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>
This commit is contained in:
Jesse_Chen
2026-08-19 19:37:02 +08:00
parent c38f11dbd3
commit 7d667fecbf
17 changed files with 487 additions and 89 deletions
+2
View File
@@ -37,6 +37,7 @@ import type { AgentExecutionReceipt, WorkflowReceipt } from "@/lib/consultation-
import {
AGENT_MAX_STEPS,
AGENT_TIMEOUT_MS,
consultationGenerationSettings,
createConsultationAgentContext,
consultationModelStepTelemetry,
consultationStepBudgetReceipt,
@@ -653,6 +654,7 @@ export async function POST(request: Request) {
maxSteps: AGENT_MAX_STEPS,
abortSignal: agentAbortSignal,
hooks,
...consultationGenerationSettings(selectedModel.model),
};
const workflowReceipt: WorkflowReceipt = consultationMode === "general_no_birth_time"
? {