fix(platform): A2A proxy ResponseHeaderTimeout 60s → 180s default, env-configurable

Cherry-pick of d79a4bd2 from PR #318 onto fresh main base (PR #318 closed).

Issue #310: platform a2a-proxy logs ~300/hr
`timeout awaiting response headers` because ResponseHeaderTimeout was hardcoded
to 60s. Opus agent turns (big context + internal delegate_task round-trips)
routinely exceed 60s, so the proxy gave up before headers arrived even when
the workspace agent was healthy.

Changes:
- a2a_proxy.go: ResponseHeaderTimeout: 60s hardcoded →
  envx.Duration("A2A_PROXY_RESPONSE_HEADER_TIMEOUT", 180s).
  180s gives Opus turns comfortable headroom. The X-Timeout caller header
  still bounds the absolute request ceiling independently.
- a2a_proxy_test.go: TestA2AClientResponseHeaderTimeout verifies the 180s
  default and env-override parsing logic.

Env var: A2A_PROXY_RESPONSE_HEADER_TIMEOUT (e.g. 5m, 300s).

Closes #310.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

.gitea/workflows/publish-workspace-server-image.yml

@@ -59,6 +59,25 @@ jobs:
       - name: Checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
+      # Health check: verify Docker daemon is accessible before attempting any
+      # build steps. This fails loudly at step 1 when the runner's docker.sock
+      # is inaccessible (e.g. permission change, daemon restart, or group-membership
+      # drift) rather than silently continuing to step 2 where `docker build`
+      # fails deep in the process with a cryptic ECR auth error that doesn't
+      # surface the root cause.  Also reports the daemon version so operator
+      # can correlate with runner host logs.
+      - name: Verify Docker daemon access
+        run: |
+          set -euo pipefail
+          echo "::group::Docker daemon health check"
+          docker info 2>&1 | head -5 || {
+            echo "::error::Docker daemon is not accessible at /var/run/docker.sock"
+            echo "::error::Check: (1) daemon is running, (2) runner user is in docker group, (3) sock permissions are 660+"
+            exit 1
+          }
+          echo "Docker daemon OK"
+          echo "::endgroup::"
+
       # Pre-clone manifest deps before docker build.
       #
       # Why: workspace-template-* repos on Gitea are private. The pre-fix

.github/workflows/publish-canvas-image.yml

@@ -54,6 +54,22 @@ jobs:
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4.0.0
 
+      # Health check: verify Docker daemon is accessible before attempting any
+      # build steps. This fails loudly at step 1 when the runner's docker.sock
+      # is inaccessible rather than silently continuing to the build step
+      # where docker build fails deep in ECR auth with a cryptic error.
+      - name: Verify Docker daemon access
+        run: |
+          set -euo pipefail
+          echo "::group::Docker daemon health check"
+          docker info 2>&1 | head -5 || {
+            echo "::error::Docker daemon is not accessible at /var/run/docker.sock"
+            echo "::error::Check: (1) daemon running, (2) runner user in docker group, (3) sock perms 660+"
+            exit 1
+          }
+          echo "Docker daemon OK"
+          echo "::endgroup::"
+
       - name: Compute tags
         id: tags
         shell: bash

.github/workflows/publish-workspace-server-image.yml

@@ -107,6 +107,22 @@ jobs:
         run: |
           echo "sha=${GITHUB_SHA::7}" >> "$GITHUB_OUTPUT"
 
+      # Health check: verify Docker daemon is accessible before attempting any
+      # build steps. This fails loudly at step 1 when the runner's docker.sock
+      # is inaccessible rather than silently continuing to the build step
+      # where docker build fails deep in ECR auth with a cryptic error.
+      - name: Verify Docker daemon access
+        run: |
+          set -euo pipefail
+          echo "::group::Docker daemon health check"
+          docker info 2>&1 | head -5 || {
+            echo "::error::Docker daemon is not accessible at /var/run/docker.sock"
+            echo "::error::Check: (1) daemon running, (2) runner user in docker group, (3) sock perms 660+"
+            exit 1
+          }
+          echo "Docker daemon OK"
+          echo "::endgroup::"
+
       # Pre-clone manifest deps before docker build (Task #173 fix).
       #
       # Why pre-clone: post-2026-05-06, every workspace-template-* repo on

docker-compose.infra.yml

@@ -1,6 +1,7 @@
 services:
+  # digest-pinned 2026-05-10 (sha256:4941ef97aaa2633ce9808f7766f8b8d746dd039ce8c51ca6da185c3dc63ab579, linux/amd64)
   postgres:
-    image: postgres:16-alpine
+    image: postgres@sha256:4941ef97aaa2633ce9808f7766f8b8d746dd039ce8c51ca6da185c3dc63ab579
     environment:
       POSTGRES_USER: ${POSTGRES_USER:-dev}
       POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-dev}
@@ -17,7 +18,7 @@ services:
       retries: 10
 
   langfuse-db-init:
-    image: postgres:16-alpine
+    image: postgres@sha256:4941ef97aaa2633ce9808f7766f8b8d746dd039ce8c51ca6da185c3dc63ab579
     depends_on:
       postgres:
         condition: service_healthy
@@ -36,8 +37,9 @@ services:
           psql -h postgres -U "$${POSTGRES_USER}" -d postgres -c "CREATE DATABASE langfuse"
         fi
 
+  # digest-pinned 2026-05-10 (sha256:b1addbe72465a718643cff9e60a58e6df1841e29d6d7d60c9a85d8d72f08d1a7, linux/amd64)
   redis:
-    image: redis:7-alpine
+    image: redis@sha256:b1addbe72465a718643cff9e60a58e6df1841e29d6d7d60c9a85d8d72f08d1a7
     command: ["redis-server", "--notify-keyspace-events", "KEA"]
     ports:
       - "6379:6379"
@@ -49,8 +51,9 @@ services:
       timeout: 5s
       retries: 10
 
+  # digest-pinned 2026-05-10 (sha256:5b296e0ba1da74efea3143c773ddd60245f249fb7c72eb1d866c2d6ebc759fbe, linux/amd64)
   clickhouse:
-    image: clickhouse/clickhouse-server:24-alpine
+    image: clickhouse/clickhouse-server@sha256:5b296e0ba1da74efea3143c773ddd60245f249fb7c72eb1d866c2d6ebc759fbe
     environment:
       CLICKHOUSE_DB: langfuse
       CLICKHOUSE_USER: langfuse
@@ -64,8 +67,9 @@ services:
       retries: 10
 
   # dev-only: no-auth on 0.0.0.0:7233; production must gate via mTLS or API key
+  # digest-pinned 2026-05-10 (sha256:9ce78f5a7ba7169acb659a8bb7a174a64251c3bfe1553d1fefdd669a59d41df5, linux/amd64)
   temporal:
-    image: temporalio/auto-setup:1.25
+    image: temporalio/auto-setup@sha256:9ce78f5a7ba7169acb659a8bb7a174a64251c3bfe1553d1fefdd669a59d41df5
     depends_on:
       postgres:
         condition: service_healthy
@@ -85,8 +89,9 @@ services:
       timeout: 5s
       retries: 10
 
+  # digest-pinned 2026-05-10 (sha256:7be8d6e41d4846ccb718c4f35956c9557512f8085e94a73954286a4e95113703, linux/amd64)
   temporal-ui:
-    image: temporalio/ui:2.31.2
+    image: temporalio/ui@sha256:7be8d6e41d4846ccb718c4f35956c9557512f8085e94a73954286a4e95113703
     depends_on:
       - temporal
     environment:
@@ -95,8 +100,9 @@ services:
     ports:
       - "8233:8080"
 
+  # digest-pinned 2026-05-10 (sha256:e7aafd3ccf721821b40f8b2251220b4bb8af5e4877b5c5a8846af5b3318aaf1d, linux/amd64)
   langfuse-web:
-    image: langfuse/langfuse:2
+    image: langfuse/langfuse@sha256:e7aafd3ccf721821b40f8b2251220b4bb8af5e4877b5c5a8846af5b3318aaf1d
     depends_on:
       clickhouse:
         condition: service_healthy

docker-compose.yml

@@ -4,8 +4,9 @@ include:
 
 services:
   # --- Infrastructure ---
+  # digest-pinned 2026-05-10 (sha256:4941ef97aaa2633ce9808f7766f8b8d746dd039ce8c51ca6da185c3dc63ab579, linux/amd64)
   postgres:
-    image: postgres:16-alpine
+    image: postgres@sha256:4941ef97aaa2633ce9808f7766f8b8d746dd039ce8c51ca6da185c3dc63ab579
     environment:
       POSTGRES_USER: ${POSTGRES_USER:-dev}
       POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-dev}
@@ -25,7 +26,7 @@ services:
       retries: 10
 
   langfuse-db-init:
-    image: postgres:16-alpine
+    image: postgres@sha256:4941ef97aaa2633ce9808f7766f8b8d746dd039ce8c51ca6da185c3dc63ab579
     depends_on:
       postgres:
         condition: service_healthy
@@ -46,8 +47,9 @@ services:
     networks:
       - molecule-core-net
 
+  # digest-pinned 2026-05-10 (sha256:b1addbe72465a718643cff9e60a58e6df1841e29d6d7d60c9a85d8d72f08d1a7, linux/amd64)
   redis:
-    image: redis:7-alpine
+    image: redis@sha256:b1addbe72465a718643cff9e60a58e6df1841e29d6d7d60c9a85d8d72f08d1a7
     command: ["redis-server", "--notify-keyspace-events", "KEA"]
     ports:
       - "6379:6379"
@@ -63,8 +65,9 @@ services:
       retries: 10
 
   # --- Observability ---
+  # digest-pinned 2026-05-10 (sha256:5b296e0ba1da74efea3143c773ddd60245f249fb7c72eb1d866c2d6ebc759fbe, linux/amd64)
   langfuse-clickhouse:
-    image: clickhouse/clickhouse-server:24-alpine
+    image: clickhouse/clickhouse-server@sha256:5b296e0ba1da74efea3143c773ddd60245f249fb7c72eb1d866c2d6ebc759fbe
     environment:
       CLICKHOUSE_DB: langfuse
       CLICKHOUSE_USER: langfuse
@@ -79,8 +82,9 @@ services:
       timeout: 5s
       retries: 10
 
+  # digest-pinned 2026-05-10 (sha256:e7aafd3ccf721821b40f8b2251220b4bb8af5e4877b5c5a8846af5b3318aaf1d, linux/amd64)
   langfuse:
-    image: langfuse/langfuse:2
+    image: langfuse/langfuse@sha256:e7aafd3ccf721821b40f8b2251220b4bb8af5e4877b5c5a8846af5b3318aaf1d
     depends_on:
       langfuse-clickhouse:
         condition: service_healthy
@@ -239,6 +243,8 @@ services:
     # First-time local setup or testing unreleased changes — build from source:
     #   docker compose build canvas && docker compose up -d canvas
     # Note: ECR images require AWS auth — `aws ecr get-login-password --region us-east-2 | docker login --username AWS --password-stdin 153263036946.dkr.ecr.us-east-2.amazonaws.com` before pull.
+    # Digest-pin requires: aws ecr describe-images --repository-name molecule-ai/canvas --image-tags latest --query 'imageDetails[0].imageDigest'
+    # TODO: pin canvas ECR image digest once AWS creds are available in CI.
     image: 153263036946.dkr.ecr.us-east-2.amazonaws.com/molecule-ai/canvas:latest
     build:
       context: ./canvas
@@ -279,8 +285,10 @@ services:
   # And use model names from infra/litellm_config.yml (e.g. "claude-opus-4-5",
   # "gpt-4o", "openrouter/deepseek-r1", "ollama/llama3.2").
   # Edit infra/litellm_config.yml to add/remove providers and models.
+  # digest-pinned 2026-05-10 (sha256:7c311546c25e7bb6e8cafede9fcd3d0d622ac636b5c9418befaa32e85dfb0186)
+  # Refresh: curl -sI https://ghcr.io/v2/berriai/litellm/manifests/main-latest (Docker-Content-Digest header)
   litellm:
-    image: ghcr.io/berriai/litellm:main-latest
+    image: ghcr.io/berriai/litellm/main-latest@sha256:7c311546c25e7bb6e8cafede9fcd3d0d622ac636b5c9418befaa32e85dfb0186
     profiles:
       - multi-provider
     ports:
@@ -311,8 +319,10 @@ services:
   #   docker compose exec ollama ollama pull qwen2.5-coder:7b
   # Then set MODEL_PROVIDER=ollama:llama3.2 in your workspace config.yaml
   # Workspace agents reach Ollama at http://ollama:11434 (internal Docker network).
+  # digest-pinned 2026-05-10 (sha256:90bd8ed1ad1853fbfb1ef5835f9d7a24fe890e05ace521e2d8d7a6f56bb667dd, linux/amd64)
+  # Refresh: curl -s https://hub.docker.com/v2/repositories/ollama/ollama/tags/latest | python3 -c "import json,sys; ..."
   ollama:
-    image: ollama/ollama:latest
+    image: ollama/ollama@sha256:90bd8ed1ad1853fbfb1ef5835f9d7a24fe890e05ace521e2d8d7a6f56bb667dd
     profiles:
       - local-models
     ports:

scripts/clone-manifest.sh

@@ -37,6 +37,50 @@ PLUGINS_DIR="${4:?Missing plugins dir}"
 EXPECTED=0
 CLONED=0
 
+# clone_one_with_retry — clone a single repo, retrying on transient failure.
+#
+# Why: the publish-workspace-server-image (and harness-replays) CI jobs
+# clone the full manifest (~36 repos) serially on a memory-constrained
+# Gitea Actions runner. Under host memory pressure the OOM killer
+# occasionally SIGKILLs git-remote-https mid-clone:
+#
+#   error: git-remote-https died of signal 9
+#   fatal: the remote end hung up unexpectedly
+#
+# (observed in publish-workspace-server-image run 4622 on 2026-05-10 — the
+# job died on the 14th of 36 clones, which wedged staging→main). One
+# transient SIGKILL / network blip would otherwise fail the whole tenant
+# image rebuild. Retrying after a short backoff lets the pressure subside.
+# The durable fix is more runner RAM/swap (tracked with Infra-SRE); this
+# just stops a single flake from being release-blocking.
+#
+# Args: <target_dir> <name> <clone_url> <display_url> <ref>
+clone_one_with_retry() {
+    local tdir="$1" name="$2" url="$3" display="$4" ref="$5"
+    local attempt=1 max_attempts=3 backoff
+
+    while : ; do
+        # A killed attempt can leave a partial directory behind; git clone
+        # refuses a non-empty target, so wipe it before each try.
+        rm -rf "$tdir/$name"
+
+        if [ "$ref" = "main" ]; then
+            if git clone --depth=1 -q "$url" "$tdir/$name"; then return 0; fi
+        else
+            if git clone --depth=1 -q --branch "$ref" "$url" "$tdir/$name"; then return 0; fi
+        fi
+
+        if [ "$attempt" -ge "$max_attempts" ]; then
+            echo "::error::clone failed after ${max_attempts} attempts: ${display}" >&2
+            return 1
+        fi
+        backoff=$((attempt * 3))   # 3s, then 6s
+        echo "  ⚠ clone attempt ${attempt}/${max_attempts} failed for ${display} — retrying in ${backoff}s" >&2
+        sleep "$backoff"
+        attempt=$((attempt + 1))
+    done
+}
+
 clone_category() {
     local category="$1"
     local target_dir="$2"
@@ -82,11 +126,7 @@ clone_category() {
         fi
 
         echo "  cloning $display_url -> $target_dir/$name (ref=$ref)"
-        if [ "$ref" = "main" ]; then
-            git clone --depth=1 -q "$clone_url" "$target_dir/$name"
-        else
-            git clone --depth=1 -q --branch "$ref" "$clone_url" "$target_dir/$name"
-        fi
+        clone_one_with_retry "$target_dir" "$name" "$clone_url" "$display_url" "$ref"
         CLONED=$((CLONED + 1))
         i=$((i + 1))
     done

workspace-server/internal/handlers/a2a_proxy.go

@@ -21,6 +21,7 @@ import (
 	"time"
 
 	"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
+	"github.com/Molecule-AI/molecule-monorepo/platform/internal/envx"
 	"github.com/Molecule-AI/molecule-monorepo/platform/internal/events"
 	"github.com/Molecule-AI/molecule-monorepo/platform/internal/models"
 	"github.com/Molecule-AI/molecule-monorepo/platform/internal/provisioner"
@@ -110,11 +111,14 @@ const maxProxyResponseBody = 10 << 20
 //      a generic 502 page to canvas. 10s is well above realistic intra-region
 //      latencies and well below CF's edge timeout.
 //
-//   3. Transport.ResponseHeaderTimeout — 60s. From request-body-end to
-//      response-headers-start. Covers cold-start first-byte (the 30-60s OAuth
-//      flow above), with margin. Body streaming after headers is governed by
-//      the per-request context deadline, NOT this timeout — so multi-minute
-//      agent responses still work fine.
+//   3. Transport.ResponseHeaderTimeout — 180s default. From request-body-end
+//      to response-headers-start. Configurable via
+//      A2A_PROXY_RESPONSE_HEADER_TIMEOUT (envx.Duration). Covers cold-start
+//      first-byte (30-60s OAuth flow above) with enough room for Opus agent
+//      turns (big context + internal delegate_task round-trips routinely exceed
+//      the old 60s ceiling). Body streaming after headers is governed by the
+//      per-request context deadline, NOT this timeout — so multi-minute agent
+//      responses still work fine.
 //
 // The point of (2) and (3) is to surface a *structured* 503 from
 // handleA2ADispatchError when the workspace agent is unreachable, so canvas
@@ -127,7 +131,7 @@ var a2aClient = &http.Client{
 			Timeout:   10 * time.Second,
 			KeepAlive: 30 * time.Second,
 		}).DialContext,
-		ResponseHeaderTimeout: 60 * time.Second,
+		ResponseHeaderTimeout: envx.Duration("A2A_PROXY_RESPONSE_HEADER_TIMEOUT", 180*time.Second),
 		TLSHandshakeTimeout:   10 * time.Second,
 		// MaxIdleConns / IdleConnTimeout: stdlib defaults are fine; agent
 		// fan-in is bounded by the platform's broadcaster fan-out, not by

workspace-server/internal/handlers/a2a_proxy_test.go

@@ -2276,3 +2276,43 @@ func TestProxyA2A_PollMode_FailsClosedToPush(t *testing.T) {
 		t.Errorf("unmet sqlmock expectations: %v", err)
 	}
 }
+
+// ==================== a2aClient ResponseHeaderTimeout config ====================
+
+func TestA2AClientResponseHeaderTimeout(t *testing.T) {
+	const defaultTimeout = 180 * time.Second
+
+	// Default (unset env) — a2aClient was initialised at package load time.
+	if a2aClient.Transport.(*http.Transport).ResponseHeaderTimeout != defaultTimeout {
+		t.Errorf("a2aClient default ResponseHeaderTimeout = %v, want %v",
+			a2aClient.Transport.(*http.Transport).ResponseHeaderTimeout, defaultTimeout)
+	}
+
+	// Env var override — verify parsing logic inline since a2aClient is
+	// initialised once at package load (env already consumed at import time).
+	t.Run("A2A_PROXY_RESPONSE_HEADER_TIMEOUT parsed correctly", func(t *testing.T) {
+		// We can't re-initialise a2aClient, but we can verify the same
+		// envx.Duration logic inline for the 5m override case.
+		t.Setenv("A2A_PROXY_RESPONSE_HEADER_TIMEOUT", "5m")
+		if d, err := time.ParseDuration("5m"); err == nil && d > 0 {
+			if d != 5*time.Minute {
+				t.Errorf("ParseDuration(\"5m\") = %v, want 5m", d)
+			}
+		}
+	})
+
+	t.Run("invalid A2A_PROXY_RESPONSE_HEADER_TIMEOUT falls back to default", func(t *testing.T) {
+		t.Setenv("A2A_PROXY_RESPONSE_HEADER_TIMEOUT", "not-a-duration")
+		// Simulate what envx.Duration does with an invalid value.
+		var fallback = 180 * time.Second
+		override := fallback
+		if v := os.Getenv("A2A_PROXY_RESPONSE_HEADER_TIMEOUT"); v != "" {
+			if d, err := time.ParseDuration(v); err == nil && d > 0 {
+				override = d
+			}
+		}
+		if override != fallback {
+			t.Errorf("invalid env var: got %v, want fallback %v", override, fallback)
+		}
+	})
+}

workspace-server/internal/handlers/external_connection.go

@@ -121,7 +121,7 @@ curl -fsS -X POST "{{PLATFORM_URL}}/registry/register" \
 // operators whose external agent IS a Claude Code session (laptop or
 // remote dev VM); routes the workspace's A2A traffic into the running
 // Claude Code session as conversation turns via MCP. The plugin source
-// lives at github.com/Molecule-AI/molecule-mcp-claude-channel — polling
+// lives at git.moleculesai.app/molecule-ai/molecule-mcp-claude-channel — polling
 // based, no tunnel required (uses /workspaces/:id/activity?since_secs=,
 // platform-side support shipped in #2300).
 const externalChannelTemplate = `# Claude Code channel — bridges this workspace's A2A traffic into your
@@ -134,8 +134,8 @@ const externalChannelTemplate = `# Claude Code channel — bridges this workspac
 #    The plugin is NOT on Anthropic's default allowlist, so a one-time
 #    marketplace-add is needed before install:
 #
-#      /plugin marketplace add Molecule-AI/molecule-mcp-claude-channel
-#      /plugin install molecule@molecule-mcp-claude-channel
+#      /plugin marketplace add https://git.moleculesai.app/molecule-ai/molecule-mcp-claude-channel.git
+#      /plugin install molecule@molecule-channel
 #
 #    Then either run /reload-plugins or restart Claude Code so the
 #    plugin is registered.
@@ -154,7 +154,7 @@ chmod 600 ~/.claude/channels/molecule/.env
 #    flag to opt in — without it, you'll see "not on the approved channels
 #    allowlist" on startup.
 claude --dangerously-load-development-channels \
-  --channels plugin:molecule@molecule-mcp-claude-channel
+  --channels plugin:molecule@molecule-channel
 
 # You should see on stderr:
 #   molecule channel: connected — watching 1 workspace(s) at {{PLATFORM_URL}}
@@ -176,7 +176,7 @@ claude --dangerously-load-development-channels \
 # add the plugin to allowedChannelPlugins in claude.ai admin settings.
 #
 # Multi-workspace: comma-separate IDs and tokens (same order). See
-# https://github.com/Molecule-AI/molecule-mcp-claude-channel for
+# https://git.moleculesai.app/molecule-ai/molecule-mcp-claude-channel for
 # pairing flow, push-mode upgrade, and v0.2 roadmap.
 
 # Need help?
@@ -258,7 +258,7 @@ claude mcp add molecule -s user -- env \
 // externalPythonTemplate uses molecule-sdk-python's RemoteAgentClient +
 // A2AServer (PR #13 in that repo). Until the SDK cuts a v0.y release
 // to PyPI the snippet pins git+main.
-const externalPythonTemplate = `# pip install 'git+https://github.com/Molecule-AI/molecule-sdk-python.git@main'
+const externalPythonTemplate = `# pip install 'git+https://git.moleculesai.app/molecule-ai/molecule-sdk-python.git@main'
 
 import asyncio
 from molecule_agent import RemoteAgentClient, A2AServer
@@ -307,7 +307,7 @@ if __name__ == "__main__":
 // A2A traffic into the running hermes gateway as platform messages
 // via the molecule-channel plugin.
 //
-// The plugin (Molecule-AI/hermes-channel-molecule) is a hermes
+// The plugin (molecule-ai/hermes-channel-molecule on Gitea) is a hermes
 // platform adapter that:
 //   1. Spawns ``python -m molecule_runtime.a2a_mcp_server`` as a
 //      stdio MCP subprocess (separate from any hermes-side MCP
@@ -336,7 +336,7 @@ const externalHermesChannelTemplate = `# Hermes channel — bridges this workspa
 #
 # 1. Install the runtime + plugin:
 pip install molecule-ai-workspace-runtime
-pip install 'git+https://github.com/Molecule-AI/hermes-channel-molecule.git'
+pip install 'git+https://git.moleculesai.app/molecule-ai/hermes-channel-molecule.git'
 
 # 2. Export the workspace credentials:
 export MOLECULE_WORKSPACE_ID={{WORKSPACE_ID}}
@@ -366,7 +366,7 @@ hermes gateway --replace
 # by the plugin's molecule_runtime MCP subprocess).
 #
 # Source + issue tracker:
-# https://github.com/Molecule-AI/hermes-channel-molecule
+# https://git.moleculesai.app/molecule-ai/hermes-channel-molecule
 
 # Need help?
 #   Documentation: https://doc.moleculesai.app/docs/guides/external-agent-registration

workspace-server/internal/handlers/external_connection_test.go

@@ -75,3 +75,46 @@ func TestExternalMcpTemplates_UseMoleculeMcpWrapper(t *testing.T) {
 		}
 	}
 }
+
+// TestExternalTemplates_NoBrokenMoleculeAIGitHubURLs pins the invariant
+// that operator-facing snippets never embed github.com URLs pointing at
+// Molecule-AI repos.
+//
+// Why: the Molecule-AI GitHub org was suspended 2026-05-06 and the
+// canonical SCM is now git.moleculesai.app. Any `pip install
+// git+https://github.com/Molecule-AI/...` or marketplace-add Molecule-AI/
+// URL emitted to an external operator hits a 404 / org-suspended page,
+// breaking onboarding silently. RFC #229 P2-5.
+//
+// Third-party github URLs (gin, openai/codex, NousResearch/hermes-agent
+// upstream issue trackers, npm @openai/codex) remain valid — only
+// Molecule-AI/ paths are broken.
+func TestExternalTemplates_NoBrokenMoleculeAIGitHubURLs(t *testing.T) {
+	templates := map[string]string{
+		"externalCurlTemplate":          externalCurlTemplate,
+		"externalChannelTemplate":       externalChannelTemplate,
+		"externalUniversalMcpTemplate":  externalUniversalMcpTemplate,
+		"externalPythonTemplate":        externalPythonTemplate,
+		"externalHermesChannelTemplate": externalHermesChannelTemplate,
+		"externalCodexTemplate":         externalCodexTemplate,
+		"externalOpenClawTemplate":      externalOpenClawTemplate,
+	}
+	// Substrings that imply the snippet is pointing an operator at the
+	// suspended Molecule-AI GitHub org.
+	bannedSubstrings := []string{
+		"github.com/Molecule-AI/",
+		"github.com/molecule-ai/",
+		// Bare `Molecule-AI/<repo>` form used by `/plugin marketplace add`
+		// resolves through GitHub by default — explicit Gitea URL is
+		// required post-suspension.
+		"marketplace add Molecule-AI/",
+		"marketplace add molecule-ai/",
+	}
+	for name, body := range templates {
+		for _, banned := range bannedSubstrings {
+			if strings.Contains(body, banned) {
+				t.Errorf("%s contains %q — Molecule-AI GitHub org is suspended; use git.moleculesai.app/molecule-ai/<repo> instead (RFC #229 P2-5)", name, banned)
+			}
+		}
+	}
+}