openclaw/src/agents/tool-policy.test.ts

204 lines
7.1 KiB
TypeScript
Raw Normal View History

2026-01-13 06:32:59 +00:00
import { describe, expect, it } from "vitest";
import type { OpenClawConfig } from "../config/config.js";
2026-02-18 01:29:02 +00:00
import { isToolAllowed, resolveSandboxToolPolicyForAgent } from "./sandbox/tool-policy.js";
import type { SandboxToolPolicy } from "./sandbox/types.js";
import { TOOL_POLICY_CONFORMANCE } from "./tool-policy.conformance.js";
import {
applyOwnerOnlyToolPolicy,
expandToolGroups,
isOwnerOnlyToolName,
normalizeToolName,
resolveToolProfilePolicy,
TOOL_GROUPS,
} from "./tool-policy.js";
import type { AnyAgentTool } from "./tools/common.js";
2026-01-13 06:32:59 +00:00
function createOwnerPolicyTools() {
return [
{
name: "read",
// oxlint-disable-next-line typescript/no-explicit-any
execute: async () => ({ content: [], details: {} }) as any,
},
{
name: "cron",
ownerOnly: true,
// oxlint-disable-next-line typescript/no-explicit-any
execute: async () => ({ content: [], details: {} }) as any,
},
{
name: "gateway",
ownerOnly: true,
// oxlint-disable-next-line typescript/no-explicit-any
execute: async () => ({ content: [], details: {} }) as any,
},
{
name: "whatsapp_login",
// oxlint-disable-next-line typescript/no-explicit-any
execute: async () => ({ content: [], details: {} }) as any,
},
] as unknown as AnyAgentTool[];
}
2026-01-13 06:32:59 +00:00
describe("tool-policy", () => {
it("expands groups and normalizes aliases", () => {
const expanded = expandToolGroups(["group:runtime", "BASH", "apply-patch", "group:fs"]);
2026-01-13 06:32:59 +00:00
const set = new Set(expanded);
expect(set.has("exec")).toBe(true);
expect(set.has("process")).toBe(true);
2026-01-24 01:21:50 -06:00
expect(set.has("bash")).toBe(false);
2026-01-13 06:32:59 +00:00
expect(set.has("apply_patch")).toBe(true);
expect(set.has("read")).toBe(true);
expect(set.has("write")).toBe(true);
expect(set.has("edit")).toBe(true);
});
it("resolves known profiles and ignores unknown ones", () => {
const coding = resolveToolProfilePolicy("coding");
expect(coding?.allow).toContain("read");
2026-01-13 06:32:59 +00:00
expect(resolveToolProfilePolicy("nope")).toBeUndefined();
});
2026-01-30 03:15:10 +01:00
it("includes core tool groups in group:openclaw", () => {
const group = TOOL_GROUPS["group:openclaw"];
2026-01-13 06:32:59 +00:00
expect(group).toContain("browser");
expect(group).toContain("message");
Agents: add nested subagent orchestration controls and reduce subagent token waste (#14447) * Agents: add subagent orchestration controls * Agents: add subagent orchestration controls (WIP uncommitted changes) * feat(subagents): add depth-based spawn gating for sub-sub-agents * feat(subagents): tool policy, registry, and announce chain for nested agents * feat(subagents): system prompt, docs, changelog for nested sub-agents * fix(subagents): prevent model fallback override, show model during active runs, and block context overflow fallback Bug 1: When a session has an explicit model override (e.g., gpt/openai-codex), the fallback candidate logic in resolveFallbackCandidates silently appended the global primary model (opus) as a backstop. On reinjection/steer with a transient error, the session could fall back to opus which has a smaller context window and crash. Fix: when storedModelOverride is set, pass fallbacksOverride ?? [] instead of undefined, preventing the implicit primary backstop. Bug 2: Active subagents showed 'model n/a' in /subagents list because resolveModelDisplay only read entry.model/modelProvider (populated after run completes). Fix: fall back to modelOverride/providerOverride fields which are populated at spawn time via sessions.patch. Bug 3: Context overflow errors (prompt too long, context_length_exceeded) could theoretically escape runEmbeddedPiAgent and be treated as failover candidates in runWithModelFallback, causing a switch to a model with a smaller context window. Fix: in runWithModelFallback, detect context overflow errors via isLikelyContextOverflowError and rethrow them immediately instead of trying the next model candidate. * fix(subagents): track spawn depth in session store and fix announce routing for nested agents * Fix compaction status tracking and dedupe overflow compaction triggers * fix(subagents): enforce depth block via session store and implement cascade kill * fix: inject group chat context into system prompt * fix(subagents): always write model to session store at spawn time * Preserve spawnDepth when agent handler rewrites session entry * fix(subagents): suppress announce on steer-restart * fix(subagents): fallback spawned session model to runtime default * fix(subagents): enforce spawn depth when caller key resolves by sessionId * feat(subagents): implement active-first ordering for numeric targets and enhance task display - Added a test to verify that subagents with numeric targets follow an active-first list ordering. - Updated `resolveSubagentTarget` to sort subagent runs based on active status and recent activity. - Enhanced task display in command responses to prevent truncation of long task descriptions. - Introduced new utility functions for compacting task text and managing subagent run states. * fix(subagents): show model for active runs via run record fallback When the spawned model matches the agent's default model, the session store's override fields are intentionally cleared (isDefault: true). The model/modelProvider fields are only populated after the run completes. This left active subagents showing 'model n/a'. Fix: store the resolved model on SubagentRunRecord at registration time, and use it as a fallback in both display paths (subagents tool and /subagents command) when the session store entry has no model info. Changes: - SubagentRunRecord: add optional model field - registerSubagentRun: accept and persist model param - sessions-spawn-tool: pass resolvedModel to registerSubagentRun - subagents-tool: pass run record model as fallback to resolveModelDisplay - commands-subagents: pass run record model as fallback to resolveModelDisplay * feat(chat): implement session key resolution and reset on sidebar navigation - Added functions to resolve the main session key and reset chat state when switching sessions from the sidebar. - Updated the `renderTab` function to handle session key changes when navigating to the chat tab. - Introduced a test to verify that the session resets to "main" when opening chat from the sidebar navigation. * fix: subagent timeout=0 passthrough and fallback prompt duplication Bug 1: runTimeoutSeconds=0 now means 'no timeout' instead of applying 600s default - sessions-spawn-tool: default to undefined (not 0) when neither timeout param is provided; use != null check so explicit 0 passes through to gateway - agent.ts: accept 0 as valid timeout (resolveAgentTimeoutMs already handles 0 → MAX_SAFE_TIMEOUT_MS) Bug 2: model fallback no longer re-injects the original prompt as a duplicate - agent.ts: track fallback attempt index; on retries use a short continuation message instead of the full original prompt since the session file already contains it from the first attempt - Also skip re-sending images on fallback retries (already in session) * feat(subagents): truncate long task descriptions in subagents command output - Introduced a new utility function to format task previews, limiting their length to improve readability. - Updated the command handler to use the new formatting function, ensuring task descriptions are truncated appropriately. - Adjusted related tests to verify that long task descriptions are now truncated in the output. * refactor(subagents): update subagent registry path resolution and improve command output formatting - Replaced direct import of STATE_DIR with a utility function to resolve the state directory dynamically. - Enhanced the formatting of command output for active and recent subagents, adding separators for better readability. - Updated related tests to reflect changes in command output structure. * fix(subagent): default sessions_spawn to no timeout when runTimeoutSeconds omitted The previous fix (75a791106) correctly handled the case where runTimeoutSeconds was explicitly set to 0 ("no timeout"). However, when models omit the parameter entirely (which is common since the schema marks it as optional), runTimeoutSeconds resolved to undefined. undefined flowed through the chain as: sessions_spawn → timeout: undefined (since undefined != null is false) → gateway agent handler → agentCommand opts.timeout: undefined → resolveAgentTimeoutMs({ overrideSeconds: undefined }) → DEFAULT_AGENT_TIMEOUT_SECONDS (600s = 10 minutes) This caused subagents to be killed at exactly 10 minutes even though the user's intent (via TOOLS.md) was for subagents to run without a timeout. Fix: default runTimeoutSeconds to 0 (no timeout) when neither runTimeoutSeconds nor timeoutSeconds is provided by the caller. Subagent spawns are long-running by design and should not inherit the 600s agent-command default timeout. * fix(subagent): accept timeout=0 in agent-via-gateway path (second 600s default) * fix: thread timeout override through getReplyFromConfig dispatch path getReplyFromConfig called resolveAgentTimeoutMs({ cfg }) with no override, always falling back to the config default (600s). Add timeoutOverrideSeconds to GetReplyOptions and pass it through as overrideSeconds so callers of the dispatch chain can specify a custom timeout (0 = no timeout). This complements the existing timeout threading in agentCommand and the cron isolated-agent runner, which already pass overrideSeconds correctly. * feat(model-fallback): normalize OpenAI Codex model references and enhance fallback handling - Added normalization for OpenAI Codex model references, specifically converting "gpt-5.3-codex" to "openai-codex" before execution. - Updated the `resolveFallbackCandidates` function to utilize the new normalization logic. - Enhanced tests to verify the correct behavior of model normalization and fallback mechanisms. - Introduced a new test case to ensure that the normalization process works as expected for various input formats. * feat(tests): add unit tests for steer failure behavior in openclaw-tools - Introduced a new test file to validate the behavior of subagents when steer replacement dispatch fails. - Implemented tests to ensure that the announce behavior is restored correctly and that the suppression reason is cleared as expected. - Enhanced the subagent registry with a new function to clear steer restart suppression. - Updated related components to support the new test scenarios. * fix(subagents): replace stop command with kill in slash commands and documentation - Updated the `/subagents` command to replace `stop` with `kill` for consistency in controlling sub-agent runs. - Modified related documentation to reflect the change in command usage. - Removed legacy timeoutSeconds references from the sessions-spawn-tool schema and tests to streamline timeout handling. - Enhanced tests to ensure correct behavior of the updated commands and their interactions. * feat(tests): add unit tests for readLatestAssistantReply function - Introduced a new test file for the `readLatestAssistantReply` function to validate its behavior with various message scenarios. - Implemented tests to ensure the function correctly retrieves the latest assistant message and handles cases where the latest message has no text. - Mocked the gateway call to simulate different message histories for comprehensive testing. * feat(tests): enhance subagent kill-all cascade tests and announce formatting - Added a new test to verify that the `kill-all` command cascades through ended parents to active descendants in subagents. - Updated the subagent announce formatting tests to reflect changes in message structure, including the replacement of "Findings:" with "Result:" and the addition of new expectations for message content. - Improved the handling of long findings and stats in the announce formatting logic to ensure concise output. - Refactored related functions to enhance clarity and maintainability in the subagent registry and tools. * refactor(subagent): update announce formatting and remove unused constants - Modified the subagent announce formatting to replace "Findings:" with "Result:" and adjusted related expectations in tests. - Removed constants for maximum announce findings characters and summary words, simplifying the announcement logic. - Updated the handling of findings to retain full content instead of truncating, ensuring more informative outputs. - Cleaned up unused imports in the commands-subagents file to enhance code clarity. * feat(tests): enhance billing error handling in user-facing text - Added tests to ensure that normal text mentioning billing plans is not rewritten, preserving user context. - Updated the `isBillingErrorMessage` and `sanitizeUserFacingText` functions to improve handling of billing-related messages. - Introduced new test cases for various scenarios involving billing messages to ensure accurate processing and output. - Enhanced the subagent announce flow to correctly manage active descendant runs, preventing premature announcements. * feat(subagent): enhance workflow guidance and auto-announcement clarity - Added a new guideline in the subagent system prompt to emphasize trust in push-based completion, discouraging busy polling for status updates. - Updated documentation to clarify that sub-agents will automatically announce their results, improving user understanding of the workflow. - Enhanced tests to verify the new guidance on avoiding polling loops and to ensure the accuracy of the updated prompts. * fix(cron): avoid announcing interim subagent spawn acks * chore: clean post-rebase imports * fix(cron): fall back to child replies when parent stays interim * fix(subagents): make active-run guidance advisory * fix(subagents): update announce flow to handle active descendants and enhance test coverage - Modified the announce flow to defer announcements when active descendant runs are present, ensuring accurate status reporting. - Updated tests to verify the new behavior, including scenarios where no fallback requester is available and ensuring proper handling of finished subagents. - Enhanced the announce formatting to include an `expectFinal` flag for better clarity in the announcement process. * fix(subagents): enhance announce flow and formatting for user updates - Updated the announce flow to provide clearer instructions for user updates based on active subagent runs and requester context. - Refactored the announcement logic to improve clarity and ensure internal context remains private. - Enhanced tests to verify the new message expectations and formatting, including updated prompts for user-facing updates. - Introduced a new function to build reply instructions based on session context, improving the overall announcement process. * fix: resolve prep blockers and changelog placement (#14447) (thanks @tyler6204) * fix: restore cron delivery-plan import after rebase (#14447) (thanks @tyler6204) * fix: resolve test failures from rebase conflicts (#14447) (thanks @tyler6204) * fix: apply formatting after rebase (#14447) (thanks @tyler6204)
2026-02-14 22:03:45 -08:00
expect(group).toContain("subagents");
2026-01-13 06:32:59 +00:00
expect(group).toContain("session_status");
expect(group).toContain("tts");
2026-01-13 06:32:59 +00:00
});
it("normalizes tool names and aliases", () => {
expect(normalizeToolName(" BASH ")).toBe("exec");
expect(normalizeToolName("apply-patch")).toBe("apply_patch");
expect(normalizeToolName("READ")).toBe("read");
});
it("identifies owner-only tools", () => {
expect(isOwnerOnlyToolName("whatsapp_login")).toBe(true);
expect(isOwnerOnlyToolName("cron")).toBe(true);
expect(isOwnerOnlyToolName("gateway")).toBe(true);
expect(isOwnerOnlyToolName("read")).toBe(false);
});
it("strips owner-only tools for non-owner senders", async () => {
const tools = createOwnerPolicyTools();
const filtered = applyOwnerOnlyToolPolicy(tools, false);
expect(filtered.map((t) => t.name)).toEqual(["read"]);
});
it("keeps owner-only tools for the owner sender", async () => {
const tools = createOwnerPolicyTools();
const filtered = applyOwnerOnlyToolPolicy(tools, true);
expect(filtered.map((t) => t.name)).toEqual(["read", "cron", "gateway", "whatsapp_login"]);
});
it("honors ownerOnly metadata for custom tool names", async () => {
const tools = [
{
name: "custom_admin_tool",
ownerOnly: true,
// oxlint-disable-next-line typescript/no-explicit-any
execute: async () => ({ content: [], details: {} }) as any,
},
] as unknown as AnyAgentTool[];
expect(applyOwnerOnlyToolPolicy(tools, false)).toEqual([]);
expect(applyOwnerOnlyToolPolicy(tools, true)).toHaveLength(1);
});
2026-01-13 06:32:59 +00:00
});
describe("TOOL_POLICY_CONFORMANCE", () => {
it("matches exported TOOL_GROUPS exactly", () => {
expect(TOOL_POLICY_CONFORMANCE.toolGroups).toEqual(TOOL_GROUPS);
});
it("is JSON-serializable", () => {
expect(() => JSON.stringify(TOOL_POLICY_CONFORMANCE)).not.toThrow();
});
});
describe("sandbox tool policy", () => {
it("allows all tools with * allow", () => {
const policy: SandboxToolPolicy = { allow: ["*"], deny: [] };
expect(isToolAllowed(policy, "browser")).toBe(true);
});
it("denies all tools with * deny", () => {
const policy: SandboxToolPolicy = { allow: [], deny: ["*"] };
expect(isToolAllowed(policy, "read")).toBe(false);
});
it("supports wildcard patterns", () => {
const policy: SandboxToolPolicy = { allow: ["web_*"] };
expect(isToolAllowed(policy, "web_fetch")).toBe(true);
expect(isToolAllowed(policy, "read")).toBe(false);
});
it("applies deny before allow", () => {
const policy: SandboxToolPolicy = { allow: ["*"], deny: ["web_*"] };
expect(isToolAllowed(policy, "web_fetch")).toBe(false);
expect(isToolAllowed(policy, "read")).toBe(true);
});
it("treats empty allowlist as allow-all (with deny exceptions)", () => {
const policy: SandboxToolPolicy = { allow: [], deny: ["web_*"] };
expect(isToolAllowed(policy, "web_fetch")).toBe(false);
expect(isToolAllowed(policy, "read")).toBe(true);
});
it("expands tool groups + aliases in patterns", () => {
const policy: SandboxToolPolicy = {
allow: ["group:fs", "BASH"],
deny: ["apply_*"],
};
expect(isToolAllowed(policy, "read")).toBe(true);
expect(isToolAllowed(policy, "exec")).toBe(true);
expect(isToolAllowed(policy, "apply_patch")).toBe(false);
});
it("normalizes whitespace + case", () => {
const policy: SandboxToolPolicy = { allow: [" WEB_* "] };
expect(isToolAllowed(policy, "WEB_FETCH")).toBe(true);
});
});
describe("resolveSandboxToolPolicyForAgent", () => {
it("keeps allow-all semantics when allow is []", () => {
const cfg = {
tools: { sandbox: { tools: { allow: [], deny: ["browser"] } } },
} as unknown as OpenClawConfig;
const resolved = resolveSandboxToolPolicyForAgent(cfg, undefined);
expect(resolved.sources.allow).toEqual({
source: "global",
key: "tools.sandbox.tools.allow",
});
expect(resolved.allow).toEqual([]);
expect(resolved.deny).toEqual(["browser"]);
const policy: SandboxToolPolicy = { allow: resolved.allow, deny: resolved.deny };
expect(isToolAllowed(policy, "read")).toBe(true);
expect(isToolAllowed(policy, "browser")).toBe(false);
});
it("auto-adds image to explicit allowlists unless denied", () => {
const cfg = {
tools: { sandbox: { tools: { allow: ["read"], deny: ["browser"] } } },
} as unknown as OpenClawConfig;
const resolved = resolveSandboxToolPolicyForAgent(cfg, undefined);
expect(resolved.allow).toEqual(["read", "image"]);
expect(resolved.deny).toEqual(["browser"]);
});
it("does not auto-add image when explicitly denied", () => {
const cfg = {
tools: { sandbox: { tools: { allow: ["read"], deny: ["image"] } } },
} as unknown as OpenClawConfig;
const resolved = resolveSandboxToolPolicyForAgent(cfg, undefined);
expect(resolved.allow).toEqual(["read"]);
expect(resolved.deny).toEqual(["image"]);
});
});