docs(proxy): clarify x-litellm-model-group vs provider model id#25497
Conversation
Made-with: Cursor
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Greptile SummaryThis docs-only PR clarifies the distinction between Confidence Score: 5/5Safe to merge; documentation-only change with no code or schema impact. All findings are P2 style suggestions. The core clarification around model-group vs model-id is accurate and adds real value. No code paths, tests, or migrations are affected. No files require special attention.
|
| Filename | Overview |
|---|---|
| docs/my-website/docs/proxy/response_headers.md | Docs-only clarification: sharpened table descriptions for x-litellm-model-group / x-litellm-model-id, added YAML example and illustrative values table; no code changes. |
Flowchart
%%{init: {'theme': 'neutral'}}%%
flowchart TD
Client["Client request\n(model: my-chat-model)"]
Proxy["LiteLLM Proxy\nroutes via model_list"]
Upstream["Upstream Provider\n(e.g. OpenAI gpt-4o-mini)"]
Headers["Response Headers set by Proxy"]
Client --> Proxy
Proxy -->|"resolves model_name → litellm_params.model"| Upstream
Upstream --> Proxy
Proxy --> Headers
Headers --> H1["x-litellm-model-group: my-chat-model\n(model_list[].model_name)"]
Headers --> H2["x-litellm-model-id: 7c9f2a1b…\n(model_info.id — deployment row)"]
Headers --> H3["x-litellm-call-id, x-litellm-version,\nx-litellm-model-api-base, …"]
Reviews (2): Last reviewed commit: "Fix docs on feedback" | Re-trigger Greptile
Congrats! CodSpeed is installed 🎉
You will start to see performance impacts in the reports once the benchmarks are run from your default branch.
|
| | `x-litellm-model-group` | string | Model group identifier | | | ||
| | `x-litellm-model-group` | string | Routed **`model_name`** from `model_list` (client-visible alias) | | | ||
|
|
||
| This header names the **model group** LiteLLM selected: the **`model_name`** entry in your proxy `model_list`—the same value clients send as `model`. It does **not** mirror **`litellm_params.model`** (the actual provider model id LiteLLM forwards upstream). Use **`x-litellm-model-id`** when you need the deployment identifier. |
There was a problem hiding this comment.
can you make this simpler ? I don't know what this means
Can you give me clear examples of diff headers and what they mean on a table with example values
|
IT is a docs change, all the failing test should be unrelated to it |
…itellm_docs-response-headers-model-group
|
Too many files changed for review. ( |
|
|
Low: No security issues foundThis PR is a large mixed change covering CI refactoring, docs updates, model registry additions, and several feature additions (DashScope image generation, Gemini embedding 2 GA, reasoning effort normalization, Responses API bridge). The security-relevant changes are all improvements: additional parameters banned from request bodies ( Status: 0 open Posted by Veria AI · 2026-04-24T16:43:43.440Z |
|
| GitGuardian id | GitGuardian status | Secret | Commit | Filename | |
|---|---|---|---|---|---|
| 31539530 | Triggered | Generic Password | c4c9af0 | .github/workflows/_test-unit-services-base.yml | View secret |
| 29203053 | Triggered | Generic Password | c4c9af0 | .circleci/config.yml | View secret |
🛠 Guidelines to remediate hardcoded secrets
- Understand the implications of revoking this secret by investigating where it is used in your code.
- Replace and store your secrets safely. Learn here the best practices.
- Revoke and rotate these secrets.
- If possible, rewrite git history. Rewriting git history is not a trivial act. You might completely break other contributing developers' workflow and you risk accidentally deleting legitimate data.
To avoid such incidents in the future consider
- following these best practices for managing and storing secrets including API keys and other credentials
- install secret detection on pre-commit to catch secret before it leaves your machine and ease remediation.
🦉 GitGuardian detects secrets in your source code to help developers and security teams secure the modern development process. You are seeing this because you or someone else with access to this repository has authorized GitGuardian to scan your pull request.
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
a0c52cd
into
litellm_internal_staging
Documents that
x-litellm-model-groupreflects proxymodel_listmodel_name(client alias), notlitellm_params.model, and points readers tox-litellm-model-idfor the deployment identifier.