@delta-infra/cli 1.1.16 → 1.1.18

package/skills/delta-science/references/qe.md

@@ -1,65 +1,70 @@
-# Quantum ESPRESSO DFT 详细规则
+# Quantum ESPRESSO DFT reference
 
-QE 用于通过 Chemistry Gateway 执行可追踪的异步 Quantum ESPRESSO 工作流。agent 只接触
-Gateway/Science Server contract，不运行本地 `pw.x`，不调用内部 QE 容器，也不提交 shell
-命令、scheduler 脚本、`pseudo_dir`、`outdir` 或主机路径。
+Use QE to run traceable, asynchronous Quantum ESPRESSO workflows through Chemistry Gateway.
+The agent interacts only with the Gateway/Science Server contract: it does not run local `pw.x`,
+call internal QE containers, or submit shell commands, scheduler scripts, `pseudo_dir`, `outdir`
+or host paths.
 
-本 reference 对应 CLI 的真实工具为 `qe`。实际 `tools.name` 与 `tool_endpoints.name`
-必须逐字取自当前 CLI catalog。下列路径是 QE 服务契约，不是可直接访问的 URL，也不是
-可以自动改写的 endpoint 别名。
+The actual CLI tool for this reference is `qe`. Copy `tools.name` and `tool_endpoints.name`
+exactly from the current CLI catalogue. The paths below describe the QE service contract; they
+are not URLs to access directly or endpoint aliases that may be rewritten automatically.
 
-## 能力分组
+## Capability groups
 
-| 服务路径 | 作用 | 类型 |
+| Service path | Purpose | Type |
 | --- | --- | --- |
-| `/chem/qe/health`、`/healthz`、`/readyz` | 运行时、scheduler、存储和 PP 就绪 | 只读 |
-| `/chem/qe/v1/qe/workflow-types` | workflow catalog 和支持状态 | 只读 |
-| `/chem/qe/v1/pp-sets`、`/pp-locks/{digest}` | 已发布 PP profile/lock | 只读 |
-| `/chem/qe/v1/pp-sets:resolve` | 按 campaign 元素全集解析 PP 候选 | 只读/校验 |
-| `/chem/qe/v1/artifacts` | 上传、查询和下载结构/fixed-coordinate artifact | 文件/二进制 |
-| `/chem/qe/v1/qe/jobs` | 提交异步计算并查询 job | 远端变更 |
-| `/chem/qe/v1/qe/jobs/{job_id}/events`、`steps`、`logs`、`artifacts` | 读取作业过程和结果 | 只读 |
-| `/chem/qe/v1/qe/jobs/{job_id}:cancel`、`:retry`、`:review` | 取消、重试和科学审核 | 远端变更 |
+| `/chem/qe/health`, `/healthz`, `/readyz` | Runtime, scheduler, storage and PP readiness | Read-only |
+| `/chem/qe/v1/qe/workflow-types` | Workflow catalogue and support status | Read-only |
+| `/chem/qe/v1/pp-sets`, `/pp-locks/{digest}` | Published PP profiles/locks | Read-only |
+| `/chem/qe/v1/pp-sets:resolve` | Resolve PP candidates for the complete set of campaign elements | Read-only/validation |
+| `/chem/qe/v1/artifacts` | Upload, query and download structure/fixed-coordinate artifacts | File/binary |
+| `/chem/qe/v1/qe/jobs` | Submit asynchronous calculations and query jobs | Remote mutation |
+| `/chem/qe/v1/qe/jobs/{job_id}/events`, `steps`, `logs`, `artifacts` | Read job progress and results | Read-only |
+| `/chem/qe/v1/qe/jobs/{job_id}:cancel`, `:retry`, `:review` | Cancel, retry and scientifically review a job | Remote mutation |
 
-选择新 operation 时，先使用：
+When selecting a new operation, first run:
 
 ```text
 delta-cli science list
 delta-cli science endpoints list <exact tool name>
 ```
 
-再用目录返回的精确名称调用；如果 catalog 没有 schema，不猜测 operation、路径参数、
-请求头或 body。
+Then call it using the exact names returned by the catalogue. If the catalogue has no schema, do
+not guess the operation, path parameters, headers or body.
 
-## CLI 的文件和幂等边界
+## CLI file and idempotency boundaries
 
-结构 artifact 上传需要 `application/octet-stream` 和 query metadata，QE job 提交要求
-稳定的 `Idempotency-Key`。`science invoke` 仍只用于 JSON/query；文件通过
-`science file`，持久化 job 通过 `science task`：
+Structure artifact uploads require `application/octet-stream` and query metadata; QE job
+submission requires a stable `Idempotency-Key`. `science invoke` remains for JSON/query only;
+send files through `science file` and persistent jobs through `science task`:
 
-- `delta-cli science file invoke --tool qe --endpoint artifact-upload --file <path>` 上传
-  结构 artifact；`custom-pp-upload` 同理并在 `--data` 中提供 `custom_pp_id`；
+- `delta-cli science file invoke --tool qe --endpoint artifact-upload --file <path>` uploads
+  a structure artifact; for `custom-pp-upload`, also provide `custom_pp_id` in `--data`;
 - `delta-cli science task submit --tool qe --operation job-submit --input JSON
-  --idempotency-key KEY` 提交 durable QE job，worker 将幂等键传给 Gateway；
+  --idempotency-key KEY` submits a durable QE job; the worker passes the idempotency key to Gateway;
 - `delta-cli science file download --tool qe --endpoint artifact-content --params JSON
-  --output <path>` 下载原始 artifact；
-- 不要把结构文本、文件路径、base64、`Idempotency-Key` 或 QE service credential 当成
-  普通业务字段发送，也不要调用公开/私有 Gateway URL 或 `qe-cloud-compute:18020`。
-
-## 新作业的正确顺序
-
-1. 读取 health；需要部署诊断时再读取 readiness，并从 workflow catalog 选择当前
-   `supported` 的 task。
-2. 计算完整 `campaign_elements` 集合，使用 `pp-sets:resolve` 得到 profile；生产作业
-   必须使用服务返回的 `pp_set_id` 与不可变 `lock_id`，不能只凭 profile 名称推断 lock。
-3. 让服务校验结构 artifact，job 只引用返回的 `sha256:<digest>` artifact ID。
-4. 用稳定幂等语义提交 `qe/jobs`；接收 `202` 只代表 accepted/queued，不代表 QE 已收敛。
-5. 轮询 job、events、steps、logs 和 artifacts；独立读取 `execution`、`solver`、
-   `scientific` 三个状态。
-6. 下载结果时校验每个 artifact 的 SHA-256，并分别报告 selected backend、资源 telemetry、
-   solver 状态、scientific review 状态和 warnings。
-
-PP 解析的最小业务数据形状如下；其中值必须来自当前服务/目录，不能填入虚构的生产 lock：
+  --output <path>` downloads a raw artifact;
+- Do not send structure text, file paths, base64, `Idempotency-Key` or QE service credentials as
+  ordinary business fields, and do not call public or private Gateway URLs or `qe-cloud-compute:18020`.
+
+## Correct sequence for a new job
+
+1. Read health. Read readiness only when diagnosing the deployment, and choose a currently
+   `supported` task from the workflow catalogue.
+2. Determine the complete `campaign_elements` set and use `pp-sets:resolve` to obtain a profile.
+   Production jobs must use the returned `pp_set_id` and immutable `lock_id`; do not infer the
+   lock from the profile name alone.
+3. Ask the service to validate the structure artifact. The job must reference only the returned
+   `sha256:<digest>` artifact ID.
+4. Submit to `qe/jobs` with stable idempotency semantics. A `202` response means accepted/queued,
+   not that QE has converged.
+5. Poll the job, events, steps, logs and artifacts; read the `execution`, `solver` and
+   `scientific` states independently.
+6. Verify each artifact's SHA-256 when downloading results. Report the selected backend, resource
+   telemetry, solver state, scientific review state and warnings separately.
+
+The minimum business-data shape for PP resolution is shown below. Values must come from the
+current service/catalogue; do not insert a fabricated production lock:
 
 ```json
 {
@@ -70,7 +75,7 @@ PP 解析的最小业务数据形状如下；其中值必须来自当前服务/
 }
 ```
 
-作业的核心结构如下，`workflow_inputs` 必须遵循当前 task schema：
+The core job structure is shown below. `workflow_inputs` must follow the current task schema:
 
 ```json
 {
@@ -101,25 +106,29 @@ PP 解析的最小业务数据形状如下；其中值必须来自当前服务/
 }
 ```
 
-## CPU/GPU 与状态解释
+## CPU/GPU and state interpretation
 
-CPU 是默认策略，尤其适用于小/中型交互任务、PP/结构/审计/归档任务和成本敏感场景。
-只有用户明确要求或项目已有 GPU 预算，并且 live catalog 返回
-`gpu_support_status: "verified"` 时，才使用 `gpu`；强制 GPU 不得静默回退 CPU。只有
-结果明确返回 `selected_backend: "gpu"` 才能声称实际使用 GPU；`auto` 不是 GPU 使用证明。
+CPU is the default, particularly for small or medium interactive jobs, PP/structure/audit/archive
+jobs, and cost-sensitive work. Use `gpu` only when the user explicitly requests it or the project
+already has a GPU budget, and the live catalogue returns `gpu_support_status: "verified"`. Do not
+silently fall back to CPU when GPU is required. Claim that GPU was used only when the result
+explicitly returns `selected_backend: "gpu"`; `auto` does not prove GPU use.
 
-三个状态通道不可合并：
+Keep the three state channels separate:
 
-- `execution`：prepared/submitted/queued/running/scheduler completion/cancelled/failed；
-- `solver`：not started/running/converged/not converged/failed/unknown；
-- `scientific`：unreviewed、scientifically accepted、accepted with limitations、needs
-  recalculation、not assessable、failed 或 archived。
+- `execution`: prepared/submitted/queued/running/scheduler completion/cancelled/failed;
+- `solver`: not started/running/converged/not converged/failed/unknown;
+- `scientific`: unreviewed, scientifically accepted, accepted with limitations, needs
+  recalculation, not assessable, failed or archived.
 
-scheduler 完成不等于 solver 收敛，solver 收敛也不等于 scientific acceptance。按稳定
-错误码而不是 message 分支，重点包括 `PP_SET_INCOMPLETE`、`PP_POLICY_INCOMPATIBLE`、
-`PP_CAPABILITY_UNKNOWN`、`ARTIFACT_MISSING`、`SOLVER_NOT_CONVERGED`、
-`SCIENTIFIC_GATE_FAILED`、`RESTART_INCOMPATIBLE`、`IDEMPOTENCY_CONFLICT`、
-`EXECUTION_BACKEND_NOT_READY`、`GPU_UNSUPPORTED` 和 `GPU_UNAVAILABLE`。
+scheduler completion does not mean solver convergence, and solver convergence does not mean
+scientific acceptance. Branch on stable error codes rather than messages. Key codes include
+`PP_SET_INCOMPLETE`, `PP_POLICY_INCOMPATIBLE`,
+`PP_CAPABILITY_UNKNOWN`, `ARTIFACT_MISSING`, `SOLVER_NOT_CONVERGED`,
+`SCIENTIFIC_GATE_FAILED`, `RESTART_INCOMPATIBLE`, `IDEMPOTENCY_CONFLICT`,
+`EXECUTION_BACKEND_NOT_READY`, `GPU_UNSUPPORTED` and `GPU_UNAVAILABLE`.
 
-提交、取消、重试或审核属于远端变更，必须有用户明确授权；结果未知时禁止重试。不要把
-GPU smoke test、scheduler 日志或可解析的 QE 输出描述成科学结论或客户级性能保证。
+Submission, cancellation, retry and review are remote mutations and require the user's explicit
+authorisation. Do not retry when the outcome is unknown. Do not describe a GPU smoke test,
+scheduler log or parseable QE output as a scientific conclusion or a customer-level performance
+guarantee.

package/skills/delta-science/references/rdkit.md

@@ -1,23 +1,26 @@
-# RDKit 详细规则
+# RDKit reference
 
-只能通过 `delta-cli science invoke` 调用。以下业务响应位于 CLI 顶层 `data`；只按本文件
-说明读取字段，不得递归搜索。这里只记录 operation schema，不授权直接 HTTP。
+Call this tool only through `delta-cli science invoke`. Business responses are in the top-level
+CLI `data`; read only the fields described here and do not search recursively. This document
+records operation schemas and does not authorise direct HTTP access.
 
-一个请求只执行完成目标所需的最少调用。同时校验、规范化并计算基础描述符时使用一次
-`batch-parse-describe`，payload 使用 `molecules:[{id,smiles}]`，不得拆成 parse 和
-descriptors。多个分子的全对相似度使用一次 `similarity-matrix`；排名字段固定为
-`a`、`b`、`similarity`，不是 `i`、`j`、`score`。
+Make only the calls needed to meet the request. To validate, canonicalise and calculate basic
+descriptors in one request, use `batch-parse-describe` with the `molecules:[{id,smiles}]` payload;
+do not split it into parse and descriptors calls. For all-pairs similarity across multiple
+molecules, use one `similarity-matrix` call. Its fixed ranking fields are `a`, `b` and
+`similarity`, not `i`, `j` or `score`.
 
-只报告业务响应实际存在的描述符。渲染 PNG 时只解码文档指定字段，并验证字节以
-`89 50 4e 47 0d 0a 1a 0a` 开头；不得把 JSON envelope 保存成图片。
+Report only descriptors actually present in the business response. When rendering a PNG, decode
+only the field specified in the documentation and verify that the bytes begin with
+`89 50 4e 47 0d 0a 1a 0a`; do not save a JSON envelope as an image.
 
 ## Health
 
-operation：`health`，无 body。
+Operation: `health`; no request body.
 
 ## Parse
 
-operation：`parse`。
+Operation: `parse`.
 
 ```json
 {"input": "CCO", "format": "smiles", "sanitize": true}
@@ -31,7 +34,7 @@ Key response fields in `data`: `valid`, `canonical_smiles`, `formula`,
 
 ## Descriptors
 
-operation：`descriptors`。
+Operation: `descriptors`.
 
 ```json
 {"smiles": "CCO", "descriptor_set": "basic", "sanitize": true}
@@ -44,7 +47,7 @@ operation：`descriptors`。
 
 ## Batch Descriptors
 
-operation：`batch-descriptors`。
+Operation: `batch-descriptors`.
 
 ```json
 {"smiles": ["CCO", "c1ccccc1"], "descriptor_set": "basic", "sanitize": true}
@@ -54,7 +57,7 @@ Limits: 1-500 SMILES.
 
 ## Batch Parse Describe
 
-operation：`batch-parse-describe`。
+Operation: `batch-parse-describe`.
 
 ```json
 {
@@ -74,7 +77,7 @@ fields, `descriptors`, optional `fingerprint_metadata`, `on_bits`, `bit_count`,
 
 ## Render
 
-operation：`render`。
+Operation: `render`.
 
 ```json
 {"smiles": "CCO", "image_format": "svg", "width": 450, "height": 320}
@@ -85,7 +88,7 @@ Width/height range: 150-2000.
 
 ## Fingerprint
 
-operation：`fingerprint`。
+Operation: `fingerprint`.
 
 ```json
 {"smiles": "CCO", "radius": 2, "n_bits": 2048}
@@ -95,7 +98,7 @@ Morgan fingerprint parameters: `radius` 1-6, `n_bits` 128-8192.
 
 ## Similarity
 
-operation：`similarity`。
+Operation: `similarity`.
 
 ```json
 {"query_smiles": "CCO", "target_smiles": "CCCO", "radius": 2, "n_bits": 2048}
@@ -105,7 +108,7 @@ Returns Tanimoto similarity.
 
 ## Similarity Matrix
 
-operation：`similarity-matrix`。
+Operation: `similarity-matrix`.
 
 ```json
 {
@@ -129,7 +132,7 @@ Do not expect `i`, `j`, or `score` fields.
 
 ## Substructure
 
-operation：`substructure`。
+Operation: `substructure`.
 
 ```json
 {"query_smarts": "c1ccccc1", "target_smiles": ["c1ccccc1", "CCO"]}

package/skills/delta-science/references/strbo.md

@@ -1,38 +1,41 @@
-# STRBO 详细规则
+# STRBO reference
 
-STRBO 用于服务端固定 **KRAS G12D** 靶点的小分子生成式多目标优化。目标顺序固定为
-`[vina, activity]`：vina 越低越好，activity 越高越好。`task` 只引导候选生成，
-不会更换靶点；不得声称支持用户自定义受体。
+STRBO performs generative multi-objective optimisation for the server-fixed **KRAS G12D**
+target. The objective order is fixed as `[vina, activity]`: lower Vina is better and higher
+activity is better. `task` guides candidate generation but does not change the target; do not
+claim that user-defined receptors are supported.
 
-所有调用均使用 `tool="strbo"`。生成、建议、评估和提交 job 都会消耗远端资源，只在
-用户确实要求执行相应科研任务时调用；请求结果未知或超时时不得重试。
+Use `tool="strbo"` for every call. Generation, suggestion, evaluation and job submission consume
+remote resources, so call them only when the user actually asks for the relevant research task.
+Do not retry if the outcome is unknown or the request times out.
 
-## 初始化
+## Initialisation
 
-- 同步 operation：`molecules-init`
-- 异步 operation：`molecules-init-job`
-- 仅校验 operation：`molecules-init-validate`
+- Synchronous operation: `molecules-init`
+- Asynchronous operation: `molecules-init-job`
+- Validation-only operation: `molecules-init-validate`
 
 ```json
 {
-  "task": "为 KRAS G12D 生成兼顾结合与活性的候选小分子",
+  "task": "Generate candidate small molecules for KRAS G12D that balance binding and activity",
   "num_initial": 3,
   "seed": 42
 }
 ```
 
-只需检查参数时使用 validate；正式执行不要先 validate 再提交，避免无必要调用。
-成功结果应包含与 `num_initial` 数量一致的候选 SMILES。
+Use validate only when you need to check parameters. For a full run, do not validate before
+submitting; that would make an unnecessary call. A successful result should contain the same
+number of candidate SMILES as `num_initial`.
 
-## 建议下一批候选
+## Suggest the next batch of candidates
 
-- 同步 operation：`molecules-suggest`
-- 异步 operation：`molecules-suggest-job`（重型任务优先）
-- 仅校验 operation：`molecules-suggest-validate`
+- Synchronous operation: `molecules-suggest`
+- Asynchronous operation: `molecules-suggest-job` (prefer it for heavy tasks)
+- Validation-only operation: `molecules-suggest-validate`
 
 ```json
 {
-  "task": "继续改善 KRAS G12D 的结合与活性",
+  "task": "Continue improving binding and activity for KRAS G12D",
   "history_xs": ["CCO", "CCN", "CCC"],
   "history_ys": [
     [-6.8, 0.31],
@@ -44,14 +47,14 @@ STRBO 用于服务端固定 **KRAS G12D** 靶点的小分子生成式多目标
 }
 ```
 
-`history_xs` 与 `history_ys` 必须等长；每个 `history_ys` 元素必须是两个有限数值，
-顺序严格为 `[vina, activity]`。不得把预测值伪装成湿实验结果。
+`history_xs` and `history_ys` must have the same length. Each `history_ys` item must contain two
+finite numbers in the exact order `[vina, activity]`. Do not present predictions as wet-lab results.
 
-## 评估候选
+## Evaluate candidates
 
-- 同步 operation：`molecules-evaluate`
-- 异步 operation：`molecules-evaluate-job`
-- 仅校验 operation：`molecules-evaluate-validate`
+- Synchronous operation: `molecules-evaluate`
+- Asynchronous operation: `molecules-evaluate-job`
+- Validation-only operation: `molecules-evaluate-validate`
 
 ```json
 {
@@ -59,29 +62,34 @@ STRBO 用于服务端固定 **KRAS G12D** 靶点的小分子生成式多目标
 }
 ```
 
-成功结果中的 score 数量必须与 designs 一致，每行必须恰好有两个有限数值。任一 item
-明确失败时，本轮整体按失败处理，不得只报告成功子集。
+The number of scores in a successful result must match the number of designs, with exactly two
+finite numbers per row. If any item explicitly fails, treat the entire run as failed; do not
+report only the successful subset.
 
-## 异步作业
+## Asynchronous jobs
 
-提交异步 operation 后，从当前业务响应读取非空 `job_id`，再轮询：
+After submitting an asynchronous operation, read a non-empty `job_id` from the current business
+response, then poll:
 
 ```text
 delta-cli science invoke --tool strbo --endpoint job-status --params JSON
 ```
 
-只有状态变为 `succeeded` 后才读取：
+Read the result only once the status changes to `succeeded`:
 
 ```text
 delta-cli science invoke --tool strbo --endpoint job-result --params JSON
 ```
 
-`queued` 或 `running` 不是完成；`failed` 立即结束。状态查询可按 5 秒左右间隔重复，
-但提交 operation 绝不重复。单次用户任务的总等待上限为 15 分钟；超限后报告作业仍
-未完成并保留 job_id，不得声称远端已取消。
+`queued` and `running` do not mean the job is complete; stop immediately on `failed`. Status
+queries may be repeated at intervals of about five seconds, but never repeat the submission
+operation. The total wait for one user task is limited to 15 minutes. If that limit is reached,
+report that the job is still incomplete and retain its `job_id`; do not claim it was cancelled
+remotely.
 
-## 完整科研流程
+## Complete research workflow
 
-用户明确要求完整迭代时按 `初始化 → 评估 → 建议 → 评估` 串行执行。每一步只使用本次
-调用已验证的业务响应作为下一步输入。用户只要求生成初始候选或评估给定 SMILES 时，
-不得擅自扩展为完整循环。
+When the user explicitly asks for a complete iteration, run `initialise → evaluate → suggest →
+evaluate` sequentially. Use only verified business responses from the current calls as inputs to
+the next step. If the user asks only for initial candidates or evaluation of supplied SMILES, do
+not expand the task into a full loop.

package/skills/delta-science/references/synbo.md

@@ -1,19 +1,22 @@
-# SynBO operation 参考
+# SynBO operation reference
 
-所有在线调用都通过 `delta-cli science invoke`，服务地址来自 CLI 的标准
-`base_url` 派生配置（`{base_url}/science_tool`）。这里的路径只说明业务 operation，不得据此直连 HTTP。
+Make all online calls with `delta-cli science invoke`; the service address comes from the CLI's
+standard `base_url` configuration (`{base_url}/science_tool`). The paths here describe business
+operations only and do not authorise direct HTTP access.
 
-用户说“优化反应条件”“推荐下一批实验”“偶联反应怎么继续做”，或给出溶剂、温度、
-催化剂、碱、配体和历史得率时，即使没有提到 SynBO、BO、CLI 或字段名也使用本节。
-每个用户任务最多一次 SynBO 业务调用；成功后立即结束，validation、502、504、
-timeout、断连或空 recommendations 均不得换参数、换模型或重试。
+Use this section when the user asks to optimise reaction conditions, recommend the next batch of
+experiments, continue a coupling reaction, or provides solvents, temperatures, catalysts, bases,
+ligands and historical yields—even if they do not mention SynBO, BO, the CLI or field names. Make
+at most one SynBO business call per user task. Stop immediately after success; for validation
+errors, 502, 504, timeouts, disconnections or empty recommendations, do not change parameters or
+models, or retry.
 
 ## Health
 
-operation：`health`，无 body。
+Operation: `health`; no request body.
 
 Reports SynBO import status, Torch/CUDA runtime availability, service limits,
-default device, and visible CUDA devices.
+default device and visible CUDA devices.
 
 Important fields inside gateway `data`:
 
@@ -46,7 +49,7 @@ Important fields inside gateway `data`:
 
 ## Initialize
 
-operation：`initialize`。
+Operation: `initialize`.
 
 Use for initial condition sampling when no measured previous results exist.
 
@@ -74,7 +77,7 @@ Supported `sampling_method` values: `sobol`, `random`, `lhs`, `kmeans`.
 
 ## Optimize
 
-operation：`optimize`。
+Operation: `optimize`.
 
 Use after measured experiment rows are available. Each previous row must contain
 all condition columns and all objective metric columns.
@@ -103,11 +106,11 @@ Request body:
 }
 ```
 
-### 数值条件必须先离散化
+### Discretise numeric conditions first
 
-SynBO 的 `condition_dict` 只接受显式列表，不接受连续范围对象。对于“温度
-40–100°C、催化剂用量 0.5–2.0%”并已有 60/70/80/90°C 与
-0.5/1.0/1.5/2.0% 历史值的任务，使用：
+SynBO's `condition_dict` accepts explicit lists only; it does not accept continuous range
+objects. For a task with a temperature range of 40–100°C and catalyst loading of 0.5–2.0%, with
+historical values at 60/70/80/90°C and 0.5/1.0/1.5/2.0%, use:
 
 ```json
 {
@@ -135,14 +138,12 @@ SynBO 的 `condition_dict` 只接受显式列表，不接受连续范围对象
 }
 ```
 
-约束：
+Constraints:
 
-- 每个条件值统一为字符串，objective metric 保持数值。
-- 每条 `previous_results` 中的条件值必须出现在对应 `condition_dict` 列表中。
-- 连续范围的离散网格必须包含用户上下界和全部历史观测值；最终答案必须说明实际网格。
-- 将条件值显式序列化为字符串，并确保每条历史记录只使用 `condition_dict` 中列出的值。
-  如需小数据 CPU 设置，显式传递 `accuracy:"tiny"`、`surrogate_model:"RF"`、
-  `acq_func:"UCB"` 和 `device:"cpu"`；不得假定客户端会补充默认值。
+- Represent every condition value as a string and keep objective metrics numeric.
+- Every condition value in each `previous_results` row must appear in the corresponding `condition_dict` list.
+- The discretised grid for a continuous range must include the user's lower and upper bounds and all historical observations. State the actual grid in the final answer.
+- Serialise condition values explicitly as strings, and ensure each historical row uses only values listed in `condition_dict`. For a small-data CPU configuration, pass `accuracy:"tiny"`, `surrogate_model:"RF"`, `acq_func:"UCB"` and `device:"cpu"` explicitly; do not assume the client supplies defaults.
 
 Useful optional fields:
 
@@ -190,9 +191,11 @@ Gateway errors have the standard envelope:
 }
 ```
 
-常见原因包括条件空间过大、条件值重复、历史条件值不在 condition_dict 中、
-descriptor 非数值、历史行缺列、metric 非数值，以及无 GPU 时请求 CUDA。
+Common causes include an oversized condition space, duplicate condition values, historical
+condition values absent from `condition_dict`, non-numeric descriptors, missing columns in
+historical rows, non-numeric metrics, and a CUDA request when no GPU is available.
 
-服务端有独立于客户端的单次请求时限。GP、EHVI、高 accuracy 或共享资源繁忙可能导致
-timeout。普通用户任务中不得自动换参数重试；应报告“未产生推荐”，保留本次错误，
-由用户决定是否另起一次明确的回归测试。
+The server has a per-request timeout independent of the client. GP, EHVI, high accuracy or busy
+shared resources may cause a timeout. Do not automatically change parameters and retry during an
+ordinary user task. Report “no recommendations were produced”, preserve the error, and let the
+user decide whether to start a separate, explicitly requested regression test.