fix(backends): forward the standard service_tier param (litellm + anyllm)

[chopratejas]

Description

service_tier is a standard provider request field (OpenAI flex/default/priority, Anthropic auto/standard_only), but the SDK-translation backends rebuilt the upstream request from a fixed field whitelist and silently dropped it — so a client that set service_tier had it discarded on --backend litellm/anyllm. The direct passthrough already forwards it; this makes the translation backends do the same, alongside temperature/top_p/tools.

Type of Change

• Bug fix (non-breaking change that fixes an issue)

Changes Made

• backends/litellm.py (Anthropic path): forward service_tier when present (the OpenAI path already forwards unconsumed fields via _build_openai_extra_body).
• backends/anyllm.py: add service_tier to the forwarded params (both the Anthropic whitelist and the OpenAI param list).

Testing

• Unit tests pass (pytest)
• Linting passes (ruff check)
• Type checking passes (mypy)
• New test added

Test Output

$ python -m pytest tests/test_backend_anyllm.py -q
16 passed in 2.51s

$ ruff check headroom/backends/litellm.py headroom/backends/anyllm.py
All checks passed!

$ mypy headroom/backends/anyllm.py headroom/backends/litellm.py   # 0 new errors

Real Behavior Proof

• Environment: local, FakeAnyLLM instance capturing acompletion kwargs.
• Steps: send_message({..., "service_tier": "standard_only"}).
• Observed: instance.calls[0]["service_tier"] == "standard_only" — the param reaches the SDK call (previously absent).
• Not tested: live provider round-trip (no keys in CI); relies on the SDK forwarding standard params.

Checklist

• Self-reviewed
• Tests added and passing
• I did not edit CHANGELOG.md

[github-actions]

PR governance

This PR does not yet satisfy the required template fields:

• Missing required section Review Readiness.
• Fill in Real Behavior Proof → Exact command / steps.
• Fill in Real Behavior Proof → Observed result.
• Check I have performed a self-review before requesting human review.
• Check This PR is ready for human review or convert the PR back to draft.

Please update the PR body, or move the PR back to draft while it is still in progress.

[JerrettDavis]

This needs one more change before approval.

The LiteLLM Anthropic translation path now forwards service_tier in send_message, but the matching stream_message path still omits it. That leaves streamed Anthropic-format requests through --backend litellm with the same silent-drop behavior this PR is fixing for non-streaming requests.

Please add the same if "service_tier" in body: kwargs["service_tier"] = body["service_tier"] handling to LiteLLMBackend.stream_message, and add/extend a LiteLLM-focused test so both the send and stream Anthropic translation paths are covered. The any-llm coverage is useful, but it does not protect the LiteLLM path where the remaining omission is.

[codecov-commenter]

⚠️ Please install the to ensure uploads and comments are reliably processed by Codecov.

Codecov Report

❌ Patch coverage is 33.33333% with 4 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
headroom/backends/anyllm.py	50.00%	1 Missing and 1 partial ⚠️
headroom/backends/litellm.py	0.00%	1 Missing and 1 partial ⚠️

📢 Thoughts on this report? Let us know!