Skip to content

chore: point charm.land/fantasy at coder/fantasy#85 - #31746

Merged
ethanndickson merged 2 commits into
ethan/openai-web-search-inline-replayfrom
codagt-1430-fantasy-media-label
Nov 10, 2026
Merged

ethanndickson merged 2 commits into
ethan/openai-web-search-inline-replayfrom
codagt-1430-fantasy-media-label

Conversation

@ethanndickson

@ethanndickson ethanndickson commented Nov 4, 2026 •

Copy link
Copy Markdown
Member

Part of CODAGT-1430
Relates to CODAGT-1541

Stacked on #31743.

This bumps fantasy to pick up coder/fantasy#84 and coder/fantasy#85.

A Chat Completions tool message can only hold text, so fantasy sends tool result media (images, audio, and now PDFs from #31384) in a role: "user" message right after it. That gives whatever the tool returned the authority of the user's own words, which Codex flagged on #31383 as a prompt injection risk for MCP tools that return untrusted files.

coder/fantasy#84 starts that user message with a text part naming the tool call and saying the content is tool output, not instructions from the user. It only changes the Chat Completions paths (openai without the Responses API, openaicompat, OpenRouter and Vercel); Anthropic and Responses keep the media inside the tool result. AI Bridge records the last user message's text as the prompt, so on the step after a tool returns media, it'll now record the label. I think that's fine for now.

coder/fantasy#85 fixes the output token limit field. The OpenAI provider sent max_tokens unless the model ID looked like a reasoning model, and reasoning models reject it:

Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.

That breaks any reasoning model whose ID fantasy doesn't recognise, e.g. an Azure deployment name, which doesn't say what model it serves (Azure providers start using this client in #31952). The OpenAI provider now sends max_completion_tokens on every Chat Completions request, which is what OpenAI deprecated max_tokens in favour of. openaicompat, OpenRouter and Vercel keep max_tokens, so self-hosted servers behind the OpenAI Compatible provider are unaffected. I've added a test that checks the field on each route, and the models docs no longer say Max Completion Tokens is only for reasoning models.

@linear-code

linear-code Bot commented Nov 4, 2026 •

Copy link
Copy Markdown

CODAGT-1430

CODAGT-1541

@ethanndickson

Copy link
Copy Markdown
Member Author

@codex review

@chatgpt-codex-connector

chatgpt-codex-connector Bot commented Nov 4, 2026 •

Copy link
Copy Markdown
Codex Review Summary: ✅ Completed

This comment shows the latest Codex review activity on this pull request.

Review Status Commit Review trigger
📝 Code Review ✅ Completed 2026-11-09T06:09:14.169212Z 1a16dd4 Manual request
ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

@chatgpt-codex-connector

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. Keep it up!

Reviewed commit: 93780fcbb9

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

@ethanndickson
ethanndickson marked this pull request as ready for review November 4, 2026 07:55
@ethanndickson
ethanndickson force-pushed the codagt-1430-fantasy-media-label branch from 93780fc to 842e051 Compare November 5, 2026 08:12
@ethanndickson
ethanndickson force-pushed the codagt-1430-fantasy-media-label branch from 842e051 to 1a16dd4 Compare November 9, 2026 06:04
@ethanndickson

Copy link
Copy Markdown
Member Author

@codex review

@chatgpt-codex-connector

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. Nice work!

Reviewed commit: 1a16dd4995

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

@ethanndickson
ethanndickson force-pushed the codagt-1430-fantasy-media-label branch from 1a16dd4 to e7fa56f Compare November 9, 2026 06:47
A Chat Completions tool message holds only text, so fantasy sends tool result media in a user message right after it. That gave tool output the authority of the user's own words. coder/fantasy#84 puts a text part ahead of the media that names the tool call and says the content is tool output, not instructions from the user. The PDF tool result test now expects that label.
@ethanndickson
ethanndickson force-pushed the codagt-1430-fantasy-media-label branch from e7fa56f to 7340799 Compare November 9, 2026 07:32
The fantasy OpenAI provider sent the output token limit as max_tokens unless the model ID looked like a reasoning model. OpenAI and Azure OpenAI reject max_tokens for reasoning models, and an Azure deployment name cannot show what model it serves. coder/fantasy#85 sends max_completion_tokens on every OpenAI Chat Completions request. The OpenAI-compatible providers keep max_tokens. A new test checks the field on the OpenAI and OpenAI-compatible routes, and the models docs no longer limit Max Completion Tokens to reasoning models.
@ethanndickson ethanndickson changed the title chore: point charm.land/fantasy at coder/fantasy#84 chore: point charm.land/fantasy at coder/fantasy#85 Nov 10, 2026
@ethanndickson
ethanndickson merged commit af7cd18 into main Nov 10, 2026
38 of 39 checks passed
@ethanndickson
ethanndickson deleted the codagt-1430-fantasy-media-label branch November 10, 2026 13:06
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants