Passthrough kept the client's own cache_control markers, which point at
pre-normalization offsets. Once normalize/dedupe reshaped system and tools,
the breakpoints landed mid-array and the tail was re-cached every request.
- Pin the last system block and last tool at ttl 1h (was the client's 5m)
- Anchor the last assistant turn at 5m, falling back to the final message
so a first turn still gets a breakpoint
- Fold mid-conversation system messages into the neighbouring user turn
instead of hoisting them into body.system, where the volatile token
counters invalidated the prefix on every request
- Run the anchoring after every token saver, at the final body
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Codex Responses Lite clients routed to a chat-native OpenAI-compatible
provider lost tool use in three places: non-streaming Chat responses
leaked the raw chat.completion envelope instead of Responses output
items, internal reasoning continuity fields leaked into the outbound
Chat body causing some upstreams to reject the request, and the
Responses to Chat request translator ignored additional_tools,
custom_tool_call, and custom_tool_call_output items entirely.
Also fixes apiType (chat vs responses) for openai-compatible nodes
being resolved from the immutable provider ID instead of the stored
node config, so editing a node's API Type had no runtime effect.
Add "ultra" reasoning level for Codex GPT-5.6 Sol and Terra, and expose
Max for Luna (Luna falls back Ultra to Max since it is not supported
upstream). Scoped to cx/ routes only; Kiro and generic OpenAI routing
unchanged.
Rotating-RT providers (xAI/grok-cli) issue a new refresh_token on every
refresh; mutate credentials in-place so refreshWithRetry reuses the fresh
RT instead of the already-consumed one.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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outdated headers, producing HTTP 429 "Update Required".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.
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.
handleStreamingResponse and buildOnStreamComplete each generated their
own streamDetailId for what should be one logical record — the
placeholder row (0 tokens) and the final row (real usage) never shared
an id, so the DB's ON CONFLICT(id) upsert never merged them, leaving a
permanent 0-token stub for every streaming request.
Share the id from buildOnStreamComplete with handleStreamingResponse
so both writes hit the same row.
Co-authored-by: Cursor <cursoragent@cursor.com>
Keep provider-required streaming when client prefers JSON. The
Accept: application/json branch no longer flips stream back to false
for forceStream providers, fixing 400 errors on stream-only providers
(e.g. Command Code) for Hermes / Claude Code / other JSON clients.
Fixes#2031
Co-authored-by: Cursor <cursoragent@cursor.com>
Add image generation for Antigravity provider via gemini-3.1-flash-image
and gemini-3-pro-image, exposed through Text to Image UI and
/v1/images/generations.
- registry: serviceKinds ['llm','image'] + image model entries
- executor: image model detection + image_gen request envelope
- chatCore: force stream=false for image models (generateContent)
- nonStreamingHandler: parse inlineData -> markdown image
- imageGenerationCore: useExecutor fast-path for executor delegation
- imageProviders/antigravity: image adapter with image input support
- usage/google: image models in quota whitelist
Co-authored-by: Cursor <cursoragent@cursor.com>
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>
Add mimo-v2.5-pro-claude alias routing to the Xiaomi TokenPlan Anthropic-compatible
/anthropic/v1/messages endpoint. Logic lives in a dedicated XiaomiTokenplanExecutor
(config-driven via targetFormat) instead of the shared DefaultExecutor.
Co-authored-by: Cursor <cursoragent@cursor.com>
- 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.
Add clientDetector utility to identify CLI tools (Claude Code, Gemini CLI,
Antigravity, Codex) from request headers. When the CLI tool and provider
are a native pair, skip all translation — only swap model and Bearer token.
Made-with: Cursor
- Respect Accept: application/json header to return non-streaming JSON
instead of SSE, fixing AI SDK generateObject/generateText compatibility
- Strip markdown code block markers (```json...```) from Claude
non-streaming responses to prevent JSON parse errors
Cherry-picked and adapted from PR #290 by @rothnic
https://github.com/decolua/9router/pull/290
Made-with: Cursor
- 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
- 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
