mirror of
https://github.com/DeusData/codebase-memory-mcp.git
synced 2026-10-21 05:59:35 +08:00
刘冲
21ae02154a
Indexing accepts whatever a repository contains. A tree carrying a vendored monorepo, a generated dump, or a runaway build directory is discovered in full, and the first sign of trouble is a host under memory pressure with nothing that attributes it to indexing. Add two opt-in limits evaluated during discovery against accepted source files only: index_max_files and index_max_source_mb. Both default to off, so nothing changes until an operator sets one. Crossing a limit fails the whole attempt with a structured resource_limit_exceeded result naming the resource, the observed value and the limit; no partial graph is published, and an existing serving index keeps answering. Limits are read from the CLI-managed _config.db and are not MCP request arguments. A supervised parent replaces any caller-supplied policy before spawning its worker, and the worker rejects a missing or incomplete contract, so the CLI, the daemon and the supervised worker all enforce the same decision. Both keys reach an operator through the existing config get/set/list/reset with no new subcommand. `set` suppresses its own generic message for them because the policy writer names the precise reason -- so that writer speaks on every failure it can return, including a validated value whose write then fails on a database that cannot be written. Exiting non-zero in silence is not an acceptable answer from a CLI. The two shell regressions that hand-roll the supervisor's worker argv carry that contract as well. Without it the worker exits before either guard can observe anything, and the guard would go quietly vacuous. Signed-off-by: 刘冲 <mail@liuchong.dev>
92 lines
3.3 KiB
Bash
Executable File
92 lines
3.3 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# A supervised worker that produces a valid MCP error response is healthy.
|
|
# The CLI may exit nonzero when presenting that error to a human, but the worker
|
|
# transport must exit zero so its parent reads the response instead of inventing
|
|
# an exit_nonzero "crashed on a file" diagnosis.
|
|
set -euo pipefail
|
|
|
|
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
|
# scripts/test.sh builds into $BUILD_DIR, which is NOT build/c on every leg (the
|
|
# Linux containers use build/linux-arm64 / build/linux-amd64). Honour the binary
|
|
# the caller built, exactly as test_parent_watchdog.sh and test_worker_watchdog.sh
|
|
# do; the build/c default keeps a bare manual invocation working.
|
|
BINARY="${CBM_TEST_BINARY:-${ROOT}/build/c/codebase-memory-mcp}"
|
|
if [[ ! -x "${BINARY}" && -x "${BINARY}.exe" ]]; then
|
|
BINARY="${BINARY}.exe"
|
|
fi
|
|
|
|
if [[ ! -x "${BINARY}" ]]; then
|
|
echo "missing binary: ${BINARY}" >&2
|
|
exit 2
|
|
fi
|
|
|
|
if command -v shasum >/dev/null 2>&1; then
|
|
BUILD_FINGERPRINT="$(shasum -a 256 "${BINARY}" | awk '{print $1}')"
|
|
elif command -v sha256sum >/dev/null 2>&1; then
|
|
BUILD_FINGERPRINT="$(sha256sum "${BINARY}" | awk '{print $1}')"
|
|
elif command -v openssl >/dev/null 2>&1; then
|
|
BUILD_FINGERPRINT="$(openssl dgst -sha256 "${BINARY}" | awk '{print $NF}')"
|
|
else
|
|
echo "no SHA-256 command available for worker build binding" >&2
|
|
exit 2
|
|
fi
|
|
if [[ ! "${BUILD_FINGERPRINT}" =~ ^[0-9a-f]{64}$ ]]; then
|
|
echo "invalid worker build fingerprint: ${BUILD_FINGERPRINT}" >&2
|
|
exit 2
|
|
fi
|
|
|
|
# shellcheck source=../scripts/test-runtime.sh
|
|
source "${ROOT}/scripts/test-runtime.sh"
|
|
cbm_test_runtime_init
|
|
tmpdir="${CBM_TEST_RUNTIME_ROOT}"
|
|
cleanup() {
|
|
CBM_CACHE_DIR="${tmpdir}/cache-supervisor" \
|
|
"${BINARY}" daemon stop >/dev/null 2>&1 || true
|
|
cbm_test_runtime_cleanup "${BINARY}"
|
|
}
|
|
trap cleanup EXIT
|
|
|
|
missing="${tmpdir}/repository-does-not-exist"
|
|
response="${tmpdir}/worker.response"
|
|
args="{\"repo_path\":\"${missing}\",\"mode\":\"fast\",$(cbm_test_index_worker_policy_json)}"
|
|
|
|
if ! CBM_CACHE_DIR="${tmpdir}/cache-worker" \
|
|
"${BINARY}" cli --index-worker \
|
|
--index-worker-build "${BUILD_FINGERPRINT}" \
|
|
index_repository "${args}" \
|
|
--response-out "${response}" >"${tmpdir}/worker.out" 2>"${tmpdir}/worker.err"; then
|
|
echo "worker treated a delivered MCP error as a process failure" >&2
|
|
cat "${tmpdir}/worker.err" >&2
|
|
exit 1
|
|
fi
|
|
|
|
if [[ ! -s "${response}" ]] || ! grep -q 'Pipeline failed' "${response}"; then
|
|
echo "worker did not deliver the underlying pipeline error" >&2
|
|
cat "${response}" 2>/dev/null >&2 || true
|
|
exit 1
|
|
fi
|
|
|
|
set +e
|
|
CBM_CACHE_DIR="${tmpdir}/cache-supervisor" \
|
|
"${BINARY}" cli index_repository --repo-path "${missing}" --mode fast \
|
|
>"${tmpdir}/supervisor.out" 2>"${tmpdir}/supervisor.err"
|
|
cli_rc=$?
|
|
set -e
|
|
|
|
if [[ ${cli_rc} -eq 0 ]]; then
|
|
echo "human-facing CLI unexpectedly accepted an indexing error" >&2
|
|
exit 1
|
|
fi
|
|
if grep -q 'crashed on a file' "${tmpdir}/supervisor.out" "${tmpdir}/supervisor.err"; then
|
|
echo "supervisor replaced a valid tool error with a false crash diagnosis" >&2
|
|
exit 1
|
|
fi
|
|
if ! grep -q 'Pipeline failed' "${tmpdir}/supervisor.out" "${tmpdir}/supervisor.err"; then
|
|
echo "supervisor did not preserve the worker's pipeline error" >&2
|
|
cat "${tmpdir}/supervisor.out" >&2
|
|
cat "${tmpdir}/supervisor.err" >&2
|
|
exit 1
|
|
fi
|
|
|
|
echo "ok: worker MCP errors remain tool errors, not process crashes"
|