Merge pull request 'feat: capture classification taxonomy + per-wing/repo tags (#50, capture 49a)' (#56) from feat/capture-classification into main

ingestion/internal/classification/classification.go

@@ -0,0 +1,189 @@
+// Package classification defines the data-sensitivity taxonomy and the
+// per-wing / per-repo tagging the capture server reads to enforce the I1
+// sovereignty gate (issue #50, capture spec §4.1).
+//
+// The single load-bearing property is fail-safe-to-strictest: a target
+// with no explicit tag and no known default classifies as Confidential,
+// never as something more permissive. A missing tag must never silently
+// downgrade — that would turn the I1 gate into theatre.
+//
+// Classification is read from an optional classification.yaml at the
+// brain root. A central, Flux-reconcilable file is deliberate: it is
+// auditable in one place (I2/I5), it does not require a live Gitea client
+// to classify a repo (so this package has no dependency on the gitea
+// tracker work), and it avoids tagging a wing's _index.md frontmatter —
+// which BuildWingIndex regenerates and would clobber.
+package classification
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+
+	"gopkg.in/yaml.v3"
+)
+
+// Level is a data-sensitivity tier. Higher is stricter, so the "stricter
+// wins" rule (spec §4.1 model C) is a plain max.
+type Level int
+
+const (
+	Public Level = iota
+	Internal
+	Confidential
+)
+
+// String returns the canonical lowercase token for a level.
+func (l Level) String() string {
+	switch l {
+	case Public:
+		return "public"
+	case Internal:
+		return "internal"
+	case Confidential:
+		return "confidential"
+	default:
+		return fmt.Sprintf("level(%d)", int(l))
+	}
+}
+
+// ParseLevel parses a level token (case-insensitive, surrounding space
+// tolerated). An unknown token is an error — callers must decide what to
+// do with bad input rather than have it silently coerced.
+func ParseLevel(s string) (Level, error) {
+	switch strings.ToLower(strings.TrimSpace(s)) {
+	case "public":
+		return Public, nil
+	case "internal":
+		return Internal, nil
+	case "confidential":
+		return Confidential, nil
+	default:
+		return Confidential, fmt.Errorf("unknown classification level %q (want public/internal/confidential)", s)
+	}
+}
+
+// Stricter returns the more restrictive of two levels.
+func Stricter(a, b Level) Level {
+	if a > b {
+		return a
+	}
+	return b
+}
+
+// TargetKind distinguishes the two kinds of capture destination.
+type TargetKind int
+
+const (
+	WingTarget TargetKind = iota // a brain wing (insights land here)
+	RepoTarget                   // a Gitea repo (tickets / summaries land here)
+)
+
+// Target names a capture destination to classify.
+type Target struct {
+	Kind TargetKind
+	Name string
+}
+
+// Config holds the explicit per-wing / per-repo classification tags read
+// from classification.yaml. Absent entries fall through to the built-in
+// defaults in defaultFor. The zero value (no file) is valid and applies
+// defaults to everything.
+type Config struct {
+	wings map[string]Level
+	repos map[string]Level
+}
+
+// rawConfig is the on-disk YAML shape: string→string maps, parsed into
+// validated levels by Load.
+type rawConfig struct {
+	Wings map[string]string `yaml:"wings"`
+	Repos map[string]string `yaml:"repos"`
+}
+
+// Load reads classification.yaml from brainDir. An absent file is not an
+// error — it yields an empty config where every target classifies by the
+// built-in defaults. A malformed file, or any unparseable level token in
+// it, is a hard error: a classification source the server cannot trust
+// must fail loud, not degrade silently.
+func Load(brainDir string) (*Config, error) {
+	cfg := &Config{wings: map[string]Level{}, repos: map[string]Level{}}
+
+	data, err := os.ReadFile(filepath.Join(brainDir, "classification.yaml"))
+	if err != nil {
+		if os.IsNotExist(err) {
+			return cfg, nil
+		}
+		return nil, fmt.Errorf("read classification.yaml: %w", err)
+	}
+
+	var raw rawConfig
+	if err := yaml.Unmarshal(data, &raw); err != nil {
+		return nil, fmt.Errorf("parse classification.yaml: %w", err)
+	}
+	for name, lvl := range raw.Wings {
+		parsed, perr := ParseLevel(lvl)
+		if perr != nil {
+			return nil, fmt.Errorf("wing %q: %w", name, perr)
+		}
+		cfg.wings[normalise(name)] = parsed
+	}
+	for name, lvl := range raw.Repos {
+		parsed, perr := ParseLevel(lvl)
+		if perr != nil {
+			return nil, fmt.Errorf("repo %q: %w", name, perr)
+		}
+		cfg.repos[normalise(name)] = parsed
+	}
+	return cfg, nil
+}
+
+// Derive returns the classification for any target — the function the
+// capture use-case calls per item.
+func (c *Config) Derive(t Target) Level {
+	if t.Kind == RepoTarget {
+		return c.Repo(t.Name)
+	}
+	return c.Wing(t.Name)
+}
+
+// Wing classifies a brain wing: an explicit tag wins, else defaults.
+func (c *Config) Wing(name string) Level {
+	if lvl, ok := c.wings[normalise(name)]; ok {
+		return lvl
+	}
+	return defaultFor(name)
+}
+
+// Repo classifies a Gitea repo: an explicit tag wins, else defaults.
+func (c *Config) Repo(name string) Level {
+	if lvl, ok := c.repos[normalise(name)]; ok {
+		return lvl
+	}
+	return defaultFor(name)
+}
+
+// defaultFor applies the built-in defaulting rules when a target has no
+// explicit tag:
+//   - client-* → Confidential (client work is confidential by default)
+//   - hyperguild / homelab → Internal (the operator's own infra)
+//   - everything else → Confidential (fail safe to strictest)
+func defaultFor(name string) Level {
+	n := normalise(name)
+	if strings.HasPrefix(n, "client-") {
+		return Confidential
+	}
+	switch n {
+	case "hyperguild", "homelab":
+		return Internal
+	default:
+		return Confidential
+	}
+}
+
+// normalise lowercases and trims a wing/repo name so matching and the
+// client-* prefix check are case-insensitive.
+func normalise(name string) string {
+	return strings.ToLower(strings.TrimSpace(name))
+}

ingestion/internal/classification/classification_test.go

@@ -0,0 +1,112 @@
+package classification
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestLevelOrderingAndString(t *testing.T) {
+	assert.True(t, Public < Internal)
+	assert.True(t, Internal < Confidential)
+	assert.Equal(t, "public", Public.String())
+	assert.Equal(t, "internal", Internal.String())
+	assert.Equal(t, "confidential", Confidential.String())
+}
+
+func TestParseLevel(t *testing.T) {
+	for s, want := range map[string]Level{
+		"public": Public, "internal": Internal, "confidential": Confidential,
+		"PUBLIC": Public, " Confidential ": Confidential,
+	} {
+		got, err := ParseLevel(s)
+		require.NoError(t, err, s)
+		assert.Equal(t, want, got, s)
+	}
+	_, err := ParseLevel("secret")
+	require.Error(t, err, "unknown level must error, not silently default")
+	_, err = ParseLevel("")
+	require.Error(t, err)
+}
+
+func TestStricterReturnsMax(t *testing.T) {
+	assert.Equal(t, Confidential, Stricter(Internal, Confidential))
+	assert.Equal(t, Confidential, Stricter(Confidential, Public))
+	assert.Equal(t, Internal, Stricter(Public, Internal))
+	assert.Equal(t, Public, Stricter(Public, Public))
+}
+
+func TestLoadAbsentFileIsDefaultsOnly(t *testing.T) {
+	cfg, err := Load(t.TempDir())
+	require.NoError(t, err, "absent classification.yaml must not be an error — defaults apply")
+	require.NotNil(t, cfg)
+	// Pure defaulting still works.
+	assert.Equal(t, Internal, cfg.Wing("hyperguild"))
+	assert.Equal(t, Confidential, cfg.Wing("anything-unknown"))
+}
+
+func TestLoadParsesExplicitTags(t *testing.T) {
+	dir := t.TempDir()
+	require.NoError(t, os.WriteFile(filepath.Join(dir, "classification.yaml"), []byte(
+		"wings:\n  research-public: public\n  hyperguild: confidential\nrepos:\n  infra: internal\n  research-public: public\n",
+	), 0o644))
+
+	cfg, err := Load(dir)
+	require.NoError(t, err)
+	// Explicit tag wins over the built-in default (hyperguild default is internal).
+	assert.Equal(t, Confidential, cfg.Wing("hyperguild"))
+	// Explicit public is honoured.
+	assert.Equal(t, Public, cfg.Wing("research-public"))
+	assert.Equal(t, Internal, cfg.Repo("infra"))
+	assert.Equal(t, Public, cfg.Repo("research-public"))
+}
+
+func TestLoadRejectsUnknownLevelInFile(t *testing.T) {
+	dir := t.TempDir()
+	require.NoError(t, os.WriteFile(filepath.Join(dir, "classification.yaml"),
+		[]byte("wings:\n  x: top-secret\n"), 0o644))
+	_, err := Load(dir)
+	require.Error(t, err, "an unparseable level in the config must fail loud, not be ignored")
+}
+
+func TestWingDefaulting(t *testing.T) {
+	cfg, err := Load(t.TempDir())
+	require.NoError(t, err)
+	cases := map[string]Level{
+		"client-seb":        Confidential, // client-* → confidential
+		"client-mastercard": Confidential,
+		"hyperguild":        Internal,
+		"homelab":           Internal,
+		"jepa-fx":           Confidential, // unknown → fail safe to strictest
+		"":                  Confidential, // empty → fail safe
+	}
+	for wing, want := range cases {
+		assert.Equal(t, want, cfg.Wing(wing), "wing %q", wing)
+	}
+}
+
+func TestRepoDefaulting(t *testing.T) {
+	cfg, err := Load(t.TempDir())
+	require.NoError(t, err)
+	assert.Equal(t, Confidential, cfg.Repo("client-seb-pipeline"))
+	assert.Equal(t, Internal, cfg.Repo("hyperguild"))
+	assert.Equal(t, Confidential, cfg.Repo("some-unknown-repo"), "untagged repo → confidential (fail safe)")
+}
+
+func TestDeriveUnifiedTarget(t *testing.T) {
+	cfg, err := Load(t.TempDir())
+	require.NoError(t, err)
+	assert.Equal(t, Internal, cfg.Derive(Target{Kind: WingTarget, Name: "homelab"}))
+	assert.Equal(t, Confidential, cfg.Derive(Target{Kind: RepoTarget, Name: "client-x"}))
+	assert.Equal(t, Confidential, cfg.Derive(Target{Kind: WingTarget, Name: "untagged"}))
+}
+
+func TestCaseInsensitiveMatching(t *testing.T) {
+	cfg, err := Load(t.TempDir())
+	require.NoError(t, err)
+	assert.Equal(t, Confidential, cfg.Wing("Client-SEB"), "client- prefix match is case-insensitive")
+	assert.Equal(t, Internal, cfg.Wing("HyperGuild"))
+}

specs/capture-bdd-spec.md

@@ -203,6 +203,12 @@ binding design decisions for the build.
    - **Prerequisite (new build work):** a classification taxonomy (e.g. `public` /
      `internal` / `confidential`) and a per-wing / per-repo classification tag the server can read.
      This must exist before the I1 gate is load-bearing. Tracked as a sub-task of #49.
+     - **Implemented (#50):** taxonomy `public < internal < confidential` (ordered so "stricter wins"
+       is `max`) in `ingestion/internal/classification/`. Tags are read from an optional
+       `classification.yaml` at the brain root (`wings:` / `repos:` maps); absent entries fall to
+       built-in defaults (`client-*` → confidential; `hyperguild`/`homelab` → internal; everything
+       else → **confidential, fail-safe**). `Config.Derive(Target)` is the function the use-case
+       calls. See brain `wiki/hyperguild/decisions/capture-classification-taxonomy`.
    - Rationale: composes with decision 2; fails safe; honours a caller flagging something *more*
      sensitive than its destination. Pure caller-trust (A) was rejected — it makes the gate theatre.