Plan smoke test integration with locally tagged catalogs

docs/roadmap/smoke-tests.md

@@ -39,12 +39,27 @@ intermediate human-review approvals, upstream releases, external publication, or
 live-provider access to progress or establish completion. Automated checks and
 focused local commits remain part of ordinary implementation.
 
-Use the currently released catalog dependencies and PromptKit-owned diagnostic
-metadata underlays for the initial delivery. This supersedes the earlier
-loader-release/catalog-release/adoption sequence. The feature must be complete
-and usable without unpublished dependencies, committed workspace files, or local
-filesystem replacements. Any later move of metadata into catalogs is optional
-follow-up work, not an unfinished stage or a prerequisite for this sprint.
+Update the local OpenRouter and RakestrawHome catalog checkouts, validate and
+commit their changes, and identify the resulting revisions with local candidate
+tags. Built-in diagnostic metadata belongs in those catalogs, not in an
+intermediate PromptKit-owned metadata underlay. This supersedes both the earlier
+loader-release/catalog-release/adoption sequence and the temporary core-owned
+underlay proposal.
+
+A temporary, uncommitted Go workspace may support coordinated development.
+Final sprint validation must also resolve the exact locally tagged catalog
+revisions through a temporary filesystem module proxy, using normal module
+requirements and checksums with `GOWORK=off` and no filesystem replacements.
+Local tags alone do not make Go discover adjacent checkouts. The proxy supplies
+that connection without public HTTPS availability or upstream publication.
+Keep workspace/proxy artifacts outside committed repository contents, following
+the [repository-independence policy](../policy/architecture.md#repository-independence).
+
+PromptKit's completed sprint commits may reference those not-yet-published
+catalog versions in `go.mod` and their corresponding Go-generated checksums in
+`go.sum`. Implementation completion and local validation do not claim that other
+machines can fetch them. Public distribution is separate: consumers eventually
+need those exact contents available through their configured module sources.
 
 Normal release preparation and publication follow implementation separately;
 this objective does not bypass the repository's release process or authorize
@@ -406,21 +421,36 @@ destination under the selected adapter's contract. It does not assert acceptance
 at the initial destination or at every redirect hop. These endpoint fields provide
 attribution without introducing a public redirect trace.
 
-Deliver initial built-in metadata through PromptKit-owned underlays composed with
-the currently released catalog assets. Arrange these defaults so catalog metadata
-and caller overlays can replace them through ordinary composition. Supply defaults
-for enabled maintained catalogs without reintroducing a backend whose catalog the
-caller excluded. Interpret and validate only the assembled final configuration.
-No catalog edits, dependency publication, or intervening PromptKit release are
-required for initial completion. Later catalog adoption, if pursued, must account
-for older strict loaders that reject new fields; it is outside this sprint.
+Deliver built-in metadata in the local catalog repositories at
+`../promptkit-backend-openrouter` and `../promptkit-backend-rakestrawhome`.
+Catalog changes, local validation, commits, candidate tags, and PromptKit adoption
+are all included in the sprint; publication and remote module availability are
+not intermediate dependencies. Caller overlays remain available through ordinary
+composition, and excluded catalogs remain excluded. Interpret and validate only
+the assembled final configuration.
+
+Use standards-compliant module archives made from the exact tagged commits for
+the temporary filesystem proxy, not mutable working-tree contents or manually
+edited module-cache entries. Update normal version requirements, let Go generate
+checksums, and validate the integrated feature without workspace substitution.
+Scope any temporary proxy/checksum-database settings to this local workflow;
+do not impose them on consumers or commit machine-specific module resolution.
+
+Local candidate tags identify validated contents; they are not published releases.
+Specify candidate version selection and reconcile the catalogs' publication-date
+versioning convention during separate publication preparation. If that requires
+new final version names, update PromptKit's pins and checksums accordingly; retain
+the validated catalog contents and never move a published tag. Older strict
+PromptKit loaders may reject the new metadata fields, so describe the compatible
+consumer versions when publishing. No intervening PromptKit loader release or
+external module-download verification is required to finish implementation.
 
 Use `promptkit-openrouter-standard` for OpenRouter's default, its `openrouter_key`
 adapter, and `rakestrawhome-gemma-4-31b` with RakestrawHome's `none` authentication
 setting. Verify each shipped default resolves in the supported assembled effective
-configuration, including any
-PromptKit-owned profiles. This is final-value integration validation, not a second
-validation pass over intermediate sources. A catalog default is replaceable metadata,
+configuration, including any PromptKit-owned profiles. This is final-value
+integration validation, not a second validation pass over intermediate sources.
+A catalog default is replaceable metadata,
 not a promise of upstream availability, cheap inference, or a stable model choice.
 
 ## Execution And Error Boundary
@@ -541,11 +571,13 @@ scheduling, and any combination with `ValidateRequest` or normal execution.
   and partial cancellation reporting through the internal evidence path while
   preserving existing client contracts. Specify destination/credential attribution
   without exposing headers or a redirect trace.
-- Supply agreed built-in metadata through PromptKit-owned underlays over existing
-  released dependencies, with ordinary catalog/caller precedence and no
-  provider-availability guarantee. Check default-profile resolution in the assembled
-  final configuration. Complete all work without intermediate review or publication
-  gates, as required by the single-sprint objective.
+- Update and validate both local catalogs with the agreed metadata, then commit
+  and locally tag their candidate revisions. Adopt those versions in PromptKit
+  with ordinary catalog/caller precedence and no provider-availability guarantee.
+  Check default-profile resolution in the assembled final configuration and final
+  local-proxy module resolution without workspace/replacement substitution.
+  Complete all work without intermediate review or publication gates, as required
+  by the single-sprint objective.
 - Add focused offline tests with controlled transports and injected clients for
   selection, rejected/absent credentials, applicability/support, transport/malformed
   responses, content/JSON/schema facts, cancellation, shared inference capacity,
@@ -579,10 +611,12 @@ focused implementation plan:
    configured default-profile references at construction versus selection. Preserve
    final-value ownership and verify shipped defaults in assembled configuration;
    do not introduce source-history validation or change ordinary profile selection.
-2. **Default metadata composition.** Choose the underlay representation and placement
-   that lets later catalog metadata and caller overlays replace the defaults while
-   respecting catalog selection. Keep released dependencies usable throughout;
-   there is no external catalog coordination gate.
+2. **Local catalog integration.** Specify local candidate versions/tags and temporary
+   workspace/proxy setup for the two catalog checkouts, with standards-compliant
+   archives of the tagged contents and ordinary Go checksum generation. Define
+   final validation without workspace/replacement substitution and keep later
+   publication separate. There is no external catalog publication gate or
+   PromptKit-owned diagnostic metadata underlay.
 3. **Internal implementation.** Choose private content and schema, the narrow evidence
    handoff, and content-free classifications for internal faults that prevent a
    meaningful report. Define ownership and copying for reports and request values.