mirror of
https://github.com/openclaw/openclaw.git
synced 2026-06-06 16:22:53 +00:00
* 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
405 lines
13 KiB
TypeScript
405 lines
13 KiB
TypeScript
import fs from "node:fs/promises";
|
|
import os from "node:os";
|
|
import path from "node:path";
|
|
import type { EmbeddedRunAttemptParams } from "openclaw/plugin-sdk/agent-harness";
|
|
import { classifyEmbeddedAgentRunResultForModelFallback } from "openclaw/plugin-sdk/agent-harness-runtime";
|
|
import {
|
|
createContractRunResult,
|
|
OUTCOME_FALLBACK_RUNTIME_CONTRACT,
|
|
} from "openclaw/plugin-sdk/agent-runtime-test-contracts";
|
|
import { SessionManager } from "openclaw/plugin-sdk/agent-sessions";
|
|
import { afterEach, describe, expect, it } from "vitest";
|
|
import {
|
|
CodexAppServerEventProjector,
|
|
type CodexAppServerToolTelemetry,
|
|
} from "./event-projector.js";
|
|
import { createCodexTestModel } from "./test-support.js";
|
|
|
|
const THREAD_ID = "thread-outcome-contract";
|
|
const TURN_ID = "turn-outcome-contract";
|
|
const tempDirs = new Set<string>();
|
|
|
|
type ProjectorNotification = Parameters<CodexAppServerEventProjector["handleNotification"]>[0];
|
|
type ProjectedAttemptResult = ReturnType<CodexAppServerEventProjector["buildResult"]>;
|
|
type MirrorTaggedMessage = { __openclaw?: { mirrorIdentity?: string } };
|
|
|
|
async function createParams(): Promise<EmbeddedRunAttemptParams> {
|
|
const tempDir = await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-codex-outcome-contract-"));
|
|
tempDirs.add(tempDir);
|
|
const sessionFile = path.join(tempDir, "session.jsonl");
|
|
SessionManager.open(sessionFile);
|
|
return {
|
|
prompt: OUTCOME_FALLBACK_RUNTIME_CONTRACT.prompt,
|
|
sessionId: OUTCOME_FALLBACK_RUNTIME_CONTRACT.sessionId,
|
|
sessionKey: OUTCOME_FALLBACK_RUNTIME_CONTRACT.sessionKey,
|
|
sessionFile,
|
|
workspaceDir: tempDir,
|
|
runId: OUTCOME_FALLBACK_RUNTIME_CONTRACT.runId,
|
|
provider: "codex",
|
|
modelId: OUTCOME_FALLBACK_RUNTIME_CONTRACT.primaryModel,
|
|
model: createCodexTestModel("codex"),
|
|
thinkLevel: "medium",
|
|
} as EmbeddedRunAttemptParams;
|
|
}
|
|
|
|
async function createProjector(): Promise<CodexAppServerEventProjector> {
|
|
return new CodexAppServerEventProjector(await createParams(), THREAD_ID, TURN_ID);
|
|
}
|
|
|
|
function buildToolTelemetry(
|
|
overrides: Partial<CodexAppServerToolTelemetry> = {},
|
|
): CodexAppServerToolTelemetry {
|
|
return {
|
|
didSendViaMessagingTool: false,
|
|
messagingToolSentTexts: [],
|
|
messagingToolSentMediaUrls: [],
|
|
messagingToolSentTargets: [],
|
|
toolMediaUrls: [],
|
|
toolAudioAsVoice: false,
|
|
...overrides,
|
|
};
|
|
}
|
|
|
|
function forCurrentTurn(
|
|
method: ProjectorNotification["method"],
|
|
params: Record<string, unknown>,
|
|
): ProjectorNotification {
|
|
return {
|
|
method,
|
|
params: { threadId: THREAD_ID, turnId: TURN_ID, ...params },
|
|
} as ProjectorNotification;
|
|
}
|
|
|
|
function classifyProjectedAttemptResult(result: ProjectedAttemptResult) {
|
|
const finalAssistantText = result.assistantTexts.join("\n\n").trim();
|
|
return classifyEmbeddedAgentRunResultForModelFallback({
|
|
provider: "codex",
|
|
model: OUTCOME_FALLBACK_RUNTIME_CONTRACT.primaryModel,
|
|
result: createContractRunResult({
|
|
...result,
|
|
meta: {
|
|
durationMs: 1,
|
|
aborted: result.aborted,
|
|
agentHarnessResultClassification: result.agentHarnessResultClassification,
|
|
finalAssistantRawText: finalAssistantText || undefined,
|
|
finalAssistantVisibleText: finalAssistantText || undefined,
|
|
},
|
|
}),
|
|
});
|
|
}
|
|
|
|
function readMirrorIdentity(message: unknown): string | undefined {
|
|
const meta = (message as MirrorTaggedMessage | undefined)?.["__openclaw"];
|
|
return meta?.mirrorIdentity;
|
|
}
|
|
|
|
afterEach(async () => {
|
|
for (const tempDir of tempDirs) {
|
|
await fs.rm(tempDir, { recursive: true, force: true });
|
|
}
|
|
tempDirs.clear();
|
|
});
|
|
|
|
describe("Outcome/fallback runtime contract - Codex app-server adapter", () => {
|
|
it("preserves an empty terminal turn for OpenClaw-owned fallback classification", async () => {
|
|
const projector = await createProjector();
|
|
await projector.handleNotification(
|
|
forCurrentTurn("turn/completed", {
|
|
turn: { id: TURN_ID, status: "completed", items: [] },
|
|
}),
|
|
);
|
|
|
|
const result = projector.buildResult(buildToolTelemetry());
|
|
|
|
expect(result.assistantTexts).toStrictEqual([]);
|
|
expect(result.lastAssistant).toBeUndefined();
|
|
expect(result.promptError).toBeNull();
|
|
});
|
|
|
|
it("preserves exact NO_REPLY as assistant text instead of classifying in the adapter", async () => {
|
|
const projector = await createProjector();
|
|
await projector.handleNotification(
|
|
forCurrentTurn("item/agentMessage/delta", {
|
|
itemId: "msg-1",
|
|
delta: "NO_REPLY",
|
|
}),
|
|
);
|
|
await projector.handleNotification(
|
|
forCurrentTurn("turn/completed", {
|
|
turn: {
|
|
id: TURN_ID,
|
|
status: "completed",
|
|
items: [{ type: "agentMessage", id: "msg-1", text: "NO_REPLY" }],
|
|
},
|
|
}),
|
|
);
|
|
|
|
const result = projector.buildResult(buildToolTelemetry());
|
|
|
|
expect(result.assistantTexts).toEqual(["NO_REPLY"]);
|
|
expect(result.lastAssistant?.content).toEqual([{ type: "text", text: "NO_REPLY" }]);
|
|
expect(result.promptError).toBeNull();
|
|
});
|
|
|
|
it("preserves reasoning-only terminal turns for OpenClaw-owned fallback classification", async () => {
|
|
const projector = await createProjector();
|
|
await projector.handleNotification(
|
|
forCurrentTurn("item/reasoning/textDelta", {
|
|
itemId: "reasoning-1",
|
|
delta: OUTCOME_FALLBACK_RUNTIME_CONTRACT.reasoningOnlyText,
|
|
}),
|
|
);
|
|
await projector.handleNotification(
|
|
forCurrentTurn("turn/completed", {
|
|
turn: {
|
|
id: TURN_ID,
|
|
status: "completed",
|
|
items: [{ type: "reasoning", id: "reasoning-1" }],
|
|
},
|
|
}),
|
|
);
|
|
|
|
const result = projector.buildResult(buildToolTelemetry());
|
|
|
|
expect(result.assistantTexts).toStrictEqual([]);
|
|
expect(result.lastAssistant).toBeUndefined();
|
|
expect(result.promptError).toBeNull();
|
|
expect(result.messagesSnapshot.map((message) => message.role)).toStrictEqual([
|
|
"user",
|
|
"assistant",
|
|
]);
|
|
const reasoningMessage = result.messagesSnapshot[1];
|
|
if (reasoningMessage?.role !== "assistant") {
|
|
throw new Error("expected Codex reasoning mirror assistant message");
|
|
}
|
|
expect(readMirrorIdentity(reasoningMessage)).toBe(`${TURN_ID}:reasoning`);
|
|
expect(reasoningMessage.content).toStrictEqual([
|
|
{
|
|
type: "text",
|
|
text: `Codex reasoning:\n${OUTCOME_FALLBACK_RUNTIME_CONTRACT.reasoningOnlyText}`,
|
|
},
|
|
]);
|
|
expect(reasoningMessage.api).toBe("openai-codex-responses");
|
|
expect(reasoningMessage.provider).toBe("codex");
|
|
expect(reasoningMessage.model).toBe(OUTCOME_FALLBACK_RUNTIME_CONTRACT.primaryModel);
|
|
expect(reasoningMessage.usage).toStrictEqual({
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
totalTokens: 0,
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
total: 0,
|
|
},
|
|
});
|
|
expect(reasoningMessage.stopReason).toBe("stop");
|
|
expect(typeof reasoningMessage.timestamp).toBe("number");
|
|
expect(reasoningMessage.timestamp).toBeGreaterThan(0);
|
|
});
|
|
|
|
it("preserves planning-only terminal turns for OpenClaw-owned fallback classification", async () => {
|
|
const projector = await createProjector();
|
|
await projector.handleNotification(
|
|
forCurrentTurn("item/plan/delta", {
|
|
itemId: "plan-1",
|
|
delta: OUTCOME_FALLBACK_RUNTIME_CONTRACT.planningOnlyText,
|
|
}),
|
|
);
|
|
await projector.handleNotification(
|
|
forCurrentTurn("turn/completed", {
|
|
turn: {
|
|
id: TURN_ID,
|
|
status: "completed",
|
|
items: [
|
|
{
|
|
type: "plan",
|
|
id: "plan-1",
|
|
text: OUTCOME_FALLBACK_RUNTIME_CONTRACT.planningOnlyText,
|
|
},
|
|
],
|
|
},
|
|
}),
|
|
);
|
|
|
|
const result = projector.buildResult(buildToolTelemetry());
|
|
|
|
expect(result.assistantTexts).toStrictEqual([]);
|
|
expect(result.lastAssistant).toBeUndefined();
|
|
expect(result.promptError).toBeNull();
|
|
expect(result.messagesSnapshot.map((message) => message.role)).toStrictEqual([
|
|
"user",
|
|
"assistant",
|
|
]);
|
|
const planMessage = result.messagesSnapshot[1];
|
|
if (planMessage?.role !== "assistant") {
|
|
throw new Error("expected Codex plan mirror assistant message");
|
|
}
|
|
expect(readMirrorIdentity(planMessage)).toBe(`${TURN_ID}:plan`);
|
|
expect(planMessage.content).toStrictEqual([
|
|
{
|
|
type: "text",
|
|
text: `Codex plan:\n${OUTCOME_FALLBACK_RUNTIME_CONTRACT.planningOnlyText}`,
|
|
},
|
|
]);
|
|
expect(planMessage.api).toBe("openai-codex-responses");
|
|
expect(planMessage.provider).toBe("codex");
|
|
expect(planMessage.model).toBe(OUTCOME_FALLBACK_RUNTIME_CONTRACT.primaryModel);
|
|
expect(planMessage.usage).toStrictEqual({
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
totalTokens: 0,
|
|
cost: {
|
|
input: 0,
|
|
output: 0,
|
|
cacheRead: 0,
|
|
cacheWrite: 0,
|
|
total: 0,
|
|
},
|
|
});
|
|
expect(planMessage.stopReason).toBe("stop");
|
|
expect(typeof planMessage.timestamp).toBe("number");
|
|
expect(planMessage.timestamp).toBeGreaterThan(0);
|
|
});
|
|
|
|
it("preserves tool side-effect telemetry so fallback can stay disabled", async () => {
|
|
const projector = await createProjector();
|
|
|
|
const result = projector.buildResult(
|
|
buildToolTelemetry({
|
|
didSendViaMessagingTool: true,
|
|
messagingToolSentTexts: ["sent out of band"],
|
|
}),
|
|
);
|
|
|
|
expect(result.assistantTexts).toStrictEqual([]);
|
|
expect(result.didSendViaMessagingTool).toBe(true);
|
|
expect(result.messagingToolSentTexts).toEqual(["sent out of band"]);
|
|
});
|
|
|
|
it.each([
|
|
{
|
|
name: "empty",
|
|
classification: "empty",
|
|
expectedCode: "empty_result",
|
|
build: async () => {
|
|
const projector = await createProjector();
|
|
await projector.handleNotification(
|
|
forCurrentTurn("turn/completed", {
|
|
turn: { id: TURN_ID, status: "completed", items: [] },
|
|
}),
|
|
);
|
|
return projector.buildResult(buildToolTelemetry());
|
|
},
|
|
},
|
|
{
|
|
name: "reasoning-only",
|
|
classification: "reasoning-only",
|
|
expectedCode: "reasoning_only_result",
|
|
build: async () => {
|
|
const projector = await createProjector();
|
|
await projector.handleNotification(
|
|
forCurrentTurn("item/reasoning/textDelta", {
|
|
itemId: "reasoning-1",
|
|
delta: OUTCOME_FALLBACK_RUNTIME_CONTRACT.reasoningOnlyText,
|
|
}),
|
|
);
|
|
await projector.handleNotification(
|
|
forCurrentTurn("turn/completed", {
|
|
turn: {
|
|
id: TURN_ID,
|
|
status: "completed",
|
|
items: [{ type: "reasoning", id: "reasoning-1" }],
|
|
},
|
|
}),
|
|
);
|
|
return projector.buildResult(buildToolTelemetry());
|
|
},
|
|
},
|
|
{
|
|
name: "planning-only",
|
|
classification: "planning-only",
|
|
expectedCode: "planning_only_result",
|
|
build: async () => {
|
|
const projector = await createProjector();
|
|
await projector.handleNotification(
|
|
forCurrentTurn("item/plan/delta", {
|
|
itemId: "plan-1",
|
|
delta: OUTCOME_FALLBACK_RUNTIME_CONTRACT.planningOnlyText,
|
|
}),
|
|
);
|
|
await projector.handleNotification(
|
|
forCurrentTurn("turn/completed", {
|
|
turn: {
|
|
id: TURN_ID,
|
|
status: "completed",
|
|
items: [
|
|
{
|
|
type: "plan",
|
|
id: "plan-1",
|
|
text: OUTCOME_FALLBACK_RUNTIME_CONTRACT.planningOnlyText,
|
|
},
|
|
],
|
|
},
|
|
}),
|
|
);
|
|
return projector.buildResult(buildToolTelemetry());
|
|
},
|
|
},
|
|
] as const)(
|
|
"keeps $name terminal turns fallback-ready with adapter-produced classification",
|
|
async ({ build, classification, expectedCode }) => {
|
|
const result = await build();
|
|
|
|
expect(result.agentHarnessResultClassification).toBe(classification);
|
|
const projected = classifyProjectedAttemptResult(result);
|
|
if (!projected || !("reason" in projected)) {
|
|
throw new Error("expected format fallback projection");
|
|
}
|
|
expect(projected.reason).toBe("format");
|
|
expect(projected.code).toBe(expectedCode);
|
|
},
|
|
);
|
|
|
|
it("keeps exact NO_REPLY classified as an intentional silent terminal reply", async () => {
|
|
const projector = await createProjector();
|
|
await projector.handleNotification(
|
|
forCurrentTurn("item/agentMessage/delta", {
|
|
itemId: "msg-1",
|
|
delta: "NO_REPLY",
|
|
}),
|
|
);
|
|
await projector.handleNotification(
|
|
forCurrentTurn("turn/completed", {
|
|
turn: {
|
|
id: TURN_ID,
|
|
status: "completed",
|
|
items: [{ type: "agentMessage", id: "msg-1", text: "NO_REPLY" }],
|
|
},
|
|
}),
|
|
);
|
|
|
|
const result = projector.buildResult(buildToolTelemetry());
|
|
|
|
expect(classifyProjectedAttemptResult(result)).toBeNull();
|
|
});
|
|
|
|
it("keeps tool side effects classified as non-fallback terminal outcomes", async () => {
|
|
const projector = await createProjector();
|
|
const result = projector.buildResult(
|
|
buildToolTelemetry({
|
|
didSendViaMessagingTool: true,
|
|
messagingToolSentTexts: ["sent out of band"],
|
|
}),
|
|
);
|
|
|
|
expect(result.agentHarnessResultClassification).toBeUndefined();
|
|
expect(classifyProjectedAttemptResult(result)).toBeNull();
|
|
});
|
|
});
|