fix(pipeline,classification): read the brain through brainfs (#157, slice 6)
The ingest pipeline read wiki/sources/<slug>.md and schema.md (both go into the LLM prompt), the pages it revises, and the pages it adds source refs to, with os.ReadFile; BackfillRefs listed wiki/sources with os.ReadDir. A symlinked file's content reached the prompt and the written pages (1.6M leaks in the race), and a FIFO hung the ingest. classification.Load (the I1 sovereignty levels) read classification.yaml the same way and hung startup on a FIFO. - pipeline: readSourcePage, loadSchema, reviseOrCreate, injectSourceRefs read through readBrainFile (brainfs ReadRegular); reviseOrCreate takes the brain dir and reads page.Path, a missing page is still created and a non-regular one is an error. BackfillRefs lists with ReadDirRegular and reads with ReadRegular. - classification.Load: read through brainfs; a symlinked or special classification.yaml is a hard error (as a malformed one is); an absent file or brain dir still yields the default config. Tests use in-brain targets and the [[slug|title]] link form the pipeline actually follows (bare [[slug]] links are ignored by it, which made a first draft of the backfill test vacuous). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,46 @@
|
||||
package classification
|
||||
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"syscall"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// hyperguild#157 slice 6: Load read classification.yaml with os.ReadFile. It
|
||||
// sets the I1 sovereignty levels; a symlinked file must not be trusted as the
|
||||
// config (a hard error, as for a malformed file), and a FIFO must not hang
|
||||
// startup.
|
||||
func TestLoadRefusesASymlinkedOrFIFOClassificationFile(t *testing.T) {
|
||||
ok := t.TempDir()
|
||||
require.NoError(t, os.WriteFile(filepath.Join(ok, "classification.yaml"), []byte("wings:\n w: confidential\n"), 0o644))
|
||||
_, err := Load(ok)
|
||||
require.NoError(t, err, "positive control")
|
||||
|
||||
linked := t.TempDir()
|
||||
require.NoError(t, os.WriteFile(filepath.Join(linked, "real.yaml"), []byte("wings:\n w: public\n"), 0o644))
|
||||
require.NoError(t, os.Symlink("real.yaml", filepath.Join(linked, "classification.yaml")))
|
||||
_, err = Load(linked)
|
||||
assert.Error(t, err, "an in-brain symlink is not trusted as the config")
|
||||
|
||||
fifo := t.TempDir()
|
||||
require.NoError(t, syscall.Mkfifo(filepath.Join(fifo, "classification.yaml"), 0o644))
|
||||
w, err := os.OpenFile(filepath.Join(fifo, "classification.yaml"), os.O_RDWR, 0)
|
||||
require.NoError(t, err)
|
||||
defer func() { _ = w.Close() }()
|
||||
done := make(chan error, 1)
|
||||
go func() { _, err := Load(fifo); done <- err }()
|
||||
select {
|
||||
case err := <-done:
|
||||
assert.Error(t, err)
|
||||
case <-time.After(3 * time.Second):
|
||||
t.Fatal("Load hung on a FIFO")
|
||||
}
|
||||
|
||||
_, err = Load(t.TempDir())
|
||||
assert.NoError(t, err, "an absent file is still not an error")
|
||||
}
|
||||
Reference in New Issue
Block a user