178 lines
9.4 KiB
Markdown
178 lines
9.4 KiB
Markdown
# Bundled OpenRouter Backend And Profiles
|
|
|
|
## Status And Purpose
|
|
|
|
Proposed; no implementation changes yet.
|
|
|
|
Ship a small OpenRouter configuration collection with PromptKit so consumers
|
|
can begin using named profiles without installing a separate catalog. Include
|
|
the backend definition those profiles require. Keep separately maintained
|
|
operator collections fully supported through the existing configuration path.
|
|
|
|
The bundle should favor provider-maintained latest aliases and routers, reducing
|
|
the need for PromptKit releases just to refresh individual model versions.
|
|
This is a convenience catalog, not an exhaustive model inventory or a promise
|
|
of stable upstream model behavior.
|
|
|
|
## Current Baseline
|
|
|
|
PromptKit depends on ConfigKit v1.1.0 and records field normalization and derived
|
|
defaults during resolution. It currently installs no backend or profile
|
|
definitions. Consumers supply configuration inputs, which ConfigKit composes
|
|
before PromptKit validates and materializes effective resources.
|
|
|
|
The existing [configuration format](../formats.md) supports root and namespaced
|
|
resource lists, explicit IDs, sibling inheritance, and ordered underlays.
|
|
A higher-layer same-ID resource replaces the lower record in full. Inputs in
|
|
the same underlay group are strictly composed; file order is not precedence.
|
|
The bundle can use these mechanisms without introducing another catalog loader
|
|
or restoring the former dependency on provider-specific Go modules.
|
|
|
|
ConfigKit v1.1.0's normalization and inspection support will apply to bundled
|
|
configuration just as it does to caller configuration. Layering itself predates
|
|
that release; no further upstream enhancement is required for this feature.
|
|
|
|
## Target Behavior
|
|
|
|
### Ordinary Embedded Configuration
|
|
|
|
Embed a small YAML collection in PromptKit and load it through the existing
|
|
ConfigKit adapter. Place it in its own lowest-priority underlay, before every
|
|
caller underlay and the main input. Preserve the existing order and grouping
|
|
of caller inputs.
|
|
|
|
Enable the bundle by default, with a public engine option to disable it entirely.
|
|
This follows the agreed convenience-oriented direction while preserving the
|
|
ability to supply an application's complete catalog. Choose the exact option
|
|
name during implementation using existing facade conventions.
|
|
|
|
Bundling a profile makes it available for explicit selection by a prompt or
|
|
request. It does not establish an implicit execution profile, change profile
|
|
selection precedence, or send a network request during engine construction.
|
|
Credentials remain runtime inputs under the existing credential rules.
|
|
|
|
Use ordinary configuration identities and expose the bundle through existing
|
|
listing and inspection APIs. Source explanations should identify embedded
|
|
configuration meaningfully. There is no need for a parallel built-in catalog
|
|
API or special provenance model.
|
|
|
|
### OpenRouter Backend
|
|
|
|
Include a backend with OpenRouter's API base endpoint,
|
|
`https://openrouter.ai/api/v1`, and the conventional environment-variable name
|
|
`OPENROUTER_API_KEY`. Store the name only; no credential value belongs in the
|
|
bundle. Reuse the existing OpenAI-compatible client and credential resolution.
|
|
|
|
Keep the backend minimal. Leave concurrency limits, queue policy, and provider
|
|
request parameters to existing defaults or application configuration. Smoke-test
|
|
metadata is a separate decision below; bundling does not automatically run
|
|
diagnostics or select an inference smoke-test profile.
|
|
|
|
### Small Profile Set
|
|
|
|
The proposed initial set contains these three model selections:
|
|
|
|
| Proposed profile ID | OpenRouter model value | Purpose |
|
|
| --- | --- | --- |
|
|
| `openrouter/gpt-sol-latest` | `~openai/gpt-sol-latest` | Follow the current GPT Sol family model. |
|
|
| `openrouter/auto` | `openrouter/auto` | Delegate model selection to OpenRouter's auto router. |
|
|
| `openrouter/free` | `openrouter/free` | Select OpenRouter's free-model router. |
|
|
|
|
These names distinguish PromptKit resource IDs from provider model values:
|
|
the tilde and slash in a provider model slug remain part of that value.
|
|
Additional latest-family aliases can be selected before implementation or added
|
|
later when useful; completeness across vendors is not a launch requirement.
|
|
|
|
Each profile should primarily specify its backend and model. Avoid baking in
|
|
temperature, reasoning, token-budget, timeout, or capability assumptions merely
|
|
to make profiles appear more complete. Operator profiles remain the place for
|
|
application-specific tuning and fixed model versions.
|
|
|
|
OpenRouter documents the
|
|
[GPT Sol latest alias](https://openrouter.ai/~openai/gpt-sol-latest),
|
|
[auto router](https://openrouter.ai/docs/guides/routing/routers/auto-router), and
|
|
[free router](https://openrouter.ai/docs/guides/routing/routers/free-router).
|
|
Verify the chosen slugs against current provider documentation when implementing.
|
|
Stable selectors reduce maintenance but do not freeze model selection, price,
|
|
availability, supported parameters, or output behavior. Describe the free router
|
|
as the provider's offering rather than adding PromptKit guarantees about future
|
|
pricing or availability.
|
|
|
|
### Application Control And Compatibility
|
|
|
|
Applications may replace bundled records through higher configuration layers or
|
|
disable the bundle and supply their own definitions. No namespace is reserved
|
|
against operator use. A same-ID replacement is a complete replacement, so an
|
|
application supplying only a new model value does not inherit the replaced
|
|
profile's backend. A distinct sibling using `extends` remains the ordinary way
|
|
to create a variant while retaining base fields.
|
|
|
|
Loading definitions by default changes inventory and inspection results, and
|
|
previously unresolved references matching bundled IDs may become resolvable.
|
|
Document these effects. Existing valid application records at higher layers
|
|
continue to win through normal composition. Changing a bundled backend may
|
|
also affect surviving bundled profiles that reference it; that is ordinary
|
|
backend completion, not a special override exception.
|
|
|
|
The embedded data ships with the PromptKit release. No catalog download or
|
|
automatic refresh mechanism is planned. Provider aliases and routers may change
|
|
their targets independently of that release; the inspected configured slug
|
|
does not identify or pin the concrete model selected upstream.
|
|
|
|
## Implementation Work
|
|
|
|
1. Resolve the identity layout and diagnostic-metadata decisions below. Confirm
|
|
the initial profile list and current provider endpoint/model values.
|
|
2. Add the embedded YAML backend and profiles, and integrate their dedicated
|
|
underlay with engine construction. Add the disable option using the existing
|
|
facade option pattern. Apply the ordinary load/normalize/validate lifecycle.
|
|
3. Verify default availability, disabling, caller precedence, whole-record
|
|
replacement, and inherited variants through the real configuration loader.
|
|
Include an application-provided OpenRouter collection and a replaced backend
|
|
to exercise interaction with external catalogs.
|
|
4. Verify listing and inspection reflect effective definitions and meaningful
|
|
source evidence. Exercise request preparation with a fake client or local
|
|
server as appropriate; construction must not depend on provider reachability
|
|
or a live API key. Reuse existing credential tests and add coverage only for
|
|
new integration behavior.
|
|
5. Update the format reference, consumer guide, relevant GoDoc, and maintained
|
|
examples when implementation lands. Explain how to disable, replace, or derive
|
|
from bundled profiles, and distinguish routers/latest aliases from fixed
|
|
models. Include the inventory/inspection change in release notes.
|
|
|
|
Keep current-state documentation unchanged until implementation lands. Retire
|
|
this roadmap after the behavior and remaining decisions reach their durable
|
|
owners. No new configuration syntax or collection specification version is
|
|
needed solely to distribute this data.
|
|
|
|
## Open Decisions
|
|
|
|
### 1. Backend Identity And Collection Layout
|
|
|
|
**Recommendation:** Put profiles in the `openrouter` collection with the local
|
|
IDs shown above, and put the backend in that collection as local ID `default`.
|
|
Profiles would reference `openrouter/default`. This keeps the bundle together,
|
|
avoids an ambiguous doubled provider name, and supports normal collection
|
|
inspection. Applications can still replace those exact IDs.
|
|
|
|
**Alternative:** Use a root backend ID `openrouter` with namespaced profiles.
|
|
This is concise and may align better with existing operator catalogs. Its
|
|
drawback is splitting the bundle between root and collection resources, and
|
|
making a common root backend name the shared override target. Before choosing,
|
|
compare maintained OpenRouter catalog conventions; the layout should minimize
|
|
consumer confusion rather than establish a new naming restriction.
|
|
|
|
### 2. Smoke-Test Metadata In The Bundled Backend
|
|
|
|
**Recommendation:** Include only the endpoint and credential-variable name in
|
|
the initial backend. Existing diagnostic behavior remains available, and the
|
|
feature stays focused on configuration convenience without choosing a diagnostic
|
|
inference model or expanding the maintained provider-specific configuration.
|
|
|
|
**Alternative:** Also provide the existing OpenRouter authentication diagnostic
|
|
configuration, after verifying its endpoint and behavior, while leaving the
|
|
inference smoke-test profile unselected. This makes the bundle more useful for
|
|
explicit preflight calls with little data, but adds another upstream convention
|
|
to maintain and test. Neither option implies automatic diagnostics during
|
|
construction or execution.
|