Replace uses of the legacy `gpt-image-2-all` model with `gpt-image-2` and standardize image workflows: no-reference generation uses POST /v1/images/generations, any-reference flows use POST /v1/images/edits with multipart `image` parts. Update SKILLs, generation scripts, decision logs, and docs to reflect the contract change and edits-vs-generations guidance. Apply corresponding changes across backend (api-server match3d/puzzle modules, openai image adapter, mappers, telemetry, spacetime client/module), frontend components and services (Match3D, Puzzle, CreativeImageInputPanel, runtime shells), and add new spritesheet/parser files and tests. Also add media/logo.png. These changes align repository code and documentation with the VectorEngine image API contract and update generation/upload handling (green-screen -> alpha processing, spritesheet handling, and related tests).
Backend: stop treating background music as a required draft asset and remove auto-submit/plan for background music; load persisted generated UI/assets into Match3D agent session responses (added helpers to resolve profile id and fetch existing generated assets). Frontend: make Match3D result preview reuse runtime UI styles, unify runtime settings entry, update PuzzleRuntime to apply immediate pointermove transforms (disable drag transition), use SVG clipPath for merged piece rounding, ensure PuzzleRuntimeShell supplies platform theme classes, and adjust related tests. Docs & logs: update decision log, pitfalls and product docs to reflect these changes.
Delete a large set of outdated documentation (many files under docs/ and .hermes/plans/, including audits, design, prd, technical, planning, assets, and todos). Update and consolidate .hermes content: refresh shared-memory pages (decision-log, development-workflow, document-map, pitfalls, project-overview, team-conventions) and several skills/references under .hermes/skills. Also modify AGENTS.md, README.md, UI_CODING_STANDARD.md, docs/README.md and .encoding-check-ignore. Purpose: clean up stale planning/audit material and keep current hermes documentation and related top-level docs in sync.
Add VectorEngine image generation config and raise request timeouts (env + scripts) from 180000 to 1000000ms. Introduce a reusable CreativeImageInputPanel component with tests and wire up mobile keyboard-focus helpers; update generation views and related tests (CustomWorldGenerationView, BarkBattle editor, Match3D, Puzzle flows). Improve API error handling / VectorEngine request guidance (packages/shared http.ts and docs), and apply multiple backend/frontend fixes for puzzle/match3d/prompt handling. Also include extensive docs and decision-log updates describing UI/UX decisions and verification steps.
Adds/updates documentation, assets and implementation for Match3D and puzzle image generation workflows. Key changes: decision logs and pitfalls updated to prefer VectorEngine Gemini for Match3D material sheets and to require edits (multipart) for 1:1 container reference images; guidance added for when to use APIMart vs VectorEngine. .env.example clarified APIMart/Responses config. Many new public assets and PPT visuals added. Code changes across frontend and backend: updated shared contracts, server-rs match3d/puzzle/image-generation handlers, VectorEngine/OpenAI image generation clients, and multiple React components/tests to handle UI/background/container image signing, edits workflow, and puzzle UI background resolution. Added src/services/puzzle-runtime/puzzleUiBackgroundSource.ts and related test updates. Includes notes about multipart HTTP/1.1 requirement and test/verification commands in docs.
