fix: preserve external INT Width and Height facade bindings
Preserve V3.8/V3.9 external dimension links across workflow restore, disable linked facade editing and keep saved Manual reserve values. Document Manual versus First Image authority in both READMEs; add frontend/CPU regressions without changing backend schemas, Sampling, Run Storage or earlier Review/cache repairs. Validation: 1569 CPU passed, 1 skipped; 22/22 new frontend and 60/60 Review cases; Chrome save/reload and five tab round trips. One V3.9 GPU smoke generation produced exactly 480x640, 96 frames at 24fps and 4-second audio in 107.3s. This is a single short resolution check, not long-form acceptance. Official workflows/ZIPs, package version and historical Releases unchanged.
This commit is contained in:
@@ -1,5 +1,26 @@
|
||||
# Project State
|
||||
|
||||
## Issue #25 — external INT dimensions, main publication candidate (2026-10-01)
|
||||
|
||||
- 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`.
|
||||
|
||||
## R0 / Fixed conditioning cache reuse — main publication candidate (2026-10-01)
|
||||
|
||||
- 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.
|
||||
|
||||
|
||||
## V3.9.0 main-source publication (2026-09-29)
|
||||
|
||||
- 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.
|
||||
|
||||
Reference in New Issue
Block a user