Commit Graph

193 Commits

Author SHA1 Message Date
nguyenha935
16cb40fda1 fix(kiro): canonicalize tool history and route API keys correctly
Route API-key inference through Amazon Q first, enforce adjacent
one-to-one tool use/result pairs after session replay, and treat
payload-invalid HTTP 400 as terminal.
2026-07-29 19:27:41 +07:00
decolua
8e04fe1734 feat(oauth): zed/trae/windsurf providers + harden callback proxies
- zed live model discovery; codebuddy-intl handler; remove duplicate workbuddy
- split oauth providers.js into per-provider files (facade re-export)
- fold 5 standard refresh providers into config-driven generic
- hide trae/windsurf from registry (no tool calling support)
- fix login-CSRF + SSRF on trae/windsurf/zed local callback proxies
  via loopback-origin guard + strict state validation + apiOrigins allowlist
- move zed RSA private key transit to POST body; redact proxy logs

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-25 17:25:19 +07:00
ryanngit
e45bd73d6e fix(tunnel): preserve successor cloudflared PID
Make PID cleanup conditional on the exiting child still owning the PID file so a stale exit cannot erase a replacement tunnel's PID. Only null the in-memory process when the exiting child is current. Explicit disable keeps unconditional cleanup.
2026-07-23 16:22:47 +07:00
Lê Tấn Thắng
4f48ab8c7f fix: resolve better-sqlite3 parameter array binding crash
Spread params into better-sqlite3 Statement.run/get/all so positional ? placeholders bind correctly. better-sqlite3 accepts positional args, not an array, so binding crashed whenever a query had parameters. Matches the bun:sqlite and node:sqlite adapters.
2026-07-20 12:08:58 +07:00
rixzkiye
e0ba667450 feat(cli-tools): configure Grok Build subagent models
Add separate model selectors for Grok Build main, general-purpose,
explore, and plan agents. Each override gets an independent 9Router
custom-model slot and context_window derived from 9Router model
capabilities. Preserve and restore pre-existing config on reset.
2026-07-19 13:35:38 +07:00
decolua
68566f53dc feat(kimi): merge OAuth into dual-auth provider, add K3/K2.7 models
Gộp kimi-coding vào kimi (oauth+apikey), parity CLIProxyAPI device flow/headers/refresh.
Thêm K3 + K2.7 Code (+ Kimi Code ids), pricing/caps vision, cập nhật baseline.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-17 12:09:14 +07:00
Ella CEO
7dfb346667 fix(grok-cli): surface expiresAt so proactive token refresh fires (#2546) 2026-07-16 12:00:14 +07:00
decolua
a6a41dfb3c Merge remote-tracking branch 'upstream/master'
# Conflicts:
#	.gitignore
#	open-sse/handlers/chatCore.js
2026-07-16 11:59:46 +07:00
decolua
a625ea9fd8 refactor(log): unify request lifecycle logging with session-colored tags
Collapse scattered per-request console lines (request/routing/auth/pending/
usage/stream-usage/stream) into 3 correlated lines: request, transform,
done. Add stable per-session color tag so concurrent request lines are
easy to follow, surface thinking intent, always-on full error logging
for debug, re-enable warn level, and uppercase keyword labels. Also fix
usage overview cards wrapping (5 cards -> grid-cols-5).

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-10 18:01:20 +07:00
decolua
74d5fedf79 feat(headroom): activate/uninstall extras + fix interpreter detection
- find interpreter next to headroom binary so extras/version read correctly
- add on/off toggle to activate [code]/[ml] via proxy restart
- add uninstall action + live install log progress + ~1GB confirm modal
2026-07-10 17:32:45 +07:00
Elio Bonfim Júnior
dcf1927f22 feat(pxpipe): PXPIPE token saver — multimodal prompt compression (#2465)
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.
2026-07-10 16:10:42 +07:00
Fadjrir Herlambang
e1f3399b73 feat(proxy-pools): auto-rotate strategy for no-auth providers (#2409)
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.
2026-07-10 16:05:07 +07:00
KunN-21
f1f9d27061 feat(headroom): add extras detection and install UI (#2403)
- add Headroom extras status + install endpoints
- show Headroom version + code/ml extras in Token Saver UI
- fix Windows interpreter selection to read from env with headroom-ai
2026-07-10 16:05:04 +07:00
decolua
b25e10160d fix: DB backup on schema change, MCP child cleanup, codex models, usage providers OOM
- Backup DB only on real SCHEMA_VERSION change, not every app version bump
- Kill idle MCP stdio bridge children to prevent orphan process leaks
- Add getDistinctProviders to avoid loading every row JSON blob (OOM fix)
- Update codex model list (gpt-5.6 sol/terra/luna, drop 5.3 codex variants)
- Reorder Claude default models (fable first)

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-10 13:08:58 +07:00
Fadjrir Herlambang
a11937cdd6 feat(grok-cli): add Grok CLI / Grok Build provider with OAuth device-code flow (#2502)
New OAuth provider routing through cli-chat-proxy.grok.com (OpenAI Responses
API), distinct from xai (api.x.ai) and grok-web (cookie SSO):

- Registry + GrokCliExecutor: Chat Completions -> Responses transform, CLI
  fingerprint headers, virtual effort models grok-4.5-{low,medium,high}
- OAuth device-code flow (auth.x.ai) with no-PKCE, shared xAI token refresh
- store=false multi-turn continuity via reasoning encrypted_content
- Quota tracker: on-demand window + prepaid balance on dashboard
- Connection test: 402 spending-limit = soft success (auth OK, out of credits)
- Alias/oauth/provider baselines + unit tests
2026-07-10 11:47:08 +07:00
Hermes Hunter
c73c419d09 fix(codex): avoid bare-email OAuth dedup (#2477)
Only update an existing Codex OAuth row when both rows share the same
chatgptAccountId, so a second Codex login no longer overwrites the first
account's rotated token pair. Also fall back to
workspaceId || chatgptAccountId || accountId for the chatgpt-account-id header.
2026-07-10 11:41:43 +07:00
ryanngit
3a7a878f91 fix(github): label Copilot profiles by account identity (#2498)
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-10 11:29:12 +07:00
nguyenha935
4dadab9d5f feat: add provider quota visibility settings 2026-07-04 23:26:49 +07:00
hodtien
54e3245ace feat(usage): track cached tokens + correct input/output/cache cost (#2209)
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>
2026-07-03 15:18:27 +07:00
KunN-21
cb0135b695 fix: prevent non-SSE stream pipe crash and cross-IdP account overwrites (#2244)
- streamingHandler: when upstream returns non-SSE/JSON (e.g. Cloudflare
  5xx HTML), read body, sanitize <title>, notify streamController and
  return a clean JSON error instead of crashing the pipe.
- connectionsRepo: dedup OAuth connections on (email + username) so
  cross-IdP accounts sharing an email no longer overwrite each other;
  workspace providers keep workspace-id matching.
- kimchi: bump User-Agent to 0.1.50, add svg asset + browser-login
  service, and 21 unit tests.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-03 11:11:07 +07:00
sternelee
b08751c4ea feat(clinepass): add ClinePass provider support
Register clinepass provider (OAuth + API-key) using Cline's
OpenAI-compatible API with 10 curated models, live /v1/models
resolver, refreshCline-based token refresh with workos: prefix,
and dashboard OAuth login handler.

Reference: https://github.com/jellydn/pi-clinepass-provider
Closes #2261

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-03 10:53:41 +07:00
Nant361
8a664d619d feat(kimchi): add Kimchi OAuth provider support
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>
2026-06-29 15:29:17 +07:00
Stevanus Pangau
a4f44e3e12 feat(kiro): add external_idp CLIProxyAPI import for Microsoft SSO
Import Kiro accounts authenticated via Microsoft Entra/365 SSO using
CLIProxyAPI JSON. Adds external_idp refresh path (form-encoded OAuth2,
Microsoft login host allowlist), TokenType: EXTERNAL_IDP header for
runtime and usage/quota requests, dashboard import UI, and unit tests.
Scoped to authMethod === "external_idp"; existing Kiro auth unchanged.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-26 11:42:05 +07:00
hamsa0x7
d8c2298d07 fix(security): patch 5 vulnerabilities from security audit
- mask API keys in usage stats/history responses (apiKeyMasked)
- validate proxy URL scheme + reject shell metachars before env write
- escape HTML in OAuth callback page to prevent XSS
- atomic O_EXCL lock file to prevent TOCTOU race in MITM startServer
- set mitmIsRestarting guard synchronously before any await

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-26 11:04:51 +07:00
Mink Nguyen
0d21668917 Fix usage logging dedupe and reduce stats churn
- batch console log buffer events and support batched SSE log messages
- debounce usage stats update/pending events to reduce UI/runtime churn
- avoid awaiting request-success bookkeeping before returning provider responses
- deduplicate identical usage writes in usageHistory/daily aggregates
- reduce default logger verbosity from DEBUG to INFO (overridable via LOG_LEVEL)

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-26 10:22:20 +07:00
Carmelo Campos
50ed79fe9e fix(headroom): support Docker sidecar proxy
Treat configured Headroom proxy as running when its /health endpoint
responds, even if local headroom CLI is not installed. Dashboard
Start/Stop stays limited to local loopback proxies while external
Docker sidecars can be enabled via HEADROOM_URL.

Closes #1948

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-21 17:45:27 +07:00
decolua
25e8723ad1 enhance API key management UI and improve watcher configuration. 2026-06-20 11:19:03 +07:00
decolua
b55cf36d2e feat(headroom): add proxy lifecycle management + dashboard UI
Build on the optional Headroom Token Saver from Carmelo Campos
(PR: feat: add optional Headroom token saver). Add managed start/stop
of the local headroom proxy from the dashboard, install detection,
status probing, and a simplified Token Saver UI.

- detect headroom CLI + python>=3.10, probe proxy /health
- spawn/stop proxy as a detached, pid-tracked process
- /api/headroom/{status,start,stop} routes, gated local-only in dashboardGuard
- one-click Start/Stop Headroom modal, no manual config needed
- claude<->openai shape conversion for /v1/compress via 9router translators

Thanks to Carmelo Campos (@carmelogunsroses) for the original Headroom integration.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-20 10:09:50 +07:00
Janu Yoga
efd20be8d8 feat(provider): add CodeBuddy CN provider (copilot.tencent.com)
Add Tencent CodeBuddy CN (codebuddy-cn) OAuth provider with full support:
OAuth login (GET poll with state query param), token refresh, 15-model
catalog, /v2 inference endpoint, forced streaming, OpenAI-style reasoning,
and per-model capabilities. Renamed from codebuddy to codebuddy-cn to allow
a future codebuddy-ai variant.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-19 15:33:26 +07:00
decolua
126aa244c5 fix(kiro): validate region to prevent SSRF (GHSA-6mwv-4mrm-5p3m)
Reject non-AWS region values before interpolating them into upstream
URLs and stop reflecting upstream response bodies to the client.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-19 15:09:18 +07:00
fjia
4078f36ced fix(usage): add missing await on getAdapter() in getRecentLogs
getAdapter() is async; without await, db was a Promise so db.all() threw
and the outer try/catch returned [] silently — usage logs endpoints
(/api/usage/logs, /api/usage/request-logs) always returned empty data.

Co-Authored-By: Claude <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-17 10:08:36 +07:00
thienpv
706e6513c9 feat(kiro): headless API-key auth + direct Claude/Kiro route
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>
2026-06-17 10:01:30 +07:00
decolua
aba4c45da6 fix(translator): ESM-safe registry + tool-id pairing + responses max_tokens; add real-creds tests
- translator/index.js: replace require() with static side-effect imports (ESM-safe),
  lazy-init registry maps to survive circular import order
- openai-responses->openai: map max_output_tokens -> max_tokens (avoid leaking field upstream)
- gemini/antigravity -> openai: derive deterministic tool_call id from name so
  functionCall/functionResponse pair correctly (fixes provider tool-pairing 400s)
- add offline unit tests (finish-reason, usage, session-manager, ollama malformed args, const guard)
- add real-creds integration tests (provider-cases + all-formats matrix: 6 inbound formats x 4 scenarios)

Includes co-located provider registry refactor (pricing/capabilities/media providers) and sessionManager updates.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-15 11:38:43 +07:00
decolua
fbf973f2e7 refactor(app): DRY pass — split large files, extract shared utils
S1: delete page.new.js (1724L abandoned) + remove dead getAntigravityProjectId
S2: split large files by natural seams
  - usage.js → usage/{github,google,claude,codex,kiro,minimax,misc,shared}.js
  - media-providers page → components/{Embedding,Tts,Generic,Stt}ExampleCard.js
  - EndpointPageClient → endpointConstants.js + endpointPing.js + components/
  - tokenRefresh.js → tokenRefresh/{dedup,providers}.js
  - ProviderLimits/index.js: 16 pure fn + 9 constants → utils.js
  - oauth/providers.js: 7 pure helpers → providerHelpers.js
S3: shared utils
  - getModelKind(m, fallback) → shared/constants/models.js (replaces 20× m.kind||m.type)
  - getStatusVariant → shared/utils/connectionStatus.js (dedup ConnectionRow/ConnectionsCard)
  - sseChunk → open-sse/utils/sse.js (dedup grok-web/perplexity-web)
  - fetchWithTimeout → usage/shared.js (replace 4× AbortController pattern in google.js)
fix: enableObservability2 field name in requestDetailsRepo
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-14 19:31:09 +07:00
decolua
d3f61aac2f refactor(open-sse): translator DRY + schema enums, bug fixes, dead code cleanup
- Bug B1-B7: media UI m.kind||m.type, serviceKinds, gemini mediaPriority, schema kind, models/info lookup by kind
- Dead code D1-D6: safeParseJSON, drop PROVIDER_ENDPOINTS, orphan fetcher, GITHUB_CONFIG derive, getProviderConfig internal, legacy kiro file
- Translator concerns: toOpenAIUsage, toOpenAIFinish (gemini/kiro/ollama + fix kiro tool finish), thinking effort maps
- Reorg helpers/ → concerns/ (logic) + formats/ (per-format) + schema/ (pure enums: roles/blocks/finishReasons/defaults)
- Wire ~280 hardcoded role/block/finish/default literals to schema enums across 20+ files
- collapseTextParts + extractTextContent dedup
- Normalize translator fn names to openaiToXRequest / xToOpenAIResponse
- Golden tests lock behavior; 0 regression (byte-for-byte providers/alias, 26=26 known fails)

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-14 18:49:38 +07:00
decolua
bb9e9aa91f refactor(open-sse): registry consolidation + DRY media/oauth/adhoc cleanup
- Single-source registry: oauth clientId/tokenUrl, usage URLs, image/embed
  configs, search defaultModel, codex fixedPort, google token url derive.
- Remove 29 unused OmniRoute providers (registry 100→71); media intact.
- De-adhoc: codex literals → registry format/oauth flags; reasoningInject,
  image/embed openrouter headers + xai bodyFields config-driven.
- Add REGISTRY_TEMPLATE.js + expand PROVIDER_DEFAULTS/schema JSDoc.
- Baselines updated; PROVIDERS 62 + alias 90 byte-for-byte, golden snapshots.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-14 13:15:48 +07:00
decolua
72ce515709 refactor(open-sse): dedupe Google OAuth client credentials (#4)
clientId/clientSecret của antigravity + gemini bị lặp 3 nơi
(registry, usage.js, src/lib/oauth). Gom vào shared.js
(ANTIGRAVITY_OAUTH_CLIENT, GOOGLE_OAUTH_CLIENT), các file spread vào.
Byte-for-byte: PROVIDERS/alias/oauth-url equal, golden 142 pass.
Thêm test guard nội dung + alias resolution.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-13 21:53:14 +07:00
decolua
0c7c9de00a fix(security): re-auth on DB export/import + SSRF guard on web fetch
- /api/settings/database now requires current password (header for GET,
  body for POST) in addition to session; CLI-token requests exempt
- add verifyDashboardPassword helper reusing login bcrypt check
- profile UI prompts password via modal before export/import
- /v1/web/fetch rejects internal/private/metadata targets via assertPublicUrl

Refs GHSA-qvfm-67h2-2qfx, GHSA-qj3v-64wj-q825

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-13 11:40:35 +07:00
decolua
b309261166 enhance Kiro profile ARN resolution 2026-06-13 09:28:55 +07:00
decolua
f8b73faf5d feat(cowork): re-enable Claude Cowork with preset-only stdio MCP
Restore Cowork feature while closing the RCE vector: drop user-defined
stdio commands so only hard-coded preset plugins (browsermcp) may spawn.
Custom MCP now accepts remote URL only. Routes stay gated to localhost.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-08 15:35:37 +07:00
decolua
7648c3412b fix(auth): real client IP rate-limiting + remote default-password guard
- 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>
2026-06-08 12:10:02 +07:00
Stefan Pirker
24a4f0863f fix(tunnel): detect system-installed Tailscale via dual-socket probe
Tailscale installed via apt/snap/brew was reported "Not Installed/Logged In"
because 9Router only probed its custom userspace socket. Probe the system
socket (/var/run/tailscale/tailscaled.sock) as fallback, add /usr/sbin and
/snap/bin to candidate paths and EXTENDED_PATH, and report separate
customDaemonRunning/systemDaemonRunning flags. Caching/non-blocking behavior
preserved.

Co-authored-by: Stefan Pirker <stefan.pirker86@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-08 10:14:59 +07:00
Quoc Nguyen
8962e466d6 feat(providers/codex): bulk add accounts via JSON
Add a "Bulk Add" button on /dashboard/providers/codex that imports
multiple OAuth accounts at once by pasting a JSON array, single object,
or { accounts: [...] } wrapper.

- New endpoint POST /api/oauth/codex/bulk-import (serial loop, no token echo)
- New BulkImportCodexModal component with JSON textarea + success/failure summary
- Persist idToken/lastRefreshAt on first insert via OPTIONAL_FIELDS
- Backfill email/chatgptAccountId/chatgptPlanType from JWT when missing
- Derive expiresAt from expiresIn when missing
- Gated to providerId === "codex" only; other providers unaffected

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-08 10:08:46 +07:00
decolua
f8c59227f6 fix(kiro): auto-resolve profileArn to prevent 403 on IDC login
AWS OIDC IDC/Builder-ID tokens omit profileArn, so CodeWhisperer calls
return 403 "User is not authorized". Resolve it natively via the
ListAvailableProfiles API instead of reading Kiro IDE profile.json.

- providers.js: add fetchKiroProfileArn() and resolve on poll (new logins)
- tokenRefresh.js: backfill profileArn on refresh so existing IDC
  connections self-heal without re-login

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-08 09:45:58 +07:00
joutvhu
dd5c575c65 fix(mitm): update Kiro API endpoint to runtime.us-east-1.kiro.dev
Kiro IDE changed its API endpoint from q.us-east-1.amazonaws.com to
runtime.us-east-1.kiro.dev. Old domains kept as fallback.

- mitm/config.js: add new hosts to TARGET_HOSTS + getToolForHost()
- cliTools.js: update mitmDomain to new endpoint
- mitmToolHosts.js: prepend new domain (keep legacy for compat)
- dataDir.js: on Windows ignore Unix-style DATA_DIR paths

Co-authored-by: joutvhu <joutvhu@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-08 09:43:45 +07:00
decolua
289214a2ea fix(tunnel): make tailscale probes non-blocking to prevent UI freeze
Convert isTailscaleLoggedIn to cached non-blocking getter and turn
isTailscaleRunningStrict / isTailscaleLoggedInStrict into async execAsync
probes. The status poll no longer blocks the event loop, so dashboard
navigation stays responsive while tunnel/tailscale checks run.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-08 09:32:29 +07:00
decolua
293cf40455 fix(tunnel): skip virtual interfaces to prevent false netchange watchdog
- Add VIRTUAL_IFACE_REGEX to filter utun/awdl/bridge from network fingerprint
- Trust cloudflared/tailscale while process is alive, never kill on force restart

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-06 15:44:33 +07:00
Kevin Le
c233c7c8fc fix(codex): durable OAuth refresh lifecycle
Add shared OAuth credential lifecycle manager with provider-aware refresh
decisions. Implement CodexExecutor.refreshCredentials so 401/403 retry
refresh works for Codex, track lastRefreshAt and refresh before the
upstream stale-token window, preserve omitted idToken, and add
per-connection single-flight refresh to avoid refresh-token rotation races.

Merged from PR #1664.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-06 11:04:36 +07:00
therunnas
61d546627e fix(qoder): allow qmodel_latest model key
- Add qmodel_latest to QODER_MODEL_MAP
- Expose qmodel_latest in static Qoder provider catalog (qd)
- Generalize executor comment so model set does not go stale
- Add unit coverage for the new model key + catalog

Closes #1638

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-06 10:44:37 +07:00
Simon Shi
4baaa5c7aa Feat : qoder provider 2026-05-29 17:36:27 +07:00