Files
hyperguild/ingestion/internal/mcp/tools_notes_test.go
T
mathiasandClaude Opus 5 36b757fabf
CI / Lint / Test / Vet (pull_request) Successful in 31s
CI / Mirror to GitHub (pull_request) Skipped
feat(mcp): add brain_read + brain_edit, contained to the sync source (brain#4)
brain_read returns a note verbatim; brain_edit is str_replace with an
exactly-once match. Both operate on INGEST_BRAIN_DIR, which is the pod's
mount of /var/lib/supervisor/brain — the tree brain-sync commits from, so
an edit reaches gitea on the next cycle rather than landing somewhere the
sync cannot see it (brain#2).

An adversarial design review before implementation changed three things,
each of which would otherwise have shipped:

1. Governance files are NOT in the model-facing tool. The original plan
   allowed root *.md so CLAUDE.md had an MCP path at all — the absence of
   one is what pushed a session to edit via the gitea REST API on
   2026-06-16 and wedge the sync. But brain content is ingested from the
   outside world, reaches a model's context via brain_query, and that
   model would hold the editor: one poisoned page could rewrite the
   CLAUDE.md a .dispatch-allow agent later loads as instructions. Worse,
   brain-sync merges with --strategy-option=ours, so the live tree wins
   against a human's corrective push on exactly the conflicting lines.
   CLAUDE.md now goes through brain_edit_root: de-surfaced from
   tools/list (the brain_index precedent, ADR-0012 rule 4) and gated on
   the local static principal, so a claude.ai-origin session is refused.
   The two scopes are disjoint — the privileged door has the smaller reach.

2. Reads needed the same allowlist, and brain_get already lacked it.
   api.ReadNote resolves any brain-relative path and parseFrontmatter
   returns the whole file when there is no fence, so brain_get reads
   verbatim session transcripts under archive/ (up to 500 KB, never
   BM25-indexed, so nobody thinks of them as reachable). A test proves
   the exposure was live; the same Resolve now gates brain_get.

3. Canonicalise before allowlisting. A prefix check on the raw argument
   accepts knowledge/../.git/hooks/post-commit, which Clean collapses to
   a git hook that brain-sync executes inside a pod holding the Gitea
   push credentials. Traversal, symlink escape, dotfiles, .git/, archive/,
   sessions/ and raw/ are refused by a static backstop that does not
   depend on the allowlist being right. There were no traversal tests in
   this repo before.

Also from the review: overlapping match counting (bytes.Count says "aa"
occurs once in "aaa", so a Count-based uniqueness check accepts an
ambiguous edit); UTF-8 validation on both sides, because encoding/json
substitutes U+FFFD and would hand back bytes the file does not contain,
making every derived old_str unmatchable; refusal while .git/MERGE_HEAD
or index.lock exists, since an edit racing brain-sync's merge is either
hard-reset away or committed as a wrongly resolved conflict; flock plus a
per-path mutex with the read taken inside the lock, because two pods
share the hostPath during a RollingUpdate and uniqueness evaluated
against a stale read loses an update while reporting success; same-dir
*.tmp + rename + chmod 0644 + fsync of file and parent; and reindex only
when the edit touches frontmatter, since BM25 walks live and embeddings
are mtime-driven.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m
2026-08-18 17:01:37 +02:00

128 lines
4.6 KiB
Go

// ingestion/internal/mcp/tools_notes_test.go
package mcp_test
import (
"encoding/json"
"net/http"
"net/http/httptest"
"os"
"path/filepath"
"testing"
"github.com/mathiasbq/hyperguild/ingestion/internal/mcp"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// ---- brain#4: brain_read / brain_edit through the JSON-RPC surface --------
func newBrainRepo(t *testing.T) string {
t.Helper()
dir := t.TempDir()
require.NoError(t, os.MkdirAll(filepath.Join(dir, ".git"), 0o755))
require.NoError(t, os.MkdirAll(filepath.Join(dir, "wiki/homelab/facts"), 0o755))
require.NoError(t, os.WriteFile(filepath.Join(dir, "wiki/homelab/facts/n.md"),
[]byte("---\ntitle: 'n'\n---\n\nalpha\nbeta\n"), 0o644))
require.NoError(t, os.WriteFile(filepath.Join(dir, "CLAUDE.md"), []byte("# rules\n"), 0o644))
return dir
}
func call(t *testing.T, srv *mcp.Server, name string, args map[string]any) map[string]any {
t.Helper()
req := httptest.NewRequest(http.MethodPost, "/mcp", body(t, map[string]any{
"jsonrpc": "2.0", "id": 1, "method": "tools/call",
"params": map[string]any{"name": name, "arguments": args},
}))
rr := httptest.NewRecorder()
srv.ServeHTTP(rr, req)
var resp map[string]any
require.NoError(t, json.Unmarshal(rr.Body.Bytes(), &resp))
return resp
}
func TestBrainReadAndEdit_RoundTripThroughJSONRPC(t *testing.T) {
// The Go functions are tested in internal/notes; this pins the transport,
// because a tool that works in-process and is unreachable over JSON-RPC
// is indistinguishable from a working one in a unit test.
dir := newBrainRepo(t)
srv := mcp.NewServer(dir, nil, nil, nil)
resp := call(t, srv, "brain_read", map[string]any{"path": "wiki/homelab/facts/n.md"})
require.NotContains(t, resp, "error", "%v", resp["error"])
resp = call(t, srv, "brain_edit", map[string]any{
"path": "wiki/homelab/facts/n.md", "old_str": "beta", "new_str": "BETA",
})
require.NotContains(t, resp, "error", "%v", resp["error"])
got, err := os.ReadFile(filepath.Join(dir, "wiki/homelab/facts/n.md"))
require.NoError(t, err)
assert.Equal(t, "---\ntitle: 'n'\n---\n\nalpha\nBETA\n", string(got),
"only the matched bytes may change")
}
func TestBrainEdit_RefusesGovernanceFilesFromTheModelFacingTool(t *testing.T) {
dir := newBrainRepo(t)
srv := mcp.NewServer(dir, nil, nil, nil)
resp := call(t, srv, "brain_edit", map[string]any{
"path": "CLAUDE.md", "old_str": "# rules", "new_str": "# rewritten",
})
require.Contains(t, resp, "error", "brain_edit must not reach CLAUDE.md")
got, err := os.ReadFile(filepath.Join(dir, "CLAUDE.md"))
require.NoError(t, err)
assert.Equal(t, "# rules\n", string(got))
}
func TestBrainEditRoot_RefusedWithoutTheLocalStaticPrincipal(t *testing.T) {
// No principal in context is the model-facing case (and the default in
// this test server): the privileged door must stay shut.
dir := newBrainRepo(t)
srv := mcp.NewServer(dir, nil, nil, nil)
resp := call(t, srv, "brain_edit_root", map[string]any{
"path": "CLAUDE.md", "old_str": "# rules", "new_str": "# rewritten",
})
require.Contains(t, resp, "error")
got, err := os.ReadFile(filepath.Join(dir, "CLAUDE.md"))
require.NoError(t, err)
assert.Equal(t, "# rules\n", string(got), "governance file must be untouched")
}
func TestBrainGet_CannotReachSessionTranscripts(t *testing.T) {
// Pre-existing hole, not introduced here: api.ReadNote resolves any
// brain-relative path and parseFrontmatter returns the WHOLE file as body
// when there is no frontmatter fence. archive/ holds verbatim Claude
// session transcripts (up to 500 KB) that BM25 never indexes, so they are
// invisible to search and trivially readable by path — and CLAUDE.md
// documents the layout.
dir := newBrainRepo(t)
require.NoError(t, os.MkdirAll(filepath.Join(dir, "archive/claude-sessions/koala"), 0o755))
require.NoError(t, os.WriteFile(
filepath.Join(dir, "archive/claude-sessions/koala/session-1.md"),
[]byte("verbatim transcript with tool output\n"), 0o644))
srv := mcp.NewServer(dir, nil, nil, nil)
resp := call(t, srv, "brain_get", map[string]any{"path": "archive/claude-sessions/koala/session-1.md"})
require.Contains(t, resp, "error", "brain_get must not read outside knowledge/ and wiki/")
assert.NotContains(t, string(mustJSON(t, resp)), "verbatim transcript")
}
func TestBrainGet_StillReadsNotes(t *testing.T) {
dir := newBrainRepo(t)
srv := mcp.NewServer(dir, nil, nil, nil)
resp := call(t, srv, "brain_get", map[string]any{"path": "wiki/homelab/facts/n.md"})
assert.NotContains(t, resp, "error", "%v", resp["error"])
}
func mustJSON(t *testing.T, v any) []byte {
t.Helper()
b, err := json.Marshal(v)
require.NoError(t, err)
return b
}