diff --git a/docs/roadmap/promptkit.md b/docs/roadmap/promptkit.md index fb104307..9e8d3700 100644 --- a/docs/roadmap/promptkit.md +++ b/docs/roadmap/promptkit.md @@ -87,8 +87,8 @@ Notarius's artifact and recovery policies. | Part | Responsibility | | --- | --- | | Application composition | Load configuration and native sources; construct one shared PromptKit engine for producers, validators, and continuation runs. | -| Artifact-family modules | Prepare domain inputs, select prompt IDs and response requirements, interpret responses, and apply deterministic domain rules. | -| Pipeline execution | Connect generation to configured validation and terminal policy; manage ordered dependencies, typed handoffs, bounded workers, and stable result ordering. | +| Artifact-family modules | Prepare domain inputs, select prompt IDs and response requirements, interpret responses, apply deterministic domain rules, and provide supported fallbacks. | +| Pipeline execution | Connect generation to configured validation and strict/permissive handling; manage ordered dependencies, typed handoffs, bounded workers, and stable result ordering. | | PromptKit | Prepare and execute requests; maintain captured exchanges and conversations; enforce native retry, repair, turn, and admission budgets; report execution facts. | | Application state and records | Publish artifacts, cache final accepted artifacts, provide a small completion summary, and capture optional debug evidence with pipeline context. | | ConfigKit and CommandKit | ConfigKit owns configuration mechanics; CommandKit and ckconfig/ckprompt own standardized commands and presentation. Notarius supplies loaders, request builders, report content, and outcome mapping. | @@ -112,10 +112,11 @@ Place one small shared producer helper alongside assessment in `internal/framework/pipeline`. Connect modules to it through ordinary functions: 1. The pipeline supplies an operation-scoped assessment callback capturing the - configured validator chain and acceptance/terminal policy. + configured validator chain and acceptance criteria. It applies the selected + strict/permissive mode when no acceptable result is obtained. 2. The module prepares source material, references, and any normalization handle mappings once. It builds the native initial request and supplies response - interpretation and correction-request functions. + interpretation, correction-request, and supported fallback functions. 3. The helper receives those functions, the shared engine, and relevant cache/debug collaborators. For cacheable work it prepares the initial request and looks up the accepted-artifact cache; on a miss it executes the retained @@ -147,7 +148,9 @@ separate known-dependency checks. Exact argument grouping and helper signatures can be refined against representative extraction and normalization during implementation; ownership and placement are settled. U4 selects prompt roles and guidance ownership below; U5 selects retry controls and the correction budget. -Remaining terminal and fallback policies stay in U6. Implementation is pending. +U6 selects strict/permissive handling and module-owned fallbacks below; its default, +configuration scope, and concrete module fallback choices remain open. +Implementation is pending. Retain the fixed `input -> chunk -> extract -> merge -> normalize -> output` shape, ordered steps and generated references, typed artifact-family boundaries, @@ -463,12 +466,13 @@ candidate, its module supplies guidance and artifact validators cannot yet run. Cancellation or fatal execution failures can interrupt assessment. An unavailable validator assessment is a separate outcome, not a detected defect or an instruction to change the artifact. Do not convert provider errors into correction guidance; -terminal/fallback disposition remains U6. +apply U6's strict/permissive handling when no acceptable result is obtained. Ownership, response contracts, and default profile behavior are resolved. Refine exact template prose, correction IDs, and necessary operation-specific inputs while implementing representative workflows. Implementation is pending; U5 selects -semantic budgets and U6 retains terminal/fallback policy choices. +semantic budgets and U6 selects terminal handling, with defaults, configuration +scope, and concrete module fallback choices still open. #### Execution And Assessment Flow @@ -492,9 +496,10 @@ The application flow is: inputs. Run the complete configured validation chain again for changed candidates, including validators that previously approved. Assess the final permitted response before declaring exhaustion. -5. Stop on acceptance or a terminal condition. Apply application rejection, - failure, or supported safe-fallback policy after exhaustion. Native `stopped` - and `exhausted` outcomes do not themselves mean application acceptance. +5. Stop on acceptance or a terminal condition. If no acceptable result is obtained, + fail in strict mode or produce the module's supported fallback in permissive + mode. Native `stopped` and `exhausted` outcomes do not themselves mean application + acceptance. Cancellation stops work without constructing a fallback. Accumulated history increases context use; U5's allowance bounds additional semantic correction while stopping as soon as the candidate is accepted. @@ -585,25 +590,71 @@ outer attempt loop. Migration guidance maps intent: a producer allowance intende for semantic correction becomes `max_additional_turns`; native transport controls and prompt-owned structural customization cover their own concerns. Remove non-LLM retry settings without a replacement generic allowance. Do not promise -equivalent total provider-attempt counts. U5 is resolved; detailed terminal and -fallback dispositions remain U6. Implementation is pending. +equivalent total provider-attempt counts. U5 is resolved; U6 selects strict/permissive +handling, with defaults, configuration scope, and concrete module fallback choices +still open. Implementation is pending. -Keep source grounding, reference resolution, candidate isolation, domain -invariants, and reconciliation safety checks. Unknown or overlapping handles -remain invalid. A supported safe fallback may retain safe merges while leaving -unsafe groups separate; it must pass configured artifact validation and terminal -policy. After structural-repair exhaustion it can be assessed directly without -restarting the same model operation. Whether an earlier safe candidate can -survive a later failed turn remains open; do not silently introduce best-so-far -acceptance. +#### Terminal Outcomes And Module Fallbacks (U6 Direction Resolved) -Preserve rejection versus unavailable/incomplete validation. A structurally -valid candidate may advance under the existing `warn_continue` policy with -explicit incomplete-validation outcome information, but it and its affected -derivatives are ineligible for accepted-artifact cache reuse or publication. A -completed rejection never advances. Cancellation cannot make an undelivered -response accepted. Keep conversation state in process, outside ordinary -artifact/cache payloads; explicitly requested detailed debug is separate. +Use two modes when an operation does not obtain a successful, validated result: + +| Mode | Terminal behavior | +| --- | --- | +| Strict | Require a successful, validated result; otherwise fail the pipeline. | +| Permissive | Produce the module's supported fallback, record a warning, and continue with that artifact. | + +The pipeline selects the mode; the module owns the fallback algorithm. Replace +the failure-category policy object and separate `fail_run`, `reject_output`, and +`warn_continue` choices with this selection. An empty artifact is a supported +fallback where the domain permits it; no separate omit-output action is needed. +The default mode, configuration spelling/scope/precedence, and concrete module +fallback definitions remain open. Do not infer them from existing policy fields. + +Attempt application-directed correction when appropriate within the selected +budget before terminal handling. Neither mode extends PromptKit's native retry +or repair budgets or adds retries to deterministic operations. Preserve the +distinction between a detected defect and an unavailable assessment for correction +guidance and diagnostics; neither establishes ordinary acceptance. Cancellation +remains cancellation and does not initiate fallback work. If a supported fallback +cannot be constructed, fail execution. + +Fallbacks must satisfy the structural artifact contract and invariants required +by downstream stages. They need not satisfy every ordinary semantic acceptance +criterion whose failure led to fallback. Do not rerun the complete ordinary +validator chain as a condition of using the fallback or claim normal validation +passed. Keep the necessary checks with module fallback construction; no separate +configurable fallback-validation framework is needed. + +The selected direction supports these domain-specific fallbacks: + +| Module | Fallback direction | +| --- | --- | +| D&D spell extraction | A valid empty spell artifact, so that the failed chunk contributes no extracted spells. | +| D&D transcript chunking | A deterministic partition preserving the entire transcript. Whole-transcript-as-one-chunk versus deterministic bounded slices remains open. | +| Normalization | Apply only safe consolidation groups from the final usable response afresh to the fixed originals, retaining everything else. If that response is unusable, use the deterministic merge of the input chunk artifacts. Reuse an already available merged input. | + +Keep source grounding, reference resolution, candidate isolation, and +reconciliation safety checks. Unknown or overlapping handles remain invalid; +partial normalization applies only compatible safe groups and leaves other +original candidates separate. Use the final response and fixed original inputs, +without recovering an earlier candidate or combining proposals across turns. +Concrete module algorithms must make their supported fallback and required +invariants explicit; these examples do not introduce a generic fallback language. + +Fallbacks may be published and consumed downstream, but they and dependent results +affected by their incompleteness are ineligible for accepted-artifact cache lookup +or storage. Carry the small application outcome facts needed to skip that reuse; +do not add dependency fingerprints or a provenance ledger. Fully validated, +unaffected predecessors remain reusable, allowing later runs to retry work that +previously needed fallback. + +Record why fallback was used and expose that qualification in the ordinary +completion report, even when diagnostic verbosity hides individual warnings. +Use the same application outcome for reporting and optional debug detail. Keep +conversation state in process, outside ordinary artifact/cache payloads; +explicitly requested detailed debug is separate. Implementation is pending, and +U6 remains open only for the default mode, configuration contract, and concrete +module fallback choices. ### Admission And Pipeline Workers @@ -644,7 +695,7 @@ Prepare initial request -> obtain MessageContentHash -> look up cache/.jso Hit: decode the accepted artifact and continue the pipeline Miss: execute the retained request and complete the Notarius operation -> interpret, validate, and perform application-directed corrections - -> on final acceptance, store the artifact under the INITIAL hash + -> on final acceptance, store the eligible artifact under the INITIAL hash ``` Use the upstream message-content hash of ordered message roles and exact text. @@ -674,7 +725,10 @@ or prepared handle. For normalization, save the accepted normalized artifact after applying the reconciliation plan, not the proposed plan itself. Save only after the entire Notarius operation succeeds, including domain validation and any application-directed corrections. Failed, rejected, and validation-incomplete -work and ineligible derivatives are not cacheable. +work is not cacheable. U6's fallbacks and dependent results affected by their +incompleteness are ineligible for both lookup and storage, even if the downstream +operation itself validates successfully. An unrelated accepted predecessor remains +reusable. This requires a small eligibility fact, not a dependency fingerprint graph. A hit loads the accepted artifact directly, with ordinary decoding/usability checks; absent or unusable entries are misses. It makes no model calls, rebuilds @@ -729,14 +783,16 @@ Use `ExecutionGroup` for selected diagnostic totals, explicitly enrolling initia continuation, and nested validator executions without overlapping double counts. Preserve terminal coverage and unknown-versus-zero usage. Reuse adds no historical usage to current totals. These facts support diagnostics and capture, not a -mandatory consumer execution ledger. Notarius's acceptance, fallback, rejection, -incomplete-validation, publication, and reuse facts feed the completion summary -and debug overview without independently maintained reporting state. +mandatory consumer execution ledger. Notarius's application outcome supplies +publication and fallback qualifications for the completion summary; assessment, +failure, and reuse details support optional diagnostics and debug capture without +independently maintained reporting state. ### Artifact Delivery And Completion Output -Artifacts are the primary deliverable: publish accepted domain artifacts as files -in the output directory. Preserve intrinsic domain content and artifact schemas. +Artifacts are the primary deliverable: publish accepted domain artifacts and +permitted module fallbacks as files in the output directory. Preserve intrinsic +domain content and artifact schemas. CLI `--format` controls the completion report, not payload encoding. Consumers need no run manifest, metadata bundle, persisted receipt, or execution history to use the artifacts. Retire reporting-only metadata and mandatory manifests instead @@ -764,11 +820,13 @@ but lose named fields in machine output; the template gives both presentations without parallel encoders. No report-version, run-ID, token, profile, warning-count, or validation-history collection is required. -When a completed run includes rejected work or permitted incomplete validation, -qualify the human summary and structured value with the rejection count and/or -incomplete-validation fact. Keep these facts visible without verbose/debug mode; -small outcome qualifications do not require per-producer histories. Exact names -of those conditional fields are implementation details. +When a completed run used a fallback, qualify the human summary and structured +value with that fact, even if native diagnostic verbosity suppresses individual +warnings. For example, a small fallback count can accompany the completion fields; +exact field names remain implementation details. Do not present the run as if all +operations obtained normally validated results. Detailed reasons belong in optional +diagnostics/debug capture, without per-producer histories in the completion report. +Quiet mode continues to suppress stdout. Wire results to stdout and diagnostics to stderr: @@ -798,9 +856,10 @@ completion report. Use native outcomes: status 0 for command completion, 1 for operational/cancellation/publication/presentation failure, 2 for invalid invocation or identifiable invalid configuration, and 3 for native `config diff --check` differences. Preserve ckconfig's structured classification and underlying causes; -not every preflight failure is invalid input. Command completion is distinct from -domain acceptance: permitted rejections/incomplete validation qualify the report, -while terminal pipeline failure fails the command. +not every preflight failure is invalid input. A permissive run that completes with +supported fallbacks succeeds with an explicit fallback qualification. Strict-mode +failure, inability to construct a supported fallback, and other terminal pipeline +failures fail the command. On failure, supply a useful native explanation and nonzero status, without a new structured error-envelope protocol. `--format` does not serialize diagnostics. @@ -878,7 +937,7 @@ implementation choices. | Execution events | Native per-execution events in occurrence order, including attempts/retries/repairs, timing, usage availability, and terminal metadata. | | Results and responses | Native `RunResult` plus exact `RawOutput` in a separate editor-readable text file. | | Conversations | Full `Exchange.Details()` for every application-visible turn, including rejected turns, plus simple readable role-labeled messages. Repeated prefixes are acceptable. Use prepared messages when no completed exchange exists and label the representation. | -| Interpretation and assessment | Candidate via its codec before acceptance; decode/safety failures; each validator's findings and correction guidance; application disposition and links to LLM validator executions. | +| Interpretation and assessment | Candidate via its codec before acceptance; decode/safety failures; each validator's findings and correction guidance; application disposition, any fallback artifact and reason, and links to LLM validator executions. | | Normalization and corrections | Proposed reconciliation plan and applied candidate; constructed correction inputs even if the next preparation fails. | | Deterministic stages and reuse | Chunk plans/materialized chunks, merged/normalized artifacts, and the loaded cached artifact with the current hit decision. No reconstructed history or fabricated execution on reuse. | @@ -921,7 +980,7 @@ reopen the architecture. IDs retain continuity with the earlier roadmap. | ID | Remaining choice or dependency | Resolve for | | --- | --- | --- | | U1 | Review the message-content hash API/release documented upstream in v0.24.0, including its ConfigKit dependency; verify the final compatible dependency set against the selected baseline. | Track in Phase 1; required to finish cache integration in Phase 5. | -| U6 | Detailed terminal/fallback policy, especially whether an earlier safe candidate survives a later failed turn. No implicit best-so-far acceptance. | Phases 3–4. | +| U6 | Default strict/permissive mode; configuration spelling, scope, and override precedence; concrete module fallbacks, particularly whole-transcript versus sliced chunking. The two-mode model, module ownership, and final-response-only handling are settled. | Phases 3–4. | | U7 | Independent worker defaults; application-supplied native backend/queue limits, if any; retired `total_llm` migration and admission-failure handling by role. | Phase 4. | | U8 | Cache directory configuration and reuse/bypass/refresh controls (names, defaults, scope); old-checkpoint treatment and unusable-entry diagnostics. Hash inputs, lookup timing, accepted value, and ownership are settled. | Design with Phase 3; finish in Phase 5. | | U9 | Observer/group enrollment and application scope; concrete conditional report fields and debug filenames/serialization within the agreed contracts; publication-layout/consumer migration details preserving intrinsic artifact schemas. | Implementation details in Phases 3–5; no new receipt/manifest inventory or capture-policy decision required. | @@ -936,15 +995,15 @@ selects native repair delegation and the application correction allowance. and the shared pipeline producer helper with module functions and a pipeline assessment callback are selected in [the execution design](#module-execution-and-assessment-u3-resolved). Implement in Phase 3 and refine signatures during Phase 4 without reopening -ownership. U4/U5 select prompt/guidance and retry behavior; remaining terminal -and fallback-policy choices stay in U6. +ownership. U4/U5 select prompt/guidance and retry behavior; U6 selects terminal +handling, with its remaining configuration and module choices listed above. **U4 resolved:** Domain-specific initial/correction prompt pairs, shared response schemas, default profile behavior, validator-owned guidance, and complete applicable-chain assessment are selected in [the prompt and guidance design](#prompt-roles-and-correction-guidance-u4-resolved). Implement templates and operation-specific inputs in Phases 3–4; exact prose does -not reopen ownership. U5 selects budgets; terminal/fallback policy remains U6. +not reopen ownership. U5 selects budgets; U6 selects strict/permissive handling. **U5 resolved:** `max_additional_turns` defaults to `2`, with binding over pipeline precedence and explicit zero disabling correction. Native transient and @@ -952,8 +1011,14 @@ structural-repair defaults remain upstream-owned; bundled prompts and applicatio requests do not pin structural repair. The [retry-control design](#retry-controls-and-correction-budget-u5-resolved) also removes generic non-LLM retries, all producer/validator `retries` fields, and the generic outer attempt loop. Any demonstrated transient I/O recovery stays -with its specific operation. Implement in Phases 3–4; U6 owns terminal/fallback -decisions. +with its specific operation. Implement in Phases 3–4; U6 selects terminal handling. + +**U6 direction resolved:** [Strict/permissive handling and module-owned fallbacks](#terminal-outcomes-and-module-fallbacks-u6-direction-resolved) +replace failure-category policies. Fallbacks satisfy artifact/downstream invariants +without asserting ordinary semantic acceptance; use only the final response and +fixed originals. Fallback and affected downstream work remain outside accepted- +artifact caching, and completion reports disclose fallback use. Default mode, +configuration contract, and concrete module fallback choices remain open above. **U10 resolved:** CommandKit versions, capabilities, commands, loaders/preflight, output, debug policy, and coordinated cutover sequencing are selected above. @@ -1003,8 +1068,9 @@ without credentials or synthetic requests. `config diff` handles two selections. ### Phase 3: Prove A Representative Native Pipeline -- Implement the resolved U3–U5 collaboration and retry policy; settle U6's - terminal/fallback details. +- Implement the resolved U3–U5 collaboration and retry policy and U6's + strict/permissive model. Settle its default mode, configuration contract, and + representative module fallbacks. Connect module request/interpretation functions to the pipeline assessment callback through the shared producer helper; refine concrete signatures here. Implement domain-specific initial/correction prompts using the same schema and @@ -1020,7 +1086,7 @@ without credentials or synthetic requests. `config diff` handles two selections. **Completion evidence:** fake-provider workflows exercise accumulated history, collection of independent validator findings without rejection short-circuiting, full candidate revalidation through the same assessor, final-turn acceptance -without duplicate final validation, selected exhaustion/fallback, and useful +without duplicate final validation, strict failure, permissive fallback, and useful failures. Unavailable assessments remain distinct from actionable defects. The executable publishes artifacts and reports them through native presentation without the private completion/correction API. @@ -1033,6 +1099,8 @@ without the private completion/correction API. - Remove the adapter, copied completion contracts, manual replay/capability checks, generic outer attempt loop, all producer/validator `retries` fields, global scheduler/ceiling, and coupled worker settings. +- Replace failure-category policy fields with the selected mode configuration + and module-owned fallback behavior. - Finish native command/inspection migration and remove custom dispatch, flags, encoders, verbosity handling, and obsolete asset registration. Retire the emptied `internal/framework/llm` package after moving engine assembly to the @@ -1057,9 +1125,11 @@ requirements remain. **Completion evidence:** downstream failure/fix/retry reuses accepted predecessors; message changes miss and settings-only changes can hit; corrected answers use the -initial key; hits make no model calls or fresh validation claims. Artifacts need -no metadata bundle. Machine output and debug capture obey the selected contracts, -including failures after publication and quiet-mode capture. +initial key; hits make no model calls or fresh validation claims. Fallbacks and +affected downstream work skip cache lookup/storage; unaffected accepted work +remains reusable. Artifacts need no metadata bundle. Machine output and debug +capture obey the selected contracts, including failures after publication and +quiet-mode capture. ### Phase 6: Verify And Document The Coordinated Cutover @@ -1086,6 +1156,7 @@ Release preparation/publication is governed separately by release policy. | `single_response_v1`, raw `ModelCandidate`/`SemanticCorrection`, manual replay, correction capability checks | Typed candidates, actionable findings, native exchanges, assessment. | | Generic `runProducerAttempts` outer loop, repeated validator executions in `executeValidationChain`, all producer/validator `retries` fields, module rerun directives, hard-coded `CorrectionRequest` message builder | Ordinary deterministic execution, native LLM execution/continuation, ordered validators, validator/module-owned guidance, native domain correction templates, and domain acceptance/rejection/fallback. | | Application `structured_output_repair_attempts` fields/resolution and explicit bundled `output.repair_attempts` | Native upstream structural-repair default, with operator customization through native prompt configuration. | +| Failure-category `validation_policy` fields and separate `fail_run`/`reject_output`/`warn_continue` actions | Strict/permissive selection, module-owned fallback construction, and explicit fallback outcomes. | | `Scheduler`, `scheduledClient`, `concurrency.total_llm`, worker coupling | Bounded pipeline work and native backend admission. | | Checkpoint stage/dependency/configuration fingerprints, invocation-wide barriers, manifests, acceptance/provenance envelopes | Small accepted-artifact cache using the upstream message hash, ordinary load checks, explicit controls. | | Inspection wrappers, copied effective parameters, usage summaries/conversions/accumulators, debug completion wrapper, synthetic IDs, profile recorder | Native facts with application scope for diagnostics. | @@ -1111,9 +1182,10 @@ retry tests or freeze complete help text and native debug snapshots. | Prompt/guidance contracts | Domain-specific initial/correction pairs use the same response schema and default profile; explicit profile/execution overrides reach both; operator correction-profile defaults work when not overridden; all applicable validators assess the same candidate despite earlier rejection; their actionable findings reach the correction template; module interpretation defects and unavailable assessments remain distinct. | | Retry controls | `max_additional_turns` resolves binding, pipeline, then application default `2`; explicit zero disables correction; acceptance stops early and the final allowed turn is assessed. Bundled declarations/application overrides leave structural repair unspecified, native operator customization remains effective, and tests do not freeze upstream default attempt counts. | | Non-LLM failure handling | Deterministic errors propagate without generic retries; rejected deterministic candidates reach terminal policy without regeneration; cancellation stops work. Producer/validator `retries` fields and the generic outer attempt loop are retired. | -| Continuation/failures | Accumulated history, full revalidation and final-turn assessment; no blanket retries beyond native exhaustion; validator failure differs from rejection; selected fallback, incomplete-validation, and cancellation policy hold. | +| Continuation/failures | Accumulated history, full revalidation and final-turn assessment; no blanket retries beyond native exhaustion; validator failure differs from rejection; no earlier-candidate recovery or cross-turn proposal union; cancellation stops without fallback work. | +| Strict/permissive outcomes | Strict failure when no acceptable result is obtained; permissive module fallback with required artifact/downstream invariants, without rerunning the ordinary full validation chain or claiming normal acceptance. Fallback construction failure fails execution; successful fallback use is disclosed in human/machine completion reports. | | Admission/workers | Shared backend pools across roles, independent backends, bounded pipeline work, nested validators, queue exhaustion, and cancellation without leaked capacity or a global ceiling. | -| Accepted-artifact cache | Downstream recovery; initial-message keys; corrected final artifact stored late under the initial key; changed messages miss; settings/ID-only changes can hit; no model/revalidation on hits; unusable entries miss; failed/rejected/incomplete work and ineligible derivatives excluded; no required history. | +| Accepted-artifact cache | Downstream recovery; initial-message keys; corrected final artifact stored late under the initial key; changed messages miss; settings/ID-only changes can hit; no model/revalidation on hits; unusable entries miss. Failed/rejected/incomplete work is not stored; fallbacks and affected downstream work skip lookup/storage while unaffected accepted predecessors remain reusable; no required history. | | Cache migration | Selected reuse/bypass/refresh and old-record treatment work; invocation configuration no longer blocks lookup; canonical chunk caching retains its distinct policy. | | Output/outcomes | Artifact files independent of report format; native text/JSON/YAML summary and qualified outcomes; no mandatory metadata bundle; quiet suppression, verbose stderr, debug path; native nonzero failures and useful explanations. Publication survives later capture/report failure without model reruns. | | Execution observations | Initial/continuation/validator totals preserve unknown-versus-zero usage without double counts; result-less failures observable; reuse does not count historical work; native execution success remains distinct from acceptance. | @@ -1150,9 +1222,11 @@ Provide practical release guidance for operators and subprocess callers: Explain retirement of all producer/validator `retries` fields and generic non-LLM retries, upstream-owned structural defaults, removal of application repair controls and bundled counts, native operator customization, accumulated-history - costs, and selected role failure policy. + costs, strict/permissive selection and precedence, and each module's fallback + behavior and downstream guarantees. - Accepted-artifact caching, message-based misses, settings-only reuse, refresh/ - bypass for changed interpretation or validation, and old-checkpoint handling. + bypass for changed interpretation or validation, fallback/affected-work exclusion, + and old-checkpoint handling. - Artifact delivery without mandatory manifests/receipts; preserve intrinsic artifact schemas and document any explicitly selected format change. - Debug root/default/empty behavior, `latest`, native mode ordering, failure