commandkit/docs/roadmap/promptkit-v0.19.0.md

PromptKit v0.19.0 adoption and operator CLI

Status: proposed roadmap for review. Scope is agreed in principle; implementation has not started. Command spellings, report designs, and API changes below are recommendations until the open decisions are resolved.

Purpose and ownership

Adopt released PromptKit v0.19.0 and expose useful operator tasks through standard CommandKit commands, flags, and reports. This roadmap covers CLI exposure, including shared configuration inspection in ckconfig. It does not turn ckprompt into a convenience library for application-internal PromptKit operations. Applications continue to own engine construction, domain inputs, credentials, execution, and their executable lifecycle.

The architecture policy, optional-module decision, and reporting decision govern implementation. The CLI reference and public GoDoc remain the owners of implemented contracts. This roadmap selects work for review, not new guarantees about upstream behavior or permanent limits on future features.

Baseline and released evidence

Repository baseline: 0b4e47c4206e323f7c5d5ec3f357494dd23008b2. The completed v0.18.0 adoption is not reopened.

Component	Current baseline	Target
Core	go.maximumdirect.net/commandkit; Go 1.26.0 minimum	No core change currently identified.
ckconfig	ConfigKit v1.1.0; Go 1.27.0; core v0.3.0	Shared CLI inspection extensions and a new appropriate module release.
ckprompt	PromptKit v0.18.0; ConfigKit v1.1.0; ckconfig/core v0.3.0; Go 1.27.0	PromptKit v0.19.0 and the ckconfig version delivering the shared work.
Candidate	ckprompt v0.3.0, recorded as unpublished	Update the unpublished candidate after checking its status during implementation.
Local workspace	Core and both integrations, Go 1.27.0	Validate local composition and independent modules separately.

Use PromptKit tag v0.19.0, commit 4f3212bfb6c1f37f43d50715c2cedc1d43203064. Its Go minimum remains 1.27.0 and its ConfigKit dependency remains v1.1.0. Reviewed sources are the release notes, request and report types, engine API, namespace API, configuration inspection API, and smoke API. Work against released versions only; do not inspect or monitor unreleased upstream work in anticipation of another adoption.

Current ckprompt supplies prompt/profile inspection, requirements discovery, concrete request validation, prompt/profile/backend/namespace/collection catalogs, and four smoke operations plus test all. Smoke commands already expose most execution overrides and detailed native evidence. Validation has profile, session, variable, and file-input flags but lacks that override surface. There is no concrete request preview or dedicated backend detail command.

Current ckconfig supplies validation, native effective YAML, source inventory, path explanation with history, and reduced semantic comparison. Its View contains effective, sources, and explanation facets. Native metadata is not exposed as a capability. config sources returns on acquisition failure before rendering evidence; loaders convert native diagnostics into presentation messages but do not expose a structured diagnostics report. Relevant boundaries are ckconfig contracts, ConfigKit adapters, and PromptKit adapters.

Targeted end state

The original adoption tasks remain included:

1. Update the dependency, checksums, attribution, and unpublished candidate note.
2. Document all three upstream compatibility changes and correct credential inspection wording.
3. Cover the new authentication reason and corrected smoke preparation-error propagation at CommandKit's boundary.
4. Validate the final independent modules and aligned workspace.

Add the following operator capabilities. Syntax is illustrative and subject to the decisions at the end of this document.

Operator task	Proposed CLI	Owning module and report
Inspect what a concrete prompt request prepares	promptkit show request ID --profile … --input … --var …	ckprompt: selected IDs, effective settings, rendered/appended messages, output contract and schema, session, hashes, and timing from PreparedRun.
Reproduce target/provider settings without editing configuration	Applicable existing smoke override flags on validation and preview; --extra-params JSON on these and smoke operations	ckprompt: native request forwarding; preview and smoke reports show returned effective settings.
Resolve unqualified resource selections in chosen namespaces	Independent prompt/profile/backend namespace flags	ckprompt: delegate to native namespace views, retaining the distinction from catalog filters.
Find configuration paths and inspect their explicitness	config paths --scope promptkit, with historical selection; metadata alongside path explanation	ckconfig, wired through ckprompt.ConfigScope: observed paths, effective presence, explicitness/null/origin evidence, and available history.
Understand both sides of configuration changes	config diff --scope promptkit --details	ckconfig: native paths, left/right snapshots, presence/redaction, and hidden-change evidence.
Investigate a failed configuration load	config sources --scope promptkit on failure; a structured diagnostics operation	ckconfig, with both native adapters: acquired source inventory and native codes, severities, paths, and locations while retaining the load failure.

Compatibility and native semantics

Document these v0.19.0 changes for consumers constructing engines and inputs:

• Successful custom ArtifactReader.Read transfers ownership of its returned artifact and mutable body storage. Readers retaining scratch storage must supply independent returned storage and stop mutating returned aliases.
• ProfileSource and BackendSource provider maps now use ConfigKit's native recursive Mapping forms: built-in scalar values, []any, and map[string]any. Explain explicit conversion of json.Number and typed containers. Runtime execution overrides have a separate accepted-value contract; do not impose configuration-source restrictions on their flags.
• Local-validation and structured-output schemas must be self-contained. External resources and filename-dependent base references fail preparation; internal references or explicit schema IDs supply the supported route.

No configuration-format migration is required from v0.18.0. Correct the CLI description of api_key_required: it indicates a usable direct or environment credential requirement and can coexist with api_key_env. Neither field is evidence of current credential availability.

The new authentication response-limit reason is factual evidence with unknown credential acceptance. Continue forwarding native findings without converting false, unknown, unsupported, or incomplete observations into command failures. Actual preparation/operation errors retain the operational outcome and supported cause identity. Native errors and their categories remain upstream-owned.

Preview and request flags

Add an independently available preview capability alongside existing suite callbacks. The native adapter calls Engine.Prepare and projects its returned snapshot; a preliminary ValidateRequest call is unnecessary. Use existing typed selection, acquisition diagnostics, and invocation reporting patterns. Exact callback names and signatures follow the selected CLI design.

Preview performs applicable resource I/O and rendering but no model call. Rendered and appended messages contain application content. Upstream excludes resolved credentials from prepared settings; that does not make the whole snapshot a redacted configuration report or a transferable execution handle. Expose the upstream snapshot evidence without implying later execution uses that exact snapshot or will succeed.

Share CLI binding implementation where it reduces duplication between smoke, validation, and preview. Preserve native explicit zero/empty values and whole-map replacement semantics. Keep parsing in CommandKit and domain validity in PromptKit. Existing application builders remain usable; resolve override precedence and the remaining request controls under OD-2 before documenting new public behavior. These helpers serve standard CLI commands only.

Namespace selection

Design independent prompt, profile, and backend defaults together. Native WithNamespaces replaces all defaults on its new view; it has no partial-update semantics. Omission must therefore have a deliberate meaning when a loader already returns a scoped engine (OD-3).

Qualified IDs pass through native selection unchanged. Captured references, configuration inspection, and namespace/collection inventories retain their native meanings. Existing --namespace/--all-namespaces catalog filters continue to describe filtering. Install new selectors only on operations where they have a defined use; define that applicability table during implementation.

Shared configuration capabilities

Extend ckconfig through optional capabilities so existing custom providers can keep their currently declared operations. Both FromConfigKit and ckprompt.ConfigScope should expose available native evidence. Do not require all providers to implement every new operation.

For metadata, use Metadata.HistoricalPaths, Lookup, IsExplicit, and History. Enumeration covers observed paths, not all possible schema fields. Do not discard history because effective lookup fails. Existing explanation already reports current/historical values; add the missing discovery and explicitness instead of reproducing upstream provenance logic. Preserve native list-index paths; do not silently reinterpret them as resource IDs.

For detailed comparison, project native Difference records. Keep snapshots and their presence/redaction fields together, including HiddenChanged when the safe values look equal. Native sequence comparisons remain atomic; this work does not add element-level resource matching or a reloadable patch format.

For failure investigation, retain LoadError.Sources() and Diagnostics() as evidence alongside the error. The current adapters and config sources failure path need changes, not just another renderer. Define an acquisition shape that distinguishes unavailable evidence from an available empty inventory. A failed load does not establish an effective configuration or metadata capability.

Render available evidence through normal invocation reporting before terminal failure presentation. Keep the original load error and supported identity; successful report delivery must not convert failure to success. Preserve render/write failures separately through the current outcome machinery. Cover cancellation with partial evidence explicitly without promising interruption of an arbitrary writer or rollback of already-delivered bytes. OD-6 selects the structured diagnostics command and its interaction with ordinary diagnostics.

Work sequence

1. Resolve the significant CLI choices. Review the open decisions, record selections here, and identify affected published reports and flag collisions. Prepare concrete command/flag/report examples for implementation review.
2. Adopt v0.19.0. Update integrations/ckprompt/go.mod and go.sum, then module attribution against the released notices and source commit. Update the unpublished candidate note and affected canonical dependency/compatibility guidance. No core Go-minimum increase follows from this adoption.
3. Implement request inspection and selection. Add preview, applicable override flags, provider-parameter input, and namespace selectors. Reuse the standard suite's lifecycle and preserve existing application adapter seams.
4. Implement shared configuration inspection. Add metadata discovery and explicitness, detailed diff presentation, source evidence on failure, and structured diagnostics in ckconfig; wire native PromptKit facets through ConfigScope. Keep each change reviewable with its boundary coverage.
5. Update operator and consumer documentation. The CLI reference owns syntax, report schemas, availability, and outcomes; GoDoc owns callback and value contracts. Extend maintained simple/composed examples to demonstrate the new CLI tasks using local fixtures, without adding application-internal execution helpers. Record intentional compatibility effects in module notes.
6. Align module dependencies and validate. Prepare the ckconfig release needed by ckprompt, update the latter's dependency/checksums, and complete the validation below. OD-7 addresses the interim development dependency. Publication and hosted delivery remain separate actions under the release procedure.

Validation and completion checklist

Select focused boundary tests under the testing policy. The checklist concerns adapter/CLI behavior; it does not ask CommandKit to retest PromptKit rendering, schema, namespace, or ConfigKit resolution algorithms. Default tests remain offline and independent of real credentials.

• Dependency, checksums, attribution commit links, and candidate notes match the final selected module versions.
• All three compatibility changes and corrected credential wording are documented, with earlier v0.18.0 migration guidance retained where relevant.
• The authentication response-limit reason survives report projection with native unknown facts. Smoke preparation errors retain supported causes and operational outcomes, including the no-report case; no model dispatch is introduced by CommandKit to handle them.
• Preview forwards the intended request and faithfully reports native fields. Its CLI path makes no model call and does not create/execute retained prepared handles.
• New flags preserve selected omission/empty/zero semantics, parse malformed inputs through the existing usage path, and do not leak state between runs. Numeric decoding of provider JSON matches the selected strategy in OD-2.
• Namespace defaults, explicit clearing, qualified selections, and catalog filters are forwarded according to the selected design.
• Metadata discovery distinguishes effective and historical paths, retains available history on absent lookup, and projects native field/change records.
• Detailed diff retains both snapshots and presence/redaction/hidden-change evidence, including empty comparisons and sequence-level changes.
• Source and diagnostic evidence can be reported with an acquisition error; the original failure, unavailable-versus-empty evidence, cancellation, and report-delivery failures remain distinguishable.
• Existing providers remain usable; help, version, and capability discovery do not start acquisition. New operation/flag metadata and static completion match the implemented surface.
• Maintained consumer examples demonstrate the selected CLI tasks and the configuration failure workflow with deterministic local evidence.
• Canonical documentation, module release notes, and roadmap links agree with the implemented boundary. Open decisions are resolved or deliberately superseded before the corresponding behavior is claimed complete.
• Final independent-module and aligned-workspace suites pass, with the dependency identities used by each recorded.

With the documented Go 1.27.0 toolchain selected, run GOWORK=off GOTOOLCHAIN=local go test ./... independently in the root, integrations/ckconfig, and integrations/ckprompt. Prepare dependencies before offline execution as described in the release procedure. Then validate the aligned workspace from the root with:

GOTOOLCHAIN=local go test ./...
GOTOOLCHAIN=local go test ./integrations/ckconfig/...
GOTOOLCHAIN=local go test ./integrations/ckprompt/...

Use the development guide for toolchain/workspace setup and documentation checks. Reuse successful checks for unchanged content; these adoption checks do not add permanent publication gates. The earlier disposable dependency-only compatibility test is preliminary evidence, not completion evidence for these features.

Deferred work

Focused backend inspection remains in future work until a released upstream API supports it. Do not reconstruct backend selection from configuration to deliver it in this roadmap. General execution, prepared handle lifecycle, sessions, and observer convenience APIs remain application responsibilities. Configuration mutation, new live probes, dynamic completion, JSON report formats, and unrelated deferred proposals are not added by this roadmap. A later ConfigKit review may propose further CLI tasks separately.

Open Decisions

These decisions concern significant choices within the proposed scope. OD numbers are local to this roadmap, not the retired adoption documents.

OD-1: Preview command and report presentation

Recommendation: use promptkit show request ID, with YAML as the initial report format and the complete relevant PreparedRun projection. It sits beside definition inspection while clearly requiring concrete inputs. A single native preparation supplies both validation and preview evidence. Document rendered content disclosure directly in help and CLI guidance.

Alternative: promptkit prepare ID, with text and YAML reports. This names the native action and makes interactive inspection easier, but can suggest an executable prepared handle and adds a second rendering contract. Both forms can stay entirely within CLI ownership; select vocabulary and formats before coding.

OD-2: Request controls and provider-parameter grammar

Recommendation: give validation and preview the applicable execution flags already on smoke tests, and add a singleton --extra-params JSON object option to all three. Use native whole-map replacement, including native behavior for empty maps. Specify JSON number decoding deliberately so supported values reach PromptKit without accidental precision loss or new numeric guarantees. Retain the current authoritative-builder rule: the standard flags seed a request and an application builder can return its complete replacement.

Alternative: repeatable --extra-param KEY=JSON assignments. This is easier for individual shell overrides, but requires rules for duplicate keys and makes whole-map replacement less obvious. It must still construct a single native map rather than imply an upstream field-by-field merge.

Remaining request surface: recommend keeping output-contract overrides, inline-input flags, and appended-message flags as separately selectable CLI extensions after execution-flag parity. Existing file inputs and application builders continue to support preview. A viable alternative is to include a whole-output-contract file option and message/input options now, supporting more reproduction workflows at the cost of additional syntax, precedence, and reporting decisions. No general-purpose request-building API follows from either choice.

OD-3: Namespace flags and loader defaults

Recommendation: make the standard namespace selectors opt-in with explicit suite-owned namespace defaults. Compose supplied fields with those defaults, then apply one native WithNamespaces call. Loaders using this option leave default selection to that adapter. This gives omission and explicit empty values predictable meanings without trying to read private engine state. Without the option, existing scoped loaders continue as before.

Alternative: pass presence-aware namespace choices to an acquisition callback and let the application combine them with its existing loader defaults. This accommodates applications whose defaults depend on domain input, but adds consumer wiring and makes consistent behavior less automatic. Either design must account for the native API replacing all three defaults at once.

OD-4: Configuration path and metadata presentation

Recommendation: add config paths with effective paths by default and an explicit historical selection, and expose optional metadata alongside existing path explanation. Use the current single-scope selection model. This makes paths discoverable and uses an established command for their meaning/history. Define availability and unavailable metadata explicitly for older providers.

Alternative: a separate config metadata --path … operation plus historical enumeration. This keeps the existing explanation report unchanged and gives metadata-only providers an independent operation, but splits related operator information across commands. Weigh that compatibility benefit against the extra command and report contract before selecting additive explanation fields.

OD-5: Detailed comparison selection and shape

Recommendation: add --details to config diff, retaining the existing default. Emit a YAML record sequence carrying native paths, snapshots, and hidden-change fields, preferably within a scope-labeled envelope. This supplies the missing evidence without changing existing reduced-report consumers.

Alternative: replace the reduced form with the detailed report in a new minor module release. One canonical report is simpler to maintain and avoids selection flags, but requires migration of published CLI consumers. The release policy permits a deliberate pre-v1 minor compatibility change; the benefit must justify that disruption.

OD-6: Failure evidence and structured diagnostic delivery

Recommendation: extend config sources to report acquired inventory on failure and add config diagnostics --format yaml for native structured records and their source legend. Build this as optional ckconfig evidence facets, including evidence returned with an acquisition error. Keep ordinary human messages on the diagnostic stream and structured results on the result stream, using existing terminal failure/outcome handling. This is a bounded operator workflow with no demonstrated need for a generic core diagnostics schema.

Alternative: add structured diagnostic output to every configuration operation through a common format option or report envelope. It avoids a second invocation when diagnosing another command, but complicates existing native YAML/report shapes and result-versus-diagnostic stream contracts. A broader core representation is viable if concrete cross-family needs justify it; it is more work than exposing ConfigKit records alone. Specify warning presentation, evidence availability, and partial-result cancellation behavior for the selected design rather than silently changing all operations.

OD-7: Module release and interim workspace coordination

Recommendation: prepare a new ckconfig minor release for the shared API/CLI features, then update the still-unpublished ckprompt candidate to require it. Confirm available versions under the existing release procedure. During joint development use the ignored aligned workspace; record that workspace success does not establish independent ckprompt compatibility with its old ckconfig requirement. Before final independent validation, pin the released ckconfig version actually supplying the APIs. Publication requires its own authorization.

Alternative: publish a compatibility-only ckprompt release first and deliver the additional CLI features in subsequent releases. This makes v0.19.0 fixes available sooner, but creates an extra consumer upgrade and does not complete this roadmap's targeted end state. A disposable local module replacement can help test intermediate changes, but cannot substitute for final validation of the declared released dependency.