chore: sync staging-v6 to main HEAD (PRs #1045 + workspace-server image rebuild)

Rebuild bakes updated openclaw config.yaml (adds MiniMax M2.7 and Kimi K2.6 entries) into /workspace-configs-templates.

.gitea/scripts/ci-required-drift.py

@@ -203,12 +203,17 @@ def ci_jobs_all(ci_doc: dict) -> set[str]:
 
 def ci_job_names(ci_doc: dict) -> set[str]:
     """Set of job keys in ci.yml MINUS the sentinel itself MINUS jobs
-    whose `if:` gates on `github.event_name` (those are event-scoped
-    and can legitimately be `skipped` for a given trigger; if we
-    required them under the sentinel `needs:`, every PR-only job
+    whose `if:` gates on `github.event_name` or `github.ref` (those are
+    event-scoped and can legitimately be `skipped` for a given trigger;
+    if we required them under the sentinel `needs:`, every PR-only job
     would be `skipped` on push and the sentinel would interpret
     `skipped != success` as failure). RFC §4 spec.
 
+    `github.ref` is the companion gate for jobs that run only on direct
+    pushes to specific branches (e.g. `github.ref == 'refs/heads/main'`).
+    These never execute in a PR context, so flagging them as missing
+    from `all-required.needs:` is a false positive (mc#958 / mc#959).
+
     Used for F1 (jobs missing from sentinel needs). NOT used for F1b
     (typos in needs) — see `ci_jobs_all` for that."""
     jobs = ci_doc.get("jobs")
@@ -221,7 +226,9 @@ def ci_job_names(ci_doc: dict) -> set[str]:
             continue
         if isinstance(v, dict):
             gate = v.get("if")
-            if isinstance(gate, str) and "github.event_name" in gate:
+            if isinstance(gate, str) and (
+                "github.event_name" in gate or "github.ref" in gate
+            ):
                 continue
         names.add(k)
     return names

.gitea/scripts/gitea-merge-queue.py

@@ -417,7 +417,21 @@ def main() -> int:
     parser.add_argument("--dry-run", action="store_true")
     args = parser.parse_args()
     _require_runtime_env()
-    return process_once(dry_run=args.dry_run)
+    try:
+        return process_once(dry_run=args.dry_run)
+    except ApiError as exc:
+        # API errors (401/403/404/500) are transient for a queue tick —
+        # log and exit 0 so the workflow is not marked failed and the next
+        # tick can retry. Returning non-zero would permanently fail the
+        # workflow run, blocking future ticks.
+        sys.stderr.write(f"::error::queue API error: {exc}\n")
+        return 0
+    except urllib.error.URLError as exc:
+        sys.stderr.write(f"::error::queue network error: {exc}\n")
+        return 0
+    except TimeoutError as exc:
+        sys.stderr.write(f"::error::queue timeout: {exc}\n")
+        return 0
 
 
 if __name__ == "__main__":

.gitea/scripts/tests/test_gitea_merge_queue.py

@@ -85,7 +85,10 @@ def test_pr_needs_update_when_base_sha_absent_from_commits():
 
 def test_merge_decision_requires_main_green_pr_green_and_current_base():
     required = ["CI / all-required (pull_request)"]
-    main_status = {"state": "success", "statuses": []}
+    main_status = {
+        "state": "success",
+        "statuses": [{"context": "CI / all-required (push)", "status": "success"}],
+    }
     pr_status = {
         "state": "success",
         "statuses": [{"context": "CI / all-required (pull_request)", "status": "success"}],
@@ -104,7 +107,10 @@ def test_merge_decision_requires_main_green_pr_green_and_current_base():
 
 def test_merge_decision_updates_stale_pr_before_merge():
     decision = mq.evaluate_merge_readiness(
-        main_status={"state": "success", "statuses": []},
+        main_status={
+            "state": "success",
+            "statuses": [{"context": "CI / all-required (push)", "status": "success"}],
+        },
         pr_status={"state": "success", "statuses": [{"context": "CI / all-required (pull_request)", "status": "success"}]},
         required_contexts=["CI / all-required (pull_request)"],
         pr_has_current_base=False,

.gitea/workflows/ci.yml

@@ -304,6 +304,7 @@ jobs:
     name: Canvas (Next.js)
     needs: changes
     runs-on: ubuntu-latest
+    timeout-minutes: 20
     # Phase 4 (RFC #219 §1): confirmed green on main 2026-05-12.
     continue-on-error: false
     defaults:
@@ -402,12 +403,13 @@ jobs:
   canvas-deploy-reminder:
     name: Canvas Deploy Reminder
     runs-on: ubuntu-latest
-    # mc#774: pre-existing continue-on-error mask; root-fix and remove, do not renew silently.
-    continue-on-error: true
+    # mc#774 root-fix: added job-level `if:` so ci-required-drift.py's
+    # ci_job_names() detects this as github.ref-gated and skips it from F1.
+    # The step-level exit 0 handles the "not main push" case; the job-level
+    # `if:` makes the gating explicit so the drift script sees it.
+    # continue-on-error removed (was mc#774 mask): step exits 0 when not applicable.
     needs: [changes, canvas-build]
-    # Keep the job itself always runnable. Gitea 1.22.6 leaves job-level
-    # event/ref `if:` gates as pending on PRs, which blocks the combined
-    # status even though this reminder is intentionally non-required.
+    if: ${{ github.ref == 'refs/heads/main' }}
     steps:
       - name: Write deploy reminder to step summary
         env:
@@ -570,11 +572,11 @@ jobs:
     #     hourly if this list diverges from status_check_contexts or from
     #     audit-force-merge.yml's REQUIRED_CHECKS env (RFC §4 + §6).
     #
-    # canvas-deploy-reminder is intentionally excluded from all-required.needs:
-    # it needs canvas-build, which is skipped on CI-only PRs (canvas=false).
-    # Including it in all-required.needs causes all-required to hang on
-    # every CI-only PR. Keep it runnable on PRs via its own
-    # `needs: [changes, canvas-build]` — the sentinel only aggregates the result.
+    # canvas-deploy-reminder IS now included in all-required.needs (mc#958 root-fix):
+    # added job-level `if: github.ref == 'refs/heads/main'` so ci-required-drift.py's
+    # ci_job_names() detects it as github.ref-gated and skips it from F1.
+    # The step-level `if: ... || REF_NAME != refs/heads/main` exits 0 when not main,
+    # so the job succeeds (not skipped) on non-main pushes — sentinel treats as green.
     #
     # Phase 3 (RFC #219 §1) safety: underlying build jobs carry
     # continue-on-error: true so their failures are masked to null (2026-05-12: re-enabled mc#774 interim)
@@ -594,6 +596,7 @@ jobs:
       - canvas-build
       - shellcheck
       - python-lint
+      - canvas-deploy-reminder
     if: ${{ always() }}
     steps:
       - name: Assert every required dependency succeeded

.staging-trigger

@@ -1 +1 @@
-staging trigger
+staging trigger 2026-05-14T17:35:02Z

_ci_trigger.txt

@@ -0,0 +1 @@
+trigger

canvas/src/components/ThemeToggle.tsx

@@ -65,9 +65,18 @@ export function ThemeToggle({ className = "" }: { className?: string }) {
       // Use direct-child query to scope strictly to this radiogroup's buttons
       // and avoid accidentally focusing unrelated [role=radio] elements
       // elsewhere in the DOM (e.g. React Flow canvas nodes).
+      // Guard: skip focus if the current target is no longer in the document
+      // (e.g. React StrictMode double-invokes handlers during re-render).
+      if (!e.currentTarget.isConnected) return;
       const radiogroup = e.currentTarget.closest("[role=radiogroup]") as HTMLElement | null;
-      const btns = radiogroup?.querySelectorAll<HTMLButtonElement>("> [role=radio]");
-      btns?.[next]?.focus();
+      if (!radiogroup) return;
+      // Use children[] instead of querySelectorAll("> [role=radio]") to avoid
+      // jsdom's child-combinator selector parsing issues in test environments.
+      const btns = Array.from(radiogroup.children).filter(
+        (el): el is HTMLButtonElement =>
+          el.tagName === "BUTTON" && el.getAttribute("role") === "radio"
+      );
+      if (next < btns.length) btns[next]?.focus();
     },
     []
   );

canvas/src/components/__tests__/ThemeToggle.test.tsx

@@ -24,8 +24,12 @@ vi.mock("@/lib/theme-provider", () => ({
   })),
 }));
 
+// Wrap cleanup in act() so any pending React state updates (e.g. from
+// keyDown handlers that call setTheme) flush before DOM unmount. Without
+// this, cleanup() can race against pending renders and cause INDEX_SIZE_ERR
+// when the handleKeyDown callback tries to query the DOM mid-teardown.
 afterEach(() => {
-  cleanup();
+  act(() => { cleanup(); });
   vi.clearAllMocks();
 });
 
@@ -146,7 +150,7 @@ describe("ThemeToggle — keyboard navigation (WCAG 2.1.1 / ARIA radiogroup)", (
     const radios = screen.getAllByRole("radio");
     // dark (index 2) is current; ArrowRight should wrap to light (index 0)
     act(() => { radios[2].focus(); });
-    fireEvent.keyDown(radios[2], { key: "ArrowRight" });
+    act(() => { fireEvent.keyDown(radios[2], { key: "ArrowRight" }); });
     expect(mockSetTheme).toHaveBeenCalledWith("light");
   });
 
@@ -160,7 +164,7 @@ describe("ThemeToggle — keyboard navigation (WCAG 2.1.1 / ARIA radiogroup)", (
     const radios = screen.getAllByRole("radio");
     // light (index 0) is current; ArrowLeft should go to dark (index 2)
     act(() => { radios[0].focus(); });
-    fireEvent.keyDown(radios[0], { key: "ArrowLeft" });
+    act(() => { fireEvent.keyDown(radios[0], { key: "ArrowLeft" }); });
     expect(mockSetTheme).toHaveBeenCalledWith("dark");
   });
 
@@ -174,7 +178,7 @@ describe("ThemeToggle — keyboard navigation (WCAG 2.1.1 / ARIA radiogroup)", (
     const radios = screen.getAllByRole("radio");
     // light (index 0) is current; ArrowDown should go to system (index 1)
     act(() => { radios[0].focus(); });
-    fireEvent.keyDown(radios[0], { key: "ArrowDown" });
+    act(() => { fireEvent.keyDown(radios[0], { key: "ArrowDown" }); });
     expect(mockSetTheme).toHaveBeenCalledWith("system");
   });
 
@@ -187,7 +191,7 @@ describe("ThemeToggle — keyboard navigation (WCAG 2.1.1 / ARIA radiogroup)", (
     render(<ThemeToggle />);
     const radios = screen.getAllByRole("radio");
     act(() => { radios[2].focus(); });
-    fireEvent.keyDown(radios[2], { key: "Home" });
+    act(() => { fireEvent.keyDown(radios[2], { key: "Home" }); });
     expect(mockSetTheme).toHaveBeenCalledWith("light");
   });
 
@@ -200,14 +204,14 @@ describe("ThemeToggle — keyboard navigation (WCAG 2.1.1 / ARIA radiogroup)", (
     render(<ThemeToggle />);
     const radios = screen.getAllByRole("radio");
     act(() => { radios[0].focus(); });
-    fireEvent.keyDown(radios[0], { key: "End" });
+    act(() => { fireEvent.keyDown(radios[0], { key: "End" }); });
     expect(mockSetTheme).toHaveBeenCalledWith("dark");
   });
 
   it("does nothing on unrelated keys", () => {
     render(<ThemeToggle />);
     const radios = screen.getAllByRole("radio");
-    fireEvent.keyDown(radios[0], { key: "Enter" });
+    act(() => { fireEvent.keyDown(radios[0], { key: "Enter" }); });
     expect(mockSetTheme).not.toHaveBeenCalled();
   });
 });

workspace-server/internal/handlers/a2a_proxy.go

@@ -97,28 +97,28 @@ const maxProxyResponseBody = 10 << 20
 //
 // Timeout model — three independent budgets, none of which gets in each other's way:
 //
-//   1. Client.Timeout — DELIBERATELY UNSET. Client.Timeout is a hard wall on
-//      the entire request including streamed body reads, and would pre-empt
-//      legitimate slow cold-start flows (Claude Code first-token over OAuth
-//      can take 30-60s on boot; long-running agent synthesis can stream
-//      tokens for minutes). Total-request budget is enforced per-request
-//      via context deadline (canvas = idle-only, agent-to-agent = 30 min ceiling).
+//  1. Client.Timeout — DELIBERATELY UNSET. Client.Timeout is a hard wall on
+//     the entire request including streamed body reads, and would pre-empt
+//     legitimate slow cold-start flows (Claude Code first-token over OAuth
+//     can take 30-60s on boot; long-running agent synthesis can stream
+//     tokens for minutes). Total-request budget is enforced per-request
+//     via context deadline (canvas = idle-only, agent-to-agent = 30 min ceiling).
 //
-//   2. Transport.DialContext — 10s connect timeout. When a workspace's EC2
-//      black-holes TCP connects (instance terminated mid-flight, security group
-//      flipped, NACL bug), the OS default is 75s on Linux / 21s on macOS — long
-//      enough that Cloudflare's ~100s edge timeout can fire first and surface
-//      a generic 502 page to canvas. 10s is well above realistic intra-region
-//      latencies and well below CF's edge timeout.
+//  2. Transport.DialContext — 10s connect timeout. When a workspace's EC2
+//     black-holes TCP connects (instance terminated mid-flight, security group
+//     flipped, NACL bug), the OS default is 75s on Linux / 21s on macOS — long
+//     enough that Cloudflare's ~100s edge timeout can fire first and surface
+//     a generic 502 page to canvas. 10s is well above realistic intra-region
+//     latencies and well below CF's edge timeout.
 //
-//   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.
+//  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
@@ -645,7 +645,7 @@ func (h *WorkspaceHandler) resolveAgentURL(ctx context.Context, workspaceID stri
 			// the caller can retry once the workspace is back online (~10s).
 			if status == "hibernated" {
 				log.Printf("ProxyA2A: waking hibernated workspace %s", workspaceID)
-				go h.RestartByID(workspaceID)
+				h.goAsync(func() { h.RestartByID(workspaceID) })
 				return "", &proxyA2AError{
 					Status:  http.StatusServiceUnavailable,
 					Headers: map[string]string{"Retry-After": "15"},

workspace-server/internal/handlers/a2a_proxy_helpers.go

@@ -194,7 +194,7 @@ func (h *WorkspaceHandler) maybeMarkContainerDead(ctx context.Context, workspace
 	}
 	db.ClearWorkspaceKeys(ctx, workspaceID)
 	h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceOffline), workspaceID, map[string]interface{}{})
-	go h.RestartByID(workspaceID)
+	h.goAsync(func() { h.RestartByID(workspaceID) })
 	return true
 }
 
@@ -241,7 +241,7 @@ func (h *WorkspaceHandler) preflightContainerHealth(ctx context.Context, workspa
 	}
 	db.ClearWorkspaceKeys(ctx, workspaceID)
 	h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceOffline), workspaceID, map[string]interface{}{})
-	go h.RestartByID(workspaceID)
+	h.goAsync(func() { h.RestartByID(workspaceID) })
 	return &proxyA2AError{
 		Status: http.StatusServiceUnavailable,
 		Response: gin.H{
@@ -262,8 +262,8 @@ func (h *WorkspaceHandler) logA2AFailure(ctx context.Context, workspaceID, calle
 		errWsName = workspaceID
 	}
 	summary := "A2A request to " + errWsName + " failed: " + errMsg
-	go func(parent context.Context) {
-		logCtx, cancel := context.WithTimeout(context.WithoutCancel(parent), 30*time.Second)
+	h.goAsync(func() {
+		logCtx, cancel := context.WithTimeout(context.WithoutCancel(ctx), 30*time.Second)
 		defer cancel()
 		LogActivity(logCtx, h.broadcaster, ActivityParams{
 			WorkspaceID:  workspaceID,
@@ -277,7 +277,7 @@ func (h *WorkspaceHandler) logA2AFailure(ctx context.Context, workspaceID, calle
 			Status:       "error",
 			ErrorDetail:  &errMsg,
 		})
-	}(ctx)
+	})
 }
 
 // logA2ASuccess records a successful A2A round-trip and (for canvas-initiated
@@ -298,19 +298,19 @@ func (h *WorkspaceHandler) logA2ASuccess(ctx context.Context, workspaceID, calle
 	// silent workspaces. Only update when callerID is a real workspace (not
 	// canvas, not a system caller) and the target returned 2xx/3xx.
 	if callerID != "" && !isSystemCaller(callerID) && statusCode < 400 {
-		go func() {
+		h.goAsync(func() {
 			bgCtx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
 			defer cancel()
 			if _, err := db.DB.ExecContext(bgCtx,
 				`UPDATE workspaces SET last_outbound_at = NOW() WHERE id = $1`, callerID); err != nil {
 				log.Printf("last_outbound_at update failed for %s: %v", callerID, err)
 			}
-		}()
+		})
 	}
 	summary := a2aMethod + " → " + wsNameForLog
 	toolTrace := extractToolTrace(respBody)
-	go func(parent context.Context) {
-		logCtx, cancel := context.WithTimeout(context.WithoutCancel(parent), 30*time.Second)
+	h.goAsync(func() {
+		logCtx, cancel := context.WithTimeout(context.WithoutCancel(ctx), 30*time.Second)
 		defer cancel()
 		LogActivity(logCtx, h.broadcaster, ActivityParams{
 			WorkspaceID:  workspaceID,
@@ -325,7 +325,7 @@ func (h *WorkspaceHandler) logA2ASuccess(ctx context.Context, workspaceID, calle
 			DurationMs:   &durationMs,
 			Status:       logStatus,
 		})
-	}(ctx)
+	})
 
 	if callerID == "" && statusCode < 400 {
 		h.broadcaster.BroadcastOnly(workspaceID, string(events.EventA2AResponse), map[string]interface{}{
@@ -510,8 +510,8 @@ func (h *WorkspaceHandler) logA2AReceiveQueued(ctx context.Context, workspaceID,
 		wsName = workspaceID
 	}
 	summary := a2aMethod + " → " + wsName + " (queued for poll)"
-	go func(parent context.Context) {
-		logCtx, cancel := context.WithTimeout(context.WithoutCancel(parent), 30*time.Second)
+	h.goAsync(func() {
+		logCtx, cancel := context.WithTimeout(context.WithoutCancel(ctx), 30*time.Second)
 		defer cancel()
 		LogActivity(logCtx, h.broadcaster, ActivityParams{
 			WorkspaceID:  workspaceID,
@@ -523,7 +523,7 @@ func (h *WorkspaceHandler) logA2AReceiveQueued(ctx context.Context, workspaceID,
 			RequestBody:  json.RawMessage(body),
 			Status:       "ok",
 		})
-	}(ctx)
+	})
 }
 
 // readUsageMap extracts input_tokens / output_tokens from the "usage" key of m.

workspace-server/internal/handlers/a2a_proxy_preflight_test.go

@@ -54,6 +54,7 @@ func TestPreflight_ContainerRunning_ReturnsNil(t *testing.T) {
 	_ = setupTestDB(t)
 	stub := &preflightLocalProv{running: true, err: nil}
 	h := NewWorkspaceHandler(newTestBroadcaster(), nil, "http://localhost:8080", t.TempDir())
+	waitForHandlerAsyncBeforeDBCleanup(t, h)
 	h.provisioner = stub
 
 	if err := h.preflightContainerHealth(context.Background(), "ws-running-123"); err != nil {
@@ -186,8 +187,8 @@ func TestProxyA2A_Preflight_RoutesThroughProvisionerSSOT(t *testing.T) {
 	}
 
 	var (
-		callsIsRunning             bool
-		callsContainerInspectRaw   bool
+		callsIsRunning                  bool
+		callsContainerInspectRaw        bool
 		callsRunningContainerNameDirect bool
 	)
 	ast.Inspect(fn.Body, func(n ast.Node) bool {

workspace-server/internal/handlers/a2a_proxy_test.go

@@ -262,6 +262,7 @@ func TestProxyA2A_Upstream502_TriggersContainerDeadCheck(t *testing.T) {
 	allowLoopbackForTest(t)
 	broadcaster := newTestBroadcaster()
 	handler := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
+	waitForHandlerAsyncBeforeDBCleanup(t, handler)
 	cp := &fakeCPProv{running: false}
 	handler.SetCPProvisioner(cp)
 
@@ -324,6 +325,7 @@ func TestProxyA2A_Upstream502_AliveAgent_PropagatesAsIs(t *testing.T) {
 	allowLoopbackForTest(t)
 	broadcaster := newTestBroadcaster()
 	handler := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
+	waitForHandlerAsyncBeforeDBCleanup(t, handler)
 	cp := &fakeCPProv{running: true}
 	handler.SetCPProvisioner(cp)
 
@@ -513,6 +515,7 @@ func TestProxyA2A_AllowedSelf_SkipsAccessCheck(t *testing.T) {
 	allowLoopbackForTest(t)
 	broadcaster := newTestBroadcaster()
 	handler := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
+	waitForHandlerAsyncBeforeDBCleanup(t, handler)
 
 	agentServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		w.Header().Set("Content-Type", "application/json")
@@ -661,18 +664,18 @@ func TestProxyA2A_CallerIDDerivedFromBearer(t *testing.T) {
 	//    (column order: workspace_id, activity_type, source_id, target_id, ...)
 	mock.ExpectExec("INSERT INTO activity_logs").
 		WithArgs(
-			"ws-target",                       // $1 workspace_id
-			"a2a_receive",                     // $2 activity_type
-			sqlmock.AnyArg(),                  // $3 source_id — *string("ws-caller"), checked below
-			sqlmock.AnyArg(),                  // $4 target_id
-			sqlmock.AnyArg(),                  // $5 method
-			sqlmock.AnyArg(),                  // $6 summary
-			sqlmock.AnyArg(),                  // $7 request_body
-			sqlmock.AnyArg(),                  // $8 response_body
-			sqlmock.AnyArg(),                  // $9 tool_trace
-			sqlmock.AnyArg(),                  // $10 duration_ms
-			sqlmock.AnyArg(),                  // $11 status
-			sqlmock.AnyArg(),                  // $12 error_detail
+			"ws-target",      // $1 workspace_id
+			"a2a_receive",    // $2 activity_type
+			sqlmock.AnyArg(), // $3 source_id — *string("ws-caller"), checked below
+			sqlmock.AnyArg(), // $4 target_id
+			sqlmock.AnyArg(), // $5 method
+			sqlmock.AnyArg(), // $6 summary
+			sqlmock.AnyArg(), // $7 request_body
+			sqlmock.AnyArg(), // $8 response_body
+			sqlmock.AnyArg(), // $9 tool_trace
+			sqlmock.AnyArg(), // $10 duration_ms
+			sqlmock.AnyArg(), // $11 status
+			sqlmock.AnyArg(), // $12 error_detail
 		).
 		WillReturnResult(sqlmock.NewResult(0, 1))
 
@@ -1716,7 +1719,6 @@ func TestDispatchA2A_RejectsUnsafeURL(t *testing.T) {
 	}
 }
 
-
 // --- handleA2ADispatchError ---
 
 func TestHandleA2ADispatchError_ContextDeadline(t *testing.T) {
@@ -1803,6 +1805,7 @@ func TestMaybeMarkContainerDead_CPOnly_NotRunning(t *testing.T) {
 	mock := setupTestDB(t)
 	setupTestRedis(t)
 	handler := NewWorkspaceHandler(newTestBroadcaster(), nil, "http://localhost:8080", t.TempDir())
+	waitForHandlerAsyncBeforeDBCleanup(t, handler)
 	cp := &fakeCPProv{running: false}
 	handler.SetCPProvisioner(cp)
 
@@ -1955,6 +1958,7 @@ func TestLogA2AFailure_Smoke(t *testing.T) {
 	mock := setupTestDB(t)
 	setupTestRedis(t)
 	handler := NewWorkspaceHandler(newTestBroadcaster(), nil, "http://localhost:8080", t.TempDir())
+	waitForHandlerAsyncBeforeDBCleanup(t, handler)
 
 	// Sync workspace-name lookup (called in the caller goroutine).
 	mock.ExpectQuery(`SELECT name FROM workspaces WHERE id =`).
@@ -1973,6 +1977,7 @@ func TestLogA2AFailure_EmptyNameFallback(t *testing.T) {
 	mock := setupTestDB(t)
 	setupTestRedis(t)
 	handler := NewWorkspaceHandler(newTestBroadcaster(), nil, "http://localhost:8080", t.TempDir())
+	waitForHandlerAsyncBeforeDBCleanup(t, handler)
 
 	// Empty name from DB → summary uses the workspaceID as the name.
 	mock.ExpectQuery(`SELECT name FROM workspaces WHERE id =`).
@@ -1989,6 +1994,7 @@ func TestLogA2ASuccess_Smoke(t *testing.T) {
 	mock := setupTestDB(t)
 	setupTestRedis(t)
 	handler := NewWorkspaceHandler(newTestBroadcaster(), nil, "http://localhost:8080", t.TempDir())
+	waitForHandlerAsyncBeforeDBCleanup(t, handler)
 
 	mock.ExpectQuery(`SELECT name FROM workspaces WHERE id =`).
 		WithArgs("ws-ok").
@@ -2005,6 +2011,7 @@ func TestLogA2ASuccess_ErrorStatus(t *testing.T) {
 	mock := setupTestDB(t)
 	setupTestRedis(t)
 	handler := NewWorkspaceHandler(newTestBroadcaster(), nil, "http://localhost:8080", t.TempDir())
+	waitForHandlerAsyncBeforeDBCleanup(t, handler)
 
 	mock.ExpectQuery(`SELECT name FROM workspaces WHERE id =`).
 		WithArgs("ws-err").

workspace-server/internal/handlers/a2a_queue_test.go

@@ -26,6 +26,10 @@ import (
 // setupTestDBForQueueTests creates a sqlmock DB using QueryMatcherEqual (exact
 // string matching) so that ExpectQuery/ExpectExec patterns are compared verbatim.
 // Uses the same global db.DB as setupTestDB so the handler can use it.
+//
+// IMPORTANT: db.DB is saved before assignment and restored via t.Cleanup so
+// that tests running after this one are not polluted by a closed mock.
+// Same fix as setupTestDB (handlers_test.go); same root cause as mc#975.
 func setupTestDBForQueueTests(t *testing.T) sqlmock.Sqlmock {
 	t.Helper()
 	mockDB, mock, err := sqlmock.New(sqlmock.QueryMatcherOption(sqlmock.QueryMatcherEqual))

workspace-server/internal/handlers/delegation.go

@@ -2,6 +2,7 @@ package handlers
 
 import (
 	"context"
+	"database/sql"
 	"encoding/json"
 	"log"
 	"net/http"
@@ -698,7 +699,8 @@ func (h *DelegationHandler) listDelegationsFromLedger(ctx context.Context, works
 
 	var result []map[string]interface{}
 	for rows.Next() {
-		var delegationID, callerID, calleeID, taskPreview, status, resultPreview, errorDetail string
+		var delegationID, callerID, calleeID, taskPreview, status string
+		var resultPreview, errorDetail sql.NullString
 		var lastHeartbeat, deadline, createdAt, updatedAt *time.Time
 		if err := rows.Scan(
 			&delegationID, &callerID, &calleeID, &taskPreview,
@@ -717,11 +719,11 @@ func (h *DelegationHandler) listDelegationsFromLedger(ctx context.Context, works
 			"updated_at":    updatedAt,
 			"_ledger":       true, // marker so callers know this row is from the ledger
 		}
-		if resultPreview != "" {
-			entry["response_preview"] = textutil.TruncateBytes(resultPreview, 300)
+		if resultPreview.Valid && resultPreview.String != "" {
+			entry["response_preview"] = textutil.TruncateBytes(resultPreview.String, 300)
 		}
-		if errorDetail != "" {
-			entry["error"] = errorDetail
+		if errorDetail.Valid && errorDetail.String != "" {
+			entry["error"] = errorDetail.String
 		}
 		if lastHeartbeat != nil {
 			entry["last_heartbeat"] = lastHeartbeat

workspace-server/internal/handlers/delegation_list_test.go

@@ -145,6 +145,54 @@ func TestListDelegationsFromLedger_MultipleRows(t *testing.T) {
 	}
 }
 
+func TestListDelegationsFromLedger_NullsOmitted(t *testing.T) {
+	// last_heartbeat, deadline, result_preview, error_detail are all NULL.
+	// Handler must not panic and must omit those keys from the map.
+	mockDB, mock, err := sqlmock.New()
+	if err != nil {
+		t.Fatalf("failed to create sqlmock: %v", err)
+	}
+	prevDB := db.DB
+	db.DB = mockDB
+	t.Cleanup(func() { mockDB.Close(); db.DB = prevDB })
+
+	now := time.Now()
+	rows := sqlmock.NewRows([]string{
+		"delegation_id", "caller_id", "callee_id", "task_preview",
+		"status", "result_preview", "error_detail",
+		"last_heartbeat", "deadline", "created_at", "updated_at",
+	}).
+		AddRow("del-1", "ws-1", "ws-2", "task", "queued", nil, nil, nil, nil, now, now)
+	mock.ExpectQuery("SELECT .+ FROM delegations").
+		WithArgs("ws-1").
+		WillReturnRows(rows)
+
+	broadcaster := newTestBroadcaster()
+	wh := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
+	dh := NewDelegationHandler(wh, broadcaster)
+
+	got := dh.listDelegationsFromLedger(context.Background(), "ws-1")
+	if len(got) != 1 {
+		t.Fatalf("expected 1 entry, got %d", len(got))
+	}
+	e := got[0]
+	if _, ok := e["last_heartbeat"]; ok {
+		t.Error("last_heartbeat should be absent when NULL")
+	}
+	if _, ok := e["deadline"]; ok {
+		t.Error("deadline should be absent when NULL")
+	}
+	if _, ok := e["response_preview"]; ok {
+		t.Error("response_preview should be absent when NULL result_preview")
+	}
+	if _, ok := e["error"]; ok {
+		t.Error("error should be absent when NULL error_detail")
+	}
+	if err := mock.ExpectationsWereMet(); err != nil {
+		t.Errorf("sqlmock expectations: %v", err)
+	}
+}
+
 func TestListDelegationsFromLedger_QueryError(t *testing.T) {
 	// Query failure returns nil — graceful fallback, no panic.
 	mockDB, mock, err := sqlmock.New()
@@ -438,10 +486,3 @@ func TestListDelegationsFromActivityLogs_RowsErr(t *testing.T) {
 		t.Errorf("sqlmock expectations: %v", err)
 	}
 }
-
-// TestListDelegationsFromActivityLogs_ScanErrorSkipped is removed.
-//
-// Same reason as TestListDelegationsFromLedger_ScanError: Go 1.25 causes
-// sqlmock.NewRows([]string{}).AddRow(...) to panic in test SETUP. The handler
-// has no recover(), so a scan panic would crash the process — the correct
-// behaviour. Real-DB integration tests cover this path.

workspace-server/internal/handlers/handlers_test.go

@@ -29,6 +29,11 @@ func init() {
 // setupTestDB creates a sqlmock DB and assigns it to the global db.DB.
 // It also disables the SSRF URL check so that httptest.NewServer loopback
 // URLs and fake hostnames (*.example) used in tests don't trigger rejections.
+//
+// IMPORTANT: db.DB is saved before assignment and restored via t.Cleanup so
+// that tests running after this one are not polluted by a closed mock.
+// This is the single root cause of the systemic CI/Platform (Go) failures on
+// main HEAD 8026f020 (mc#975).
 func setupTestDB(t *testing.T) sqlmock.Sqlmock {
 	t.Helper()
 	mockDB, mock, err := sqlmock.New()
@@ -57,6 +62,11 @@ func setupTestDB(t *testing.T) sqlmock.Sqlmock {
 	return mock
 }
 
+func waitForHandlerAsyncBeforeDBCleanup(t *testing.T, h *WorkspaceHandler) {
+	t.Helper()
+	t.Cleanup(h.waitAsyncForTest)
+}
+
 // setupTestRedis creates a miniredis instance and assigns it to the global db.RDB.
 func setupTestRedis(t *testing.T) *miniredis.Miniredis {
 	t.Helper()
@@ -356,6 +366,11 @@ func TestWorkspaceCreate(t *testing.T) {
 }
 
 func TestBuildProvisionerConfig_IncludesAwarenessSettings(t *testing.T) {
+	mock := setupTestDB(t)
+	mock.ExpectQuery(`SELECT digest FROM runtime_image_pins`).
+		WithArgs("claude-code").
+		WillReturnError(sql.ErrNoRows)
+
 	broadcaster := newTestBroadcaster()
 	handler := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", "/tmp/configs")
 

workspace-server/internal/handlers/org_helpers.go

@@ -15,6 +15,7 @@ import (
 
 	"gopkg.in/yaml.v3"
 )
+
 // resolvePromptRef reads a prompt body from either an inline string or a
 // file ref relative to the workspace's files_dir. Inline always wins when
 // both are non-empty (caller-provided inline is more authoritative than a
@@ -78,23 +79,81 @@ func hasUnresolvedVarRef(original, expanded string) bool {
 }
 
 // expandWithEnv expands ${VAR} and $VAR references in s using the env map.
-// Falls back to the platform process env if a var isn't in the map.
-// Shell variables must start with a letter or '_' per POSIX; invalid identifiers
-// are returned literally so that "$100" and "$5" stay as-is.
+// Falls back to the platform process env only when the whole value is a
+// single variable reference; embedded process-env expansion is too broad for
+// imported org YAML because host variables such as HOME are not template data.
 func expandWithEnv(s string, env map[string]string) string {
-	return os.Expand(s, func(key string) string {
-		if len(key) == 0 {
-			return "$"
+	if s == "" {
+		return ""
+	}
+	var b strings.Builder
+	for i := 0; i < len(s); {
+		if s[i] != '$' {
+			b.WriteByte(s[i])
+			i++
+			continue
 		}
-		c := key[0]
-		if !((c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || c == '_') {
-			return "$" + key // not a valid shell identifier — return literal
+
+		if i+1 >= len(s) {
+			b.WriteByte('$')
+			i++
+			continue
 		}
-		if v, ok := env[key]; ok {
-			return v
+
+		if s[i+1] == '{' {
+			end := strings.IndexByte(s[i+2:], '}')
+			if end < 0 {
+				b.WriteByte('$')
+				i++
+				continue
+			}
+			end += i + 2
+			key := s[i+2 : end]
+			ref := s[i : end+1]
+			b.WriteString(expandEnvRef(key, ref, s, env))
+			i = end + 1
+			continue
 		}
+
+		if !isEnvIdentStart(s[i+1]) {
+			b.WriteByte('$')
+			i++
+			continue
+		}
+		j := i + 2
+		for j < len(s) && isEnvIdentPart(s[j]) {
+			j++
+		}
+		key := s[i+1 : j]
+		ref := s[i:j]
+		b.WriteString(expandEnvRef(key, ref, s, env))
+		i = j
+	}
+	return b.String()
+}
+
+func expandEnvRef(key, ref, whole string, env map[string]string) string {
+	if key == "" {
+		return "$"
+	}
+	if !isEnvIdentStart(key[0]) {
+		return "$" + key
+	}
+	if v, ok := env[key]; ok {
+		return v
+	}
+	if ref == whole {
 		return os.Getenv(key)
-	})
+	}
+	return ref
+}
+
+func isEnvIdentStart(c byte) bool {
+	return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || c == '_'
+}
+
+func isEnvIdentPart(c byte) bool {
+	return isEnvIdentStart(c) || (c >= '0' && c <= '9')
 }
 
 // loadWorkspaceEnv reads the org root .env and the workspace-specific .env

workspace-server/internal/handlers/org_helpers_pure_test.go

@@ -104,8 +104,8 @@ func TestHasUnresolvedVarRef_Resolved(t *testing.T) {
 		// documents this design choice; callers who need empty=resolved should
 		// pre-process the output before calling hasUnresolvedVarRef.
 		{"${VAR}", "", true},
-		{"${VAR}", "value", false},                    // var replaced
-		{"$VAR", "value", false},                      // bare var replaced
+		{"${VAR}", "value", false}, // var replaced
+		{"$VAR", "value", false},   // bare var replaced
 		{"prefix${VAR}suffix", "prefixvaluesuffix", false},
 		{"${A}${B}", "ab", false},
 		// FOO=FOO and BAR=BAR — both vars found and replaced. Expanded output
@@ -125,14 +125,14 @@ func TestHasUnresolvedVarRef_Resolved(t *testing.T) {
 func TestHasUnresolvedVarRef_Unresolved(t *testing.T) {
 	// Expansion left the refs intact → unresolved.
 	cases := []struct {
-		orig    string
+		orig     string
 		expanded string
 	}{
-		{"${VAR}", "${VAR}"},       // untouched
-		{"$VAR", "$VAR"},           // bare untouched
+		{"${VAR}", "${VAR}"}, // untouched
+		{"$VAR", "$VAR"},     // bare untouched
 		{"prefix${VAR}suffix", "prefix${VAR}suffix"},
-		{"${A}${B}", "${A}${B}"},   // both unresolved
-		{"${FOO}", ""},             // empty result with var ref in original
+		{"${A}${B}", "${A}${B}"}, // both unresolved
+		{"${FOO}", ""},           // empty result with var ref in original
 	}
 	for _, tc := range cases {
 		t.Run(tc.orig, func(t *testing.T) {
@@ -205,8 +205,8 @@ func TestMergeCategoryRouting_WorkspaceOverrides(t *testing.T) {
 		"ui":       {"Frontend Engineer"},
 	}
 	ws := map[string][]string{
-		"security": {"SRE Team"}, // narrows
-		"ui":       {},           // drops
+		"security": {"SRE Team"},      // narrows
+		"ui":       {},                // drops
 		"infra":    {"Platform Team"}, // adds
 	}
 	r := mergeCategoryRouting(defaults, ws)
@@ -287,7 +287,7 @@ func TestRenderCategoryRoutingYAML_StableOrdering(t *testing.T) {
 	if ai <= 0 || zi <= 0 || mi <= 0 {
 		t.Fatalf("could not locate all keys in output: %s", out)
 	}
-	if !(ai < mi && mi < zi) {
+	if ai >= mi || mi >= zi {
 		t.Errorf("keys not sorted: alpha=%d middle=%d zebra=%d, output:\n%s", ai, mi, zi, out)
 	}
 }
@@ -462,8 +462,45 @@ func TestExpandWithEnv_LiteralDollar(t *testing.T) {
 func TestExpandWithEnv_PartiallyPresent(t *testing.T) {
 	env := map[string]string{"SET": "yes"}
 	result := expandWithEnv("${SET} and ${NOT_SET}", env)
-	// ${SET} resolved; ${NOT_SET} -> "" via empty fallback.
-	assert.Equal(t, "yes and ", result)
+	assert.Equal(t, "yes and ${NOT_SET}", result)
+}
+
+func TestExpandWithEnv_EmbeddedMissingProcessEnvStaysLiteral(t *testing.T) {
+	t.Setenv("MOL_TEST_EMBEDDED_MISSING", "")
+
+	result := expandWithEnv("prefix/${MOL_TEST_EMBEDDED_MISSING}/suffix", map[string]string{})
+	assert.Equal(t, "prefix/${MOL_TEST_EMBEDDED_MISSING}/suffix", result)
+}
+
+// POSIX identifier guard regression tests (CWE-78 fix).
+// Keys not starting with [a-zA-Z_] must not be looked up in env or os.Getenv.
+func TestExpandWithEnv_DigitPrefix_NotExpanded(t *testing.T) {
+	// ${0}, ${5}, ${1VAR} — numeric prefix → not a valid shell identifier.
+	// Guard must return "$0", "$5", "$1VAR" literally; no env lookup.
+	cases := []struct {
+		input string
+		want  string
+	}{
+		{"${0}", "$0"},
+		{"${5}", "$5"},
+		{"${1VAR}", "$1VAR"},
+		{"prefix ${0} suffix", "prefix $0 suffix"},
+		{"$0", "$0"},
+		{"$5", "$5"},
+		{"HOME=${HOME}", "HOME=${HOME}"}, // HOME is valid but embedded in larger string
+	}
+	for _, tc := range cases {
+		t.Run(tc.input, func(t *testing.T) {
+			got := expandWithEnv(tc.input, map[string]string{})
+			assert.Equal(t, tc.want, got)
+		})
+	}
+}
+
+func TestExpandWithEnv_EmptyKey_ReturnsDollar(t *testing.T) {
+	// ${} → "$" (empty key, guard returns "$")
+	result := expandWithEnv("value=${}", map[string]string{})
+	assert.Equal(t, "value=$", result)
 }
 
 // mergeCategoryRouting tests — unions defaults with per-workspace routing.
@@ -545,8 +582,8 @@ func TestRenderCategoryRoutingYAML_SingleCategory(t *testing.T) {
 
 func TestRenderCategoryRoutingYAML_MultipleCategoriesSorted(t *testing.T) {
 	routing := map[string][]string{
-		"zebra":   {"RoleZ"},
-		"alpha":   {"RoleA"},
+		"zebra":      {"RoleZ"},
+		"alpha":      {"RoleA"},
 		"middleware": {"RoleM"},
 	}
 	result, err := renderCategoryRoutingYAML(routing)

workspace-server/internal/handlers/org_helpers_security_test.go

@@ -93,7 +93,7 @@ func TestResolveInsideRoot_DotPathComponent(t *testing.T) {
 	if err != nil {
 		t.Fatalf("dot path component: unexpected error: %v", err)
 	}
-	if got[len(got)-14:] != "/subdir/file.txt" {
+	if !strings.HasSuffix(got, "/subdir/file.txt") {
 		t.Errorf("dot path component: got %q, want suffix /subdir/file.txt", got)
 	}
 }
@@ -138,23 +138,6 @@ func TestResolveInsideRoot_SiblingNotEscaped(t *testing.T) {
 
 // ── isSafeRoleName ────────────────────────────────────────────────────────────
 
-func TestIsSafeRoleName_Valid(t *testing.T) {
-	valid := []string{
-		"backend",
-		"Frontend-Engineer",
-		"research_lead",
-		"devOps123",
-		"a",
-		"A",
-		"team_42-leads",
-	}
-	for _, name := range valid {
-		if !isSafeRoleName(name) {
-			t.Errorf("isSafeRoleName(%q): expected true, got false", name)
-		}
-	}
-}
-
 func TestIsSafeRoleName_Empty(t *testing.T) {
 	if isSafeRoleName("") {
 		t.Error("isSafeRoleName(\"\"): expected false, got true")
@@ -268,33 +251,6 @@ func TestMergeCategoryRouting_WsOverrideDropsDefault(t *testing.T) {
 	}
 }
 
-func TestMergeCategoryRouting_EmptyListDropsCategory(t *testing.T) {
-	defaultRouting := map[string][]string{
-		"security": {"Backend Engineer"},
-		"ui":       {"Frontend Engineer"},
-	}
-	wsRouting := map[string][]string{
-		"security": {}, // empty list = opt out
-	}
-	got := mergeCategoryRouting(defaultRouting, wsRouting)
-	if _, exists := got["security"]; exists {
-		t.Error("empty ws list should delete the category from output")
-	}
-	if len(got["ui"]) != 1 {
-		t.Errorf("ui should still exist: got %v", got["ui"])
-	}
-}
-
-func TestMergeCategoryRouting_EmptyKeySkipped(t *testing.T) {
-	defaultRouting := map[string][]string{
-		"": {"Backend Engineer"},
-	}
-	got := mergeCategoryRouting(defaultRouting, nil)
-	if _, exists := got[""]; exists {
-		t.Error("empty key should be skipped")
-	}
-}
-
 func TestMergeCategoryRouting_EmptyRolesInDefaultSkipped(t *testing.T) {
 	defaultRouting := map[string][]string{
 		"security": {},

workspace-server/internal/handlers/plugins_install_eic_test.go

@@ -342,6 +342,11 @@ func TestPluginInstall_InstanceLookupError_Returns503(t *testing.T) {
 // ---------- dispatch: uninstall ----------
 
 func TestPluginUninstall_SaaS_DispatchesToEIC(t *testing.T) {
+	mock := setupTestDB(t)
+	mock.ExpectExec("DELETE FROM workspace_plugins WHERE workspace_id").
+		WithArgs("ws-1", "browser-automation").
+		WillReturnResult(sqlmock.NewResult(0, 1))
+
 	stubReadPluginManifestViaEIC(t, func(ctx context.Context, instanceID, runtime, pluginName string) ([]byte, error) {
 		return []byte("name: browser-automation\nskills:\n  - browse\n"), nil
 	})

workspace-server/internal/handlers/plugins_test.go

@@ -629,6 +629,9 @@ func TestPluginInstall_RejectsUnknownScheme(t *testing.T) {
 }
 
 func TestPluginInstall_LocalSourceReachesContainerLookup(t *testing.T) {
+	mock := setupTestDB(t)
+	expectAllowlistAllowAll(mock)
+
 	base := t.TempDir()
 	pluginDir := filepath.Join(base, "demo")
 	_ = os.MkdirAll(pluginDir, 0o755)
@@ -955,14 +958,14 @@ func TestLogInstallLimitsOnce(t *testing.T) {
 
 func TestRegexpEscapeForAwk(t *testing.T) {
 	cases := map[string]string{
-		"my-plugin":                 `my-plugin`,
-		"# Plugin: foo /":           `# Plugin: foo \/`,
-		"# Plugin: a.b /":           `# Plugin: a\.b \/`,
-		"foo[bar]":                  `foo\[bar\]`,
-		"a*b+c?":                    `a\*b\+c\?`,
-		"path|with|pipes":           `path\|with\|pipes`,
-		`back\slash`:                `back\\slash`,
-		"":                          ``,
+		"my-plugin":       `my-plugin`,
+		"# Plugin: foo /": `# Plugin: foo \/`,
+		"# Plugin: a.b /": `# Plugin: a\.b \/`,
+		"foo[bar]":        `foo\[bar\]`,
+		"a*b+c?":          `a\*b\+c\?`,
+		"path|with|pipes": `path\|with\|pipes`,
+		`back\slash`:      `back\\slash`,
+		"":                ``,
 	}
 	for in, want := range cases {
 		got := regexpEscapeForAwk(in)
@@ -1247,7 +1250,7 @@ func TestPluginDownload_GithubSchemeStreamsTarball(t *testing.T) {
 		scheme: "github",
 		fetchFn: func(_ context.Context, _ string, dst string) (string, error) {
 			files := map[string]string{
-				"plugin.yaml":            "name: remote-plugin\nversion: 1.0.0\n",
+				"plugin.yaml":             "name: remote-plugin\nversion: 1.0.0\n",
 				"skills/x/SKILL.md":       "---\nname: x\n---\n",
 				"adapters/claude_code.py": "from plugins_registry.builtins import AgentskillsAdaptor as Adaptor\n",
 			}

workspace-server/internal/handlers/restart_signals.go

@@ -58,7 +58,7 @@ func (h *WorkspaceHandler) gracefulPreRestart(ctx context.Context, workspaceID s
 	// Non-blocking send — don't stall the restart cycle.
 	// Run in a detached goroutine so the caller (runRestartCycle) can
 	// proceed to stopForRestart without waiting.
-	go func() {
+	h.goAsync(func() {
 		signalCtx, cancel := context.WithTimeout(context.Background(), restartSignalTimeout)
 		defer cancel()
 
@@ -109,7 +109,7 @@ func (h *WorkspaceHandler) gracefulPreRestart(ctx context.Context, workspaceID s
 		} else {
 			log.Printf("A2AGracefulRestart: %s returned status %d — proceeding with stop", workspaceID, resp.StatusCode)
 		}
-	}()
+	})
 }
 
 // resolveAgentURLForRestartSignal returns the routable URL for the workspace

workspace-server/internal/handlers/restart_signals_test.go

@@ -271,6 +271,7 @@ func TestGracefulPreRestart_URLResolutionError(t *testing.T) {
 		WorkspaceHandler: newHandlerWithTestDeps(t),
 		errToReturn:      context.DeadlineExceeded,
 	}
+	waitForHandlerAsyncBeforeDBCleanup(t, hWrapper.WorkspaceHandler)
 
 	hWrapper.gracefulPreRestart(context.Background(), "ws-url-err-111")
 	time.Sleep(200 * time.Millisecond)

workspace-server/internal/handlers/secrets.go

@@ -63,6 +63,9 @@ func (h *SecretsHandler) List(c *gin.Context) {
 			"updated_at": updatedAt,
 		})
 	}
+	if err := rows.Err(); err != nil {
+		log.Printf("List secrets rows.Err: %v", err)
+	}
 
 	// 2. Global secrets not overridden at workspace level
 	globalRows, err := db.DB.QueryContext(ctx,
@@ -91,6 +94,9 @@ func (h *SecretsHandler) List(c *gin.Context) {
 			"updated_at": updatedAt,
 		})
 	}
+	if err := globalRows.Err(); err != nil {
+		log.Printf("List secrets (global) rows.Err: %v", err)
+	}
 
 	c.JSON(http.StatusOK, secrets)
 }
@@ -174,6 +180,9 @@ func (h *SecretsHandler) Values(c *gin.Context) {
 				out[k] = string(decrypted)
 			}
 		}
+		if err := globalRows.Err(); err != nil {
+			log.Printf("secrets.Values globalRows.Err: %v", err)
+		}
 	}
 
 	wsRows, wErr := db.DB.QueryContext(ctx,
@@ -195,6 +204,9 @@ func (h *SecretsHandler) Values(c *gin.Context) {
 				out[k] = string(decrypted) // workspace override wins over global
 			}
 		}
+		if err := wsRows.Err(); err != nil {
+			log.Printf("secrets.Values wsRows.Err: %v", err)
+		}
 	}
 
 	if len(failedKeys) > 0 {
@@ -324,6 +336,9 @@ func (h *SecretsHandler) ListGlobal(c *gin.Context) {
 			"scope":      "global",
 		})
 	}
+	if err := rows.Err(); err != nil {
+		log.Printf("ListGlobal rows.Err: %v", err)
+	}
 	c.JSON(http.StatusOK, secrets)
 }
 
@@ -400,6 +415,9 @@ func (h *SecretsHandler) restartAllAffectedByGlobalKey(key string) {
 			ids = append(ids, id)
 		}
 	}
+	if err := rows.Err(); err != nil {
+		log.Printf("restartAllAffectedByGlobalKey rows.Err: %v", err)
+	}
 	if len(ids) == 0 {
 		return
 	}

workspace-server/internal/handlers/terminal_test.go

@@ -340,6 +340,11 @@ func TestSSHCommandCmd_BuildsArgv(t *testing.T) {
 // a workspace must still be able to access its own terminal. The CanCommunicate
 // fast-path returns true when callerID == targetID.
 func TestTerminalConnect_KI005_AllowsOwnTerminal(t *testing.T) {
+	mock := setupTestDB(t)
+	mock.ExpectQuery("SELECT COALESCE").
+		WithArgs("ws-alice").
+		WillReturnRows(sqlmock.NewRows([]string{"instance_id"}).AddRow(""))
+
 	// CanCommunicate fast-path: callerID == targetID → returns true without DB.
 	prev := canCommunicateCheck
 	canCommunicateCheck = func(callerID, targetID string) bool { return callerID == targetID }
@@ -367,6 +372,11 @@ func TestTerminalConnect_KI005_AllowsOwnTerminal(t *testing.T) {
 // skip the CanCommunicate check entirely and fall through to the Docker auth path.
 // We assert they get the nil-docker 503 instead of 403.
 func TestTerminalConnect_KI005_SkipsCheckWithoutHeader(t *testing.T) {
+	mock := setupTestDB(t)
+	mock.ExpectQuery("SELECT COALESCE").
+		WithArgs("ws-any").
+		WillReturnRows(sqlmock.NewRows([]string{"instance_id"}).AddRow(""))
+
 	h := NewTerminalHandler(nil) // nil docker → 503 if reached
 	w := httptest.NewRecorder()
 	c, _ := gin.CreateTestContext(w)
@@ -439,6 +449,9 @@ func TestTerminalConnect_KI005_AllowsSiblingWorkspace(t *testing.T) {
 	mock.ExpectExec(`UPDATE workspace_auth_tokens SET last_used_at`).
 		WithArgs(sqlmock.AnyArg()).
 		WillReturnResult(sqlmock.NewResult(0, 1))
+	mock.ExpectQuery("SELECT COALESCE").
+		WithArgs("ws-dev").
+		WillReturnRows(sqlmock.NewRows([]string{"instance_id"}).AddRow(""))
 
 	h := NewTerminalHandler(nil)
 	w := httptest.NewRecorder()
@@ -463,7 +476,10 @@ func TestTerminalConnect_KI005_AllowsSiblingWorkspace(t *testing.T) {
 // introduced in GH#1885: internal routing uses org tokens which are not in
 // workspace_auth_tokens, so ValidateToken would always fail for them.
 func TestKI005_OrgToken_SkipsValidateToken(t *testing.T) {
-	setupTestDB(t) // no ValidateToken ExpectQuery — none should fire
+	mock := setupTestDB(t) // no ValidateToken ExpectQuery — none should fire
+	mock.ExpectQuery("SELECT COALESCE").
+		WithArgs("ws-target").
+		WillReturnRows(sqlmock.NewRows([]string{"instance_id"}).AddRow(""))
 	prev := canCommunicateCheck
 	canCommunicateCheck = func(callerID, targetID string) bool {
 		// Simulate platform agent → target workspace (same org).
@@ -544,4 +560,3 @@ func TestSSHCommandCmd_ConnectTimeoutPresent(t *testing.T) {
 			args)
 	}
 }
-

workspace-server/internal/handlers/workspace.go

@@ -15,6 +15,7 @@ import (
 	"os"
 	"path/filepath"
 	"strings"
+	"sync"
 	"time"
 
 	"github.com/Molecule-AI/molecule-monorepo/platform/internal/crypto"
@@ -73,6 +74,19 @@ type WorkspaceHandler struct {
 	// memory plugin). main.go sets this to plugin.DeleteNamespace
 	// when MEMORY_PLUGIN_URL is configured.
 	namespaceCleanupFn func(ctx context.Context, workspaceID string)
+	asyncWG            sync.WaitGroup
+}
+
+func (h *WorkspaceHandler) goAsync(fn func()) {
+	h.asyncWG.Add(1)
+	go func() {
+		defer h.asyncWG.Done()
+		fn()
+	}()
+}
+
+func (h *WorkspaceHandler) waitAsyncForTest() {
+	h.asyncWG.Wait()
 }
 
 func NewWorkspaceHandler(b events.EventEmitter, p *provisioner.Provisioner, platformURL, configsDir string) *WorkspaceHandler {

workspace-server/internal/handlers/workspace_dispatchers.go

@@ -111,11 +111,11 @@ func (h *WorkspaceHandler) provisionWorkspaceAuto(workspaceID, templatePath stri
 		"sync":         false,
 	})
 	if h.cpProv != nil {
-		go h.provisionWorkspaceCP(workspaceID, templatePath, configFiles, payload)
+		h.goAsync(func() { h.provisionWorkspaceCP(workspaceID, templatePath, configFiles, payload) })
 		return true
 	}
 	if h.provisioner != nil {
-		go h.provisionWorkspace(workspaceID, templatePath, configFiles, payload)
+		h.goAsync(func() { h.provisionWorkspace(workspaceID, templatePath, configFiles, payload) })
 		return true
 	}
 	// No backend wired — mark failed so the workspace doesn't linger in
@@ -275,13 +275,13 @@ func (h *WorkspaceHandler) RestartWorkspaceAutoOpts(ctx context.Context, workspa
 	if h.cpProv != nil {
 		h.cpStopWithRetry(ctx, workspaceID, "RestartWorkspaceAuto")
 		// resetClaudeSession is Docker-only — CP has no session state to clear.
-		go h.provisionWorkspaceCP(workspaceID, templatePath, configFiles, payload)
+		h.goAsync(func() { h.provisionWorkspaceCP(workspaceID, templatePath, configFiles, payload) })
 		return true
 	}
 	if h.provisioner != nil {
 		// Docker.Stop has no retry — see docstring rationale.
 		h.provisioner.Stop(ctx, workspaceID)
-		go h.provisionWorkspaceOpts(workspaceID, templatePath, configFiles, payload, resetClaudeSession)
+		h.goAsync(func() { h.provisionWorkspaceOpts(workspaceID, templatePath, configFiles, payload, resetClaudeSession) })
 		return true
 	}
 	// No backend wired — same shape as provisionWorkspaceAuto's no-backend

workspace-server/internal/handlers/workspace_provision_auto_test.go

@@ -144,6 +144,7 @@ func TestProvisionWorkspaceAuto_RoutesToCPWhenSet(t *testing.T) {
 	rec := &trackingCPProv{startErr: errors.New("simulated CP rejection")}
 	bcast := &concurrentSafeBroadcaster{}
 	h := NewWorkspaceHandler(bcast, nil, "http://localhost:8080", t.TempDir())
+	waitForHandlerAsyncBeforeDBCleanup(t, h)
 	h.SetCPProvisioner(rec)
 
 	wsID := "ws-routes-to-cp-0123456789abcdef"
@@ -595,6 +596,7 @@ func TestRestartWorkspaceAuto_RoutesToCPWhenSet(t *testing.T) {
 
 	// Mock DB so cpStopWithRetry can run without a real Postgres.
 	mock := setupTestDB(t)
+	waitForHandlerAsyncBeforeDBCleanup(t, h)
 	mock.MatchExpectationsInOrder(false)
 	// provisionWorkspaceCP runs in the goroutine and will hit secrets
 	// SELECTs + UPDATE workspace as failed (we make CP Start return
@@ -670,6 +672,7 @@ func TestRestartWorkspaceAuto_RoutesToDockerWhenOnlyDocker(t *testing.T) {
 
 	bcast := &concurrentSafeBroadcaster{}
 	h := NewWorkspaceHandler(bcast, nil, "http://localhost:8080", t.TempDir())
+	waitForHandlerAsyncBeforeDBCleanup(t, h)
 	stub := &stoppingLocalProv{}
 	h.provisioner = stub
 

workspace-server/internal/handlers/workspace_provision_test.go

@@ -2,6 +2,7 @@ package handlers
 
 import (
 	"context"
+	"database/sql"
 	"fmt"
 	"net/http"
 	"os"
@@ -634,6 +635,11 @@ func TestSeedInitialMemories_EmptyMemoriesNil(t *testing.T) {
 // ==================== buildProvisionerConfig ====================
 
 func TestBuildProvisionerConfig_BasicFields(t *testing.T) {
+	mock := setupTestDB(t)
+	mock.ExpectQuery(`SELECT COALESCE\(workspace_dir`).
+		WithArgs("ws-basic").
+		WillReturnRows(sqlmock.NewRows([]string{"workspace_dir", "workspace_access"}).AddRow("", "none"))
+
 	broadcaster := newTestBroadcaster()
 	tmpDir := t.TempDir()
 	handler := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", tmpDir)
@@ -678,6 +684,14 @@ func TestBuildProvisionerConfig_BasicFields(t *testing.T) {
 }
 
 func TestBuildProvisionerConfig_WorkspacePathFromEnv(t *testing.T) {
+	mock := setupTestDB(t)
+	mock.ExpectQuery(`SELECT COALESCE\(workspace_dir`).
+		WithArgs("ws-env").
+		WillReturnError(sql.ErrNoRows)
+	mock.ExpectQuery(`SELECT digest FROM runtime_image_pins`).
+		WithArgs("claude-code").
+		WillReturnError(sql.ErrNoRows)
+
 	broadcaster := newTestBroadcaster()
 	handler := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
 

workspace-server/internal/provisioner/provisioner.go

@@ -481,6 +481,22 @@ func (p *Provisioner) Start(ctx context.Context, cfg WorkspaceConfig) (string, e
 		return "", fmt.Errorf("failed to create container: %w", err)
 	}
 
+	// Seed /configs before the entrypoint starts. molecule-runtime reads
+	// /configs/config.yaml immediately; post-start copy races fast runtimes
+	// into a FileNotFoundError crash loop.
+	if cfg.TemplatePath != "" {
+		if err := p.CopyTemplateToContainer(ctx, resp.ID, cfg.TemplatePath); err != nil {
+			_ = p.cli.ContainerRemove(ctx, resp.ID, container.RemoveOptions{Force: true})
+			return "", fmt.Errorf("failed to copy template to container %s before start: %w", name, err)
+		}
+	}
+	if len(cfg.ConfigFiles) > 0 {
+		if err := p.WriteFilesToContainer(ctx, resp.ID, cfg.ConfigFiles); err != nil {
+			_ = p.cli.ContainerRemove(ctx, resp.ID, container.RemoveOptions{Force: true})
+			return "", fmt.Errorf("failed to write config files to container %s before start: %w", name, err)
+		}
+	}
+
 	if err := p.cli.ContainerStart(ctx, resp.ID, container.StartOptions{}); err != nil {
 		// Clean up created container on start failure
 		_ = p.cli.ContainerRemove(ctx, resp.ID, container.RemoveOptions{Force: true})
@@ -496,20 +512,6 @@ func (p *Provisioner) Start(ctx context.Context, cfg WorkspaceConfig) (string, e
 	// /configs and /workspace, then drops to agent via gosu). No per-start
 	// chown needed here.
 
-	// Copy template files into /configs if TemplatePath is set
-	if cfg.TemplatePath != "" {
-		if err := p.CopyTemplateToContainer(ctx, resp.ID, cfg.TemplatePath); err != nil {
-			log.Printf("Provisioner: warning — failed to copy template to container %s: %v", name, err)
-		}
-	}
-
-	// Write generated config files into /configs if ConfigFiles is set
-	if len(cfg.ConfigFiles) > 0 {
-		if err := p.WriteFilesToContainer(ctx, resp.ID, cfg.ConfigFiles); err != nil {
-			log.Printf("Provisioner: warning — failed to write config files to container %s: %v", name, err)
-		}
-	}
-
 	// Resolve the host-mapped port. Retry inspect up to 3 times if Docker hasn't
 	// bound the ephemeral port yet (rare race under heavy load).
 	hostURL := InternalURL(cfg.WorkspaceID) // fallback to Docker-internal

workspace-server/internal/provisioner/provisioner_test.go

@@ -62,6 +62,24 @@ func TestValidateConfigSource_TemplateIsDirName(t *testing.T) {
 	}
 }
 
+func TestStartSeedsConfigsBeforeContainerStart(t *testing.T) {
+	src, err := os.ReadFile("provisioner.go")
+	if err != nil {
+		t.Fatalf("read provisioner.go: %v", err)
+	}
+	text := string(src)
+	copyTemplate := strings.Index(text, "p.CopyTemplateToContainer(ctx, resp.ID, cfg.TemplatePath)")
+	writeFiles := strings.Index(text, "p.WriteFilesToContainer(ctx, resp.ID, cfg.ConfigFiles)")
+	start := strings.Index(text, "p.cli.ContainerStart(ctx, resp.ID, container.StartOptions{})")
+
+	if copyTemplate < 0 || writeFiles < 0 || start < 0 {
+		t.Fatalf("expected Start to copy template, write config files, and start container")
+	}
+	if copyTemplate >= start || writeFiles >= start {
+		t.Fatalf("config seeding must happen before ContainerStart: copyTemplate=%d writeFiles=%d start=%d", copyTemplate, writeFiles, start)
+	}
+}
+
 // baseHostConfig returns a fresh HostConfig with typical pre-tier binds,
 // mimicking what Start() builds before calling ApplyTierConfig.
 func baseHostConfig(pluginsPath string) *container.HostConfig {

workspace-server/internal/registry/access_test.go

@@ -14,8 +14,9 @@ func setupMockDB(t *testing.T) sqlmock.Sqlmock {
 	if err != nil {
 		t.Fatalf("sqlmock: %v", err)
 	}
+	prevDB := db.DB
 	db.DB = mockDB
-	t.Cleanup(func() { mockDB.Close() })
+	t.Cleanup(func() { mockDB.Close(); db.DB = prevDB })
 	return mock
 }
 

workspace-server/internal/registry/healthsweep_test.go

@@ -31,8 +31,9 @@ func setupTestDB(t *testing.T) sqlmock.Sqlmock {
 	if err != nil {
 		t.Fatalf("failed to create sqlmock: %v", err)
 	}
+	prevDB := db.DB
 	db.DB = mockDB
-	t.Cleanup(func() { mockDB.Close() })
+	t.Cleanup(func() { mockDB.Close(); db.DB = prevDB })
 	return mock
 }
 

workspace-server/internal/registry/hibernation_test.go

@@ -17,8 +17,9 @@ func setupHibernationMock(t *testing.T) sqlmock.Sqlmock {
 	if err != nil {
 		t.Fatalf("sqlmock.New: %v", err)
 	}
+	prevDB := db.DB
 	db.DB = mockDB
-	t.Cleanup(func() { mockDB.Close() })
+	t.Cleanup(func() { mockDB.Close(); db.DB = prevDB })
 	return mock
 }
 

workspace-server/internal/registry/liveness_test.go

@@ -18,8 +18,9 @@ func setupLivenessTestDB(t *testing.T) sqlmock.Sqlmock {
 	if err != nil {
 		t.Fatalf("failed to create sqlmock: %v", err)
 	}
+	prevDB := db.DB
 	db.DB = mockDB
-	t.Cleanup(func() { mockDB.Close() })
+	t.Cleanup(func() { mockDB.Close(); db.DB = prevDB })
 	return mock
 }
 

workspace-server/internal/scheduler/scheduler_test.go

@@ -24,8 +24,9 @@ func setupTestDB(t *testing.T) sqlmock.Sqlmock {
 	if err != nil {
 		t.Fatalf("failed to create sqlmock: %v", err)
 	}
+	prevDB := db.DB
 	db.DB = mockDB
-	t.Cleanup(func() { mockDB.Close() })
+	t.Cleanup(func() { mockDB.Close(); db.DB = prevDB })
 	return mock
 }