``` # Step-11 - Deterministic simulation runbook validation and preview ## Status COMPLETE. Strict bounded manual schema/source/head/template validation, immutable exact preview/staleness, actual local UI, real-source no-side-effect tests, post-green self-review, nine-project Release build/full regressions and native smoke passed. Step-11 remains pending manual orchestrator review; this report grants no acceptance or mutation authority. Corrected Step-10/10A remains accepted. Step-12 local inference/knowledge and runbook execution were not started. No model/runtime/retrieval/network feature, authoring Save, target command, approval or app-level Git persistence was implemented. ## Files, functions and interfaces - [RunbookPreviewService.cs](../src/AutoForge.Application/Features/Vehicles/Runbooks/RunbookPreviewService.cs): typed RunbookPreviewException/failures, immutable source/result/snapshot contracts, strict allowlisted parsing, Validate, CreateInputTemplate and fresh Snapshot status. The only constructor dependency is the existing CalibrationAuthoringService; validation reads its immutable snapshot and publishes under its existing narrow current-head guard. - Existing SyntheticEngineCalibration validates complete scalar/table values; existing CalibrationValueDifferences supplies the pure exact diff. Neither helper, authoring Save, rehearsal, target or source model implementation was changed or duplicated. - [RunbookPage.razor](../src/AutoForge.UI/Features/Vehicles/Runbooks/RunbookPage.razor): /runbooks, manual JSON input, explicit source template/Validate actions, typed input errors, previous successful result labels, current/Stale source status, canonical candidate/diff and optional display-only units. Authoring/preview notifications only schedule rendering; they never rebase input, validate, save or execute. - [AddAutoForgeUi.cs](../src/AutoForge.UI/Features/Foundation/AddAutoForgeUi.cs), [MainLayout.razor](../src/AutoForge.UI/Layout/MainLayout.razor) and [Home.razor](../src/AutoForge.UI/Features/Foundation/Home.razor): minimal preview registration and shared navigation. Client DI and all nine project references remain unchanged. Executable evidence: - [RunbookPreviewTests.cs](../src/tests/AutoForge.IntegrationTests/RunbookPreviewTests.cs) - [RunbookPreviewUiTests.cs](../src/tests/AutoForge.IntegrationTests/RunbookPreviewUiTests.cs) - [RunbookPreviewIsolationTests.cs](../src/tests/AutoForge.IntegrationTests/RunbookPreviewIsolationTests.cs) The initial frozen schema/source/value/limit/immutability/stale/UI/isolation tests were written before production implementation. The post-green review added exact exponent/Unicode/escaped-property/count/missing-source vectors. ## Frozen C-01..C-10 matrix All rows below are PASSED. Named methods were executed tests, not proposals. | ID | Named evidence and exact result | |---|---| | C-01 | ExplicitSourceAndNoChanges_PreviewCopiesWholeHeadWithoutImplicitWorkspaceOrSave; MissingActualWorkspace_RejectsStructuredInputWithoutCreatingSourceOrPreview. No source/template/preview is created implicitly. Valid unchanged complete current-head input yields NoChanges, empty diff, exact copied workspace/head/applicability, scalar 650 and six original torque rows. Missing actual workspace rejects SourceUnavailable even for structured otherwise-valid input. Source/history remain the same immutable snapshot. Both Baseline and Proposed current heads are usable. | | C-02 | ScalarTableMultiCellReverseAndTinyChanges_AreExactCanonicalDiffNotAuthoringSave. Independent candidate 1250 rpm plus 2000-rpm torque 350 yields exactly two ordered canonical entries: table before 360/after 350/delta -10 N*m/axis 2000 rpm; scalar before 650/after 1250/delta +600 rpm. Multiple-cell ordering, reverse +10/-600 and representable tiny differences are asserted without tolerance. No authoring/config/target is changed by preview. | | C-03 | EverySchemaObject_RejectsMissingDuplicateUnknownFieldsAtomically (18 object/mutation vectors); WrongKindsAndIntegerSyntax_RejectWithoutReplacingPriorSuccessfulPreview (24 vectors); MalformedCommentsTrailingDataAndWrongRoot_AreHandledAtomicErrors; EscapedDuplicatePropertiesInvalidUnicodeAndNonJsonNumbers_AreTypedAtomicRejections. Root/step/source/values/scalar/table properties are all required, unique and allowlisted. Wrong kinds, fractional/exponent reference syntax, malformed/comments/trailing input, unsupported version, null input and invalid strings/numbers reject through typed failure/path/reason before replacement. Prior preview and source/head/history remain identical. | | C-04 | OperationAllowlistAndSingleStep_RejectExecutionOrOtherTargets (10 vectors); ArbitraryCommandAndAuthorityFields_AreNeverInterpreted (6 vectors); safe rationale rendered test. Only exact simulation/proposeCalibration and one step are allowed. Physical/replay/undefined/case-changed target/operation, empty/multiple steps and SQL/script/frame/offset/approval/execute fields reject. Rationale is safely rendered informational text and never grants command or policy authority. | | C-05 | EverySourceComponent_MustMatchActualWorkspaceAndCurrentHead (10 vectors); FieldSpecificCasePolicies_AcceptProfileModuleButNotFingerprintModelDefinitionKeyOrUnit. Every workspace/head/profile revision/config/module/model version/definition reference must match actual current source. Profile/module case variants preserve existing ordinal-insensitive policy; fingerprint/model/definition/key/unit stay exact. No catalogue, role or latest-head fallback occurs. | | C-06 | FullTemplateInvalidNumbersKeysUnitsAxisAndShape_RejectAtomically (14 vectors); ExactTemplateBoundsAndNoOp_KeepCanonicalValuesWithoutClipping; SupplementaryStepIdentifierAndWholeCandidateCounts_FollowExactExistingLimits; exact tiny/reverse diff test. Full existing template validates finite scalar/cells, keys/units/fixed axes/counts. Out-of-range/non-finite/wrong-axis/shape/key/unit candidates reject atomically. Inclusive 650/5000 rpm and 1/1000 N*m boundaries remain exact; tiny canonical deltas are not rounded away and no sorting/clipping occurs. | | C-07 | SourceChangeAndReplacement_MarkImmutableOldPreviewStaleUntilExplicitCorrectRevalidation; actual rendered stale/draft test. Old-head request rejects; source/head change/replacement after success marks the same immutable captured result Stale. Its before/candidate/diff/identity are not rebased. Explicit correct input/revalidation is required; source changes do not alter draft or invoke validation. Publication reuses the actual source/head guard. | | C-08 | Utf8PayloadBoundary_IsExactly131072BytesIncludingMultibyteRationaleAndWhitespace; RationaleAndStepIdentifier_AreExactUtf16CodeUnitLimits; supplementary Unicode/depth tests. Valid original payload exactly 131072 UTF-8 bytes succeeds despite shorter string.Length; one more byte rejects with prior result retained. Rationale 2000 succeeds/2001 rejects; step 128 succeeds/129 rejects. Supplementary Unicode is counted in UTF-16 correctly. Depth 32 parses then receives appropriate schema rejection for the deliberately unknown structure; depth 33 is handled InvalidJson. Invalid UTF-8 encoding/escaped surrogate and non-JSON NaN are handled without fallback. | | C-09 | PreviewCollectionsAndRetainedResult_AreDefensiveAndBoundedToOneSuccess; RunbookUi_TemplateValidateRejectedDraftStaleAndUnits_NeverAutoValidateOrRebase. Parsed collections/current-head values/diff are copied/read-only; mutation attempts reject and old preview contents survive a later success. Service retains one last success, invalid attempt preserves its identity, and UI separates old result from rejected/edited input. Units/rerenders/source notifications do not validate or modify canonical input/data/diff. | | C-10 | RunbookUi_SafeRationaleUnavailableSourceAndNoExecutionControls_AreRealRenderedBehavior; RunbookIsolation_ActualLiveRecordingReplayAndApprovedRehearsalRemainUntouched; native evidence. Actual route/template/Validate/error/stale/rendering path works without Save/approval/Execute controls. Real live source/recording/replay/approved rehearsal coexist around invocation: transport/model/archive-Save/rehearsal open/read/write deltas=0, authoring changes/history mutation=0, approval remains same/unconsumed, and source export/trace/status/archive bytes/replay snapshot are unchanged. Constructor/source-path review confirms no Save/approval/network/model path. All 442 regressions plus 105 new cases, nine-project Release and native smoke pass. | ## Acceptance criteria | ID | Result | Evidence | |---|---|---| | AC-01 | PASSED | C-03..C-06/C-08 independent strict schema/allowlist/kind/reference/full-template vectors, exact UTF-8/UTF-16/depth bounds and typed atomic rejection assertions. | | AC-02 | PASSED | C-01/C-02/C-07/C-09 exact immutable before/candidate/source/head/diff, NoChanges/ChangesProposed, tiny changes, defensive copies, Stale versus current and bounded one-preview retention. | | AC-03 | PASSED | C-10 real rendered/native controls, safely encoded rationale, unchanged approved real rehearsal/live/recording/replay/source counters/state, no execution or inference dependency/path. | | AC-04 | PASSED | Final 547 passes with all 442 baseline cases preserved; all nine Release projects/native Client, 0 warnings/errors; required native normal preview/rejection/staleness/source/unit smoke passed. | | AC-05 | PASSED | Frozen executable matrix, own post-green source-path review, exact schema/usage/docs/README, protection/history/manual gate preserved and this single fenced report saved. | ## Final commands and outcomes SDK: dotnet --version -> 10.0.403 under the unchanged global.json policy. Existing xUnit v2/VSTest is unchanged. No package/SDK/workload/tool install, restore, update or repair occurred. Focused, required build and complete regressions ran sequentially: | Exact command | Exit | Result | |---|---:|---| | dotnet test .\src\tests\AutoForge.IntegrationTests\AutoForge.IntegrationTests.csproj --configuration Release --no-restore --filter "FullyQualifiedName~RunbookPreviewTests|FullyQualifiedName~RunbookUi_|FullyQualifiedName~RunbookIsolation_" | 0 | 105 new runbook cases passed, zero failed/skipped. | | dotnet build .\src\AutoForge.slnx --configuration Release --no-restore | 0 | All nine projects/native Client; 0 warnings, 0 errors. MAUI XAML source-generation output was informational. | | dotnet test .\src\AutoForge.slnx --configuration Release --no-build | 0 | 179 unit + 368 integration = 547 passed, zero failed/skipped. | | git --no-pager diff --check | 0 | No whitespace errors; existing README/build-guide LF-to-CRLF notices only. | | git --no-pager diff --exit-code -- prompts global.json Directory.Build.props Directory.Packages.props NuGet.Config src\AutoForge.Core src\AutoForge.Diagnostics src\AutoForge.Simulation src\AutoForge.Client src\AutoForge.Application\Features\Vehicles\Calibration src\AutoForge.Application\Features\Vehicles\Telemetry | 0 | Existing protected history/dependencies/core/ports/models/Client/authoring/rehearsal/recording/replay implementations unchanged before adding this report. | Per-project Release: AutoForge.Core, AutoForge.Diagnostics, AutoForge.Simulation, AutoForge.Application, AutoForge.Components, AutoForge.UI, AutoForge.Client, AutoForge.UnitTests and AutoForge.IntegrationTests all PASSED. Portable projects remain net10.0; Client remains net10.0-windows10.0.26100.0 / win-x64. The baseline is unchanged: 179 unit + 263 integration = 442 cases. This step adds 105 integration cases; no baseline safety/source assertion was deleted or weakened. Preview limits are 131072 original UTF-8 bytes, depth 32, rationale 2000 UTF-16 units, step ID 1..128 trimmed UTF-16 units and one allowlisted step. Existing authoring/rehearsal/archive/gauge limits remain. Iteration: - First executable focused run passed 99 cases without compilation/behavioral failures. The post-green review added exponent/escaped-property/Unicode/ full-count cases, yielding 104. A final independent missing-workspace validator case raised the final count to 105. - The full reviewed suite initially passed 546; final focused/build/full checks passed 105/547 after that last test addition. Production source was unchanged after the initial implementation/source-path review. - Native automation initially matched the explanatory word ChangesProposed in a NoChanges status before the actual diff rendered, causing a helper null-DOM read. It was corrected to wait for the exact captured indication and element presence. This was not a parser/app failure or a successful observation. The actual native workflow then completed without an error overlay. - No pre-fix behavioral reproduction is claimed: this is a new feature, not an existing validator bug correction. ## Native normal evidence versus headless proof The actual rebuilt Windows Client was operated through task-owned WebView2 data/local DevTools port 9382 with a temporary built-in Node/WebSocket helper. No new application web host, runtime/model or dependency was added. Native observations: 1. /runbooks entered with empty input/no preview. Explicit template attempt without source gave SourceUnavailable and created no source/default result. 2. Explicitly created warm source through existing simulation/calibration UI. Actual workspace f1b8740bd2414b7aa3e7be78ff35139f, baseline head 60bc53bc58d04ae38ab208aecf4d8ced. Template copied that source without validation; explicit Validate yielded NoChanges/current/empty diff. 3. Manual canonical edits 1250 rpm and torque 350 at 2000 rpm yielded preview 493f4f636782496eb50df0e4294e5a9f, ChangesProposed/current, with exactly: engine.torque-curve axis 2000 rpm, 360->350 N*m, signed delta -10 N*m; engine.warm-idle-target 650->1250 rpm, signed delta +600 rpm. 4. Rationale "Manual preview only: this is not approval." rendered as text. Its HTML used <b> and no b element was created. Metric->Imperial changed optional torque display only; JSON draft, preview identity and exact canonical diff stayed unchanged. 5. Malformed JSON, physicalHardware target, wrong expected head and scalar 600 each yielded the appropriate InvalidJson/OperationNotAllowed/ StaleSource/InvalidValues error with path/reason, while the previous preview ID and diff remained exactly unchanged and explicitly labeled Previous successful preview retained. 6. Returning to authoring confirmed history count 1 and original scalar 650; rehearsal remained Inactive/audit 0. Preview created no saved proposal, target or approval. 7. A separate explicit authoring Save changed current head to revision 2 / c2cb7ddefe474f44a17754896b3fde9c. On runbooks re-entry the original preview was visibly Stale, with its old identity/diff unchanged. Old JSON input rejected StaleSource. A new template still did not validate/clear stale result automatically; explicit Validate produced NoChanges/current for the current Proposed head. History remained exactly 2, not 3. 8. Original source configuration export stayed exactly identical, fingerprint sha256:v1:e8991ae139b54959ec53a4fe64b08dc9bfc03feb533496cf741f2c9f3a2342da. No model/session/target execution was opened by this native preview smoke. Original Metric/Road preferences were restored and observed; existing replay/Home routes worked, with replay Unloaded. Native evidence is normal real-UI/source behavior, not exact-limit or concurrency/coexistence proof. Actual active live/recording/replay/approved- rehearsal coexistence and zero boundary calls are headless real-service/port tests. Normal route cleanup is not attributed to validator invocation. No inference, knowledge, physical target or programming was used. Cleanup PASSED: task Client PID 40340 completed after route cleanup. Transient WebView PIDs 45756/44632 were checked against the task profile before any specific-PID cleanup. No owned WebView/listener remained; port 9382 was closed. Exact task-only profile/helper were removed. Native source/proposal/preview data were process-memory only; the app-local recordings directory remained empty. No unrelated file/archive/default WebView data/preferences were reset. ## Own post-green producer/consumer review Reviewed manual JSON -> original strict UTF-8 bound -> JsonDocument depth/ syntax/object/type/allowlist checks -> detached source/value contracts -> actual authoring snapshot/component matching -> full existing template -> pure exact diff -> current-head guarded publication -> copied last success -> current versus Stale snapshot -> actual input/error/preview UI. Public entry points reviewed: Validate, CreateInputTemplate, Snapshot and route template/Validate/subscription/render/disposal paths. Normal, rejected, boundary, source-change/replacement, old-preview, draft/error and unit cases were walked against C-01..C-10. All schema/source/template checks precede replacement. Publication is under the existing exact source/head guard. Snapshot releases the preview gate before reading the authoring gate, avoiding inverse lock order. Captured values/source/head/diff remain immutable; later source data only determines freshness, never rebasing. No method calls Save, Approve, target/model/store/ network or arbitrary tool code. UI notifications only render, with separate rejected/edited draft and previous successful labels. Rationale is plain safe text. The retained state is one preview, not a version/history framework. Review strengthened actual integer syntax, escaped duplicate property, invalid Unicode/NaN, supplementary-code-unit, duplicate whole-value-array and missing-real-workspace assertions. No production defect required a follow-up fix. Affected focused and full build/regressions were rerun to 105/547 passes. Native used the same unchanged production implementation. No known unresolved assigned exit-contract defect remains. ## Documentation and preservation Added [runbook schema-v1/preview guide](../docs/runbooks-v1.md); updated [README.md](../README.md), [documentation index](../docs/README.md), [architecture](../docs/architecture.md), [build/test guide](../docs/build-and-test.md) and the directly related accepted-status note in [rehearsal contracts](../docs/calibration-rehearsal.md). They document exact fields/limits/allowlist, source/head/template/canonical rules, defensive one-preview/current-Stale behavior, input versus old result, manual/no-model/no-save/no-execution/no-authority scope and actual evidence. Corrected Step-10/10A is accepted; Step-11 remains pending manual review. Future generated Step-12 text must use this same boundary, not a privileged path. Inference/knowledge and executor integration remain unimplemented. Worktree began clean on main at bccb797 and HEAD is unchanged. Existing prompts/state/roadmap/assignments/shared gate/reports and protected files were not edited; this is the only new prompts file. Index remains empty. All nine projects/references/dependencies and existing Core/profile/config/ Simulation/Diagnostics/authoring/rehearsal/recording/replay/physics contracts are unchanged. Source/tests remain under src/src/tests; docs under docs. The separately disclosed recording navigation issue was not modified. No new project/package/host/model/runtime/schema change to other features, permission/version-control/backup framework, app Git persistence, agent, automatic handoff, staging, commit, push, system installation or unrelated cleanup occurred. STOP. ```