feat: escalate brain search to web when facts cannot confirm (#17)

internal/brain/http.go

@@ -7,6 +7,8 @@ import (
 	"context"
 	"encoding/json"
 	"fmt"
+
+	"github.com/eSlider/2dph/internal/brain/rank"
 )
 
 // Ready opens the Ladybug file for the life of the serve process.
@@ -17,7 +19,7 @@ func Ready() error {
 // HTTP is the in-process API used by bin/brain/serve.go.
 type HTTP struct{}
 
-func (HTTP) Search(_ context.Context, query string, limit int) ([]byte, error) {
+func (HTTP) Search(ctx context.Context, query string, limit int) ([]byte, error) {
 	hits, err := searchHits(query, "", "", limit)
 	if err != nil {
 		return nil, err
@@ -31,10 +33,13 @@ func (HTTP) Search(_ context.Context, query string, limit int) ([]byte, error) {
 			hits[i].Snippet = string(runes)
 		}
 	}
+	webOut := rank.Deduce(hits, query, "", false, func(q string) rank.SecondSource {
+		return lookupWeb(ctx, q)
+	})
 	var buf bytes.Buffer
 	enc := json.NewEncoder(&buf)
 	enc.SetEscapeHTML(false)
-	if err := enc.Encode(toJSONOut(hits, query, "")); err != nil {
+	if err := enc.Encode(toJSONOut(hits, query, "", webOut)); err != nil {
 		return nil, err
 	}
 	return buf.Bytes(), nil

internal/brain/rank/args.go

@@ -6,7 +6,7 @@ import (
 	"strings"
 )
 
-const Usage = `usage: bin/brain/search.go "query" [--root facts|info] [--repo REPO] [-n N] [--json]
+const Usage = `usage: bin/brain/search.go "query" [--root facts|info] [--repo REPO] [-n N] [--json] [--no-web]
        bin/brain/search.go serve [port]
        bin/brain/search.go --list-model`
 
@@ -17,6 +17,7 @@ type Options struct {
 	Limit     int
 	JSONOut   bool
 	ListModel bool
+	NoWeb     bool
 }
 
 // ParseArgs reads flags. Unknown flags are an error: silently dropping them
@@ -54,6 +55,8 @@ func ParseArgs(args []string) (Options, error) {
 			return opt, fmt.Errorf("--hop is not implemented yet (needs File/FROM_FILE edges)")
 		case "--json":
 			opt.JSONOut = true
+		case "--no-web":
+			opt.NoWeb = true
 		case "--list-model":
 			opt.ListModel = true
 		default:

internal/brain/rank/escalate.go

@@ -0,0 +1,43 @@
+package rank
+
+// SecondSource is the web-search block on a deduction answer.
+// Kept apart from graph hits so "ours" and "not ours" stay visible.
+type SecondSource struct {
+	Status  string            `json:"status"`
+	Note    string            `json:"note,omitempty"`
+	Cached  bool              `json:"cached,omitempty"`
+	Results []SecondSourceHit `json:"results,omitempty"`
+}
+
+type SecondSourceHit struct {
+	Rank    int    `json:"rank"`
+	Title   string `json:"title"`
+	URL     string `json:"url"`
+	Snippet string `json:"snippet"`
+	Engine  string `json:"engine"`
+}
+
+type WebFn func(query string) SecondSource
+
+// ShouldEscalate is true when the default deduction path has no facts hit.
+// `--root facts|info` is a single-root ask: do not mix in the web.
+func ShouldEscalate(hits []Hit, rootFilter string) bool {
+	if rootFilter != "" {
+		return false
+	}
+	for _, h := range hits {
+		if h.Root == "facts" {
+			return false
+		}
+	}
+	return true
+}
+
+// Deduce returns the second-source block, or nil when web must not run.
+func Deduce(hits []Hit, query, rootFilter string, noWeb bool, web WebFn) *SecondSource {
+	if noWeb || web == nil || !ShouldEscalate(hits, rootFilter) {
+		return nil
+	}
+	out := web(query)
+	return &out
+}

internal/brain/rank/escalate_test.go

@@ -0,0 +1,78 @@
+package rank
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestShouldEscalateWhenNoFacts(t *testing.T) {
+	if !ShouldEscalate(nil, "") {
+		t.Fatal("empty local graph must escalate")
+	}
+	if !ShouldEscalate([]Hit{h("i", "info", "docs/a.md")}, "") {
+		t.Fatal("info-only must escalate (not confirmed)")
+	}
+}
+
+func TestShouldNotEscalateWhenFactsConfirm(t *testing.T) {
+	hits := []Hit{h("f", "facts", "docker ps x compose"), h("i", "info", "docs/a.md")}
+	if ShouldEscalate(hits, "") {
+		t.Fatal("facts hit is already confirmed; do not mix web")
+	}
+}
+
+func TestShouldNotEscalateWhenRootFilterSet(t *testing.T) {
+	if ShouldEscalate(nil, "facts") {
+		t.Fatal("--root facts must stay local")
+	}
+	if ShouldEscalate([]Hit{h("i", "info", "x")}, "info") {
+		t.Fatal("--root info must stay local")
+	}
+}
+
+func TestDeduceCallsWebOnlyWhenEscalating(t *testing.T) {
+	called := 0
+	web := func(q string) SecondSource {
+		called++
+		if q != "LadybugDB" {
+			t.Fatalf("query = %q", q)
+		}
+		return SecondSource{Status: "ok", Results: []SecondSourceHit{{Title: "t", URL: "http://example.com"}}}
+	}
+	got := Deduce([]Hit{h("i", "info", "x")}, "LadybugDB", "", false, web)
+	if called != 1 || got == nil || got.Status != "ok" {
+		t.Fatalf("got %+v called=%d", got, called)
+	}
+}
+
+func TestDeduceNilWhenFactsOrNoWeb(t *testing.T) {
+	web := func(string) SecondSource {
+		t.Fatal("web must not run")
+		return SecondSource{}
+	}
+	if Deduce([]Hit{h("f", "facts", "x")}, "q", "", false, web) != nil {
+		t.Fatal("facts")
+	}
+	if Deduce([]Hit{h("i", "info", "x")}, "q", "", true, web) != nil {
+		t.Fatal("--no-web")
+	}
+	if Deduce(nil, "q", "facts", false, web) != nil {
+		t.Fatal("--root facts")
+	}
+	if Deduce(nil, "q", "", false, nil) != nil {
+		t.Fatal("nil web fn")
+	}
+}
+
+func TestParseNoWeb(t *testing.T) {
+	opt, err := ParseArgs([]string{"query", "--no-web", "--json"})
+	if err != nil || !opt.NoWeb || !opt.JSONOut || opt.Query != "query" {
+		t.Fatalf("got %+v err=%v", opt, err)
+	}
+}
+
+func TestUsageNamesNoWeb(t *testing.T) {
+	if !strings.Contains(Usage, "--no-web") {
+		t.Fatalf("usage must name --no-web, got:\n%s", Usage)
+	}
+}

internal/brain/search.go

@@ -68,18 +68,25 @@ func runSearch(args []string) int {
 		}
 	}
 
+	webOut := rank.Deduce(results, query, root, opt.NoWeb, func(q string) rank.SecondSource {
+		return lookupWeb(context.Background(), q)
+	})
+
 	out := Dict{
 		{"query", query},
 		{"root_filter", root},
 		{"count", len(results)},
 		{"results", resultsToDicts(results)},
 	}
+	if webOut != nil {
+		out = append(out, KV{"web", secondToDict(*webOut)})
+	}
 
 	if jsonOut {
 		enc := json.NewEncoder(os.Stdout)
 		enc.SetIndent("", "  ")
 		enc.SetEscapeHTML(false)
-		return b2i(enc.Encode(toJSONOut(results, query, root)))
+		return b2i(enc.Encode(toJSONOut(results, query, root, webOut)))
 	}
 	fmt.Print(toYAML(out, 0))
 	return 0
@@ -168,10 +175,11 @@ func rowsToHits(res *lbug.QueryResult) ([]Hit, error) {
 
 // JSON output types
 type jsonOut struct {
-	Query      string    `json:"query"`
-	RootFilter string    `json:"root_filter"`
-	Count      int       `json:"count"`
-	Results    []jsonHit `json:"results"`
+	Query      string             `json:"query"`
+	RootFilter string             `json:"root_filter"`
+	Count      int                `json:"count"`
+	Results    []jsonHit          `json:"results"`
+	Web        *rank.SecondSource `json:"web,omitempty"`
 }
 
 type jsonHit struct {
@@ -182,7 +190,7 @@ type jsonHit struct {
 	Snippet string  `json:"snippet,omitempty"`
 }
 
-func toJSONOut(hits []Hit, query, rootFilter string) *jsonOut {
+func toJSONOut(hits []Hit, query, rootFilter string, web *rank.SecondSource) *jsonOut {
 	out := make([]jsonHit, len(hits))
 	for i, h := range hits {
 		out[i] = jsonHit{
@@ -198,6 +206,7 @@ func toJSONOut(hits []Hit, query, rootFilter string) *jsonOut {
 		RootFilter: rootFilter,
 		Count:      len(hits),
 		Results:    out,
+		Web:        web,
 	}
 }
 

internal/brain/web.go

@@ -0,0 +1,56 @@
+package brain
+
+import (
+	"context"
+
+	"github.com/eSlider/2dph/internal/brain/rank"
+	"github.com/eSlider/2dph/internal/websearch"
+)
+
+func lookupWeb(ctx context.Context, query string) rank.SecondSource {
+	o := websearch.Lookup(ctx, query, websearch.LookupOpt{Limit: 5})
+	return toSecond(o)
+}
+
+func toSecond(o websearch.Output) rank.SecondSource {
+	hits := make([]rank.SecondSourceHit, 0, len(o.Results))
+	for _, h := range o.Results {
+		hits = append(hits, rank.SecondSourceHit{
+			Rank:    h.Rank,
+			Title:   h.Title,
+			URL:     h.URL,
+			Snippet: h.Snippet,
+			Engine:  h.Engine,
+		})
+	}
+	return rank.SecondSource{
+		Status:  o.Status,
+		Note:    o.Note,
+		Cached:  o.Cached,
+		Results: hits,
+	}
+}
+
+func secondToDict(w rank.SecondSource) Dict {
+	d := Dict{
+		{"status", w.Status},
+	}
+	if w.Note != "" {
+		d = append(d, KV{"note", w.Note})
+	}
+	if w.Cached {
+		d = append(d, KV{"cached", true})
+	}
+	rows := make([]any, 0, len(w.Results))
+	for _, h := range w.Results {
+		rows = append(rows, Dict{
+			{"rank", h.Rank},
+			{"title", h.Title},
+			{"url", h.URL},
+			{"snippet", h.Snippet},
+			{"engine", h.Engine},
+		})
+	}
+	d = append(d, KV{"results", rows})
+	return d
+}