chore: allow passing scope id for watsonx inferencing

[MateuszOssGit]

Relevant issues

Allow passing scope id for watsonx inferencing

Pre-Submission checklist

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

• I have Added testing in the tests/litellm/ directory, Adding at least 1 test is a hard requirement - see details
• My PR passes all unit tests on make test-unit
• My PR's scope is as isolated as possible, it only solves 1 specific problem
• poetry run pytest tests/test_litellm/llms/watsonx/test_watsonx.py -x -vv
  
• poetry run pytest tests/llm_translation/test_watsonx.py -x -vv
  

CI (LiteLLM team)

CI status guideline:

• 50-55 passing tests: main is stable with minor issues.
• 45-49 passing tests: acceptable but needs attention
• <= 40 passing tests: unstable; be careful with your merges and assess the risk.

• Branch creation CI run
  Link:

• CI run for the last commit
  Link:

• Merge / cherry-pick CI run
  Links:

Type

🐛 Bug Fix
🧹 Refactoring
✅ Test

Changes

The changes introduced allow for the successful completion of the following scenarios:

ENV: Python LieteLLM package 1.80.15

1. The watsonx.ai API docs (https://cloud.ibm.com/apidocs/watsonx-ai#text-chat) allow to run inference in both space and project scopes. But with current impelmentation in LiteLLM, there is impossible to run inference in space scope:

from litellm import completion

## Call WATSONX `/text/chat` endpoint - supports function calling
response = completion(
  model="watsonx/meta-llama/llama-3-1-8b-instruct",
  messages=[{ "content": "what is your favorite colour?","role": "user"}],
  space_id="space_id"
)

Error:

AuthenticationError: litellm.AuthenticationError: watsonxException - Error: Watsonx project_id not set. Set WX_PROJECT_ID in environment variables or pass in as a parameter.

2. The deployments does not require scope id in payload. Also, the deployment can be created in project scope - current implementation only consider deployments in space.

from litellm import completion

response = completion(
    model="watsonx_text/deployment/6d6783d5-d8bb-4088-b152-6c9fa7fb2f0a",
    messages=[{"role": "user", "content": "What is the capital of France?"}],
    project_id="project_id",
)

Error:

...
APIConnectionError: litellm.APIConnectionError: Watsonx_textException - Error: space_id is required for models called using the 'deployment/' endpoint. Pass in the space_id as a parameter or set it in the WX_SPACE_ID environment variable.

second scenario:

from litellm import completion

response = completion(
    model="watsonx_text/deployment/ef1401f2-1358-4052-b729-4050e50bfc16",
    messages=[{"role": "user", "content": "What is the capital of France?"}],
    space_id="space_id",
    project_id="project_id"
)

Error:

APIConnectionError: litellm.APIConnectionError: Watsonx_textException - {"errors":[{"code":"json_validation_error","message":"Json document validation error: 'project_id' or 'space_id' cannot be specified in the request body","more_info":"https://cloud.ibm.com/apidocs/watsonx-ai#deployments-text-generation"}],"trace":"4e0bb86eadae2093ac9d4bc6cb5e5c81","status_code":400}

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Review	Updated (UTC)
litellm	Ready	Preview, Comment	Jan 12, 2026 0:29am

[MateuszOssGit]

Failing tests are not related my changes

@Sameerlite @Chesars @Harshit28j @ishaan-berri @krrishdholakia Could you please review my PR and merge if possible?
These changes are quite important for our AI Agents templates in https://github.com/IBM/watsonx-developer-hub/tree/main/agents/base

[MateuszOssGit]

@ishaan-jaff Could you please review my PR and merge if possible?