feat: convert AM516 lead times to workdays

capabilities/am516-delivery-prediction/docs/AM516自然日转工作日需求说明_给AR836_20260902.md

@@ -5,6 +5,8 @@
 **日期**：2026-09-02
 **目的**：将 AM516 交期预测输出的自然日转换为工作日，并据此得到最终交货日期。
 
+**当前临时处理**：因 AR836 排期较晚，AM516 飞书机器人先在 API 返回后的输出层执行同一换算；不修改 AR836 API 原始数据。待 API 正式提供工作日口径后，应移除本地临时换算，避免重复转换。
+
 ## 一、需求背景
 
 AM516 当前输出的是自然日交期。销售希望得到工作日口径的交期，即：

capabilities/am516-delivery-prediction/docs/acceptance_samples.md

@@ -14,6 +14,7 @@ Expected:
 
 - model parses successfully;
 - quantity is accepted;
+- the bot immediately replies with `👀` after the valid trigger is accepted and before the API query starts;
 - the controlled script uses the macOS system trust store and keeps TLS verification enabled;
 - no temporary TLS-bypass parameter is required for the normal happy path;
 - API script runs;
@@ -39,6 +40,18 @@ Expected:
 - record-table columns follow this order: 序号、记录时间、型号、推荐类型、差异项、API状态、AM516预测交期、可用库存、主导因素;
 - unavailable candidates remain in their original rule order and are recorded as `❌ 不存在` with unavailable result fields shown as `—`;
 
+## Sample 1B | Natural Days To Workdays
+
+Rules and expected results:
+
+- treat `AM516总交期`, or numeric `总交期` when the AM516 field is absent, as the original natural-day lead time `N`;
+- convert `N` with the approved quotient-and-remainder rule, including `r = 4` as one rest day and `r = 0` as no remainder workday;
+- exclude the local query date itself, then count the converted workdays using the configured China statutory workday calendar;
+- statutory holidays are excluded and official makeup weekend workdays are included;
+- for a query date of `2026-09-02`, `31` natural days convert to `22` workdays and produce `2026-10-09`;
+- output `2026-10-09（原始31个自然日，折算22个工作日）` instead of adding a separate National Day exception;
+- when counting reaches an unconfigured calendar year, do not silently fall back to a Monday-Friday estimate.
+
 ## Sample 1A | Continue With Other Candidates
 
 Preconditions:
@@ -59,6 +72,7 @@ is not required.
 
 Expected:
 
+- the bot immediately replies with `👀` after the continuation and active-context gates pass;
 - the bot reuses the active model and quantity only for that same sender and chat;
 - the bot queries candidate positions 5-8 in the unchanged rule order;
 - the original model and candidate positions 1-4 are not queried or displayed again;
@@ -83,6 +97,7 @@ eRob110H160I-FHM-18ET[V6]
 Expected:
 
 - bot stays silent;
+- no acknowledgement emoji is sent;
 - no API call is made;
 - no record is appended.
 

capabilities/am516-delivery-prediction/docs/runbook.md

@@ -8,20 +8,22 @@
 4. Confirm a separate trusted AR51 approval record explicitly covers `api.zeroerr-agent.com`, the AM516 use case, and API-key use.
 5. If that domain-and-permission record is absent, stop before any outbound request; a general functional-test approval is insufficient by itself.
 6. Use model recommendation rules to generate the complete ordered internal candidate pool.
-7. Run the controlled script for the original model baseline and only the first four candidate models.
-8. Summarize the current batch, state how many candidates remain, and invite the same sender to ask naturally for more when candidates remain; exact wording is not required.
-9. Append a non-secret record.
-10. Return Feishu-friendly text with the fixed disclaimer.
+7. Immediately reply with `👀` to acknowledge the valid request.
+8. Run the controlled script for the original model baseline and only the first four candidate models.
+9. Convert each numeric natural-day lead time to workdays with the approved quotient-and-remainder rule, then count those workdays from the local query date through the configured China statutory workday calendar. The query date itself is excluded.
+10. Summarize the current batch, including the original natural days, converted workdays, and calculated delivery date; state how many candidates remain and invite the same sender to ask naturally for more when candidates remain.
+11. Append a non-secret record.
+12. Return Feishu-friendly text with the fixed disclaimer.
 
 ## Candidate Continuation
 
 1. Accept a clear request for more candidates only from the same sender in the same Feishu chat as the active initial query. Equivalent expressions such as `还有吗`、`有没有别的`、`再推荐几个`、`继续`、`下一批` or `more candidates` are valid; no exact phrase is required.
 2. The in-memory continuation context expires after six hours and is cleared by a bridge restart. If no matching context exists, stay silent and require a new complete model-and-quantity query.
-3. Query the next four unqueried rule candidates; do not re-query the original baseline or any earlier candidate.
+3. Immediately reply with `👀`, then query the next four unqueried rule candidates; do not re-query the original baseline or any earlier candidate.
 4. Missing or unsupported candidates still consume their rule-order positions and remain under `不可用候选`.
 5. Append one record block for the models queried in this continuation batch, then state whether more candidates remain.
 6. A new complete model-and-quantity request replaces the earlier continuation context for that sender and chat.
-7. Keep the dual gate of continuation intent plus valid context: unrelated text such as `more interesting` or `继续查询英语例句` must not trigger the old query.
+7. Keep the dual gate of continuation intent plus valid context: unrelated text such as `more interesting` or `继续查询英语例句` must not trigger the old query or acknowledgement.
 
 ## Approved Script