fix(brain): provenance keeps only provably plain frontmatter; pipeline stamps
Round 2 of the PR #147 review forged origin: static for yaml.v3 with an alias key plus a "..." document-end line: per-line judgement cannot see context-dependent YAML. It also found REST ingest writing pages with no provenance (stampPages lived only in the MCP server). - New package internal/provenance. Apply keeps only top-level groups `key: value` with a bare-identifier key whose group decodes on its own to exactly that key, drops reserved and duplicate keys and everything else (aliases, anchors as keys, document markers, complex/merge keys, flow maps, tags, quoted keys), appends the stamp, then decodes the whole result with yaml.v3 and refuses the write unless it reads back exactly the stamp. api.StampProvenance wraps it and now returns an error, which every caller propagates. - The ingest pipeline stamps every page it writes or merges, from provenance.FromContext(ctx); MCP attaches the caller's stamp, REST and the watcher stamp unknown. RunRaw takes a ctx. - brain_edit snapshots the note and rolls the edit back if the stamp cannot be verified. Tests: R1/R2 payloads join the write/update variant table, plus brain_edit with the alias payload; REST /ingest-raw (title newline checked with the line-oriented reader) and REST /ingest (stub LLM) stamp unknown. Two existing byte-exact tests updated for the stamp line. Refs #145 #144 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -11,6 +11,7 @@ import (
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/provenance"
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/wiki"
|
||||
)
|
||||
|
||||
@@ -89,13 +90,17 @@ func Run(ctx context.Context, cfg Config, brainDir, content, source string, dryR
|
||||
meta.BodyHash = bodyHash
|
||||
applySourceMeta(allRaw, meta)
|
||||
|
||||
return buildAndWrite(allRaw, sourceSlug, date, brainDir, source, inventory, allWarnings, dryRun)
|
||||
return buildAndWrite(ctx, allRaw, sourceSlug, date, brainDir, source, inventory, allWarnings, dryRun)
|
||||
}
|
||||
|
||||
// RunRaw runs the pipeline on pre-parsed RawPages, skipping the LLM extraction
|
||||
// step. Use this when the caller has already produced the structured RawPage data
|
||||
// (e.g. from a more capable model or manual curation).
|
||||
func RunRaw(brainDir, source string, rawPages []RawPage, dryRun bool) (Result, error) {
|
||||
//
|
||||
// Every page written is stamped with provenance.FromContext(ctx)
|
||||
// (hyperguild#145); a caller that knows the principal attaches it with
|
||||
// provenance.WithStamp, everyone else stamps origin: unknown.
|
||||
func RunRaw(ctx context.Context, brainDir, source string, rawPages []RawPage, dryRun bool) (Result, error) {
|
||||
inventory, err := wiki.LoadInventory(brainDir)
|
||||
if err != nil {
|
||||
return Result{}, fmt.Errorf("load inventory: %w", err)
|
||||
@@ -104,11 +109,11 @@ func RunRaw(brainDir, source string, rawPages []RawPage, dryRun bool) (Result, e
|
||||
sourceSlug := wiki.Slug(source)
|
||||
date := time.Now().UTC().Format("2006-01-02")
|
||||
|
||||
return buildAndWrite(rawPages, sourceSlug, date, brainDir, source, inventory, nil, dryRun)
|
||||
return buildAndWrite(ctx, rawPages, sourceSlug, date, brainDir, source, inventory, nil, dryRun)
|
||||
}
|
||||
|
||||
// buildAndWrite runs BuildPages through write for both Run and RunRaw.
|
||||
func buildAndWrite(rawPages []RawPage, sourceSlug, date, brainDir, source string, inventory map[wiki.PageType][]wiki.Entry, warnings []string, dryRun bool) (Result, error) {
|
||||
func buildAndWrite(ctx context.Context, rawPages []RawPage, sourceSlug, date, brainDir, source string, inventory map[wiki.PageType][]wiki.Entry, warnings []string, dryRun bool) (Result, error) {
|
||||
pages, buildWarnings := BuildPages(rawPages, sourceSlug, date)
|
||||
warnings = append(warnings, buildWarnings...)
|
||||
resolved := Resolve(pages, inventory)
|
||||
@@ -136,7 +141,13 @@ func buildAndWrite(rawPages []RawPage, sourceSlug, date, brainDir, source string
|
||||
"%s: source now disagrees on section %q — on-disk version kept",
|
||||
page.Path, heading))
|
||||
}
|
||||
if err := os.WriteFile(dest, []byte(content), 0o644); err != nil {
|
||||
// Stamped as the last step, after merge/revise, so a page that
|
||||
// was merged into is re-attributed to this ingest too.
|
||||
stamped, err := provenance.Apply(content, provenance.FromContext(ctx))
|
||||
if err != nil {
|
||||
return Result{}, fmt.Errorf("stamp %s: %w", page.Path, err)
|
||||
}
|
||||
if err := os.WriteFile(dest, []byte(stamped), 0o644); err != nil {
|
||||
return Result{}, fmt.Errorf("write %s: %w", page.Path, err)
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user