[APIServer]Change the default value of the strict field to False.

[luukunn]

Motivation

修改strict字段默认值为False

Modifications

Usage or Command

Accuracy Tests

Checklist

• Add at least a tag in the PR title.
  • Tag list: [[FDConfig],[APIServer],[Engine], [Scheduler], [PD Disaggregation], [Executor], [Graph Optimization], [Speculative Decoding], [RL], [Models], [Quantization], [Loader], [OP], [KVCache], [DataProcessor], [BugFix], [Docs], [CI], [Optimization], [Feature], [Benchmark], [Others], [XPU], [HPU], [GCU], [DCU], [Iluvatar], [Metax]]
  • You can add new tags based on the PR content, but the semantics must be clear.
• Format your code, run pre-commit before commit.
• Add unit tests. Please write the reason in this PR if no unit tests.
• Provide accuracy results.
• If the current PR is submitting to the release branch, make sure the PR has been submitted to the develop branch, then cherry-pick it to the release branch with the [Cherry-Pick] PR tag.

[paddle-bot]

Thanks for your contribution!

[PaddlePaddle-bot]

🤖 AI Code Review | 2026-04-24 17:18:47

📋 Review 摘要

PR 概述：将 FunctionDefinition 中 strict 字段的默认值从 Optional[bool] = None 改为 bool = False
变更范围：fastdeploy/entrypoints/openai/protocol.py
影响面 Tag：APIServer

---

📝 PR 规范检查

Modifications 章节未填写：PR 描述中 Modifications 部分为空，需要补充说明本次变更的具体内容和影响。

标题建议（可直接复制）：

• [APIServer] Change the default value of the strict field to False

（原标题 [APIServer]Change... 缺少 Tag 与描述之间的空格，以及描述末尾不需要句号）

Modifications 建议（可直接复制）：

## Modifications
将 `FunctionDefinition.strict` 字段类型从 `Optional[bool] = None` 改为 `bool = False`，
确保在客户端未传递 strict 字段时，默认值为 False 而非 None，避免下游逻辑处理 None 值。

---

问题

级别	文件	概述
🔴 兼容性	protocol.py:233	类型从 Optional[bool] 改为 bool，导致传入 null 时 Pydantic 验证失败
❓ 疑问	protocol.py:466	同文件 JsonSchemaResponseFormat.strict 仍为 Optional[bool] = None，两处不一致

---

🔴 兼容性问题：破坏 OpenAI API 规范兼容性

变更前：strict: Optional[bool] = None
变更后：strict: bool = False

问题：OpenAI 官方 API 规范 中，FunctionDefinition.strict 的类型为 boolean or null，即客户端可以合法地传递 "strict": null。本次变更将类型从 Optional[bool] 改为 bool，导致以下问题：

1. 当客户端发送 "strict": null 时，Pydantic 会抛出验证错误（null 无法转换为 bool），请求将失败，破坏现有兼容性。
2. 与同文件 JsonSchemaResponseFormat.strict: Optional[bool] = None（第 466 行）的处理方式不一致。

建议修复：保留 Optional[bool]，仅修改默认值：

# 修改前
strict: Optional[bool] = None

# 建议修改为（兼容 null 传入，同时提供 False 作为默认值）
strict: Optional[bool] = False

这样既满足"默认值为 False"的需求，也不会拒绝传入 null 的合法请求。

---

❓ 疑问：同文件另一处 strict 字段是否需要同步修改？

JsonSchemaResponseFormat（第 466 行）同样有 strict: Optional[bool] = None，与本次修改后的 FunctionDefinition.strict 不一致。请确认是否需要统一处理？

---

总体评价

变更目标合理（为 strict 提供明确默认值），但直接将类型从 Optional[bool] 改为 bool 会导致 Pydantic 拒绝 null 输入，破坏 OpenAI API 兼容性。建议改为 Optional[bool] = False 以同时满足两个目标。

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (develop@ee81b57). Learn more about missing BASE report.

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #7611   +/-   ##
==========================================
  Coverage           ?   72.25%           
==========================================
  Files              ?      419           
  Lines              ?    57854           
  Branches           ?     9077           
==========================================
  Hits               ?    41800           
  Misses             ?    13202           
  Partials           ?     2852           

Flag	Coverage Δ
GPU	72.25% <100.00%> (?)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.