Files
openclaw/src/system-agent/inference-fallback.test.ts
T
Peter Steinberger 82d1a03f25 refactor(agents): move implicit-main fallback into load-time roster injection (#112678)
* refactor(agents): require explicit roster defaults

* feat(onboard): create named first roster agent

* refactor(agents): remove runtime main fallbacks

* style(agents): apply roster refactor formatting

* refactor(agents): finish roster-only runtime sweep

* fix(doctor): migrate legacy main session sqlite

* fix(doctor): harden roster session migrations

* fix(onboard): commit first agent atomically

* fix(config): support empty-roster analysis

* fix(agents): preserve legacy main state during creation

* fix(setup): materialize baseline agent roster

* fix(agents): harden legacy default transfer recovery

* fix(agents): simplify roster-only legacy compatibility

* fix(agents): preserve staged first-agent entries

* fix(config): migrate persisted implicit-main rosters

* fix(config): preserve staged empty rosters

* fix(agents): finalize roster-only upgrade paths

* fix(sessions): close legacy main migration outcomes

* fix(config): migrate legacy roster markers at load

* fix(sessions): preserve roster upgrade history

* refactor(sessions): restore lean legacy main compatibility

* fix(setup): prepare first-agent credentials before publish

* fix(config): stabilize roster snapshot migration

* refactor(sessions): shrink legacy main compatibility

* fix(agents): restore roster compatibility fidelity

* fix(sessions): preserve divergent legacy history

* refactor(agents): narrow roster-only scope

* fix(config): isolate roster migration

* test(agents): align roster-only fixtures

* fix(agents): keep main agent undeletable

* fix(agents): harden roster migration invariants

* fix(agents): close setup and audit scope gaps

* fix(cron): scope session reaper throttles by agent

* fix(agents): preserve scoped owner precedence

* fix(config): preserve authored config ownership

* fix(setup): keep default workspace and roster in sync

* fix(setup): preserve default entry workspace on bare runs

* fix(agents): adapt roster rebase to keyed entries

* fix(agents): honor both roster representations

* fix(agents): route roster reads through shared helpers

* fix(config): preserve canonical roster writes

* fix(cron): resolve dynamic default for session reaper

* fix(agents): close dynamic default migration gaps

* fix(agents): align scoped session ownership

* fix(sessions): preserve legacy main directory casing

* fix(agents): align cron and legacy auth ownership

* fix(setup): provision the committed default workspace

* fix(cron): align scoped ownership and reaping

* fix(cron): treat blank agent ids as absent

* fix(cron): retain configured session-store owners

* fix(agents): repair roster-aware CI boundaries

* fix(cron): preserve scoped ownership resolution

* fix(agents): preserve rosterless maintenance paths

* fix(agents): propagate roster ownership through runtime boundaries

* fix(agents): preserve roster ownership across runtime paths

* fix(agents): harden roster diagnostics and legacy routing

* fix(agents): remove redundant diagnostic import

* test(agents): type CLI policy fixture explicitly

* fix(config): preserve canonical roster mutation identity

* fix(doctor): read canonical agent rosters consistently

* fix(config): resolve compound roster unsets safely

* fix(config): finalize main-session reconciliation

* fix(doctor): read canonical session state safely

* fix(sessions): preserve current visibility alias

* fix(config): track roster include provenance

* test(config): type roster provenance cases

* fix(config): refine roster include ownership

* fix(agents): preserve staged roster invariants

* test(config): align fixtures with explicit roster ownership

* test(node-host): preserve optional plan typing

* fix(config): preserve authored roster projections

* test(config): keep raw roster fixtures explicit

* test(config): normalize rosters at runtime fixtures

* fix(config): protect authored roster ownership

* fix(agents): require explicit session ownership

* fix(agents): enforce scoped roster ownership

* fix(sessions): merge fixed-store agent partitions

* fix(agents): harden roster ownership boundaries

* fix(config): reject ambiguous roster projections

* fix(sessions): preserve persisted store ownership

* fix(sessions): keep collision diagnostics additive

* fix(security): scan malformed roster workspaces

* test(config): align snapshot fixtures after rebase

* test(agents): use explicit roster fixtures

* fix(config): harden roster diagnostic boundaries

* fix(sessions): isolate fixed-store agent databases

* test(agents): type malformed default markers

* refactor(sessions): extract store collision resolution

* test(system-agent): split oversized setup coverage

* style(system-agent): format split setup suite

* fix(sessions): preserve promoted store ownership

* fix(sessions): derive scoped owner before target

* fix(sessions): preserve explicit sqlite ownership

* fix(agents): restore roster compatibility across CI

* fix(agents): enforce roster-owned runtime boundaries

* fix(agents): satisfy default lookup lint

* test(sessions): split known-owner coverage

* fix(state): satisfy path identity lint

* fix(agents): preserve malformed roster safety boundaries

* fix(agents): restore roster compatibility at runtime boundaries

* fix(config): satisfy roster boundary type checks

* fix(agents): preserve roster ownership across runtime probes

Setup inference probes now execute as the configured roster owner. Malformed agent-prefixed session rows are intentionally omitted by the fail-closed visibility contract rather than normalized by tests.

* fix(agents): satisfy session list owner lint

* fix(agents): preserve roster-owned runtime boundaries

Restore shared logical rows for exact SQLite session locators while keeping their physical database owner separate. The ownership regression test now constructs an explicit sole-owner database directly instead of relying on first-touch capture, matching the intentional shared-store contract.

* fix(sessions): preserve multiply owned exact stores

* fix(sessions): restore runtime owner boundaries

Keep incognito sentinels agent-owned, fold default-agent approvals into the global snapshot, and preserve the configless legacy-main CLI policy fallback. Also repair the existing CLI watchdog test lifecycle so the compact shard observes its timeout without an unawaited assertion or async timer stall; product behavior is unchanged by that test-only fix.

* test(ci): align owner-scoped fixtures

These assertions are unchanged. The fixtures now declare the intended non-default runner, expose the session-key constant imported by production status code, and select the main approvals bucket explicitly on Windows.

* fix(agents): close final roster ownership gaps
2026-07-24 22:38:09 -07:00

254 lines
8.4 KiB
TypeScript

import { describe, expect, it, vi } from "vitest";
import type { OpenClawConfig } from "../config/types.openclaw.js";
import type { RuntimeEnv } from "../runtime.js";
import { verifySystemAgentInferenceWithFallback } from "./inference-fallback.js";
import type { SystemAgentConfiguredRoute } from "./inference-route.js";
const runtime = {} as RuntimeEnv;
function route(agentId: string, provider: string): SystemAgentConfiguredRoute {
return {
runner: "embedded",
agentHarnessRuntimeOverride: "openclaw",
runConfig: {},
modelLabel: `${provider}/model`,
provider,
model: "model",
agentDir: `/tmp/${agentId}`,
agentId,
};
}
const config: OpenClawConfig = {
agents: {
defaults: { model: { primary: "zeta/model" } },
list: [
{ id: "requester", model: "zeta/model" },
{ id: "beta", model: "beta/model" },
{ id: "alpha", model: "alpha/model" },
],
},
};
describe("system-agent inference fallback", () => {
it("tries requester first, then authenticated providers by provider id", async () => {
const attempts: string[] = [];
const verify = vi.fn(async ({ agentId }: { agentId: string }) => {
attempts.push(agentId);
return agentId === "beta"
? ({ ok: true, modelRef: "beta/model", latencyMs: 1, binding: {} } as never)
: ({ ok: false, status: "unavailable", error: "down" } as const);
});
const result = await verifySystemAgentInferenceWithFallback({
requestingAgentId: "requester",
runtime,
deps: {
readConfig: async () => config,
resolveRoute: async (_cfg, agentId) =>
route(agentId, agentId === "requester" ? "zeta" : agentId),
hasAuth: async () => true,
verify: verify as never,
},
});
expect(result.ok).toBe(true);
expect(attempts).toEqual(["requester", "alpha", "beta"]);
});
it("retains the implicit main fallback for a pre-roster config", async () => {
const attempts: string[] = [];
const result = await verifySystemAgentInferenceWithFallback({
requestingAgentId: "requester",
runtime,
deps: {
readConfig: async () => ({}),
resolveRoute: async (_cfg, agentId) => route(agentId, agentId),
hasAuth: async () => true,
verify: async ({ agentId }) => {
attempts.push(agentId);
return agentId === "main"
? ({ ok: true, modelRef: "main/model", latencyMs: 1, binding: {} } as never)
: ({ ok: false, status: "unavailable", error: "down" } as const);
},
},
});
expect(result.ok).toBe(true);
expect(attempts).toEqual(["requester", "main"]);
});
it("skips unauthenticated fallback providers", async () => {
const attempts: string[] = [];
await verifySystemAgentInferenceWithFallback({
requestingAgentId: "requester",
runtime,
deps: {
readConfig: async () => config,
resolveRoute: async (_cfg, agentId) =>
route(agentId, agentId === "requester" ? "zeta" : agentId),
hasAuth: async ({ provider }) => provider !== "alpha",
verify: async ({ agentId }) => {
attempts.push(agentId);
return { ok: false, status: "unavailable", error: "down" };
},
},
});
expect(attempts).toEqual(["requester", "beta"]);
});
it("uses a later authenticated route for one fallback provider", async () => {
const attempts: string[] = [];
const duplicateProviderConfig: OpenClawConfig = {
agents: {
defaults: { model: { primary: "zeta/model" } },
list: [
{ id: "requester", model: "zeta/model" },
{ id: "alpha-bad", model: "alpha/model" },
{ id: "alpha-good", model: "alpha/model" },
],
},
};
const result = await verifySystemAgentInferenceWithFallback({
requestingAgentId: "requester",
runtime,
deps: {
readConfig: async () => duplicateProviderConfig,
resolveRoute: async (_cfg, agentId) =>
route(agentId, agentId === "requester" ? "zeta" : "alpha"),
hasAuth: async ({ agentDir }) => agentDir?.endsWith("alpha-good") === true,
verify: async ({ agentId }) => {
attempts.push(agentId);
return agentId === "alpha-good"
? ({ ok: true, modelRef: "alpha/model", latencyMs: 1, binding: {} } as never)
: ({ ok: false, status: "unavailable", error: "down" } as const);
},
},
});
expect(result.ok).toBe(true);
expect(attempts).toEqual(["requester", "alpha-good"]);
});
it("tries another credential owner of the same provider after an auth failure", async () => {
const attempts: string[] = [];
const sameProviderConfig: OpenClawConfig = {
agents: {
defaults: { model: { primary: "alpha/model" } },
list: [
{ id: "requester", model: "alpha/model" },
{ id: "alpha-other", model: "alpha/model" },
],
},
};
const result = await verifySystemAgentInferenceWithFallback({
requestingAgentId: "requester",
runtime,
deps: {
readConfig: async () => sameProviderConfig,
resolveRoute: async (_cfg, agentId) => route(agentId, "alpha"),
hasAuth: async () => true,
verify: async ({ agentId }) => {
attempts.push(agentId);
return agentId === "alpha-other"
? ({ ok: true, modelRef: "alpha/model", latencyMs: 1, binding: {} } as never)
: ({ ok: false, status: "auth", error: "stale key" } as const);
},
},
});
expect(result.ok).toBe(true);
expect(attempts).toEqual(["requester", "alpha-other"]);
});
it("treats a rate limit as credential-scoped and tries another owner", async () => {
const attempts: string[] = [];
const sameProviderConfig: OpenClawConfig = {
agents: {
defaults: { model: { primary: "alpha/model" } },
list: [
{ id: "requester", model: "alpha/model" },
{ id: "alpha-other", model: "alpha/model" },
],
},
};
const result = await verifySystemAgentInferenceWithFallback({
requestingAgentId: "requester",
runtime,
deps: {
readConfig: async () => sameProviderConfig,
resolveRoute: async (_cfg, agentId) => route(agentId, "alpha"),
hasAuth: async () => true,
verify: async ({ agentId }) => {
attempts.push(agentId);
return agentId === "alpha-other"
? ({ ok: true, modelRef: "alpha/model", latencyMs: 1, binding: {} } as never)
: ({ ok: false, status: "rate_limit", error: "429" } as const);
},
},
});
expect(result.ok).toBe(true);
expect(attempts).toEqual(["requester", "alpha-other"]);
});
it("retires the whole provider after a provider-wide failure", async () => {
const attempts: string[] = [];
const cfg: OpenClawConfig = {
agents: {
defaults: { model: { primary: "alpha/model" } },
list: [
{ id: "requester", model: "alpha/model" },
{ id: "alpha-other", model: "alpha/model" },
{ id: "beta", model: "beta/model" },
],
},
};
const result = await verifySystemAgentInferenceWithFallback({
requestingAgentId: "requester",
runtime,
deps: {
readConfig: async () => cfg,
resolveRoute: async (_cfg, agentId) =>
route(agentId, agentId === "beta" ? "beta" : "alpha"),
hasAuth: async () => true,
verify: async ({ agentId }) => {
attempts.push(agentId);
return agentId === "beta"
? ({ ok: true, modelRef: "beta/model", latencyMs: 1, binding: {} } as never)
: ({ ok: false, status: "unavailable", error: "down" } as const);
},
},
});
expect(result.ok).toBe(true);
// alpha-other is skipped: the requester's alpha route failed provider-wide.
expect(attempts).toEqual(["requester", "beta"]);
});
it("does not fail over on bad answers", async () => {
const verify = vi.fn(
async () => ({ ok: false, status: "format", error: "bad answer" }) as const,
);
await verifySystemAgentInferenceWithFallback({
requestingAgentId: "requester",
runtime,
deps: {
readConfig: async () => config,
resolveRoute: async (_cfg, agentId) =>
route(agentId, agentId === "requester" ? "zeta" : agentId),
hasAuth: async () => true,
verify,
},
});
expect(verify).toHaveBeenCalledOnce();
});
});