[AmriaLin]

问题

流式请求下 UniResponse.usage 恒为 None，ledger 里只有非流式轮次的记录，最终统计的 token 用量远小于实际消耗。

原因

OpenAI 兼容的流式响应，最后一个 chunk 携带 usage，而它的 choices 是空数组：

{"choices": [], "usage": {"prompt_tokens": 100, "completion_tokens": 20, "total_tokens": 120}}

call_api 的流式分支里，usage 提取写在 try 内部，且排在 chunk.choices[0] 之后：

async for chunk in completion:
    try:
        if chunk.choices[0].finish_reason is not None:
            ...
        if chunk.usage:              # 永远走不到
            uni_usage = ...
    except IndexError:
        break                        # 循环在这里结束

空列表访问 choices[0] 抛 IndexError，except 直接 break，那个带 usage 的 chunk 被整个跳过。

call_tools 的分支写法是对的——先取 usage，再 if not chunk.choices: continue。两处不一致。

改动

• usage 提取移到 try 之前
• IndexError 分支由 break 改为 continue

验证

新增回归测试 test_call_api_streaming_usage_in_tail_chunk，构造一个正文 chunk 加一个 choices=[] 的尾块，断言 usage 的 prompt_tokens/completion_tokens/total_tokens 都能拿到。

回退源码后该测试失败（usage 为 null），应用修复后通过。

全量测试：687 passed。

Summary by Sourcery

Fix streaming response accounting so token usage from the final usage-only chunk is retained.

Bug Fixes:

• Preserve usage metadata from usage-only tail chunks in streaming OpenAI-compatible responses.

Tests:

• Add regression coverage for streaming responses whose final empty-choices chunk contains token usage.

[sourcery-ai]

Reviewer's Guide

Implementation

Extract usage before accessing choices and continue past empty-choice chunks so streaming tail usage is retained.

• src/amrita_core/adapters/openai.py L161-168, L182 (removed lines), L204-206

Tests

Add a regression test for usage on an empty-choices tail chunk and import its usage type.

• tests/test_adapter.py L18, L319-364

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey - I've reviewed your changes and they look great!

Sourcery assessment

Approved.

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook