feat(providers): add gpt-5.2-codex model to openai-native provider

[hannesrudolph]

Summary

Adds the new GPT-5.2-Codex model to the openai-native provider. This is OpenAI's most intelligent coding model optimized for long-horizon, agentic coding tasks.

Changes

• Added gpt-5.2-codex model definition to packages/types/src/providers/openai.ts

Model Specifications

Property	Value
Context Window	400,000 tokens
Max Output	128,000 tokens
Reasoning Effort	low, medium, high, xhigh (default: medium)
Standard Input Price	$1.75/1M tokens
Standard Output Price	$14.00/1M tokens
Cached Input Price	$0.175/1M tokens
Priority Input Price	$3.50/1M tokens
Priority Output Price	$28.00/1M tokens
Image Support	Yes
Prompt Cache	24h retention
Included Tools	apply_patch
Excluded Tools	apply_diff, write_to_file

---

Important

Adds gpt-5.2-codex model to openai.ts, optimized for coding tasks with specific token limits, pricing, and tool support.

• Model Addition:
  • Adds gpt-5.2-codex to openAiNativeModels in openai.ts.
  • Optimized for long-horizon, agentic coding tasks.
• Specifications:
  • Context window: 400,000 tokens, Max output: 128,000 tokens.
  • Reasoning effort: low, medium, high, xhigh (default: medium).
  • Pricing: Standard input $1.75/1M tokens, output $14.00/1M tokens.
  • Supports images, prompt cache (24h retention), and apply_patch tool.
  • Excludes apply_diff and write_to_file tools.

^{This description was created by for a60521b. You can customize this summary. It will automatically update as commits are pushed.}

[roomote]

Oroocle   See task on Roo Cloud

Review complete. No issues found in this change.

• No issues found

_{Mention @roomote in a comment to request specific changes to this pull request or fix all unresolved issues.}