fix(status-cards): spell out the summary sentinels and the failure path in update tasks

An update task told any assigned summarizer to preserve the Summarizer's
STATUS and SUMMARY-DRAFT sentinels without defining them. A non-built-in
summarizer searched for the format for minutes, including other runs' local
files. State the exact lines, that the PUT body is plain Markdown, and that a
summarizer that cannot produce a summary comments and blocks the task so the
card keeps its previous summary.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

server/src/__tests__/status-cards.test.ts

@@ -500,6 +500,11 @@ describeEmbeddedPostgres("status card routes", () => {
     expect(res.body.enqueued).toBe(true);
     // The queued refresh carries the card's page, so the requester can link it instead of waiting for the summary.
     expect(res.body.card.href).toBe(`/${company.issuePrefix}/status/${card.id}`);
+    // Any assigned summarizer, not only the built-in one, gets the full write-back and failure contract inline.
+    const [generation] = await db.select().from(issues).where(eq(issues.id, res.body.generatingIssue.id));
+    expect(generation?.description).toContain("put the final Markdown between a `<<<SUMMARY-DRAFT>>>` line and a `<<<END-SUMMARY-DRAFT>>>` line");
+    expect(generation?.description).toContain("there is no other format to look up");
+    expect(generation?.description).toContain("comment the reason on this task and set it to blocked");
   });
 
   it("requires tasks:assign for mutations", async () => {

server/src/services/status-cards.ts

@@ -95,7 +95,7 @@ function updateDescription(input: {
   previousSummary: string | null;
   snapshot: CompanySearchIssueSummary[];
 }) {
-  const mechanical = `Return the completed Markdown through \`PUT /api/status-cards/${input.card.id}/summary\` with \`generationIssueId\`, a short non-empty \`changeSummary\`, and the model id. Do not call issue-list endpoints. Preserve the streaming STATUS and <<<SUMMARY-DRAFT>>> sentinels used by the Summarizer. Issues the Markdown references by identifier (e.g. ABC-123) or issue link automatically join the card's watched set, so reference an issue only when the board should keep tracking it.`;
+  const mechanical = `Return the completed Markdown through \`PUT /api/status-cards/${input.card.id}/summary\` with \`generationIssueId\`, a short non-empty \`changeSummary\`, and the model id. Do not call issue-list endpoints. While you work, write short plain-text \`STATUS:\` lines; before the write, put the final Markdown between a \`<<<SUMMARY-DRAFT>>>\` line and a \`<<<END-SUMMARY-DRAFT>>>\` line in your reply text. These lines only drive the card's live preview; the PUT body is the plain Markdown, and there is no other format to look up. If you cannot produce a summary from what you can read, comment the reason on this task and set it to blocked; the card then keeps its previous summary and shows the failure. Issues the Markdown references by identifier (e.g. ABC-123) or issue link automatically join the card's watched set, so reference an issue only when the board should keep tracking it.`;
   // The card prompt is the board's single standing request: it already says
   // what to watch and how the update should read, so it doubles as the
   // summary instructions — there is no separate default prompt to append to