🔨 chore(model-runtime): support azure openai router runtime#13823
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 1f1a244e8b
ℹ️ 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 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| const unsupportedReasoningParams = isAzureReasoningModel(model) | ||
| ? {} | ||
| : { |
There was a problem hiding this comment.
Preserve sampling controls when reasoning is disabled
This logic strips temperature, top_p, logprobs, and related fields for every model matched by isAzureReasoningModel, regardless of reasoning_effort. For requests such as gpt-5.* with reasoning_effort: 'none', user sampling settings are silently dropped because unsupportedReasoningParams is {}, which can change output behavior and prevents users from controlling determinism/creativity in that mode.
Useful? React with 👍 / 👎.
| const runtimeModel = router.models?.[0] ?? ''; | ||
| const { id: resolvedApiType, runtime } = await this.createRuntimeFromOption( | ||
| router, | ||
| routerOptions[0], | ||
| runtimeModel, |
There was a problem hiding this comment.
Avoid model-order-dependent API version in models()
The models() path now feeds router.models?.[0] into createRuntimeFromOption, so apiVersionMapping resolution depends on the first model’s position in config rather than an explicit discovery version. Because models() is not tied to a specific model request, this can initialize a runtime with a preview API version intended for one model and make model discovery behavior change when the model array order changes.
Useful? React with 👍 / 👎.
Codecov Report❌ Patch coverage is Additional details and impacted files@@ Coverage Diff @@
## canary #13823 +/- ##
===========================================
- Coverage 86.12% 67.57% -18.56%
===========================================
Files 610 2192 +1582
Lines 51406 188837 +137431
Branches 8689 22458 +13769
===========================================
+ Hits 44273 127603 +83330
- Misses 7005 61106 +54101
Partials 128 128
Flags with carried forward coverage won't be shown. Click here to find out more.
🚀 New features to boost your workflow:
|
2cbe45f to
3e3e7cf
Compare
0aace8c to
995fadd
Compare
995fadd to
504bc2d
Compare
504bc2d to
1c3f583
Compare
1c3f583 to
79e6513
Compare
79e6513 to
b076542
Compare
This reverts commit 2464414.
- rename `unsupportedReasoningParams` to `supportedSamplingParams` so the variable name reflects its actual role (params passed through for non-reasoning models) and drop the misleading `_` prefix on destructured params that were re-read - tighten `normalizeAzureBaseURL` path check to use segment-boundary matching so values like `/openaifoo` no longer falsely satisfy the already-has-`openai` condition and get rewritten - hoist `convertImageUrlToFile` dynamic import out of the two mutually exclusive image-input branches to avoid duplicate imports on the hot path - strengthen `createRuntime.test.ts` "preserve unsupported version fields" assertion so it explicitly verifies `apiVersionMapping` is forwarded to every constructor call rather than relying on `objectContaining` that silently ignores the field
…omOption The `model` parameter was threaded through `createRuntimeFromOption` as scaffolding for per-model `apiVersionMapping` resolution, but LOBE-7220 drops the apiVersion dependency entirely in favor of the Azure `/openai/v1/` endpoint. Remove the dead signature noise and the companion `apiVersionMapping` preservation test so the router contract no longer implies behavior that will never ship. Refs: LOBE-7220
c0b9b6b to
ca5b923
Compare
# 🚀 LobeHub v2.1.53 (20260427) **Release Date:** April 27, 2026 **Since v2.1.52:** 194 merged PRs · 17 contributors > Introduce Heterogeneous Agent — 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. --- ## ✨ Highlights - **Introduce Heterogeneous Agent** — 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** — 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** — 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** — One-click pull/push from the branch chip, ahead/behind badge, and submodule/worktree repo detection. (#14041, #13980, #13978) - **Agent Signal package** — 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** — 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** — OpenCode Zen, OpenCode Go, and Azure OpenAI Router runtime. (#13943, #14064, #13823) - **Mobile settings overhaul** — Full settings menu and responsive profile layout for mobile. (#14019) --- ## 🏗️ 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) --- ## 🧠 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) --- ## 💬 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) --- ## 📱 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) --- ## 🤖 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) --- ## 🖥️ User Experience - **Onboarding** — 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** — Agent documents promoted as primary workspace panel; history management and compare workflow; web-crawl docs associated with agent documents. (#13924, #13725, #13893) - **cmdk** — 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) --- ## 🔧 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) --- ## 🔒 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) --- ## 👥 Contributors Huge thanks to **17 contributors** who shipped **194 merged PRs** this week. @hardy · @shaun0927 · @hezhijie0327 · @sxjeru · @arvinxx · @Innei · @tjx666 · @lijian · @neko · @rdmclin2 · @AmAzing129 · @sudongyuer · @CanisMinor · @rivertwilight Plus @lobehubbot and renovate[bot] for maintenance. --- **Full Changelog**: v2.1.52...v2.1.53
💻 Change Type
🔗 Related Issue
N/A
🔀 Description of Change
azureopenaiRouterRuntime apiType instead of routing Azure OpenAI traffic throughazureaiapiVersionMappingresolution in RouterRuntime provider options🧪 How to Test
Manual verification:
gpt-5.4throughazureopenaiin local router runtime configusagecomputeChatPricingandcreateCostTrackerrecord non-zero spend forgpt-5.4@lobehubAutomated coverage added:
packages/model-runtime/src/providers/azureOpenai/index.test.tspackages/model-runtime/src/core/RouterRuntime/createRuntime.test.tsNote:
zodinitialization issue duringmodel-bankimport in this environment📸 Screenshots / Videos
📝 Additional Information
azureai) and Azure OpenAI (azureopenai) routing semantics separate to avoid endpoint/runtime mismatchesapiVersionMappingallows chat and embeddings on the same Azure resource to use different API versions when required