Files
rea/tests/boundary/cli/cliToolCoverage.test.ts
gensokyo-dev f72638f6b1 feat(investigation)!: retain records across engine cleanup (#8361)
Separate engine cleanup, investigation reset and terminal disposal in the shared application owner. Keep stable Evidence IDs and full Unknown revision history through engine close and target changes; serialize reset with all record writers and cleanup owners, optionally acknowledging a complete checkpoint before clearing. Bound retained representation without eviction.

Validation: 43 focused files / 533 distinct tests, source/type/lint/schema/documentation checks, nine genuine source cases across eight families, real Ghidra session identity and cleanup, and nine actual local Codex CLI terra/high runs with independent full-result and checkpoint audits. See docs/verification/investigation-lifecycle.md for measurements, partial attempts and verification limits.

Fixes #8347.

BREAKING CHANGE: close_binary retains investigation records. Use reset_investigation to clear them. Cross-process recovery requires an explicitly acknowledged Evidence bundle checkpoint.

Assisted-by: Suika (gensokyo-skills:suika-scatter-gather-planning)
2026-10-31 21:34:45 +00:00

135 lines
4.4 KiB
TypeScript

import { describe, expect, it } from "vitest";
import { createCli } from "../../../src/cli.js";
import { createCliInventory } from "../../../scripts/lib/catalog-cli.mjs";
import { TOOL_CONTRACTS } from "../../../src/contracts/toolContracts.js";
import { CLI_COMMAND_NAMES } from "../../../src/cliCommandNames.js";
/** Canonical MCP operations reached by CLI commands with different names. */
const CLI_COMMAND_TOOL_ALIASES = Object.freeze({
"environment-build": ["export_environment_bundle"],
guidance: ["search_guidance", "read_guidance_section"],
analyze: ["binary_overview"],
inspect: ["binary_overview"],
decompile: ["procedure_pseudo_code"],
function: ["analyze_function"],
instructions: ["read_function_instructions"],
trace: ["trace_feature"],
search: ["search_strings", "search_procedures"],
"capture-process": ["capture_process_scenario"],
compare: ["compare_bundles"],
"list-objdump-architectures": ["inspect_with_objdump"],
"debug-with-gdb": ["gdb_console"],
"debug-with-rizin": ["rizin_debug_command"],
});
/** MCP operations without a dedicated CLI command or direct command alias. */
const MCP_TOOLS_WITHOUT_DEDICATED_CLI = Object.freeze([
// Runtime settings belong to the long-lived MCP server; CLI calls use launch/per-call controls.
"inspect_analysis_settings",
"update_analysis_settings",
// MCP session control selects a resource root; CLI resource commands take paths directly.
"open_bundle_resources",
"address_name",
"comment",
"current_address",
"current_procedure",
"current_document",
"goto_address",
"inline_comment",
"list_bookmarks",
"list_documents",
"list_names",
"list_procedures",
"list_segments",
"list_strings",
"next_address",
"prev_address",
"procedure_address",
"procedure_assembly",
"procedure_callees",
"procedure_callers",
"procedure_info",
"procedure_references",
"resolve_containing_procedure",
"set_address_name",
"set_addresses_names",
"set_bookmark",
"set_comment",
"set_inline_comment",
"unset_bookmark",
"get_objc_classes",
"get_objc_protocols",
"batch_decompile",
"get_call_graph",
"analyze_swift_types",
"find_xrefs_to_name",
"trace_call_path",
"open_binary",
"close_binary",
// Investigation reset acts on the long-lived MCP server's retained history.
"reset_investigation",
"binary_session",
"export_evidence_bundle",
"import_evidence_bundle",
"compare_functions",
"find_changed_behavior",
"build_call_path",
"correlate_static_and_runtime",
"verify_reconstruction",
"list_unknowns",
"record_unknown",
"update_unknown",
"verify_unknown_resolution",
"get_evidence_bundle",
"get_navigation_context",
"inspect_address_context",
"start_gdb_session",
"gdb_session_status",
"close_gdb_session",
"start_rizin_debug_session",
"rizin_debug_session_status",
"close_rizin_debug_session",
"start_frida_session",
"load_frida_script",
"resume_frida_session",
"unload_frida_script",
"frida_session_status",
"close_frida_session",
]);
describe("CLI canonical tool coverage", () => {
it("accounts for every MCP tool on the CLI or marks it intentionally MCP-only", () => {
const registeredCli = createCliInventory(createCli());
const registeredCommandNames = new Set([
...registeredCli.primary,
...registeredCli.aliases.map(({ name }) => name),
]);
const cliToolNames = new Set(
registeredCli.primary.map((command) => command.replaceAll("-", "_")),
);
for (const [command, names] of Object.entries(CLI_COMMAND_TOOL_ALIASES)) {
expect(registeredCommandNames.has(command)).toBe(true);
for (const name of names) cliToolNames.add(name);
}
for (const command of CLI_COMMAND_NAMES)
expect(registeredCommandNames.has(command)).toBe(true);
const intentionalMcpOnly = new Set<string>(MCP_TOOLS_WITHOUT_DEDICATED_CLI);
expect(
[...intentionalMcpOnly].filter((name) => cliToolNames.has(name)).sort(),
).toEqual([]);
const unaccounted = TOOL_CONTRACTS.map(({ name }) => name).filter(
(name) => !cliToolNames.has(name) && !intentionalMcpOnly.has(name),
);
expect(unaccounted).toEqual([]);
expect(new Set(MCP_TOOLS_WITHOUT_DEDICATED_CLI).size).toBe(
MCP_TOOLS_WITHOUT_DEDICATED_CLI.length,
);
expect(
MCP_TOOLS_WITHOUT_DEDICATED_CLI.every((name) =>
TOOL_CONTRACTS.some((contract) => contract.name === name),
),
).toBe(true);
});
});