feat: 合并上游 Rust 实现,扩展 API/运行时/工具链能力

将 claw-code/rust/crates 的完整实现合并到主 workspace,涵盖
  9 个 crate 的更新与 2 个新 crate 的引入。

  API 层:
  - 用原生 Anthropic 客户端(anthropic.rs)替换 claw_provider,
    新增 prompt cache 减少重复请求开销
  - 新增 HTTP 客户端构建器统一代理配置,OpenAI 兼容端增加
    DashScope/Qwen 支持与抖动重试
  - MessageRequest 扩展 temperature/top_p 等模型调参字段
  - SSE 解析器增加 provider 上下文感知的错误信息

  运行时(~11,000 行新增):
  - 新增 bash 命令安全校验、分支锁碰撞检测、配置文件校验
  - 新增会话存储与控制面、MCP 生命周期状态机与服务端实现
  - 新增权限执行引擎、策略引擎、插件生命周期管理
  - 新增 worker 启动编排、任务/定时任务注册表、信任解析器
  - 保留 Windows cmd /C fallback

  命令/插件/工具:
  - commands 大幅重写,扩展 sandbox、doctor、plan 等 slash 命令
  - plugins 新增 PostToolUseFailure hook 与宽容加载机制
  - tools 新增 PDF 提取与 lane 补全工具

  新增 crate:mock-anthropic-service(测试)、telemetry(遥测)

  适配 claw-cli/server:ClawApiClient→AnthropicClient 重命名,
  SlashCommand::parse 返回 Result,移除 session 级 Thinking 变体,
  TokenUsage/ConversationMessage 补充序列化支持
This commit is contained in:
fengmengqi
2026-04-13 14:39:17 +08:00
parent 4a04faf926
commit d8d77824f4
94 changed files with 49049 additions and 4429 deletions
+1
View File
@@ -10,6 +10,7 @@ reqwest = { version = "0.12", default-features = false, features = ["json", "rus
runtime = { path = "../runtime" }
serde = { version = "1", features = ["derive"] }
serde_json.workspace = true
telemetry = { path = "../telemetry" }
tokio = { version = "1", features = ["io-util", "macros", "net", "rt-multi-thread", "time"] }
[lints]
+138 -38
View File
@@ -1,70 +1,91 @@
use crate::error::ApiError;
use crate::providers::claw_provider::{self, AuthSource, ClawApiClient};
use crate::prompt_cache::{PromptCache, PromptCacheRecord, PromptCacheStats};
use crate::providers::anthropic::{self, AnthropicClient, AuthSource};
use crate::providers::openai_compat::{self, OpenAiCompatClient, OpenAiCompatConfig};
use crate::providers::{self, Provider, ProviderKind};
use crate::providers::{self, ProviderKind};
use crate::types::{MessageRequest, MessageResponse, StreamEvent};
async fn send_via_provider<P: Provider>(
provider: &P,
request: &MessageRequest,
) -> Result<MessageResponse, ApiError> {
provider.send_message(request).await
}
async fn stream_via_provider<P: Provider>(
provider: &P,
request: &MessageRequest,
) -> Result<P::Stream, ApiError> {
provider.stream_message(request).await
}
#[allow(clippy::large_enum_variant)]
#[derive(Debug, Clone)]
pub enum ProviderClient {
ClawApi(ClawApiClient),
Anthropic(AnthropicClient),
Xai(OpenAiCompatClient),
OpenAi(OpenAiCompatClient),
}
impl ProviderClient {
pub fn from_model(model: &str) -> Result<Self, ApiError> {
Self::from_model_with_default_auth(model, None)
Self::from_model_with_anthropic_auth(model, None)
}
pub fn from_model_with_default_auth(
pub fn from_model_with_anthropic_auth(
model: &str,
default_auth: Option<AuthSource>,
anthropic_auth: Option<AuthSource>,
) -> Result<Self, ApiError> {
let resolved_model = providers::resolve_model_alias(model);
match providers::detect_provider_kind(&resolved_model) {
ProviderKind::ClawApi => Ok(Self::ClawApi(match default_auth {
Some(auth) => ClawApiClient::from_auth(auth),
None => ClawApiClient::from_env()?,
ProviderKind::Anthropic => Ok(Self::Anthropic(match anthropic_auth {
Some(auth) => AnthropicClient::from_auth(auth),
None => AnthropicClient::from_env()?,
})),
ProviderKind::Xai => Ok(Self::Xai(OpenAiCompatClient::from_env(
OpenAiCompatConfig::xai(),
)?)),
ProviderKind::OpenAi => Ok(Self::OpenAi(OpenAiCompatClient::from_env(
OpenAiCompatConfig::openai(),
)?)),
ProviderKind::OpenAi => {
// DashScope models (qwen-*) also return ProviderKind::OpenAi because they
// speak the OpenAI wire format, but they need the DashScope config which
// reads DASHSCOPE_API_KEY and points at dashscope.aliyuncs.com.
let config = match providers::metadata_for_model(&resolved_model) {
Some(meta) if meta.auth_env == "DASHSCOPE_API_KEY" => {
OpenAiCompatConfig::dashscope()
}
_ => OpenAiCompatConfig::openai(),
};
Ok(Self::OpenAi(OpenAiCompatClient::from_env(config)?))
}
}
}
#[must_use]
pub const fn provider_kind(&self) -> ProviderKind {
match self {
Self::ClawApi(_) => ProviderKind::ClawApi,
Self::Anthropic(_) => ProviderKind::Anthropic,
Self::Xai(_) => ProviderKind::Xai,
Self::OpenAi(_) => ProviderKind::OpenAi,
}
}
#[must_use]
pub fn with_prompt_cache(self, prompt_cache: PromptCache) -> Self {
match self {
Self::Anthropic(client) => Self::Anthropic(client.with_prompt_cache(prompt_cache)),
other => other,
}
}
#[must_use]
pub fn prompt_cache_stats(&self) -> Option<PromptCacheStats> {
match self {
Self::Anthropic(client) => client.prompt_cache_stats(),
Self::Xai(_) | Self::OpenAi(_) => None,
}
}
#[must_use]
pub fn take_last_prompt_cache_record(&self) -> Option<PromptCacheRecord> {
match self {
Self::Anthropic(client) => client.take_last_prompt_cache_record(),
Self::Xai(_) | Self::OpenAi(_) => None,
}
}
pub async fn send_message(
&self,
request: &MessageRequest,
) -> Result<MessageResponse, ApiError> {
match self {
Self::ClawApi(client) => send_via_provider(client, request).await,
Self::Xai(client) | Self::OpenAi(client) => send_via_provider(client, request).await,
Self::Anthropic(client) => client.send_message(request).await,
Self::Xai(client) | Self::OpenAi(client) => client.send_message(request).await,
}
}
@@ -73,10 +94,12 @@ impl ProviderClient {
request: &MessageRequest,
) -> Result<MessageStream, ApiError> {
match self {
Self::ClawApi(client) => stream_via_provider(client, request)
Self::Anthropic(client) => client
.stream_message(request)
.await
.map(MessageStream::ClawApi),
Self::Xai(client) | Self::OpenAi(client) => stream_via_provider(client, request)
.map(MessageStream::Anthropic),
Self::Xai(client) | Self::OpenAi(client) => client
.stream_message(request)
.await
.map(MessageStream::OpenAiCompat),
}
@@ -85,7 +108,7 @@ impl ProviderClient {
#[derive(Debug)]
pub enum MessageStream {
ClawApi(claw_provider::MessageStream),
Anthropic(anthropic::MessageStream),
OpenAiCompat(openai_compat::MessageStream),
}
@@ -93,25 +116,25 @@ impl MessageStream {
#[must_use]
pub fn request_id(&self) -> Option<&str> {
match self {
Self::ClawApi(stream) => stream.request_id(),
Self::Anthropic(stream) => stream.request_id(),
Self::OpenAiCompat(stream) => stream.request_id(),
}
}
pub async fn next_event(&mut self) -> Result<Option<StreamEvent>, ApiError> {
match self {
Self::ClawApi(stream) => stream.next_event().await,
Self::Anthropic(stream) => stream.next_event().await,
Self::OpenAiCompat(stream) => stream.next_event().await,
}
}
}
pub use claw_provider::{
pub use anthropic::{
oauth_token_is_expired, resolve_saved_oauth_token, resolve_startup_auth_source, OAuthTokenSet,
};
#[must_use]
pub fn read_base_url() -> String {
claw_provider::read_base_url()
anthropic::read_base_url()
}
#[must_use]
@@ -121,8 +144,21 @@ pub fn read_xai_base_url() -> String {
#[cfg(test)]
mod tests {
use std::sync::{Mutex, OnceLock};
use super::ProviderClient;
use crate::providers::{detect_provider_kind, resolve_model_alias, ProviderKind};
/// Serializes every test in this module that mutates process-wide
/// environment variables so concurrent test threads cannot observe
/// each other's partially-applied state.
fn env_lock() -> std::sync::MutexGuard<'static, ()> {
static LOCK: OnceLock<Mutex<()>> = OnceLock::new();
LOCK.get_or_init(|| Mutex::new(()))
.lock()
.unwrap_or_else(std::sync::PoisonError::into_inner)
}
#[test]
fn resolves_existing_and_grok_aliases() {
assert_eq!(resolve_model_alias("opus"), "claude-opus-4-6");
@@ -135,7 +171,71 @@ mod tests {
assert_eq!(detect_provider_kind("grok-3"), ProviderKind::Xai);
assert_eq!(
detect_provider_kind("claude-sonnet-4-6"),
ProviderKind::ClawApi
ProviderKind::Anthropic
);
}
/// Snapshot-restore guard for a single environment variable. Mirrors
/// the pattern used in `providers/mod.rs` tests: captures the original
/// value on construction, applies the override, and restores on drop so
/// tests leave the process env untouched even when they panic.
struct EnvVarGuard {
key: &'static str,
original: Option<std::ffi::OsString>,
}
impl EnvVarGuard {
fn set(key: &'static str, value: Option<&str>) -> Self {
let original = std::env::var_os(key);
match value {
Some(value) => std::env::set_var(key, value),
None => std::env::remove_var(key),
}
Self { key, original }
}
}
impl Drop for EnvVarGuard {
fn drop(&mut self) {
match self.original.take() {
Some(value) => std::env::set_var(self.key, value),
None => std::env::remove_var(self.key),
}
}
}
#[test]
fn dashscope_model_uses_dashscope_config_not_openai() {
// Regression: qwen-plus was being routed to OpenAiCompatConfig::openai()
// which reads OPENAI_API_KEY and points at api.openai.com, when it should
// use OpenAiCompatConfig::dashscope() which reads DASHSCOPE_API_KEY and
// points at dashscope.aliyuncs.com.
let _lock = env_lock();
let _dashscope = EnvVarGuard::set("DASHSCOPE_API_KEY", Some("test-dashscope-key"));
let _openai = EnvVarGuard::set("OPENAI_API_KEY", None);
let client = ProviderClient::from_model("qwen-plus");
// Must succeed (not fail with "missing OPENAI_API_KEY")
assert!(
client.is_ok(),
"qwen-plus with DASHSCOPE_API_KEY set should build successfully, got: {:?}",
client.err()
);
// Verify it's the OpenAi variant pointed at the DashScope base URL.
match client.unwrap() {
ProviderClient::OpenAi(openai_client) => {
assert!(
openai_client.base_url().contains("dashscope.aliyuncs.com"),
"qwen-plus should route to DashScope base URL (contains 'dashscope.aliyuncs.com'), got: {}",
openai_client.base_url()
);
}
other => panic!(
"Expected ProviderClient::OpenAi for qwen-plus, got: {:?}",
other
),
}
}
}
+450 -13
View File
@@ -2,22 +2,55 @@ use std::env::VarError;
use std::fmt::{Display, Formatter};
use std::time::Duration;
const GENERIC_FATAL_WRAPPER_MARKERS: &[&str] = &[
"something went wrong while processing your request",
"please try again, or use /new to start a fresh session",
];
const CONTEXT_WINDOW_ERROR_MARKERS: &[&str] = &[
"maximum context length",
"context window",
"context length",
"too many tokens",
"prompt is too long",
"input is too long",
"request is too large",
];
#[derive(Debug)]
pub enum ApiError {
MissingCredentials {
provider: &'static str,
env_vars: &'static [&'static str],
/// Optional, runtime-computed hint appended to the error Display
/// output. Populated when the provider resolver can infer what the
/// user probably intended (e.g. an OpenAI key is set but Anthropic
/// was selected because no Anthropic credentials exist).
hint: Option<String>,
},
ContextWindowExceeded {
model: String,
estimated_input_tokens: u32,
requested_output_tokens: u32,
estimated_total_tokens: u32,
context_window_tokens: u32,
},
ExpiredOAuthToken,
Auth(String),
InvalidApiKeyEnv(VarError),
Http(reqwest::Error),
Io(std::io::Error),
Json(serde_json::Error),
Json {
provider: String,
model: String,
body_snippet: String,
source: serde_json::Error,
},
Api {
status: reqwest::StatusCode,
error_type: Option<String>,
message: Option<String>,
request_id: Option<String>,
body: String,
retryable: bool,
},
@@ -38,7 +71,48 @@ impl ApiError {
provider: &'static str,
env_vars: &'static [&'static str],
) -> Self {
Self::MissingCredentials { provider, env_vars }
Self::MissingCredentials {
provider,
env_vars,
hint: None,
}
}
/// Build a `MissingCredentials` error carrying an extra, runtime-computed
/// hint string that the Display impl appends after the canonical "missing
/// <provider> credentials" message. Used by the provider resolver to
/// suggest the likely fix when the user has credentials for a different
/// provider already in the environment.
#[must_use]
pub fn missing_credentials_with_hint(
provider: &'static str,
env_vars: &'static [&'static str],
hint: impl Into<String>,
) -> Self {
Self::MissingCredentials {
provider,
env_vars,
hint: Some(hint.into()),
}
}
/// Build a `Self::Json` enriched with the provider name, the model that
/// was requested, and the first 200 characters of the raw response body so
/// that callers can diagnose deserialization failures without re-running
/// the request.
#[must_use]
pub fn json_deserialize(
provider: impl Into<String>,
model: impl Into<String>,
body: &str,
source: serde_json::Error,
) -> Self {
Self::Json {
provider: provider.into(),
model: model.into(),
body_snippet: truncate_body_snippet(body, 200),
source,
}
}
#[must_use]
@@ -48,11 +122,106 @@ impl ApiError {
Self::Api { retryable, .. } => *retryable,
Self::RetriesExhausted { last_error, .. } => last_error.is_retryable(),
Self::MissingCredentials { .. }
| Self::ContextWindowExceeded { .. }
| Self::ExpiredOAuthToken
| Self::Auth(_)
| Self::InvalidApiKeyEnv(_)
| Self::Io(_)
| Self::Json(_)
| Self::Json { .. }
| Self::InvalidSseFrame(_)
| Self::BackoffOverflow { .. } => false,
}
}
#[must_use]
pub fn request_id(&self) -> Option<&str> {
match self {
Self::Api { request_id, .. } => request_id.as_deref(),
Self::RetriesExhausted { last_error, .. } => last_error.request_id(),
Self::MissingCredentials { .. }
| Self::ContextWindowExceeded { .. }
| Self::ExpiredOAuthToken
| Self::Auth(_)
| Self::InvalidApiKeyEnv(_)
| Self::Http(_)
| Self::Io(_)
| Self::Json { .. }
| Self::InvalidSseFrame(_)
| Self::BackoffOverflow { .. } => None,
}
}
#[must_use]
pub fn safe_failure_class(&self) -> &'static str {
match self {
Self::RetriesExhausted { .. } if self.is_context_window_failure() => "context_window",
Self::RetriesExhausted { .. } if self.is_generic_fatal_wrapper() => {
"provider_retry_exhausted"
}
Self::RetriesExhausted { last_error, .. } => last_error.safe_failure_class(),
Self::MissingCredentials { .. } | Self::ExpiredOAuthToken | Self::Auth(_) => {
"provider_auth"
}
Self::Api { status, .. } if matches!(status.as_u16(), 401 | 403) => "provider_auth",
Self::ContextWindowExceeded { .. } => "context_window",
Self::Api { .. } if self.is_context_window_failure() => "context_window",
Self::Api { status, .. } if status.as_u16() == 429 => "provider_rate_limit",
Self::Api { .. } if self.is_generic_fatal_wrapper() => "provider_internal",
Self::Api { .. } => "provider_error",
Self::Http(_) | Self::InvalidSseFrame(_) | Self::BackoffOverflow { .. } => {
"provider_transport"
}
Self::InvalidApiKeyEnv(_) | Self::Io(_) | Self::Json { .. } => "runtime_io",
}
}
#[must_use]
pub fn is_generic_fatal_wrapper(&self) -> bool {
match self {
Self::Api { message, body, .. } => {
message
.as_deref()
.is_some_and(looks_like_generic_fatal_wrapper)
|| looks_like_generic_fatal_wrapper(body)
}
Self::RetriesExhausted { last_error, .. } => last_error.is_generic_fatal_wrapper(),
Self::MissingCredentials { .. }
| Self::ContextWindowExceeded { .. }
| Self::ExpiredOAuthToken
| Self::Auth(_)
| Self::InvalidApiKeyEnv(_)
| Self::Http(_)
| Self::Io(_)
| Self::Json { .. }
| Self::InvalidSseFrame(_)
| Self::BackoffOverflow { .. } => false,
}
}
#[must_use]
pub fn is_context_window_failure(&self) -> bool {
match self {
Self::ContextWindowExceeded { .. } => true,
Self::Api {
status,
message,
body,
..
} => {
matches!(status.as_u16(), 400 | 413 | 422)
&& (message
.as_deref()
.is_some_and(looks_like_context_window_error)
|| looks_like_context_window_error(body))
}
Self::RetriesExhausted { last_error, .. } => last_error.is_context_window_failure(),
Self::MissingCredentials { .. }
| Self::ExpiredOAuthToken
| Self::Auth(_)
| Self::InvalidApiKeyEnv(_)
| Self::Http(_)
| Self::Io(_)
| Self::Json { .. }
| Self::InvalidSseFrame(_)
| Self::BackoffOverflow { .. } => false,
}
@@ -62,10 +231,43 @@ impl ApiError {
impl Display for ApiError {
fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
match self {
Self::MissingCredentials { provider, env_vars } => write!(
Self::MissingCredentials {
provider,
env_vars,
hint,
} => {
write!(
f,
"missing {provider} credentials; export {} before calling the {provider} API",
env_vars.join(" or ")
)?;
if cfg!(target_os = "windows") {
if let Some(primary) = env_vars.first() {
write!(
f,
" (on Windows, environment variables set in PowerShell only persist for the current session; use `setx {primary} <value>` to make it permanent, then open a new terminal, or place a `.env` file containing `{primary}=<value>` in the current working directory)"
)?;
} else {
write!(
f,
" (on Windows, environment variables set in PowerShell only persist for the current session; use `setx` to make them permanent, then open a new terminal, or place a `.env` file in the current working directory)"
)?;
}
}
if let Some(hint) = hint {
write!(f, " — hint: {hint}")?;
}
Ok(())
}
Self::ContextWindowExceeded {
model,
estimated_input_tokens,
requested_output_tokens,
estimated_total_tokens,
context_window_tokens,
} => write!(
f,
"missing {provider} credentials; export {} before calling the {provider} API",
env_vars.join(" or ")
"context_window_blocked for {model}: estimated input {estimated_input_tokens} + requested output {requested_output_tokens} = {estimated_total_tokens} tokens exceeds the {context_window_tokens}-token context window; compact the session or reduce request size before retrying"
),
Self::ExpiredOAuthToken => {
write!(
@@ -79,19 +281,37 @@ impl Display for ApiError {
}
Self::Http(error) => write!(f, "http error: {error}"),
Self::Io(error) => write!(f, "io error: {error}"),
Self::Json(error) => write!(f, "json error: {error}"),
Self::Json {
provider,
model,
body_snippet,
source,
} => write!(
f,
"failed to parse {provider} response for model {model}: {source}; first 200 chars of body: {body_snippet}"
),
Self::Api {
status,
error_type,
message,
request_id,
body,
..
} => match (error_type, message) {
(Some(error_type), Some(message)) => {
write!(f, "api returned {status} ({error_type}): {message}")
} => {
if let (Some(error_type), Some(message)) = (error_type, message) {
write!(f, "api returned {status} ({error_type})")?;
if let Some(request_id) = request_id {
write!(f, " [trace {request_id}]")?;
}
write!(f, ": {message}")
} else {
write!(f, "api returned {status}")?;
if let Some(request_id) = request_id {
write!(f, " [trace {request_id}]")?;
}
write!(f, ": {body}")
}
_ => write!(f, "api returned {status}: {body}"),
},
}
Self::RetriesExhausted {
attempts,
last_error,
@@ -124,7 +344,12 @@ impl From<std::io::Error> for ApiError {
impl From<serde_json::Error> for ApiError {
fn from(value: serde_json::Error) -> Self {
Self::Json(value)
Self::Json {
provider: "unknown".to_string(),
model: "unknown".to_string(),
body_snippet: String::new(),
source: value,
}
}
}
@@ -133,3 +358,215 @@ impl From<VarError> for ApiError {
Self::InvalidApiKeyEnv(value)
}
}
fn looks_like_generic_fatal_wrapper(text: &str) -> bool {
let lowered = text.to_ascii_lowercase();
GENERIC_FATAL_WRAPPER_MARKERS
.iter()
.any(|marker| lowered.contains(marker))
}
fn looks_like_context_window_error(text: &str) -> bool {
let lowered = text.to_ascii_lowercase();
CONTEXT_WINDOW_ERROR_MARKERS
.iter()
.any(|marker| lowered.contains(marker))
}
/// Truncate `body` so the resulting snippet contains at most `max_chars`
/// characters (counted by Unicode scalar values, not bytes), preserving the
/// leading slice of the body that the caller most often needs to inspect.
fn truncate_body_snippet(body: &str, max_chars: usize) -> String {
let mut taken_chars = 0;
let mut byte_end = 0;
for (offset, character) in body.char_indices() {
if taken_chars >= max_chars {
break;
}
taken_chars += 1;
byte_end = offset + character.len_utf8();
}
if taken_chars >= max_chars && byte_end < body.len() {
format!("{}", &body[..byte_end])
} else {
body[..byte_end].to_string()
}
}
#[cfg(test)]
mod tests {
use super::{truncate_body_snippet, ApiError};
#[test]
fn json_deserialize_error_includes_provider_model_and_truncated_body_snippet() {
let raw_body = format!("{}{}", "x".repeat(190), "_TAIL_PAST_200_CHARS_MARKER_");
let source = serde_json::from_str::<serde_json::Value>("{not json")
.expect_err("invalid json should fail to parse");
let error = ApiError::json_deserialize("Anthropic", "claude-opus-4-6", &raw_body, source);
let rendered = error.to_string();
assert!(
rendered.starts_with("failed to parse Anthropic response for model claude-opus-4-6: "),
"rendered error should lead with provider and model: {rendered}"
);
assert!(
rendered.contains("first 200 chars of body: "),
"rendered error should label the body snippet: {rendered}"
);
let snippet = rendered
.split("first 200 chars of body: ")
.nth(1)
.expect("snippet section should be present");
assert!(
snippet.starts_with(&"x".repeat(190)),
"snippet should preserve the leading characters of the body: {snippet}"
);
assert!(
snippet.ends_with('…'),
"snippet should signal truncation with an ellipsis: {snippet}"
);
assert!(
!snippet.contains("_TAIL_PAST_200_CHARS_MARKER_"),
"snippet should drop characters past the 200-char cap: {snippet}"
);
assert_eq!(error.safe_failure_class(), "runtime_io");
assert_eq!(error.request_id(), None);
assert!(!error.is_retryable());
}
#[test]
fn truncate_body_snippet_keeps_short_bodies_intact() {
assert_eq!(truncate_body_snippet("hello", 200), "hello");
assert_eq!(truncate_body_snippet("", 200), "");
}
#[test]
fn truncate_body_snippet_caps_long_bodies_at_max_chars() {
let body = "a".repeat(250);
let snippet = truncate_body_snippet(&body, 200);
assert_eq!(snippet.chars().count(), 201, "200 chars + ellipsis");
assert!(snippet.ends_with('…'));
assert!(snippet.starts_with(&"a".repeat(200)));
}
#[test]
fn truncate_body_snippet_does_not_split_multibyte_characters() {
let body = "한글한글한글한글한글한글";
let snippet = truncate_body_snippet(body, 4);
assert_eq!(snippet, "한글한글…");
}
#[test]
fn detects_generic_fatal_wrapper_and_classifies_it_as_provider_internal() {
let error = ApiError::Api {
status: reqwest::StatusCode::INTERNAL_SERVER_ERROR,
error_type: Some("api_error".to_string()),
message: Some(
"Something went wrong while processing your request. Please try again, or use /new to start a fresh session."
.to_string(),
),
request_id: Some("req_jobdori_123".to_string()),
body: String::new(),
retryable: true,
};
assert!(error.is_generic_fatal_wrapper());
assert_eq!(error.safe_failure_class(), "provider_internal");
assert_eq!(error.request_id(), Some("req_jobdori_123"));
assert!(error.to_string().contains("[trace req_jobdori_123]"));
}
#[test]
fn retries_exhausted_preserves_nested_request_id_and_failure_class() {
let error = ApiError::RetriesExhausted {
attempts: 3,
last_error: Box::new(ApiError::Api {
status: reqwest::StatusCode::BAD_GATEWAY,
error_type: Some("api_error".to_string()),
message: Some(
"Something went wrong while processing your request. Please try again, or use /new to start a fresh session."
.to_string(),
),
request_id: Some("req_nested_456".to_string()),
body: String::new(),
retryable: true,
}),
};
assert!(error.is_generic_fatal_wrapper());
assert_eq!(error.safe_failure_class(), "provider_retry_exhausted");
assert_eq!(error.request_id(), Some("req_nested_456"));
}
#[test]
fn classifies_provider_context_window_errors() {
let error = ApiError::Api {
status: reqwest::StatusCode::BAD_REQUEST,
error_type: Some("invalid_request_error".to_string()),
message: Some(
"This model's maximum context length is 200000 tokens, but your request used 230000 tokens."
.to_string(),
),
request_id: Some("req_ctx_123".to_string()),
body: String::new(),
retryable: false,
};
assert!(error.is_context_window_failure());
assert_eq!(error.safe_failure_class(), "context_window");
assert_eq!(error.request_id(), Some("req_ctx_123"));
}
#[test]
fn missing_credentials_without_hint_renders_the_canonical_message() {
// given
let error = ApiError::missing_credentials(
"Anthropic",
&["ANTHROPIC_AUTH_TOKEN", "ANTHROPIC_API_KEY"],
);
// when
let rendered = error.to_string();
// then
assert!(
rendered.starts_with(
"missing Anthropic credentials; export ANTHROPIC_AUTH_TOKEN or ANTHROPIC_API_KEY before calling the Anthropic API"
),
"rendered error should lead with the canonical missing-credential message: {rendered}"
);
assert!(
!rendered.contains(" — hint: "),
"no hint should be appended when none is supplied: {rendered}"
);
}
#[test]
fn missing_credentials_with_hint_appends_the_hint_after_base_message() {
// given
let error = ApiError::missing_credentials_with_hint(
"Anthropic",
&["ANTHROPIC_AUTH_TOKEN", "ANTHROPIC_API_KEY"],
"I see OPENAI_API_KEY is set — if you meant to use the OpenAI-compat provider, prefix your model name with `openai/` so prefix routing selects it.",
);
// when
let rendered = error.to_string();
// then
assert!(
rendered.starts_with("missing Anthropic credentials;"),
"hint should be appended, not replace the base message: {rendered}"
);
let hint_marker = " — hint: I see OPENAI_API_KEY is set — if you meant to use the OpenAI-compat provider, prefix your model name with `openai/` so prefix routing selects it.";
assert!(
rendered.ends_with(hint_marker),
"rendered error should end with the hint: {rendered}"
);
// Classification semantics are unaffected by the presence of a hint.
assert_eq!(error.safe_failure_class(), "provider_auth");
assert!(!error.is_retryable());
assert_eq!(error.request_id(), None);
}
}
+344
View File
@@ -0,0 +1,344 @@
use crate::error::ApiError;
const HTTP_PROXY_KEYS: [&str; 2] = ["HTTP_PROXY", "http_proxy"];
const HTTPS_PROXY_KEYS: [&str; 2] = ["HTTPS_PROXY", "https_proxy"];
const NO_PROXY_KEYS: [&str; 2] = ["NO_PROXY", "no_proxy"];
/// Snapshot of the proxy-related environment variables that influence the
/// outbound HTTP client. Captured up front so callers can inspect, log, and
/// test the resolved configuration without re-reading the process environment.
///
/// When `proxy_url` is set it acts as a single catch-all proxy for both
/// HTTP and HTTPS traffic, taking precedence over the per-scheme fields.
#[derive(Debug, Clone, Default, PartialEq, Eq)]
pub struct ProxyConfig {
pub http_proxy: Option<String>,
pub https_proxy: Option<String>,
pub no_proxy: Option<String>,
/// Optional unified proxy URL that applies to both HTTP and HTTPS.
/// When set, this takes precedence over `http_proxy` and `https_proxy`.
pub proxy_url: Option<String>,
}
impl ProxyConfig {
/// Read proxy settings from the live process environment, honouring both
/// the upper- and lower-case spellings used by curl, git, and friends.
#[must_use]
pub fn from_env() -> Self {
Self::from_lookup(|key| std::env::var(key).ok())
}
/// Create a proxy configuration from a single URL that applies to both
/// HTTP and HTTPS traffic. This is the config-file alternative to setting
/// `HTTP_PROXY` and `HTTPS_PROXY` environment variables separately.
#[must_use]
pub fn from_proxy_url(url: impl Into<String>) -> Self {
Self {
proxy_url: Some(url.into()),
..Self::default()
}
}
fn from_lookup<F>(mut lookup: F) -> Self
where
F: FnMut(&str) -> Option<String>,
{
Self {
http_proxy: first_non_empty(&HTTP_PROXY_KEYS, &mut lookup),
https_proxy: first_non_empty(&HTTPS_PROXY_KEYS, &mut lookup),
no_proxy: first_non_empty(&NO_PROXY_KEYS, &mut lookup),
proxy_url: None,
}
}
#[must_use]
pub fn is_empty(&self) -> bool {
self.proxy_url.is_none() && self.http_proxy.is_none() && self.https_proxy.is_none()
}
}
/// Build a `reqwest::Client` that honours the standard `HTTP_PROXY`,
/// `HTTPS_PROXY`, and `NO_PROXY` environment variables. When no proxy is
/// configured the client behaves identically to `reqwest::Client::new()`.
pub fn build_http_client() -> Result<reqwest::Client, ApiError> {
build_http_client_with(&ProxyConfig::from_env())
}
/// Infallible counterpart to [`build_http_client`] for constructors that
/// historically returned `Self` rather than `Result<Self, _>`. When the proxy
/// configuration is malformed we fall back to a default client so that
/// callers retain the previous behaviour and the failure surfaces on the
/// first outbound request instead of at construction time.
#[must_use]
pub fn build_http_client_or_default() -> reqwest::Client {
build_http_client().unwrap_or_else(|_| reqwest::Client::new())
}
/// Build a `reqwest::Client` from an explicit [`ProxyConfig`]. Used by tests
/// and by callers that want to override process-level environment lookups.
///
/// When `config.proxy_url` is set it overrides the per-scheme `http_proxy`
/// and `https_proxy` fields and is registered as both an HTTP and HTTPS
/// proxy so a single value can route every outbound request.
pub fn build_http_client_with(config: &ProxyConfig) -> Result<reqwest::Client, ApiError> {
let mut builder = reqwest::Client::builder().no_proxy();
let no_proxy = config
.no_proxy
.as_deref()
.and_then(reqwest::NoProxy::from_string);
let (http_proxy_url, https_proxy_url) = match config.proxy_url.as_deref() {
Some(unified) => (Some(unified), Some(unified)),
None => (config.http_proxy.as_deref(), config.https_proxy.as_deref()),
};
if let Some(url) = https_proxy_url {
let mut proxy = reqwest::Proxy::https(url)?;
if let Some(filter) = no_proxy.clone() {
proxy = proxy.no_proxy(Some(filter));
}
builder = builder.proxy(proxy);
}
if let Some(url) = http_proxy_url {
let mut proxy = reqwest::Proxy::http(url)?;
if let Some(filter) = no_proxy.clone() {
proxy = proxy.no_proxy(Some(filter));
}
builder = builder.proxy(proxy);
}
Ok(builder.build()?)
}
fn first_non_empty<F>(keys: &[&str], lookup: &mut F) -> Option<String>
where
F: FnMut(&str) -> Option<String>,
{
keys.iter()
.find_map(|key| lookup(key).filter(|value| !value.is_empty()))
}
#[cfg(test)]
mod tests {
use std::collections::HashMap;
use super::{build_http_client_with, ProxyConfig};
fn config_from_map(pairs: &[(&str, &str)]) -> ProxyConfig {
let map: HashMap<String, String> = pairs
.iter()
.map(|(key, value)| ((*key).to_string(), (*value).to_string()))
.collect();
ProxyConfig::from_lookup(|key| map.get(key).cloned())
}
#[test]
fn proxy_config_is_empty_when_no_env_vars_are_set() {
// given
let config = config_from_map(&[]);
// when
let empty = config.is_empty();
// then
assert!(empty);
assert_eq!(config, ProxyConfig::default());
}
#[test]
fn proxy_config_reads_uppercase_http_https_and_no_proxy() {
// given
let pairs = [
("HTTP_PROXY", "http://proxy.internal:3128"),
("HTTPS_PROXY", "http://secure.internal:3129"),
("NO_PROXY", "localhost,127.0.0.1,.corp"),
];
// when
let config = config_from_map(&pairs);
// then
assert_eq!(
config.http_proxy.as_deref(),
Some("http://proxy.internal:3128")
);
assert_eq!(
config.https_proxy.as_deref(),
Some("http://secure.internal:3129")
);
assert_eq!(
config.no_proxy.as_deref(),
Some("localhost,127.0.0.1,.corp")
);
assert!(!config.is_empty());
}
#[test]
fn proxy_config_falls_back_to_lowercase_keys() {
// given
let pairs = [
("http_proxy", "http://lower.internal:3128"),
("https_proxy", "http://lower-secure.internal:3129"),
("no_proxy", ".lower"),
];
// when
let config = config_from_map(&pairs);
// then
assert_eq!(
config.http_proxy.as_deref(),
Some("http://lower.internal:3128")
);
assert_eq!(
config.https_proxy.as_deref(),
Some("http://lower-secure.internal:3129")
);
assert_eq!(config.no_proxy.as_deref(), Some(".lower"));
}
#[test]
fn proxy_config_prefers_uppercase_over_lowercase_when_both_set() {
// given
let pairs = [
("HTTP_PROXY", "http://upper.internal:3128"),
("http_proxy", "http://lower.internal:3128"),
];
// when
let config = config_from_map(&pairs);
// then
assert_eq!(
config.http_proxy.as_deref(),
Some("http://upper.internal:3128")
);
}
#[test]
fn proxy_config_treats_empty_strings_as_unset() {
// given
let pairs = [("HTTP_PROXY", ""), ("http_proxy", "")];
// when
let config = config_from_map(&pairs);
// then
assert!(config.http_proxy.is_none());
}
#[test]
fn build_http_client_succeeds_when_no_proxy_is_configured() {
// given
let config = ProxyConfig::default();
// when
let result = build_http_client_with(&config);
// then
assert!(result.is_ok());
}
#[test]
fn build_http_client_succeeds_with_valid_http_and_https_proxies() {
// given
let config = ProxyConfig {
http_proxy: Some("http://proxy.internal:3128".to_string()),
https_proxy: Some("http://secure.internal:3129".to_string()),
no_proxy: Some("localhost,127.0.0.1".to_string()),
proxy_url: None,
};
// when
let result = build_http_client_with(&config);
// then
assert!(result.is_ok());
}
#[test]
fn build_http_client_returns_http_error_for_invalid_proxy_url() {
// given
let config = ProxyConfig {
http_proxy: None,
https_proxy: Some("not a url".to_string()),
no_proxy: None,
proxy_url: None,
};
// when
let result = build_http_client_with(&config);
// then
let error = result.expect_err("invalid proxy URL must be reported as a build failure");
assert!(
matches!(error, crate::error::ApiError::Http(_)),
"expected ApiError::Http for invalid proxy URL, got: {error:?}"
);
}
#[test]
fn from_proxy_url_sets_unified_field_and_leaves_per_scheme_empty() {
// given / when
let config = ProxyConfig::from_proxy_url("http://unified.internal:3128");
// then
assert_eq!(
config.proxy_url.as_deref(),
Some("http://unified.internal:3128")
);
assert!(config.http_proxy.is_none());
assert!(config.https_proxy.is_none());
assert!(!config.is_empty());
}
#[test]
fn build_http_client_succeeds_with_unified_proxy_url() {
// given
let config = ProxyConfig {
proxy_url: Some("http://unified.internal:3128".to_string()),
no_proxy: Some("localhost".to_string()),
..ProxyConfig::default()
};
// when
let result = build_http_client_with(&config);
// then
assert!(result.is_ok());
}
#[test]
fn proxy_url_takes_precedence_over_per_scheme_fields() {
// given both per-scheme and unified are set
let config = ProxyConfig {
http_proxy: Some("http://per-scheme.internal:1111".to_string()),
https_proxy: Some("http://per-scheme.internal:2222".to_string()),
no_proxy: None,
proxy_url: Some("http://unified.internal:3128".to_string()),
};
// when building succeeds (the unified URL is valid)
let result = build_http_client_with(&config);
// then
assert!(result.is_ok());
}
#[test]
fn build_http_client_returns_error_for_invalid_unified_proxy_url() {
// given
let config = ProxyConfig::from_proxy_url("not a url");
// when
let result = build_http_client_with(&config);
// then
assert!(
matches!(result, Err(crate::error::ApiError::Http(_))),
"invalid unified proxy URL should fail: {result:?}"
);
}
}
+18 -2
View File
@@ -1,5 +1,7 @@
mod client;
mod error;
mod http_client;
mod prompt_cache;
mod providers;
mod sse;
mod types;
@@ -9,10 +11,18 @@ pub use client::{
resolve_startup_auth_source, MessageStream, OAuthTokenSet, ProviderClient,
};
pub use error::ApiError;
pub use providers::claw_provider::{AuthSource, ClawApiClient, ClawApiClient as ApiClient};
pub use http_client::{
build_http_client, build_http_client_or_default, build_http_client_with, ProxyConfig,
};
pub use prompt_cache::{
CacheBreakEvent, PromptCache, PromptCacheConfig, PromptCachePaths, PromptCacheRecord,
PromptCacheStats,
};
pub use providers::anthropic::{AnthropicClient, AnthropicClient as ApiClient, AuthSource};
pub use providers::openai_compat::{OpenAiCompatClient, OpenAiCompatConfig};
pub use providers::{
detect_provider_kind, max_tokens_for_model, resolve_model_alias, ProviderKind,
detect_provider_kind, max_tokens_for_model, max_tokens_for_model_with_override,
resolve_model_alias, ProviderKind,
};
pub use sse::{parse_frame, SseParser};
pub use types::{
@@ -21,3 +31,9 @@ pub use types::{
MessageResponse, MessageStartEvent, MessageStopEvent, OutputContentBlock, StreamEvent,
ToolChoice, ToolDefinition, ToolResultContentBlock, Usage,
};
pub use telemetry::{
AnalyticsEvent, AnthropicRequestProfile, ClientIdentity, JsonlTelemetrySink,
MemoryTelemetrySink, SessionTraceRecord, SessionTracer, TelemetryEvent, TelemetrySink,
DEFAULT_ANTHROPIC_VERSION,
};
+735
View File
@@ -0,0 +1,735 @@
use std::fs;
use std::path::{Path, PathBuf};
use std::sync::{Arc, Mutex};
use std::time::{Duration, SystemTime, UNIX_EPOCH};
use serde::{Deserialize, Serialize};
use crate::types::{MessageRequest, MessageResponse, Usage};
const DEFAULT_COMPLETION_TTL_SECS: u64 = 30;
const DEFAULT_PROMPT_TTL_SECS: u64 = 5 * 60;
const DEFAULT_BREAK_MIN_DROP: u32 = 2_000;
const MAX_SANITIZED_LENGTH: usize = 80;
const REQUEST_FINGERPRINT_VERSION: u32 = 1;
const REQUEST_FINGERPRINT_PREFIX: &str = "v1";
const FNV_OFFSET_BASIS: u64 = 0xcbf2_9ce4_8422_2325;
const FNV_PRIME: u64 = 0x0000_0100_0000_01b3;
#[derive(Debug, Clone)]
pub struct PromptCacheConfig {
pub session_id: String,
pub completion_ttl: Duration,
pub prompt_ttl: Duration,
pub cache_break_min_drop: u32,
}
impl PromptCacheConfig {
#[must_use]
pub fn new(session_id: impl Into<String>) -> Self {
Self {
session_id: session_id.into(),
completion_ttl: Duration::from_secs(DEFAULT_COMPLETION_TTL_SECS),
prompt_ttl: Duration::from_secs(DEFAULT_PROMPT_TTL_SECS),
cache_break_min_drop: DEFAULT_BREAK_MIN_DROP,
}
}
}
impl Default for PromptCacheConfig {
fn default() -> Self {
Self::new("default")
}
}
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
pub struct PromptCachePaths {
pub root: PathBuf,
pub session_dir: PathBuf,
pub completion_dir: PathBuf,
pub session_state_path: PathBuf,
pub stats_path: PathBuf,
}
impl PromptCachePaths {
#[must_use]
pub fn for_session(session_id: &str) -> Self {
let root = base_cache_root();
let session_dir = root.join(sanitize_path_segment(session_id));
let completion_dir = session_dir.join("completions");
Self {
root,
session_state_path: session_dir.join("session-state.json"),
stats_path: session_dir.join("stats.json"),
session_dir,
completion_dir,
}
}
#[must_use]
pub fn completion_entry_path(&self, request_hash: &str) -> PathBuf {
self.completion_dir.join(format!("{request_hash}.json"))
}
}
#[derive(Debug, Clone, Default, PartialEq, Eq, Serialize, Deserialize)]
pub struct PromptCacheStats {
pub tracked_requests: u64,
pub completion_cache_hits: u64,
pub completion_cache_misses: u64,
pub completion_cache_writes: u64,
pub expected_invalidations: u64,
pub unexpected_cache_breaks: u64,
pub total_cache_creation_input_tokens: u64,
pub total_cache_read_input_tokens: u64,
pub last_cache_creation_input_tokens: Option<u32>,
pub last_cache_read_input_tokens: Option<u32>,
pub last_request_hash: Option<String>,
pub last_completion_cache_key: Option<String>,
pub last_break_reason: Option<String>,
pub last_cache_source: Option<String>,
}
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
pub struct CacheBreakEvent {
pub unexpected: bool,
pub reason: String,
pub previous_cache_read_input_tokens: u32,
pub current_cache_read_input_tokens: u32,
pub token_drop: u32,
}
#[derive(Debug, Clone, PartialEq, Eq)]
pub struct PromptCacheRecord {
pub cache_break: Option<CacheBreakEvent>,
pub stats: PromptCacheStats,
}
#[derive(Debug, Clone)]
pub struct PromptCache {
inner: Arc<Mutex<PromptCacheInner>>,
}
impl PromptCache {
#[must_use]
pub fn new(session_id: impl Into<String>) -> Self {
Self::with_config(PromptCacheConfig::new(session_id))
}
#[must_use]
pub fn with_config(config: PromptCacheConfig) -> Self {
let paths = PromptCachePaths::for_session(&config.session_id);
let stats = read_json::<PromptCacheStats>(&paths.stats_path).unwrap_or_default();
let previous = read_json::<TrackedPromptState>(&paths.session_state_path);
Self {
inner: Arc::new(Mutex::new(PromptCacheInner {
config,
paths,
stats,
previous,
})),
}
}
#[must_use]
pub fn paths(&self) -> PromptCachePaths {
self.lock().paths.clone()
}
#[must_use]
pub fn stats(&self) -> PromptCacheStats {
self.lock().stats.clone()
}
#[must_use]
pub fn lookup_completion(&self, request: &MessageRequest) -> Option<MessageResponse> {
let request_hash = request_hash_hex(request);
let (paths, ttl) = {
let inner = self.lock();
(inner.paths.clone(), inner.config.completion_ttl)
};
let entry_path = paths.completion_entry_path(&request_hash);
let entry = read_json::<CompletionCacheEntry>(&entry_path);
let Some(entry) = entry else {
let mut inner = self.lock();
inner.stats.completion_cache_misses += 1;
inner.stats.last_completion_cache_key = Some(request_hash);
persist_state(&inner);
return None;
};
if entry.fingerprint_version != current_fingerprint_version() {
let mut inner = self.lock();
inner.stats.completion_cache_misses += 1;
inner.stats.last_completion_cache_key = Some(request_hash.clone());
let _ = fs::remove_file(entry_path);
persist_state(&inner);
return None;
}
let expired = now_unix_secs().saturating_sub(entry.cached_at_unix_secs) >= ttl.as_secs();
let mut inner = self.lock();
inner.stats.last_completion_cache_key = Some(request_hash.clone());
if expired {
inner.stats.completion_cache_misses += 1;
let _ = fs::remove_file(entry_path);
persist_state(&inner);
return None;
}
inner.stats.completion_cache_hits += 1;
apply_usage_to_stats(
&mut inner.stats,
&entry.response.usage,
&request_hash,
"completion-cache",
);
inner.previous = Some(TrackedPromptState::from_usage(
request,
&entry.response.usage,
));
persist_state(&inner);
Some(entry.response)
}
#[must_use]
pub fn record_response(
&self,
request: &MessageRequest,
response: &MessageResponse,
) -> PromptCacheRecord {
self.record_usage_internal(request, &response.usage, Some(response))
}
#[must_use]
pub fn record_usage(&self, request: &MessageRequest, usage: &Usage) -> PromptCacheRecord {
self.record_usage_internal(request, usage, None)
}
fn record_usage_internal(
&self,
request: &MessageRequest,
usage: &Usage,
response: Option<&MessageResponse>,
) -> PromptCacheRecord {
let request_hash = request_hash_hex(request);
let mut inner = self.lock();
let previous = inner.previous.clone();
let current = TrackedPromptState::from_usage(request, usage);
let cache_break = detect_cache_break(&inner.config, previous.as_ref(), &current);
inner.stats.tracked_requests += 1;
apply_usage_to_stats(&mut inner.stats, usage, &request_hash, "api-response");
if let Some(event) = &cache_break {
if event.unexpected {
inner.stats.unexpected_cache_breaks += 1;
} else {
inner.stats.expected_invalidations += 1;
}
inner.stats.last_break_reason = Some(event.reason.clone());
}
inner.previous = Some(current);
if let Some(response) = response {
write_completion_entry(&inner.paths, &request_hash, response);
inner.stats.completion_cache_writes += 1;
}
persist_state(&inner);
PromptCacheRecord {
cache_break,
stats: inner.stats.clone(),
}
}
fn lock(&self) -> std::sync::MutexGuard<'_, PromptCacheInner> {
self.inner
.lock()
.unwrap_or_else(std::sync::PoisonError::into_inner)
}
}
#[derive(Debug)]
struct PromptCacheInner {
config: PromptCacheConfig,
paths: PromptCachePaths,
stats: PromptCacheStats,
previous: Option<TrackedPromptState>,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
struct CompletionCacheEntry {
cached_at_unix_secs: u64,
#[serde(default = "current_fingerprint_version")]
fingerprint_version: u32,
response: MessageResponse,
}
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
struct TrackedPromptState {
observed_at_unix_secs: u64,
#[serde(default = "current_fingerprint_version")]
fingerprint_version: u32,
model_hash: u64,
system_hash: u64,
tools_hash: u64,
messages_hash: u64,
cache_read_input_tokens: u32,
}
impl TrackedPromptState {
fn from_usage(request: &MessageRequest, usage: &Usage) -> Self {
let hashes = RequestFingerprints::from_request(request);
Self {
observed_at_unix_secs: now_unix_secs(),
fingerprint_version: current_fingerprint_version(),
model_hash: hashes.model,
system_hash: hashes.system,
tools_hash: hashes.tools,
messages_hash: hashes.messages,
cache_read_input_tokens: usage.cache_read_input_tokens,
}
}
}
#[derive(Debug, Clone, Copy)]
struct RequestFingerprints {
model: u64,
system: u64,
tools: u64,
messages: u64,
}
impl RequestFingerprints {
fn from_request(request: &MessageRequest) -> Self {
Self {
model: hash_serializable(&request.model),
system: hash_serializable(&request.system),
tools: hash_serializable(&request.tools),
messages: hash_serializable(&request.messages),
}
}
}
fn detect_cache_break(
config: &PromptCacheConfig,
previous: Option<&TrackedPromptState>,
current: &TrackedPromptState,
) -> Option<CacheBreakEvent> {
let previous = previous?;
if previous.fingerprint_version != current.fingerprint_version {
return Some(CacheBreakEvent {
unexpected: false,
reason: format!(
"fingerprint version changed (v{} -> v{})",
previous.fingerprint_version, current.fingerprint_version
),
previous_cache_read_input_tokens: previous.cache_read_input_tokens,
current_cache_read_input_tokens: current.cache_read_input_tokens,
token_drop: previous
.cache_read_input_tokens
.saturating_sub(current.cache_read_input_tokens),
});
}
let token_drop = previous
.cache_read_input_tokens
.saturating_sub(current.cache_read_input_tokens);
if token_drop < config.cache_break_min_drop {
return None;
}
let mut reasons = Vec::new();
if previous.model_hash != current.model_hash {
reasons.push("model changed");
}
if previous.system_hash != current.system_hash {
reasons.push("system prompt changed");
}
if previous.tools_hash != current.tools_hash {
reasons.push("tool definitions changed");
}
if previous.messages_hash != current.messages_hash {
reasons.push("message payload changed");
}
let elapsed = current
.observed_at_unix_secs
.saturating_sub(previous.observed_at_unix_secs);
let (unexpected, reason) = if reasons.is_empty() {
if elapsed > config.prompt_ttl.as_secs() {
(
false,
format!("possible prompt cache TTL expiry after {elapsed}s"),
)
} else {
(
true,
"cache read tokens dropped while prompt fingerprint remained stable".to_string(),
)
}
} else {
(false, reasons.join(", "))
};
Some(CacheBreakEvent {
unexpected,
reason,
previous_cache_read_input_tokens: previous.cache_read_input_tokens,
current_cache_read_input_tokens: current.cache_read_input_tokens,
token_drop,
})
}
fn apply_usage_to_stats(
stats: &mut PromptCacheStats,
usage: &Usage,
request_hash: &str,
source: &str,
) {
stats.total_cache_creation_input_tokens += u64::from(usage.cache_creation_input_tokens);
stats.total_cache_read_input_tokens += u64::from(usage.cache_read_input_tokens);
stats.last_cache_creation_input_tokens = Some(usage.cache_creation_input_tokens);
stats.last_cache_read_input_tokens = Some(usage.cache_read_input_tokens);
stats.last_request_hash = Some(request_hash.to_string());
stats.last_cache_source = Some(source.to_string());
}
fn persist_state(inner: &PromptCacheInner) {
let _ = ensure_cache_dirs(&inner.paths);
let _ = write_json(&inner.paths.stats_path, &inner.stats);
if let Some(previous) = &inner.previous {
let _ = write_json(&inner.paths.session_state_path, previous);
}
}
fn write_completion_entry(
paths: &PromptCachePaths,
request_hash: &str,
response: &MessageResponse,
) {
let _ = ensure_cache_dirs(paths);
let entry = CompletionCacheEntry {
cached_at_unix_secs: now_unix_secs(),
fingerprint_version: current_fingerprint_version(),
response: response.clone(),
};
let _ = write_json(&paths.completion_entry_path(request_hash), &entry);
}
fn ensure_cache_dirs(paths: &PromptCachePaths) -> std::io::Result<()> {
fs::create_dir_all(&paths.completion_dir)
}
fn write_json<T: Serialize>(path: &Path, value: &T) -> std::io::Result<()> {
let json = serde_json::to_vec_pretty(value)
.map_err(|error| std::io::Error::new(std::io::ErrorKind::InvalidData, error))?;
fs::write(path, json)
}
fn read_json<T: for<'de> Deserialize<'de>>(path: &Path) -> Option<T> {
let bytes = fs::read(path).ok()?;
serde_json::from_slice(&bytes).ok()
}
fn request_hash_hex(request: &MessageRequest) -> String {
format!(
"{REQUEST_FINGERPRINT_PREFIX}-{:016x}",
hash_serializable(request)
)
}
fn hash_serializable<T: Serialize>(value: &T) -> u64 {
let json = serde_json::to_vec(value).unwrap_or_default();
stable_hash_bytes(&json)
}
fn sanitize_path_segment(value: &str) -> String {
let sanitized: String = value
.chars()
.map(|ch| if ch.is_ascii_alphanumeric() { ch } else { '-' })
.collect();
if sanitized.len() <= MAX_SANITIZED_LENGTH {
return sanitized;
}
let suffix = format!("-{:x}", hash_string(value));
format!(
"{}{}",
&sanitized[..MAX_SANITIZED_LENGTH.saturating_sub(suffix.len())],
suffix
)
}
fn hash_string(value: &str) -> u64 {
stable_hash_bytes(value.as_bytes())
}
fn base_cache_root() -> PathBuf {
if let Some(config_home) = std::env::var_os("CLAUDE_CONFIG_HOME") {
return PathBuf::from(config_home)
.join("cache")
.join("prompt-cache");
}
if let Some(home) = std::env::var_os("HOME") {
return PathBuf::from(home)
.join(".claude")
.join("cache")
.join("prompt-cache");
}
std::env::temp_dir().join("claude-prompt-cache")
}
fn now_unix_secs() -> u64 {
SystemTime::now()
.duration_since(UNIX_EPOCH)
.map_or(0, |duration| duration.as_secs())
}
const fn current_fingerprint_version() -> u32 {
REQUEST_FINGERPRINT_VERSION
}
fn stable_hash_bytes(bytes: &[u8]) -> u64 {
let mut hash = FNV_OFFSET_BASIS;
for byte in bytes {
hash ^= u64::from(*byte);
hash = hash.wrapping_mul(FNV_PRIME);
}
hash
}
#[cfg(test)]
mod tests {
use std::sync::{Mutex, OnceLock};
use std::time::{Duration, SystemTime, UNIX_EPOCH};
use super::{
detect_cache_break, read_json, request_hash_hex, sanitize_path_segment, PromptCache,
PromptCacheConfig, PromptCachePaths, TrackedPromptState, REQUEST_FINGERPRINT_PREFIX,
};
use crate::types::{InputMessage, MessageRequest, MessageResponse, OutputContentBlock, Usage};
fn test_env_lock() -> std::sync::MutexGuard<'static, ()> {
static LOCK: OnceLock<Mutex<()>> = OnceLock::new();
LOCK.get_or_init(|| Mutex::new(()))
.lock()
.unwrap_or_else(std::sync::PoisonError::into_inner)
}
#[test]
fn path_builder_sanitizes_session_identifier() {
let paths = PromptCachePaths::for_session("session:/with spaces");
let session_dir = paths
.session_dir
.file_name()
.and_then(|value| value.to_str())
.expect("session dir name");
assert_eq!(session_dir, "session--with-spaces");
assert!(paths.completion_dir.ends_with("completions"));
assert!(paths.stats_path.ends_with("stats.json"));
assert!(paths.session_state_path.ends_with("session-state.json"));
}
#[test]
fn request_fingerprint_drives_unexpected_break_detection() {
let request = sample_request("same");
let previous = TrackedPromptState::from_usage(
&request,
&Usage {
input_tokens: 0,
cache_creation_input_tokens: 0,
cache_read_input_tokens: 6_000,
output_tokens: 0,
},
);
let current = TrackedPromptState::from_usage(
&request,
&Usage {
input_tokens: 0,
cache_creation_input_tokens: 0,
cache_read_input_tokens: 1_000,
output_tokens: 0,
},
);
let event = detect_cache_break(&PromptCacheConfig::default(), Some(&previous), &current)
.expect("break should be detected");
assert!(event.unexpected);
assert!(event.reason.contains("stable"));
}
#[test]
fn changed_prompt_marks_break_as_expected() {
let previous_request = sample_request("first");
let current_request = sample_request("second");
let previous = TrackedPromptState::from_usage(
&previous_request,
&Usage {
input_tokens: 0,
cache_creation_input_tokens: 0,
cache_read_input_tokens: 6_000,
output_tokens: 0,
},
);
let current = TrackedPromptState::from_usage(
&current_request,
&Usage {
input_tokens: 0,
cache_creation_input_tokens: 0,
cache_read_input_tokens: 1_000,
output_tokens: 0,
},
);
let event = detect_cache_break(&PromptCacheConfig::default(), Some(&previous), &current)
.expect("break should be detected");
assert!(!event.unexpected);
assert!(event.reason.contains("message payload changed"));
}
#[test]
fn completion_cache_round_trip_persists_recent_response() {
let _guard = test_env_lock();
let temp_root = std::env::temp_dir().join(format!(
"prompt-cache-test-{}-{}",
std::process::id(),
SystemTime::now()
.duration_since(UNIX_EPOCH)
.expect("time")
.as_nanos()
));
std::env::set_var("CLAUDE_CONFIG_HOME", &temp_root);
let cache = PromptCache::new("unit-test-session");
let request = sample_request("cache me");
let response = sample_response(42, 12, "cached");
assert!(cache.lookup_completion(&request).is_none());
let record = cache.record_response(&request, &response);
assert!(record.cache_break.is_none());
let cached = cache
.lookup_completion(&request)
.expect("cached response should load");
assert_eq!(cached.content, response.content);
let stats = cache.stats();
assert_eq!(stats.completion_cache_hits, 1);
assert_eq!(stats.completion_cache_misses, 1);
assert_eq!(stats.completion_cache_writes, 1);
let persisted = read_json::<super::PromptCacheStats>(&cache.paths().stats_path)
.expect("stats should persist");
assert_eq!(persisted.completion_cache_hits, 1);
std::fs::remove_dir_all(temp_root).expect("cleanup temp root");
std::env::remove_var("CLAUDE_CONFIG_HOME");
}
#[test]
fn distinct_requests_do_not_collide_in_completion_cache() {
let _guard = test_env_lock();
let temp_root = std::env::temp_dir().join(format!(
"prompt-cache-distinct-{}-{}",
std::process::id(),
SystemTime::now()
.duration_since(UNIX_EPOCH)
.expect("time")
.as_nanos()
));
std::env::set_var("CLAUDE_CONFIG_HOME", &temp_root);
let cache = PromptCache::new("distinct-request-session");
let first_request = sample_request("first");
let second_request = sample_request("second");
let response = sample_response(42, 12, "cached");
let _ = cache.record_response(&first_request, &response);
assert!(cache.lookup_completion(&second_request).is_none());
std::fs::remove_dir_all(temp_root).expect("cleanup temp root");
std::env::remove_var("CLAUDE_CONFIG_HOME");
}
#[test]
fn expired_completion_entries_are_not_reused() {
let _guard = test_env_lock();
let temp_root = std::env::temp_dir().join(format!(
"prompt-cache-expired-{}-{}",
std::process::id(),
SystemTime::now()
.duration_since(UNIX_EPOCH)
.expect("time")
.as_nanos()
));
std::env::set_var("CLAUDE_CONFIG_HOME", &temp_root);
let cache = PromptCache::with_config(PromptCacheConfig {
session_id: "expired-session".to_string(),
completion_ttl: Duration::ZERO,
..PromptCacheConfig::default()
});
let request = sample_request("expire me");
let response = sample_response(7, 3, "stale");
let _ = cache.record_response(&request, &response);
assert!(cache.lookup_completion(&request).is_none());
let stats = cache.stats();
assert_eq!(stats.completion_cache_hits, 0);
assert_eq!(stats.completion_cache_misses, 1);
std::fs::remove_dir_all(temp_root).expect("cleanup temp root");
std::env::remove_var("CLAUDE_CONFIG_HOME");
}
#[test]
fn sanitize_path_caps_long_values() {
let long_value = "x".repeat(200);
let sanitized = sanitize_path_segment(&long_value);
assert!(sanitized.len() <= 80);
}
#[test]
fn request_hashes_are_versioned_and_stable() {
let request = sample_request("stable");
let first = request_hash_hex(&request);
let second = request_hash_hex(&request);
assert_eq!(first, second);
assert!(first.starts_with(REQUEST_FINGERPRINT_PREFIX));
}
fn sample_request(text: &str) -> MessageRequest {
MessageRequest {
model: "claude-3-7-sonnet-latest".to_string(),
max_tokens: 64,
messages: vec![InputMessage::user_text(text)],
system: Some("system".to_string()),
tools: None,
tool_choice: None,
stream: false,
..Default::default()
}
}
fn sample_response(
cache_read_input_tokens: u32,
output_tokens: u32,
text: &str,
) -> MessageResponse {
MessageResponse {
id: "msg_test".to_string(),
kind: "message".to_string(),
role: "assistant".to_string(),
content: vec![OutputContentBlock::Text {
text: text.to_string(),
}],
model: "claude-3-7-sonnet-latest".to_string(),
stop_reason: Some("end_turn".to_string()),
stop_sequence: None,
usage: Usage {
input_tokens: 10,
cache_creation_input_tokens: 5,
cache_read_input_tokens,
output_tokens,
},
request_id: Some("req_test".to_string()),
}
}
}
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
+56 -93
View File
@@ -1,11 +1,11 @@
use crate::error::ApiError;
use crate::types::StreamEvent;
use serde_json::Value;
use reqwest::StatusCode;
#[derive(Debug, Default)]
pub struct SseParser {
buffer: Vec<u8>,
provider: Option<String>,
model: Option<String>,
}
impl SseParser {
@@ -14,12 +14,23 @@ impl SseParser {
Self::default()
}
/// Attach the provider name and model to this parser so that JSON
/// deserialization failures within streamed frames carry enough context
/// for callers to understand which upstream produced the unparseable
/// payload.
#[must_use]
pub fn with_context(mut self, provider: impl Into<String>, model: impl Into<String>) -> Self {
self.provider = Some(provider.into());
self.model = Some(model.into());
self
}
pub fn push(&mut self, chunk: &[u8]) -> Result<Vec<StreamEvent>, ApiError> {
self.buffer.extend_from_slice(chunk);
let mut events = Vec::new();
while let Some(frame) = self.next_frame() {
if let Some(event) = parse_frame(&frame)? {
if let Some(event) = self.parse_frame_with_context(&frame)? {
events.push(event);
}
}
@@ -33,12 +44,18 @@ impl SseParser {
}
let trailing = std::mem::take(&mut self.buffer);
match parse_frame(&String::from_utf8_lossy(&trailing))? {
match self.parse_frame_with_context(&String::from_utf8_lossy(&trailing))? {
Some(event) => Ok(vec![event]),
None => Ok(Vec::new()),
}
}
fn parse_frame_with_context(&self, frame: &str) -> Result<Option<StreamEvent>, ApiError> {
let provider = self.provider.as_deref().unwrap_or("unknown");
let model = self.model.as_deref().unwrap_or("unknown");
parse_frame_with_provider(frame, provider, model)
}
fn next_frame(&mut self) -> Option<String> {
let separator = self
.buffer
@@ -63,6 +80,14 @@ impl SseParser {
}
pub fn parse_frame(frame: &str) -> Result<Option<StreamEvent>, ApiError> {
parse_frame_with_provider(frame, "unknown", "unknown")
}
pub(crate) fn parse_frame_with_provider(
frame: &str,
provider: &str,
model: &str,
) -> Result<Option<StreamEvent>, ApiError> {
let trimmed = frame.trim();
if trimmed.is_empty() {
return Ok(None);
@@ -97,75 +122,9 @@ pub fn parse_frame(frame: &str) -> Result<Option<StreamEvent>, ApiError> {
return Ok(None);
}
if matches!(event_name, Some("error")) {
return Err(parse_error_event(&payload));
}
// Some "Anthropic-compatible" gateways put the event type in the SSE `event:` field,
// and omit the `{ "type": ... }` discriminator from the JSON `data:` payload.
// Our Rust enums are tagged with `#[serde(tag = "type")]`, so we synthesize it here.
match serde_json::from_str::<StreamEvent>(&payload) {
Ok(event) => Ok(Some(event)),
Err(error) => {
// Best-effort: if we have an SSE event name and the payload is a JSON object
// without a `type` field, inject it and retry.
let Some(event_name) = event_name else {
return Err(ApiError::from(error));
};
let Ok(Value::Object(mut object)) = serde_json::from_str::<Value>(&payload) else {
return Err(ApiError::from(error));
};
if object
.get("type")
.and_then(Value::as_str)
.is_some_and(|value| value == "error")
{
return Err(parse_error_object(&object, payload));
}
if object.contains_key("type") {
return Err(ApiError::from(error));
}
object.insert("type".to_string(), Value::String(event_name.to_string()));
serde_json::from_value::<StreamEvent>(Value::Object(object))
.map(Some)
.map_err(ApiError::from)
}
}
}
fn parse_error_event(payload: &str) -> ApiError {
match serde_json::from_str::<Value>(payload) {
Ok(Value::Object(object)) => parse_error_object(&object, payload.to_string()),
_ => ApiError::Api {
status: StatusCode::BAD_GATEWAY,
error_type: Some("stream_error".to_string()),
message: Some(payload.to_string()),
body: payload.to_string(),
retryable: false,
},
}
}
fn parse_error_object(object: &serde_json::Map<String, Value>, body: String) -> ApiError {
let nested = object.get("error").and_then(Value::as_object);
let error_type = nested
.and_then(|error| error.get("type"))
.or_else(|| object.get("type"))
.and_then(Value::as_str)
.map(ToOwned::to_owned);
let message = nested
.and_then(|error| error.get("message"))
.or_else(|| object.get("message"))
.and_then(Value::as_str)
.map(ToOwned::to_owned);
ApiError::Api {
status: StatusCode::BAD_GATEWAY,
error_type,
message,
body,
retryable: false,
}
serde_json::from_str::<StreamEvent>(&payload)
.map(Some)
.map_err(|error| ApiError::json_deserialize(provider, model, &payload, error))
}
#[cfg(test)]
@@ -263,26 +222,6 @@ mod tests {
assert_eq!(event, None);
}
#[test]
fn parses_event_name_when_payload_omits_type() {
let frame = concat!("event: message_stop\n", "data: {}\n\n");
let event = parse_frame(frame).expect("frame should parse");
assert_eq!(event, Some(StreamEvent::MessageStop(crate::types::MessageStopEvent {})));
}
#[test]
fn surfaces_stream_error_events() {
let frame = concat!(
"event: error\n",
"data: {\"error\":{\"type\":\"invalid_request_error\",\"message\":\"bad input\"}}\n\n"
);
let error = parse_frame(frame).expect_err("error frame should surface");
assert_eq!(
error.to_string(),
"api returned 502 Bad Gateway (invalid_request_error): bad input"
);
}
#[test]
fn parses_split_json_across_data_lines() {
let frame = concat!(
@@ -364,4 +303,28 @@ mod tests {
))
);
}
#[test]
fn given_message_delta_frame_with_empty_usage_when_parsed_then_usage_defaults_to_zero() {
// given
let frame = concat!(
"event: message_delta\n",
"data: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"end_turn\",\"stop_sequence\":null},\"usage\":{}}\n\n"
);
// when
let event = parse_frame(frame).expect("frame should parse");
// then
assert_eq!(
event,
Some(StreamEvent::MessageDelta(crate::types::MessageDeltaEvent {
delta: MessageDelta {
stop_reason: Some("end_turn".to_string()),
stop_sequence: None,
},
usage: Usage::default(),
}))
);
}
}
+90 -11
View File
@@ -1,7 +1,8 @@
use runtime::{pricing_for_model, TokenUsage, UsageCostEstimate};
use serde::{Deserialize, Serialize};
use serde_json::Value;
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize, Default)]
pub struct MessageRequest {
pub model: String,
pub max_tokens: u32,
@@ -14,6 +15,22 @@ pub struct MessageRequest {
pub tool_choice: Option<ToolChoice>,
#[serde(default, skip_serializing_if = "std::ops::Not::not")]
pub stream: bool,
/// OpenAI-compatible tuning parameters. Optional — omitted from payload when None.
#[serde(skip_serializing_if = "Option::is_none")]
pub temperature: Option<f64>,
#[serde(skip_serializing_if = "Option::is_none")]
pub top_p: Option<f64>,
#[serde(skip_serializing_if = "Option::is_none")]
pub frequency_penalty: Option<f64>,
#[serde(skip_serializing_if = "Option::is_none")]
pub presence_penalty: Option<f64>,
#[serde(skip_serializing_if = "Option::is_none")]
pub stop: Option<Vec<String>>,
/// Reasoning effort level for OpenAI-compatible reasoning models (e.g. `o4-mini`).
/// Accepted values: `"low"`, `"medium"`, `"high"`. Omitted when `None`.
/// Silently ignored by backends that do not support it.
#[serde(skip_serializing_if = "Option::is_none")]
pub reasoning_effort: Option<String>,
}
impl MessageRequest {
@@ -75,14 +92,6 @@ pub enum InputContentBlock {
#[serde(default, skip_serializing_if = "std::ops::Not::not")]
is_error: bool,
},
Thinking {
thinking: String,
#[serde(default, skip_serializing_if = "Option::is_none")]
signature: Option<String>,
},
RedactedThinking {
data: Value,
},
}
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
@@ -120,6 +129,7 @@ pub struct MessageResponse {
pub stop_reason: Option<String>,
#[serde(default)]
pub stop_sequence: Option<String>,
#[serde(default)]
pub usage: Usage,
#[serde(default)]
pub request_id: Option<String>,
@@ -154,20 +164,44 @@ pub enum OutputContentBlock {
},
}
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
#[derive(Debug, Clone, Default, PartialEq, Eq, Serialize, Deserialize)]
pub struct Usage {
#[serde(default)]
pub input_tokens: u32,
#[serde(default)]
pub cache_creation_input_tokens: u32,
#[serde(default)]
pub cache_read_input_tokens: u32,
#[serde(default)]
pub output_tokens: u32,
}
impl Usage {
#[must_use]
pub const fn total_tokens(&self) -> u32 {
self.input_tokens + self.output_tokens
self.input_tokens
+ self.output_tokens
+ self.cache_creation_input_tokens
+ self.cache_read_input_tokens
}
#[must_use]
pub const fn token_usage(&self) -> TokenUsage {
TokenUsage {
input_tokens: self.input_tokens,
output_tokens: self.output_tokens,
cache_creation_input_tokens: self.cache_creation_input_tokens,
cache_read_input_tokens: self.cache_read_input_tokens,
}
}
#[must_use]
pub fn estimated_cost_usd(&self, model: &str) -> UsageCostEstimate {
let usage = self.token_usage();
pricing_for_model(model).map_or_else(
|| usage.estimate_cost_usd(),
|pricing| usage.estimate_cost_usd_with_pricing(pricing),
)
}
}
@@ -179,6 +213,7 @@ pub struct MessageStartEvent {
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
pub struct MessageDeltaEvent {
pub delta: MessageDelta,
#[serde(default)]
pub usage: Usage,
}
@@ -229,3 +264,47 @@ pub enum StreamEvent {
ContentBlockStop(ContentBlockStopEvent),
MessageStop(MessageStopEvent),
}
#[cfg(test)]
mod tests {
use runtime::format_usd;
use super::{MessageResponse, Usage};
#[test]
fn usage_total_tokens_includes_cache_tokens() {
let usage = Usage {
input_tokens: 10,
cache_creation_input_tokens: 2,
cache_read_input_tokens: 3,
output_tokens: 4,
};
assert_eq!(usage.total_tokens(), 19);
assert_eq!(usage.token_usage().total_tokens(), 19);
}
#[test]
fn message_response_estimates_cost_from_model_usage() {
let response = MessageResponse {
id: "msg_cost".to_string(),
kind: "message".to_string(),
role: "assistant".to_string(),
content: Vec::new(),
model: "claude-sonnet-4-20250514".to_string(),
stop_reason: Some("end_turn".to_string()),
stop_sequence: None,
usage: Usage {
input_tokens: 1_000_000,
cache_creation_input_tokens: 100_000,
cache_read_input_tokens: 200_000,
output_tokens: 500_000,
},
request_id: None,
};
let cost = response.usage.estimated_cost_usd(&response.model);
assert_eq!(format_usd(cost.total_cost_usd()), "$54.6750");
assert_eq!(response.total_tokens(), 1_800_000);
}
}
+464 -19
View File
@@ -1,17 +1,27 @@
use std::collections::HashMap;
use std::sync::Arc;
use std::sync::{Mutex as StdMutex, OnceLock};
use std::time::Duration;
use api::{
ApiClient, ApiError, AuthSource, ContentBlockDelta, ContentBlockDeltaEvent,
AnthropicClient, ApiClient, ApiError, AuthSource, ContentBlockDelta, ContentBlockDeltaEvent,
ContentBlockStartEvent, InputContentBlock, InputMessage, MessageDeltaEvent, MessageRequest,
OutputContentBlock, ProviderClient, StreamEvent, ToolChoice, ToolDefinition,
OutputContentBlock, PromptCache, PromptCacheConfig, ProviderClient, StreamEvent, ToolChoice,
ToolDefinition,
};
use serde_json::json;
use telemetry::{ClientIdentity, MemoryTelemetrySink, SessionTracer, TelemetryEvent};
use tokio::io::{AsyncReadExt, AsyncWriteExt};
use tokio::net::TcpListener;
use tokio::sync::Mutex;
fn env_lock() -> std::sync::MutexGuard<'static, ()> {
static LOCK: OnceLock<StdMutex<()>> = OnceLock::new();
LOCK.get_or_init(|| StdMutex::new(()))
.lock()
.unwrap_or_else(std::sync::PoisonError::into_inner)
}
#[tokio::test]
async fn send_message_posts_json_and_parses_response() {
let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
@@ -20,8 +30,8 @@ async fn send_message_posts_json_and_parses_response() {
"\"id\":\"msg_test\",",
"\"type\":\"message\",",
"\"role\":\"assistant\",",
"\"content\":[{\"type\":\"text\",\"text\":\"Hello from Claw\"}],",
"\"model\":\"claude-sonnet-4-6\",",
"\"content\":[{\"type\":\"text\",\"text\":\"Hello from Claude\"}],",
"\"model\":\"claude-3-7-sonnet-latest\",",
"\"stop_reason\":\"end_turn\",",
"\"stop_sequence\":null,",
"\"usage\":{\"input_tokens\":12,\"output_tokens\":4},",
@@ -45,10 +55,12 @@ async fn send_message_posts_json_and_parses_response() {
assert_eq!(response.id, "msg_test");
assert_eq!(response.total_tokens(), 16);
assert_eq!(response.request_id.as_deref(), Some("req_body_123"));
assert_eq!(response.usage.cache_creation_input_tokens, 0);
assert_eq!(response.usage.cache_read_input_tokens, 0);
assert_eq!(
response.content,
vec![OutputContentBlock::Text {
text: "Hello from Claw".to_string(),
text: "Hello from Claude".to_string(),
}]
);
@@ -64,23 +76,258 @@ async fn send_message_posts_json_and_parses_response() {
request.headers.get("authorization").map(String::as_str),
Some("Bearer proxy-token")
);
assert_eq!(
request.headers.get("anthropic-version").map(String::as_str),
Some("2023-06-01")
);
assert_eq!(
request.headers.get("user-agent").map(String::as_str),
Some("claude-code/0.1.0")
);
assert_eq!(
request.headers.get("anthropic-beta").map(String::as_str),
Some("claude-code-20250219,prompt-caching-scope-2026-01-05")
);
let body: serde_json::Value =
serde_json::from_str(&request.body).expect("request body should be json");
assert_eq!(
body.get("model").and_then(serde_json::Value::as_str),
Some("claude-sonnet-4-6")
Some("claude-3-7-sonnet-latest")
);
assert!(body.get("stream").is_none());
assert_eq!(body["tools"][0]["name"], json!("get_weather"));
assert_eq!(body["tool_choice"]["type"], json!("auto"));
assert!(
body.get("betas").is_none(),
"betas must travel via the anthropic-beta header, not the request body"
);
}
#[tokio::test]
async fn send_message_blocks_oversized_requests_before_the_http_call() {
let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
let server = spawn_server(
state.clone(),
vec![http_response("200 OK", "application/json", "{}")],
)
.await;
let client = AnthropicClient::new("test-key").with_base_url(server.base_url());
let error = client
.send_message(&MessageRequest {
model: "claude-sonnet-4-6".to_string(),
max_tokens: 64_000,
messages: vec![InputMessage {
role: "user".to_string(),
content: vec![InputContentBlock::Text {
text: "x".repeat(600_000),
}],
}],
system: Some("Keep the answer short.".to_string()),
tools: None,
tool_choice: None,
stream: false,
..Default::default()
})
.await
.expect_err("oversized request should fail local context-window preflight");
assert!(matches!(error, ApiError::ContextWindowExceeded { .. }));
assert!(
state.lock().await.is_empty(),
"preflight failure should avoid any upstream HTTP request"
);
}
#[tokio::test]
async fn send_message_applies_request_profile_and_records_telemetry() {
let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
let server = spawn_server(
state.clone(),
vec![http_response_with_headers(
"200 OK",
"application/json",
concat!(
"{",
"\"id\":\"msg_profile\",",
"\"type\":\"message\",",
"\"role\":\"assistant\",",
"\"content\":[{\"type\":\"text\",\"text\":\"ok\"}],",
"\"model\":\"claude-3-7-sonnet-latest\",",
"\"stop_reason\":\"end_turn\",",
"\"stop_sequence\":null,",
"\"usage\":{\"input_tokens\":1,\"cache_creation_input_tokens\":2,\"cache_read_input_tokens\":3,\"output_tokens\":1}",
"}"
),
&[("request-id", "req_profile_123")],
)],
)
.await;
let sink = Arc::new(MemoryTelemetrySink::default());
let client = AnthropicClient::new("test-key")
.with_base_url(server.base_url())
.with_client_identity(ClientIdentity::new("claude-code", "9.9.9").with_runtime("rust-cli"))
.with_beta("tools-2026-04-01")
.with_extra_body_param("metadata", json!({"source": "clawd-code"}))
.with_session_tracer(SessionTracer::new("session-telemetry", sink.clone()));
let response = client
.send_message(&sample_request(false))
.await
.expect("request should succeed");
assert_eq!(response.request_id.as_deref(), Some("req_profile_123"));
let captured = state.lock().await;
let request = captured.first().expect("server should capture request");
assert_eq!(
request.headers.get("anthropic-beta").map(String::as_str),
Some("claude-code-20250219,prompt-caching-scope-2026-01-05,tools-2026-04-01")
);
assert_eq!(
request.headers.get("user-agent").map(String::as_str),
Some("claude-code/9.9.9")
);
let body: serde_json::Value =
serde_json::from_str(&request.body).expect("request body should be json");
assert_eq!(body["metadata"]["source"], json!("clawd-code"));
assert!(
body.get("betas").is_none(),
"betas must travel via the anthropic-beta header, not the request body"
);
let events = sink.events();
assert_eq!(events.len(), 6);
assert!(matches!(
&events[0],
TelemetryEvent::HttpRequestStarted {
session_id,
attempt: 1,
method,
path,
..
} if session_id == "session-telemetry" && method == "POST" && path == "/v1/messages"
));
assert!(matches!(
&events[1],
TelemetryEvent::SessionTrace(trace) if trace.name == "http_request_started"
));
assert!(matches!(
&events[2],
TelemetryEvent::HttpRequestSucceeded {
request_id,
status: 200,
..
} if request_id.as_deref() == Some("req_profile_123")
));
assert!(matches!(
&events[3],
TelemetryEvent::SessionTrace(trace) if trace.name == "http_request_succeeded"
));
assert!(matches!(
&events[4],
TelemetryEvent::Analytics(event)
if event.namespace == "api"
&& event.action == "message_usage"
&& event.properties.get("request_id") == Some(&json!("req_profile_123"))
&& event.properties.get("total_tokens") == Some(&json!(7))
&& event.properties.get("estimated_cost_usd") == Some(&json!("$0.0001"))
));
assert!(matches!(
&events[5],
TelemetryEvent::SessionTrace(trace) if trace.name == "analytics"
));
}
#[tokio::test]
async fn send_message_parses_prompt_cache_token_usage_from_response() {
let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
let body = concat!(
"{",
"\"id\":\"msg_cache_tokens\",",
"\"type\":\"message\",",
"\"role\":\"assistant\",",
"\"content\":[{\"type\":\"text\",\"text\":\"Cache tokens\"}],",
"\"model\":\"claude-3-7-sonnet-latest\",",
"\"stop_reason\":\"end_turn\",",
"\"stop_sequence\":null,",
"\"usage\":{\"input_tokens\":12,\"cache_creation_input_tokens\":321,\"cache_read_input_tokens\":654,\"output_tokens\":4}",
"}"
);
let server = spawn_server(
state,
vec![http_response("200 OK", "application/json", body)],
)
.await;
let client = AnthropicClient::new("test-key").with_base_url(server.base_url());
let response = client
.send_message(&sample_request(false))
.await
.expect("request should succeed");
assert_eq!(response.usage.input_tokens, 12);
assert_eq!(response.usage.cache_creation_input_tokens, 321);
assert_eq!(response.usage.cache_read_input_tokens, 654);
assert_eq!(response.usage.output_tokens, 4);
}
#[tokio::test]
async fn given_empty_usage_object_when_send_message_parses_response_then_usage_defaults_to_zero() {
// given
let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
let body = concat!(
"{",
"\"id\":\"msg_empty_usage\",",
"\"type\":\"message\",",
"\"role\":\"assistant\",",
"\"content\":[{\"type\":\"text\",\"text\":\"Hello from Claude\"}],",
"\"model\":\"claude-3-7-sonnet-latest\",",
"\"stop_reason\":\"end_turn\",",
"\"stop_sequence\":null,",
"\"usage\":{}",
"}"
);
let server = spawn_server(
state,
vec![http_response("200 OK", "application/json", body)],
)
.await;
let client = AnthropicClient::new("test-key").with_base_url(server.base_url());
// when
let response = client
.send_message(&sample_request(false))
.await
.expect("response with empty usage object should still parse");
// then
assert_eq!(response.id, "msg_empty_usage");
assert_eq!(response.total_tokens(), 0);
assert_eq!(response.usage.input_tokens, 0);
assert_eq!(response.usage.cache_creation_input_tokens, 0);
assert_eq!(response.usage.cache_read_input_tokens, 0);
assert_eq!(response.usage.output_tokens, 0);
}
#[tokio::test]
#[allow(clippy::await_holding_lock)]
async fn stream_message_parses_sse_events_with_tool_use() {
let _guard = env_lock();
let temp_root = std::env::temp_dir().join(format!(
"api-stream-cache-{}-{}",
std::process::id(),
std::time::SystemTime::now()
.duration_since(std::time::UNIX_EPOCH)
.expect("time")
.as_nanos()
));
std::env::set_var("CLAUDE_CONFIG_HOME", &temp_root);
let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
let sse = concat!(
"event: message_start\n",
"data: {\"type\":\"message_start\",\"message\":{\"id\":\"msg_stream\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"claude-sonnet-4-6\",\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":8,\"output_tokens\":0}}}\n\n",
"data: {\"type\":\"message_start\",\"message\":{\"id\":\"msg_stream\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"claude-3-7-sonnet-latest\",\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":8,\"cache_creation_input_tokens\":13,\"cache_read_input_tokens\":21,\"output_tokens\":0}}}\n\n",
"event: content_block_start\n",
"data: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"tool_use\",\"id\":\"toolu_123\",\"name\":\"get_weather\",\"input\":{}}}\n\n",
"event: content_block_delta\n",
@@ -88,7 +335,7 @@ async fn stream_message_parses_sse_events_with_tool_use() {
"event: content_block_stop\n",
"data: {\"type\":\"content_block_stop\",\"index\":0}\n\n",
"event: message_delta\n",
"data: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"tool_use\",\"stop_sequence\":null},\"usage\":{\"input_tokens\":8,\"output_tokens\":1}}\n\n",
"data: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"tool_use\",\"stop_sequence\":null},\"usage\":{\"input_tokens\":8,\"cache_creation_input_tokens\":34,\"cache_read_input_tokens\":55,\"output_tokens\":1}}\n\n",
"event: message_stop\n",
"data: {\"type\":\"message_stop\"}\n\n",
"data: [DONE]\n\n"
@@ -106,7 +353,8 @@ async fn stream_message_parses_sse_events_with_tool_use() {
let client = ApiClient::new("test-key")
.with_auth_token(Some("proxy-token".to_string()))
.with_base_url(server.base_url());
.with_base_url(server.base_url())
.with_prompt_cache(PromptCache::new("stream-session"));
let mut stream = client
.stream_message(&sample_request(false))
.await
@@ -160,6 +408,20 @@ async fn stream_message_parses_sse_events_with_tool_use() {
let captured = state.lock().await;
let request = captured.first().expect("server should capture request");
assert!(request.body.contains("\"stream\":true"));
let cache_stats = client
.prompt_cache_stats()
.expect("prompt cache stats should exist");
assert_eq!(cache_stats.tracked_requests, 1);
assert_eq!(cache_stats.last_cache_creation_input_tokens, Some(34));
assert_eq!(cache_stats.last_cache_read_input_tokens, Some(55));
assert_eq!(
cache_stats.last_cache_source.as_deref(),
Some("api-response")
);
std::fs::remove_dir_all(temp_root).expect("cleanup temp root");
std::env::remove_var("CLAUDE_CONFIG_HOME");
}
#[tokio::test]
@@ -176,7 +438,7 @@ async fn retries_retryable_failures_before_succeeding() {
http_response(
"200 OK",
"application/json",
"{\"id\":\"msg_retry\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":\"Recovered\"}],\"model\":\"claude-sonnet-4-6\",\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"usage\":{\"input_tokens\":3,\"output_tokens\":2}}",
"{\"id\":\"msg_retry\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":\"Recovered\"}],\"model\":\"claude-3-7-sonnet-latest\",\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"usage\":{\"input_tokens\":3,\"output_tokens\":2}}",
),
],
)
@@ -196,28 +458,28 @@ async fn retries_retryable_failures_before_succeeding() {
}
#[tokio::test]
async fn provider_client_dispatches_api_requests() {
async fn provider_client_dispatches_anthropic_requests() {
let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
let server = spawn_server(
state.clone(),
vec![http_response(
"200 OK",
"application/json",
"{\"id\":\"msg_provider\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":\"Dispatched\"}],\"model\":\"claude-sonnet-4-6\",\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"usage\":{\"input_tokens\":3,\"output_tokens\":2}}",
"{\"id\":\"msg_provider\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":\"Dispatched\"}],\"model\":\"claude-3-7-sonnet-latest\",\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"usage\":{\"input_tokens\":3,\"output_tokens\":2}}",
)],
)
.await;
let client = ProviderClient::from_model_with_default_auth(
let client = ProviderClient::from_model_with_anthropic_auth(
"claude-sonnet-4-6",
Some(AuthSource::ApiKey("test-key".to_string())),
)
.expect("api provider client should be constructed");
.expect("anthropic provider client should be constructed");
let client = match client {
ProviderClient::ClawApi(client) => {
ProviderClient::ClawApi(client.with_base_url(server.base_url()))
ProviderClient::Anthropic(client) => {
ProviderClient::Anthropic(client.with_base_url(server.base_url()))
}
other => panic!("expected default provider, got {other:?}"),
other => panic!("expected anthropic provider, got {other:?}"),
};
let response = client
@@ -284,13 +546,194 @@ async fn surfaces_retry_exhaustion_for_persistent_retryable_errors() {
}
}
#[tokio::test]
async fn retries_multiple_retryable_failures_with_exponential_backoff_and_jitter() {
let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
let server = spawn_server(
state.clone(),
vec![
http_response(
"429 Too Many Requests",
"application/json",
"{\"type\":\"error\",\"error\":{\"type\":\"rate_limit_error\",\"message\":\"slow down\"}}",
),
http_response(
"500 Internal Server Error",
"application/json",
"{\"type\":\"error\",\"error\":{\"type\":\"api_error\",\"message\":\"boom\"}}",
),
http_response(
"503 Service Unavailable",
"application/json",
"{\"type\":\"error\",\"error\":{\"type\":\"overloaded_error\",\"message\":\"busy\"}}",
),
http_response(
"429 Too Many Requests",
"application/json",
"{\"type\":\"error\",\"error\":{\"type\":\"rate_limit_error\",\"message\":\"slow down again\"}}",
),
http_response(
"503 Service Unavailable",
"application/json",
"{\"type\":\"error\",\"error\":{\"type\":\"overloaded_error\",\"message\":\"still busy\"}}",
),
http_response(
"200 OK",
"application/json",
"{\"id\":\"msg_exp_retry\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":\"Recovered after 5\"}],\"model\":\"claude-3-7-sonnet-latest\",\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"usage\":{\"input_tokens\":3,\"output_tokens\":2}}",
),
],
)
.await;
let client = ApiClient::new("test-key")
.with_base_url(server.base_url())
.with_retry_policy(8, Duration::from_millis(1), Duration::from_millis(4));
let started_at = std::time::Instant::now();
let response = client
.send_message(&sample_request(false))
.await
.expect("8-retry policy should absorb 5 retryable failures");
let elapsed = started_at.elapsed();
assert_eq!(response.total_tokens(), 5);
assert_eq!(
state.lock().await.len(),
6,
"client should issue 1 original + 5 retry requests before the 200"
);
// Jittered sleeps are bounded by 2 * max_backoff per retry (base + jitter),
// so 5 sleeps fit comfortably below this upper bound with generous slack.
assert!(
elapsed < Duration::from_secs(5),
"retries should complete promptly, took {elapsed:?}"
);
}
#[tokio::test]
#[allow(clippy::await_holding_lock)]
async fn send_message_reuses_recent_completion_cache_entries() {
let _guard = env_lock();
let temp_root = std::env::temp_dir().join(format!(
"api-prompt-cache-{}-{}",
std::process::id(),
std::time::SystemTime::now()
.duration_since(std::time::UNIX_EPOCH)
.expect("time")
.as_nanos()
));
std::env::set_var("CLAUDE_CONFIG_HOME", &temp_root);
let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
let server = spawn_server(
state.clone(),
vec![http_response(
"200 OK",
"application/json",
"{\"id\":\"msg_cached\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":\"Cached once\"}],\"model\":\"claude-3-7-sonnet-latest\",\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"usage\":{\"input_tokens\":3,\"cache_creation_input_tokens\":5,\"cache_read_input_tokens\":4000,\"output_tokens\":2}}",
)],
)
.await;
let client = AnthropicClient::new("test-key")
.with_base_url(server.base_url())
.with_prompt_cache(PromptCache::new("integration-session"));
let first = client
.send_message(&sample_request(false))
.await
.expect("first request should succeed");
let second = client
.send_message(&sample_request(false))
.await
.expect("second request should reuse cache");
assert_eq!(first.content, second.content);
assert_eq!(state.lock().await.len(), 1);
let cache_stats = client
.prompt_cache_stats()
.expect("prompt cache stats should exist");
assert_eq!(cache_stats.completion_cache_hits, 1);
assert_eq!(cache_stats.completion_cache_misses, 1);
assert_eq!(cache_stats.completion_cache_writes, 1);
std::fs::remove_dir_all(temp_root).expect("cleanup temp root");
std::env::remove_var("CLAUDE_CONFIG_HOME");
}
#[tokio::test]
#[allow(clippy::await_holding_lock)]
async fn send_message_tracks_unexpected_prompt_cache_breaks() {
let _guard = env_lock();
let temp_root = std::env::temp_dir().join(format!(
"api-prompt-break-{}-{}",
std::process::id(),
std::time::SystemTime::now()
.duration_since(std::time::UNIX_EPOCH)
.expect("time")
.as_nanos()
));
std::env::set_var("CLAUDE_CONFIG_HOME", &temp_root);
let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
let server = spawn_server(
state,
vec![
http_response(
"200 OK",
"application/json",
"{\"id\":\"msg_one\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":\"One\"}],\"model\":\"claude-3-7-sonnet-latest\",\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"usage\":{\"input_tokens\":3,\"cache_creation_input_tokens\":5,\"cache_read_input_tokens\":6000,\"output_tokens\":2}}",
),
http_response(
"200 OK",
"application/json",
"{\"id\":\"msg_two\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":\"Two\"}],\"model\":\"claude-3-7-sonnet-latest\",\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"usage\":{\"input_tokens\":3,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":1000,\"output_tokens\":2}}",
),
],
)
.await;
let request = sample_request(false);
let client = AnthropicClient::new("test-key")
.with_base_url(server.base_url())
.with_prompt_cache(PromptCache::with_config(PromptCacheConfig {
session_id: "break-session".to_string(),
completion_ttl: Duration::from_secs(0),
..PromptCacheConfig::default()
}));
client
.send_message(&request)
.await
.expect("first response should succeed");
client
.send_message(&request)
.await
.expect("second response should succeed");
let cache_stats = client
.prompt_cache_stats()
.expect("prompt cache stats should exist");
assert_eq!(cache_stats.unexpected_cache_breaks, 1);
assert_eq!(
cache_stats.last_break_reason.as_deref(),
Some("cache read tokens dropped while prompt fingerprint remained stable")
);
std::fs::remove_dir_all(temp_root).expect("cleanup temp root");
std::env::remove_var("CLAUDE_CONFIG_HOME");
}
#[tokio::test]
#[ignore = "requires ANTHROPIC_API_KEY and network access"]
async fn live_stream_smoke_test() {
let client = ApiClient::from_env().expect("ANTHROPIC_API_KEY must be set");
let mut stream = client
.stream_message(&MessageRequest {
model: std::env::var("CLAW_MODEL").unwrap_or_else(|_| "claude-sonnet-4-6".to_string()),
model: std::env::var("ANTHROPIC_MODEL")
.unwrap_or_else(|_| "claude-3-7-sonnet-latest".to_string()),
max_tokens: 32,
messages: vec![InputMessage::user_text(
"Reply with exactly: hello from rust",
@@ -299,6 +742,7 @@ async fn live_stream_smoke_test() {
tools: None,
tool_choice: None,
stream: false,
..Default::default()
})
.await
.expect("live stream should start");
@@ -450,7 +894,7 @@ fn http_response_with_headers(
fn sample_request(stream: bool) -> MessageRequest {
MessageRequest {
model: "claude-sonnet-4-6".to_string(),
model: "claude-3-7-sonnet-latest".to_string(),
max_tokens: 64,
messages: vec![InputMessage {
role: "user".to_string(),
@@ -479,5 +923,6 @@ fn sample_request(stream: bool) -> MessageRequest {
}]),
tool_choice: Some(ToolChoice::Auto),
stream,
..Default::default()
}
}
+120 -4
View File
@@ -4,9 +4,10 @@ use std::sync::Arc;
use std::sync::{Mutex as StdMutex, OnceLock};
use api::{
ContentBlockDelta, ContentBlockDeltaEvent, ContentBlockStartEvent, ContentBlockStopEvent,
InputContentBlock, InputMessage, MessageRequest, OpenAiCompatClient, OpenAiCompatConfig,
OutputContentBlock, ProviderClient, StreamEvent, ToolChoice, ToolDefinition,
ApiError, ContentBlockDelta, ContentBlockDeltaEvent, ContentBlockStartEvent,
ContentBlockStopEvent, InputContentBlock, InputMessage, MessageDeltaEvent, MessageRequest,
OpenAiCompatClient, OpenAiCompatConfig, OutputContentBlock, ProviderClient, StreamEvent,
ToolChoice, ToolDefinition,
};
use serde_json::json;
use tokio::io::{AsyncReadExt, AsyncWriteExt};
@@ -62,6 +63,43 @@ async fn send_message_uses_openai_compatible_endpoint_and_auth() {
assert_eq!(body["tools"][0]["type"], json!("function"));
}
#[tokio::test]
async fn send_message_blocks_oversized_xai_requests_before_the_http_call() {
let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
let server = spawn_server(
state.clone(),
vec![http_response("200 OK", "application/json", "{}")],
)
.await;
let client = OpenAiCompatClient::new("xai-test-key", OpenAiCompatConfig::xai())
.with_base_url(server.base_url());
let error = client
.send_message(&MessageRequest {
model: "grok-3".to_string(),
max_tokens: 64_000,
messages: vec![InputMessage {
role: "user".to_string(),
content: vec![InputContentBlock::Text {
text: "x".repeat(300_000),
}],
}],
system: Some("Keep the answer short.".to_string()),
tools: None,
tool_choice: None,
stream: false,
..Default::default()
})
.await
.expect_err("oversized request should fail local context-window preflight");
assert!(matches!(error, ApiError::ContextWindowExceeded { .. }));
assert!(
state.lock().await.is_empty(),
"preflight failure should avoid any upstream HTTP request"
);
}
#[tokio::test]
async fn send_message_accepts_full_chat_completions_endpoint_override() {
let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
@@ -195,6 +233,83 @@ async fn stream_message_normalizes_text_and_multiple_tool_calls() {
assert!(request.body.contains("\"stream\":true"));
}
#[allow(clippy::await_holding_lock)]
#[tokio::test]
async fn openai_streaming_requests_opt_into_usage_chunks() {
let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
let sse = concat!(
"data: {\"id\":\"chatcmpl_openai_stream\",\"model\":\"gpt-5\",\"choices\":[{\"delta\":{\"content\":\"Hi\"}}]}\n\n",
"data: {\"id\":\"chatcmpl_openai_stream\",\"choices\":[{\"delta\":{},\"finish_reason\":\"stop\"}]}\n\n",
"data: {\"id\":\"chatcmpl_openai_stream\",\"choices\":[],\"usage\":{\"prompt_tokens\":9,\"completion_tokens\":4}}\n\n",
"data: [DONE]\n\n"
);
let server = spawn_server(
state.clone(),
vec![http_response_with_headers(
"200 OK",
"text/event-stream",
sse,
&[("x-request-id", "req_openai_stream")],
)],
)
.await;
let client = OpenAiCompatClient::new("openai-test-key", OpenAiCompatConfig::openai())
.with_base_url(server.base_url());
let mut stream = client
.stream_message(&sample_request(false))
.await
.expect("stream should start");
assert_eq!(stream.request_id(), Some("req_openai_stream"));
let mut events = Vec::new();
while let Some(event) = stream.next_event().await.expect("event should parse") {
events.push(event);
}
assert!(matches!(events[0], StreamEvent::MessageStart(_)));
assert!(matches!(
events[1],
StreamEvent::ContentBlockStart(ContentBlockStartEvent {
content_block: OutputContentBlock::Text { .. },
..
})
));
assert!(matches!(
events[2],
StreamEvent::ContentBlockDelta(ContentBlockDeltaEvent {
delta: ContentBlockDelta::TextDelta { .. },
..
})
));
assert!(matches!(
events[3],
StreamEvent::ContentBlockStop(ContentBlockStopEvent { index: 0 })
));
assert!(matches!(
events[4],
StreamEvent::MessageDelta(MessageDeltaEvent { .. })
));
assert!(matches!(events[5], StreamEvent::MessageStop(_)));
match &events[4] {
StreamEvent::MessageDelta(MessageDeltaEvent { usage, .. }) => {
assert_eq!(usage.input_tokens, 9);
assert_eq!(usage.output_tokens, 4);
}
other => panic!("expected message delta, got {other:?}"),
}
let captured = state.lock().await;
let request = captured.first().expect("captured request");
assert_eq!(request.path, "/chat/completions");
let body: serde_json::Value = serde_json::from_str(&request.body).expect("json body");
assert_eq!(body["stream"], json!(true));
assert_eq!(body["stream_options"], json!({"include_usage": true}));
}
#[allow(clippy::await_holding_lock)]
#[tokio::test]
async fn provider_client_dispatches_xai_requests_from_env() {
let _lock = env_lock();
@@ -382,6 +497,7 @@ fn sample_request(stream: bool) -> MessageRequest {
}]),
tool_choice: Some(ToolChoice::Auto),
stream,
..Default::default()
}
}
@@ -389,7 +505,7 @@ fn env_lock() -> std::sync::MutexGuard<'static, ()> {
static LOCK: OnceLock<StdMutex<()>> = OnceLock::new();
LOCK.get_or_init(|| StdMutex::new(()))
.lock()
.unwrap_or_else(|poisoned| poisoned.into_inner())
.unwrap_or_else(std::sync::PoisonError::into_inner)
}
struct ScopedEnvVar {
@@ -22,7 +22,9 @@ fn provider_client_reports_missing_xai_credentials_for_grok_models() {
.expect_err("grok requests without XAI_API_KEY should fail fast");
match error {
ApiError::MissingCredentials { provider, env_vars } => {
ApiError::MissingCredentials {
provider, env_vars, ..
} => {
assert_eq!(provider, "xAI");
assert_eq!(env_vars, &["XAI_API_KEY"]);
}
@@ -31,18 +33,18 @@ fn provider_client_reports_missing_xai_credentials_for_grok_models() {
}
#[test]
fn provider_client_uses_explicit_auth_without_env_lookup() {
fn provider_client_uses_explicit_anthropic_auth_without_env_lookup() {
let _lock = env_lock();
let _api_key = EnvVarGuard::set("ANTHROPIC_API_KEY", None);
let _auth_token = EnvVarGuard::set("ANTHROPIC_AUTH_TOKEN", None);
let _anthropic_api_key = EnvVarGuard::set("ANTHROPIC_API_KEY", None);
let _anthropic_auth_token = EnvVarGuard::set("ANTHROPIC_AUTH_TOKEN", None);
let client = ProviderClient::from_model_with_default_auth(
let client = ProviderClient::from_model_with_anthropic_auth(
"claude-sonnet-4-6",
Some(AuthSource::ApiKey("claw-test-key".to_string())),
Some(AuthSource::ApiKey("anthropic-test-key".to_string())),
)
.expect("explicit auth should avoid env lookup");
.expect("explicit anthropic auth should avoid env lookup");
assert_eq!(client.provider_kind(), ProviderKind::ClawApi);
assert_eq!(client.provider_kind(), ProviderKind::Anthropic);
}
#[test]
@@ -57,7 +59,7 @@ fn env_lock() -> std::sync::MutexGuard<'static, ()> {
static LOCK: OnceLock<Mutex<()>> = OnceLock::new();
LOCK.get_or_init(|| Mutex::new(()))
.lock()
.unwrap_or_else(|poisoned| poisoned.into_inner())
.unwrap_or_else(std::sync::PoisonError::into_inner)
}
struct EnvVarGuard {
+173
View File
@@ -0,0 +1,173 @@
use std::ffi::OsString;
use std::sync::{Mutex, OnceLock};
use api::{build_http_client_with, ProxyConfig};
fn env_lock() -> std::sync::MutexGuard<'static, ()> {
static LOCK: OnceLock<Mutex<()>> = OnceLock::new();
LOCK.get_or_init(|| Mutex::new(()))
.lock()
.unwrap_or_else(std::sync::PoisonError::into_inner)
}
struct EnvVarGuard {
key: &'static str,
original: Option<OsString>,
}
impl EnvVarGuard {
fn set(key: &'static str, value: Option<&str>) -> Self {
let original = std::env::var_os(key);
match value {
Some(value) => std::env::set_var(key, value),
None => std::env::remove_var(key),
}
Self { key, original }
}
}
impl Drop for EnvVarGuard {
fn drop(&mut self) {
match &self.original {
Some(value) => std::env::set_var(self.key, value),
None => std::env::remove_var(self.key),
}
}
}
#[test]
fn proxy_config_from_env_reads_uppercase_proxy_vars() {
// given
let _lock = env_lock();
let _http = EnvVarGuard::set("HTTP_PROXY", Some("http://proxy.corp:3128"));
let _https = EnvVarGuard::set("HTTPS_PROXY", Some("http://secure.corp:3129"));
let _no = EnvVarGuard::set("NO_PROXY", Some("localhost,127.0.0.1"));
let _http_lower = EnvVarGuard::set("http_proxy", None);
let _https_lower = EnvVarGuard::set("https_proxy", None);
let _no_lower = EnvVarGuard::set("no_proxy", None);
// when
let config = ProxyConfig::from_env();
// then
assert_eq!(config.http_proxy.as_deref(), Some("http://proxy.corp:3128"));
assert_eq!(
config.https_proxy.as_deref(),
Some("http://secure.corp:3129")
);
assert_eq!(config.no_proxy.as_deref(), Some("localhost,127.0.0.1"));
assert!(config.proxy_url.is_none());
assert!(!config.is_empty());
}
#[test]
fn proxy_config_from_env_reads_lowercase_proxy_vars() {
// given
let _lock = env_lock();
let _http = EnvVarGuard::set("HTTP_PROXY", None);
let _https = EnvVarGuard::set("HTTPS_PROXY", None);
let _no = EnvVarGuard::set("NO_PROXY", None);
let _http_lower = EnvVarGuard::set("http_proxy", Some("http://lower.corp:3128"));
let _https_lower = EnvVarGuard::set("https_proxy", Some("http://lower-secure.corp:3129"));
let _no_lower = EnvVarGuard::set("no_proxy", Some(".internal"));
// when
let config = ProxyConfig::from_env();
// then
assert_eq!(config.http_proxy.as_deref(), Some("http://lower.corp:3128"));
assert_eq!(
config.https_proxy.as_deref(),
Some("http://lower-secure.corp:3129")
);
assert_eq!(config.no_proxy.as_deref(), Some(".internal"));
assert!(!config.is_empty());
}
#[test]
fn proxy_config_from_env_is_empty_when_no_vars_set() {
// given
let _lock = env_lock();
let _http = EnvVarGuard::set("HTTP_PROXY", None);
let _https = EnvVarGuard::set("HTTPS_PROXY", None);
let _no = EnvVarGuard::set("NO_PROXY", None);
let _http_lower = EnvVarGuard::set("http_proxy", None);
let _https_lower = EnvVarGuard::set("https_proxy", None);
let _no_lower = EnvVarGuard::set("no_proxy", None);
// when
let config = ProxyConfig::from_env();
// then
assert!(config.is_empty());
assert!(config.http_proxy.is_none());
assert!(config.https_proxy.is_none());
assert!(config.no_proxy.is_none());
}
#[test]
fn proxy_config_from_env_treats_empty_values_as_unset() {
// given
let _lock = env_lock();
let _http = EnvVarGuard::set("HTTP_PROXY", Some(""));
let _https = EnvVarGuard::set("HTTPS_PROXY", Some(""));
let _http_lower = EnvVarGuard::set("http_proxy", Some(""));
let _https_lower = EnvVarGuard::set("https_proxy", Some(""));
let _no = EnvVarGuard::set("NO_PROXY", Some(""));
let _no_lower = EnvVarGuard::set("no_proxy", Some(""));
// when
let config = ProxyConfig::from_env();
// then
assert!(config.is_empty());
}
#[test]
fn build_client_with_env_proxy_config_succeeds() {
// given
let _lock = env_lock();
let _http = EnvVarGuard::set("HTTP_PROXY", Some("http://proxy.corp:3128"));
let _https = EnvVarGuard::set("HTTPS_PROXY", Some("http://secure.corp:3129"));
let _no = EnvVarGuard::set("NO_PROXY", Some("localhost"));
let _http_lower = EnvVarGuard::set("http_proxy", None);
let _https_lower = EnvVarGuard::set("https_proxy", None);
let _no_lower = EnvVarGuard::set("no_proxy", None);
let config = ProxyConfig::from_env();
// when
let result = build_http_client_with(&config);
// then
assert!(result.is_ok());
}
#[test]
fn build_client_with_proxy_url_config_succeeds() {
// given
let config = ProxyConfig::from_proxy_url("http://unified.corp:3128");
// when
let result = build_http_client_with(&config);
// then
assert!(result.is_ok());
}
#[test]
fn proxy_config_from_env_prefers_uppercase_over_lowercase() {
// given
let _lock = env_lock();
let _http_upper = EnvVarGuard::set("HTTP_PROXY", Some("http://upper.corp:3128"));
let _http_lower = EnvVarGuard::set("http_proxy", Some("http://lower.corp:3128"));
let _https = EnvVarGuard::set("HTTPS_PROXY", None);
let _https_lower = EnvVarGuard::set("https_proxy", None);
let _no = EnvVarGuard::set("NO_PROXY", None);
let _no_lower = EnvVarGuard::set("no_proxy", None);
// when
let config = ProxyConfig::from_env();
// then
assert_eq!(config.http_proxy.as_deref(), Some("http://upper.corp:3128"));
}