diff --git a/packages/adapters/opencode-local/src/server/models.test.ts b/packages/adapters/opencode-local/src/server/models.test.ts index 71748e3792..b4fde5986a 100644 --- a/packages/adapters/opencode-local/src/server/models.test.ts +++ b/packages/adapters/opencode-local/src/server/models.test.ts @@ -1,5 +1,7 @@ -import { afterEach, describe, expect, it } from "vitest"; +import { afterEach, describe, expect, it, vi } from "vitest"; +import * as serverUtils from "@paperclipai/adapter-utils/server-utils"; import { + discoverOpenCodeModels, ensureOpenCodeModelConfiguredAndAvailable, listOpenCodeModels, requireOpenCodeModelId, @@ -11,6 +13,8 @@ describe("openCode models", () => { delete process.env.PAPERCLIP_OPENCODE_COMMAND; delete process.env.OPENCODE_ALLOW_ALL_MODELS; resetOpenCodeModelsCacheForTests(); + vi.restoreAllMocks(); + vi.useRealTimers(); }); it("returns an empty list when discovery command is unavailable", async () => { @@ -74,4 +78,68 @@ describe("openCode models", () => { }), ).rejects.toThrow("OpenCode requires `adapterConfig.model`"); }); + + it("retries a transient `opencode models` failure with backoff before succeeding", async () => { + vi.useFakeTimers(); + const spy = vi + .spyOn(serverUtils, "runChildProcess") + .mockResolvedValueOnce({ + exitCode: 1, + signal: null, + timedOut: false, + stdout: "", + stderr: "queued behind another opencode run", + pid: 1, + startedAt: new Date().toISOString(), + }) + .mockResolvedValueOnce({ + exitCode: null, + signal: null, + timedOut: true, + stdout: "", + stderr: "", + pid: 1, + startedAt: new Date().toISOString(), + }) + .mockResolvedValueOnce({ + exitCode: 0, + signal: null, + timedOut: false, + stdout: "ollama/qwen2.5-coder:7b\n", + stderr: "", + pid: 1, + startedAt: new Date().toISOString(), + }); + + const promise = discoverOpenCodeModels(); + await vi.runAllTimersAsync(); + + await expect(promise).resolves.toEqual([ + { id: "ollama/qwen2.5-coder:7b", label: "ollama/qwen2.5-coder:7b" }, + ]); + expect(spy).toHaveBeenCalledTimes(3); + }); + + it("surfaces the last error once retries are exhausted", async () => { + vi.useFakeTimers(); + const spy = vi + .spyOn(serverUtils, "runChildProcess") + .mockResolvedValue({ + exitCode: 1, + signal: null, + timedOut: false, + stdout: "", + stderr: "queued behind another opencode run", + pid: 1, + startedAt: new Date().toISOString(), + }); + + const promise = discoverOpenCodeModels(); + const assertion = expect(promise).rejects.toThrow( + "`opencode models` failed: queued behind another opencode run", + ); + await vi.runAllTimersAsync(); + await assertion; + expect(spy).toHaveBeenCalledTimes(3); + }); }); diff --git a/packages/adapters/opencode-local/src/server/models.ts b/packages/adapters/opencode-local/src/server/models.ts index 172a5ce242..5af8c203c9 100644 --- a/packages/adapters/opencode-local/src/server/models.ts +++ b/packages/adapters/opencode-local/src/server/models.ts @@ -10,6 +10,15 @@ import { isValidOpenCodeModelId } from "../index.js"; const MODELS_CACHE_TTL_MS = 60_000; const MODELS_DISCOVERY_TIMEOUT_MS = 20_000; +// `opencode models` is a lightweight metadata call, but on a shared ollama +// daemon it can queue behind an in-flight `opencode run` generation on the +// same host and either time out or fail with an opaque error. Retry a few +// times with backoff before surfacing a hard failure (SAG-6326/SAG-6336). +const MODELS_DISCOVERY_RETRY_DELAYS_MS = [2_000, 4_000]; + +function sleep(ms: number): Promise { + return new Promise((resolve) => setTimeout(resolve, ms)); +} function resolveOpenCodeCommand(input: unknown): string { const envOverride = @@ -132,28 +141,38 @@ export async function discoverOpenCodeModels(input: { // Prevent OpenCode from writing an opencode.json into the working directory. const runtimeEnv = normalizeEnv(ensurePathInEnv({ ...process.env, ...env, ...(resolvedHome ? { HOME: resolvedHome } : {}), OPENCODE_DISABLE_PROJECT_CONFIG: "true" })); - const result = await runChildProcess( - `opencode-models-${Date.now()}-${Math.random().toString(16).slice(2)}`, - command, - ["models"], - { - cwd, - env: runtimeEnv, - timeoutSec: MODELS_DISCOVERY_TIMEOUT_MS / 1000, - graceSec: 3, - onLog: async () => {}, - }, - ); + const maxAttempts = MODELS_DISCOVERY_RETRY_DELAYS_MS.length + 1; + let lastError: Error | undefined; - if (result.timedOut) { - throw new Error(`\`opencode models\` timed out after ${MODELS_DISCOVERY_TIMEOUT_MS / 1000}s.`); - } - if ((result.exitCode ?? 1) !== 0) { - const detail = firstNonEmptyLine(result.stderr) || firstNonEmptyLine(result.stdout); - throw new Error(detail ? `\`opencode models\` failed: ${detail}` : "`opencode models` failed."); + for (let attempt = 1; attempt <= maxAttempts; attempt++) { + const result = await runChildProcess( + `opencode-models-${Date.now()}-${Math.random().toString(16).slice(2)}`, + command, + ["models"], + { + cwd, + env: runtimeEnv, + timeoutSec: MODELS_DISCOVERY_TIMEOUT_MS / 1000, + graceSec: 3, + onLog: async () => {}, + }, + ); + + if (result.timedOut) { + lastError = new Error(`\`opencode models\` timed out after ${MODELS_DISCOVERY_TIMEOUT_MS / 1000}s.`); + } else if ((result.exitCode ?? 1) !== 0) { + const detail = firstNonEmptyLine(result.stderr) || firstNonEmptyLine(result.stdout); + lastError = new Error(detail ? `\`opencode models\` failed: ${detail}` : "`opencode models` failed."); + } else { + return sortModels(parseOpenCodeModelsOutput(result.stdout)); + } + + const delayMs = MODELS_DISCOVERY_RETRY_DELAYS_MS[attempt - 1]; + if (delayMs === undefined) break; + await sleep(delayMs); } - return sortModels(parseOpenCodeModelsOutput(result.stdout)); + throw lastError ?? new Error("`opencode models` failed."); } export async function discoverOpenCodeModelsCached(input: { diff --git a/server/src/__tests__/opencode-local-adapter-environment.test.ts b/server/src/__tests__/opencode-local-adapter-environment.test.ts index 736dd9f8e5..234c300d46 100644 --- a/server/src/__tests__/opencode-local-adapter-environment.test.ts +++ b/server/src/__tests__/opencode-local-adapter-environment.test.ts @@ -57,7 +57,7 @@ describe("opencode_local environment diagnostics", () => { } await fs.rm(cwd, { recursive: true, force: true }); } - }); + }, 10_000); it("classifies ProviderModelNotFoundError probe output as model-unavailable warning", async () => { const cwd = await fs.mkdtemp(path.join(os.tmpdir(), "paperclip-opencode-env-probe-cwd-")); @@ -92,5 +92,5 @@ describe("opencode_local environment diagnostics", () => { await fs.rm(cwd, { recursive: true, force: true }); await fs.rm(binDir, { recursive: true, force: true }); } - }); + }, 10_000); });