the private path is exercised, and the guardrail stops crying wolf

Closes the last unexercised assumption with a throwaway token: partial clone over HTTPS with a token against a private repository, list through the tool, the short-form raw URL redirecting to a resolved branch under auth, and a conditional request returning 304 across that redirect. A private repository can adopt from another private one, by name or by URL, and check works off the lock afterwards. Fixes what would have shipped as noise. The warning fired whenever a fetch needed a credential, which in a private repository adopting from a private repository is every time and legitimate. add now resolves origin and makes one anonymous request to learn whether this repository is public, so the warning fires when the source is private and the destination is not. The limit is stated in the message rather than implied away: the signal tells public from not-public and nothing finer, so two repositories private to different people is the case that genuinely widens access and the one this cannot see. No origin means cannot tell, which warns — cannot tell must never read as not public. Notes when an adopted document did not come from .loom/published/, without refusing. What is not exported is not hidden, but a lock against it records a dependency on something that was never a contract. And records the framing that settles all of this: the tool is a mast, not a lock. It grants no access, everything it does is possible with copy and paste, and the locks mean nothing outside the tool and the discipline of the agreement — so it makes the wrong thing deliberate rather than impossible. What it adds over a paste is not restriction but provenance. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018UTxuSizozEA8yDitPuris
2026-09-08 08:47:12 -04:00
parent 73b3a97dce
commit fb96b2f90b
5 changed files with 222 additions and 9 deletions
@@ -168,7 +168,8 @@ func Add(root, raw, override string, out io.Writer) error {

 	fmt.Fprintf(out, "adopted  %s\n", rel)
 	fmt.Fprintf(out, "  from   %s\n", body.url)
-	warnIfNotPublic(cfg, body.url, out)
+	warnIfNotPublic(cfg, root, body.url, out)
+	notePublishedSurface(body.url, out)
 	if etag == "" {
 		fmt.Fprintf(out, "  etag   (none served — check cannot ask conditionally)\n")
 	} else {
@@ -185,7 +186,7 @@ func Add(root, raw, override string, out io.Writer) error {
 // moment of adoption. The tool can see half of that — whether this fetch needed
 // a credential — and cannot see the other half, which is who can read the
 // repository the copy is landing in. It reports the half it knows.
-func warnIfNotPublic(cfg *config.Config, raw string, out io.Writer) {
+func warnIfNotPublic(cfg *config.Config, root, raw string, out io.Writer) {
 	req, err := http.NewRequest(http.MethodHead, raw, nil)
 	if err != nil {
 		return
@@ -201,10 +202,27 @@ func warnIfNotPublic(cfg *config.Config, raw string, out io.Writer) {
 	if resp.StatusCode == http.StatusOK {
 		return
 	}
-	fmt.Fprintf(out, "  WARN   this needed a credential — anonymously it is %s.\n", resp.Status)
-	fmt.Fprintf(out, "         Confidentiality does not travel with the copy: this now lives in\n")
-	fmt.Fprintf(out, "         .loom/externals/ and is readable by anyone who can read THIS\n")
-	fmt.Fprintf(out, "         repository, which I cannot see. Do not adopt from a source less\n")
+
+	// The source is private. Whether that matters depends on where it is
+	// landing, and a warning on every adoption a private repository performs is
+	// noise in exactly the workflow that is legitimate.
+	public, known := selfVisibility(root)
+	if known && !public {
+		fmt.Fprintf(out, "  NOTE   private source, and this repository is not public either.\n")
+		fmt.Fprintf(out, "         Access is not widened by that alone — but this check only\n")
+		fmt.Fprintf(out, "         tells public from not-public, so it cannot see two repositories\n")
+		fmt.Fprintf(out, "         private to different people. That case does widen it.\n")
+		return
+	}
+	if !known {
+		fmt.Fprintf(out, "  WARN   this needed a credential, and I cannot tell who may read this\n")
+		fmt.Fprintf(out, "         repository — no usable origin. Check before you commit.\n")
+		return
+	}
+	fmt.Fprintf(out, "  WARN   this needed a credential — anonymously it is %s — and THIS\n", resp.Status)
+	fmt.Fprintf(out, "         repository is public.\n")
+	fmt.Fprintf(out, "         Confidentiality does not travel with the copy: adopting this\n")
+	fmt.Fprintf(out, "         publishes it to everyone. Do not adopt from a source less\n")
 	fmt.Fprintf(out, "         readable than the repository you are adopting into.\n")
 	fmt.Fprintf(out, "         Two ways out: ask them to publish it — usually the thing you\n")
 	fmt.Fprintf(out, "         needed was not the confidential part — or keep no copy and\n")
@@ -0,0 +1,97 @@
+package external
+
+import (
+	"bytes"
+	"fmt"
+	"net/http"
+	"os/exec"
+	"strings"
+)
+
+// selfVisibility reports whether the repository we are adopting into can be read
+// anonymously.
+//
+// This is the half of the confidentiality rule the tool was previously blind to.
+// Knowing only that a source is private makes the warning fire on every adoption
+// a private repository performs, which is the legitimate case — and a warning
+// that always fires is a warning nobody reads.
+//
+// The signal is coarse on purpose. It distinguishes public from not-public and
+// nothing finer, so it cannot see that two repositories are private to different
+// groups. That case widens access and this check will miss it.
+func selfVisibility(root string) (public bool, known bool) {
+	out, err := exec.Command("git", "-C", root, "remote", "get-url", "origin").Output()
+	if err != nil {
+		return false, false
+	}
+	host, ownerRepo, ok := splitRemote(strings.TrimSpace(string(out)))
+	if !ok {
+		return false, false
+	}
+	req, err := http.NewRequest(http.MethodHead, "https://"+host+"/"+ownerRepo, nil)
+	if err != nil {
+		return false, false
+	}
+	resp, err := client.Do(req)
+	if err != nil {
+		return false, false
+	}
+	defer resp.Body.Close()
+	return resp.StatusCode == http.StatusOK, true
+}
+
+// splitRemote pulls a host and owner/repo out of a git remote, whether it is
+// ssh, ssh:// or https.
+func splitRemote(remote string) (host, ownerRepo string, ok bool) {
+	s := remote
+	if i := strings.Index(s, "://"); i >= 0 {
+		s = s[i+3:]
+	}
+	if at := strings.Index(s, "@"); at >= 0 {
+		s = s[at+1:]
+	}
+	// scp-style "host:owner/repo.git" and url-style "host:port/owner/repo.git"
+	var rest string
+	if i := strings.IndexAny(s, ":/"); i >= 0 {
+		host, rest = s[:i], s[i+1:]
+	} else {
+		return "", "", false
+	}
+	if j := strings.Index(rest, "/"); j >= 0 && isPort(rest[:j]) {
+		rest = rest[j+1:]
+	}
+	rest = strings.TrimSuffix(strings.Trim(rest, "/"), ".git")
+	if host == "" || strings.Count(rest, "/") != 1 {
+		return "", "", false
+	}
+	return host, rest, true
+}
+
+func isPort(s string) bool {
+	if s == "" {
+		return false
+	}
+	for _, r := range s {
+		if r < '0' || r > '9' {
+			return false
+		}
+	}
+	return true
+}
+
+// notePublishedSurface says when an adopted document did not come from the
+// publisher's published surface.
+//
+// What is not exported is not hidden — the rest of a repository is there to read.
+// It is simply not what you depend on, and a lock against it records a dependency
+// on something that was never a contract.
+func notePublishedSurface(rawURL string, out interface{ Write([]byte) (int, error) }) {
+	if strings.Contains(rawURL, "/"+PublishedDir+"/") {
+		return
+	}
+	var b bytes.Buffer
+	fmt.Fprintf(&b, "  NOTE   not from %s — what is not exported is not hidden, but it is\n", PublishedDir)
+	fmt.Fprintf(&b, "         not what you depend on. Nothing promises this path will still\n")
+	fmt.Fprintf(&b, "         be there, or still mean this, tomorrow.\n")
+	out.Write(b.Bytes())
+}
@@ -0,0 +1,34 @@
+package external
+
+import "testing"
+
+func TestSplitRemote(t *testing.T) {
+	for _, tc := range []struct {
+		remote, host, ownerRepo string
+		ok                      bool
+	}{
+		{"ssh://git@git.hypertheory-labs.dev:2222/loom/loom-cli.git", "git.hypertheory-labs.dev", "loom/loom-cli", true},
+		{"ssh://git@git.hypertheory-labs.dev/loom/loom-cli.git", "git.hypertheory-labs.dev", "loom/loom-cli", true},
+		{"git@github.com:octocat/Hello-World.git", "github.com", "octocat/Hello-World", true},
+		{"https://gitlab.com/gitlab-org/gitlab-svgs.git", "gitlab.com", "gitlab-org/gitlab-svgs", true},
+		{"https://gitlab.com/gitlab-org/gitlab-svgs", "gitlab.com", "gitlab-org/gitlab-svgs", true},
+		// A nested group is not owner/repo, and guessing would produce a URL
+		// that answers about the wrong repository.
+		{"https://gitlab.com/group/sub/project.git", "", "", false},
+		{"/srv/git/bare.git", "", "", false},
+		{"", "", "", false},
+	} {
+		host, or, ok := splitRemote(tc.remote)
+		if ok != tc.ok || host != tc.host || or != tc.ownerRepo {
+			t.Errorf("splitRemote(%q) = (%q, %q, %v), want (%q, %q, %v)",
+				tc.remote, host, or, ok, tc.host, tc.ownerRepo, tc.ok)
+		}
+	}
+}
+
+func TestSelfVisibilityUnknownOutsideARepo(t *testing.T) {
+	// Failing open matters: "cannot tell" must not read as "not public".
+	if _, known := selfVisibility(t.TempDir()); known {
+		t.Error("selfVisibility in a non-repository reported a known answer")
+	}
+}