Files
infosave2007 0b071279ac
CI / lint (push) Canceled after 0s
CI / test (macos-14) (push) Canceled after 0s
CI / test (ubuntu-latest) (push) Canceled after 0s
CI / test (windows-latest) (push) Canceled after 0s
Release / crates-io (push) Canceled after 0s
Release / release (macos-14, aarch64-apple-darwin) (push) Canceled after 0s
Release / release (ubuntu-latest, x86_64-unknown-linux-gnu) (push) Canceled after 0s
Release / release (windows-latest, x86_64-pc-windows-msvc) (push) Canceled after 0s
Docker / publish (push) Canceled after 0s
fix(stream): no choice-less chunks unless the client asks for usage
Every stream used to carry two chunks with an empty choices array: usage,
which the upstream emits BEFORE the stop reason, and a cortiq_cost_usd chunk
the gateway added itself. OpenAI ships the usage chunk only when the request
sets stream_options: {"include_usage": true}, and chat UIs do not set it -
which is why the same tool, in the same Open WebUI, sees neither chunk from
Groq and two from us.

Honour the flag. With no stream_options a stream is now exactly
role -> content... -> tool_calls -> finish_reason -> [DONE], with no
choice-less chunks at all. When usage is requested it ships once, after the
stop reason, with cortiq_cost_usd folded into the same chunk rather than
trailing behind it.

Token accounting, cost and the X-Cortiq-* headers are untouched: those numbers
were never read back off the wire.

Verified: the default stream matches the reference shape byte for byte, the
opt-in stream matches OpenAI's, the official OpenAI SDK reassembles the
streamed tool call, and the full Open WebUI 0.11.0 tool loop still runs the
tool and answers from its result.
2026-08-21 21:24:11 +03:00

80 lines
2.2 KiB
TOML

[package]
name = "cortiq-gateway"
version = "0.2.49"
edition = "2021"
rust-version = "1.75"
license = "Apache-2.0"
description = "Universal LLM gateway with intelligent routing and an embedded multilingual admin console"
repository = "https://github.com/infosave2007/cortiq-gateway"
homepage = "https://api.allaigate.com"
readme = "README.md"
keywords = ["llm", "gateway", "proxy", "openai", "routing"]
categories = ["web-programming::http-server", "command-line-utilities"]
# Files shipped in the published crate. The embedded admin SPA MUST be included
# because rust-embed compiles it in; docs/screenshots are excluded to keep the
# crate lean. The web/ subfolders are listed one by one rather than as web/**/*
# so stray scratch files dropped next to the SPA never end up published.
include = [
"src/**/*",
"web/index.html",
"web/favicon.svg",
"web/css/**/*",
"web/js/**/*",
"config/gateway.example.toml",
"README.md",
"CHANGELOG.md",
"LICENSE",
]
[dependencies]
# async runtime + HTTP server
tokio = { version = "1", features = ["full"] }
axum = { version = "0.7", features = ["macros"] }
tower = "0.5"
tower-http = { version = "0.6", features = ["limit", "trace", "cors"] }
# HTTP client to providers and to cortiq-router (rustls, no OpenSSL)
reqwest = { version = "0.12", default-features = false, features = ["json", "stream", "rustls-tls"] }
# serialization
serde = { version = "1", features = ["derive"] }
serde_json = "1"
toml = "0.8"
# hot-reloadable shared state + embedded admin SPA
arc-swap = "1"
rust-embed = "8"
mime_guess = "2"
# cross-platform CSPRNG for admin/key token generation (Linux/macOS/Windows)
getrandom = "0.2"
# streaming / async utils
futures = "0.3"
async-trait = "0.1"
async-stream = "0.3"
bytes = "1"
tokio-stream = "0.1"
# CLI / config
clap = { version = "4", features = ["derive"] }
# open browser on first run (optional)
open = { version = "5", optional = true }
# host metrics for the admin dashboard (CPU / RAM / disk)
sysinfo = "0.39"
# errors / logging / metrics
thiserror = "1"
anyhow = "1"
tracing = "0.1"
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
[features]
default = ["open-browser"]
open-browser = ["open"]
[profile.release]
lto = true
codegen-units = 1