Organize downstream feature requests in the future roadmap
This commit is contained in:
@@ -33,9 +33,68 @@ consumers.
|
||||
|
||||
## Ideas
|
||||
|
||||
No ideas are currently cataloged. Backend-specific concurrency management has
|
||||
been selected for active planning in the
|
||||
[focused concurrency roadmap](concurrency.md).
|
||||
### Executable preparation handles
|
||||
|
||||
Allow a consumer to prepare one exact execution, inspect and retain its
|
||||
caller-owned preparation details, and later execute that already-prepared work
|
||||
without reloading or rerendering prompt, profile, schema, or input sources.
|
||||
This would remove the duplicate `Prepare`-then-`Run` workaround reported by
|
||||
[Notarius](notarius-promptkit-wishlist.md#priority-1-atomic-execution-with-prepared-details)
|
||||
and
|
||||
[Weatherreporter](weatherreporter-promptkit-wishlist.md#priority-1-executable-preparation-handles).
|
||||
|
||||
- Keep the handle opaque, engine-bound, non-serializable, and initially
|
||||
one-shot.
|
||||
- Keep existing `Prepare` and `Run` workflows available.
|
||||
- Return public preparation details under existing caller-ownership and
|
||||
credential-redaction rules.
|
||||
- Perform backend admission when execution begins rather than reserving
|
||||
capacity while a consumer retains the prepared handle.
|
||||
- Treat a separate atomic detailed-run method as possible later convenience
|
||||
rather than a second initial execution model.
|
||||
|
||||
### Prompt-independent profile inspection
|
||||
|
||||
Provide exact profile lookup and structural resolution without requiring a
|
||||
synthetic prompt, placeholder inputs, or model generation. This shared need is
|
||||
described by
|
||||
[Notarius](notarius-promptkit-wishlist.md#priority-2-prompt-independent-profile-inspection)
|
||||
and
|
||||
[Weatherreporter](weatherreporter-promptkit-wishlist.md#priority-3-prompt-independent-profile-inspection).
|
||||
|
||||
- Apply ordinary built-in, file-backed, and programmatic profile precedence.
|
||||
- Validate referenced backend membership and the structurally resolved
|
||||
execution target.
|
||||
- Report credential requirements and environment-variable names without
|
||||
exposing credential values or requiring current credential availability.
|
||||
- Support exact lookup by profile ID; enumeration is not required initially.
|
||||
|
||||
### Prompt-definition inspection
|
||||
|
||||
Provide exact prompt-definition lookup without rendering, placeholder inputs,
|
||||
profile resolution, or model generation, as requested by
|
||||
[Weatherreporter](weatherreporter-promptkit-wishlist.md#priority-2-prompt-definition-inspection).
|
||||
|
||||
- Return caller-owned identity, version, input definitions, default-profile,
|
||||
output-contract, and opaque definition-equality information.
|
||||
- Apply ordinary prompt-source precedence and exact ID/version selection.
|
||||
- Validate the selected definition and referenced prompt content
|
||||
structurally, without returning source bodies or rendered messages.
|
||||
- Leave complete cross-source corpus validation and enumeration outside the
|
||||
initial inspection contract.
|
||||
|
||||
### Structured capacity errors
|
||||
|
||||
Add safe structured context to backend admission rejection, as requested by
|
||||
[Notarius](notarius-promptkit-wishlist.md#priority-4-structured-capacity-errors)
|
||||
and
|
||||
[Weatherreporter](weatherreporter-promptkit-wishlist.md#structured-capacity-errors).
|
||||
|
||||
- Preserve compatibility with `errors.Is(err, ErrCapacityExceeded)`.
|
||||
- Support `errors.As` to obtain the stable backend ID.
|
||||
- Do not expose endpoints, credential configuration or values, request
|
||||
content, or speculative retry timing.
|
||||
- Keep retry and backoff policy with downstream consumers.
|
||||
|
||||
## Entry Format
|
||||
|
||||
|
||||
Reference in New Issue
Block a user