Files
openclaw/src/agents/execution-contract.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

221 lines
6.2 KiB
TypeScript

// Covers provider/model gates for strict agentic execution-contract activation.
import { describe, expect, it } from "vitest";
import type { OpenClawConfig } from "../config/types.openclaw.js";
import { isStrictAgenticExecutionContractActive } from "./execution-contract.js";
describe("isStrictAgenticExecutionContractActive", () => {
const supportedProvider = "openai";
const unsupportedProvider = "anthropic";
const emptyConfig: OpenClawConfig = {
agents: { entries: { main: { default: true } } },
};
describe("supported provider + model detection", () => {
it("auto-activates on bare gpt-5 model ids", () => {
expect(
isStrictAgenticExecutionContractActive({
config: emptyConfig,
provider: supportedProvider,
modelId: "gpt-5.4",
}),
).toBe(true);
});
it("auto-activates on the mock-openai qa lane", () => {
expect(
isStrictAgenticExecutionContractActive({
config: emptyConfig,
provider: "mock-openai",
modelId: "mock-openai/gpt-5.4",
}),
).toBe(true);
});
it("auto-activates on gpt-5o and variants without a separator", () => {
for (const modelId of ["gpt-5", "gpt-5o", "gpt-5o-mini"]) {
expect(
isStrictAgenticExecutionContractActive({
config: emptyConfig,
provider: supportedProvider,
modelId,
}),
).toBe(true);
}
});
it("auto-activates on dot-separated variants", () => {
for (const modelId of ["gpt-5.0", "gpt-5.4", "gpt-5.4-alt", "gpt-5.99"]) {
expect(
isStrictAgenticExecutionContractActive({
config: emptyConfig,
provider: supportedProvider,
modelId,
}),
).toBe(true);
}
});
it("auto-activates on dash-separated variants", () => {
for (const modelId of ["gpt-5-preview", "gpt-5-turbo", "gpt-5-2025-03"]) {
expect(
isStrictAgenticExecutionContractActive({
config: emptyConfig,
provider: supportedProvider,
modelId,
}),
).toBe(true);
}
});
it("auto-activates on prefixed model ids (openai/gpt-5.4, openai:gpt-5.4)", () => {
// Regression for the adversarial review finding: prefixed model ids
// must strip the provider prefix before matching the regex.
for (const modelId of [
"openai/gpt-5.4",
"openai:gpt-5.4",
"openai/gpt-5o-mini",
"openai/gpt-5.4",
"openai:gpt-5.4",
" openai/gpt-5.4 ",
" OPENAI:GPT-5.4 ",
]) {
expect(
isStrictAgenticExecutionContractActive({
config: emptyConfig,
provider: supportedProvider,
modelId,
}),
).toBe(true);
}
});
it("is case-insensitive", () => {
for (const modelId of ["GPT-5.4", "Gpt-5O", "OPENAI/GPT-5.4"]) {
expect(
isStrictAgenticExecutionContractActive({
config: emptyConfig,
provider: supportedProvider,
modelId,
}),
).toBe(true);
}
});
it("does not match non-gpt-5 family ids", () => {
for (const modelId of [
"gpt-4.5",
"gpt-4o",
"gpt-6",
"gpt-50",
"claude-opus-4-6",
"llama-3-70b",
"mistral-large",
]) {
expect(
isStrictAgenticExecutionContractActive({
config: emptyConfig,
provider: supportedProvider,
modelId,
}),
).toBe(false);
}
});
it("collapses to default on unsupported providers even with gpt-5 model ids", () => {
// Model naming alone is insufficient; unsupported providers must not
// inherit OpenAI-specific strict-agentic handling by accident.
expect(
isStrictAgenticExecutionContractActive({
config: emptyConfig,
provider: unsupportedProvider,
modelId: "gpt-5.4",
}),
).toBe(false);
});
});
describe("explicit override behavior", () => {
it("honors explicit strict-agentic on the supported lane", () => {
const config: OpenClawConfig = {
agents: {
entries: { main: { default: true } },
defaults: {
embeddedAgent: {
executionContract: "strict-agentic",
},
},
},
};
expect(
isStrictAgenticExecutionContractActive({
config,
provider: supportedProvider,
modelId: "gpt-5.4",
}),
).toBe(true);
});
it("honors explicit default opt-out even on the supported lane", () => {
const config: OpenClawConfig = {
agents: {
entries: { main: { default: true } },
defaults: {
embeddedAgent: {
executionContract: "default",
},
},
},
};
expect(
isStrictAgenticExecutionContractActive({
config,
provider: supportedProvider,
modelId: "gpt-5.4",
}),
).toBe(false);
});
it("collapses explicit strict-agentic to default on an unsupported lane", () => {
const config: OpenClawConfig = {
agents: {
entries: { main: { default: true } },
defaults: {
embeddedAgent: {
executionContract: "strict-agentic",
},
},
},
};
expect(
isStrictAgenticExecutionContractActive({
config,
provider: unsupportedProvider,
modelId: "claude-opus-4-6",
}),
).toBe(false);
});
});
describe("active flag helper", () => {
it("returns true when the effective contract is strict-agentic", () => {
expect(
isStrictAgenticExecutionContractActive({
config: emptyConfig,
provider: supportedProvider,
modelId: "openai/gpt-5.4",
}),
).toBe(true);
});
it("returns false when the effective contract is default", () => {
expect(
isStrictAgenticExecutionContractActive({
config: emptyConfig,
provider: supportedProvider,
modelId: "gpt-4.5",
}),
).toBe(false);
});
});
});