Compare commits

...
25 Commits
Author SHA1 Message Date
UnixNight 404b4b4d4a docs(01): verify bundled checker repair and restart pending UAT 2026-11-14 17:00:38 -05:00
UnixNight 2fe8b40ea5 fix(01): keep bundled Python commands from writing bytecode caches 2026-11-14 16:53:30 -05:00
UnixNight 23ee1c2e47 test(01): reproduce bundled checker creating immutable bytecode caches 2026-11-14 16:50:04 -05:00
UnixNight 07793af9fc docs(01): keep local-only API declaration within preflight limit 2026-11-14 16:33:42 -05:00
UnixNight 898aef7ffa docs(01): normalize final verification report whitespace 2026-11-14 00:41:11 -05:00
UnixNight f7e7033514 docs(01): persist final verification and pending combined-session UAT 2026-11-14 00:40:51 -05:00
UnixNight febb4a9d98 docs(01): express existing verification goal as required user story 2026-11-14 00:32:22 -05:00
UnixNight 08150c0199 docs(pause): preserve final verification continuation at quota reserve 2026-11-13 17:27:15 -05:00
UnixNight 71366e7d45 docs(01): close review and security gates with acceptance pending 2026-11-13 17:22:39 -05:00
UnixNight 02d182f35d fix(01-07): validate actual copy-state artifacts at scenario boundary 2026-11-13 17:18:39 -05:00
UnixNight 48fca0df52 test(01-07): reject copy-state identities without backing artifacts 2026-11-13 17:16:54 -05:00
UnixNight a821754b67 test(01): WR-01 verify readiness after transfer without Git 2026-11-13 17:08:10 -05:00
UnixNight 2608517c37 fix(01): WR-02 recover interrupted Windows runs without invented clocks 2026-11-13 17:07:44 -05:00
UnixNight 548c97aa58 fix(01): WR-01 preserve validated capability history in checkpoint viewer 2026-11-13 17:07:44 -05:00
UnixNight 6e5ee0bd25 fix(01): CR-03 bind lifetime continuity to named copy snapshots 2026-11-13 17:02:22 -05:00
UnixNight bda35e5bf5 fix(01): CR-02 bind original evidence to pristine inventory members 2026-11-13 17:01:42 -05:00
UnixNight 5569bc2b8b fix(01): CR-01 bind review digest to selected receipt bytes 2026-11-13 17:00:47 -05:00
UnixNight 5915128570 docs(01): record final code review findings and disposition 2026-11-13 16:58:55 -05:00
UnixNight 215d01e43e docs(01-07): track completed preparation and open acceptance gate 2026-11-13 16:49:31 -05:00
UnixNight 52a3e2d5ff docs(01-07): record verified preparation and pending human acceptance 2026-11-13 16:48:09 -05:00
UnixNight 472500bf4e test(01-07): integrate counted fidelity regressions and exact local results
Run existing fidelity Python, Node and observer checks with positive-count guards and explicit TAP output. Record the completed 782.05-second local suite and preserve human acceptance at 0/120.
2026-11-13 16:44:59 -05:00
UnixNight b732256751 docs(pause): save quota-guard checkpoint at 01-07 task3 2026-11-13 12:29:02 -05:00
UnixNight fc5e936fd7 docs(01-07): retain pending combined-session acceptance and diagnostic identity 2026-11-13 12:18:43 -05:00
UnixNight 026def9c5a feat(01-07): audit prepared fidelity materials and strict human acceptance 2026-11-13 12:17:46 -05:00
UnixNight d78b13566d test(01-07): specify strict final fidelity acceptance gates 2026-11-13 12:09:46 -05:00
38 changed files with 2526 additions and 123 deletions

No files matched your search

+48 -14
View File
@@ -1,35 +1,69 @@
{ {
"version": "1.0", "version": "1.0",
"timestamp": "2026-11-13T16:07:37.872347+00:00", "timestamp": "2026-11-13T22:26:46.798618+00:00",
"phase": "01", "phase": "01",
"phase_name": "Reproducible Fidelity Baseline", "phase_name": "Reproducible Fidelity Baseline",
"phase_dir": ".planning/phases/01-reproducible-fidelity-baseline", "phase_dir": ".planning/phases/01-reproducible-fidelity-baseline",
"plan": 5, "plan": 7,
"task": 2, "task": 3,
"total_tasks": 2, "total_tasks": 3,
"status": "consumed", "status": "consumed",
"completed_tasks": [ "completed_tasks": [
{ {
"id": 1, "id": 1,
"name": "Identified offline checkpoint tracer", "name": "Readiness/audit tooling plus review closure",
"status": "done", "status": "done",
"commit": "6112339" "commit": "026def9",
"fix_head": "02d182f"
}, },
{ {
"id": 2, "id": 2,
"name": "Complete Windows materials/collection/selftests", "name": "Actual combined session status projection",
"status": "partial",
"commit": "fc5e936",
"actual_acceptance": "0/120 OPEN"
},
{
"id": 3,
"name": "Suite integration and review",
"status": "done", "status": "done",
"commit": "8574665", "commit": "472500b",
"correction": "aa4b862" "review_docs": "71366e7"
} }
], ],
"remaining_tasks": [], "remaining_tasks": [
"blockers": [], {
"id": 2,
"name": "Actual original/native combined session and strict acceptance",
"status": "human_pending"
}
],
"blockers": [
{
"type": "human_action",
"description": "Combined original/native session and ten named UAT checks remain pending; 0/120 accepted."
}
],
"background_processes": {
"tests": "finished",
"verifier": "finished human_needed",
"quota_watcher": "running; no automatic resume"
},
"async_jobs": [], "async_jobs": [],
"human_actions_pending": [], "human_actions_pending": [
{
"action": "AfterfinalreadinessverificationperformonecombinedWindowsDxWnd/nativeWindows/physicalLinuxreviewsession",
"blocking": true
}
],
"uncommitted_files": [ "uncommitted_files": [
" M .planning/HANDOFF.json",
" M .planning/ROADMAP.md",
" M .planning/STATE.md",
" M .planning/phases/01-reproducible-fidelity-baseline/.continue-here.md",
" M .planning/phases/01-reproducible-fidelity-baseline/HANDOFF.md",
"?? tools.yaml" "?? tools.yaml"
], ],
"next_action": "Consumed historical handoff. Plans01-05 and01-06 complete and reviewed. Continue01-07 task1; actual session acceptance remains0/120 OPEN.", "next_action": "Use $gsd-verify-work 1 and docs/evidence/checkpoint-session.md for one combined actual human session; do not repeat completed implementation/tests/review or advance Phase2 automatically.",
"context_notes": "Quota interruption after server-restart recovery. Plans01-01..04 complete, primary-reviewed and pushed through de68796. Currentplan01-05 task1 RED446930d/GREEN6112339; task2 RED818191c. No01-05SUMMARY. Preserve partial uncommitted edits to scripts/collect-fidelity-windows.ps1 and tools/recon/fidelity_checkpoint.py; preserve unrelated tools.yaml. Do not restart task1 or treatREDcommit as completion. Inspect actual gitdiff before continuation.\nExisting generated packages artifacts/fidelity/01-05-packages/{linux-x64,win-x64} and tracerbundle artifacts/fidelity/01-05-tracer-checkpoint exist; inspect manifests/logs rather than rebuilding blindly. Task2 REDreproduced23tests with missing-session-materials assertion/statusAPI error. Cached local PowerShell executable .tools/powershell-check/root/opt/microsoft/powershell/7/pwsh and cacheddeb found; no successful execution/provenance was reported before quota. No third-party installers redistributed. Need finish task2Windowsagenda/selftests/complete truthfulresults, verify, writeSUMMARY andhandlerstate; then primaryreview/push. All120actualoriginal-DxWnd/nativeLinux/nativeWindowsacceptanceOPEN. Plans01-06Linuxcapture/01-07combinedhands-onreadiness+acceptance remain.\nSequential nativeexecutors because worktreebasecheckcannotresolveorigin/HEAD (repoGitea/main). Maincommits authorized;git.allow_default_branch_commits=true. Local sockettests/Node runner needescalation to actuallyexecute namedtests. Fullwave2scripts/test.sh authorizedpasses462Python+2HUD/allmanaged/36GPUzeroerrorsGTX1070/539hashes; observer23managed+7process/privateXvfb4onoffidentical. No newWindowsororiginalcomparison.\nUser asked howtoresumeandautomatelow5husagepause. Researched officialCodexaccount/rateLimits/read plusaccount/rateLimits/updated andPreToolUse/PostToolUsehooks; no guardconfigured. OnlySessionStarthook currentlyconfigured;statuslinealreadyfive-hour-limit. Do not claimautopauseinstalled. Need customwatcher/hook before it canbeautomatic. No activeworkersknown;recover_01_05 returnedquotaerror, do notimmediatelyredispatchwhilequotaexhausted. Resumewhenuserrequestsafterlimitreset; inspectactualremainingquota ratherthanstale10:28PMreset. No sourcefeatureworkwasdonebyprimaryforthisquestion.\n\n2026-11-13 quota-guard setup: tools/workflow/codex_quota_guard.py and .codex/hooks.json implement local Linux 60-second actual 300-minute quota polling; <=20% denies new worker dispatch, <=15% independent recovery snapshot plus cooperative GSD pause request. The watcher is running and live quota read works. Five project hooks are discovered but require user /hooks trust before registration/tool blocking activate. See docs/codex-quota-guard.md. No feature tasks resumed or partial collector edits committed during this setup. After reset/user resume, continue plan 01-05 task 2 from this original handoff.\n\nConsumed after successful continuation: SUMMARY2d48ee5/tracking1af5217. Primary repeats24 checkpoint and17 PowerShell checks successfully. Both full bundle preflights passed. Retained for preservation after auto-review rejected deletion. New current position is01-06 task1; old quota blocker is resolved.\n" "context_notes": "Quota guard explicitly requested pause at15%. Resume completed task01-07-03 and recovered fullsuite exit0 (782.049626s), then reviewed/fixed allfive source-integrity findings. Do NOT redo implementation or tests. Source commits through02d182f, review/coverage/security documentation71366e7. Fullsuite556Python/180fidelity,27Node,23observer,2HUD,51managedentrypoints,36GPUrenderedreceipts,zeroVulkanvalidationerrors,SDLdummychecks,539originalhashes. Latertooling-onlyfixes: all191fidelityregressions PASS43.355s; focused26scenario,23capture,29acceptance,27Node,18LinuxhostedPowerShell. All539originals unchanged. No runtime changes afterfullsuite; no need13minGPUrerun forcurrentPython/collector fixes.\nHistoricalreview5915128: CR01selected-vs-reviewedpath,CR02originalinventory/executablebinding,CR03copy-stateidentity,WR01viewerledgerprojection,WR02interruptedWindowsfinalization. Fixes5569bc2,bda35e5,6e5ee0b,548c97a,2608517,a821754. Independentre-reviewcaughtremaininghash-onlycopy-statebypass; RED48fca0d/GREEN02d182f requiresactual_checked_artifactwithrootinside_scenario_observation; callersupdated. Finalindependentre-reviewallfiveFIXED in01-REVIEW-VERIFY.md; dispositionopen0. Securityauditorfinal22/22mitigated, threats_open0 in01-SECURITY.md. Nyquistautomationcoveragevalidatedall15taskbindings; manualacceptanceopen;191fidelityaggregate43.355sec exceeds30secquicktargethonestly. UIreviewdisabledconfigfalse. No remainingknowncode/securityblockers.\nCurrentfreshfinalbundle dist/fidelity/phase01 has11001immutableentries. Currenthashes/readinessreceipt artifacts/fidelity/verification/01-07-final-checkpoint.json. readyexit0true,strictauditexit1 errors[] accepted0/120,10humanpending; logs artifacts/fidelity/01-review-fixes/readiness-final.json,acceptance-final.json,python-fidelity-final.log. Oldbundlespreserved phase01-pre-review-48100025 andphase01-pre-copy-artifact-7ceebcb3. ActualLinuxfailedpreflightimportedcurrentbundle/results/imported. Runtimepackage source446930d dirty/diff90cef956 unchanged; source/docscommitsmustnotrelabelitsidentity. Original/nativeWindows+DxWnd andphysicalLinuxvisible/audible/browserreviewremainonecombinedhuman session pending. Humanonlycollects/observes/returns; agent-ownedexactnormalizationmapping incheckpoint-session.md. No capture request issued yet because finalphaseverification/handoffpending.\nFinal typed verifier phase01_final_verification was dispatched at21%; quota15% interrupted it, instructedfinishonlyboundedhuman_neededreport/fingerprint thenreturn. It had readall7musthaves/summaries, checked25capabilities/33requirements/0unmapped/6groups/33rows,16/16decisioncoverage,40sourcefilesnoskip/debtscan. A mandatoryMVPgoalformatguard exposed existingROADMAPMode:mvp plainproseGoal. Rootauthorizedformat-only identicalintentuserstory and modifiedROADMAP.md uncommitted: As a tester, I want to reproduce identified original/port comparison scenarios, so that I understand exactly what the current reconstruction proves on each native platform. Validatorvalidtrue; no scope/successcriteriamodified. OneverifiercommandusedwrongunittestclassFidelityAcceptance (loadererror,correctclassAcceptanceTests); twoothernamedbehaviorcheckspassed; don'tmislabelthatcommandassuccess. Priorfulltargeted29passestablishactualcoverage.\nNEXT: Reconcile currentverifier's 01-VERIFICATION.md and CLI verification.status; ifreport/fingerprintabsentfinishthat ONLY beforeanynewphase. FingerprintmustbeownerCLIgenerated, notmanual. Oncehuman_neededstatusvalid, persistUATfromnamedhumanitems, updateSTATE/consumedhandoffs, commitverifiedreport+goalmetadata+handoffdocs andpush verifiedsource/tooling toauthorizedGitea/main. Lastpushedhead remainsd18f551; later01-07/task3/reviewfix/auditcommits arelocalawaitingfinalverification. Preserveunrelatedtools.yaml. Do notadvancephase2orclaimPhase1accepted; allEVIDIDsPending0/120humanacceptance. No source changesuncommittedexceptROADMAPformatandpossiblynewverifierreport.\nNativeagents/sourcewritesallfinishedexceptverifierreportbeingclosed. Quota watcher runs and actual15%steeringworks. Noauto-resume; usermust $gsd-resume-workafterreset. Don'tspendquota rereadingmassiveGSDscriptbodies orrerunningfinished13minfullsuite. Existinglocalpackages/media/originalcopiesstaylocal, noCI/uploads. MaintracksGitea/main, scoped.gitwriteescalation; retainhistoricalhandoffsmarkconsumedratherthandelete (priorautomaticreviewrejecteddeletion).\nRootinterruptedverifieratfinalpause tostopallmodelwork. Reconcileactualreportfileifpresent; ifabsentfinishboundedreport/fingerprintafterreset.\n\n2026-11-14 final typed verifier completed: human_needed,29/42verified13uncertain,all10namedhumanitems saved01-UAT.md. Ownerstatusacceptedreport; verificationfingerprintrefreshedafterfinalstatusnotes. Goalformatfebb4a9committed. Remainingworkisactualcombinedhumanverification, notcoding/fulltests.\n"
} }
+12 -4
View File
@@ -30,7 +30,7 @@ Integer phases are planned work; decimal phases may be inserted for urgent recov
## Phase Details ## Phase Details
### Phase 1: Reproducible Fidelity Baseline ### Phase 1: Reproducible Fidelity Baseline
**Goal:** Testers can reproduce identified original/port comparison scenarios and understand exactly what the current reconstruction proves on each native platform. **Goal:** As a tester, I want to reproduce identified original/port comparison scenarios, so that I understand exactly what the current reconstruction proves on each native platform.
**Mode:** mvp **Mode:** mvp
**Depends on:** Nothing (existing codebase and evidence are the starting point). **Depends on:** Nothing (existing codebase and evidence are the starting point).
**Requirements:** EVID-01, EVID-02, EVID-03, EVID-04 **Requirements:** EVID-01, EVID-02, EVID-03, EVID-04
@@ -39,7 +39,7 @@ Integer phases are planned work; decimal phases may be inserted for urgent recov
2. A tester can reproduce identified whole-original reference scenarios from an isolated generated installation and inspect corresponding input/events, images and audio where applicable; unavailable execution keeps this criterion open. 2. A tester can reproduce identified whole-original reference scenarios from an isolated generated installation and inspect corresponding input/events, images and audio where applicable; unavailable execution keeps this criterion open.
3. A reviewer can trace every full-game capability from original evidence through current implementation, platform receipts, discrepancies and its remaining acceptance condition. 3. A reviewer can trace every full-game capability from original evidence through current implementation, platform receipts, discrepancies and its remaining acceptance condition.
4. Testers can repeat the same baseline movement/route scenarios on native Linux and native Windows with exact revision identities; Wine/cross-publish receipts remain separately labeled and cannot close missing native execution. 4. Testers can repeat the same baseline movement/route scenarios on native Linux and native Windows with exact revision identities; Wine/cross-publish receipts remain separately labeled and cannot close missing native execution.
**Plans:** 6/7 plans executed **Plans:** 7/7 autonomous preparation/reconciliation plans recorded; actual 01-07-02 capture/review and Phase 1 acceptance remain pending.
**Wave 1** **Wave 1**
- [x] 01-01-PLAN.md - [x] 01-01-PLAN.md
@@ -55,7 +55,15 @@ Integer phases are planned work; decimal phases may be inserted for urgent recov
- [x] 01-06-PLAN.md - [x] 01-06-PLAN.md
**Wave 5** *(blocked on Wave 4 completion)* **Wave 5** *(blocked on Wave 4 completion)*
- [ ] 01-07-PLAN.md - [x] 01-07-PLAN.md
Autonomous preparation is complete: 11,000 immutable files pass readiness and
the complete local suite passes in 782.05s. Actual task 01-07-02 capture/review
remains human_needed: 0/120 original/native obligations accepted and ten human
findings pending. All EVID requirements remain Pending; Phase 1 is not accepted.
The primary reviews readiness before one combined session. Retained quota
handoff files are historical until primary consumption; the final SUMMARY
records completed task 3 and pending human dependencies. No Phase 2 advancement.
### Phase 2: Faithful Movement and Scene Handoffs ### Phase 2: Faithful Movement and Scene Handoffs
**Goal:** Players move, contact the world and return from scripts/scenes with the original movement, animation, camera and state ownership intact. **Goal:** Players move, contact the world and return from scripts/scenes with the original movement, animation, camera and state ownership intact.
@@ -151,7 +159,7 @@ Execution follows 1 → 2 → 3 → 4 → 5 → 6 → 7 → 8, subject to the ex
| Phase | Plans Complete | Status | Completed | | Phase | Plans Complete | Status | Completed |
|-------|----------------|--------|-----------| |-------|----------------|--------|-----------|
| 1. Reproducible Fidelity Baseline | 6/7 | In Progress | - | | 1. Reproducible Fidelity Baseline | 7/7 preparation | Human acceptance pending (0/120) | - |
| 2. Faithful Movement and Scene Handoffs | 0/TBD | Not started | - | | 2. Faithful Movement and Scene Handoffs | 0/TBD | Not started | - |
| 3. Original Actors, Hazards and Combat | 0/TBD | Not started | - | | 3. Original Actors, Hazards and Combat | 0/TBD | Not started | - |
| 4. Complete Gadget and Vehicle Use | 0/TBD | Not started | - | | 4. Complete Gadget and Vehicle Use | 0/TBD | Not started | - |
+22 -18
View File
@@ -2,17 +2,17 @@
gsd_state_version: "1.0" gsd_state_version: "1.0"
current_phase: 01 current_phase: 01
current_phase_name: Reproducible Fidelity Baseline current_phase_name: Reproducible Fidelity Baseline
status: executing status: awaiting_human_verification
stopped_at: Completed 01-06-PLAN.md stopped_at: Phase1 verified human_needed; ten UAT checks and combined actual session pending
last_updated: "2026-11-13T17:04:40.651Z" last_updated: "2026-11-14T05:39:47.960Z"
last_activity: 2026-11-12 last_activity: 2026-11-13
last_activity_desc: Phase 01 execution started last_activity_desc: 01-07 autonomous preparation verified; actual human acceptance pending 0/120
state_head: c60248dbfe5c8d151677babca0543af1f1d1b5e0 state_head: febb4a9d98071b19998bcecfab4a236d9c0adfce
progress: progress:
total_phases: 8 total_phases: 8
completed_phases: 0 completed_phases: 0
total_plans: 7 total_plans: 7
completed_plans: 6 completed_plans: 7
percent: 0 percent: 0
--- ---
@@ -27,24 +27,24 @@ See: .planning/PROJECT.md (updated 2026-11-12)
## Current Position ## Current Position
Phase: 01 (Reproducible Fidelity Baseline) — EXECUTING Phase: 01 (Reproducible Fidelity Baseline) — HUMAN ACCEPTANCE PENDING
Plan: 7 of 7 Plan: 7 of 7
Status: Ready to execute Status: Preparation complete; actual original/native acceptance human_needed
Last activity: 2026-11-12 — Phase 01 execution started Last activity: 2026-11-13 — Task 3 committed, complete local suite passed in 782.05s; final summary committed.
Progress: [░░░░░░░░░░] 0% Progress: [░░░░░░░░░░] 0%
## Performance Metrics ## Performance Metrics
- Total plans completed: 0 - Autonomous preparation plans recorded: 7/7; accepted phases: 0/8
- Average duration: Not established - Average duration: See per-plan metrics; elapsed intervals include pauses
- Total execution time: 0 hours - Total active execution time: Not continuously measured
| Phase | Plans | Total | Avg/Plan | | Phase | Plans | Total | Avg/Plan |
|-------|-------|-------|----------| |-------|-------|-------|----------|
| - | - | - | - | | - | - | - | - |
Recent trend: No execution plans completed in this roadmap. Existing project work predates initialization and retains its documented bounded evidence. Recent trend: All seven preparation/reconciliation records exist; actual task 01-07-02 and Phase 1/EVID acceptance remain open. Existing project work retains its documented bounded evidence.
**Per-Plan Metrics:** **Per-Plan Metrics:**
| Plan | Duration | Tasks | Files | | Plan | Duration | Tasks | Files |
@@ -55,6 +55,7 @@ Recent trend: No execution plans completed in this roadmap. Existing project wor
| Phase 01 P04 | 16 min | 2 tasks | 5 files | | Phase 01 P04 | 16 min | 2 tasks | 5 files |
| Phase 01 P05 | 12h 4min | 2 tasks | 7 files | | Phase 01 P05 | 12h 4min | 2 tasks | 7 files |
| Phase 01 P06 | 14 min | 2 tasks | 4 files | | Phase 01 P06 | 14 min | 2 tasks | 4 files |
| Phase 01 P07 | 4h 36min elapsed incl quota pause; suite 782.05s | 2 tasks | 16 files |
## Accumulated Context ## Accumulated Context
@@ -78,13 +79,16 @@ Recent trend: No execution plans completed in this roadmap. Existing project wor
- [Phase 01]: Runtime package provenance retains actual completed publish source/dirty/diff identity; selected external tools are identified without redistributing executables. - [Phase 01]: Runtime package provenance retains actual completed publish source/dirty/diff identity; selected external tools are identified without redistributing executables.
- [Phase 01]: No display and only auto_null audio yields failed native preflight; all forty Linux obligations retain explicit physical/audible capture dependencies. - [Phase 01]: No display and only auto_null audio yields failed native preflight; all forty Linux obligations retain explicit physical/audible capture dependencies.
- [Phase 01]: Linux matrix history revalidates saved receipt hashes and requires new launch/session IDs; focused captures cannot replace continuous route lifetimes. - [Phase 01]: Linux matrix history revalidates saved receipt hashes and requires new launch/session IDs; focused captures cannot replace continuous route lifetimes.
- [Phase 01]: Ready materials and local regressions never substitute for actual original/native acceptance; all 120 obligations and ten named human findings remain open.
- [Phase 01]: The integration agent reconciles returned collector records through specified artifact mappings; the tester collects, observes and returns one combined session.
### Pending Todos ### Pending Todos
None captured separately. Next action: `$gsd-discuss-phase 1` or `$gsd-plan-phase 1`. Primary readiness review of final 01-07 source/materials, then the single combined human session in docs/evidence/checkpoint-session.md. All EVID requirements remain Pending. Do not launch Phase 2 from preparation counts.
### Blockers/Concerns ### Blockers/Concerns
- Final 01-07 readiness passes 11,000 immutable files and local suite passes; strict audit still exits 1 with no structural errors, 0/120 accepted obligations and ten pending human findings. This is an actual evidence dependency, not a test failure or auto-approval gate.
- Phase 1: Working whole-original reference capture and current native Windows comparison remain unverified access dependencies. Record limitations; keep acceptance open while independent source-backed recovery continues. - Phase 1: Working whole-original reference capture and current native Windows comparison remain unverified access dependencies. Record limitations; keep acceptance open while independent source-backed recovery continues.
- Phase 2: Real derived responses, helper membership/activation/cleanup, physical order and shared mutable reclip remain live admission gates. Lab/outside capsule stays until its replacement gate closes. - Phase 2: Real derived responses, helper membership/activation/cleanup, physical order and shared mutable reclip remain live admission gates. Lab/outside capsule stays until its replacement gate closes.
- Full-game completion requires current integrated native Linux/Windows and original-reference evidence. Compilation, copied-original probes and Wine have narrower scopes. - Full-game completion requires current integrated native Linux/Windows and original-reference evidence. Compilation, copied-original probes and Wine have narrower scopes.
@@ -104,6 +108,6 @@ No original-required category deferred outside full reconstruction. Later phases
## Session Continuity ## Session Continuity
Last session: 2026-11-13T17:04:40.619Z Last session: 2026-11-14T05:39:45.079Z
Stopped at: Completed 01-06-PLAN.md Stopped at: Phase1 verified human_needed; ten UAT checks and combined actual session pending
Resume file: None Resume file: .planning/phases/01-reproducible-fidelity-baseline/01-UAT.md
+17 -3
View File
@@ -1,10 +1,10 @@
--- ---
schema_version: 1 schema_version: 1
open_count: 1 open_count: 2
waived_count: 0 waived_count: 0
fixed_count: 1 fixed_count: 1
total_count: 2 total_count: 3
last_updated: 2026-11-13T17:02:56.623Z last_updated: 2026-11-13T17:20:49.885Z
--- ---
# Broken Windows Ledger # Broken Windows Ledger
@@ -17,6 +17,7 @@ last_updated: 2026-11-13T17:02:56.623Z
|----|-------|------|------|------|-------------|--------|--------|-------------|-------------| |----|-------|------|------|------|-------------|--------|--------|-------------|-------------|
| 1 | 01 | deviation | tests/test_fidelity_sessions.py | | Task 2 also strengthens shared receipt security regressions in the task-1 test file; fixed and verified. | fixed | | 2026-11-13T00:12:34.143Z | 2026-11-13T00:13:04.410Z | | 1 | 01 | deviation | tests/test_fidelity_sessions.py | | Task 2 also strengthens shared receipt security regressions in the task-1 test file; fixed and verified. | fixed | | 2026-11-13T00:12:34.143Z | 2026-11-13T00:13:04.410Z |
| 2 | 01 | unrun-verify | docs/evidence/linux-session.md | | Actual Linux display, physical-input and audible capture remains open: no display session and only auto_null audio; all 40 Linux obligations await the final combined session. | open | | 2026-11-13T17:02:56.623Z | | | 2 | 01 | unrun-verify | docs/evidence/linux-session.md | | Actual Linux display, physical-input and audible capture remains open: no display session and only auto_null audio; all 40 Linux obligations await the final combined session. | open | | 2026-11-13T17:02:56.623Z | |
| 3 | 01 | unmet-truth | docs/evidence/phase01-baseline.md | | Actual original-DxWnd/native Linux/native Windows capture and combined human review remain OPEN0/120; strict audit human_needed. | open | | 2026-11-13T17:20:49.885Z | |
````json ````json
[ [
@@ -45,6 +46,19 @@ last_updated: 2026-11-13T17:02:56.623Z
"recorded_at": "2026-11-13T17:02:56.623Z", "recorded_at": "2026-11-13T17:02:56.623Z",
"resolved_at": null, "resolved_at": null,
"milestone": null "milestone": null
},
{
"id": 3,
"kind": "unmet-truth",
"phase": "01",
"file": "docs/evidence/phase01-baseline.md",
"line": null,
"description": "Actual original-DxWnd/native Linux/native Windows capture and combined human review remain OPEN0/120; strict audit human_needed.",
"status": "open",
"reason": "",
"recorded_at": "2026-11-13T17:20:49.885Z",
"resolved_at": null,
"milestone": null
} }
] ]
```` ````
@@ -1,37 +1,35 @@
<!-- CONSUMED: final verification completed human_needed on2026-11-14. Current next action: $gsd-verify-work 1 and combined actual human session; historical interrupted-verifier notes below are superseded. -->
--- ---
context: phase context: phase
phase: 01-reproducible-fidelity-baseline phase: 01-reproducible-fidelity-baseline
plan: "05" plan: "07"
task: 2 task: 3
total_tasks: 2 total_tasks: 3
status: consumed status: consumed
last_updated: "2026-11-13T16:07:37.872347+00:00" last_updated: "2026-11-13T22:26:46.798618+00:00"
--- ---
# Consumed quota-interrupted checkpoint # Final verification quota checkpoint
Plan01-05 is now complete and primary-reviewed (SUMMARY2d48ee5, tracking1af5217).
Continue01-06 task1; do not repeat the historical interrupted task below.
Quota watcher is installed/running; hook trust remains separate.
Quota interruption after server-restart recovery. Plans01-01..04 complete, primary-reviewed and pushed through de68796. Currentplan01-05 task1 RED446930d/GREEN6112339; task2 RED818191c. No01-05SUMMARY. Preserve partial uncommitted edits to scripts/collect-fidelity-windows.ps1 and tools/recon/fidelity_checkpoint.py; preserve unrelated tools.yaml. Do not restart task1 or treatREDcommit as completion. Inspect actual gitdiff before continuation.
Existing generated packages artifacts/fidelity/01-05-packages/{linux-x64,win-x64} and tracerbundle artifacts/fidelity/01-05-tracer-checkpoint exist; inspect manifests/logs rather than rebuilding blindly. Task2 REDreproduced23tests with missing-session-materials assertion/statusAPI error. Cached local PowerShell executable .tools/powershell-check/root/opt/microsoft/powershell/7/pwsh and cacheddeb found; no successful execution/provenance was reported before quota. No third-party installers redistributed. Need finish task2Windowsagenda/selftests/complete truthfulresults, verify, writeSUMMARY andhandlerstate; then primaryreview/push. All120actualoriginal-DxWnd/nativeLinux/nativeWindowsacceptanceOPEN. Plans01-06Linuxcapture/01-07combinedhands-onreadiness+acceptance remain.
Sequential nativeexecutors because worktreebasecheckcannotresolveorigin/HEAD (repoGitea/main). Maincommits authorized;git.allow_default_branch_commits=true. Local sockettests/Node runner needescalation to actuallyexecute namedtests. Fullwave2scripts/test.sh authorizedpasses462Python+2HUD/allmanaged/36GPUzeroerrorsGTX1070/539hashes; observer23managed+7process/privateXvfb4onoffidentical. No newWindowsororiginalcomparison.
User asked howtoresumeandautomatelow5husagepause. Researched officialCodexaccount/rateLimits/read plusaccount/rateLimits/updated andPreToolUse/PostToolUsehooks; no guardconfigured. OnlySessionStarthook currentlyconfigured;statuslinealreadyfive-hour-limit. Do not claimautopauseinstalled. Need customwatcher/hook before it canbeautomatic. No activeworkersknown;recover_01_05 returnedquotaerror, do notimmediatelyredispatchwhilequotaexhausted. Resumewhenuserrequestsafterlimitreset; inspectactualremainingquota ratherthanstale10:28PMreset. No sourcefeatureworkwasdonebyprimaryforthisquestion.
Quota guard explicitly requested pause at15%. Resume completed task01-07-03 and recovered fullsuite exit0 (782.049626s), then reviewed/fixed allfive source-integrity findings. Do NOT redo implementation or tests. Source commits through02d182f, review/coverage/security documentation71366e7. Fullsuite556Python/180fidelity,27Node,23observer,2HUD,51managedentrypoints,36GPUrenderedreceipts,zeroVulkanvalidationerrors,SDLdummychecks,539originalhashes. Latertooling-onlyfixes: all191fidelityregressions PASS43.355s; focused26scenario,23capture,29acceptance,27Node,18LinuxhostedPowerShell. All539originals unchanged. No runtime changes afterfullsuite; no need13minGPUrerun forcurrentPython/collector fixes.
Historicalreview5915128: CR01selected-vs-reviewedpath,CR02originalinventory/executablebinding,CR03copy-stateidentity,WR01viewerledgerprojection,WR02interruptedWindowsfinalization. Fixes5569bc2,bda35e5,6e5ee0b,548c97a,2608517,a821754. Independentre-reviewcaughtremaininghash-onlycopy-statebypass; RED48fca0d/GREEN02d182f requiresactual_checked_artifactwithrootinside_scenario_observation; callersupdated. Finalindependentre-reviewallfiveFIXED in01-REVIEW-VERIFY.md; dispositionopen0. Securityauditorfinal22/22mitigated, threats_open0 in01-SECURITY.md. Nyquistautomationcoveragevalidatedall15taskbindings; manualacceptanceopen;191fidelityaggregate43.355sec exceeds30secquicktargethonestly. UIreviewdisabledconfigfalse. No remainingknowncode/securityblockers.
Currentfreshfinalbundle dist/fidelity/phase01 has11001immutableentries. Currenthashes/readinessreceipt artifacts/fidelity/verification/01-07-final-checkpoint.json. readyexit0true,strictauditexit1 errors[] accepted0/120,10humanpending; logs artifacts/fidelity/01-review-fixes/readiness-final.json,acceptance-final.json,python-fidelity-final.log. Oldbundlespreserved phase01-pre-review-48100025 andphase01-pre-copy-artifact-7ceebcb3. ActualLinuxfailedpreflightimportedcurrentbundle/results/imported. Runtimepackage source446930d dirty/diff90cef956 unchanged; source/docscommitsmustnotrelabelitsidentity. Original/nativeWindows+DxWnd andphysicalLinuxvisible/audible/browserreviewremainonecombinedhuman session pending. Humanonlycollects/observes/returns; agent-ownedexactnormalizationmapping incheckpoint-session.md. No capture request issued yet because finalphaseverification/handoffpending.
Final typed verifier phase01_final_verification was dispatched at21%; quota15% interrupted it, instructedfinishonlyboundedhuman_neededreport/fingerprint thenreturn. It had readall7musthaves/summaries, checked25capabilities/33requirements/0unmapped/6groups/33rows,16/16decisioncoverage,40sourcefilesnoskip/debtscan. A mandatoryMVPgoalformatguard exposed existingROADMAPMode:mvp plainproseGoal. Rootauthorizedformat-only identicalintentuserstory and modifiedROADMAP.md uncommitted: As a tester, I want to reproduce identified original/port comparison scenarios, so that I understand exactly what the current reconstruction proves on each native platform. Validatorvalidtrue; no scope/successcriteriamodified. OneverifiercommandusedwrongunittestclassFidelityAcceptance (loadererror,correctclassAcceptanceTests); twoothernamedbehaviorcheckspassed; don'tmislabelthatcommandassuccess. Priorfulltargeted29passestablishactualcoverage.
NEXT: Reconcile currentverifier's 01-VERIFICATION.md and CLI verification.status; ifreport/fingerprintabsentfinishthat ONLY beforeanynewphase. FingerprintmustbeownerCLIgenerated, notmanual. Oncehuman_neededstatusvalid, persistUATfromnamedhumanitems, updateSTATE/consumedhandoffs, commitverifiedreport+goalmetadata+handoffdocs andpush verifiedsource/tooling toauthorizedGitea/main. Lastpushedhead remainsd18f551; later01-07/task3/reviewfix/auditcommits arelocalawaitingfinalverification. Preserveunrelatedtools.yaml. Do notadvancephase2orclaimPhase1accepted; allEVIDIDsPending0/120humanacceptance. No source changesuncommittedexceptROADMAPformatandpossiblynewverifierreport.
Nativeagents/sourcewritesallfinishedexceptverifierreportbeingclosed. Quota watcher runs and actual15%steeringworks. Noauto-resume; usermust $gsd-resume-workafterreset. Don'tspendquota rereadingmassiveGSDscriptbodies orrerunningfinished13minfullsuite. Existinglocalpackages/media/originalcopiesstaylocal, noCI/uploads. MaintracksGitea/main, scoped.gitwriteescalation; retainhistoricalhandoffsmarkconsumedratherthandelete (priorautomaticreviewrejecteddeletion).
## Required Reading ## Required Reading
AGENTS.md; ../AGENTS.md; ../prompt.MD;01-CONTEXT.md;01-05-PLAN.md;01-01..04-SUMMARY.md; actualcheckpoint/PowerShell source/tests and gitdiff. AGENTS.md,parentinstructions,HANDOFF.json,01-07SUMMARY,01-REVIEW-VERIFY,01-SECURITY,01-VALIDATION,and01-VERIFICATIONifpresent.
## Critical Anti-Patterns ## Critical Anti-Patterns
| Pattern | Description | Severity | Prevention Mechanism | | Pattern | Description | Severity | Prevention Mechanism |
|---|---|---|---| |---|---|---|---|
| Duplicate partialplan | Existing taskcommits withoutSUMMARY | advisory | Reconcile git/history/diff; resume task2, never reruntask1 | | Redo completed tests | Fullsuiteand191fidelitychecksfinished | advisory | Reconcile savedlogs first; rerunonlyafternewchanges |
| False nativeacceptance | Preparedbundle/PowerShellonLinux isnotWindowsgameplay | advisory | Retain actualplatform/method and pendingoriginal/nativeacceptance | | False phase completion | Preparedmaterialsfailactualstrictacceptance0/120 | advisory | KeepEVIDPending andhuman_needed; owner verification.status beforeadvance |
## Infrastructure State ## Infrastructure State
No liveexecutor reported afterrestart; lastrecoverexecutorreturnedquotaerror. Generatedpackages/cachedPowerShellremainlocal. No externalasyncjobs known. Testsfinished; verifierinterruptedatpause; reportreconciliationpending; localquota watcher running. No sourceworkeractive.
## Next Action ## Next Action
Afterquotareset resume01-05task2; finishmaterials/selftests before01-06/07. Userhasnotconfiguredautomaticquota-pausing. Inspect01-VERIFICATION.md and owner verification.status; finish report/fingerprint/UAT ifneeded, commit/pushverified01-07reviewedwork; neverredo task3/fulltests orautoapprovehumanacceptance.
@@ -0,0 +1,196 @@
---
phase: 01-reproducible-fidelity-baseline
plan: "07"
status: complete
completion_scope: autonomous preparation and pending-evidence reconciliation
acceptance: human_needed
subsystem: testing
tags: [fidelity, acceptance, checkpoint, local-regressions]
requires:
- phase: 01-06
provides: Linux collector and failed native preflight diagnostic
provides:
- Strict ready/audit gates and fresh local combined-session materials
- Pending original/native/human acceptance and exact reconciliation mapping
- Counted consolidated local regressions and measured final evidence status
affects: [phase01-acceptance, phase02]
tech-stack:
added: []
patterns: [receipt-bound human findings, immutable materials, explicit current selection, positive test counts]
key-files:
created: [tools/recon/fidelity_acceptance.py, tests/test_fidelity_acceptance.py, docs/evidence/checkpoint-session.md, docs/evidence/phase01-baseline.md]
modified: [tools/recon/fidelity_checkpoint.py, tests/test_fidelity_checkpoint.py, docs/evidence/capabilities.json, scripts/test.sh, docs/progress.md, docs/tasks.md, docs/decisions.md, docs/compatibility.md]
key-decisions:
- "Ready materials and local regressions never substitute for actual original/native acceptance; all 120 obligations and ten named human findings remain open."
- "The integration agent reconciles returned collector records through specified artifact mappings; the tester collects, observes and returns one combined session."
requirements-completed: []
actuals:
tokens: 18163
tasks: 2
commits: 5
plan_head_before: d18f551a26f90cd645309dcd545295911b581357
plan_head_after: 472500bf4e191c2080764471b6b08486c1909b3a
duration: "4h 36min observed commit-to-closeout elapsed, including quota pause; full suite 782.05s"
completed: 2026-11-13
coverage:
- id: D1
description: Immutable readiness and strict rejection of missing original/native/human evidence
verification:
- kind: integration
ref: tests/test_fidelity_acceptance.py; 23 checks in completed local suite
status: pass
- kind: integration
ref: fidelity_acceptance.py ready; 11000 immutable files
status: pass
human_judgment: false
- id: D2
description: Actual combined original-DxWnd/native Linux/native Windows capture and review
verification:
- kind: manual_procedural
ref: docs/evidence/checkpoint-session.md; acceptance.json 0/120
status: unknown
human_judgment: true
rationale: Actual moving content, physical input, audibility and paired playback remain unavailable; strict acceptance exits 1.
- id: D3
description: Counted fidelity regressions integrated with the existing complete local suite
verification:
- kind: integration
ref: artifacts/fidelity/01-07-full-suite.json; exit 0 in 782.0496263504028 seconds
status: pass
human_judgment: false
---
# Phase 01 Plan 07: Strict Fidelity Acceptance Checkpoint Summary
**Fresh 11,000-file offline materials pass readiness and the complete local suite; strict acceptance retains 0/120 original/native obligations and ten human judgments.**
Autonomous preparation and truthful pending-status reconciliation are complete.
Tasks 01-07-01 and 01-07-03 are complete. Task 01-07-02's permitted unavailable-
evidence projection is committed; its actual combined capture/review remains
pending. `status: complete` describes that preparation scope, never Phase 1 or
EVID acceptance. All EVID requirements remain Pending. Phase 2 is not advanced.
The stale quota handoff is retained for primary review/consumption separately.
## Performance and Accounting
- Earliest production-task commit: 2026-11-13T17:09:46Z; closeout: approximately 21:46Z.
- Observed elapsed interval includes the quota pause; active execution time was not measured continuously.
- Full authorized local suite: 782.0496263504028s, exit 0; runner reports 783s.
- Realized diff: 72,652 characters / 4 = 18,163 tokens, including committed quota metadata.
- Persisted plan ledger measures five commits before this summary; hashes above bound that measurement.
- Two fully completed tasks; one pending actual human task with its permitted documentation complete.
## Task Commits
| Task | Commit | Result |
|---|---|---|
| 01-07-01 RED | d78b135 | 18 intentional missing-API assertions fail; machine RED_EVIDENCE_OK |
| 01-07-01 GREEN | 026def9 | Strict audit, 23 passing tests, fresh final bundle and reconciliation checklist |
| 01-07-02 pending projection | fc5e936 | Capability ledger retains failed diagnostic and unresolved human states |
| Quota checkpoint | b732256 | Existing handoff/state only; no production behavior change |
| 01-07-03 | 472500b | Counted existing regressions and actual full-suite/status results |
## Verification Results
The complete suite ran once after the scoped reporter correction; its completed
receipt is `artifacts/fidelity/01-07-full-suite.json` and full output is
`artifacts/fidelity/01-07-full-suite.log`. No duplicate final suite was run.
| Verification | Actual result |
|---|---|
| Python discovery | 556 tests in 68.110s; 180 fidelity across all eight modules |
| Fidelity module counts | acceptance 23, capture 23, checkpoint 24, ledger 31, observation 7, review 21, scenarios 22, sessions 29 |
| Node viewer | 27 tests pass with explicit TAP reporter |
| Standalone managed observer | 23 checks pass |
| HUD Python | 2 separate tests in 0.171s |
| Managed entry points/build | All 51 test-project invocations and main build pass |
| Vulkan | 36 rendered receipts across 32 device groups; 27 saved readbacks; zero reported validation errors |
| Material regression | 17 Vulkan material/readback assertions pass, zero validation errors |
| SDL audio | Existing dummy-audio effect/stream/scene/cutscene checks pass; audibility remains unverified |
| Preservation | Verified 539 unchanged original files |
| Final readiness recheck | 11,000 immutable files; materials_ready=true, acceptance=human_needed |
| Final strict audit recheck | Exit 1; errors=[], accepted 0/120; ten human findings pending |
Optional `NEUTRON_WINDOW_TEST=1` checks were not enabled; no new native window,
physical-input, audible, original gameplay or native Windows execution is claimed.
Existing NU1900 unavailable vulnerability-metadata warnings remain unrelated.
First attempt: Python 556 passed in 71.765s and Node 27 passed, but the new TAP
count guard rejected Node's default spec reporter. Its 74.647s attempt/log is
retained as `01-07-full-suite-attempt1.{json,log}`. Explicit TAP passed focused
checks and the completed full rerun.
## Exact Evidence and Package Identity
- Final bundle: `dist/fidelity/phase01`; READY SHA-256 `48100025fbdcbb5310bdae28b5cae1e8f17412aa7b03be5f823616cd88211951`.
- Manifest SHA-256: `46610a4029f1341e7f48147370a81daaa8ff799a60fba388b641a0678d2032aa`.
- Exact tool/package identities: `artifacts/fidelity/verification/01-07-final-checkpoint.json`.
- Runtime source: `446930d2a30d6d616c60ac5e59e4169a840bea09`, dirty true, diff `90cef95669caece53fe2d2c4736cf2ac05ed27f5d25ca03ab572589686bcb73d`. Later tool/docs commits do not relabel existing packages.
- Actual failed receipt: `linux-01-06-matrix-preflight-linux`, imported under final `results/imported/`; diagnostic viewer: `results/failed-linux-review/index.html`.
- Final audit: `dist/fidelity/phase01/results/acceptance.json`; actual capture and human acceptance remain OPEN.
- Capability validation: 25 capabilities, 33 requirements, 33 reconciled rows, six groups; acceptance OPEN.
No runtime source changed in task 3, no package rebuild/relabel occurred, and no
originals, generated packages, media or traces were uploaded. All remain local.
## Files Created/Modified
`fidelity_acceptance.py` and its dedicated tests separate readiness from strict
acceptance. The existing checkpoint assembler/tests add required final materials
and tool provenance. `checkpoint-session.md` prepares one combined review and
`phase01-baseline.md` records actual/pending findings. `capabilities.json` retains
the failed receipt and unresolved current states. `scripts/test.sh` counts the
existing fidelity Python/Node/observer checks; the four root status reports cite
the completed suite, exact identities and pending acceptance. Planning artifacts
record the quota interruption and final autonomous preparation scope.
## Decisions Made
Prepared bytes, diagnostic fixtures and local regression success do not replace
actual original/native receipts or human judgments. Reconciliation remains an
agent-owned operation after one combined tester session; no fragmented early
capture request or new universal fidelity tolerance is introduced.
## Deviations from Plan
- Approved ownership extension: minimal checkpoint MATERIALS expansion, actual tool_source metadata and existing material-membership assertion update make the final immutable bundle contain Linux/audit dependencies; no second assembler/capture subsystem.
- Baseline pending report was created with task 1 because it must exist before immutable assembly; task 2 actual capture acceptance remains open.
- **[Rule 1 - Bug]** Task 3's new positive-count guard expected TAP while installed Node emitted spec. Explicit `--test-reporter=tap` fixes that scoped runner mismatch; focused 27 checks and complete rerun pass. Commit: `472500b`.
- Quota reserve interrupted closeout; the retained quota commit did not add behavior. The completed suite was recovered after reset without repeating it.
## TDD Gate Compliance
Task 1 RED preceded GREEN: `d78b135` then `026def9`. Saved
`artifacts/fidelity/01-07-red.{log,json}` records RED_EVIDENCE_OK. Prior semantic
inspection confirmed the empty-matrix test ran and failed on planned API existence,
without load/setup failure. Final suite executes all 23 acceptance checks.
## Deferred Issues and Human Dependencies
Actual original-DxWnd 40/native Windows 40/native Linux 40 obligations remain OPEN.
A1/A2, both EVID-02/EVID-04 unclassified assumptions, P1/P2/P3, browser,
paired_review and physical_input are the ten pending named findings. No strict
acceptance verification passed; its expected nonzero result records that missing
evidence. `.planning/WINDOWS.md` entry 3 tracks this unmet truth; entry 2 retains
the Linux capture access dependency. The primary reviews readiness before the
single combined human session. The roadmap source-backed continuation exception
does not waive these dependencies or authorize a phase transition here.
## Known Stubs
None preventing autonomous preparation. Checklist JSON metavariables are explicit
human-review templates, never positive findings. Empty review dictionaries in
negative tests and fail-closed audit defaults intentionally exercise missing
evidence; no production UI/data stub was introduced. Existing gameplay admission
gates remain unchanged. No new security surface beyond the planned local evidence
file/import boundaries was introduced.
## Self-Check: PASSED
All created source/test/checklist/baseline files, final local checkpoint, completed
suite receipt and exact identity receipt exist. All five recorded commits are
ancestors of the measured HEAD. Final readiness passes and strict audit retains
errors=[], 0/120 and ten pending findings. Unrelated `tools.yaml` is preserved.
## Independent review closure
Five confirmed findings were fixed and independently verified; see01-REVIEW.md,01-FIX-REPORT.md,01-REVIEW-VERIFY.md and01-REVIEW-DISPOSITION.md. Final refinement02d182f requires actual artifact bytes at the scenario boundary;191 fidelity checks pass43.355s. The new checkpoint has11,001 immutable entries with current local identities in artifacts/fidelity/verification/01-07-final-checkpoint.json; prior identity notes remain historical. All22 planned security threats are closed, while actual0/120 acceptance and ten named human findings stayOPEN. No original/native acceptance or phase advancement is implied.
@@ -0,0 +1,114 @@
---
phase: 01-reproducible-fidelity-baseline
fixed_at: 2026-11-13T22:09:37Z
review_path: .planning/phases/01-reproducible-fidelity-baseline/01-REVIEW.md
iteration: 1
findings_in_scope: 5
fixed: 5
skipped: 0
status: all_fixed
---
# Phase 01: Code Review Fix Report
All five confirmed findings were fixed. Their logic changes require independent
human/reviewer verification; automated results below establish the stated tooling
contracts, never original/native gameplay acceptance. No runtime/gameplay source,
original file, package bytes, review disposition, or phase state was changed.
| Finding | Status | Commit | Applied fix and regression |
|---|---|---|---|
| CR-01 | fixed: requires human verification | `5569bc2` | Carry the actual selected receipt path into digest review. Two different sibling JSON files without a sidecar prove that only the selected file's digest satisfies the human finding; absent/unrelated digests leave findings pending. |
| CR-02 | fixed: requires human verification | `bda35e5` | Supply the complete checkpoint original file inventory, recompute its digest, and bind `identity.executable.original_member` plus size/header/hash to the exact pristine member. Original pre/post/package/resources require full baseline file records and digest. Positive original fixtures retain actual member/executable hashes; wrong executable/member and altered inventory records fail. Writable-copy post changes are separately identified and remain allowed. |
| CR-03 | fixed: requires human verification | `6e5ee0b` | Bind both lifetimes to the validated named `identity.copy_pre` record; retained lifetimes also require `identity.retained_copy`. Unknown hashes and hashes of launcher/package/other state records fail. Fixtures now retain distinct actual copy-state files. |
| WR-01 | fixed: requires human verification | `548c97a` | Assemble the existing validated ledger projection before review export, seal it at `protocol/capability-ledger.json`, and compare viewer current/history against it during readiness. Actual preparation-to-bundled-renderer regression retains the named current and superseded startup records; a sealed viewer missing history is rejected. |
| WR-02 | fixed: requires human verification | `2608517` | Recover missing `run.json` only as aborted from the retained incomplete record. Preserve the raw initial bytes as an importable `recovery-initial.json` diagnostic artifact, retain session/start identity, remove initial placeholder end clocks, and reject captured promotion or launch-aligned events. Shared validation/import permits this open aborted record with absent end clocks. |
WR-01 has one additional positive regression commit, `a821754`, proving readiness
on a standalone copied checkpoint with no source Git checkout. No fix was skipped
or rolled back. Five finding commits plus this verification commit were made.
Modified source: `tools/recon/fidelity_acceptance.py`, `fidelity_receipts.py`,
`fidelity_checkpoint.py`, and `scripts/collect-fidelity-windows.ps1`. Tests:
`tests/test_fidelity_acceptance.py`, `test_fidelity_scenarios.py`,
`test_fidelity_checkpoint.py`, and `fidelity-windows.Tests.ps1`. Field contracts:
`docs/evidence/checkpoint-session.md` and `windows-session.md`. No new source file
or dependency was required.
## Verification
All gates ran locally in the **main checkout**. The primary explicitly authorized
a temporary `workflow.use_worktrees=false` override. Its original absent setting
was restored without staging or committing it; the unused clean worktree was
removed before edits. Unrelated untracked `tools.yaml` remains unchanged. Normal
Git hooks ran for every commit. The WR-01 refinement was folded into its commit
before the primary's no-rebase steering arrived; subsequent history is preserved.
Logs are retained under ignored `artifacts/fidelity/01-review-fixes/`:
- `python-fidelity.log`: all 189 fidelity regressions passed in 40.072 seconds.
Initial sandbox execution hit eight loopback-socket permission errors; the
successful scoped-escalation run permits only the local tests' necessary host
operations. These were environment errors, not accepted failed tests.
- `acceptance-final.log`: 29 acceptance tests passed after the final standalone
transfer regression was added. This includes the refined readiness path; these
tests overlap the 189-test run and are not added to its count.
- `node-viewer-direct.log`: 27 actual Node behavior tests passed. On this host
`node --test` reports an aggregate one-file result; direct execution supplied
the explicit 27-test count. The preparation test also rendered the real bundled
model with the bundled renderer and a DOM double, without claiming browser
playback evidence.
- `powershell.log`: 18 package-free synthetic tooling checks passed under cached
Linux-hosted PowerShell. This is not native Windows execution evidence.
- `recovered-import.log`: the actual incomplete-only PowerShell output passed
shared validation and atomic import; accepted is false. Raw fixture output and
imported bytes are retained in separate `test-windows-results/` and
`test-recovered-imports/` namespaces.
- `original-preservation.log`: all 539 original files unchanged. The same
inventory command passed after assembly as well; preparation independently
checked the original inventory before and after copying.
- Python parse checks and `git diff --check` passed. The prior 13-minute full
managed/GPU suite was not repeated because these changes touch tooling and
evidence contracts only.
## Fresh immutable checkpoint
The final checkpoint was assembled **once**, using unchanged existing
`artifacts/fidelity/01-05-packages/{linux-x64,win-x64}` bytes. The prior tree was
preserved at `dist/fidelity/phase01-pre-review-48100025`; the documented current
path remains `dist/fidelity/phase01`. No sealed member was patched after assembly.
Mutable results contain a fresh import of the existing failed Linux preflight
receipt and the unchanged pending human-review controls; no captured evidence was
invented. The former assembly remains historical evidence.
| Item | Identity/result |
|---|---|
| Current checkpoint | `dist/fidelity/phase01` |
| Immutable members | 11001 |
| READY SHA-256 | `7ceebcb3a22549a59bb9f7032c5c686b4ca4d32cf7b6a7d934e12e37f05e7aba` |
| Manifest SHA-256 | `a4da759bb264d63b716a931ae3b16a410baf01e36a7b2696ae8ed5649f77f7a9` |
| Tool commit | `a821754b6755151a0e33e4ac5065c8efd252b2e6` |
| Tool working-tree provenance | Tracked diff empty; dirty true solely from preserved untracked `tools.yaml`, identified by the manifest |
| Sealed runtime source | `446930d2a30d6d616c60ac5e59e4169a840bea09`, dirty true |
| Runtime publish diff | `90cef95669caece53fe2d2c4736cf2ac05ed27f5d25ca03ab572589686bcb73d` |
| Linux package tree | `124cf271e4952f3822eec5c24358447fcffc9e9e1803aded8d96d4d4472dc5a3` |
| Windows package tree | `335e5b75ec15c0fa904113d8b69d4f50e2cfa403f1f2f225353bd9e586322ef4` |
| Startup viewer projection | Two current and two historical records retained |
| Readiness | Exit 0, `materials_ready: true`, `acceptance: human_needed` |
| Strict acceptance | Exit 1, 0/120, no structural errors, all ten human findings pending |
`prepare-checkpoint.log`, `readiness.json`, `acceptance.json`, and
`failed-linux-import.json` retain the actual results. The readiness and acceptance
reports also reside under the current bundle's mutable `results/` directory.
The ten pending findings remain A1, A2, EVID-02-unclassified,
EVID-04-unclassified, P1, P2, P3, browser, paired_review, and physical_input.
The host still lacks actual original/native Windows capture access and a usable
Linux display/audio session. Independent re-review and the primary's remaining
security/coverage gates precede any combined capture request.
This report is intentionally uncommitted for the primary workflow to review and
commit. No push, package upload, original execution, or original write occurred.
## Final artifact-boundary refinement
CR-03 independent re-review caught pathless hash-only named records. RED48fca0d reproduces fresh/retained missing-file, wrong-size and hash-only cases; GREEN02d182f validates actual named files inside scenario observation with an explicit root. All191 fidelity tests pass in43.355s; focused26 scenario/23 capture/29 acceptance checks pass. Independent reviewer confirms allfive findings fixed; security auditor closes22/22 planned threats. The earlier11001-file bundle is retained locally; current dist/fidelity/phase01 is freshly assembled from corrected source with original runtime package identities unchanged.
@@ -0,0 +1,39 @@
---
phase: 01
review: 01-REVIEW.md
titles: json
findings:
- id: CR-01
severity: critical
disposition: fixed
title: "Human review is checked against a different file from the selected receipt"
- id: CR-02
severity: critical
disposition: fixed
title: "Original applicability never binds the executed executable or preservation inventories"
- id: CR-03
severity: critical
disposition: fixed
title: "Fresh-copy continuity accepts a hash that identifies no artifact"
- id: WR-01
severity: warning
disposition: fixed
title: "Checkpoint assembly bypasses the capability ledger projection"
- id: WR-02
severity: warning
disposition: fixed
title: "An interrupted Windows collector cannot be finalized through the documented recovery command"
open: 0
total: 5
recorded: 2026-11-13T21:58:50.502559+00:00
---
# Phase 01: Code Review Disposition
| Finding | Severity | Disposition | Source |
|---|---|---|---|
| CR-01 | critical | fixed | 01-REVIEW-VERIFY.md; independent re-review |
| CR-02 | critical | fixed | 01-REVIEW-VERIFY.md; independent re-review |
| CR-03 | critical | fixed | 01-REVIEW-VERIFY.md; independent re-review |
| WR-01 | warning | fixed | 01-REVIEW-VERIFY.md; independent re-review |
| WR-02 | warning | fixed | 01-REVIEW-VERIFY.md; independent re-review |
@@ -0,0 +1,75 @@
---
phase: 01-reproducible-fidelity-baseline
verified: 2026-11-13T22:19:18Z
review_path: .planning/phases/01-reproducible-fidelity-baseline/01-REVIEW.md
fix_report_path: .planning/phases/01-reproducible-fidelity-baseline/01-FIX-REPORT.md
verified_head: 02d182f35de643f9d68699b2fff1d219dd132edb
findings_verified: 5
fixed: 5
open: 0
findings:
critical: 0
warning: 0
info: 0
total: 0
status: clean
---
# Phase 01 review-fix verification
All five fixes are verified. The final CR-03 refinement requires actual backing artifacts for named copy-state identities and rejects the hash-only records that survived its first fix. No reviewed finding remains open.
| Finding | Disposition | Independent verification |
|---|---|---|
| CR-01 | FIXED | The selected path is retained and its own digest is compared with the human finding. The sibling-digest and absent-digest regressions leave human checks pending; the actual selected-file digest satisfies that boundary. |
| CR-02 | FIXED | Complete baseline records and their recomputed digest bind original pre/post/package/resources. The explicit executed `original_member` binds executable size/header/hash. Wrong executable/member and inconsistent inventories are rejected; independently identified writable `copy_post` changes remain allowed. |
| CR-03 | FIXED | Scenario validation now checks the actual named copy-pre artifact for both lifetimes and the retained snapshot for retained runs. Previous hash-only reproductions and an isolated retained-snapshot reproduction are rejected; valid named state files still qualify. |
| WR-01 | FIXED | Assembly exports the validated ledger projection; readiness compares current/history with the sealed projection. The preparation-to-bundled-renderer check preserves named current/superseded records. The standalone-transfer check needs no source Git checkout, and missing viewer history is rejected. |
| WR-02 | FIXED | A real Linux-hosted PowerShell finalizer reproduction recovered an incomplete-only synthetic run as aborted. Initial raw bytes and session identity survived, end clocks remained absent, captured promotion was rejected, and shared validation plus atomic import succeeded with acceptance false. |
## CR-03 refinement verified
**Original classification:** BLOCKER
**Current disposition:** FIXED by `02d182f35de643f9d68699b2fff1d219dd132edb`, with regression `48fca0d`.
**File:** `/home/cristian/codex/Neutron/GamePort/tools/recon/fidelity_receipts.py:667-678`
**Related:** `/home/cristian/codex/Neutron/GamePort/tools/recon/fidelity_receipts.py:383-385`
At `a821754`, `_scenario_observation()` compared continuity digests with named identity strings while the generic validator skipped dictionaries without `path`. The refinement now passes the receipt root to scenario validation and calls `_checked_artifact()` on the actual named state records before comparing digests. The scenario audit and Linux capture matrix both pass their artifact root; their direct test callers were updated as well.
The bounded reproduction below uses existing synthetic metadata fixtures and launches no game. It previously demonstrated the gap and now demonstrates rejection for both native lifetimes:
```python
from test_fidelity_scenarios import FidelityScenarios
import fidelity_receipts as receipts
fixture = FidelityScenarios()
fixture.setUp()
try:
for lifetime in ('fresh', 'retained'):
value, root = fixture.receipt(
lifetime + '-natural-ordinary', 'dialogue-return')
value['identity']['copy_pre'] = {'sha256': 'f' * 64}
value['continuity']['copy_pre_sha256'] = 'f' * 64
if lifetime == 'retained':
value['identity']['retained_copy'] = {'sha256': 'e' * 64}
value['continuity']['retained_copy_sha256'] = 'e' * 64
result = receipts.audit_scenarios(
fixture.protocol(), [(value, root)])
print(lifetime, result['accepted'], result['invalid'])
finally:
fixture.doCleanups()
```
Run from the repository with `PYTHONPATH=tests:tools/recon`. Earlier output at `a821754` was `fresh 1 []` and `retained 1 []`. Rerunning at `02d182f` gives zero accepted slots and `Reference must be a bounded relative POSIX path` in each invalid list. A third reproduction retaining valid copy-pre but supplying only a hash for `identity.retained_copy` is rejected independently. The unmodified fresh and retained metadata controls each still accept one slot.
**Additional verification:** Four selected scenario tests passed in **0.424 seconds**: backing-file rejection for both lifetimes, named continuity binding, unrelated retained-snapshot rejection, and complete positive coverage of all 120 metadata slots. The new backing-file test covers hash-only, missing-file and wrong-size state identities, including the retained snapshot. This closes the reported artifact-binding gap without changing the four other verified fixes.
## Verification evidence and limits
Read the historical review, fix report and actual source/test diffs for `5569bc2`, `bda35e5`, `6e5ee0b`, `548c97a`, `2608517`, and `a821754`, then the final `48fca0d` regression and `02d182f` refinement. Initially ran 11 selected Python tests in **2.109 seconds**, all passing: selected-file review binding; original executable/member and inventory rejection; mutable generated-copy allowance; complete positive metadata matrix; standalone readiness without Git; malformed viewer history; actual assembled model through its bundled renderer; named pre/retained continuity; and aborted missing-end-clock import. The additional hash-only identity gap discovered during that verification is closed by the independently repeated checks above.
Separately exercised the actual PowerShell recovery function with a disposable synthetic prepared checkpoint, rejected captured promotion, recovered raw media, compared both raw initial copies byte-for-byte, verified absent end clocks, validated and imported the resulting open aborted receipt. This was Linux-hosted tooling execution, not native Windows evidence.
No full suite, whole 11,001-file checkpoint readiness/hash walk, original execution or gameplay capture was repeated. The primary's current bundle identities and pending 0/120 human acceptance remain separate evidence; this verification does not promote them. Source and tests were read-only, no commit was made, and unrelated concurrent report edits were preserved.
Historical `01-REVIEW.md` is unchanged; its SHA-256 is `493c0b9b7b491f7dcc896d6cfda675ced837f56ee32daf2bbf1cd98f1527f74c`.
@@ -0,0 +1,137 @@
---
phase: 01-reproducible-fidelity-baseline
reviewed: 2026-11-13T21:56:48Z
depth: standard
files_reviewed: 44
files_reviewed_list:
- .codex/hooks.json
- docs/codex-quota-guard.md
- docs/compatibility.md
- docs/decisions.md
- docs/evidence/README.md
- docs/evidence/capabilities.json
- docs/evidence/checkpoint-session.md
- docs/evidence/linux-session.md
- docs/evidence/phase01-baseline.md
- docs/evidence/scenarios.json
- docs/evidence/windows-session.md
- docs/progress.md
- docs/tasks.md
- scripts/collect-fidelity-linux.sh
- scripts/collect-fidelity-windows.cmd
- scripts/collect-fidelity-windows.ps1
- scripts/prepare-fidelity-checkpoint.sh
- scripts/test.sh
- src/GamePort/Application/FidelityObservation.cs
- src/GamePort/Program.cs
- tests/GamePort.FidelityObservationTests/GamePort.FidelityObservationTests.csproj
- tests/GamePort.FidelityObservationTests/Program.cs
- tests/fidelity-viewer.test.mjs
- tests/fidelity-windows.Tests.ps1
- tests/test_codex_quota_guard.py
- tests/test_fidelity_acceptance.py
- tests/test_fidelity_capture.py
- tests/test_fidelity_checkpoint.py
- tests/test_fidelity_ledger.py
- tests/test_fidelity_observation.py
- tests/test_fidelity_review.py
- tests/test_fidelity_scenarios.py
- tests/test_fidelity_sessions.py
- tools/recon/fidelity.py
- tools/recon/fidelity_acceptance.py
- tools/recon/fidelity_capture.py
- tools/recon/fidelity_checkpoint.py
- tools/recon/fidelity_ledger.py
- tools/recon/fidelity_receipts.py
- tools/recon/fidelity_review.py
- tools/recon/fidelity_viewer/index.html
- tools/recon/fidelity_viewer/style.css
- tools/recon/fidelity_viewer/viewer.mjs
- tools/workflow/codex_quota_guard.py
findings:
critical: 3
warning: 2
info: 0
total: 5
necessity: 0
status: issues_found
---
# Phase 01: Code Review Report
**Reviewed:** 2026-11-13T21:56:48Z
**Depth:** standard
**Files Reviewed:** 44
**Status:** issues_found
## Summary
Three acceptance-integrity defects permit mismatched reviewed bytes, unrelated original executable bytes, or an unbound fresh-copy identity to contribute accepted obligations. The prepared capability viewer also omits current/history evidence, and the Windows finalizer cannot recover the interrupted-run state described by its instructions.
Scope is the canonical `/tmp/gameport-phase01-review-scope.json` file union at HEAD `215d01e43e103f3fbb7e26b43607cd09f2856492`. Resolver status is **degraded**, reason `no-task-commit-rows`, using its real phase range from `9aa49970e43bc9ca5470b884757e3481e0c0293a`. The union contains 44 files; all seven SUMMARY key-file lists are covered, and none of these paths is ignored. No structural pre-pass or external reviewer evidence was supplied. The necessity rubric was read; no necessity finding was established.
The pending 0/120 original/native obligations and ten human findings are expected acceptance dependencies, not implementation defects. Findings below concern enforceable identity/continuation contracts. Reproductions used disposable synthetic metadata only; the Windows recovery reproduction used Linux-hosted PowerShell, not native Windows. The existing complete-suite run was not repeated. No original was executed or modified, no source was edited, and no commit was made; unrelated `tools.yaml` was preserved.
## Narrative Findings (AI reviewer)
## Critical Issues
### CR-01: Human review is checked against a different file from the selected receipt
**Classification:** BLOCKER
**File:** `/home/cristian/codex/Neutron/GamePort/tools/recon/fidelity_acceptance.py:134-143`
**Issue:** `current.json` may select any contained receipt filename. The loop reads that path, discards it, then compares the human-review digest against `directory / 'receipt.json'`. A sibling `selected.json` can therefore supply the accepted record while the human finding binds unrelated `receipt.json` bytes. Raw result directories need not have an import sidecar, so `read_receipt` does not close this gap. This defeats the explicit receipt-byte review boundary; the same mismatch can affect every selected slot.
**Evidence:** A bounded synthetic reproduction selected `run/selected.json`, stored a different object at `run/receipt.json`, and supplied the latter's digest in `human-review.json`. The real `audit()` returned `matrix.accepted == 1`, `human_needed == []`, and `errors == []`, despite the selected digest differing from the reviewed digest. Only material readiness was mocked to isolate receipt selection; hash checking, parsing and matrix evaluation ran normally.
**Fix:** Carry the actual selected path/digest alongside each record and compare `receipt_sha256[receipt_id]` with that file. Alternatively, explicitly reject every selected basename other than `receipt.json` before reading it. Missing or different selected-file digests must invalidate the human finding. Add a regression with two different sibling JSON files and no sidecar.
### CR-02: Original applicability never binds the executed executable or preservation inventories
**Classification:** BLOCKER
**File:** `/home/cristian/codex/Neutron/GamePort/tools/recon/fidelity_acceptance.py:81-84`
**Issue:** The original-DxWnd branch checks only a `tree_sha256` string inside the receipt's `original_pre` JSON. It does not compare the actual identified executable against its selected pristine inventory member, validate original package/resource identities against that baseline, or check `original_post`. The generic validator checks each referenced file's own hash, which establishes identity but not applicability. Consequently, attaching a correct original-pre inventory to an unrelated executable is sufficient to pass `_bind`. This is weaker than the concrete executable/pre/post mapping promised in `docs/evidence/checkpoint-session.md:90-94`.
**Evidence:** Starting with the existing complete metadata fixture for an original-DxWnd slot, a synthetic diagnostic replaced only `identity.executable` with the actual size/hash of a new file containing `synthetic wrong original executable`. The expected original-pre record stayed unchanged. `audit_records()` still returned one accepted obligation and no errors. The receipt schema otherwise remained valid; no false artifact hash was required.
**Fix:** Pass the checkpoint's actual pristine file inventory into original binding, retain the exact selected original member path, and compare the receipt executable identity with that member. Validate package/resources and authoritative pre/post inventories against the same baseline; recompute inventory digests from their file records rather than trusting an embedded digest alone. Writable-copy changes must stay separately recorded. Add negative tests for a wrong executable and inconsistent pre/post inventory content.
### CR-03: Fresh-copy continuity accepts a hash that identifies no artifact
**Classification:** BLOCKER
**File:** `/home/cristian/codex/Neutron/GamePort/tools/recon/fidelity_receipts.py:659-669`
**Issue:** All cells require `copy_pre_sha256`, but fresh cells only check its 64-hex syntax. Actual identity membership is checked inside the retained-only branch. Thus a fresh observation can claim a nonexistent copy state and still fill an accepted slot, contrary to the fresh lifetime procedure's separately identified generated execution copy. The executable/package binding does not identify that per-run startup state.
**Evidence:** With `FidelityScenarios.receipt('fresh-natural-ordinary', 'dialogue-return', 'native_port', 'linux')`, replacing `continuity.copy_pre_sha256` with `'f' * 64` produces `audit_scenarios(...).accepted == 1` and `invalid == []`. No identity file has that digest. This reproduction is a synthetic metadata diagnostic, not gameplay evidence.
**Fix:** Require `copy_pre_sha256` to match the validated, explicitly named `identity.copy_pre` record for both lifetimes before branching. Bind retained-copy state to its explicitly named retained snapshot as well, rather than any unrelated identity hash. Add fresh-copy negative tests for an unknown digest and a digest belonging to the launcher/package instead of the per-run copy record.
## Warnings
### WR-01: Checkpoint assembly bypasses the capability ledger projection
**Classification:** WARNING
**File:** `/home/cristian/codex/Neutron/GamePort/tools/recon/fidelity_checkpoint.py:165-167`
**Related:** `/home/cristian/codex/Neutron/GamePort/tools/recon/fidelity_viewer/viewer.mjs:228-244`
**Issue:** Assembly passes authoritative `capabilities.json` directly to `export_review()`. That export validates/copies source links but does not call `export_ledger()`, so its rows retain `evidence` without derived `current` and `history`. The browser renders only `row.current` and `row.history`, displaying `Unrecorded` in both sections and concealing the revision/classification details prepared for the reviewer. The separate CLI ledger-to-viewer test exercises the correct projection, but checkpoint assembly does not use that route.
**Evidence:** In the actual sealed `dist/fidelity/phase01/review/review.json`, all 25 capability rows lack both fields. Applying `export_ledger()` to the authoritative input yields two current and two historical records for `startup-order`; none appears in those viewer sections in the prepared model. This is independent of missing original/native recordings.
**Fix:** Generate the validated ledger projection before checkpoint review export, then preserve its current/history fields through source-link copying. Make `ready()` reject a malformed viewer ledger rather than checking only source hrefs. Add a preparation-to-renderer regression asserting that named current and superseded records survive the actual checkpoint assembly path.
### WR-02: An interrupted Windows collector cannot be finalized through the documented recovery command
**Classification:** WARNING
**File:** `/home/cristian/codex/Neutron/GamePort/scripts/collect-fidelity-windows.ps1:332-336`
**Related:** `/home/cristian/codex/Neutron/GamePort/docs/evidence/windows-session.md:150-152`
**Issue:** Startup writes `incomplete.json` before launching, while `run.json` is written only in the final `finally` block. If the collector is terminated before that block completes, its durable result has only the incomplete record. The instructions explicitly tell the tester to recover that state with `Finish -Outcome aborted`, but `Complete-FidelityRun` unconditionally reads missing `run.json` first. The supplied recovery command therefore cannot retain the interrupted launch's media as a terminal receipt; asking for a fresh launch would misidentify its lifetime.
**Evidence:** A disposable synthetic prepared bundle with `results/interrupted/incomplete.json` and no `run.json` was passed to the real finalizer through Linux-hosted PowerShell. It failed immediately with `Cannot find path '.../results/interrupted/run.json' because it does not exist.` The failed lookup precedes annotation/media recovery. Existing terminal tests always create `run.json` and do not cover this durable interrupted state.
**Fix:** Add an explicit aborted-recovery path using the retained initial record when `run.json` is absent. Preserve its launch identity and raw bytes, prohibit captured/reviewed promotion, and leave unavailable end clocks/observations explicitly missing. Recover media into a new write-once diagnostic receipt without inventing elapsed times. Test an incomplete-only result folder and verify that it remains open and structurally importable.
---
_Reviewed: 2026-11-13T21:56:48Z_
_Reviewer: gsd-code-reviewer_
_Depth: standard_
@@ -0,0 +1,60 @@
---
phase: "01"
slug: reproducible-fidelity-baseline
status: verified
threats_open: 0
threats_total: 22
threats_closed: 22
asvs_level: 1
block_on: high
register_authored_at_plan_time: true
verified_head: 02d182f35de643f9d68699b2fff1d219dd132edb
created: "2026-11-13T22:21:09.119266+00:00"
---
# Phase 01 — Security
The typed security auditor verified all planned mitigation boundaries. The repeated reserved T-01-SC is counted once. All dispositions are mitigate; no accepted or transferred risks.
## Trust Boundaries
Originals → generated copies; local paths → file/process operations; media/receipts → review and acceptance; observer → gameplay; transferred checkpoint → immutable validation.
## Threat Register
| Threat ID | Category | Severity | Disposition | Mitigation evidence | Status |
|---|---|---|---|---|---|
| T-01-01 | Tampering | high | mitigate | fidelity_receipts.py:123,221,239,257 | closed |
| T-01-02 | Spoofing | high | mitigate | fidelity_receipts.py:275,667,672,714 | closed |
| T-01-03 | Tampering | high | mitigate | fidelity_receipts.py:198,212,482,500 | closed |
| T-01-04 | Information disclosure | high | mitigate | fidelity_review.py:202,211,219,274 | closed |
| T-01-05 | Tampering | high | mitigate | viewer.mjs:2,190; fidelity_review.py:238 | closed |
| T-01-06 | Spoofing | medium | mitigate | viewer.mjs:43,79,302,318,324 | closed |
| T-01-07 | Spoofing | high | mitigate | fidelity_ledger.py:97,197,203,285 | closed |
| T-01-08 | Repudiation | medium | mitigate | fidelity_ledger.py:69,220,299,320 | closed |
| T-01-09 | Tampering | medium | mitigate | fidelity_ledger.py:117,339,372 | closed |
| T-01-10 | Tampering | high | mitigate | FidelityObservation.cs:54,78,93,109; test_fidelity_observation.py:130 | closed |
| T-01-11 | Denial of service | medium | mitigate | FidelityObservation.cs:165,171,179,192,233 | closed |
| T-01-12 | Spoofing | high | mitigate | FidelityObservation.cs:47,109,130,166; Program.cs:18,1328 | closed |
| T-01-13 | Elevation of privilege | high | mitigate | collect-fidelity-windows.ps1:128,136,144,253,303 | closed |
| T-01-14 | Tampering | high | mitigate | fidelity_checkpoint.py:103,120,198,215,220 | closed |
| T-01-15 | Spoofing | high | mitigate | collect-fidelity-windows.ps1:176,208,234,285,332 | closed |
| T-01-16 | Tampering | high | mitigate | fidelity_capture.py:154,156,195,239,347 | closed |
| T-01-17 | Spoofing | high | mitigate | fidelity_capture.py:85,98,107,325,338 | closed |
| T-01-18 | Denial of service | medium | mitigate | fidelity_capture.py:30,128,148,202,220,224 | closed |
| T-01-19 | Spoofing | high | mitigate | fidelity_acceptance.py:124; fidelity_receipts.py:275,667,672,714; fidelity_capture.py:390 | closed |
| T-01-20 | Tampering | high | mitigate | fidelity_receipts.py:453,482,488,494,500 | closed |
| T-01-21 | Repudiation | medium | mitigate | fidelity_acceptance.py:127,130,160,184; fidelity_ledger.py:328 | closed |
| T-01-SC | Tampering | high | mitigate | fidelity_checkpoint.py:301; collect-fidelity-windows.ps1:253; observer csproj:1 | closed |
## Accepted Risks Log
No accepted risks.
## Security Audit Trail
Initial source audit identified 20/22 closed and T-01-02/T-01-19 open because hash-only copy identities bypassed file checks. Regression48fca0d reproduced it; fix02d182f validates actual named artifacts at the scenario boundary. Independent auditor reinspection closes both. Code re-review confirms all five findings fixed; see01-REVIEW-VERIFY.md. All191 affected fidelity regressions pass in43.355s.
## Sign-Off
All22 planned threats have implemented, verified mitigations; threats_open=0. This tooling verdict does not approve original/native gameplay, physical input, audio or human findings; runtime acceptance remains0/120 OPEN.
@@ -0,0 +1,74 @@
---
status: testing
phase: 01-reproducible-fidelity-baseline
source: [01-VERIFICATION.md]
started: 2026-11-14T21:56:41.166382+00:00
updated: 2026-11-14T21:56:41.166382+00:00
---
## Current Test
number: 1
name: A1 — Capture and observe the isolated original through the selected DxWnd setup
expected: |
Complete 40 original-Windows-DxWnd obligations; observe moving game imagery and intelligible game audio, retaining actual executable/profile/copy inventories and wrapper/configuration limitations.
awaiting: user response
## Tests
### 1. A1 — Capture and observe the isolated original through the selected DxWnd setup
expected: Complete 40 original-Windows-DxWnd obligations; observe moving game imagery and intelligible game audio, retaining actual executable/profile/copy inventories and wrapper/configuration limitations.
result: [pending]
### 2. A2 — Exercise actual paired recordings in the identified browser
expected: Both real recordings decode, play at actual speed, seek to their own observed events, preserve full tails and switch exclusive audio without concealing elapsed time.
result: [pending]
### 3. EVID-02-unclassified — Review original capture boundaries and limitations
expected: Document observed original/DxWnd launch, crop, aspect, timing, recording boundaries and retained/fresh lifetimes for the actual reference captures.
result: [pending]
### 4. EVID-04-unclassified — Collect and inspect both native platform routes
expected: Complete 40 native Windows and 40 native Linux obligations with actual OS/GPU/driver/Vulkan/SDL/source/package/resource identity and observed route/input/audio continuity.
result: [pending]
### 5. P1 — Resolve the original-preservation prohibition explicitly
expected: Confirm authoritative originals were never executed or changed; compare all 539 recorded hashes and generated-copy pre/retained/post inventories after the session.
result: [pending]
### 6. P2 — Resolve the honest-comparison prohibition explicitly
expected: Confirm genuine original media, no retiming or concealed drift, no mixed simultaneous soundtracks, and visible review gain/derivation provenance.
result: [pending]
### 7. P3 — Resolve the history/full-scope/native-transparency prohibition explicitly
expected: Confirm all 33 requirements and unimplemented content stay visible; conflicting/superseded evidence and native/Wine/component/cross-publish distinctions are preserved after reconciliation.
result: [pending]
### 8. browser — Review the complete local comparison interface
expected: With real captures, verify readable independent clocks/drift, keyboard controls, raw unobstructed default views, optional annotations/differences and visible loading/error/tail states.
result: [pending]
### 9. paired_review — Compare all corresponding actual recordings and record discrepancies
expected: Review matched events, imagery and sound across the required cases, retaining raw drift and justified system-specific observations without invented tolerances.
result: [pending]
### 10. physical_input — Exercise visible native gameplay and actual audible devices
expected: On Linux and Windows use physical supported inputs through lab → VR04 → lab → outside, natural/skipped and fresh/retained cases, held input, banked jumps, landing and idle; confirm real display/audio output.
result: [pending]
## Summary
total: 10
passed: 0
issues: 0
pending: 10
skipped: 0
blocked: 0
## Gaps
No implementation issues reported in this UAT session. All ten actual human checks remain pending; 0/120 capture obligations are accepted. Follow docs/evidence/checkpoint-session.md as one combined session. Prepared materials and prior tests do not supply human approval.
## Session Notes
Restart requested by the user. Readiness then failed on generated tools/recon/__pycache__/fidelity_checkpoint.cpython-312.pyc before any human capture test. Fixed by2fe8b40; real bundled readiness succeeds twice with no bytecode writes. This automated preflight repair does not pass A1 or any other human check.
@@ -1,9 +1,9 @@
--- ---
phase: "01" phase: "01"
slug: "reproducible-fidelity-baseline" slug: "reproducible-fidelity-baseline"
status: draft status: validated
nyquist_compliant: false nyquist_compliant: true
wave_0_complete: false wave_0_complete: true
created: "2026-11-12" created: "2026-11-12"
--- ---
@@ -13,12 +13,12 @@ created: "2026-11-12"
| Property | Value | | Property | Value |
|---|---| |---|---|
| Framework | Existing Python stdlib unittest, standalone .NET 10 console projects; proposed Node built-in tests for pure viewer logic | | Framework | Existing Python stdlib unittest, standalone .NET 10 console projects; Node built-in tests for pure viewer logic |
| Config file | Existing scripts/test.sh and scripts/env.sh; no new package dependencies | | Config file | Existing scripts/test.sh and scripts/env.sh; no new package dependencies |
| Quick run command | `python3 -m unittest discover -s tests -p 'test_fidelity_*.py' -v` (new tests created with their owning slice) | | Quick run command | `python3 -m unittest discover -s tests -p 'test_fidelity_*.py' -v` |
| Viewer quick command | `node --test tests/fidelity-viewer.test.mjs` (new test file created with viewer slice) | | Viewer quick command | `node --test tests/fidelity-viewer.test.mjs` |
| Full suite command | `scripts/test.sh` plus the viewer quick command | | Full suite command | `scripts/test.sh` (includes counted Python, Node viewer and managed observer checks) |
| Runtime | Quick target below 30 seconds; measure during execution. Full GPU/original-data suite runs at wave boundaries and has a separate measured duration. | | Runtime | Broad fidelity run: 40.072 seconds (30-second target exceeded); focused tooling checks typically 1–5 seconds, process/observer checks can take longer. Complete local suite: 782.049626 seconds. |
## Sampling Rate ## Sampling Rate
@@ -30,35 +30,35 @@ created: "2026-11-12"
## Per-Task Verification Map ## Per-Task Verification Map
Final task bindings below reference the exact executable `<automated>` blocks in the named PLAN.md/task. Each block carries its adjacent observable `<fails_when>`; Python commands assert the minimum discovered count before running. These tests are intended new artifacts, not checks already executed. Final task bindings below reference the exact executable `<automated>` blocks in the named PLAN.md/task. Each block carries its adjacent observable `<fails_when>`; Python commands assert the minimum discovered count before running. The tests exist and have run with positive counts. The status column separates passing automation from actual capture/review still OPEN. Shared EVID requirement acceptance is not implied by any green tooling row.
| Task | Wave | Exact automated command binding | Minimum count / threat refs | | Task | Wave | Exact automated command binding | Minimum count / threat refs | Actual result |
|---|---|---|---| |---|---|---|---|---|
| 01-01-01 | 1 | 01-01-PLAN.md task 01-01-01: counted `test_fidelity_sessions.py` runner and mandated original inventory invocation | 16; T-01-01/02/03 | | 01-01-01 | 1 | 01-01-PLAN.md task 01-01-01: counted `test_fidelity_sessions.py` runner and mandated original inventory invocation | 16; T-01-01/02/03 | green: 29 session tests; 539 originals |
| 01-01-02 | 1 | 01-01-PLAN.md task 01-01-02: counted `test_fidelity_scenarios.py` runner | 12; T-01-02 | | 01-01-02 | 1 | 01-01-PLAN.md task 01-01-02: counted `test_fidelity_scenarios.py` runner | 12; T-01-02 | green: 25 scenario tests |
| 01-02-01 | 2 | 01-02-PLAN.md task 01-02-01: counted `test_fidelity_review.py` runner; `node --test tests/fidelity-viewer.test.mjs` | Python 10, Node positive; T-01-04/05/06 | | 01-02-01 | 2 | 01-02-PLAN.md task 01-02-01: counted `test_fidelity_review.py` runner; `node --test tests/fidelity-viewer.test.mjs` | Python 10, Node positive; T-01-04/05/06 | green: 21 review + 27 Node tests |
| 01-02-02 | 2 | 01-02-PLAN.md task 01-02-02: `node --test tests/fidelity-viewer.test.mjs` | 16; T-01-04/05/06 | | 01-02-02 | 2 | 01-02-PLAN.md task 01-02-02: `node --test tests/fidelity-viewer.test.mjs` | 16; T-01-04/05/06 | green: 27 Node tests |
| 01-03-01 | 2 | 01-03-PLAN.md task 01-03-01: counted `test_fidelity_ledger.py` runner | 12; T-01-07/08/09 | | 01-03-01 | 2 | 01-03-PLAN.md task 01-03-01: counted `test_fidelity_ledger.py` runner | 12; T-01-07/08/09 | green: 31 ledger tests |
| 01-03-02 | 2 | 01-03-PLAN.md task 01-03-02: counted ledger runner; `python3 tools/recon/fidelity_ledger.py validate --ledger docs/evidence/capabilities.json --requirements .planning/REQUIREMENTS.md` | 16 tests, 33 requirements; T-01-07/08/09 | | 01-03-02 | 2 | 01-03-PLAN.md task 01-03-02: counted ledger runner; `python3 tools/recon/fidelity_ledger.py validate --ledger docs/evidence/capabilities.json --requirements .planning/REQUIREMENTS.md` | 16 tests, 33 requirements; T-01-07/08/09 | green: 31 tests; 33 requirement mappings validated |
| 01-04-01 | 2 | 01-04-PLAN.md task 01-04-01: exact sourced-SDK observer command and counted `test_fidelity_observation.py` runner | Managed 8, Python 4; T-01-10/11/12 | | 01-04-01 | 2 | 01-04-PLAN.md task 01-04-01: exact sourced-SDK observer command and counted `test_fidelity_observation.py` runner | Managed 8, Python 4; T-01-10/11/12 | green: 23 managed + 7 process tests |
| 01-04-02 | 2 | 01-04-PLAN.md task 01-04-02: sourced-SDK observer/build and MovementTests/DirectorTests/CheckpointTests/BodyOwnershipTests commands | Managed 14 plus positive existing groups; T-01-10/11/12 | | 01-04-02 | 2 | 01-04-PLAN.md task 01-04-02: sourced-SDK observer/build and MovementTests/DirectorTests/CheckpointTests/BodyOwnershipTests commands | Managed 14 plus positive existing groups; T-01-10/11/12 | green: observer/build and protected groups 28/23/4/3 |
| 01-05-01 | 3 | 01-05-PLAN.md task 01-05-01: counted `test_fidelity_checkpoint.py` runner; `bash -n scripts/prepare-fidelity-checkpoint.sh` | 12; T-01-13/14/15 | | 01-05-01 | 3 | 01-05-PLAN.md task 01-05-01: counted `test_fidelity_checkpoint.py` runner; `bash -n scripts/prepare-fidelity-checkpoint.sh` | 12; T-01-13/14/15 | green: 25 checkpoint tests; shell syntax |
| 01-05-02 | 3 | 01-05-PLAN.md task 01-05-02: counted checkpoint runner; package-free PowerShell command deferred to final human session | Python 16, Windows 8; T-01-13/14/15 | | 01-05-02 | 3 | 01-05-PLAN.md task 01-05-02: counted checkpoint runner; package-free PowerShell command deferred to final human session | Python 16, Windows 8; T-01-13/14/15 | green: 25 Python + 18 Linux-hosted PowerShell checks; native Windows session OPEN |
| 01-06-01 | 4 | 01-06-PLAN.md task 01-06-01: counted `test_fidelity_capture.py` runner | 10; T-01-16/17/18 | | 01-06-01 | 4 | 01-06-PLAN.md task 01-06-01: counted `test_fidelity_capture.py` runner | 10; T-01-16/17/18 | green: 23 capture tests; actual Linux capture OPEN |
| 01-06-02 | 4 | 01-06-PLAN.md task 01-06-02: counted capture runner and original inventory command | 14; T-01-16/17/18 | | 01-06-02 | 4 | 01-06-PLAN.md task 01-06-02: counted capture runner and original inventory command | 14; T-01-16/17/18 | green: 23 capture tests; 539 originals; actual matrix OPEN |
| 01-07-01 | 5 | 01-07-PLAN.md task 01-07-01: counted `test_fidelity_acceptance.py` runner; `python3 tools/recon/fidelity_acceptance.py ready --checkpoint dist/fidelity/phase01` | 14; T-01-19/20/21 | | 01-07-01 | 5 | 01-07-PLAN.md task 01-07-01: counted `test_fidelity_acceptance.py` runner; `python3 tools/recon/fidelity_acceptance.py ready --checkpoint dist/fidelity/phase01` | 14; T-01-19/20/21 | green: 29 acceptance tests; readiness exit 0 |
| 01-07-02 | 5 | `python3 tools/recon/fidelity_acceptance.py audit --checkpoint dist/fidelity/phase01 --results dist/fidelity/phase01/results --require-complete` | Real matrix/native/original/human checks required; T-01-19/20/21 | | 01-07-02 | 5 | `python3 tools/recon/fidelity_acceptance.py audit --checkpoint dist/fidelity/phase01 --results dist/fidelity/phase01/results --require-complete` | Real matrix/native/original/human checks required; T-01-19/20/21 | OPEN: strict audit exit 1, errors=[], 0/120; fail-closed behavior covered by passing acceptance tests |
| 01-07-03 | 5 | `scripts/test.sh`; `python3 tools/recon/inventory.py ../Original --verify docs/original-manifest.json` | Positive consolidated counts, 539 originals; all threats | | 01-07-03 | 5 | `scripts/test.sh`; `python3 tools/recon/inventory.py ../Original --verify docs/original-manifest.json` | Positive consolidated counts, 539 originals; all threats | green: completed full suite exit 0; 539 originals |
All plan subcommands/paths are explicitly introduced in their owning tasks before verification. Run every focused task command after that task; at integrated checkpoint run the full suite once and repeat only after changes/failures. Quick checks target below 30 seconds, to be measured. Existing full suite and native runs can take longer and record separate durations. No new runtime/fixture/Windows results are claimed here. All 15 task bindings were checked against the seven PLAN verify blocks and SUMMARY interfaces. No missing automated contract was found. Task 01-07-02 remains an explicit actual-evidence dependency; its expected nonzero strict audit is not a green acceptance result. Focused commands ran during their owning slices; the completed integrated suite and subsequent tooling regressions are recorded below. No full suite or large checkpoint hash walk was repeated for this audit.
The seven explicit classified spec-less boundaries and two unresolved unclassified manual assumptions are reconciled in 01-SOURCE-AUDIT.md. The two research backstop truths abstain to human_needed if actual original audiovisual capture/browser review is insufficient. Descriptor-less project prohibitions remain flagged-unverified, not silently passed. ASVS1 high/critical threats block acceptance; T-01-SC is reserved across plans. The seven explicit classified spec-less boundaries and two unresolved unclassified manual assumptions are reconciled in 01-SOURCE-AUDIT.md. The two research backstop truths abstain to human_needed if actual original audiovisual capture/browser review is insufficient. Descriptor-less project prohibitions remain flagged-unverified, not silently passed. ASVS1 high/critical threats block acceptance; T-01-SC is reserved across plans.
## Wave 0 Requirements ## Wave 0 Requirements — Complete (Automation)
- Each implementation slice creates meaningful tests together with its production code; no empty stubs counted as validation. - Each implementation slice creates meaningful tests together with its production code; no empty stubs counted as validation.
- Create fidelity test fixtures covering changed/missing/added originals, output overlap, symlink/drive/case escape, reused session, tampered hash, invalid marker and unsupported schema. - Implemented fidelity test fixtures covering changed/missing/added originals, output overlap, symlink/drive/case escape, reused session, tampered hash, invalid marker and unsupported schema.
- Create pure viewer tests including asymmetric durations, missing/buffering tracks, preserved playbackRate 1.0 and exclusive audio switching. - Implemented pure viewer tests including asymmetric durations, missing/buffering tracks, preserved playbackRate 1.0 and exclusive audio switching.
- No external test-framework installation required. Existing full suite remains available. - No external test-framework installation required. Existing full suite remains available.
## Manual-Only Verifications ## Manual-Only Verifications
@@ -72,14 +72,39 @@ The seven explicit classified spec-less boundaries and two unresolved unclassifi
Unavailable/failed executions are recorded as open dependencies. Completing tools or preparing a bundle does not close EVID-02/EVID-04 or mark Phase 1 accepted. Source-backed later work may continue only under the existing roadmap exception. Unavailable/failed executions are recorded as open dependencies. Completing tools or preparing a bundle does not close EVID-02/EVID-04 or mark Phase 1 accepted. Source-backed later work may continue only under the existing roadmap exception.
## Measured Verification Evidence
- Completed integrated run: `artifacts/fidelity/01-07-full-suite.json` and `.log`, exit 0 in **782.049626 seconds**. Actual output records 556 Python tests (180 fidelity), 27 Node tests, 23 standalone managed observer checks, two separate HUD tests, all 51 managed entry-point invocations/build, 36 rendered Vulkan receipts with zero reported validation errors, SDL dummy-audio checks and 539 unchanged originals. Optional native-window checks were not enabled. Dummy audio does not establish audibility.
- Subsequent code-review fixes: `01-FIX-REPORT.md` and `artifacts/fidelity/01-review-fixes/`. `python-fidelity.log` records **189 passing tests in 40.072 seconds**; `acceptance-final.log` records **29 passing acceptance tests** after the final standalone-transfer regression. These runs overlap; do not add their counts. `node-viewer-direct.log` records 27 behavior tests, `powershell.log` 18 synthetic checks under Linux-hosted PowerShell, and `original-preservation.log` 539 unchanged originals. The initial sandbox socket errors were resolved by the scoped local run; they are not represented as passes.
- Current discovery, without executing runtime loops: acceptance 29, capture 23, checkpoint 25, ledger 31, observation 7, review 21, scenarios 25, sessions 29: **190 current fidelity tests**. The final added acceptance test explains the difference from the earlier 189-test aggregate; it was executed in the final 29-test acceptance run. Discovery alone is not execution evidence.
- Review fixes exercise selected-receipt digest binding, pristine executable/inventory identity, named copy-state lifetime binding, sealed ledger/history projection including standalone transfer, and incomplete-session recovery without captured promotion. They strengthen existing covered contracts; independent review remains separate.
- Fresh immutable checkpoint: **11001 members**, `dist/fidelity/phase01`. Saved `01-review-fixes/readiness.json` reports `materials_ready: true`, `acceptance: human_needed` (command exit 0). Saved `acceptance.json` reports `errors: []`, **0/120**, all ten human findings pending (strict command exit 1). Original-DxWnd, native Windows and native Linux each retain 40 outstanding obligations.
- Focused tooling feedback is generally around 1–5 seconds (session/scenario/ledger around one second, checkpoint 4.742 seconds, review 5.234 seconds in owning summaries); observer process integration measured 19.126 seconds. The broad 40.072-second regression **exceeds** the proposed 30-second quick target. This is a latency WARNING, not a missing behavioral check or evidence acceptance.
## Validation Sign-Off ## Validation Sign-Off
- [ ] Final plans bind every task to automated checks or explicit human/native evidence - [x] Final plans bind every task to automated checks or explicit human/native evidence
- [ ] Sampling continuity has no three consecutive tasks without automated verification - [x] Sampling continuity has no three consecutive tasks without automated verification
- [ ] New test files exist and execute nonzero test counts - [x] New test files exist and execute nonzero test counts
- [ ] No watch-mode flags - [x] No watch-mode flags
- [ ] Quick feedback latency measured below 30 seconds - [ ] Broad quick feedback below 30 seconds — measured 40.072 seconds; WARNING retained
- [ ] Native/original capture limitations recorded - [x] Native/original capture limitations recorded
- [ ] nyquist_compliant updated only after the implemented validation contract is audited - [x] Implemented automated validation contract audited; `nyquist_compliant` and `wave_0_complete` refer only to automation coverage
- [ ] Actual combined capture and human review complete — OPEN
- [ ] EVID requirements and Phase 01 acceptance complete — OPEN
**Approval:** Pending execution; final task bindings are planned, while nyquist_compliant and wave_0_complete remain false until actual implementation and validation are audited. **Automation validation:** Validated on 2026-11-13 from executed tests and retained logs; no new automated gap found, no tests or implementation changed. The latency target remains a documented warning. `status: validated` does not advance the phase or promote any EVID requirement.
**Acceptance dependencies:** A1, A2, EVID-02-unclassified, EVID-04-unclassified, P1, P2, P3, browser, paired_review and physical_input remain OPEN. Follow the single combined agenda in `docs/evidence/checkpoint-session.md` and its Windows/Linux session procedures. Collect actual original-DxWnd/native Windows/native Linux recordings, physical input and audible checks, review real paired playback, return the identified local results, then rerun strict acceptance. The Linux preflight's missing usable display/audio is an explicit dependency. Cross-publish, Wine, headless/synthetic fixtures and preparation cannot close it. Independent review/security gates remain owned by their respective audits.
## Final copy-state refinement
All191 fidelity checks pass in43.355s after02d182f (26 scenario,23 capture,29 acceptance); missing/hash-only/wrong-size state records are explicitly rejected for both lifetimes. The43.355s aggregate still exceeds the30s quick target. No manual acceptance was promoted.
## Validation Audit 2026-11-13
| Metric | Count |
|---|---|
| Gaps found | 0 |
| Resolved | 0 |
| Escalated | 0 |
@@ -0,0 +1,325 @@
---
phase: 01-reproducible-fidelity-baseline
verified: 2026-11-14T05:34:19Z
status: human_needed
score: 29/42 must-haves verified
covered_files: [".planning/REQUIREMENTS.md",".planning/ROADMAP.md",".planning/phases/01-reproducible-fidelity-baseline/01-01-PLAN.md",".planning/phases/01-reproducible-fidelity-baseline/01-01-SUMMARY.md",".planning/phases/01-reproducible-fidelity-baseline/01-02-PLAN.md",".planning/phases/01-reproducible-fidelity-baseline/01-02-SUMMARY.md",".planning/phases/01-reproducible-fidelity-baseline/01-03-PLAN.md",".planning/phases/01-reproducible-fidelity-baseline/01-03-SUMMARY.md",".planning/phases/01-reproducible-fidelity-baseline/01-04-PLAN.md",".planning/phases/01-reproducible-fidelity-baseline/01-04-SUMMARY.md",".planning/phases/01-reproducible-fidelity-baseline/01-05-PLAN.md",".planning/phases/01-reproducible-fidelity-baseline/01-05-SUMMARY.md",".planning/phases/01-reproducible-fidelity-baseline/01-06-PLAN.md",".planning/phases/01-reproducible-fidelity-baseline/01-06-SUMMARY.md",".planning/phases/01-reproducible-fidelity-baseline/01-07-PLAN.md",".planning/phases/01-reproducible-fidelity-baseline/01-07-SUMMARY.md","artifacts/fidelity/01-07-full-suite.json","artifacts/fidelity/01-07-full-suite.log","artifacts/fidelity/01-review-fixes/acceptance-final.json","artifacts/fidelity/01-review-fixes/python-fidelity-final.log","artifacts/fidelity/01-review-fixes/readiness-final.json","artifacts/fidelity/bytecode-fix/acceptance.json","artifacts/fidelity/bytecode-fix/fidelity-tests.log","artifacts/fidelity/bytecode-fix/observer-build.log","artifacts/fidelity/bytecode-fix/observer-retry.log","artifacts/fidelity/bytecode-fix/ready-bundled-1.json","artifacts/fidelity/bytecode-fix/ready-bundled-2.json","artifacts/fidelity/verification/01-07-final-checkpoint.json","docs/compatibility.md","docs/decisions.md","docs/evidence/README.md","docs/evidence/capabilities.json","docs/evidence/checkpoint-session.md","docs/evidence/linux-session.md","docs/evidence/phase01-baseline.md","docs/evidence/scenarios.json","docs/evidence/windows-session.md","docs/original-manifest.json","docs/progress.md","docs/tasks.md","scripts/collect-fidelity-linux.sh","scripts/collect-fidelity-windows.cmd","scripts/collect-fidelity-windows.ps1","scripts/env.sh","scripts/prepare-fidelity-checkpoint.sh","scripts/test.sh","src/GamePort/Application/FidelityObservation.cs","src/GamePort/Program.cs","tests/GamePort.FidelityObservationTests/GamePort.FidelityObservationTests.csproj","tests/GamePort.FidelityObservationTests/Program.cs","tests/fidelity-viewer.test.mjs","tests/fidelity-windows.Tests.ps1","tests/test_fidelity_acceptance.py","tests/test_fidelity_capture.py","tests/test_fidelity_checkpoint.py","tests/test_fidelity_ledger.py","tests/test_fidelity_observation.py","tests/test_fidelity_review.py","tests/test_fidelity_scenarios.py","tests/test_fidelity_sessions.py","tools/recon/fidelity.py","tools/recon/fidelity_acceptance.py","tools/recon/fidelity_capture.py","tools/recon/fidelity_checkpoint.py","tools/recon/fidelity_ledger.py","tools/recon/fidelity_receipts.py","tools/recon/fidelity_review.py","tools/recon/fidelity_viewer/index.html","tools/recon/fidelity_viewer/style.css","tools/recon/fidelity_viewer/viewer.mjs","tools/recon/inventory.py"]
covered_digest: "v4:sha256:acca5bdaa1f405a74d29d69c8ebe048085a6a4ff4c86e3b3f80c97cebfba8ac3"
behavior_unverified: 0
overrides_applied: 0
decision_coverage:
honored: 16
total: 16
not_honored: []
non_inferable_checks:
- truth: "Actual original-DxWnd moving game imagery and intelligible audio are observed and reviewed with wrapper/config limitations recorded."
status: uncertain
reason: insufficient_spec
human_check: A1
- truth: "Actual paired recordings decode, seek and switch exclusive audio in the identified local browser without concealing elapsed time."
status: uncertain
reason: insufficient_spec
human_check: A2
unverified_prohibitions:
- id: P1
statement: "MUST NOT sacrifice authoritative original bytes or execute the authoritative installation to make reference collection convenient."
status: unverified
flag: "unverified-prohibition — human review recommended"
- id: P2
statement: "MUST NOT manufacture apparent parity by retiming recordings, hiding drift, mixing both soundtracks or presenting synthetic media as an original reference."
status: unverified
flag: "unverified-prohibition — human review recommended"
- id: P3
statement: "MUST NOT erase contradictory history, hide unimplemented required content or turn missing evidence into a fidelity-completion claim."
status: unverified
flag: "unverified-prohibition — human review recommended"
human_verification:
- test: "A1 — Capture and observe the isolated original through the selected DxWnd setup"
expected: "Complete 40 original-Windows-DxWnd obligations; observe moving game imagery and intelligible game audio, retaining actual executable/profile/copy inventories and wrapper/configuration limitations."
why_human: "Original execution and audiovisual truth are unobserved; the backstop abstains with insufficient_spec."
- test: "A2 — Exercise actual paired recordings in the identified browser"
expected: "Both real recordings decode, play at actual speed, seek to their own observed events, preserve full tails and switch exclusive audio without concealing elapsed time."
why_human: "Controller tests use media doubles; they cannot establish real codec/browser/physical-audio behavior. Backstop: insufficient_spec."
- test: "EVID-02-unclassified — Review original capture boundaries and limitations"
expected: "Document observed original/DxWnd launch, crop, aspect, timing, recording boundaries and retained/fresh lifetimes for the actual reference captures."
why_human: "This flagged assumption cannot be inferred from prepared settings or synthetic metadata."
- test: "EVID-04-unclassified — Collect and inspect both native platform routes"
expected: "Complete 40 native Windows and 40 native Linux obligations with actual OS/GPU/driver/Vulkan/SDL/source/package/resource identity and observed route/input/audio continuity."
why_human: "Windows is cross-published only; current Linux TTY/auto_null preflight cannot capture native physical gameplay."
- test: "P1 — Resolve the original-preservation prohibition explicitly"
expected: "Confirm authoritative originals were never executed or changed; compare all 539 recorded hashes and generated-copy pre/retained/post inventories after the session."
why_human: "Descriptor-less unresolved prohibition requires explicit disposition; current preserved hashes do not prove future session conduct."
- test: "P2 — Resolve the honest-comparison prohibition explicitly"
expected: "Confirm genuine original media, no retiming or concealed drift, no mixed simultaneous soundtracks, and visible review gain/derivation provenance."
why_human: "Unverified-prohibition — human review recommended; genuine playback and perceived audiovisual comparison require observation."
- test: "P3 — Resolve the history/full-scope/native-transparency prohibition explicitly"
expected: "Confirm all 33 requirements and unimplemented content stay visible; conflicting/superseded evidence and native/Wine/component/cross-publish distinctions are preserved after reconciliation."
why_human: "Unverified-prohibition — human review recommended; final returned-evidence reconciliation requires explicit judgment."
- test: "browser — Review the complete local comparison interface"
expected: "With real captures, verify readable independent clocks/drift, keyboard controls, raw unobstructed default views, optional annotations/differences and visible loading/error/tail states."
why_human: "No actual browser visual/usability/codec review has been performed."
- test: "paired_review — Compare all corresponding actual recordings and record discrepancies"
expected: "Review matched events, imagery and sound across the required cases, retaining raw drift and justified system-specific observations without invented tolerances."
why_human: "No corresponding original/native pair or completed visual/audible comparison exists."
- test: "physical_input — Exercise visible native gameplay and actual audible devices"
expected: "On Linux and Windows use physical supported inputs through lab → VR04 → lab → outside, natural/skipped and fresh/retained cases, held input, banked jumps, landing and idle; confirm real display/audio output."
why_human: "Injected/headless/GPU/dummy-audio fixtures prove narrower behavior and cannot satisfy physical-input or audibility acceptance."
---
# Phase 1: Reproducible Fidelity Baseline Verification Report
**Phase Goal:** As a tester, I want to reproduce identified original/port comparison scenarios, so that I understand exactly what the current reconstruction proves on each native platform.
**Verified:** 2026-11-14T05:34:19Z
**Status:** human_needed
**Re-verification:** No existing VERIFICATION.md; completion of the interrupted initial verification after the MVP goal-format correction (`febb4a9`). No scope change or override.
## User Flow Coverage
| Step | Expected | Evidence | Status |
|---|---|---|---|
| Open the local checkpoint and inspect identities | Identified offline original copy, both port packages, complete agenda and viewer | Final readiness receipt: 11,001 immutable members; materials_ready true | VERIFIED for preparation |
| Reproduce isolated original scenarios | Moving imagery, intelligible audio, input/events and retained/fresh provenance from the actual selected DxWnd configuration | Collector/guide prepared; no returned original gameplay captures; 0/40 accepted | UNCERTAIN — WARNING; A1, EVID-02, P1 |
| Repeat matching native Linux/Windows routes | Same route/cases with physical input, real display/audio and exact runtime identities | Windows cross-publish only; real Linux preflight failed without selected X11/real audio; 0/80 accepted | UNCERTAIN — WARNING; EVID-04, physical_input |
| Inspect paired playback | Actual corresponding media with independent event times, exposed drift and exclusive audio | Controller is implemented/tested; prepared viewer contains no actual pair | UNCERTAIN — WARNING; A2, browser, paired_review, P2 |
| Trace what each capability proves | Source/implementation/platform/scope/discrepancy/remaining-acceptance links across the full game | 25 capabilities, six groups, all 33 requirements; current/history preserved | VERIFIED for traceability; P3 final judgment pending |
| Understand the reconstruction on each native platform | Actual identified original/native evidence plus honest discrepancies and unresolved limitations | Audit: errors [], 0/120 accepted; ten named human findings pending | UNCERTAIN — WARNING; user-story outcome remains open |
The MVP user flow is incomplete. No new technical runtime/test run was started to bypass it. The implementation evidence below records inspected code and already completed local verification; it does not constitute manual acceptance. Phase 1 is not passed and Phase 2 is not advanced by this report.
## Goal Achievement
### Observable Truths
Roadmap criteria are retained in full; PLAN truths add detail and do not reduce them. VERIFIED on a tooling truth certifies its bounded implementation, not original/native fidelity. UNCERTAIN items request human verification rather than asserting missing implementation. No accepted override exists.
| ID | Truth | Status | Evidence |
|---|---|---|---|
| SC1 | A reviewer can verify every original against the recorded inventory and run investigation/reference copies without altering the original installation. | UNCERTAIN — WARNING | `verify_inventory`/staging and saved 539-file check prove current preservation; actual generated-copy reference execution and P1 disposition remain unobserved. |
| SC2 | A tester can reproduce identified whole-original reference scenarios from an isolated generated installation and inspect corresponding input/events, images and audio where applicable; unavailable execution keeps this criterion open. | UNCERTAIN — WARNING | Actual original-DxWnd captures absent; explicit access limitation leaves 40 obligations open (A1/EVID-02). |
| SC3 | A reviewer can trace every full-game capability from original evidence through current implementation, platform receipts, discrepancies and its remaining acceptance condition. | VERIFIED | Ledger validator/export/renderer connect 25 capabilities to all 33 requirements, source paths, implementation revisions, scoped platform records, differences and open acceptance. |
| SC4 | Testers can repeat the same baseline movement/route scenarios on native Linux and native Windows with exact revision identities; Wine/cross-publish receipts remain separately labeled and cannot close missing native execution. | UNCERTAIN — WARNING | No accepted current native baseline capture on either platform: 40 Linux + 40 Windows obligations remain open (EVID-04/physical_input). |
| 01.1 | A reviewer can stage and identify a pristine generated original installation without altering any original byte (EVID-01, D-15). | VERIFIED | `fidelity.py:stage` calls `stage_original`; `verify_inventory` compares all recorded file identities before/after isolated copying. Saved original-preservation log verifies 539 unchanged originals. Actual DxWnd execution remains separately pending. |
| 01.2 | The protocol requires continuous lab → VR04 → lab → outside and focused dialogue-return, left/right banked-jump, landing and idle captures per D-01 and D-04. | VERIFIED | `scenarios.json` requires continuous lab → VR04 → lab → outside plus dialogue-return, left/right bank, landing/idle; `validate_scenario_contract`/`audit_scenarios` enforce obligations. |
| 01.3 | Natural/skipped dialogue and fresh/retained entry are equally required, independently identified dimensions per D-02 and D-03. | VERIFIED | Eight case IDs independently cross fresh/retained, natural/skipped and ordinary/held-input; scenario validator rejects collapsed dimensions. |
| 01.4 | Equal, nested, symlink-aliased and Windows case-aliased source/output paths fail before any staging write; sibling paths merely sharing a textual prefix remain distinct. | VERIFIED | `separated_roots`, symlink rejection and canonical path checks precede staging writes; session regressions cover equal/nested/case/symlink/prefix cases. |
| 01.5 | Empty/missing inventories fail; single-file fixtures round-trip, while changed, missing and added files invalidate identity. | VERIFIED | `identify_tree` rejects empty inventory; exact file-list comparison rejects changed/missing/added files; single-file round-trip regressions are active. |
| 01.6 | Manifest order is canonical relative POSIX path order; case-colliding identities fail instead of acquiring filesystem-dependent order. | VERIFIED | `identify_tree` sorts POSIX paths and rejects casefold collisions; canonical-order regression checks actual list/digest values. |
| 01.7 | Interrupted staging/import leaves an explicit incomplete diagnostic and no completed receipt; simultaneous same-session allocation has one winner, and duplicate receipt imports are idempotent only for byte-identical content. | VERIFIED | `_reserve`, exclusive writes, incomplete siblings and atomic publication implement allocation/import ownership. Named concurrency/interruption/duplicate regressions in `test_fidelity_sessions.py` pass in saved 191-test run. |
| 01.8 | Typed receipt validation retains failures and missing evidence as open acceptance; D-13 Windows availability is not a runtime receipt. | VERIFIED | `validate_receipt`/`audit_scenarios` separate failure, synthetic, component, Wine and native kinds. Current real failed Linux receipt remains OPEN; availability is no receipt. |
| 02.1 | A tester opens a local scenario with paired original/port playback and corresponding image, audio and input/event links per D-05. | UNCERTAIN — WARNING | Exporter/controller support paired validated receipts, but final `review.json` has no actual original/native pair. A1/A2/browser/paired_review remain human checks. |
| 02.2 | Raw captures are unobstructed by default; annotations and provenance-bound image differences are optional overlays per D-06. | VERIFIED | Controller defaults `annotations`/`difference` false; corresponding Node overlay/provenance regressions cover opt-in state. Actual visual unobstruction remains part of browser review. |
| 02.3 | Selecting an event seeks each recording to its own observed time; both play at actual speed with separate elapsed clocks, event drift and playback drift per D-07. | VERIFIED | Named Node event-selection/drift/readiness tests assert separate observed times, rate 1, independent elapsed clocks and exposed drift. This verifies controller behavior, not actual codec/browser playback. |
| 02.4 | The reviewer switches corresponding original/port audio with at most one source audible and visible review gain per D-08. | VERIFIED | Named exclusive-soundtrack/gain tests assert both muted before selecting one and labeled review-only gain. Physical audibility remains pending. |
| 02.5 | Missing, buffering, rejected-play, decoding and asymmetric-end states remain visible and preserve the full recording tails. | VERIFIED | Named rejected-play/buffering/decode/asymmetric-end tests assert paired pause, visible cause and resumable full longer tail. Real browser observation is still A2. |
| 03.1 | Reviewers browse movement, contacts, gadgets, progression, visuals and audio with requirement/source/scenario/platform links per D-09. | VERIFIED | `GROUPS` and ledger contain movement, contacts, gadgets, progression, visuals and audio; exported capability links include source/requirement/scenario/platform. |
| 03.2 | Each capability leads with working behavior, verified scope/platform, known differences and remaining acceptance per D-10. | VERIFIED | Capability rows carry working summary, verified scope, implementation revision, differences and open acceptance; renderer presents supplied facts. |
| 03.3 | Current applicable evidence precedes expandable explicitly superseded revision history per D-11; applicability uses content/scope/platform rather than newest date. | VERIFIED | Scope/content/platform applicability and explicit supersession retain current/history. Final reviewed fix verifies both projections survive bundle export; newest date is not acceptance. |
| 03.4 | Discrepancies order blocking/disruptive failures before subtler differences and missing verification per D-12; all missing evidence keeps acceptance open. | VERIFIED | `IMPACTS` orders blocking/disruptive/subtle/missing_verification; acceptance stays open. Strict current audit has no accepted runtime obligations. |
| 03.5 | All 33 full-game requirements have capability coverage even when unimplemented; an empty ledger fails and one capability remains renderable. | VERIFIED | Ledger covers 25 capabilities and all 33 requirements across six groups; validator rejects empty ledger, renderer supports a singleton. Full-game implementation is not claimed. |
| 03.6 | Equal receipt/content identities merge only when the record bytes match; conflicts remain explicit, and duplicate history rows never silently overwrite evidence. | VERIFIED | Canonical byte conflict checks prevent contradictory receipt/content deduplication and preserve history; ledger regression assertions cover conflicts. |
| 03.7 | Equal-priority entries have deterministic stable ID ordering; explicit supersession cycles and unresolved contradictory current claims fail validation. | VERIFIED | Stable ID sorting, supersession-cycle and contradictory-current validation are implemented and covered by active ledger regressions. |
| 04.1 | An optional passive observer records actual native port input/control/scene events across the continuous route per D-01, without changing gameplay or scene lifetime. | VERIFIED | `Program.cs:18-30` owns one optional observer across outer Run continuations; post-Step calls at 1328-1333 use actual accepted input/state. Managed/process regressions cover observer wiring; no physical route acceptance inferred. |
| 04.2 | Natural/skipped and fresh/retained runs have distinct case identities, with one monotonic session across actual retained continuations per D-02 and D-03. | VERIFIED | One retained observer/monotonic session spans Run continuations; distinct case identity and simulation ticks are preserved. Existing observer tests exercise clock/order/continuation. |
| 04.3 | Held/neutral input, banked jump, landing and idle observations retain their real owner/tick/time per D-04; injected smoke fixtures stay separately classified. | VERIFIED | Actual raw SDL/input/state/control calls include owner/tick/time; smoke/injected paths are separately classified. Managed and process assertions check payload/receipt interoperability. |
| 04.4 | An output failure leaves the observation incomplete and visible rather than reporting acceptance or changing movement/state to finish the recording. | VERIFIED | Observer write failure emits an incomplete diagnostic without completing acceptance; standalone managed failure regressions exercise this path. |
| 05.1 | One complete local checkpoint bundle contains identified port packages, a verified generated original copy, scenarios, viewer and result collection per D-14. | VERIFIED | Final checkpoint receipt identifies 11,001 immutable members, both sealed packages, generated original seed, protocol, viewer and result collectors; readiness true. |
| 05.2 | The available Windows PC is treated as a pending execution environment per D-13; actual OS/GPU/driver/tool identities are collected during the session. | VERIFIED | Windows session guide/collector require actual OS/GPU/driver/tool observations; no native Windows receipt exists. Pending environment is explicitly distinguished from execution. |
| 05.3 | The original launches only from a generated copy through the user's identified DxWnd binary/exported profile, separately from native port receipts, per D-15. | UNCERTAIN — WARNING | Collector protects original-pristine, copies a writable run, retains selected DxWnd/profile and requires GUI launch. Actual user-selected DxWnd execution/configuration is unobserved; A1/P1 pending. |
| 05.4 | All original-reference and port materials are prepared before one combined session per D-16; preparation does not close EVID-02 or EVID-04. | VERIFIED | Readiness validates both package identities and complete 80-obligation Windows agenda; guide also requires 40 Linux obligations. `ready()` always reports human_needed. |
| 05.5 | Launcher preflight or recording failure produces an actionable local failure receipt without inventing successful capture or downloading dependencies. | VERIFIED | Collector/preflight failures retain diagnostic/open states. Actual Linux TTY/null-audio failure is retained; PowerShell recovery checks cover aborted incomplete collection without invented success. |
| 06.1 | An identified native Linux package yields actual input/event and audiovisual captures where execution is available; synthetic/headless replays remain distinct (EVID-04). | UNCERTAIN — WARNING | Native Linux collector invokes identified package/observer and real recorder only after preflight. Current host has no selected real display/audio and produced failed preflight, with no gameplay capture. |
| 06.2 | Continuous route and focused captures cover all natural/skipped, fresh/retained and ordinary/edge cells per D-01–D-04, with missing executions explicitly open. | UNCERTAIN — WARNING | Matrix/scenario implementation requires all 40 Linux obligations and tracks missing cases, but no physical Linux route/focused capture is accepted. |
| 06.3 | Physical input/audio and real visible gameplay require actual native receipts/human review; dummy audio and window-only fixtures cannot complete acceptance. | VERIFIED | Preflight rejects dummy/null devices; native review requires real input/audibility/visibility. Strict audit cannot accept headless/synthetic fixtures. |
| 07.1 | One fully prepared combined session covers original-DxWnd and native Windows cases, local Linux review and real paired playback, per D-13–D-16. | UNCERTAIN — WARNING | Materials and one-session agenda are ready; the combined original/native/browser session has not occurred. |
| 07.2 | Every required original-reference and native Linux/Windows case has exact revision/package/resource/media and observation provenance; absent or failed cases keep EVID-02/EVID-04 open. | UNCERTAIN — WARNING | Strict audit reports 0/120 accepted, no structural errors and every missing obligation. Exact successful runtime/media provenance cannot yet be verified. |
| 07.3 | Paired review of actual original/port captures applies D-05–D-08 and publishes raw drift, discrepancies and audible/visible checks. | UNCERTAIN — WARNING | No actual paired recordings or witnessed drift/audio/visual review returned; paired_review/P2 remain pending. |
| 07.4 | Current capabilities/history/discrepancies are reconciled to returned receipts per D-09–D-12, with full matrix completeness per D-01–D-04. | UNCERTAIN — WARNING | Current baseline and ledger honestly retain missing evidence; returned-receipt reconciliation awaits actual collection and agent-owned normalization/import. |
| 07.5 | Actual original-DxWnd moving game imagery and intelligible audio are observed and reviewed with wrapper/config limitations recorded. | UNCERTAIN — WARNING | UNCERTAIN — insufficient_spec: no observed original-DxWnd moving imagery/intelligible audio and wrapper review (A1); metadata fixtures cannot prove it. |
| 07.6 | Actual paired recordings decode, seek and switch exclusive audio in the identified local browser without concealing elapsed time. | UNCERTAIN — WARNING | UNCERTAIN — insufficient_spec: no actual identified-browser decode/seek/exclusive-audio observation (A2); Node media doubles cannot prove browser codecs or audibility. |
**Score:** 29/42 truths verified; 13 UNCERTAIN. **Present-but-behavior-unverified invariants:** 0. Existing behavioral regressions exercise the tooling transitions; the unverified items concern actual external execution, media, physical experience and final reconciliation. A1/A2 separately abstain with `insufficient_spec`.
### Required Artifacts and Wiring Evidence
Owner `query verify.artifacts` independently returned exit 0 for each of seven PLANs: **21/21 declared artifacts** exist and are substantive. Source inspection then checked their actual callers and data contracts.
| Plan | Declared artifacts | Implementation/wiring evidence | Status |
|---|---|---|---|
| 01-01 | fidelity.py; fidelity_receipts.py; scenarios.json | CLI dispatches stage/identify/import/validate; shared validators consume supplied protocol and real byte inventories | VERIFIED |
| 01-02 | fidelity_review.py; fidelity_viewer/viewer.mjs; fidelity-viewer.test.mjs | Validated receipt export → review.json/local media → fetch → controller/renderer; actual pair absent | VERIFIED implementation; actual browser pending |
| 01-03 | capabilities.json; fidelity_ledger.py; docs/evidence/README.md | Validator checks tracked source/requirements/scenarios; canonical export supplies bundle and viewer current/history projection | VERIFIED |
| 01-04 | FidelityObservation.cs; managed observer test Program.cs; test_fidelity_observation.py | Outer Program continuation owns observer; actual raw/input/control/state hooks feed ordered JSONL; process tests feed receipt contract | VERIFIED bounded observer |
| 01-05 | fidelity_checkpoint.py; collect-fidelity-windows.ps1; windows-session.md | Preparation launcher calls assembler; actual files sealed/preflighted; PowerShell emits same versioned contract for later validated import | VERIFIED implementation; native execution pending |
| 01-06 | fidelity_capture.py; linux-session.md; collect-fidelity-linux.sh | Shell execs collector; selected package/observer/recorder argv and real-device preflight feed failure/capture collection and matrix | VERIFIED implementation; native physical capture pending |
| 01-07 | fidelity_acceptance.py; checkpoint-session.md; phase01-baseline.md | Explicit selected receipts/hashes + complete scenario audit + ten findings decide strict acceptance; baseline accurately leaves evidence open | VERIFIED implementation; final reconciliation pending |
Paths above are the exact declared repository paths shown in each PLAN and fingerprint; no artifact is merely an unused placeholder.
### Key Link Verification
The owner heuristic returned 1/14 literal-path links and exit 1 on each PLAN. It searches literal target paths; Python module imports, C# class use, external schema contracts and prose names do not match. Those negative heuristic results are not treated as verified. Manual traces establish the implemented connections below; runtime-return links stay explicitly pending.
| From → To | Actual connection | Status |
|---|---|---|
| fidelity.py → inventory baseline | stage_original → verify_inventory compares inventory.py-compatible file list with docs/original-manifest.json; no direct inventory.py import is needed | WIRED by shared inventory contract |
| fidelity_receipts.py → scenarios.json | CLI/capture pass loaded protocol to validate_scenario_contract/audit_scenarios; stable IDs and required obligations validated | WIRED |
| fidelity_review.py → fidelity_receipts.py | Imports and calls read_receipt, validate_receipt, contained_path, identify_file before export | WIRED |
| viewer.mjs → generated review/media | fetch('review.json') supplies per-side media/events to createPairController; controller enforces exclusive mute and independent times | WIRED; actual media/browser pending |
| capabilities.json → REQUIREMENTS.md | Validator extracts exact IDs and rejects incomplete coverage; all 33 IDs accounted for | WIRED |
| fidelity_ledger.py → viewer ledger | Canonical export/current/history projection copied during checkpoint assembly and rendered by renderCapabilities | WIRED |
| Program.cs → FidelityObservation.cs | Optional outer using owner passed through Run; real post-Step acceptsInput/state/control/raw SDL hooks call observer | WIRED |
| Observed JSONL → shared receipts | Versioned session/case/elapsed/tick payload validated through process interoperability and collector; synthetic scope preserved | WIRED contract; real route pending |
| prepare-fidelity-checkpoint.sh → fidelity_checkpoint.py | Explicit Python invocation consumes original inventory and completed sealed packages | WIRED |
| Windows collector → shared receipts | Emits schema-versioned raw receipts, exact content identities and failure states; documented agent-owned validation/import normalizes returned reviewed records | WIRED contract; actual returned data pending |
| fidelity_capture.py → Linux package/observer | Uses actual package executable/assets and --fidelity-* arguments after real display/audio preflight | WIRED; hardware execution pending |
| Linux receipts → review/acceptance | Collected diagnostics undergo shared validation/import and explicit current selection; real failed Linux receipt remains open | WIRED failure path; successful route pending |
| Returned Windows/Linux results → strict audit | audit reads current.json, validates contained selected receipts and receipt_sha256 binding, checks all 120 slots and named reviews | WIRED implementation; human return pending |
| phase01-baseline.md → capability ledger | Same open acceptance/current scope retained; documented reconciliation updates receipt-bound current/history after return | WIRED present baseline; future reconciliation pending |
### Data-Flow Trace (Level 4)
| Rendered/accepted value | Actual source and flow | Finding |
|---|---|---|
| Capability navigation/current/history/discrepancies | capabilities.json → validate/export → sealed protocol/capability-ledger.json → review.json → renderCapabilities | FLOWING: real maintained evidence; unimplemented and missing scopes remain visible |
| Paired video/audio/event times | Actual imported receipt artifacts/hashes → _side/_events export → review.json → media/controller | Implementation wired; current source is explicitly missing, not synthetic original footage |
| Observer input/state/elapsed | Actual SDL/control/post-Step data → retained observer → bounded JSONL → collector/receipt validation | FLOWING in bounded regressions; current complete physical capture unavailable |
| Native acceptance totals | Explicit selected actual receipt files + content identities → audit_scenarios + CHECKS → strict report | FLOWING: actual failed diagnostic yields 0/120, errors [], human_needed |
Missing media is expected open evidence and is displayed as such; no hardcoded empty success path or invented original recording closes it.
### Existing Behavioral Evidence Reviewed
This completion pass did not rerun tests or launch services. Commands/results below are from retained execution receipts/logs, not SUMMARY assertions; fresh owner queries covered artifact presence, story validity and decision coverage.
| Evidence | Recorded invocation/result | Limit |
|---|---|---|
| Integrated local suite | artifacts/fidelity/01-07-full-suite.json and .log: scripts/test.sh, exit 0, 782.049626s; 556 Python (180 fidelity), 27 Node, 23 managed observer, 2 HUD, 51 managed entry-point invocations, 36 rendered GPU receipts, zero Vulkan errors, 539 originals | Before later tooling-only review fixes; dummy audio/headless checks are not physical/native baseline capture |
| Final tooling regression | artifacts/fidelity/01-review-fixes/python-fidelity-final.log: 191 tests, 43.355s, OK | Includes final copy-state artifact-root fix; no new runtime change or full GPU rerun claimed |
| Media controller | artifacts/fidelity/01-review-fixes/node-viewer-direct.log: 27 pass, 0 fail/skipped; named independent seek/drift, exclusive mute, rejected play, buffering, decode and full-tail assertions inspected | Media doubles exercise controller transitions, not actual browser decoding/audibility |
| Preservation | artifacts/fidelity/01-review-fixes/original-preservation.log: 539 unchanged originals | Byte preservation at check time; final P1 session conduct still needs disposition |
| Readiness | artifacts/fidelity/01-review-fixes/readiness-final.json plus verification/01-07-final-checkpoint.json: 11,001 members, materials_ready true, human_needed | Sealed runtime provenance retained as 446930d dirty true / diff 90cef956…; later tooling revision does not relabel it |
| Strict acceptance | artifacts/fidelity/01-review-fixes/acceptance-final.json: require-complete exit 1, errors [], accepted 0/120, all ten findings pending | Expected open evidence; no malformed acceptance input or observed code failure |
No phase-declared shell probe requiring a separate new execution was identified; the phase relies on the retained local CLI/test/preflight evidence. No full suite was repeated in this completion pass.
### Requirements Coverage
All four accountable requirement IDs are declared across the seven PLANs; no Phase 1 requirement is orphaned. Pending is retained in REQUIREMENTS.md.
| Requirement | Source PLANs | Evidence and remaining dependency | Disposition |
|---|---|---|---|
| EVID-01 | 01,05,06,07 | 539 unchanged originals; bounded isolated staging, canonical inventory and pre/post checks implemented. Final actual session preservation/P1 remains pending | Pending — current preservation verified; final human disposition required |
| EVID-02 | 01,02,04,05,07 | Original-DxWnd collector/protocol/identity/review tooling ready; 0/40 actual original obligations and A1/original-boundary review open | Pending — NEEDS HUMAN |
| EVID-03 | 02,03,07 | All 33 full-game requirements represented in 25 capabilities/six groups; source/implementation/platform/history/discrepancy/open acceptance traceable. Returned-evidence reconciliation and P3 remain open | Pending — ledger implementation verified; final human/reconciliation dependency |
| EVID-04 | 01,02,04,05,06,07 | Native collectors, observer and exact package binding implemented; failed Linux physical preflight retained, no accepted native route; 0/80 accepted | Pending — NEEDS HUMAN |
### Decision Coverage
Owner query: **16/16** trackable CONTEXT decisions honored, not_honored []. “All trackable CONTEXT.md decisions are honored by shipped artifacts.” Advisory gate only; it does not change acceptance.
### Test Quality and Anti-Patterns
Active tests assert concrete identity bytes, rejection behavior, monotonic ownership/state, media-controller transitions and acceptance classification. Test-generated metadata/media are explicitly synthetic fixtures: they verify validators/controller behavior and are never original/native fidelity oracles. The complete-metadata positive matrix test cannot establish actual physical execution; strict real matrix stays 0/120.
The targeted completion scan found no unreferenced TBD/FIXME/XXX or disabled requirement-test markers in the fidelity source/tests/scripts/observer scope; the prior completed 40-file debt/skip scan is retained. Expected empty initial review and false human-review fields preserve missing evidence. They are not stubs claiming completion. No new blocking anti-pattern was established.
Existing gates remain recorded: security 22/22 mitigated, zero open; validation automation complete with manual checks open; independent review verification closes all five historical findings after 02d182f. UI review was explicitly disabled for this phase by the recorded gate configuration; TDD is inactive. These gates were not reopened. Broad tooling feedback 43.355s exceeds its 30s quick target (WARNING), with no effect on native acceptance.
### Human Verification Required
**Ten named findings remain pending.** Collect, observe and return one complete local result tree following docs/evidence/checkpoint-session.md and its Windows/Linux subguides. The integration agent owns evidence-backed normalization, reviewed-copy creation, hash validation, import, current selection, ledger reconciliation and final strict audit after return. Raw receipts remain immutable. Positive human findings must never be generated automatically.
#### 1. A1 — Capture and observe the isolated original through the selected DxWnd setup
**Test:** A1 — Capture and observe the isolated original through the selected DxWnd setup using the combined-session guide.
**Expected:** Complete 40 original-Windows-DxWnd obligations; observe moving game imagery and intelligible game audio, retaining actual executable/profile/copy inventories and wrapper/configuration limitations.
**Why human:** Original execution and audiovisual truth are unobserved; the backstop abstains with insufficient_spec.
#### 2. A2 — Exercise actual paired recordings in the identified browser
**Test:** A2 — Exercise actual paired recordings in the identified browser using the combined-session guide.
**Expected:** Both real recordings decode, play at actual speed, seek to their own observed events, preserve full tails and switch exclusive audio without concealing elapsed time.
**Why human:** Controller tests use media doubles; they cannot establish real codec/browser/physical-audio behavior. Backstop: insufficient_spec.
#### 3. EVID-02-unclassified — Review original capture boundaries and limitations
**Test:** EVID-02-unclassified — Review original capture boundaries and limitations using the combined-session guide.
**Expected:** Document observed original/DxWnd launch, crop, aspect, timing, recording boundaries and retained/fresh lifetimes for the actual reference captures.
**Why human:** This flagged assumption cannot be inferred from prepared settings or synthetic metadata.
#### 4. EVID-04-unclassified — Collect and inspect both native platform routes
**Test:** EVID-04-unclassified — Collect and inspect both native platform routes using the combined-session guide.
**Expected:** Complete 40 native Windows and 40 native Linux obligations with actual OS/GPU/driver/Vulkan/SDL/source/package/resource identity and observed route/input/audio continuity.
**Why human:** Windows is cross-published only; current Linux TTY/auto_null preflight cannot capture native physical gameplay.
#### 5. P1 — Resolve the original-preservation prohibition explicitly
**Test:** P1 — Resolve the original-preservation prohibition explicitly using the combined-session guide.
**Expected:** Confirm authoritative originals were never executed or changed; compare all 539 recorded hashes and generated-copy pre/retained/post inventories after the session.
**Why human:** Descriptor-less unresolved prohibition requires explicit disposition; current preserved hashes do not prove future session conduct.
#### 6. P2 — Resolve the honest-comparison prohibition explicitly
**Test:** P2 — Resolve the honest-comparison prohibition explicitly using the combined-session guide.
**Expected:** Confirm genuine original media, no retiming or concealed drift, no mixed simultaneous soundtracks, and visible review gain/derivation provenance.
**Why human:** Unverified-prohibition — human review recommended; genuine playback and perceived audiovisual comparison require observation.
#### 7. P3 — Resolve the history/full-scope/native-transparency prohibition explicitly
**Test:** P3 — Resolve the history/full-scope/native-transparency prohibition explicitly using the combined-session guide.
**Expected:** Confirm all 33 requirements and unimplemented content stay visible; conflicting/superseded evidence and native/Wine/component/cross-publish distinctions are preserved after reconciliation.
**Why human:** Unverified-prohibition — human review recommended; final returned-evidence reconciliation requires explicit judgment.
#### 8. browser — Review the complete local comparison interface
**Test:** browser — Review the complete local comparison interface using the combined-session guide.
**Expected:** With real captures, verify readable independent clocks/drift, keyboard controls, raw unobstructed default views, optional annotations/differences and visible loading/error/tail states.
**Why human:** No actual browser visual/usability/codec review has been performed.
#### 9. paired_review — Compare all corresponding actual recordings and record discrepancies
**Test:** paired_review — Compare all corresponding actual recordings and record discrepancies using the combined-session guide.
**Expected:** Review matched events, imagery and sound across the required cases, retaining raw drift and justified system-specific observations without invented tolerances.
**Why human:** No corresponding original/native pair or completed visual/audible comparison exists.
#### 10. physical_input — Exercise visible native gameplay and actual audible devices
**Test:** physical_input — Exercise visible native gameplay and actual audible devices using the combined-session guide.
**Expected:** On Linux and Windows use physical supported inputs through lab → VR04 → lab → outside, natural/skipped and fresh/retained cases, held input, banked jumps, landing and idle; confirm real display/audio output.
**Why human:** Injected/headless/GPU/dummy-audio fixtures prove narrower behavior and cannot satisfy physical-input or audibility acceptance.
### Acceptance Conclusion
Autonomous preparation is complete; the promised real comparison outcome remains human_needed. No implementation BLOCKER was established in this bounded completion. The observable absence of original/native accepted captures is a documented human/external evidence dependency, explicitly kept open by the roadmap contract, not silently passed.
A1/A2 are **unverified non-inferable checks** (`insufficient_spec`); P1/P2/P3 are **unverified-prohibition — human review recommended**, with no automatic resolution. No later phase specifically replaces Phase 1 capture/review obligations, so none are deferred. No phase completion, advancement, commit or push was performed.
The fingerprint was produced by the owner CLI `query verification.fingerprint` over the listed actual source/test/document/evidence inputs; its returned fields are copied verbatim. Planning PLAN/SUMMARY coverage was added by the owner. SUMMARYs supply intended interfaces, not proof of behavior.
---
_Verified: 2026-11-14T05:34:19Z_
_Verifier: gsd-verifier_
## Bounded Verification Follow-up — Bundled Bytecode Fix (2026-11-14)
The first actual UAT readiness command exposed a tooling defect: Python local imports created `__pycache__/*.pyc` inside the sealed checkpoint, so later immutable-tree checks could fail. This qualifies the earlier readiness evidence; it was not an original/native capture or an A1 pass. Historical bundle `phase01-before-bytecode-fix-20261114T215109Z` is preserved. The freshly assembled `dist/fidelity/phase01` retains 11,001 immutable members and existing result/run history.
Independently inspected regression commit `23ee1c2` and implementation commit `2fe8b40`. The regression invokes all five copied bundled CLI entry points using `python -E`, checks that no bytecode appears, invokes copied checkpoint preflight twice, and compares the complete tree identity before/after. The fix sets `sys.dont_write_bytecode = True` only under `__name__ == '__main__'`, before local imports, in acceptance/checkpoint/capture/review/ledger. It adds two required sys imports and changes no gameplay, library algorithm, receipt schema or acceptance decision.
| Retained evidence inspected | Actual result and scope |
|---|---|
| bytecode-fix/ready-bundled-1.json and ready-bundled-2.json | Exact bundled-cwd default-python readiness command succeeded twice without -B: materials_ready true, 11,001 members, human_needed; updated checkpoint identity receipt records zero created bytecode files |
| bytecode-fix/fidelity-tests.log | Initial broad attempt ran 185 test methods, with an observer-class setup ERROR caused by its 90-second .NET build timeout; the run is FAILED, not a passing aggregate. The completed methods include the 26 checkpoint regressions |
| bytecode-fix/observer-build.log | Separate bounded build succeeded in 72.12s, zero errors; one NU1900 vulnerability-index access warning retained |
| bytecode-fix/observer-retry.log | Observer-only retry: seven tests PASS in 24.473s; 192 target checks are covered across the separate runs, not by a successful initial full run |
| bytecode-fix/acceptance.json | Strict audit remains exit 1, errors [], 0/120 accepted, all ten named human findings pending |
| verification/01-07-final-checkpoint.json | Current manifest/READY identities updated for source fix 2fe8b40; package runtime provenance remains separately identified |
Evidence paths above are under `artifacts/fidelity/`. No tests, runtime, full GPU suite or wider audit were rerun by this follow-up verifier. The reviewed change is confined to bundled CLI cache behavior; no new native compatibility or gameplay claim follows. The user-selected UAT restart preserves all ten pending findings and agent-owned result reconciliation.
**Follow-up verdict:** the bounded bytecode defect is corrected by the inspected implementation and retained behavioral evidence. Overall status remains **human_needed**, score **29/42**, with **all ten human checks pending**. Fingerprint refreshed through the owner CLI over the prior 65 inputs plus the six evidence files above; prior proof is retained.
_Follow-up verified: 2026-11-14T21:58:58Z_
@@ -1 +1 @@
No external API integration: Phase 01 implements local filesystem provenance, native process capture, offline media review and a contained loopback file viewer; it consumes existing game/tool executables without adding a hosted service, external SDK integration or remote API capability. No external API integration: Phase 01 uses local files, native capture, offline media review and a loopback viewer; no hosted API or external SDK is added.
@@ -0,0 +1,35 @@
<!-- CONSUMED: final verification completed human_needed on2026-11-14. Current next action: $gsd-verify-work 1 and combined actual human session; historical interrupted-verifier notes below are superseded. -->
---
context: phase
phase: 01-reproducible-fidelity-baseline
plan: "07"
task: 3
total_tasks: 3
status: consumed
last_updated: "2026-11-13T22:26:46.798618+00:00"
---
# Final verification quota checkpoint
Quota guard explicitly requested pause at15%. Resume completed task01-07-03 and recovered fullsuite exit0 (782.049626s), then reviewed/fixed allfive source-integrity findings. Do NOT redo implementation or tests. Source commits through02d182f, review/coverage/security documentation71366e7. Fullsuite556Python/180fidelity,27Node,23observer,2HUD,51managedentrypoints,36GPUrenderedreceipts,zeroVulkanvalidationerrors,SDLdummychecks,539originalhashes. Latertooling-onlyfixes: all191fidelityregressions PASS43.355s; focused26scenario,23capture,29acceptance,27Node,18LinuxhostedPowerShell. All539originals unchanged. No runtime changes afterfullsuite; no need13minGPUrerun forcurrentPython/collector fixes.
Historicalreview5915128: CR01selected-vs-reviewedpath,CR02originalinventory/executablebinding,CR03copy-stateidentity,WR01viewerledgerprojection,WR02interruptedWindowsfinalization. Fixes5569bc2,bda35e5,6e5ee0b,548c97a,2608517,a821754. Independentre-reviewcaughtremaininghash-onlycopy-statebypass; RED48fca0d/GREEN02d182f requiresactual_checked_artifactwithrootinside_scenario_observation; callersupdated. Finalindependentre-reviewallfiveFIXED in01-REVIEW-VERIFY.md; dispositionopen0. Securityauditorfinal22/22mitigated, threats_open0 in01-SECURITY.md. Nyquistautomationcoveragevalidatedall15taskbindings; manualacceptanceopen;191fidelityaggregate43.355sec exceeds30secquicktargethonestly. UIreviewdisabledconfigfalse. No remainingknowncode/securityblockers.
Currentfreshfinalbundle dist/fidelity/phase01 has11001immutableentries. Currenthashes/readinessreceipt artifacts/fidelity/verification/01-07-final-checkpoint.json. readyexit0true,strictauditexit1 errors[] accepted0/120,10humanpending; logs artifacts/fidelity/01-review-fixes/readiness-final.json,acceptance-final.json,python-fidelity-final.log. Oldbundlespreserved phase01-pre-review-48100025 andphase01-pre-copy-artifact-7ceebcb3. ActualLinuxfailedpreflightimportedcurrentbundle/results/imported. Runtimepackage source446930d dirty/diff90cef956 unchanged; source/docscommitsmustnotrelabelitsidentity. Original/nativeWindows+DxWnd andphysicalLinuxvisible/audible/browserreviewremainonecombinedhuman session pending. Humanonlycollects/observes/returns; agent-ownedexactnormalizationmapping incheckpoint-session.md. No capture request issued yet because finalphaseverification/handoffpending.
Final typed verifier phase01_final_verification was dispatched at21%; quota15% interrupted it, instructedfinishonlyboundedhuman_neededreport/fingerprint thenreturn. It had readall7musthaves/summaries, checked25capabilities/33requirements/0unmapped/6groups/33rows,16/16decisioncoverage,40sourcefilesnoskip/debtscan. A mandatoryMVPgoalformatguard exposed existingROADMAPMode:mvp plainproseGoal. Rootauthorizedformat-only identicalintentuserstory and modifiedROADMAP.md uncommitted: As a tester, I want to reproduce identified original/port comparison scenarios, so that I understand exactly what the current reconstruction proves on each native platform. Validatorvalidtrue; no scope/successcriteriamodified. OneverifiercommandusedwrongunittestclassFidelityAcceptance (loadererror,correctclassAcceptanceTests); twoothernamedbehaviorcheckspassed; don'tmislabelthatcommandassuccess. Priorfulltargeted29passestablishactualcoverage.
NEXT: Reconcile currentverifier's 01-VERIFICATION.md and CLI verification.status; ifreport/fingerprintabsentfinishthat ONLY beforeanynewphase. FingerprintmustbeownerCLIgenerated, notmanual. Oncehuman_neededstatusvalid, persistUATfromnamedhumanitems, updateSTATE/consumedhandoffs, commitverifiedreport+goalmetadata+handoffdocs andpush verifiedsource/tooling toauthorizedGitea/main. Lastpushedhead remainsd18f551; later01-07/task3/reviewfix/auditcommits arelocalawaitingfinalverification. Preserveunrelatedtools.yaml. Do notadvancephase2orclaimPhase1accepted; allEVIDIDsPending0/120humanacceptance. No source changesuncommittedexceptROADMAPformatandpossiblynewverifierreport.
Nativeagents/sourcewritesallfinishedexceptverifierreportbeingclosed. Quota watcher runs and actual15%steeringworks. Noauto-resume; usermust $gsd-resume-workafterreset. Don'tspendquota rereadingmassiveGSDscriptbodies orrerunningfinished13minfullsuite. Existinglocalpackages/media/originalcopiesstaylocal, noCI/uploads. MaintracksGitea/main, scoped.gitwriteescalation; retainhistoricalhandoffsmarkconsumedratherthandelete (priorautomaticreviewrejecteddeletion).
## Required Reading
AGENTS.md,parentinstructions,HANDOFF.json,01-07SUMMARY,01-REVIEW-VERIFY,01-SECURITY,01-VALIDATION,and01-VERIFICATIONifpresent.
## Critical Anti-Patterns
| Pattern | Description | Severity | Prevention Mechanism |
|---|---|---|---|
| Redo completed tests | Fullsuiteand191fidelitychecksfinished | advisory | Reconcile savedlogs first; rerunonlyafternewchanges |
| False phase completion | Preparedmaterialsfailactualstrictacceptance0/120 | advisory | KeepEVIDPending andhuman_needed; owner verification.status beforeadvance |
## Infrastructure State
Testsfinished; verifierinterruptedatpause; reportreconciliationpending; localquota watcher running. No sourceworkeractive.
## Next Action
Inspect01-VERIFICATION.md and owner verification.status; finish report/fingerprint/UAT ifneeded, commit/pushverified01-07reviewedwork; neverredo task3/fulltests orautoapprovehumanacceptance.
+3 -3
View File
@@ -46,8 +46,8 @@
], ],
"next": { "next": {
"command": "$gsd-progress --next", "command": "$gsd-progress --next",
"label": "Advance to the next step", "label": "Review prepared Phase 1 checkpoint and pending combined human session",
"reason": "Phase 1 of 8 · 0% · executing" "reason": "Phase 1 remains open: 7/7 autonomous preparation records, actual acceptance human_needed 0/120; Phase 2 not advanced"
}, },
"updated_at": "2026-11-13T17:04:38.735Z" "updated_at": "2026-11-13T21:49:00Z"
} }
+67
View File
@@ -1,5 +1,72 @@
# Compatibility and validation # Compatibility and validation
## Bundled checker cache fix — 2026-11-14
A user readiness check created Python bytecode inside the sealed checkpoint and
then rejected it as unexpected immutable material. Regression23ee1c2 reproduces
this; fix2fe8b40 disables bytecode writes before local imports in all five bundled
Python command entry points. All26 checkpoint tests pass, including a real copied
CLI test with environment overrides ignored. The exact bundled readiness command
passes twice without creating pyc files. A fresh11,001-member checkpoint replaces
phase01; the old tree and its cache/results are retained in local history, and
existing results/generated execution copies were copied into the new mutable roots.
The broader attempt ran185 tests but failed observer class setup after a90-second
.NET build timeout. A separate bounded local build passed; the seven observer
checks then passed on their own retry. Thus all192 fidelity checks are covered
across the two runs; the initial full attempt remains recorded as failed.
No runtime implementation changed. Actual original/native acceptance remains
0/120 OPEN and all ten human UAT items remain pending.
## Phase 1 verification — human session pending
Final owner-validated verification is `human_needed`:29/42 truths verified and13
uncertain pending actual observations. Ten named checks are saved in
`.planning/phases/01-reproducible-fidelity-baseline/01-UAT.md`. Autonomous materials,
review fixes, security and automation coverage are complete. Actual acceptance
remains0/120 OPEN; all EVID requirements stay Pending and Phase2 is unadvanced.
The combined session guide is `docs/evidence/checkpoint-session.md`; the local
checkpoint is `dist/fidelity/phase01`. Resume human verification with
`$gsd-verify-work 1`. No new build/test or gameplay claim accompanies this report.
## Final phase 1 review closure
All five review findings are independently verified fixed. The final copy-state
refinement is02d182f; all191 fidelity regressions pass in43.355s, with29 acceptance,
26 scenario and23 capture checks in the affected suites. Earlier review fixes
also pass27 Node and18 Linux-hosted PowerShell checks;539 originals stay unchanged.
The recovered full local suite passed782.049626s before these tooling-only review
fixes:556 Python,27 Node,23 observer,2 HUD,51 managed entry points and36 GPU render
receipts, zero Vulkan validation errors. The full GPU suite was not repeated for
these Python/collector fixes. Independent security audit closes22/22 planned
threats. Current fresh checkpoint is `dist/fidelity/phase01` (11,001 immutable
entries); exact current manifest/READY identities are recorded locally in
`artifacts/fidelity/verification/01-07-final-checkpoint.json`. Earlier bundle
history is preserved locally. All120 actual original/native acceptance obligations
and ten named human findings remainOPEN. Final phase verification is pending.
## Phase 1 final checkpoint — materials ready, runtime acceptance OPEN
Fresh `dist/fidelity/phase01` readiness passes11,000 immutable members. Strict audit
exits1 with0/120 accepted and ten pending human findings. Failed Linux preflight
`linux-01-06-matrix-preflight-linux` identifies no display/auto_null only; it is
diagnostic evidence, not captured gameplay. Native Windows and actual original-
DxWnd remain unexecuted; automated GPU/SDL fixtures cannot establish physical
input/audibility. Runtime packages retain446930d dirty/diff90cef956, separately
from later tools/docs commits; originals and generated packages/media stay local.
Complete local suite: exit 0 in 782.05s (runner: 783s), with 556 Python
(180 fidelity), 27 Node, 23 managed observer, 2 separate HUD Python tests,
51 managed test entry points and the main build. The 36 GPU rendered receipts,
27 saved readbacks and 17 material/readback assertions report zero validation
errors. SDL dummy-audio checks pass; 539 original hashes match. Optional native
window tests were not enabled; dummy consumption supplies no audible proof.
Final exit/duration: `artifacts/fidelity/01-07-full-suite.json`, with the complete
log alongside it; the first74.65s attempt is retained
separately for the corrected Node reporter/count guard failure. Exact final
checkpoint identities: `artifacts/fidelity/verification/01-07-final-checkpoint.json`.
See [remaining acceptance](evidence/phase01-baseline.md). All EVID requirements and
Phase1 acceptance stay OPEN under the roadmap source-backed continuation exception.
## Phase 1 plan 01-06 — reviewed tooling evidence ## Phase 1 plan 01-06 — reviewed tooling evidence
Primary repeats23 capture tests; executor records156 broader fidelity tests Primary repeats23 capture tests; executor records156 broader fidelity tests
+65
View File
@@ -1,5 +1,70 @@
# Decisions # Decisions
## Bundled checker cache fix — 2026-11-14
A user readiness check created Python bytecode inside the sealed checkpoint and
then rejected it as unexpected immutable material. Regression23ee1c2 reproduces
this; fix2fe8b40 disables bytecode writes before local imports in all five bundled
Python command entry points. All26 checkpoint tests pass, including a real copied
CLI test with environment overrides ignored. The exact bundled readiness command
passes twice without creating pyc files. A fresh11,001-member checkpoint replaces
phase01; the old tree and its cache/results are retained in local history, and
existing results/generated execution copies were copied into the new mutable roots.
The broader attempt ran185 tests but failed observer class setup after a90-second
.NET build timeout. A separate bounded local build passed; the seven observer
checks then passed on their own retry. Thus all192 fidelity checks are covered
across the two runs; the initial full attempt remains recorded as failed.
No runtime implementation changed. Actual original/native acceptance remains
0/120 OPEN and all ten human UAT items remain pending.
## Phase 1 verification — human session pending
Final owner-validated verification is `human_needed`:29/42 truths verified and13
uncertain pending actual observations. Ten named checks are saved in
`.planning/phases/01-reproducible-fidelity-baseline/01-UAT.md`. Autonomous materials,
review fixes, security and automation coverage are complete. Actual acceptance
remains0/120 OPEN; all EVID requirements stay Pending and Phase2 is unadvanced.
The combined session guide is `docs/evidence/checkpoint-session.md`; the local
checkpoint is `dist/fidelity/phase01`. Resume human verification with
`$gsd-verify-work 1`. No new build/test or gameplay claim accompanies this report.
## Final phase 1 review closure
All five review findings are independently verified fixed. The final copy-state
refinement is02d182f; all191 fidelity regressions pass in43.355s, with29 acceptance,
26 scenario and23 capture checks in the affected suites. Earlier review fixes
also pass27 Node and18 Linux-hosted PowerShell checks;539 originals stay unchanged.
The recovered full local suite passed782.049626s before these tooling-only review
fixes:556 Python,27 Node,23 observer,2 HUD,51 managed entry points and36 GPU render
receipts, zero Vulkan validation errors. The full GPU suite was not repeated for
these Python/collector fixes. Independent security audit closes22/22 planned
threats. Current fresh checkpoint is `dist/fidelity/phase01` (11,001 immutable
entries); exact current manifest/READY identities are recorded locally in
`artifacts/fidelity/verification/01-07-final-checkpoint.json`. Earlier bundle
history is preserved locally. All120 actual original/native acceptance obligations
and ten named human findings remainOPEN. Final phase verification is pending.
## Final fidelity audit — phase 1 plan 01-07
Readiness verifies immutable prepared bytes and current copied materials;
strict acceptance separately requires complete original/native matrix coverage,
matching package/source/resource identities and receipt-bound human judgments.
Structural `--allow-open` success never promotes acceptance. Preserve raw collector
receipts and failed/superseded history; the integration agent performs explicitly
specified evidence-backed post-return normalization, while the tester only
collects, observes and returns local files. A1/A2, both unclassified assumptions
and P1/P2/P3 remain visible until actual review. No universal fidelity tolerance,
automatic physical/audible pass or movement/landing reset is introduced.
Current result: ready11,000 files; strict audit human_needed,0/120. Positive-count
guards cover the existing fidelity suites in one consolidated local run; Node
uses explicit TAP so installed reporter defaults cannot hide the executed count.
The completed local run exits 0 in 782.05s: 556 Python (180 fidelity), 27 Node,
23 observer and 2 separate HUD Python tests; all 51 managed test entry points,
the main build, 36 GPU rendered receipts, 17 material/readback assertions,
dummy-audio checks and 539 original hashes pass. These bounded regression facts
do not resolve physical/audible/native/original acceptance.
## Linux capture access — phase 1 plan 01-06 ## Linux capture access — phase 1 plan 01-06
A common failed native display/audio preflight may explain all40 Linux open A common failed native display/audio preflight may explain all40 Linux open
+25 -1
View File
@@ -3539,5 +3539,29 @@
] ]
} }
], ],
"evidence_policy": "Typed report records reference existing documentation, not new executions or automatically imported runtime receipts. Every row remains open. Reconciliation retains 16 systems, 11 owners and 6 assumptions, including superseded baseline wording; continuation rows refine it without erasure." "evidence_policy": "Typed report records reference existing documentation, not new executions or automatically imported runtime receipts. Every row remains open. Reconciliation retains 16 systems, 11 owners and 6 assumptions, including superseded baseline wording; continuation rows refine it without erasure.",
"phase01_checkpoint": {
"acceptance": "human_needed",
"required_obligations": 120,
"accepted_obligations": 0,
"current_diagnostic_receipt_ids": [
"linux-01-06-matrix-preflight-linux"
],
"diagnostic_scope": "failed native Linux display/audio preflight; no gameplay launch",
"baseline_report": "docs/evidence/phase01-baseline.md",
"session_checklist": "docs/evidence/checkpoint-session.md",
"unclassified_assumptions": {
"EVID-02": "human_needed",
"EVID-04": "human_needed"
},
"backstops": {
"A1": "human_needed",
"A2": "human_needed"
},
"prohibitions": {
"P1": "flagged-unverified",
"P2": "flagged-unverified",
"P3": "flagged-unverified"
}
}
} }
+169
View File
@@ -0,0 +1,169 @@
# Phase 01 combined acceptance session
Materials preparation is separate from acceptance. The final local checkpoint is
`dist/fidelity/phase01`; all 120 obligations remain OPEN until actual captures and
human review. This document prepares the single combined session; it does not
report that any physical, audible, Windows or original fact has been observed.
Read [Windows/DxWnd instructions](windows-session.md) and
[Linux capture instructions](linux-session.md) together. They contain the exact
collector commands, settings, annotation fields and complete procedures. The
sealed packages retain source `446930d2a30d6d616c60ac5e59e4169a840bea09`, dirty true,
diff `90cef95669caece53fe2d2c4736cf2ac05ed27f5d25ca03ab572589686bcb73d`.
The later tools/checklist revision never replaces that runtime provenance.
1. Recheck immutable materials immediately before local transfer:
`python3 tools/recon/fidelity_acceptance.py ready --checkpoint dist/fidelity/phase01`.
Require `materials_ready: true`, separately `acceptance: human_needed`. A changed
package/resource requires a fresh identified checkpoint. Preserve the old bundle.
2. On the actual Windows PC select already installed DxWnd, its original exported
profile, recorder, browser and media tools. Record versions, executable hashes,
Windows/GPU/driver identities and actual settings. Run the bundled PowerShell
preflight and selftests; save their complete positive counts and failures.
3. Use only generated original copies. Retain pristine/pre/retained/post inventories,
original and relocated DxWnd profiles, wrapper limitations and the actual child
launch method. Observe moving game imagery, intelligible game audio, crop and
aspect before recording scenarios. Black/silent captures remain failed evidence.
4. Follow `protocol/agenda.json`: eight fresh/retained × natural/skipped × ordinary/
held-input cells, each with continuous, dialogue-return, bank-left, bank-right,
landing-idle obligations on original-DxWnd and native Windows (80). Follow the
same 40 obligations on native Linux. Retained departure/return must remain in
one process/clock. Continuous is lab → VR04 → lab → outside. No fixture, warp,
Wine, cross-publish, injected input or second fresh launch fills these slots.
5. Complete Linux real-display, physical-input and actual audible-device checks.
The saved `linux-01-06-matrix-preflight-linux` failure explains the current TTY/
auto_null limitation; it proves no captured gameplay. Retain failed/aborted/
skipped results and use fresh launch IDs for retries.
6. Review actual paired recordings in the identified local browser, including
decode/playback, seeking, complete tails, exclusive audio, corresponding events,
raw elapsed/event drift, actual speed and optional overlays. Keep source MKV,
derivation tool/hash/argv/time mapping and visible review gain. Do not invent
timing/pixel/angle/audio thresholds or hide drift through retiming.
7. Record the following named human findings with reviewer and concrete notes:
`A1` original moving imagery/intelligible audio/DxWnd limits; `A2` actual browser
decode/seek/exclusive audio; `EVID-02-unclassified` original capture boundaries;
`EVID-04-unclassified` native route/input/audio/identity; `P1` preservation;
`P2` honest unretimed/unmixed/non-synthetic comparison; `P3` history/full-scope/
native transparency; `browser`; `paired_review`; `physical_input`. A1/A2 are
separate from the two flagged assumptions. Insufficient observation remains
human_needed; descriptor-less P1/P2/P3 cannot be automatically dismissed.
8. Return the complete tree once by local filesystem/USB/existing local share.
Compare mutable result/original-run inventories with the source transfer
inventory, recheck READY/manifest and every linked hash before atomic import.
Keep packages, original copies and media local and ignored.
## Result reconciliation contract — integration agent only
The human tester collects, observes and returns the tree. The integration agent
performs the following local reconciliation after return; the tester is never
asked to engineer JSON or run the Python tooling. No normalized gameplay receipt
exists yet. Do not run reconciliation on failed/skipped/aborted/incomplete runs as
if they were successful; import those unchanged as diagnostic history.
Keep raw collector receipts immutable. Use the existing receipt importer on a
fresh local result destination; it validates hashes/containment and rejects
conflicting duplicates. Reviewed acceptance receipts are separately authored
records retaining the raw collector identity, actual media/events and limitations;
they must satisfy the shared receipt schema, source/package/resource binding and
full scenario continuity. Raw collection success never becomes review success.
Windows source/package/resources initially identify the exact `fidelity-build.json`
seal. Original reviewed receipts additionally identify the unchanged original
inventory and actual generated-copy pre/post inventories; missing raw collector
fields require evidence-backed normalization, never invented values.
Work on a **fresh sibling derived directory** for each captured raw receipt. Copy
every raw referenced file byte-identically into that directory, copy the raw
`receipt.json` as `raw-receipt.json`, and preserve `raw-receipt.sha256`. Make the
reviewed receipt a new ID ending `-reviewed`; retain the original launch/session
and clock IDs. Add the hashed raw receipt to `artifacts` with role `diagnostic`.
The integration agent uses this exact mapping; every new path is inside that fresh
derived directory and every identity uses `identify_file(actual_path)` including
SHA-256, size and header. No path or command from returned metadata is executed.
| Reviewed field | Actual source and required validation |
|---|---|
| Native executable | Raw identity copy; match manifest package executable SHA-256 |
| Native package | Exact selected RID's copied `fidelity-build.json`; match sealed package SHA-256 |
| Windows native source/resources | Same actual `fidelity-build.json` file; retain its source commit/dirty/diff fields. Resources are proven by exact full seal equality |
| Linux native source | Raw `identity/BUILD-INFO.txt`, with commit/dirty/diff taken from the matching exact package seal |
| Linux native resources | Raw `identity/resources.json`, exactly equal to manifest package resources |
| Original executable | Actual selected executable from the generated run (`Neutron.exe` or the recorded selected variant); retain its exact pristine relative path in `identity.executable.original_member` and compare size/header/hash to that member, retaining any mismatch as open |
| Original package/resources | Both identify hashed `identify_tree(original-pristine)` inventories whose complete file records and recomputed digest equal the checkpoint baseline. Generated-copy pre/post inventories remain separate; preserve all raw original content identities |
| Original pre/post | Save complete actual `identify_tree(original-pristine)` before/after return validation; require files and tree digest equal to the baseline and manifest original_pre. These describe authoritative/pristine preservation, separately from writable copy changes |
| Original copy pre/post/retained | Raw `copy-pre.json`, `copy-post.json`, `retained-copy.json`; preserve exact actual bytes/hashes in `identity.copy_pre`, `identity.copy_post`, `identity.retained_copy`. For both lifetimes bind `copy_pre_sha256` to the named pre record; retained runs also bind `retained_copy_sha256` to the named retained snapshot. Native reviewed runs use the same explicit state-record contract |
| Original source/launcher | Save manifest `tool_source` as `collector-source.json` and identify the actual bundled Windows collector; source commit/dirty/diff describes collector tooling, never recovered original source code |
| Original DxWnd/profile | Retain hashed actual `dxwnd-tool.json`, source profile and relocated export; explicit wrapper settings/limits are required |
| Platform/version/GPU/driver/Vulkan/SDL | Actual raw queries and human device/version records; absent observations remain missing, never guessed |
| Events/continuity/derivatives | Preserve actual raw values and hashed media; supplement only from observed annotations with methods/uncertainty; never generate invented markers |
| Review | Set visible/audible/ordinary_input/human_reviewed true only from the named, receipt-bound actual reviewer findings |
For example a Windows native raw receipt `port-fresh-natural-ordinary-continuous-01`
already identifies `identity/build.json` as source/package/resources. Its reviewed
identity retains that **same file/hash**, keeps source commit/dirty/diff from its
contents, and binds executable to manifest `packages.win-x64.executable`. It does
not substitute BUILD-INFO for that raw source or regenerate a package seal.
The reviewed record's minimal projection looks like this (metavariables below
are populated from the actual retained records by the integration agent):
```json
{
"receipt_id": "port-fresh-natural-ordinary-continuous-01-reviewed",
"session_id": "port-fresh-natural-ordinary-continuous-01",
"status": "reviewed",
"identity": {
"source": {"path":"identity/build.json", "sha256":"ACTUAL_SEAL_HASH", "size":0,
"header":"ACTUAL_HEADER", "commit":"ACTUAL_BUILD_COMMIT", "dirty":true,
"diff_sha256":"ACTUAL_BUILD_DIFF"}
},
"review": {"visible":true,"audible":true,"ordinary_input":true,"human_reviewed":true},
"acceptance": {"state":"accepted","remaining":[]}
}
```
This projection is **not a usable receipt or positive finding**: retain all other
required raw fields, replace every metavariable/size with identified actual values,
keep limitations/discrepancies, and include missing identity mappings above.
Clear `missing_evidence` and acceptance remaining only when each corresponding
fact has actually been supplied and reviewed. Otherwise preserve the gap and
`state: open`. The shared validator and strict audit reject incomplete reviewed
records. Do not overwrite raw receipts or label normalized copies as raw captures.
After writing the complete derived receipt, the agent validates/imports with the
existing API (run from repository root; substitute the actual derived directory):
```sh
PYTHONPATH=tools/recon python3 -c 'from pathlib import Path; from fidelity_receipts import read_receipt,validate_receipt,import_receipt; p=Path("LOCAL_DERIVED/receipt.json"); print(validate_receipt(read_receipt(p),p.parent)); print(import_receipt(p,p.parent,Path("dist/fidelity/phase01/results/imported")))'
```
An absent mapping or unobserved human fact is an OPEN result. Never manufacture
source, original, device, media or review identities to make this command pass.
In `results/current.json`, list the explicit current receipt paths as
`{"receipts":["imported/receipt-id/receipt.json"]}`. Preserve historical/superseded
records outside that selection. Conflicting duplicate slots cannot be selected.
In `results/human-review.json`, use `schema_version: 1`, exact selected
`receipt_ids`, a `receipt_sha256` object mapping each ID to its actual receipt hash,
and `checks` mapping every name above to `{ "observed": true, "reviewer":
"actual reviewer", "notes": "specific observation and limitations" }`. Empty or
false findings remain pending. These fields describe witnessed facts; tools never
generate positive human findings.
Run strict audit on the complete local result tree:
`python3 tools/recon/fidelity_acceptance.py audit --checkpoint dist/fidelity/phase01 --results dist/fidelity/phase01/results --require-complete`.
Nonzero means acceptance remains open. `--allow-open` may return zero for structural
inspection while explicitly reporting human_needed and every missing obligation;
it never satisfies EVID-02/EVID-04. Export actual paired selected receipts with the
existing `fidelity_review.py export` command; the prepared viewer starts empty.
## Pending acceptance checklist
- [ ] Original-DxWnd 40 obligations, actual imagery/audio/input and wrapper review.
- [ ] Native Windows 40 obligations, physical input/audio and exact runtime identity.
- [ ] Native Linux 40 obligations, real display/audio and physical input.
- [ ] Actual paired browser playback, seeking, exclusive audio and exposed drift.
- [ ] Both unclassified assumptions, A1/A2 backstops and P1/P2/P3 dispositions.
- [ ] Returned identities and strict audit passed; current/history discrepancies reconciled.
Phase 1 and all EVID requirements remain pending. The roadmap permits independent
source-backed recovery while these access dependencies remain open; it does not
waive them or authorize broader gameplay admission.
+44
View File
@@ -0,0 +1,44 @@
# Phase 01 evidence baseline — preparation, acceptance OPEN
The final acceptance checkpoint is `dist/fidelity/phase01`, freshly assembled from
the existing sealed 01-05 packages plus the final Linux/audit/session materials.
Prepared identities and generated media remain local and ignored. Runtime source:
`446930d2a30d6d616c60ac5e59e4169a840bea09`, dirty true; publish diff:
`90cef95669caece53fe2d2c4736cf2ac05ed27f5d25ca03ab572589686bcb73d`.
Original files remain governed by `docs/original-manifest.json` (539 files).
| Proof category | Current result | Acceptance |
|---|---|---|
| Immutable local tools/protocol/packages | Separate readiness audit | Materials only |
| Actual original-DxWnd | No returned gameplay recordings | OPEN 0/40 |
| Native Windows | Cross-publish/resource identity only | OPEN 0/40 |
| Native Linux physical/audible route | Failed TTY/null-audio preflight | OPEN 0/40 |
| Actual paired browser/audio review | No original/native recording pair | human_needed |
The retained actual diagnostic receipt is
`linux-01-06-matrix-preflight-linux`, from
`artifacts/fidelity/linux-current-receipts/`. It records no selected X11 display,
only `auto_null.monitor`, absent recording and absent observer events. No game was
launched. This is failed native preflight evidence, not native gameplay acceptance.
Historical Wine/component/GPU results keep their original scope and revision.
The strict audit reports every missing case/obligation and rejects synthetic,
misclassified, stale, wrong-resource, historical/conflicting or unreviewed evidence.
Its metadata unit fixtures exercise both complete coverage and rejection behavior;
their invented media/observations are never imported as runtime proof.
## Remaining discrepancies and judgments
The blocking gaps are actual original-DxWnd and native Windows execution, Linux
display/audio/physical-input access, complete 120-obligation captures, returned
media identity and real paired review. The NewGame.tsk story entry is not the
original main menu. DxWnd wrapper/timing/render behavior must remain separately
identified. No universal timing/pixel/audio tolerance is asserted.
A1 (original moving imagery/intelligible audio) and A2 (actual browser playback,
seek and exclusive audio) remain **human_needed**. EVID-02/EVID-04 unclassified
assumptions remain unresolved/flagged; P1 preservation, P2 honest comparison and
P3 history/native transparency require explicit final judgment. Follow the single
[combined session checklist](checkpoint-session.md). All EVID requirements and
Phase 1 acceptance remain OPEN under the roadmap source-backed continuation
exception. No movement, rendering, gameplay or collision admission changed.
+6
View File
@@ -150,6 +150,12 @@ powershell.exe -NoProfile -File .\scripts\collect-fidelity-windows.ps1 -Action S
selection. An interrupted active run retains its initial `incomplete.json`; selection. An interrupted active run retains its initial `incomplete.json`;
when safe, collect its artifacts with `Finish -Outcome aborted -Reason '...'` when safe, collect its artifacts with `Finish -Outcome aborted -Reason '...'`
instead of pretending a separate aborted launch describes its lifetime. instead of pretending a separate aborted launch describes its lifetime.
When only `incomplete.json` survived, this command preserves its exact bytes as
a diagnostic artifact and permits only `aborted`. End clocks remain absent;
initial placeholder end values are discarded. Keep recovered media and source
notes, with an empty `events` array because no complete launch interval was
observed. The receipt remains open and importable; recovery does not establish
missing executable identity, process completion, or a captured/reviewed run.
Failed starts preserve `run.json`, `failure.json` and available logs. To collect Failed starts preserve `run.json`, `failure.json` and available logs. To collect
failed/skipped/aborted media use `Finish -Outcome failed|skipped|aborted` matching failed/skipped/aborted media use `Finish -Outcome failed|skipped|aborted` matching
the prior status, a reason and annotation/artifact directories (empty arrays are the prior status, a reason and annotation/artifact directories (empty arrays are
+70
View File
@@ -1,5 +1,75 @@
# Progress — 2026-11-07 # Progress — 2026-11-07
## Bundled checker cache fix — 2026-11-14
A user readiness check created Python bytecode inside the sealed checkpoint and
then rejected it as unexpected immutable material. Regression23ee1c2 reproduces
this; fix2fe8b40 disables bytecode writes before local imports in all five bundled
Python command entry points. All26 checkpoint tests pass, including a real copied
CLI test with environment overrides ignored. The exact bundled readiness command
passes twice without creating pyc files. A fresh11,001-member checkpoint replaces
phase01; the old tree and its cache/results are retained in local history, and
existing results/generated execution copies were copied into the new mutable roots.
The broader attempt ran185 tests but failed observer class setup after a90-second
.NET build timeout. A separate bounded local build passed; the seven observer
checks then passed on their own retry. Thus all192 fidelity checks are covered
across the two runs; the initial full attempt remains recorded as failed.
No runtime implementation changed. Actual original/native acceptance remains
0/120 OPEN and all ten human UAT items remain pending.
## Phase 1 verification — human session pending
Final owner-validated verification is `human_needed`:29/42 truths verified and13
uncertain pending actual observations. Ten named checks are saved in
`.planning/phases/01-reproducible-fidelity-baseline/01-UAT.md`. Autonomous materials,
review fixes, security and automation coverage are complete. Actual acceptance
remains0/120 OPEN; all EVID requirements stay Pending and Phase2 is unadvanced.
The combined session guide is `docs/evidence/checkpoint-session.md`; the local
checkpoint is `dist/fidelity/phase01`. Resume human verification with
`$gsd-verify-work 1`. No new build/test or gameplay claim accompanies this report.
## Final phase 1 review closure
All five review findings are independently verified fixed. The final copy-state
refinement is02d182f; all191 fidelity regressions pass in43.355s, with29 acceptance,
26 scenario and23 capture checks in the affected suites. Earlier review fixes
also pass27 Node and18 Linux-hosted PowerShell checks;539 originals stay unchanged.
The recovered full local suite passed782.049626s before these tooling-only review
fixes:556 Python,27 Node,23 observer,2 HUD,51 managed entry points and36 GPU render
receipts, zero Vulkan validation errors. The full GPU suite was not repeated for
these Python/collector fixes. Independent security audit closes22/22 planned
threats. Current fresh checkpoint is `dist/fidelity/phase01` (11,001 immutable
entries); exact current manifest/READY identities are recorded locally in
`artifacts/fidelity/verification/01-07-final-checkpoint.json`. Earlier bundle
history is preserved locally. All120 actual original/native acceptance obligations
and ten named human findings remainOPEN. Final phase verification is pending.
## Phase 1 final preparation — acceptance human_needed
The fresh local `dist/fidelity/phase01` checkpoint passes readiness over11,000
immutable files. Strict audit exits1:0/120 original-DxWnd/native Linux/native
Windows obligations accepted, all ten human findings pending. The actual failed
`linux-01-06-matrix-preflight-linux` receipt is imported with a diagnostic viewer;
no gameplay was launched. Runtime source remains446930d dirty, diff90cef956;
exact package/tool identities are local in
`artifacts/fidelity/verification/01-07-final-checkpoint.json`.
The consolidated runner now rejects zero fidelity Python/viewer/observer counts.
The complete local suite passed in 782.05s (runner clock: 783s): 556 Python
(180 fidelity), 27 Node, 23 managed observer, 2 separate HUD Python tests and
51 managed test entry points, followed by the main build. The log records
36 GPU rendered receipts, 27 saved readbacks and 17 material/readback assertions,
all with zero Vulkan validation errors; SDL dummy-audio checks pass and all
539 originals remain unchanged. No physical input, audible or window-session
acceptance is inferred. Receipt: `artifacts/fidelity/01-07-full-suite.json`;
full output: `artifacts/fidelity/01-07-full-suite.log`.
The first74.65s attempt passed Python but exposed the new Node reporter/count
guard mismatch; explicit TAP fixes it and the complete rerun is retained.
See [baseline](evidence/phase01-baseline.md) and the single
[combined session](evidence/checkpoint-session.md). All EVID requirements and
Phase1 acceptance remain OPEN; source-backed continuation follows the roadmap
exception. Movement/gameplay/admission and historical runtime evidence are unchanged.
## Phase 1 plan 01-06 — reviewed completion ## Phase 1 plan 01-06 — reviewed completion
Linux capture tooling and full40-obligation matrix are complete. Primary repeats Linux capture tooling and full40-obligation matrix are complete. Primary repeats
+64
View File
@@ -1,5 +1,69 @@
# Tasks # Tasks
## Bundled checker cache fix — 2026-11-14
A user readiness check created Python bytecode inside the sealed checkpoint and
then rejected it as unexpected immutable material. Regression23ee1c2 reproduces
this; fix2fe8b40 disables bytecode writes before local imports in all five bundled
Python command entry points. All26 checkpoint tests pass, including a real copied
CLI test with environment overrides ignored. The exact bundled readiness command
passes twice without creating pyc files. A fresh11,001-member checkpoint replaces
phase01; the old tree and its cache/results are retained in local history, and
existing results/generated execution copies were copied into the new mutable roots.
The broader attempt ran185 tests but failed observer class setup after a90-second
.NET build timeout. A separate bounded local build passed; the seven observer
checks then passed on their own retry. Thus all192 fidelity checks are covered
across the two runs; the initial full attempt remains recorded as failed.
No runtime implementation changed. Actual original/native acceptance remains
0/120 OPEN and all ten human UAT items remain pending.
## Phase 1 verification — human session pending
Final owner-validated verification is `human_needed`:29/42 truths verified and13
uncertain pending actual observations. Ten named checks are saved in
`.planning/phases/01-reproducible-fidelity-baseline/01-UAT.md`. Autonomous materials,
review fixes, security and automation coverage are complete. Actual acceptance
remains0/120 OPEN; all EVID requirements stay Pending and Phase2 is unadvanced.
The combined session guide is `docs/evidence/checkpoint-session.md`; the local
checkpoint is `dist/fidelity/phase01`. Resume human verification with
`$gsd-verify-work 1`. No new build/test or gameplay claim accompanies this report.
## Final phase 1 review closure
All five review findings are independently verified fixed. The final copy-state
refinement is02d182f; all191 fidelity regressions pass in43.355s, with29 acceptance,
26 scenario and23 capture checks in the affected suites. Earlier review fixes
also pass27 Node and18 Linux-hosted PowerShell checks;539 originals stay unchanged.
The recovered full local suite passed782.049626s before these tooling-only review
fixes:556 Python,27 Node,23 observer,2 HUD,51 managed entry points and36 GPU render
receipts, zero Vulkan validation errors. The full GPU suite was not repeated for
these Python/collector fixes. Independent security audit closes22/22 planned
threats. Current fresh checkpoint is `dist/fidelity/phase01` (11,001 immutable
entries); exact current manifest/READY identities are recorded locally in
`artifacts/fidelity/verification/01-07-final-checkpoint.json`. Earlier bundle
history is preserved locally. All120 actual original/native acceptance obligations
and ten named human findings remainOPEN. Final phase verification is pending.
## Phase 1 final preparation — human session pending
- [x] Strict ready/audit tools:23 acceptance checks and24 checkpoint checks pass.
- [x] Fresh11,000-file offline bundle and actual failed Linux diagnostic import.
- [x] Strict audit rejects acceptance:0/120 obligations; all named human findings pending.
- [x] Integrate positive-count fidelity Python/Node/managed observer checks into runner.
- [x] Complete local suite: exit 0 in 782.05s; 556 Python (180 fidelity),
27 Node, 23 observer, 2 separate HUD Python tests, 51 managed test entry points,
main build, 36 GPU rendered receipts, 17 material/readback assertions,
SDL dummy-audio checks and 539 unchanged originals. No window-session claim.
- [ ] Actual original-DxWnd40/native Windows40/native Linux40 capture obligations.
- [ ] Single combined physical/audible/browser review, A1/A2, both unclassified
assumptions and P1/P2/P3 judgments; post-return agent-owned reconciliation.
- [ ] Phase1/EVID-02/EVID-04 acceptance; retain all EVID requirements Pending.
Full-suite receipt: `artifacts/fidelity/01-07-full-suite.json`; final local bundle:
`dist/fidelity/phase01`. See [complete checklist](evidence/checkpoint-session.md).
The roadmap's independent source-backed recovery exception does not waive these
acceptance dependencies or broaden gameplay admission.
## Phase 1 plan 01-06 — reviewed completion ## Phase 1 plan 01-06 — reviewed completion
- [x] Linux collector and23 targeted checks, full40-obligation open matrix. - [x] Linux collector and23 targeted checks, full40-obligation open matrix.
+22 -1
View File
@@ -333,12 +333,28 @@ function Complete-FidelityRun {
$null = Test-FidelityId $SessionId $null = Test-FidelityId $SessionId
$run = Get-FidelityPath $Bundle ('results/' + $SessionId) $run = Get-FidelityPath $Bundle ('results/' + $SessionId)
$null = Test-FidelityBundle $Bundle $null = Test-FidelityBundle $Bundle
$receipt = Read-FidelityJson (Join-Path $run 'run.json') $runPath = Join-Path $run 'run.json'
$recovering = -not (Test-Path -LiteralPath $runPath)
if ($recovering) {
if ($Outcome -ne 'aborted') { throw 'Interrupted initial record can only be finalized as aborted' }
$runPath = Join-Path $run 'incomplete.json'
}
$receipt = Read-FidelityJson $runPath
if ($recovering) {
if ($receipt.status -ne 'incomplete' -or $receipt.session_id -cne $SessionId) { throw 'Interrupted initial record does not match the incomplete session' }
# Initial records from older collectors contain placeholder end values.
# Neither those placeholders nor recovery time observed the process end.
$receipt.clocks.PSObject.Properties.Remove('wall_end')
$receipt.clocks.PSObject.Properties.Remove('monotonic_end')
$receipt.missing_evidence += 'Interrupted collector: end clocks and launch-aligned observations unavailable'
$receipt | Add-Member -Force -NotePropertyName diagnostic -NotePropertyValue $true
}
if (Test-Path -LiteralPath (Join-Path $run 'receipt.json')) { throw 'Result already finalized; preserve it and use a new result ID' } if (Test-Path -LiteralPath (Join-Path $run 'receipt.json')) { throw 'Result already finalized; preserve it and use a new result ID' }
if (-not $AnnotationPath -or -not $ArtifactsDirectory) { throw 'Finish requires actual annotations and a local artifact directory' } if (-not $AnnotationPath -or -not $ArtifactsDirectory) { throw 'Finish requires actual annotations and a local artifact directory' }
$annotation = Read-FidelityJson $AnnotationPath $annotation = Read-FidelityJson $AnnotationPath
$requested = Get-FidelityOutcome $receipt.status $Outcome $Reason $requested = Get-FidelityOutcome $receipt.status $Outcome $Reason
if ($annotation.schema_version -ne 1) { throw 'Unsupported annotation schema' } if ($annotation.schema_version -ne 1) { throw 'Unsupported annotation schema' }
if ($recovering -and @($annotation.events).Count) { throw 'Interrupted run has no observed end interval; retain annotations without launch-aligned events' }
if (@($annotation.artifacts).Count -gt 10000) { throw 'Too many artifacts' } if (@($annotation.artifacts).Count -gt 10000) { throw 'Too many artifacts' }
$names = @{} $names = @{}
foreach ($file in $annotation.artifacts) { foreach ($file in $annotation.artifacts) {
@@ -366,6 +382,11 @@ function Complete-FidelityRun {
} }
} }
$receipt.artifacts = @() $receipt.artifacts = @()
if ($recovering) {
$initial = Copy-FidelityEvidence $runPath $run 'recovery-initial.json'
$initial.role = 'diagnostic'
$receipt.artifacts += $initial
}
foreach ($file in $annotation.artifacts) { foreach ($file in $annotation.artifacts) {
$source = Get-FidelityPath $ArtifactsDirectory $file.path $source = Get-FidelityPath $ArtifactsDirectory $file.path
$id = Copy-FidelityEvidence $source $run ('media/' + $file.path) $id = Copy-FidelityEvidence $source $run ('media/' + $file.path)
+38 -1
View File
@@ -1,7 +1,43 @@
#!/usr/bin/env bash #!/usr/bin/env bash
set -euo pipefail set -euo pipefail
source "$(dirname "$0")/env.sh" source "$(dirname "$0")/env.sh"
python3 -m unittest discover -s tests -p 'test_*.py' -v suite_started=$SECONDS
mkdir -p artifacts/fidelity
python3 - <<'PY'
import sys
import unittest
suite = unittest.defaultTestLoader.discover('tests', pattern='test_*.py')
def cases(node):
for item in node:
if isinstance(item, unittest.TestSuite):
yield from cases(item)
else:
yield item
counts = {}
for case in cases(suite):
module = case.id().split('.')[0]
if module.startswith('test_fidelity_'):
counts[module] = counts.get(module, 0) + 1
required = ('sessions', 'scenarios', 'review', 'ledger', 'observation',
'checkpoint', 'capture', 'acceptance')
assert all(counts.get('test_fidelity_' + name, 0) > 0 for name in required), counts
print('Fidelity Python checks:', sum(counts.values()), counts, flush=True)
sys.exit(not unittest.TextTestRunner(verbosity=2).run(suite).wasSuccessful())
PY
node --test --test-reporter=tap tests/fidelity-viewer.test.mjs | tee artifacts/fidelity/consolidated-viewer.log
python3 - <<'PY'
import re
from pathlib import Path
text = Path('artifacts/fidelity/consolidated-viewer.log').read_text()
assert re.search(r'^# tests [1-9][0-9]*$', text, re.M), 'zero/missing viewer checks'
PY
dotnet run --project tests/GamePort.FidelityObservationTests | tee artifacts/fidelity/consolidated-observer.log
python3 - <<'PY'
import re
from pathlib import Path
text = Path('artifacts/fidelity/consolidated-observer.log').read_text()
assert re.search(r'Fidelity observation checks: [1-9][0-9]* passed', text), 'zero/missing observer checks'
PY
python3 tools/extractors/prepare.py --all-scenes --audio sounds musicsecretlab python3 tools/extractors/prepare.py --all-scenes --audio sounds musicsecretlab
dotnet run --project tests/GamePort.DataTests -- ../Original dotnet run --project tests/GamePort.DataTests -- ../Original
dotnet run --project tests/GamePort.CollisionTests -- ../Original dotnet run --project tests/GamePort.CollisionTests -- ../Original
@@ -118,3 +154,4 @@ if [[ "${NEUTRON_WINDOW_TEST:-0}" == 1 ]]; then
dotnet run --no-build -- --scene artifacts/extracted/level1b/scene.json --smoke-window --frames 6 --screenshot artifacts/test-window.ppm dotnet run --no-build -- --scene artifacts/extracted/level1b/scene.json --smoke-window --frames 6 --screenshot artifacts/test-window.ppm
dotnet run --no-build -- --smoke-walk --screenshot artifacts/test-walk-window.ppm dotnet run --no-build -- --smoke-walk --screenshot artifacts/test-walk-window.ppm
fi fi
printf 'Complete local suite passed in %s seconds; fidelity Python/Node/observer counts verified positive.\n' "$((SECONDS - suite_started))"
+31
View File
@@ -177,6 +177,37 @@ try {
Assert-True ($saved.status -eq $state -and $saved.artifacts.Count -eq 1 -and $saved.events -is [array] -and $saved.events.Count -eq 0 -and $saved.acceptance.state -eq 'open') 'Terminal fixture changed' Assert-True ($saved.status -eq $state -and $saved.artifacts.Count -eq 1 -and $saved.events -is [array] -and $saved.events.Count -eq 0 -and $saved.acceptance.state -eq 'open') 'Terminal fixture changed'
} }
} }
Check 'incomplete-only interrupted recovery preserves launch bytes and absent end clocks' {
$script:SessionId = 'fixture-interrupted'
$interruptedRun = Join-Path $bundleRoot ('results/' + $SessionId)
$null = [IO.Directory]::CreateDirectory($interruptedRun)
$initial = New-FidelityReceipt $SessionId 'fresh-natural-ordinary' 'continuous' 'synthetic' 'incomplete' @{os='test';execution='synthetic'} $clock 'Interrupted synthetic collector'
Write-FidelityJson (Join-Path $interruptedRun 'incomplete.json') $initial
$before = Get-FidelityIdentity (Join-Path $interruptedRun 'incomplete.json')
$script:AnnotationPath = Join-Path $temporary 'interrupted-notes.json'
Write-FidelityJson $AnnotationPath @{schema_version=1;artifacts=@(@{path='raw.mkv';role='video';duration_seconds=2});events=@();derivatives=@();limitations=@('Recovered synthetic media only')}
$script:Reason = 'Interrupted before final collector state'
$script:Outcome = 'captured'
Assert-Throws { Complete-FidelityRun }
Assert-True (-not (Test-Path -LiteralPath (Join-Path $interruptedRun 'receipt.json'))) 'Interrupted record promoted'
$script:Outcome = 'aborted'
[IO.File]::Delete($AnnotationPath)
Write-FidelityJson $AnnotationPath @{schema_version=1;artifacts=@();events=@(@{name='invented';artifact='raw.mkv';elapsed_seconds=1});derivatives=@();limitations=@()}
Assert-Throws { Complete-FidelityRun }
Assert-True (-not (Test-Path -LiteralPath (Join-Path $interruptedRun 'recovery-initial.json'))) 'Invalid recovery wrote evidence'
[IO.File]::Delete($AnnotationPath)
Write-FidelityJson $AnnotationPath @{schema_version=1;artifacts=@(@{path='raw.mkv';role='video';duration_seconds=2});events=@();derivatives=@();limitations=@('Recovered synthetic media only')}
Complete-FidelityRun
$saved = Read-FidelityJson (Join-Path $interruptedRun 'receipt.json')
Assert-True ($saved.status -eq 'aborted' -and $saved.acceptance.state -eq 'open' -and $saved.session_id -ceq $SessionId) 'Recovery changed launch/status'
Assert-True ($saved.clocks.PSObject.Properties.Name -notcontains 'wall_end' -and $saved.clocks.PSObject.Properties.Name -notcontains 'monotonic_end') 'Recovery invented end clocks'
$rawInitial = Read-FidelityJson (Join-Path $interruptedRun 'incomplete.json')
Assert-True ($saved.clocks.wall_start -eq $rawInitial.clocks.wall_start -and $saved.clocks.monotonic_start -eq $rawInitial.clocks.monotonic_start) 'Recovery changed initial clocks'
Assert-True ((Get-FidelityIdentity (Join-Path $interruptedRun 'incomplete.json')).sha256 -eq $before.sha256) 'Recovery changed raw initial bytes'
Assert-True ($saved.artifacts[0].path -eq 'recovery-initial.json' -and $saved.artifacts[0].sha256 -eq $before.sha256) 'Missing raw initial identity'
Assert-True (Test-Path -LiteralPath (Join-Path $interruptedRun 'media/raw.mkv')) 'Missing recovered media'
Assert-Throws { Complete-FidelityRun }
}
if ($FixtureOutput) { if ($FixtureOutput) {
if (Test-Path -LiteralPath $FixtureOutput) { throw 'Fixture output must be new' } if (Test-Path -LiteralPath $FixtureOutput) { throw 'Fixture output must be new' }
$null = [IO.Directory]::CreateDirectory($FixtureOutput) $null = [IO.Directory]::CreateDirectory($FixtureOutput)
+323
View File
@@ -0,0 +1,323 @@
"""Acceptance metadata doubles are synthetic tests, never runtime proof."""
import copy
import hashlib
import importlib
import json
from pathlib import Path
import subprocess
import sys
import unittest
from unittest import mock
import test_fidelity_scenarios
import test_fidelity_checkpoint
ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(ROOT / 'tools/recon'))
import fidelity_receipts as receipts
from fidelity_review import export_review
try:
acceptance = importlib.import_module('fidelity_acceptance')
except ModuleNotFoundError:
acceptance = None
class AcceptanceTests(unittest.TestCase):
def setUp(self):
self.fixture = test_fidelity_scenarios.FidelityScenarios()
self.fixture.setUp()
self.addCleanup(self.fixture.doCleanups)
self.root = self.fixture.base
self.protocol = self.fixture.protocol()
self.record, self.record_root = self.fixture.receipt()
identity = self.record['identity']
self.package = {'executable': identity['executable'],
'build_info': identity['source'],
'resources': {'assets': {'tree_sha256': 'a' * 64}}}
self.package['build'] = {'source': {k: identity['source'][k]
for k in ('commit', 'dirty', 'diff_sha256')}}
# Bind real hashed metadata files in the test instead of accepting labels.
self.original_files = [dict(path='Neutron.exe', **receipts.identify_file(self.record_root / 'setup.txt'))]
self.original_inventory = {'files': self.original_files,
'tree_sha256': hashlib.sha256(receipts.canonical_bytes(self.original_files)).hexdigest()}
for key, data in [('original_pre', self.original_inventory),
('original_post', self.original_inventory),
('original-package', self.original_inventory),
('original-resources', self.original_inventory),
('package', {'source': self.package['build']['source']}),
('resources', self.package['resources'])]:
path = self.record_root / (key + '.json')
path.write_bytes(receipts.canonical_bytes(data))
identity[key] = dict(receipts.identify_file(path), path=path.name)
self.package['seal'] = identity['package']
self.manifest = {'tooling_only': False, 'packages': {
'linux-x64': self.package, 'win-x64': self.package},
'original_pre': {'tree_sha256': self.original_inventory['tree_sha256'], 'count': 1}}
self.review = {'schema_version': 1,
'checks': {key: {'observed': True, 'reviewer': 'metadata test',
'notes': 'Synthetic unit assertion only'} for key in
('A1', 'A2', 'EVID-02-unclassified', 'EVID-04-unclassified',
'P1', 'P2', 'P3', 'browser', 'paired_review', 'physical_input')},
'receipt_ids': [self.record['receipt_id']]}
def api(self):
self.assertIsNotNone(acceptance, 'strict readiness/acceptance API must exist')
return acceptance
def audit(self, records=None, review=None):
return self.api().audit_records(self.protocol, self.manifest,
[(self.record, self.record_root)] if records is None else records,
self.review if review is None else review, self.original_inventory)
def original_record(self):
value = copy.deepcopy(self.record)
value['evidence_kind'] = 'original_dxwnd'
value['platform'].update(os='windows', execution='dxwnd')
value['identity']['executable']['original_member'] = 'Neutron.exe'
for key in ('package', 'resources'):
value['identity'][key] = value['identity']['original-' + key]
return value
def test_empty_matrix_never_passes(self):
report = self.audit([])
self.assertEqual(report['acceptance'], 'human_needed')
self.assertEqual(len(report['matrix']['missing_obligations']), 120)
def test_identified_valid_cell_covers_only_one_slot(self):
self.assertEqual(self.audit()['matrix']['accepted'], 1)
self.assertEqual(self.audit()['acceptance'], 'human_needed')
def test_complete_metadata_matrix_with_human_findings(self):
records = []
for cell in self.protocol['cells']:
for obligation in cell['obligations']:
for kind, os_name in [('native_port', 'linux'), ('native_port', 'windows'),
('original_dxwnd', 'windows')]:
value, root = self.fixture.receipt(cell['id'], obligation, kind, os_name)
value['identity'] = copy.deepcopy(self.record['identity'])
value['continuity']['copy_pre_sha256'] = value['identity']['copy_pre']['sha256']
value['continuity']['retained_copy_sha256'] = value['identity']['retained_copy']['sha256']
if kind == 'original_dxwnd':
value['identity'] = self.original_record()['identity']
for path in self.record_root.iterdir():
if path.is_file() and root != self.record_root:
(root / path.name).write_bytes(path.read_bytes())
records.append((value, root))
review = copy.deepcopy(self.review)
review['receipt_ids'] = [r['receipt_id'] for r, _ in records]
self.assertEqual(self.audit(records, review)['acceptance'], 'passed')
def test_original_executable_must_match_named_pristine_member(self):
value = self.original_record()
self.assertEqual(self.audit([(value, self.record_root)])['matrix']['accepted'], 1)
wrong = self.record_root / 'wrong.exe'
wrong.write_bytes(b'synthetic wrong original executable')
value['identity']['executable'] = dict(receipts.identify_file(wrong), path=wrong.name,
original_member='Neutron.exe')
self.assertEqual(self.audit([(value, self.record_root)])['matrix']['accepted'], 0)
value = self.original_record()
value['identity']['executable']['original_member'] = 'unselected.exe'
self.assertEqual(self.audit([(value, self.record_root)])['matrix']['accepted'], 0)
def test_original_inventories_require_actual_files_and_digest(self):
for key in ('original_pre', 'original_post', 'package', 'resources'):
with self.subTest(key=key):
value = self.original_record()
path = self.record_root / ('altered-' + key + '.json')
forged = copy.deepcopy(self.original_inventory)
forged['files'][0]['sha256'] = 'f' * 64
path.write_bytes(receipts.canonical_bytes(forged))
value['identity'][key] = dict(receipts.identify_file(path), path=path.name)
self.assertEqual(self.audit([(value, self.record_root)])['matrix']['accepted'], 0)
def test_generated_copy_changes_are_separate_from_original_preservation(self):
value = self.original_record()
path = self.record_root / 'changed-copy.json'
path.write_bytes(receipts.canonical_bytes({'files': [], 'generated_change': True}))
value['identity']['copy_post'] = dict(receipts.identify_file(path), path=path.name)
self.assertEqual(self.audit([(value, self.record_root)])['matrix']['accepted'], 1)
def test_aborted_case_stays_open(self):
self.record['status'] = 'aborted'
self.record['acceptance'] = {'state': 'open', 'remaining': ['aborted']}
self.assertEqual(self.audit()['matrix']['accepted'], 0)
def test_wine_label_cannot_fill_native(self):
self.record['platform']['execution'] = 'wine'
self.assertEqual(self.audit()['matrix']['accepted'], 0)
def test_wrong_package_rejected(self):
self.package['seal'] = {'sha256': '0' * 64}
self.assertTrue(self.audit()['errors'])
def test_wrong_resource_tree_rejected(self):
self.package['resources']['assets']['tree_sha256'] = '0' * 64
self.assertTrue(self.audit()['errors'])
def test_windows_seal_source_and_resource_format_is_supported(self):
source = self.record['identity']['source']
self.record['identity']['source'] = dict(self.record['identity']['package'],
**{k: source[k] for k in ('commit', 'dirty', 'diff_sha256')})
self.record['identity']['resources'] = self.record['identity']['package']
self.package['build']['source']['status_sha256'] = 'not copied into receipt'
path = self.record_root / 'package.json'
path.write_bytes(receipts.canonical_bytes({'source': self.package['build']['source']}))
updated = dict(receipts.identify_file(path), path=path.name)
self.package['seal'] = updated
for key in ('package', 'resources', 'source'):
self.record['identity'][key].update(updated)
self.assertEqual(self.audit()['matrix']['accepted'], 1)
def test_mismatched_source_revision_rejected(self):
self.record['identity']['source']['commit'] = 'wrong revision'
self.assertTrue(self.audit()['errors'])
def test_synthetic_original_rejected(self):
self.record['artifacts'][0]['synthetic'] = True
self.assertEqual(self.audit()['matrix']['accepted'], 0)
def test_absent_visible_audible_reviews_rejected(self):
self.record['review']['audible'] = False
self.assertEqual(self.audit()['matrix']['accepted'], 0)
def test_physical_input_disposition_required(self):
del self.review['checks']['physical_input']
self.assertIn('physical_input', self.audit()['human_needed'])
def test_duplicate_history_conflict_rejected(self):
self.assertTrue(self.audit([(self.record, self.record_root)] * 2)['errors'])
def test_historical_receipt_cannot_be_current(self):
self.record['historical'] = True
self.assertEqual(self.audit()['matrix']['accepted'], 0)
def test_both_unclassified_assumptions_stay_visible(self):
for key in ('EVID-02-unclassified', 'EVID-04-unclassified'):
self.review['checks'][key]['observed'] = False
self.assertTrue(set(('EVID-02-unclassified', 'EVID-04-unclassified')) <=
set(self.audit()['human_needed']))
def test_backstops_and_prohibitions_cannot_be_auto_dismissed(self):
self.assertTrue(set(('A1', 'A2', 'P1', 'P2', 'P3')) <=
set(self.audit(review={})['human_needed']))
def test_review_must_bind_actual_receipt_ids(self):
self.review['receipt_ids'] = ['different']
self.assertTrue(self.audit()['errors'])
def test_review_digest_binds_selected_filename_without_sidecar(self):
checkpoint = self.root / 'checkpoint'
(checkpoint / 'protocol').mkdir(parents=True)
(checkpoint / 'manifest.json').write_bytes(receipts.canonical_bytes(
dict(self.manifest, packages={})))
(checkpoint / 'protocol/scenarios.json').write_bytes(receipts.canonical_bytes(self.protocol))
(checkpoint / 'protocol/original-manifest.json').write_bytes(receipts.canonical_bytes(self.original_inventory))
selected = self.record_root / 'selected.json'
selected.write_bytes(receipts.canonical_bytes(self.record))
sibling = self.record_root / 'receipt.json'
sibling.write_text('{"unrelated": true}')
(self.root / 'current.json').write_bytes(receipts.canonical_bytes(
{'receipts': [selected.relative_to(self.root).as_posix()]}))
for reviewed, expected_pending in ((sibling, True), (None, True), (selected, False)):
review = dict(self.review, receipt_sha256={} if reviewed is None else {
self.record['receipt_id']: receipts.identify_file(reviewed)['sha256']})
(self.root / 'human-review.json').write_bytes(receipts.canonical_bytes(review))
with mock.patch.object(self.api(), 'ready'), mock.patch.object(self.api(), '_bind'):
report = self.api().audit(checkpoint, self.root)
self.assertEqual(bool(report['human_needed']), expected_pending)
self.assertEqual(report['matrix']['accepted'], 1)
def test_actual_failed_linux_receipt_import_and_review_remains_open(self):
source = ROOT / 'artifacts/fidelity/linux-current-receipts/linux-01-06-matrix-preflight-linux'
if not source.exists():
self.assertTrue(self.audit([])['matrix']['missing_obligations'])
return # Local ignored evidence is not a prerequisite on other checkouts.
imported = receipts.import_receipt(source / 'receipt.json', source, self.root / 'imports')
path = Path(imported['path'])
value = receipts.read_receipt(path)
report = self.audit([(value, path.parent)], {})
self.assertEqual(report['matrix']['accepted'], 0)
self.assertEqual(report['acceptance'], 'human_needed')
export_review(None, path, self.root / 'review')
self.assertTrue((self.root / 'review/index.html').is_file())
def test_cli_strict_nonzero_and_allow_open_explicit(self):
api = self.api()
report = self.audit([])
with mock.patch.object(api, 'audit', return_value=report):
self.assertEqual(api.main(['audit', '--checkpoint', str(self.root),
'--results', str(self.root), '--require-complete']), 1)
self.assertEqual(api.main(['audit', '--checkpoint', str(self.root),
'--results', str(self.root), '--allow-open']), 0)
def test_ready_cannot_accept_old_incomplete_material_set(self):
with mock.patch.object(self.api(), 'preflight', return_value={'status': 'ready'}):
with self.assertRaises((ValueError, FileNotFoundError)):
self.api().ready(self.root)
def prepared(self):
fixture = test_fidelity_checkpoint.FidelityCheckpoint()
fixture.setUp()
self.addCleanup(fixture.doCleanups)
fixture.prepare()
root = fixture.output
manifest = receipts.read_json(root / 'manifest.json')
manifest['tooling_only'] = False
(root / 'manifest.json').write_bytes(receipts.canonical_bytes(manifest))
prepared = receipts.read_json(root / 'READY.json')
prepared['manifest'] = dict(receipts.identify_file(root / 'manifest.json'), path='manifest.json')
(root / 'READY.json').write_bytes(receipts.canonical_bytes(prepared))
return root, manifest
def test_ready_validates_all_materials_separately_from_acceptance(self):
root, manifest = self.prepared()
with mock.patch.object(self.api(), '_package', side_effect=lambda _, rid, __: manifest['packages'][rid]):
report = self.api().ready(root)
self.assertTrue(report['materials_ready'])
self.assertEqual(report['acceptance'], 'human_needed')
def test_standalone_transferred_ready_needs_no_source_git_checkout(self):
root, manifest = self.prepared()
self.assertFalse((root / '.git').exists())
with mock.patch.object(self.api(), 'PROJECT', root), mock.patch.object(
self.api(), '_package', side_effect=lambda _, rid, __: manifest['packages'][rid]), \
mock.patch('fidelity_ledger._tracked', side_effect=AssertionError('No source Git on recipient')):
report = self.api().ready(root)
self.assertTrue(report['materials_ready'])
self.assertEqual(report['acceptance'], 'human_needed')
def test_ready_rejects_tampered_final_checklist(self):
root, _ = self.prepared()
(root / 'docs/evidence/checkpoint-session.md').write_text('changed')
with self.assertRaises(ValueError):
self.api().ready(root)
def test_ready_rejects_sealed_viewer_missing_history_projection(self):
root, manifest = self.prepared()
viewer = root / 'review/review.json'
data = receipts.read_json(viewer)
del data['ledger']['capabilities'][0]['history']
viewer.write_bytes(receipts.canonical_bytes(data))
manifest['files'] = [dict(entry, **receipts.identify_file(viewer))
if entry['path'] == 'review/review.json' else entry for entry in manifest['files']]
(root / 'manifest.json').write_bytes(receipts.canonical_bytes(manifest))
seal = receipts.read_json(root / 'READY.json')
seal['manifest'] = dict(path='manifest.json', **receipts.identify_file(root / 'manifest.json'))
(root / 'READY.json').write_bytes(receipts.canonical_bytes(seal))
with mock.patch.object(self.api(), '_package', side_effect=lambda _, rid, __: manifest['packages'][rid]):
with self.assertRaisesRegex(ValueError, 'viewer ledger projection'):
self.api().ready(root)
def test_audit_explicit_selection_reads_actual_failed_linux_hashes(self):
root, manifest = self.prepared()
source = ROOT / 'artifacts/fidelity/linux-current-receipts/linux-01-06-matrix-preflight-linux'
paths = []
if source.exists():
imported = receipts.import_receipt(source / 'receipt.json', source, root / 'results/imported')
paths.append(Path(imported['path']).relative_to(root / 'results').as_posix())
(root / 'results/current.json').write_bytes(receipts.canonical_bytes({'receipts': paths}))
with mock.patch.object(self.api(), '_package', side_effect=lambda _, rid, __: manifest['packages'][rid]):
report = self.api().audit(root, root / 'results')
self.assertEqual(report['acceptance'], 'human_needed')
self.assertEqual(report['matrix']['accepted'], 0)
+2 -2
View File
@@ -247,9 +247,9 @@ class CaptureTests(unittest.TestCase):
receipt = self.api().collect(self.run, probe=self.probe, annotations=note) receipt = self.api().collect(self.run, probe=self.probe, annotations=note)
protocol = receipts.read_json(ROOT / 'docs/evidence/scenarios.json') protocol = receipts.read_json(ROOT / 'docs/evidence/scenarios.json')
cell = next(c for c in protocol['cells'] if c['id'] == receipt['case_id']) cell = next(c for c in protocol['cells'] if c['id'] == receipt['case_id'])
receipts._scenario_observation(protocol, cell, receipt) receipts._scenario_observation(protocol, cell, receipt, self.run)
receipt['continuity']['return_session_id'] = 'other-process' receipt['continuity']['return_session_id'] = 'other-process'
with self.assertRaises(ValueError): receipts._scenario_observation(protocol, cell, receipt) with self.assertRaises(ValueError): receipts._scenario_observation(protocol, cell, receipt, self.run)
self.assertEqual(receipt['acceptance']['state'], 'open') self.assertEqual(receipt['acceptance']['state'], 'open')
def test_annotated_prerequisite_cannot_escape_capture_root(self): def test_annotated_prerequisite_cannot_escape_capture_root(self):
+50 -1
View File
@@ -76,6 +76,24 @@ class FidelityCheckpoint(unittest.TestCase):
self.assertEqual(receipts.identify_tree(self.original)['files'], self.assertEqual(receipts.identify_tree(self.original)['files'],
receipts.read_json(self.manifest)['files']) receipts.read_json(self.manifest)['files'])
def test_bundled_python_commands_preserve_immutable_tree(self):
self.prepare()
before = receipts.identify_tree(self.output)
for name in ('fidelity_acceptance', 'fidelity_checkpoint', 'fidelity_capture',
'fidelity_review', 'fidelity_ledger'):
result = subprocess.run(
[sys.executable, '-E', 'tools/recon/' + name + '.py', '--help'],
cwd=self.output, capture_output=True, text=True, timeout=20)
self.assertEqual(result.returncode, 0, result.stderr)
self.assertFalse(list((self.output / 'tools/recon').rglob('*.pyc')), name)
for _ in range(2):
result = subprocess.run(
[sys.executable, '-E', 'tools/recon/fidelity_checkpoint.py',
'preflight', '--checkpoint', '.'], cwd=self.output,
capture_output=True, text=True, timeout=20)
self.assertEqual(result.returncode, 0, result.stderr)
self.assertEqual(receipts.identify_tree(self.output), before)
def test_actual_package_and_resource_bytes_identified(self): def test_actual_package_and_resource_bytes_identified(self):
self.prepare() self.prepare()
manifest = receipts.read_json(self.output / 'manifest.json') manifest = receipts.read_json(self.output / 'manifest.json')
@@ -85,6 +103,37 @@ class FidelityCheckpoint(unittest.TestCase):
self.assertEqual(manifest['packages'][rid]['resources']['assets']['tree_sha256'], self.assertEqual(manifest['packages'][rid]['resources']['assets']['tree_sha256'],
receipts.identify_tree(package / 'assets')['tree_sha256']) receipts.identify_tree(package / 'assets')['tree_sha256'])
def test_preparation_preserves_current_and_superseded_records_through_renderer(self):
self.prepare()
model = self.output / 'review/review.json'
row = next(row for row in receipts.read_json(model)['ledger']['capabilities']
if row['id'] == 'startup-order')
self.assertEqual(len(row['current']), 2)
self.assertEqual(len(row['history']), 2)
script = '''
import {readFileSync} from 'node:fs';
const api = await import(process.argv[1]);
const model = JSON.parse(readFileSync(process.argv[2]));
class Element {
constructor(text='') { this.textContent=text; this.children=[]; }
append(...items) { this.children.push(...items); }
replaceChildren(...items) { this.children=items; }
get text() { return this.textContent + this.children.map(x=>x.text??String(x)).join(' '); }
}
const doc={createElement:()=>new Element()};
const container=new Element(); container.ownerDocument=doc;
api.renderCapabilities(container, model.ledger);
process.stdout.write(container.text);
'''
# Render the actual assembled model with its bundled renderer, using only
# a DOM double. This proves fields reach the UI, not browser playback.
rendered = subprocess.run(['node', '--input-type=module', '-e', script,
(self.output / 'review/viewer.mjs').as_uri(), str(model)],
capture_output=True, text=True, timeout=15)
self.assertEqual(rendered.returncode, 0, rendered.stderr)
for record in row['current'] + row['history']:
self.assertIn(record['id'], rendered.stdout)
def test_original_change_rejected_before_output(self): def test_original_change_rejected_before_output(self):
(self.original / 'Jimmy Neutron.exe').write_bytes(b'changed') (self.original / 'Jimmy Neutron.exe').write_bytes(b'changed')
with self.assertRaises(ValueError): self.prepare() with self.assertRaises(ValueError): self.prepare()
@@ -164,7 +213,7 @@ class FidelityCheckpoint(unittest.TestCase):
def test_complete_session_materials_and_eighty_windows_obligations(self): def test_complete_session_materials_and_eighty_windows_obligations(self):
self.prepare() self.prepare()
for name in ('tests/fidelity-windows.Tests.ps1', 'docs/evidence/windows-session.md', for name in (*self.api().MATERIALS,
'protocol/annotation-template.json', 'protocol/settings-template.json'): 'protocol/annotation-template.json', 'protocol/settings-template.json'):
self.assertTrue((self.output / name).is_file(), 'complete session material missing: ' + name) self.assertTrue((self.output / name).is_file(), 'complete session material missing: ' + name)
agenda = receipts.read_json(self.output / 'protocol/agenda.json') agenda = receipts.read_json(self.output / 'protocol/agenda.json')
+61 -3
View File
@@ -89,8 +89,13 @@ class FidelityScenarios(unittest.TestCase):
duration_seconds=100)) duration_seconds=100))
identity = {} identity = {}
for key in ('executable', 'package', 'resources', 'launcher', 'source', 'original_pre', for key in ('executable', 'package', 'resources', 'launcher', 'source', 'original_pre',
'original_post', 'copy_pre', 'copy_post', 'dxwnd', 'dxwnd_config'): 'original_post', 'copy_pre', 'copy_post', 'retained_copy', 'dxwnd', 'dxwnd_config'):
identity[key] = dict(api.identify_file(d / 'setup.txt'), path='setup.txt') if key in ('copy_pre', 'retained_copy'):
path = d / (key + '.json')
path.write_text(json.dumps({'copy_state': key, 'session': d.name}))
else:
path = d / 'setup.txt'
identity[key] = dict(api.identify_file(path), path=path.name)
identity['source'].update(commit='a' * 40, dirty=False, diff_sha256='b' * 64) identity['source'].update(commit='a' * 40, dirty=False, diff_sha256='b' * 64)
required = api.required_events(p, c, obligation) required = api.required_events(p, c, obligation)
events = [dict(name=name, artifact='video.txt', media_seconds=index + 2, events = [dict(name=name, artifact='video.txt', media_seconds=index + 2,
@@ -117,7 +122,7 @@ class FidelityScenarios(unittest.TestCase):
'continuity': {'lifetime_id': d.name, 'departure_session_id': d.name, 'continuity': {'lifetime_id': d.name, 'departure_session_id': d.name,
'return_session_id': d.name, 'prerequisite_artifact': 'setup.txt', 'return_session_id': d.name, 'prerequisite_artifact': 'setup.txt',
'copy_pre_sha256': identity['copy_pre']['sha256'], 'copy_pre_sha256': identity['copy_pre']['sha256'],
'retained_copy_sha256': identity['copy_post']['sha256']}} 'retained_copy_sha256': identity['retained_copy']['sha256']}}
return value, d return value, d
def test_identified_metadata_cell_can_cover_one_obligation(self): def test_identified_metadata_cell_can_cover_one_obligation(self):
@@ -143,6 +148,41 @@ class FidelityScenarios(unittest.TestCase):
del value['continuity']['retained_copy_sha256'] del value['continuity']['retained_copy_sha256']
self.assertEqual(api.audit_scenarios(self.protocol(), [(value, root)])['accepted'], 0) self.assertEqual(api.audit_scenarios(self.protocol(), [(value, root)])['accepted'], 0)
def test_copy_continuity_requires_named_state_for_both_lifetimes(self):
for lifetime in ('fresh', 'retained'):
for digest in ('f' * 64, 'launcher', 'package'):
with self.subTest(lifetime=lifetime, digest=digest):
value, root = self.receipt(lifetime + '-natural-ordinary', 'dialogue-return')
self.assertEqual(api.audit_scenarios(self.protocol(), [(value, root)])['accepted'], 1)
value['continuity']['copy_pre_sha256'] = (
value['identity'][digest]['sha256'] if digest in value['identity'] else digest)
result = api.audit_scenarios(self.protocol(), [(value, root)])
self.assertEqual(result['accepted'], 0)
self.assertTrue(result['invalid'])
def test_retained_snapshot_cannot_bind_unrelated_identity(self):
for name in ('copy_pre', 'copy_post', 'launcher'):
value, root = self.receipt()
value['continuity']['retained_copy_sha256'] = value['identity'][name]['sha256']
self.assertEqual(api.audit_scenarios(self.protocol(), [(value, root)])['accepted'], 0)
def test_copy_state_requires_backing_files_for_both_lifetimes(self):
for lifetime in ('fresh', 'retained'):
for name in ('copy_pre', 'retained_copy') if lifetime == 'retained' else ('copy_pre',):
for defect in ('hash-only', 'missing-file', 'wrong-size'):
with self.subTest(lifetime=lifetime, name=name, defect=defect):
value, root = self.receipt(lifetime + '-natural-ordinary', 'dialogue-return')
item = value['identity'][name]
if defect == 'hash-only':
value['identity'][name] = {'sha256': item['sha256']}
elif defect == 'missing-file':
(root / item['path']).unlink()
else:
item['size'] += 1
result = api.audit_scenarios(self.protocol(), [(value, root)])
self.assertEqual(result['accepted'], 0)
self.assertTrue(result['invalid'])
def test_reset_timestamps_fail(self): def test_reset_timestamps_fail(self):
value, root = self.receipt() value, root = self.receipt()
value['events'][-1]['elapsed_seconds'] = 0 value['events'][-1]['elapsed_seconds'] = 0
@@ -170,6 +210,24 @@ class FidelityScenarios(unittest.TestCase):
value['acceptance'] = {'state': 'open', 'remaining': [status]} value['acceptance'] = {'state': 'open', 'remaining': [status]}
self.assertEqual(api.audit_scenarios(self.protocol(), [(value, root)])['accepted'], 0) self.assertEqual(api.audit_scenarios(self.protocol(), [(value, root)])['accepted'], 0)
def test_aborted_missing_end_clocks_imports_without_invented_observations(self):
value, root = self.receipt()
value['status'] = 'aborted'
value['acceptance'] = {'state': 'open', 'remaining': ['interrupted']}
value['events'] = []
for field in ('wall_end', 'monotonic_end'):
del value['clocks'][field]
(root / 'receipt.json').write_bytes(api.canonical_bytes(value))
imported = api.import_receipt(root / 'receipt.json', root, self.base / 'imports')
path = Path(imported['path'])
saved = api.read_receipt(path)
result = api.validate_receipt(saved, path.parent)
self.assertFalse(result['accepted'])
self.assertNotIn('wall_end', saved['clocks'])
self.assertNotIn('monotonic_end', saved['clocks'])
value['status'] = 'reviewed'
with self.assertRaises(ValueError): api.validate_receipt(value, root)
def test_missing_event_and_media_out_of_range_rejected(self): def test_missing_event_and_media_out_of_range_rejected(self):
value, root = self.receipt() value, root = self.receipt()
value['events'].pop() value['events'].pop()
+195
View File
@@ -0,0 +1,195 @@
#!/usr/bin/env python3
"""Offline checkpoint readiness and strict original/native acceptance.
Human findings are declarations bound to exact receipts, never inferred from
successful tools. --allow-open is structural inspection, not acceptance.
"""
import argparse
import hashlib
from pathlib import Path
import sys
# A bundled CLI must not create bytecode inside the sealed checkpoint.
if __name__ == '__main__':
sys.dont_write_bytecode = True
from fidelity_checkpoint import MATERIALS, PROJECT, _package, preflight
from fidelity_receipts import (audit_scenarios, canonical_bytes, contained_path,
identify_file, identify_tree, read_json, read_receipt, validate_receipt,
validate_scenario_contract)
CHECKS = ('A1', 'A2', 'EVID-02-unclassified', 'EVID-04-unclassified',
'P1', 'P2', 'P3', 'browser', 'paired_review', 'physical_input')
def ready(checkpoint):
root = Path(checkpoint)
checked = preflight(root)
manifest = read_json(root / 'manifest.json')
if manifest['tooling_only']:
raise ValueError('Synthetic checkpoint is tooling-only, not final materials')
names = {entry['path'] for entry in manifest['files']}
required = set(MATERIALS) | {'protocol/scenarios.json', 'protocol/capabilities.json',
'protocol/agenda.json', 'protocol/settings-template.json', 'protocol/capability-ledger.json',
'protocol/annotation-template.json', 'review/index.html', 'review/viewer.mjs',
'review/review.json'}
if required - names:
raise ValueError('Missing final session materials: ' + ', '.join(sorted(required - names)))
# A source checkout must not hand off an older tooling/checklist copy after
# later edits. On a transferred checkpoint PROJECT is the checkpoint itself.
for name in MATERIALS:
if identify_file(PROJECT / name) != identify_file(root / name):
raise ValueError('Final material differs from current source; assemble a fresh checkpoint: ' + name)
protocol = read_json(root / 'protocol/scenarios.json')
validate_scenario_contract(protocol)
for rid, identity in manifest['packages'].items():
if _package(root / 'port' / rid, rid, False) != identity:
raise ValueError('Package/observer identity inconsistent: ' + rid)
agenda = read_json(root / 'protocol/agenda.json')
expected = {(s, c['id'], o) for s in ('original-windows-dxwnd', 'port-windows-native')
for c in protocol['cells'] for o in c['obligations']}
actual = {(r['side'], r['case_id'], r['obligation_id']) for r in agenda['runs']}
if actual != expected or len(agenda['runs']) != 80:
raise ValueError('Incomplete or duplicate Windows session agenda')
# Exported ledger links are already normalized by the exporter. Recheck
# every active link against the sealed actual materials at final handoff.
ledger = read_json(root / 'review/review.json')['ledger']
expected_ledger = read_json(root / 'protocol/capability-ledger.json')
for field in ('current', 'history'):
if [(row['id'], row.get(field)) for row in ledger['capabilities']] != [
(row['id'], row[field]) for row in expected_ledger['capabilities']]:
raise ValueError('Malformed viewer ledger projection: ' + field)
for capability in ledger['capabilities']:
for link in capability.get('source_links', []):
if link.get('href'):
identify_file(contained_path(root / 'review', link['href']))
return {'schema_version': 1, 'materials_ready': checked['status'] == 'ready',
'checked_files': checked['checked_files'], 'acceptance': 'human_needed',
'required': 120, 'pending': list(CHECKS),
'meaning': 'Identified offline materials only; all execution/review remains separate'}
def _bind(receipt, root, manifest, original_inventory=None):
identity = receipt['identity']
if receipt['evidence_kind'] == 'native_port':
rid = {'linux': 'linux-x64', 'windows': 'win-x64'}[receipt['platform']['os']]
expected = manifest['packages'][rid]
if identity['executable']['sha256'] != expected['executable']['sha256']:
raise ValueError('Wrong current executable identity')
if identity['source']['sha256'] not in (expected['build_info']['sha256'], expected['seal']['sha256']):
raise ValueError('Wrong current source identity')
if any(identity['source'].get(k) != expected['build']['source'].get(k)
for k in ('commit', 'dirty', 'diff_sha256')):
raise ValueError('Wrong source revision/dirty/diff provenance')
package = read_json(contained_path(root, identity['package']['path']))
resources = read_json(contained_path(root, identity['resources']['path']))
if (package.get('source') != expected['build']['source'] or
identity['package']['sha256'] != expected['seal']['sha256']):
raise ValueError('Wrong current package seal/source')
if resources != expected['resources'] and identity['resources']['sha256'] != expected['seal']['sha256']:
raise ValueError('Wrong current resources')
elif receipt['evidence_kind'] == 'original_dxwnd':
files = (original_inventory or {}).get('files')
if not isinstance(files, list) or not files:
raise ValueError('Missing authoritative original file inventory')
digest = hashlib.sha256(canonical_bytes(files)).hexdigest()
if (digest != manifest['original_pre']['tree_sha256'] or
len(files) != manifest['original_pre']['count']):
raise ValueError('Wrong authoritative original inventory')
for key in ('original_pre', 'original_post', 'package', 'resources'):
inventory = read_json(contained_path(root, identity[key]['path']))
if inventory.get('files') != files or inventory.get('tree_sha256') != digest:
raise ValueError('Wrong authoritative original inventory: ' + key)
executable = identity['executable']
member = executable.get('original_member')
expected = next((item for item in files if item['path'] == member), None)
if not expected or any(executable.get(k) != expected[k] for k in ('sha256', 'size', 'header')):
raise ValueError('Wrong selected original executable member identity')
def audit_records(protocol, manifest, records, review, original_inventory=None):
errors, usable, seen = [], [], set()
if manifest.get('tooling_only'):
errors.append('Synthetic checkpoint cannot qualify as runtime evidence')
for receipt, root in records:
label = str(receipt.get('receipt_id', '<missing>'))
try:
if label in seen:
raise ValueError('Duplicate/conflicting receipt ID; retain history outside current selection')
seen.add(label)
valid = validate_receipt(receipt, root)
if receipt.get('superseded_by') or receipt.get('historical'):
raise ValueError('Superseded/historical receipt is not current applicability')
if valid['accepted']:
_bind(receipt, root, manifest, original_inventory)
usable.append((receipt, root))
except (KeyError, TypeError, ValueError, OSError) as error:
errors.append(label + ': ' + str(error))
matrix = audit_scenarios(protocol, usable)
errors.extend(matrix['invalid'])
checks = review.get('checks', {})
human_needed = [key for key in CHECKS if not (isinstance(checks.get(key), dict)
and checks[key].get('observed') is True and checks[key].get('reviewer')
and checks[key].get('notes'))]
if set(review.get('receipt_ids', [])) != seen:
errors.append('Human review must bind the exact selected receipt IDs')
passed = matrix['complete'] and not errors and not human_needed
return {'schema_version': 1, 'materials_ready': True,
'acceptance': 'passed' if passed else 'human_needed', 'matrix': matrix,
'errors': errors, 'human_needed': human_needed,
'meaning': 'Declared reviewed evidence; no automatic physical/audible truth or universal tolerance'}
def audit(checkpoint, results):
root, results = Path(checkpoint), Path(results)
ready(root)
manifest = read_json(root / 'manifest.json')
for rid, package in manifest['packages'].items():
package['seal'] = identify_file(root / 'port' / rid / 'fidelity-build.json')
# A strict, explicit selection prevents newest-date selection and preserves
# failed/superseded histories. The tree walk rejects symlinks/case aliases.
identify_tree(results)
selection = results / 'current.json'
paths = read_json(selection).get('receipts', []) if selection.exists() else []
if not isinstance(paths, list) or len(paths) > 120 or len(set(paths)) != len(paths):
raise ValueError('Current receipt selection must be a bounded unique array')
records, selected = [], []
for name in paths:
path = contained_path(results, name)
records.append((read_receipt(path), path.parent))
selected.append(path)
review_path = results / 'human-review.json'
review = read_json(review_path) if review_path.exists() else {}
# Bind review to actual receipt bytes, not just reusable labels.
for (receipt, _), path in zip(records, selected):
expected = review.get('receipt_sha256', {}).get(receipt['receipt_id'])
if expected != identify_file(path)['sha256']:
review = dict(review, checks={})
break
return audit_records(read_json(root / 'protocol/scenarios.json'), manifest, records, review,
read_json(root / 'protocol/original-manifest.json'))
def main(argv=None):
parser = argparse.ArgumentParser(description=__doc__)
sub = parser.add_subparsers(dest='command', required=True)
prepare = sub.add_parser('ready')
prepare.add_argument('--checkpoint', type=Path, required=True)
check = sub.add_parser('audit')
check.add_argument('--checkpoint', type=Path, required=True)
check.add_argument('--results', type=Path, required=True)
mode = check.add_mutually_exclusive_group(required=True)
mode.add_argument('--require-complete', action='store_true')
mode.add_argument('--allow-open', action='store_true')
args = parser.parse_args(argv)
try:
report = ready(args.checkpoint) if args.command == 'ready' else audit(args.checkpoint, args.results)
print(canonical_bytes(report).decode())
return 0 if args.command == 'ready' or args.allow_open or report['acceptance'] == 'passed' else 1
except (ValueError, OSError, KeyError, TypeError) as error:
print('Fidelity audit failed; acceptance OPEN: ' + str(error), file=sys.stderr)
return 2
if __name__ == '__main__':
sys.exit(main())
+6 -1
View File
@@ -17,9 +17,14 @@ import re
import shutil import shutil
import signal import signal
import subprocess import subprocess
import sys
import tempfile import tempfile
import time import time
# A bundled CLI must not create bytecode inside the sealed checkpoint.
if __name__ == '__main__':
sys.dont_write_bytecode = True
from fidelity_checkpoint import _package from fidelity_checkpoint import _package
from fidelity_receipts import (MAX_JSON_BYTES, _id, _write_json, canonical_bytes, from fidelity_receipts import (MAX_JSON_BYTES, _id, _write_json, canonical_bytes,
contained_path, identify_file, import_receipt, read_json, separated_roots, contained_path, identify_file, import_receipt, read_json, separated_roots,
@@ -387,7 +392,7 @@ def matrix(protocol, records=(), previous=None, dependency=None):
sessions[session_id] = record_id; seen[record_id] = digest sessions[session_id] = record_id; seen[record_id] = digest
reasons = list(validated['missing_evidence']) reasons = list(validated['missing_evidence'])
try: try:
_scenario_observation(protocol, cells[key[0]], receipt) _scenario_observation(protocol, cells[key[0]], receipt, root)
except (ValueError, KeyError, StopIteration) as error: except (ValueError, KeyError, StopIteration) as error:
reasons.append('Scenario continuity: ' + str(error)) reasons.append('Scenario continuity: ' + str(error))
if receipt['evidence_kind'] != 'native_port': if receipt['evidence_kind'] != 'native_port':
+22 -3
View File
@@ -14,20 +14,36 @@ import subprocess
import sys import sys
import uuid import uuid
# A bundled CLI must not create bytecode inside the sealed checkpoint.
if __name__ == '__main__':
sys.dont_write_bytecode = True
from fidelity_receipts import (canonical_bytes, contained_path, identify_file, from fidelity_receipts import (canonical_bytes, contained_path, identify_file,
identify_tree, read_json, relative_name, separated_roots, source_identity, identify_tree, read_json, relative_name, separated_roots, source_identity,
utc_now, validate_receipt, validate_scenario_contract, verify_inventory, utc_now, validate_receipt, validate_scenario_contract, verify_inventory,
_id, _write_json) _id, _write_json)
from fidelity_review import export_review from fidelity_review import export_review
from fidelity_ledger import export_ledger
PROJECT = Path(__file__).resolve().parents[2] PROJECT = Path(__file__).resolve().parents[2]
RIDS = ('linux-x64', 'win-x64') RIDS = ('linux-x64', 'win-x64')
FLAGS = ['--fidelity-output', '--fidelity-session', '--fidelity-case'] FLAGS = ['--fidelity-output', '--fidelity-session', '--fidelity-case']
MAX_FILE_BYTES = 8 * 1024**3 MAX_FILE_BYTES = 8 * 1024**3
MUTABLE = ('results', 'original-runs') MUTABLE = ('results', 'original-runs')
MATERIALS = ('scripts/collect-fidelity-windows.ps1', MATERIALS = ('scripts/collect-fidelity-linux.sh',
'scripts/collect-fidelity-windows.ps1',
'scripts/collect-fidelity-windows.cmd', 'scripts/collect-fidelity-windows.cmd',
'tests/fidelity-windows.Tests.ps1', 'docs/evidence/windows-session.md') 'tests/fidelity-windows.Tests.ps1', 'docs/evidence/windows-session.md',
'docs/evidence/linux-session.md', 'docs/evidence/checkpoint-session.md',
'docs/evidence/phase01-baseline.md', 'docs/evidence/scenarios.json',
'docs/evidence/capabilities.json', 'tests/test_fidelity_acceptance.py',
'tests/test_fidelity_scenarios.py',
'tools/recon/fidelity_acceptance.py', 'tools/recon/fidelity_checkpoint.py',
'tools/recon/fidelity_capture.py', 'tools/recon/fidelity_receipts.py',
'tools/recon/fidelity_review.py', 'tools/recon/fidelity_ledger.py',
'tools/recon/fidelity_viewer/index.html',
'tools/recon/fidelity_viewer/viewer.mjs',
'tools/recon/fidelity_viewer/style.css')
def _copy_file(source, target): def _copy_file(source, target):
@@ -153,7 +169,9 @@ def prepare_checkpoint(original, original_manifest, packages, output, tooling=Fa
_copy_file(original_manifest, temporary / 'protocol/original-manifest.json') _copy_file(original_manifest, temporary / 'protocol/original-manifest.json')
for name in ('scenarios.json', 'capabilities.json'): for name in ('scenarios.json', 'capabilities.json'):
_copy_file(PROJECT / 'docs/evidence' / name, temporary / 'protocol' / name) _copy_file(PROJECT / 'docs/evidence' / name, temporary / 'protocol' / name)
export_review(None, None, temporary / 'review', PROJECT / 'docs/evidence/capabilities.json') ledger = temporary / 'protocol/capability-ledger.json'
_write_json(ledger, export_ledger(read_json(PROJECT / 'docs/evidence/capabilities.json'), PROJECT))
export_review(None, None, temporary / 'review', ledger)
for name in MUTABLE: for name in MUTABLE:
(temporary / name).mkdir() (temporary / name).mkdir()
# All 80 Windows obligations are prepared; Linux's remaining40 use the same protocol. # All 80 Windows obligations are prepared; Linux's remaining40 use the same protocol.
@@ -185,6 +203,7 @@ def prepare_checkpoint(original, original_manifest, packages, output, tooling=Fa
(temporary / 'incomplete.json').unlink() (temporary / 'incomplete.json').unlink()
files = identify_tree(temporary)['files'] files = identify_tree(temporary)['files']
manifest = {'schema_version': 1, 'checkpoint_id': output.name, manifest = {'schema_version': 1, 'checkpoint_id': output.name,
'tool_source': source_identity(PROJECT),
'created_utc': utc_now(), 'tooling_only': tooling, 'packages': identities, 'created_utc': utc_now(), 'tooling_only': tooling, 'packages': identities,
'original_manifest': identify_file(original_manifest), 'original_manifest': identify_file(original_manifest),
'original_pre': {'tree_sha256': before['tree_sha256'], 'count': len(before['files'])}, 'original_pre': {'tree_sha256': before['tree_sha256'], 'count': len(before['files'])},
+4
View File
@@ -20,6 +20,10 @@ import subprocess
import sys import sys
from urllib.parse import quote from urllib.parse import quote
# A bundled CLI must not create bytecode inside the sealed checkpoint.
if __name__ == '__main__':
sys.dont_write_bytecode = True
from fidelity_receipts import (KINDS, MAX_JSON_BYTES, canonical_bytes, contained_path, from fidelity_receipts import (KINDS, MAX_JSON_BYTES, canonical_bytes, contained_path,
identify_file, read_json, validate_receipt) identify_file, read_json, validate_receipt)
+18 -9
View File
@@ -331,9 +331,15 @@ def validate_receipt(receipt, root):
if not isinstance(clocks, dict): if not isinstance(clocks, dict):
raise ValueError('Clocks must be an object') raise ValueError('Clocks must be an object')
start, end = clocks.get('monotonic_start'), clocks.get('monotonic_end') start, end = clocks.get('monotonic_start'), clocks.get('monotonic_end')
if not _finite(start) or not _finite(end) or start < 0 or end < start: missing_end = (status == 'aborted' and receipt.get('acceptance', {}).get('state') == 'open'
and end is None and clocks.get('wall_end') is None)
if not _finite(start) or start < 0 or (not missing_end and (not _finite(end) or end < start)):
raise ValueError('Invalid/reset monotonic clocks') raise ValueError('Invalid/reset monotonic clocks')
if missing_end and receipt['events']:
raise ValueError('Missing end clocks cannot bound launch-aligned event observations')
for key in ('wall_start', 'wall_end'): for key in ('wall_start', 'wall_end'):
if key == 'wall_end' and missing_end:
continue
try: try:
dt = datetime.fromisoformat(clocks[key].replace('Z', '+00:00')) dt = datetime.fromisoformat(clocks[key].replace('Z', '+00:00'))
if dt.tzinfo is None: if dt.tzinfo is None:
@@ -395,6 +401,8 @@ def validate_receipt(receipt, root):
if synthetic and kind != 'synthetic': if synthetic and kind != 'synthetic':
raise ValueError('Synthetic artifacts cannot be relabeled as runtime evidence') raise ValueError('Synthetic artifacts cannot be relabeled as runtime evidence')
missing = list(receipt['missing_evidence']) + list(acceptance['remaining']) missing = list(receipt['missing_evidence']) + list(acceptance['remaining'])
if missing_end:
missing.append('Interrupted collector end clocks unavailable')
if kind not in ('native_port', 'original_dxwnd'): if kind not in ('native_port', 'original_dxwnd'):
missing.append(kind + ' is not original/native gameplay acceptance') missing.append(kind + ' is not original/native gameplay acceptance')
if receipt['historical']: if receipt['historical']:
@@ -618,7 +626,7 @@ def required_events(protocol, cell, obligation_id):
return events return events
def _scenario_observation(protocol, cell, receipt): def _scenario_observation(protocol, cell, receipt, root):
obligation = receipt['obligation_id'] obligation = receipt['obligation_id']
if receipt.get('scope') != obligation: if receipt.get('scope') != obligation:
raise ValueError('Receipt scope must match its explicit obligation') raise ValueError('Receipt scope must match its explicit obligation')
@@ -656,17 +664,18 @@ def _scenario_observation(protocol, cell, receipt):
if continuity.get('prerequisite_artifact') not in { if continuity.get('prerequisite_artifact') not in {
a['path'] for a in receipt['artifacts'] if a.get('role') == 'prerequisite'}: a['path'] for a in receipt['artifacts'] if a.get('role') == 'prerequisite'}:
raise ValueError('Visible identified prerequisite setup required') raise ValueError('Visible identified prerequisite setup required')
if not re.fullmatch('[0-9a-f]{64}', continuity.get('copy_pre_sha256', '')): _checked_artifact(receipt['identity'].get('copy_pre'), root)
raise ValueError('Missing pristine copy/package session identity') if (not re.fullmatch('[0-9a-f]{64}', continuity.get('copy_pre_sha256', '')) or
continuity['copy_pre_sha256'] != receipt['identity'].get('copy_pre', {}).get('sha256')):
raise ValueError('Copy pre state must bind the actual named copy_pre identity record')
if cell['lifetime'] == 'retained': if cell['lifetime'] == 'retained':
_checked_artifact(receipt['identity'].get('retained_copy'), root)
if (continuity.get('departure_session_id') != receipt['session_id'] or if (continuity.get('departure_session_id') != receipt['session_id'] or
continuity.get('return_session_id') != receipt['session_id'] or continuity.get('return_session_id') != receipt['session_id'] or
not re.fullmatch('[0-9a-f]{64}', continuity.get('retained_copy_sha256', ''))): not re.fullmatch('[0-9a-f]{64}', continuity.get('retained_copy_sha256', ''))):
raise ValueError('Retained departure/return/copy must preserve the same session') raise ValueError('Retained departure/return/copy must preserve the same session')
identified = {item.get('sha256') for item in receipt['identity'].values() if isinstance(item, dict)} if continuity['retained_copy_sha256'] != receipt['identity'].get('retained_copy', {}).get('sha256'):
if (continuity['copy_pre_sha256'] not in identified or raise ValueError('Retained copy state must bind the actual named retained_copy identity record')
continuity['retained_copy_sha256'] not in identified):
raise ValueError('Retained copy state must bind actual hashed identity records')
prerequisite = [e for e in events if e['artifact'] == continuity['prerequisite_artifact']] prerequisite = [e for e in events if e['artifact'] == continuity['prerequisite_artifact']]
names = [e['name'] for e in prerequisite] names = [e['name'] for e in prerequisite]
if ('prerequisite_departure' not in names or 'prerequisite_return' not in names or if ('prerequisite_departure' not in names or 'prerequisite_return' not in names or
@@ -702,7 +711,7 @@ def audit_scenarios(protocol, records):
if not result['accepted']: if not result['accepted']:
open_receipts.append(label + ': ' + '; '.join(result['missing_evidence'])) open_receipts.append(label + ': ' + '; '.join(result['missing_evidence']))
continue continue
_scenario_observation(protocol, cells[case], receipt) _scenario_observation(protocol, cells[case], receipt, root)
if cells[case]['lifetime'] == 'fresh': if cells[case]['lifetime'] == 'fresh':
session_key = (receipt['evidence_kind'], receipt['platform']['os'], receipt['session_id']) session_key = (receipt['evidence_kind'], receipt['platform']['os'], receipt['session_id'])
if session_key in fresh_sessions: if session_key in fresh_sessions:
+5
View File
@@ -15,9 +15,14 @@ from pathlib import Path
import re import re
import shutil import shutil
import subprocess import subprocess
import sys
import tempfile import tempfile
from urllib.parse import quote, unquote, urlsplit from urllib.parse import quote, unquote, urlsplit
# A bundled CLI must not create bytecode inside the sealed checkpoint.
if __name__ == '__main__':
sys.dont_write_bytecode = True
from fidelity_receipts import (MAX_JSON_BYTES, canonical_bytes, contained_path, from fidelity_receipts import (MAX_JSON_BYTES, canonical_bytes, contained_path,
identify_file, read_json, read_receipt, separated_roots, identify_file, read_json, read_receipt, separated_roots,
validate_receipt) validate_receipt)