Files
openclaw/src/agents/embedded-agent-runner.extensions.test.ts
Peter Steinberger bb46b79d3c refactor: internalize OpenClaw agent runtime (#85341)
* refactor: extract agent core package

Introduce packages/agent-core as the OpenClaw-owned home for reusable agent loop, harness, session, prompt, and runtime dependency contracts.

* refactor: extract shared llm runtime

Move provider model registries, stream wrappers, OAuth helpers, and LLM utilities into src/llm with plugin-sdk barrels instead of depending on the old embedded runtime layout.

* refactor: remove pi runtime internals

Rename remaining Pi-shaped agent surfaces to OpenClaw agent runtime names, delete obsolete Pi docs and package graph checks, and add the third-party notice for incorporated code.

* refactor: tighten agent session runtime

Make agent-core/runtime dependencies explicit, consolidate compaction and session transcript helpers, and move model/session helpers behind OpenClaw-owned contracts.

* refactor: remove static model and pi auth paths

Drop static model catalogs and Pi auth bridges, move model/provider facts to manifest-owned runtime contracts, and harden internal embedded-agent utilities.

* refactor: remove legacy provider compat paths

* docs: remove agent parity notes

* fix: skip provider wildcard metadata parsing

* refactor: share session extension sdk loading

* refactor: inline acpx proxy error formatter

* refactor: fold edit recovery into edit tool

* fix: accept extension batch separator

* test: align startup provider plugin expectations

* fix: restore provider-scoped release discovery

* test: align static asset packaging expectations

* fix: run static provider catalogs during scoped discovery

* fix: add provider entry catalogs for scoped live discovery

* fix: load lightweight provider catalog entries

* fix: refresh provider-scoped plugin metadata

* fix: keep provider catalog entries on release live path

* fix: keep static manifest models in release live checks

* fix: harden release model discovery

* fix: reduce OpenAI live cache probe reasoning

* fix: disable OpenAI cache probe reasoning

* ci: extend OpenAI gateway live timeout

* fix: extend live gateway model budget

* fix: stabilize release validation regressions

* fix: honor provider aliases in model rows

* fix: stabilize release validation lanes

* fix: stabilize release memory qa

* ci: stabilize release validation lanes

* ci: prefer ipv4 for live docker node calls

* fix: restore shared tool-call stream wrapper

* ci: remove legacy pi test shard alias

* fix: clean up embedded agent test drift

* fix: stabilize runtime alias status

* fix: clean up embedded agent ci drift

* fix: restore release ci invariants

* fix: clean up post-rebase runtime drift

* fix: restore release ci checks

* fix: restore release ci after rebase

* fix: remove stale pi runtime path

* test: align compaction runtime expectations

* test: update plugin prerelease expectations

* fix: handle claude live tool approvals

* fix: stabilize release validation gates

* fix: finish agent runtime import

* test: finish post-rebase agent runtime mocks

* fix: keep codex compaction native

* fix: stabilize codex app-server hook tests

* test: isolate codex diagnostic active run

* test: remove codex diagnostic completion race

# Conflicts:
#	extensions/codex/src/app-server/run-attempt.test.ts

* ci: fix full release manifest performance run id

* refactor: narrow llm plugin sdk boundary

* chore: drop generated google boundary stamps

* fix: repair rebase fallout

* fix: clean up rebased runtime references

* fix: decode codex jwt payloads as base64url

* fix: preserve shipped pi runtime alias

* fix: add scoped sdk virtual modules

* fix: decode llm codex oauth jwt as base64url

* fix: avoid stale vertex adc negative cache

* fix: harden tool arg decoding and codeql path

* fix: keep vertex adc negative checks live

* refactor: consolidate codex jwt and edit helpers

* fix: await codex oauth node runtime imports

* fix: preserve sdk tool and notice contracts

* fix: preserve shipped compat config boundaries

* fix: align codex oauth callback host

* fix: terminate agent-core loop streams on failure

* fix: keep codex oauth callback alive during fallback

* ci: include session tools in critical codeql scans

* fix: keep Cloudflare Anthropic provider auth header

* docs: redirect legacy pi runtime pages

* fix: honor bundled web provider compat discovery

* fix: protect session output spill files

* fix: keep legacy agent dir env blocked

* fix: contain auto-discovered skill symlinks

* fix: harden agent core sdk proxy surfaces

* fix: restore approval reaction sdk compat

* fix: keep live docker runs bounded

* fix: keep codex oauth redirect host aligned

* fix: resolve post-rebase agent runtime drift

* fix: redact anthropic oauth parse failures

* fix: preserve responses strict tool shaping

* fix: repair agent runtime rebase cleanup

* docs: redirect retired parity pages

* fix: bound auto-discovered resources to roots

* fix: repair post-rebase agent test drift

* fix: preserve bundled provider allowlist migration

* fix: preserve manifest-owned provider aliases

* fix: declare photon image dependency

* fix: keep provider headers out of proxy body

* fix: preserve shipped env aliases

* fix: refresh control ui i18n generated state

* fix: quote read fallback paths

* fix: preview edits through configured backend

* test: satisfy core test typecheck

* fix: preserve ZAI usage auth fallback

* test: repair codex diagnostic test

* fix: repair agent runtime rebase drift

* test: finish embedded runner import rename

* fix: repair agent runtime rebase integrations

* test: align compaction oauth fallback expectations

* fix: allow sdk-auth session models

* fix: update doctor tool schema import

* fix: preserve bedrock plugin region

* fix: stream harmony-like prose immediately

* ci: include session runtime in codeql shards

* fix: repair latest rebase integrations

* fix: honor explicit codex websocket transport

* fix: keep openai-compatible credentials provider-scoped

* fix: refresh sdk api baseline after rebase

* fix: route cli runtime aliases through openclaw harness

* test: rename stale harness mock expectation

* test: rename embedded agent overflow calls

* test: clean embedded auth test wording

* test: use openclaw stream types in deepinfra cache test

* fix: refresh sdk api baseline on latest main

* fix: honor bundled discovery compat allowlists

* fix: refresh sdk api baseline after latest rebase

* fix: remove stale rebase imports

* test: rename stale model catalog mock

* test: mock renamed doctor runtime modules

* fix: map canonical kimi env auth

* fix: use internal model registry in bench script

* fix: migrate deepinfra provider catalog entry

* fix: enforce builtin tool suppression

* fix: route compaction auth and proxy payloads safely

* refactor: prune unused llm registry leftovers

* test: update codex hooks session import

* test: fix model picker ci coverage

* test: align model picker auth mock types
2026-05-27 19:24:04 +01:00

255 lines
7.5 KiB
TypeScript

import { SessionManager } from "openclaw/plugin-sdk/agent-sessions";
import { afterEach, describe, expect, it } from "vitest";
import { createEmptyPluginRegistry } from "../plugins/registry.js";
import { setActivePluginRegistry } from "../plugins/runtime.js";
import { buildEmbeddedExtensionFactories } from "./embedded-agent-runner/extensions.js";
import { cleanupTempPluginTestEnvironment } from "./test-helpers/temp-plugin-extension-fixtures.js";
const originalBundledPluginsDir = process.env.OPENCLAW_BUNDLED_PLUGINS_DIR;
const tempDirs: string[] = [];
afterEach(() => {
cleanupTempPluginTestEnvironment(tempDirs, originalBundledPluginsDir);
});
describe("buildEmbeddedExtensionFactories", () => {
it("bridges middleware mutations with unique fallback tool call ids", async () => {
const seenToolCallIds: string[] = [];
const registry = createEmptyPluginRegistry();
registry.agentToolResultMiddlewares.push({
pluginId: "tokenjuice",
pluginName: "tokenjuice",
rawHandler: () => undefined,
handler: (event) => {
seenToolCallIds.push(event.toolCallId);
event.result.content = [{ type: "text", text: `compacted ${seenToolCallIds.length}` }];
return undefined;
},
runtimes: ["openclaw"],
source: "test",
});
setActivePluginRegistry(registry);
const factories = buildEmbeddedExtensionFactories({
cfg: undefined,
sessionManager: SessionManager.inMemory(),
provider: "openai",
modelId: "gpt-5.4",
model: undefined,
});
expect(factories).toHaveLength(1);
const handlers = new Map<string, Function>();
await factories[0]?.({
on(event: string, handler: Function) {
handlers.set(event, handler);
},
} as never);
const handler = handlers.get("tool_result");
const first = await handler?.(
{ toolName: "exec", content: [{ type: "text", text: "raw 1" }], details: {} },
{ cwd: "/tmp" },
);
const second = await handler?.(
{ toolName: "exec", content: [{ type: "text", text: "raw 2" }], details: {} },
{ cwd: "/tmp" },
);
expect(first).toEqual({
content: [{ type: "text", text: "compacted 1" }],
details: {},
});
expect(second).toEqual({
content: [{ type: "text", text: "compacted 2" }],
details: {},
});
expect(seenToolCallIds).toHaveLength(2);
expect(seenToolCallIds[0]).toMatch(/^openclaw-/);
expect(seenToolCallIds[1]).toMatch(/^openclaw-/);
expect(seenToolCallIds[0]).not.toBe(seenToolCallIds[1]);
});
it("marks status-error tool results as model-visible failures", async () => {
setActivePluginRegistry(createEmptyPluginRegistry());
const factories = buildEmbeddedExtensionFactories({
cfg: undefined,
sessionManager: SessionManager.inMemory(),
provider: "openai",
modelId: "gpt-5.4",
model: undefined,
});
const handlers = new Map<string, Function>();
await factories[0]?.({
on(event: string, handler: Function) {
handlers.set(event, handler);
},
} as never);
const handler = handlers.get("tool_result");
const content = [{ type: "text", text: "oldText must be unique" }];
const details = {
status: "error",
tool: "edit",
error: "oldText must be unique",
};
const result = await handler?.(
{
toolName: "edit",
toolCallId: "call-edit",
content,
details,
isError: false,
},
{ cwd: "/tmp" },
);
expect(result).toEqual({
content,
details,
isError: true,
});
});
it("preserves model-visible failures when middleware rewrites details", async () => {
const registry = createEmptyPluginRegistry();
registry.agentToolResultMiddlewares.push({
pluginId: "redactor",
pluginName: "redactor",
rawHandler: () => undefined,
handler: (event) => {
event.result.content = [{ type: "text", text: "redacted error" }];
event.result.details = { redacted: true };
return undefined;
},
runtimes: ["openclaw"],
source: "test",
});
setActivePluginRegistry(registry);
const factories = buildEmbeddedExtensionFactories({
cfg: undefined,
sessionManager: SessionManager.inMemory(),
provider: "openai",
modelId: "gpt-5.4",
model: undefined,
});
const handlers = new Map<string, Function>();
await factories[0]?.({
on(event: string, handler: Function) {
handlers.set(event, handler);
},
} as never);
const handler = handlers.get("tool_result");
const result = await handler?.(
{
toolName: "edit",
toolCallId: "call-edit",
content: [{ type: "text", text: "oldText must be unique" }],
details: { status: "error", tool: "edit", error: "oldText must be unique" },
isError: false,
},
{ cwd: "/tmp" },
);
expect(result).toEqual({
content: [{ type: "text", text: "redacted error" }],
details: { redacted: true },
isError: true,
});
});
it("marks status-timeout tool results as model-visible failures", async () => {
setActivePluginRegistry(createEmptyPluginRegistry());
const factories = buildEmbeddedExtensionFactories({
cfg: undefined,
sessionManager: SessionManager.inMemory(),
provider: "openai",
modelId: "gpt-5.4",
model: undefined,
});
const handlers = new Map<string, Function>();
await factories[0]?.({
on(event: string, handler: Function) {
handlers.set(event, handler);
},
} as never);
const handler = handlers.get("tool_result");
const result = await handler?.(
{
toolName: "exec",
toolCallId: "call-exec",
content: [{ type: "text", text: "Timed out" }],
details: { status: "timeout", tool: "exec", error: "Timed out" },
isError: false,
},
{ cwd: "/tmp" },
);
expect(result).toEqual({
content: [{ type: "text", text: "Timed out" }],
details: { status: "timeout", tool: "exec", error: "Timed out" },
isError: true,
});
});
it("does not mark results as errors when status is absent or non-error", async () => {
setActivePluginRegistry(createEmptyPluginRegistry());
const factories = buildEmbeddedExtensionFactories({
cfg: undefined,
sessionManager: SessionManager.inMemory(),
provider: "openai",
modelId: "gpt-5.4",
model: undefined,
});
const handlers = new Map<string, Function>();
await factories[0]?.({
on(event: string, handler: Function) {
handlers.set(event, handler);
},
} as never);
const handler = handlers.get("tool_result");
// Empty details — no status field
const noStatusResult = await handler?.(
{
toolName: "read",
toolCallId: "call-read",
content: [{ type: "text", text: "file contents" }],
details: {},
isError: false,
},
{ cwd: "/tmp" },
);
expect(noStatusResult).toEqual({
content: [{ type: "text", text: "file contents" }],
details: {},
});
// Explicit ok status
const okResult = await handler?.(
{
toolName: "read",
toolCallId: "call-read-2",
content: [{ type: "text", text: "ok" }],
details: { status: "ok" },
isError: false,
},
{ cwd: "/tmp" },
);
expect(okResult).toEqual({
content: [{ type: "text", text: "ok" }],
details: { status: "ok" },
});
});
});