How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

wow-viewer Editor UI Surface Plan - Prompt

Name: wow-viewer Editor UI Surface Plan
Author: akspa0

Prompt file imported from akspa0/parp-tools (.codex/prompts/wow-viewer-editor-ui-surface-plan.md). Copyright stays with the author.

Design the wow-viewer editor UI surface so the current viewer and editing workflows become organized workspaces instead of scattered debug panels.

Read First

gillijimproject_refactor/memory-bank/activeContext.md
gillijimproject_refactor/memory-bank/progress.md
gillijimproject_refactor/src/MdxViewer/memory-bank/activeContext.md
gillijimproject_refactor/plans/wow_viewer_editor_plan_2026-04-03.md
wow-viewer/README.md
AGENTS.md

Goal

Define how wow-viewer should expose distinct viewer and editor workspaces, preset panel layouts, and task-centered tool groupings so map editing becomes intentional and discoverable.

Existing UI Inputs To Account For

left and right sidebars plus docked inspectors in MdxViewer
chunk clipboard panel and editor overlays
alpha-mask import or export menus and terrain export surfaces
PM4 workbench tabs and overlay controls
asset catalog, minimap, capture automation, and map export workflows

Non-Negotiable Constraints

The new UI organization must sit on shared services; it cannot become a new source of format or save logic.
Viewer mode and editor mode should be workspace profiles or panel presets, not separate apps.
Editing affordances must make dirty state, current target, and save scope obvious.
Existing useful tools such as chunk clipboard and alpha-mask import should be preserved, but reorganized around editing tasks instead of buried in generic menus.
Avoid a generic "toolbox" dump. Group tools by task: terrain, objects, PM4 evidence, save/publish, inspection.

What The Plan Must Produce

workspace or mode model for viewer vs editor
panel and dock preset layout by mode
task-grouped tool families for editing
selection, target, dirty-state, and save-status affordances
which legacy panels survive, merge, move, or die
the first UI-only slice to implement safely
risks if the current scattered UI is left in place

Deliverables

Return all items:

mode or workspace model
panel tree per mode
task-grouped editor tool map
status or affordance design
legacy panel migration decisions
first UI slice
remaining UI risks

First Output

Start with:

the editor tasks that most need a dedicated workspace
the current panels or menus that should be regrouped first
the minimum mode-switch model that would already improve the tool
what the UI slice should not try to solve yet

Install wow-viewer Editor UI Surface Plan and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

Design the `wow-viewer` editor UI surface so the current viewer and editing workflows become organized workspaces instead of scattered debug panels. ## Read First 1. `gillijimproject_refactor/memory-bank/activeContext.md` 2. `gillijimproject_refactor/memory-bank/progress.md` 3. `gillijimproject_refactor/src/MdxViewer/memory-bank/activeContext.md` 4. `gillijimproject_refactor/plans/wow_viewer_editor_plan_2026-04-03.md` 5. `wow-viewer/README.md` 6. `AGENTS.md` ## Goal Define how `wow-viewer` should expose distinct viewer and editor workspaces, preset panel layouts, and task-centered tool groupings so map editing becomes intentional and discoverable. ## Existing UI Inputs To Account For - left and right sidebars plus docked inspectors in `MdxViewer` - chunk clipboard panel and editor overlays - alpha-mask import or export menus and terrain export surfaces - PM4 workbench tabs and overlay controls - asset catalog, minimap, capture automation, and map export workflows ## Non-Negotiable Constraints - The new UI organization must sit on shared services; it cannot become a new source of format or save logic. - Viewer mode and editor mode should be workspace profiles or panel presets, not separate apps. - Editing affordances must make dirty state, current target, and save scope obvious. - Existing useful tools such as chunk clipboard and alpha-mask import should be preserved, but reorganized around editing tasks instead of buried in generic menus. - Avoid a generic "toolbox" dump. Group tools by task: terrain, objects, PM4 evidence, save/publish, inspection. ## What The Plan Must Produce 1. workspace or mode model for viewer vs editor 2. panel and dock preset layout by mode 3. task-grouped tool families for editing 4. selection, target, dirty-state, and save-status affordances 5. which legacy panels survive, merge, move, or die 6. the first UI-only slice to implement safely 7. risks if the current scattered UI is left in place ## Deliverables Return all items: 1. mode or workspace model 2. panel tree per mode 3. task-grouped editor tool map 4. status or affordance design 5. legacy panel migration decisions 6. first UI slice 7. remaining UI risks ## First Output Start with: 1. the editor tasks that most need a dedicated workspace 2. the current panels or menus that should be regrouped first 3. the minimum mode-switch model that would already improve the tool 4. what the UI slice should not try to solve yet

{ "prompt": "Design the `wow-viewer` editor UI surface so the current viewer and editing workflows become organized workspaces instead of scattered debug panels.\n\n## Read First\n\n1. `gillijimproject_refactor/memory-bank/activeContext.md`\n2. `gillijimproject_refactor/memory-bank/progress.md`\n3. `gillijimproject_refactor/src/MdxViewer/memory-bank/activeContext.md`\n4. `gillijimproject_refactor/plans/wow_viewer_editor_plan_2026-04-03.md`\n5. `wow-viewer/README.md`\n6. `AGENTS.md`\n\n## Goal\n\nDefine how `wow-viewer` should expose distinct viewer and editor workspaces, preset panel layouts, and task-centered tool groupings so map editing becomes intentional and discoverable.\n\n## Existing UI Inputs To Account For\n\n- left and right sidebars plus docked inspectors in `MdxViewer`\n- chunk clipboard panel and editor overlays\n- alpha-mask import or export menus and terrain export surfaces\n- PM4 workbench tabs and overlay controls\n- asset catalog, minimap, capture automation, and map export workflows\n\n## Non-Negotiable Constraints\n\n- The new UI organization must sit on shared services; it cannot become a new source of format or save logic.\n- Viewer mode and editor mode should be workspace profiles or panel presets, not separate apps.\n- Editing affordances must make dirty state, current target, and save scope obvious.\n- Existing useful tools such as chunk clipboard and alpha-mask import should be preserved, but reorganized around editing tasks instead of buried in generic menus.\n- Avoid a generic \"toolbox\" dump. Group tools by task: terrain, objects, PM4 evidence, save/publish, inspection.\n\n## What The Plan Must Produce\n\n1. workspace or mode model for viewer vs editor\n2. panel and dock preset layout by mode\n3. task-grouped tool families for editing\n4. selection, target, dirty-state, and save-status affordances\n5. which legacy panels survive, merge, move, or die\n6. the first UI-only slice to implement safely\n7. risks if the current scattered UI is left in place\n\n## Deliverables\n\nReturn all items:\n\n1. mode or workspace model\n2. panel tree per mode\n3. task-grouped editor tool map\n4. status or affordance design\n5. legacy panel migration decisions\n6. first UI slice\n7. remaining UI risks\n\n## First Output\n\nStart with:\n\n1. the editor tasks that most need a dedicated workspace\n2. the current panels or menus that should be regrouped first\n3. the minimum mode-switch model that would already improve the tool\n4. what the UI slice should not try to solve yet", "variables": [], "notes": "Plan wow-viewer editor-mode UI and panel organization. Use when the ask is viewer-vs-editor workspace switching, preset panel layouts, editor tool clustering, PM4 and terrain tool surfacing, or making wow-viewer feel like the modern map viewer-editor instead of a pile of debug windows. Arguments: Optional panel family, workspace mode, dock preset, or editing workflow to prioritize.", "metadata": { "source": { "provider": "github-codex-prompts", "repository": "https://github.com/akspa0/parp-tools", "path": ".codex/prompts/wow-viewer-editor-ui-surface-plan.md", "ref": "4f7fb94cfad6bf6348c55c28ae9361c2d2fd9cb7", "url": "https://github.com/akspa0/parp-tools/blob/4f7fb94cfad6bf6348c55c28ae9361c2d2fd9cb7/.codex/prompts/wow-viewer-editor-ui-surface-plan.md", "key": "akspa0/parp-tools/.codex/prompts/wow-viewer-editor-ui-surface-plan.md" } } }

wow-viewer Editor UI Surface Plan

About

Read First

Goal

Existing UI Inputs To Account For

Non-Negotiable Constraints

What The Plan Must Produce

Deliverables

First Output

Install wow-viewer Editor UI Surface Plan and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Use it

Manifest

Reviews