mirror of
https://github.com/openclaw/openclaw.git
synced 2026-05-07 21:21:24 +00:00
* 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)
502 lines
16 KiB
TypeScript
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 });
|
|
}
|
|
});
|
|
});
|