F3: Kimi inference pipeline + full grok cloud-surface excision
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"
This commit is contained in:
@@ -653,16 +653,6 @@ pub struct AgentSession {
|
||||
/// fires, so the subsequent `TurnFailed` can be suppressed (the retry handler
|
||||
/// already displayed a user-friendly message). Cleared on `finish_turn`.
|
||||
pub model_incompatible: bool,
|
||||
/// Set when a `RetryState::Failed` carries a 403 credit-limit error, so
|
||||
/// the error message is suppressed in favour of the upsell modal.
|
||||
/// Cleared on `finish_turn`.
|
||||
pub credit_limit_blocked: bool,
|
||||
/// Set when a rate-limit `RetryState::Exhausted` carries the
|
||||
/// `subscription:free-usage-exhausted` code, so the PromptResponse
|
||||
/// handler shows the free-usage paywall instead of the generic
|
||||
/// rate-limit message. Always set together with [`Self::rate_limited`].
|
||||
/// Cleared on `finish_turn`.
|
||||
pub free_usage_blocked: bool,
|
||||
pub(crate) tracker: AcpUpdateTracker,
|
||||
/// ACP-advertised slash commands. Seeded from `InitializeResponse.meta`,
|
||||
/// updated by `AvailableCommandsUpdate`. The prompt-side registry syncs
|
||||
@@ -796,8 +786,6 @@ impl AgentSession {
|
||||
self.state = AgentState::Idle;
|
||||
self.rate_limited = false;
|
||||
self.model_incompatible = false;
|
||||
self.credit_limit_blocked = false;
|
||||
self.free_usage_blocked = false;
|
||||
self.in_flight_prompt = None;
|
||||
self.current_prompt_id = None;
|
||||
}
|
||||
@@ -999,8 +987,6 @@ mod tests {
|
||||
restore_degree: None,
|
||||
rate_limited: false,
|
||||
model_incompatible: false,
|
||||
credit_limit_blocked: false,
|
||||
free_usage_blocked: false,
|
||||
available_commands: Vec::new(),
|
||||
available_commands_generation: 0,
|
||||
available_tools: None,
|
||||
|
||||
Reference in New Issue
Block a user