The ReadableStream cancel() callback is not reliably invoked on client
disconnect under Next.js, causing emitter listeners (line/clear) and the
keepalive interval to accumulate, eventually triggering
MaxListenersExceededWarning.
Use request.signal as the primary disconnect trigger, with cancel() and
enqueue failures as fallbacks. Cleanup is idempotent via state.closed.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Removed the isCloud check from proxyFetch.js, simplifying the fetch patching logic.
- Updated MediaProviderDetailPage to include a new section for API key retrieval, improving user experience with clearer layout and additional notice text.
- Enhanced ConnectionRow to better handle email display names.
- Improved ProviderDetailPage to conditionally render provider notices and API key links.
- Refactored localDb, requestDetailsDb, and usageDb to remove unnecessary isCloud checks, streamlining database interactions.
- Updated OAuthModal to combine waiting and manual input steps for a more cohesive user flow.
- Added API key URLs to several providers in providers.js for better accessibility.
- Introduced Xiaomi MiMo as a new provider in providerModels.js and providers.js.
- Updated model alias mapping in model.js to include Xiaomi MiMo.
- Enhanced validation route to support Xiaomi MiMo API endpoints.
- Added Xiaomi MiMo to APIKEY_PROVIDERS with relevant details.
This update expands the range of supported providers, improving integration capabilities.
When a custom OpenAI-compatible provider uses a prefix that matches
a built-in alias (e.g. 'ark' -> 'volcengine-ark'), resolveProviderAlias()
converts it to the built-in provider ID, causing the provider-node
matching logic to be skipped. The request is then routed to the wrong
provider, resulting in a 404 model_not_found error.
Fix: always check provider-node prefix matching using the original
user input (parsed.providerAlias) before falling back to the resolved
alias, regardless of whether resolveProviderAlias() transformed it.
Co-authored-by: H1d3rOne <H1d3rOne@users.noreply.github.com>
Made-with: Cursor
- Refactored handleChatCore to include Caveman functionality, allowing for terse-style system prompts to reduce output token usage.
- Updated APIPageClient to manage Caveman settings, including enabling/disabling and selecting compression levels.
- Adjusted AntigravityExecutor to consolidate function declarations for compatibility with Gemini.
- Removed unnecessary console logs during translator initialization across multiple routes.
- Updated refreshCredentials methods in various executors (Antigravity, Base, Default, Github, Kiro) to accept optional proxyOptions for improved proxy handling.
- Modified token refresh logic to utilize proxy-aware fetch for better network management.
- Enhanced usage retrieval functions to support proxy options, ensuring seamless integration with proxy configurations.
- Updated ModelSelectModal and ProviderInfoCard components to incorporate kind filtering for improved user experience in model selection.
- Added validation for API keys in the provider validation route, including support for webSearch/webFetch providers.
- Introduced Cloudflare AI as a new provider with specific configurations in providerModels.js and providers.js.
- Updated DefaultExecutor to handle account ID resolution for Cloudflare AI connections.
- Enhanced AddApiKeyModal and EditConnectionModal to include account ID input for Cloudflare AI.
- Implemented validation for Cloudflare AI API key connections in testUtils.js and route.js.
- Updated UI components to reflect changes in provider management and connection handling.
- Added new image models for GPT 5.2, 5.3, and 5.4, including capabilities for text-to-image and editing.
- Updated embedding handling to include optional dimensions in requests.
- Introduced support for custom embedding providers, allowing dynamic fetching and validation of custom nodes.
- Improved image generation handling with Codex integration, including progress tracking and error handling.
- Enhanced UI components to support adding custom embeddings and displaying their status.
Add Volcengine Ark as a first-class API key provider with official model presets, endpoint configuration, API key validation, model discovery, connection testing, provider logo, and runtime alias mapping for `ark/*` model IDs.
Made-with: Cursor
Co-authored-by: kingsy <kingsylin@vip.qq.com>
- Introduced OpenCode Go provider with relevant configurations.
- Enhanced model management by allowing users to add and delete custom models.
- Updated UI components to support model selection for image types.
- Adjusted sidebar visibility to include image media kinds.
Add a shared resolveOllamaLocalHost() helper and wire it through the
executor, models/validate/test routes, so users can point ollama-local
at a remote Ollama instance instead of being locked to localhost:11434.
Also expose the host as an "Ollama Host URL" field in AddApiKeyModal
(empty = default localhost:11434), making the option reachable from the
dashboard without hand-editing db.json.
Co-authored-by: anuragg-saxenaa <anuragg.saxenaa@gmail.com>
Made-with: Cursor
- Add optional chaining check for navigator.clipboard
- Fallback to textarea + execCommand for SSR/non-HTTPS contexts
- Fixes TypeError when clipboard API is unavailable
Co-authored-by: Дмитрий Золотарь <d.zolotar@solarl.ru>
The sync icon has counter-clockwise arrows by design, making the spin
animation appear counter-clockwise even though CSS rotates clockwise.
Keep play_arrow as the icon in both loading and idle states so the
clockwise spin is visually unambiguous.
* fix: add multi-model support for Factory Droid CLI tool (closes#521)
* Add Claude Opus 4.7 to cc and cl provider lists
RESEARCH confirmed GA release April 16, 2026. Adding to:
- cc (Claude Code): claude-opus-4-7
- cl (Cline): anthropic/claude-opus-4.7
Refs: TICKET-20260416-ENG-O4.7-001
* fix: add Blackbox AI as a supported provider (closes#599)
- Integrated Google TTS languages from a separate module for better maintainability.
- Updated local device voice fetching to support both macOS and Windows, improving cross-platform compatibility.
- Enhanced dashboard route protection by adding dynamic settings for login requirements and tunnel access.
- Introduced UI elements for managing security settings related to API key requirements and dashboard access via tunnel.
- Added default TTS response example in the media provider page for better user guidance.
- Updated constants to reflect changes in TTS provider configurations.
This commit improves the overall user experience and security of the TTS features.
The fetchCompatibleModelIds() function had no timeout on its fetch() call,
causing /v1/models to hang indefinitely when an openai-compatible provider
was unreachable or slow to respond.
Additionally, upstream/cross-instance connections (provider IDs containing
a UUID suffix like openai-compatible-chat-XXXXXXXX) would trigger recursive
/models fetches between instances, creating infinite loops.
Fixes:
- Add AbortController with 5-second timeout to the fetch() call
- Skip dynamic model fetching for upstream/cross-instance connections
(detected by UUID suffix pattern in provider ID)
- Existing try/catch already handles abort errors gracefully
Co-authored-by: Agent Zero <agent@agent-zero.local>
- Allow selecting multiple models for 9router provider
- Merge models instead of overwriting (backwards-compatible)
- Support setting active model via click or Apply
- Click active model to clear default (model = '')
- Remove individual models via X button (persists to config)
- Add PATCH endpoint for clearing active model
- Update GET to return normalized model list
- Preserve subagent model configuration for explorer subagent
Made-with: Cursor
The shutdown API calls `process.exit(0)` on POST without any authentication or authorization checks. Any party that can reach this endpoint can terminate the server process, causing immediate service disruption.
Affected files: route.js
Signed-off-by: tuanaiseo <221258316+tuanaiseo@users.noreply.github.com>
Cursor's API now rejects requests with outdated client versions,
returning [400]: Update Required for Composer 2. Bump
x-cursor-client-version from 2.3.41 to 3.1.0 across all three
locations where it is set.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Sửa lỗi /v1/models chỉ biết lấy model từ danh sách tĩnh hoặc từ providerSpecificData.enabledModels. Với API Key Compatible Providers, endpoint test /api/providers/<id>/models vẫn lấy được model động từ upstream, nhưng /v1/models lại không fallback sang danh sách động đó. Ngoài ra alias trả ra cũng đang dùng providerId nội bộ thay vì prefix trong cấu hình.
Đã fix để OpenAI/Anthropic Compatible dùng đúng prefix làm alias public nếu chưa có enabledModels, /v1/models sẽ tự fetch động từ upstream /models
checkAndRefreshToken() updated providerSpecificData.copilotToken but
not the top-level creds.copilotToken. GithubExecutor.buildHeaders()
reads the top-level key, so every request after a proactive refresh
still sent the expired token, causing 401 "IDE token expired".
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
- Add /api/providers/kilo/free-models endpoint with 1hr cache
- Fetch and merge Kilo free models with hardcoded models for kilocode provider
- Display 'Free' badge on models fetched from Kilo API
- Fix Windows build: add cross-env, remove --webpack flag, add turbopack config
- Add outputFileTracingExcludes for Windows system directories
- Encode thoughtSignature into tool_call.id using _TSIG_ delimiter and base64url
- Decode _TSIG_ on request to restore thoughtSignature for Gemini multi-turn thinking
- Track pendingThoughtSignature across parts for deferred signature attachment
- Add LocalMutex (2-layer locking) to prevent ELOCKED on concurrent DB access
- Increase lockfile retries from 5 to 15 for multi-process robustness
- Restore db.json seed on first run to prevent ENOENT on lockfile.lock
- Use process.env.BASE_URL fallback in models test route
- Remove gemini-3-flash-lite-preview from provider models
Co-authored-by: kwanLeeFrmVi <quanle96@outlook.com>
Closes#450
Made-with: Cursor
- Add claudeHeaderCache.js to intercept and cache live Claude Code client headers
- Forward cached headers dynamically to api.anthropic.com via default.js
- Strip first-party identity headers (x-app, claude-code-* beta) for non-Anthropic upstreams
- Validate and sanitize tool call IDs to match Anthropic pattern (^[a-zA-Z0-9_-]+$)
- Skip thinking blocks when applying cache_control; fix max_tokens buffer (+1024)
- Strip cache_control from thinking blocks in openai-to-claude translator
- Comment out thoughtSignature in Gemini translator (kept for reference)
- Expand .gitignore to match all deploy*.sh variants
Co-authored-by: kwanLeeFrmVi <quanle96@outlook.com>
Closes#433
Made-with: Cursor
Adds OpenCode (https://github.com/opencode-ai/opencode) as a supported
provider. OpenCode is an open-source terminal AI coding assistant with
an OpenAI-compatible API running locally.
Changes:
- open-sse/config/providers.js: add opencode baseUrl (localhost:4096)
with openai format (fully compatible, no custom headers needed)
- open-sse/services/model.js: add 'oc' alias → opencode
- src/shared/constants/providers.js: add opencode to subscription
providers with alias 'oc', icon 'terminal', color #E87040
Usage after setup: use model prefix 'oc/<model>' to route through
a running OpenCode instance (e.g. oc/claude-sonnet-4-5).
Closes#378
On Linux, verify that Cursor IDE is actually installed before importing
tokens. Previously, leftover config files from a removed Cursor installation
would trigger a false positive, creating a phantom Cursor provider connection.
The check uses `which cursor` and falls back to checking for a .desktop file
in ~/.local/share/applications/
Fixes#313
Co-authored-by: Ibrahim Ryan <ryan@nuevanext.com>
Made-with: Cursor
Change Codex test from token-expiry-only check to probing the real
Codex API endpoint. Sends a minimal request body that triggers a fast
400 without consuming quota. A 400 confirms auth works; only 401/403
indicates a bad token.
Also adds generic acceptStatuses support to the OAuth test framework
so other providers can define non-200 success statuses.
When a provider has credentials but all are disabled, return 404 (NOT_FOUND)
instead of 400 (BAD_REQUEST). The combo handler already treats 404 as a
fallbackable error, so it will skip to the next model in the chain.
Previously, the 400 status caused the combo to stop with a hard error,
killing the client (e.g., Claude Code) even though other models in the
combo chain were available.
Also changed log level from error to warn since disabled credentials
are an expected configuration state, not an error.
Fixes#334
Add ability to configure round-robin strategy for individual combos,
similar to per-provider strategy overrides.
Changes:
- Add comboStrategies setting to store per-combo strategy overrides
- Add Round Robin toggle to each combo card in combos page
- Update chat handler to check combo-specific strategy before global
- Combo-specific strategy takes precedence over global comboStrategy
When enabled, each request to that combo will cycle through providers
instead of always starting with the first one.
Made-with: Cursor
- Add comboRotationState Map to track rotation per combo
- Add getRotatedModels() to rotate model order based on strategy
- Pass comboName and comboStrategy to handleComboChat()
- Add comboStrategy setting (default: fallback)
- Add UI toggle for Combo Round Robin in profile settings
When enabled, each request to a combo starts with a different provider
instead of always starting with the first one, distributing load evenly.
Co-authored-by: Antigravity Agent <antigravity@example.com>
Add a simple chat UI to the dashboard for quickly testing AI models from
connected providers. Features include:
- Model picker from all connected providers
- Streaming chat responses
- Image attachment support
- Session history with localStorage persistence
- Responsive design with dark theme
Note: Removed build.sh from original PR as it contained syntax errors and
was unrelated to the chat UI feature.
Co-authored-by: Nguyễn Trung Hiếu <140531897+bonelag@users.noreply.github.com>
Made-with: Cursor
* fix(usage): track lifetime request total beyond history cap
* fix(ui): restore provider assets and model availability endpoint
* fix(cursor): remove sql.js dependency from auto-import route
- Replaced message state with modalError in both components for better error management.
- Removed unused message display logic and adjusted action handling to improve clarity.
- Enhanced error handling in doAction and doDnsAction functions to ignore errors gracefully.
- Updated API call responses to streamline user feedback on actions.
Add MiniMax-M2.7 to provider models and pricing config alongside
existing M2.5. M2.7 is the latest reasoning model with 204K context.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
- Remove hard exit when ROUTER_API_KEY is missing
- Conditionally attach Authorization header only if API_KEY is set
- Allow MITM auto-start without requiring an active API key
- Fallback to default key when no active key is found
Made-with: Cursor
- Add 30 new locale files (ar, bn, cs, da, de, el, es, fi, fr, he, hi, hu, id, it, ja, ko, nl, no, pl, pt-BR, pt-PT, ro, ru, sv, th, tl, tr, uk, ur, zh-TW)
- Update i18n config to register new languages
- Update LanguageSwitcher component to support expanded language list
- Update localDb and pricing constants for i18n compatibility
Made-with: Cursor
* feat: add modelId fallback for provider validation
- If /models endpoint unavailable, validate via /chat/completions
- Add optional Model ID input in EditCompatibleNodeModal
- Improves compatibility with providers lacking /models endpoint
* feat: improve provider validation with modelId fallback
- Add Model ID input for chat/completions fallback validation
- Reorder UI: API Key → Model ID → Check button + Badge
- Display detailed BE error messages in FE
- Add status-specific error handling (401/403/400/404/5xx)
- Add unit tests for error message helpers
- Add vitest devDependency
Co-authored-by: Quan <quanle96@outlook.com>
PR: https://github.com/decolua/9router/pull/298
Thanks to @kwanLeeFrmVi for the original implementation. Here is a summary
of changes made during review integration:
- Replaced google-auth-library with jose (already a project dependency)
for SA JSON -> OAuth2 Bearer token minting (RS256 JWT assertion flow)
- Moved auth logic (parseSaJson, refreshVertexToken, token cache) from
executor into open-sse/services/tokenRefresh.js to match project pattern
- Fixed executor to use proxyAwareFetch instead of raw fetch (proxy support)
- Simplified buildUrl: use global aiplatform.googleapis.com endpoint for
both vertex (Gemini) and vertex-partner; removed region/modelFamily fields
- Added auto-detection of GCP project_id from raw API key via probe request
(vertex-partner only, cached per key)
- Added vertex/vertex-partner cases to /api/providers/validate/route.js
- Updated model lists based on live testing:
- vertex: gemini-3.1-pro-preview, gemini-3.1-flash-lite-preview,
gemini-3-flash-preview, gemini-2.5-flash (removed gemini-2.5-pro: 404)
- vertex-partner: deepseek-v3.2, qwen3-next-80b (instruct+thinking),
glm-5 (removed Mistral/Llama: not enabled in test project)
- gemini provider: added gemini-3.1-pro-preview, gemini-3.1-flash-lite-preview
- Removed bun.lock (project uses npm/package-lock.json)
- Removed region and modelFamily UI fields (global endpoint, auto-detect)
- Kiro token auto-refresh on AccessDeniedException (from commit 2)
Made-with: Cursor
- Added new provider models: DeepSeek 3.1, DeepSeek 3.2, and Qwen3 Coder Next.
- Implemented UI changes to support round-robin strategy with sticky limits in the provider detail page.
- Improved logging to display connection names instead of IDs for better clarity.
- Centralize proxy management with reusable proxy pools
- Per-connection proxy binding with legacy fallback
- Add strictProxy option: fail hard instead of silently falling back to direct
- Resolve alicode-intl conflict: keep alicode-intl support + proxy support
Made-with: Cursor
- Introduce BATCH_SIZE configuration for parallel language translation
- Update translation logic to process languages in batches with a delay to avoid rate limits
- Enhance logging to display current batch being processed
Also, add a new TimeAgo component for auto-updating time display in UsageStats.
- Implement runtime i18n using MutationObserver for automatic DOM translation
- Add language switcher dropdown in dashboard header (EN/VI/ZH)
- Support 3 languages: English (default), Tiếng Việt, 简体中文
- Add translation files: vi.json (197 entries), zh-CN.json (513 entries, cleaned)
- Translate dashboard UI: sidebar menu, header, settings, MITM page
- Use cookie-based locale persistence with /api/locale endpoint
- Zero component changes required - translations applied at runtime
- Fix Header flicker on route change with key={pathname}
Co-authored-by: eachann <each1024@qq.com>
Based on PR #247 from decolua/9router with runtime approach
Made-with: Cursor
- Add buildQwenBaseUrl function to construct URLs for Qwen resources.
- Update buildProviderUrl to support Qwen model requests.
- Enhance token refresh logic to include provider-specific data for Qwen.
- Refactor CLI Tools page to exclude MITM tools and streamline model retrieval.
- Introduce new components for MITM server management.
- Update API routes to handle Qwen-specific resource URLs and improve error handling.
Dashboard routes were accessible without authentication because
dashboardGuard.js was not connected to Next.js middleware pipeline.
Created src/proxy.js to export the auth guard using Next.js 16
proxy convention. Now /dashboard routes properly redirect to
/login when auth_token cookie is missing or invalid.
* fix(translator): filter nameless hosted tools when converting Responses API to Chat format
Codex CLI sends "hosted" tools (e.g. `request_user_input`) via the OpenAI
Responses API. These tools have no explicit `name` field. The previous
`body.tools.map()` pass propagated `name: undefined` into the resulting
Chat Completions function declarations, which then became anonymous
`functionDeclarations` after the OpenAI→Gemini translation step.
Gemini strictly requires every function declaration to have a valid name
and rejects the entire request with:
GenerateContentRequest.tools[0].function_declarations[4].name:
Invalid function name. Must start with a letter or an underscore.
Fix: filter out any Responses API tool that lacks a non-empty `name`
string before converting to `{ type: "function", function: { name, ... } }`.
Named function tools are unaffected; only unnamed hosted tools are skipped.
Fixes: Gemini 400 error when Codex CLI is routed through 9router.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat(gemini): convert OpenAI SSE to Gemini SSE format in /v1beta/models route
The @google/genai SDK always uses :streamGenerateContent?alt=sse for chat
and expects Gemini SSE chunk format. The upstream handleChat returns OpenAI
SSE format, causing the SDK to crash on the [DONE] sentinel.
Changes:
- Add transformOpenAISSEToGeminiSSE() using TransformStream that converts
each OpenAI SSE chunk (choices[0].delta) to Gemini SSE format
(candidates[0].content.parts) on the fly
- Drop the OpenAI [DONE] sentinel (Gemini SSE ends by stream close)
- Map finish_reason -> finishReason, attach usageMetadata on final chunk
- Support reasoning_content -> thought: true parts for thinking models
- Refactor finishReasonMap to shared FINISH_REASON_MAP constant
- Fix streaming dispatch: stream=true now calls transformOpenAISSEToGeminiSSE
instead of passing OpenAI SSE through raw
Fixes: SyntaxError: "[DONE]" is not valid JSON in Gemini CLI
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
- Add a warning message for Windows users in AntigravityToolCard to run the terminal as Administrator for MITM functionality.
- Refactor model testing logic in ProviderDetailPage to improve state management and user experience.
- Introduce new version notification in Sidebar for available updates.
- Add a 10-second timeout for fetch requests in getAntigravityUsage and getAntigravitySubscriptionInfo functions.
- Include error logging for fetch failures in both functions.
- Update headers to include "x-request-source" for MITM bypass.
- Enhance proxyFetch with DNS resolution and MITM bypass capabilities.
- Ensure proxyFetch is loaded in the API route for proper fetch patching.
- Added eye icon button to show/hide individual API keys
- Keys hidden by default on page load for security
- Copy button always copies full key regardless of visibility state
- Implemented per-key visibility state with React useState
- Added maskKey helper to display first 8 characters + "..."
- Clean up visibility state when keys are deleted
Improves security and UX when managing API keys in the dashboard.
- Patch Node fetch via undici ProxyAgent when HTTP_PROXY/HTTPS_PROXY/ALL_PROXY is set
- Ensure proxy patch is loaded for both chat pipeline and OAuth token exchange
- Add Dashboard Settings → Network to edit outbound proxy and apply immediately
- Persist outbound proxy settings in local db and initialize on server startup
- Move proxy helpers to src/lib/network/ for better structure
- Rename src/proxy.js → src/dashboardGuard.js to avoid naming confusion
- Re-apply proxy env after DB import
- Fix: close old dispatcher on proxy URL change to prevent connection pool leak
- Fix: idempotency guard to avoid patching globalThis.fetch multiple times
Made-with: Cursor
- Add alicode provider with OpenAI-compatible API endpoint
- Support 8 models via Aliyun Bailian Coding Plan
- Add API key validation and connection testing
- Use getDefaultModel() instead of hardcoded model names
Co-authored-by: decolua <decoluadt@example.com>
Made-with: Cursor
Rename alicloud to alicode to clearly indicate Aliyun's Coding Plan service.
- Provider ID: alicode (short for Aliyun Coding)
- Model format: alicode/qwen3.5-plus
- Simplified mapping - no more bidirectional aliases
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add support for Alibaba Cloud Bailian Coding Plan, a coding-focused AI service
that provides fixed monthly pricing for multiple models.
Changes:
- Add alicloud provider with OpenAI-compatible API endpoint
- Support 8 models: qwen3.5-plus, kimi-k2.5, glm-5, MiniMax-M2.5,
qwen3-max, qwen3-coder-next, qwen3-coder-plus, glm-4.7
- Use "ali" as provider alias (ali/model format)
- Add API key validation and connection testing
- Add frontend provider definition with "ALi" text icon
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Added functionality to fetch and set statuses for various CLI tools (Claude, Codex, Droid, OpenClaw, Antigravity) on component mount.
- Enhanced error handling and logging in the OAuth provider test utilities and DNS management functions.
- Improved the MITM server to handle multiple target hosts and provide clearer error messages regarding port usage.
- Introduced a new ProviderDetailPage component to handle provider-specific functionalities.
- Implemented state management for connections, loading states, and model selections.
- Added API calls for fetching provider connections and model aliases.
- Included modals for OAuth and API key management.
- Enhanced user experience with model selection and saving capabilities.
Cherry-picked from decolua/9router PR #183.
Note: open-sse changes included but need further review due to extensive modifications.
Co-authored-by: Cursor <cursoragent@cursor.com>
- Add glm-cn to APIKEY_PROVIDERS in src/shared/constants/providers.js
- Align with existing glm-cn model definitions in providerModels.js
- Users can now see and select GLM (China) option in Web UI
- Follows same pattern as minimax-cn (red color for China region)
* feat: implement Project ID service to fetch and cache real Project IDs from Google Cloud Code API
* fix: implement caching and cleanup for Project ID retrieval
* feat: add project ID invalidation and refresh logic after token updates
* refactor: remove unnecessary format changes
* feat: add on-demand project ID retrieval for antigravity requests
The macOS auto-import was failing with "Cursor database not found" even
when Cursor was installed and logged in. This was caused by a single
hardcoded path and no fallback when the DB file existed but couldn't be
opened (e.g. WAL lock, Insiders variant).
Changes (macOS only — linux/win32 paths are unchanged):
- Probe both standard and Insiders DB locations on macOS
- Return a descriptive error when the DB file exists but can't be opened
- Try multiple known key names for token and machine ID
- Add fuzzy key fallback for future Cursor schema changes
- Normalize JSON-encoded string values from the DB
Adds unit tests covering all new and existing behavior.
Co-authored-by: Cursor <cursoragent@cursor.com>
- Add isActive field to API key schema with migration
- Implement PUT /api/keys/[id] endpoint for toggle
- Update validation to reject paused keys (403)
- Add UI toggle controls with confirmation
- Ensure cloud sync preserves pause state
- Tracks endpoints like /v1/chat/completions, /v1/messages, /v1/responses
- New sortable/groupable table in usage dashboard with expandable groups
- Enhanced usage database aggregation by endpoint + model + provider
- Added endpoint tracking to all saveRequestUsage/saveRequestDetail calls
- Maintains backward compatibility with existing data structure
- Add URL search params to track active tab
- Persist tab selection on page refresh
- Enable direct linking to specific tabs (overview, logs, limits, details)
- Implement smooth navigation without page scroll
- Added detailed request logging and latency tracking in handleChatCore.
- Improved error handling for SSE to JSON conversion and JSON parsing in streamToJsonConverter.
- Introduced a safe JSON parsing utility to handle potential parsing errors gracefully in requestDetailsDb.
Co-authored-by: zx <me@char.moe>
Providers like Antigravity maintain separate quota buckets per model family
(e.g. Claude vs Gemini). A 429 on claude-opus previously locked the entire
account, preventing gemini-pro requests even though its quota was full.
This adds in-memory per-model locking so that only the specific model is
skipped during account selection while other models remain accessible.
Changes:
- Add model-aware lock tracking in auth.js (Map<connectionId:model, expiry>)
- Pass model context from chat handler to auth service
- Multi-bucket behavior gated to known providers (MULTI_BUCKET_PROVIDERS set)
- No database schema changes — locks are in-memory and clear on restart
Closes#110
- Added handling for HTTP_STATUS.NOT_ACCEPTABLE in error types and messages.
- Enhanced the `prepareClaudeRequest` function to filter built-in tools for non-Anthropic providers and clean up empty tool arrays.
- Updated the `openaiToClaudeRequest` function to handle built-in tools more effectively and ensure proper tool conversion.
- Improved the `claudeToOpenAIResponse` function to skip processing for built-in server tool blocks.
- Refined error message handling in the `parseUpstreamError` function to ensure meaningful output.
- Adjusted command checks for tool installations across various settings routes to use `command -v` for better compatibility.
* feat: add AI request details feature with latency tracking
Add comprehensive request history and debugging capability to the Usage dashboard:
**Storage Layer** (usageDb.js):
- Add saveRequestDetail() for storing full request/response details
- Implement FIFO queue with 1000-record limit in request-details.json
- Auto-sanitize sensitive headers (authorization, api-key, cookie, token)
- Add getRequestDetails() with pagination and filtering support
- Add getRequestDetailById() for single record lookup
**Pipeline Integration** (chatCore.js):
- Track request start time and calculate total latency
- Record TTFT (Time To First Token) and total latency for all requests
- Capture full request details (messages, model, parameters)
- Save response content for non-streaming, mark streaming responses
- Handle error cases with detailed error information
- Async non-blocking saves to avoid impacting request performance
**API Layer** (/api/usage/request-details):
- GET endpoint with pagination (page, pageSize: 1-100)
- Filter by provider, model, connectionId, status, date range
- Returns { details: [...], pagination: {...} } format
**UI Components**:
- Drawer.js: Right slide-out panel with backdrop blur and ESC close
- Pagination.js: Full pagination with page size selector (10/20/50)
- RequestDetailsTab.js: Complete table view with filters and detail drawer
**Dashboard Integration**:
- Add "Details" tab to Usage page (4th tab after Overview/Logger/Limits)
- Table columns: Timestamp, Model, Provider, Input Tokens, Output Tokens, Latency (TTFT/Total), Action
- Provider filter dropdown (9 providers supported)
- Date range filters (start/end datetime)
- Click "Detail" button to view full request/response JSON in slide-out drawer
**Features**:
- Real-time latency monitoring (TTFT & Total)
- Complete request/response inspection for debugging
- Filterable and searchable request history
- Responsive design with mobile-friendly filters
- Data security with automatic header sanitization
- Performance: async saves don't block request pipeline
**Files Created/Modified**:
- src/lib/usageDb.js (modified)
- open-sse/handlers/chatCore.js (modified)
- src/app/api/usage/request-details/route.js (new)
- src/shared/components/Drawer.js (new)
- src/shared/components/Pagination.js (new)
- src/app/(dashboard)/dashboard/usage/components/RequestDetailsTab.js (new)
- src/app/(dashboard)/dashboard/usage/page.js (modified)
Closes: AI Observability Dashboard feature
* feat: enhance request details with full config and streaming content capture
Improve Request Details feature to capture comprehensive request parameters
and actual streaming response content:
**Request Configuration Enhancement** (chatCore.js):
- Add extractRequestConfig() helper function to capture all request parameters
- Include temperature controls: temperature, top_p, top_k
- Include token limits: max_tokens, max_completion_tokens
- Include thinking/reasoning modes: thinking, reasoning, enable_thinking
- Include OpenAI parameters: presence_penalty, frequency_penalty, seed, stop,
tools, tool_choice, response_format, n, logprobs, top_logprobs, logit_bias,
user, parallel_tool_calls, prediction, store, metadata
- Apply to all request types: non-streaming, streaming, and error cases
**Streaming Content Capture** (chatCore.js & stream.js):
- Add onStreamComplete callback mechanism to stream processors
- Accumulate content from all formats: OpenAI, Claude, Gemini
- Track content from delta.content, delta.reasoning_content, delta.text,
delta.thinking, and Gemini content.parts
- Save initial record with "[Streaming in progress...]" marker
- Update record with actual content when stream completes
- Include usage tokens when available from stream
**Files Modified**:
- open-sse/handlers/chatCore.js - extractRequestConfig() + streaming capture
- open-sse/utils/stream.js - onStreamComplete callback + content accumulation
**Benefits**:
- View complete request configuration in Request Details (thinking mode, etc.)
- See actual streaming response content instead of placeholder
- Better debugging and observability for AI requests
Refs: #request-details-enhancement
* feat: separate thinking/reasoning content from response content
Improve Request Details to display thinking process separately from final response:
**Backend Changes**:
- stream.js: Capture content and thinking separately in streaming mode
- Add accumulatedThinking variable alongside accumulatedContent
- Route delta.content to content, delta.reasoning_content to thinking
- Support OpenAI (reasoning_content), Claude (thinking), Gemini (part.thought)
- Update onStreamComplete callback to return { content, thinking } object
- chatCore.js: Update response structure to include thinking field
- Non-streaming: Extract thinking from reasoning_content field
- Streaming: Receive { content, thinking } from stream callback
- Error responses: Include thinking: null
- Initial streaming save: Include thinking: null
**Frontend Changes**:
- RequestDetailsTab.js: Display thinking and content in separate sections
- Add amber/yellow themed "Thinking Process" section with psychology icon
- Show "Final Response" label when thinking is present
- Use distinct visual styling for thinking (amber bg) vs content (gray bg)
- Only show thinking section when thinking content exists
**Benefits**:
- Users can clearly see model's reasoning process vs final answer
- Better debugging for models with thinking capabilities (Claude, o1, etc.)
- Visual distinction makes it easy to identify thinking vs response
Refs: #thinking-content-separation
* fix: map Claude thinking to reasoning_content field
Fix Claude thinking content to be properly captured as reasoning_content
instead of regular content, enabling separate display in Request Details:
**Changes**:
- claude-to-openai.js: Use reasoning_content field for thinking blocks
- thinking start: send { reasoning_content: "" } instead of { content: "```\n```" }
- thinking delta: map to reasoning_content instead of content
- thinking stop: send { reasoning_content: "" } instead of { content: "```\n```" }
**Why This Matters**:
- Previously Claude thinking was sent as `content` field, mixed with actual response
- Now thinking uses `reasoning_content` field, matching OpenAI's o1 format
- stream.js can now properly route thinking to accumulatedThinking variable
- Request Details UI will show Claude thinking in separate "Thinking Process" section
**Supported Thinking Formats**:
- OpenAI: delta.reasoning_content → thinking
- Claude: delta.thinking → reasoning_content (now fixed)
- Gemini: part.thought === true → thinking
Refs: #claude-thinking-fix
* feat(observability): capture and display full 4-layer request chain
Capture complete request/response chain in AI Request Details:
- Add providerRequest field (translated request sent to provider)
- Add providerResponse field (raw provider response, streaming indicator)
- Update chatCore.js at all 5 saveRequestDetail() call sites
- Reorganize UI into 4 collapsible sections with Material icons
- Preserve backward compatibility for old records
- Add distinct styling for streaming indicator
* fix(observability): resolve React duplicate key warning in request details table
- Use composite key (detail.id + index) to ensure unique keys
- Prevents React warnings when database contains duplicate IDs from old ID generation
* fix(observability): display actual content in streaming request details
Change providerResponse field for streaming requests from placeholder
"[Streaming - raw response not captured]" to actual final content.
This improves debugging experience by showing the real AI response
in the "Provider Response (Raw)" section instead of a confusing
placeholder message.
Files changed:
- open-sse/handlers/chatCore.js: Save contentObj.content to providerResponse
- src/app/.../RequestDetailsTab.js: Remove special handling for placeholder
* refactor(observability): migrate request details to SQLite for improved concurrency
- Replace LowDB JSON storage with better-sqlite3
- Enable WAL mode for true concurrent read/write support
- Add 5 indexes to accelerate queries (timestamp, provider, model, connection_id, status)
- Perform pagination at the database level to reduce memory footprint
- Maintain 1000 record limit with automatic cleanup of old data
- Ensure API compatibility via re-exports, requiring no caller changes
Performance improvements:
- Concurrent Writes: Lock-free WAL mode prevents data contention
- Query Efficiency: Index-based searches replace full dataset loading
- Data Integrity: Atomic operations prevent file corruption
* fix(observability): resolve pagination statistics display issues
- Fix issue where totalItems=0 showed 'Showing 1 to 0 of 0 results'
- Hide pagination controls when totalItems=0 or totalPages<=1
- Standardize API response fields: pagination.total -> pagination.totalItems
Before: Incorrect stats shown for empty data, and pager visible even for single-page results
After: Stats hidden for empty data, pager hidden when navigation is unnecessary
* feat(observability): display friendly provider names in request details
- Add /api/usage/providers endpoint to dynamically fetch provider list with names
- Replace hardcoded provider options with dynamic loading from database
- Display friendly provider names instead of IDs in both table and detail drawer
- Support custom provider nodes (e.g., OpenAI-compatible) with user-defined names
- Add provider name caching to optimize performance
* fix(observability): use INSERT OR REPLACE for request details to handle streaming updates
* fix(observability): resolve zero-token display issue by ensuring streaming usage capture and fixing key mismatch
* fix(observability): separate TTFT and total latency calculation for streaming requests
* feat(observability): implement SQLite write queue and JSON size limits
- Added in-memory buffer and batch writing for SQLite to prevent lock contention
- Implemented with configurable 1MB limit to prevent DB bloat
- Added dashboard UI for observability performance and data management settings
- Integrated graceful shutdown handlers to prevent data loss
* fix(observability): resolve ReferenceError by declaring dbInstance
- Added new observability settings in the dashboard for max records, batch size, flush interval, and max JSON size.
- Introduced `extractRequestConfig` function to capture full request configurations.
- Enhanced error handling by saving detailed request information on failures.
- Updated usage tracking to include new token metrics.
- Modified streaming functions to support detailed content and reasoning tracking.
- Added null checks for undefined/null values in database operations
- Improved error handling for corrupt JSON recovery
- Added schema migration support for missing keys
- Target: database stability and data integrity
