Adds the missing 'novita' case to the OpenAI-compatible provider
block in the validate-model API route, fixing 400 errors when
users test their Novita API key in the UI.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add NOVITA_API_KEY and NOVITA_BASE_URL to env.example so users
can discover the configuration variables. Also add novita to
the AI_PROVIDER options list.
Add Novita AI as a new LLM provider with OpenAI-compatible API support.
Users can now select Novita from all entry points (CLI, config, UI).
- Add 'novita' to ProviderName type
- Add Novita AI entry to PROVIDER_INFO with default base URL
- Add Novita suggested models (kimi-k2.5, glm-5, minimax-m2.5)
- Add 'novita' to ALLOWED_CLIENT_PROVIDERS
- Add NOVITA_API_KEY environment variable mapping
- Add novita case to getAIModel() switch using OpenAI-compatible API
- Add novita to SINGLE_SYSTEM_PROVIDERS for proper message handling
Replace wildcard `Access-Control-Allow-Origin: *` with same-origin check,
preventing external websites from accessing MCP server APIs via cross-origin requests.
* Implement GLM model identification logic
Add checks for GLM text and visual model naming conventions.
* fix: simplify GLM vision detection and add tests
- Remove redundant includes("v-") check that could cause false positives
on model names containing "dev-", "csv-", etc.
- Remove unnecessary includes("v") pre-check
- Update comments with real GLM model names
- Add unit tests for GLM text and vision models
* feat: add vision detection for MiniMax, Moonshot, and fix Qwen
- Add MiniMax text model detection (M2.x series are text-only)
- Add Moonshot v1 text model detection (moonshot-v1-* are text-only)
- Add qwen3.5-flash to Qwen vision model exceptions
- Add unit tests for all new model checks
---------
Co-authored-by: dayuan.jiang <jdy.toh@gmail.com>
The npm audit check was failing due to vulnerabilities in transitive
dependencies (e.g. wrangler), blocking unrelated PRs.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add MiniMax-M2.7 and MiniMax-M2.7-highspeed to model list
- Set MiniMax-M2.7 as default model
- Keep all previous models as alternatives
- Update docs in EN/CN/JA
Co-authored-by: PR Bot <pr-bot@minimaxi.com>
- Replace newyear-referral URL with new Coding Plan referral URL across all files
- Update model name from K2-thinking to glm-4.7
- Add volcengine invite poster to Chinese README and about page
Use explicit from/to/filter file sets instead of top-level globs to
avoid a regression in electron-builder 26.8.x where dist-electron
files were not being included in the asar archive.
electron-builder 26.8.x no longer auto-includes package.json when a
custom files array is specified, causing the main entry file to not be
found in the asar archive.
* feat: add custom system message setting for AI personalization
Allow users to enter custom instructions via a textarea in Settings
that get appended to the AI's system prompt. Includes server-side
validation (type check + 5000 char limit), localStorage persistence,
and i18n support for all 4 locales.
* fix: add accessibility htmlFor/id pairing on custom system message textarea
* feat: Add support for Chinese AI providers (GLM, Qwen, Kimi, MiniMax, Qiniu)
- Add minimax, glm, qwen, qiniu, kimi to ProviderName type
- Add provider configurations to PROVIDER_INFO with default base URLs
- Add suggested models for MiniMax in SUGGESTED_MODELS
- Add minimax/glm/qwen/qiniu/kimi cases to getAIModel using OpenAI-compatible SDK
- Update ALLOWED_CLIENT_PROVIDERS and error messages
- Add environment variable examples to env.example
Fixes: MiniMax API compatibility issue (invalid chat setting 2013)
* fix: Add missing providers to PROVIDER_ENV_VARS type
* fix: Handle null case in PROVIDER_ENV_VARS for new providers
* fix: Add minimax/glm/qwen/kimi/qiniu support to validate-model API
- Add getDefaultBaseUrl helper function
- Add validation cases for new providers in validate-model route
* fix: Add new providers to buildProviderOptions switch case
* fix: Merge multiple system messages into one for minimax/glm/qwen/kimi/qiniu
MiniMax API doesn't support multiple system messages.
This fix combines them into a single message for Chinese providers.
* fix: Handle null provider in system message check
* debug: Add logging for allMessages count
* fix: Use effective provider (including env var fallback) for isSingleSystemProvider check
* fix: apply biome formatting (line-wrapping)
* docs: add Chinese AI providers documentation (MiniMax, GLM, Qwen, Kimi, Qiniu)
- Add i18n translations for new providers in all language dictionaries
- Add provider configuration documentation in en/cn/ja docs
* fix: 改进 PR #722 的代码审查反馈
1. 删除重复的 getDefaultBaseUrl 函数，改用 model-config.ts 的 PROVIDER_INFO
2. validate-model 路由改用 AI SDK 的 createOpenAI + generateText
3. 修复 resolveBaseURL 回退逻辑，传入 PROVIDER_INFO 的 defaultBaseUrl
4. 删除无用的 .bak 备份文件
Co-authored-by: Shinyi <shinyi@openclaw.ai>
* fix: 修正中国 AI provider 端点配置
- qiniu: api.qiniucdn.com → api.qnaigc.com
- qwen: dashscope.aliyun.com → dashscope.aliyuncs.com
- 更新 env.example 文档链接
Co-authored-by: Shinyi <shinyi@openclaw.ai>
* feat: MiniMax 使用 Anthropic 兼容 API
- MiniMax 改用 createAnthropic (而非 createOpenAI)
- 支持 api.minimax.io/anthropic 和 api.minimaxi.com/anthropic
- 合并多个 system 消息为单个 (MiniMax/GLM/Qwen/Kimi/Qiniu)
- 更新默认模型为 MiniMax-M2.5 系列
- 支持 MINIMAX_BASE_URL 环境变量配置
Co-authored-by: Shinyi <shinyi@openclaw.ai>
* docs: 更新 MiniMax 文档
- 添加 Anthropic 兼容 API 说明
- 更新默认模型为 MiniMax-M2.5
- 添加国际版/中国大陆版配置示例
- 更新 env.example 注释
Co-authored-by: Shinyi <shinyi@openclaw.ai>
* fix: 完善 MiniMax 双端点支持及问题修复
- 支持 MiniMax Anthropic 兼容端点和 OpenAI 兼容端点自动切换
- 修正默认端点为 api.minimaxi.com (中国大陆可用)
- 修复端点路径缺少 /v1 的问题
- 添加前端 MiniMax logo 映射
- 移除调试日志
- 修正 env.example 默认配置
* chore: clean backup artifacts and align biome formatting
* fix: resolve effectiveProvider bug, deduplicate MiniMax URL logic, fix docs
- Fix critical bug: effectiveProvider was empty during auto-detection,
causing multi-system-message to be sent to MiniMax (which rejects it).
Now uses resolved provider from getAIModel instead of re-deriving it.
- Extract normalizeMiniMaxBaseURL() shared helper to eliminate duplication
between ai-providers.ts and validate-model/route.ts
- Add guard for undefined MiniMax baseURL to prevent hitting api.anthropic.com
- Fix docs: mark China mainland URL as default (matches code behavior)
- Restructure minimax/glm/qwen/kimi/qiniu validation to use shared pattern
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: document MiniMax dual API formats in docs and UI
- Add hint below Base URL input when MiniMax is selected, explaining
Anthropic-compatible (/anthropic) vs OpenAI-compatible (/v1) endpoints
- Update all 3 ai-providers docs (en/cn/ja) to list all 4 endpoint options
(China/International × Anthropic/OpenAI)
- Add i18n translations for the hint in all 4 locales
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: deduplicate PROVIDER_LOGO_MAP, remove unnecessary optional chaining
- Extract PROVIDER_LOGO_MAP to lib/types/model-config.ts (was duplicated
in model-config-dialog.tsx and model-selector.tsx)
- Remove unnecessary ?. on PROVIDER_INFO.minimax (it's a full Record)
---------
Co-authored-by: msga-oc <msga-oc@gitea.misakiga.top>
Co-authored-by: Shinyi <shinyi@openclaw.ai>
Co-authored-by: dayuan.jiang <jdy.toh@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: Eliminate spurious biome schema version errors on "biome ci" command
Stronger fix for commit dd9d79d2d6
Apply the BKM at https://biomejs.dev/internals/versioning/
that recommends pinning a specific version of biome
(current version of package-lock.json uses 2.4.4,
which was previously installed with ^2.3.10)
Otherwise, if npm is allowed to upgrade at its discretion,
project will have to continually chase the latest schema version.
The specific error that is fixed when "biome ci" is invoked:
```
ℹ The configuration schema version does not match the CLI version (local installed version)
> 2 │ "$schema": "https://biomejs.dev/schemas/2.3.14/schema.json",
│ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
```
package-lock.json is also updated to reflect the package.json change.
Signed-off-by: Bryon Nevis <bryon.nevis@intel.com>
* fix: clean up unrelated package-lock.json changes
Revert unrelated peer/encoding metadata changes that were
artifacts of a different npm version, keeping only the
biome version pin change.
Signed-off-by: Dayuan Jiang <dayuan.jiang@gmail.com>
---------
Signed-off-by: Bryon Nevis <bryon.nevis@intel.com>
Signed-off-by: Dayuan Jiang <dayuan.jiang@gmail.com>
Co-authored-by: dayuan.jiang <jdy.toh@gmail.com>
* feat: Turn off certain features of quota popup for self-hosting
This commit introduces a new variable, NEXT_PUBLIC_SELFHOSTED,
that alters the behavior of the quota popup. Downstream
consumers of the application may have their own quota-checking
logic, and the front-end reacts to the 429 error by displaying
the quota popup. In the case of a self-hosted version of the app,
it is inappropriate to ask for sponsorship or provide a
hyperlink to the public version of the tool to apply for an
increased quota. An alternative string translation is provided
with an empty message for adopter customization.
To use this feature, compile with NEXT_PUBLIC_SELFHOSTED=true
and those parts of the quota popup will be omitted.
The downstream consumer is still expected to customize
the internationalized strings for the popup content
to be appropriate to their organization on their local forks.
Signed-off-by: Bryon Nevis <bryon.nevis@intel.com>
* refactor: improve readability and provide sensible selfhosted defaults
- Extract nested ternary expressions into quotaMessage and tipHtml variables
- Combine two separate !isSelfHosted conditional blocks into one
- Replace null tipSelfHosted with meaningful default strings across all locales
---------
Signed-off-by: Bryon Nevis <bryon.nevis@intel.com>
Co-authored-by: dayuan.jiang <jdy.toh@gmail.com>
The Lint & Unit Tests PR status check is failing
at the "Run lint" step over a half-dozen issues.
This is causing all PR's to fail the Lint & Unit tets check.
This fix resolves those issues.
Signed-off-by: Bryon Nevis <bryon.nevis@intel.com>
By default, the electron package tries to download binaries using
a direct HTTP connection. This fix adds an build-time varaible to
the Dockerfile to skip the download of the electron binary,
which is enabled by default.
Note that if binary download is still wanted for some reason,
and the download is happening behidn a proxy,
one must modify the Dockerfile to use ELECTRON_GET_USE_PROXY
and supply http_proxy, https_proxy, NO_PROXY build args.
Signed-off-by: Bryon Nevis <bryon.nevis@intel.com>
- Try legacy port (61337) first to preserve existing users' localStorage,
fall back to 13370 which is below the Windows Hyper-V ephemeral range (#705)
- Bind server and all URL references to 127.0.0.1 instead of localhost
to fix IPv4/IPv6 mismatch on Linux (#684)
- Add OS-assigned port fallback (port 0) so startup never throws
- Log error codes in port checks for easier debugging
- Update localhost guards in index.ts and window-manager.ts to also
match 127.0.0.1
Related: #705, #684
* Add Ollama Cloud support with Base URL and API Key configuration
* implemented feedback
* fix: use OLLAMA_BASE_URL env fallback in validate-model endpoint
* Remove dedicated Ollama configuration block
* security(ollama): prevent API key leak to client-controlled URLs
* added test
* fix: security hardening and Ollama Cloud default URL
- Add server OLLAMA_API_KEY fallback to validate-model endpoint with
SSRF guard mirroring ai-providers.ts
- Tighten top-level SSRF exemption: only exempt Ollama when no server
OLLAMA_API_KEY is configured
- Update Electron config to support OLLAMA_API_KEY env var
- Change default Ollama URL from localhost:11434 to ollama.com/api
(Ollama Cloud) for web UI users
- Add tests for server env combo, API-key-only, and SSRF guard scenarios
---------
Co-authored-by: dayuan.jiang <jdy.toh@gmail.com>
Add qwen3.5-plus to SiliconFlow and ModelScope suggested models.
Mark qwen3.5-plus as a vision-capable model in supportsImageInput check.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add Material Design Icons shape library (#685)
Add Google Material Design Icons as a new shape library using Google's
CDN. Includes top 300 most popular icons by usage, and updates system
prompts to guide the AI to call get_shape_library before using any icon
library.
* fix: align get_shape_library guidance for non-cloud icon libraries
* feat: add PNG/SVG export support to MCP server export_diagram tool
Previously export_diagram only supported .drawio XML files. This adds
PNG and SVG export by leveraging the existing browser sync mechanism:
the MCP tool sets an exportFormat flag on the session state, the browser
detects it via polling and triggers an iframe export, then POSTs the
result back as exportData which the tool reads and writes to disk.
* fix: address PR review feedback for export feature
- Validate exportData is a string in POST /api/state
- Update lastUpdated in setExportFormat to prevent session expiry
- Gate export postMessage on isReady to avoid lost messages
- Remove unused fmt variable
- Fix double extension when path has a different supported extension
* fix: resolve high severity npm audit vulnerabilities
Run npm audit fix to update @aws-sdk and @smithy transitive dependencies
that had high severity advisories, which was failing the CI security audit step.
* fix: address second round of PR review feedback
- Add 8s timeout for pendingMcpExport to prevent permanent blocking
- Move export trigger after version update in poll() to export latest diagram
- Return 404 when session not found for exportData POST
- Sync browser state before .drawio export to avoid stale XML
- Handle URL-encoded SVG data URIs in addition to base64
* fix: address third round of PR review feedback
- Sync browser state before PNG/SVG export (not just drawio)
- Add 10MB body size limit on POST /api/state
- Validate export response format matches request to prevent race conditions
* refactor: remove over-engineered defensive code from export feature
Strip unnecessary validation/guards added from Copilot review that
don't make sense for a localhost-only MCP server: body size limit,
type validation, 404 for missing session, lastUpdated refresh,
URL-encoded SVG handling. Also deduplicate requestSync call.
* refactor: keep original drawio export path unchanged
Don't restructure the existing drawio logic - just add png/svg
as a separate branch after it.
* refactor: remove redundant helper functions, inline state access
Remove setExportFormat/getExportData/clearExportData wrappers that
were each called once. Access state fields directly via getState().
* chore: bump mcp-server version to 0.1.16
* feat(ui): conditional model selector shadow logic (#678)
- Update ModelSelectorList to conditionally render shadow based on scroll state
- Update CommandList to forward ref for scroll detection
- Resolves#678
* Update components/ui/command.tsx
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* fix(ui): update listRef type to match CommandList forwarded ref
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* enhancement: Pin Configure Models button to bottom of model selector (#637)
Keep "Configure Models..." and info text fixed at bottom of dropdown when the model list scrolls. Wire button to open Model Config dialog.
* Address PR review: use ModelSelectorItem, z-10 footer, padding on wrapper
* fix: reduce spacing between Configure Models button and info text
---------
Co-authored-by: dayuan.jiang <jdy.toh@gmail.com>
Support multiple API keys per provider with random selection for load
balancing. When AI_MODELS_CONFIG has multiple apiKeyEnv values for
a provider, requests will randomly select one available key.
- Update schema to accept apiKeyEnv as string or string array
- Add random key selection in resolveApiKey()
- Update validation to check at least one key exists
- Add tests for array format support
* fix: enable image support for Kimi K2.5 model
Kimi K2.5 supports image input but was incorrectly blocked by the
supportsImageInput check that excluded all Kimi models without
"vision" in the name. Updated the condition to only exclude the
older K2 model while allowing K2.5.
* fix: improve Kimi K2.5 image support logic and add tests
- Only block kimi-k2 specifically, not all Kimi models
- Add unit test for kimi-k2.5 image support
