Add Custom routers documentation page#256
Conversation
Add a standalone Custom routers page under Inference & providers covering complexity-based and rule-based routing, creating routers in settings or as YAML files, selecting them from the model picker, and team-synced routers for Enterprise admins. Cross-reference the page from Model choice, the sidebar, and the Admin Panel Models section. Co-Authored-By: Oz <oz-agent@warp.dev>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Tighten the intro, sharpen Key features labels, smooth a few sentences, and remove minor redundancy. Co-Authored-By: Oz <oz-agent@warp.dev>
|
I'm starting a first review of this pull request. You can view the conversation on Warp. I completed the review and no human review was requested for this pull request. Comment Powered by Oz |
![oz-for-oss[bot]](https://avatars.githubusercontent.com/in/3450139?s=60&v=4){kind=small}
There was a problem hiding this comment.
Overview
This PR adds a new Custom routers documentation page, links it from Model choice and Admin Panel docs, and adds the page to the Inference & providers sidebar. The structure and YAML examples mostly match the implementation, and I did not find security or spec-alignment issues.
Concerns
- The Warp app currently exposes the router type dropdown as Complexity and Prompt, with prompt rules labeled Description and Model; the draft documents Complexity-based, Rule-based, and Classification prompt, which would send readers looking for UI labels that are not present.
Verdict
Found: 0 critical, 1 important, 0 suggestions
Request changes
Comment /oz-review on this pull request to retrigger a review (up to 3 times on the same pull request).
Powered by Oz
| 3. Under **Routing type**, choose **Complexity-based** or **Rule-based**. | ||
| 4. Configure the routing: | ||
| * **Complexity-based** - Select a **Default** model, then assign models to **Easy**, **Medium**, and **Hard**. | ||
| * **Rule-based** - Select a **Default model**, then click **Add rule** for each rule, write a **Classification prompt** describing when to use the model, and select the model. Rules are matched top to bottom, so order them by precedence. |
There was a problem hiding this comment.
| 3. Under **Routing type**, choose **Complexity-based** or **Rule-based**. | |
| 4. Configure the routing: | |
| * **Complexity-based** - Select a **Default** model, then assign models to **Easy**, **Medium**, and **Hard**. | |
| * **Rule-based** - Select a **Default model**, then click **Add rule** for each rule, write a **Classification prompt** describing when to use the model, and select the model. Rules are matched top to bottom, so order them by precedence. | |
| 3. Under **Routing type**, choose **Complexity** or **Prompt**. | |
| 4. Configure the routing: | |
| * **Complexity** - Select a **Default** model, then assign models to **Easy**, **Medium**, and **Hard**. | |
| * **Prompt** - Select a **Default model**, then click **+ Add rule** for each rule, enter a **Description** for when to use the model, and select the **Model**. Rules are matched top to bottom, so order them by precedence. |
There was a problem hiding this comment.
i'll keep this as is since we'll be changing the copy afterwards
Document that router targets must be Warp-supported models (custom inference endpoint models can't be targets) and that, like Auto models, custom routers consume Warp credits and don't use your BYOK keys. Co-Authored-By: Oz <oz-agent@warp.dev>
Update the example routers to current models (Claude Opus 4.8, Claude Sonnet 4.6) and add Claude Opus 4.8 to the Model choice table. Co-Authored-By: Oz <oz-agent@warp.dev>
| default: claude-4-6-sonnet-high | ||
| routing: | ||
| - description: debugging or fixing failing tests | ||
| model: claude-4-8-opus-high |
There was a problem hiding this comment.
might wanna link out to the page that lists out the model IDs? https://docs.warp.dev/agent-platform/inference/model-choice/#available-models
(just realized that page is missing some entries)
There was a problem hiding this comment.
Good call — updated the examples to link to the model IDs list (/agent-platform/inference/model-choice/#available-models) in 599d4ed. Opening a separate PR to add the missing public model entries to that page.
There was a problem hiding this comment.
updated and added some missing OSS models
|
|
||
| A custom router resolves to a concrete model, so credit usage matches whichever model the router selects for each task. See [Credits](/support-and-community/plans-and-billing/credits/) for how credits are consumed. | ||
|
|
||
| Like Warp's built-in Auto models, custom routers consume Warp credits and don't draw on your own provider keys, even if you've configured [Bring Your Own API Key (BYOK)](/agent-platform/inference/bring-your-own-api-key/). To run a model on your own key, select that model directly instead of a router. |
There was a problem hiding this comment.
I'm actually not sure about this - need to check lol
Point the model_id reference to the Model choice #available-models section so readers can quickly find valid model IDs. Co-Authored-By: Oz <oz-agent@warp.dev>
2 participants
Summary
Adds a standalone Custom routers documentation page under Inference & providers, and cross-references it from related pages.
Custom routers let users define a router that automatically selects a concrete model for each task, using either complexity-based or rule-based routing. Admins can publish team-synced routers to an entire team (Enterprise).
Changes
agent-platform/inference/custom-routers.mdx- how routing works, the two routing types (complexity-based and rule-based), creating a router in settings, authoring routers as YAML files, selecting a router from the model picker, team-synced routers for Enterprise admins, and credit/availability behavior.src/sidebar.tsunder Inference & providers, after Model choice.Notes for reviewers
style_lint --changedpasses for the new page. Two pre-existing screenshot-width warnings on unrelated figures inmodel-choice.mdxandadmin-panel.mdxare left unchanged.Conversation: https://staging.warp.dev/conversation/2a9a2183-616a-474c-bad3-36ea7a1a813b
Run: https://oz.staging.warp.dev/runs/019f0024-3ae2-7680-bebe-e15a191fee16
Plans:
This PR was generated with Oz.