chore: remove hardcoded parameters from nooa client

[gaiadilorenzo]

Summary

Remove hardcoded parameters from nooa client.

Why? Parameter "none" in reasoning was refused and raised an error.

Related Issue

There is currently no way to pass parameters configurations to the client model.

Changes

Type of Change

• Bug fix
• Code change with documentation updates
• Documentation only
• Contributor tooling or automation
• CI, build, or test infrastructure

Quality Gates

• Tests added or updated for changed behavior
• Existing tests cover changed behavior — justification:
• Tests not applicable — justification:
• Documentation updated for user-visible behavior
• [] Documentation not applicable — justification: internal change

Verification

• Pull request title follows the repository's Conventional Commit format
• Every commit includes an appropriate Signed-off-by: trailer
• uv run pre-commit run -a passes, or any blocked checks are identified below
• Targeted tests pass, or tests are marked not applicable above
• No secrets, API keys, or credentials are included

Targeted validation:

Summary by CodeRabbit

• Bug Fixes

  • Simplified OpenAI request configuration for more predictable handling.
  • Preserved compatibility for supported request flows.

• Documentation

  • Added troubleshooting guidance for function-tool errors related to reasoning_effort.
  • Explained how to set reasoning_effort to none for a provider and how request-level settings interact with provider defaults.

• Tests

  • Updated validation coverage to reflect the streamlined configuration and preserve existing behavior.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 84f6c64d-50b9-4400-84df-a0e04cf23515

📥 Commits

Reviewing files that changed from the base of the PR and between b10cfb4 and 2912e40.

📒 Files selected for processing (1)

• docs/run-inference/about.mdx

🚧 Files skipped from review as they are similar to previous changes (1)

• docs/run-inference/about.mdx

---

📝 Walkthrough

Walkthrough

The OpenAI model client no longer queries LiteLLM for reasoning capabilities or passes reasoning_effort. Related tests are removed. Inference documentation adds troubleshooting guidance for provider-specific reasoning-effort configuration.

Changes

OpenAI reasoning configuration

Layer / File(s)	Summary
Remove reasoning-effort handling packages/nemo_platform_plugin/src/nemo_platform_plugin/nooa_model_client.py, packages/nemo_platform_plugin/tests/test_nooa_model_client.py	The client removes the LiteLLM model-info import, capability helper, reasoning-effort constant, and constructor argument. Tests remove related helper tests and assertions.
Document reasoning-effort troubleshooting docs/run-inference/about.mdx	The documentation describes unsupported reasoning_effort errors, provider configuration, and per-request overrides.

Suggested reviewers: aleckhoury, schuellc-nvidia

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly and concisely describes the removal of hardcoded parameters from the NOOA client.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch fix-remove-hardcoded-reasoning-effort/gdilorenzo

---

_{Comment @coderabbitai help to get the list of available commands.}

[github-actions]

Suite	Lines Covered	Line Rate	Branch Rate
Unit Tests	32006/40705	78.6%	63.4%
Integration Tests	18571/38631	48.1%	20.8%

[coderabbitai]

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@docs/run-inference/about.mdx`:
- Around line 316-318: Update the provider requirements guidance near the
`--default-extra-body` explanation to explicitly state that function-tool
requests may override `reasoning_effort` only with `"none"`, preventing
per-request non-`none` values that are rejected by the validation described near
line 303.

🪄 Autofix

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: aa95c11b-1042-402a-9cea-5131892890b5

📥 Commits

Reviewing files that changed from the base of the PR and between 173b837 and b10cfb4.

📒 Files selected for processing (1)

• docs/run-inference/about.mdx

[github-actions]

🌿 Preview your docs: https://nvidia-preview-pr-1249-fix-remove-hardcoded-reasoning-effort-g.docs.buildwithfern.com/nemo-platform