Files
paperclip/server/src/adapters/codex-models.ts
T
Dotta 8f1cd0474f [codex] Improve transient recovery and Codex model refresh (#4383)
## 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>
2026-04-24 09:40:40 -05:00

114 lines
3.5 KiB
TypeScript

import type { AdapterModel } from "./types.js";
import { models as codexFallbackModels } from "@paperclipai/adapter-codex-local";
import { readConfigFile } from "../config-file.js";
const OPENAI_MODELS_ENDPOINT = "https://api.openai.com/v1/models";
const OPENAI_MODELS_TIMEOUT_MS = 5000;
const OPENAI_MODELS_CACHE_TTL_MS = 60_000;
let cached: { keyFingerprint: string; expiresAt: number; models: AdapterModel[] } | null = null;
function fingerprint(apiKey: string): string {
return `${apiKey.length}:${apiKey.slice(-6)}`;
}
function dedupeModels(models: AdapterModel[]): AdapterModel[] {
const seen = new Set<string>();
const deduped: AdapterModel[] = [];
for (const model of models) {
const id = model.id.trim();
if (!id || seen.has(id)) continue;
seen.add(id);
deduped.push({ id, label: model.label.trim() || id });
}
return deduped;
}
function mergedWithFallback(models: AdapterModel[]): AdapterModel[] {
return dedupeModels([
...models,
...codexFallbackModels,
]).sort((a, b) => a.id.localeCompare(b.id, "en", { numeric: true, sensitivity: "base" }));
}
function resolveOpenAiApiKey(): string | null {
const envKey = process.env.OPENAI_API_KEY?.trim();
if (envKey) return envKey;
const config = readConfigFile();
if (config?.llm?.provider !== "openai") return null;
const configKey = config.llm.apiKey?.trim();
return configKey && configKey.length > 0 ? configKey : null;
}
async function fetchOpenAiModels(apiKey: string): Promise<AdapterModel[]> {
const controller = new AbortController();
const timeout = setTimeout(() => controller.abort(), OPENAI_MODELS_TIMEOUT_MS);
try {
const response = await fetch(OPENAI_MODELS_ENDPOINT, {
headers: {
Authorization: `Bearer ${apiKey}`,
},
signal: controller.signal,
});
if (!response.ok) return [];
const payload = (await response.json()) as { data?: unknown };
const data = Array.isArray(payload.data) ? payload.data : [];
const models: AdapterModel[] = [];
for (const item of data) {
if (typeof item !== "object" || item === null) continue;
const id = (item as { id?: unknown }).id;
if (typeof id !== "string" || id.trim().length === 0) continue;
models.push({ id, label: id });
}
return dedupeModels(models);
} catch {
return [];
} finally {
clearTimeout(timeout);
}
}
async function loadCodexModels(options?: { forceRefresh?: boolean }): Promise<AdapterModel[]> {
const forceRefresh = options?.forceRefresh === true;
const apiKey = resolveOpenAiApiKey();
const fallback = dedupeModels(codexFallbackModels);
if (!apiKey) return fallback;
const now = Date.now();
const keyFingerprint = fingerprint(apiKey);
if (!forceRefresh && cached && cached.keyFingerprint === keyFingerprint && cached.expiresAt > now) {
return cached.models;
}
const fetched = await fetchOpenAiModels(apiKey);
if (fetched.length > 0) {
const merged = mergedWithFallback(fetched);
cached = {
keyFingerprint,
expiresAt: now + OPENAI_MODELS_CACHE_TTL_MS,
models: merged,
};
return merged;
}
if (cached && cached.keyFingerprint === keyFingerprint && cached.models.length > 0) {
return cached.models;
}
return fallback;
}
export async function listCodexModels(): Promise<AdapterModel[]> {
return loadCodexModels();
}
export async function refreshCodexModels(): Promise<AdapterModel[]> {
return loadCodexModels({ forceRefresh: true });
}
export function resetCodexModelsCacheForTests() {
cached = null;
}