e244ee5240
Some checks failed
Forgejo Android APK / Root app tests (push) Successful in 1m0s
Forgejo Docker Build / Root app tests (push) Successful in 47s
Forgejo Android APK / Build signed APK (push) Successful in 2m13s
Forgejo Docker Build / Build Docker image (push) Successful in 24s
Forgejo Docker Build / Deploy to the host (push) Failing after 0s
The model editing a deck could not see it, which made most of what people actually ask for unanswerable: "that slide is too crowded", "the diagram is in the wrong place", "this one looks empty" are facts about the rendered page, not about the JSON. When a vision model is configured, modifying now renders the current deck — with its figures, unlike the review pass, which runs while they are still being drawn — and hands the model one image per slide alongside the JSON. Same pipeline as review, reused rather than reimplemented: pptx, Gotenberg, PDF, pdftoppm, capped at MAX_SLIDES. The vision model then does the editing, which is a second and separately measured benefit. On a real 20-slide deck, ds-deepseek-v4-flash returned the deck unchanged for "make it better" — the echo reported yesterday — while openrouter-gemini-3.8-flash applied it. So the stronger model fixes the echo even without sight. A model the author picks explicitly still wins over both. The result is rendered and reviewed again. Generation-only was the old rule, on the reasoning that refining is a text edit; it is not. The edit is made against how the deck looked before it, so a slide that gains two bullets only overflows once it is rendered again. The reviewer may reposition but is held to the same words, so a verification pass cannot quietly undo what was just asked for. Whether an instruction achieved anything is judged on the model's edit, before the reviewer runs, or a reviewer nudging a slide into two columns would mask an instruction that did nothing. Sight is an upgrade, never a dependency: no vision model, Gotenberg down, a render that fails — each falls through to editing blind, and a test covers each of those paths. Verified against two mutations: keeping the text model when images are attached, and dropping the verification pass, each fail exactly one test. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Dv6sqaY6Vq3ChZHMem3cnU |
||
|---|---|---|
| .. | ||
| logic | ||
| ai-providers.md | ||
| api-reference.md | ||
| architecture.md | ||
| authentication.md | ||
| clinical-assistant.md | ||
| configuration.md | ||
| database.md | ||
| deployment.md | ||
| developer-guide.md | ||
| embeddings-setup.md | ||
| features-explained.md | ||
| global-prompt-administration.md | ||
| improvements.md | ||
| learning-hub.md | ||
| migrations.md | ||
| mobile-build.md | ||
| module-conventions.md | ||
| my-resources.md | ||
| openid-setup.md | ||
| ops-docs-ped-ai-and-milvus.md | ||
| retrieval-tuning.md | ||
| scaling.md | ||
| speech.md | ||