fix(openai): send max_completion_tokens for gpt-5 models

[hlubek]

Problem

gpt-5-class models reject the max_tokens parameter with HTTP 400 — they require max_completion_tokens instead. Any caller that sets a token budget against a gpt-5 model (e.g. gpt-5, gpt-5-mini, gpt-5.4-2026-03-05) currently gets a 400.

Fix

needsMaxCompletionTokens() already recognizes the o-series and 4o models that need max_completion_tokens; this extends it to gpt-5*. Both SetOption and the PrepareRequest variants route through that single predicate, so every request path is covered by the one change.

Tests

• Detection table cases for gpt-5, gpt-5-mini, and gpt-5.4-2026-03-05.
• A PrepareRequest test asserting a gpt-5 request body carries max_completion_tokens and never max_tokens, with the token budget preserved across the conversion.

Summary by Sourcery

Ensure OpenAI provider uses max_completion_tokens for gpt-5-class models instead of max_tokens to avoid API errors.

Tests:

• Add detection cases confirming gpt-5 variants require max_completion_tokens.
• Add a PrepareRequest test verifying gpt-5 requests send max_completion_tokens, never max_tokens, while preserving the token budget.

[sourcery-ai]

Reviewer's Guide

Extends OpenAI provider handling so that all gpt-5* models use max_completion_tokens instead of max_tokens, and adds tests to verify detection and request preparation behavior.

Sequence diagram for OpenAIProvider request preparation using max_completion_tokens for gpt-5 models

sequenceDiagram
    actor Caller
    participant OpenAIProvider

    Caller->>OpenAIProvider: SetOption(max_tokens)
    OpenAIProvider->>OpenAIProvider: needsMaxCompletionTokens()
    alt model is gpt-5*
        OpenAIProvider->>OpenAIProvider: store max_completion_tokens
    else other model
        OpenAIProvider->>OpenAIProvider: store max_tokens
    end

    Caller->>OpenAIProvider: PrepareRequest()
    OpenAIProvider->>OpenAIProvider: needsMaxCompletionTokens()
    alt model is gpt-5*
        OpenAIProvider-->>Caller: request body with max_completion_tokens
    else other model
        OpenAIProvider-->>Caller: request body with max_tokens
    end

Loading

File-Level Changes

Change	Details	Files
Update model detection to treat all gpt-5* chat models as requiring max_completion_tokens instead of max_tokens.	Extend needsMaxCompletionTokens predicate to return true when the configured model name starts with gpt-5. Document in a comment that gpt-5-class models reject max_tokens with HTTP 400 and give examples of affected model IDs.	providers/openai.go
Add unit tests to ensure gpt-5* models are recognized correctly and that requests for these models send max_completion_tokens only.	Add gpt-5, gpt-5-mini, and gpt-5.4-2026-03-05 cases to the existing TestNeedsMaxCompletionTokens table. Add TestPrepareRequestGPT5UsesMaxCompletionTokens to assert that PrepareRequest for a gpt-5* model strips max_tokens, sets max_completion_tokens, and preserves the configured token budget.	providers/openai_test.go

---

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

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}