feat: replace category with a multi-facet tag vocabulary

A single category could not describe tools that ship as a CLI, an editor
plugin and a desktop app at once, and 7 of the 40 entries were filed
under a surface they only partly match — cline is "an SDK, IDE extension
or CLI assistant" in one `extension` slot, Reasonix ships CLI, desktop
and VS Code under `cli`, warp is a terminal filed as `ide`.

Tags cover five facets: surface (at least one), model access, workflow,
integration, and origin (at most one). tagVocabulary in validate.go is
the single source of truth — the validator, its error messages, and the
dashboard's filter chips all derive from it, the last via a new facets
field in site/data.json.

The dashboard now filters on tags with multi-select chips grouped by
facet: OR within a facet, AND across facets, plus a clear-filters
control, and search matches tags as well as name and description. Only
tags some row actually carries get a chip, so chips and rows cannot
disagree. Tag pills are tinted per facet, replacing the category badge.

All 40 entries are tagged from each repo's own README, topics and docs;
CONTRIBUTING documents every tag and the evidence rule for applying one.
A leftover `category:` key now fails validation with a message naming
its replacement, rather than being silently ignored.

README.md and data/history.jsonl are the regenerated updater output.

validate_test.go

@@ -8,9 +8,9 @@ import (
 
 func TestValidateAgents_ValidEntriesNoViolations(t *testing.T) {
 	agents := []Agent{
-		{Owner: "aider-ai", Repo: "aider", Category: "cli"},
-		{Owner: "cline", Repo: "cline", Category: "extension"},
-		{Owner: "a", Repo: "b.c-d_e", Category: "web"},
+		{Owner: "aider-ai", Repo: "aider", Tags: []string{"terminal", "community"}},
+		{Owner: "cline", Repo: "cline", Tags: []string{"terminal", "community"}},
+		{Owner: "a", Repo: "b.c-d_e", Tags: []string{"terminal", "community"}},
 	}
 	violations := validateAgents(agents)
 	if len(violations) != 0 {
@@ -19,7 +19,7 @@ func TestValidateAgents_ValidEntriesNoViolations(t *testing.T) {
 }
 
 func TestValidateAgents_EmptyOwner(t *testing.T) {
-	violations := validateAgents([]Agent{{Owner: "", Repo: "repo1", Category: "cli"}})
+	violations := validateAgents([]Agent{{Owner: "", Repo: "repo1", Tags: []string{"terminal", "community"}}})
 	if !anyContains(violations, "owner is empty") {
 		t.Errorf("expected 'owner is empty' violation, got %v", violations)
 	}
@@ -29,7 +29,7 @@ func TestValidateAgents_InvalidOwnerChars(t *testing.T) {
 	tests := []string{"foo_bar", "-leading", "trailing-", "double--hyphen", "foo owner"}
 	for _, owner := range tests {
 		t.Run(owner, func(t *testing.T) {
-			violations := validateAgents([]Agent{{Owner: owner, Repo: "repo1", Category: "cli"}})
+			violations := validateAgents([]Agent{{Owner: owner, Repo: "repo1", Tags: []string{"terminal", "community"}}})
 			if !anyContains(violations, "does not look like a valid GitHub username/org") {
 				t.Errorf("owner %q: expected invalid-owner violation, got %v", owner, violations)
 			}
@@ -38,7 +38,7 @@ func TestValidateAgents_InvalidOwnerChars(t *testing.T) {
 }
 
 func TestValidateAgents_EmptyRepo(t *testing.T) {
-	violations := validateAgents([]Agent{{Owner: "org", Repo: "", Category: "cli"}})
+	violations := validateAgents([]Agent{{Owner: "org", Repo: "", Tags: []string{"terminal", "community"}}})
 	if !anyContains(violations, "repo is empty") {
 		t.Errorf("expected 'repo is empty' violation, got %v", violations)
 	}
@@ -48,7 +48,7 @@ func TestValidateAgents_InvalidRepoChars(t *testing.T) {
 	tests := []string{"foo/bar", "foo bar", "foo@bar", "foo#bar"}
 	for _, repo := range tests {
 		t.Run(repo, func(t *testing.T) {
-			violations := validateAgents([]Agent{{Owner: "org", Repo: repo, Category: "cli"}})
+			violations := validateAgents([]Agent{{Owner: "org", Repo: repo, Tags: []string{"terminal", "community"}}})
 			if !anyContains(violations, "characters not allowed in a GitHub repo name") {
 				t.Errorf("repo %q: expected invalid-repo violation, got %v", repo, violations)
 			}
@@ -56,35 +56,67 @@ func TestValidateAgents_InvalidRepoChars(t *testing.T) {
 	}
 }
 
-func TestValidateAgents_MissingCategory(t *testing.T) {
-	violations := validateAgents([]Agent{{Owner: "org", Repo: "repo1", Category: ""}})
-	if !anyContains(violations, "category is required") {
-		t.Errorf("expected 'category is required' violation, got %v", violations)
+func TestValidateAgents_LegacyCategoryFieldIsRejected(t *testing.T) {
+	// An entry left on the retired schema must fail loudly, not be ignored.
+	violations := validateAgents([]Agent{{Owner: "org", Repo: "repo1", Category: "cli", Tags: []string{"terminal"}}})
+	if !anyContains(violations, "no longer a field") {
+		t.Errorf("expected a legacy-category violation, got %v", violations)
 	}
 }
 
-func TestValidateAgents_InvalidCategory(t *testing.T) {
-	violations := validateAgents([]Agent{{Owner: "org", Repo: "repo1", Category: "framework"}})
-	if !anyContains(violations, "is not one of cli, ide, extension, library, research, web") {
-		t.Errorf("expected invalid-category violation, got %v", violations)
+func TestValidateAgents_MissingSurfaceTag(t *testing.T) {
+	violations := validateAgents([]Agent{{Owner: "org", Repo: "repo1", Tags: []string{"byo-model", "community"}}})
+	if !anyContains(violations, "at least one surface tag") {
+		t.Errorf("expected a missing-surface violation, got %v", violations)
 	}
 }
 
-func TestValidateAgents_AllValidCategoriesAccepted(t *testing.T) {
-	for _, cat := range []string{"cli", "ide", "extension", "library", "research", "web"} {
-		t.Run(cat, func(t *testing.T) {
-			violations := validateAgents([]Agent{{Owner: "org", Repo: "repo1", Category: cat}})
-			if len(violations) != 0 {
-				t.Errorf("category %q: expected no violations, got %v", cat, violations)
-			}
-		})
+func TestValidateAgents_NoTagsAtAll(t *testing.T) {
+	violations := validateAgents([]Agent{{Owner: "org", Repo: "repo1"}})
+	if !anyContains(violations, "at least one surface tag") {
+		t.Errorf("expected a missing-surface violation, got %v", violations)
+	}
+}
+
+func TestValidateAgents_UnknownTag(t *testing.T) {
+	violations := validateAgents([]Agent{{Owner: "org", Repo: "repo1", Tags: []string{"terminal", "gpt-4"}}})
+	if !anyContains(violations, `tag "gpt-4" is not in the vocabulary`) {
+		t.Errorf("expected an unknown-tag violation, got %v", violations)
+	}
+}
+
+func TestValidateAgents_RepeatedTag(t *testing.T) {
+	violations := validateAgents([]Agent{{Owner: "org", Repo: "repo1", Tags: []string{"terminal", "terminal"}}})
+	if !anyContains(violations, `tag "terminal" is repeated`) {
+		t.Errorf("expected a repeated-tag violation, got %v", violations)
+	}
+}
+
+func TestValidateAgents_TwoOriginTags(t *testing.T) {
+	violations := validateAgents([]Agent{{Owner: "org", Repo: "repo1", Tags: []string{"terminal", "vendor", "community"}}})
+	if !anyContains(violations, "origin tags, expected at most one") {
+		t.Errorf("expected a multiple-origin violation, got %v", violations)
+	}
+}
+
+func TestValidateAgents_EveryVocabularyTagAccepted(t *testing.T) {
+	// Each legal tag must pass alongside a surface tag, so a typo in
+	// tagFacets can't silently make a documented tag unusable.
+	for tag := range tagFacetIDs {
+		tags := []string{"terminal", tag}
+		if tag == "terminal" {
+			tags = []string{"terminal"}
+		}
+		if violations := validateAgents([]Agent{{Owner: "org", Repo: "repo1", Tags: tags}}); len(violations) > 0 {
+			t.Errorf("tag %q: expected no violations, got %v", tag, violations)
+		}
 	}
 }
 
 func TestValidateAgents_DuplicateCaseInsensitive(t *testing.T) {
 	agents := []Agent{
-		{Owner: "Foo", Repo: "Bar", Category: "cli"},
-		{Owner: "foo", Repo: "bar", Category: "cli"},
+		{Owner: "Foo", Repo: "Bar", Tags: []string{"terminal", "community"}},
+		{Owner: "foo", Repo: "bar", Tags: []string{"terminal", "community"}},
 	}
 	violations := validateAgents(agents)
 	if !anyContains(violations, "duplicate of entry 0") {
@@ -94,8 +126,8 @@ func TestValidateAgents_DuplicateCaseInsensitive(t *testing.T) {
 
 func TestValidateAgents_NoDuplicateForDistinctRepos(t *testing.T) {
 	agents := []Agent{
-		{Owner: "foo", Repo: "bar", Category: "cli"},
-		{Owner: "foo", Repo: "baz", Category: "cli"},
+		{Owner: "foo", Repo: "bar", Tags: []string{"terminal", "community"}},
+		{Owner: "foo", Repo: "baz", Tags: []string{"terminal", "community"}},
 	}
 	violations := validateAgents(agents)
 	if len(violations) != 0 {
@@ -105,14 +137,14 @@ func TestValidateAgents_NoDuplicateForDistinctRepos(t *testing.T) {
 
 func TestValidateAgents_CollectsAllViolationsNotJustFirst(t *testing.T) {
 	agents := []Agent{
-		{Owner: "", Repo: "", Category: ""},
-		{Owner: "org", Repo: "repo1", Category: "not-a-category"},
+		{Owner: "", Repo: "", Tags: nil},
+		{Owner: "org", Repo: "repo1", Tags: []string{"terminal", "nonsense", "vendor", "community"}},
 	}
 	violations := validateAgents(agents)
-	// entry 0: owner empty, repo empty, category empty = 3 violations.
-	// entry 1: invalid category = 1 violation.
-	if len(violations) != 4 {
-		t.Errorf("expected 4 violations collected across both entries, got %d: %v", len(violations), violations)
+	// entry 0: owner empty, repo empty, no surface tag = 3 violations.
+	// entry 1: unknown tag, two origin tags = 2 violations.
+	if len(violations) != 5 {
+		t.Errorf("expected 5 violations collected across both entries, got %d: %v", len(violations), violations)
 	}
 }