Commit Graph

7 Commits

Author SHA1 Message Date
root a339e09859 feat(agent): guide creative agent to use purposeful emoji in replies
Add prompt instructions for emoji-led list formatting in visible
responses, plan narration, and image summaries, with guardrails against
hyphen chaining and empty numbered choices. Tighten the planner's
userFacingResponse description.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-08 14:33:16 +08:00
root 7679854b5d feat(image): stream text-to-image generation with SSE and fallback
Send stream=true for text-to-image requests and consume the SSE
response, falling back to a non-streamed request when the stream errors
in a way that warrants it. Raises the scanner line limit to handle large
base64 image payloads.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-08 12:06:39 +08:00
root ad67fe1ebe feat(agent): clarify vague briefs before generating and harden prompts
Let the planner return a clarify/chat intent that asks 2-4 targeted
questions (imageCount 0) when essentials are missing, instead of forging
ahead. Tighten prompt guidance to preserve user wording and stated
reference-image roles, avoid inventing copy/specs, keep durable brand
constraints, and treat vague taste feedback as clarification. Also
fix the generation heartbeat goroutine to stop cleanly via defer, add
research-query fallbacks, and refresh image-only capability copy.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-08 10:56:55 +08:00
root 1a1c0a6544 fix(image): add response-header timeout and idempotent retry
Give the image client a configurable ResponseHeaderTimeout (default 4m,
capped at the overall timeout) so a stalled upstream fails fast, and
retry such timeouts when an idempotency key is set so a slow-but-safe
request can recover instead of terminating. Raise the Next.js API proxy
maxDuration to 1200s to accommodate long generations.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-08 10:56:42 +08:00
root 836de5b597 feat(research): hydrate web-search results with cleaned page content
Fetch and clean each search result's page body (bounded by size,
concurrency, and a configurable MaxPageContentRunes), store it on the
new ResearchResult.Content field, and surface those excerpts in agent
memory so the model reasons over real page text rather than snippets
alone. Promotes golang.org/x/net to a direct dependency for HTML
parsing.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-08 10:56:31 +08:00
root 2f5291a0f9 feat(image): pass reference images to GPT image model for edits
Server: forward canvas/reference images to the image model so extract,
continue, and edit requests stay faithful to the source product.
- Add ImageRequestOptions.Images and route requests with inputs to the
  /v1/images/edits endpoint, via multipart upload (default) or JSON
  image_url payload, selectable through Agent.Image.InputImageTransport.
- Extract reference URLs from prompt directives, inline @image tokens,
  and chat message image/mask contents; fold them into the idempotency
  key and prepend a reference-fidelity instruction to the prompt.

Frontend:
- Shrink CanvasToast to a compact top pill.
- Paste an internal transparent clipboard node instead of re-uploading
  when it matches the clipboard image.
- Keep agent-project polling alive on stream error while streaming.
2026-07-08 01:19:20 +08:00
root 44406b72db Initial commit: img-infinite-canvas AI design workbench MVP
Moteva-style AI design workbench replica. Home prompt creates a project;
the project page provides an infinite canvas with node drag, zoom/pan,
a design chat panel, history replay, image asset upload, and project
save/regenerate.

- Backend: go-zero, DDD layering, sqlc/pgx, optional PostgreSQL; memory
  or Redis cache; asynq job queue; MinIO/S3/R2/OSS object storage;
  sky-valley/pi agent runtime adapter.
- Frontend: Next.js App Router + Vite artifact build, TypeScript, i18n,
  shadcn/ui components, auth (OTP/Turnstile/Google/WeChat).
- Deploy: Docker Compose and k3s manifests.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-07 23:15:37 +08:00