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 Bootstrap Layout Plan - Prompt

Name: wow-viewer Bootstrap Layout Plan
Author: akspa0

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

Design the concrete repository and solution bootstrap plan for https://github.com/akspa0/wow-viewer.

Read First

gillijimproject_refactor/memory-bank/activeContext.md
gillijimproject_refactor/memory-bank/progress.md
gillijimproject_refactor/src/MdxViewer/memory-bank/activeContext.md
AGENTS.md
gillijimproject_refactor/plans/v0_5_0_wow_viewer_bootstrap_and_migration_draft_2026-03-25.md

Goal

Produce a concrete repo and solution layout for wow-viewer so the shipping app, shared library, standalone tools, upstream libs, bootstrap scripts, and archaeology-only leftovers stop living in one tangled tree.

Old Repo Inputs To Account For

gillijimproject_refactor/src/MdxViewer
gillijimproject_refactor/src/WoWMapConverter
gillijimproject_refactor/src/gillijimproject-csharp
gillijimproject_refactor/AlphaWDTAnalysisTool
gillijimproject_refactor/AlphaWdtInspector
gillijimproject_refactor/DBCTool
gillijimproject_refactor/DBCTool.V2
gillijimproject_refactor/BlpResizer
gillijimproject_refactor/AlphaLkToAlphaStandalone
gillijimproject_refactor/src/Pm4Research.Cli
gillijimproject_refactor/src/MDX-L_Tool
gillijimproject_refactor/tools/WlAnalyzer
top-level archaeology/source inputs such as parpToolbox, PM4Tool, ADTPrefabTool, and WoWRollback

Non-Negotiable Constraints

The main viewer app must have one obvious home.
First-party shared code must not be mixed into libs/.
Upstream repos must remain external and trackable under libs/.
Tool executables must not each reinvent their own mini-core.
R&D and archaeology leftovers should not quietly become production dependencies.
Do not mirror the old repo structure into the new repo out of laziness.

What The Plan Must Produce

The exact top-level repo tree.
The exact solution/project grouping.
Which projects are app-only, core-only, tool-only, or research-only.
Which upstream repos are baseline bootstrap dependencies versus optional evaluation dependencies.
What bootstrap scripts should do on a clean clone.
What stays in parp-tools instead of moving.
The first bootstrap milestone that proves the repo shape is real.

Deliverables

Return all items:

proposed top-level repo tree
proposed project/solution tree
bootstrap dependency matrix
scripts/bootstrap responsibilities
what stays in parp-tools
first bootstrap milestone
risks if the tree is done badly

First Output

Start with:

the minimum repo tree you would create on day one
the first-party projects that must exist immediately
the upstream repos that should be auto-cloned immediately
what parts of the old repo should not be copied forward blindly

Install wow-viewer Bootstrap Layout 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 concrete repository and solution bootstrap plan for `https://github.com/akspa0/wow-viewer`. ## 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. `AGENTS.md` 5. `gillijimproject_refactor/plans/v0_5_0_wow_viewer_bootstrap_and_migration_draft_2026-03-25.md` ## Goal Produce a concrete repo and solution layout for `wow-viewer` so the shipping app, shared library, standalone tools, upstream libs, bootstrap scripts, and archaeology-only leftovers stop living in one tangled tree. ## Old Repo Inputs To Account For - `gillijimproject_refactor/src/MdxViewer` - `gillijimproject_refactor/src/WoWMapConverter` - `gillijimproject_refactor/src/gillijimproject-csharp` - `gillijimproject_refactor/AlphaWDTAnalysisTool` - `gillijimproject_refactor/AlphaWdtInspector` - `gillijimproject_refactor/DBCTool` - `gillijimproject_refactor/DBCTool.V2` - `gillijimproject_refactor/BlpResizer` - `gillijimproject_refactor/AlphaLkToAlphaStandalone` - `gillijimproject_refactor/src/Pm4Research.Cli` - `gillijimproject_refactor/src/MDX-L_Tool` - `gillijimproject_refactor/tools/WlAnalyzer` - top-level archaeology/source inputs such as `parpToolbox`, `PM4Tool`, `ADTPrefabTool`, and `WoWRollback` ## Non-Negotiable Constraints - The main viewer app must have one obvious home. - First-party shared code must not be mixed into `libs/`. - Upstream repos must remain external and trackable under `libs/`. - Tool executables must not each reinvent their own mini-core. - R&D and archaeology leftovers should not quietly become production dependencies. - Do not mirror the old repo structure into the new repo out of laziness. ## What The Plan Must Produce 1. The exact top-level repo tree. 2. The exact solution/project grouping. 3. Which projects are app-only, core-only, tool-only, or research-only. 4. Which upstream repos are baseline bootstrap dependencies versus optional evaluation dependencies. 5. What bootstrap scripts should do on a clean clone. 6. What stays in `parp-tools` instead of moving. 7. The first bootstrap milestone that proves the repo shape is real. ## Deliverables Return all items: 1. proposed top-level repo tree 2. proposed project/solution tree 3. bootstrap dependency matrix 4. scripts/bootstrap responsibilities 5. what stays in `parp-tools` 6. first bootstrap milestone 7. risks if the tree is done badly ## First Output Start with: 1. the minimum repo tree you would create on day one 2. the first-party projects that must exist immediately 3. the upstream repos that should be auto-cloned immediately 4. what parts of the old repo should not be copied forward blindly

{ "prompt": "Design the concrete repository and solution bootstrap plan for `https://github.com/akspa0/wow-viewer`.\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. `AGENTS.md`\n5. `gillijimproject_refactor/plans/v0_5_0_wow_viewer_bootstrap_and_migration_draft_2026-03-25.md`\n\n## Goal\n\nProduce a concrete repo and solution layout for `wow-viewer` so the shipping app, shared library, standalone tools, upstream libs, bootstrap scripts, and archaeology-only leftovers stop living in one tangled tree.\n\n## Old Repo Inputs To Account For\n\n- `gillijimproject_refactor/src/MdxViewer`\n- `gillijimproject_refactor/src/WoWMapConverter`\n- `gillijimproject_refactor/src/gillijimproject-csharp`\n- `gillijimproject_refactor/AlphaWDTAnalysisTool`\n- `gillijimproject_refactor/AlphaWdtInspector`\n- `gillijimproject_refactor/DBCTool`\n- `gillijimproject_refactor/DBCTool.V2`\n- `gillijimproject_refactor/BlpResizer`\n- `gillijimproject_refactor/AlphaLkToAlphaStandalone`\n- `gillijimproject_refactor/src/Pm4Research.Cli`\n- `gillijimproject_refactor/src/MDX-L_Tool`\n- `gillijimproject_refactor/tools/WlAnalyzer`\n- top-level archaeology/source inputs such as `parpToolbox`, `PM4Tool`, `ADTPrefabTool`, and `WoWRollback`\n\n## Non-Negotiable Constraints\n\n- The main viewer app must have one obvious home.\n- First-party shared code must not be mixed into `libs/`.\n- Upstream repos must remain external and trackable under `libs/`.\n- Tool executables must not each reinvent their own mini-core.\n- R&D and archaeology leftovers should not quietly become production dependencies.\n- Do not mirror the old repo structure into the new repo out of laziness.\n\n## What The Plan Must Produce\n\n1. The exact top-level repo tree.\n2. The exact solution/project grouping.\n3. Which projects are app-only, core-only, tool-only, or research-only.\n4. Which upstream repos are baseline bootstrap dependencies versus optional evaluation dependencies.\n5. What bootstrap scripts should do on a clean clone.\n6. What stays in `parp-tools` instead of moving.\n7. The first bootstrap milestone that proves the repo shape is real.\n\n## Deliverables\n\nReturn all items:\n\n1. proposed top-level repo tree\n2. proposed project/solution tree\n3. bootstrap dependency matrix\n4. scripts/bootstrap responsibilities\n5. what stays in `parp-tools`\n6. first bootstrap milestone\n7. risks if the tree is done badly\n\n## First Output\n\nStart with:\n\n1. the minimum repo tree you would create on day one\n2. the first-party projects that must exist immediately\n3. the upstream repos that should be auto-cloned immediately\n4. what parts of the old repo should not be copied forward blindly", "variables": [], "notes": "Design the concrete wow-viewer repo, solution, and bootstrap layout for the reformed tool suite. Use when deciding where the app, shared library, tools, libs, scripts, and research leftovers should live. Arguments: Optional repo-shape concern, tool family, or bootstrap constraint to prioritize.", "metadata": { "source": { "provider": "github-codex-prompts", "repository": "https://github.com/akspa0/parp-tools", "path": ".codex/prompts/wow-viewer-bootstrap-layout-plan.md", "ref": "4f7fb94cfad6bf6348c55c28ae9361c2d2fd9cb7", "url": "https://github.com/akspa0/parp-tools/blob/4f7fb94cfad6bf6348c55c28ae9361c2d2fd9cb7/.codex/prompts/wow-viewer-bootstrap-layout-plan.md", "key": "akspa0/parp-tools/.codex/prompts/wow-viewer-bootstrap-layout-plan.md" } } }

wow-viewer Bootstrap Layout Plan

About

Read First

Goal

Old Repo Inputs To Account For

Non-Negotiable Constraints

What The Plan Must Produce

Deliverables

First Output

Install wow-viewer Bootstrap Layout 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