[Cherry-Pick][BugFix] fix tool call parser(#7369)

[EmmonsCurse]

Cherry-pick of #7369 (authored by @luukunn) to release/2.5.

devPR:#7369

---

Motivation

• 修复 extract_tool_calls 中 tools_called 在 tool_calls 为空时仍返回 True 的问题
• 修复空字典 {} 被误判为无参数的问题
• 修复流式输出结束处理中 '"}' 检查过于严格导致数字/布尔值结尾的参数无法正确流式传输的问题

Modifications

• 将 tools_called=True 改为 tools_called=len(tool_calls) > 0
• 将 if diff: 改为 if diff is not None:，正确处理空字典
• 将 if '"}' not in delta_text: 改为 if "}" not in delta_text:，并使用 rindex("}") 获取正确位置
• 将所有 if not cur_arguments 改为 if cur_arguments is None，避免空字典误判
• 新增回归测试覆盖空参数、数字/布尔值结尾参数、嵌套对象等边界情况

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 | 2026-04-15

📋 Review 摘要

PR 概述：修复 ErnieX1ToolParser 中的 3 个 bug：tools_called 错误判断、空字典 {} 误判、流式输出结束处理过于严格

变更范围：fastdeploy/entrypoints/openai/tool_parsers/ernie_x1_tool_parser.py

影响面 Tag：[APIServer]

问题

级别	文件	概述
无	-	未发现阻塞性问题

总体评价

这是一个高质量的 bug 修复 PR。变更正确地修复了以下问题：

1. tools_called 判断修复（Line 113）：异常情况下 tool_calls 为空列表时，正确返回 False
2. 空字典处理修复（Lines 184, 252, 256, 260, 304）：将 if diff:/if not cur_arguments 改为显式 is None 检查，避免 {} 被误判
3. 流式结束处理修复（Lines 185-190）：将 '"}' 改为 '}'，支持数字/布尔值结尾的参数
4. 参数处理增强（Lines 274-281）：新增处理正则过度捕获的情况

测试用例新增充分，覆盖了空参数、数字结尾、布尔值结尾、嵌套对象等边界场景。Cherry-Pick 到 release/2.5 分支合理。

[codecov-commenter]

Codecov Report

❌ Patch coverage is 77.77778% with 4 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (release/2.5@f3fb7e0). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
...points/openai/tool_parsers/ernie_x1_tool_parser.py	77.77%	0 Missing and 4 partials ⚠️

Additional details and impacted files

@@              Coverage Diff               @@
##             release/2.5    #7418   +/-   ##
==============================================
  Coverage               ?   69.62%           
==============================================
  Files                  ?      390           
  Lines                  ?    54387           
  Branches               ?     8579           
==============================================
  Hits                   ?    37868           
  Misses                 ?    13805           
  Partials               ?     2714           

Flag	Coverage Δ
GPU	69.62% <77.77%> (?)

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.