hyperguild/ingestion/internal/brain/tunnel.go

package brain

import (
	"bufio"
	"errors"
	"fmt"
	"io/fs"
	"os"
	"path"
	"path/filepath"
	"strings"
	"time"

	"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
)

// seeAlsoHeader is the markdown heading used to group cross-wing links.
const seeAlsoHeader = "## See also"

// TunnelCandidate is a cross-wing match surfaced by DetectTunnels. It is
// not yet a written link — the caller decides whether confidence is high
// enough to commit it via WriteTunnel.
type TunnelCandidate struct {
	// TargetPath is the candidate note's path relative to brainDir
	// (forward-slashed), e.g. "wiki/hyperguild/decisions/routing.md".
	TargetPath string
	// MatchedTerm is the title that matched in the source content.
	MatchedTerm string
	// Exact is true when the match was a case-insensitive whole-token
	// hit on the target's frontmatter title. Fuzzy matches (substring
	// only) are flagged Exact=false and should not be auto-written.
	Exact bool
}

// DetectTunnels scans brain/wiki/ for notes whose title appears in
// content. Returns one TunnelCandidate per matching note. Exact is true
// when content contains the title as a whole-word case-insensitive
// token; false when only a substring matched (caller treats these as
// fuzzy and should not auto-write them).
//
// A note's title is read from YAML frontmatter `title:`; failing that,
// the filename slug (sans `.md`, hyphens → spaces) is used.
func DetectTunnels(brainDir, content string) ([]TunnelCandidate, error) {
	// Walked and read through the brain root, regular files only
	// (hyperguild#174, #157): this runs inside every brain_write, so a FIFO
	// must not block it and a symlinked note's title must not become a
	// candidate.
	bfs, err := brainfs.Open(brainDir)
	if err != nil {
		return nil, fmt.Errorf("open brain: %w", err)
	}
	defer func() { _ = bfs.Close() }()
	if _, err := bfs.Lstat("wiki"); errors.Is(err, fs.ErrNotExist) {
		return nil, nil
	}

	lowerContent := strings.ToLower(content)

	var out []TunnelCandidate
	var walkErr error
	err = bfs.WalkRegular("wiki", func(rel string) error {
		name := path.Base(rel)
		if !strings.HasSuffix(name, ".md") || name == "_index.md" {
			return nil
		}
		title, _ := readTitleAndCreatedIn(bfs, rel, strings.TrimSuffix(name, ".md"))
		title = strings.TrimSpace(title)
		if title == "" {
			return nil
		}

		// A one-word title has to match the prose case-exactly. Matched
		// case-insensitively, it links every entry that happens to use the
		// word: "WRONG" (wiki/telos/decisions/wrong.md) collected 185 inbound
		// See-also links and "Status" 136, making the two most-linked nodes in
		// the graph artifacts of the English language rather than references.
		// Multi-word titles keep the case-insensitive match — "risk tier
		// middleware" in prose is a real mention however it is capitalised,
		// and a three-word collision is not an accident.
		haystack, needle := lowerContent, strings.ToLower(title)
		if isSingleWord(title) {
			haystack, needle = content, title
		}
		idx := strings.Index(haystack, needle)
		if idx == -1 {
			return nil
		}
		out = append(out, TunnelCandidate{
			TargetPath:  rel,
			MatchedTerm: title,
			Exact:       isWholeWord(haystack, idx, len(needle)),
		})
		return nil
	}, func(rel string, err error) {
		// A wiki/ that is not a real directory yields no candidates, as
		// filepath.WalkDir did; other walk errors still abort.
		if rel == "wiki" && errors.Is(err, brainfs.ErrNotRegular) {
			return
		}
		if walkErr == nil {
			walkErr = fmt.Errorf("%s: %w", rel, err)
		}
	})
	if err == nil {
		err = walkErr
	}
	if err != nil {
		return nil, err
	}
	return out, nil
}

// isSingleWord reports whether title is one whitespace-free token.
func isSingleWord(title string) bool {
	return !strings.ContainsAny(title, " \t")
}

// isWholeWord reports whether the substring at [idx, idx+n) in s is
// bounded by non-alphanumeric characters (or string edges).
func isWholeWord(s string, idx, n int) bool {
	left := idx == 0 || !isWordByte(s[idx-1])
	right := idx+n == len(s) || !isWordByte(s[idx+n])
	return left && right
}

func isWordByte(b byte) bool {
	return (b >= 'a' && b <= 'z') ||
		(b >= 'A' && b <= 'Z') ||
		(b >= '0' && b <= '9')
}

// AutoTunnel runs DetectTunnels against content and, for each
// candidate, either writes a bidirectional tunnel (when the match is
// exact and in a different wing) or stages it for human review in
// brain/raw/tunnel-candidates-<YYYY-MM-DD>.md.
//
// sourcePath is the note that originated the content — used to skip
// self-matches and same-wing tunnels. Errors writing individual
// tunnels are recorded into the candidates file but never abort the
// rest of the scan; the caller's primary write has already succeeded
// and auto-linking is best-effort.
func AutoTunnel(brainDir, sourcePath, content string) error {
	srcWing, err := wingOf(sourcePath)
	if err != nil {
		return err
	}
	candidates, err := DetectTunnels(brainDir, content)
	if err != nil {
		return err
	}

	var fuzzy []TunnelCandidate
	for _, c := range candidates {
		if c.TargetPath == sourcePath {
			continue
		}
		tgtWing, err := wingOf(c.TargetPath)
		if err != nil || tgtWing == srcWing {
			continue
		}
		if !c.Exact {
			fuzzy = append(fuzzy, c)
			continue
		}
		if err := WriteTunnel(brainDir, sourcePath, c.TargetPath); err != nil {
			fuzzy = append(fuzzy, c)
		}
	}
	return logFuzzyCandidates(brainDir, sourcePath, fuzzy)
}

// logFuzzyCandidates appends one row per candidate to
// brain/raw/tunnel-candidates-<YYYY-MM-DD>.md, creating the file with a
// header on first write of the day. No-op when the candidate list is empty.
func logFuzzyCandidates(brainDir, sourcePath string, cs []TunnelCandidate) error {
	if len(cs) == 0 {
		return nil
	}
	rawDir := filepath.Join(brainDir, "raw")
	if err := os.MkdirAll(rawDir, 0o755); err != nil {
		return err
	}
	stamp := time.Now().UTC().Format("2006-01-02")
	path := filepath.Join(rawDir, "tunnel-candidates-"+stamp+".md")
	existed := fileExists(path)
	f, err := os.OpenFile(path, os.O_APPEND|os.O_CREATE|os.O_WRONLY, 0o644)
	if err != nil {
		return err
	}
	defer func() { _ = f.Close() }()
	if !existed {
		if _, err := f.WriteString("# Tunnel candidates " + stamp + "\n\nFuzzy cross-wing matches surfaced by AutoTunnel. Review and promote to a tunnel via `brain_tunnel` if relevant.\n\n"); err != nil {
			return err
		}
	}
	for _, c := range cs {
		line := fmt.Sprintf("- `%s` ↔ `%s` (term: %q)\n", sourcePath, c.TargetPath, c.MatchedTerm)
		if _, err := f.WriteString(line); err != nil {
			return err
		}
	}
	return nil
}

func fileExists(p string) bool {
	_, err := os.Stat(p)
	return err == nil
}

// WriteTunnel appends a bidirectional wikilink between sourcePath and
// targetPath under a `## See also` section in each note. Paths are
// relative to brainDir (forward-slashed), e.g. wiki/<wing>/<hall>/<slug>.md.
//
// Idempotent: re-calling with the same pair does not duplicate links or
// section headers. Rejects same-wing pairs (a tunnel is by definition
// cross-wing) and missing notes.
func WriteTunnel(brainDir, sourcePath, targetPath string) error {
	if err := checkNotePath(sourcePath); err != nil {
		return fmt.Errorf("source: %w", err)
	}
	if err := checkNotePath(targetPath); err != nil {
		return fmt.Errorf("target: %w", err)
	}
	srcWing, err := wingOf(sourcePath)
	if err != nil {
		return fmt.Errorf("source: %w", err)
	}
	tgtWing, err := wingOf(targetPath)
	if err != nil {
		return fmt.Errorf("target: %w", err)
	}
	if srcWing == tgtWing {
		return fmt.Errorf("tunnel must cross wings; got both in %q", srcWing)
	}

	// Both notes are read and rewritten through the brain root, regular
	// files only: brain_tunnel passes caller-supplied paths, and the brain is
	// a Syncthing folder that can hold symlinks.
	bfs, err := brainfs.Open(brainDir)
	if err != nil {
		return fmt.Errorf("open brain: %w", err)
	}
	defer func() { _ = bfs.Close() }()
	srcContent, err := bfs.ReadRegular(sourcePath)
	if err != nil {
		return fmt.Errorf("source note: %w", err)
	}
	tgtContent, err := bfs.ReadRegular(targetPath)
	if err != nil {
		return fmt.Errorf("target note: %w", err)
	}

	if out, changed, err := withSeeAlso(srcContent, wikilinkOf(targetPath)); err != nil {
		return fmt.Errorf("update source: %w", err)
	} else if changed {
		if err := bfs.WriteRegular(sourcePath, out); err != nil {
			return fmt.Errorf("update source: %w", err)
		}
	}
	if out, changed, err := withSeeAlso(tgtContent, wikilinkOf(sourcePath)); err != nil {
		return fmt.Errorf("update target: %w", err)
	} else if changed {
		if err := bfs.WriteRegular(targetPath, out); err != nil {
			return fmt.Errorf("update target: %w", err)
		}
	}
	return nil
}

// checkNotePath accepts only a clean, local wiki/<wing>/<hall>/.../<slug>.md
// path: no "." or ".." segments, no empty segments, no leading slash.
func checkNotePath(p string) error {
	if p == "" || path.Clean(p) != p || !filepath.IsLocal(p) || !strings.HasSuffix(p, ".md") {
		return fmt.Errorf("not a clean wiki note path: %q", p)
	}
	for _, part := range strings.Split(p, "/") {
		if part == "" || part == "." || part == ".." {
			return fmt.Errorf("not a clean wiki note path: %q", p)
		}
	}
	return nil
}

// wikilinkOf turns "wiki/<wing>/<hall>/<slug>.md" into "<wing>/<hall>/<slug>"
// for use inside `[[...]]`.
func wikilinkOf(relPath string) string {
	p := strings.TrimSuffix(relPath, ".md")
	p = strings.TrimPrefix(p, "wiki/")
	return p
}

// wingOf extracts the wing segment from a relative wiki path
// "wiki/<wing>/<hall>/<slug>.md".
func wingOf(relPath string) (string, error) {
	parts := strings.Split(relPath, "/")
	if len(parts) < 4 || parts[0] != "wiki" {
		return "", fmt.Errorf("not a wiki path: %q", relPath)
	}
	if parts[1] == "" {
		return "", fmt.Errorf("empty wing in path: %q", relPath)
	}
	return parts[1], nil
}

// withSeeAlso returns content with `- [[link]]` under its See also section,
// creating the section if absent. changed is false when the link is already
// present.
func withSeeAlso(content []byte, link string) (out []byte, changed bool, err error) {
	wikilink := "[[" + link + "]]"
	if strings.Contains(string(content), wikilink) {
		return content, false, nil
	}

	bullet := "- " + wikilink

	if !strings.Contains(string(content), seeAlsoHeader) {
		// No section yet — append a fresh one. Always emit a trailing
		// newline so subsequent appends don't merge into the previous line.
		trimmed := strings.TrimRight(string(content), "\n")
		return []byte(trimmed + "\n\n" + seeAlsoHeader + "\n\n" + bullet + "\n"), true, nil
	}

	// Section exists — splice the bullet in just before the next `## `
	// heading (or EOF). Reading the file line-by-line keeps this robust
	// against arbitrary section ordering.
	var b strings.Builder
	scanner := bufio.NewScanner(strings.NewReader(string(content)))
	scanner.Buffer(make([]byte, 0, 64*1024), 1024*1024)
	inSeeAlso, inserted := false, false
	for scanner.Scan() {
		line := scanner.Text()
		if !inserted && inSeeAlso && strings.HasPrefix(line, "## ") &&
			strings.TrimSpace(line) != seeAlsoHeader {
			b.WriteString(bullet)
			b.WriteByte('\n')
			b.WriteByte('\n')
			inserted = true
		}
		if strings.TrimSpace(line) == seeAlsoHeader {
			inSeeAlso = true
		}
		b.WriteString(line)
		b.WriteByte('\n')
	}
	if err := scanner.Err(); err != nil {
		return nil, false, err
	}
	if !inserted {
		// section was the last thing in the file — just append bullet
		return []byte(strings.TrimRight(b.String(), "\n") + "\n" + bullet + "\n"), true, nil
	}
	return []byte(b.String()), true, nil
}