feat(brain): validate the claim-property envelope on write (brain#21) (#102)
First half of brain#21: half_life (volatile|seasonal|durable), applies (local|homelab|universal), claim_provenance (asserted|inferred). writeHallNote already passed unknown frontmatter keys through verbatim, so preservation was free — a test now pins it so a refactor of the merge loop cannot silently drop the fields. What was missing is validation, and it fails closed: a value outside the enum is rejected (a lint skips what it cannot parse, so the note would read as classified while nothing acts on it); an envelope field without claim_provenance is rejected (a value a model inferred must never be indistinguishable from one a human asserted, or a single classifier pass launders guesses into apparent judgement across the corpus); provenance alone is rejected too. Validation runs before MkdirAll, so a rejected write leaves nothing behind. The field is `applies`, not `scope`: scope: has been in use since brain#5 for glossary terms (homelab-core, project:<repo>), a disjoint value space on the same key. The shipped schema keeps the name. Notes with none of these fields are byte-identical to before. Bulk backfill stays out of scope. Schema documented in brain/CLAUDE.md via brain_edit_root, which produced the hyperguild#97 audit record for the rewrite. Refs brain#21, brain#19 (superseded), brain#5, hyperguild#97. Co-authored-by: Mathias <mthbqv@gmail.com>
This commit was merged in pull request #102.
This commit is contained in:
@@ -0,0 +1,98 @@
|
||||
// Package claim validates the claim-property frontmatter that says when and
|
||||
// where a note's claim holds, and who decided that (brain#21).
|
||||
//
|
||||
// Two families were designed together and land separately. This is the
|
||||
// applicability envelope:
|
||||
//
|
||||
// half_life: volatile | seasonal | durable — how fast it decays
|
||||
// applies: local | homelab | universal — how widely it holds
|
||||
// claim_provenance: asserted | inferred — who set the above
|
||||
//
|
||||
// The strength family (confidence, contested) follows once the ingest-time
|
||||
// contradiction detector exists to populate it.
|
||||
//
|
||||
// Why the envelope is validated rather than merely accepted: a value outside
|
||||
// the enum is worse than an absent one. A lint skips what it cannot parse, so
|
||||
// the note reads as classified while nothing acts on it — the field becomes
|
||||
// decoration that suppresses the very review it was added to trigger.
|
||||
//
|
||||
// Why `applies` and not `scope`: `scope:` has been in use since brain#5 for
|
||||
// glossary terms (`homelab-core`, `project:<repo>`) — a disjoint value space
|
||||
// on the same key. The shipped schema keeps the name; this one takes another.
|
||||
package claim
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"strings"
|
||||
)
|
||||
|
||||
// Field names, exported so writers and lints agree on the spelling.
|
||||
const (
|
||||
FieldHalfLife = "half_life"
|
||||
FieldApplies = "applies"
|
||||
FieldProvenance = "claim_provenance"
|
||||
)
|
||||
|
||||
var (
|
||||
halfLives = []string{"volatile", "seasonal", "durable"}
|
||||
appliesTo = []string{"local", "homelab", "universal"}
|
||||
provenances = []string{"asserted", "inferred"}
|
||||
)
|
||||
|
||||
// ValidateEnvelope checks the envelope fields of one note's frontmatter.
|
||||
//
|
||||
// Absent fields are valid: the envelope is opt-in for new writes, and a
|
||||
// corpus-wide backfill is deliberately out of scope (brain#21) — inferring
|
||||
// 1113 notes' properties in bulk has the same failure mode as the extraction
|
||||
// pass that produced 28 wrong wikilinks out of 67.
|
||||
func ValidateEnvelope(fm map[string]string) error {
|
||||
halfLife, hasHalfLife := present(fm, FieldHalfLife)
|
||||
applies, hasApplies := present(fm, FieldApplies)
|
||||
prov, hasProv := present(fm, FieldProvenance)
|
||||
|
||||
if hasHalfLife {
|
||||
if err := oneOf(FieldHalfLife, halfLife, halfLives); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
if hasApplies {
|
||||
if err := oneOf(FieldApplies, applies, appliesTo); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
if hasProv {
|
||||
if err := oneOf(FieldProvenance, prov, provenances); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
|
||||
// The field and its provenance travel together or not at all. A value
|
||||
// whose author is unknown cannot be trusted differently from one Mathias
|
||||
// asserted, which is how an inferred guess hardens into accepted fact.
|
||||
switch {
|
||||
case (hasHalfLife || hasApplies) && !hasProv:
|
||||
return fmt.Errorf("%s is required when %s or %s is set",
|
||||
FieldProvenance, FieldHalfLife, FieldApplies)
|
||||
case hasProv && !hasHalfLife && !hasApplies:
|
||||
return fmt.Errorf("%s is set but neither %s nor %s is",
|
||||
FieldProvenance, FieldHalfLife, FieldApplies)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// present reports a trimmed field value and whether it was set to anything
|
||||
// non-empty. A key written with an empty value is treated as absent rather
|
||||
// than as an error: that is a caller emitting a placeholder, not asserting.
|
||||
func present(fm map[string]string, key string) (string, bool) {
|
||||
v := strings.TrimSpace(fm[key])
|
||||
return v, v != ""
|
||||
}
|
||||
|
||||
func oneOf(field, value string, allowed []string) error {
|
||||
for _, a := range allowed {
|
||||
if a == value {
|
||||
return nil
|
||||
}
|
||||
}
|
||||
return fmt.Errorf("%s: %q is not one of %s", field, value, strings.Join(allowed, ", "))
|
||||
}
|
||||
@@ -0,0 +1,89 @@
|
||||
// Package claim_test covers the claim-property envelope (brain#21).
|
||||
package claim_test
|
||||
|
||||
import (
|
||||
"testing"
|
||||
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/claim"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
func TestValidateEnvelope(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
fm map[string]string
|
||||
wantErr string
|
||||
}{
|
||||
{
|
||||
name: "absent is fine — the fields are opt-in on new writes",
|
||||
fm: map[string]string{"wing": "homelab", "hall": "facts"},
|
||||
},
|
||||
{
|
||||
name: "complete envelope with provenance",
|
||||
fm: map[string]string{
|
||||
"half_life": "durable", "applies": "universal", "claim_provenance": "asserted",
|
||||
},
|
||||
},
|
||||
{
|
||||
name: "inferred provenance is equally valid — it just must be stated",
|
||||
fm: map[string]string{
|
||||
"half_life": "volatile", "applies": "local", "claim_provenance": "inferred",
|
||||
},
|
||||
},
|
||||
{
|
||||
// A value nobody can act on is worse than no value: a lint
|
||||
// silently skips it, so the note looks classified and isn't.
|
||||
name: "unknown half_life value",
|
||||
fm: map[string]string{"half_life": "forever", "claim_provenance": "asserted"},
|
||||
wantErr: `half_life: "forever" is not one of volatile, seasonal, durable`,
|
||||
},
|
||||
{
|
||||
name: "unknown applies value",
|
||||
fm: map[string]string{"applies": "galaxy", "claim_provenance": "asserted"},
|
||||
wantErr: `applies: "galaxy" is not one of local, homelab, universal`,
|
||||
},
|
||||
{
|
||||
// brain#21: a value a model inferred must never be
|
||||
// indistinguishable from one Mathias asserted. Writing the field
|
||||
// without saying who set it is exactly that laundering.
|
||||
name: "envelope field without provenance",
|
||||
fm: map[string]string{"half_life": "durable"},
|
||||
wantErr: "claim_provenance is required when half_life or applies is set",
|
||||
},
|
||||
{
|
||||
name: "applies without provenance",
|
||||
fm: map[string]string{"applies": "homelab"},
|
||||
wantErr: "claim_provenance is required when half_life or applies is set",
|
||||
},
|
||||
{
|
||||
name: "unknown provenance value",
|
||||
fm: map[string]string{"half_life": "durable", "claim_provenance": "probably"},
|
||||
wantErr: `claim_provenance: "probably" is not one of asserted, inferred`,
|
||||
},
|
||||
{
|
||||
// Provenance alone says who set fields that aren't there.
|
||||
name: "provenance without any envelope field",
|
||||
fm: map[string]string{"claim_provenance": "asserted"},
|
||||
wantErr: "claim_provenance is set but neither half_life nor applies is",
|
||||
},
|
||||
{
|
||||
// The glossary wing has used scope: homelab-core since #5. The
|
||||
// envelope deliberately does NOT claim that key (brain#21).
|
||||
name: "glossary scope is untouched",
|
||||
fm: map[string]string{"scope": "homelab-core", "term": "koala"},
|
||||
},
|
||||
}
|
||||
|
||||
for _, tt := range tests {
|
||||
t.Run(tt.name, func(t *testing.T) {
|
||||
err := claim.ValidateEnvelope(tt.fm)
|
||||
if tt.wantErr == "" {
|
||||
assert.NoError(t, err)
|
||||
return
|
||||
}
|
||||
require.Error(t, err)
|
||||
assert.Contains(t, err.Error(), tt.wantErr)
|
||||
})
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user