diff --git a/.gitignore b/.gitignore index 8eea6d0..4e4fe86 100644 --- a/.gitignore +++ b/.gitignore @@ -2,4 +2,5 @@ __pycache__/ .pytest_cache/ *.py[cod] *.safetensors +!tests/fixtures/v39_sampling_v5/**/*.safetensors *.tmp diff --git a/AGENTS.md b/AGENTS.md index 9bef51c..a708075 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -1,112 +1,42 @@ -# AGENTS.md - +# Contributor rules + ## Scope -MiniMax H3 Continuum for ComfyUI. Current `main` is package 3.9.0: it keeps V3.8X2 and adds a separate V3.9 Sampler and Reference Images V3.9 helper. This source publication is not a new GitHub Release or Registry publication. Treat the accepted V3.7 Production engine and V3.8 GPU Gates as protected execution baselines. Pre-V3.8 public Node IDs and saved workflows remain historical Release/tag contracts, not automatic V3.9 migrations. Experimental controls must not change Production behavior. Still Image Guide remains Experimental / Production HOLD. -Current release-hygiene baseline: O1 and AUDIO-R1 are PASS; the original V3.8 launch had seven IDs, V3.8X2 has ten including deprecated loader compatibility IDs, and V3.9 registers twelve in total. Sampling Contract v5, Run Storage v3, State, Session, Assembly, Driving Audio, and Second Pass/O1 remain protected. V3.9 browser/default-template GPU acceptance and Release / Registry readiness remain HOLD. - -## Non-negotiable rules -- Follow ComfyUI Core behavior for user-facing validation. Continuum-only prompt restrictions, model allowlists, compatibility gates, and policy-based execution stops are prohibited. -- Do not implement a new user-facing hard stop. If execution is structurally impossible or continuing risks corrupting stored data, document the exact broken internal contract and obtain explicit approval before changing the stop. -- Prompt content must never block execution. Empty, malformed, incomplete, or unknown prompt syntax falls back to a Fixed prompt and is passed through as entered. Valid Timeline/List/JSON syntax is still parsed normally. -- Keep warnings diagnostic-only unless execution cannot continue safely. Hard stops are limited to corrupt internal contracts such as invalid latent/layout topology, incompatible Assembly Plan data, broken stored revision schema/hash, unusable required payloads, or decode formats that cannot be assembled. -- Unknown upstream nodes, models, wrappers, or merged models must not be rejected solely because they are unknown. -- Keep legacy `strict_compatibility` inputs loadable for old workflows, but ignore their value. They must never enable blocking behavior. -- Before every change, run `tools\snapshot.ps1` against the authoritative source. Preserve the current V3.8 backend schema and serialized widget order until a separately approved UI/public-surface implementation changes them. -- In public templates, connection examples, screenshots, and documentation, keep ComfyUI Core nodes on their standard display titles. Do not assign custom titles to Core nodes, because users must be able to distinguish Core nodes from Continuum and third-party custom nodes immediately. -- Runtime tests must record the workflow, prompt, media inputs, model/LoRA/sampler/step settings, dimensions, chunk count/duration, elapsed time, and observed result. Inspect embedded workflow metadata when present. -- Do not globally replace `PackedLayout`, `MiniMaxH3.extra_conds`, or other ComfyUI classes. -- Keep SageAttention, Sol-Attn, and Spectrum external; integrate through public ComfyUI wrappers and H3 payload contracts. -- Preserve the identity of `layout.position_ids` when changing MM-RoPE coordinates. -- Never silently resize a continuation State or Session to a different resolution. -- Unknown H3 layout contracts must fail clearly instead of rendering a subtly incorrect join. -- State and Session files remain safetensors + JSON and are written atomically. -- UI nodes call reusable non-UI modules. Legacy nodes and V3.4 must share temporal, state, continuation, and layout logic where their contracts overlap. -- V2 must not decode Video/Audio VAE between H3 chunks. -- Accepted full chunk latents remain on CPU; do not accumulate generated chunks in VRAM. -- Spectrum history must remain run-scoped through its public sampler wrappers; never import Spectrum private runtime functions. -- Do not treat V1-V3.7 public Node IDs as V3.8 compatibility requirements. Removing their V3.8 registration still requires an explicit audited public-surface change; historical implementations may remain internally while V3.8 depends on them. Preserve State/Session data safely unless a separately approved migration replaces it. - -## Project files - -- `AGENTS.md`: durable rules and prohibitions only. -- `PROJECT_STATE.md`: current paths, version, active direction, and known gaps. -- `WORKLOG.md`: append-only summaries of completed work and evidence. -- Do not duplicate long history across these files. Update `PROJECT_STATE.md` when facts change and append one concise entry to `WORKLOG.md` after completed work. +MiniMax H3 Continuum for ComfyUI. Package 3.9.1 provides the V3.9 Sampler and Reference Images helper, while retaining the separate V3.8X2 workflow. Source publication does not imply a GitHub Release or Registry package publication. -## Product direction +Sampling Contract v6 and Graph Contract v4 apply to new generation. Keep original v5 history readable, without reusing its Takes in v6 generation or rewriting stored manifests. Public node IDs, socket/widget order, official workflows, Run Storage v3 and State/Session formats remain unchanged. -- Product definition: H3 Continuum is a Production Sampler that generates, reviews, partially regenerates, and resumes long-form video without restarting the entire work. -- Keep one discoverable Main surface plus an in-node `Advanced` disclosure. Do not require users to discover a hidden node property before normal Production controls become usable. -- Evaluate new work against three pillars: `Continuation Quality`, `Non-destructive Production`, and `Open Integration`. Prefer external integration or `Deferred` when work does not clearly strengthen one of them. -- `Main / Production` must be simple by default and expose Production controls when expanded. Do not develop a separate Easy product path. Its primary flow is Continuation Quality, Review/Regenerate, Resume/Branch, and Finalize. -- `Advanced` contains Second Pass, Selective/Temporal Refine, external integration, and diagnostics. Experimental or development-only nodes do not become public merely because their code and tests are retained. -- Do not build an all-in-one node pack. Keep external Upscaler, TensorRT, FBC, Sol-Attn, Spectrum, Director, Prompt Planner, Save/Encoder, and Core or external VAE Decode outside Continuum unless an explicit integration contract is approved. -- Do not grow the Main Sampler with unbounded sockets or serialized widgets. Prefer stable latent/assembly/refine/run contracts and external adapters. -- V3.8X2 remains available as a separate workflow and Sampler alongside V3.9 on `main`. V3.7 and earlier remain obtainable from historical GitHub Release/tag rather than being carried as automatic V3.9 Node-ID compatibility. -- A saved workflow that references a Node ID not exported by V3.8 may load as an unknown node. State this explicitly in the V3.8 README, Release Notes, and migration note, and direct users to the corresponding historical Release/tag. Do not restore old registrations solely to hide this intentional support boundary. -- The accepted V3.8 launch surface is seven searchable nodes: Sampler V3.8, Reference Audios, Finalize, Load Image, Load Audio, Load Video, and Second Pass. AUDIO-R1 is the approved one-node modular-input exception; existing six node IDs and schemas remain compatible. -- Public-surface cleanup changes export mappings only. Do not physically delete legacy classes/modules while current V3.8 imports or inherits them, and do not exclude runtime-imported legacy modules from the package archive. -- Main UI disclosure state is presentation-only. It must not enter Sampling or Run Storage identity, alter backend kwargs, or rewrite values of hidden widgets. Connection-specific size controls must be visible when their corresponding input is connected. -- Keep the accepted V3.8 Main facade explicit rather than inference-driven. Its first controls are `Prompt Format`, `Continuity`, `Base Seed`, `Control After Generate`, and `Audio Continuity`, followed by independent `Chunks` and `Seconds per Chunk`, a read-only calculated `Total Length`, an always-visible `Size Source = First Image | Manual`, the applicable Resolution or exact Width/Height controls, Run, Progress, a clear Queue-ready summary, and one Advanced disclosure. Do not show permanent connected/unconnected input badges, infer an Input Mode, derive chunks from a total-duration selector, or automatically change Size Source when an upstream node is bypassed or disconnected. When the canonical backend revision is `review_ready`, replace the setup facade with the amber review status and the three explicit Queue actions; do not infer this state in the frontend. -- Keep Main UI numbers compact: Chunks and pixel dimensions are integers, and Seconds per Chunk shows a decimal only when one is meaningful. Use user-facing `Full Video`, `Review by Chunk`, and `Resume & History` labels while preserving their existing backend values. Review action buttons must remain hidden until the canonical Run Storage revision reports `review_ready`; never infer readiness from frontend widgets alone. Hide empty Render History and keep Advanced settings behind the visible in-node disclosure. -- Every visible V3.8 Main, Advanced, Review, and Render History control, plus every public Sampler input, must have non-empty mouse-over help. Context-sensitive controls must explain the currently selected behavior; `Output Size` must explicitly distinguish First Image for I2VA/FL2VA from Manual Width/Height for T2VA or workflows without a First Image. -- Completed-review UI exception (2026-09-07, user-authorized repair): a canonical backend revision with status `complete` must retain its completion panel, Back to Settings/Return to Review, and non-empty Render History. Show Try this chunk again only when that revision carries a valid review_unit, as already supported by the backend. Hide the no-op Continue/Finish buttons on completion. This extends the earlier review_ready-only presentation rule; never rewrite backend status, infer readiness from widget counts, or invent a retry unit for a full-run completion. -- Keep Core node display names unchanged in every public workflow. -- User-approved distribution exception (2026-09-07): publish the supplied Spectrum graph as `MiniMax_H3_Continuum_V38.json` and the user's matching ZIP, byte-for-byte, including its existing titles, prompts, media names, and saved settings. It is one graph with external Spectrum, rgthree, KJNodes, and ComfyUI-Easy-Use dependencies, not a Core-only template. Document setup differences instead of silently rewriting the workflow. Keep unrelated backup ZIPs out of new commits/packages. -- Hi-Res Fix is not part of the new standard workflow. Preserve its historical implementation until cleanup is approved; use Second Pass as the external latent-processor bridge. -- Keep P1a First Block Cache and P2 boundary-aware Sol-Attn `Deferred`. Keep A5 and A8b `HOLD` under their recorded release contracts. Issue #13 reporter-exact R3 remains the highest Continuation Quality investigation when its required workflow is available. +## Product and data contracts -## H3 completion review handoff +- Keep normal generation, Review, retry, continuation and finalization discoverable. Advanced controls must not rewrite hidden values or generation identity. +- Follow ComfyUI Core validation. Do not reject prompts, unknown models, wrappers or merged models solely because they are unknown. Unrecognized prompt syntax falls back to Fixed and passes through as entered. +- Keep legacy strict_compatibility inputs loadable but ignore their values. Warnings remain diagnostic unless an unusable internal payload or corrupted data makes execution impossible. +- Preserve accepted chunks and prior Takes. State and Session remain safetensors plus JSON, written atomically. +- Keep full accepted chunk latents on CPU. Do not accumulate generated chunks in VRAM or decode Video/Audio VAE between chunks. +- Preserve native PackedLayout behavior and position_ids identity. Never silently resize continuation State or Session. +- Keep Reference conditioning, First/Last Image, Driving Audio and generated Audio contracts separate. Second Pass must preserve First Pass audio when the selected path requires passthrough. +- Keep SageAttention, Sol-Attn and Spectrum external and use their public wrappers. Do not replace Core classes globally or import private Spectrum runtime functions. +- UI nodes delegate to reusable modules. Preserve legacy implementation modules while current registered nodes import or inherit them. +- Main UI disclosure is presentation-only. It must not change backend kwargs, Sampling Contract or Run Storage identity. +- Keep standard Core display titles in public examples so users can identify node providers. +- Experimental changes default OFF and must not change Production behavior. Still Image Guide and deferred continuation interventions remain outside accepted Production scope. +- Keep V3.8X2 and V3.9 as distinct workflows. Do not automatically migrate historical node IDs, workflows, Runs or Takes. +- Keep the shipped workflow JSON/ZIP files byte-for-byte unless a workflow change is explicitly requested. -- User decision (2026-09-16): do not send implementation or Gate reports to `H3情報チェック` automatically, ask for handoff approval, or wait for a reply. Send only when the user explicitly requests it again. +## Validation and contribution -## A8b and A5 HOLD release contracts +- Preserve unrelated work and take a verified snapshot before changes. The snapshot destination is configurable through tools/snapshot.ps1. +- Reuse the existing pytest configuration, tests and runtime verifier. Distinguish CPU checks, offline registration, live loading, browser acceptance and GPU results. +- Runtime checks record prompts, media, model/LoRA/sampler settings, dimensions, chunk timings and observed results. Check saved workflow metadata when available. +- Verify all hashes declared by MANIFEST.sha256 and REGISTRY_MANIFEST.sha256 after modifying their payloads. +- Current public registration contains twelve nodes. Do not register experimental implementations implicitly. +- Do not claim whole-release acceptance from a targeted repair test. Browser save/reload and the unchanged default workflow remain separate acceptance checks. +- Keep machine-specific paths, credentials, service addresses, process identifiers and private operational records out of public documentation. +- Record public behavior and version history in CHANGELOG.md and WORKLOG.md. PROJECT_STATE.md describes the public source status. +- Commit and publish only when explicitly requested. Release/tag/Registry publication is a separate action. -- 2026-09-05 explicit user exception ("許可、許可。"): Issue13 R3B may run one isolated Video-only weak tapered context-noise A/B experiment before reporter-exact R3. This waives only the reporter-exact/independence prerequisite for that diagnostic. Keep Production/source runtime unchanged, Audio/masks/depth/Seed/SIGMAS/grouping unchanged, default OFF bit-exact, and pass CPU/Shadow/Replay before GPU. Restore clean exported prefix after the diagnostic perturbation. No combined interventions, A5 work, public controls, or Production promotion are authorized. General A8b and Release HOLD remain; GPU-audit sharing is limited to the fixed H3情報チェック task. +Run the standard validation entry point from the repository root: -- A8a is the accepted read-only baseline: full pytest `1041`, Manifest `242/242`, every observer record has `execution_applied=false`, and Production/Sampling/Run Storage/State/Session/Assembly parity is preserved. -- Keep A8b execution policy on HOLD until one intervention type is specified and approved. Do not change context, transport, mask, latent, or conditioning in combination. Seed, SIGMAS, and physical grouping remain unchanged unless separately approved. -- Exclude the failed Issue #13 candidates from A8b: effective 13-frame history, 22-frame Video prefix with 75% preservation, Soft Re-anchor, and Production Fixed Prefix/teacher forcing. -- Before A8b GPU Sampling, either complete reporter-exact Issue #13 R3 or prove by static and replay evidence that the proposed intervention is independent of the recursive-feedback path. Then pass an A8a Shadow/Replay Gate with no unnecessary action, Terminal misclassification, or Run Storage replay difference. -- Any approved A8b implementation starts Experimental and Default OFF. Existing Production must remain bit-exact, public schema changes require separate approval, and external Sage/Sol/Spectrum wrappers must remain intact. -- Keep A5 Reference Video Influence Schedule/Fade on HOLD until reporter-exact Issue #13 R3 classifies Reference Video as unrelated, an amplification-only factor with a defined safe range, or a necessary/strong cause candidate. Only the first two outcomes may unlock Experimental A5 work; the last keeps A5 on HOLD. -- A5 OFF must remain bit-exact with Production. Initial A5 may change only Reference Video influence; it must not change Video continuation, Audio, Seed, SIGMAS, Terminal Merge, Assembly, or Run Storage. Do not implement A5 and A8b concurrently. -- A5 promotion requires at least `3x5` plus a long-form continuation GPU Gate covering trajectory, identity, saturation, contrast, sharpness, and highlight drift. Short-form evidence alone is insufficient. - -## Validation - -```bash -powershell -ExecutionPolicy Bypass -File tools\validate.ps1 -``` - -Runtime installer verification must check native PackedLayout behavior and all registered nodes. - -GPU checks must cover Sage only, Sage+Sol, Sage+Spectrum, and Sage+Sol+Spectrum with identical prompts and seeds. V2 must also be compared against the equivalent V1 3×5-second graph. - -- Once the user has explicitly approved a GPU run, free-VRAM and process-RSS readings are advisory. Do not refuse to start or stop an otherwise healthy run solely because a numeric free-VRAM/RSS threshold was crossed. Continue unless an actual CUDA/PyTorch/Windows OOM or allocation failure, backend crash/health failure, NaN/Inf, or a structural layout/AV/duration integrity failure makes the run unsafe or invalid. - -## Reusable local environment - -- Source repository: `D:\Codex\_git_push_work\ComfyUI-H3-Continuum` -- Primary tested runtime: `D:\StabilityMatrix\Data\Packages\ComfyUI_W\custom_nodes\ComfyUI-H3-Continuum` -- Secondary runtime: `D:\StabilityMatrix\Data\Packages\ComfyUI_WAN\custom_nodes\ComfyUI-H3-Continuum` -- User-organized V3.8 test videos and related test artifacts are under `D:\output\video\comfy_video\v38`. Reuse that path when inspecting prior V3.8 outputs; do not move, rename, or delete its contents without explicit approval. -- Restart ComfyUI_W with `D:\StabilityMatrix\Data\Packages\ComfyUI_W\venv\Scripts\python.exe`. Do not launch the base executable reported by `Get-Process.Path`; it omits the venv dependencies even though it is the resolved process image. -- When the source adds or changes runtime imports, do not synchronize only the visibly changed files. Install the complete current `REGISTRY_MANIFEST.sha256` set, or first prove a dependency-complete narrow set; then verify registration through the live ComfyUI `object_info` endpoint. A standalone verifier launched from the source checkout is not sufficient evidence for a mixed installed runtime. -- Reuse the repository's existing pytest configuration and helper scripts instead of rediscovering paths on every task. -- Read this file before each task. Record durable project decisions, paths, commands, failure causes, and validation methods here so later work reuses them instead of restarting from zero. -- GitHub authentication for this repository is already configured. Do not request a new login or token unless an actual authentication command fails. -- Commit and push only when the user explicitly requests publication. - -## User-approved loader migration (2026-09-21) - -- Keep H3EasyLoadImage and Enable Image; delegate inherited mode accessors and leave Core widget collections, drawing and serialization intact. -- New official workflows use Core LoadAudio and Core LoadVideo -> H3ContinuumVideoAdapter. The adapter has no Enable/file/upload UI and reuses the existing frame-rate conversion. Preserve the original Audio/Video IDs as deprecated compatibility nodes; never infer lost filenames or saved OFF states. -- The approved export exception adds H3ContinuumVideoAdapter to the existing nine-node mapping. Do not change Main Sampler, Sampling, external wrappers, Decode Cache or Run Storage semantics for this repair. - -## User-approved Timeline Video experiment (2026-09-21) - -- This ZIP adds one optional appended Video Reference Mode to V38. Missing mode stays Repeat Reference. Follow Timeline is opt-in and uses the existing physical visible range; do not change grouping, seed, audio or masks. -- Keep current public workflow files unchanged. Separate Experimental Follow/Repeat templates are used until browser and GPU acceptance. -- CPU module/patch-fixture tests do not constitute a full ComfyUI or GPU gate. H3 information-check handoff remains pending. +```powershell +powershell -ExecutionPolicy Bypass -File tools/validate.ps1 +``` diff --git a/CHANGELOG.md b/CHANGELOG.md index 426f81a..f7cfd3b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,14 @@ # Changelog +## 3.9.1 — stability fixes (2026-10-04) + +- Preserve audio-only and mixed Second Pass keyframes while spatially adapting only video. +- Use Sampling Contract v6 / Graph Contract v4 for safe Take reuse, including sampler closures and MODEL CFG/wrappers. Keep v5 history readable without adopting its prefixes into v6 generation or rewriting old manifests. +- Slice Review Driving Audio once from physical-group natural time; use Core resampling and document explicit Reference Encode Cache invalidation for direct VAE weight mutation. +- Match V3.9 partial Review conditioning and Reference routes to actual output-group identities before Second Pass. Preserve complete-run behavior, original audio LATENT objects and saved Takes. +- The repaired runtime passed 1696 CPU cases (1 skipped) and three targeted 512×512 Review Second Pass GPU cases. Browser acceptance remains pending. Optional latent-upscale doubled outlines are tracked separately in Issue #27 and are not a required gate for this stabilization. +- Bump package metadata to 3.9.1 while preserving V3.9 public node IDs, widget order and official workflows. Restart ComfyUI and refresh the browser after updating. Keep historical V3.8 releases untouched; this main-source update adds no LoRA Plan and does not create a GitHub Release or Registry package. + ## 3.9.0 — V3.9 source on main (2026-09-29) - Publish the separate V3.9 Sampler and nine-slot Reference Images V3.9 helper with fixed `@R1`–`@R9` identities and All / Per chunk assignments. V3.8X2 keeps its existing Sampler and Reference connections; saved Runs/Takes are not automatically migrated. @@ -11,12 +20,12 @@ - Add a separate nine-slot Reference Images V3.9 helper with fixed `@R1`–`@R9` IDs, in-node All chunks / Per chunk table, and one typed connection to the V3.9 Sampler. Both choices use the existing group-effective routing engine; disconnected or unassigned slots do not renumber later images. - Supply a separate V3.9 workflow JSON/ZIP and user guide. V3.8 Sampler and V38X2 workflow JSON/ZIP remain unchanged. Older V3.9 prototype graphs require manual rewiring and saved Runs/Takes do not migrate automatically. - Local CPU `1530 passed / 1 skipped / 0 failed`, frontend Reference Images and Review Queue contracts, and standalone runtime verification passed. Live-browser and GPU acceptance of this new helper/UI remain pending. No commit, push, Release or Registry publication. -- Rebase the separate V3.9 JSON/ZIP on the supplied V38X2+Decode Cache Helper workflow, preserving its appended Repeat Reference video setting, media loader values, Image bypass and Decode Cache Helper. Route Reference Images 1–9 through the new helper; keep all other graph nodes and settings unchanged. The running 8188 backend still exposed the old V3.9 schema until a full backend restart. +- Rebase the separate V3.9 JSON/ZIP on the supplied V38X2+Decode Cache Helper workflow, preserving its appended Repeat Reference video setting, media loader values, Image bypass and Decode Cache Helper. Route Reference Images 1–9 through the new helper; keep all other graph nodes and settings unchanged. Restart ComfyUI fully after updating to load the new node schema. ## Prior local prototype — V3.9 Reference Routing RR-R6B (2026-09-25) - Add a separate V3.9 Sampler ID with default All (unchanged V3.8 Reference path) and opt-in Custom R1–R9 per-chunk selectors. Keep the V3.8 schema/widget order and official V3.8X2 workflow files unchanged. -- Carry the frozen RR-R5 group contract through the private runtime to a read-only, post-Queue Plan Inspector. Pending groups remain configured/unverified; accepted groups display backend-verified generated/reused status, effective Picture mapping, SHA and warnings. +- Carry the frozen RR-R5 group contract to a read-only, post-Queue Plan Inspector. Pending groups remain configured/unverified; accepted groups display backend-verified generated/reused status, effective Picture mapping, SHA and warnings. - Capture matching group-local routed conditioning in same-Queue Refine Context; Second Pass distinguishes verified Reference inheritance from prompt-only fallback. No cross-session reconstruction is claimed. - Local full CPU: `1524 passed / 1 skipped / 0 failed`. RR-R6 GPU/API integration passed 11 Queues, including Review Q1–Q3, Second Pass, and the Sage/Sol/Spectrum wrapper matrix. The subsequent real-browser B0–B5 Review, completion, and save/reload gate passed using a corrected Ref2V 8-step LoRA / eight-step workflow; this is not a six-step rerun. Subjective identity and long-form image quality remain ungraded. - V3.8X2 workflow JSON/ZIP and the V3.8 Sampler remain available. V3.9 `All` uses the V3.8 shared-reference path; changing to V3.9 `Custom` is a manual workflow change and does not automatically migrate an accepted Run or Take. diff --git a/INSTALL_JA.txt b/INSTALL_JA.txt index e9a0304..87f8df1 100644 --- a/INSTALL_JA.txt +++ b/INSTALL_JA.txt @@ -1,14 +1,13 @@ -ComfyUI-H3-Continuum 3.9.0 — V3.9 / V3.8X2 インストール +ComfyUI-H3-Continuum 3.9.1 — V3.9 / V3.8X2 インストール -V3.9.0はmainの現行ソースです。新しいGitHub Release/Registry公開は別工程で、過去のRelease/tagは残します。V3.8X2 WorkflowをV3.9へ自動変換せず、別々のWorkflowとして保存してください。保存済みRun/Takeも自動移行しません。 +3.9.1はV3.9の安定化修正版です。旧v5 Takeと履歴は読めますが、新しいv6生成の前半には再利用できません。新規Full VideoまたはStart again from Chunk 1で開始してください。新しいGitHub Release/Registry公開は別工程で、過去のRelease/tagは残します。V3.8X2 WorkflowをV3.9へ自動変換せず、別々のWorkflowとして保存してください。保存済みRun/Takeも自動移行しません。 1. ComfyUIを終了します。 2. 既存の `ComfyUI-H3-Continuum` を更新する場合は、作業中のworkflowとRun Storageを先に退避します。 3. ZIPを展開し、`ComfyUI-H3-Continuum` フォルダーを `ComfyUI/custom_nodes/` に配置します。 4. ComfyUIを再起動します。旧UIが残る場合はブラウザをハードリロードします。 -StabilityMatrixの配置例: -`D:\StabilityMatrix\Data\Packages\ComfyUI_W\custom_nodes\ComfyUI-H3-Continuum\` +インストール先は、使用しているComfyUIの `custom_nodes/ComfyUI-H3-Continuum/` です。 PowerShellによる自動インストール: `install_windows.ps1` diff --git a/MANIFEST.sha256 b/MANIFEST.sha256 index 88ac8ef..5995925 100644 --- a/MANIFEST.sha256 +++ b/MANIFEST.sha256 @@ -2,9 +2,9 @@ dca65fb1393e67f59c6f81f9411e3e745eb8f1097e9a2adf7ffc6f4e3901ca9f __init__.py 54ba2a58388c42063d24335aa2737e86bd4c15fe9632dcc9ffba18c328e04641 .comfyignore 3d681ded5d4c50cc20c2382e29fdc98d8a48e76d552c41ad5a195d941e66e612 .gitattributes 8296f0afc7be47171e439c02fb2988cfeb0df904acbe3fc4f507f426d709157e .github/workflows/tests.yml -0a2f69d4cec89d440f5d5aa1ec68a7c9a741382d313f80dcddf96d13f70b3e68 .gitignore +a28c4c592d56c57e0967f0adce5655313b942b8cc04f77766c0db1bec96c13e0 .gitignore 3e7a1ec3380be2a222c8a3e9b8a6bb184d3a760478957f48186438f15235bdba branch_provenance.py -593ec5bafb8e506cc7b326bdc7e3f024a142569f24f8d39c1aaa3b5acfd0beca CHANGELOG.md +16f886cd4b296290880e549a3f4683308246dd1fd93e479c3bbd6ab29307beda CHANGELOG.md c1ed3a0342730450958fb62fd21854a876991f3a4aefb24e5383b0c73cd2312d compatibility.py 4d62508f900af9f93ec320afb900c27cc9a300d1e0c0a94714258498c5ede5fc conditioning.py 294251c40b1be2e296c5e5f627b68091d087bdb39179e3a0c3cebd2ee8a344f5 constants.py @@ -75,7 +75,7 @@ ae3338f720fc22c05ab4a661c68f9c5dcb20d751a835f0e60d4738333be48e63 docs/images/v3 b765b37502b012b462606c4d2dcef43f13950e5fd682824fb18cdb19d542c121 docs/images/v39/v39-sampler-node.png 77c225d1e49e06d00b04acf811177c9a4317e792d4bfe92df539de99420c3563 docs/LOADER_PERSISTENCE_REPAIR.md b30fe4640359bebfcdeeb94dbeec94cb346c8e3646509e1dcdb87d7021ba04ff docs/N2B_BRANCH_PROVENANCE_CONTRACT_V1.md -a884c0bb08fca1f3a2f2b8f0e607f5d2c9ea27feec902fdce720743026fae019 docs/R0_RUNTIME_CHARACTERIZATION.md +994b0b969089247921ca21306496cc1e8e6f729b587a8206b6403e0b7a11734c docs/R0_RUNTIME_CHARACTERIZATION.md e6b8cc3250776868f473357cd97ce299fcea31ae18b879ec6e6466f47dbf704e docs/R6_NODE_FACADE_DELTA.md 91ee4adf828415e84e2f413e3a4e20dc16356f139e8ef1f6756f584cad04f3c8 docs/REVIEW_RESTORATION_REPAIR.md 93f07aa727b34802bce3d333426b8ba2af522500882a6d222d00cf577ca82e49 docs/SEAM_TEST_SOURCE_JA.md @@ -89,9 +89,9 @@ ca9f1aecd1032f0f0b237948c7fc1e4e693440dff35f5f17fd5e6d5ca4dab7f9 docs/V38_BEGIN 717577efdec5e61600504b77bc2a099ef022c4fe2333e936c3310c7182d8f2a0 docs/V38_OPEN_INTEGRATION_CONTRACT.md 3496636f645b39336fd95a4f21a562810c56f8e1d92fa6eeb1e4b0786ad11b37 docs/V38_RELEASE_AND_MIGRATION.md 4d17d74107e78404b190fec9494b443249e5aff4f58670c50d54dfdfb064334b docs/V39_REFERENCE_INLINE.md -f0806bb2b999794ddda072e98424dbd1b613df1cd8a096b12d979f124e066d8a docs/VALIDATION_JA.md +1f5d49944c6b1dd0ff1c2edd1fcb54b6c2698f0b8cba85f5f59425c80df18460 docs/VALIDATION_JA.md 3fec541a675c1e4e5e287cc8e498036001f34f7a62460321e16f9ba27b5e4c18 docs/VALIDATION_RESULTS.md -cedd7b07901d6065079ef37380f0062d535a39c98c8f614e1b26582f549d7183 driving_audio.py +a8c56379abe23b98c8ceed6ea5e60a02ecc3c6d9636232d7371615f4eb306e81 driving_audio.py 6771c9905d35666121c4892d2ec26202505f96d244ce814ad9a87a02878952cd examples/H3_CONTINUUM_V1_WIRING.md be419d6c773784823af7b58a3423ef2e21d3cc3e23c40e60e274560895ca034b examples/H3_Continuum_V2_README.txt 4b94f779a98bfc555f6999113a694da07746cc3cf400bfc70ebc580592034d52 examples/H3_Continuum_V2_reference.webp @@ -116,38 +116,38 @@ f3d8dd0f0872afdd97fe24e58b5cb74190d03e3583a66a5d013fee41f6894cda examples/workf 65689fd800a60ab6939bea020d630616b03a453cf6d48022cd1361992a765abc examples/workflows/MiniMax_H3_Continuum_V39_Reference_Inline.zip 40199d2500174ba51c040d6983f88d74c4bfbaf19191e728818e6b969b869b0f examples/workflows/MiniMax_H3_Continuum_V39.json f69b734b5bf19fb6db78bbe4737db0bef69c2a6cef2710f28767882ef35ec847 examples/workflows/MiniMax_H3_Continuum_V39.zip -7861fac4c8fe82372c5459aa574d35ea003bdb4fd846d567bd891c2e38571b3d graph_contract.py +a344da581b3c2d77558a460d2b5256e6c9a63b5008c98b52999ceda2e0b2b767 graph_contract.py bf0556b076dbaca67c3405a7d86c333ca7fdf3d4381529b0a9edc906519943e9 guide_timeline.py 6e889c42490ccb5f376694b5944c693a84e7febedf38e631d687e96bc1e76376 H3-Continuum-LLM-System-Prompt-v1.zip 144324850d4ba086938da5f4ed7b02ff0668dec554f092695328240e43fec3ec H3-Continuum-Skill-v1.zip 1473c384082700f422f2cf9141e0d012d87d2b43ac8a8a433edc7172e6ca7bf6 hardening.py -9fca2d9c04be387160dee84e5ee9ce538cb910e79e356b9236e6d2240ea6d4ee INSTALL_JA.txt +199f946243bed42786319517f26e628612877df61ce36d55552485155b5df44b INSTALL_JA.txt 23bddc5a41d2e997f4fbf789c7128e32f4f197f1405b2aef1c76794f57482446 install_windows.bat 12bf572a65d57bbc9a72b459f29691c2057768f4fb7a74f9db87f4775e995bda install_windows.ps1 139546ec1ff459945aa89b50f74b5ee69f62a0e07bbddfcae06936091a409a83 layout_adapter.py c44abbd789091bbead01250dbd5453e60539d2665c69f162335fdbd2936019c2 LICENSE d3e213005670e94dee33a240349a4d245cf9a3b6602099f11ed30cf5a32e2c21 media.py -8ce5a7c255088fb6038925a93b71b87972bf2f02e450af86da5c317e95506c41 metadata.ini +ad0835f8fb6d171d8ff8d7295fb48291abc93ef02fd46a2e283265c15b93366a metadata.ini fd23c7f32810788aaaf1709c4959c40ec72303aecc6f6afa5fa68d824cca97a8 minimax-h3-continuum-dance-director.zip d7e613e2cc24110213b477bdd1d390234a41f2af3b1ed006a809066d71d658eb model_patch.py ecb65a5dbf9e1683c5a3cadd82daaea3a90a2b776f6ebabfbe8b07aa93177422 nodes.py 99405e4357a143b0f5d0b374c9c0d2089435a7055bea2f3d1216dbbad25e4339 PACKAGE_INFO_JA.txt ea64b8e0aa0dda828047c9c12818be8554429774049b9e8c0482c84b9c4f4071 PACKAGE_VALIDATION.txt b470819f16fc179654dc1600721a63f0a5a14e777f4c004d574b499da6886ba5 public_api.py -667f2646e82362d472d91a7cf5dc9a86c95f6637f3bc8c672dd516800b1a598c pyproject.toml +1047d05b0aedc405e3a36ee571a8939111d69bb5565e09a3e1caa3c40bf33170 pyproject.toml 94fdc2d545b2d4077a4d70229fd22ba3ccac21d49d1097d2873f76d04e9a3c7a pytest.ini -47f5e57dc6c84b0103d89d6549e87ad45ab4c263cadb36f21a952843a65204a7 README_JA.md -b89e0cc5348a8dbab8781a1b57c99c4c42f47598efe218cc087a77bc58419839 README.md -44127adcfa30ee84bff9cd4b2d0c695355209550e76982d374122008728aa5bc reference_audio.py +cea43f63792a28b9d19035b3ee64ff482cf0357aec9edd6fab34eb84956b2973 README_JA.md +828fc5d51539c3bb5c4bddaa741b25fcda3faf2c1dec89ed545a63247b7b02a1 README.md +9539f5cb9fb695841073fa58d9246d5a7410bc372f6cd340378185004dfaf978 reference_audio.py 5cb9bfd6810d3a93a637451980a4cc5c1436e5b84cfd1c7a111cd192e876351b reference_video.py caa572ea65dafc86850db99f52433d360ac9c4ab36b854292a3dccd5ba32dc76 reference.py -108e455b9df90d677e43381b5443675500e1acce0cee2a5a327bb4b56dd078b4 REGISTRY_MANIFEST.sha256 +136a59c87ba789b5ddf5046a27811c4700c77d52f7fb16291d83af774a7dfeec REGISTRY_MANIFEST.sha256 467edb2c188d024c2392aafe7423b3f835e16b10f570da76e2f7dda8a962c1c5 requirements.txt -53827c94b3f588f35bb8eacb404e1bd5e233d25f4ee0fdd286efc7d8ddb52b6f run_storage.py +1845cbf7ba4d3b35afd087a15f5a4d92dc73d4858e61982f8ccf431a836a22b1 run_storage.py 6056de6c0a5322a8a51ba5a114538dca2ef67788cd1afba10fedd483b95f6afa state_io.py 3a359a0467725cc292ccb4c86cf0c3d30bb6a114d01f5345792b09ea3d45441d state.py 43ec4023dc06c941e5d7a04db4b8a89fb58d744ceb986f6eb9bf534d4fdcb87b temporal.py -e8badc6a30c3006904944a27e905a02ffd45b3abe63cd1a0e9d97f75a2508ff4 tests/conftest.py +0c10bed921279860b0c9f330a4d4c2ec619f8bdf1bbcaff0a49f81c4dc693063 tests/conftest.py 7f34c43ea74c43cfc4f9453848c69c8ed7546de5b78c7c7d063d643f2c483c36 tests/decode_cache/conftest.py 8d0cced8c945c4333ef78688b51a988d7e1d560e5f9e6cceec8310b17c98ad53 tests/decode_cache/helpers/cache_process_worker.py a41a4de12e6fe5690845f9f0795fa82c4907f0afe2551034fa2a4c95617ac39c tests/decode_cache/test_adapter_nodes.py @@ -158,10 +158,10 @@ db08ce77cc5c5835f2403d4d589394090fa5d25ff3b1840312b2808e1bc203b7 tests/fixtures 606b3985f2b644fac40c84de3e08d1453e87a988acca51ce9595516a7c60a577 tests/frontend_decode_cache_helper.mjs 868c613654467c2c739e07de5dd9b4679b36f98cd96d631d91e1d4afe5698cf5 tests/frontend_external_int_size.cjs da45ac4b9422f04a6867ff4cff4b12cf1dff88422522b8010a960b5ecfce046a tests/frontend_reference_images_v39.cjs -19bb25dea15f20fac9874b9d18c9b75156446dda7e6da91e8a9e758282c5f777 tests/frontend_review_queue.cjs +751f38be4351d459145beb3a533530e0c667552fe148de2f732efbb04494b660 tests/frontend_review_queue.cjs 36f74c03a40c4b62b90eede070d976bcd1b7f0ea828983d1e61a6cb6d80a0ea8 tests/helpers/r5_process_crash_worker.py 706029af8c8d979b2b700f5bc2b96a3064fe7c728f487698d9f079abb02e9409 tests/terminal_merge_diagnostics.py -fe23752312d62ddc8c23a3c598ed2f92f2d46e2e4460f06aea91921659092451 tests/test_audit_boundary_repairs.py +02e6286857353b76080b73928c0d1e7ec48b1ed16339231a4a450743f193315b tests/test_audit_boundary_repairs.py 041289556cc621ea1857cbb8931ae41d817f69e084b2e8a7622e184a3197b61b tests/test_compatibility.py 875ac33b5458ec5e8d845850ed495707c394436aaadb668a44f36f6a1b73764d tests/test_conditioning_modes.py 2be669b6d21ec40a8b0e172b8ab431f82681f3c97c7de0935d87ad43b0ae8b4e tests/test_context_diagnostics.py @@ -193,7 +193,7 @@ c2560cbafc5962bce5f063e262cf6a173dd8df18f7b58035ec326f616617d61c tests/test_p25 2d16f6de7bcaf1f92718d3719654a746438f6218bba8d25b3632c318a1ab9c98 tests/test_packed_layout_preflight.py 1ae0369943ba2fb13f21ad0cf56ee58621ba09bf20174379595e157a1775c7fd tests/test_public_api.py 892d3e3e022a527652dd995508c8bbb650c370caf9ee66fa3eb1f7fd288bba38 tests/test_public_workflow_integrity.py -5d487395fb78c3d9ef98d0af037059ca87a92a28e65285023c234f4151c8b093 tests/test_release_metadata.py +6e31f0891e592138a911c4ffffda9ebe5b5db6350318c4d1bfdf3c5e1f149678 tests/test_release_metadata.py 5f6caf1814052798f20571ebb863c098bec23d8f2e091fc1f30ce1ef9c58675a tests/test_review_identity_lifecycle.py 5f7d3e01bc78fa076ecb17f8532b6d3f3137545da4028032ad6769407d80be07 tests/test_review_provenance_reroll.py d5e255a5fdd06ea18e70f4077f855ed2f02664f91caf79b66bfbdf7df44ad07b tests/test_review_rehydration.py @@ -217,11 +217,11 @@ b42bcc0983147462d96c6b71cc4a38e846995dafa6eebefc3ae0d9bb36caf359 tests/test_v2_ 0b5b20a8318862d167f135720e0489b8d4f93406d67c6646e052e35b03dcb876 tests/test_v2_session.py b5c320279fd38d2038e39951a3d016aa9b80741523d2816e01ceda1bdecb71b8 tests/test_v2_terminal_merge.py e22486ac62c53132c275614e4e161c78e6dce09dd0d1a7cf64f641a3b7052b99 tests/test_v2_widget_migration.py -dff09049cbcc59896dad32d36cf3fdef2e6a67c6a8ff3150a33d784d8ca165c5 tests/test_v217_stable_facade.py +7b4edd7d09e382926f94f391f5a58fdee4204affbf6a72c225313ea0a5c9d9f6 tests/test_v217_stable_facade.py 473abac48a57aa5f297c6e141a94de17ddcb9424a8744bae1c46e6a6a734a0ab tests/test_v3_hardening.py 9242f74663ccb04020ad2fb1199990c84433c9b4c5cf0560e93416c7b15e1913 tests/test_v3_physical_decode_groups.py 35b26c8cade7acb2eec35375d7dfa9a4a112f67a5cec6a842d61c69039de0d84 tests/test_v3_video_seam.py -42ac5b9337fce10a236f140d000e620ac45079ca1aaafcb8be731cfc6e0d858e tests/test_v31_run_storage.py +1c84723b0c14f3169760fe1ae95d230416f6e947ada7d97ee890a2da33e9c988 tests/test_v31_run_storage.py 3af78ab85c8e19dee8d0a98bfd11a2c0e88c30d87256da1f9699c49a19a684e9 tests/test_v32_reference.py 43aef01fc587c9f9e87baf312eb4d588975aaaacab161a36bfcb638a4c11e31c tests/test_v34_driving_audio.py aa1f36601489c360d2f1f989c10c5424bd85bd2115df2427afe696758eefd239 tests/test_v34_hybrid_reference.py @@ -252,10 +252,10 @@ e813b5d21af2963a325862acd344b33caa124d0cd3940a940c58118cf27742e0 tests/test_v38 c9577e9b2d430c9435a287bf679a920020192d51f780e02b47f286e2e4b6a615 tests/test_v38_easy_mode.py bb5a1530c890d357dc48ea74039340d746e876e8f85e06d4d9a19369f8ff5961 tests/test_v38_hover_help.py 98eb59407741dd187dc22d94b4f433f341294d05cc38106fde15b580b1465001 tests/test_v38_memory_action_policy.py -8edaae5f1ca93925e9269c9a4447c97edf5958395f08659e61a09e8d7efa088a tests/test_v38_multi_reference_audio.py +8fb637f1d61389a86ef545adf35a518a5ae44322655a38fe598fd3b3c8e0a4a9 tests/test_v38_multi_reference_audio.py 623d528a02b6712cba28c374ba3ad979bc84e2ac5318640692589a04ba6ab15f tests/test_v38_open_integration_contract.py 12337a491fa67b38b32aaeb16e0b209393960dbc46db2a8bf968b8c3902855ef tests/test_v38_packed_row_planner.py -35c7a49eb6ff0159bb13ce0f731f10a6b6eca0972bd9a2debbffe650a0dc4867 tests/test_v38_public_surface_cleanup.py +94eb249f407bf6858d936721d4a8752c5a95be6fa00dfc7f828b944e53ab1bc7 tests/test_v38_public_surface_cleanup.py 7aebd3668e04233f34c2d94e75d4708cadd64d6882cf77ec59afa0a394dcb006 tests/test_v38_public_workflow.py 14ff6561a127287d0a20887790a978612ef9d291f1d3be7d5e85b37b2c74760e tests/test_v38_ref_encode_cache.py 8b376f45261d045b584f02b4d14cd70c2d6269b9c814d4e62b5c612f6e30e36f tests/test_v38_refine_target.py @@ -264,7 +264,7 @@ aa72293fe5ba6f4499e1ec95aace3b2e94813fa35cf987a767e77bbf2ae525b1 tests/test_v38 2ac395009e49f9554af8d1a251d93fc5d5e7070bf80f5a0b7b3f7e00cde15077 tests/test_v38_review_cache.py 72a0e3cb334049b66dd36f52c826931067c242fa63557933fd667138b38d6e8d tests/test_v38_review_control.py f62daa235117a3041c66ebb17adedb13c0452c3a2fc0acdd51006d7aa0078a9b tests/test_v38_review_execution_cap.py -615b51cafb1441fe49486381d9cd30f53b570eec10d35b785bc13629664d84ac tests/test_v38_review_run_storage.py +3a5e298bc9b0d46e9560e397576352117d6353dd03977ad54fe41e4881c58287 tests/test_v38_review_run_storage.py 2d8b74a56da4c15509ef9ef082f87321182d9d97ca6c417d5a6c055d67a4ee8e tests/test_v38_review_ui.py 75697036f361a9b8ea74f69b15e408670f686c8c0e8a6c1d48fe059cc837d12a tests/test_v38_selective_second_pass_node.py 8026a241301dfc4de518649305458a538ef17a0b1567b113877a2af377738528 tests/test_v38_temporal_window_refine.py @@ -353,10 +353,10 @@ be0d8585fa57e0ccd6d02577bbc7299629e5bfe20e186747f571fccc98b67d7e v2/seam_types. 3ea23dbce6fcd217b6e81235855479b9b16fed7a21693cf156f9014555c4fe13 v2/session.py 78c830cdf49034c6e3b2cd3da5914d5cfc5638eb63ec6dbd1bab13c50d6d4caf v3/__init__.py ea2922567df90436dd6fa21696833a49dd0cbfeee142a5fedc3a7c303824d473 v3/adaptive_continuity.py -b3dc61503d35d9ef0a0dc7fed1c9b2fdc00fcb2072d4e39f64ae0826f9ec7dca v3/assembly_v35.py +c03f9f6307b5e3a658fe6d94b01b48bbf5726737e1a8979d6d6f374965f2dc50 v3/assembly_v35.py 7815230e0a9540bc2edeaf818e940b7a1fdd817fd217ba8a4f9cb21aaf6a308e v3/assembly.py 3f62fdb35e804f42d7cbf0828b4e87e69a2b99246c3f7467fe4fa698f1d803c9 v3/conditioning_bridge_nodes.py -e3a6f537a8709c7d05e4df95f1ff40c9129e7845e9ea23097d64953b4770e06d v3/driving_nodes.py +fa7a355e52fbcfe1f53b16fa1c37af5d839215b49412adb41c90129ae4e9d9f7 v3/driving_nodes.py 147a1d3fc5e09b323a4c3d13d30e432410389bae52b58330462375b9f307b791 v3/easy_audio_nodes.py 64b3e54b42e5156642f9957ccc374fd190d9fc7145637984e702534fb1bf80b4 v3/easy_image_nodes.py ac859cb1a6e23b8ceae300d818c24fe1346b649a0d663017a9b3ac64aa96fca3 v3/easy_nodes.py @@ -369,10 +369,10 @@ cb53e1b104415032ec79b7e7aa1c99848e63da3eedaa251eeba102970e4172b5 v3/hires_fix_n 91a868d2e392b018b01d0396209849c146b0d560ceb109fcdd87dea7f3d786aa v3/memory_action_policy.py 85477badd85281cfb77582fdd5b34228a9f6b68376f1b7743af2ca7d4b55aa36 v3/memory_attribution.py 4a48f74584d8ba3187e1accc31ae5acd3a2ffb9a491bb4f5ca43322db418e770 v3/node_facade.py -7fe71802319ad7659c90839f960238d0fd054662af31a4d320806c426e755ecb v3/nodes.py +f2779a7453a84dec8b993cf044e69ec90da6fe86940a73181234b5000f5a8fa4 v3/nodes.py a3411c7a295308d21623551cf4aeca5bef511eb5f063f31ac84032e3bdf4e16d v3/packed_row_planner.py b7c4a35a5e73f528492bc6946b97b687c412f1d3f5f976c19d45c6dc20288c9a v3/pixel_vae_resize.py -b139843ccfc826937c80f118920bbee2609c37d45ef88291f80f491744fd5e76 v3/plan.py +7e8681bc1ca1633389e1af1ab14100338d23a047f96c59c19151acbbfae5c108 v3/plan.py 0e3dd69d6d2bec6d9491c2fb806c25f0c62629b1eb5f9e4f77ae8d27a5b19cfc v3/planning_types.py ec71e3965f445756d54d005c0e27bea520e26dbac44e1ee3d3867bfe2da100b0 v3/ref_encode_cache.py 8b9c1cadf76e2c2425d6bf8a5783ced593a75f83a6b3f219a0f870b4c177e058 v3/reference_effective_plan.py @@ -382,7 +382,7 @@ b64f4d3d9547ac00f8edb2155109476df5b8baea730fb94e8b5bfca6d11564e6 v3/reference_i 1366da221237853eddc9e4b724d4c28917868ea32607dd086361a84df052cfde v3/reference_runtime.py 4fb950bbdc7cdb55365fde373ee190af6cdf99f7ce4c54ef73b94f0aca4e1fda v3/reference_storage_contract.py 057921bf2b05e88c2cbc08c16e2ac483aea905b8a144fbadf4a21d6ae8252427 v3/reference_video.py -b191009d686680c6eec1fdba15b76b7c9f40f11f331faaf7b69ef784e99f4989 v3/refine_context.py +8d6cd0d7f507fd6c2d33667a6ea205e131d47571444abc94d529a98748a52517 v3/refine_context.py 519586b1b3f48c73d329f7a2aaa8a1bfc6fe31ac2ecb64f2b1fdf9c19026001a v3/refine_sampling.py 43f33f989eb70ca87b916fc33267732a2be3dd4581fc72af17c53f840b53ca49 v3/refine_schedule.py afc149dc347b4c1502ddf32ea4229e633799cd34d2b2c6f98bf8a47910a9ef77 v3/refine_scope.py @@ -394,13 +394,13 @@ ae909b43ad17934c85881d3b0bea81e7b45c215eeb4d1f9f6a9ea72faf633ddf v3/reliability be6610fb9427546d9485a17015cfbdc8786715e6a0967f3e4c1dee35d8768385 v3/runtime_coordinator.py d0a004aa3030c8adaa5ea788f9acc758fcb4a556f203f9a3f63fa4e4b5772063 v3/sampling_engine.py 452022107cea233aa84d5366ec4943ac5aadbd5fcf786113f1d542a641eac8f7 v3/second_pass_nodes.py -aa4afff697bd9b8a8505e6cc7d94fcef7aabf9d93ed123ec226fad1960807e77 v3/second_pass.py +97fcb293e0714c3a74b89f08e11c21dce45d25a3010948be1af9dc059d288187 v3/second_pass.py 6e71e944313339f14e14e11cec682593159ca5542aa5d38095371da781d60224 v3/targeted_refine_sampling.py 5a044bdd70c546e4446e0c26af92aae88049ffa2e0e2d01b52033a83a3152d0e v3/targeted_second_pass.py 26b13614ba0a5fd8b192a106c9503b2f4b6fe7f9268a0fcb0f544979a49cab34 v3/video_adapter_nodes.py 4178dcfa442abdb06ce276e05bd7bcbaa6da28469ba5e57d3da3c663de4e4a9d v3/video_seam_v35.py 2f07ace1462644f0bee553827b3571535de4d0c2d9ef847bd9e0ca73a4eed5cb v3/video_seam.py -0d08a173819d63d969694f14e4a1d59ccbec357f37342e00a4db03e1144c2e02 version.py +f1c9df5eb9f6c75bd0e505fb84731951fcd9ef1ab5d7f93a0c72f05488fa05fb version.py b935ad3bb729948bb3890ce967b0ecbef737a5e51ddfc47a0060fc20aa78dcda video_reference_modes.py 685df8e0fa23e3663ab31da1e4470cd19bdaa0dc16362cb606e874d9d6153c2c web/decode_cache_helper.js fefafd4550511d80bd85ade46a0476f0cf3de13ddb94a908dff6b175f2a0e199 web/easy_bypass_toggle.js @@ -408,7 +408,7 @@ fefafd4550511d80bd85ade46a0476f0cf3de13ddb94a908dff6b175f2a0e199 web/easy_bypas 9db0aa94f634578a962d5db49e5c70356040a59df968e3a2e531b327a623081f web/easy_load_image.js 35090816ba7470a7255eb85d003b7e79f8a0065982dacf98a18f41c8ebff655d web/easy_load_video.js 0c68d13a1f8beb7431a32b471f8b0612c42fcc4bf72dd97611a025d158008662 web/easy_v38.js -c3e2e606af4e5f3e38d64b1338baedea8cadf26060da2a8618e18bf73f220f24 web/project_id.js +fbceb922aa3a5ef54886f0ca4c1a07c516ec9fadca04080049ef11f15d584668 web/project_id.js ae59273f163a116ece418957c557c4fd8c3285e3c60814679b9361d2e6e6fa02 web/reference_audio_ui.js 46c9f75c9462bf26300332448f4431cca801f38964ca0a49bc2c50a88a7cc40f web/reference_image_ui.js e9d7753f313ebbe3d13e477f5b4e4767a735b0619b52ba54bcc5218f3eb7eb7c web/reference_images_v39.js @@ -417,3 +417,13 @@ bf41bf08dd0504eb753fa5781e6c2b8c1285758ad4bb7309975bb9231d5f8e41 web/video_refe a9f7b67bd65a9beda622aa5fdc5f8a2ecae1b58b18690d91fb0107a16a3e384e write-h3-v39-reference-prompts/references/simple-3x5.txt 81d7b4f4da797339b46911bc96d0a3736d70df29e092715c6684bb1786908593 write-h3-v39-reference-prompts/references/structured.md 3dfd0e7042070f62b9e78239c0e75d82a7df32098db10832465f3049b7f0b38f write-h3-v39-reference-prompts/SKILL.md +7fd122ff08232e114a6ef32171217ea6324e980eb7257d560c466b8177a3d3ec audio_compat.py +82efab13baacb9a229671eda5f4a2d24bb839b160b2bfb40591df51a5ddf80a4 tests/fixtures/v39_sampling_v5/project.json +8b8ca1b0c802d024c6915d903747d8722bea25628369997ab008ff896462b96a tests/fixtures/v39_sampling_v5/revisions/d8352287737286e5/chunks/rev-d8352287737286e5-txn-008f52b93a88461481ead25f91627af0-chunk-0002.safetensors +26e771cffc57f171f4cc4c6859876350bdf717d1e8213fc005343006a34f002f tests/fixtures/v39_sampling_v5/revisions/d8352287737286e5/chunks/rev-d8352287737286e5-txn-9bb0a584b7344342b114bd31b175225c-chunk-0001.safetensors +7bf0cf46f049e072a68e71cf8bbab10aef695f0931b16842a890c084021f5a11 tests/fixtures/v39_sampling_v5/revisions/d8352287737286e5/manifest.json +2e09cde80073085ac6dda5cdaf50ea9d76f1c9db15cd1b444e13e50cea8fe210 tests/test_v39_stability_r1.py +d924698cdaea82dd7212d356e368cf9701231c6a4d1f9794f1e28e7b36125124 tests/test_v39_stability_r2.py +d2e59eae0a724626b0a4e361921643dd31cb3612ae1f0d1b8b355c9d42c06174 tests/test_v39_stability_r3.py +1dc932ec0ee825a8ad95509824d225c6bd091344229da7e1ff361b7512f190d9 tests/test_v39_stability_r4_r5.py +319258798ca198312cf684f369990924657d1af168a148ad34303af31c06a350 tests/test_v39_review_refine_scope.py diff --git a/PROJECT_STATE.md b/PROJECT_STATE.md index be90483..e38c305 100644 --- a/PROJECT_STATE.md +++ b/PROJECT_STATE.md @@ -1,1949 +1,34 @@ -# Project State +# Public source status -## V3.9 getting-started tutorial (2026-10-02) +Updated: 2026-10-04 (Japan time). -- Published tutorial: https://youtu.be/AKJxBXaiG6Q (12:26), with English narration/subtitles and seven timestamped chapters. Covers basic First Image setup, chunks, Review/Take retries, Timeline prompts, and Reference Images using version-labeled UI stills and actual generated examples. -- English and Japanese front-page READMEs link to it immediately after the V3.9 introduction. +## Package 3.9.1 -## Issue #25 — external INT dimensions, main publication candidate (2026-10-01) +This patch stabilizes V3.9 generation and Review without adding LoRA Plan or V4.0. Public V3.9 node IDs and official workflows remain unchanged. V3.8X2 stays available as a separate workflow; historical releases and tags remain available. -- Verified against main `21a857115d2a2e1bfe71a4fcdf417c2d1d0edba8`, installed ComfyUI 0.38.0 / frontend 1.53.6. Source and runtime JS matched before repair. Runtime snapshot: `pre-issue25-external-int-size-20261001_182740` (641 files); source selected-file snapshot: `pre-issue25-external-int-source-20261001_182742` (7 files). -- Generalized Facade input binding for Chunks, Seconds, Width and Height after proxy creation; each configure pass rebinds current slots. Connected dimension controls retain their native Manual reserve values and are not editable. First Image remains size authority; linked dimensions are fallback inputs, not an automatic mode change. Ready text does not guess upstream runtime values. -- Required schemas/defaults/order, Python resolver, Sampling/Run Storage identity, Review snapshot/lifecycle and Fixed cache implementation remain unchanged. Core backend Int nodes retain API link arrays; virtual Primitive nodes may be expanded by ComfyUI itself. -- New actual-JS regression gate: old code failed 20/22 cases, repair passes 22/22; existing Review fixture remains 60/60. Focused CPU gate: 217 PASS. Final full CPU suite: 1569 PASS / 1 skipped in 106.02s; Registry Manifest 143 entries and development Manifest 419 entries match. Protected Production Python 94 files and stored Take metadata are unchanged. The final public tree/commit verification is recorded in the separate publication receipt. -- Runtime JS deployed and SHA-256 verified. After the user opened a fresh Chrome tab, dedicated V38/V39 graphs passed real save/reload, five tab round trips, both/one-axis/unlinked API exports, connected read-only behavior and preserved Manual reserves during actual First Image preview. Editing an upstream INT withdrew V39 Review actions; restoration remains covered by CPU fixtures rather than a new browser restore claim. The original unsaved workflow was preserved. -- User accepted a one-run resolution GPU smoke gate and authorized commit/main publication with README updates. V39 external Core Int 480/640, Manual, existing First Image/Fixed prompt, 1x4 seconds and 20 steps produced 480x640 / 96 frames / 24 fps, with 4-second audio, in 107.318s (Sampling host wall 98.695s). No OOM; all video frames/audio decoded, queue empty. A 2-second proposal was rejected by Core's 4-second minimum before Sampling. The collector's missing per-step WebSocket callbacks were independently verified through the existing Detailed Report (one physical group, 20 steps); original records are preserved. No GPU continuation/quality or broad model acceptance claim. -- Bilingual README explains Manual vs First Image authority, connected displayed reserve values and browser hard-refresh. Package version, official JSONs/ZIPs and historical Releases remain unchanged. Exact local/remote commit IDs and read-back checks will be recorded in an external publication receipt; no new Release or Registry publication. -- Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue25-external-int-20261001`. +The included repairs cover: -## R0 / Fixed conditioning cache reuse — main publication candidate (2026-10-01) +- Second Pass audio-only and mixed keyframes, with video-only spatial adaptation. +- Conditioning and Reference inheritance for the actual Review output, including partial output and a single middle chunk. +- Take compatibility using Sampling Contract v6 and Graph Contract v4, including sampler closures and MODEL CFG/wrapper settings. +- Review Driving Audio cropped once from the physical group's natural frame range, sharing the PCM origin for Exact ON/OFF. +- Core-standard audio resampling with the legacy fallback when the API is unavailable. +- The documented Reference Encode Cache limitation for direct weight mutation inside the same VAE object. -- Approved scope: Reference-free, Fixed-only V3.9 prompt reuse; no public socket/widget, Sampling, Run Storage, reference routing, official workflow or version change. V3.8 remains unchanged. The user subsequently authorized a main-branch commit/publication and bilingual README update; no Release or Registry publication. -- Authoritative runtime snapshot: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v39-r0-fixed-cache-20261001_145052` (640 files); source snapshot: `pre-v39-r0-fixed-cache-source-20261001_145125` (513 files). Both changed Production modules matched by SHA-256 before editing. -- `v2/sequence.py` passes the existing cache switch only for resolved Fixed plans. `v3/reference_runtime.py` reuses the existing bounded CLIP cache only when the entire schedule has no selected References, no reference audio/video conditioning, and no terminal-pair policy. Storage/group preflight and per-group metadata remain intact; CLIP special modes and CUDA outputs retain existing uncached fallback. -- CPU: existing focused baseline 27 PASS; the new Fixed integration test showed 2 encodes instead of 1 in old code. After repair focused 49 PASS, full 1558 PASS / 1 skipped. Cache ON/OFF CPU replay preserves latent tensors, seeds and saved descriptors. The first full run had 269 setup errors from inaccessible default temporary storage; a fresh workspace-local basetemp resolved those without Production changes. -- GPU completed after the user's normal backend restart (PID 4832): all 8 planned runs PASS; warm V3.9 hits=2 / encode_calls=0 on all 3 runs. Every run preserves two Sampling calls / 40 steps, seeds, physical geometry and 480x640 / 240-frame / 10-second video+audio. No OOM, queue empty. Warm total medians V38 273.579s / V39 273.779s (+0.200s, +0.073%); ranges overlap. Group preparation V39 0.012874s versus pre-fix 10.762069s (separate session). Sampling host-wall medians 255.961s / 256.350s; not isolated CUDA kernel time. No general quality/Reference/Timeline/long-run claim. -- Final report: `D:\Codex\_test_results\ComfyUI-H3-Continuum\v39-r0-fixed-cache-20261001\gpu_pack\results_20261001_150955\GPU_TEST_REPORT_JA.md`. GPU queue wall sum 2202.594s (36m42.6s). Production Python94 and frozen execution assets remained unchanged during GPU. Publication receipt is recorded separately under that evidence root after remote read-back; no Release/Registry publication. +## Compatibility +Original v5 Takes and history remain readable and are not deleted or converted. They cannot supply prefixes for v6 generation. Start a new Full Video or use Start again from Chunk 1 when moving an older Run to the repaired runtime. -## V3.9.0 main-source publication (2026-09-29) +Run Storage v3 and State/Session formats are retained. Unknown upstream settings can still generate; when their identity cannot be observed safely, automatic Take reuse is disabled. -- The authoritative ComfyUI_W worktree was snapshotted before publication to `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v39-main-publication-20260929-20260929_010140` (635 files). The user-selected Workflow (4) remains byte-identical to the supplied JSON (SHA-256 `40199D2500174BA51C040D6983F88D74C4BFBAF19191E728818E6B969B869B0F`). V3.8X2's official JSON and Sampler remain separate. -- Package version and README EN/JA now identify V3.9.0 as current `main` source. Both V3.9 and V3.8X2 templates and workflow ZIPs remain available; Reference wiring and saved Runs/Takes are not automatically migrated. The earlier GitHub Releases/tags are untouched. This source commit does not create a new Release or Registry publication. -- Full Windows CPU suite passed `1536 passed / 1 skipped / 0 failed` after Manifest synchronization. The previously recorded configured Reference-only GPU/API result is not a new GPU run; browser save/reload and GPU acceptance for the unchanged default V3.9 template remain pending. The ComfyUI backend was not restarted or replaced for documentation/publication work. +## Validation and remaining limits -## V3.9 user-selected Workflow (4) — local only (2026-09-29) +- Full CPU regression: 1,696 passed, 1 skipped, no failures; CUDA initialization attempts: zero. +- Offline verification: native PackedLayout and Fixed 3x5-second planning passed; twelve public nodes registered. +- Targeted GPU checks passed partial-prefix Review, single-middle-chunk Review and complete three-group reuse at 512x512 / 24 fps. Corresponding saved FLAC matched source PCM, and original Take/raw files were retained. +- Integrated generation and Take-reuse GPU checks passed for the repaired runtime. +- Browser save/reload acceptance and full acceptance of the unchanged default workflow remain pending. These targeted results do not establish every accelerator or quality combination. +- Optional latent-upscale doubled outlines are tracked separately in [Issue #27](https://github.com/ukr8b3g-cmyk/ComfyUI-H3-Continuum/issues/27). +- Publishing these sources does not create a GitHub Release, tag or Registry package. -- The latest instruction selects `C:\Users\links\Downloads\MiniMax_H3_Continuum_V39 (4).json` byte-for-byte. A verified 635-file pre-change snapshot is `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v39-user-workflow4-20260929-20260929_004809`. This supersedes Workflow (3) below. -- Workflow (4) differs from (3) only in the First Image loader's saved mode (enabled rather than bypassed) and canvas viewport coordinates. Its saved Size Source remains First Image + Draft 0.30 MP, 2×10 seconds, Full Run, blank Sequence Prompt, and six prewired bypassed Reference Image loaders. Users select their own First Image before Queue; Reference-only use requires turning First Image off and choosing Manual. JSON, gallery copy, V3.9-only ZIP, and combined V38X2 ZIP were synchronized; no JSON fields were edited. -- The Templates API exposes separate V38X2 and V39 entries and serves both JSONs with HTTP 200. Focused workflow/public-surface tests passed 28/28; Registry Manifest 138/138 and development Manifest 406/406 hashes matched, and `git diff --check` passed. Visual Chrome confirmation remains pending because the browser tool blocked opening a new localhost tab and the user's original ComfyUI tab may have unsaved work. No GPU, commit, push, Release, or Registry publication. - -## V3.9 user-selected workflow (3) and two-template bundle — local only (2026-09-29) - -- New pre-change snapshot: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v39-user-workflow3-template-20260929-20260929_003918` (635 files). This section supersedes the prior selected-Workflow-(2) settings below. -- Copied `C:\Users\links\Downloads\MiniMax_H3_Continuum_V39 (3).json` without modifying its bytes to the official V3.9 workflow and Templates gallery. V3.9 remains 32 nodes/39 links, prompt empty, loaders 1–6 connected and bypassed, slots 7–9 unconnected; its saved Size Source is **First Image** with **Draft — 0.30 MP**, but the First Image loader is bypassed. Before Queue, enable/select First Image or choose Manual for Reference-only generation; saved 480×640 values are Manual-only. -- The standard V38X2 workflow ZIP contains both unchanged V38X2 JSON and the selected V3.9 JSON. The V3.9-only ZIP and V38X2 helper-explicit ZIP remain available. The old V38X2 JSON itself and both Sampler/Reference node implementations remain unchanged. Live `/workflow_templates` already lists exactly V38X2/V39; the user's screenshot still showed old recommended-settings thumbnails, so browser-side refresh/visual confirmation remains necessary. -- No GPU run, version bump, commit, push, Release, or Registry publication has been performed for this revision. - -## V3.9 selected official workflow refinement — local only (2026-09-29) - -- The ComfyUI_W runtime remains authoritative. Before editing, a 635-file snapshot was verified at `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v39-launch-readme-rewrite-20260929-20260929_002433`. -- The user's `MiniMax_H3_Continuum_V39 (2).json` is now the selected 32-node/39-link official candidate. Only its accidental `[` Sequence Prompt value was cleared; the prompt node and wire remain. Loaders 1–6 are connected and bypassed; helper slots 7–9 are empty for optional user-added loaders. The JSON, template-gallery copy, and one-JSON ZIP match. The separate V38X2 JSON/ZIP and both V3.8/V3.9 node registrations remain intact. -- Saved V3.9 controls are Per chunk with no assignments, Timeline with blank prompt, Full Run, two 10-second chunks, Manual 480×640 (~0.307 MP; not the Draft 0.30 MP preset), and Reference Image Size Match Output. README EN/JA and launch-package guidance describe these facts and the high memory cost of 7–9 active images. This supersedes the 35-node/42-link template descriptions below. -- No GPU run, browser save/reload, version bump, commit, push, Release, or Registry publication was performed for this revision. - -## V3.9 documentation reconciliation — local only (2026-09-29) - -- The ComfyUI_W runtime remains the authoritative local candidate; `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v39-doc-reconciliation-20260928-20260928_235123` preserves 635 pre-edit files. The separate Git publishing checkout is not synchronized. -- README EN/JA, package validation/install/info, historical V3.8 migration guidance, and the AGENTS current baseline now distinguish V3.8X2's ten IDs from the local V3.9 candidate's twelve. The official V3.9 graph remains 35 nodes/42 links; no generation code or Workflow changed. -- Windows CPU `1536 passed / 1 skipped` remains the last recorded full-suite result, not a new run for this edit. Configured GPU/API evidence is separate from the pending current-template browser save/reload and GPU acceptance. No commit/push, Release, or Registry publish was requested. - -## V3.9 launch template and README — local commit preparation (2026-09-28) - -- Authoritative runtime is ComfyUI_W. A verified 633-file snapshot precedes the edits: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v39-launch-template-readme-20260928-20260928_212956`. -- The user-selected 35-node V3.9 graph is the official JSON; its saved one-character `[` prompt was replaced with the prior valid two-chunk example and a non-persistent empty helper widget was removed. One-JSON ZIP and gallery copy match this final graph. The gallery also exposes the unchanged V38X2 graph. Old settings files moved byte-for-byte into `examples/settings/`. -- Live `/workflow_templates` lists only V38X2 and V39; the V39 template endpoint returns HTTP 200. Full CPU `1536 passed, 1 skipped, 0 failed`; Manifest 406/406 and Registry Manifest 138/138 match. V38X2 JSON/ZIP bytes match the pre-change snapshot. -- Both READMEs now lead with V3.9 setup, separate V3.8 compatibility, Reference-only guidance, First/Last terminal-merge constraint, prompt tags, and resource warning. Package metadata remains 3.8.3. Exact default-template browser save/reload and GPU acceptance, V3.9 version bump, commit/push, tag/Release and Registry publication are still pending. - -## V3.9 full official workflow candidate — local preparation (2026-09-28) - -- Added a separate `examples/workflows/MiniMax_H3_Continuum_V39.json` and matching ZIP from the full V38X2 + Decode Cache Helper V3.9 migration graph. It has all nine Reference Image loaders wired but bypassed, a non-empty two-chunk Timeline prompt, Manual 480×640 sizing while First Image is bypassed, fresh graph/Project IDs, and a V3.9 Save prefix. Existing V38X2 and earlier V3.9 migration workflows remain unchanged. -- Model/LoRA, 20-step res_multistep scheduler, Spectrum OFF, 2×10-second Review, Decode Cache and output chain are inherited. Static graph/prompt/ZIP tests passed. Live browser load/save-reload and GPU generation remain pending; this is not a release or production acceptance. - -## V3.9 stale direct Reference sockets — local UI fix (2026-09-27) - -- The current live `127.0.0.6:8188/object_info/H3ContinuumSamplerV39` reports only `reference_images`, and the new candidate workflow's Sampler #312 has only that input. The user's separate Sampler #359 still visibly carried obsolete direct Image 1–3 inputs, so the browser UI Gate was not satisfied. -- Snapshotted the authoritative ComfyUI_W worktree to `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v39-legacy-ports-ui-fix-20260927_211644` (625 files). The separate Git checkout is behind and lacks the new V3.9 files; no synchronization or publication was attempted. -- Frontend now prunes only unconnected obsolete V3.9 Sampler Reference inputs when configuring a loaded or new node. Connected obsolete inputs remain linked and receive a visible instruction to reconnect them through the V3.9 nine-image helper. V3.8 input behavior and backend routing are unchanged. Focused frontend and Review tests, 16 focused Python tests, JS syntax, development Manifest `401/401`, and Registry Manifest `134/134` passed; the live server serves the updated JS. Actual Chrome canvas refresh and GPU acceptance are still pending; the user's unsaved ComfyUI tab was not reloaded. - -## V3.9 supplied-workflow rebase and live-registration gap (2026-09-27) - -- Snapshotted the authoritative ComfyUI_W worktree before changes at `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v39-user-workflow-rebase-20260927_202722` (623 files). Its V3.9 code is newer than the separate Git checkout; no repository synchronization or publication was attempted. -- Rebuilt the V3.9 candidate JSON/ZIP from the supplied `MiniMax_H3_Continuum_V38X2+Decode_Cache_Helper (1).json` (SHA-256 `0af34446b56381568d0fce7be5c96324cff5b02b30b753f9db8871efd90206c7`). Only Sampler/helper nodes and Reference link endpoints changed; a distinct Project ID intentionally separates V3.9 Run Storage. The supplied media, model/LoRA, audio/video mode, Image bypass, and Decode Cache Helper remain in place. -- Live 8188 began at 14:49 before the new source was installed. Its `/object_info` still reports the old V3.9 required `reference_routing_mode`/R1–R9 selectors, optional direct Image 1–3 sockets, and no new helper. This is a live registration gap, not evidence that the on-disk V3.9 schema includes those controls. The user-owned backend was not stopped or replaced. Full restart/hard-refresh and browser/GPU acceptance remain pending. -- Final local validation: full CPU `1530 passed / 1 skipped / 0 failed`, focused graph/public/Registry tests `22 passed`, JS UI contract and syntax PASS, standalone runtime verifier PASS, Manifest `401/401` and Registry Manifest `134/134` SHA-256 PASS. No commit/push/publication. - -## V3.9 Reference Images in-node UI — local implementation (2026-09-27) - -- Authoritative ComfyUI_W source was snapshotted before edits at `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v39-reference-inline-implementation-20260927_194410` (617 source files and 617 copies). Existing uncommitted work was preserved. -- Added a separate nine-slot V3.9 Reference Images helper with fixed `@R1`–`@R9` IDs and an in-node All chunks / Per chunk assignment table. V3.9 Sampler now accepts one typed helper output; the backend uses the existing effective Reference Plan and group runtime. V3.8 Sampler, official V38X2 workflows and package version 3.8.3 were left unchanged. -- Added a separate V3.9 workflow JSON/ZIP, user guide and CPU/JS contracts. The first full CPU run exposed stale target input indices in the generated workflow. The generator now remaps every Sampler link by input name. Final full CPU: `1530 passed / 1 skipped / 0 failed`; focused workflow/manifest regression: `22 passed`. Frontend contracts, syntax and standalone runtime verifier passed. -- This is local code/contract verification, not live-browser or GPU acceptance of the new UI. The user-managed ComfyUI backend was not restarted. No commit, push, tag, Release or Registry publication. - -## V3.9 Reference Routing local CPU audit correction (2026-09-27) - -- The authoritative ComfyUI_W worktree was snapshotted before edits at `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v39-local-audit-fix-20260927_144329` (617 files, copied byte-for-byte from the original snapshot). Existing uncommitted V3.9 work was retained. -- The same group-effective prompt resolver now supplies disconnected `@R` warnings to generated and reused physical groups. Warnings remain outside the storage descriptor/hash, and an observed warning for an accepted group is not overwritten by a configured one. Plan publication occurs only after all group contracts validate. -- `ReferenceStoragePlan.group_for()` uses a private first-match group index built once; the public constructor fields, descriptor bytes, and returned independent records are preserved. Outdated R2/R4 module descriptions and the historical V3.8X2-only package validation header were clarified. -- This is a CPU-only local audit. It does not re-run the prior V3.9 GPU/browser gates, alter official workflows or the V3.8 public schema, restart ComfyUI, or authorize commit/push/publication. Final full CPU and manifest verification are to be recorded at handoff. - -## V3.9 Reference Routing RR-R6B — local CPU/GPU/browser Functional PASS; Local RC preparation next (2026-09-25) - -- The ComfyUI_W installed source is the authoritative local worktree. Snapshot before R6: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v39-rr-r6-implementation-20260925_134552` (615 files); a second source-verified snapshot was taken before documentation/Manifest edits. No commit, push, tag, Release or Registry publication was performed. -- Added a distinct `H3ContinuumSamplerV39` public ID. Its `All` default calls the existing V3.8 path; `Custom` sends R1–R9 selectors through the private R2–R5 route. V3.8's required/optional schema, serialized widget order, official V38X2 JSON/ZIP, Run Storage implementation, Sampling Engine and Runtime Coordinator remain unchanged. V3.9 alone adds the routing controls and read-only, transient Plan Inspector. Pending groups are configured/unverified; accepted groups use observed or frozen backend contracts and show generated/reused, Picture map, hash and warnings. Route edits and changed connections invalidate the last-Queue display; saved workflows keep selectors but not the observed display text. -- The same Queue's routed group contract is captured with Refine Context and checked against the First Pass Assembly Plan. Second Pass reports `verified` only for matching Refine Context conditioning; prompt-only fallback remains available but reports `not_inherited`. There is no cross-session Refine reconstruction or automatic terminal-route split. -- Final RR-R6 GPU/API gate passed 11 Queues, including Review Q1–Q3, Second Pass and the Sage/Sol/Spectrum wrapper matrix. Full CPU passed `1524 passed, 1 skipped, 0 failed`; Manifest and Registry Manifest were synchronized before the documentation update. The subsequent RR-R6B real-browser B0–B5 Review, complete and save/reload gate passed on the user-corrected Ref2V eight-step workflow. Its eight steps differ from the original six-step manual. Subjective identity and long-form quality remain ungraded. Reports: `D:\Codex\_test_results\ComfyUI-H3-Continuum\v39-rr-r6-gpu-20260925\GPU_TEST_SUMMARY_JA.md` and `D:\Codex\_test_results\ComfyUI-H3-Continuum\v39-rr-r6b-browser-20260925\RR_R6B_BROWSER_REVIEW_REPORT_JA.md`. -- Next: prepare a V3.9 Local RC with separate V3.8X2 and V3.9 workflows, exact compatibility guidance and distribution integrity. The V3.8X2 tag/Release and proposed `release/3.8x2` maintenance branch do not yet exist. No V3.9 commit, push, tag, Release or Registry publication has occurred. User-owned 8188 was not restarted or stopped for the RR-R6B test. - -## V3.9 Reference Routing RR-R5 — local CPU and GPU Functional PASS (2026-09-25) - -- Added the private `v3/reference_storage_contract.py` group-effective descriptor/identity contract and connected it to opt-in Run Storage v3 / Sampling Contract v5 and explicit Session reuse. Unselected images and selector spelling stay outside generating identity; changed groups stop contiguous prefix reuse, and terminal pairs remain atomic. Generated groups recheck the frozen image hash, Picture map, and effective Prompt before VAE/CLIP/Sampling. -- Cross-lineage explicit Take selection now verifies the selected Take's complete producer chain and compatible prefix, then imports raw into a new-plan-owned revision. Incompatible selected Takes stop without canonical fallback or a foreign-lineage provenance splice. Legacy V3.8 requests retain their previous path and contract. -- At the CPU checkpoint: Full CPU `1515 passed, 1 skipped, 0 failed`; Development Manifest `393/393`, Registry Manifest `128/128`, both with zero SHA mismatch; `git diff --check` PASS. Public V3.8 nodes, runtime coordinator, sampling engine, frontend and four official V38X2 JSON/ZIP files were SHA-identical to the pre-R5 snapshot. -- The subsequent isolated RR-R5 private GPU Functional Gate passed `7/7`: Full A/B, Review Q1–Q3, Session S0/S1. Reuse/generation matched the group plan; source/target accepted-prefix AV tensor values and SHA matched, terminal status and output durations were correct, and no OOM/crash occurred. The initial test-only V3.8 Refine-path rejection happened before Sampling; the test adapter was corrected without Production source changes. Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\v39-rr-r5-gpu-prep-20260925\RR_R5_GPU_RESULT_JA.md`. Browser save/reload and subjective quality were not R5 Gate items; RR-R6 status is recorded above. - -## V3.9 Reference Routing RR-R4 — internal group-local runtime/CPU PASS (2026-09-24) - -- Added internal `v3/reference_runtime.py` and a private `run_sequence_with_reference_routing` entrypoint. The public V3.8 Sampler, its node schema/widget order, both 41-keyword `run_sequence` signatures, frontend, and official V38X2 workflow JSON/ZIP remain unchanged. The private entrypoint is not yet wired to a V3.9 public UI. -- A generated physical group now prepares, resizes, hashes, VAE-encodes, and presents only its routed connected R1-R9 images. Unselected and future-group images are not prepared. RR-R3 supplies compact Picture numbering; active `@R` tags are rewritten to the group's `` and inactive/disconnected tags produce visible nonblocking warnings. Explicit Custom all-off does not fall back to all References. Same-prompt groups use separate conditioning; a terminal atomic pair uses one shared group route. -- The existing Last Image presentation timing is retained for groups with no selected References. R4 uses a queue-local identity and rejects saved Run/Session, initial State, legacy prepared Reference assets, or Refine only through its private entrypoint; RR-R5/RR-R6 must define those contracts before public activation. Public V3.8 execution does not enter this path. -- Focused R4/runtime-signature CPU: `22 passed` after the compatibility correction. Full CPU: `1499 passed, 1 skipped, 0 failed`. Development Manifest `391/391` and Registry Manifest `127/127` matched actual SHA-256 with zero missing/duplicate entries; `git diff --check` and new-file whitespace checks passed. Run Storage, Sampling Engine, public nodes/frontend, and official V38X2 workflow files match the pre-R4 snapshot hashes. -- Source snapshots include `pre-v39-rr-r4-implementation-20260924_160641` (610 files), `pre-v39-rr-r4-signature-compat-fix-20260924_174300` (613 files), and `pre-v39-rr-r4-state-record-20260924_181103` (613 files). No live backend restart, browser/GPU run, commit, push, tag, release, or Registry publication. RR-R5/RR-R6 remain pending; R4 CPU PASS is not V3.9 release acceptance. - -## V3.9 Reference Routing RR-R3 — pure effective plan/CPU PASS (2026-09-24) - -- Added isolated `v3/reference_effective_plan.py`. It joins the full RR-R2 logical/physical schedule with RR-R1 fixed source IDs, compact asset indices, and prepared-image SHA-256 values, then assigns Core Qwen Picture numbers from the existing First → Last → selected References presentation order. First/Last presence is supplied by the caller; this phase does not decide their runtime timing. -- Sparse slots retain their R identities while selected References are compacted per route. Explicit Custom all-off stays empty; a requested but disconnected slot does not become another image. Identical content hashes in different slots remain separate identities. A terminal physical group with differing member routes remains a conflict without a group Picture map; no route is silently chosen or split. -- Focused RR-R3 CPU contracts: `20 passed`. Full CPU suite: `1485 passed, 1 skipped, 0 failed`. Development Manifest `388/388`; Registry Manifest `126/126`; no missing, duplicate, or SHA mismatch. `git diff --check` and new-file whitespace checks passed. Protected RR-R1/RR-R2/runtime/public workflow files match the pre-R3 snapshot hashes. -- Snapshots: `pre-v39-rr-r3-20260924_145949` (608 files), `pre-v39-rr-r3-identity-completion-20260924_153135` (610 files), `pre-v39-rr-r3-manifest-20260924_153655` (610 files), and `pre-v39-rr-r3-state-record-20260924_154545` (610 files). -- RR-R3 remains a pure CPU plan: no image selection applied to Qwen/DiT/VAE, no prompt rewrite, cache or Run Storage change, public schema/UI change, GPU/browser test, backend restart, commit, push, tag, release, or Registry publication. RR-R4 runtime integration and later phases remain pending. - -## V3.9 Reference Routing RR-R2 — pure routing/CPU PASS (2026-09-24) - -- Added `v3/reference_routing.py` as an isolated pure module. It parses `all`, `off`, one-based chunk numbers, inclusive ranges, and comma combinations for fixed R1-R9 slot IDs; absent mode preserves legacy All, while explicit Custom all-off is a valid distinct state. -- The compiler emits the complete project-wide logical schedule and derives physical groups only through the existing `physical_groups()` contract. A terminal atomic group with differing member routes is represented as `conflict`; no route is auto-selected, unioned, split, or converted into a runtime hard stop. -- Focused RR-R2 CPU contracts: `20 passed`. Full CPU suite: `1465 passed, 1 skipped, 0 failed`. Development Manifest `386/386`; Registry Manifest `125/125`; no missing/hash mismatch. `git diff --check` passed. -- RR-R2 remains unconnected to public schema/UI, Sampling, Review, Run Storage, or the Execution Planner. No GPU/browser test, ComfyUI restart, commit, push, tag, release, or Registry publication was part of RR-R2. RR-R3 status is recorded above. - -## V3.9 Reference Routing RR-R1 — local CPU/distribution PASS; GPU integration smoke PASS (2026-09-24) - -- ComfyUI_W local runtime remains at HEAD `085943ad` plus its preserved pre-existing worktree changes. `reference.py` now retains the fixed source slot IDs R1-R9 alongside compact prepared images, processed hashes, and VAE latents; existing V3.8 Reference contract, combined hash, presentation order, and public schema are unchanged. -- RR-R1 source snapshot: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v39-rr-r1-20260924_013515` (605 files; relevant source SHA matches). Before Manifest synchronization, RR-R1 and related CPU/public-surface tests: `180 passed, 1 deselected` (the stale Registry Manifest SHA assertion). -- Pre-Manifest snapshot: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v39-rr-r1-manifest-green-20260924_015359` (606/606 files; Manifest and `reference.py` SHA match). Synchronized the existing PackedLayout and RR-R1 source hashes, and added both new CPU tests to the source Manifest. Final Manifest audit: source `384/384`, Registry `124/124`, missing/duplicate/mismatched files 0; isolated declaration stage `125` files including Registry Manifest, SHA mismatch 0. All four official/experimental workflow JSON-ZIP payload pairs match. Full CPU: `1445 passed, 1 skipped, 0 failed`. -- T01 sparse R1/R4/R9 and T02 all-nine R1-R9 GPU integration runs both completed on ComfyUI_W without OOM or execution failure. Both outputs were 448x672, 24fps, 120 frames/5s with 32kHz stereo audio. T01 peak VRAM/RAM used was 15,565 MiB/35.54 GiB; T02 was 15,165 MiB/40.17 GiB. T02 minimum free VRAM was 1,118 MiB. Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\v39-rr-r1-gpu-20260924\T01_GPU_REPORT_JA.md` and `T02_GPU_REPORT_JA.md`. T02 used the same image in every slot, so neither run proves distinct-image slot separation. These smokes do not prove that Sampling consumes `source_slot_ids`, per-group selection, or output parity; those are not RR-R1 behaviors. No further equivalent GPU run is planned for RR-R1. -- At the RR-R1 checkpoint, RR-R2 through RR-R6, browser checks, official comfy-cli pack, commit, push, and publication were unperformed; later RR-phase status is recorded above. ComfyUI_W is user-owned and remains running; no restart or stop was performed. - -## Unified Timeline Video Experimental 1 — h3-timeline-video-experimental-1 (2026-09-21) - -- User-approved offline ZIP implementation based on main `085943ad9cb8023a2042d4d731c83e638361c06e`. One appended optional `video_reference_mode`, old `reference_video_1` IMAGE input retained. Missing mode is Repeat; experimental copies explicitly select Follow/Repeat. -- Follow selects the existing physical group's natural visible frame interval, excluding continuation context. It does not use the old timeline source that disables Terminal Merge. Per-slice VAE keys and fresh group-local prompt-cache dictionaries separate equal-prompt intervals. After source EOF, use no video reference; no automatic loop/stretch/long hold. -- Source mode/content/preprocess identity does not depend on configured Chunks. Preserve sampling, seed, SIGMAS, masks, Audio, wrappers, existing public workflow bytes and old Repeat preprocessing. -- Creation-time validation: isolated CPU backend tests with three Git-blob-verified upstream helpers, AST source-transform fixtures, Node.js restoration fixtures and installer transaction tests. See the ZIP's verification/evidence report for exact counts and scope. This is NOT full-repository, installed-ComfyUI, real-browser or GPU validation. -- The offline updater requires exact baseline fingerprints, compiles intended Python changes before writing, and runs repository tools/snapshot.ps1 on the selected authoritative source before applying. The updater does not commit/push, restart the backend, submit a Queue, or access saved runs/media. Applied location and actual snapshot are recorded in .h3-timeline-experimental.json. -- Production/GPU acceptance HOLD. Fixed H3情報チェック handoff PENDING; no cross-task transport in the creation environment. No Release/tag/Registry promotion. - -## PackedLayout conditioning preflight — local implementation (2026-09-23) - -- ComfyUI_W runtime now validates every H3 keyframe/reference Video and Audio latent against its block metadata and Core PackedLayout condition-row totals immediately before Core Sampling. Unsafe geometry mismatches fail before Sampling with the exact block type, shape, expected/actual rows and delta; no tensor is resized, padded, truncated or replaced. -- A stale PackedLayout is rebuilt only when every current block is self-consistent and a fresh layout constructed from the current payload exactly matches the actual Visual and Audio rows. The queue-local repaired layout is retained across model evaluations, Continuum MM-RoPE is then applied to that layout, and a final post-materialization validation is required. -- Snapshot: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-packed-layout-preflight-repair-20260923_015014` (`604` files). Focused CPU: `18 passed`. Full CPU excluding the intentionally stale Registry Manifest assertion: `1430 passed, 1 skipped, 1 deselected`. Real ComfyUI 0.37.0 `PackedLayout` reconstruction probe: PASS. -- `MANIFEST.sha256` and `REGISTRY_MANIFEST.sha256` were not updated because this is a local implementation pending the T1/T2/T3 and optional T4 GPU cause-isolation Gate. Source repository, public workflow, backend lifecycle, commit and push remain unchanged. - - -## Loader repair full-suite follow-up (2026-09-21) - -- Main repair `f8eb40d8b44e54386bcf3c5197c48f0f71daf6df` passed the 46 focused tests. Its first full CI returned 1376 passed, 3 skipped, and one stale pre-migration workflow fingerprint failure in `test_v38x2_decode_cache_integration.py`. -- Updated only that expected fingerprint to the user-approved migrated workflow (1B2212B7511FAC0B63DFA6E9F006CD8644C72D08C6945AB0E4ED0E722C97A730); all Decode Cache route and output assertions remain. No runtime or workflow bytes changed in this follow-up. -- Full isolated CPU/Node suite: 1377 passed, 3 skipped, zero failures/errors. Actions run 35558988542. Source was snapshotted with `tools/snapshot.ps1` before edits; source/Registry manifest hashes verified. -- Windows deployment, live-browser checks and GPU generation were not performed; fixed H3情報チェック handoff remains pending. No Release/tag/Registry publication. - - -## Loader persistence repair (2026-09-21) - -- User approved Image Enable repair, Core Audio workflow replacement, and Core Video plus Enable-free 24fps adapter, including commit/push. Legacy Audio/Video IDs remain deprecated/loadable. Main Sampler, Sampling and stored generation contracts are unchanged. -- Source baseline 3d7c2fd6928a545b12b84968b09dc455e7f9da65. Real source was snapshotted using tools/snapshot.ps1 before edits on an isolated Actions runner. Original-code regression exposed 3 failures; focused CPU/Node suite 46 PASS. See docs/LOADER_PERSISTENCE_REPAIR.md. -- Windows worktree/runtime/browser and GPU were not accessed. Live frontend 1.53.6 tab switching/save/reopen and fixed H3情報チェック handoff remain PENDING. No Release/tag/Registry publication. - - -## Issue #20 workflow persistence hotfix (2026-09-10) - -- User authorized repair and publication to main from pinned 6b453fe. The only runtime change is `serialize: false` on the read-only Render History widget in `web/project_id.js`; existing `options.serialize: false` is retained. Backend widget order, Sampling, Audio, Run Storage, public workflow/ZIP bytes, and Easy Loader Bypass behavior are unchanged. -- Added a regression using the real Continuum frontend script with modeled compact store persistence and forceInput migration. It covers ordinary serialization, store serialization, positional/named round trips, Advanced/Review/History/completion views, and API-input parity. It fails on the unmodified runtime; all 45 pre-existing fixture cases remain green. Full CPU pytest: 1154 passed, 2 skipped; frontend fixture: 46/46 passed. -- Validation ran on an isolated GitHub Actions CPU runner after byte-verified snapshots made with `tools/snapshot.ps1`. This is not a real-browser or GPU validation. Windows source/runtime and saved Takes were not accessed or changed. Existing corrupted workflows need separate recovery; model/VAE/LoRA reset reports and the separate Bypass issue remain unverified. No Release/tag or Registry publication. Fixed H3情報チェック cross-task handoff was not sent from this session. - -## Review boundary repair — CPU validated, live 3x5 pending (2026-09-08) - -- The latest actual Review Queue did not generate Chunk 1: backend history proved it reused all three saved chunks and returned the prior `complete` revision. The previous mode-selection presentation repair therefore did not satisfy the user's acceptance condition and is superseded by this entry. -- Source now treats an explicit Full Video -> Review Each Chunk selection as a new non-destructive review series. Before Queue it refreshes canonical Run Storage state; when saved `review_ready` or `complete` history exists, only the queued payload receives `Regenerate From = Chunk 1`, automatic nonce, and no Take selection. The visible settings and saved Takes remain unchanged. The first actual Sampler result releases setup mode and loads its canonical review state; later Continue queues inherit that new branch and advance one physical group at a time. -- Exact CPU contracts cover `3 x 5s`: fresh Chunk 1 -> review, Continue -> Chunk 2 review, Continue -> Chunk 3 complete. The real frontend lifecycle and backend branch/nonce resolver pass. Focused Review/UI suite `123` PASS and full CPU suite `1156/1156` PASS in `50.69s`; Registry/source declarations, JavaScript syntax and `git diff --check` pass. Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\v38-review-boundary-20260908`. -- Fixed H3情報チェック returned `PASS / local runtime deploy OK`; its nonblocking queued-identity note was applied by binding setup release to the exact setup token and Run name. Installed ComfyUI_W still has the superseded frontend SHA `d84877206cc1142dbfe7fce3f7e9c1b6edb8a22cae5ab117a1407f9435f6dea7`; validated source SHA is `fe5e00020b9e942ec2e27286576aca69fb3add3f18afeea8edcfd28f6183cd91`. Runtime deployment, browser refresh and actual GPU `3 x 5s` Chunk1/2/3 screen acceptance remain pending. No workflow, Production/Sampling backend, saved Take, commit, push, tag or release change. - -## Local Review mode-selection repair (2026-09-08) - -- Deployed locally after H3情報チェック returned PASS / local deployment OK (report-only review). Source, installed web/project_id.js and live8188 HTTP200 payload SHA all equal d84877206cc1142dbfe7fce3f7e9c1b6edb8a22cae5ab117a1407f9435f6dea7. Runtime snapshot verified1 file. Browser hard-refresh and user-visible check remain; no browser reload, GPU, backend restart or publication performed. This supersedes deployment-pending wording below. -- User-reported Full Video -> Review Each Chunk opened an old complete revision before generation. Reproduced with the real frontend harness (red.xml); mode selection now retains setup and the normal readiness summary without showing Retry/Restart. Existing Return to Review explicitly opens the saved result. Saved progress remains reusable; selecting Review does not mean starting a new Run. -- Presentation token is transient, not serialized or a backend identity. A matching queued generation's new review revision releases it; same-revision history reads, delayed initial history before Queue, a previously queued result, or another Run's result do not take focus. Hidden old Retry/Finish is normalized to ordinary Continue at Queue while manual boundaries remain intact. Reload recovery, review completion, saved takes, Python and workflow bytes remain unchanged. -- Focused90 PASS; final full1155 PASS in48.44s, CPU-only. Initial full had one old UI fixture failure: it injected a ready revision without Queue; fixture now models queued completion and keeps its prior expectations. Evidence: D:/Codex/_test_results/ComfyUI-H3-Continuum/v38-mode-settings-20260908. Completion report sent to fixed H3情報チェック; local deployment/readback pending that review. No commit/push/GPU or backend restart authorized/performed. - -## Review UI hotfix — validated for user-authorized main publication (2026-09-08) - -- User explicitly authorized a hotfix commit/push to existing origin/main for the confirmed Xarfai Review restart UI mismatch. Scope is frontend only: withdraw stale review actions after settings edits, preserve manual regeneration boundaries, add a non-destructive one-shot Start again from Chunk 1 button. Saved takes, sampler/transport/Audio/schema/workflow files and installed runtime remain unchanged. -- Browser-side edit detection only withdraws stale actions; it does not approve saved-prefix reuse. Existing Run Storage compatibility checks remain authoritative. The separate 15-second Review chunk2 static/noise report is unresolved and is explicitly excluded from the hotfix claim. -- Related pre-fix diagnostic evidence: D:/Codex/_test_results/ComfyUI-H3-Continuum/v38-xarfai-review-20260908/FINDINGS.md. New validation/publication evidence: D:/Codex/_test_results/ComfyUI-H3-Continuum/v38-review-hotfix-20260908. Initial source snapshots: nine verified one-file snapshots under before-review-hotfix-*. Final checks and publication result are recorded in WORKLOG and the task response. -- Final full guarded CPU suite1155/1155 PASS (46.62s), focused61 PASS, Registry105/105 and source declaration256/256 hashes match. All guarded processes exited CUDA-uninitialized, zero blocked initialization calls. Final additions cover delayed history response and queued-baseline isolation between Run Names. User authorized waiving the external review once due delayed delivery; the fixed H3情報チェック reply subsequently arrived with PASS / PUSH TO MAIN OK. Non-blocking review note: keep revision updated_utc tied to backend writes, not ordinary history reads. No GPU or Registry/tag/release-asset publication. - -## Main publication preparation (2026-09-07) - -- User explicitly approved commit/push to existing origin/main, then prioritized immediate README/file upload after announcing on Civitai and requested no further workflow tests. Publish the current Spectrum graph as MiniMax_H3_Continuum_V38.json and its matching ZIP, unchanged: JSON SHA e490c87e4995930f95c8fffc4c678111d7897e74003e1962b9b4a247ba43f4ac; ZIP SHA 83d28cc0cd549066962dc21ceae05d2b189fe22391b556887eab2cc1800e1e80. README, migration, package declarations and tests now describe one graph in two formats requiring Spectrum/rgthree/KJNodes/Easy Use. No separate Turbo graph and no prompt/media/title cleanup. -- English and Japanese READMEs link JSON/ZIP and LightX2V near the top with git clone/pull instructions. Git exact-byte attributes prevent automatic EOL conversion from invalidating file hashes. Historical V3.7 ZIP remains a source regression fixture; unrelated node.zip and external backup archives are not publication payload. -- Publication audit initially ran 1,155 tests: 1,154 passed; the real-Core CPU cache subprocess stopped at optional SageAttention import requesting CUDA capability. Initialization was blocked. The CPU cache harness now models that optional package as absent in its child process only; installed Core/Sage and Production remain unchanged. Focused rerun is recorded in v38-main-publication-20260907/focused.xml. Do not relabel the initial run as full-suite PASS. No further workflow test runs after the user's stop instruction. -- Evidence: D:/Codex/_test_results/ComfyUI-H3-Continuum/v38-main-publication-20260907. Source snapshots verified before changes. This is GitHub source publication only, not a GitHub Release/tag or Registry publish. Runtime synchronization and Registry official validate/pack remain separate; user backend and GPU were untouched. - -## README accuracy corrections (2026-09-07) - -- Corrected the English/Japanese README only: insert Core Create Video before Save Video; distinguish automatic nonce0, explicit positive nonce, interrupted resume and review Retry; scope historical compatibility promises to their releases and preserve the exact current seven-node boundary; identify Audio Switch as Core; align Japanese Advanced/Manual visibility guidance; separate the latest CPU1,154/1,154 audit from historical V3.6/GPU acceptance. -- Refreshed only README-related hashes in Registry (104/104 matched) and source Manifest (254/254 matched). Final focused CPU regressions90/90 PASS; initialization tripwires stayed clean. README local links53/53 resolve and Markdown fences/whitespace checks pass. Evidence: D:\Codex\_test_results\ComfyUI-H3-Continuum\v38-readme-correction-20260907. Initial six one-file snapshots verified under before-readme-correction-*-20260907_195135. -- No workflow, image, ZIP, generation code, public schema, installed runtime, backend, commit, push or release change. The prior runtime synchronization remains pending separately; documentation checks do not promote release/GPU-quality status. - -## CPU release hygiene fixes and ZIP scope correction (2026-09-07) - -- The previously inspected ZIP was D:\Codex\_git_push_work\ComfyUI-H3-Continuum\node.zip, not the user's Continuum.zip / Continuum3-8.zip backups. Its distribution role was never established; withdraw the ZIP-based launch blocker. Backup/local ZIPs are excluded from this release check and remain unchanged. The older audit report carries this correction at its top. -- Fixed only hardening.format_memory_snapshot's CUDA observation guard: read counters only after CUDA is already initialized. Added three CPU tests for no probe/no tensor or RNG mutation, initialized-counter preservation, and nonfatal diagnostic failure. The real-Core cache test now uses explicit CPU bootstrap, initialization tripwires, and the diagnostic-only Kitchen capability bypass. -- Full guarded pytest: 1,154/1,154 PASS in55.60s, zero deselection and zero intercepted initialization calls in recorded guard logs. Focused tests60/60 PASS. Registry104/104 and source Manifest254/254 refreshed for current declared files. No Sampling, Audio, mask, seed, SIGMAS, public schema, workflow, or ZIP change. -- Reconstructed105-file Registry payload (104 declared files plus manifest) under D:\Codex\_test_results\ComfyUI-H3-Continuum\v38-cpu-release-fix-20260907\registry_payload, without using or creating a ZIP. Isolated CPU import, public7-node registration, PackedLayout, diagnostics and atomic JSON replacement PASS; CUDA remains uninitialized. -- Runtime update plan is a dependency-complete two-file sync of hardening.py and run_storage.py; only added import is stdlib time. One-file snapshots of each installed target verified. Deployment attempted no writes because user queue was running1/pending0. Existing backend remains untouched; disk synchronization is pending an idle queue, and an eventual user-managed restart is still needed for the running process to load the changes. - -## V3.8 prelaunch CPU audit (2026-09-07, Release HOLD) - -- Fresh guarded full suite: 1,149 passed / 2 failed, 1,151 total in 99 modules; no deselection. Failures: stale Registry manifest and real-Core cache test launching without CPU bootstrap. Same cache harness passes all four assertions under explicit CPU/W2 bootstrap; original tests remain unchanged. -- Source CPU/Core 0.34.5 probe: all seven public nodes, callable inputs, native PackedLayout and Fixed prompt self-test PASS. V3.8 core workflow 19 nodes/25 links and user Spectrum 32 nodes/38 links pass graph/schema checks; external Spectrum/KJ/Easy/rgthree sockets checked via GET metadata only. Spectrum remains byte-identical to user Downloads SHA E490C87E4995930F95C8FFFC4C678111D7897E74003E1962B9B4A247BA43F4AC. Python226/JS7 syntax PASS. -- Historical observations: Registry manifest4/source Manifest7 mismatches before record update (subsequently repaired above). Root node.zip has75 files and an incomplete import, but is not an established distribution artifact and is excluded from the launch verdict. Runtime source diff was functional only in run_storage.py (source-only Windows atomic replacement retry); reference.py and v3/reference_video.py differences are whitespace/line endings with matching AST. -- New independent CPU diagnostic finding: hardening.format_memory_snapshot reaches CUDA lazy init through mem_get_info even with Core --cpu when CUDA is available. Full suite blocked14 such calls plus1 Core startup call; standalone CPU diagnostic reproduces. All actual initializations were blocked. No Production/workflow/runtime fix, model load, Sampling, Queue submission, backend restart, commit, push, or publication. -- Source README local links exist; 44 references across shipped docs point to non-Registry assets and need GitHub/local-documentation handling. Full report and evidence: D:\Codex\_test_results\ComfyUI-H3-Continuum\v38-prelaunch-cpu-audit-20260907\CPU_PRELAUNCH_REPORT_JA.md. Record-only snapshots before-cpu-prelaunch-audit-state/worklog-20260907_182042 verified1+1 files. CPU wiring PASS does not grant GPU-quality or Release PASS. - -## V3.8 Civitai feature infographic (2026-09-07) - -- Rebuilt the supplied V3.7 feature infographic as a V3.8 Civitai graphic at the exact original `1536x1024` 3:2 landscape format. The new content covers Review Each Chunk, Resume/Regenerate, simplified V3.8 controls, and the shared Spectrum/Turbo graph; it explicitly retains the V3.7 Production foundation and states that Issue #13 remains open. Saved as `docs/images/v38-manual/h3-continuum-v38-whats-new.png` (SHA-256 `5E4B876585FAC3A2D580CDAF99B83EC3E10DA90036B7923B4DFFDCF0240560BD`). No workflow/runtime change. - -## Spectrum-only optional V3.8 workflow and top-level Git instructions (2026-09-07) - -- Added the user-supplied `MiniMax_H3_Continuum_V38_Spectrum.json` to `examples/workflows/` without changing its contents. Source and repository SHA-256 are both `E490C87E4995930F95C8FFFC4C678111D7897E74003E1962B9B4A247BA43F4AC`; its 32 nodes / 38 links parse with zero missing endpoint nodes. -- Kept `MiniMax_H3_Continuum_V38.json` as the only dependency-free Registry workflow. The Spectrum graph is a GitHub-source optional workflow and is excluded by the existing Registry packaging rules. No separate Turbo JSON is published; README explains how the same optional graph can switch from its saved Spectrum/20-step state to one task-matched LightX2V Turbo LoRA after Spectrum is disabled. -- Added `git clone` and `git pull --ff-only origin main` near the top of the English README and linked the LightX2V/ModelTC GitHub plus Hugging Face project. Per user direction, the Spectrum workflow's empty prompt, media filenames, node titles, widgets, and links were not edited. -- Validation: focused release/public workflow tests `11 passed`, with only the existing Registry manifest hash test deselected pending the final package freeze. Snapshot: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v38-spectrum-readme-workflow-20260907_162216`. No commit/push/tag/release. - -## English README complete V3.8 UI reference draft (2026-09-07) - -- Expanded the English README from the Review-only walkthrough into a complete reference for every user-facing socket/control/output on the seven-node V3.8 public surface. It now distinguishes Main, Advanced, Review/Take, three Continuum Settings, loader bypass, First/Last/Reference Image roles, Video Guide, Driving/Reference Audio, Reference Audios, Finalize, and Second Pass. Hidden frontend-managed IDs are not presented as editable UI. -- Added a top-level provider-neutral “ask an AI to read this manual” path using current official ChatGPT/Gemini/Grok information. The text does not promise that a pasted GitHub URL always imports a repository; Gemini's explicit Import code route and README paste/upload fallback are stated. -- Copied seven user-supplied PNGs unchanged into `docs/images/v38-manual/`: loader bypass, three Reference Images, First/Last Image, First Image Draft sizing, LightX2V LoRA selector, First Image tooltip, and Manual Width/Height. Source/destination SHA-256 matched for all seven; README now has 32 local image links and zero missing targets. -- Confirmed from source that Manual accepts 32x32, size selection is built into the V3.8 Sampler, loader OFF uses native bypass behavior, and the public surface remains exactly seven nodes. LightX2V's own Hugging Face/GitHub records were used to separate FL2VA/Ref2VA and 4/8-step targets; a 4-step LoRA at six inference steps is labeled workflow-specific rather than an upstream default. -- Recorded Issue #13 conservatively: still Open; Standard V3.8 has no active mitigation; the isolated 6x5 R6-A improvement did not become a Production claim because the later 4x8 gate produced gains 1.0 and A/C bit-exact no-op. This documentation change does not alter Production, runtime, workflows, manifests, Sampling, or backend state. -- Validation: focused tests `120 passed`; one registry-manifest test remains expectedly red because README plus pre-existing `run_storage.py` and `web/project_id.js` are not yet re-frozen into `REGISTRY_MANIFEST.sha256`. README image-link audit is `32/32`; no manifest was rewritten before the final workflow/package freeze. Snapshot: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\before-v38-full-ui-readme-20260907_152253`. No commit/push/tag/release. - -## English illustrated continuation manual live revalidation (2026-09-07, Continue PASS) - -- Used the user-owned `127.0.0.6:8188` Chrome workflow `MiniMax_H3_00058_` through Computer Use with Turbo4 v1.2, actual Steps 4, Euler/simple, Spectrum OFF, Draft 0.30 MP, fixed seed, Review Each Chunk, Progress ON, and 2x5 seconds. The backend was not stopped or replaced. -- Fresh Chunk 1 reached the three-action review panel. Selecting `Use it and continue` did not execute by itself; the top-right blue `Run` queued the action. The next Queue sampled only Chunk 2 (Sampler UI time 43.738s), reused the accepted Chunk 1, and reached `Saved sequence is complete` at 10 seconds. First Queue Sampler UI time was 103.802s; do not interpret the cold/warm difference as a general speed ratio. -- Added exact UI crops for review actions, selected Continue, completed sequence, Back-to-Settings completion state, Render History actions, and Regenerate From with visible Variation Nonce. README removed the obsolete retry-failure warning, uses the new screenshots, explains that Chunks is the final total, and updates the diagnostic four-step expectation to `sampling_steps_total=4`. -- Evidence full screenshots are under `D:\Codex\_test_results\ComfyUI-H3-Continuum\v38-manual-live-20260907`. Snapshot before edits: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\before-manual-steps4-capture-20260907_142631`. No commit, push, tag, release, or backend shutdown was performed. - -## V3.8 Continuation Regression Final Gate (2026-09-07, Pre-GPU PASS / approval pending) - -- Supersedes the stale restart-required review status below. The repaired Review state was live-validated: `Try this chunk again` regenerated the selected chunk and returned the three-action review screen; after the user disabled an accidentally enabled Spectrum node, `Continue / Next` completed normally. Manual screenshots remain deferred. -- Current task follows the supplied `H3 Continuum V3.8 — Continuation Regression Final Gate`: compare current Standard/Balanced22/Audio ON Masked AV against Compatibility Reference Context under one frozen `4×8s`, `896×896` GPU A/B. No Production transport change is allowed unless GPU result is Case A. -- Snapshot `pre-v38-continuation-regression-final-gate-rg-20260907_110054`:935 entries, manifest SHA `DD62DCA87437CABB049D16BFB720DF45FAC04988096C7A3827433D95206CD698`, creation-time source mismatch0. Normal snapshot helper hit the inherited pytest-cache ACL; verified robocopy+rg fallback retained the same authoritative source. -- Code audit confirms V3.4 final code baseline `d3dab7b` uses fresh-target Reference Context; current Standard/Balanced22/Audio ON uses masked AV target prefixes and Compatibility uses Reference Context. Both remove the later-group hard First Image keyframe while retaining original visual/Qwen identity tokens. -- Actual Comfy CPU Shadow PASS: Standard has exact Video7/Audio37 tail prefixes with zero prefix masks and no continuation refs; Compatibility has one exact AV ref, fresh zero target, no mask, target-head MM-RoPE alignment and preserved `position_ids` identity. CUDA remained uninitialized; owned PIDs/8190/HTTP ended. -- Pre-GPU focused5/5 and syntax PASS; stage/source runtime153/153 exact. Frozen semantic graph diff is only `continuation_backend`; Spectrum/Sol/Still/Driving/Reference/Last/Run Storage/Second Pass/Hi-Res/R6-A are OFF. Protocol SHA `7c525971a0a98694f75915b304c349b5f95d59ae0d450a07efd98ceb91ab4736`; execution manifest SHA `3f801370f69e8709f24a6849535483fbb00d49978ba419acf779c127d7afd412`. -- GPU authorization artifact is absent. Negative launch test refused before creating a run or opening8190. GPU Sampling, A/B result, reset/seam and Case A/B/C are pending explicit approval. User-owned8188 is untouched; no Production/commit/push/tag/release. -- Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\v38-continuation-regression-final-gate-20260907\PRE_GPU_REPORT.md`. The previously recorded fixed-task id was no longer readable; the current task list resolves title `H3情報チェック` to ChatGPT conversation `6a8ef934-10ac-83e8-9af2-9e2417af7224`, but detailed handoff was rejected because this changed destination identity lacks fresh explicit authorization. No workaround was attempted. Mandatory review and GPU remain pending user authorization. - -## Regenerate From / provenance reuse repair (2026-09-07, installed / restart required) - -- Immediate current task: reach the user's actual Chunk1-review screen with Continue / Retry / Finish buttons, then STOP before generating Chunk2. Manual screenshots and transport research remain deferred. Do not fake readiness or delete existing media. -- Actual UI run29e95cfc-1c9d-41fd-b32c-0d07855353a6 submitted Review Each Chunk,2x5s,Regenerate From Chunk1,nonce0,Continue / Next,Take Automatic. Unexpected result: cb575f0c6aa00705 nonce1/new_revision,2 reused/0generated,10s video00070,52.35s. This is NOT successful first-chunk regeneration. -- Root cause: prepare's provenance candidate path checked ancestry/lineage/prompt but ignored changed per-chunk sampling contracts. `_valid_provenance_prefix` now optionally enforces actual producer-revision chunk-contract hashes from the requested branch boundary onward; prepare enables it. Prefix before the cut remains reusable, same-nonce interrupted work remains resumable, explicit Take selection remains separate. Stored-manifest validation is unchanged. No new hard stop or Sampling/Audio/Assembly/schema change. -- Also repaired blank Render History: actual custom canvas widget now draws selected/canonical Take text instead of relying on an unsupported multiline primitive. Existing transient serialization guard retained. Lifecycle fixture verifies that Selected text is actually drawn. -- Tests107 PASS (9 new on-disk provenance cases plus review/branch/control/execution suites); UI19 PASS; extra canvas-draw fixture PASS; diff check PASS. First test collection failed due to importlib-mode fixture import and was corrected without production changes. Stage AST confirms ONLY prepare/_valid_provenance_prefix differ from previous runtime, exactly matching tested source, zero import changes; old source-only atomic JSON helper remains excluded. -- Installed runtime run_storage SHA0E402AD912926AE02FDC2A50BED9009B4C3A090EF6D52F6344C3B26FA33C1676; JS SHA7B318BE7E0A6FFA7A0B924F149EE90C10E4EBFB731DA2BC40297BAD0ECF63269. Full runtime snapshot181files before-review-reuse-runtime-20260907_104350; source scoped4files before-review-reuse-scoped-20260907_104350 (normal helper hit inherited cache ACL). -- User-owned8188 remains running old Python code, queue0/0 at deployment. User restart and browser reload REQUIRED before another Run. Then keep Regenerate From Chunk1 for exactly one Review execution, verify1generated/1of2available,review_ready and visible3buttons. Reset manual Regenerate From to Auto through UI before later continuation (do not rerun Chunk1 inadvertently). Smart Retry GPU still unverified; no completion handoff/commit/push/release. Previous full-suite2 failures remain documented below. - -## Completed-review UI repair (2026-09-07, deployed / browser reload and GPU retry pending) - -- Supersedes the older diagnostic-only status below. Review identity repair is installed in runtime run_storage.py (SHA59593daf4e2021bad2e6849427aae95a439220745f582b406ea1d240b19ebe45): canonical set observation and Core archived parameter dtype observation prevent false LoRA/VAE identity changes. CPU169 focused tests passed. Post-fix fresh Chunk1 `45dc7891-f3a8-4995-8bd7-25c1f3e959d2` and Continue `ffff7252-33b9-4f38-8bf7-fe3033c2d453` succeeded; revision99684d4a78b5855b, Chunk1 file SHA unchanged, only Chunk2 generated, 10-second video00065. Smart retry GPU remains unverified. -- Current UI failure independently reproduced: `/view?...project.json` returns200, canonical99684d4a78b5855b is complete with review_unit2, while frontend reviewReady accepted only review_ready. Backend already permits Regenerate Current for complete+review_unit. User Runs638b84ae and2c52c22f actually submitted Continue / Next and reused2/generated0, not retry; latestvideo00068, workflow25.34s. -- Changed web/project_id.js only for the runtime UI: backend-derived completed panel remains accessible; valid reviewed unit allows retry; completed Continue/Finish hidden; history/settings retained even for complete without a retry unit. No Sampling/Assembly/schema/status/persisted-revision changes. Source/runtime JS exact SHAB571FD4E061B113931D5470DD9844CAD77390B5227CC0EF05576ECCDA9662812. Scoped web snapshots7+7files and records3files verified under before-completed-review-*20260907_101839. -- New real-JS lifecycle fixture covers initial/partial/running/interrupted/completed,1..6 chunks, Terminal Merge label, one-shot queued retry, settings round-trip serialization parity, history, reload and failed fetch. Focused128 passed; additional frontend15 passed with one distribution-manifest hash failure. Full suite:1139 passed /2 failed (same manifest mismatch and identity test assumes process-global CUDA remains uninitialized after earlier tests; isolated identity suite passes). Do not claim full-suite PASS or pure CPU-only full-suite execution. Package/Release remains HOLD; these two failures need separate disposition. -- Auto-review blocked browser Ctrl+R because current00058 tab is dirty (`*`). No reload or extra GPU Queue occurred. Ask the user to save/reload or explicitly approve reloading the unsaved tab; do not circumvent the block. Then verify completed UI, select Try this chunk again, submit once, compare saved Chunk1 SHA and generated/reused counters. User-owned8188 remains running. Manual screenshots and Standard/Compatibility proposal remain deferred; no commit/push. Completion handoff is pending the live repair gate, not yet complete. - -## Review retry diagnosis follow-up (2026-09-07, restart required / root cause still unresolved) - -- User authorized fixing the live retry failure. Read-only CPU load of saved revision `52e4e5124afd5d7a` passes `_validated_review_head` and `find_latest_review_head` against its stored contract: prefix1, review_ready, no notes, CUDA uninitialized before/after. Saved data corruption is not demonstrated; the actual retry-time contract remains uncaptured. A model/runtime fingerprint change is a hypothesis, not a confirmed cause. -- Added hash-only mismatch diagnostics to `run_storage.py`: when no compatible head exists, report up to three nearest stored contracts and differing contract sections. Retry retains its original error and rejection policy; no unsafe fallback, identity relaxation, Sampling/seed/mask change, or automatic fresh generation. Successful lookup skips the new comparison. Tests: Run Storage/review79 plus policy/cache/UI/branch83 =162 PASS; diff check PASS. -- Installed only the three diagnostic-definition changes into runtime `run_storage.py`, SHA `16f0bb17b863dc0b1aef95656deae9a4783338b35145f010bec95a661feae6df`. AST audit proves no other runtime/import changes and exact agreement with tested source for those definitions. The source's pre-existing atomic-replacement retry helper was intentionally NOT included in this narrow deployment. Full runtime snapshot181 files: `before-review-mismatch-runtime-20260907_093306`; source scoped snapshot4 files/SHA4: `before-review-mismatch-scoped-20260907_092947` (normal source helper encountered existing cache ACL). -- Diagnostic code is on disk but the user-owned8188 process has NOT been restarted or stopped; queue0/0. User restart is required before further Computer Use retry diagnosis. No new GPU run, publication, final manual validation or completion handoff. Resume using evidence `D:\Codex\_test_results\ComfyUI-H3-Continuum\v38-manual-live-20260907\RETRY_DIAGNOSTIC_STATUS.md`; do not claim the underlying bug fixed. - -## English illustrated continuation manual (2026-09-07, Computer Use recovered / retry validation FAIL) - -- Computer Use now initializes successfully. Used the existing Chrome tab `927290933` (`00058`, user-owned `127.0.0.6:8188`) directly. Exported the current UI workflow before edits and snapshotted five files at `before-live-manual-scoped-20260907_090852`. Changed only seed control to fixed and Run to Review Each Chunk (UI enabled Progress automatically); retained supplied Turbo4 v1.2 / actual4 Euler/simple / Spectrum ON / KJ Sage / blank prompt / 2x5s / effective544x544. -- First UI Run PASS: prompt `e2c6038a-6403-4b27-bc4e-4d390a61741e`, backend execution75.232s, sampling30.447705s,120frames/5s, video `D:\output\video\comfy_video\video\MiniMax_H3_00064_.mp4`. Review panel actually appeared. New exact-pixel crops show settings, blue top-right Run, review-ready, and selected retry; README distinguishes top-right execution Run from the in-node Run setting (review messages still say Queue). -- Second UI Run, Try this chunk again: FAIL before new sampling, prompt `f8c18378-7a42-40b5-8408-19e8e86b877b`, `Regenerate Current requires an existing reviewed unit`. Full submitted graph differs only by `review_action`. Saved manifest remains `review_ready`, unit1..1, resume_safe=true; saved chunk SHA matches manifest. The read-only trace locates missing compatible review-head resolution, but why it rejects/misses this stored head remains unresolved. Do not blame a seed change or claim retry/continue/finish verified. Stop further GPU runs pending diagnosis/fix authority. -- Runtime/source check: review_control.py, v3/nodes.py, web/project_id.js exact; run_storage.py differs only by the source's Windows atomic JSON replacement retry helper. No evidence links that difference to the observed missing-head error. No runtime installation or code fix performed. Queue running0/pending0; user backend intentionally left running. Source README has an explicit draft-validation warning; no commit/push. -- Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\v38-manual-live-20260907` contains exported workflow, both full prompt/history records, summaries, saved manifest, full screenshots and UI action timestamps. Failure screenshot kept as internal evidence, not public manual artwork. Remaining history/settings/continue/finish/regeneration/extension screenshots and final release documentation review are pending. Earlier tool-blocked notes below are historical. - -- README now contains a general 11-section Review/continue/retry/finish/settings/history/regeneration/extension/timing guide, with six unmodified user-supplied UI crops under `docs/images/v38-manual/`. Two chunks is only an example; total-vs-added count, fixed Base Seed, later-section rebuild, and Last Image/Terminal Merge exceptions are explicit. README_JA is unchanged by this task. -- Source/code cross-check and six PNG relative links plus section anchors PASS; no claim of fresh UI or arbitrary extension GPU validation. Prior two-Queue six-step timing is identified separately; downstream time is not individually profiled. GitHub-ready source assets only; Registry/package refresh and commit/push are not performed. -- User then supplied a running ComfyUI at `http://127.0.0.6:8188/`, workflow `00058`, Turbo at four steps, and requested live Computer Use screenshots plus execution timing. Use that user-owned backend after visual verification; do not stop or replace it. No Queue, UI edit, or new GPU execution has occurred in this documentation task. -- Both `node_repl` (`@oai/sky` bootstrap) and `cua_repl` fail before execution with `failed to write kernel assets: 指定されたパスが見つかりません。 (os error 3)`. Resetting each kernel did not resolve it; workspace/TEMP/TMP exist. Exact missing internal path and root cause are unknown. No unsupported screenshot/desktop automation fallback was used. Live capture remains blocked pending tool recovery; record new observed UI before any action. -- Verified four-file pre-edit snapshot: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\before-illustrated-review-readme-scoped-20260907_085726`; standard helper first failed on inherited `.pytest_cache` ACL. Resume from README and the current-scope note in `docs/V38_BEGINNER_MANUAL_PLAN_AND_CAPTURE_SCRIPT_JA.md`. Completion review is pending until live documentation validation is complete; do not send to the unpinned duplicate H3 task. - -## Issue13 R6-A Turbo4 v1.2 / actual 6-step / 0.30 MP A/B (2026-09-07, VALID / NEGATIVE-HOLD) - -- Executed the supplied Turbo4 v1.2 / 6-step Euler/simple / Draft0.30 MP settings as an adapted `6x5s` efficacy test, not an exact reproduction of the supplied `2x5s` workflow. Effective size was `544x544`; prompt remained empty; Audio Continuity/Balanced22/KJ Sage were ON. Fresh Group1 was shared; A had R6 OFF and B differed only by frozen global latent AC contraction. -- Execution contract PASS: both arms are `720f/24fps/30s`, stereo32k PCM `960000` samples; Assembly exact; Sampling traces complete; resources `5/5` with hard-stop/contract errors zero; both dedicated backends normal-shutdown with owned PIDs gone,8190 closed and HTTP offline. Exactly five policy evaluations occurred: G2 required no-op, G3 natural no-op, then gains G4 `.9`, G5 `.95440975`, G6 `.9`. Raw AV is exact through G3 and diverges from the first effective intervention at G4. -- Numeric promotion evidence is NEGATIVE/HOLD for this condition: endpoint Laplacian `+8.28%`, Gradient `+11.85%`, Contrast `+113.44%`, Shadow `+71.07%` worse; motion proxies about `1.6%` lower and seam metrics warn worse. Highlight endpoint improved `99.14%` and mean-saturation endpoint improved `20.20%`, but they do not offset the primary/guard negatives. Perceptual A/B playback remains pending; seam ratios are not a perceptual-cut claim. -- Interpretation is narrow. The empty prompt produced severe shared semantic excursions before R6 acted, including near-white G3 and green-background G5, so this is weak evidence for Issue13 natural cumulative drift. Do not generalize to R6 overall or invalidate the separate earlier Turbo8 numeric candidate. No Production/public schema/default/package or release change. -- The first attempt stopped pre-Sampling on expected-plan evidence ordering; it was preserved and the isolated runner ordering was corrected without graph/Sampling change. The completed wrapper later exited only because atomic `RESULT.json` refused to overwrite that first attempt; all A/B artifacts were durable and shutdown complete, so no GPU rerun was needed. -- Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r6a-turbo4-6step-0p3mp-20260907\TURBO4_6STEP_0P3MP_REPORT.md`. Fixed `H3情報チェック` completion review `bd47c1b1-8aa6-4f87-b24a-efa7c8d74fe7` accepted `EXPERIMENT VALID / EXECUTION CONTRACT PASS / NUMERIC PROMOTION EVIDENCE NEGATIVE / HOLD / DO NOT PROMOTE` with no mandatory correction. Source-record snapshot `pre-r6-turbo4-report-record-filtered-20260907_081550` has `919` files after the standard helper met the inherited `.pytest_cache` ACL. No commit/push/tag/release. - -## Issue13 R6-A resumed B: numeric candidate, perceptual review pending (2026-09-07) - -- Fixed completion summary review25ee8534/9747f470 read: accepted with explicit NUMERIC GPU EXPERIMENTAL CANDIDATE qualifier, not perceptual PASS. Full30s A/B playback/listening is next, before additional GPU/new workflow experiments. Review did not independently inspect local media/artifacts. Final source230 code hashes unchanged; diff --check0; B41648/40316/36912 absent,8190 listeners0. -- User explicitly resumed B before supplied Turbo/Spectrum workflows or Audio Continuity experiments. Completed A evidence reverified (R3B rawAV12/12 plus exact historical decoded/PCM and owned shutdown); interrupted B retained. New fresh B0b0b607953934a6bb2e7ed7142784ae6 completed13m08s from shared savedG1 under unchanged frozen protocol79bbe9a5..., after53/53 resume CPU tests and fixed-task prelaunch review542d0853/3bfd0ff3 accepted inside-lock checks. No numerical method or threshold changed. -- EXPERIMENT VALID / FROZEN NUMERIC GATES PASS / PERCEPTUAL REVIEW PENDING. Lap endpoint drift39.86749->13.36942 (66.47% reduction), Gradient72.91%,Highlight91.17%,Contrast26.82% better. Saturation4.10% worse; seam1.38317->1.51302 (9.39% worse); both within frozen guards. Motion/detail/PCM numeric screens PASS. These are metric-drift changes, not overall quality percentages. -- Counterevidence: largest benefit is Group6; G5 Lap nearA and Gradient slightly worse. Peak Lap excursion reduction only15.15%, so uniform long-trajectory suppression is NOT established. Paired stills are coherent but full playback/listening and perceptual identity/detail/seam PASS remain unverified. One scene/seed only, not Issue13 solved or Production promotion. -- Actual invariants/noise5/5 match, rawG1/G2AV4/4 exact, scope violations0,720frames/30s/960000sample stereo32kHz PCM. GainsG2..6=1,.991727,.995747,.994723,.973105. Both owned backends normal shutdown/PID/8190/HTTP confirmed; user backend untouched. No additional GPU phase started. -- Evidence `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r6a-pre-gpu-20260907\FINAL_REPORT.md`, QUALITY_SCREEN.json,PAIR_REVIEW. Two supplied workflows retained unchanged in user_workflows, NOT executed/mixed intoB. Completion review requested at fixed H3情報チェック before any next phase. Source record snapshot919 pre-r6-B-completion-record-excluding-cache-20260907_063034. Production/Release/A5/general A8b HOLD; no commit/push/tag/release. Earlier user-paused state below is historical. - -## Issue13 R6-A: Standard A complete, B USER-PAUSED (2026-09-07) - -- Latest user instruction stopped continuation and requested analysis of A only. GPU authorization is now false; do not resume B or start another GPU run without a new user instruction. The stop arrived after B Group2 had begun (last log2/8 steps); immediate launcher interrupt ended the run. This is not a B quality FAIL or completed experiment. -- Fresh A completed13m04s: R3B rawAV12/12 exact, historical decoded metrics and PCM exact, five Sampling/noise records, intervention-scope violations0, normal A shutdown confirmed. Review of the corrected PreGPU gate was accepted by fixed summary reply70782869-06e2-461a-96fb-0edb978f4eea before launch. -- All six A/B owned PIDs41304/21224/20080/19020/2276/4140 independently confirmed gone;8190 listener0/HTTPoff. B normal queue-drained shutdown was not established because immediate interruption took priority. User backend untouched. Pause evidence `issue13-r6a-pre-gpu-20260907\USER_PAUSE.json`. -- A-only CPU analysis:720f/24fps/576x864/30s, central25-frame means show Lap248.55->288.42 (+39.8675 units, +16.04%, NOT +39.87%), Gradient+5.44%, highlight clipped fraction0.1794%->0.5662%. Sampled subject/composition remains coherent; late edge/texture strengthening persists. Strongest normalized seam at15.0833s=1.3832. PCM intact/exact but RMS~-54.9dBFS; no listening/full-playback perceptual PASS claimed. This is baseline reproduction, not mitigation success. -- Evidence `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r6a-pre-gpu-20260907\A_ANALYSIS\REPORT.md`, summary/seam/detail/join artifacts. Fixed summary review c4a59d67/f1b2f17a accepted interpretation, emphasizing that observed late-stage edge strengthening is not a fresh causal proof, nor a playback/listening PASS. Review does not authorize GPU resume. Source-record snapshot919 `pre-r6-A-analysis-record-excluding-cache-20260907_034446`. Production, commits, push, release unchanged. - -## Issue13 R6-A corrected Pre-GPU freeze (2026-09-07, supersedes prior freeze) - -- User approved correction, CPU verification, refreeze and the single Fresh A -> conditional Fresh B GPU pair; no renewed GPU permission is needed for that pair. Fixed-task completion review is pending before launch. GPU efficacy is still untested. -- Independent local inspection corrected signed-negative Laplacian acceptance, seam threshold discrepancy, unrelated two-secondary-improvements requirement and missing actual Sampling invariant recording. Absolute Laplacian threshold remains31.89399101047766; per-chunk Lap/Gradient>=80% shared Group1 is an added blur screen, not perceptual proof. Secondary absolute drift<=1.2A, motion>=.8A, seam<=1.2A. One-seed candidate only. -- Symmetric observer records actual seed/noise/SIGMAS/conditioning/ordered wrapper and sampler evidence; B must match current A before model execution. Intervention source/reference/Audio/generated-region/mask hashes remain exact; Group2 prefix no-op. Completion manifest requires both sampling_trace and pin_renorm evidence. Fresh A rawAV12/12 and exact historical decoded/PCM parity remain mandatory. -- CPU46+controller/lifecycle45=91 PASS; CUDA tripwire clear in correction suite; canonical/stage230 code SHA exact; upstream14 and execution259 hashes exact. New protocol SHA79bbe9a5b671ed2d6d2c66d0d549e759ab28bef1b4a67938cd0e80a3049a442d. Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r6a-pre-gpu-20260907\CORRECTION_GATE_REPORT.md`. -- Research pre-edit snapshot353 files; pre-record source snapshot919 files `pre-r6-correction-record-excluding-cache-20260907_031923` after inherited .pytest_cache ACL prevented ordinary helper completion. Production/commit/push/release unchanged. No automatic retry or sweep. - -## Issue13 R6-A Pre-GPU Gate PASS (2026-09-07) - -- Frozen comparison is one pair only: A is Standard/Balanced22 with the R6 hook disabled; B differs only by enabling the global latent AC scalar contraction on protected Video-prefix slots. Shared saved Group1, 576x864/24fps/6x5, seed131325, FL2VA INT8/Turbo8/Euler/simple/KJ Sage and all other settings are fixed. This is not a texture- or frequency-specific correction. -- Fresh A must pass R3B raw Video6/6 + Audio6/6 exact plus PCM/artifact/resource/Assembly/owned-shutdown checks. It must also exactly reproduce frozen historical A decoded metrics and PCM after excluding only run ID and output path. Any raw or decoded baseline difference prohibits B. Historical Laplacian drift39.8674887631 and B threshold<=31.8939910105 remain fixed; motion>=80%A, seam<=1.2xA, secondary Video metrics, PCM and perceptual review are guards. -- Dedicated CPU tests passed55, including all existing fail-closed cases, authorization refusal, graph parity, and exact-A-quality acceptance plus a 1e-9 motion-metric rejection. Upstream hashes14/14 and execution files251 are frozen. Protocol SHA `48d110db7d376622f4275125207220a997d3134c1ecdf48276cd37d65fab936a`. GPU authorization artifact is absent; no backend/GPU ran;8190 listener zero. Production remains unchanged. -- Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r6a-pre-gpu-20260907\PRE_GPU_REPORT.md`. Snapshot `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-r6a-pregpu-record-excluding-cache-20260907_024434` has919 files; ordinary helper first stopped only on inherited `.pytest_cache` ACL. Fixed review aa0cb846-a49f-44ea-a3e3-e682d6a144d5/9a9dc5e1-3363-459c-bc3e-86511dfb97e2 required decoded-A parity; after correction, review91ee90f4-ebf4-4659-a329-e85747c4aac0/a5c3e54b-6ff7-4a08-84f2-a11c58a42664 accepted final Pre-GPU PASS with no remaining design correction. GPU still requires explicit immediate approval. - -## Issue13 R6-A actual Comfy CPU Shadow PASS (2026-09-07) - -- One owned CPU-only Comfy backend completed an actual Queue/history request using staged public V3.8 registration, Core NestedTensor, the real masked AV prefix builder, and saved R3B rawAV. No model/VAE/noise/Sampling. OFF returned original latent object for Groups2..6. ON Group2 gain1.0 was exact no-op; only Groups3..6 protected Video first7 slots changed with gains0.9917270/0.9927173/0.9882362/0.9733208. -- Generated Video, whole Audio object/content, masks object/content, metadata, conditioning fixture, SIGMAS, current tails, fixed Group1 reference, saved raw12 and Python/Torch RNG remained exact. Five events shared one reference SHA.9 prototype tests and15 actual verification checksPASS. -- CUDA false at import/bypass/node/shutdown; no tripwire. OwnedPIDs9704/36796/29444 ended; queue empty,8190 listener/HTTP off; user backend untouched. Evidence `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r6a-actual-comfy-shadow-20260907\REPORT.md`. Snapshot `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-r6a-shadow-record-20260907_013958` has924 files. -- Pre-GPU Gate remains incomplete: actual model Sampling OFF rawAV12/12, noise/derived-seed/full-conditioning/wrapper/Assembly invariants, execution hash freeze, and decoded AV quality remain GPU-stage evidence. GPU not started and requires explicit approval immediately before launch. User-authorized fixed summary review 6ae817e0-7654-4c06-a06b-75bd9eee42fc /a1bab86c-09b8-4132-aa30-91e2f85bb637 accepted classification with no mandatory correction. R6 does not directly change Sampling-input Audio, but joint AV generation may indirectly change output Audio; GPU must measure it. Review is not independent local-artifact inspection. - -## Issue13 R6-A Pin Renorm CPU design audit PASS WITH CONDITIONS (2026-09-07) - -- Isolated non-Production prototype freezes Group1 final seven Video slots as the Balanced22 reference and applies `current_mean + gain*(current_tail-current_mean)` only to the protected seven Video prefix slots for Groups2 onward. `gain=clamp(reference_std/current_std,0.90,1.00)`; amplification prohibited. Audio37T, masks, generated regions, seed/noise/SIGMAS/conditioning/Assembly/State/Session/RunStorage remain unchanged by contract. This is global latent AC scaling, not texture-only/frequency-selective. -- Actual R3B shadow requested gains feeding Groups2..6:1.0000000,0.9917270,0.9927173,0.9882362,0.9733208. Thus Group2 is unchanged and intervention first appears at Group3; maximum measured reduction2.67%. Per-channel ratios are heterogeneous, so decoded efficacy/motion safety remain unproven. -- Focused CPU9 passed: OFF object identity and RNG neutrality, Group1 exclusion, source/reference immutability, Video-prefix-only scope, Audio/mask/metadata preservation, bounded/no-amplification gain, and invalid/degenerate/shape/transport fail handling. Actual rawAV finite/expected shapes; CUDA remained uninitialized; no backend/GPU Sampling. Evidence `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r6a-pin-renorm-cpu-20260907\REPORT.md`. -- Valid pre-record snapshot `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-r6a-cpu-record-20260907_012541` has924 files. GPU not authorized by this CPU Gate; next phase requires isolated actual-Comfy OFF parity/Shadow/lineage wiring and frozen decoded evaluation, followed by explicit GPU approval under the latest instruction. User-authorized fixed summary review 05b4095a-89d0-4262-9323-d5932f3ea630 /f8e60c80-b3d1-4637-9cbb-48f490d178f6 accepted PASS WITH CONDITIONS. Numeric degeneracy contract is explicitly CPU float64,epsilon1e-12; reference <=epsilon fails, current <=epsilon no-op. Review is not independent local-artifact inspection. - -## Issue13 R5 5f actual GPU pair closed: PRIMARY QUALITY FAIL (2026-09-07) - -- Actual fresh A matched R3B raw Video6/6 + Audio6/6 bit-exact. PCM/artifact/plan/resource checks and full owned-backend shutdown passed before fresh B. B applied immutable Group1 first5f reference exactly for Groups2..6. Both720frames/30s and stereo32kHz960000sample PCM. Execution/integrity PASS; no OOM/nonfinite. -- Primary Laplacian drift A+39.86749 -> B+74.97015 (88.05% larger drift; not overall image-quality percentage), failing frozen <=31.894. Gradient drift91.44% worse. Several tone/color drifts improved, but cannot override primary failure. Motion/seam numerical guards PASS; PCM numeric screen clean, listening/full-playback perceptual verdict not established. -- DO NOT PROMOTE this fixed5f compound content+rows+AV-position intervention. No sweep; Issue13 unresolved; Release HOLD. No Production code/commit/push/tag/release change. Source230 py/js hashes match924-file pre-run snapshot. A/B owned processes zero and8190 listeners zero rechecked after completion; user backend untouched. -- Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r5-gpu-ab-20260907\FINAL_REPORT.md`. Fixed H3 information-check summary review f62e27e4-6b3c-477b-aa0b-7a25c9d20454 /827767df-4345-48e2-b511-f36b1eeeb583 read: no mandatory correction; not independent artifact review. - -## Issue13 R5 GPU A/B authorized; preparation frozen (2026-09-07) - -- User expressly authorizes continued GPU testing without repeated confirmation, within current R5 single5f A/B scope. Previous GPU-unapproved entries are historical. A actualR3B rawAV12/12 +PCM/artifacts/resource/plan/normalshutdown remain mandatory beforeB. No sweep/Production/publication authority added. -- Isolated runner/graphs at `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r5-gpu-ab-20260907`; PRE_GPU_REPORT.md and final execution hashes.14upstream/assets/protocol hashes matched;4CPU preparationtestsPASS. GPU not started at this record; mandatory fixed review requested before launch. DirectGPU startup never uses W2 CPU bypass. - -## Issue13 R5-W2 scoped CPU wiring PASS (2026-09-07) - -- Fixed summary review c03e9c5b-823c-4f74-93e1-bba5a8bd48c2 /56226d50-cf39-4acf-ab2c-1f5949fa947f read; accepts scoped PASS, no mandatory correction. Synthetic evidence is not quality/GPU parity. Actual A12/12 and R5 ON execution remain POST-approval GPU checks; preparation/freeze remains CPU work, not authority to start GPU. - -- CPU bootstrap alone bypasses kitchen INT8 availability; lazy/C initializer tripwires retained, CUDA availability API unmodified. Actual Fresh Comfy A/B fixture Queue/history and PCM-observed stage Finalize completed720frames/960000samples each with observer parity/RNG unchanged and CUDA uninitialized through preexit. No model/VAE/Sampling; R5 source and GPU Sage/KJ unchanged. -- Real A live denied B; current A synthetic raw12/PCM/evidence verified only after queue0/0 and owned PID/listener/HTTP shutdown, then rechecked under exclusive lock before CPU fixture B. Raw12 fixture is NOT GPU baseline parity. A41480/2120/9176 and B24760/5132/30700 ended. 15 offline evidence assertions plus37 regressions PASS. Source230 unchanged vs snapshot924 pre-r5-w2-20260907_000922. -- Evidence `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r5-w2-cpu-bootstrap\REPORT.md`. Full R5-2 NOT YET PASS: actual GPU runner quality metrics/resource/plan bindings and final execution freeze remain. GPU unapproved. Fixed summary review requested. No Production/publication change. - -## Issue13 R5-W1 first CUDA initialization cause isolated (2026-09-07) - -- Fixed-task summary review read:738aad5c-f71f-43fa-af16-b0f82de4a8e1 /0938013b-95fc-4e41-963b-0ff48cddec72. Accepts first-cause isolation PASS only; no remediation, no exhaustive-trigger claim, no inference of normal GPU Sage defect. Next CPU-specific workaround requires its own scope; not started. - -- One guarded startup intercepted Core attention.py54 -> comfy_kitchen.sage_attention.is_available:75 -> torch.cuda.get_device_capability -> _lazy_init before actual initialization. torch initialized false before/after; intentional exit86. No prompt/model/Sampling or automatic retry. First observed cause is CPU-unconditional Core/kitchen capability probe, before R5 registration; later triggers not ruled out. -- Nine offline checks PASS; source230 py/js unchanged against snapshot924 pre-r5-w1-init-isolation-20260906_235631. Owned26156/33568/15832 ended,8190 listener/HTTP offline. Evidence `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r5-w1-init-isolation\REPORT.md` plus full stack, command, result and hashes. -- Cause isolation PASS only; no remediation or installed-runtime edit. Full R5-2 NOT YET PASS; GPU unapproved. CPU-specific availability-probe avoidance remains proposed, retaining the tripwire and preserving eventual GPU Sage configuration. Fixed-task review requested. - -## Issue13 R5 actual Comfy wiring HOLD (2026-09-06) - -- Isolated stage/Sampler/PCM Finalize graph adapters created; nine CPU tests PASS. Actual Comfy object_info and nonce-only prompt/history binding worked. No model or Sampling request submitted. -- Strict probe detected torch.cuda.is_initialized=True despite --cpu and Device:cpu. CPU-only integration is NOT PASS; initializer unresolved. Do not automatically repeat startup or weaken the guard. All owned PIDs4812/10092/38456 and earlier attempts gone; queue0/0,8190 listener/HTTP offline. Production unchanged. -- Full R5-2 NOT YET PASS: real metrics/resource/plan binding, controller integration and final freeze remain incomplete. GPU unapproved. Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r5-comfy-wire-20260906\REPORT.md`. Snapshot pre-r5-comfy-wire-20260906_233825:924 files. Fixed-task summary review requested; awaiting reply. - -- Fixed review ec956664-22e1-4846-8023-e574b7967a2b / 02c95f2c-ef0e-42d4-83a9-afd26c748f4e read: summary-only PARTIAL wiring PASS, CPU-only claim rejected, full NOT YET PASS. CUDA runtime initialization is observed; GPU computation is not established by that fact. Next is initialization isolation and full controller/evidence/freeze, not GPU sampling. - -## Issue13 R5-2 CPU launch lifecycle (2026-09-06) - -- CPU lifecycle sub-Gate PASS: 8 tests, actual minimal loopback CPU service A/B start/shutdown, PID tree/create_time/8190/HTTP verified stopped. No ComfyUI/model/torch/CUDA/GPU. Cross-process exclusive lock, fresh controller identities/root, atomic completion-last publication with bounded retry, immutable decision hash and B recheck verified. First test exposed Windows read-only fsync Errno9; diagnostic r+b flush correction passes, no B launched on failure and A cleaned up. -- Final A PIDs14284/18348/38780 and B25704/40888/39560 exited;8190 absent. Fixture12/12 is not GPU baseline parity. Source230 unchanged versus snapshot924 pre-r5-launch-lifecycle-20260906_231926, diff check0. Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r5-launch-lifecycle-20260906\REPORT.md` and JSON/XML/frozen evidence. -- Fixed summary review `fd337f43-4b58-494a-bbf6-6339635fb0d7` / `913264ed-3b1b-42f2-8aaa-d8acd33930dc` accepts CPU Launch Lifecycle PASS. Full R5-2 NOT YET PASS pending actual ComfyUI prompt/history/resource/shutdown adapters and real R5 stage graph wiring/freeze. Future actual GPU A12/12 is post-approval B permission gate, not a prerequisite to running CPU preparation. GPU remains unapproved; no publication. - -## Issue13 R5-2 CPU evidence evaluator / Finalize adapter (2026-09-06) - -- Sub-Gate PASS: 37 CPU/Shadow tests. Evaluator reads actual safetensors keys/shape/dtype/SHA, recomputes PCM slices/assembly/pad/capture, checks artifact completeness/hashes/run provenance/settings/plan/resource and live-OS probe interface. Tests mock OS/launch only; no backend/GPU. Actual historical R3B 12 raw files hashed, 14 CPU assets frozen with mismatch0; source230 unchanged against snapshot924 pre-r5-runner-control-20260906_230811. -- Fixed review turn `fa12ae03-03e4-430e-a2eb-26408a82ab1b`, reply `cde10501-5542-4b83-b075-864125170228` accepts sub-Gate PASS only (summary review). Full Pre-GPU remains NOT YET PASS pending real launcher/controller context ownership, exclusive lifecycle, atomic completion-last publication, and actual shutdown E2E. Review proposes non-sampling service for shutdown E2E, but none was started; current CPU-only/no-backend scope is preserved and any service-start authority must be resolved before execution. -- Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r5-runner-control-20260906\REPORT.md`, SHADOW_TESTS.xml, R3B_BASELINE_RAW.json, HASH_FREEZE.json. No Production/runtime change, GPU approval, commit or push. GPU observer Sampling transparency remains unproven until separately approved Fresh A actual12/12. - -## Issue13 R5-2 real Assembly/Finalize PCM integration (2026-09-06) - -- CPU integration sub-Gate PASS: real Finalize/Assembly with synthetic decoded stereo32k PCM and 8x8 images, 85 tests (14 integration/predicate +25 detector +46 Assembly regression). No VAE/model/backend; CUDA uninitialized. Source230 code files unchanged versus snapshot924 `pre-r5-pcm-integration-20260906_224938`. -- Complete sample ledger checks input/copy order, exact retained content, hidden padding, natural958667 -> repeat-tail1333 -> final960000, capture SHA and restoration/RNG/input parity. Shortfall hidden by native padding, duplicate copy, wrong final pad and wrong capture point are detected. Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r5-pcm-integration-20260906\REPORT.md`, JSON/XML/fixtures and 23-file hash freeze. -- Fixed-task review delivered and read: turn `26c56b98-8172-4f3c-bd58-ff3d391d851e`, reply `771b11bf-9d7f-49f1-88c9-bdcd8d16335a`. Summary-only review accepts sub-Gate PASS. Full R5-2 remains INCOMPLETE pending runner integration, real file-hash A12/12 + actual shutdown E2E control, and final runner/prompt/prototype/observer execution-hash freeze. No GPU approval requested; user explicitly requires GPU waiting. - -## Issue13 R5-2 Audio CPU preparation (2026-09-06) - -- Audio CPU sub-Gate PASS: offline NumPy PCM screen and capture helper, 25 tests passed. Stereo32k/960000 samples, actual five cuts, per-channel RMS/spectral/edge/click/dropout limits frozen. Numeric clean means review pending; confirmed Audio harm fails R5 regardless of Video improvement. -- Natural Assembly 719f/958667 samples -> exact 720f/960000 adds 1333 samples. Future isolated runner must capture decoded counts, retained slices and pre/post adjustment; final count alone cannot establish no hidden shortfall. -- Full R5-2 remains INCOMPLETE: executable runner/capture integration, CPU validation and runnable prompt/observer hash freeze remain pending. No GPU/backend or Production edits. Model/media/shared Group1 hashes 8/8 match; 244 CPU assets frozen; source230 code files unchanged from snapshot924. Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r5-2-pre-gpu-20260906\R5_2_AUDIO_CPU_REPORT_JA.md`. -- Following explicit user CPU sharing permission, the previously denied report was delivered: turn `b738494e-a202-4736-a9c8-a2c6380d110c`, reply `bf27b4da-9d2c-4313-95dc-4d43b1f04867`. Review accepted Audio CPU PASS and thresholds, requiring real-path PCM ledger/capture integration. This requirement is now CPU-tested as recorded above. GPU requires separate later approval. - -## Issue13 R5 position-control CPU audit (2026-09-06) - -- Same-layout zero Reference is constructible, but it is not a neutral no-anchor control: Core default augmentation makes all 93,312 zero-latent row values nonzero; removing augmentation does not remove projection/modulation/unmasked-attention participation. Metadata without latent leaves 972 required condition rows missing. -- Within the current native Reference contract and without row/attention/position rewrites, an inert matched control was not found. Reclassify Standard-versus-R5 as generated Group 1 reference plus additional conditioning rows and Core-native AV positional shift; do not claim pure appearance-content causality or general mathematical impossibility of controls. -- Zero-ref versus real-ref remains a possible non-neutral content ablation, not a no-anchor baseline. No extra GPU arm has been authorized or run. R5-1 PASS WITH CONDITIONS remains; Pre-GPU design uses 5f only, Run Storage OFF and explicit shared saved Group 1. -- Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r5-position-control-20260906\POSITION_CONTROL_REPORT_JA.md` and `POSITION_CONTROL_RESULT.json`. CPU assertions passed, source tensor immutable, CUDA uninitialized, backend/GPU Sampling absent. Fixed-task turn `57811644-8575-4e2d-87cd-930a7065ad45`, reply `5ac513f9-ba7e-4814-87c4-d42bff3f2518` accepted `Position-Matched Control Audit PASS` and the limited reclassification. Next freeze is Standard A versus R5 B only, with Video quality, motion/identity, Video join, Audio join and Audio continuity guards. GPU remains unapproved. - -## Issue13 R5-1 isolated CPU/Shadow prototype (2026-09-06) - -- Implemented Default-OFF diagnostic scope, immutable 5f Group 1 Video-only reference, ordinary/Terminal sequence integration, exception cleanup and ON identity separation only in `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r5-1-prototype-20260906\prototype_src`. Production 230 Python/JavaScript files match the 924-file pre-change snapshot. -- CPU tests: 88 passed; actual unmodified Core PackedLayout definitions: 10 cases passed. OFF sequence parity, Group 2-6 fixed anchor, user-reference presentation/tags, Replay/Review/Branch and Terminal shadows passed. These are stub-sampling structural tests, not GPU quality or kernel parity. -- Conditional finding: native reference addition shifts absolute target Video and Audio positions by 8.333333 while preserving Audio values/count/relative timing. Do not claim absolute Audio position invariance. Persistent old-lineage selection after Group 1 replacement and ON disk-restart E2E remain unimplemented; proposed GPU scope must use explicit saved Group 1 and Run Storage OFF. -- Two full-Core import attempts initialized CUDA as an import side effect and exited without model loading/forward/Sampling/backend. Final layout runner executes unmodified Core layout AST definitions and verifies CUDA uninitialized. Ports 8188/8190 have no listener. Release/A5/general A8b HOLD; no publication. -- Formal verdict: CPU/Shadow PASS WITH CONDITIONS. Fixed-task turn `87d13aed-685c-4b5c-b13b-22a484da8766`, reply `f64a95b6-219d-4f8c-9073-006290220483` accepted it and requires a position-matched control feasibility audit before R5-2, or explicit reclassification as anchor plus native AV positional shift. A zero latent is not assumed neutral. No custom Core position correction is allowed. Evidence: `R5_1_REPORT_JA.md`, `R5_1_TESTS.xml`, `R5_1_PACKED_ROWS.json`, `R5_1_SOURCE_PARITY.json`. GPU remains unapproved. - -## Issue13 R5-0 Dual-Role Anchor / Tail CPU architecture audit (2026-09-06, PASS WITH CONDITIONS) - -- Audited a long-term Group 1 anchor and the existing short-term previous-tail transport without starting a backend or GPU. The current I2VA Standard path already retains the original First Image as Qwen visual tokens while Balanced 22 uses the immediately previous `22f Video / 37T Audio` as a masked target prefix; R5 therefore must add only the generated Group 1 appearance cue, not duplicate the existing first-image role. -- Rejected a Group 1 frame-zero keyframe: Core `PackedLayout` places it at the same position as the masked target head, so it competes directly with the previous-tail pose. The viable prototype route is one fixed Group 1 head `5f / 2 video slots` as a Video-only `minimax_refs` block, appended after existing user refs, while the previous `22f / 37T` AV tail, masks, restoration, trim, and Audio ownership stay unchanged. -- CPU evidence using the frozen R4 Standard Group 1 raw Video proved source immutability and separate segments. Baseline rows were `21,501`; the 5f Video-only reference produced `22,473` (`+972 / +4.52%`). A 22f reference is structurally valid but deferred at `24,903` rows (`+15.82%`) because it repeats substantially more Group 1 motion and approaches the R2.6 over-constraint mode. -- Shadow `PackedLayout` also accepted the hidden Video-only anchor after existing image/audio refs while retaining a final-frame keyframe; hidden anchor Audio rows remained zero. This proves packability only. Quality improvement, motion freedom, user-reference semantics, wrapper runtime behavior, and GPU cost remain unproven. -- R5-1 may proceed only as an isolated Default-OFF diagnostic policy: OFF bit-exact, Group 1 and tail immutable, one anchor from Group 2 onward, no Audio in the anchor, existing reference order preserved, no new schema, and safe Standard fallback when only an initial State is available without the Group 1 entry. Review/branch/replay and Terminal Merge must pass CPU/Shadow before any GPU proposal. -- Fixed-task review turn `3f6fc599-b9b0-4ca9-8e5e-8910cce205d6`, reply `3179d562-3414-41bd-8e38-d91ec4bf03a5` accepted `PASS WITH CONDITIONS` and froze three R5-1 prerequisites: hidden anchor is appended after all user refs without changing numbering/presentation/tags; PackedLayout row ranges and positions for target/current-tail/user-refs/hidden-anchor/Audio are measured separately without custom row-order or position-ID rewriting; and the anchor remains the immutable Group 1 of the run lineage across replay, branch, and Review. -- Formal verdict: `R5-0 CPU ARCHITECTURE AUDIT = PASS WITH CONDITIONS`. Production, public schema, Sampling v5, seed/SIGMAS, State, Session, Run Storage v3, Assembly, Release, A5, and general A8b remain unchanged/HOLD. Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r5-dual-role-anchor-audit-20260906\R5_DUAL_ROLE_ANCHOR_AUDIT_JA.md` and `R5_CPU_AUDIT_RESULT.json`. - -## Issue13 R4 Native Guided Overlap final GPU A/B (2026-09-06, VALID / FAIL / DO NOT PROMOTE) - -- After explicit GPU approval and the user's durable resource-policy correction, executed the frozen full pair in the required order. Fresh Standard A completed `6x5` and reproduced the R3B raw Video `6/6` plus Audio `6/6` exactly (`12/12`), then its Queue `0/0` backend was fully stopped before Fresh R4 B started. -- R4 B completed `720` frames / `30.000s` Video and `30.000s` Audio with `6` finite raw AV groups and no OOM, allocation error, backend crash, NaN/Inf, packed-layout, AV-alignment, or duration hard stop. Hidden overlap did not extend final duration. -- Formal verdict: `ISSUE13 R4 NATIVE GUIDED OVERLAP = GPU A/B VALID / FAIL / DO NOT PROMOTE`. Laplacian drift worsened from `+39.8675` to `+74.1887` (`+86.1%`), Video join was `2.1225 > 1.6598`, Audio join was `3.3896 > 1.6069`, highlight drift worsened `282.9%`, and gradient drift worsened `74.2%`. Saturation improved `63.0%` and the frozen motion floor passed, but they do not offset the primary failures. -- B sampling was `22.0%` slower and peak backend RSS was `47.24 GiB` versus A `43.29 GiB`. Per user instruction, low free VRAM and RSS alone are advisory for future approved GPU runs; actual OOM/allocation/backend/integrity failure is the stop boundary. -- Fixed task `H3情報チェック` completion review turn `a2e7fa47-e1ec-44c4-b83c-ff9e9872f25a`, reply `e7884bfc-6a46-4aad-8618-3ebead295311` accepted the verdict without mandatory correction. The result is limited to this frozen one-scene, one-seed condition; it does not invalidate Native Guided Overlap in general. -- Do not retry, sweep, or promote R4. The next research candidate may be a CPU/read-only design audit of `Group 1 persistent anchor + current tail`, keeping Video and Audio intervention roles separate and preserving clean tail, State/Session/Assembly, Replay/Terminal/Review, and Core layout contracts. -- Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r4-final-ab-20260906\R4_FINAL_AB_REPORT_JA.md`, `R4_FINAL_AB_RESULT.json`, `A_RAW_PARITY.json`, and the preserved A/B raw AV, videos, resource logs, decoded analyses, contact sheets, and boundary sheets. -- A owned PIDs `40224/36876` and B `9164/41744` were each stopped after Queue `0/0`; port `8190` listener and HTTP are offline. User `8188` was absent and never operated. Production/runtime/contracts and commit/push/tag/release remain unchanged. - -## Issue13 Standard Group 2 repeatability (2026-09-06, PASS / prior M3A divergence not reproduced) - -- After fresh explicit GPU approval, ran the frozen Standard Group 2 trace on three fully independent fresh 8190 backends. All three reproduced the R3B generated Video SHA `38e8eb8f...a188` and Audio SHA `2b482cfc...12d8` exactly. -- Every run matched all `150/150` ordered trace boundaries and all `8/8` predict-noise, diffusion-forward, and sampling-step records. Different/missing were `0/0`, first divergence was `null`, runtime/model options/wrapper order matched, and hook transparency passed `3/3`. -- Reverified the frozen model, CLIP, Video VAE, Audio VAE, Turbo8 LoRA, First Image, Core H3 nodes/model, KJ Sage patch, and shared Group 1 AV hashes. OOM, NaN/Inf, and unexpected backend crash were `0`. -- Formal verdict: `STANDARD GROUP 2 REPEATABILITY PASS / PRIOR M3A DIVERGENCE NOT REPRODUCED`. This closes the Group 2 repeatability blocker but does not identify the earlier M3A cause and does not assess R4 efficacy. -- Fixed task `H3情報チェック` completion review turn `0da950e6-2fc3-4c75-8a69-9daac82c9374`, reply `1d3c4727-9259-4832-8219-ae227a9477b1` accepted the verdict without mandatory correction. The next authorized proposal must resume the original frozen Gate order: fresh Standard A full `6x5`, require R3B raw AV `12/12` exact and no hard stop, stop A backend, then and only then run one frozen R4 B in another fresh backend. -- Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-standard-group2-repeatability-20260906\STANDARD_GROUP2_REPEATABILITY_REPORT_JA.md` and `STANDARD_GROUP2_REPEATABILITY_RESULT.json`; raw traces remain under the prior M3B result root with `standard_group2_repeat_1` through `_3` case names. -- Run 1 PIDs `18612/39884`, Run 2 `19416/39548`, and Run 3 `6968/4652` were each stopped after Queue `0/0`; 8190 listener and HTTP are offline. User 8188 was absent and not operated. Production/runtime/contracts and commit/push/tag/release remain unchanged. R4 B and final video were not run. - -## Issue13 R4-M3B Group 2 GPU trace (2026-09-06, PASS / no divergence reproduced) - -- After explicit GPU approval, executed the frozen Group-2-only diagnostic in the mandatory order. The R3B control generated-region hashes reproduced historical Video `38e8eb8f...a188` and Audio `2b482cfc...12d8` exactly, so and only so the R4-M3A Standard harness ran in a separate fresh backend. -- The two current traces are bit-exact through all 150 ordered boundaries: conditioning, pre-sampler latent/SIGMAS/noise/mask, eight `predict_noise` calls, all eight diffusion forwards, all sampling-step `x/x0`, sampler output and Group 2 generated Video/Audio. Different/missing are `0/0`; model options, wrapper order, memory runtime and PyTorch/CUDA settings also match. -- The first raw comparator mismatch was only the isolated Python module location (`stage_r3b` versus `stage_r4`) for the same `model_patch.py` SHA and callable. Comparator post-processing now ignores only that capture-location string when source SHA/name/qualname match; capture contract remains frozen at SHA `39affe50...19c2`. Dedicated tests pass `13`. -- Formal verdict: `R4-M3B GPU TRACE PASS / NO DIVERGENCE REPRODUCED / PRIOR M3A CAUSE UNRESOLVED`. The earlier R4-M3A output mismatch is not reproducible under this one frozen pair, so no internal first-divergence point or cause can be assigned. This one pair does not prove repeated determinism. -- R4 Native Guided Overlap B, quality A/B, retry and sweep were not run. R4 quality remains unassessed and requires a new direction decision before any additional GPU work. -- Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r4-m3b-first-divergence-20260906\R4_M3B_GPU_RESULT_JA.md`, machine result `R4_M3B_GPU_RESULT.json`, ordered comparison `R4_M3B_FIRST_DIVERGENCE.json` and both raw traces/logs. -- Fixed task `H3情報チェック` completion review turn `d9289f52-2ed6-49f5-937a-73ca63e6efe3`, reply `ebb530f8-372d-4707-8636-84d3dc306980` accepted the verdict with no mandatory correction. It explicitly forbids calling this one-pair match `baseline recovery confirmed` and prioritizes a separate fresh-backend Standard Group-2 repeatability Gate before any R4 Native Guided Overlap quality A/B. -- R3B backend PIDs `7608/35932` and R4 PIDs `35984/39160` were stopped after Queue `0/0`; port 8190 listener and HTTP are offline. User 8188 was absent and not operated. Production/runtime/contracts and commit/push/tag/release remain unchanged. - -## Issue13 R4-M3A baseline parity root-cause audit (2026-09-06, first contract divergence identified / output cause unresolved) - -- CPU/read-only comparison of R3B baseline, the earlier R4 A `retry2`, and R4-M3 A `rerun2` found the first contract-level bit-exact break at Assembly Plan `chunks[0].context_frames`: R3B `5`, R4 shared-Group-1 harness `0`. -- This metadata difference is not the Group 2 output cause: R4 `retry2` has the same value `0` and nevertheless matches every R3B Group 1-6 Video/Audio tensor bit-exact. `entry_to_state()` does not consume the plan's `context_frames` field. -- The first saved tensor SHA divergence is Group 2's generated region: Video begins at latent `T=7`, Audio at `T=37`. The protected 7-slot/37-tick prefixes match the exact Group 1 tail and remain bit-exact. -- Normalized prompt graph, Group 2 derived seed, shape, scheduler settings and CPU-reconstructed target/mask/noise recipe match. R3B did not capture actual conditioning, actual SIGMAS, pre-sampler latent, first-forward, or per-step SHA, so A/B/C internal classification remains unresolved. -- Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r4-m3a-parity-audit-20260906\R4_M3A_BASELINE_PARITY_ROOT_CAUSE_AUDIT_JA.md` and `R4_M3A_FIRST_DIVERGENCE_AUDIT.json`. No GPU, backend, Production change, A rerun, B execution, commit, push, tag, or release. -- After separate explicit user authorization, the fixed task `H3情報チェック` reviewed this CPU audit (turn `b9306a6b-b2da-486e-80d8-0b054eb80f76`, reply `7e67d0bf-783b-4a52-a2d7-d8d9cb2f6c16`). It accepted the formal verdict and the R4 B STOP. The next Group-2-only instrumentation must also capture model options, wrapper registration/order, attention patch identity and Dynamic RAM/runtime settings. The `context_frames=0` difference is not sufficient by itself to explain the output divergence; interactions are not excluded. -- R4 quality remains unassessed. Any next in-sampling telemetry run requires a separately frozen diagnostic plan and fresh user approval immediately before GPU execution. - -## Issue13 R4-M3 GPU rerun (2026-09-06, INCOMPLETE / A baseline parity stop) - -- After explicit GPU approval, corrected only the isolated observer runtime hook from the facade `v3.driving_nodes` to the actual Production binding `v2.nodes.run_sequence`; compile/static checks and R4 focused CPU tests passed `4/4`. Production source and installed runtime were unchanged. -- Fresh-backend A `A_standard_6x5_s131325_rerun2` completed Group 2-6 Sampling and produced 720 frames / exact 30.000 seconds / 24 fps / 576x864 / 32 kHz stereo in `780.011 s`, with no OOM, allocation error, NaN/Inf, backend crash, layout, AV, or duration failure. -- The mandatory pre-B check failed: frozen Group 1 Video/Audio remained exact, but Groups 2-6 Video/Audio did not reproduce the prior R3B baseline tensor bit-exact (`2/12` exact total). Derived seeds, prompt and geometry remained fixed; this is not a file-metadata-only difference. Per the frozen protocol, B and all retries/sweeps were not started, so R4 quality and the Group 5 B-A memory delta remain unassessed. -- A Group 5 RSS was `41.715 GiB` before Sampling, `41.854 GiB` immediately after, and `41.846 GiB` after cleanup. Overall minimum available RAM was `2.989 GiB`, peak commit `72.219%`; no hard resource stop fired. -- Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r4-native-guided-overlap-20260906\R4_M3_GPU_RERUN_RESULT_JA.md`. Dedicated 8190 Queue was `0/0` before stopping listener PID `34336` and launcher PID `34940`; HTTP/listener shutdown was verified. 8188 was not operated. No commit/push/tag/release. -- Fixed-task completion review turn `c476af69-2f07-4dfb-a495-fea7f881199e`, reply `7259d478-7029-4077-9e8c-94d94f83ce78` confirmed the verdict with no mandatory correction. Next is a CPU/read-only-first bit-exact reproducibility cause audit; no further GPU A/B is authorized by this result. - -## Issue13 R4-M1 Memory Ownership Audit (2026-09-06, PASS / GPU rerun awaiting approval) - -- CPU/read-only ownership audit found no R4-specific major leak or unbounded Group-to-Group retention. The R4 guide clones are call-local, share one tensor pair across conditioning entries, and are released with conditioning; fresh targets are not referenced by R4 conditioning. Existing full physical CPU entries and the latest continuation tail are bounded A/B-common ownership required by the current Assembly Plan. -- Prior R4-3 wording is corrected to `R4-3 INCOMPLETE — SOFT RESOURCE THRESHOLD EXCEEDED`. Groups 2-5 sampled normally; the old 46 GiB exception fired before the Group 5 result returned to sequence cleanup. R4 remains a continuation candidate, not HOLD / FAIL. -- CPU verification: weak-reference ownership check PASS; existing R4 6-Group and Terminal Merge shadow tests `4 passed`; modified isolated files compile. At 576x864 BF16 the R4-specific 22f guide clone is about 0.623 MiB video plus 0.0045 MiB audio, not a GiB-scale explanation for backend RSS. -- The isolated R4 observer and test copy now treat RSS >=46 GiB as a Soft Warning, record Sampling-before/after and Group-cleanup snapshots plus system RAM/pagefile/commit/GPU/time, and defer resource stops until cleanup where possible. Production and installed runtime remain unchanged. -- Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r4-native-guided-overlap-20260906\R4_M1_MEMORY_OWNERSHIP_AUDIT_JA.md`. The unchanged frozen R4-3 A/B GPU rerun is eligible only after fresh explicit user approval immediately before execution. -- Fixed-task review was supplied/read: `R4-M1 PASS`, no mandatory correction, and Pre-GPU conditions may be presented. The required follow-up is an explicit A/B Group 5 comparison at Sampling-immediate and post-cleanup points. -- R4-M2 Pre-GPU final freeze is `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r4-native-guided-overlap-20260906\R4_M2_PRE_GPU_FINAL_CHECK_JA.md` with machine freeze `R4_M2_PRE_GPU_FINAL_CHECK.json` SHA-256 `b31daaf81c00534df8811755d47b956ee27c16b34e00772722427fdaaef3c959`. -- Fixed-task review turn `72fc3888-2e94-4911-a531-39598e855576`, reply `13c5d2dc-0013-436c-8d23-3c5bafd48ab0`: R4-M2 PASS WITH CONDITIONS. The one mandatory correction is applied: backend health failure now has mechanical process/API/stall criteria. Results must emphasize fresh-process run-internal RSS deltas. This review is not GPU authorization. - -## V3.8 beginner manual plan and capture script (2026-09-06, draft ready / capture deferred) - -- Created the persistent Japanese manual design and Computer Use capture script at `docs/V38_BEGINNER_MANUAL_PLAN_AND_CAPTURE_SCRIPT_JA.md`. It is the canonical restart point for the later image-led V3.8 beginner guide. -- The plan reuses the current exact `README_JA.md` Review walkthrough, separates Quick Start from reverse-lookup help, defines stable Shot IDs, capture prerequisites, environment records, filenames, abnormal-state coverage, a bug-report template, and completion checks. -- Final screenshots remain deferred until the V3.8 public UI, standard workflow, and launch treatment of the active drift investigation are stable. A later instruction to start the manual must read the plan first and verify current labels before capturing `V38-M01` onward. -- No Computer Use capture, runtime synchronization, backend operation, GPU generation, publication, commit, or push was performed in this planning step. - -## Issue13 Texture-only RGB/VAE-delta Feedback Clamp (2026-09-06, FAIL / closed) - -- Static prototype/policy/source-order checks passed `13/13`, but the real fp16 H3 Video VAE feasibility gate failed before any Diffusion Sampling. GPU placement OOMed on the first 22f decode, including tiled retry: peak allocated `14,764,005,888` and reserved `16,280,190,976` bytes on the 16GB device. -- Corrected `--cpu-vae` fallback was then attempted. After about five minutes its owned PID used `54,954,274,816` bytes working set, private allocation reached `163,648,221,184` bytes with paging, available RAM fell to about `6,658MB`, and Windows displayed a Python memory application error. The owned process was interrupted; available RAM recovered to about `56,262MB` and GPU free memory to about `14.9GB`. -- Therefore the decoded-RGB `encode(corrected)-encode(decoded original)` path is operationally infeasible here and also conflicts with the protected V2 rule against Video/Audio VAE decode between H3 chunks. Close this concrete candidate; do not run its `6x5` efficacy A/B, switch to int8-only, lower resolution, CPU forcing, or threshold tuning automatically. -- Production/source runtime is unchanged. No ComfyUI backend or listener was started; owned PIDs `9440` and `4472` exited. Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-texture-clamp-cpu-design-20260905\REAL_VAE_PREFLIGHT_RESULT_JA.md`. New GPU work still requires fresh explicit confirmation. A5/general A8b/Release HOLD remain unchanged. - -## Issue13 Schedule-Matched Disposable Prefix screen (2026-09-05, closed) - -- Completion review faf8917a-b718-48e6-b40c-b380cc68c17a / reply26bc256c-bf10-49e8-b131-0d01e2740844 received/read: experimentPASS / this22f screenFAIL, no mandatory correction, pair closed. Report-only review; no independent media inspection. No next GPU phase authorized by this result. - -- User explicitly approved proposal execution and one frozen6x5 pair after integration gates. Experiment validity PASS / specified22f mitigation FAIL: edge drift39.8675→56.3675 (+41.39%); contrast/highlight guards failed, saturation/gradient/shadow passed. Flow mean0.510734→0.534240 (+4.60%); not full motion/semantic AV certification. No sweep or60s promotion. -- Same savedGroup1 on both sides,10new physical groups total. A801.79s/B779.90s, each720f/30s. A rawAV12/12 exact vs baseline. Actual Core noise/seed/SIGMAS/inputmask/shape5/5 equal; conditioning/Assembly equal; B40H3 mask observations valid; cleanAV exports10boundaries exact. CPU14+protected85 PASS, assets10/sourceRegistry104/isolatedPython83 unchanged,Public7. Fullpytest not rerun. -- Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-schedule-prefix-20260905\RESULT_JA.md`. Production/runtime unchanged; only isolated experiment and source state/history docs edited. A5/generalA8b/Release HOLD, no commit/push. Owned8190 PIDs13280/26320 and monitors stopped, listener offline; user8188 idle/reachable/unmodified. PreGPU fixed-task review26665e59 read before A; completion review pending at report creation. - -## Issue13 R3B consolidated report / direction review (2026-09-05) - -- User requested consolidation of all completed R3B tests and direction review, not new GPU or Production changes. Ten30s runs/57physical groups/300s output; all completed, no accepted mitigation. Existing analysis equal_5s_windows and MP4 SHA were rechecked10/10. Do not substitute 3x10 chunk-center metrics for common5s windows. -- Consolidated report: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r3b-consolidated-20260905\ISSUE13_R3B_CONSOLIDATED_REPORT_JA.md`. GPU_TEST_MATRIX.json retains exact values/provenance. HistoricalR2.6 remains a strong diagnostic positive, not a failed experiment; Video/Audio fixed-tail and motion confounds remain. R3B did not establish handoff-count-only causality or a motion-preserving fix. -- Fixed H3情報チェック review received/read: turn4ee9d332-985c-49b5-8f3c-1e3c5186d3d2, reply7326b44b-f2b4-4828-a1f6-d8011f5113c3. Supports investigation progress/Production mitigation none/initiating bias unresolved. Reviewer read report only, not local media independently; broad exclusion language is restricted to the tested settings. -- Proposed priorities only: reporter-exact differential, saved-data temporal/region analysis, then design one controlled same-prefix intervention if justified. No new intervention method approved or ready; temporal observations alone do not establish causality. No additional GPU, backend launch, Production fix or publication in this consolidation. A5/general A8b/Release HOLD remain. Source Registry104/104 unchanged; source edits only state/history documentation. - -## Issue13 R3B non-Turbo Reference20 pair (2026-09-05) - -- User explicitly authorized only two matched non-Turbo20step30s Reference OFF/ON cases. Ref2VA pruned INT8, seed131325,6x5,Manual576x864,Standard/Balanced22,AudioON,FirstImage; no LoRA node executed. Production/runtime and general A5/A8b/Release HOLD unchanged. -- Experiment PASS / this Reference mitigation screen FAIL. OFF1771.584s, ON1854.748s; each720f/30s AV,6physical groups. Laplacian delta25.1840→39.2554 (+55.87% larger, not a global quality score); saturation drift0.00238→0.01139 and highlight drift failed guards. Contrast drift improved58.05%; gradient/shadow nearly equal. No candidate accepted; one scene/seed does not reject native Reference generally or isolate Turbo causality versus prior8step. -- Actual Core noise/seed/SIGMAS/mask/target-shape6/6 match; both21SIGMAS unchanged and modelpatches0. Clean Video/Audio prefixes each10/10 exact. Same FirstImage keyframe and persistent native Reference payload in all6 ON groups; Assembly equal except runtime start. Sampled identity/scene retained; similar ON poses are a caution, not proof of freeze. Full semantic AV/motion unqualified. -- Evidence/report: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r3b-ref2va-standard20-20260905\ISSUE13_R3B_STANDARD20_REFERENCE_GPU_REPORT_JA.md`. Registry104/104, livePublic7/7 before/after,10assets unchanged,AST18,observerCPU anddiff-check PASS; fullpytest not rerun. Only state/history documentation changes. Existing Development mismatch1/254 remains separate. -- Dedicated8190 launcher29056/backend29368 stopped19:14:23JST; PID/listener/HTTP,conhost32972 andmonitor exit verified. User8188 untouched. Monitoring370samples,minRAM0.995GiB,no safetyinterrupt. OuterPowerShell stale LASTEXITCODE check falsely returned nonzero after successful shutdown; independent exit checks confirmed success, no GPU rerun. -- Current R3B total10runs/57physical groups, no accepted mitigation. Fixed-task completion review a9db6c24-27cc-4b15-b0c6-da908eb1702f received/read: experimentPASS/screenFAIL, no mandatory rerun. Clarified that Reference changes the first generated image too; compare each conditioning trajectory's own start-to-end change, not identical initial videos. Reviewer did not independently view local media. Approved pair closed; no additional GPU, multiseed/long-form, Production promotion or publication under this two-case approval. - -## Issue13 R3B isolated context-noise GPU screen (2026-09-05) - -- User explicitly approved the proposed single-intervention Video context-noise experiment with "許可、許可。" after the Ref2VA review. This supersedes the earlier waiting-for-approval status only for this isolated A/B. Product A8b, A5 and Release remain HOLD. Production/runtime must stay unchanged. -- Work directory: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r3b-noise-20260905`. CPU10/10 + existing69 protection tests, observer and5-boundary Shadow passed. Fixed-task review received; corrected Gaussian0.05 definition to a standard-deviation multiplier (not maximum amplitude), then ran only the approved pair. -- GPU experiment PASS / this0.05 tapered Video-noise screen FAIL. OFF876.398s and ON830.900s, each720f/30s. Laplacian delta39.8675→43.9942 (+10.35% worse), saturation delta+47.25% worse; contrast/highlight/shadow partly improved. Motion proxy0.510734→0.336667 (−34.08%) and repeated sampled poses are cautions, not proof of complete freeze. No candidate accepted or Production promotion. -- Fresh OFF raw Video/Audio matches prior baseline12/12. OFF/ON first raw AV exact, actual packed Core noise/SIGMAS/derived seeds6/6 exact, Assembly geometry and exogenous conditioning exact. Intended interventions5/5; newest slot delta0; clean Video/Audio prefixes each10/10 exact. Recursive Audio diverges fromGroup3 through joint generation but is never directly modified. -- Registry104/104 and livePublic7/7 passed;10asset files rehashed unchanged. Source changes are only AGENTS, PROJECT_STATE, WORKLOG and the AGENTS hash row in Development Manifest. Pre-existing Registry-manifest mismatch remains1/254; package/Production source unchanged. Full pytest not rerun. Dedicated8190 launcher1972/child4128 stopped16:26:44JST; PID/listener/HTTP and monitor exit verified, user8188 untouched. -- Report: `ISSUE13_R3B_NOISE_GPU_REPORT_JA.md`. Current exploration totals8runs/45physical groups, no accepted mitigation. This narrowly approved pair is complete; do not infer approval for a parameter sweep, another intervention, multiseed/long-form, or Production changes. Fixed H3情報チェック completion review received/read in turn4832f123-abeb-47de-9d97-56e25840a79c: experiment PASS / this condition screen FAIL; no mandatory correction or additional GPU. Reviewer did not independently view local media. Issue13 remains unresolved; A5/general A8b/Release HOLD remain. - -## Issue #13 R3B Ref2VA paired GPU screen (2026-09-05) - -- Initial-screen review was received from fixed H3情報チェック task `6a94b91e-af7c-83e8-be18-ddc504f690c4` (turn `1ca3ed8b-f859-43d7-84ee-7459c3a87ce9`) before this phase. It supported matched Ref2VA Reference OFF/ON and retained the initial conclusion: no accepted mitigation; Audio OFF is mixed. -- Ref2VA checkpoint + matching Ref2V8step LoRA, seed131325,6x5s,Manual576x864,Standard/Balanced22,AudioON: OFF and ON completed720f/30s AV in888.343s/918.375s. Reference connection was the only sampling-input delta. Laplacian increase was13.1606 OFF versus27.7282 ON (6.75%/13.20% from each starting value); native Reference did not meet the predeclared mitigation screen. Some secondary metrics improved, but no multi-seed/long-form promotion or Production fix is justified by this pair. -- Raw Video/Audio prefixes each10/10 exact; actual public-call SIGMAS identical and unchanged; First Image latent exact between cases; same Reference payload present in all6 ON groups. Twelve pre-sampling Refine conditioning signatures were recorded without hooks or mutation. CPU noise replay6/6 matches are reconstruction, not actual-noise telemetry. Sampled identity/scene remained, but semantic AV and full temporal naturalness remain unqualified. -- Report: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r3b-ref2va-20260905\ISSUE13_R3B_REF2VA_GPU_REPORT_JA.md`. Six current-environment30s cases/33physical groups total across both screens; Issue13 remains unresolved. Pair completion review was received and read (turn `b916ed28-cb5f-4587-8456-4a7bff915049`): experiment PASS / mitigation screen FAIL; no candidate promotion, no additional mandatory GPU for this screen. Next requires reporter-exact workflow or explicit single-intervention experimental approval. Context-noise interventions remain subject to A8b HOLD; generic GPU authorization does not waive its release conditions. A5 and Release HOLD remain. -- Production/source runtime files unchanged; only project state/history recorded. Registry source/stage104/104 and live Public7/7 passed. Development Manifest's pre-existing stale REGISTRY_MANIFEST.sha256 entry (1/254 mismatch) remains separate. Full pytest not rerun. Dedicated8190 PIDs5792/3228, listener/HTTP and monitor exit verified at15:13:36JST, user8188 untouched. No commit/push/tag/release/publish. - -## Issue #13 R3B initial GPU screen (2026-09-05) - -- GPU execution completed for four matched current-environment30s cases:6x5 baseline,3x10,6x5 with native Reference Image1,6x5 with Audio Continuity OFF. All21 physical groups and four720f/30s AV outputs succeeded; no accepted Issue13 mitigation yet. Longer chunks and clean Reference did not meet the frozen screen. Audio OFF reduced Laplacian drift41.83% but increased saturation drift51.25%; keep it diagnostic, not a recommended default. -- Current FL2VA8step LoRA is not the unavailable historical4step LoRA. This is not reporter-exact R3. A/D first raw AV group is bit-exact; Video prefixes17/17 and Audio-ON prefixes12/12 are exact. CPU reconstructed noise parity is evidence replay, not actual Sampling-time telemetry. One seed/scene only; long-form, multiple seeds, semantic AV and wrapper matrix remain untested. A5/A8b remain HOLD. -- Evidence/report: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue13-r3b-20260905\ISSUE13_R3B_INITIAL_GPU_SCREEN_REPORT_JA.md`. User explicitly authorized sharing this GPU audit only with pinned H3情報チェック task `6a94b91e-af7c-83e8-be18-ddc504f690c4`. Completion review was received before the paired Ref2VA-model native Reference gate; see the later phase above. -- Source/runtime Production was unchanged. Dedicated8190 PIDs36076/28936 and its monitor were stopped and checked offline at14:15JST; user8188 remained live and untouched. Registry104/104 passes. Development Manifest has one pre-existing stale entry for REGISTRY_MANIFEST.sha256 (same bytes as pre-GPU snapshot), retained for separate Release Track correction. Full pytest was not rerun in this GPU screen. Release HOLD and publication prohibition remain. - -## V3.8 Review Fixed-Seed Guard (2026-09-05) - -- `Run = Review Each Chunk` now requires the visible `Control After Generate = fixed` setting. With `randomize`, `increment`, or `decrement`, the Main card shows `Set Control After Generate to fixed`, explains that Base Seed must remain unchanged, and the frontend cancels Queue with the same exact instruction instead of silently creating another unrelated Chunk 1 revision. -- `Try this chunk again` continues to create a distinct Take through the existing Review variation/nonce contract; users must not randomize Base Seed for it. Full Run and V3.7 or earlier nodes retain their existing Control After Generate behavior. -- Run Storage reload now runs after `execution_success`, `execution_error`, and `execution_interrupted`, with the existing node-local execution callback retained as fallback. This makes completed, failed, and interrupted persistence states visible without changing Queue or Review intent. -- The immediate README walkthrough now begins with `Control After Generate = fixed`. A separate image-led, exact-label, one-action-per-step beginner guide remains a required follow-up before release; it must describe a known-good `2 × 5s` path without internal terminology or inferred UI labels. -- Focused Review/UI regression passed `116/116`; full pytest passed `1127/1127`; JavaScript syntax, Development Manifest `254/254`, Registry Manifest `104/104`, runtime verifier/public surface `7/7`, source/runtime SHA `2/2`, all four live served-extension markers, and `git diff --check` passed. -- Public/backend schema, widget/socket order, Sampling v5, Run Storage v3, Branch/Take provenance, State/Session, Assembly, and GPU behavior remain unchanged. Release / Registry readiness remains **HOLD** pending package staging after this UI/documentation change. -- Pre-change snapshot: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v38-review-seed-guard-filtered-20260905_024733-0a7c670` (`11/11`, mismatch `0`). - -## V3.8 Review Completion Refresh + Step-by-step Guide (2026-09-05) - -- Confirmed the reported `2 × 5s` run was configured correctly and that the first 5-second output is the intentional first Review unit. Run Storage contained a valid canonical `review_ready` Chunk 1 with 33 Takes; the defect was the stale frontend view after execution, not missing backend generation or storage. -- The V3.8 frontend now reloads Run Storage on ComfyUI's global `execution_success` event, with the existing per-node `onExecuted` hook retained as a fallback. The first load is immediate and one bounded 250 ms follow-up covers filesystem/UI timing without changing a widget, choosing an action, or automatically starting Queue. -- `README.md` and `README_JA.md` now give a literal `Chunks = 2`, `Seconds per Chunk = 5`, `Total Length = 10 seconds`, `Run = Review Each Chunk`, `Progress = On — Resume and Takes available` walkthrough. It explains the intentional 5-second first result, all three visible Review buttons, the required second Queue, Back to Settings/Return to Review, and common mistakes using the exact UI labels. -- Focused Review/UI regression passed `86/86`; full pytest passed `1126/1126`; JavaScript syntax, Development Manifest `254/254`, Registry Manifest `104/104`, runtime verifier/public surface `7/7`, source/runtime SHA `2/2`, live served-extension markers, and `git diff --check` passed. -- Public/backend schema, serialized widgets, Review intent, Run Storage v3, Branch/Take provenance, Sampling v5, State/Session, Assembly, and GPU behavior are unchanged. Release / Registry readiness remains **HOLD** pending package staging after this frontend/documentation change. -- Pre-change snapshot: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v38-review-refresh-readme-filtered-20260905_022621-0a7c670` (`10/10`, mismatch `0`). - -## V3.8 Single-chunk Review Guidance (2026-09-05) - -- `Run = Review Each Chunk` with `Chunks = 1` no longer presents a misleading `Ready to Queue` card. The Main card now explains that the first chunk is also the last and directs the user to set `Chunks` to `2` or more before Queue to use Review and Continue. -- The `Chunks` and `Run` mouse-over help carries the same instruction. This is diagnostic guidance only: values are not changed automatically and Queue is not blocked. -- Public/backend schema, serialization, Run Storage v3, Review/Branch semantics, Sampling v5, State/Session, Assembly, and GPU behavior are unchanged. Release / Registry readiness remains **HOLD** pending package staging after the UI change. -- Pre-change snapshot: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v38-review-single-chunk-guidance-filtered-20260905_010500-0a7c670` (`10` exact files, mismatch `0`). - -## V3.8 Review Back to Settings (2026-09-05) - -- A canonical `review_ready` screen now includes `Back to Settings`. It restores the normal Main controls without changing the pending Review action, selected Take, canonical branch, Queue, or any serialized backend value. `Return to Review` returns to the three Review actions. -- The normal `Ready to Queue` card shows the still-pending chunk Review while Settings are open. A newly completed review revision opens the Review screen automatically; the view toggle itself is transient and non-serialized. -- This is Frontend presentation only. Public schema/sockets, Sampling v5, Run Storage v3, State/Session, Assembly, Branch/Take provenance, Seed/SIGMAS, and GPU behavior are unchanged. Release / Registry readiness remains **HOLD** pending package staging after the UI change. -- Pre-change snapshot: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v38-review-back-to-settings-20260905_002018-0a7c670` (`8` exact files, mismatch `0`). - -## V3.8 Main Core Controls + Card Alignment (2026-09-04) - -- Restored `Prompt Format`, `Continuity`, `Base Seed`, `Control After Generate`, and `Audio Continuity` as the first five normal Main controls, using readable facade labels while preserving the existing serialized backend widgets and values. These controls no longer require opening Advanced. -- Fixed the custom Ready/warning/Review card draw contract. The card now always draws with its declared 62/68 px height instead of accepting an incorrect 20 px widget-height argument from the canvas callback, so the rounded border no longer crosses the headline or detail text. -- Focused UI/schema passed `86/86`; full pytest passed `1124/1124`; JavaScript passed `7/7`; Development Manifest passed `254/254`; Registry Manifest passed `104/104`; source/runtime UI SHA matched; runtime verifier/public surface passed `7/7`; and `git diff --check` passed. Public Schema, sockets, Sampling, Run Storage, State/Session, Assembly, and GPU behavior remain unchanged. -- Pre-change snapshots: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v38-main-core-controls-card-alignment-source-filtered-20260904_223526-0a7c670` (`10` exact files, mismatch `0`) and `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v38-main-core-controls-card-alignment-runtime-w-filtered-20260904_223526` (`2` exact files, mismatch `0`). The standard helper stopped only on the known `.pytest_cache` ACL. - -## V3.8 Explicit Main Controls (2026-09-04) - -- Replaced the over-automatic Main facade with explicit, independent `Chunks` and `Seconds per Chunk` controls. `Total Length` is now a read-only calculation only; changing it cannot recalculate either generation setting. Values such as `3 chunks × 10 seconds` and `2 chunks × 15 seconds` are directly configurable again. -- Removed the permanent Connected Inputs badges and automatic Input Mode row. `Size Source` is always visible and remains exactly `First Image` or `Manual` until the user changes it. First Image uses the existing Resolution choices; Manual shows the exact Width and Height directly. The facade no longer converts an inactive First Image into an apparently user-selected custom frame size. -- If `Size Source = First Image` has no active First Image because it is missing, disabled, or bypassed, the Queue summary reports `Check First Image` and the exact fallback size without silently changing the selection. Reference Image and Video Guide size controls remain conditional inside Advanced. -- Review-ready behavior remains the approved amber state with three explicit Queue actions. Public Python schema, sockets/order, serialized widget values/order, Sampling v5, Run Storage v3, State/Session, Assembly, Branch/Take, Seed/SIGMAS, and GPU behavior are unchanged. Focused UI/schema passed `86/86`; full pytest passed `1124/1124`. -- The standard pre-change snapshot stopped only on the established `.pytest_cache` ACL. Accepted filtered snapshots are `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v38-explicit-controls-source-filtered-20260904_214419-0a7c670` (`10` exact files, mismatch `0`) and `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v38-explicit-controls-runtime-w-filtered-20260904_214419` (`2` exact files, mismatch `0`). Release / Registry readiness remains **HOLD** pending package staging after this UI change. - -## V3.8 Mock-faithful Main UI (2026-09-04, superseded by Explicit Main Controls) - -- Reworked the presentation-only V3.8 Main facade to follow the approved mock hierarchy: active-input badges, automatic `Input Mode`, one `Video Length` selector plus `chunks × seconds` detail, conditional Output/Quality or Frame Size, Run, Progress, a Queue-ready summary card, and one Advanced disclosure. Existing serialized widgets remain behind that facade and keep their original values/order. -- Input detection now follows effective graph state. A connected First Image, Video Guide, or Audio loader in ComfyUI bypass/never mode (`2`/`4`) or with its enable widget OFF is shown as inactive. This prevents the public workflow's bypassed optional loaders from falsely changing T2VA to I2VA or exposing irrelevant controls. -- Review mode uses the second approved mock state only when Run Storage reports the canonical revision as `review_ready`: an amber chunk-ready card, `Use it and continue`, `Try this chunk again`, and `Use it and finish the rest`, followed by Render History and Advanced. Selecting an action does not auto-Queue and does not change the canonical branch until the normal Queue runs. -- Public Python schema, input sockets/order, serialized widget values/order, Sampling v5, Run Storage v3, State/Session, Assembly, Branch/Take, Seed/SIGMAS, and GPU behavior are unchanged. Focused UI/schema passed `86/86`; full pytest passed `1124/1124`. Live visual acceptance remains for the user's next ComfyUI reload because the isolated browser route could not be used without joining an existing Edge process; no user tab was touched. -- Pre-change snapshots: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v38-mock-faithful-ui-source-20260904_201500-0a7c670` (`327` files, mismatch `0`) and `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v38-mock-faithful-ui-runtime-w-20260904_201500` (`105` files, mismatch `0`). The dedicated validation backend on port `8190` and its exact temporary Edge profile were stopped; ports `8190`, `8188`, and `9223` were not listening at cleanup. Release / Registry readiness remains **HOLD** pending package staging after this UI change. - -## V3.8 Complete Mouse-over Help (2026-09-04) - -- Added non-empty mouse-over help to all 12 Main facade controls, all nine visible Advanced controls, Review/Render History actions, and all 47 required/optional public V3.8 Sampler inputs. Tooltip text is stored on both the widget and widget options so current ComfyUI frontend paths can display it consistently. -- `Output Size` now explains the selected behavior directly: First Image preserves the connected image aspect for I2VA/FL2VA, while Manual exposes exact 32-aligned Width/Height for T2VA, missing-First-Image workflows, or explicit canvases. Resolution, Resume & History, Reference Image Size, and Video Guide Size help also updates with the current selection. -- This is help text and presentation metadata only. Widget names/order/values, sockets/types, Public `7/7`, Sampling v5, Run Storage v3, State/Session, Assembly, Branch/Take, Seed/SIGMAS, and GPU behavior remain unchanged. Focused UI/schema passed `85`; full pytest passed `1124/1124`; JavaScript passed `7/7`; Development Manifest `254/254`; Registry Manifest `104/104`. -- Pre-change snapshots: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v38-all-hover-help-source-filtered-20260904_192259` (`326` files, mismatch `0`) and `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v38-all-hover-help-runtime-w-filtered-20260904_192318` (`105` files, mismatch `0`). The four changed Registry files are synchronized to ComfyUI_W with source/runtime SHA `4/4`; the live extension route returns the new help code. The already-running backend was deliberately not restarted, so new Python socket help becomes visible after the user's next restart. Eight unrelated source/runtime Registry mismatches predated this task and were preserved for a separate full-runtime sync decision. Release / Registry readiness remains **HOLD** until a tooltip-inclusive package staging Gate passes. - -## V3.8 Intuitive Main UI Refinement (2026-09-04) - -- The compact facade now exposes `Generation = Full Video | Review by Chunk`, integer `Chunks`, compact `Seconds per Chunk`, `Output Size`, `Resolution`, `Resume & History = Off | On`, connection-specific Reference/Video Guide sizing, and one `Show/Hide Advanced Settings` button. Seed remains available inside Advanced Settings. -- Chunks and Width/Height display without decimal places. Seconds display only a meaningful single decimal, so `3.000` and `5.000` render as `3` and `5` while values such as `5.5` remain available. `Review by Chunk` automatically enables the unchanged backend `Save + Auto Resume` requirement. -- Review controls no longer appear merely because Review mode was selected. Before the first Queue, the UI asks the user to create the first chunk. Only a canonical Run Storage revision with backend status `review_ready` reveals `Keep & Continue`, `Try This Chunk Again`, and `Finish Automatically`; selecting one leaves a persistent Queue instruction instead of only a momentary button flash. -- Empty Render History is hidden. Once at least one backend Take exists, the collapsed History button becomes visible and retains the existing N2c Take selection/actions. Video Guide and Reference Image sizing remain connection-driven. -- This is Frontend presentation only. The serialized V3.8 widget order and values, Python/public schema, seven public nodes, Sampling v5, Run Storage v3, Branch Provenance, State/Session, Assembly, Seed/SIGMAS, and GPU behavior are unchanged. Focused UI passed `15`; full pytest passed `1120/1120`. -- Source/runtime snapshots: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v38-intuitive-ui-prototype-source-filtered-20260904_144147` (`915/915`, mismatch zero) and `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v38-intuitive-ui-prototype-runtime-w-20260904_144128` (`179` files). The user-provided rollback ZIP remains unchanged at `D:\StabilityMatrix\Data\Packages\ComfyUI_W\custom_nodes\ComfyUI-H3-Continuum38_924.zip`, SHA-256 `6FF68ECA71DA9459C15EAB5B31480D65F03E2734E3ED3A2D86D7DCB024CB802D`. -- Refinement snapshot: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v38-intuitive-ui-refinement-20260904_153802` (`9` exact source/runtime files). Synced only `web/project_id.js` and `REGISTRY_MANIFEST.sha256` to ComfyUI_W; hashes match, the live extension route returns HTTP 200 with every new marker, and runtime verification passes public `7/7`. User visual acceptance, README/CBT images, and package staging remain later work. **Release / Registry readiness = HOLD.** - -## V3.8 Resolution / Size Source UX Refactor PASS (2026-09-03) - -- The user moved V3.8 test videos and test artifacts to `D:\output\video\comfy_video\v38`; the verified directory currently contains 868 files. Treat it as the current V3.8 output archive and preserve its contents. -- Main V3.8 now presents only `Size Source = First Image | Manual`. First Image preserves the connected First Image aspect and reuses the existing Draft 0.30 MP, Balanced 0.60 MP, Native 768, Custom MP, 32-pixel alignment, and 1344 long-edge-cap resolver. Manual accepts exact aligned Width and Height and does not apply the preset. -- Width and Height are appended after every existing serialized V3.8 widget. They remain visible, are read-only in First Image mode, and become editable in Manual mode. The frontend updates them from exact available First Image preview geometry before Queue; the backend remains authoritative and reports the final resolved canvas in Status. -- The prior `aspect` key and its old values remain accepted as a hidden compatibility field. Frontend migration maps Auto to First Image and maps Landscape, Portrait, and Square to Manual using the exact former resolved canvas. API prompts that omit the new fields retain the legacy resolver path. -- If First Image is selected but no usable First Image reaches the sampler, execution follows the project fail-open rule: the displayed Manual Width and Height are used deterministically and Status states the fallback. Reference Image and Video Guide are never implicit size sources. FL2VA without First Image therefore uses the same explicit Manual fallback. -- Public node count remains `7/7`. The only Python schema change is the approved append-only `size_source`, `width`, and `height` UI contract; existing keys/order/sockets remain intact. Sampling Contract v5, Seed/SIGMAS, physical grouping, Run Storage v3, Branch Provenance, State/Session, Assembly, Driving Audio, Reference Audio, Second Pass/O1, and Terminal Merge are unchanged. -- Validation passed focused `107`, full pytest `1117`, JavaScript `7/7`, Development Manifest `253/253`, Registry Manifest `102/102`, public workflow `19` nodes / `25` links / orphan `0`, protected contracts `16/16`, Python compile, and `git diff --check`. -- Snapshot: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v38-resolution-size-source-ux-refactor-filtered-20260903_152559-0a7c670` (`320/320`, mismatch zero). Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\v38-resolution-size-source-ux-20260903_153907`. -- Accepted snapshot: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\accepted-v38-resolution-size-source-ux-final-20260903_160000-0a7c670` (`320/320`, mismatch zero). Formal result: **Resolution / Size Source UX Refactor = PASS**. Because the last staged ZIP predates this UX/schema/workflow change, **Release / Registry readiness returns to HOLD until a new package staging Gate passes**. GPU was unnecessary. On user request, ComfyUI_W was preserved in exact 199-file runtime snapshot `pre-v38-resolution-size-source-runtime-w-sync-20260903_163000`, then synchronized from the current 102-entry Registry Manifest. The initial four-file-only attempt exposed the expected missing N2b dependency `branch_provenance.py`; the complete manifest sync resolved it. Restarted only the command-line-verified ComfyUI_W backend at `127.0.0.6:8188`; live `object_info` and frontend routes now pass public registration `7/7`, Size Source/Width/Height schema, and current `project_id.js`. No commit, push, tag, release, or publish was performed. - -## ComfyUI_W Reference-Audio / Installer Sync PASS (2026-09-03) - -- Treated the already-correct ComfyUI_W implementation as authoritative for this limited synchronization. `reference.py` now adds each bundled Reference Audio individually and in order when Reference Image conditioning is also present; legacy single-Audio behavior remains unchanged. -- Added the public-surface verifier helper to the package allowlist, made the Windows installer stop explicitly when that helper is absent, and included the runtime dependency `v3/reference_video.py`. Registry Manifest is now `104/104`; Development Manifest remains `253/253`, both with zero mismatch. -- Focused source regression passed `18`; it includes the new Reference Image + Audio 1/2/3 presentation and `minimax_refs` ordering test. Stage-only import and runtime verifier both passed with public `7/7`. No runtime synchronization, backend/frontend operation, GPU, commit, push, tag, release, or publish occurred. Release / Registry readiness remains HOLD pending official package staging. - -## V3.8 Final Package Staging Re-Gate PASS / Release readiness GO (2026-09-03) - -- The latest 320-file working tree was staged through official `comfy-cli 1.18.0`. The first current-tree archive exposed one packaging-only gap: historical validation/design documents, old-version UI images, `.github`, `.gitignore`, and `pytest.ini` were still included. -- The minimal correction changed only `.comfyignore` plus the two Manifests. Historical/internal docs and repository-only configuration are excluded; only the current N2b, O1, and V3.8 release/migration contracts are retained. Production Python/JavaScript/workflow/schema/Sampling/Run Storage/State/Session/Assembly code is unchanged. -- Official `comfy node validate` and `pack` exited zero. The final archive contains 103 files, is 349704 bytes, and has SHA-256 `9675373D8BD37A345D4467BF3BDB6E869EA3BFE051B730E316AE338A60B0D97F`. -- Source→stage and stage→archive missing/extra/mismatch are all zero. Registry Manifest is `102/102`; Development Manifest is `253/253`. Duplicate, unsafe, zero-byte, banned internal, secret, user-specific-path, and temporary-log findings are all zero. -- Isolated stage-only import passed with no repository fallback. Public class/display/category/schema is `7/7`; AUDIO-R1 helper/backend/frontend/socket and O1 Second Pass finite validation/contract are present. The package contains exactly the two required `tools/` runtime files and one V3.8 public workflow with no orphan/duplicate links or old/experimental nodes. -- Validation passed focused `126`, full pytest `1086`, JavaScript `7/7`, runtime verifier, protected contracts `16/16`, and `git diff --check`. GPU was not run. -- Snapshot: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-v38-final-package-staging-regate-filtered-20260903_141442-0a7c670` (`320/320`, mismatch zero). Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\v38-final-package-staging-regate-20260903_141519`. -- The designated `H3情報チェック` task accepted **V3.8 Final Package Staging Re-Gate = PASS**, found no mandatory correction or additional Gate, and approved **Release / Registry readiness = GO**. Commit, push, tag, GitHub Release, Registry publish, and all other publication remain separate explicit-approval actions and were not performed. - -## Issue #19 Chunk Boundary Continuity PARTIAL REPRODUCTION (2026-09-03) - -- The reported severe video/audio cut resembling separately joined clips was not reproduced under the wrapper-free V3.8 baseline. Dedicated `8190` completed `1x5`, `2x5`, `3x5`, `2x10`, and matched-seed `2x5` explicit-prompt cases; optional `3x10` was safely omitted after the `2x10` run reduced available system RAM to about `0.004 GiB` without exposing a new anomaly. -- Video and Audio latent prefixes were bit-exact at all five physical boundaries. Separately decoding each physical group nevertheless made the same 22-frame RGB overlap non-bit-exact at `5/5` boundaries and increased the visible-join frame MAE by `10.657–21.899%` relative to the raw same-group prefix-to-generated transition. Finalized boundaries remained non-outliers (`0/5`) with SSIM `0.953167–0.972468`; no severe visual cut or trajectory restart was observed. -- Audio had no silence or dropout. Five-second Seam-OFF splice jumps remained below each case's ordinary adjacent-sample P99.9, and existing Audio Seam Auto reduced them from about `0.0958–0.0964` to `0.00354–0.01428`. The accepted FL2VA Terminal `[1]+[2,3]` evidence also showed no new video or audio cut and preserved Terminal atomicity. -- Issue #13 remains a separate cumulative Group 4–6 recursive-feedback pattern. The immediate weak decode-context effect observed here starts at Group 1→2 and did not worsen through three groups. Prefix corruption is rejected for both; Fixed Prefix remains diagnostic-only and was not run for Issue #19. -- Formal cause status: **separate-decode context asymmetry is a reproducible low-level candidate, but causal contribution to the reporter's severity is unproven**. Production remains unchanged. Further promotion requires either reporter-exact reproduction or a cache-only A/B of the same saved latent through separate versus consistent-context/overlap-aware Video VAE decode. -- Validation passed focused `72`, full pytest `1086`, development Manifest `253/253`, Registry Manifest `141/141`, runtime/public export `7/7`, pre-Gate snapshot comparison `320/320`, and `git diff --check`. Dedicated `8190` was stopped after Queue `0/0`; the temporary probe was removed; `8188` and the user Frontend were untouched. -- Evidence: `D:\Codex\_test_results\ComfyUI-H3-Continuum\issue19-chunk-boundary-continuity-20260903_130500`. Pre-Gate snapshot: `D:\Codex\_snapshots\ComfyUI-H3-Continuum\pre-issue19-chunk-boundary-reproduction-filtered-20260903_130348-0a7c670` (`320/320`, mismatch zero). -- The designated `H3情報チェック` task formally accepted **ISSUE19 PARTIAL REPRODUCTION**, found no mandatory correction or additional GPU requirement for this Gate, and agreed that no Production change is justified. Release / Registry readiness remains HOLD; no commit, push, tag, or release was performed. - -## V3.8 AUDIO-R1 Multi Reference Audio 1/2/3 PASS (2026-09-03) - -- Core ComfyUI 0.34.2 formally supports up to three standalone `ref_audios`, presents them to the tokenizer in connection order as `