Feat/add commandcode provider

[ImajiPietersz]

TLDR

Problem this solves:

• Adds LiteLLM support for CommandCode API endpoints
• Enables users to call CommandCode models through LiteLLM

How it solves it:

• Adds OpenAI-compatible CommandCode chat completion support
• Adds Anthropic-compatible CommandCode messages API support
• Handles CommandCode API authentication and endpoint routing

Relevant issues

Fixes #27582

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

• Verified with make lint
• Verified formatting, linting, and type checks pass

Type

🆕 New Feature

Changes

• Added CommandCode provider implementation
• Added OpenAI-compatible provider routing
• Added Anthropic-compatible provider routing
• Added CommandCode API credential handling

Final Attestation

• The tests check the right things, including the edge cases, and regressions in the respective real-world customer use-cases are not possible after this PR

[greptile-apps]

Greptile Summary

Adds CommandCode as a chat provider with OpenAI- and Anthropic-compatible routing.

• Registers CommandCode provider detection, credentials, and pricing metadata.
• Adds shared HTTP-handler integration for OpenAI-compatible models.
• Adds a Claude-specific Anthropic dispatch path.
• Adds configuration and mocked tests for provider URLs and authentication.

Confidence Score: 3/5

The PR is not safe to merge until CommandCode Claude requests are wired to a usable provider configuration and the required authentication behavior.

OpenAI-compatible CommandCode requests use the shared HTTP handler, but every Claude request reaches an Anthropic handler that cannot resolve COMMANDCODE and raises before making the upstream request.

Files Needing Attention: litellm/main.py, litellm/llms/commandcode/chat/transformation.py

Important Files Changed

Filename	Overview
litellm/main.py	Adds CommandCode dispatch, but the Claude branch cannot resolve or apply its provider configuration.
litellm/llms/commandcode/chat/transformation.py	Defines OpenAI and Anthropic endpoint/auth transformations, although the Anthropic configuration is disconnected from runtime dispatch.
litellm/litellm_core_utils/get_llm_provider_logic.py	Adds CommandCode prefix detection and OpenAI-compatible credential resolution.
litellm/types/utils.py	Registers commandcode in the provider enum.
model_prices_and_context_window.json	Adds pricing and capability metadata for two CommandCode models.
tests/test_litellm/llms/commandcode/test_commandcode_chat_transformation.py	Covers configuration helpers and the OpenAI runtime path but does not exercise the broken Claude runtime dispatch.

_{Reviews (1): Last reviewed commit: "Format CommandCode provider changes" | Re-trigger Greptile}

[greptile-apps]

Claude provider config is disconnected

When a commandcode/claude-* request reaches this branch, the Anthropic handler looks up LlmProviders.COMMANDCODE, which has no ProviderConfigManager mapping, and raises Provider config not found before sending the request. The instantiated commandcode_anthropic_config is never used here; additionally, the handler validates with the base AnthropicConfig, producing x-api-key authentication instead of CommandCode's required Bearer header.

Rule Used: Block new LLM Provider integrations if they're ope... (source)

Knowledge Base Used: LLM Provider Adapters

[codecov]

Codecov Report

❌ Patch coverage is 85.36585% with 12 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
litellm/llms/commandcode/chat/transformation.py	84.44%	7 Missing ⚠️
litellm/main.py	87.09%	4 Missing ⚠️
...tellm/litellm_core_utils/get_llm_provider_logic.py	75.00%	1 Missing ⚠️

📢 Thoughts on this report? Let us know!

[codspeed-hq]

Merging this PR will not alter performance

✅ 31 untouched benchmarks

---

_{Comparing ImajiPietersz:feat/add-commandcode-provider (770acef) with litellm_internal_staging (2412326)}