mirror of
https://github.com/openclaw/openclaw.git
synced 2026-06-06 02:12:59 +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
368 lines
12 KiB
TypeScript
368 lines
12 KiB
TypeScript
import { afterEach, describe, expect, it, vi } from "vitest";
|
|
import * as loggingConfigModule from "../logging/config.js";
|
|
import {
|
|
buildToolLifecycleErrorResult,
|
|
extractToolErrorCode,
|
|
extractToolErrorMessage,
|
|
sanitizeToolArgs,
|
|
sanitizeToolResult,
|
|
} from "./embedded-agent-subscribe.tools.js";
|
|
|
|
afterEach(() => {
|
|
vi.restoreAllMocks();
|
|
});
|
|
|
|
describe("extractToolErrorMessage", () => {
|
|
it("ignores non-error status values", () => {
|
|
expect(extractToolErrorMessage({ details: { status: "0" } })).toBeUndefined();
|
|
expect(extractToolErrorMessage({ details: { status: "completed" } })).toBeUndefined();
|
|
expect(extractToolErrorMessage({ details: { status: "ok" } })).toBeUndefined();
|
|
});
|
|
|
|
it("keeps error-like status values", () => {
|
|
expect(extractToolErrorMessage({ details: { status: "failed" } })).toBe("failed");
|
|
expect(extractToolErrorMessage({ details: { status: "timeout" } })).toBe("timeout");
|
|
});
|
|
|
|
it("prefers node-host aggregated denial text over generic failed status", () => {
|
|
expect(
|
|
extractToolErrorMessage({
|
|
content: [{ type: "text", text: "SYSTEM_RUN_DENIED: approval required" }],
|
|
details: {
|
|
status: "failed",
|
|
aggregated: "SYSTEM_RUN_DENIED: approval required",
|
|
},
|
|
}),
|
|
).toBe("SYSTEM_RUN_DENIED: approval required");
|
|
});
|
|
|
|
it("does not promote prose-only denial output ahead of generic failed status", () => {
|
|
expect(
|
|
extractToolErrorMessage({
|
|
content: [{ type: "text", text: "SYSTEM_RUN_DENIED: approval required" }],
|
|
details: { status: "failed" },
|
|
}),
|
|
).toBe("failed");
|
|
});
|
|
|
|
it("extracts structured tool error codes", () => {
|
|
expect(
|
|
extractToolErrorCode({
|
|
details: {
|
|
status: "failed",
|
|
error: {
|
|
code: "SYSTEM_RUN_DENIED",
|
|
message: "approval required",
|
|
},
|
|
},
|
|
}),
|
|
).toBe("SYSTEM_RUN_DENIED");
|
|
expect(
|
|
extractToolErrorCode({
|
|
details: {
|
|
status: "failed",
|
|
gatewayCode: "UNAVAILABLE",
|
|
nodeError: {
|
|
code: "UNAVAILABLE",
|
|
message: "SYSTEM_RUN_DENIED: approval required",
|
|
},
|
|
},
|
|
}),
|
|
).toBe("SYSTEM_RUN_DENIED");
|
|
expect(
|
|
extractToolErrorCode({
|
|
details: {
|
|
status: "failed",
|
|
nodeError: {
|
|
code: "INVALID_REQUEST",
|
|
message: "approval expired",
|
|
},
|
|
},
|
|
}),
|
|
).toBe("INVALID_REQUEST");
|
|
});
|
|
|
|
it("does not extract error codes from prose-only tool output", () => {
|
|
expect(
|
|
extractToolErrorCode({
|
|
content: [{ type: "text", text: "SYSTEM_RUN_DENIED: approval required" }],
|
|
details: { status: "failed" },
|
|
}),
|
|
).toBeUndefined();
|
|
expect(
|
|
extractToolErrorCode({
|
|
details: {
|
|
status: "failed",
|
|
error: "SYSTEM_RUN_DENIED: approval required",
|
|
},
|
|
}),
|
|
).toBeUndefined();
|
|
});
|
|
|
|
it("preserves structured codes from thrown gateway errors", () => {
|
|
const error = new Error("UNAVAILABLE: SYSTEM_RUN_DENIED: approval required") as Error & {
|
|
gatewayCode?: string;
|
|
details?: unknown;
|
|
};
|
|
error.gatewayCode = "UNAVAILABLE";
|
|
error.details = {
|
|
nodeError: {
|
|
code: "UNAVAILABLE",
|
|
message: "SYSTEM_RUN_DENIED: approval required",
|
|
},
|
|
};
|
|
|
|
const result = buildToolLifecycleErrorResult(error);
|
|
|
|
expect(extractToolErrorCode(result)).toBe("SYSTEM_RUN_DENIED");
|
|
expect(extractToolErrorMessage(result)).toBe(
|
|
"UNAVAILABLE: SYSTEM_RUN_DENIED: approval required",
|
|
);
|
|
});
|
|
});
|
|
|
|
function getTextContent(result: unknown, index = 0): string {
|
|
const record = result as { content: Array<{ text: string }> };
|
|
return record.content[index].text;
|
|
}
|
|
|
|
describe("sanitizeToolResult", () => {
|
|
it("redacts JSON-style apiKey fields in text content blocks", () => {
|
|
const result = {
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: '{"apiKey":"sk-1234567890abcdef","model":"gpt-4"}',
|
|
},
|
|
],
|
|
};
|
|
const text = getTextContent(sanitizeToolResult(result));
|
|
expect(text).not.toContain("sk-1234567890abcdef");
|
|
expect(text).toContain("model");
|
|
});
|
|
|
|
it("redacts Link-like payment credential fields in tool result payloads", () => {
|
|
const result = {
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: '{"shared_payment_token":"spt_abcdefghijklmnopqrstuvwxyz","paymentCredential":"paycred_abcdefghijklmnopqrstuvwxyz","card_number":"4242424242424242","cvc":"123","amount":"4200"}',
|
|
},
|
|
],
|
|
details: {
|
|
structuredContent: {
|
|
sharedPaymentToken: "spt_zyxwvutsrqponmlkjihgfedcba",
|
|
cardNumber: "4000056655665556",
|
|
amount: "4200",
|
|
},
|
|
},
|
|
};
|
|
const sanitized = sanitizeToolResult(result) as {
|
|
content: Array<{ text: string }>;
|
|
details: {
|
|
structuredContent: { sharedPaymentToken: string; cardNumber: string; amount: string };
|
|
};
|
|
};
|
|
const serialized = JSON.stringify(sanitized);
|
|
expect(serialized).not.toContain("spt_abcdefghijklmnopqrstuvwxyz");
|
|
expect(serialized).not.toContain("paycred_abcdefghijklmnopqrstuvwxyz");
|
|
expect(serialized).not.toContain("4242424242424242");
|
|
expect(serialized).not.toContain("123");
|
|
expect(serialized).not.toContain("spt_zyxwvutsrqponmlkjihgfedcba");
|
|
expect(serialized).not.toContain("4000056655665556");
|
|
expect(sanitized.content[0]?.text).toContain('"amount":"4200"');
|
|
expect(sanitized.details.structuredContent.amount).toBe("4200");
|
|
});
|
|
|
|
it("redacts ENV-style credential assignments", () => {
|
|
const result = {
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: "OPENROUTER_API_KEY=sk-or-v1-abcdef0123456789\nMODEL=gpt-4",
|
|
},
|
|
],
|
|
};
|
|
const text = getTextContent(sanitizeToolResult(result));
|
|
expect(text).not.toContain("sk-or-v1-abcdef0123456789");
|
|
expect(text).toContain("MODEL=gpt-4");
|
|
});
|
|
|
|
it("preserves env placeholders in tool output text", () => {
|
|
const result = {
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: 'DISCORD_BOT_TOKEN="${DISCORD_BOT_TOKEN:-}"\nTELEGRAM_BOT_TOKEN="${TELEGRAM_BOT_TOKEN:-}"',
|
|
},
|
|
],
|
|
};
|
|
|
|
const text = getTextContent(sanitizeToolResult(result));
|
|
|
|
expect(text).toBe(
|
|
'DISCORD_BOT_TOKEN="${DISCORD_BOT_TOKEN:-}"\nTELEGRAM_BOT_TOKEN="${TELEGRAM_BOT_TOKEN:-}"',
|
|
);
|
|
});
|
|
|
|
it("redacts Bearer authorization tokens", () => {
|
|
const result = {
|
|
content: [{ type: "text", text: "Authorization: Bearer abcdef0123456789QWERTY=" }],
|
|
};
|
|
const text = getTextContent(sanitizeToolResult(result));
|
|
expect(text).not.toContain("abcdef0123456789QWERTY=");
|
|
});
|
|
|
|
it("preserves image content stripping behavior", () => {
|
|
const result = {
|
|
content: [{ type: "image", data: "base64imagedata", mimeType: "image/png" }],
|
|
};
|
|
const sanitized = sanitizeToolResult(result) as {
|
|
content: Array<{ data?: string; bytes?: number; omitted?: boolean }>;
|
|
};
|
|
expect(sanitized.content[0].data).toBeUndefined();
|
|
expect(sanitized.content[0].omitted).toBe(true);
|
|
expect(sanitized.content[0].bytes).toBe("base64imagedata".length);
|
|
});
|
|
|
|
it("redacts secrets inside result.details (e.g. exec aggregated stdout)", () => {
|
|
const result = {
|
|
content: [{ type: "text", text: "ok" }],
|
|
details: {
|
|
status: "completed",
|
|
aggregated:
|
|
'OPENROUTER_API_KEY=sk-or-v1-abcdef0123456789\napiKey: "ghp_abcdefghij1234567890"',
|
|
exitCode: 0,
|
|
cwd: "/tmp/work",
|
|
},
|
|
};
|
|
const sanitized = sanitizeToolResult(result) as {
|
|
details: { status: string; aggregated: string; exitCode: number; cwd: string };
|
|
};
|
|
expect(sanitized.details.aggregated).not.toContain("sk-or-v1-abcdef0123456789");
|
|
expect(sanitized.details.aggregated).not.toContain("ghp_abcdefghij1234567890");
|
|
expect(sanitized.details.status).toBe("completed");
|
|
expect(sanitized.details.exitCode).toBe(0);
|
|
expect(sanitized.details.cwd).toBe("/tmp/work");
|
|
});
|
|
|
|
it("redacts secrets at the top level outside content/details", () => {
|
|
const result = {
|
|
output: "OPENROUTER_API_KEY=sk-or-v1-abcdef0123456789",
|
|
metadata: {
|
|
token: "ghp_abcdefghij1234567890ABCDEF",
|
|
nested: { auth: "Bearer abcdef0123456789QWERTY=" },
|
|
},
|
|
summary: "ok",
|
|
};
|
|
const sanitized = sanitizeToolResult(result) as {
|
|
output: string;
|
|
metadata: { token: string; nested: { auth: string } };
|
|
summary: string;
|
|
};
|
|
expect(sanitized.output).not.toContain("sk-or-v1-abcdef0123456789");
|
|
expect(sanitized.metadata.token).not.toContain("ghp_abcdefghij1234567890ABCDEF");
|
|
expect(sanitized.metadata.nested.auth).not.toContain("abcdef0123456789QWERTY=");
|
|
expect(sanitized.summary).toBe("ok");
|
|
});
|
|
|
|
it("redacts a details-only result with no content array", () => {
|
|
const result = {
|
|
details: {
|
|
config: { apiKey: "sk-1234567890abcdefXYZ", model: "gpt-4" },
|
|
},
|
|
};
|
|
const sanitized = sanitizeToolResult(result) as {
|
|
details: { config: { apiKey: string; model: string } };
|
|
};
|
|
expect(sanitized.details.config.apiKey).not.toContain("sk-1234567890abcdefXYZ");
|
|
expect(sanitized.details.config.model).toBe("gpt-4");
|
|
});
|
|
|
|
it("redacts primitive string results", () => {
|
|
const sanitized = sanitizeToolResult("OPENROUTER_API_KEY=sk-or-v1-abcdef0123456789") as string;
|
|
|
|
expect(sanitized).not.toContain("sk-or-v1-abcdef0123456789");
|
|
expect(sanitized).toContain("OPENROUTER_API_KEY=");
|
|
});
|
|
|
|
it("preserves top-level arrays while redacting nested strings", () => {
|
|
const sanitized = sanitizeToolResult([
|
|
{ output: "Authorization: Bearer abcdef0123456789QWERTY=" },
|
|
"apiKey=sk-1234567890abcdefXYZ",
|
|
]) as Array<{ output: string } | string>;
|
|
|
|
expect(Array.isArray(sanitized)).toBe(true);
|
|
expect(JSON.stringify(sanitized)).not.toContain("abcdef0123456789QWERTY=");
|
|
expect(JSON.stringify(sanitized)).not.toContain("sk-1234567890abcdefXYZ");
|
|
expect((sanitized[0] as { output: string }).output).toContain("Authorization: Bearer");
|
|
});
|
|
|
|
it("applies configured redact patterns to Control UI tool payloads", () => {
|
|
vi.spyOn(loggingConfigModule, "readLoggingConfig").mockReturnValue({
|
|
redactSensitive: "off",
|
|
redactPatterns: [String.raw`\bcustom-secret-[A-Za-z0-9]+\b`],
|
|
});
|
|
|
|
const result = {
|
|
content: [{ type: "text", text: "value custom-secret-abc123" }],
|
|
};
|
|
const text = getTextContent(sanitizeToolResult(result));
|
|
|
|
expect(text).not.toContain("custom-secret-abc123");
|
|
expect(text).toContain("custom…c123");
|
|
});
|
|
});
|
|
|
|
describe("sanitizeToolArgs", () => {
|
|
it("redacts string-valued credentials nested anywhere in args", () => {
|
|
const args = {
|
|
apiKey: "sk-1234567890abcdefXYZ",
|
|
headers: { Authorization: "Bearer abcdef0123456789QWERTY=" },
|
|
command: "OPENROUTER_API_KEY=sk-or-v1-abcdef0123456789 ./run.sh",
|
|
flags: ["--api-key", "sk-1234567890abcdefXYZ"],
|
|
};
|
|
const sanitized = sanitizeToolArgs(args) as {
|
|
apiKey: string;
|
|
headers: { Authorization: string };
|
|
command: string;
|
|
flags: string[];
|
|
};
|
|
expect(sanitized.apiKey).not.toContain("sk-1234567890abcdefXYZ");
|
|
expect(sanitized.headers.Authorization).not.toContain("abcdef0123456789QWERTY=");
|
|
expect(sanitized.command).not.toContain("sk-or-v1-abcdef0123456789");
|
|
expect(sanitized.flags.join(" ")).not.toContain("sk-1234567890abcdefXYZ");
|
|
expect(sanitized.flags[0]).toBe("--api-key");
|
|
});
|
|
|
|
it("preserves structured env placeholders in args", () => {
|
|
const args = {
|
|
DISCORD_BOT_TOKEN: "${DISCORD_BOT_TOKEN:-}",
|
|
nested: {
|
|
apiKey: "${OPENAI_API_KEY:-}",
|
|
GITHUB_TOKEN: "${GITHUB_TOKEN:-literalgithub1234567890}",
|
|
},
|
|
};
|
|
const sanitized = sanitizeToolArgs(args) as {
|
|
DISCORD_BOT_TOKEN: string;
|
|
nested: {
|
|
apiKey: string;
|
|
GITHUB_TOKEN: string;
|
|
};
|
|
};
|
|
expect(sanitized.DISCORD_BOT_TOKEN).toBe("${DISCORD_BOT_TOKEN:-}");
|
|
expect(sanitized.nested.apiKey).toBe("${OPEN…Y:-}");
|
|
expect(sanitized.nested.GITHUB_TOKEN).toBe("${GITHUB_TOKEN:-liter…890}");
|
|
});
|
|
|
|
it("passes through null/undefined and non-string primitives unchanged", () => {
|
|
expect(sanitizeToolArgs(undefined)).toBeUndefined();
|
|
expect(sanitizeToolArgs(null)).toBeNull();
|
|
expect(sanitizeToolArgs(42)).toBe(42);
|
|
expect(sanitizeToolArgs({ count: 3, file_path: "/tmp/x.txt" })).toEqual({
|
|
count: 3,
|
|
file_path: "/tmp/x.txt",
|
|
});
|
|
});
|
|
});
|