feat(provisioner): env-driven RegistryPrefix() for workspace template images (#6)

Allows MOLECULE_IMAGE_REGISTRY env override on the tenant workspace-server. Used to flip from ghcr.io/molecule-ai → private ECR mirror after the GitHub org suspension on 2026-05-06. Default unchanged for OSS users.

Closes #6.

workspace-server/internal/handlers/admin_workspace_images.go

@@ -56,10 +56,17 @@ type RefreshResult struct {
 	Recreated []string `json:"recreated"`
 }
 
-// TemplateImageRef returns the canonical GHCR ref for a runtime's template
-// image. Single source of truth shared with imagewatch.
+// TemplateImageRef returns the canonical image ref for a runtime's template,
+// using the configured registry (provisioner.RegistryPrefix()) and the
+// moving `:latest` tag. Single source of truth shared with imagewatch.
+//
+// Defaults to ghcr.io/molecule-ai/workspace-template-<runtime>:latest
+// (upstream OSS). When MOLECULE_IMAGE_REGISTRY is set in the environment
+// (typically the AWS ECR mirror in production), this returns the prefixed
+// equivalent so admin operations and image-watch checks hit the same
+// registry the provisioner pulls from.
 func TemplateImageRef(runtime string) string {
-	return fmt.Sprintf("ghcr.io/molecule-ai/workspace-template-%s:latest", runtime)
+	return fmt.Sprintf("%s/workspace-template-%s:latest", provisioner.RegistryPrefix(), runtime)
 }
 
 // ghcrAuthHeader returns the base64-encoded JSON auth payload Docker's

workspace-server/internal/provisioner/provisioner.go

@@ -35,36 +35,37 @@ import (
 // drift-risk #6.
 var ErrNoBackend = errors.New("provisioner: no backend configured (zero-valued receiver)")
 
-// RuntimeImages maps runtime names to their Docker image refs on GHCR.
+// RuntimeImages maps runtime names to their Docker image refs.
 // Each standalone template repo publishes its image via the reusable
 // publish-template-image workflow in molecule-ci on every main merge.
 // The provisioner pulls these on demand (see ensureImageLocal) — no
 // pre-build step on the tenant host.
 //
+// The registry prefix is determined by RegistryPrefix() in registry.go;
+// defaults to ghcr.io/molecule-ai (upstream OSS) and is overridden via the
+// MOLECULE_IMAGE_REGISTRY env var in production tenants that mirror to
+// AWS ECR or another registry. The map is computed at package init and
+// captures whatever prefix was active then.
+//
 // Legacy local-build path (`docker build -t workspace-template:<runtime>`
 // via scripts/build-images.sh) is still supported for development:
 // when a bare `workspace-template:<runtime>` image is present locally,
 // Docker's image resolver matches it before any pull is attempted. Set
 // the env var WORKSPACE_IMAGE_LOCAL_OVERRIDE=1 (enforced by callers) to
 // short-circuit pulls entirely if needed.
-var RuntimeImages = map[string]string{
-	"langgraph":   "ghcr.io/molecule-ai/workspace-template-langgraph:latest",
-	"claude-code": "ghcr.io/molecule-ai/workspace-template-claude-code:latest",
-	"openclaw":    "ghcr.io/molecule-ai/workspace-template-openclaw:latest",
-	"deepagents":  "ghcr.io/molecule-ai/workspace-template-deepagents:latest",
-	"crewai":      "ghcr.io/molecule-ai/workspace-template-crewai:latest",
-	"autogen":     "ghcr.io/molecule-ai/workspace-template-autogen:latest",
-	"hermes":      "ghcr.io/molecule-ai/workspace-template-hermes:latest",     // Hermes (Nous Research) — real hermes-agent behind A2A bridge
-	"gemini-cli":  "ghcr.io/molecule-ai/workspace-template-gemini-cli:latest", // Google Gemini CLI
-}
+var RuntimeImages = computeRuntimeImages()
+
+// DefaultImage is the fallback workspace Docker image (langgraph is the
+// most common runtime). Computed via RegistryPrefix() so the prefix
+// override applies to the fallback path too.
+//
+// NOTE: Every runtime MUST have an entry in knownRuntimes (registry.go).
+// If a runtime is missing, it falls back to DefaultImage which may have
+// wrong deps. Add new runtimes to knownRuntimes AND create the standalone
+// template repo.
+var DefaultImage = RuntimeImage(defaultRuntime)
 
 const (
-	// DefaultImage is the fallback workspace Docker image (langgraph is the most common runtime).
-	DefaultImage = "ghcr.io/molecule-ai/workspace-template-langgraph:latest"
-	// NOTE: Every runtime MUST have an entry in RuntimeImages above. If a runtime is missing,
-	// it falls back to DefaultImage which may have wrong deps. Add new runtimes to both
-	// RuntimeImages AND create the standalone template repo.
-
 	// DefaultNetwork is the Docker network workspaces join.
 	DefaultNetwork = "molecule-monorepo-net"
 

workspace-server/internal/provisioner/registry.go

@@ -0,0 +1,95 @@
+package provisioner
+
+import (
+	"fmt"
+	"os"
+)
+
+// defaultRegistryPrefix is the upstream OSS face for all workspace template
+// images. Self-hosted Molecule deployments without the MOLECULE_IMAGE_REGISTRY
+// override pull from here.
+const defaultRegistryPrefix = "ghcr.io/molecule-ai"
+
+// knownRuntimes is the canonical list of workspace template runtimes shipped
+// in main. Any runtime added here MUST also have a standalone template repo
+// (Molecule-AI/molecule-ai-workspace-template-<name>) and an entry in the
+// publish-template-image workflow that builds it.
+//
+// Order matters for deterministic test snapshots; keep alphabetical.
+var knownRuntimes = []string{
+	"autogen",
+	"claude-code",
+	"codex",
+	"crewai",
+	"deepagents",
+	"gemini-cli",
+	"hermes",
+	"langgraph",
+	"openclaw",
+}
+
+// defaultRuntime is the fallback when a workspace's config doesn't specify a
+// runtime. Picked because LangGraph is the most common in our org templates
+// and has the smallest "first impression" cold-start surface.
+const defaultRuntime = "langgraph"
+
+// RegistryPrefix returns the registry prefix all workspace-template image
+// references should use. Defaults to ghcr.io/molecule-ai (the upstream OSS
+// face) and is overridden by the MOLECULE_IMAGE_REGISTRY env var in
+// production tenants where we mirror images to a private registry.
+//
+// The override is set at deploy time (Railway env, EC2 user-data) — never
+// from user-supplied input — so the value is trusted by the time it reaches
+// this code. Validation is deliberately minimal: an operator-supplied
+// prefix that points at a registry the EC2 can't authenticate to will fail
+// loudly at docker-pull time, which is the right blast radius.
+//
+// Example values:
+//
+//	(unset)                                              → ghcr.io/molecule-ai (OSS default)
+//	"123456789012.dkr.ecr.us-east-2.amazonaws.com/molecule-ai"  → AWS ECR mirror
+//	"git.moleculesai.app/molecule-ai"                    → self-hosted Gitea Container Registry (future)
+//
+// Auth is registry-specific and configured outside this function:
+//   - GHCR: GHCR_USER/GHCR_TOKEN env vars consumed by ghcrAuthHeader()
+//   - ECR: docker credential helper (amazon-ecr-credential-helper) configured
+//     in EC2 user-data; ~/.docker/config.json has credHelpers entry; the
+//     daemon resolves auth automatically on every pull.
+func RegistryPrefix() string {
+	if v := os.Getenv("MOLECULE_IMAGE_REGISTRY"); v != "" {
+		return v
+	}
+	return defaultRegistryPrefix
+}
+
+// RuntimeImage returns the canonical image reference for the given runtime,
+// using the current RegistryPrefix() and the moving `:latest` tag.
+//
+// For SHA-pinned references (production thin-AMI launches), the
+// runtime_image_pins lookup in handlers/runtime_image_pin.go strips the
+// `:latest` suffix and appends an immutable `@sha256:<digest>` from the DB.
+// That code path naturally inherits any RegistryPrefix() change because it
+// reads from RuntimeImages[runtime] and only re-formats the tag suffix.
+//
+// Returns the empty string for unknown runtimes; callers should fall through
+// to DefaultImage in that case (matching legacy behavior).
+func RuntimeImage(runtime string) string {
+	for _, r := range knownRuntimes {
+		if r == runtime {
+			return fmt.Sprintf("%s/workspace-template-%s:latest", RegistryPrefix(), runtime)
+		}
+	}
+	return ""
+}
+
+// computeRuntimeImages returns the {runtime: image-ref} map evaluated against
+// the current RegistryPrefix(). Called at package init to populate the
+// exported RuntimeImages var. Tests that flip MOLECULE_IMAGE_REGISTRY between
+// expected values use this helper to rebuild the map mid-run.
+func computeRuntimeImages() map[string]string {
+	out := make(map[string]string, len(knownRuntimes))
+	for _, r := range knownRuntimes {
+		out[r] = RuntimeImage(r)
+	}
+	return out
+}

workspace-server/internal/provisioner/registry_test.go

@@ -0,0 +1,140 @@
+package provisioner
+
+import (
+	"strings"
+	"testing"
+)
+
+// TestRegistryPrefix_DefaultsToGHCR pins the OSS-default behavior. If a future
+// refactor accidentally drops the default, OSS users self-hosting Molecule
+// would silently lose image pulls — this test should fail loudly instead.
+func TestRegistryPrefix_DefaultsToGHCR(t *testing.T) {
+	t.Setenv("MOLECULE_IMAGE_REGISTRY", "")
+	got := RegistryPrefix()
+	want := "ghcr.io/molecule-ai"
+	if got != want {
+		t.Fatalf("RegistryPrefix() = %q, want %q (default must remain GHCR for OSS users)", got, want)
+	}
+}
+
+// TestRegistryPrefix_RespectsEnv verifies the override path used in
+// production tenants where MOLECULE_IMAGE_REGISTRY points at a private
+// mirror (AWS ECR, self-hosted Harbor, etc.).
+func TestRegistryPrefix_RespectsEnv(t *testing.T) {
+	t.Setenv("MOLECULE_IMAGE_REGISTRY", "123456789012.dkr.ecr.us-east-2.amazonaws.com/molecule-ai")
+	got := RegistryPrefix()
+	want := "123456789012.dkr.ecr.us-east-2.amazonaws.com/molecule-ai"
+	if got != want {
+		t.Fatalf("RegistryPrefix() = %q, want %q (env override path is the production cutover mechanism)", got, want)
+	}
+}
+
+// TestRegistryPrefix_EmptyEnvFallsBackToDefault — guard against an operator
+// setting MOLECULE_IMAGE_REGISTRY="" by mistake (e.g. unset deploy variable
+// becomes empty string, not literally absent). We treat "" as "use default"
+// so a misconfigured env doesn't mean an empty registry prefix.
+func TestRegistryPrefix_EmptyEnvFallsBackToDefault(t *testing.T) {
+	t.Setenv("MOLECULE_IMAGE_REGISTRY", "")
+	if RegistryPrefix() != defaultRegistryPrefix {
+		t.Fatalf("empty MOLECULE_IMAGE_REGISTRY should fall back to %q, got %q", defaultRegistryPrefix, RegistryPrefix())
+	}
+}
+
+// TestRuntimeImage_AllKnownRuntimes — every runtime in the canonical list
+// must produce a properly-formatted image ref. If a new runtime is added to
+// knownRuntimes but the format changes, this catches it.
+func TestRuntimeImage_AllKnownRuntimes(t *testing.T) {
+	t.Setenv("MOLECULE_IMAGE_REGISTRY", "")
+	for _, r := range knownRuntimes {
+		got := RuntimeImage(r)
+		want := "ghcr.io/molecule-ai/workspace-template-" + r + ":latest"
+		if got != want {
+			t.Errorf("RuntimeImage(%q) = %q, want %q", r, got, want)
+		}
+	}
+	// Pin the count so adding a runtime requires explicit test acknowledgement.
+	if len(knownRuntimes) != 9 {
+		t.Errorf("knownRuntimes length = %d, want 9 (autogen, claude-code, codex, crewai, deepagents, gemini-cli, hermes, langgraph, openclaw)", len(knownRuntimes))
+	}
+}
+
+// TestRuntimeImage_UnknownRuntime — defensive: callers must fall back to
+// DefaultImage when a runtime is unknown, never silently use the wrong
+// prefix. Returning "" enforces an explicit fallback at every call site.
+func TestRuntimeImage_UnknownRuntime(t *testing.T) {
+	for _, name := range []string{"", "nonexistent", "WORKSPACE-TEMPLATE-FAKE", "../../../etc/passwd"} {
+		if got := RuntimeImage(name); got != "" {
+			t.Errorf("RuntimeImage(%q) = %q, want empty string for unknown runtime", name, got)
+		}
+	}
+}
+
+// TestRuntimeImage_RegistryOverrideAppliesToAllRuntimes — the override
+// flips ALL runtimes consistently. If a refactor accidentally hardcoded
+// the prefix in some runtimes but not others (the failure mode that
+// triggered this whole rollout), this test catches it.
+func TestRuntimeImage_RegistryOverrideAppliesToAllRuntimes(t *testing.T) {
+	const ecr = "999999999999.dkr.ecr.us-east-2.amazonaws.com/molecule-ai"
+	t.Setenv("MOLECULE_IMAGE_REGISTRY", ecr)
+
+	for _, r := range knownRuntimes {
+		got := RuntimeImage(r)
+		if !strings.HasPrefix(got, ecr+"/workspace-template-") {
+			t.Errorf("RuntimeImage(%q) = %q, must start with override prefix %q", r, got, ecr)
+		}
+		if !strings.HasSuffix(got, ":latest") {
+			t.Errorf("RuntimeImage(%q) = %q, must keep :latest tag suffix", r, got)
+		}
+	}
+}
+
+// TestComputeRuntimeImages_AllRuntimesPresent — the map must contain every
+// known runtime. Drift between knownRuntimes and computeRuntimeImages would
+// silently break the runtime → image lookup that provisioner.Start uses.
+func TestComputeRuntimeImages_AllRuntimesPresent(t *testing.T) {
+	t.Setenv("MOLECULE_IMAGE_REGISTRY", "")
+	m := computeRuntimeImages()
+	if len(m) != len(knownRuntimes) {
+		t.Fatalf("computeRuntimeImages() has %d entries, want %d (one per knownRuntime)", len(m), len(knownRuntimes))
+	}
+	for _, r := range knownRuntimes {
+		img, ok := m[r]
+		if !ok {
+			t.Errorf("computeRuntimeImages() missing runtime %q", r)
+			continue
+		}
+		if img == "" {
+			t.Errorf("computeRuntimeImages()[%q] is empty", r)
+		}
+	}
+}
+
+// TestComputeRuntimeImages_ReflectsCurrentEnv — calling computeRuntimeImages
+// after env change rebuilds the map with new prefix. Tests + ops procedures
+// that flip the env in-process rely on this.
+func TestComputeRuntimeImages_ReflectsCurrentEnv(t *testing.T) {
+	t.Setenv("MOLECULE_IMAGE_REGISTRY", "")
+	defaultMap := computeRuntimeImages()
+	if !strings.HasPrefix(defaultMap["claude-code"], "ghcr.io/molecule-ai/") {
+		t.Fatalf("default map should be GHCR-prefixed, got %q", defaultMap["claude-code"])
+	}
+
+	const mirror = "registry.example.com/molecule-ai"
+	t.Setenv("MOLECULE_IMAGE_REGISTRY", mirror)
+	mirrorMap := computeRuntimeImages()
+	if !strings.HasPrefix(mirrorMap["claude-code"], mirror+"/") {
+		t.Fatalf("mirror-prefixed map should start with %q, got %q", mirror, mirrorMap["claude-code"])
+	}
+}
+
+// TestKnownRuntimes_AlphabeticalOrder — pin the order so test snapshots
+// (and human readers diffing the file) see deterministic output. Adding a
+// new runtime out of alphabetical order will fail this test, which is the
+// nudge to keep the file readable.
+func TestKnownRuntimes_AlphabeticalOrder(t *testing.T) {
+	for i := 1; i < len(knownRuntimes); i++ {
+		if knownRuntimes[i-1] >= knownRuntimes[i] {
+			t.Errorf("knownRuntimes not alphabetical: %q comes before %q", knownRuntimes[i-1], knownRuntimes[i])
+		}
+	}
+}