forked from farhoodlabs/paperclip
8f1cd0474f
## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Adapter execution and retry classification decide whether agent work pauses, retries, or recovers automatically > - Transient provider failures need to be classified precisely so Paperclip does not convert retryable upstream conditions into false hard failures > - At the same time, operators need an up-to-date model list for Codex-backed agents and prompts should nudge agents toward targeted verification instead of repo-wide sweeps > - This pull request tightens transient recovery classification for Claude and Codex, updates the agent prompt guidance, and adds Codex model refresh support end-to-end > - The benefit is better automatic retry behavior plus fresher operator-facing model configuration ## What Changed - added Codex usage-limit retry-window parsing and Claude extra-usage transient classification - normalized the heartbeat transient-recovery contract across adapter executions and heartbeat scheduling - documented that deferred comment wakes only reopen completed issues for human/comment-reopen interactions, while system follow-ups leave closed work closed - updated adapter-utils prompt guidance to prefer targeted verification - added Codex model refresh support in the server route, registry, shared types, and agent config form - added adapter/server tests covering the new parsing, retry scheduling, and model-refresh behavior ## Verification - `pnpm exec vitest run --project @paperclipai/adapter-utils packages/adapter-utils/src/server-utils.test.ts` - `pnpm exec vitest run --project @paperclipai/adapter-claude-local packages/adapters/claude-local/src/server/parse.test.ts` - `pnpm exec vitest run --project @paperclipai/adapter-codex-local packages/adapters/codex-local/src/server/parse.test.ts` - `pnpm exec vitest run --project @paperclipai/server server/src/__tests__/adapter-model-refresh-routes.test.ts server/src/__tests__/adapter-models.test.ts server/src/__tests__/claude-local-execute.test.ts server/src/__tests__/codex-local-execute.test.ts server/src/__tests__/heartbeat-process-recovery.test.ts server/src/__tests__/heartbeat-retry-scheduling.test.ts` ## Risks - Moderate behavior risk: retry classification affects whether runs auto-recover or block, so mistakes here could either suppress needed retries or over-retry real failures - Low workflow risk: deferred comment wake reopening is intentionally scoped to human/comment-reopen interactions so system follow-ups do not revive completed issues unexpectedly > For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and discuss it in `#dev` before opening the PR. Feature PRs that overlap with planned core work may need to be redirected — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used - OpenAI Codex GPT-5-based coding agent with tool use and code execution in the Codex CLI environment ## 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 run tests locally and they pass - [x] I have added or updated tests where applicable - [ ] If this change affects the UI, I have included before/after screenshots - [ ] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
141 lines
4.8 KiB
TypeScript
141 lines
4.8 KiB
TypeScript
import { describe, expect, it } from "vitest";
|
||
import {
|
||
extractCodexRetryNotBefore,
|
||
isCodexTransientUpstreamError,
|
||
isCodexUnknownSessionError,
|
||
parseCodexJsonl,
|
||
} from "./parse.js";
|
||
|
||
describe("parseCodexJsonl", () => {
|
||
it("captures session id, assistant summary, usage, and error message", () => {
|
||
const stdout = [
|
||
JSON.stringify({ type: "thread.started", thread_id: "thread_123" }),
|
||
JSON.stringify({
|
||
type: "item.completed",
|
||
item: { type: "agent_message", text: "Recovered response" },
|
||
}),
|
||
JSON.stringify({
|
||
type: "turn.completed",
|
||
usage: { input_tokens: 10, cached_input_tokens: 2, output_tokens: 4 },
|
||
}),
|
||
JSON.stringify({ type: "turn.failed", error: { message: "resume failed" } }),
|
||
].join("\n");
|
||
|
||
expect(parseCodexJsonl(stdout)).toEqual({
|
||
sessionId: "thread_123",
|
||
summary: "Recovered response",
|
||
usage: {
|
||
inputTokens: 10,
|
||
cachedInputTokens: 2,
|
||
outputTokens: 4,
|
||
},
|
||
errorMessage: "resume failed",
|
||
});
|
||
});
|
||
|
||
it("uses the last agent message as the summary when commentary updates precede the final answer", () => {
|
||
const stdout = [
|
||
JSON.stringify({ type: "thread.started", thread_id: "thread_123" }),
|
||
JSON.stringify({
|
||
type: "item.completed",
|
||
item: { type: "reasoning", text: "Checking the heartbeat procedure" },
|
||
}),
|
||
JSON.stringify({
|
||
type: "item.completed",
|
||
item: { type: "agent_message", text: "I’m checking out the issue and reading the docs now." },
|
||
}),
|
||
JSON.stringify({
|
||
type: "item.completed",
|
||
item: { type: "agent_message", text: "Fixed the issue and verified the targeted tests pass." },
|
||
}),
|
||
JSON.stringify({
|
||
type: "turn.completed",
|
||
usage: { input_tokens: 10, cached_input_tokens: 2, output_tokens: 4 },
|
||
}),
|
||
].join("\n");
|
||
|
||
expect(parseCodexJsonl(stdout)).toEqual({
|
||
sessionId: "thread_123",
|
||
summary: "Fixed the issue and verified the targeted tests pass.",
|
||
usage: {
|
||
inputTokens: 10,
|
||
cachedInputTokens: 2,
|
||
outputTokens: 4,
|
||
},
|
||
errorMessage: null,
|
||
});
|
||
});
|
||
});
|
||
|
||
describe("isCodexUnknownSessionError", () => {
|
||
it("detects the current missing-rollout thread error", () => {
|
||
expect(
|
||
isCodexUnknownSessionError(
|
||
"",
|
||
"Error: thread/resume: thread/resume failed: no rollout found for thread id d448e715-7607-4bcc-91fc-7a3c0c5a9632",
|
||
),
|
||
).toBe(true);
|
||
});
|
||
|
||
it("still detects existing stale-session wordings", () => {
|
||
expect(isCodexUnknownSessionError("unknown thread id", "")).toBe(true);
|
||
expect(isCodexUnknownSessionError("", "state db missing rollout path for thread abc")).toBe(true);
|
||
});
|
||
|
||
it("does not classify unrelated Codex failures as stale sessions", () => {
|
||
expect(isCodexUnknownSessionError("", "model overloaded")).toBe(false);
|
||
});
|
||
});
|
||
|
||
describe("isCodexTransientUpstreamError", () => {
|
||
it("classifies the remote-compaction high-demand failure as transient upstream", () => {
|
||
expect(
|
||
isCodexTransientUpstreamError({
|
||
errorMessage:
|
||
"Error running remote compact task: We're currently experiencing high demand, which may cause temporary errors.",
|
||
}),
|
||
).toBe(true);
|
||
expect(
|
||
isCodexTransientUpstreamError({
|
||
stderr: "We're currently experiencing high demand, which may cause temporary errors.",
|
||
}),
|
||
).toBe(true);
|
||
});
|
||
|
||
it("classifies usage-limit windows as transient and extracts the retry time", () => {
|
||
const errorMessage = "You've hit your usage limit for GPT-5.3-Codex-Spark. Switch to another model now, or try again at 11:31 PM.";
|
||
const now = new Date(2026, 3, 22, 22, 29, 2);
|
||
|
||
expect(isCodexTransientUpstreamError({ errorMessage })).toBe(true);
|
||
expect(extractCodexRetryNotBefore({ errorMessage }, now)?.getTime()).toBe(
|
||
new Date(2026, 3, 22, 23, 31, 0, 0).getTime(),
|
||
);
|
||
});
|
||
|
||
it("parses explicit timezone hints on usage-limit retry windows", () => {
|
||
const errorMessage = "You've hit your usage limit for GPT-5.3-Codex-Spark. Switch to another model now, or try again at 11:31 PM (America/Chicago).";
|
||
const now = new Date("2026-04-23T03:29:02.000Z");
|
||
|
||
expect(extractCodexRetryNotBefore({ errorMessage }, now)?.toISOString()).toBe(
|
||
"2026-04-23T04:31:00.000Z",
|
||
);
|
||
});
|
||
|
||
it("does not classify deterministic compaction errors as transient", () => {
|
||
expect(
|
||
isCodexTransientUpstreamError({
|
||
errorMessage: [
|
||
"Error running remote compact task: {",
|
||
' "error": {',
|
||
' "message": "Unknown parameter: \'prompt_cache_retention\'.",',
|
||
' "type": "invalid_request_error",',
|
||
' "param": "prompt_cache_retention",',
|
||
' "code": "unknown_parameter"',
|
||
" }",
|
||
"}",
|
||
].join("\n"),
|
||
}),
|
||
).toBe(false);
|
||
});
|
||
});
|