Files
paperclip/server/src/__tests__/adapter-models.test.ts
T
Dotta 5153b01ada [codex] Add Claude model refresh (#6953)
## Thinking Path

> - Paperclip orchestrates AI-agent companies through adapter-backed
local and external runtimes.
> - The agent configuration UI lets operators choose adapter models and
refresh model lists when adapters support live discovery.
> - Codex already had a live refresh path, but Claude Local only exposed
static fallback models and the UI hid the refresh action for Claude.
> - A newly available Claude Opus model should not require a code
release every time the model catalog changes.
> - This pull request adds Anthropic model discovery for Claude Local,
keeps the static fallback current with Claude Opus 4.8, and exposes the
existing refresh button in the Claude Local dropdown.
> - The benefit is that operators can refresh Claude models from the
same model selector flow they already use for Codex.

## What Changed

- Added `claude-opus-4-8` to the Claude Local fallback model list.
- Added Claude model discovery through Anthropic-compatible `GET
/v1/models` when `ANTHROPIC_API_KEY` is available.
- Added normal cache reuse, forced refresh support, a SHA-256-based
API-key fingerprint for cache keys, and warning logging for discovery
errors before fallback.
- Wired `claude_local.refreshModels` into the server adapter registry.
- Enabled the existing `Refresh models` dropdown action for
`claude_local` in `AgentConfigForm`.
- Added tests for Claude fallback, live discovery, API-failure fallback,
forced refresh, and the UI refresh-button gate.

## Verification

- `pnpm exec vitest run server/src/__tests__/adapter-models.test.ts`
- `pnpm exec vitest run ui/src/components/AgentConfigForm.test.ts`
- `pnpm --filter @paperclipai/adapter-claude-local typecheck`
- `pnpm --filter @paperclipai/server typecheck`
- `pnpm --filter @paperclipai/ui typecheck`
- Greptile review reached Confidence Score: 5/5 on commit `b796cf4f1`
with addressed threads resolved.

UI note: the visible change is a conditional action row inside the
existing model dropdown; the regression test covers that `claude_local`
now receives the refresh action.

## Risks

- Low risk. Without `ANTHROPIC_API_KEY`, Claude Local still uses the
static fallback list.
- If Anthropic model discovery fails or times out, Paperclip falls back
to the existing cached or static list.
- Bedrock environments remain on Bedrock-native model IDs.

## Model Used

OpenAI GPT-5 via Codex local coding agent, with repository file access,
shell command execution, git operations, and targeted test/typecheck
verification. Exact context window is not exposed by the runtime.

## 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
- [x] If this change affects the UI, I have included before/after
screenshots
- [x] 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
2026-05-29 07:03:07 -10:00

219 lines
8.0 KiB
TypeScript

import { beforeEach, describe, expect, it, vi } from "vitest";
import { models as claudeFallbackModels } from "@paperclipai/adapter-claude-local";
import { resetClaudeModelsCacheForTests } from "@paperclipai/adapter-claude-local/server";
import { models as codexFallbackModels } from "@paperclipai/adapter-codex-local";
import { models as cursorFallbackModels } from "@paperclipai/adapter-cursor-local";
import { models as opencodeFallbackModels } from "@paperclipai/adapter-opencode-local";
import { resetOpenCodeModelsCacheForTests } from "@paperclipai/adapter-opencode-local/server";
import { listAdapterModels, listServerAdapters, refreshAdapterModels } from "../adapters/index.js";
import { resetCodexModelsCacheForTests } from "../adapters/codex-models.js";
import { resetCursorModelsCacheForTests, setCursorModelsRunnerForTests } from "../adapters/cursor-models.js";
vi.mock("acpx/runtime", () => ({
createAcpRuntime: vi.fn(),
createAgentRegistry: vi.fn(),
createRuntimeStore: vi.fn(),
isAcpRuntimeError: vi.fn(() => false),
}));
describe("adapter model listing", () => {
beforeEach(() => {
delete process.env.OPENAI_API_KEY;
delete process.env.ANTHROPIC_API_KEY;
delete process.env.ANTHROPIC_BASE_URL;
delete process.env.ANTHROPIC_BEDROCK_BASE_URL;
delete process.env.CLAUDE_CODE_USE_BEDROCK;
delete process.env.PAPERCLIP_OPENCODE_COMMAND;
resetClaudeModelsCacheForTests();
resetCodexModelsCacheForTests();
resetCursorModelsCacheForTests();
setCursorModelsRunnerForTests(null);
resetOpenCodeModelsCacheForTests();
vi.restoreAllMocks();
});
it("returns an empty list for unknown adapters", async () => {
const models = await listAdapterModels("unknown_adapter");
expect(models).toEqual([]);
});
it("uses provider-prefixed ACPX fallback model labels", () => {
const adapter = listServerAdapters().find((candidate) => candidate.type === "acpx_local");
expect(adapter?.models?.some((model) => model.label.startsWith("Claude: "))).toBe(true);
expect(adapter?.models?.some((model) => model.label.startsWith("Codex: "))).toBe(true);
});
it("returns codex fallback models when no OpenAI key is available", async () => {
const fetchSpy = vi.spyOn(globalThis, "fetch");
const models = await listAdapterModels("codex_local");
expect(models).toEqual(codexFallbackModels);
expect(fetchSpy).not.toHaveBeenCalled();
});
it("returns claude fallback models including the latest Opus alias when no Anthropic key is available", async () => {
const fetchSpy = vi.spyOn(globalThis, "fetch");
const models = await listAdapterModels("claude_local");
expect(models).toEqual(claudeFallbackModels);
expect(models.some((model) => model.id === "claude-opus-4-8")).toBe(true);
expect(fetchSpy).not.toHaveBeenCalled();
});
it("loads claude models dynamically and merges fallback options", async () => {
process.env.ANTHROPIC_API_KEY = "sk-ant-test";
const fetchSpy = vi.spyOn(globalThis, "fetch").mockResolvedValue({
ok: true,
json: async () => ({
data: [
{ id: "claude-sonnet-4-20250514", display_name: "Claude Sonnet 4" },
{ id: "claude-opus-4-8-20260529", display_name: "Claude Opus 4.8" },
],
}),
} as Response);
const first = await listAdapterModels("claude_local");
const second = await listAdapterModels("claude_local");
expect(fetchSpy).toHaveBeenCalledTimes(1);
expect(first).toEqual(second);
expect(first.some((model) => model.id === "claude-opus-4-8-20260529")).toBe(true);
expect(first.some((model) => model.id === "claude-opus-4-8")).toBe(true);
});
it("refreshes cached claude models on demand", async () => {
process.env.ANTHROPIC_API_KEY = "sk-ant-test";
const fetchSpy = vi.spyOn(globalThis, "fetch")
.mockResolvedValueOnce({
ok: true,
json: async () => ({
data: [{ id: "claude-sonnet-4-20250514", display_name: "Claude Sonnet 4" }],
}),
} as Response)
.mockResolvedValueOnce({
ok: true,
json: async () => ({
data: [{ id: "claude-opus-4-8-20260529", display_name: "Claude Opus 4.8" }],
}),
} as Response);
const initial = await listAdapterModels("claude_local");
const refreshed = await refreshAdapterModels("claude_local");
expect(fetchSpy).toHaveBeenCalledTimes(2);
expect(initial.some((model) => model.id === "claude-sonnet-4-20250514")).toBe(true);
expect(refreshed.some((model) => model.id === "claude-opus-4-8-20260529")).toBe(true);
});
it("falls back to static claude models when Anthropic model discovery fails", async () => {
process.env.ANTHROPIC_API_KEY = "sk-ant-test";
vi.spyOn(globalThis, "fetch").mockResolvedValue({
ok: false,
status: 401,
json: async () => ({}),
} as Response);
const models = await listAdapterModels("claude_local");
expect(models).toEqual(claudeFallbackModels);
});
it("loads codex models dynamically and merges fallback options", async () => {
process.env.OPENAI_API_KEY = "sk-test";
const fetchSpy = vi.spyOn(globalThis, "fetch").mockResolvedValue({
ok: true,
json: async () => ({
data: [
{ id: "gpt-5-pro" },
{ id: "gpt-5" },
],
}),
} as Response);
const first = await listAdapterModels("codex_local");
const second = await listAdapterModels("codex_local");
expect(fetchSpy).toHaveBeenCalledTimes(1);
expect(first).toEqual(second);
expect(first.some((model) => model.id === "gpt-5-pro")).toBe(true);
expect(first.some((model) => model.id === "codex-mini-latest")).toBe(true);
});
it("refreshes cached codex models on demand", async () => {
process.env.OPENAI_API_KEY = "sk-test";
const fetchSpy = vi.spyOn(globalThis, "fetch")
.mockResolvedValueOnce({
ok: true,
json: async () => ({
data: [{ id: "gpt-5" }],
}),
} as Response)
.mockResolvedValueOnce({
ok: true,
json: async () => ({
data: [{ id: "gpt-5.5" }],
}),
} as Response);
const initial = await listAdapterModels("codex_local");
const refreshed = await refreshAdapterModels("codex_local");
expect(fetchSpy).toHaveBeenCalledTimes(2);
expect(initial.some((model) => model.id === "gpt-5")).toBe(true);
expect(refreshed.some((model) => model.id === "gpt-5.5")).toBe(true);
});
it("falls back to static codex models when OpenAI model discovery fails", async () => {
process.env.OPENAI_API_KEY = "sk-test";
vi.spyOn(globalThis, "fetch").mockResolvedValue({
ok: false,
status: 401,
json: async () => ({}),
} as Response);
const models = await listAdapterModels("codex_local");
expect(models).toEqual(codexFallbackModels);
});
it("returns cursor fallback models when CLI discovery is unavailable", async () => {
setCursorModelsRunnerForTests(() => ({
status: null,
stdout: "",
stderr: "",
hasError: true,
}));
const models = await listAdapterModels("cursor");
expect(models).toEqual(cursorFallbackModels);
});
it("returns opencode fallback models including gpt-5.4", async () => {
process.env.PAPERCLIP_OPENCODE_COMMAND = "__paperclip_missing_opencode_command__";
const models = await listAdapterModels("opencode_local");
expect(models).toEqual(opencodeFallbackModels);
});
it("loads cursor models dynamically and caches them", async () => {
const runner = vi.fn(() => ({
status: 0,
stdout: "Available models: auto, composer-1.5, gpt-5.3-codex-high, sonnet-4.6",
stderr: "",
hasError: false,
}));
setCursorModelsRunnerForTests(runner);
const first = await listAdapterModels("cursor");
const second = await listAdapterModels("cursor");
expect(runner).toHaveBeenCalledTimes(1);
expect(first).toEqual(second);
expect(first.some((model) => model.id === "auto")).toBe(true);
expect(first.some((model) => model.id === "gpt-5.3-codex-high")).toBe(true);
expect(first.some((model) => model.id === "composer-1")).toBe(true);
});
});