feat(github_copilot): add gpt-5.6 luna, terra, sol

[derrik-fleming]

Relevant issues

Fixes #33893

Linear ticket

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

• I have added meaningful tests
• My PR passes all CI/CD checks (e.g., lint, format, unit tests)
• My PR's scope is as isolated as possible; it only solves 1 specific problem
• I have received a Greptile Confidence Score of at least 4/5 before requesting a maintainer review (Greptile reviews automatically once the PR is opened; only comment @greptileai to re-request a review after pushing changes)

Screenshots / Proof of Fix

Type

🆕 New Feature
🐛 Bug Fix

Changes

added 5.6 models for GitHub Copilot in model_prices_and_context_window.json

[CLAassistant]

All committers have signed the CLA.

[greptile-apps]

Greptile Summary

Adds three new GitHub Copilot gpt-5.6 model variants (luna, terra, sol) to the LiteLLM model pricing catalog, following the existing pattern for responses-mode GitHub Copilot entries.

• Both model_prices_and_context_window.json and the bundled backup file receive identical entries for each model, with mode: "responses", max_tokens: 128000, and the appropriate per-token pricing tiers.
• A parametrized unit test is added that uses the autouse local-catalog fixture to verify each model's metadata and that ProviderConfigManager resolves the correct GithubCopilotResponsesAPIConfig for all three models — no real network calls are made.

Confidence Score: 5/5

Safe to merge — the change is purely additive JSON data with no logic modifications.

The PR adds three new model entries to two JSON files and a corresponding mock-based unit test. The entries are consistent with each other and with the existing responses-mode catalog entries. No production logic is altered, and the test confirms the metadata is correct without making live API calls.

No files require special attention.

Important Files Changed

Filename	Overview
model_prices_and_context_window.json	Adds three new github_copilot gpt-5.6 model entries (luna, terra, sol) with consistent fields matching the pattern of existing responses-mode catalog entries
litellm/model_prices_and_context_window_backup.json	Identical additions to the backup file; the three new gpt-5.6 model entries are consistent with the primary JSON file
tests/test_litellm/llms/github_copilot/responses/test_github_copilot_responses_transformation.py	Adds a parametrized test that validates all three new model catalog entries; relies on the module-level autouse fixture to pin litellm.model_cost to the local backup file, so no real network calls are made

_{Reviews (1): Last reviewed commit: "feat(github_copilot): add gpt-5.6 luna, ..." | Re-trigger Greptile}

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

[codspeed-hq]

Merging this PR will not alter performance

✅ 31 untouched benchmarks

---

_{Comparing derrik-fleming:feat/add-gh-copilot-gpt-5-6 (3192c49) with litellm_internal_staging (9de3315)¹}

Footnotes

1. No successful run was found on litellm_internal_staging (9bca9df) during the generation of this report, so 9de3315 was used instead as the comparison base. There might be some changes unrelated to this pull request in this report. ↩

[bamarc]

Any update on this?

[alexandrescieux]

gpt-5.6 Luna, Terra and Sol via GitHub Copilot would really be appreciated here