Files
openclaw/src/agents/pi-tools.create-openclaw-coding-tools.adds-claude-style-aliases-schemas-without-dropping.e2e.test.ts
Tyler Yust b8f66c260d 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

502 lines
16 KiB
TypeScript

import type { AgentTool } from "@mariozechner/pi-agent-core";
import fs from "node:fs/promises";
import os from "node:os";
import path from "node:path";
import { describe, expect, it, vi } from "vitest";
import "./test-helpers/fast-coding-tools.js";
import { createOpenClawTools } from "./openclaw-tools.js";
import { __testing, createOpenClawCodingTools } from "./pi-tools.js";
import { createSandboxedReadTool } from "./pi-tools.read.js";
import { createHostSandboxFsBridge } from "./test-helpers/host-sandbox-fs-bridge.js";
import { createBrowserTool } from "./tools/browser-tool.js";
const defaultTools = createOpenClawCodingTools();
function findUnionKeywordOffenders(
tools: Array<{ name: string; parameters: unknown }>,
opts?: { onlyNames?: Set<string> },
) {
const offenders: Array<{
name: string;
keyword: string;
path: string;
}> = [];
const keywords = new Set(["anyOf", "oneOf", "allOf"]);
const walk = (value: unknown, path: string, name: string): void => {
if (!value) {
return;
}
if (Array.isArray(value)) {
for (const [index, entry] of value.entries()) {
walk(entry, `${path}[${index}]`, name);
}
return;
}
if (typeof value !== "object") {
return;
}
const record = value as Record<string, unknown>;
for (const [key, entry] of Object.entries(record)) {
const nextPath = path ? `${path}.${key}` : key;
if (keywords.has(key)) {
offenders.push({ name, keyword: key, path: nextPath });
}
walk(entry, nextPath, name);
}
};
for (const tool of tools) {
if (opts?.onlyNames && !opts.onlyNames.has(tool.name)) {
continue;
}
walk(tool.parameters, "", tool.name);
}
return offenders;
}
describe("createOpenClawCodingTools", () => {
describe("Claude/Gemini alias support", () => {
it("adds Claude-style aliases to schemas without dropping metadata", () => {
const base: AgentTool = {
name: "write",
description: "test",
parameters: {
type: "object",
required: ["path", "content"],
properties: {
path: { type: "string", description: "Path" },
content: { type: "string", description: "Body" },
},
},
execute: vi.fn(),
};
const patched = __testing.patchToolSchemaForClaudeCompatibility(base);
const params = patched.parameters as {
properties?: Record<string, unknown>;
required?: string[];
};
const props = params.properties ?? {};
expect(props.file_path).toEqual(props.path);
expect(params.required ?? []).not.toContain("path");
expect(params.required ?? []).not.toContain("file_path");
});
it("normalizes file_path to path and enforces required groups at runtime", async () => {
const execute = vi.fn(async (_id, args) => args);
const tool: AgentTool = {
name: "write",
description: "test",
parameters: {
type: "object",
required: ["path", "content"],
properties: {
path: { type: "string" },
content: { type: "string" },
},
},
execute,
};
const wrapped = __testing.wrapToolParamNormalization(tool, [{ keys: ["path", "file_path"] }]);
await wrapped.execute("tool-1", { file_path: "foo.txt", content: "x" });
expect(execute).toHaveBeenCalledWith(
"tool-1",
{ path: "foo.txt", content: "x" },
undefined,
undefined,
);
await expect(wrapped.execute("tool-2", { content: "x" })).rejects.toThrow(
/Missing required parameter/,
);
await expect(wrapped.execute("tool-3", { file_path: " ", content: "x" })).rejects.toThrow(
/Missing required parameter/,
);
});
});
it("keeps browser tool schema OpenAI-compatible without normalization", () => {
const browser = createBrowserTool();
const schema = browser.parameters as { type?: unknown; anyOf?: unknown };
expect(schema.type).toBe("object");
expect(schema.anyOf).toBeUndefined();
});
it("mentions Chrome extension relay in browser tool description", () => {
const browser = createBrowserTool();
expect(browser.description).toMatch(/Chrome extension/i);
expect(browser.description).toMatch(/profile="chrome"/i);
});
it("keeps browser tool schema properties after normalization", () => {
const browser = defaultTools.find((tool) => tool.name === "browser");
expect(browser).toBeDefined();
const parameters = browser?.parameters as {
anyOf?: unknown[];
properties?: Record<string, unknown>;
required?: string[];
};
expect(parameters.properties?.action).toBeDefined();
expect(parameters.properties?.target).toBeDefined();
expect(parameters.properties?.targetUrl).toBeDefined();
expect(parameters.properties?.request).toBeDefined();
expect(parameters.required ?? []).toContain("action");
});
it("exposes raw for gateway config.apply tool calls", () => {
const gateway = defaultTools.find((tool) => tool.name === "gateway");
expect(gateway).toBeDefined();
const parameters = gateway?.parameters as {
type?: unknown;
required?: string[];
properties?: Record<string, unknown>;
};
expect(parameters.type).toBe("object");
expect(parameters.properties?.raw).toBeDefined();
expect(parameters.required ?? []).not.toContain("raw");
});
it("flattens anyOf-of-literals to enum for provider compatibility", () => {
const browser = defaultTools.find((tool) => tool.name === "browser");
expect(browser).toBeDefined();
const parameters = browser?.parameters as {
properties?: Record<string, unknown>;
};
const action = parameters.properties?.action as
| {
type?: unknown;
enum?: unknown[];
anyOf?: unknown[];
}
| undefined;
expect(action?.type).toBe("string");
expect(action?.anyOf).toBeUndefined();
expect(Array.isArray(action?.enum)).toBe(true);
expect(action?.enum).toContain("act");
const snapshotFormat = parameters.properties?.snapshotFormat as
| {
type?: unknown;
enum?: unknown[];
anyOf?: unknown[];
}
| undefined;
expect(snapshotFormat?.type).toBe("string");
expect(snapshotFormat?.anyOf).toBeUndefined();
expect(snapshotFormat?.enum).toEqual(["aria", "ai"]);
});
it("inlines local $ref before removing unsupported keywords", () => {
const cleaned = __testing.cleanToolSchemaForGemini({
type: "object",
properties: {
foo: { $ref: "#/$defs/Foo" },
},
$defs: {
Foo: { type: "string", enum: ["a", "b"] },
},
}) as {
$defs?: unknown;
properties?: Record<string, unknown>;
};
expect(cleaned.$defs).toBeUndefined();
expect(cleaned.properties).toBeDefined();
expect(cleaned.properties?.foo).toMatchObject({
type: "string",
enum: ["a", "b"],
});
});
it("cleans tuple items schemas", () => {
const cleaned = __testing.cleanToolSchemaForGemini({
type: "object",
properties: {
tuples: {
type: "array",
items: [
{ type: "string", format: "uuid" },
{ type: "number", minimum: 1 },
],
},
},
}) as {
properties?: Record<string, unknown>;
};
const tuples = cleaned.properties?.tuples as { items?: unknown } | undefined;
const items = Array.isArray(tuples?.items) ? tuples?.items : [];
const first = items[0] as { format?: unknown } | undefined;
const second = items[1] as { minimum?: unknown } | undefined;
expect(first?.format).toBeUndefined();
expect(second?.minimum).toBeUndefined();
});
it("drops null-only union variants without flattening other unions", () => {
const cleaned = __testing.cleanToolSchemaForGemini({
type: "object",
properties: {
parentId: { anyOf: [{ type: "string" }, { type: "null" }] },
count: { oneOf: [{ type: "string" }, { type: "number" }] },
},
}) as {
properties?: Record<string, unknown>;
};
const parentId = cleaned.properties?.parentId as
| { type?: unknown; anyOf?: unknown; oneOf?: unknown }
| undefined;
const count = cleaned.properties?.count as
| { type?: unknown; anyOf?: unknown; oneOf?: unknown }
| undefined;
expect(parentId?.type).toBe("string");
expect(parentId?.anyOf).toBeUndefined();
expect(count?.oneOf).toBeDefined();
});
it("avoids anyOf/oneOf/allOf in tool schemas", () => {
expect(findUnionKeywordOffenders(defaultTools)).toEqual([]);
});
it("keeps raw core tool schemas union-free", () => {
const tools = createOpenClawTools();
const coreTools = new Set([
"browser",
"canvas",
"nodes",
"cron",
"message",
"gateway",
"agents_list",
"sessions_list",
"sessions_history",
"sessions_send",
"sessions_spawn",
"subagents",
"session_status",
"image",
]);
expect(findUnionKeywordOffenders(tools, { onlyNames: coreTools })).toEqual([]);
});
it("does not expose provider-specific message tools", () => {
const tools = createOpenClawCodingTools({ messageProvider: "discord" });
const names = new Set(tools.map((tool) => tool.name));
expect(names.has("discord")).toBe(false);
expect(names.has("slack")).toBe(false);
expect(names.has("telegram")).toBe(false);
expect(names.has("whatsapp")).toBe(false);
});
it("filters session tools for sub-agent sessions by default", () => {
const tools = createOpenClawCodingTools({
sessionKey: "agent:main:subagent:test",
});
const names = new Set(tools.map((tool) => tool.name));
expect(names.has("sessions_list")).toBe(false);
expect(names.has("sessions_history")).toBe(false);
expect(names.has("sessions_send")).toBe(false);
expect(names.has("sessions_spawn")).toBe(false);
// Explicit subagent orchestration tool remains available (list/steer/kill with safeguards).
expect(names.has("subagents")).toBe(true);
expect(names.has("read")).toBe(true);
expect(names.has("exec")).toBe(true);
expect(names.has("process")).toBe(true);
expect(names.has("apply_patch")).toBe(false);
});
it("uses stored spawnDepth to apply leaf tool policy for flat depth-2 session keys", async () => {
const tmpDir = await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-depth-policy-"));
const storeTemplate = path.join(tmpDir, "sessions-{agentId}.json");
const storePath = storeTemplate.replaceAll("{agentId}", "main");
await fs.writeFile(
storePath,
JSON.stringify(
{
"agent:main:subagent:flat": {
sessionId: "session-flat-depth-2",
updatedAt: Date.now(),
spawnDepth: 2,
},
},
null,
2,
),
"utf-8",
);
const tools = createOpenClawCodingTools({
sessionKey: "agent:main:subagent:flat",
config: {
session: {
store: storeTemplate,
},
agents: {
defaults: {
subagents: {
maxSpawnDepth: 2,
},
},
},
},
});
const names = new Set(tools.map((tool) => tool.name));
expect(names.has("sessions_spawn")).toBe(false);
expect(names.has("sessions_list")).toBe(false);
expect(names.has("sessions_history")).toBe(false);
expect(names.has("subagents")).toBe(true);
});
it("supports allow-only sub-agent tool policy", () => {
const tools = createOpenClawCodingTools({
sessionKey: "agent:main:subagent:test",
// Intentionally partial config; only fields used by pi-tools are provided.
config: {
tools: {
subagents: {
tools: {
// Policy matching is case-insensitive
allow: ["read"],
},
},
},
},
});
expect(tools.map((tool) => tool.name)).toEqual(["read"]);
});
it("applies tool profiles before allow/deny policies", () => {
const tools = createOpenClawCodingTools({
config: { tools: { profile: "messaging" } },
});
const names = new Set(tools.map((tool) => tool.name));
expect(names.has("message")).toBe(true);
expect(names.has("sessions_send")).toBe(true);
expect(names.has("sessions_spawn")).toBe(false);
expect(names.has("exec")).toBe(false);
expect(names.has("browser")).toBe(false);
});
it("expands group shorthands in global tool policy", () => {
const tools = createOpenClawCodingTools({
config: { tools: { allow: ["group:fs"] } },
});
const names = new Set(tools.map((tool) => tool.name));
expect(names.has("read")).toBe(true);
expect(names.has("write")).toBe(true);
expect(names.has("edit")).toBe(true);
expect(names.has("exec")).toBe(false);
expect(names.has("browser")).toBe(false);
});
it("expands group shorthands in global tool deny policy", () => {
const tools = createOpenClawCodingTools({
config: { tools: { deny: ["group:fs"] } },
});
const names = new Set(tools.map((tool) => tool.name));
expect(names.has("read")).toBe(false);
expect(names.has("write")).toBe(false);
expect(names.has("edit")).toBe(false);
expect(names.has("exec")).toBe(true);
});
it("lets agent profiles override global profiles", () => {
const tools = createOpenClawCodingTools({
sessionKey: "agent:work:main",
config: {
tools: { profile: "coding" },
agents: {
list: [{ id: "work", tools: { profile: "messaging" } }],
},
},
});
const names = new Set(tools.map((tool) => tool.name));
expect(names.has("message")).toBe(true);
expect(names.has("exec")).toBe(false);
expect(names.has("read")).toBe(false);
});
it("removes unsupported JSON Schema keywords for Cloud Code Assist API compatibility", () => {
// Helper to recursively check schema for unsupported keywords
const unsupportedKeywords = new Set([
"patternProperties",
"additionalProperties",
"$schema",
"$id",
"$ref",
"$defs",
"definitions",
"examples",
"minLength",
"maxLength",
"minimum",
"maximum",
"multipleOf",
"pattern",
"format",
"minItems",
"maxItems",
"uniqueItems",
"minProperties",
"maxProperties",
]);
const findUnsupportedKeywords = (schema: unknown, path: string): string[] => {
const found: string[] = [];
if (!schema || typeof schema !== "object") {
return found;
}
if (Array.isArray(schema)) {
schema.forEach((item, i) => {
found.push(...findUnsupportedKeywords(item, `${path}[${i}]`));
});
return found;
}
const record = schema as Record<string, unknown>;
const properties =
record.properties &&
typeof record.properties === "object" &&
!Array.isArray(record.properties)
? (record.properties as Record<string, unknown>)
: undefined;
if (properties) {
for (const [key, value] of Object.entries(properties)) {
found.push(...findUnsupportedKeywords(value, `${path}.properties.${key}`));
}
}
for (const [key, value] of Object.entries(record)) {
if (key === "properties") {
continue;
}
if (unsupportedKeywords.has(key)) {
found.push(`${path}.${key}`);
}
if (value && typeof value === "object") {
found.push(...findUnsupportedKeywords(value, `${path}.${key}`));
}
}
return found;
};
for (const tool of defaultTools) {
const violations = findUnsupportedKeywords(tool.parameters, `${tool.name}.parameters`);
expect(violations).toEqual([]);
}
});
it("applies sandbox path guards to file_path alias", async () => {
const tmpDir = await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-sbx-"));
const outsidePath = path.join(os.tmpdir(), "openclaw-outside.txt");
await fs.writeFile(outsidePath, "outside", "utf8");
try {
const readTool = createSandboxedReadTool({
root: tmpDir,
bridge: createHostSandboxFsBridge(tmpDir),
});
await expect(readTool.execute("sandbox-1", { file_path: outsidePath })).rejects.toThrow(
/sandbox root/i,
);
} finally {
await fs.rm(outsidePath, { force: true });
await fs.rm(tmpDir, { recursive: true, force: true });
}
});
});