
|
|
const event: PrpEvent = {
|
|
schema: "paperclip.prp.event.v1", runId: "run", normalizedSessionId: "session", turnId: "turn",
|
|
sourceInstanceId: "runner", sourceEventId: "failure", sourceSeq: 1, sourceKind: "runner",
|
|
eventType: "turn.failed", schemaVersion: 1, priority: 0, emittedAt: "2026-01-01T00:00:00.000Z",
|
|
payload: { status: "failed", error: { message: JSON.stringify(response), codexErrorInfo: "other" } },
|
|
};
|
|
const terminal: PrpTerminalState = {
|
|
schema: "paperclip.prp.terminal.v1", turnTerminalState: "failed", runTerminalState: "failed", reportedWorkDisposition: "blocked",
|
|
};
|
|
const observation = () => createNativeProviderFailureObservation({ kind: "codex", model });
|
|
|
|
describe("native provider failure observation", () => {
|
|
it("surfaces a structured capacity failure without copying arbitrary provider text", () => {
|
|
const observed = createNativeProviderFailureObservation({ kind: "codex" });
|
|
observed.observe({ ...event, payload: { status: "failed", error: { codexErrorInfo: "serverOverloaded", message: "Private arbitrary response" } } });
|
|
expect(observed.forTerminal("turn", terminal)).toEqual({ errorCode: "native_provider_overloaded", errorMessage: NATIVE_PROVIDER_OVERLOADED_MESSAGE, diagnostic: { provider: "codex", category: "server_overloaded" } });
|
|
expect(observed.forTerminal("different-turn", terminal)).toBeNull();
|
|
expect(observed.forTerminal("turn", { ...terminal, runTerminalState: "succeeded" })).toBeNull();
|
|
});
|
|
|
|
it.each(["usageLimitExceeded", "other", "unauthorized", undefined])("does not retry unrelated provider errors (%s)", (codexErrorInfo) => {
|
|
const observed = observation();
|
|
observed.observe({ ...event, payload: { status: "failed", error: { codexErrorInfo, message: NATIVE_PROVIDER_OVERLOADED_MESSAGE } } });
|
|
expect(observed.forTerminal("turn", terminal)).toBeNull();
|
|
});
|
|
it("binds the structured rejection to the failed turn and emits no response or model text", () => {
|
|
const observed = observation();
|
|
observed.observe(event);
|
|
observed.observe(event); // A byte-identical committed replay remains idempotent.
|
|
const result = observed.forTerminal("turn", terminal);
|
|
expect(result).toEqual({ errorCode: "native_provider_model_rejected", errorMessage: NATIVE_MODEL_REJECTION_MESSAGE, diagnostic: NATIVE_MODEL_REJECTION_DIAGNOSTIC });
|
|
expect(JSON.stringify(result)).not.toContain(model);
|
|
expect(JSON.stringify(result)).not.toContain("invalid_request_error");
|
|
expect(observed.forTerminal("later-turn", terminal)).toBeNull();
|
|
expect(observed.forTerminal(null, terminal)).toBeNull();
|
|
expect(observed.forTerminal("turn", { ...terminal, runTerminalState: "succeeded" })).toBeNull();
|
|
expect(observed.forTerminal("turn", { ...terminal, turnTerminalState: "cancelled" })).toBeNull();
|
|
});
|
|
|
|
it.each([
|
|
{ ...event, sourceKind: "control_plane" as const },
|
|
{ ...event, eventType: "item.completed" as const },
|
|
{ ...event, eventType: "harness.diagnostic" as const },
|
|
{ ...event, turnId: undefined },
|
|
{ ...event, payload: { ...event.payload, status: "completed" } },
|
|
{ ...event, payload: { ...event.payload, recoverable: true } },
|
|
{ ...event, payload: { status: "failed", error: { message: JSON.stringify(response), recoverable: true } } },
|
|
])("ignores non-authoritative or retryable evidence %#", (unrelated) => {
|
|
const observed = observation();
|
|
observed.observe(unrelated);
|
|
expect(observed.forTerminal("turn", terminal)).toBeNull();
|
|
});
|
|
|
|
it.each([
|
|
response.error.message, "malformed JSON", " ".repeat(4_097),
|
|
JSON.stringify({ ...response, status: 401 }),
|
|
JSON.stringify({ ...response, status: "400" }),
|
|
JSON.stringify({ ...response, type: "notice" }),
|
|
JSON.stringify({ ...response, error: { ...response.error, type: "server_error" } }),
|
|
JSON.stringify({ ...response, error: { ...response.error, message: "Private arbitrary provider text" } }),
|
|
JSON.stringify({ ...response, error: { ...response.error, message: response.error.message + " Private suffix" } }),
|
|
JSON.stringify({ ...response, error: { ...response.error, message: response.error.message.replace(model, "another-model") } }),
|
|
JSON.stringify([response]), "null",
|
|
])("leaves unknown failures unchanged %#", (message) => {
|
|
const observed = observation();
|
|
observed.observe({ ...event, payload: { status: "failed", error: { message } } });
|
|
expect(observed.forTerminal("turn", terminal)).toBeNull();
|
|
});
|
|
|
|
it.each([{ kind: "claude", model }, { kind: "codex" }, { kind: "codex", model: "other" }])(
|
|
"does not apply a rejection to another selected provider/model (%j)", (provider) => {
|
|
const observed = createNativeProviderFailureObservation(provider);
|
|
observed.observe(event);
|
|
expect(observed.forTerminal("turn", terminal)).toBeNull();
|
|
},
|
|
);
|
|
});
|