fix(consult): treat pinched answers as failed and restore reply actions

Incomplete Flash generations were billed as completed consultations. Fail
those runs, keep the partial text, and reuse the rectification like/copy/rerun
bar on ordinary chat replies.

Co-authored-by: Cursor <cursoragent@cursor.com>

frontend/tests/consultation-workflow-contract.test.ts

@@ -65,6 +65,15 @@ test("the model step budget and the wall-clock budget are declared as one pair",
   assert.doesNotMatch(route, /AbortSignal\.timeout\(\d/);
 });
 
+test("consult streams cap visible output and disable thinking instead of sharing the token budget with hidden reasoning", () => {
+  assert.match(tools, /export const CONSULTATION_MAX_OUTPUT_TOKENS = 8192;/);
+  assert.match(tools, /function consultationGenerationSettings/);
+  assert.match(tools, /thinking: \{ type: "disabled"/);
+  assert.match(tools, /maxOutputTokens: CONSULTATION_MAX_OUTPUT_TOKENS/);
+  assert.match(route, /\.\.\.consultationGenerationSettings\(selectedModel\.model\)/);
+  assert.doesNotMatch(route, /maxOutputTokens:\s*\d/);
+});
+
 test("uses one runtime step append entry and no scattered hard-coded step cap", () => {
   assert.match(tools, /export function appendConsultationRuntimeStep/);
   assert.doesNotMatch(tools, /steps\.length\s*>=\s*32/);