Commit Graph
9 Commits
Author SHA1 Message Date
decoluaandClaude Fable 5 de2da19a9e feat(providers): add api-airforce, baidu, bazaarlink, bluesminds, kilo-gateway, llm7, morph, sambanova, tencent
Register 9 new upstream providers with logos and update the auto-generated
registry index. Refresh providers/alias baselines and extend the alias
token allowlist so verify-alias stays green.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-26 10:03:10 +07:00
Phuong Lambert 783e271c16 feat(gemini): add Gemini 3.6 Flash tier routing and 3.5 Flash Lite
Add gemini-3.6-flash tiered (high/medium/low) for Antigravity routing
via upstreamModelId "gemini-3.6-flash-tiered(level)" + thinkingLevel,
plus gemini-3.6-flash and gemini-3.5-flash-lite direct API models.

- getModelUpstreamId: split (level) suffix before lookup, re-append after
- Antigravity executor: preserve transformed body.model
- MITM extractModel: parse thinkingLevel for tiered model (default medium)
- Isolate Cloud Code endpoints: discovery (loadCodeAssist/onboardUser/
  quota) on PROD cloudcode-pa, chat transport on daily-cloudcode-pa
  to bypass prod 429
2026-07-23 16:34:24 +07:00
long2ice 6994cd1f70 fix(cursor): HTTP/2 AgentService support + version bump to 3.12.17
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outdated headers, producing HTTP 429 "Update Required".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.
2026-07-20 15:39:55 +07:00
decoluaandClaude Fable 5 55628eea02 fix(alicode-intl): split into Coding Plan + Model Studio providers
8b9cac1 swapped alicode-intl to the DashScope compatible-mode endpoint to
fix #2591 for standard DashScope keys, but that broke Coding Plan keys
(sk-sp-...) which only work on coding-intl.dashscope.aliyuncs.com. The two
key types use two different hosts and are not interchangeable.

- alicode-intl: revert to coding-intl endpoint (Coding Plan keys)
- alims-intl: new provider for dashscope-intl/compatible-mode (standard keys)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-19 16:29:55 +07:00
decoluaandCursor 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
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
Janu YogaandCursor 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
decoluaandCursor 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
decoluaandCursor f4c39042a0 refactor(open-sse): dedup format default in PROVIDERS via resolver (C1)
Wrap PROVIDERS in defineProviders() that appends format:"openai" when omitted,
removing 72 repeated `format:"openai"` lines. Output stays byte-for-byte
identical (verified by tests/__baseline__/verify-providers.mjs deep-equal
against snapshot). No runtime fields added; consumers unchanged.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-13 17:57:51 +07:00