chore: add support for gpt 5.1

[uinstinct]

Description

Support for the new gpt 5.1

resolves CON-4932

AI Code Review

• Team members only: AI review runs automatically when PR is opened or marked ready for review
• Team members can also trigger a review by commenting @continue-review

Checklist

• [] I've read the contributing guide
• [] The relevant docs, if any, have been updated or created
• [] The relevant tests, if any, have been updated or created

Screen recording or screenshot

[ When applicable, please include a short screen recording or screenshot - this makes it much easier for us as contributors to review and understand your changes. See this PR as a good example. ]

Tests

[ What tests were added or updated to ensure the changes work as expected? ]

---

Summary by cubic

Add support for gpt-5.1 with correct model metadata. Enables chat with a 400k context window and 128k max completion; adds it to recommended models, agent model detection, and the Add Model form; updates docs; addresses Linear CON-4932.

• New Features
  • Registered gpt-5.1 in the provider registry (display name, 400k context, 128k max completion).
  • Added gpt-5.1 to CometAPI recommended chat models, agent model detection, and OpenAI options in the Add Model UI.

^{Written for commit dacfee0. Summary will update automatically on new commits.}

[cubic-dev-ai]

No issues found across 2 files

[RomneyDa]

See comments, also can we

• add to the add models form in GUI
• add it to recommended agent models i.e. make sure it gets multi edit tool
• add comments about how the model was tested e.g. does it do well in agent mode? both CLI and extensions?
• make sure it's added to auto tool support
• update the docs

[uinstinct]

make sure it's added to auto tool support

already present (as prefix starts with gpt-5)

add comments about how the model was tested e.g. does it do well in agent mode? both CLI and extensions?

tested and it works fine on cn

[cubic-dev-ai]

2 issues found across 7 files

Prompt for AI agents (all 2 issues)

Understand the root cause of the following 2 issues and fix them.


<file name="docs/customize/deep-dives/model-capabilities.mdx">

<violation number="1" location="docs/customize/deep-dives/model-capabilities.mdx:175">
Update the GPT-5 context window to match the 128k limit defined in the model metadata so the capability table stays accurate.</violation>
</file>

<file name="packages/llm-info/src/providers/openai.ts">

<violation number="1" location="packages/llm-info/src/providers/openai.ts:100">
Escape the dot in the GPT‑5.1 regex so only the literal model name matches.</violation>
</file>

_{Reply to cubic to teach it or ask questions. Re-run a review with @cubic-dev-ai review this PR}

[cubic-dev-ai]

No issues found across 8 files

[RomneyDa]

this may match funky dates but should be fine since 2-digit month/day won't start w 5

[sestinj]

🎉 This PR is included in version 1.6.0 🎉

The release is available on:

• npm package (@latest dist-tag)
• GitHub release

Your semantic-release bot 📦🚀

[sestinj]

🎉 This PR is included in version 1.36.0 🎉

The release is available on:

• npm package (@latest dist-tag)
• GitHub release

Your semantic-release bot 📦🚀