fix(aihubmix): use full models endpoint to return complete model list by Bianzinan · Pull Request #14511 · lobehub/lobehub

Bianzinan · 2026-05-08T03:38:31Z

Problem

AiHubMix has two model list endpoints with different behavior:

Endpoint	Behavior
`GET https://api.aihubmix.com/v1/models`	Only models in the user's subscription group (~256)
`GET https://aihubmix.com/api/v1/models`	Complete model catalog (800+)

The previous implementation called client.models.list(), which hits the first endpoint via the configured baseURL = 'https://api.aihubmix.com'. As a result, self-hosted LobeHub instances only showed ~256 AiHubMix models instead of all available ones.

This is documented in the AiHubMix API docs: https://docs.aihubmix.com/cn/api/Models-API

Solution

Fetch directly from https://aihubmix.com/api/v1/models using the user's API key. This endpoint returns the full catalog without user-group restrictions. The chat request routing (via routers) is unchanged and continues to use the existing baseURL.

Additional robustness improvements:

API key guard: extract apiKey with a runtime check; throws immediately instead of silently sending Bearer undefined
Timeout: AbortController with a 10-second timeout prevents the request from hanging indefinitely; clearTimeout in finally prevents timer leaks
Better error messages: non-OK responses include the response body for easier debugging
model_id normalization: the full endpoint returns model_id instead of id; each item is normalized to { id: m.id ?? m.model_id, ...m } before being passed to processMultiProviderModelList
APP-Code header comment: added a doc link explaining why this header is required

Testing

After applying this change, fetching the remote model list for AiHubMix returns 800+ models instead of ~256.

Unit tests added/updated in index.test.ts:

Mock global fetch with vi.fn(); reset in afterEach
Verifies the correct endpoint and headers are used
Verifies model_id → id normalization does not throw
Returns empty array when API key is missing (no fetch call made)
Returns empty array on HTTP 401
Returns empty array on network error
Returns empty array on AbortError (timeout)

The /v1/models endpoint at api.aihubmix.com returns only per-user-group models (~256). The new endpoint at aihubmix.com/api/v1/models returns the complete catalog (800+). Fetch from the full endpoint directly.

vercel · 2026-05-08T03:38:35Z

@Bianzinan is attempting to deploy a commit to the LobeHub OSS Team on Vercel.

A member of the Team first needs to authorize it.

sourcery-ai

Sorry @Bianzinan, you have reached your weekly rate limit of 500000 diff characters.

Please try again later or upgrade to continue using Sourcery

lobehubbot · 2026-05-08T03:40:11Z

@tjx666 - This is a provider (AiHubMix) fix. Please take a look.

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 808fbf9467

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".

chatgpt-codex-connector · 2026-05-08T03:42:42Z

+      const modelList: AiHubMixModelCard[] = json.data || [];
      return await processMultiProviderModelList(modelList, 'aihubmix');


Normalize model_id to id before processing model list

The new /api/v1/models response is passed straight through as json.data, but downstream parsing assumes every entry has an id field. In processMultiProviderModelList, detectModelProvider(model.id) calls toLowerCase() on model.id; if the endpoint returns the documented model_id shape, this throws and the catch path returns an empty list, so users see no AiHubMix models. Map each item to { id: model_id, ... } (or equivalent) before calling processMultiProviderModelList.

Useful? React with 👍 / 👎.

The https://aihubmix.com/api/v1/models endpoint uses `model_id` instead of `id`. Map it to `id` before passing to processMultiProviderModelList to prevent toLowerCase() errors and empty model list.

…error messages - Extract apiKey with runtime guard to fail fast when key is missing - Add AbortController with 10s timeout to prevent indefinite hanging - Include response body in error message for easier debugging - Add APP-Code header comment pointing to docs - Expand tests: mock global fetch, cover missing key / HTTP error / network error / AbortError cases

tjx666 · 2026-05-10T03:18:36Z

The direction of this change is correct: AiHubMix's new https://aihubmix.com/api/v1/models endpoint does return the full catalog (I've verified it currently returns 803 entries), while the old /v1/models only returns 200+.

However, the current implementation only handles model_id -> id, without adapting the other fields from the new API to LobeHub's model card fields. This results in "a longer model list" but with incomplete or inaccurate model information:

model_name is not mapped to displayName
desc is not mapped to description
types is not mapped to type, e.g., llm -> chat, image_generation -> image, embedding -> embedding
features is not mapped to functionCall / reasoning / search capabilities
input_modalities is not mapped to vision / file-related abilities
context_length is not mapped to contextWindowTokens
max_output is not mapped to maxOutput
pricing.cache_read / pricing.cache_write is not mapped to pricing.cachedInput / pricing.writeCacheInput

Note that pricing.input / pricing.output happen to match the existing parser field names, so those two are currently consumed correctly.

This issue looks more like a schema adapter gap exposed when switching the data source. The old API returned OpenAI-style id/object/created/owned_by, and previously relying only on id was acceptable; the new API returns AiHubMix's own richer schema, so an AiHubMix -> ChatModelCard field mapping layer is needed here. Otherwise, the value of the full catalog will be diminished, and some image model / capability information may be filtered out or displayed incorrectly.

Additionally, the test should normalize model_id field to id currently only asserts Array.isArray(list), which is too weak. If you remove the normalization, an internal error would be caught and return [], and the test would still pass. I recommend at least asserting that the returned results contain the expected id, or mocking processMultiProviderModelList and asserting that the model passed in already has id: "some-model".

One more minor point: the current timeout only covers the fetch() resolve; the response.json() / response.text() body reading phase is not protected by this 10s timeout. If the server returns headers first but the body hangs, the request can still get stuck. Consider placing the body read within the same abort timeout scope, and add a fake timer test for this.

This comment was translated by Claude.

Original Content

这次改动方向是对的：AiHubMix 新的 https://aihubmix.com/api/v1/models 确实能返回完整目录（我这边实测当前是 803 条），旧的 /v1/models 只有 200 多条。

不过现在实现只做了 model_id -> id，还没有把新接口的其他字段适配成 LobeHub 的 model card 字段。这样会导致模型列表变长了，但模型信息不完整或不准：

model_name 没有映射到 displayName
desc 没有映射到 description
types 没有映射到 type，例如 llm -> chat、image_generation -> image、embedding -> embedding
features 没有映射到 functionCall / reasoning / search 等能力
input_modalities 没有映射到 vision / file-related abilities
context_length 没有映射到 contextWindowTokens
max_output 没有映射到 maxOutput
pricing.cache_read / pricing.cache_write 没有映射到 pricing.cachedInput / pricing.writeCacheInput

其中 pricing.input / pricing.output 刚好和现有 parser 字段名一致，所以这两个目前能被吃到。

这个问题更像是这次切换数据源后暴露出来的 schema adapter 缺口。旧接口返回 OpenAI-style id/object/created/owned_by，之前只依赖 id 还说得过去；新接口返回的是 AiHubMix 自己的 richer schema，所以这里需要加一层 AiHubMix -> ChatModelCard 的字段转换，不然完整 catalog 的价值会打折，部分图片模型/能力信息也可能被过滤或显示错误。

另外测试里 should normalize model_id field to id 现在只断言 Array.isArray(list)，这个断言太弱了。如果删掉 normalization，内部抛错后会被 catch 成 []，测试仍然会过。建议至少断言返回结果里包含目标 id，或者 mock processMultiProviderModelList 后断言传进去的 model 已经有 id: "some-model"。

还有一个小点：当前 timeout 只覆盖到 fetch() resolve，response.json() / response.text() 读 body 阶段不受这个 10s timeout 保护。如果服务端先返回 headers 但 body 卡住，仍然可能挂住。可以把 body read 也放在同一个 abort timeout 范围里，并补一个 fake timer 测试。

Address review feedback from lobehub#14511: - Update AiHubMixModelCard interface to reflect the new endpoint schema with full JSDoc (model_id, desc, types, features, input_modalities, context_length, max_output, pricing.cache_read/cache_write) - Add mapAiHubMixModel() to adapt API response fields to LobeHub model card fields before passing to processMultiProviderModelList: desc -> description model_name -> displayName context_length -> contextWindowTokens max_output -> maxOutput types -> type (llm/t2t->chat, image_generation/t2i->image, video/t2v->video, tts, stt, embedding, rerank/reranking->rerank) pricing.cache_read -> pricing.cachedInput pricing.cache_write -> pricing.writeCacheInput features(tools/function_calling) -> functionCall features(thinking) -> reasoning features(web) -> search input_modalities(image) -> vision - Fix timeout scope: move clearTimeout into the finally block so the AbortController stays active during response.json() body read, not just during the initial fetch() call - Update baseURL from https://api.aihubmix.com to https://aihubmix.com to match official integration docs (https://docs.aihubmix.com/cn/api/Aihubmix-Integration) - Strengthen normalize test: assert list.some(m => m.id === 'some-model') instead of just Array.isArray to detect normalization failures - Add field-mapping test using vi.spyOn on processMultiProviderModelList to assert that all adapted fields are passed correctly

tjx666 · 2026-05-10T15:49:24Z

+  embedding: 'embedding',
+  image_generation: 'image',
+  llm: 'chat',
+  rerank: 'rerank',


rerank is not a supported LobeHub AiModelType, so this mapping currently makes rerank models fall back to chat in processModelCard. The full AiHubMix endpoint does return real rerank models such as cohere-rerank-v4.0-* and qwen3-reranker-*, so after this PR those services can show up in the chat model list and then fail when selected because they are routed through chat completions.

Please either filter unsupported AiHubMix types before passing them to processMultiProviderModelList, or add proper rerank type/runtime support first. A regression test with types: "rerank" should assert that it is not returned as a chat model.

…llback - Remove rerank/reranking from TYPE_MAP; they have no LobeHub AiModelType equivalent and would silently fall back to 'chat' in processModelCard - Add UNSUPPORTED_AIHUBMIX_TYPES set and filter before mapAiHubMixModel() - Add regression test asserting rerank/reranking models are excluded and llm models still pass through

lobehubbot · 2026-05-11T08:25:16Z

❤️ Great PR @Bianzinan ❤️

The growth of project is inseparable from user feedback and contribution, thanks for your contribution! If you are interesting with the lobehub developer community, please join our discord and then dm @arvinxx or @canisminor1990. They will invite you to our private developer channel. We are talking about the lobe-chat development or sharing ai newsletter around the world.

…lobehub#14511) * fix(aihubmix): use full models endpoint to return complete model list The /v1/models endpoint at api.aihubmix.com returns only per-user-group models (~256). The new endpoint at aihubmix.com/api/v1/models returns the complete catalog (800+). Fetch from the full endpoint directly. * fix(aihubmix): normalize model_id to id from full models endpoint The https://aihubmix.com/api/v1/models endpoint uses `model_id` instead of `id`. Map it to `id` before passing to processMultiProviderModelList to prevent toLowerCase() errors and empty model list. * fix(aihubmix): add apiKey guard, AbortController timeout, and better error messages - Extract apiKey with runtime guard to fail fast when key is missing - Add AbortController with 10s timeout to prevent indefinite hanging - Include response body in error message for easier debugging - Add APP-Code header comment pointing to docs - Expand tests: mock global fetch, cover missing key / HTTP error / network error / AbortError cases * fix(aihubmix): add field mapping adapter and fix timeout scope Address review feedback from lobehub#14511: - Update AiHubMixModelCard interface to reflect the new endpoint schema with full JSDoc (model_id, desc, types, features, input_modalities, context_length, max_output, pricing.cache_read/cache_write) - Add mapAiHubMixModel() to adapt API response fields to LobeHub model card fields before passing to processMultiProviderModelList: desc -> description model_name -> displayName context_length -> contextWindowTokens max_output -> maxOutput types -> type (llm/t2t->chat, image_generation/t2i->image, video/t2v->video, tts, stt, embedding, rerank/reranking->rerank) pricing.cache_read -> pricing.cachedInput pricing.cache_write -> pricing.writeCacheInput features(tools/function_calling) -> functionCall features(thinking) -> reasoning features(web) -> search input_modalities(image) -> vision - Fix timeout scope: move clearTimeout into the finally block so the AbortController stays active during response.json() body read, not just during the initial fetch() call - Update baseURL from https://api.aihubmix.com to https://aihubmix.com to match official integration docs (https://docs.aihubmix.com/cn/api/Aihubmix-Integration) - Strengthen normalize test: assert list.some(m => m.id === 'some-model') instead of just Array.isArray to detect normalization failures - Add field-mapping test using vi.spyOn on processMultiProviderModelList to assert that all adapted fields are passed correctly * fix(aihubmix): filter out unsupported rerank types to prevent chat fallback - Remove rerank/reranking from TYPE_MAP; they have no LobeHub AiModelType equivalent and would silently fall back to 'chat' in processModelCard - Add UNSUPPORTED_AIHUBMIX_TYPES set and filter before mapAiHubMixModel() - Add regression test asserting rerank/reranking models are excluded and llm models still pass through --------- Co-authored-by: Bianzinan <bianzinan@users.noreply.github.com>

…#14511) * fix(aihubmix): use full models endpoint to return complete model list The /v1/models endpoint at api.aihubmix.com returns only per-user-group models (~256). The new endpoint at aihubmix.com/api/v1/models returns the complete catalog (800+). Fetch from the full endpoint directly. * fix(aihubmix): normalize model_id to id from full models endpoint The https://aihubmix.com/api/v1/models endpoint uses `model_id` instead of `id`. Map it to `id` before passing to processMultiProviderModelList to prevent toLowerCase() errors and empty model list. * fix(aihubmix): add apiKey guard, AbortController timeout, and better error messages - Extract apiKey with runtime guard to fail fast when key is missing - Add AbortController with 10s timeout to prevent indefinite hanging - Include response body in error message for easier debugging - Add APP-Code header comment pointing to docs - Expand tests: mock global fetch, cover missing key / HTTP error / network error / AbortError cases * fix(aihubmix): add field mapping adapter and fix timeout scope Address review feedback from #14511: - Update AiHubMixModelCard interface to reflect the new endpoint schema with full JSDoc (model_id, desc, types, features, input_modalities, context_length, max_output, pricing.cache_read/cache_write) - Add mapAiHubMixModel() to adapt API response fields to LobeHub model card fields before passing to processMultiProviderModelList: desc -> description model_name -> displayName context_length -> contextWindowTokens max_output -> maxOutput types -> type (llm/t2t->chat, image_generation/t2i->image, video/t2v->video, tts, stt, embedding, rerank/reranking->rerank) pricing.cache_read -> pricing.cachedInput pricing.cache_write -> pricing.writeCacheInput features(tools/function_calling) -> functionCall features(thinking) -> reasoning features(web) -> search input_modalities(image) -> vision - Fix timeout scope: move clearTimeout into the finally block so the AbortController stays active during response.json() body read, not just during the initial fetch() call - Update baseURL from https://api.aihubmix.com to https://aihubmix.com to match official integration docs (https://docs.aihubmix.com/cn/api/Aihubmix-Integration) - Strengthen normalize test: assert list.some(m => m.id === 'some-model') instead of just Array.isArray to detect normalization failures - Add field-mapping test using vi.spyOn on processMultiProviderModelList to assert that all adapted fields are passed correctly * fix(aihubmix): filter out unsupported rerank types to prevent chat fallback - Remove rerank/reranking from TYPE_MAP; they have no LobeHub AiModelType equivalent and would silently fall back to 'chat' in processModelCard - Add UNSUPPORTED_AIHUBMIX_TYPES set and filter before mapAiHubMixModel() - Add regression test asserting rerank/reranking models are excluded and llm models still pass through --------- Co-authored-by: Bianzinan <bianzinan@users.noreply.github.com>

…lobehub#14511) * fix(aihubmix): use full models endpoint to return complete model list The /v1/models endpoint at api.aihubmix.com returns only per-user-group models (~256). The new endpoint at aihubmix.com/api/v1/models returns the complete catalog (800+). Fetch from the full endpoint directly. * fix(aihubmix): normalize model_id to id from full models endpoint The https://aihubmix.com/api/v1/models endpoint uses `model_id` instead of `id`. Map it to `id` before passing to processMultiProviderModelList to prevent toLowerCase() errors and empty model list. * fix(aihubmix): add apiKey guard, AbortController timeout, and better error messages - Extract apiKey with runtime guard to fail fast when key is missing - Add AbortController with 10s timeout to prevent indefinite hanging - Include response body in error message for easier debugging - Add APP-Code header comment pointing to docs - Expand tests: mock global fetch, cover missing key / HTTP error / network error / AbortError cases * fix(aihubmix): add field mapping adapter and fix timeout scope Address review feedback from lobehub#14511: - Update AiHubMixModelCard interface to reflect the new endpoint schema with full JSDoc (model_id, desc, types, features, input_modalities, context_length, max_output, pricing.cache_read/cache_write) - Add mapAiHubMixModel() to adapt API response fields to LobeHub model card fields before passing to processMultiProviderModelList: desc -> description model_name -> displayName context_length -> contextWindowTokens max_output -> maxOutput types -> type (llm/t2t->chat, image_generation/t2i->image, video/t2v->video, tts, stt, embedding, rerank/reranking->rerank) pricing.cache_read -> pricing.cachedInput pricing.cache_write -> pricing.writeCacheInput features(tools/function_calling) -> functionCall features(thinking) -> reasoning features(web) -> search input_modalities(image) -> vision - Fix timeout scope: move clearTimeout into the finally block so the AbortController stays active during response.json() body read, not just during the initial fetch() call - Update baseURL from https://api.aihubmix.com to https://aihubmix.com to match official integration docs (https://docs.aihubmix.com/cn/api/Aihubmix-Integration) - Strengthen normalize test: assert list.some(m => m.id === 'some-model') instead of just Array.isArray to detect normalization failures - Add field-mapping test using vi.spyOn on processMultiProviderModelList to assert that all adapted fields are passed correctly * fix(aihubmix): filter out unsupported rerank types to prevent chat fallback - Remove rerank/reranking from TYPE_MAP; they have no LobeHub AiModelType equivalent and would silently fall back to 'chat' in processModelCard - Add UNSUPPORTED_AIHUBMIX_TYPES set and filter before mapAiHubMixModel() - Add regression test asserting rerank/reranking models are excluded and llm models still pass through --------- Co-authored-by: Bianzinan <bianzinan@users.noreply.github.com>

@hezhijie0327

# 🚀 LobeHub Release (20260518) **Release Date:** May 18, 2026 **Since v2.1.58:** 208 merged PRs · 209 commits · 16 contributors > v2.2.0 introduces the **Chief Agent Operator** — an agent that runs itself end-to-end. It self-iterates against its own output, assembles sub-agent teams on demand through the heterogeneous runtime, and drives a unified task system that knows when to pause for a human. Self-review, AssistantGroup, and tasks/scheduling all converge into one operator surface. --- ## ✨ Highlights ### 🎩 Chief Agent Operator - **Self-iteration exits Lab** — Agent Signal's self-review pipeline ships proposal actions straight into briefs and auto-executes the approved follow-ups, with prompts hardened against eval. The operator now critiques and re-runs its own work without a human in the loop. (#14769, #14583, #14647, #14882) - **Auto-formed agent teams** — Heterogeneous AssistantGroup gains Monitor-style signal callbacks, read-only SubAgent threads with breadcrumb headers, and a thread switcher. The operator dispatches sub-agents and you can step into any branch to see what the team is doing. (#14859, #14658, #14845, #14715) - **Task system as the operator's runway** — Claude Code surfaces task tools, AskUserQuestion freeform notes, and a dedicated `waitingForHuman` topic status; `lobe-task` exposes `setTaskSchedule`; the scheduler is hardened (maxExecutions cap, sub-10min heartbeat block, race-free SchedulerForm). Long-running operator runs no longer go silent and stop themselves when human input is needed. (#14870, #14639, #14713, #14865, #14853) ### 🚀 Cloud & runtime - **Cloud Claude Code V3** — Repo picker, GitHub token flow, and sandbox-aware context bring cloud-hosted Claude Code to feature parity with local; cloud sandbox completion now triggers the task lifecycle end-to-end. (#14568, #14822, #14681) - **Heterogeneous agent multi-replica safety** — Subagent threads, ingest refresh, and parallel-tool counts now survive replica swaps without losing parent_id or rolling back tool state. (#14897, #14631, #14806, #14838) - **Built-in tool lifecycle hooks** — `onBeforeCall` / `onAfterCall` land on the built-in tool runtime; sub-agent dispatch moves to `lobe-agent`; self-iteration aligns with the shared inspector pattern. (#14719, #14715, #14827) - **Knowledge base RAG unified** — Client and server share one `KnowledgeBaseSearchService`; KB files preserved on `NoSuchKey` instead of silently lost. (#14673, #14501) ### 💬 Workspace experience - **Home daily brief + recommendations** — The home screen opens with a linkable welcome, paired input hint, and a recommendations module sourced from the operator's hetero action library. (#14589, #14645, #14770) - **Chat mode + redesigned action bar** — The chat input gains a Chat/Agent mode toggle and a re-pitched action bar with icon-and-color action tag chips. (#14774, #14903, #14846) - **Documents tree, optimistic** — Document tree creates, deletes, and inline renames now apply optimistically; the agent-documents index hides web crawls and switches to a table layout. (#14714, #14292) - **Branded MCP inspectors** — Linear MCP tool calls render with the same branded inspector as the built-in Linear skill; CC MCP and built-in skills now share inspector code. (#14864, #14884) - **Bot identity gating** — Device tools are gated by sender identity, the activator bypass is closed, and Slack mpim plus Discord DM regressions are fixed. (#14634, #14664, #14733) --- ## 🏗️ Core Agent & Signal Pipeline ### Self-iteration & Agent Signal - Self-iteration graduates out of Lab, with service, tool, name, and concept structure unified across `agent-signal`, `prompts`, `database`, and `builtin-tool-self-iteration`. (#14699, #14769) - Self-review now proposes actions to briefs and auto-executes the approved set, with eval-verified prompt hardening. (#14583, #14657, #14647) - Self-iteration built-in tool aligns with the shared runtime + inspector patterns. (#14827) - Agent Signal prompts adapt their response language and avoid blocking agent execution. (#14890, #14775, #14882) - Receipt descriptions now carry an Agent Signal marker, and self-review hinted skill documents route correctly. (#14764, #14895) ### Heterogeneous agent runtime - Subagent threads render read-only with a breadcrumb header and thread switcher; SUBAGENT badge dropped, indentation tightened. (#14658, #14845, #14783) - Multi-replica safety: ingest refresh restores tools/model from DB to fix parent_id breaks; new-step assistants sync across replicas; subagent-tagged events no longer leak into the main gateway handler. (#14897, #14631, #14838) - Fetch-triggering events are deferred to keep parallel tool counts from rolling back. (#14806) - AskUserQuestion is wired for Claude Code, with auto-decline disabled and a freeform note input on the cloud side; `waitingForHuman` is a first-class topic status. (#14639, #14629, #14870) - AssistantGroup gains Monitor-style signal callbacks; project skills surface in the working sidebar and markdown preview. (#14859, #14896) - Cloud Claude Code V3 — repo picker, GitHub token, sandbox context; credentials alert and disabled input when not configured. (#14568, #14822) - Cloud sandbox completion now triggers the task lifecycle end-to-end. (#14681) ### Agent runtime & context engine - Built-in tool runtime gets `onBeforeCall` / `onAfterCall` lifecycle hooks. (#14719) - `CompletionLifecycle`, `HumanInterventionHandler`, and `stepPresentation` are extracted from the runtime monolith. (#14441) - Per-tool timeout is honored end-to-end for client tool dispatch. (#14817) - Compression budget accounts for `tool_calls`, reasoning content, and tool defs; `call_llm` forwards tools into the budget. (#14813, #14837) - Pre-flight context check now fails fast for OpenAI-compatible providers. (#14824) - Malformed `tool_call` names are recovered instead of finishing the step silently. (#14577) - Sub-agent dispatch moves from `lobe-gtd` to `lobe-agent`. (#14715) - Hidden built-in tools now appear in the system prompt @-mention list. (#14823) ### Agent tracing & operations - New `agent_operations` table and runtime persistence for every hetero-agent operation. (#14416, #14736) - `signOperationJwt` issues 4-hour signed operation tokens. (#14586) - S3 trace snapshots are zstd-compressed; DB `trace_s3_key` aligns with the `.json.zst` suffix; legacy `.json` fallback preserved on fetch. (#14807, #14860, #14826) --- ## 📱 Platform & Integrations ### Bot / Channels - Device tools are gated by sender identity. (#14634) - Activator bypass closed and device-access checks converged. (#14664) - Slack mpim supported; Discord DM regression fixed; Slack connect + slash commands repaired. (#14733, #14591) - Bot channels, bot watch, bot callback service, and system bot reliability fixes. (#14847, #14796, #14570, #14784, #14649) - Online Messager scaffolding. (#14755) ### Onboarding - Home daily brief with linkable welcome and paired input hint. (#14589) - Recommendations module sourced from the hetero agent action library. (#14645) - Chat onboarding passes request triggers via metadata and preserves the resume request. (#14770, #14798) - Discovery turn progress gated by phase, with a reminder on stalled discovery. (#14842, #14833) - FullNameStep back button rejoins the shared prefix; ModeSwitch hidden in production. (#14898, #14760) - Agent marketplace folds into the web onboarding tool. (#14578, #14672) - Onboarding interests stored as keys instead of free text; early-exit skips marketplace and drops CJK prompts. (#14624, #14598) ### Model providers - Gemini 3.1 Flash-Lite cards; Gemini schema sanitizer drops non-compliant `enum` / `required`; zero `cachedContentTokenCount` handled in usage conversion. (#14604, #14740, #14567) - DeepSeek-V4 model cards and pricing restored to official rates. (#14110, #14911) - ernie-5.1 and spark-x2-flash support; Grok 4.3 `reasoning_effort` support. (#14643, #14731, #14642) - SiliconCloud catalog synced with API; duplicates removed; reasoning params adjusted. (#14464) - Minimax derives `max_tokens` from context window to avoid `ExceededContextWindow`. (#14814) - aihubmix uses the full models endpoint for a complete list; stale empty-apiKey test dropped. (#14511, #14669) - Stream parse errors are enriched with provider + model context. (#14636) - Visual content parts are consumed in the server runtime; video image references move to a JSON object. (#14637, #14900) - Google function call magic `thoughtSignature` now attaches to every part, not just the last turn. (#14904) - Service model assignments settings added; model extend-param options removed. (#14712, #14607) ### Built-in tools & knowledge base - `lobe-task` exposes `setTaskSchedule`; task scheduler hardened (maxExecutions cap, sub-10min heartbeat blocked, SchedulerForm race fix, rapid automation-mode toggle stabilized). (#14713, #14865, #14853, #14801) - KnowledgeBaseSearchService shares RAG runtime across client and server. (#14673) - KB files preserved on `NoSuchKey` and orphan documents/tasks cleaned. (#14501) - Document tree gets optimistic create/delete + inline rename. (#14714) - agent-documents index hides web crawls and switches to a table layout. (#14292) - `lobe-clarify` and SKILL.md frontmatter parsing/edit validation are unified. (#14566) - AnalyzeVisualMedia inspector + Portal HTML preview refactor; HTML preview restored for AssistantGroup messages. (#14777, #14811) - Branded inspector shared between CC MCP and built-in Linear skill. (#14884, #14864) --- ## 🖥️ CLI & User Experience ### Chat & Conversation - Chat mode toggle and redesigned chat input action bar. (#14774) - Action tag chips switch to icon + colored label; ActionDropdown closes on sibling-open and focus-out; submenu uses native header/footer slots. (#14903, #14802, #14901) - Action bar padding equalized around the send button; skeleton shows in action bar while config loads. (#14846, #14656) - `useCmdEnterToSend` is respected in thread & task inputs; send button enables after pasting into thread/comment input. (#14850, #14816) - TopicChatDrawer state preserved during close animation. (#14803) - Only the last assistant block animates during markdown streaming. (#14906) - Right working panel no longer auto-collapses on chat mount; home agent config fetched so knowledge toggles reflect in UI. (#14883, #14834) ### Tasks - Task scheduler, hotkey, comment, and TodoList polish. (#14707) - Add Subtask button & card baseline aligned; activity card stop run; task agent manager polish. (#14848, #14559, #14569) - Task template skeleton CLS reduced; task page placeholder copy refreshed. (#14788, #14704) - Task agent model snapshotted into `task.config` at create time. (#14670) - User-feedback card, task card polish, and Run-now context menu in markdown. (#14727) - Inline skill auth in recommended task templates. (#14676) ### Navigation & Layout - Tab bar gains a Chrome-style divider between inactive tabs. (#14892) - SideBarDrawer & header layout polish; nav ActionIcon sizing unified; TodoList encapsulation improved. (#14762, #14692) - Desktop header icons, sidebar density, and task menus polished. (#14724) - Standardized header action icon sizes. (#14717) - Chat topic title length increased; copy session ID added to topic dropdown menu. (#14659, #14595) - Heterogeneous agent topic rows regain indentation. (#14783) ### Other polish - Usage token details shortened; tool execution time formatted as `Xmin Ys`. (#14849, #14641) - Tool arguments display gets word-wrap toggle; long tool-call params wrap instead of truncate. (#14706, #14640) - Editor stops showing per-line placeholder once content is present. (#14852) - Visible divider between queued messages; intervention confirmation bar polished. (#14593, #14587) - Credit top-up copy refreshed; auth captcha retry copy refreshed; brief recommendations layout polished. (#14821, #14561, #14871) --- ## 🔧 Tooling & Developer Experience - Dev-only feature flag override panel. (#14565) - `__DEV__` define replaces `process.env.NODE_ENV` in the SPA. (#14696) - Agent-settings drops Meta/Documents tabs and restores `inputTemplate`. (#14874) - `local-system` forwards all `grepContent` params and moves the executor to `/client`. (#14888) - `lobe-task` and `setTaskSchedule` exposed. (#14713) - Memory user-memory benchmark agent config and source-id extraction schemas. (#14779, #14778) - CLI man page drops stale cron entry; `clearMessages` hotkey removed. (#14709, #14906) - Skill docs simplified; cloud heteroContext gains sandbox TTL + public-repo fork push guide. (#14785, #14761) --- ## 🔒 Security & Reliability - **Security:** Sensitive comments and examples sanitized from the production JS bundle. (#14557) - **Security:** Inactive OIDC access rejected. (#14674) - **Security:** CASC `new Function()` template replaced with safe string builders. (#14751) - **Security:** Sign-in captcha flow removed in favor of safer flow. (#14573) - **Security:** Desktop local file previews restricted to safe roots. (#14789) - **Security:** Image binary capped at 3.75 MB so base64 payload stays under the Anthropic 5 MB limit. (#14711) - **Reliability:** Neon/Node pools get error listeners to prevent Lambda crashes. (#14606) - **Reliability:** `paradedb.match(...)` replaces hardcoded normalizer in memory search. (#14590) - **Reliability:** `PlaceholderVariablesProcessor` errors carry diagnostic context. (#14741) - **Reliability:** File storage upload checks are serialized; multiple account link bug fixed. (#14829, #14562) - **Reliability:** `ScrollShadow` replaced with `ScrollArea` to fix a React infinite render loop (error code 185). (#14689) - **Reliability:** Embedding token cap enforced — long memory queries are limited and truncated before search. (#14757) - **Reliability:** Embed binary blob guard + oversized output cap in `local-system.readFile`. (#14602) - **Reliability:** Windows npm CLI shims resolved before spawning agents. (#14772, #14720) - **Reliability:** Vite pinned to 8.0.12 to avoid the rolldown 1.0.1 preload regression; desktop runtime externals split from native deps. (#14804, #14776) - **Reliability:** Old lobehub cron job removed; WeChat URL rules dropped from web crawler. (#14630, #14633) --- ## 👥 Contributors Huge thanks to **16 contributors** who shipped **208 merged PRs** this cycle. @hezhijie0327 · @sxjeru · @hardy-one · @Bianzinan · @brone1323 · @YuSaZh · @Wxh16144 · @arvinxx · @Innei · @tjx666 · @neko · @lijian · @rdmclin2 · @sudongyuer · @AmAzing129 · @rivertwilight Plus @lobehubbot for maintenance translations. --- **Full Changelog**: v2.1.58...v2.2.0

fix(aihubmix): use full models endpoint to return complete model list

808fbf9

The /v1/models endpoint at api.aihubmix.com returns only per-user-group models (~256). The new endpoint at aihubmix.com/api/v1/models returns the complete catalog (800+). Fetch from the full endpoint directly.

dosubot Bot added the size:S This PR changes 10-29 lines, ignoring generated files. label May 8, 2026

sourcery-ai Bot reviewed May 8, 2026

View reviewed changes

dosubot Bot added the provider:aihubmix Issues related to AIHubMix provider label May 8, 2026

chatgpt-codex-connector Bot reviewed May 8, 2026

View reviewed changes

Bianzinan and others added 2 commits May 8, 2026 11:48

fix(aihubmix): normalize model_id to id from full models endpoint

9488166

The https://aihubmix.com/api/v1/models endpoint uses `model_id` instead of `id`. Map it to `id` before passing to processMultiProviderModelList to prevent toLowerCase() errors and empty model list.

dosubot Bot added size:M This PR changes 30-99 lines, ignoring generated files. and removed size:S This PR changes 10-29 lines, ignoring generated files. labels May 9, 2026

dosubot Bot added size:L This PR changes 100-499 lines, ignoring generated files. and removed size:M This PR changes 30-99 lines, ignoring generated files. labels May 10, 2026

tjx666 reviewed May 10, 2026

View reviewed changes

tjx666 merged commit f3a7859 into lobehub:canary May 11, 2026
2 of 3 checks passed

tjx666 mentioned this pull request May 11, 2026

🐛 fix: drop unreachable aihubmix empty-apiKey test #14669

Merged

2 tasks

arvinxx mentioned this pull request May 12, 2026

🚀 release: 20260512 #14722

Closed

arvinxx mentioned this pull request May 18, 2026

🚀 release: v2.2.0 #14915

Merged

lobehubbot mentioned this pull request May 18, 2026

ProviderBizError: { message: 'fetch failed' } #14930

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(aihubmix): use full models endpoint to return complete model list#14511

fix(aihubmix): use full models endpoint to return complete model list#14511
tjx666 merged 5 commits into
lobehub:canaryfrom
Bianzinan:fix/aihubmix-full-model-list

Bianzinan commented May 8, 2026 •

edited

Loading

Uh oh!

vercel Bot commented May 8, 2026

Uh oh!

sourcery-ai Bot left a comment

Uh oh!

lobehubbot commented May 8, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Uh oh!

chatgpt-codex-connector Bot May 8, 2026

Uh oh!

tjx666 commented May 10, 2026 •

edited by lobehubbot

Loading

Uh oh!

tjx666 May 10, 2026

Uh oh!

Uh oh!

lobehubbot commented May 11, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

		const modelList: AiHubMixModelCard[] = json.data \|\| [];
		return await processMultiProviderModelList(modelList, 'aihubmix');

Uh oh!

Conversation

Bianzinan commented May 8, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Problem

Solution

Testing

Uh oh!

vercel Bot commented May 8, 2026

Uh oh!

sourcery-ai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

lobehubbot commented May 8, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

chatgpt-codex-connector Bot May 8, 2026

Choose a reason for hiding this comment

Uh oh!

tjx666 commented May 10, 2026 • edited by lobehubbot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

tjx666 May 10, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

lobehubbot commented May 11, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Bianzinan commented May 8, 2026 •

edited

Loading

tjx666 commented May 10, 2026 •

edited by lobehubbot

Loading