mirror of
https://github.com/openclaw/openclaw.git
synced 2026-05-09 10:27:38 +00:00
perf(test): trim duplicate sanitize-session-history e2e cases
This commit is contained in:
@@ -7,7 +7,6 @@ type SanitizeSessionHistory =
|
|||||||
typeof import("./pi-embedded-runner/google.js").sanitizeSessionHistory;
|
typeof import("./pi-embedded-runner/google.js").sanitizeSessionHistory;
|
||||||
let sanitizeSessionHistory: SanitizeSessionHistory;
|
let sanitizeSessionHistory: SanitizeSessionHistory;
|
||||||
|
|
||||||
// Mock dependencies
|
|
||||||
vi.mock("./pi-embedded-helpers.js", async () => {
|
vi.mock("./pi-embedded-helpers.js", async () => {
|
||||||
const actual = await vi.importActual("./pi-embedded-helpers.js");
|
const actual = await vi.importActual("./pi-embedded-helpers.js");
|
||||||
return {
|
return {
|
||||||
@@ -17,15 +16,11 @@ vi.mock("./pi-embedded-helpers.js", async () => {
|
|||||||
};
|
};
|
||||||
});
|
});
|
||||||
|
|
||||||
// We don't mock session-transcript-repair.js as it is a pure function and complicates mocking.
|
describe("sanitizeSessionHistory e2e smoke", () => {
|
||||||
// We rely on the real implementation which should pass through our simple messages.
|
|
||||||
|
|
||||||
describe("sanitizeSessionHistory", () => {
|
|
||||||
const mockSessionManager = {
|
const mockSessionManager = {
|
||||||
getEntries: vi.fn().mockReturnValue([]),
|
getEntries: vi.fn().mockReturnValue([]),
|
||||||
appendCustomEntry: vi.fn(),
|
appendCustomEntry: vi.fn(),
|
||||||
} as unknown as SessionManager;
|
} as unknown as SessionManager;
|
||||||
|
|
||||||
const mockMessages: AgentMessage[] = [{ role: "user", content: "hello" }];
|
const mockMessages: AgentMessage[] = [{ role: "user", content: "hello" }];
|
||||||
|
|
||||||
beforeEach(async () => {
|
beforeEach(async () => {
|
||||||
@@ -34,7 +29,7 @@ describe("sanitizeSessionHistory", () => {
|
|||||||
({ sanitizeSessionHistory } = await import("./pi-embedded-runner/google.js"));
|
({ sanitizeSessionHistory } = await import("./pi-embedded-runner/google.js"));
|
||||||
});
|
});
|
||||||
|
|
||||||
it("sanitizes tool call ids for Google model APIs", async () => {
|
it("applies full sanitize policy for google model APIs", async () => {
|
||||||
vi.mocked(helpers.isGoogleModelApi).mockReturnValue(true);
|
vi.mocked(helpers.isGoogleModelApi).mockReturnValue(true);
|
||||||
|
|
||||||
await sanitizeSessionHistory({
|
await sanitizeSessionHistory({
|
||||||
@@ -52,48 +47,7 @@ describe("sanitizeSessionHistory", () => {
|
|||||||
);
|
);
|
||||||
});
|
});
|
||||||
|
|
||||||
it("sanitizes tool call ids with strict9 for Mistral models", async () => {
|
it("applies strict tool-call sanitization for openai-responses", async () => {
|
||||||
vi.mocked(helpers.isGoogleModelApi).mockReturnValue(false);
|
|
||||||
|
|
||||||
await sanitizeSessionHistory({
|
|
||||||
messages: mockMessages,
|
|
||||||
modelApi: "openai-responses",
|
|
||||||
provider: "openrouter",
|
|
||||||
modelId: "mistralai/devstral-2512:free",
|
|
||||||
sessionManager: mockSessionManager,
|
|
||||||
sessionId: "test-session",
|
|
||||||
});
|
|
||||||
|
|
||||||
expect(helpers.sanitizeSessionMessagesImages).toHaveBeenCalledWith(
|
|
||||||
mockMessages,
|
|
||||||
"session:history",
|
|
||||||
expect.objectContaining({
|
|
||||||
sanitizeMode: "full",
|
|
||||||
sanitizeToolCallIds: true,
|
|
||||||
toolCallIdMode: "strict9",
|
|
||||||
}),
|
|
||||||
);
|
|
||||||
});
|
|
||||||
|
|
||||||
it("sanitizes tool call ids for Anthropic APIs", async () => {
|
|
||||||
vi.mocked(helpers.isGoogleModelApi).mockReturnValue(false);
|
|
||||||
|
|
||||||
await sanitizeSessionHistory({
|
|
||||||
messages: mockMessages,
|
|
||||||
modelApi: "anthropic-messages",
|
|
||||||
provider: "anthropic",
|
|
||||||
sessionManager: mockSessionManager,
|
|
||||||
sessionId: "test-session",
|
|
||||||
});
|
|
||||||
|
|
||||||
expect(helpers.sanitizeSessionMessagesImages).toHaveBeenCalledWith(
|
|
||||||
mockMessages,
|
|
||||||
"session:history",
|
|
||||||
expect.objectContaining({ sanitizeMode: "full", sanitizeToolCallIds: true }),
|
|
||||||
);
|
|
||||||
});
|
|
||||||
|
|
||||||
it("sanitizes tool call ids for openai-responses", async () => {
|
|
||||||
vi.mocked(helpers.isGoogleModelApi).mockReturnValue(false);
|
vi.mocked(helpers.isGoogleModelApi).mockReturnValue(false);
|
||||||
|
|
||||||
await sanitizeSessionHistory({
|
await sanitizeSessionHistory({
|
||||||
@@ -115,151 +69,7 @@ describe("sanitizeSessionHistory", () => {
|
|||||||
);
|
);
|
||||||
});
|
});
|
||||||
|
|
||||||
it("annotates inter-session user messages before context sanitization", async () => {
|
it("downgrades openai reasoning blocks when the model snapshot changed", async () => {
|
||||||
vi.mocked(helpers.isGoogleModelApi).mockReturnValue(false);
|
|
||||||
|
|
||||||
const messages: AgentMessage[] = [
|
|
||||||
{
|
|
||||||
role: "user",
|
|
||||||
content: "forwarded instruction",
|
|
||||||
provenance: {
|
|
||||||
kind: "inter_session",
|
|
||||||
sourceSessionKey: "agent:main:req",
|
|
||||||
sourceTool: "sessions_send",
|
|
||||||
},
|
|
||||||
} as unknown as AgentMessage,
|
|
||||||
];
|
|
||||||
|
|
||||||
const result = await sanitizeSessionHistory({
|
|
||||||
messages,
|
|
||||||
modelApi: "openai-responses",
|
|
||||||
provider: "openai",
|
|
||||||
sessionManager: mockSessionManager,
|
|
||||||
sessionId: "test-session",
|
|
||||||
});
|
|
||||||
|
|
||||||
const first = result[0] as Extract<AgentMessage, { role: "user" }>;
|
|
||||||
expect(first.role).toBe("user");
|
|
||||||
expect(typeof first.content).toBe("string");
|
|
||||||
expect(first.content as string).toContain("[Inter-session message]");
|
|
||||||
expect(first.content as string).toContain("sourceSession=agent:main:req");
|
|
||||||
});
|
|
||||||
|
|
||||||
it("keeps reasoning-only assistant messages for openai-responses", async () => {
|
|
||||||
vi.mocked(helpers.isGoogleModelApi).mockReturnValue(false);
|
|
||||||
|
|
||||||
const messages: AgentMessage[] = [
|
|
||||||
{ role: "user", content: "hello" },
|
|
||||||
{
|
|
||||||
role: "assistant",
|
|
||||||
stopReason: "aborted",
|
|
||||||
content: [
|
|
||||||
{
|
|
||||||
type: "thinking",
|
|
||||||
thinking: "reasoning",
|
|
||||||
thinkingSignature: "sig",
|
|
||||||
},
|
|
||||||
],
|
|
||||||
},
|
|
||||||
];
|
|
||||||
|
|
||||||
const result = await sanitizeSessionHistory({
|
|
||||||
messages,
|
|
||||||
modelApi: "openai-responses",
|
|
||||||
provider: "openai",
|
|
||||||
sessionManager: mockSessionManager,
|
|
||||||
sessionId: "test-session",
|
|
||||||
});
|
|
||||||
|
|
||||||
expect(result).toHaveLength(2);
|
|
||||||
expect(result[1]?.role).toBe("assistant");
|
|
||||||
});
|
|
||||||
|
|
||||||
it("does not synthesize tool results for openai-responses", async () => {
|
|
||||||
const messages: AgentMessage[] = [
|
|
||||||
{
|
|
||||||
role: "assistant",
|
|
||||||
content: [{ type: "toolCall", id: "call_1", name: "read", arguments: {} }],
|
|
||||||
},
|
|
||||||
];
|
|
||||||
|
|
||||||
const result = await sanitizeSessionHistory({
|
|
||||||
messages,
|
|
||||||
modelApi: "openai-responses",
|
|
||||||
provider: "openai",
|
|
||||||
sessionManager: mockSessionManager,
|
|
||||||
sessionId: "test-session",
|
|
||||||
});
|
|
||||||
|
|
||||||
expect(result).toHaveLength(1);
|
|
||||||
expect(result[0]?.role).toBe("assistant");
|
|
||||||
});
|
|
||||||
|
|
||||||
it("drops malformed tool calls missing input or arguments", async () => {
|
|
||||||
const messages: AgentMessage[] = [
|
|
||||||
{
|
|
||||||
role: "assistant",
|
|
||||||
content: [{ type: "toolCall", id: "call_1", name: "read" }],
|
|
||||||
},
|
|
||||||
{ role: "user", content: "hello" },
|
|
||||||
];
|
|
||||||
|
|
||||||
const result = await sanitizeSessionHistory({
|
|
||||||
messages,
|
|
||||||
modelApi: "openai-responses",
|
|
||||||
provider: "openai",
|
|
||||||
sessionManager: mockSessionManager,
|
|
||||||
sessionId: "test-session",
|
|
||||||
});
|
|
||||||
|
|
||||||
expect(result.map((msg) => msg.role)).toEqual(["user"]);
|
|
||||||
});
|
|
||||||
|
|
||||||
it("does not downgrade openai reasoning when the model has not changed", async () => {
|
|
||||||
const sessionEntries: Array<{ type: string; customType: string; data: unknown }> = [
|
|
||||||
{
|
|
||||||
type: "custom",
|
|
||||||
customType: "model-snapshot",
|
|
||||||
data: {
|
|
||||||
timestamp: Date.now(),
|
|
||||||
provider: "openai",
|
|
||||||
modelApi: "openai-responses",
|
|
||||||
modelId: "gpt-5.2-codex",
|
|
||||||
},
|
|
||||||
},
|
|
||||||
];
|
|
||||||
const sessionManager = {
|
|
||||||
getEntries: vi.fn(() => sessionEntries),
|
|
||||||
appendCustomEntry: vi.fn((customType: string, data: unknown) => {
|
|
||||||
sessionEntries.push({ type: "custom", customType, data });
|
|
||||||
}),
|
|
||||||
} as unknown as SessionManager;
|
|
||||||
const messages: AgentMessage[] = [
|
|
||||||
{
|
|
||||||
role: "assistant",
|
|
||||||
content: [
|
|
||||||
{
|
|
||||||
type: "thinking",
|
|
||||||
thinking: "reasoning",
|
|
||||||
thinkingSignature: JSON.stringify({ id: "rs_test", type: "reasoning" }),
|
|
||||||
},
|
|
||||||
],
|
|
||||||
},
|
|
||||||
];
|
|
||||||
|
|
||||||
const result = await sanitizeSessionHistory({
|
|
||||||
messages,
|
|
||||||
modelApi: "openai-responses",
|
|
||||||
provider: "openai",
|
|
||||||
modelId: "gpt-5.2-codex",
|
|
||||||
sessionManager,
|
|
||||||
sessionId: "test-session",
|
|
||||||
});
|
|
||||||
|
|
||||||
expect(result).toEqual(messages);
|
|
||||||
});
|
|
||||||
|
|
||||||
it("downgrades openai reasoning only when the model changes", async () => {
|
|
||||||
const sessionEntries: Array<{ type: string; customType: string; data: unknown }> = [
|
const sessionEntries: Array<{ type: string; customType: string; data: unknown }> = [
|
||||||
{
|
{
|
||||||
type: "custom",
|
type: "custom",
|
||||||
|
|||||||
Reference in New Issue
Block a user