Compare commits

..
Author SHA1 Message Date
mathias 9345a0a867 feat(pipeline): report when a re-ingest disagrees with the page on disk (#104)
CI / Lint / Test / Vet (pull_request) Successful in 34s
CI / Mirror to GitHub (pull_request) Skipped
The asymmetry that makes unattended ingest safe (#103) also discarded a
real signal. When a fresh extraction produced a different version of a
section already on disk, the on-disk version won and the model's version
went in the bin without a word — so "the source is unchanged" and "the
source changed its mind and we ignored it" were indistinguishable.

wiki.MergeReport now returns the headings where the incoming version
disagreed and lost, and the ingest run reports them as warnings, which
AppendLog already writes into log.md.

This is the simplified answer to contradiction flagging at ingest. The
issue proposed calling brain-gardener's Judge from the ingest path, which
needs either a shared Go module across two repos or an HTTP service that
does not exist — and puts an LLM call on the write path, where a timeout
must neither fail the ingest nor silently mark nothing as contested.

None of that is necessary to get the signal. The merge already computes
the disagreement; it was throwing it away. Surfacing it costs nothing,
needs no model, no cue-word matcher, no cross-repo dependency, and is
deterministic.

Deliberately textual disagreement, not semantic contradiction. Deciding
whether a disagreement is a genuine contradiction stays with the
Judge-gated enrich pass that already runs hourly and is approval-gated by
design (brain-gardener#175). Detection here, adjudication there.

Merge is kept as a thin wrapper over MergeReport so existing callers are
untouched.

Refs #104, #103, brain-gardener#175, brain#21.
2026-09-23 06:51:49 +02:00
mathias a5a328fea5 feat(pipeline): skip extraction when the source has not changed (#105)
CI / Lint / Test / Vet (pull_request) Successful in 34s
CI / Mirror to GitHub (pull_request) Skipped
Ingest now stamps source_hash — sha256 of the ingested body, frontmatter
excluded — onto the source page, and compares it before doing any work. An
unchanged source returns Skipped with no LLM call at all.

This is cost and signal, not correctness: #103 already made a re-ingest
byte-identical, so a repeated run was harmless but not free — a full
extraction over every chunk to produce a result that merges to nothing.
Building this first would have put idempotency in the guard rather than in
the write, which is the wrong dependency direction.

Body-only hashing on purpose. A re-crawl that stamps a new fetch date has
not changed the source, and treating that as drift would re-extract the
whole corpus every time a crawler ran. A missing or unreadable hash always
means "extract": a missed skip costs one extraction, a wrong skip loses an
update silently, and silence is the failure mode this repo keeps paying
for.

The skip is reported (Result.Skipped plus a warning naming the hash), not
silent — a run that does nothing must say so, or "the pipeline is fine" and
"the pipeline stopped working" look identical (#107).

Storing the hash required settling who owns which frontmatter field. #103
made the on-disk block win wholesale, which protects human-set metadata
from a regenerating writer but froze fields the generator legitimately
owns. wiki.Merge now refreshes an explicit generatorOwned allowlist —
last_updated and source_hash — and keeps everything else on disk. An
allowlist rather than a carve-out, so a field nobody has thought about
stays human-owned by default. That also retires the last_updated
limitation #103 shipped with.

Refs #105, #103, #107, brain#21.
2026-09-22 23:45:25 +02:00
30 changed files with 649 additions and 1455 deletions
+4 -7
View File
@@ -55,21 +55,18 @@ Flags:
- `--limit N` — max results (default 5)
- `--json` — emit the raw response envelope
### `hyperguild brain write <wing> <hall> <slug>`
### `hyperguild brain write <type> <slug>`
Reads markdown from stdin, writes it to `brain/wiki/<wing>/<hall>/<slug>.md`
with `wing`/`hall`/`created_at` frontmatter injected (there is no legacy
`brain/knowledge/` fallback — ADR-0012 / #79, both wing and hall are
required).
Reads markdown from stdin, writes a knowledge entry.
```bash
$ cat <<EOF | hyperguild brain write homelab facts example-lesson
$ cat <<EOF | hyperguild brain write knowledge example-lesson
# Example lesson
## Lesson
...
EOF
wiki/homelab/facts/example-lesson.md
knowledge/example-lesson.md
```
### `hyperguild brain pass-rate <skill>`
+5 -6
View File
@@ -60,14 +60,13 @@ func runBrainWrite(ctx context.Context, args []string, stdin io.Reader, stdout,
if err := fs.Parse(args); err != nil {
return fmt.Errorf("parse flags: %w", err)
}
if fs.NArg() < 3 {
return errors.New("wing, hall and slug required (e.g. brain write homelab facts my-slug)")
if fs.NArg() < 2 {
return errors.New("type and slug required (e.g. brain write knowledge my-slug)")
}
wing := fs.Arg(0)
hall := fs.Arg(1)
slug := fs.Arg(2)
kind := fs.Arg(0)
slug := fs.Arg(1)
res, err := newBrainClient().Write(ctx, wing, hall, slug, stdin)
res, err := newBrainClient().Write(ctx, kind, slug, stdin)
if err != nil {
return err
}
+5 -5
View File
@@ -101,7 +101,7 @@ func TestRunBrainWrite_Success(t *testing.T) {
var out, errBuf bytes.Buffer
err := runBrain(
context.Background(),
[]string{"write", "homelab", "facts", "test-slug"},
[]string{"write", "knowledge", "test-slug"},
strings.NewReader("# Test\n\nSome body content.\n"),
&out, &errBuf,
)
@@ -111,9 +111,9 @@ func TestRunBrainWrite_Success(t *testing.T) {
func TestRunBrainWrite_MissingArgs(t *testing.T) {
var out, errBuf bytes.Buffer
err := runBrain(context.Background(), []string{"write", "homelab"}, strings.NewReader("x"), &out, &errBuf)
err := runBrain(context.Background(), []string{"write", "knowledge"}, strings.NewReader("x"), &out, &errBuf)
assert.Error(t, err)
assert.Contains(t, err.Error(), "wing, hall and slug required")
assert.Contains(t, err.Error(), "type and slug required")
}
func TestRunBrainWrite_BackendError(t *testing.T) {
@@ -127,7 +127,7 @@ func TestRunBrainWrite_BackendError(t *testing.T) {
var out, errBuf bytes.Buffer
err := runBrain(
context.Background(),
[]string{"write", "homelab", "facts", "bad slug"},
[]string{"write", "knowledge", "bad slug"},
strings.NewReader("body"),
&out, &errBuf,
)
@@ -150,7 +150,7 @@ func TestRunBrainWrite_EmptyStdin(t *testing.T) {
t.Setenv("BRAIN_URL", srv.URL)
var out, errBuf bytes.Buffer
err := runBrain(context.Background(), []string{"write", "homelab", "facts", "empty"}, strings.NewReader(""), &out, &errBuf)
err := runBrain(context.Background(), []string{"write", "knowledge", "empty"}, strings.NewReader(""), &out, &errBuf)
require.NoError(t, err)
assert.Equal(t, 0, gotLen, "empty stdin should produce empty content payload")
}
+5 -6
View File
@@ -84,17 +84,16 @@ type WriteResult struct {
Path string `json:"path"`
}
func (c *brainClient) Write(ctx context.Context, wing, hall, filename string, content io.Reader) (*WriteResult, error) {
func (c *brainClient) Write(ctx context.Context, kind, slug string, content io.Reader) (*WriteResult, error) {
body, err := io.ReadAll(content)
if err != nil {
return nil, fmt.Errorf("read content: %w", err)
}
payload, err := json.Marshal(struct {
Wing string `json:"wing"`
Hall string `json:"hall"`
Filename string `json:"filename"`
Content string `json:"content"`
}{Wing: wing, Hall: hall, Filename: filename, Content: string(body)})
Type string `json:"type"`
Slug string `json:"slug"`
Content string `json:"content"`
}{Type: kind, Slug: slug, Content: string(body)})
if err != nil {
return nil, fmt.Errorf("marshal payload: %w", err)
}
+8 -10
View File
@@ -65,25 +65,23 @@ func TestBrainClient_Write_Success(t *testing.T) {
assert.Equal(t, http.MethodPost, r.Method)
body, _ := io.ReadAll(r.Body)
var got struct {
Wing string `json:"wing"`
Hall string `json:"hall"`
Filename string `json:"filename"`
Content string `json:"content"`
Type string `json:"type"`
Slug string `json:"slug"`
Content string `json:"content"`
}
require.NoError(t, json.Unmarshal(body, &got))
assert.Equal(t, "homelab", got.Wing)
assert.Equal(t, "facts", got.Hall)
assert.Equal(t, "find-h", got.Filename)
assert.Equal(t, "knowledge", got.Type)
assert.Equal(t, "find-h", got.Slug)
assert.Equal(t, "# body\n", got.Content)
w.Header().Set("Content-Type", "application/json")
_, _ = w.Write([]byte(`{"path":"wiki/homelab/facts/find-h.md"}`))
_, _ = w.Write([]byte(`{"path":"knowledge/find-h.md"}`))
}))
defer srv.Close()
c := &brainClient{baseURL: srv.URL, http: srv.Client()}
res, err := c.Write(context.Background(), "homelab", "facts", "find-h", strings.NewReader("# body\n"))
res, err := c.Write(context.Background(), "knowledge", "find-h", strings.NewReader("# body\n"))
require.NoError(t, err)
assert.Equal(t, "wiki/homelab/facts/find-h.md", res.Path)
assert.Equal(t, "knowledge/find-h.md", res.Path)
}
func TestBrainClient_PassRate_Success(t *testing.T) {
@@ -16,7 +16,7 @@ Three needs converge on a single small Go binary:
- [ ] `hyperguild tier` returns the same `tier.Info` that `internal/tier.Detect` produces for the same probe URLs, in < 3 s under all three tier conditions, with both human-readable and `--json` output.
- [ ] `hyperguild brain query <topic>` returns BM25 results from the brain HTTP REST `/query` endpoint, exit 0 on success and non-zero on transport failure.
- [ ] `hyperguild brain write <wing> <hall> <slug>` reads markdown content from stdin, posts to `/write` with wing/hall/filename, and creates `brain/wiki/<wing>/<hall>/<slug>.md`. A round-trip (`hyperguild brain query <slug>` immediately after) finds the entry. (Updated post-ADR-0012/#79: the legacy `<type> <slug>` shape and the `brain/knowledge/` fallback were removed; wing and hall are now required.)
- [ ] `hyperguild brain write <type> <slug>` reads markdown content from stdin, posts to `/write` with the type and slug, and creates `brain/knowledge/<slug>.md`. A round-trip (`hyperguild brain query <slug>` immediately after) finds the entry.
- [ ] `hyperguild mode <cloud|client-local|sovereign>` writes a parseable JSON file at the target path with the per-mode `mcpServers` entries; `jq -e .mcpServers` succeeds on the output.
- [ ] All commands print usage on `--help`, exit 2 on unknown flags, exit non-zero on operational errors.
- [ ] `task check` passes (lint + test + vet) on each task and on the merged branch.
@@ -50,7 +50,7 @@ Three needs converge on a single small Go binary:
- **`brain` subcommand calls the HTTP REST API.** Two nested subcommands:
- `brain query <topic>` issues `POST /query` with JSON body `{query, limit}` (default `--limit 5`), prints results in human-readable form by default and with `--json` for machine consumption.
- `brain write <wing> <hall> <slug>` reads stdin, posts `POST /write` with JSON body `{wing, hall, filename, content}`, prints the resulting path on success. (Updated post-ADR-0012/#79: wing and hall are required, replacing the old `<type> <slug>` shape and the `brain/knowledge/` legacy fallback.)
- `brain write <type> <slug>` reads stdin, posts `POST /write` with JSON body `{type, slug, content}`, prints the resulting path on success.
Rationale: HTTP REST is simpler than MCP framing for a CLI. Per CLAUDE.md, the REST endpoints are documented as the official non-MCP interface.
- **`mode <name>` writes a per-mode `.mcp.json` template.** Defaults to writing `./.mcp.json` (cwd); accepts `--out <path>`. Per-mode bodies:
+2 -21
View File
@@ -40,15 +40,6 @@ func parseFrontmatter(src string) (frontmatter, string) {
body := rest[end+len("\n---\n"):]
for _, line := range strings.Split(block, "\n") {
// An indented line is a continuation (a YAML block-list item, a
// wrapped value) never a top-level key, regardless of whether it
// happens to contain a colon — " - 'Chapter 3: The Reckoning'" is
// not a key named "- 'Chapter 3" (hyperguild#128). Checked before
// Cut so a colon inside one never reaches the key/value path.
if line != "" && (line[0] == ' ' || line[0] == '\t') {
fm.lines = append(fm.lines, fmLine{raw: line})
continue
}
key, val, ok := strings.Cut(line, ":")
key = strings.TrimSpace(key)
if !ok || key == "" || strings.HasPrefix(strings.TrimSpace(line), "#") {
@@ -92,19 +83,9 @@ func (f *frontmatter) render() string {
var b strings.Builder
b.WriteString("---\n")
for _, l := range f.lines {
switch {
case l.key == "":
if l.key == "" {
b.WriteString(l.raw)
case l.value == "":
// A key with nothing after the colon (the YAML block-list
// shape: "aliases:" followed by indented "- item" lines on
// their own raw lines) must stay bare — "key: " with a
// trailing space is a different byte sequence than the
// original, and this type's whole purpose (see the package
// doc) is a byte-preserving round-trip.
b.WriteString(l.key)
b.WriteByte(':')
default:
} else {
b.WriteString(l.key)
b.WriteString(": ")
b.WriteString(l.value)
@@ -59,37 +59,3 @@ func TestFrontmatterRenderRoundTrips(t *testing.T) {
fm, _ := parseFrontmatter(src)
assert.Equal(t, src, fm.render())
}
func TestParseFrontmatterIndentedListItemWithColonIsNotMisparsedAsKey(t *testing.T) {
// hyperguild#128: an indented YAML block-list item that happens to
// contain a colon (e.g. a title with a subtitle) is a continuation
// line, never a top-level key — strings.Cut doesn't know that just
// because TrimSpace(key) happens to be non-empty. Misparsing it as a
// key/value pair and re-rendering strips its indentation, de-indenting
// it out of the list it belongs to. Same bug class already found and
// fixed in the sibling internal/wiki package's parseFrontmatterBlock
// (hyperguild#126 review round 3) — this package was the original the
// reimplementation was modeled on and had the gap too.
src := "---\naliases:\n - 'Chapter 3: The Reckoning'\ntitle: 'X'\n---\nbody\n"
fm, _ := parseFrontmatter(src)
fm.set("updated_at", "2026-09-23T00:00:00Z")
out := fm.render()
assert.Contains(t, out, " - 'Chapter 3: The Reckoning'",
"the indented list item must survive verbatim, not get re-emitted as a de-indented fake key")
assert.NotContains(t, out, "\n- 'Chapter 3",
"must not be split into a fake key/value pair at column 0 (as opposed to surviving indented, asserted above)")
}
func TestFrontmatterRenderEmptyValueKeyStaysBareNoTrailingSpace(t *testing.T) {
// Companion to the indented-list-item fix: "aliases:" (a key with
// nothing after the colon, the YAML block-list header) must round-trip
// bare, not as "aliases: " with a trailing space — a different byte
// sequence than the original, breaking this type's whole reason for
// being a line-preserving view rather than a YAML re-marshal.
// render() returns only the frontmatter block (see
// TestFrontmatterRenderRoundTrips), no trailing body.
src := "---\naliases:\n - one\n - two\n---\n"
fm, _ := parseFrontmatter(src)
assert.Equal(t, src, fm.render())
}
+71 -13
View File
@@ -54,6 +54,8 @@ type queryRequest struct {
type writeRequest struct {
Content string `json:"content"`
Filename string `json:"filename,omitempty"`
Type string `json:"type,omitempty"`
Domain string `json:"domain,omitempty"`
Wing string `json:"wing,omitempty"`
Hall string `json:"hall,omitempty"`
SourceType string `json:"source_type,omitempty"` // "external" opts a hall=facts entry out of the internal default
@@ -108,13 +110,17 @@ func (h *Handler) Query(w http.ResponseWriter, r *http.Request) {
// WriteNoteOptions configures how a brain note is written.
//
// Wing and Hall are both required: the note routes into the structured
// wiki at brain/wiki/<wing>/<hall>/<slug>.md and gets wing/hall/created_at
// injected into its YAML frontmatter. There is no other valid destination
// (the legacy brain/knowledge/ fallback was removed — ADR-0012 / #79).
// When both Wing and Hall are non-empty, the note routes into the
// structured wiki at brain/wiki/<wing>/<hall>/<slug>.md and gets
// wing/hall/created_at injected into its YAML frontmatter.
//
// When either is empty, the note falls back to brain/knowledge/<filename>
// with optional type/domain frontmatter (legacy behaviour).
type WriteNoteOptions struct {
Content string
Filename string
Type string
Domain string
Wing string
Hall string
SourceType string // "internal" marks a first-party observation (e.g. claudewatcher) that needs no external citation
@@ -126,9 +132,6 @@ func WriteNote(brainDir string, opts WriteNoteOptions) (string, error) {
if opts.Content == "" {
return "", fmt.Errorf("content is required")
}
if opts.Wing == "" || opts.Hall == "" {
return "", fmt.Errorf("wing and hall are required")
}
// In the primitive, not in a caller: POST /write reaches here directly,
// without the BrainStore, and a gate one door wide is not a gate.
@@ -140,7 +143,13 @@ func WriteNote(brainDir string, opts WriteNoteOptions) (string, error) {
}
opts.Content = clean
return writeHallNote(brainDir, opts)
if opts.Wing != "" && opts.Hall != "" {
return writeHallNote(brainDir, opts)
}
if opts.Wing != "" || opts.Hall != "" {
return "", fmt.Errorf("wing and hall must be set together")
}
return writeLegacyNote(brainDir, opts)
}
// writeHallNote routes a note into brain/wiki/<wing>/<hall>/ and injects
@@ -198,6 +207,9 @@ func writeHallNote(brainDir string, opts WriteNoteOptions) (string, error) {
fmt.Fprintf(&fm, "%s: %s\n", key, fallback)
}
}
writeField("type", opts.Type)
writeField("domain", opts.Domain)
sourceType := opts.SourceType
if sourceType == "" && opts.Hall == "facts" {
// Most hall=facts entries are first-party (an eval/benchmark the
@@ -288,7 +300,53 @@ func splitFrontmatter(content string) (fields []frontmatterField, body string) {
return fields, body
}
// Write handles POST /write — write a note into brain/wiki/<wing>/<hall>/.
// writeLegacyNote preserves the original brain/knowledge/ behaviour for
// callers that have not adopted the wing/hall taxonomy.
func writeLegacyNote(brainDir string, opts WriteNoteOptions) (string, error) {
filename := opts.Filename
if filename == "" {
filename = fmt.Sprintf("%s-auto.md", time.Now().UTC().Format("2006-01-02-150405"))
}
rawDir := filepath.Join(brainDir, "knowledge")
if err := os.MkdirAll(rawDir, 0o755); err != nil {
return "", fmt.Errorf("create raw dir: %w", err)
}
finalContent := opts.Content
if opts.Type != "" || opts.Domain != "" {
var fm strings.Builder
fm.WriteString("---\n")
if opts.Type != "" {
fmt.Fprintf(&fm, "type: %s\n", opts.Type)
}
if opts.Domain != "" {
fmt.Fprintf(&fm, "domain: %s\n", opts.Domain)
}
fm.WriteString("---\n")
finalContent = fm.String() + opts.Content
}
if strings.ContainsAny(filename, `/\`) {
return "", fmt.Errorf("invalid filename")
}
base := filepath.Base(filename)
if base == "." || base == ".." || base == "" {
return "", fmt.Errorf("invalid filename")
}
if !strings.HasSuffix(base, ".md") {
base += ".md"
}
dest := filepath.Join(rawDir, base)
if err := os.WriteFile(dest, []byte(finalContent), 0o644); err != nil {
return "", fmt.Errorf("write: %w", err)
}
rel, _ := filepath.Rel(brainDir, dest)
return filepath.ToSlash(rel), nil
}
// Write handles POST /write — write raw content to brain/knowledge/.
func (h *Handler) Write(w http.ResponseWriter, r *http.Request) {
var req writeRequest
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
@@ -301,10 +359,10 @@ func (h *Handler) Write(w http.ResponseWriter, r *http.Request) {
writeError(w, http.StatusBadRequest, err.Error())
return
}
// WriteNote errors out above unless both are set, so this always runs —
// no legacy fallback path left to guard against.
if err := brain.BuildWingIndex(h.brainDir, req.Wing); err != nil {
h.logger.Warn("auto-index failed", "wing", req.Wing, "err", err)
if req.Wing != "" && req.Hall != "" {
if err := brain.BuildWingIndex(h.brainDir, req.Wing); err != nil {
h.logger.Warn("auto-index failed", "wing", req.Wing, "err", err)
}
}
writeJSON(w, map[string]string{"path": relPath})
}
+46 -98
View File
@@ -65,13 +65,11 @@ func TestQuery_ReturnsResults(t *testing.T) {
assert.NotEmpty(t, results)
}
func TestWrite_CreatesWikiFile(t *testing.T) {
func TestWrite_CreatesKnowledgeFile(t *testing.T) {
dir, h := setup(t)
body, _ := json.Marshal(map[string]any{
"content": "# Test note\n\nSome content.",
"filename": "test-note",
"wing": "homelab",
"hall": "facts",
"filename": "test-note.md",
})
req := httptest.NewRequest(http.MethodPost, "/write", bytes.NewReader(body))
rec := httptest.NewRecorder()
@@ -83,25 +81,11 @@ func TestWrite_CreatesWikiFile(t *testing.T) {
require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &resp))
assert.NotEmpty(t, resp["path"])
content, err := os.ReadFile(filepath.Join(dir, "wiki", "homelab", "facts", "test-note.md"))
content, err := os.ReadFile(filepath.Join(dir, "knowledge", "test-note.md"))
require.NoError(t, err)
assert.Contains(t, string(content), "Some content.")
}
// TestWrite_RequiresWingAndHall is the HTTP-contract counterpart of
// TestWriteNote_RequiresWingAndHall: a caller (e.g. the MCP brain_write
// handler) that omits wing/hall gets a 400, not a silent legacy write.
func TestWrite_RequiresWingAndHall(t *testing.T) {
_, h := setup(t)
body, _ := json.Marshal(map[string]any{"content": "no destination"})
req := httptest.NewRequest(http.MethodPost, "/write", bytes.NewReader(body))
rec := httptest.NewRecorder()
h.Write(rec, req)
assert.Equal(t, http.StatusBadRequest, rec.Code)
}
func TestQuery_RequiresQuery(t *testing.T) {
_, h := setup(t)
body, _ := json.Marshal(map[string]any{"limit": 5})
@@ -113,6 +97,27 @@ func TestQuery_RequiresQuery(t *testing.T) {
assert.Equal(t, http.StatusBadRequest, rec.Code)
}
func TestWrite_IncludesFrontmatterWhenTypeProvided(t *testing.T) {
dir, h := setup(t)
body, _ := json.Marshal(map[string]any{
"content": "Some learning.",
"filename": "typed-note.md",
"type": "concept",
"domain": "software",
})
req := httptest.NewRequest(http.MethodPost, "/write", bytes.NewReader(body))
rec := httptest.NewRecorder()
h.Write(rec, req)
assert.Equal(t, http.StatusOK, rec.Code)
content, err := os.ReadFile(filepath.Join(dir, "knowledge", "typed-note.md"))
require.NoError(t, err)
assert.Contains(t, string(content), "type: concept")
assert.Contains(t, string(content), "domain: software")
assert.Contains(t, string(content), "Some learning.")
}
func TestWriteNote_HallRouteIncludesSourceTypeWhenSet(t *testing.T) {
dir := t.TempDir()
@@ -121,6 +126,7 @@ func TestWriteNote_HallRouteIncludesSourceTypeWhenSet(t *testing.T) {
Filename: "session-koala-abc",
Wing: "claude-sessions",
Hall: "facts",
Type: "source",
SourceType: "internal",
})
require.NoError(t, err)
@@ -204,95 +210,37 @@ func TestWriteNote_HallRouteMergesExistingFrontmatterInsteadOfStacking(t *testin
assert.Contains(t, body, "# Body")
}
// TestWriteNote_RequiresWingAndHall pins the post-legacy-removal contract
// (hyperguild#79 / ADR-0012): with the knowledge/ fallback gone, wing+hall
// is the only valid destination, so omitting either is a caller error, not
// a silent fallback.
func TestWriteNote_RequiresWingAndHall(t *testing.T) {
cases := []struct {
name string
wing string
hall string
}{
{"neither set", "", ""},
{"wing only", "homelab", ""},
{"hall only", "", "facts"},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
dir := t.TempDir()
_, err := api.WriteNote(dir, api.WriteNoteOptions{
Content: "body",
Wing: tc.wing,
Hall: tc.hall,
})
require.Error(t, err)
assert.Contains(t, err.Error(), "wing and hall are required")
})
}
func TestWriteNote_HallRouteExistingTypeWinsOverOptsType(t *testing.T) {
dir := t.TempDir()
rel, err := api.WriteNote(dir, api.WriteNoteOptions{
Content: "---\ntype: hypothesis\n---\n\nBody.\n",
Filename: "note",
Wing: "agentsquad",
Hall: "decisions",
Type: "decision", // should lose to content's own "type: hypothesis"
})
require.NoError(t, err)
got, err := os.ReadFile(filepath.Join(dir, filepath.FromSlash(rel)))
require.NoError(t, err)
assert.Contains(t, string(got), "type: hypothesis")
assert.NotContains(t, string(got), "type: decision")
}
func TestWrite_GeneratesFilenameIfAbsent(t *testing.T) {
dir, h := setup(t)
body, _ := json.Marshal(map[string]any{
"content": "auto name",
"wing": "homelab",
"hall": "facts",
})
body, _ := json.Marshal(map[string]any{"content": "auto name"})
req := httptest.NewRequest(http.MethodPost, "/write", bytes.NewReader(body))
rec := httptest.NewRecorder()
h.Write(rec, req)
assert.Equal(t, http.StatusOK, rec.Code)
entries, err := os.ReadDir(filepath.Join(dir, "wiki", "homelab", "facts"))
require.NoError(t, err)
require.Len(t, entries, 1)
assert.True(t, strings.HasSuffix(entries[0].Name(), ".md"))
}
// TestWrite_CLIPayloadRoundTrips exercises the real Handler.Write (not a
// hand-rolled mock) over an actual HTTP round trip, POSTing the exact JSON
// envelope cmd/hyperguild's brainClient.Write sends: {wing, hall, filename,
// content}. cmd/hyperguild lives in a separate Go module from ingestion
// (no shared go.work), so a Go-level test can't import brainClient
// directly — this test instead pins the wire contract from the server
// side and proves a real `hyperguild brain write <wing> <hall> <slug>`
// invocation writes a real file with real frontmatter under wiki/<wing>/<hall>/.
// A prior version of this contract test on the client side (in
// cmd/hyperguild/http_test.go) used only an httptest.NewServer with a
// hand-rolled mock body, so it stayed green through a regression where the
// server required wing/hall but the client never sent them (hyperguild#79
// PR review).
func TestWrite_CLIPayloadRoundTrips(t *testing.T) {
dir, h := setup(t)
srv := httptest.NewServer(http.HandlerFunc(h.Write))
defer srv.Close()
payload, err := json.Marshal(struct {
Wing string `json:"wing"`
Hall string `json:"hall"`
Filename string `json:"filename"`
Content string `json:"content"`
}{Wing: "homelab", Hall: "facts", Filename: "cli-roundtrip", Content: "# CLI roundtrip\n\nReal write.\n"})
require.NoError(t, err)
resp, err := http.Post(srv.URL+"/write", "application/json", bytes.NewReader(payload)) //nolint:noctx
require.NoError(t, err)
defer resp.Body.Close() //nolint:errcheck
assert.Equal(t, http.StatusOK, resp.StatusCode)
var out struct {
Path string `json:"path"`
}
require.NoError(t, json.NewDecoder(resp.Body).Decode(&out))
assert.Equal(t, "wiki/homelab/facts/cli-roundtrip.md", out.Path)
written, err := os.ReadFile(filepath.Join(dir, "wiki", "homelab", "facts", "cli-roundtrip.md"))
require.NoError(t, err)
assert.Contains(t, string(written), "wing: homelab")
assert.Contains(t, string(written), "hall: facts")
assert.Contains(t, string(written), "Real write.")
entries, _ := os.ReadDir(filepath.Join(dir, "knowledge"))
// +1 because setup already wrote tdd.md
assert.Len(t, entries, 2)
assert.True(t, strings.HasSuffix(entries[1].Name(), ".md"))
}
// ---------------------------------------------------------------------------
-62
View File
@@ -145,68 +145,6 @@ func PromoteNote(brainDir string, opts PromoteOptions) (string, error) {
return relSlash, nil
}
// RejectOptions identifies a raw note to reject and why.
type RejectOptions struct {
Filename string // basename in brain/raw/
Reason string // optional
}
// RejectNote records a human decision not to promote a brain/raw/ note,
// without silently losing it: it stamps rejected_at (+ reject_reason when
// given) into frontmatter and moves the file to brain/raw/rejected/, using
// the same write-then-delete safety PromoteNote uses — the source survives
// any write failure — and the same basename-only filename validation.
//
// A rejected note never entered the wiki, so no index rebuild or
// auto-tunnel run: unlike PromoteNote, this is the end of the note's
// journey, not the start of a new one. It stays out of ListPending's view
// (raw/rejected/ is a subdirectory, and ListPending's os.ReadDir on raw/
// does not recurse), so a rejected note is never re-surfaced as pending —
// the human decision, once made, stays made, the same principle behind
// this estate's "issue status is surfaced, not auto-closed, but once a
// human decides, the decision is recorded" rule applied one level earlier.
func RejectNote(brainDir string, opts RejectOptions) (string, error) {
base := filepath.Base(opts.Filename)
if base != opts.Filename || base == "." || base == ".." || strings.ContainsAny(opts.Filename, `/\`) {
return "", fmt.Errorf("invalid filename %q", opts.Filename)
}
src := filepath.Join(brainDir, "raw", base)
raw, err := os.ReadFile(src)
if err != nil {
if os.IsNotExist(err) {
return "", fmt.Errorf("pending note %q does not exist in raw/", base)
}
return "", fmt.Errorf("read source: %w", err)
}
dest := filepath.Join(brainDir, "raw", "rejected", base)
if _, statErr := os.Stat(dest); statErr == nil {
rel, _ := filepath.Rel(brainDir, dest)
return "", fmt.Errorf("a rejected note named %s already exists", filepath.ToSlash(rel))
}
fm, body := parseFrontmatter(string(raw))
fm.set("rejected_at", time.Now().UTC().Format(time.RFC3339))
if opts.Reason != "" {
fm.set("reject_reason", opts.Reason)
}
if err := os.MkdirAll(filepath.Dir(dest), 0o755); err != nil {
return "", fmt.Errorf("create rejected dir: %w", err)
}
// Write-then-delete: the source survives any write failure.
if err := os.WriteFile(dest, []byte(fm.render()+body), 0o644); err != nil {
return "", fmt.Errorf("write rejected note: %w", err)
}
if err := os.Remove(src); err != nil {
return "", fmt.Errorf("rejected note written but source removal failed: %w", err)
}
rel, _ := filepath.Rel(brainDir, dest)
return filepath.ToSlash(rel), nil
}
// excerpt returns the first n runes of s, trimmed, single-spaced.
func excerpt(s string, n int) string {
s = strings.TrimSpace(s)
-82
View File
@@ -119,85 +119,3 @@ func TestPromoteRebuildsWingIndex(t *testing.T) {
require.NoError(t, err, "wing _index regenerated")
assert.Contains(t, string(idx), "x", "promoted note appears in the index")
}
// --- RejectNote (hyperguild#81) ---------------------------------------------
func TestRejectHappyPath(t *testing.T) {
dir := t.TempDir()
writeRaw(t, dir, "2026-04-23-fed-sentiment-scrape.md",
"---\ncreated_at: 2026-04-23T13:20:07Z\n---\n# Sentiment scrape\n\nbody.\n")
rel, err := RejectNote(dir, RejectOptions{
Filename: "2026-04-23-fed-sentiment-scrape.md", Reason: "generic scrape, not homelab-relevant",
})
require.NoError(t, err)
assert.Equal(t, "raw/rejected/2026-04-23-fed-sentiment-scrape.md", rel)
// Source removed from the pending queue.
_, statErr := os.Stat(filepath.Join(dir, "raw", "2026-04-23-fed-sentiment-scrape.md"))
assert.True(t, os.IsNotExist(statErr), "source removed from raw/ after reject")
got, err := os.ReadFile(filepath.Join(dir, filepath.FromSlash(rel)))
require.NoError(t, err)
s := string(got)
assert.Contains(t, s, "created_at: 2026-04-23T13:20:07Z", "original created_at preserved")
assert.Contains(t, s, "rejected_at:")
assert.Contains(t, s, "reject_reason: generic scrape, not homelab-relevant")
assert.Contains(t, s, "# Sentiment scrape", "body preserved for later reference")
// Rejected notes never entered the wiki, and are no longer pending.
pending, err := ListPending(dir)
require.NoError(t, err)
assert.Empty(t, pending)
}
func TestRejectWithoutReason(t *testing.T) {
dir := t.TempDir()
writeRaw(t, dir, "2026-06-01-x.md", "body\n")
rel, err := RejectNote(dir, RejectOptions{Filename: "2026-06-01-x.md"})
require.NoError(t, err)
got, _ := os.ReadFile(filepath.Join(dir, filepath.FromSlash(rel)))
assert.NotContains(t, string(got), "reject_reason:", "no reason given, none stamped")
}
func TestRejectMissingSourceErrors(t *testing.T) {
_, err := RejectNote(t.TempDir(), RejectOptions{Filename: "ghost.md"})
require.Error(t, err)
}
func TestRejectRejectsTraversalFilename(t *testing.T) {
_, err := RejectNote(t.TempDir(), RejectOptions{Filename: "../escape.md"})
require.Error(t, err)
}
func TestRejectCollisionNoOverwrite(t *testing.T) {
dir := t.TempDir()
dest := filepath.Join(dir, "raw", "rejected", "x.md")
require.NoError(t, os.MkdirAll(filepath.Dir(dest), 0o755))
require.NoError(t, os.WriteFile(dest, []byte("EXISTING\n"), 0o644))
writeRaw(t, dir, "x.md", "NEW\n")
_, err := RejectNote(dir, RejectOptions{Filename: "x.md"})
require.Error(t, err, "collision must error, not overwrite")
got, _ := os.ReadFile(dest)
assert.Equal(t, "EXISTING\n", string(got), "target not overwritten")
_, statErr := os.Stat(filepath.Join(dir, "raw", "x.md"))
assert.NoError(t, statErr, "source preserved on collision (atomic: no delete without write)")
}
func TestRejectedNotesAreNotListedAsPendingAgain(t *testing.T) {
// ListPending already skips tunnel-candidates-*.md; confirm raw/rejected/
// (a subdirectory) doesn't leak into the top-level pending listing either
// — os.ReadDir on raw/ doesn't recurse, but pin it so a future change to
// ListPending can't silently start surfacing rejected notes as pending
// again.
dir := t.TempDir()
writeRaw(t, dir, "2026-06-01-x.md", "body\n")
_, err := RejectNote(dir, RejectOptions{Filename: "2026-06-01-x.md"})
require.NoError(t, err)
pending, err := ListPending(dir)
require.NoError(t, err)
assert.Empty(t, pending, "a rejected note must not still appear as pending")
}
+2
View File
@@ -51,6 +51,8 @@ func (s *Store) Write(ctx context.Context, n capture.Note) (capture.Ref, error)
relPath, err := api.WriteNote(s.brainDir, api.WriteNoteOptions{
Content: n.Content,
Filename: n.Filename,
Type: n.Type,
Domain: n.Domain,
Wing: n.Wing,
Hall: n.Hall,
})
+5 -2
View File
@@ -31,14 +31,17 @@ type StoredNote struct {
Body string
}
// Note is the brain-write payload: wing+hall are the only routing fields
// (the legacy type/domain params were removed — ADR-0012 / #79). Reason is
// Note is the brain-write payload. It carries both the wing/hall taxonomy
// and the legacy type/domain fields so a single BrainStore serves both
// capture insights and the existing MCP brain_write surface. Reason is
// the supersede rationale, used only by Update.
type Note struct {
Content string
Filename string
Wing string
Hall string
Type string
Domain string
Reason string
}
+10 -32
View File
@@ -53,12 +53,14 @@ func (s *Server) tools() []map[string]any {
},
{
"name": "brain_write",
"description": "Write a markdown note to brain/wiki/<wing>/<hall>/ with wing/hall/created_at frontmatter. Both wing and hall are required.",
"inputSchema": schema([]string{"content", "wing", "hall"}, map[string]any{
"description": "Write a markdown note to the brain. With wing+hall set, routes to brain/wiki/<wing>/<hall>/ with wing/hall/created_at frontmatter; otherwise writes to brain/knowledge/ (legacy).",
"inputSchema": schema([]string{"content"}, map[string]any{
"content": str("markdown content"),
"filename": str("optional filename or slug"),
"wing": str("topic domain, e.g. jepa-fx"),
"hall": enum("memory type", halls...),
"type": str("optional frontmatter type (legacy)"),
"domain": str("optional frontmatter domain (legacy)"),
"wing": str("optional topic domain, e.g. jepa-fx"),
"hall": enum("optional memory type (requires wing)", halls...),
}),
},
{
@@ -96,14 +98,6 @@ func (s *Server) tools() []map[string]any {
"slug": str("optional target slug; defaults to filename minus date prefix"),
}),
},
{
"name": "brain_reject",
"description": "Reject a brain/raw/ note: stamps rejected_at (+ reject_reason if given) into frontmatter and moves it to brain/raw/rejected/ — never deleted outright, and never re-surfaced by brain_pending. The third option alongside promote/leave-pending; a human decision, never automatic. Returns {path}.",
"inputSchema": schema([]string{"filename"}, map[string]any{
"filename": str("basename in brain/raw/, e.g. 2026-04-23-fed-sentiment-scrape.md"),
"reason": str("optional; why this isn't worth promoting"),
}),
},
noteToolDescriptors()[0],
noteToolDescriptors()[1],
{
@@ -233,6 +227,8 @@ func (s *Server) brainQuery(ctx context.Context, args json.RawMessage) (json.Raw
type brainWriteArgs struct {
Content string `json:"content"`
Filename string `json:"filename,omitempty"`
Type string `json:"type,omitempty"`
Domain string `json:"domain,omitempty"`
Wing string `json:"wing,omitempty"`
Hall string `json:"hall,omitempty"`
}
@@ -258,6 +254,8 @@ func (s *Server) brainWrite(ctx context.Context, args json.RawMessage) (json.Raw
ref, err := s.store.Write(ctx, capture.Note{
Content: a.Content,
Filename: a.Filename,
Type: a.Type,
Domain: a.Domain,
Wing: a.Wing,
Hall: a.Hall,
})
@@ -397,26 +395,6 @@ func (s *Server) brainPromote(ctx context.Context, args json.RawMessage) (json.R
return json.Marshal(map[string]string{"path": relPath})
}
type brainRejectArgs struct {
Filename string `json:"filename"`
Reason string `json:"reason,omitempty"`
}
// brainReject records a decision not to promote a raw/ note (api.RejectNote:
// frontmatter-stamp + move to raw/rejected/). No graph indexing — a rejected
// note never entered the wiki, so there's nothing to index.
func (s *Server) brainReject(_ context.Context, args json.RawMessage) (json.RawMessage, error) {
var a brainRejectArgs
if err := json.Unmarshal(args, &a); err != nil {
return nil, fmt.Errorf("parse args: %w", err)
}
relPath, err := api.RejectNote(s.brainDir, api.RejectOptions{Filename: a.Filename, Reason: a.Reason})
if err != nil {
return nil, err
}
return json.Marshal(map[string]string{"path": relPath})
}
// indexInGraph is a best-effort wrapper around graphsync.IndexDoc that
// logs failures but never propagates them — the underlying write/ingest
// has already succeeded and the graph is an augmentation, not a
+29 -70
View File
@@ -51,50 +51,25 @@ func TestBrainQueryReturnsResults(t *testing.T) {
assert.Contains(t, text, "tdd.md")
}
// TestBrainWriteIgnoresLegacyTypeAndDomainParams pins the post-#79 contract:
// domain/type were removed from the schema and the handler's arg struct, so
// a caller that still sends them (the old MCP surface) gets a normal wing+
// hall write with no error and no effect from the stale fields — silently
// dropped by json.Unmarshal, not rejected. Only content in its OWN
// frontmatter (unrelated to these params) can set type/domain, per
// TestWriteNote_HallRouteMergesExistingFrontmatterInsteadOfStacking in the
// api package.
func TestBrainWriteIgnoresLegacyTypeAndDomainParams(t *testing.T) {
func TestBrainWriteCreatesFile(t *testing.T) {
brainDir := t.TempDir()
srv := mcp.NewServer(brainDir, nil, nil, nil)
resp := toolCall(t, srv, "brain_write", map[string]any{
"content": "# Test\n\nbody",
"filename": "test",
"wing": "homelab",
"hall": "facts",
"filename": "test.md",
"type": "note",
"domain": "personal",
})
require.Nil(t, resp["error"])
got, err := os.ReadFile(filepath.Join(brainDir, "wiki", "homelab", "facts", "test.md"))
got, err := os.ReadFile(filepath.Join(brainDir, "knowledge", "test.md"))
require.NoError(t, err)
assert.NotContains(t, string(got), "type: note")
assert.NotContains(t, string(got), "domain: personal")
assert.Contains(t, string(got), "type: note")
assert.Contains(t, string(got), "domain: personal")
assert.Contains(t, string(got), "# Test")
}
// TestBrainWriteRequiresWingAndHall is the MCP-tool-call counterpart of
// api.TestWriteNote_RequiresWingAndHall: the legacy brain/knowledge/
// fallback is gone, so a caller omitting either param gets a tool error,
// not a silent legacy write.
func TestBrainWriteRequiresWingAndHall(t *testing.T) {
brainDir := t.TempDir()
srv := mcp.NewServer(brainDir, nil, nil, nil)
resp := toolCall(t, srv, "brain_write", map[string]any{
"content": "x",
"filename": "no-destination",
})
require.NotNil(t, resp["error"])
}
func TestBrainWriteWingHallRoutesToWiki(t *testing.T) {
brainDir := t.TempDir()
srv := mcp.NewServer(brainDir, nil, nil, nil)
@@ -233,11 +208,30 @@ func TestBrainTunnelRejectsMissing(t *testing.T) {
require.NotNil(t, resp["error"])
}
// Filename traversal/sanitisation on the wiki route is covered directly
// against brain.NotePath/Sanitise in internal/brain/path_test.go
// (TestNotePath_SanitisesWingAndSlug, TestSanitise) — those tests exercised
// the now-deleted brain/knowledge/ legacy path's own separate filename
// validation, which had no equivalent once that path was removed (#79).
func TestBrainWriteRejectsTraversal(t *testing.T) {
brainDir := t.TempDir()
srv := mcp.NewServer(brainDir, nil, nil, nil)
resp := toolCall(t, srv, "brain_write", map[string]any{
"content": "x",
"filename": "../escape.md",
})
require.NotNil(t, resp["error"])
}
func TestBrainWriteAcceptsDoubleDotInName(t *testing.T) {
brainDir := t.TempDir()
srv := mcp.NewServer(brainDir, nil, nil, nil)
resp := toolCall(t, srv, "brain_write", map[string]any{
"content": "x",
"filename": "notes..draft.md",
})
require.Nil(t, resp["error"])
_, err := os.Stat(filepath.Join(brainDir, "knowledge", "notes..draft.md"))
require.NoError(t, err, "filename with embedded .. should be allowed")
}
func TestBrainIngestRawDryRun(t *testing.T) {
brainDir := t.TempDir()
@@ -396,38 +390,3 @@ func TestBrainPromoteInvalidHallErrors(t *testing.T) {
_, srcErr := os.Stat(filepath.Join(raw, "x.md"))
assert.NoError(t, srcErr, "source untouched on validation error")
}
func TestBrainRejectMovesToRejectedSubdir(t *testing.T) {
brainDir := t.TempDir()
raw := filepath.Join(brainDir, "raw")
require.NoError(t, os.MkdirAll(raw, 0o755))
require.NoError(t, os.WriteFile(filepath.Join(raw, "2026-04-23-scrape.md"),
[]byte("---\ncreated_at: 2026-04-23T13:20:07Z\n---\n# Scrape\n\nbody\n"), 0o644))
srv := mcp.NewServer(brainDir, nil, nil, nil)
resp := toolCall(t, srv, "brain_reject", map[string]any{
"filename": "2026-04-23-scrape.md", "reason": "generic scrape, not homelab-relevant",
})
require.Nil(t, resp["error"], "got: %v", resp["error"])
text := resp["result"].(map[string]any)["content"].([]any)[0].(map[string]any)["text"].(string)
assert.Contains(t, text, "raw/rejected/2026-04-23-scrape.md")
got, err := os.ReadFile(filepath.Join(brainDir, "raw/rejected/2026-04-23-scrape.md"))
require.NoError(t, err)
assert.Contains(t, string(got), "reject_reason: generic scrape, not homelab-relevant")
_, srcErr := os.Stat(filepath.Join(raw, "2026-04-23-scrape.md"))
assert.True(t, os.IsNotExist(srcErr), "source removed from raw/")
// A rejected note must not still show up as pending.
pendingResp := toolCall(t, srv, "brain_pending", map[string]any{})
pendingText := pendingResp["result"].(map[string]any)["content"].([]any)[0].(map[string]any)["text"].(string)
assert.Contains(t, pendingText, `"pending":[]`)
}
func TestBrainRejectMissingSourceErrors(t *testing.T) {
brainDir := t.TempDir()
srv := mcp.NewServer(brainDir, nil, nil, nil)
resp := toolCall(t, srv, "brain_reject", map[string]any{"filename": "ghost.md"})
require.NotNil(t, resp["error"])
}
-2
View File
@@ -275,8 +275,6 @@ func (s *Server) handleCall(ctx context.Context, name string, args json.RawMessa
return s.brainPending(ctx, args)
case "brain_promote":
return s.brainPromote(ctx, args)
case "brain_reject":
return s.brainReject(ctx, args)
case "capture":
return s.brainCapture(ctx, args)
case "brain_read":
+1 -1
View File
@@ -58,7 +58,7 @@ func TestServerToolsList(t *testing.T) {
}
assert.ElementsMatch(t, []string{
"brain_query", "brain_write", "brain_update", "brain_get",
"brain_pending", "brain_promote", "brain_reject",
"brain_pending", "brain_promote",
"brain_read", "brain_edit",
"brain_tunnel",
"brain_ingest_raw", "brain_ingest",
-175
View File
@@ -11,7 +11,6 @@ import (
"github.com/mathiasbq/hyperguild/ingestion/internal/brain"
"github.com/mathiasbq/hyperguild/ingestion/internal/capture"
"github.com/mathiasbq/hyperguild/ingestion/internal/claim"
"github.com/mathiasbq/hyperguild/ingestion/internal/classification"
"github.com/mathiasbq/hyperguild/ingestion/internal/notes"
)
@@ -180,20 +179,6 @@ func (s *Server) editWithScope(args json.RawMessage, scope notes.Scope) (notes.R
if err := json.Unmarshal(args, &a); err != nil {
return notes.Result{}, nil, fmt.Errorf("parse args: %w", err)
}
// hyperguild#123: brain_write/brain_update both validate the claim
// envelope before writing (hyperguild#111: "same rules when a note
// changes as when it's born"); brain_edit didn't — a byte-level string
// replace has no frontmatter awareness at all, so it could rewrite an
// existing half_life:/applies:/claim_provenance: line straight past the
// validator entirely. Scoped to notes only (governance files have no
// claim-envelope concept).
if scope == notes.ScopeNotes {
if verr := checkClaimEnvelope(s.brainDir, a.Path, a.OldStr, a.NewStr); verr != nil {
return notes.Result{}, nil, fmt.Errorf("claim envelope: %w", verr)
}
}
res, err := notes.Edit(s.brainDir, a.Path, a.OldStr, a.NewStr, scope)
if err != nil {
if errors.Is(err, notes.ErrDegenerate) && a.OldStr == "" {
@@ -243,163 +228,3 @@ func touchesFrontmatter(oldStr, newStr string) bool {
}
return false
}
// checkClaimEnvelope previews what old_str->new_str would produce — the
// exact strings.Replace(before, oldStr, newStr, 1) formula notes.Edit
// itself uses internally — and validates the resulting frontmatter's claim
// envelope before the real edit is allowed to run. Fail-closed: an invalid
// result blocks the edit entirely, the same posture writeHallNote/UpdateNote
// already apply on create/supersede.
//
// Gated on old_str appearing within the note's frontmatter BLOCK, not on
// old_str/new_str mentioning a claim-envelope field NAME — found in review:
// a field-name-substring gate misses a value-only edit like
// "asserted"->"guessed" on a claim_provenance line, which never mentions
// the field name at all. That is exactly the shape of edit a minimal,
// natural diff produces, so a field-name gate was closing the issue in
// name only. Checking block containment instead means any edit that
// couldn't possibly touch the frontmatter (its target text only exists in
// the body) is still skipped cheaply, while nothing inside the fence can
// slip through unvalidated regardless of which token it targets.
//
// This does not replicate notes.Edit's uniqueness/CRLF/conflict-marker
// checks — if old_str is absent or ambiguous, this preview may not match
// what Edit ultimately does, but Edit independently and correctly rejects
// those cases at write time regardless of what this function decides, so
// the only thing riding on this preview's accuracy is the envelope check
// itself, not write safety.
// checkClaimEnvelope previews what old_str->new_str would produce and
// validates the resulting claim envelope before the real edit runs
// (hyperguild#123). Seven review rounds closed every plausible bypass in the
// fence-detection family (field-name substring, block-containment,
// fence-stripping, CRLF, UTF-8 BOM) and the first instance of a
// value-extraction gap (a folded YAML block scalar hiding a value behind an
// empty inline colon).
//
// Known, accepted v1 gap: frontmatterScalars's block-scalar fold is a
// best-effort approximation, not a YAML parser — a blank line interrupting a
// folded continuation, or other contrived multi-line YAML shapes not yet
// probed (block-scalar indicators `|`/`>`, inline comments on a key line,
// quoted multi-line values), can still hide an invalid value from
// ValidateEnvelope. Accepted deliberately rather than chased indefinitely:
// every bypass found so far requires the caller to already hold brain_edit
// write access and to deliberately construct a specific malformed-YAML shape
// with knowledge of this exact gap — a narrow, low-likelihood threat next to
// the diminishing returns of another incremental patch round. The real fix
// (a shared, tested, encoding-normalized frontmatter parser used by all
// three independent implementations in this codebase) is tracked separately
// as hyperguild#138, not bolted on here piece by piece.
func checkClaimEnvelope(brainDir, path, oldStr, newStr string) error {
if oldStr == "" {
// hyperguild#115: strings.Replace treats "" as matching position 0,
// which would make an empty old_str look like an edit that inserts
// text before the fence — a degenerate-input case that belongs to
// notes.Edit's own "old_str is empty" refusal, not to the envelope
// check.
return nil
}
before, err := notes.Read(brainDir, path)
if err != nil {
// Let notes.Edit itself produce the real error (missing file, etc.)
// — this function's job is the envelope, not read failures.
return nil
}
// No gate on where old_str falls relative to the frontmatter fence:
// round 2 found that requiring old_str to be fully contained in the
// extracted block was itself bypassable by an old_str disambiguated
// across the closing "---" into the body. Simpler and bypass-proof:
// always compute what the edit would produce and validate that
// resulting state's envelope. A body-only edit leaves the frontmatter
// (and thus the validation outcome) unchanged, so this is a no-op for
// the common case and fail-closed for every case that touches the
// envelope, regardless of how old_str is phrased.
_, hadFence := frontmatterBlock(string(before))
after := strings.Replace(string(before), oldStr, newStr, 1)
_, hasFence := frontmatterBlock(after)
if hadFence && !hasFence {
// Round 3: an edit that drops the closing fence degrades `after`
// to "unfenced" — frontmatterScalars then sees an empty map and
// ValidateEnvelope({}) is nil by design (absent fields are valid),
// so an invalid value would otherwise land with zero error while
// also corrupting the note's structure. A previously-fenced note
// must stay fenced, full stop.
return fmt.Errorf("edit would remove the frontmatter fence")
}
return claim.ValidateEnvelope(frontmatterScalars(after))
}
// frontmatterBlock returns the raw text between doc's opening and closing
// `---` fences, or ok=false if doc has no (properly closed) fence.
func frontmatterBlock(doc string) (block string, ok bool) {
// Round 4 found a note with CRLF fence lines ("---\r\n") silently
// defeats HasPrefix(doc, "---\n") on the precondition read — not an
// adversarial old_str/new_str, just an encoding difference — which
// makes checkClaimEnvelope no-op entirely. Round 5 found the same
// mechanism one layer earlier: a leading UTF-8 BOM (a live, plausible
// byte sequence — Notepad's default "UTF-8" save and PowerShell's
// pre-v6 Out-File/Set-Content both emit one) defeats the same prefix
// check before CRLF normalization even applies. Strip both, here, so
// every caller (hadFence/hasFence detection and frontmatterScalars)
// agrees regardless of encoding.
doc = strings.TrimPrefix(doc, "\xef\xbb\xbf")
doc = strings.ReplaceAll(doc, "\r\n", "\n")
if !strings.HasPrefix(doc, "---\n") {
return "", false
}
rest := doc[len("---\n"):]
end := strings.Index(rest, "\n---\n")
if end < 0 {
return "", false
}
return rest[:end], true
}
// frontmatterScalars extracts top-level "key: value" scalar pairs from
// doc's leading fence block, for the claim-envelope check only — not a
// general frontmatter parser. Indented lines (YAML block-list items,
// wrapped values) are skipped rather than misparsed as keys, same fix as
// hyperguild#126/#128 in the sibling packages this mirrors.
func frontmatterScalars(doc string) map[string]string {
out := map[string]string{}
block, ok := frontmatterBlock(doc)
if !ok {
return out
}
lines := strings.Split(block, "\n")
for i := 0; i < len(lines); i++ {
line := lines[i]
if line != "" && (line[0] == ' ' || line[0] == '\t') {
continue
}
key, val, ok := strings.Cut(line, ":")
if !ok {
continue
}
val = strings.TrimSpace(val)
if val == "" {
// Round 6: a colon with nothing after it is ambiguous — it can
// be a genuinely empty/omitted value, or the start of a YAML
// block scalar whose real value lives on the indented
// continuation line(s) that follow (e.g. "half_life:\n
// durable"). Treating the latter as absent let an edit smuggle
// an invalid value straight past ValidateEnvelope: the field
// read as unset while the disk actually carried a value. Fold
// the continuation in as a best-effort join so oneOf() still
// sees it. A genuinely empty value (no indented line follows)
// still folds to "", preserving present()'s existing
// placeholder-not-assertion contract.
var cont []string
for i+1 < len(lines) {
next := lines[i+1]
if next == "" || (next[0] != ' ' && next[0] != '\t') {
break
}
cont = append(cont, strings.TrimSpace(next))
i++
}
val = strings.Join(cont, " ")
}
out[strings.TrimSpace(key)] = val
}
return out
}
-237
View File
@@ -93,243 +93,6 @@ func TestBrainEdit_EmptyOldStrErrorNamesRawArgumentBytes(t *testing.T) {
assert.Contains(t, errMsg, "raw arguments were", "%v", errMsg)
}
func TestBrainEdit_RejectsAnInvalidClaimEnvelopeWrittenViaStringReplace(t *testing.T) {
// hyperguild#123: brain_write/brain_update both validate the claim
// envelope (half_life/applies/claim_provenance) before writing —
// brain_edit didn't, even though it's the one live, model-facing path
// that can rewrite an existing envelope line directly via raw string
// replace, no parsing involved. "same rules when a note changes as when
// it's born" (hyperguild#111's own framing) applies here too.
dir := newBrainRepo(t)
note := filepath.Join(dir, "wiki/homelab/facts/n.md")
require.NoError(t, os.WriteFile(note,
[]byte("---\ntitle: 'n'\nhalf_life: durable\napplies: universal\nclaim_provenance: asserted\n---\n\nbody\n"), 0o644))
srv := mcp.NewServer(dir, nil, nil, nil)
resp := call(t, srv, "brain_edit", map[string]any{
"path": "wiki/homelab/facts/n.md", "old_str": "claim_provenance: asserted", "new_str": "claim_provenance: guessed",
})
require.Contains(t, resp, "error", "%v", resp)
got, err := os.ReadFile(note)
require.NoError(t, err)
assert.Contains(t, string(got), "claim_provenance: asserted", "rejected edit must leave the note byte-identical")
}
func TestBrainEdit_RejectsAValueOnlyEditThatBreaksTheEnvelope(t *testing.T) {
// Found in review: the original gate (touchesClaimEnvelope) checked
// whether old_str/new_str mention the FIELD NAME — but a minimal diff
// (the natural shape of any real edit, model-generated or human) can
// target just the VALUE token and never mention the field name at all.
// "asserted" -> "guessed" on a claim_provenance line walked straight
// past the field-name substring check and wrote an invalid enum value
// with no error — the exact bypass #123 was supposed to close, closed
// in name only.
dir := newBrainRepo(t)
note := filepath.Join(dir, "wiki/homelab/facts/n.md")
require.NoError(t, os.WriteFile(note,
[]byte("---\ntitle: 'n'\nhalf_life: durable\napplies: universal\nclaim_provenance: asserted\n---\n\nbody\n"), 0o644))
srv := mcp.NewServer(dir, nil, nil, nil)
resp := call(t, srv, "brain_edit", map[string]any{
"path": "wiki/homelab/facts/n.md", "old_str": "asserted", "new_str": "guessed",
})
require.Contains(t, resp, "error", "%v", resp)
got, err := os.ReadFile(note)
require.NoError(t, err)
assert.Contains(t, string(got), "claim_provenance: asserted", "rejected edit must leave the note byte-identical")
}
func TestBrainEdit_RejectsAnOldStrThatCrossesTheClosingFence(t *testing.T) {
// Found in round-2 review: the position-based gate required old_str to
// be fully CONTAINED in the extracted frontmatter block (which excludes
// both "---" fence lines). An old_str disambiguated by extending past
// the closing fence into the body — a natural choice, since notes.Edit
// requires old_str to be unique in the file — fails that containment
// test, so checkClaimEnvelope skips validation entirely while
// notes.Edit still applies the replace verbatim. Same invalid-enum
// outcome as the original two bypasses, reached a third way.
dir := newBrainRepo(t)
note := filepath.Join(dir, "wiki/homelab/facts/n.md")
require.NoError(t, os.WriteFile(note,
[]byte("---\ntitle: 'n'\nhalf_life: durable\napplies: universal\nclaim_provenance: asserted\n---\n\nbody\n"), 0o644))
srv := mcp.NewServer(dir, nil, nil, nil)
resp := call(t, srv, "brain_edit", map[string]any{
"path": "wiki/homelab/facts/n.md",
"old_str": "asserted\n---\n\nbody",
"new_str": "guessed\n---\n\nbody",
})
require.Contains(t, resp, "error", "%v", resp)
got, err := os.ReadFile(note)
require.NoError(t, err)
assert.Contains(t, string(got), "claim_provenance: asserted", "rejected edit must leave the note byte-identical")
}
func TestBrainEdit_RejectsAnEditThatRemovesTheClosingFence(t *testing.T) {
// Found in round-3 review: checkClaimEnvelope always validates the
// resulting frontmatter of `after` — but an edit whose new_str drops
// the closing "---" degrades `after` to "unfenced" in the same call.
// frontmatterBlock(after) then returns ok=false, frontmatterScalars
// returns an empty map, and claim.ValidateEnvelope({}) is nil by
// design (absent fields are valid) — so an invalid enum value lands on
// disk with zero error, and the note is left permanently unfenced.
// Structural fix: a note that had a valid fence before the edit must
// still have one after, or the edit is rejected outright.
dir := newBrainRepo(t)
note := filepath.Join(dir, "wiki/homelab/facts/n.md")
require.NoError(t, os.WriteFile(note,
[]byte("---\ntitle: 'n'\nhalf_life: durable\napplies: universal\nclaim_provenance: asserted\n---\n\nbody\n"), 0o644))
srv := mcp.NewServer(dir, nil, nil, nil)
resp := call(t, srv, "brain_edit", map[string]any{
"path": "wiki/homelab/facts/n.md",
"old_str": "claim_provenance: asserted\n---\n",
"new_str": "claim_provenance: not-a-real-value\n",
})
require.Contains(t, resp, "error", "%v", resp)
got, err := os.ReadFile(note)
require.NoError(t, err)
assert.Contains(t, string(got), "claim_provenance: asserted\n---\n", "rejected edit must leave the note byte-identical, fence intact")
}
func TestBrainEdit_RejectsAnInvalidEnvelopeOnACRLFFencedNote(t *testing.T) {
// Found in round-4 review: frontmatterBlock's fence detection matches
// the literal byte sequence "---\n" / "\n---\n". A note whose fence
// lines use CRLF ("---\r\n") fails strings.HasPrefix(doc, "---\n") on
// the BEFORE read, so hadFence is false — not because the fence is
// missing, but because \r sits in front of every \n. hadFence&&!hasFence
// can then never fire, frontmatterScalars falls back to an empty map,
// and claim.ValidateEnvelope({}) is nil by design. No adversarial
// old_str/new_str crafting needed: encoding alone silently disables the
// whole envelope check for this note. Zero CRLF-fenced notes exist in
// the live corpus today, but nothing in the code prevents one.
dir := newBrainRepo(t)
note := filepath.Join(dir, "wiki/homelab/facts/n.md")
require.NoError(t, os.WriteFile(note,
[]byte("---\r\ntitle: 'n'\r\nhalf_life: durable\r\napplies: universal\r\nclaim_provenance: asserted\r\n---\r\n\r\nbody\r\n"), 0o644))
srv := mcp.NewServer(dir, nil, nil, nil)
resp := call(t, srv, "brain_edit", map[string]any{
"path": "wiki/homelab/facts/n.md", "old_str": "asserted", "new_str": "guessed",
})
require.Contains(t, resp, "error", "%v", resp)
got, err := os.ReadFile(note)
require.NoError(t, err)
assert.Contains(t, string(got), "claim_provenance: asserted", "rejected edit must leave the note byte-identical")
}
func TestBrainEdit_RejectsAnInvalidEnvelopeOnABOMPrefixedNote(t *testing.T) {
// Found in round-5 review: the same "encoding property empties
// frontmatterScalars's map" mechanism as the CRLF bypass, one layer
// earlier — a leading UTF-8 BOM (EF BB BF) defeats
// strings.HasPrefix(doc, "---\n") exactly like CRLF did, before that
// prefix is even reached. Notepad's default "UTF-8" save and
// PowerShell's pre-v6 Out-File/Set-Content both emit a BOM, so this is
// a live, plausible authoring path, not an exotic one — same severity
// and same one-line cost as the CRLF fix, fixed the same way rather
// than deferred to hyperguild#138.
dir := newBrainRepo(t)
note := filepath.Join(dir, "wiki/homelab/facts/n.md")
require.NoError(t, os.WriteFile(note,
[]byte("\xef\xbb\xbf---\ntitle: 'n'\nhalf_life: durable\napplies: universal\nclaim_provenance: asserted\n---\n\nbody\n"), 0o644))
srv := mcp.NewServer(dir, nil, nil, nil)
resp := call(t, srv, "brain_edit", map[string]any{
"path": "wiki/homelab/facts/n.md", "old_str": "asserted", "new_str": "guessed",
})
require.Contains(t, resp, "error", "%v", resp)
got, err := os.ReadFile(note)
require.NoError(t, err)
assert.Contains(t, string(got), "claim_provenance: asserted", "rejected edit must leave the note byte-identical")
}
func TestBrainEdit_RejectsAFoldedScalarThatHidesAnInvalidValue(t *testing.T) {
// Found in round-6 review: a different mechanism from the encoding
// family (rounds 1-6 were all about fence detection; this is the field
// extractor). old_str="half_life: durable", new_str="half_life:\n
// garbage-value" turns the field into a YAML block-scalar shape: the
// top-level line is now "half_life:" with an empty inline value, and
// the real value lives on the indented continuation line that follows.
// frontmatterScalars's indentation guard skips that continuation line
// outright, so the field reads as present-with-empty-value —
// present()'s own contract then treats that as absent (a placeholder,
// not an assertion) — and claim.ValidateEnvelope never sees the
// invalid value at all. No encoding quirk needed: one ordinary
// brain_edit call smuggles an out-of-enum value straight past the
// check the field was supposed to be validated by.
dir := newBrainRepo(t)
note := filepath.Join(dir, "wiki/homelab/facts/n.md")
require.NoError(t, os.WriteFile(note,
[]byte("---\ntitle: 'n'\nhalf_life: durable\napplies: universal\nclaim_provenance: asserted\n---\n\nbody\n"), 0o644))
srv := mcp.NewServer(dir, nil, nil, nil)
resp := call(t, srv, "brain_edit", map[string]any{
"path": "wiki/homelab/facts/n.md",
"old_str": "half_life: durable",
"new_str": "half_life:\n garbage-value",
})
require.Contains(t, resp, "error", "%v", resp)
got, err := os.ReadFile(note)
require.NoError(t, err)
assert.Contains(t, string(got), "half_life: durable", "rejected edit must leave the note byte-identical")
}
func TestBrainEdit_AllowsAValidClaimEnvelopeEdit(t *testing.T) {
dir := newBrainRepo(t)
note := filepath.Join(dir, "wiki/homelab/facts/n.md")
require.NoError(t, os.WriteFile(note,
[]byte("---\ntitle: 'n'\nhalf_life: durable\napplies: universal\nclaim_provenance: asserted\n---\n\nbody\n"), 0o644))
srv := mcp.NewServer(dir, nil, nil, nil)
resp := call(t, srv, "brain_edit", map[string]any{
"path": "wiki/homelab/facts/n.md", "old_str": "half_life: durable", "new_str": "half_life: seasonal",
})
require.NotContains(t, resp, "error", "%v", resp)
got, err := os.ReadFile(note)
require.NoError(t, err)
assert.Contains(t, string(got), "half_life: seasonal")
}
func TestBrainEdit_UnrelatedEditsSkipTheEnvelopeCheckEntirely(t *testing.T) {
// The gate only engages when old_str/new_str actually mention an
// envelope field name — an ordinary body edit on a note that happens to
// carry a valid envelope must not pay for (or be affected by) a check
// that has nothing to do with it.
dir := newBrainRepo(t)
note := filepath.Join(dir, "wiki/homelab/facts/n.md")
require.NoError(t, os.WriteFile(note,
[]byte("---\ntitle: 'n'\nhalf_life: durable\napplies: universal\nclaim_provenance: asserted\n---\n\nold body\n"), 0o644))
srv := mcp.NewServer(dir, nil, nil, nil)
resp := call(t, srv, "brain_edit", map[string]any{
"path": "wiki/homelab/facts/n.md", "old_str": "old body", "new_str": "new body",
})
require.NotContains(t, resp, "error", "%v", resp)
got, err := os.ReadFile(note)
require.NoError(t, err)
assert.Contains(t, string(got), "new body")
}
func TestBrainEditRoot_GovernanceFilesAreNeverEnvelopeChecked(t *testing.T) {
// CLAUDE.md has no claim-envelope concept at all — the check must be
// scoped to notes (ScopeNotes), never applied on the governance path.
srv, _, _, _ := govServer(t)
resp := authCall(t, srv, "Bearer "+capStaticTok, "brain_edit_root", map[string]any{
"path": "CLAUDE.md", "old_str": "# rules", "new_str": "half_life: durable",
})
require.NotContains(t, resp, "error", "%v", resp)
}
func TestBrainEdit_RefusesGovernanceFilesFromTheModelFacingTool(t *testing.T) {
dir := newBrainRepo(t)
srv := mcp.NewServer(dir, nil, nil, nil)
+6 -19
View File
@@ -62,20 +62,13 @@ func Run(ctx context.Context, cfg Config, brainDir, content, source string, dryR
}}, nil
}
// The source's own page path is deterministic (sourceSlug, computed above)
// even before extraction runs, unlike a concept/entity page's path, which
// only exists once the model has produced a title. So page-aware
// extraction (#106) is scoped to the source page: it's the one page every
// chunk's prompt can be given in advance.
existingPage := readSourcePage(brainDir, sourceSlug)
chunks := Chunk(content, cfg.ChunkSize)
var allRaw []RawPage
var allWarnings []string
for _, chunk := range chunks {
userPrompt := BuildPrompt(schema, source, chunk, inventory, existingPage)
userPrompt := BuildPrompt(schema, source, chunk, inventory)
output, err := cfg.Complete(ctx, systemPrompt, userPrompt)
if err != nil {
return Result{}, fmt.Errorf("LLM call: %w", err)
@@ -175,16 +168,6 @@ func hashBody(content string) string {
return hex.EncodeToString(sum[:])
}
// readSourcePage returns the full on-disk content of the source page at
// wiki/sources/<sourceSlug>.md, or "" when it doesn't exist yet.
func readSourcePage(brainDir, sourceSlug string) string {
raw, err := os.ReadFile(filepath.Join(brainDir, "wiki", "sources", sourceSlug+".md"))
if err != nil {
return ""
}
return string(raw)
}
// storedSourceHash reads source_hash from the source page a previous ingest
// wrote, or "" when there is no such page or no such field.
//
@@ -192,7 +175,11 @@ func readSourcePage(brainDir, sourceSlug string) string {
// skip costs one extraction, while a wrong skip loses an update silently — and
// silence is the failure mode this repo keeps paying for.
func storedSourceHash(brainDir, sourceSlug string) string {
for _, line := range strings.Split(readSourcePage(brainDir, sourceSlug), "\n") {
raw, err := os.ReadFile(filepath.Join(brainDir, "wiki", "sources", sourceSlug+".md"))
if err != nil {
return ""
}
for _, line := range strings.Split(string(raw), "\n") {
if key, value, found := strings.Cut(line, ":"); found && strings.TrimSpace(key) == "source_hash" {
return strings.TrimSpace(value)
}
@@ -277,104 +277,6 @@ func TestRun_ReExtractsWhenTheSourceBodyChanged(t *testing.T) {
assert.Equal(t, 2, calls, "changed content must be re-extracted")
}
// --- #106: page-aware extraction — the model sees the page it is revising --
func TestRun_ExistingSourcePageIsIncludedInTheExtractionPrompt(t *testing.T) {
// #103 made the merge asymmetric (on-disk wins); #106 is the other half —
// the extraction itself gets to see what's already there instead of
// producing a page blind and letting the merge reconcile it afterwards.
// This only proves the existing page reaches the prompt; the byte-identical
// guarantee for an echoed-back revision is a separate test below.
dir := t.TempDir()
for _, sub := range []string{"wiki/concepts", "wiki/entities", "wiki/sources"} {
require.NoError(t, os.MkdirAll(filepath.Join(dir, sub), 0o755))
}
seeded := "---\ntitle: 'Shape Up'\n---\n\n## Summary\n\nA book about shaping product work.\n\n## Key Claims\n\n- Appetite beats estimation.\n"
page := filepath.Join(dir, "wiki", "sources", "shape-up.md")
require.NoError(t, os.WriteFile(page, []byte(seeded), 0o644))
var gotPrompt string
cfg := Config{Complete: func(_ context.Context, _, user string) (string, error) {
gotPrompt = user
return mustJSON([]RawPage{{
Title: "Shape Up", Type: "source", Subtype: "book",
Content: "## Summary\n\nA book about shaping product work.\n",
}}), nil
}}
// Deliberately does not mention "Appetite beats estimation." — that phrase
// can only reach the prompt via the existing on-disk page, not the source
// content, so its presence proves the page was threaded through.
content := "A short editorial update to the book's listing. No new claims here."
_, err := Run(context.Background(), cfg, dir, content, "shape-up", false)
require.NoError(t, err)
assert.Contains(t, gotPrompt, "Appetite beats estimation.",
"the existing page's content must be visible to the extraction prompt")
assert.Contains(t, gotPrompt, "revis", "the prompt must ask for a revision, not a fresh page")
}
func TestRun_NewSourceHasNoExistingPageInThePrompt(t *testing.T) {
// The other side of the same behavior: a source with no page on disk yet
// must not get an "existing page" section injected into its prompt at all.
dir := t.TempDir()
for _, sub := range []string{"wiki/concepts", "wiki/entities", "wiki/sources"} {
require.NoError(t, os.MkdirAll(filepath.Join(dir, sub), 0o755))
}
var gotPrompt string
cfg := Config{Complete: func(_ context.Context, _, user string) (string, error) {
gotPrompt = user
return mustJSON([]RawPage{{
Title: "New Thing", Type: "source", Subtype: "article",
Content: "## Summary\n\nBrand new.\n",
}}), nil
}}
_, err := Run(context.Background(), cfg, dir, "Brand new content.", "new-thing", false)
require.NoError(t, err)
assert.NotContains(t, gotPrompt, "Current page",
"a source with no page on disk yet must not get a revision section in its prompt")
}
func TestRun_RevisionEchoingExistingPageStaysByteIdentical(t *testing.T) {
// The issue's explicit risk: a model given the current page will sometimes
// echo it back verbatim. That must not duplicate content or otherwise
// perturb the page — the deterministic merge is still the backstop.
dir := t.TempDir()
for _, sub := range []string{"wiki/concepts", "wiki/entities", "wiki/sources"} {
require.NoError(t, os.MkdirAll(filepath.Join(dir, sub), 0o755))
}
seeded := "---\ntitle: 'Shape Up'\n---\n\n## Summary\n\nA book about shaping product work.\n\n## Key Claims\n\n- Appetite beats estimation.\n"
page := filepath.Join(dir, "wiki", "sources", "shape-up.md")
require.NoError(t, os.WriteFile(page, []byte(seeded), 0o644))
cfg := Config{Complete: func(_ context.Context, _, _ string) (string, error) {
return mustJSON([]RawPage{{
Title: "Shape Up", Type: "source", Subtype: "book",
Content: "## Summary\n\nA book about shaping product work.\n\n## Key Claims\n\n- Appetite beats estimation.\n",
}}), nil
}}
content := "A short editorial update to the book's listing. No new claims here."
result, err := Run(context.Background(), cfg, dir, content, "shape-up", false)
require.NoError(t, err)
require.False(t, result.Skipped)
got, err := os.ReadFile(page)
require.NoError(t, err)
want := "---\ntitle: 'Shape Up'\nlast_updated: " + time.Now().UTC().Format("2006-01-02") +
"\nsource_hash: " + hashBody(content) + "\n---\n\n" +
"## Summary\n\nA book about shaping product work.\n\n" +
"## Key Claims\n\n- Appetite beats estimation.\n"
assert.Equal(t, want, string(got),
"a revision pass that echoes the existing page back must not duplicate or alter its content")
}
func TestRun_FrontmatterOnlyChangeIsNotDrift(t *testing.T) {
// The hash covers the body, so re-fetching a page whose metadata moved
// (a re-crawl stamping a new date) is not treated as the source changing.
+2 -24
View File
@@ -22,18 +22,8 @@ Each element must have exactly these fields:
Wikilinks in content: [[Display Name]] — just the display name, no slug, no pipe separator.
Only link to pages listed in the inventory or pages you are creating in this response.`
// BuildPrompt constructs the user prompt for a single chunk. existingPage is
// the full current content (frontmatter + body) of the source's own wiki page
// when one already exists on disk, or "" for a source being ingested for the
// first time. When non-empty, the model is asked to revise that page rather
// than write a fresh one — see hyperguild#106. The deterministic merge in
// wiki.Merge remains the backstop regardless of what the model returns: an
// on-disk section the model doesn't touch survives untouched, and a section
// it does touch only takes effect where Merge's strategy allows the fresh
// side to change anything (bullet union, append) — never for an ordinary
// section, so the model proposing a revision is never how a page gets
// overwritten.
func BuildPrompt(schema, source, content string, inventory map[wiki.PageType][]wiki.Entry, existingPage string) string {
// BuildPrompt constructs the user prompt for a single chunk.
func BuildPrompt(schema, source, content string, inventory map[wiki.PageType][]wiki.Entry) string {
var sb strings.Builder
fmt.Fprintf(&sb, "Today's date is %s.\n\n", time.Now().UTC().Format("2006-01-02"))
@@ -59,18 +49,6 @@ func BuildPrompt(schema, source, content string, inventory map[wiki.PageType][]w
sb.WriteString("\n")
}
if existingPage != "" {
sb.WriteString("## Current page for this source — revise it, don't restart\n\n")
sb.WriteString("This source has already been ingested and has the wiki page shown below.\n")
sb.WriteString("You are revising that page, not writing a fresh one:\n")
sb.WriteString(" - Add sections or claims the source below supports that this page doesn't have yet.\n")
sb.WriteString(" - Strengthen a claim where the source gives more detail, evidence, or nuance than what's already there.\n")
sb.WriteString(" - Leave unchanged whatever the source doesn't affect — reuse the existing wording verbatim rather than paraphrasing it, so an unchanged claim is recognized as unchanged.\n")
sb.WriteString(" - A merge step keeps this page's on-disk content for any section you don't return, so it's fine to omit a section you aren't revising.\n\n")
sb.WriteString(existingPage)
sb.WriteString("\n\n")
}
sb.WriteString("## Non-negotiable rules\n\n")
sb.WriteString("1. Output ONLY a valid JSON array — no prose, no fences.\n")
sb.WriteString("2. Fields: title, type, subtype (if applicable), domain (if applicable), content.\n")
+2 -8
View File
@@ -59,16 +59,10 @@ func processDir(ctx context.Context, cfg Config, date string) []error {
return nil
}
// Skip processed/, failed/, and rejected/ subdirectories entirely.
// rejected/ (hyperguild#81, brain_reject) holds notes a human already
// looked at and declined — walking into it would run the extraction
// pipeline over a note and publish it to the wiki, the exact opposite
// of the human's decision. The whole reason RejectNote moves a note
// there instead of leaving it in raw/ was to keep it out of every
// path that treats raw/ as "awaiting processing" — this is that path.
// Skip processed/ and failed/ subdirectories entirely.
if d.IsDir() {
name := d.Name()
if name == "processed" || name == "failed" || name == "rejected" {
if name == "processed" || name == "failed" {
return filepath.SkipDir
}
return nil
+3 -10
View File
@@ -176,20 +176,15 @@ func TestDeriveSource(t *testing.T) {
func TestProcessDir_SkipsSubdirs(t *testing.T) {
brainDir := setupBrainDir(t)
// Create processed/, failed/, and rejected/ subdirs with files inside.
for _, sub := range []string{"processed/2026-04-22", "failed", "rejected"} {
// Create processed/ and failed/ subdirs with files inside.
for _, sub := range []string{"processed/2026-04-22", "failed"} {
require.NoError(t, os.MkdirAll(filepath.Join(brainDir, "raw", sub), 0o755))
}
processedFile := filepath.Join(brainDir, "raw", "processed", "2026-04-22", "old-file.md")
failedFile := filepath.Join(brainDir, "raw", "failed", "broken-file.md")
// hyperguild#81/#133: a human already declined this note via brain_reject.
// If the watcher walks into rejected/, it re-ingests and publishes it to
// the wiki — the exact opposite of the human's decision.
rejectedFile := filepath.Join(brainDir, "raw", "rejected", "declined-file.md")
require.NoError(t, os.WriteFile(processedFile, []byte("old"), 0o644))
require.NoError(t, os.WriteFile(failedFile, []byte("broken"), 0o644))
require.NoError(t, os.WriteFile(rejectedFile, []byte("---\nrejected_at: 2026-09-23T00:00:00Z\n---\ndeclined"), 0o644))
// Also place a valid file in raw/ root that should be processed.
validFile := filepath.Join(brainDir, "raw", "valid.md")
@@ -228,13 +223,11 @@ func TestProcessDir_SkipsSubdirs(t *testing.T) {
// Complete should have been called exactly once (for valid.md, not for files in subdirs).
assert.Len(t, processedSources, 1, "only the file in raw/ root should be processed")
// Files in processed/, failed/, and rejected/ must remain untouched.
// Files in processed/ and failed/ must remain untouched.
_, err := os.Stat(processedFile)
assert.NoError(t, err, "processed subdir file should be untouched")
_, err = os.Stat(failedFile)
assert.NoError(t, err, "failed subdir file should be untouched")
_, err = os.Stat(rejectedFile)
assert.NoError(t, err, "rejected subdir file should be untouched, never re-ingested")
}
// TestProcessDir_SkipsTunnelCandidateFiles guards against hyperguild#88:
+26 -192
View File
@@ -3,7 +3,6 @@ package wiki
import (
"fmt"
"sort"
"strings"
)
@@ -64,54 +63,27 @@ func MergeReport(a, b Page) (Page, []string) {
fmB, _, secsB := parseSections(b.Content)
var conflicts []string
// Sections in secsA sharing a normalized heading (pre-existing corpus
// drift — "## Notes" and "## NOTES" both already on disk, the exact
// pattern this normalization exists to catch going forward, found in
// review of PR #130/#132) are matched to b's occurrences of that same
// heading POSITIONALLY: b's 1st occurrence of the key pairs with a's
// 1st, b's 2nd with a's 2nd, and so on. A single "last write wins" (or
// even "first write wins") map from key to one index would instead
// route every one of b's occurrences to the SAME on-disk section —
// which either freezes every duplicate but one (never receiving
// updates again) or, worse, compares mismatched pairs and reports a
// disagreement between two sections that were never supposed to be
// compared, false-positiving on the plain self-merge case a revision
// pass produces when the model echoes a page back unchanged (found in
// review of PR #132).
byKey := make(map[string][]int, len(secsA))
idx := make(map[string]int, len(secsA))
for i, s := range secsA {
key := normalizeHeading(s.heading)
byKey[key] = append(byKey[key], i)
idx[s.heading] = i
}
cursor := make(map[string]int, len(byKey))
for _, sB := range secsB {
key := normalizeHeading(sB.heading)
indices := byKey[key]
pos := cursor[key]
cursor[key] = pos + 1
if pos >= len(indices) {
// b has more occurrences of this heading than a does (including
// the case where a has none at all) — the extra is new content,
// appended as its own section and registered so a THIRD
// occurrence of the same heading in b pairs with this one
// rather than appending yet another duplicate.
byKey[key] = append(byKey[key], len(secsA))
i, exists := idx[sB.heading]
if !exists {
idx[sB.heading] = len(secsA)
secsA = append(secsA, sB)
continue
}
i := indices[pos]
sA := secsA[i]
switch {
case bulletSectionsNorm[key]:
case bulletSections[sB.heading]:
secsA[i].content = mergeBullets(sA.content, sB.content)
case appendSectionsNorm[key]:
case appendSections[sB.heading]:
secsA[i].content = appendNew(sA.content, sB.content)
default:
// a wins — but say that b disagreed, rather than dropping it mute.
if canonicalBlock(sA.content) != canonicalBlock(sB.content) {
if strings.TrimSpace(sA.content) != strings.TrimSpace(sB.content) {
conflicts = append(conflicts, sB.heading)
}
}
@@ -120,34 +92,6 @@ func MergeReport(a, b Page) (Page, []string) {
return Page{Path: a.Path, Content: rebuildContent(refreshOwned(fmA, fmB), preambleA, secsA)}, conflicts
}
// normalizeHeading returns the key Merge uses to decide "is this the same
// section" — trimmed and case-folded, so "Key Claims" and "Key claims" match
// (hyperguild#106: heading casing drift must not fork a section). It is used
// only for that comparison; the on-disk section's original heading text
// (secsA[i].heading, untouched here) is what actually gets written out, so a
// human's heading casing is never silently rewritten by a merge.
func normalizeHeading(h string) string {
return strings.ToLower(strings.TrimSpace(h))
}
// bulletSectionsNorm and appendSectionsNorm are bulletSections/appendSections
// keyed by normalizeHeading instead of exact text, so a section's merge
// strategy (union bullets, append) is chosen by the same normalized identity
// Merge uses to match it — otherwise a heading that matched an on-disk
// section (case-insensitively) could still fail the exact-string strategy
// lookup and silently fall through to "keep a's version," dropping b's
// content instead of unioning or appending it.
var bulletSectionsNorm = normalizeSet(bulletSections)
var appendSectionsNorm = normalizeSet(appendSections)
func normalizeSet(names map[string]bool) map[string]bool {
out := make(map[string]bool, len(names))
for k := range names {
out[normalizeHeading(k)] = true
}
return out
}
// generatorOwned names the frontmatter fields the ingest pipeline may refresh
// on a page it is revising. Everything else on disk wins.
//
@@ -165,131 +109,36 @@ var generatorOwned = map[string]bool{
"source_hash": true,
}
// fmLine is one line of a frontmatter block: a parsed key/value pair, or a
// raw line (blank, comment, or anything else that isn't a simple "key:
// value") kept verbatim. Same shape as api.frontmatter's fmLine — this
// package doesn't import that one (it's unexported there, and a's/b's
// frontmatter here always arrives as a string, not a parsed struct), so the
// small, already-proven set()-appends-if-absent behavior is reproduced
// locally rather than string-index surgery reinvented per call site.
type fmLine struct {
key, value, raw string
}
// parseFrontmatterBlock parses a "---\n...\n---\n" fenced block (the shape
// parseSections produces) into an ordered line list. A block with no
// opening/closing fence — including the empty string, a page with no
// frontmatter at all — returns nil, ok=false: there is nothing to update in
// place, only something to potentially create.
func parseFrontmatterBlock(block string) (lines []fmLine, ok bool) {
if !strings.HasPrefix(block, "---\n") {
return nil, false
}
rest := block[len("---\n"):]
end := strings.Index(rest, "\n---\n")
if end < 0 {
return nil, false
}
for _, line := range strings.Split(rest[:end], "\n") {
// An indented line is a continuation (a YAML block-list item, a
// wrapped value) never a top-level key, regardless of whether it
// happens to contain a colon — " - 'Chapter 3: The Reckoning'"
// is not a key named "- 'Chapter 3". Checked before Cut so a
// colon inside one never reaches the key/value path at all.
if line != "" && (line[0] == ' ' || line[0] == '\t') {
lines = append(lines, fmLine{raw: line})
continue
}
key, val, found := strings.Cut(line, ":")
key = strings.TrimSpace(key)
if !found || key == "" || strings.HasPrefix(strings.TrimSpace(line), "#") {
lines = append(lines, fmLine{raw: line})
continue
}
lines = append(lines, fmLine{key: key, value: strings.TrimSpace(val)})
}
return lines, true
}
// setLine updates key's value in place if lines already has it, or appends
// a new entry if it doesn't — the one behavior the original refreshOwned
// got wrong (PR #126 review, round 2: it only ever updated in place).
func setLine(lines []fmLine, key, value string) []fmLine {
for i := range lines {
if lines[i].key == key {
lines[i].value = value
return lines
}
}
return append(lines, fmLine{key: key, value: value})
}
func renderFrontmatterBlock(lines []fmLine) string {
if len(lines) == 0 {
return ""
}
var sb strings.Builder
sb.WriteString("---\n")
for _, l := range lines {
switch {
case l.key == "":
sb.WriteString(l.raw)
case l.value == "":
// A key with nothing after the colon (the YAML block-list shape:
// "aliases:" followed by indented "- item" lines on their own
// raw lines) must stay bare — "key: " with a trailing space
// is a different, if invisible, byte sequence, and this file's
// whole purpose is byte-stability across an unrelated merge.
sb.WriteString(l.key)
sb.WriteByte(':')
default:
sb.WriteString(l.key)
sb.WriteString(": ")
sb.WriteString(l.value)
}
sb.WriteByte('\n')
}
sb.WriteString("---\n")
return sb.String()
}
// refreshOwned returns a's frontmatter with the generator-owned fields taken
// from b where b supplies them. Fields absent from b keep a's value, so a
// generator that stops emitting a field cannot blank it.
//
// A field b supplies that a doesn't have yet — every page ingested before
// this mechanism existed has no source_hash line at all — is appended, not
// dropped (round 1 of review: dropping it silently meant source_hash never
// populated for the pre-existing corpus). If a has no frontmatter fence at
// all, one is created to hold the new fields rather than splicing raw
// "key: value" text into the body (round 2: that corrupted the page and the
// fields would duplicate on every subsequent merge, since unfenced text
// isn't recognized as frontmatter by parseSections on the next pass).
func refreshOwned(a, b string) string {
bLines, _ := parseFrontmatterBlock(b)
bVals := make(map[string]string)
for _, l := range bLines {
if l.key != "" && generatorOwned[l.key] {
bVals[l.key] = l.value
for _, line := range strings.Split(b, "\n") {
key, value, found := strings.Cut(line, ":")
if !found || !generatorOwned[strings.TrimSpace(key)] {
continue
}
bVals[strings.TrimSpace(key)] = strings.TrimSpace(value)
}
if len(bVals) == 0 {
return a
}
aLines, _ := parseFrontmatterBlock(a) // ok==false (no fence) -> aLines nil, same as "start fresh"
// Sorted for a deterministic, byte-stable result when more than one
// field is appended in the same call — map iteration order isn't.
keys := make([]string, 0, len(bVals))
for k := range bVals {
keys = append(keys, k)
out := make([]string, 0, len(strings.Split(a, "\n")))
for _, line := range strings.Split(a, "\n") {
key, _, found := strings.Cut(line, ":")
k := strings.TrimSpace(key)
if found && generatorOwned[k] {
if v, ok := bVals[k]; ok {
out = append(out, k+": "+v)
delete(bVals, k)
continue
}
}
out = append(out, line)
}
sort.Strings(keys)
for _, k := range keys {
aLines = setLine(aLines, k, bVals[k])
}
return renderFrontmatterBlock(aLines)
return strings.Join(out, "\n")
}
// parseSections splits markdown into its frontmatter, its preamble (content
@@ -384,21 +233,6 @@ func canonicalLine(line string) string {
return strings.Join(strings.Fields(line), " ")
}
// canonicalBlock applies canonicalLine per line of a multi-line section body
// — the same whitespace-insensitivity appendNew/mergeBullets already give a
// single line, extended to a whole section for MergeReport's disagreement
// check (found in review, PR #129: comparing raw strings.TrimSpace only
// tolerated leading/trailing whitespace, not a re-extraction's mid-line
// spacing, which every other comparison in this file already tolerates).
func canonicalBlock(block string) string {
lines := strings.Split(block, "\n")
out := make([]string, len(lines))
for i, l := range lines {
out[i] = canonicalLine(l)
}
return strings.Join(out, "\n")
}
// appendNew concatenates the lines of b that a does not already carry.
//
// Append sections used to concatenate wholesale, which is correct exactly once.
-239
View File
@@ -215,216 +215,6 @@ Rewritten by the model.
assert.NotContains(t, got, "Renamed by the model")
}
func TestMerge_GeneratorOwnedFieldsAreAppendedWhenAPageNeverHadThemBefore(t *testing.T) {
// Found in review of PR #126: refreshOwned only replaced a generator-owned
// line that already existed in a's frontmatter — it never appended one a
// didn't have. Every page ingested before this feature shipped has no
// source_hash line at all, so on its first re-ingest after deploy, the
// fresh hash was silently dropped and the skip-on-unchanged feature this
// PR exists to build would never engage for the entire pre-existing
// corpus, permanently, with nothing telling anyone.
existing := Page{Path: "wiki/sources/x.md", Content: `---
title: 'X'
---
## Summary
Original.
`}
fresh := Page{Path: "wiki/sources/x.md", Content: `---
title: 'Renamed by the model'
last_updated: 2026-08-22
source_hash: bbbb
---
## Summary
Rewritten by the model.
`}
got := Merge(existing, fresh).Content
// Exact frontmatter block, not Contains: the second review round found
// that a substring check doesn't prove the fields landed inside a valid
// fence, in the right order, or that the fence itself wasn't corrupted —
// two independent mutations (closeIdx targeting the wrong fence, reversed
// sort) both survived a Contains-only version of this test.
want := "---\ntitle: 'X'\nlast_updated: 2026-08-22\nsource_hash: bbbb\n---\n\n## Summary\n\nOriginal.\n"
assert.Equal(t, want, got)
}
func TestMerge_GeneratorOwnedFieldsCreateAFrontmatterBlockWhenThePageHadNoneAtAll(t *testing.T) {
// Second review round on PR #126: when a has no frontmatter fence at all,
// the append fallback spliced raw, unfenced "key: value" lines straight
// into the body -- worse than the original bug, because the next
// parseSections call wouldn't recognize them as frontmatter (they don't
// start with `---`), so they'd be absorbed as ordinary preamble text and
// re-duplicate on every subsequent merge instead of updating in place.
existing := Page{Path: "wiki/sources/x.md", Content: "## Summary\n\nOriginal.\n"}
fresh := Page{Path: "wiki/sources/x.md", Content: `---
last_updated: 2026-08-22
source_hash: bbbb
---
## Summary
Rewritten by the model.
`}
got := Merge(existing, fresh).Content
want := "---\nlast_updated: 2026-08-22\nsource_hash: bbbb\n---\n\n## Summary\n\nOriginal.\n"
assert.Equal(t, want, got)
}
func TestMerge_GeneratorOwnedFieldsMixedReplaceAndAppend(t *testing.T) {
// a already has last_updated (replace in place) but not source_hash
// (append) -- the two code paths in the same call, together.
existing := Page{Path: "wiki/sources/x.md", Content: `---
title: 'X'
last_updated: 2026-01-01
---
## Summary
Original.
`}
fresh := Page{Path: "wiki/sources/x.md", Content: `---
last_updated: 2026-08-22
source_hash: bbbb
---
## Summary
Rewritten by the model.
`}
got := Merge(existing, fresh).Content
want := "---\ntitle: 'X'\nlast_updated: 2026-08-22\nsource_hash: bbbb\n---\n\n## Summary\n\nOriginal.\n"
assert.Equal(t, want, got)
}
// --- hyperguild#106: heading casing drift must not fork a section ----------
// Page-aware extraction asks the model to revise the page it's given, but
// nothing guarantees the model reproduces a heading's exact on-disk casing
// ("Key Claims" vs "Key claims"). Without normalizing the match key, that
// drift silently creates a near-duplicate section instead of updating the
// original — the failure mode #106 exists to close.
func TestMerge_HeadingCaseDriftMatchesSameSection(t *testing.T) {
a := Page{Path: "p.md", Content: "---\ntitle: X\n---\n\n## Key Claims\n\n- Appetite beats estimation.\n"}
b := Page{Path: "p.md", Content: "---\ntitle: X\n---\n\n## Key claims\n\n- New pattern holds under load.\n"}
got := Merge(a, b).Content
assert.Equal(t, 1, strings.Count(got, "## Key"),
"casing drift in the heading must not create a second section")
assert.Contains(t, got, "Appetite beats estimation.")
assert.Contains(t, got, "New pattern holds under load.",
"the differently-cased section's content must still be unioned in")
assert.Contains(t, got, "## Key Claims",
"the on-disk heading's original casing must be preserved in the output")
assert.NotContains(t, got, "## Key claims",
"the fresh extraction's heading casing must not overwrite the on-disk display text")
}
func TestMerge_HeadingWhitespaceDriftMatchesSameSection(t *testing.T) {
a := Page{Path: "p.md", Content: "---\ntitle: X\n---\n\n## Open Questions \n\n- Does appetite scale?\n"}
b := Page{Path: "p.md", Content: "---\ntitle: X\n---\n\n## Open Questions\n\n- What about remote teams?\n"}
got := Merge(a, b).Content
assert.Equal(t, 1, strings.Count(got, "## Open Questions"),
"surrounding whitespace drift in the heading must not create a second section")
assert.Contains(t, got, "Does appetite scale?")
assert.Contains(t, got, "What about remote teams?")
}
func TestMerge_PreExistingCaseDuplicateHeadingsRouteToTheFirstOccurrence(t *testing.T) {
// Found in review of PR #130: normalizeHeading's idx map is built by
// iterating secsA with idx[normalizeHeading(s.heading)] = i -- last
// write wins. Before heading normalization existed, two on-disk
// sections differing only by case (real, pre-existing corpus drift --
// the exact pattern #106 itself cites) never collided, since idx keyed
// on the exact string. After normalization they collide, and every
// fresh update silently, deterministically routes to whichever
// duplicate happens to appear LAST in the file -- the first one is
// frozen forever, never receiving updates again, with nothing to say
// so. A Contains-only check doesn't catch this: nothing is literally
// deleted, a bullet just lands under the wrong of two still-present
// headings. Assert it lands under the FIRST occurrence instead —
// deterministic and matches "earliest is canonical," same reasoning
// as every other on-disk-wins default in this file.
a := Page{Path: "p.md", Content: "---\ntitle: X\n---\n\n## Key Claims\n\n- claim one\n\n## KEY CLAIMS\n\n- claim two\n"}
b := Page{Path: "p.md", Content: "---\ntitle: X\n---\n\n## Key Claims\n\n- claim one\n- fresh claim\n"}
got := Merge(a, b).Content
assert.Contains(t, got, "## Key Claims\n\n- claim one\n- fresh claim\n",
"the fresh bullet must land in the first-occurrence section, not silently route to the last duplicate")
assert.Contains(t, got, "## KEY CLAIMS\n\n- claim two\n",
"the second duplicate is untouched by this update, not merged into or overwritten")
}
func TestMergeReport_SelfMergeOfPreExistingDuplicateHeadingsReportsNoConflict(t *testing.T) {
// Found in review of PR #132: first-occurrence-wins routes ALL of b's
// occurrences of a normalized heading to a's FIRST occurrence, not to
// their own positional counterpart. So merging a page against itself
// (or an echoed-back copy, exactly what #106's revision prompt can
// produce) pairs b's second "## NOTES" against a's first "## Notes" —
// different content, same normalized key — and MergeReport wrongly
// reports a disagreement where none exists. Fixed by pairing
// positionally: b's Nth occurrence of a normalized heading matches a's
// Nth occurrence, not always the first.
page := Page{Path: "p.md", Content: "---\ntitle: X\n---\n\n## Notes\n\nFirst note.\n\n## NOTES\n\nSecond note.\n"}
_, conflicts := MergeReport(page, page)
assert.Empty(t, conflicts, "merging a page with pre-existing duplicate headings against itself must report no conflicts")
}
func TestMergeReport_DuplicateHeadingsPairPositionallyNotAllToFirst(t *testing.T) {
// Companion case: b has genuinely different content in its second
// occurrence of the normalized heading — that must compare against a's
// second occurrence (and report if they disagree), not against a's
// first (which would either false-positive if a's first differs, or
// false-negative-mask a real disagreement in the second pair).
a := Page{Path: "p.md", Content: "---\ntitle: X\n---\n\n## Notes\n\nFirst note.\n\n## NOTES\n\nSecond note.\n"}
b := Page{Path: "p.md", Content: "---\ntitle: X\n---\n\n## Notes\n\nFirst note.\n\n## NOTES\n\nSecond note, revised.\n"}
_, conflicts := MergeReport(a, b)
assert.Equal(t, []string{"NOTES"}, conflicts,
"only the second occurrence, which actually disagrees, is reported")
}
func TestRefreshOwned_CommentLinesSurviveUnmangled(t *testing.T) {
// Third review round on PR #126: parseFrontmatterBlock dropped the
// sibling api package's comment guard (strings.HasPrefix(trimmed, "#")).
// Without it, a comment line containing a colon gets cut at the colon
// and re-rendered with collapsed whitespace instead of surviving
// verbatim.
a := "---\n#see also: https://x/y\ntitle: 'X'\n---\n"
b := "---\nsource_hash: bbbb\n---\n"
got := refreshOwned(a, b)
assert.Equal(t, "---\n#see also: https://x/y\ntitle: 'X'\nsource_hash: bbbb\n---\n", got)
}
func TestRefreshOwned_IndentedListItemsWithColonsAreNotMisparsedAsKeys(t *testing.T) {
// Same round: an indented YAML block-list item that happens to contain a
// colon (e.g. a title with a subtitle) is a continuation line, never a
// top-level key, regardless of what strings.Cut finds in it. Misparsing
// it as a key/value pair and re-rendering strips its indentation,
// de-indenting it out of the list it belongs to -- and refreshOwned
// re-renders this block on essentially every non-skipped ingest, so this
// is the normal path, not an edge case.
a := "---\naliases:\n - 'Chapter 3: The Reckoning'\ntitle: 'X'\n---\n"
b := "---\nsource_hash: bbbb\n---\n"
got := refreshOwned(a, b)
assert.Equal(t, "---\naliases:\n - 'Chapter 3: The Reckoning'\ntitle: 'X'\nsource_hash: bbbb\n---\n", got)
}
func TestMerge_ReportsSectionsWhereTheFreshVersionWasDiscarded(t *testing.T) {
// The asymmetry that makes ingest safe (on-disk wins) also throws away a
// real signal: the source now says something different about a section we
@@ -477,32 +267,3 @@ Appetite is fixed, scope is variable.
_, conflicts := MergeReport(page, page)
assert.Empty(t, conflicts, "identical content is not a disagreement")
}
func TestMerge_ReportsNothingForInternalWhitespaceVariantsOnly(t *testing.T) {
// Found in review of PR #129: the conflict comparison used raw
// strings.TrimSpace, which only tolerates LEADING/TRAILING whitespace —
// unlike appendNew/mergeBullets, which already canonicalize internal
// whitespace runs too (#103: a re-extraction's spacing isn't guaranteed
// byte-stable). A mid-line double-space from re-extraction would
// false-positive as a "disagreement" here even though every other
// whitespace-sensitive comparison in this file already tolerates it.
existing := Page{Path: "wiki/sources/x.md", Content: `---
title: 'X'
---
## Summary
Appetite is fixed, scope is variable.
`}
fresh := Page{Path: "wiki/sources/x.md", Content: `---
title: 'X'
---
## Summary
Appetite is fixed, scope is variable.
`}
_, conflicts := MergeReport(existing, fresh)
assert.Empty(t, conflicts, "internal whitespace differences alone are not a disagreement")
}
+182
View File
@@ -0,0 +1,182 @@
// internal/skills/brain/handlers.go
package brain
import (
"bytes"
"context"
"encoding/json"
"fmt"
"io"
"net/http"
)
// Handle dispatches brain tool calls.
func (s *Skill) Handle(ctx context.Context, tool string, args json.RawMessage) (json.RawMessage, error) {
switch tool {
case "brain_query":
return s.query(ctx, args)
case "brain_write":
return s.write(ctx, args)
case "brain_ingest_raw":
return s.ingestRaw(ctx, args)
case "brain_ingest":
return s.ingest(ctx, args)
case "brain_search":
return s.search(ctx, args)
default:
return nil, fmt.Errorf("unknown brain tool: %s", tool)
}
}
type queryArgs struct {
Query string `json:"query"`
Limit int `json:"limit,omitempty"`
}
func (s *Skill) query(ctx context.Context, args json.RawMessage) (json.RawMessage, error) {
var a queryArgs
if err := json.Unmarshal(args, &a); err != nil {
return nil, fmt.Errorf("parse args: %w", err)
}
if a.Query == "" {
return nil, fmt.Errorf("query is required")
}
if a.Limit == 0 {
a.Limit = 5
}
return s.post(ctx, "/query", a)
}
type writeArgs struct {
Content string `json:"content"`
Type string `json:"type,omitempty"`
Domain string `json:"domain,omitempty"`
Filename string `json:"filename,omitempty"`
}
func (s *Skill) write(ctx context.Context, args json.RawMessage) (json.RawMessage, error) {
var a writeArgs
if err := json.Unmarshal(args, &a); err != nil {
return nil, fmt.Errorf("parse args: %w", err)
}
if a.Content == "" {
return nil, fmt.Errorf("content is required")
}
return s.post(ctx, "/write", a)
}
type ingestArgs struct {
Content string `json:"content,omitempty"`
Source string `json:"source,omitempty"`
Path string `json:"path,omitempty"`
DryRun bool `json:"dry_run,omitempty"`
}
func (s *Skill) ingest(ctx context.Context, args json.RawMessage) (json.RawMessage, error) {
var a ingestArgs
if err := json.Unmarshal(args, &a); err != nil {
return nil, fmt.Errorf("parse args: %w", err)
}
if s.cfg.IngestSvcURL == "" {
return nil, fmt.Errorf("brain_ingest: INGEST_SVC_URL not configured")
}
if a.Path != "" && a.Content != "" {
return nil, fmt.Errorf("path and content+source are mutually exclusive: provide one or the other")
}
if a.Path != "" {
return s.postTo(ctx, s.cfg.IngestSvcURL+"/ingest-path", map[string]any{
"path": a.Path,
"source": a.Source,
"dry_run": a.DryRun,
})
}
if a.Content != "" && a.Source != "" {
return s.postTo(ctx, s.cfg.IngestSvcURL+"/ingest", map[string]any{
"content": a.Content,
"source": a.Source,
"dry_run": a.DryRun,
})
}
return nil, fmt.Errorf("either content+source or path is required")
}
type ingestRawArgs struct {
Source string `json:"source"`
Pages []any `json:"pages"`
DryRun bool `json:"dry_run,omitempty"`
}
func (s *Skill) ingestRaw(ctx context.Context, args json.RawMessage) (json.RawMessage, error) {
var a ingestRawArgs
if err := json.Unmarshal(args, &a); err != nil {
return nil, fmt.Errorf("parse args: %w", err)
}
if s.cfg.IngestSvcURL == "" {
return nil, fmt.Errorf("brain_ingest_raw: INGEST_SVC_URL not configured")
}
if a.Source == "" {
return nil, fmt.Errorf("source is required")
}
if len(a.Pages) == 0 {
return nil, fmt.Errorf("pages is required and must be non-empty")
}
return s.postTo(ctx, s.cfg.IngestSvcURL+"/ingest-raw", map[string]any{
"source": a.Source,
"pages": a.Pages,
"dry_run": a.DryRun,
})
}
type searchArgs struct {
Query string `json:"query"`
Collection string `json:"collection,omitempty"`
Limit int `json:"limit,omitempty"`
}
func (s *Skill) search(ctx context.Context, args json.RawMessage) (json.RawMessage, error) {
var a searchArgs
if err := json.Unmarshal(args, &a); err != nil {
return nil, fmt.Errorf("parse args: %w", err)
}
if a.Query == "" {
return nil, fmt.Errorf("query is required")
}
if a.Limit == 0 {
a.Limit = 5
}
if s.cfg.KBRetrievalURL == "" {
return nil, fmt.Errorf("brain_search: KB_RETRIEVAL_URL not configured")
}
return s.postTo(ctx, s.cfg.KBRetrievalURL+"/api/v1/search", a)
}
func (s *Skill) post(ctx context.Context, path string, body any) (json.RawMessage, error) {
return s.postTo(ctx, s.cfg.IngestBaseURL+path, body)
}
func (s *Skill) postTo(ctx context.Context, url string, body any) (json.RawMessage, error) {
b, err := json.Marshal(body)
if err != nil {
return nil, fmt.Errorf("marshal request: %w", err)
}
req, err := http.NewRequestWithContext(ctx, http.MethodPost, url, bytes.NewReader(b))
if err != nil {
return nil, fmt.Errorf("build request: %w", err)
}
req.Header.Set("Content-Type", "application/json")
resp, err := http.DefaultClient.Do(req)
if err != nil {
return nil, fmt.Errorf("call ingestion server: %w", err)
}
defer func() { _ = resp.Body.Close() }()
out, err := io.ReadAll(resp.Body)
if err != nil {
return nil, fmt.Errorf("read response: %w", err)
}
if resp.StatusCode != http.StatusOK {
return nil, fmt.Errorf("ingestion server returned %d: %s", resp.StatusCode, out)
}
return json.RawMessage(out), nil
}
+122
View File
@@ -0,0 +1,122 @@
// internal/skills/brain/handlers_test.go
package brain_test
import (
"context"
"encoding/json"
"net/http"
"net/http/httptest"
"testing"
"git.d-ma.be/mathias/hyperguild/internal/skills/brain"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func TestHandle_BrainQuery_CallsIngestServer(t *testing.T) {
called := false
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
assert.Equal(t, "/query", r.URL.Path)
called = true
_ = json.NewEncoder(w).Encode(map[string]any{
"results": []map[string]any{
{"path": "wiki/concepts/tdd.md", "title": "TDD", "excerpt": "Test-driven development.", "score": 3},
},
})
}))
defer srv.Close()
s := brain.New(brain.Config{IngestBaseURL: srv.URL})
args, _ := json.Marshal(map[string]string{"query": "test driven development"})
out, err := s.Handle(context.Background(), "brain_query", args)
require.NoError(t, err)
assert.True(t, called)
var result map[string]any
require.NoError(t, json.Unmarshal(out, &result))
results := result["results"].([]any)
assert.Len(t, results, 1)
}
func TestHandle_BrainWrite_CallsIngestServer(t *testing.T) {
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
assert.Equal(t, "/write", r.URL.Path)
var body map[string]string
require.NoError(t, json.NewDecoder(r.Body).Decode(&body))
assert.Equal(t, "concept", body["type"])
assert.Equal(t, "# Test\n\nSome learning.", body["content"])
_ = json.NewEncoder(w).Encode(map[string]string{"path": "raw/test.md"})
}))
defer srv.Close()
s := brain.New(brain.Config{IngestBaseURL: srv.URL})
args, _ := json.Marshal(map[string]string{"content": "# Test\n\nSome learning.", "type": "concept"})
out, err := s.Handle(context.Background(), "brain_write", args)
require.NoError(t, err)
var result map[string]string
require.NoError(t, json.Unmarshal(out, &result))
assert.Equal(t, "raw/test.md", result["path"])
}
func TestHandle_UnknownTool_ReturnsError(t *testing.T) {
s := brain.New(brain.Config{IngestBaseURL: "http://localhost:3300"})
_, err := s.Handle(context.Background(), "brain_unknown", nil)
assert.Error(t, err)
}
func TestIngest_RoutesToIngestPath(t *testing.T) {
var capturedPath string
var capturedBody map[string]any
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
capturedPath = r.URL.Path
require.NoError(t, json.NewDecoder(r.Body).Decode(&capturedBody))
_ = json.NewEncoder(w).Encode(map[string]any{"pages": []string{"wiki/foo.md"}})
}))
defer srv.Close()
s := brain.New(brain.Config{IngestSvcURL: srv.URL})
args, _ := json.Marshal(map[string]any{"path": "/tmp/some-file.md"})
out, err := s.Handle(context.Background(), "brain_ingest", args)
require.NoError(t, err)
assert.Equal(t, "/ingest-path", capturedPath)
assert.Equal(t, "/tmp/some-file.md", capturedBody["path"])
var result map[string]any
require.NoError(t, json.Unmarshal(out, &result))
pages := result["pages"].([]any)
assert.Len(t, pages, 1)
}
func TestIngest_RoutesToIngest(t *testing.T) {
var capturedPath string
var capturedBody map[string]any
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
capturedPath = r.URL.Path
require.NoError(t, json.NewDecoder(r.Body).Decode(&capturedBody))
_ = json.NewEncoder(w).Encode(map[string]any{"pages": []string{"wiki/bar.md"}})
}))
defer srv.Close()
s := brain.New(brain.Config{IngestSvcURL: srv.URL})
args, _ := json.Marshal(map[string]any{"content": "some content", "source": "my-source.md"})
out, err := s.Handle(context.Background(), "brain_ingest", args)
require.NoError(t, err)
assert.Equal(t, "/ingest", capturedPath)
assert.Equal(t, "some content", capturedBody["content"])
assert.Equal(t, "my-source.md", capturedBody["source"])
var result map[string]any
require.NoError(t, json.Unmarshal(out, &result))
pages := result["pages"].([]any)
assert.Len(t, pages, 1)
}
func TestIngest_MissingRequiredFields(t *testing.T) {
s := brain.New(brain.Config{IngestSvcURL: "http://localhost:3300"})
args, _ := json.Marshal(map[string]any{})
_, err := s.Handle(context.Background(), "brain_ingest", args)
require.Error(t, err)
assert.Contains(t, err.Error(), "either content+source or path is required")
}
+111
View File
@@ -0,0 +1,111 @@
// internal/skills/brain/skill.go
package brain
import (
"encoding/json"
"git.d-ma.be/mathias/hyperguild/internal/registry"
)
// Config holds brain skill configuration.
type Config struct {
IngestBaseURL string // base URL of the ingestion HTTP server (brain_query, brain_write)
IngestSvcURL string // base URL of the ingestion-svc HTTP server (brain_ingest)
KBRetrievalURL string // base URL of the kb-retrieval server (brain_search)
}
// Skill implements registry.Skill for brain_query and brain_write.
type Skill struct {
cfg Config
}
// New constructs a brain Skill.
func New(cfg Config) *Skill { return &Skill{cfg: cfg} }
// Name returns the skill name used for routing.
func (s *Skill) Name() string { return "brain" }
// Tools returns the MCP tool definitions for brain_query and brain_write.
func (s *Skill) Tools() []registry.ToolDef {
schema := func(required []string, props map[string]any) json.RawMessage {
b, _ := json.Marshal(map[string]any{"type": "object", "required": required, "properties": props})
return b
}
str := map[string]any{"type": "string"}
num := map[string]any{"type": "integer"}
tools := []registry.ToolDef{
{
Name: "brain_query",
Description: "BM25 full-text search across brain/knowledge/ and brain/wiki/ markdown files. Fast, no embeddings needed. Call before any significant task.",
InputSchema: schema([]string{"query"}, map[string]any{
"query": str,
"limit": num,
}),
},
{
Name: "brain_write",
Description: "Write a raw knowledge note to brain/knowledge/ for later ingestion.",
InputSchema: schema([]string{"content"}, map[string]any{
"content": str,
"type": str,
"domain": str,
"filename": str,
}),
},
}
if s.cfg.IngestSvcURL != "" {
tools = append(tools, registry.ToolDef{
Name: "brain_ingest_raw",
Description: "Ingest pre-structured pages into the brain wiki, bypassing the LLM extraction step. " +
"Use when you (the calling agent) have already extracted entities, concepts, and content from a source. " +
"Provide source (human-readable name) and pages (array of {title, type, subtype, domain, content} objects). " +
"The pipeline computes slugs, paths, frontmatter, wikilink canonicalization, and source back-references. " +
"Returns the list of wiki pages written.",
InputSchema: schema([]string{"source", "pages"}, map[string]any{
"source": map[string]any{"type": "string", "description": "human-readable name for the source, e.g. 'shape-up-book'"},
"pages": map[string]any{
"type": "array",
"items": map[string]any{
"type": "object",
"required": []string{"title", "type", "content"},
"properties": map[string]any{
"title": map[string]any{"type": "string", "description": "page title, e.g. 'Hash Encoding'"},
"type": map[string]any{"type": "string", "enum": []string{"source", "concept", "entity"}, "description": "page type"},
"subtype": map[string]any{"type": "string", "description": "entity: person|company|tool|model|framework|technology; source: article|pdf|book|video|note|project"},
"domain": map[string]any{"type": "string", "description": "knowledge domain, e.g. 'Machine Learning'"},
"content": map[string]any{"type": "string", "description": "markdown body — no frontmatter, use [[Display Name]] for wikilinks"},
},
},
},
"dry_run": map[string]any{"type": "boolean"},
}),
})
tools = append(tools, registry.ToolDef{
Name: "brain_ingest",
Description: "Ingest content into the brain wiki (brain/wiki/). Calls an LLM to produce structured wiki pages. " +
"Use for substantial documents, articles, or knowledge worth structuring. " +
"Provide EITHER (a) path — absolute path to a file or directory, " +
"OR (b) content + source — raw text and a human-readable name. " +
"Providing both is an error. Returns the list of wiki pages written.",
InputSchema: schema([]string{}, map[string]any{
"content": map[string]any{"type": "string", "description": "raw text to ingest; required when path is not set"},
"source": map[string]any{"type": "string", "description": "human-readable name for the content, e.g. 'shape-up-book'; required when path is not set"},
"path": map[string]any{"type": "string", "description": "absolute path to a file or directory to ingest; mutually exclusive with content+source"},
"dry_run": map[string]any{"type": "boolean"},
}),
})
}
if s.cfg.KBRetrievalURL != "" {
tools = append(tools, registry.ToolDef{
Name: "brain_search",
Description: "Semantic vector search across the brain wiki using embeddings. Use when brain_query returns no results or you need conceptually-related results rather than keyword matches.",
InputSchema: schema([]string{"query"}, map[string]any{
"query": str,
"collection": str,
"limit": num,
}),
})
}
return tools
}