View which models Weave Router can choose, grouped by provider. Enable or disable individual models or entire providers, set a preference order, and review the updated selection without restarting the router.
List the models the Weave Router may route to, and turn them on or off.
Review the instructions the agent will receive before you install.
When the user invokes $router-models, show which models this
installation lets the router pick from, and change that selection when asked.
This is the same list — and the same stored setting — as the checkboxes on the
router dashboard's settings page.
Start by running:
npx --package @weave-os/router -y -- weave-router models --codex{{SCOPE}}
That prints every deployed model grouped by provider, with [x] for models the
router may pick and [ ] for models it may not. Present it back as a compact
checklist in that same [x] / [ ] form, keeping the provider grouping and the
exact model ids — the user selects models by id.
Then:
weave-router models enable <id>... --codex{{SCOPE}} or
weave-router models disable <id>... --codex{{SCOPE}} (add providers before
enable/disable to switch a whole provider). Several ids can go in one
call. Then re-run the list and show the result.Other things they might ask for:
weave-router models prefer <id> <id>... --codex{{SCOPE}} (order matters), or
weave-router models prefer clear --codex{{SCOPE}} to drop the ranking.weave-router models providers --codex{{SCOPE}}.If the command reports that this router doesn't expose model selection, that's a Weave-hosted router: model selection belongs to the whole organization there, so tell the user to change it at https://router.workweave.ai/models — don't try to work around it. Its listing carries no on/off state, so present it as a plain list; don't infer which models are enabled.
Disabling a model takes effect on the router's next routing decision; no restart is needed.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Investigate unexpected Claude Code output by matching a session’s local transcript with production router logs. Identify the serving model and trace response conversion code to explain empty blocks, tool output, or other rendering symptoms.
Investigate a Codex CLI session by matching its local conversation record with production router logs. Use the session ID to examine missing reasoning summaries, routing markers, unexpected models, or unusual tool calls and trace relevant code paths.
Switch Codex from Weave Router back to its normal provider for future sessions. Keep the existing login and router configuration, receive the command result, and retain the option to turn routing on again later.
Pin the current Codex session to a chosen model through Weave Router. This short alias accepts a model ID, runs the included script, and reports the router’s response while allowing the current turn to continue.
Pin the current Codex session to a specific model through Weave Router by providing its model ID. The skill applies the pin, continues the same turn, and reports the router's response.
Set up language servers, programs that help tools understand source code, for Go, TypeScript, Python, and Rust. Check missing prerequisites, install them with approval, and verify the lsp tool against a real source file.