β¨ feat: add gpt-image-2 to LobeHub-hosted card#14039
Merged
Merged
Conversation
Add GPT Image 2 (released 2026-04-21) with its official "Popular sizes" preset list (up to 4K) and standard-tier pricing. Keep gpt-image-1.5 enabled as the previous-generation sibling.
maxFileSize is compared against file.size (bytes) in UploadCard, but gptImage1Schema/gptImage2Schema had it set to a bare `5` instead of `5 * 1024 * 1024`, so every ref image upload was silently filtered out.
Medium quality 1024x1024 uses ~1767 output tokens at \$30/M, which is \$0.053 per image β not \$0.032. Source: https://developers.openai.com/api/docs/guides/image-generation#calculating-costs
gpt-image-2 dropped the input_fidelity parameter ("output is already
high fidelity by default"), so the old includes('gpt-image-') allowlist
would attach an unsupported arg and break edit requests.
Switch to an explicit allowlist of gpt-image-1 / gpt-image-1.5, and
attach { cause } to the pre-existing rethrows (lint gate).
Source: https://developers.openai.com/cookbook/examples/multimodal/image-gen-models-prompting-guide
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Replace the generic "Image Generation" starter with a featured "GPT Image 2 π₯" entry (mirroring the Seedance 2.0 treatment), and land users directly on /image with gpt-image-2 pre-selected.
There was a problem hiding this comment.
π‘ Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 8e2709187c
βΉοΈ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with π.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| // gpt-image-2 dropped input_fidelity ("output is already high fidelity by default"). | ||
| // https://developers.openai.com/cookbook/examples/multimodal/image-gen-models-prompting-guide | ||
| const supportsInputFidelity = | ||
| isImageEdit && (model === 'gpt-image-1' || model === 'gpt-image-1.5'); |
There was a problem hiding this comment.
Preserve input_fidelity for gpt-image-1 snapshot aliases
The new supportsInputFidelity check only matches exact model IDs (gpt-image-1/gpt-image-1.5), but createImage forwards payload.model as-is, so snapshot or aliased IDs (for example dated snapshots of GPT Image 1) no longer get input_fidelity: 'high' on edit calls even though the previous logic covered them. In those cases image-edit requests regress in behavior/quality without any explicit error, so this should use alias normalization or a prefix-based match for the gpt-image-1 family instead of exact equality.
Useful? React with πΒ / π.
Codecov Reportβ
All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## canary #14039 +/- ##
========================================
Coverage 66.98% 66.98%
========================================
Files 2104 2104
Lines 179774 179774
Branches 21270 22051 +781
========================================
+ Hits 120419 120421 +2
+ Misses 59232 59230 -2
Partials 123 123
Flags with carried forward coverage won't be shown. Click here to find out more.
π New features to boost your workflow:
|
Exact-equality allowlist missed dated snapshot IDs (e.g. gpt-image-1-2026-01-15) that the old includes() check previously covered, so edits against those aliases would silently regress. Use a family-prefix regex with a delimiter guard, and keep the mini exclusion. Covers both gpt-image-1 and gpt-image-1.5 including their snapshot aliases; still excludes gpt-image-2.
Brand-colored Jimeng icon reads better alongside the "Seedance 2.0 π₯" label than the generic lucide VideoIcon. Revert the icon portion of 6d0c8d7 while keeping the model query param navigation.
|
I'm using the Canary version and have configured both gpt-image-1.5 and gpt-image-2, but in the drawing interface only gpt-image-1.5 is available to select, while gpt-image-2 shows up in the chat interface. |
arvinxx
added a commit
that referenced
this pull request
Apr 27, 2026
# π LobeHub v2.1.53 (20260427) **Release Date:** April 27, 2026 **Since v2.1.52:** 194 merged PRs Β· 17 contributors > Introduce Heterogeneous Agent β Claude Code and Codex run as first-class desktop runtimes, paired with a new Agent Signal package, sharper desktop UX, and a wave of flagship model additions. --- ## β¨ Highlights - **Introduce Heterogeneous Agent** β Claude Code and Codex run as first-class desktop agents: subagent rendering, partial-message streaming, multi-turn resume, terminal error surfacing, rich tool inspectors, and runtime polish. (#14162, #13754, #14067, #14001, #13970, #13942) - **Screen capture & Quick Chat tray** β New desktop screen capture overlay (macOS permission-gated) with Quick Chat tray and upload pipeline improvements; chat input auto-focuses on overlay mount. (#13818, #14097, #14105) - **Desktop topic & tab UX** β Dedicated topic popup window with cross-window sync, Cmd+W/Cmd+T tab shortcuts, TabBar polish, recent working directories expanded to 20, and human approval notifications. (#13957, #13983, #13972, #14036, #14092) - **Git workflow built-in** β One-click pull/push from the branch chip, ahead/behind badge, and submodule/worktree repo detection. (#14041, #13980, #13978) - **Agent Signal package** β New `@lobechat/agent-signal` runtime for dynamic memory feedback signals, with OTel metrics and self-iteration in Lab. (#14157, #14170, #14159, #14169, #14187) - **New models** β Claude Opus 4.7 with `xhigh` effort tier, GPT-5.5, DeepSeek V4 Flash/Pro with reasoning slider, Kimi K2.6, MiMo-V2.5/Pro, gpt-image-2, Qwen3.6 Flash/Plus, and Pixverse-c1. (#13903, #14147, #14114, #14004, #14089, #14039, #13923) - **New providers** β OpenCode Zen, OpenCode Go, and Azure OpenAI Router runtime. (#13943, #14064, #13823) - **Mobile settings overhaul** β Full settings menu and responsive profile layout for mobile. (#14019) --- ## ποΈ Heterogeneous Agent - Claude Code runtime, working-directory awareness, and sidebar polish. (#13970) - CC subagent rendering with persistent streamed text; parallel-tool orphan fix. (#14001, #13968, #14024) - Per-step usage persisted to each step assistant message. (#13964) - Per-phase workflow expand defaults; full-expand toggle with three-level expansion. (#14171, #13906) - Hetero-mode actions bar; tool inspector polish. (#13963, #14034, #14030) - Codex desktop integration with rich tool rendering and devtools preview. (#14067, #14100) - Codex terminal error surfacing and CLI output tracing. (#14166) - Tighten `isCanUseVision` default and add aggregator fallback. (#14172) - Persist `ccSessionId` in topic metadata for CC multi-turn resume. (#13902) - CC account card, topic filter, and integration polish. (#13955, #13942, #13950) - Token-level deltas streamed via `--include-partial-messages`. (#13929) --- ## π§ Agent Signal & Self-Iteration - New `@lobechat/agent-signal` package with dynamic feedback signals. (#14157) - AgentSignalRuntime wired through agent-tracing and observability-otel metrics. (#14170, #14159) - Self-iteration feature flag added to Lab; front-side flag check. (#14169, #14186) - Signal policy for receiving memory feedback dynamically. (#14187) --- ## π¬ Conversation - Queue follow-up sends during running CC turns. (#14179) - Persist per-topic chat scroll position; pin user message + fold long messages. (#14191, #14056) - Inline resend when editing last user message. (#14080) - Disable first-block markdown streaming to prevent flicker. (#14193, #13904) - Prevent Markdown stream replay when vlist remounts streaming items. (#14086) - Stop repinning after manual scroll; unify scroll-to-user + spacer hooks. (#14099, #14132) --- ## π± Platforms & Integrations ### Desktop / Electron - Screen capture overlay, Quick Chat tray, and upload pipeline improvements. (#13818) - macOS permission gate for screen capture; auto-focus chat panel input. (#14097, #14105) - Dedicated topic popup window with cross-window sync. (#13957) - TabBar polish: `+` button for new topic, dark theme blend, close icon by default. (#13972, #14203, #13973) - Recent working directories expanded from 5 to 20; submodule/worktree repo detection. (#14036, #13978) - Cmd+W / Cmd+T tab shortcuts and global shortcut consolidation. (#13983, #13880) - Linux icon configuration; human approval desktop notifications. (#14042, #14092) ### Git Workflow - One-click pull/push from branch chip; ahead/behind badge with refactored GitCtr. (#14041, #13980) ### Mobile - Full settings menu and responsive profile layout. (#14019) - Agent route added to mobile router; mobile agent topic route registered. (#14103, #14158) - Session list skeleton row layout corrected. (#14040) ### Bot / Messaging - DM strategy support; bot emoji and markdown render optimization. (#14201, #14091, #14140) - Slack webhook fix; bot platform setup guide reference. (#14052, #14121) --- ## π€ Models & Providers ### New models - **Claude Opus 4.7** with `xhigh` effort tier; strip temperature/top_p. (#13903, #13909) - **GPT-5.5**. (#14147) - **DeepSeek V4** Flash/Pro cards with reasoning slider; cache-hit and Pro discount pricing. (#14114, #14209, #14196, #14131) - **Kimi K2.6** model with LobeHub-hosted card. (#14004, #14006) - **MiMo-V2.5 / V2.5-Pro**. (#14089) - **gpt-image-2**, **Qwen3.6 Flash/Plus**, **Pixverse-c1**. (#14039, #13923) ### New providers - **OpenCode Zen** and **OpenCode Go** with env-var support. (#13943, #14064) - **Azure OpenAI Router** runtime support. (#13823) - Model alias mapping for image and video runtimes. (#13896) - Seedance video models migrated to Dreamina. (#14144) ### Runtime reliability - Sanitize invalid tool_call arguments to unbreak strict providers. (#14033) - Tolerate null `function.name` in streaming tool_call deltas. (#14139) - Preserve Gemini 3 `thoughtSignature` in `call_tools_batch` normalization. (#14032) - Downgrade `image_url` parts when target model lacks vision. (#14029) - Preserve Cloudflare provider error context. (#14136) - Use `safety_identifier` for OpenAI Responses API. (#14148) - Unwrap underlying PG error in `formatErrorEventData`. (#14038) --- ## π₯οΈ User Experience - **Onboarding** β Preset agent naming suggestions, structured hunk ops for `updateDocument`, persona analytics snapshot, footer promotion pipeline, wrap-up button. (#13931, #13989, #13930, #13853, #13934) - **Document workflow** β Agent documents promoted as primary workspace panel; history management and compare workflow; web-crawl docs associated with agent documents. (#13924, #13725, #13893) - **cmdk** β Agent identity surfaced on topic search results; topic/message search scoped to current agent. (#14204, #13960) - **Floating chat panel** and workspace improvements. (#13887) - **Topic completion status** with dropdown action and filter. (#14005) --- ## π§ Tooling - Redis-backed feature flag provider for runtime config. (#14098) - Vite upgraded to 8.0.0 with Rolldown strict execution order. (#12720, #14058) - `@lobechat/model-bank` automated npm release with provenance. (#14015, #14017, #14018) - Skill activation fallback when `activateTools` cannot find identifier. (#14010) - Cron tool: timezone and existing jobs injected into system prompt; clarified `lobe-gtd` and `lobe-cron` descriptions. (#14012, #14013) --- ## π Security & Reliability - **Security:** uuid bumped to v14 (advisory). (#14083) - **Security:** validate avatar URL and scope old-avatar deletion to owner. (#13982) - **Security:** clear OIDC sessions on better-auth signout; return 401 (not 500) for expired OIDC JWT. (#13916, #14014) - **Reliability:** scope pending-approval check to current assistant turn. (#14182) - **Reliability:** sanitize heterogeneous-agent attachment cache filenames. (#13937) - **Reliability:** reduce subagent task status error noise. (#14026) --- ## π₯ Contributors Huge thanks to **17 contributors** who shipped **194 merged PRs** this week. @hardy Β· @shaun0927 Β· @hezhijie0327 Β· @sxjeru Β· @arvinxx Β· @Innei Β· @tjx666 Β· @lijian Β· @neko Β· @rdmclin2 Β· @AmAzing129 Β· @sudongyuer Β· @CanisMinor Β· @rivertwilight Plus @lobehubbot and renovate[bot] for maintenance. --- **Full Changelog**: v2.1.52...v2.1.53
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
π» Change Type
π Related Issue
N/A β ships OpenAI's gpt-image-2 (released 2026-04-21) on the LobeHub-hosted card, and fixes three pre-existing or newly-surfaced bugs along the way.
π Description of Change
1. Add
gpt-image-2card (lobehub/chat/image.ts+ newgptImage2Schema)approximatePricePerImage: 0.053(medium 1024Γ1024 β 1767 output tokens Γ $30/M).sizeenum exposes the 8 official "Popular sizes" from the image-generation guide. Model actually accepts any WΓH satisfying max edge β€ 3840, both edges multiples of 16, AR β€ 3:1, pixels 655,360β8,294,400 β but our schema/UI does not yet support free-form inputs, so we stick to the documented Popular list for now.releasedAt: '2026-04-21'(matches thegpt-image-2-2026-04-21snapshot ID).2. Fix:
maxFileSizeunit in gpt-image schemasUploadCardcomparesfile.size(bytes) againstmaxFileSize, butgptImage1SchemahadmaxFileSize: 5(bare number), so every ref image upload was silently dropped by the front-end filter with no network request. Changed to5 * 1024 * 1024. Fixes the same bug in gpt-image-1 that nobody noticed becauseimageUrlshad no UI affordance until now.3. Fix: do not send
input_fidelitytogpt-image-2gpt-image-2 dropped this parameter ("output is already high fidelity by default" β cookbook). The old
model.includes('gpt-image-') && !model.includes('mini')check would attach an unsupported arg and break edit requests. Switched to an explicit allowlist (gpt-image-1/gpt-image-1.5).π§ͺ How to Test
should NOT send input_fidelity for gpt-image-2 (unsupported param)should include input_fidelity parameter for gpt-image-1 modelstill passes/imageβ ref image upload now makes network requests instead of being silently filteredπ Additional Information
Breaking changes vs gpt-image-1.5:
input_fidelityremoved (always high)sizeis now constraint-based, not enum (we still enumerate Popular sizes for UI)Not addressed in this PR (potential follow-ups):
qualityparameter (low/medium/high) is not exposed β 35Γ price range ($0.006 / $0.053 / $0.211 @ 1024Γ1024); users cannot opt into low-cost mode, and ourapproximatePricePerImageassumes medium.backgroundparameter (opaque β pure white, not alpha transparent) β not exposed.azureOpenai/index.ts:178) still unconditionally sendsinput_fidelity; fine for now since Azure endpoints are single-model, but needs the same allowlist treatment when gpt-image-2 lands on Azure.