Qwen OAuth flow (portal.qwen.ai) stopped working reliably; drop the
executor, registry entry, OAuth provider/service, token refresh
profile, usage handler, and related test coverage and baselines.
- Enable vision + audioInput capacity-adapter pools by default for new
and existing users (mergeWithDefaults backward-compat)
- Fall back to oc/mimo-v2.5-free when an enabled pool has no models
configured, both in the backend resolver and the combos UI (auto
refill on removing the last model from a pool)
- Hide PDF/Video from the Vision Adapter UI (PDF never implemented,
Video lacks translator support) while keeping the settings shape
- Exclude combos from the model picker when opened from the Vision
Adapter section
- mimo-v2.5 registry entry now declares audioInput/videoInput
- Simplify combo strategy and Vision Adapter descriptions
Real Cursor IDE now uses AgentService at agent.api5.cursor.sh (HTTP/2-only)
while 9router still spoke the retired ChatService at api2.cursor.sh with
outdated headers, producing HTTP 429 "Update Required". Add an executeAgent
path that builds an agent.v1.RunRequest Connect RPC over a raw http2 stream
and fetches the account-specific usable model catalog via GetUsableModels.
Also implement MCP tool calling over AgentService: encode OpenAI tools as
AgentRunRequest.mcp_tools (McpToolDefinition with google.protobuf.Value
input_schema), decode McpArgs tool calls, and forward them to the client as
OpenAI tool_calls so the client runs the tool and resumes in the next turn.
Reply to request_context_args with a non-empty RequestContext, to server
heartbeats with client_heartbeat, and to KV blob get/set with empty results,
so action queries no longer stall the stream. Fold the client system prompt
into the user message (custom_system_prompt makes the server return an empty
turn). Bump clientVersion to 3.12.17 and add the x-cursor-client-commit
header so the gateway identifies as a current Cursor IDE release.
Register Khmer (km) locale, add complete 1,394-entry dashboard translation,
and show the Cambodia flag in the language selector. Place Khmer immediately
before Thai in the selector and keep the header locale in sync after switching.
Share one /api/models fetch via useModelCaps cache, mount ModelSelectModal
only when open, stop double fetchModelAliases on CLI tool cards, and resolve
provider icons through a session 404 cache with missing PNGs + loading=lazy.
Also include Claude Exa MCP toggle (claude-settings + ClaudeToolCard) that
was already in the working tree.
Co-authored-by: Cursor <cursoragent@cursor.com>
Add pxpipe as an experimental fifth Token Saver: Claude-format request
bodies above a configurable size threshold are rendered as dense PNGs
via the pxpipe-proxy library API (transformAnthropicMessages) before
dispatch, cutting estimated input tokens by ~35-60% on token-dense
contexts. Integration follows the Headroom pattern: applied to the final
body in chatCore just before dispatch, fail-open on any error/timeout.
Managed npm install into DATA_DIR/pxpipe, dynamic loader with per-version
cache-bust, JSONL event log with rotation, /api/pxpipe/* endpoints, Token
Saver card (marked experimental) + /dashboard/pxpipe page, and per-request
Activated/Skipped annotation in Request Details. Disabled by default.
Add round-robin/random proxy pool rotation for no-auth free providers
(e.g. OpenCode Free) to distribute load across all active pools and
avoid per-IP rate limits. Rotation strategy is selectable per provider
in NoAuthProxyCard and persisted to settings.providerStrategies.
- Switch dev default to Turbopack (5-14x faster compile); keep webpack as dev:webpack
- Tailwind v4 source() base so JIT scans identically under both bundlers
- Lazy-load @xyflow/react via next/dynamic to keep it out of the shared bundle
- optimizePackageImports for heavy barrel imports (xyflow, dnd-kit, material-symbols, marked)
- Replace blind setTimeout waits with TCP health-check (waitServerReady)
- Run checkForUpdate in parallel instead of blocking server spawn
- Background MITM/tunnel/cloudflared kills off the critical path
Co-authored-by: Cursor <cursoragent@cursor.com>
Normalize every provider to one cache-inclusive convention via
canonicalizeUsage() before persist, and price cached + cache_creation as
subsets of prompt_tokens in calculateCostFromTokens() to stop
double-counting. usageRepo now delegates cost math to a single source.
Surface Cached tokens/cost across dashboard (overview, tokens, cost,
details). Merge Claude message_start cache with message_delta output so
cache counts survive. Compatible LLM nodes now allow multiple API-key
connections (key pool).
Co-authored-by: Cursor <cursoragent@cursor.com>
Add Kimchi as a browser-token OAuth provider routed through its
OpenAI-compatible gateway. Discover live models for /v1/models and
provider models, normalize Claude-compatible requests, and wire up
provider connection tests.
Co-authored-by: Cursor <cursoragent@cursor.com>
Use full-page navigation after login/logout so the dashboard reloads
with the fresh auth cookie, and mark login/logout responses no-store.
Fixes#2100
Co-authored-by: Cursor <cursoragent@cursor.com>
Merge customModels from /api/models/custom into the isCustomProvider
branch so custom compatible providers display imported models instead
of the prefix/model-id placeholder. Mirrors the passthrough pattern;
filter by providerId since providerAlias stores the raw provider ID.
Co-authored-by: Cursor <cursoragent@cursor.com>
When logged in to Kiro IDE as an organization (AWS IAM Identity Center),
token import fails because IDC tokens require clientId/clientSecret for
refresh and use a different profileArn than social/builder-id accounts.
Changes:
- auto-import: read clientId/clientSecret from SSO cache client registration
file, read profileArn from Kiro IDE profile.json, normalize ARN region
- import: accept IDC credentials, use KiroService.refreshToken with them,
persist credentials for future automatic refreshes
- KiroAuthModal: pass IDC credentials from auto-detect through to import
Co-authored-by: Cursor <cursoragent@cursor.com>
- extract token saver into its own route /dashboard/token-saver
- slim down EndpointPageClient
- add token-saver nav to Header and Sidebar
Co-authored-by: Cursor <cursoragent@cursor.com>
Expose user-added imageToText custom models as vision-capable chat
models in the default LLM selector and /v1/models, map custom service
kinds to runtime capabilities, and keep typed filtering for
/v1/models/{kind}.
Co-authored-by: Cursor <cursoragent@cursor.com>
Adds long-lived API-key (ksk_) authentication for Kiro/AWS CodeWhisperer
and a direct claude:kiro / kiro:claude translation route that avoids the
lossy OpenAI two-hop pivot.
- translator: claude-to-kiro request + kiro-to-claude response translators,
registered on the exact source:target pair (direct route ahead of the
OpenAI pivot in index.js). claude-to-kiro uses shared schema constants
(ROLE/CLAUDE_BLOCK/DEFAULT_IMAGE_MIME) per app convention.
- auth: POST /api/oauth/kiro/api-key imports + validates a key via
ListAvailableProfiles, persists authMethod="api_key" (no refresh token).
- executor: send tokentype: API_KEY header and try *.amazonaws.com hosts
first for api-key creds; OAuth keeps kiro.dev first.
- fix: never inject the default placeholder profileArn for api-key auth
(CodeWhisperer 403s an ARN not owned by the key's account).
- ui: API Key method in the Kiro connect modal; surface api-key accounts
on the Quota Tracker and provider count.
- stream: env-overridable TTFT vs stall timeouts + Kiro keepalive frame.
- tests: claude-kiro-direct + kiro-profile-arn (11 tests).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Skip creating partial stats from SSE before the initial REST load
completes, keeping real-time merges limited to existing full stats.
Co-authored-by: Cursor <cursoragent@cursor.com>
- Add custom-server.js: inject unspoofable socket IP, strip client XFF
(wired into Docker CMD + CLI spawn + build-cli copy)
- loginLimiter: key on trusted x-9r-real-ip, TRUST_PROXY opt-in, global fallback
- Force password change on first remote login while default is in use
- Add /api/auth/reset-password (local-only) so CLI reset writes live SQLite
- CLI settings: reset via API instead of stale db.json
- Fix OAuth modals opening duplicate browser tabs on add-connection
- Add cli:pack / cli:publish scripts
Co-authored-by: Cursor <cursoragent@cursor.com>
Move shutdown into header popup + profile, move remote into sidebar above
settings, add flag-only language switcher in header, and add language card
plus shutdown/logout actions to the profile page.
Co-authored-by: Cursor <cursoragent@cursor.com>
Correctness:
- testUtils: drop checkExpiry so the userinfo URL probe actually runs (revoked
tokens used to look "active" until local 30-day expiry passed)
- auth.parseExpiry: handle numeric expiresAt, swap parseInt before Date.parse
so "2026" doesn't get interpreted as year-2026, treat expires_in:0 as
already-expired instead of fabricating a 30-day default
- providers.mapTokens: synthesize email from userId when fetchUserInfo fails
so OAuth dedup works (re-logins no longer accumulate "Account N" rows)
SSE wrapper:
- wrapQoderSSE: add !doneEmitted guard on success branch (chunks could leak
past [DONE] when an error envelope shared a TCP packet with a valid one)
- flush(): finalize TextDecoder + drain trailing buffer so the chunk carrying
finish_reason is delivered when upstream closes without a final \n
- sanitize literal \n inside inner OpenAI body so SSE framing stays intact
Robustness:
- executor: wrap buildCosyHeaders in try/catch so a missing accessToken
returns 401 (re-auth) instead of bubbling as 500
- executor: short-circuit on missing accessToken before signing
- executor: plumb proxyOptions/signal through buildQoderRequestBody so
proxy-only networks can fetch the model_config catalog
- qoderModels: dedupe concurrent first-time misses with an in-flight Promise
map (parallel chat windows now do 1 upstream fetch instead of N)
- qoderModels: check signal.aborted before addEventListener so a pre-aborted
parent signal cancels the inner fetch immediately
- auth: AbortController + 15s timeout on pollDeviceToken / fetchUserInfo to
prevent hung sockets when openapi.qoder.sh stalls mid-response
UX:
- OAuthModal: derive polling deadline from device-code expires_in (qoder
publishes 300s; the previous fixed 120s caused timeouts when users took
more than 2 minutes on the consent page)
Cleanup:
- delete src/lib/oauth/services/qoder.js — referenced removed config fields
(clientId/clientSecret/tokenUrl/authorizeUrl) and was re-exported from
services/index.js, so any future caller would TypeError on first use
- LanguageSwitcher: remove mounted state + useLayoutEffect pattern
Portal renders directly based on open state (SSR-safe without client check)
- UsageStats: replace stats-null check with isInitialLoad ref to avoid
setState in effect body (cascading render issue)
commit 6561679f5c396bb07f5f7ba5bc5ec75e81c803a4
Author: OpenClaw Patch <patch@openclaw.local>
Date: Tue May 19 16:26:01 2026 -0700
fix: never dedup access_token connections
Access tokens should always create new entries. User decides
which to keep (refresh-based OAuth vs no-expiry website token)
and removes the other manually.
commit d773451657999a2965ca4a094a7f0b7a54066693
Author: OpenClaw Patch <patch@openclaw.local>
Date: Tue May 19 16:24:30 2026 -0700
fix: support ChatGPT website token format (account_id, plan_type)
ChatGPT website access tokens use top-level 'account_id' and
'plan_type' fields, while OAuth id_tokens use nested claims
under 'https://api.openai.com/auth'. Now both formats are
handled, so workspace dedup works for website tokens too.
commit cb895a5f6be59c51267874f11567646fa1f43016
Author: OpenClaw Patch <patch@openclaw.local>
Date: Tue May 19 16:12:56 2026 -0700
fix: detect JWT in manual callback URL field
When user pastes a JWT access token (starts with eyJ) in the
'paste callback URL' input field, skip URL parsing and send
it directly to the exchange endpoint as the code. Fixes
'Failed to construct URL: Invalid URL' error.
commit 29650d4a6732e3cf0958c9963b53209e41c8281e
Author: OpenClaw Patch <patch@openclaw.local>
Date: Tue May 19 15:37:02 2026 -0700
feat: auto-detect access token in OAuth exchange
When the exchange endpoint receives a JWT (starts with eyJ)
instead of an OAuth authorization code, it detects this and
creates an access_token connection directly — skipping the
OAuth token exchange flow.
This lets users paste a ChatGPT access token where the OAuth
code would normally go, and have it work automatically.
commit e8e7c5709a783abd0c45246a44de1cc6abdba100
Author: OpenClaw Patch <patch@openclaw.local>
Date: Tue May 19 15:14:48 2026 -0700
feat: workspace-aware dedup + ChatGPT access token import
1. Dedup now checks email AND workspace (chatgptAccountId)
- Same email in different workspaces = separate connections
- Backward compatible: non-workspace providers still dedup by email
2. New authType 'access_token' for ChatGPT website tokens
- POST /api/oauth/codex/import-token accepts raw access tokens
- Extracts email, workspace, plan from JWT claims
- Deduplicates by email+workspace like OAuth
- No refresh token needed (avoids OAuth relogin issues)
On viewports below 640px the pagination row at Dashboard > Usage >
Details rendered the rows-per-page select plus the full numbered page
list plus the prev/next chevrons in one unwrapped flex row with no
horizontal padding. On a 390px phone the Rows: label was clipped on
the left and the next chevron was clipped on the right.
Add px-2 to the outer container so the pagination card has horizontal
breathing room. Switch the inner controls group to flex-wrap with
gap-2 on mobile (and gap-4 from sm: up) so the rows-per-page select
can wrap below the chevrons. Hide the numbered page buttons, the
1 / last anchors, and the ... ellipses below sm: -- only the prev,
current page indicator, and next chevrons render on mobile, which
keeps every control reachable while fitting inside the card.
Desktop layout (>= 640px) is unchanged.
Refs decolua/9router#1146
- Fix duplicate tray icon on macOS when hiding to tray
- Fix tray not showing in background mode on macOS
- Fix hide to tray broken on Windows/Linux
- Fix Shutdown button in web UI not working
* feat(model-select-modal): highlight added models and support bulk selection
- Add addedModelValues prop to highlight already-added models with primary color
- Sort models alphabetically per provider, with added models floated to top
- Replace green highlight with primary brand color (orange #E56A4A)
- Use check icon (10px) inline with model name instead of check_circle
- Replace Done button with info bar explaining click-to-toggle behavior
- Add ProviderIcon to provider group headers replacing colored dot
- Import ProviderIcon, remove unused Button import
* feat(cli-tools): wire addedModelValues, onDeselect, and auto-save to model select modals
- Pass selectedModels as addedModelValues to ModelSelectModal in OpenCode and Copilot cards
- Add onDeselect handler to remove model from list on second click
- Set closeOnSelect=false to allow bulk model selection
- Remove manual setModalOpen(false) from onSelect callbacks
- Add saveModels() silent auto-save triggered on modal close (OpenCodeToolCard)
- Use useRef to track latest selectedModels in closure-safe way
* feat(modal): functional traffic light close button with hover icon and tooltip
- Make red dot a clickable button that closes the modal
- Show ✕ icon inside red dot on hover via group-hover opacity transition
- Gray out yellow and green dots (cursor-not-allowed, no tooltip)
- Increase dot size from w-3 h-3 to w-4 h-4
- Add Tooltip with brand-matched color #FF5F56 on red dot
- Remove X close button from modal header
* feat(tooltip): add color prop for themed tooltip backgrounds
* feat(i18n): add translations for model select info bar and close tooltip
- Add 'Click to add, click again to remove. Changes are saved automatically.' to all 32 locales
- Add 'Close' translation to all 32 locales
* fix(ui): address code review feedback on modal UX and auto-save
- Modal: remove showCloseButton prop, use showTrafficLights for header
condition, hide traffic lights on mobile (hidden md:flex), add mobile
X button (md:hidden) with aria-label, add aria-label and title on
traffic light close button
- OpenCodeToolCard: validate activeModel membership before saving —
fallback to models[0] or empty string; clear/reassign activeModel
on deselect when removed model was the active one
- CopilotToolCard: add useRef + selectedModelsRef, add saveModels()
using /api/cli-tools/copilot-settings, wire auto-save on modal close
- ModelSelectModal: fix JSX formatting — separate info bar closing div
from Search comment onto its own line
* feat(usage): add Today period option to Usage & Analytics
Bổ sung lựa chọn Today vào bộ lọc thời gian của trang Usage & Analytics
(trước đây chỉ có 24h, 7D, 30D, 60D).
Khác biệt với 24h:
- 24h: cuộn 24 giờ trước → hiện tại
- Today: cố định từ 00:00 hôm nay (giờ local) → hiện tại
Thay đổi:
- page.js, UsageStats.js: thêm option Today vào danh sách PERIODS,
đổi grid mobile từ 4 cột sang 5 cột để fit option mới.
- api/usage/stats, api/usage/chart: cho phép giá trị period today.
- usageRepo.js:
+ getUsageStats: dùng nhánh live history khi period = today,
cutoff lấy từ 00:00 hôm nay theo local time.
+ getChartData: thêm 24 bucket theo giờ từ 00:00 → 23:59 hôm nay.
* feat(usage): đặt mặc định period là Today khi mở dashboard/usage
Người dùng thường quan tâm usage trong ngày hôm nay nhiều hơn 7 ngày,
nên hiển thị Today ngay khi vừa mở trang để giảm 1 thao tác chuyển period.
Đồng bộ luôn fallback trong UsageStats để giữ nhất quán khi component
dùng standalone.
Bổ sung lựa chọn Today vào bộ lọc thời gian của trang Usage & Analytics
(trước đây chỉ có 24h, 7D, 30D, 60D).
Khác biệt với 24h:
- 24h: cuộn 24 giờ trước → hiện tại
- Today: cố định từ 00:00 hôm nay (giờ local) → hiện tại
Thay đổi:
- page.js, UsageStats.js: thêm option Today vào danh sách PERIODS,
đổi grid mobile từ 4 cột sang 5 cột để fit option mới.
- api/usage/stats, api/usage/chart: cho phép giá trị period today.
- usageRepo.js:
+ getUsageStats: dùng nhánh live history khi period = today,
cutoff lấy từ 00:00 hôm nay theo local time.
+ getChartData: thêm 24 bucket theo giờ từ 00:00 → 23:59 hôm nay.
