ZacharyZhang-NY
ea0ce9d15f
Sampler / inference (PRD F3):
- kimi_compat.rs: single adaptation point for the Kimi chat/completions
dialect (thinking-field mapping, model_id stripping, empty-content
tool-call message fix, stream_options.include_usage), with kimi-cli
source citations
- Rate-limit handling reworked for Kimi/Moonshot semantics; UA kigi/{version}
- /models replaces the xAI models-v2 endpoint everywhere; idle model
refresh carries X-Msh-* device headers only (X-XAI-Token-Auth and
x-grok-client-mode/CLIENT_MODE_HEADER machinery deleted)
Cloud-surface excision (PRD §5, zero-egress):
- remote/ conversations lane, cli-chat-proxy-types crate, prod/ dir,
share command, credit bar: deleted (single local session lane;
paginate() replaces merge_and_paginate)
- Subscription/tier gate stack deleted end-to-end: AppView
gate/tier/team/ZDR fields, app/subscription.rs watch loop,
dispatch/billing.rs paywall + SuperGrok upsell, free-usage-exhausted
chain, tier-restricted commands, GateInfo, RemoteSettings gate fields,
SettingsUpdateNotification gate fields
- /privacy + coding-data-sharing setting deleted (backed by a dead xAI
RPC; Kigi is zero-egress — nothing to share or retain remotely)
Auth UX correctness (user-reported):
- Device-flow fixtures now mirror the live Kimi payload shape
(https://www.kimi.com/code/authorize_device?user_code=..., verified
against auth.kimi.com); the fabricated auth.kimi.com/device?code=...
URLs are gone
- open_browser_detached is a no-op under cfg(test): unit tests drove
wiremock fixture URLs into the real browser (root cause of the
"garbage mock link" ABCD-1234 tabs)
- Welcome/pager-minimal rebrand: Grok Build -> Kigi, grok.com ->
kimi.com, "Sign in to Grok" -> "Sign in to Kimi"
47 lines
1.4 KiB
TOML
47 lines
1.4 KiB
TOML
[package]
|
|
license = "Apache-2.0"
|
|
name = "kigi-sampler"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
description = "Actor-based sampling/inference layer for the Kimi APIs (HTTP streaming + retry, no shell coupling)"
|
|
|
|
[dependencies]
|
|
# Internal
|
|
kigi-sampling-types = { path = "../kigi-sampling-types" }
|
|
kigi-version = { workspace = true }
|
|
|
|
# External
|
|
async-openai = { workspace = true }
|
|
async-stream = { workspace = true }
|
|
chrono = { workspace = true, features = ["serde"] }
|
|
eventsource-stream = { workspace = true }
|
|
futures-util = { workspace = true }
|
|
indexmap = { workspace = true, features = ["serde"] }
|
|
reqwest = { workspace = true, features = ["stream"] }
|
|
serde = { workspace = true, features = ["derive"] }
|
|
serde_json = { workspace = true }
|
|
tokio = { workspace = true, features = ["rt", "macros", "time", "sync"] }
|
|
tokio-util = { workspace = true }
|
|
tracing = { workspace = true }
|
|
uuid = { workspace = true, features = ["v4"] }
|
|
|
|
[dev-dependencies]
|
|
# Mock HTTP server for actor / request_task integration tests.
|
|
axum = { workspace = true }
|
|
# Shared SSE generators for the happy-path mock payloads.
|
|
kigi-test-support = { workspace = true }
|
|
# `start_paused = true` for deterministic timeout testing; `net` for
|
|
# `TcpListener::bind` in the mock server harness.
|
|
tokio = { workspace = true, features = [
|
|
"rt",
|
|
"macros",
|
|
"time",
|
|
"sync",
|
|
"test-util",
|
|
"net",
|
|
"rt-multi-thread",
|
|
] }
|
|
|
|
[lints]
|
|
workspace = true
|