fix(scholars): improve validation, fix delete, add status badges

- Extract scholar ID parsing to dedicated module with robust URL
  handling (trailing slashes, fragments, extra query params, encoded
  characters) and per-token error feedback showing why each invalid
  entry was skipped
- Wrap delete_scholar DB commit in IntegrityError handler so cascade
  failures return a proper API error instead of 500
- Add ScholarStatusBadges component showing Pending/Failed/Partial/OK
  badges on scholar rows based on baseline_completed and last_run_status
- Show Pending badge in ScholarSettingsModal for unscraped scholars
- Surface failed_count and partial_count in dashboard latest run summary
  and recent run list items
- Extend backend validator tests with edge cases (empty, whitespace,
  unicode, URL-as-ID)
- Add integration tests for DELETE 404, DELETE with cascade, and POST
  with corrupted scholar_id
- Add comprehensive frontend tests for parsing logic and component
  behavior

frontend/src/features/scholars/components/ScholarBatchAdd.test.ts

@@ -2,10 +2,144 @@
 import { describe, expect, it } from "vitest";
 import { mount } from "@vue/test-utils";
 import ScholarBatchAdd from "./ScholarBatchAdd.vue";
+import {
+  parseScholarIds,
+  parseScholarTokens,
+  extractScholarIdFromUrl,
+  validateTokenAsId,
+} from "./scholar-batch-parsing";
 
 const defaultProps = { saving: false, loading: false };
 
-describe("ScholarBatchAdd", () => {
+describe("parseScholarIds (unit)", () => {
+  it("parses a single bare ID", () => {
+    expect(parseScholarIds("A-UbBTPM15wL")).toEqual(["A-UbBTPM15wL"]);
+  });
+
+  it("parses multiple IDs separated by commas", () => {
+    expect(parseScholarIds("A-UbBTPM15wL, B-UbBTPM15wL")).toEqual(["A-UbBTPM15wL", "B-UbBTPM15wL"]);
+  });
+
+  it("deduplicates IDs", () => {
+    expect(parseScholarIds("A-UbBTPM15wL\nA-UbBTPM15wL")).toEqual(["A-UbBTPM15wL"]);
+  });
+
+  it("extracts ID from standard Google Scholar URL", () => {
+    expect(parseScholarIds("https://scholar.google.com/citations?hl=en&user=A-UbBTPM15wL")).toEqual(["A-UbBTPM15wL"]);
+  });
+
+  it("extracts ID from URL with trailing slash", () => {
+    expect(parseScholarIds("https://scholar.google.com/citations?user=A-UbBTPM15wL/")).toEqual(["A-UbBTPM15wL"]);
+  });
+
+  it("extracts ID from URL with fragment", () => {
+    expect(parseScholarIds("https://scholar.google.com/citations?user=A-UbBTPM15wL#section")).toEqual(["A-UbBTPM15wL"]);
+  });
+
+  it("extracts ID from URL with extra query params", () => {
+    expect(parseScholarIds("https://scholar.google.com/citations?hl=en&user=A-UbBTPM15wL&view_op=list_works&sortby=pubdate")).toEqual(["A-UbBTPM15wL"]);
+  });
+
+  it("handles URL-encoded characters in non-ID parts", () => {
+    expect(parseScholarIds("https://scholar.google.com/citations?hl=en&user=A-UbBTPM15wL&label=%E4%B8%AD%E6%96%87")).toEqual(["A-UbBTPM15wL"]);
+  });
+
+  it("rejects malformed IDs (too short)", () => {
+    expect(parseScholarIds("ABC123")).toEqual([]);
+  });
+
+  it("rejects malformed IDs (too long)", () => {
+    expect(parseScholarIds("ABCDEF1234567")).toEqual([]);
+  });
+
+  it("rejects IDs with special characters", () => {
+    expect(parseScholarIds("ABCDEF12345!")).toEqual([]);
+  });
+
+  it("rejects IDs with embedded whitespace", () => {
+    expect(parseScholarIds("ABC DEF12345")).toEqual([]);
+  });
+
+  it("handles mixed valid and invalid tokens", () => {
+    expect(parseScholarIds("A-UbBTPM15wL, invalid, B-UbBTPM15wL")).toEqual(["A-UbBTPM15wL", "B-UbBTPM15wL"]);
+  });
+
+  it("returns empty array for empty string", () => {
+    expect(parseScholarIds("")).toEqual([]);
+  });
+
+  it("returns empty array for whitespace only", () => {
+    expect(parseScholarIds("   ")).toEqual([]);
+  });
+});
+
+describe("extractScholarIdFromUrl", () => {
+  it("returns null for non-URL strings", () => {
+    expect(extractScholarIdFromUrl("not-a-url")).toBeNull();
+  });
+
+  it("returns null for URL without user param", () => {
+    expect(extractScholarIdFromUrl("https://scholar.google.com/citations?hl=en")).toBeNull();
+  });
+
+  it("extracts from URL with trailing slashes", () => {
+    expect(extractScholarIdFromUrl("https://scholar.google.com/citations?user=A-UbBTPM15wL///")).toBe("A-UbBTPM15wL");
+  });
+
+  it("strips fragment before parsing", () => {
+    expect(extractScholarIdFromUrl("https://scholar.google.com/citations?user=A-UbBTPM15wL#foo")).toBe("A-UbBTPM15wL");
+  });
+
+  it("returns null when user param is invalid length", () => {
+    expect(extractScholarIdFromUrl("https://scholar.google.com/citations?user=short")).toBeNull();
+  });
+});
+
+describe("validateTokenAsId", () => {
+  it("returns null for valid 12-char ID", () => {
+    expect(validateTokenAsId("ABCDEF123456")).toBeNull();
+  });
+
+  it("detects wrong length", () => {
+    expect(validateTokenAsId("ABC")).toContain("12 characters");
+  });
+
+  it("detects invalid characters", () => {
+    expect(validateTokenAsId("ABCDEF12345!")).toContain("invalid characters");
+  });
+
+  it("detects whitespace", () => {
+    expect(validateTokenAsId("ABC DEF12345")).toContain("whitespace");
+  });
+
+  it("detects empty input", () => {
+    expect(validateTokenAsId("")).toContain("empty");
+  });
+});
+
+describe("parseScholarTokens (per-token errors)", () => {
+  it("marks invalid tokens with error messages", () => {
+    const tokens = parseScholarTokens("A-UbBTPM15wL, short, B-UbBTPM15wL");
+    expect(tokens).toHaveLength(3);
+    expect(tokens[0].id).toBe("A-UbBTPM15wL");
+    expect(tokens[0].error).toBeNull();
+    expect(tokens[1].id).toBeNull();
+    expect(tokens[1].error).toContain("12 characters");
+    expect(tokens[2].id).toBe("B-UbBTPM15wL");
+  });
+
+  it("marks duplicate tokens", () => {
+    const tokens = parseScholarTokens("A-UbBTPM15wL, A-UbBTPM15wL");
+    expect(tokens[1].error).toBe("duplicate");
+  });
+
+  it("marks bad URL tokens", () => {
+    const tokens = parseScholarTokens("https://scholar.google.com/citations?hl=en");
+    expect(tokens[0].error).toContain("could not extract");
+  });
+});
+
+describe("ScholarBatchAdd (component)", () => {
   it("renders the heading and input", () => {
     const wrapper = mount(ScholarBatchAdd, { props: defaultProps });
     expect(wrapper.text()).toContain("Add Scholar Profiles");
@@ -73,4 +207,18 @@ describe("ScholarBatchAdd", () => {
     const wrapper = mount(ScholarBatchAdd, { props: { ...defaultProps, saving: true } });
     expect(wrapper.text()).toContain("Adding...");
   });
+
+  it("shows validation errors for invalid tokens", async () => {
+    const wrapper = mount(ScholarBatchAdd, { props: defaultProps });
+    await wrapper.find("textarea").setValue("A-UbBTPM15wL, bad!");
+    const errors = wrapper.find("[data-testid='validation-errors']");
+    expect(errors.exists()).toBe(true);
+  });
+
+  it("shows skipped count alongside valid count", async () => {
+    const wrapper = mount(ScholarBatchAdd, { props: defaultProps });
+    await wrapper.find("textarea").setValue("A-UbBTPM15wL, tooshort");
+    expect(wrapper.text()).toContain("1 valid");
+    expect(wrapper.text()).toContain("1 skipped");
+  });
 });

frontend/src/features/scholars/components/ScholarBatchAdd.vue

@@ -3,6 +3,7 @@ import { computed, ref } from "vue";
 import AppButton from "@/components/ui/AppButton.vue";
 import AppCard from "@/components/ui/AppCard.vue";
 import AppHelpHint from "@/components/ui/AppHelpHint.vue";
+import { parseScholarTokens } from "./scholar-batch-parsing";
 
 defineProps<{
   saving: boolean;
@@ -15,38 +16,13 @@ const emit = defineEmits<{
 
 const scholarBatchInput = ref("");
 
-const SCHOLAR_ID_PATTERN = /^[a-zA-Z0-9_-]{12}$/;
-const URL_USER_PARAM_PATTERN = /(?:\?|&)user=([a-zA-Z0-9_-]{12})(?:&|#|$)/i;
-
-function parseScholarIds(raw: string): string[] {
-  const ordered: string[] = [];
-  const seen = new Set<string>();
-  const tokens = raw.split(/[\s,;]+/).map((v) => v.trim()).filter((v) => v.length > 0);
-  for (const token of tokens) {
-    let candidate: string | null = null;
-    if (SCHOLAR_ID_PATTERN.test(token)) candidate = token;
-    if (!candidate) {
-      const directParamMatch = token.match(URL_USER_PARAM_PATTERN);
-      if (directParamMatch) candidate = directParamMatch[1];
-    }
-    if (!candidate && token.includes("scholar.google")) {
-      try {
-        const parsed = new URL(token);
-        const userParam = parsed.searchParams.get("user");
-        if (userParam && SCHOLAR_ID_PATTERN.test(userParam)) candidate = userParam;
-      } catch (_error) { /* Ignore non-URL tokens. */ }
-    }
-    if (!candidate || seen.has(candidate)) continue;
-    seen.add(candidate);
-    ordered.push(candidate);
-  }
-  return ordered;
-}
-
-const parsedBatchCount = computed(() => parseScholarIds(scholarBatchInput.value).length);
+const parsedTokens = computed(() => parseScholarTokens(scholarBatchInput.value));
+const validIds = computed(() => parsedTokens.value.filter((t) => t.id !== null));
+const invalidTokens = computed(() => parsedTokens.value.filter((t) => t.id === null));
+const parsedBatchCount = computed(() => validIds.value.length);
 
 function onSubmit(): void {
-  const ids = parseScholarIds(scholarBatchInput.value);
+  const ids = validIds.value.map((t) => t.id!);
   if (ids.length > 0) {
     emit("add-scholars", ids);
     scholarBatchInput.value = "";
@@ -76,11 +52,33 @@ function onSubmit(): void {
         />
       </label>
 
-      <div class="flex flex-wrap items-center justify-between gap-2">
+      <div v-if="parsedTokens.length > 0" class="space-y-1">
         <p class="text-xs text-secondary">
-          Parsed IDs: <strong class="text-ink-primary">{{ parsedBatchCount }}</strong>
+          <strong class="text-ink-primary">{{ parsedBatchCount }}</strong> valid ID{{ parsedBatchCount === 1 ? "" : "s" }}
+          <template v-if="invalidTokens.length > 0">
+            · <span class="text-state-warning-text">{{ invalidTokens.length }} skipped</span>
+          </template>
         </p>
-        <AppButton type="submit" :disabled="saving || loading">
+        <ul v-if="invalidTokens.length > 0" class="space-y-0.5" data-testid="validation-errors">
+          <li
+            v-for="item in invalidTokens.slice(0, 5)"
+            :key="item.index"
+            class="text-xs text-state-warning-text"
+          >
+            #{{ item.index }}: {{ item.error }}
+            <code class="ml-1 break-all text-ink-muted">{{ item.raw.length > 60 ? item.raw.slice(0, 57) + "..." : item.raw }}</code>
+          </li>
+          <li v-if="invalidTokens.length > 5" class="text-xs text-state-warning-text">
+            +{{ invalidTokens.length - 5 }} more skipped
+          </li>
+        </ul>
+      </div>
+      <div v-else class="text-xs text-secondary">
+        Parsed IDs: <strong class="text-ink-primary">0</strong>
+      </div>
+
+      <div class="flex flex-wrap items-center justify-end gap-2">
+        <AppButton type="submit" :disabled="saving || loading || parsedBatchCount === 0">
           {{ saving ? "Adding..." : "Add scholars" }}
         </AppButton>
       </div>

frontend/src/features/scholars/components/ScholarSettingsModal.vue

@@ -47,7 +47,14 @@ function scholarPublicationsRoute(profile: ScholarProfile): { name: string; quer
           :image-url="scholar.profile_image_url"
         />
         <div class="min-w-0 space-y-1">
-          <p class="truncate text-sm font-semibold text-ink-primary">{{ scholarLabel(scholar) }}</p>
+          <p class="truncate text-sm font-semibold text-ink-primary">
+            {{ scholarLabel(scholar) }}
+            <span
+              v-if="!scholar.baseline_completed"
+              class="ml-1.5 inline-flex items-center rounded-full bg-amber-50 px-1.5 py-0.5 text-[10px] font-medium text-amber-700 ring-1 ring-inset ring-amber-600/20 dark:bg-amber-950 dark:text-amber-400 dark:ring-amber-400/20"
+              title="This scholar hasn't been scraped yet. Publications will appear after the next run."
+            >Pending</span>
+          </p>
           <p class="text-xs text-secondary">ID: <code>{{ scholar.scholar_id }}</code></p>
           <div class="flex flex-wrap items-center gap-3">
             <RouterLink :to="scholarPublicationsRoute(scholar)" class="link-inline text-xs">

frontend/src/features/scholars/components/ScholarStatusBadges.vue

@@ -0,0 +1,29 @@
+<script setup lang="ts">
+defineProps<{
+  baselineCompleted: boolean;
+  lastRunStatus: string | null;
+}>();
+</script>
+
+<template>
+  <span
+    v-if="!baselineCompleted"
+    class="ml-1.5 inline-flex items-center rounded-full bg-amber-50 px-1.5 py-0.5 text-[10px] font-medium text-amber-700 ring-1 ring-inset ring-amber-600/20 dark:bg-amber-950 dark:text-amber-400 dark:ring-amber-400/20"
+    title="This scholar hasn't been scraped yet. Publications will appear after the next run."
+  >Pending</span>
+  <span
+    v-if="lastRunStatus === 'failed'"
+    class="ml-1.5 inline-flex items-center rounded-full bg-red-50 px-1.5 py-0.5 text-[10px] font-medium text-red-700 ring-1 ring-inset ring-red-600/20 dark:bg-red-950 dark:text-red-400 dark:ring-red-400/20"
+    title="The last scrape run for this scholar failed."
+  >Failed</span>
+  <span
+    v-else-if="lastRunStatus === 'partial'"
+    class="ml-1.5 inline-flex items-center rounded-full bg-amber-50 px-1.5 py-0.5 text-[10px] font-medium text-amber-700 ring-1 ring-inset ring-amber-600/20 dark:bg-amber-950 dark:text-amber-400 dark:ring-amber-400/20"
+    title="The last scrape run for this scholar completed with partial results."
+  >Partial</span>
+  <span
+    v-else-if="lastRunStatus === 'success'"
+    class="ml-1.5 inline-flex items-center rounded-full bg-green-50 px-1.5 py-0.5 text-[10px] font-medium text-green-700 ring-1 ring-inset ring-green-600/20 dark:bg-green-950 dark:text-green-400 dark:ring-green-400/20"
+    title="The last scrape run for this scholar completed successfully."
+  >OK</span>
+</template>

frontend/src/features/scholars/components/scholar-batch-parsing.ts

@@ -0,0 +1,76 @@
+const SCHOLAR_ID_PATTERN = /^[a-zA-Z0-9_-]{12}$/;
+
+export interface ParsedToken {
+  index: number;
+  raw: string;
+  id: string | null;
+  error: string | null;
+}
+
+export function extractScholarIdFromUrl(token: string): string | null {
+  const cleaned = token.replace(/\/+$/, "").replace(/#.*$/, "");
+  try {
+    const parsed = new URL(cleaned);
+    const userParam = parsed.searchParams.get("user");
+    if (!userParam) return null;
+    const decoded = decodeURIComponent(userParam).trim();
+    if (SCHOLAR_ID_PATTERN.test(decoded)) return decoded;
+    return null;
+  } catch {
+    return null;
+  }
+}
+
+export function validateTokenAsId(token: string): string | null {
+  const trimmed = token.trim();
+  if (!trimmed) return "empty input";
+  if (/\s/.test(trimmed)) return "contains whitespace";
+  if (trimmed.length !== 12) return `must be 12 characters (got ${trimmed.length})`;
+  if (!/^[a-zA-Z0-9_-]+$/.test(trimmed)) {
+    return "contains invalid characters (only a-z, A-Z, 0-9, _ and - allowed)";
+  }
+  return null;
+}
+
+export function parseScholarTokens(raw: string): ParsedToken[] {
+  const tokens = raw.split(/[\s,;]+/).map((v) => v.trim()).filter((v) => v.length > 0);
+  const results: ParsedToken[] = [];
+  const seen = new Set<string>();
+
+  for (let i = 0; i < tokens.length; i++) {
+    const token = tokens[i];
+
+    if (SCHOLAR_ID_PATTERN.test(token)) {
+      if (seen.has(token)) {
+        results.push({ index: i + 1, raw: token, id: null, error: "duplicate" });
+        continue;
+      }
+      seen.add(token);
+      results.push({ index: i + 1, raw: token, id: token, error: null });
+      continue;
+    }
+
+    if (token.includes("scholar.google") || token.startsWith("http")) {
+      const extracted = extractScholarIdFromUrl(token);
+      if (extracted) {
+        if (seen.has(extracted)) {
+          results.push({ index: i + 1, raw: token, id: null, error: "duplicate" });
+          continue;
+        }
+        seen.add(extracted);
+        results.push({ index: i + 1, raw: token, id: extracted, error: null });
+        continue;
+      }
+      results.push({ index: i + 1, raw: token, id: null, error: "could not extract scholar ID from URL" });
+      continue;
+    }
+
+    const reason = validateTokenAsId(token);
+    results.push({ index: i + 1, raw: token, id: null, error: reason ?? "invalid scholar ID" });
+  }
+  return results;
+}
+
+export function parseScholarIds(raw: string): string[] {
+  return parseScholarTokens(raw).filter((t) => t.id !== null).map((t) => t.id!);
+}

frontend/src/pages/DashboardPage.vue

@@ -494,6 +494,11 @@ watch(
                       <template v-else>
                         Processed {{ displayedLatestRun.scholar_count }} scholars and discovered
                         {{ displayedLatestRun.new_publication_count }} new publications.
+                        <template v-if="displayedLatestRun.failed_count > 0 || displayedLatestRun.partial_count > 0">
+                          <span class="text-state-warning-text">
+                            {{ displayedLatestRun.failed_count > 0 ? `${displayedLatestRun.failed_count} failed` : "" }}{{ displayedLatestRun.failed_count > 0 && displayedLatestRun.partial_count > 0 ? ", " : "" }}{{ displayedLatestRun.partial_count > 0 ? `${displayedLatestRun.partial_count} partial` : "" }}.
+                          </span>
+                        </template>
                       </template>
                     </p>
                   </div>
@@ -527,6 +532,9 @@ watch(
                         </div>
                         <span class="text-xs text-secondary">
                           {{ formatDate(run.start_dt) }} • {{ run.new_publication_count }} new
+                          <template v-if="run.failed_count > 0">
+                            • <span class="text-state-warning-text">{{ run.failed_count }} failed</span>
+                          </template>
                         </span>
                       </li>
                     </ul>

frontend/src/pages/ScholarsPage.vue

@@ -31,6 +31,7 @@ import ScholarAvatar from "@/features/scholars/components/ScholarAvatar.vue";
 import ScholarBatchAdd from "@/features/scholars/components/ScholarBatchAdd.vue";
 import ScholarNameSearch from "@/features/scholars/components/ScholarNameSearch.vue";
 import ScholarSettingsModal from "@/features/scholars/components/ScholarSettingsModal.vue";
+import ScholarStatusBadges from "@/features/scholars/components/ScholarStatusBadges.vue";
 import { ApiRequestError } from "@/lib/api/errors";
 import { useRunStatusStore } from "@/stores/run_status";
 
@@ -505,7 +506,10 @@ watch(
                     <div class="flex items-start gap-3">
                       <ScholarAvatar :label="item.display_name" :scholar-id="item.scholar_id" :image-url="item.profile_image_url" />
                       <div class="min-w-0 flex-1 space-y-1">
-                        <p class="truncate text-sm font-semibold text-ink-primary">{{ scholarLabel(item) }}</p>
+                        <p class="truncate text-sm font-semibold text-ink-primary">
+                          {{ scholarLabel(item) }}
+                          <ScholarStatusBadges :baseline-completed="item.baseline_completed" :last-run-status="item.last_run_status" />
+                        </p>
                         <div class="flex flex-wrap items-center gap-3">
                           <RouterLink :to="scholarPublicationsRoute(item)" class="link-inline text-xs">Publications</RouterLink>
                           <a :href="scholarProfileUrl(item.scholar_id)" target="_blank" rel="noreferrer" class="link-inline text-xs">Open profile</a>
@@ -529,7 +533,10 @@ watch(
                           <div class="flex items-start gap-3">
                             <ScholarAvatar :label="item.display_name" :scholar-id="item.scholar_id" :image-url="item.profile_image_url" />
                             <div class="grid min-w-0 gap-1">
-                              <strong class="truncate text-ink-primary">{{ scholarLabel(item) }}</strong>
+                              <strong class="truncate text-ink-primary">
+                                {{ scholarLabel(item) }}
+                                <ScholarStatusBadges :baseline-completed="item.baseline_completed" :last-run-status="item.last_run_status" />
+                              </strong>
                               <div class="flex flex-wrap items-center gap-3">
                                 <RouterLink :to="scholarPublicationsRoute(item)" class="link-inline text-xs">Publications</RouterLink>
                                 <a :href="scholarProfileUrl(item.scholar_id)" target="_blank" rel="noreferrer" class="link-inline text-xs">Open profile</a>