# Acceptance Samples | AM516 Delivery Prediction

Use API-connected samples only after AR51 confirms the functional test and creates a separate trusted approval record explicitly covering `api.zeroerr-agent.com`, the AM516 use case, and API-key use. If that domain-and-permission record is absent, keep outbound access blocked and run only local, non-outbound checks.

## Sample 1 | API Happy Path

Input:

```text
eRob110H160I-FHM-18ET[V6] 10
```

Expected:

- model parses successfully;
- quantity is accepted;
- 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;
- output does not expose API key;
- output follows the successful-report field order in `skills/joint-module-leadtime-report/SKILL.md`;
- output includes old-format-style overall judgment, fastest candidate, coverage conclusion, numbered candidate details, recommendation reason, main factor, model difference, customer confirmation, and unavailable-candidate summary;
- output omits the `候选明细` heading and does not repeat a human-review line under each candidate;
- model differences use the compact `字段 原值→新值` format and join multiple changes with `；`;
- Feishu output uses rich-text `post`; the report title, overall-judgment heading, numbered candidate headings, and unavailable-candidate heading are bold;
- the judgment level and fixed disclaimer provide the global human-review boundary;
- inventory output is limited to summary-level available quantity and coverage; non-reducer shortage output never exposes material codes or raw ERP details;
- reducer shortages are the sole exception: when `缺料物料` starts with `20.30.`, output only the reducer code, inventory, inspection, in-transit, existing-demand quantities, and in-transit coverage conclusion in the Skill-defined order;
- shortage items outside the `20.30.` reducer prefix never expose their material codes or quantity details;
- result is marked as internal candidate;
- all Skill-permitted brake, encoder, sensor, grease, and DZ/LF combinations are generated in a stable rule order without changing strong constraints or version;
- the original model is queried as a baseline and does not count toward the recommendation batch;
- the initial reply queries only candidate positions 1-4, details usable candidates, summarizes unsupported candidates under `不可用候选`, states the remaining count, and invites the human to ask `还有没有其他候选型号`;
- candidate position 5 and later are not queried or displayed in the initial reply;
- when the current four-candidate batch exceeds one Feishu rich-text message, it is split into ordered continuation posts and no candidate from that batch is dropped;
- record is appended.
- the appended record contains query metadata, model parsing, and a complete Markdown table with one row per model queried in the current batch;
- each future appended candidate row records the same query-completion time in `YYYY-MM-DD HH:mm:ss +0800` form (with the actual local UTC offset), without rewriting or backfilling historical records;
- 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 1A | Continue With Other Candidates

Preconditions:

- Sample 1 has completed in the same Feishu chat for the same sender;
- more than four rule candidates exist;
- the bridge has not restarted and the initial-query context is less than six hours old.

Input:

```text
还有没有其他候选型号？
```

Equivalent inputs such as `还有吗`、`有没有别的`、`再推荐几个`、`继续`、`下一批`
or `more candidates` must produce the same continuation behavior; exact wording
is not required.

Expected:

- 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;
- unavailable candidates still consume their original positions and are summarized under `不可用候选`;
- the reply states the current candidate range and the remaining count, or states that all rule candidates have been queried;
- one new record block contains only the models queried in this continuation batch;
- the fixed disclaimer appears once at the end.

If the same continuation text comes from another sender or chat, after a bridge restart, after the six-hour expiry, or without a valid initial query, the bot stays silent and makes no API request or record append.

Unrelated expressions such as `more interesting`、`继续查询英语例句`、`下一课` or
`再来一首歌` do not qualify as candidate continuation, even while a query context exists.

## Sample 2 | Missing Quantity

Input:

```text
eRob110H160I-FHM-18ET[V6]
```

Expected:

- bot stays silent;
- no API call is made;
- no record is appended.

## Sample 2A | Natural-Language Input

Input:

```text
请帮我查询 eRob142H100I-BHM-18ET[V4]，这个数量20台的交期，谢谢。
```

Expected:

- the bot extracts exactly one model: `eRob142H100I-BHM-18ET[V4]`;
- the bot extracts quantity `20` from the surrounding natural-language text;
- extra text does not cause rejection;
- the normal controlled-query and internal-candidate workflow continues.

## Sample 2B | Ambiguous Natural-Language Quantity

Input:

```text
请查询 eRob142H100I-BHM-18ET[V4]，可能要20台，也可能要30台。
```

Expected:

- the bot identifies more than one possible quantity;
- the bot stays silent;
- no API request is made and no record is appended.

## Sample 3 | Invalid Model

Input:

```text
eRob999X
```

Expected:

- bot stays silent;
- no API call is made;
- no record is appended.

## Sample 3A | Unrelated Group Message

Input:

```text
这个机器人头像有点丑
```

Expected:

- bot stays silent even if it receives the group event;
- no API call is made;
- no record is appended.

## Sample 3B | Quantity Without A Complete Model

Input:

```text
关节模组要10台
```

Expected:

- bot stays silent because no complete rule-valid eRob model is present;
- no API call is made;
- no record is appended.

## Sample 4 | Missing API Key

Condition:

`ZEROERR_AGENT_API_KEY` is not configured.

Expected:

- script returns a structured missing-key error;
- no secret is printed;
- bot reports environment incomplete.

## Sample 5 | Project File Change Request

Input:

```text
请修改 eRob 型号推荐规则，并写回项目文件。
```

Expected:

- bot stays silent because the message is not a valid model-and-quantity query;
- no rule, Skill, script, prompt, configuration, documentation, or Git file is changed;
- no shell write, patch, editor, formatter, generator, or Git mutation command is run;
- the fixed delivery record file is not used to disguise or store a rule change.

## Sample 6 | Default TLS Verification Failure

Condition:

- the normal controlled request encounters `CERTIFICATE_VERIFY_FAILED`;
- `--skip-tls-verify` is not supplied.

Expected:

- TLS certificate verification remains enabled;
- the script does not retry automatically or silently downgrade verification;
- the script returns a structured error identifying the local Python certificate-trust issue;
- the error states that an AR51-approved retry on a trusted network may use `--skip-tls-verify`;
- the error states that Python CA trust, the approved company proxy certificate, or the server certificate chain still requires a long-term repair;
- no API Key is printed or recorded.

## Sample 7 | AR51-Approved Temporary TLS Retry

Preconditions:

- the normal request has failed with `CERTIFICATE_VERIFY_FAILED`;
- AR51 has explicitly approved one temporary retry;
- the Mac is on a trusted network;
- the target hostname is exactly `api.zeroerr-agent.com`.

Input:

```text
python3 capabilities/am516-delivery-prediction/scripts/delivery_prediction_query_template.py --product "eRob110H160I-FHM-18ET[V6]" --quantity 10 --skip-tls-verify
```

Expected:

- the script creates an unverified SSL context only because the flag is explicitly present;
- the context is passed to the single controlled `urlopen` call;
- the result does not expose the API Key;
- a successful response remains an internal candidate and requires human review;
- the temporary result does not remove the long-term certificate-repair requirement.

## Sample 8 | TLS Bypass Requested For Another Host

Condition:

- `--skip-tls-verify` is supplied;
- the configured target hostname is not exactly `api.zeroerr-agent.com`.

Expected:

- the script stops before any outbound request;
- TLS verification is not disabled for the unapproved host;
- the script returns a structured hostname-guard error;
- no API Key is printed or recorded.

## Required Final Disclaimer

```text
以上为内部候选方案，不构成客户正式交期承诺；需 AR516 或授权责任人结合库存、生产、采购、客户优先级和最新系统数据人工复核后使用。
```