feat(openrouter/openai/gpt-6-astra-pro): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for openrouter/openai/gpt-6-astra-pro.

---

Note

Low Risk
Adds a new static model definition only; no runtime logic, auth, or data-handling changes.

Overview
Registers OpenRouter model openai/gpt-6-astra-pro via a new provider YAML so routing, pricing, and capability metadata are available to the rest of the stack.

The entry defines chat mode with thinking enabled, a 1.05M context window and 128k max output, text/image/PDF inputs, and features such as function calling, tool choice, structured/JSON output, and prompt caching with per-token and cache read/create costs.

^{Reviewed by Cursor Bugbot for commit 2bf39cc. Bugbot is set up for automated code reviews on this repo. Configure here.}

[cursor]

Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit a81eaa4. Configure here.}

[cursor]

Missing max_tokens output limit override

Medium Severity

This fuller entry advertises limits.max_output_tokens of 128000 but does not override inherited params.max_tokens. OpenRouter default.yaml caps maxValue at 4096, so callers cannot request the model's advertised output length.

 

^{Triggered by learned rule: Override max_tokens maxValue to match limits}

^{Reviewed by Cursor Bugbot for commit a81eaa4. Configure here.}

[github-actions]

/test-models