feat: API client with streaming, OAuth, and provider abstraction

rust/crates/api/Cargo.toml

@@ -0,0 +1,16 @@
+[package]
+name = "api"
+version.workspace = true
+edition.workspace = true
+license.workspace = true
+publish.workspace = true
+
+[dependencies]
+reqwest = { version = "0.12", default-features = false, features = ["json", "rustls-tls"] }
+runtime = { path = "../runtime" }
+serde = { version = "1", features = ["derive"] }
+serde_json.workspace = true
+tokio = { version = "1", features = ["io-util", "macros", "net", "rt-multi-thread", "time"] }
+
+[lints]
+workspace = true

rust/crates/api/src/client.rs

@@ -0,0 +1,141 @@
+use crate::error::ApiError;
+use crate::providers::claw_provider::{self, ClawApiClient, AuthSource};
+use crate::providers::openai_compat::{self, OpenAiCompatClient, OpenAiCompatConfig};
+use crate::providers::{self, Provider, 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
+}
+
+#[derive(Debug, Clone)]
+pub enum ProviderClient {
+    ClawApi(ClawApiClient),
+    Xai(OpenAiCompatClient),
+    OpenAi(OpenAiCompatClient),
+}
+
+impl ProviderClient {
+    pub fn from_model(model: &str) -> Result<Self, ApiError> {
+        Self::from_model_with_default_auth(model, None)
+    }
+
+    pub fn from_model_with_default_auth(
+        model: &str,
+        default_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::Xai => Ok(Self::Xai(OpenAiCompatClient::from_env(
+                OpenAiCompatConfig::xai(),
+            )?)),
+            ProviderKind::OpenAi => Ok(Self::OpenAi(OpenAiCompatClient::from_env(
+                OpenAiCompatConfig::openai(),
+            )?)),
+        }
+    }
+
+    #[must_use]
+    pub const fn provider_kind(&self) -> ProviderKind {
+        match self {
+            Self::ClawApi(_) => ProviderKind::ClawApi,
+            Self::Xai(_) => ProviderKind::Xai,
+            Self::OpenAi(_) => ProviderKind::OpenAi,
+        }
+    }
+
+    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,
+        }
+    }
+
+    pub async fn stream_message(
+        &self,
+        request: &MessageRequest,
+    ) -> Result<MessageStream, ApiError> {
+        match self {
+            Self::ClawApi(client) => stream_via_provider(client, request)
+                .await
+                .map(MessageStream::ClawApi),
+            Self::Xai(client) | Self::OpenAi(client) => stream_via_provider(client, request)
+                .await
+                .map(MessageStream::OpenAiCompat),
+        }
+    }
+}
+
+#[derive(Debug)]
+pub enum MessageStream {
+    ClawApi(claw_provider::MessageStream),
+    OpenAiCompat(openai_compat::MessageStream),
+}
+
+impl MessageStream {
+    #[must_use]
+    pub fn request_id(&self) -> Option<&str> {
+        match self {
+            Self::ClawApi(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::OpenAiCompat(stream) => stream.next_event().await,
+        }
+    }
+}
+
+pub use claw_provider::{
+    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()
+}
+
+#[must_use]
+pub fn read_xai_base_url() -> String {
+    openai_compat::read_base_url(OpenAiCompatConfig::xai())
+}
+
+#[cfg(test)]
+mod tests {
+    use crate::providers::{detect_provider_kind, resolve_model_alias, ProviderKind};
+
+    #[test]
+    fn resolves_existing_and_grok_aliases() {
+        assert_eq!(resolve_model_alias("opus"), "claude-opus-4-6");
+        assert_eq!(resolve_model_alias("grok"), "grok-3");
+        assert_eq!(resolve_model_alias("grok-mini"), "grok-3-mini");
+    }
+
+    #[test]
+    fn provider_detection_prefers_model_family() {
+        assert_eq!(detect_provider_kind("grok-3"), ProviderKind::Xai);
+        assert_eq!(
+            detect_provider_kind("claude-sonnet-4-6"),
+            ProviderKind::ClawApi
+        );
+    }
+}

rust/crates/api/src/error.rs

@@ -0,0 +1,135 @@
+use std::env::VarError;
+use std::fmt::{Display, Formatter};
+use std::time::Duration;
+
+#[derive(Debug)]
+pub enum ApiError {
+    MissingCredentials {
+        provider: &'static str,
+        env_vars: &'static [&'static str],
+    },
+    ExpiredOAuthToken,
+    Auth(String),
+    InvalidApiKeyEnv(VarError),
+    Http(reqwest::Error),
+    Io(std::io::Error),
+    Json(serde_json::Error),
+    Api {
+        status: reqwest::StatusCode,
+        error_type: Option<String>,
+        message: Option<String>,
+        body: String,
+        retryable: bool,
+    },
+    RetriesExhausted {
+        attempts: u32,
+        last_error: Box<ApiError>,
+    },
+    InvalidSseFrame(&'static str),
+    BackoffOverflow {
+        attempt: u32,
+        base_delay: Duration,
+    },
+}
+
+impl ApiError {
+    #[must_use]
+    pub const fn missing_credentials(
+        provider: &'static str,
+        env_vars: &'static [&'static str],
+    ) -> Self {
+        Self::MissingCredentials { provider, env_vars }
+    }
+
+    #[must_use]
+    pub fn is_retryable(&self) -> bool {
+        match self {
+            Self::Http(error) => error.is_connect() || error.is_timeout() || error.is_request(),
+            Self::Api { retryable, .. } => *retryable,
+            Self::RetriesExhausted { last_error, .. } => last_error.is_retryable(),
+            Self::MissingCredentials { .. }
+            | Self::ExpiredOAuthToken
+            | Self::Auth(_)
+            | Self::InvalidApiKeyEnv(_)
+            | Self::Io(_)
+            | Self::Json(_)
+            | Self::InvalidSseFrame(_)
+            | Self::BackoffOverflow { .. } => false,
+        }
+    }
+}
+
+impl Display for ApiError {
+    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
+        match self {
+            Self::MissingCredentials { provider, env_vars } => write!(
+                f,
+                "missing {provider} credentials; export {} before calling the {provider} API",
+                env_vars.join(" or ")
+            ),
+            Self::ExpiredOAuthToken => {
+                write!(
+                    f,
+                    "saved OAuth token is expired and no refresh token is available"
+                )
+            }
+            Self::Auth(message) => write!(f, "auth error: {message}"),
+            Self::InvalidApiKeyEnv(error) => {
+                write!(f, "failed to read credential environment variable: {error}")
+            }
+            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::Api {
+                status,
+                error_type,
+                message,
+                body,
+                ..
+            } => match (error_type, message) {
+                (Some(error_type), Some(message)) => {
+                    write!(f, "api returned {status} ({error_type}): {message}")
+                }
+                _ => write!(f, "api returned {status}: {body}"),
+            },
+            Self::RetriesExhausted {
+                attempts,
+                last_error,
+            } => write!(f, "api failed after {attempts} attempts: {last_error}"),
+            Self::InvalidSseFrame(message) => write!(f, "invalid sse frame: {message}"),
+            Self::BackoffOverflow {
+                attempt,
+                base_delay,
+            } => write!(
+                f,
+                "retry backoff overflowed on attempt {attempt} with base delay {base_delay:?}"
+            ),
+        }
+    }
+}
+
+impl std::error::Error for ApiError {}
+
+impl From<reqwest::Error> for ApiError {
+    fn from(value: reqwest::Error) -> Self {
+        Self::Http(value)
+    }
+}
+
+impl From<std::io::Error> for ApiError {
+    fn from(value: std::io::Error) -> Self {
+        Self::Io(value)
+    }
+}
+
+impl From<serde_json::Error> for ApiError {
+    fn from(value: serde_json::Error) -> Self {
+        Self::Json(value)
+    }
+}
+
+impl From<VarError> for ApiError {
+    fn from(value: VarError) -> Self {
+        Self::InvalidApiKeyEnv(value)
+    }
+}

rust/crates/api/src/lib.rs

@@ -0,0 +1,23 @@
+mod client;
+mod error;
+mod providers;
+mod sse;
+mod types;
+
+pub use client::{
+    oauth_token_is_expired, read_base_url, read_xai_base_url, resolve_saved_oauth_token,
+    resolve_startup_auth_source, MessageStream, OAuthTokenSet, ProviderClient,
+};
+pub use error::ApiError;
+pub use providers::claw_provider::{ClawApiClient, ClawApiClient as ApiClient, AuthSource};
+pub use providers::openai_compat::{OpenAiCompatClient, OpenAiCompatConfig};
+pub use providers::{
+    detect_provider_kind, max_tokens_for_model, resolve_model_alias, ProviderKind,
+};
+pub use sse::{parse_frame, SseParser};
+pub use types::{
+    ContentBlockDelta, ContentBlockDeltaEvent, ContentBlockStartEvent, ContentBlockStopEvent,
+    InputContentBlock, InputMessage, MessageDelta, MessageDeltaEvent, MessageRequest,
+    MessageResponse, MessageStartEvent, MessageStopEvent, OutputContentBlock, StreamEvent,
+    ToolChoice, ToolDefinition, ToolResultContentBlock, Usage,
+};

rust/crates/api/src/providers/mod.rs

@@ -0,0 +1,239 @@
+use std::future::Future;
+use std::pin::Pin;
+
+use crate::error::ApiError;
+use crate::types::{MessageRequest, MessageResponse};
+
+pub mod claw_provider;
+pub mod openai_compat;
+
+pub type ProviderFuture<'a, T> = Pin<Box<dyn Future<Output = Result<T, ApiError>> + Send + 'a>>;
+
+pub trait Provider {
+    type Stream;
+
+    fn send_message<'a>(
+        &'a self,
+        request: &'a MessageRequest,
+    ) -> ProviderFuture<'a, MessageResponse>;
+
+    fn stream_message<'a>(
+        &'a self,
+        request: &'a MessageRequest,
+    ) -> ProviderFuture<'a, Self::Stream>;
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum ProviderKind {
+    ClawApi,
+    Xai,
+    OpenAi,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub struct ProviderMetadata {
+    pub provider: ProviderKind,
+    pub auth_env: &'static str,
+    pub base_url_env: &'static str,
+    pub default_base_url: &'static str,
+}
+
+const MODEL_REGISTRY: &[(&str, ProviderMetadata)] = &[
+    (
+        "opus",
+        ProviderMetadata {
+            provider: ProviderKind::ClawApi,
+            auth_env: "ANTHROPIC_API_KEY",
+            base_url_env: "ANTHROPIC_BASE_URL",
+            default_base_url: claw_provider::DEFAULT_BASE_URL,
+        },
+    ),
+    (
+        "sonnet",
+        ProviderMetadata {
+            provider: ProviderKind::ClawApi,
+            auth_env: "ANTHROPIC_API_KEY",
+            base_url_env: "ANTHROPIC_BASE_URL",
+            default_base_url: claw_provider::DEFAULT_BASE_URL,
+        },
+    ),
+    (
+        "haiku",
+        ProviderMetadata {
+            provider: ProviderKind::ClawApi,
+            auth_env: "ANTHROPIC_API_KEY",
+            base_url_env: "ANTHROPIC_BASE_URL",
+            default_base_url: claw_provider::DEFAULT_BASE_URL,
+        },
+    ),
+    (
+        "claude-opus-4-6",
+        ProviderMetadata {
+            provider: ProviderKind::ClawApi,
+            auth_env: "ANTHROPIC_API_KEY",
+            base_url_env: "ANTHROPIC_BASE_URL",
+            default_base_url: claw_provider::DEFAULT_BASE_URL,
+        },
+    ),
+    (
+        "claude-sonnet-4-6",
+        ProviderMetadata {
+            provider: ProviderKind::ClawApi,
+            auth_env: "ANTHROPIC_API_KEY",
+            base_url_env: "ANTHROPIC_BASE_URL",
+            default_base_url: claw_provider::DEFAULT_BASE_URL,
+        },
+    ),
+    (
+        "claude-haiku-4-5-20251213",
+        ProviderMetadata {
+            provider: ProviderKind::ClawApi,
+            auth_env: "ANTHROPIC_API_KEY",
+            base_url_env: "ANTHROPIC_BASE_URL",
+            default_base_url: claw_provider::DEFAULT_BASE_URL,
+        },
+    ),
+    (
+        "grok",
+        ProviderMetadata {
+            provider: ProviderKind::Xai,
+            auth_env: "XAI_API_KEY",
+            base_url_env: "XAI_BASE_URL",
+            default_base_url: openai_compat::DEFAULT_XAI_BASE_URL,
+        },
+    ),
+    (
+        "grok-3",
+        ProviderMetadata {
+            provider: ProviderKind::Xai,
+            auth_env: "XAI_API_KEY",
+            base_url_env: "XAI_BASE_URL",
+            default_base_url: openai_compat::DEFAULT_XAI_BASE_URL,
+        },
+    ),
+    (
+        "grok-mini",
+        ProviderMetadata {
+            provider: ProviderKind::Xai,
+            auth_env: "XAI_API_KEY",
+            base_url_env: "XAI_BASE_URL",
+            default_base_url: openai_compat::DEFAULT_XAI_BASE_URL,
+        },
+    ),
+    (
+        "grok-3-mini",
+        ProviderMetadata {
+            provider: ProviderKind::Xai,
+            auth_env: "XAI_API_KEY",
+            base_url_env: "XAI_BASE_URL",
+            default_base_url: openai_compat::DEFAULT_XAI_BASE_URL,
+        },
+    ),
+    (
+        "grok-2",
+        ProviderMetadata {
+            provider: ProviderKind::Xai,
+            auth_env: "XAI_API_KEY",
+            base_url_env: "XAI_BASE_URL",
+            default_base_url: openai_compat::DEFAULT_XAI_BASE_URL,
+        },
+    ),
+];
+
+#[must_use]
+pub fn resolve_model_alias(model: &str) -> String {
+    let trimmed = model.trim();
+    let lower = trimmed.to_ascii_lowercase();
+    MODEL_REGISTRY
+        .iter()
+        .find_map(|(alias, metadata)| {
+            (*alias == lower).then_some(match metadata.provider {
+                ProviderKind::ClawApi => match *alias {
+                    "opus" => "claude-opus-4-6",
+                    "sonnet" => "claude-sonnet-4-6",
+                    "haiku" => "claude-haiku-4-5-20251213",
+                    _ => trimmed,
+                },
+                ProviderKind::Xai => match *alias {
+                    "grok" | "grok-3" => "grok-3",
+                    "grok-mini" | "grok-3-mini" => "grok-3-mini",
+                    "grok-2" => "grok-2",
+                    _ => trimmed,
+                },
+                ProviderKind::OpenAi => trimmed,
+            })
+        })
+        .map_or_else(|| trimmed.to_string(), ToOwned::to_owned)
+}
+
+#[must_use]
+pub fn metadata_for_model(model: &str) -> Option<ProviderMetadata> {
+    let canonical = resolve_model_alias(model);
+    let lower = canonical.to_ascii_lowercase();
+    if let Some((_, metadata)) = MODEL_REGISTRY.iter().find(|(alias, _)| *alias == lower) {
+        return Some(*metadata);
+    }
+    if lower.starts_with("grok") {
+        return Some(ProviderMetadata {
+            provider: ProviderKind::Xai,
+            auth_env: "XAI_API_KEY",
+            base_url_env: "XAI_BASE_URL",
+            default_base_url: openai_compat::DEFAULT_XAI_BASE_URL,
+        });
+    }
+    None
+}
+
+#[must_use]
+pub fn detect_provider_kind(model: &str) -> ProviderKind {
+    if let Some(metadata) = metadata_for_model(model) {
+        return metadata.provider;
+    }
+    if claw_provider::has_auth_from_env_or_saved().unwrap_or(false) {
+        return ProviderKind::ClawApi;
+    }
+    if openai_compat::has_api_key("OPENAI_API_KEY") {
+        return ProviderKind::OpenAi;
+    }
+    if openai_compat::has_api_key("XAI_API_KEY") {
+        return ProviderKind::Xai;
+    }
+    ProviderKind::ClawApi
+}
+
+#[must_use]
+pub fn max_tokens_for_model(model: &str) -> u32 {
+    let canonical = resolve_model_alias(model);
+    if canonical.contains("opus") {
+        32_000
+    } else {
+        64_000
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::{detect_provider_kind, max_tokens_for_model, resolve_model_alias, ProviderKind};
+
+    #[test]
+    fn resolves_grok_aliases() {
+        assert_eq!(resolve_model_alias("grok"), "grok-3");
+        assert_eq!(resolve_model_alias("grok-mini"), "grok-3-mini");
+        assert_eq!(resolve_model_alias("grok-2"), "grok-2");
+    }
+
+    #[test]
+    fn detects_provider_from_model_name_first() {
+        assert_eq!(detect_provider_kind("grok"), ProviderKind::Xai);
+        assert_eq!(
+            detect_provider_kind("claude-sonnet-4-6"),
+            ProviderKind::ClawApi
+        );
+    }
+
+    #[test]
+    fn keeps_existing_max_token_heuristic() {
+        assert_eq!(max_tokens_for_model("opus"), 32_000);
+        assert_eq!(max_tokens_for_model("grok-3"), 64_000);
+    }
+}

rust/crates/api/src/sse.rs

@@ -0,0 +1,279 @@
+use crate::error::ApiError;
+use crate::types::StreamEvent;
+
+#[derive(Debug, Default)]
+pub struct SseParser {
+    buffer: Vec<u8>,
+}
+
+impl SseParser {
+    #[must_use]
+    pub fn new() -> Self {
+        Self::default()
+    }
+
+    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)? {
+                events.push(event);
+            }
+        }
+
+        Ok(events)
+    }
+
+    pub fn finish(&mut self) -> Result<Vec<StreamEvent>, ApiError> {
+        if self.buffer.is_empty() {
+            return Ok(Vec::new());
+        }
+
+        let trailing = std::mem::take(&mut self.buffer);
+        match parse_frame(&String::from_utf8_lossy(&trailing))? {
+            Some(event) => Ok(vec![event]),
+            None => Ok(Vec::new()),
+        }
+    }
+
+    fn next_frame(&mut self) -> Option<String> {
+        let separator = self
+            .buffer
+            .windows(2)
+            .position(|window| window == b"\n\n")
+            .map(|position| (position, 2))
+            .or_else(|| {
+                self.buffer
+                    .windows(4)
+                    .position(|window| window == b"\r\n\r\n")
+                    .map(|position| (position, 4))
+            })?;
+
+        let (position, separator_len) = separator;
+        let frame = self
+            .buffer
+            .drain(..position + separator_len)
+            .collect::<Vec<_>>();
+        let frame_len = frame.len().saturating_sub(separator_len);
+        Some(String::from_utf8_lossy(&frame[..frame_len]).into_owned())
+    }
+}
+
+pub fn parse_frame(frame: &str) -> Result<Option<StreamEvent>, ApiError> {
+    let trimmed = frame.trim();
+    if trimmed.is_empty() {
+        return Ok(None);
+    }
+
+    let mut data_lines = Vec::new();
+    let mut event_name: Option<&str> = None;
+
+    for line in trimmed.lines() {
+        if line.starts_with(':') {
+            continue;
+        }
+        if let Some(name) = line.strip_prefix("event:") {
+            event_name = Some(name.trim());
+            continue;
+        }
+        if let Some(data) = line.strip_prefix("data:") {
+            data_lines.push(data.trim_start());
+        }
+    }
+
+    if matches!(event_name, Some("ping")) {
+        return Ok(None);
+    }
+
+    if data_lines.is_empty() {
+        return Ok(None);
+    }
+
+    let payload = data_lines.join("\n");
+    if payload == "[DONE]" {
+        return Ok(None);
+    }
+
+    serde_json::from_str::<StreamEvent>(&payload)
+        .map(Some)
+        .map_err(ApiError::from)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::{parse_frame, SseParser};
+    use crate::types::{ContentBlockDelta, MessageDelta, OutputContentBlock, StreamEvent, Usage};
+
+    #[test]
+    fn parses_single_frame() {
+        let frame = concat!(
+            "event: content_block_start\n",
+            "data: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"text\",\"text\":\"Hi\"}}\n\n"
+        );
+
+        let event = parse_frame(frame).expect("frame should parse");
+        assert_eq!(
+            event,
+            Some(StreamEvent::ContentBlockStart(
+                crate::types::ContentBlockStartEvent {
+                    index: 0,
+                    content_block: OutputContentBlock::Text {
+                        text: "Hi".to_string(),
+                    },
+                },
+            ))
+        );
+    }
+
+    #[test]
+    fn parses_chunked_stream() {
+        let mut parser = SseParser::new();
+        let first = b"event: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"Hel";
+        let second = b"lo\"}}\n\n";
+
+        assert!(parser
+            .push(first)
+            .expect("first chunk should buffer")
+            .is_empty());
+        let events = parser.push(second).expect("second chunk should parse");
+
+        assert_eq!(
+            events,
+            vec![StreamEvent::ContentBlockDelta(
+                crate::types::ContentBlockDeltaEvent {
+                    index: 0,
+                    delta: ContentBlockDelta::TextDelta {
+                        text: "Hello".to_string(),
+                    },
+                }
+            )]
+        );
+    }
+
+    #[test]
+    fn ignores_ping_and_done() {
+        let mut parser = SseParser::new();
+        let payload = concat!(
+            ": keepalive\n",
+            "event: ping\n",
+            "data: {\"type\":\"ping\"}\n\n",
+            "event: message_delta\n",
+            "data: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"tool_use\",\"stop_sequence\":null},\"usage\":{\"input_tokens\":1,\"output_tokens\":2}}\n\n",
+            "event: message_stop\n",
+            "data: {\"type\":\"message_stop\"}\n\n",
+            "data: [DONE]\n\n"
+        );
+
+        let events = parser
+            .push(payload.as_bytes())
+            .expect("parser should succeed");
+        assert_eq!(
+            events,
+            vec![
+                StreamEvent::MessageDelta(crate::types::MessageDeltaEvent {
+                    delta: MessageDelta {
+                        stop_reason: Some("tool_use".to_string()),
+                        stop_sequence: None,
+                    },
+                    usage: Usage {
+                        input_tokens: 1,
+                        cache_creation_input_tokens: 0,
+                        cache_read_input_tokens: 0,
+                        output_tokens: 2,
+                    },
+                }),
+                StreamEvent::MessageStop(crate::types::MessageStopEvent {}),
+            ]
+        );
+    }
+
+    #[test]
+    fn ignores_data_less_event_frames() {
+        let frame = "event: ping\n\n";
+        let event = parse_frame(frame).expect("frame without data should be ignored");
+        assert_eq!(event, None);
+    }
+
+    #[test]
+    fn parses_split_json_across_data_lines() {
+        let frame = concat!(
+            "event: content_block_delta\n",
+            "data: {\"type\":\"content_block_delta\",\"index\":0,\n",
+            "data: \"delta\":{\"type\":\"text_delta\",\"text\":\"Hello\"}}\n\n"
+        );
+
+        let event = parse_frame(frame).expect("frame should parse");
+        assert_eq!(
+            event,
+            Some(StreamEvent::ContentBlockDelta(
+                crate::types::ContentBlockDeltaEvent {
+                    index: 0,
+                    delta: ContentBlockDelta::TextDelta {
+                        text: "Hello".to_string(),
+                    },
+                }
+            ))
+        );
+    }
+
+    #[test]
+    fn parses_thinking_content_block_start() {
+        let frame = concat!(
+            "event: content_block_start\n",
+            "data: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"thinking\",\"thinking\":\"\",\"signature\":null}}\n\n"
+        );
+
+        let event = parse_frame(frame).expect("frame should parse");
+        assert_eq!(
+            event,
+            Some(StreamEvent::ContentBlockStart(
+                crate::types::ContentBlockStartEvent {
+                    index: 0,
+                    content_block: OutputContentBlock::Thinking {
+                        thinking: String::new(),
+                        signature: None,
+                    },
+                },
+            ))
+        );
+    }
+
+    #[test]
+    fn parses_thinking_related_deltas() {
+        let thinking = concat!(
+            "event: content_block_delta\n",
+            "data: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"step 1\"}}\n\n"
+        );
+        let signature = concat!(
+            "event: content_block_delta\n",
+            "data: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"signature_delta\",\"signature\":\"sig_123\"}}\n\n"
+        );
+
+        let thinking_event = parse_frame(thinking).expect("thinking delta should parse");
+        let signature_event = parse_frame(signature).expect("signature delta should parse");
+
+        assert_eq!(
+            thinking_event,
+            Some(StreamEvent::ContentBlockDelta(
+                crate::types::ContentBlockDeltaEvent {
+                    index: 0,
+                    delta: ContentBlockDelta::ThinkingDelta {
+                        thinking: "step 1".to_string(),
+                    },
+                }
+            ))
+        );
+        assert_eq!(
+            signature_event,
+            Some(StreamEvent::ContentBlockDelta(
+                crate::types::ContentBlockDeltaEvent {
+                    index: 0,
+                    delta: ContentBlockDelta::SignatureDelta {
+                        signature: "sig_123".to_string(),
+                    },
+                }
+            ))
+        );
+    }
+}

rust/crates/api/src/types.rs

@@ -0,0 +1,223 @@
+use serde::{Deserialize, Serialize};
+use serde_json::Value;
+
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
+pub struct MessageRequest {
+    pub model: String,
+    pub max_tokens: u32,
+    pub messages: Vec<InputMessage>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub system: Option<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub tools: Option<Vec<ToolDefinition>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub tool_choice: Option<ToolChoice>,
+    #[serde(default, skip_serializing_if = "std::ops::Not::not")]
+    pub stream: bool,
+}
+
+impl MessageRequest {
+    #[must_use]
+    pub fn with_streaming(mut self) -> Self {
+        self.stream = true;
+        self
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
+pub struct InputMessage {
+    pub role: String,
+    pub content: Vec<InputContentBlock>,
+}
+
+impl InputMessage {
+    #[must_use]
+    pub fn user_text(text: impl Into<String>) -> Self {
+        Self {
+            role: "user".to_string(),
+            content: vec![InputContentBlock::Text { text: text.into() }],
+        }
+    }
+
+    #[must_use]
+    pub fn user_tool_result(
+        tool_use_id: impl Into<String>,
+        content: impl Into<String>,
+        is_error: bool,
+    ) -> Self {
+        Self {
+            role: "user".to_string(),
+            content: vec![InputContentBlock::ToolResult {
+                tool_use_id: tool_use_id.into(),
+                content: vec![ToolResultContentBlock::Text {
+                    text: content.into(),
+                }],
+                is_error,
+            }],
+        }
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
+#[serde(tag = "type", rename_all = "snake_case")]
+pub enum InputContentBlock {
+    Text {
+        text: String,
+    },
+    ToolUse {
+        id: String,
+        name: String,
+        input: Value,
+    },
+    ToolResult {
+        tool_use_id: String,
+        content: Vec<ToolResultContentBlock>,
+        #[serde(default, skip_serializing_if = "std::ops::Not::not")]
+        is_error: bool,
+    },
+}
+
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
+#[serde(tag = "type", rename_all = "snake_case")]
+pub enum ToolResultContentBlock {
+    Text { text: String },
+    Json { value: Value },
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct ToolDefinition {
+    pub name: String,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub description: Option<String>,
+    pub input_schema: Value,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+#[serde(tag = "type", rename_all = "snake_case")]
+pub enum ToolChoice {
+    Auto,
+    Any,
+    Tool { name: String },
+}
+
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
+pub struct MessageResponse {
+    pub id: String,
+    #[serde(rename = "type")]
+    pub kind: String,
+    pub role: String,
+    pub content: Vec<OutputContentBlock>,
+    pub model: String,
+    #[serde(default)]
+    pub stop_reason: Option<String>,
+    #[serde(default)]
+    pub stop_sequence: Option<String>,
+    pub usage: Usage,
+    #[serde(default)]
+    pub request_id: Option<String>,
+}
+
+impl MessageResponse {
+    #[must_use]
+    pub fn total_tokens(&self) -> u32 {
+        self.usage.total_tokens()
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
+#[serde(tag = "type", rename_all = "snake_case")]
+pub enum OutputContentBlock {
+    Text {
+        text: String,
+    },
+    ToolUse {
+        id: String,
+        name: String,
+        input: Value,
+    },
+    Thinking {
+        #[serde(default)]
+        thinking: String,
+        #[serde(default, skip_serializing_if = "Option::is_none")]
+        signature: Option<String>,
+    },
+    RedactedThinking {
+        data: Value,
+    },
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct Usage {
+    pub input_tokens: u32,
+    #[serde(default)]
+    pub cache_creation_input_tokens: u32,
+    #[serde(default)]
+    pub cache_read_input_tokens: u32,
+    pub output_tokens: u32,
+}
+
+impl Usage {
+    #[must_use]
+    pub const fn total_tokens(&self) -> u32 {
+        self.input_tokens + self.output_tokens
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
+pub struct MessageStartEvent {
+    pub message: MessageResponse,
+}
+
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
+pub struct MessageDeltaEvent {
+    pub delta: MessageDelta,
+    pub usage: Usage,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct MessageDelta {
+    #[serde(default)]
+    pub stop_reason: Option<String>,
+    #[serde(default)]
+    pub stop_sequence: Option<String>,
+}
+
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
+pub struct ContentBlockStartEvent {
+    pub index: u32,
+    pub content_block: OutputContentBlock,
+}
+
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
+pub struct ContentBlockDeltaEvent {
+    pub index: u32,
+    pub delta: ContentBlockDelta,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+#[serde(tag = "type", rename_all = "snake_case")]
+pub enum ContentBlockDelta {
+    TextDelta { text: String },
+    InputJsonDelta { partial_json: String },
+    ThinkingDelta { thinking: String },
+    SignatureDelta { signature: String },
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct ContentBlockStopEvent {
+    pub index: u32,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct MessageStopEvent {}
+
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
+#[serde(tag = "type", rename_all = "snake_case")]
+pub enum StreamEvent {
+    MessageStart(MessageStartEvent),
+    MessageDelta(MessageDeltaEvent),
+    ContentBlockStart(ContentBlockStartEvent),
+    ContentBlockDelta(ContentBlockDeltaEvent),
+    ContentBlockStop(ContentBlockStopEvent),
+    MessageStop(MessageStopEvent),
+}

rust/crates/api/tests/client_integration.rs

@@ -0,0 +1,484 @@
+use std::collections::HashMap;
+use std::sync::Arc;
+use std::time::Duration;
+
+use api::{
+    ApiClient, ApiError, AuthSource, ContentBlockDelta, ContentBlockDeltaEvent,
+    ContentBlockStartEvent, InputContentBlock, InputMessage, MessageDeltaEvent, MessageRequest,
+    OutputContentBlock, ProviderClient, StreamEvent, ToolChoice, ToolDefinition,
+};
+use serde_json::json;
+use tokio::io::{AsyncReadExt, AsyncWriteExt};
+use tokio::net::TcpListener;
+use tokio::sync::Mutex;
+
+#[tokio::test]
+async fn send_message_posts_json_and_parses_response() {
+    let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
+    let body = concat!(
+        "{",
+        "\"id\":\"msg_test\",",
+        "\"type\":\"message\",",
+        "\"role\":\"assistant\",",
+        "\"content\":[{\"type\":\"text\",\"text\":\"Hello from Claw\"}],",
+        "\"model\":\"claude-sonnet-4-6\",",
+        "\"stop_reason\":\"end_turn\",",
+        "\"stop_sequence\":null,",
+        "\"usage\":{\"input_tokens\":12,\"output_tokens\":4},",
+        "\"request_id\":\"req_body_123\"",
+        "}"
+    );
+    let server = spawn_server(
+        state.clone(),
+        vec![http_response("200 OK", "application/json", body)],
+    )
+    .await;
+
+    let client = ApiClient::new("test-key")
+        .with_auth_token(Some("proxy-token".to_string()))
+        .with_base_url(server.base_url());
+    let response = client
+        .send_message(&sample_request(false))
+        .await
+        .expect("request should succeed");
+
+    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.content,
+        vec![OutputContentBlock::Text {
+            text: "Hello from Claw".to_string(),
+        }]
+    );
+
+    let captured = state.lock().await;
+    let request = captured.first().expect("server should capture request");
+    assert_eq!(request.method, "POST");
+    assert_eq!(request.path, "/v1/messages");
+    assert_eq!(
+        request.headers.get("x-api-key").map(String::as_str),
+        Some("test-key")
+    );
+    assert_eq!(
+        request.headers.get("authorization").map(String::as_str),
+        Some("Bearer proxy-token")
+    );
+    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")
+    );
+    assert!(body.get("stream").is_none());
+    assert_eq!(body["tools"][0]["name"], json!("get_weather"));
+    assert_eq!(body["tool_choice"]["type"], json!("auto"));
+}
+
+#[tokio::test]
+async fn stream_message_parses_sse_events_with_tool_use() {
+    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",
+        "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",
+        "data: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"{\\\"city\\\":\\\"Paris\\\"}\"}}\n\n",
+        "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",
+        "event: message_stop\n",
+        "data: {\"type\":\"message_stop\"}\n\n",
+        "data: [DONE]\n\n"
+    );
+    let server = spawn_server(
+        state.clone(),
+        vec![http_response_with_headers(
+            "200 OK",
+            "text/event-stream",
+            sse,
+            &[("request-id", "req_stream_456")],
+        )],
+    )
+    .await;
+
+    let client = ApiClient::new("test-key")
+        .with_auth_token(Some("proxy-token".to_string()))
+        .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_stream_456"));
+
+    let mut events = Vec::new();
+    while let Some(event) = stream
+        .next_event()
+        .await
+        .expect("stream event should parse")
+    {
+        events.push(event);
+    }
+
+    assert_eq!(events.len(), 6);
+    assert!(matches!(events[0], StreamEvent::MessageStart(_)));
+    assert!(matches!(
+        events[1],
+        StreamEvent::ContentBlockStart(ContentBlockStartEvent {
+            content_block: OutputContentBlock::ToolUse { .. },
+            ..
+        })
+    ));
+    assert!(matches!(
+        events[2],
+        StreamEvent::ContentBlockDelta(ContentBlockDeltaEvent {
+            delta: ContentBlockDelta::InputJsonDelta { .. },
+            ..
+        })
+    ));
+    assert!(matches!(events[3], StreamEvent::ContentBlockStop(_)));
+    assert!(matches!(
+        events[4],
+        StreamEvent::MessageDelta(MessageDeltaEvent { .. })
+    ));
+    assert!(matches!(events[5], StreamEvent::MessageStop(_)));
+
+    match &events[1] {
+        StreamEvent::ContentBlockStart(ContentBlockStartEvent {
+            content_block: OutputContentBlock::ToolUse { name, input, .. },
+            ..
+        }) => {
+            assert_eq!(name, "get_weather");
+            assert_eq!(input, &json!({}));
+        }
+        other => panic!("expected tool_use block, got {other:?}"),
+    }
+
+    let captured = state.lock().await;
+    let request = captured.first().expect("server should capture request");
+    assert!(request.body.contains("\"stream\":true"));
+}
+
+#[tokio::test]
+async fn retries_retryable_failures_before_succeeding() {
+    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(
+                "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}}",
+            ),
+        ],
+    )
+    .await;
+
+    let client = ApiClient::new("test-key")
+        .with_base_url(server.base_url())
+        .with_retry_policy(2, Duration::from_millis(1), Duration::from_millis(2));
+
+    let response = client
+        .send_message(&sample_request(false))
+        .await
+        .expect("retry should eventually succeed");
+
+    assert_eq!(response.total_tokens(), 5);
+    assert_eq!(state.lock().await.len(), 2);
+}
+
+#[tokio::test]
+async fn provider_client_dispatches_api_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}}",
+        )],
+    )
+    .await;
+
+    let client = ProviderClient::from_model_with_default_auth(
+        "claude-sonnet-4-6",
+        Some(AuthSource::ApiKey("test-key".to_string())),
+    )
+    .expect("api provider client should be constructed");
+    let client = match client {
+        ProviderClient::ClawApi(client) => {
+            ProviderClient::ClawApi(client.with_base_url(server.base_url()))
+        }
+        other => panic!("expected default provider, got {other:?}"),
+    };
+
+    let response = client
+        .send_message(&sample_request(false))
+        .await
+        .expect("provider-dispatched request should succeed");
+
+    assert_eq!(response.total_tokens(), 5);
+
+    let captured = state.lock().await;
+    let request = captured.first().expect("server should capture request");
+    assert_eq!(request.path, "/v1/messages");
+    assert_eq!(
+        request.headers.get("x-api-key").map(String::as_str),
+        Some("test-key")
+    );
+}
+
+#[tokio::test]
+async fn surfaces_retry_exhaustion_for_persistent_retryable_errors() {
+    let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
+    let server = spawn_server(
+        state.clone(),
+        vec![
+            http_response(
+                "503 Service Unavailable",
+                "application/json",
+                "{\"type\":\"error\",\"error\":{\"type\":\"overloaded_error\",\"message\":\"busy\"}}",
+            ),
+            http_response(
+                "503 Service Unavailable",
+                "application/json",
+                "{\"type\":\"error\",\"error\":{\"type\":\"overloaded_error\",\"message\":\"still busy\"}}",
+            ),
+        ],
+    )
+    .await;
+
+    let client = ApiClient::new("test-key")
+        .with_base_url(server.base_url())
+        .with_retry_policy(1, Duration::from_millis(1), Duration::from_millis(2));
+
+    let error = client
+        .send_message(&sample_request(false))
+        .await
+        .expect_err("persistent 503 should fail");
+
+    match error {
+        ApiError::RetriesExhausted {
+            attempts,
+            last_error,
+        } => {
+            assert_eq!(attempts, 2);
+            assert!(matches!(
+                *last_error,
+                ApiError::Api {
+                    status: reqwest::StatusCode::SERVICE_UNAVAILABLE,
+                    retryable: true,
+                    ..
+                }
+            ));
+        }
+        other => panic!("expected retries exhausted, got {other:?}"),
+    }
+}
+
+#[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()),
+            max_tokens: 32,
+            messages: vec![InputMessage::user_text(
+                "Reply with exactly: hello from rust",
+            )],
+            system: None,
+            tools: None,
+            tool_choice: None,
+            stream: false,
+        })
+        .await
+        .expect("live stream should start");
+
+    while let Some(_event) = stream
+        .next_event()
+        .await
+        .expect("live stream should yield events")
+    {}
+}
+
+#[derive(Debug, Clone, PartialEq, Eq)]
+struct CapturedRequest {
+    method: String,
+    path: String,
+    headers: HashMap<String, String>,
+    body: String,
+}
+
+struct TestServer {
+    base_url: String,
+    join_handle: tokio::task::JoinHandle<()>,
+}
+
+impl TestServer {
+    fn base_url(&self) -> String {
+        self.base_url.clone()
+    }
+}
+
+impl Drop for TestServer {
+    fn drop(&mut self) {
+        self.join_handle.abort();
+    }
+}
+
+async fn spawn_server(
+    state: Arc<Mutex<Vec<CapturedRequest>>>,
+    responses: Vec<String>,
+) -> TestServer {
+    let listener = TcpListener::bind("127.0.0.1:0")
+        .await
+        .expect("listener should bind");
+    let address = listener
+        .local_addr()
+        .expect("listener should have local addr");
+    let join_handle = tokio::spawn(async move {
+        for response in responses {
+            let (mut socket, _) = listener.accept().await.expect("server should accept");
+            let mut buffer = Vec::new();
+            let mut header_end = None;
+
+            loop {
+                let mut chunk = [0_u8; 1024];
+                let read = socket
+                    .read(&mut chunk)
+                    .await
+                    .expect("request read should succeed");
+                if read == 0 {
+                    break;
+                }
+                buffer.extend_from_slice(&chunk[..read]);
+                if let Some(position) = find_header_end(&buffer) {
+                    header_end = Some(position);
+                    break;
+                }
+            }
+
+            let header_end = header_end.expect("request should include headers");
+            let (header_bytes, remaining) = buffer.split_at(header_end);
+            let header_text =
+                String::from_utf8(header_bytes.to_vec()).expect("headers should be utf8");
+            let mut lines = header_text.split("\r\n");
+            let request_line = lines.next().expect("request line should exist");
+            let mut parts = request_line.split_whitespace();
+            let method = parts.next().expect("method should exist").to_string();
+            let path = parts.next().expect("path should exist").to_string();
+            let mut headers = HashMap::new();
+            let mut content_length = 0_usize;
+            for line in lines {
+                if line.is_empty() {
+                    continue;
+                }
+                let (name, value) = line.split_once(':').expect("header should have colon");
+                let value = value.trim().to_string();
+                if name.eq_ignore_ascii_case("content-length") {
+                    content_length = value.parse().expect("content length should parse");
+                }
+                headers.insert(name.to_ascii_lowercase(), value);
+            }
+
+            let mut body = remaining[4..].to_vec();
+            while body.len() < content_length {
+                let mut chunk = vec![0_u8; content_length - body.len()];
+                let read = socket
+                    .read(&mut chunk)
+                    .await
+                    .expect("body read should succeed");
+                if read == 0 {
+                    break;
+                }
+                body.extend_from_slice(&chunk[..read]);
+            }
+
+            state.lock().await.push(CapturedRequest {
+                method,
+                path,
+                headers,
+                body: String::from_utf8(body).expect("body should be utf8"),
+            });
+
+            socket
+                .write_all(response.as_bytes())
+                .await
+                .expect("response write should succeed");
+        }
+    });
+
+    TestServer {
+        base_url: format!("http://{address}"),
+        join_handle,
+    }
+}
+
+fn find_header_end(bytes: &[u8]) -> Option<usize> {
+    bytes.windows(4).position(|window| window == b"\r\n\r\n")
+}
+
+fn http_response(status: &str, content_type: &str, body: &str) -> String {
+    http_response_with_headers(status, content_type, body, &[])
+}
+
+fn http_response_with_headers(
+    status: &str,
+    content_type: &str,
+    body: &str,
+    headers: &[(&str, &str)],
+) -> String {
+    let mut extra_headers = String::new();
+    for (name, value) in headers {
+        use std::fmt::Write as _;
+        write!(&mut extra_headers, "{name}: {value}\r\n").expect("header write should succeed");
+    }
+    format!(
+        "HTTP/1.1 {status}\r\ncontent-type: {content_type}\r\n{extra_headers}content-length: {}\r\nconnection: close\r\n\r\n{body}",
+        body.len()
+    )
+}
+
+fn sample_request(stream: bool) -> MessageRequest {
+    MessageRequest {
+        model: "claude-sonnet-4-6".to_string(),
+        max_tokens: 64,
+        messages: vec![InputMessage {
+            role: "user".to_string(),
+            content: vec![
+                InputContentBlock::Text {
+                    text: "Say hello".to_string(),
+                },
+                InputContentBlock::ToolResult {
+                    tool_use_id: "toolu_prev".to_string(),
+                    content: vec![api::ToolResultContentBlock::Json {
+                        value: json!({"forecast": "sunny"}),
+                    }],
+                    is_error: false,
+                },
+            ],
+        }],
+        system: Some("Use tools when needed".to_string()),
+        tools: Some(vec![ToolDefinition {
+            name: "get_weather".to_string(),
+            description: Some("Fetches the weather".to_string()),
+            input_schema: json!({
+                "type": "object",
+                "properties": {"city": {"type": "string"}},
+                "required": ["city"]
+            }),
+        }]),
+        tool_choice: Some(ToolChoice::Auto),
+        stream,
+    }
+}

rust/crates/api/tests/openai_compat_integration.rs

@@ -0,0 +1,415 @@
+use std::collections::HashMap;
+use std::ffi::OsString;
+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,
+};
+use serde_json::json;
+use tokio::io::{AsyncReadExt, AsyncWriteExt};
+use tokio::net::TcpListener;
+use tokio::sync::Mutex;
+
+#[tokio::test]
+async fn send_message_uses_openai_compatible_endpoint_and_auth() {
+    let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
+    let body = concat!(
+        "{",
+        "\"id\":\"chatcmpl_test\",",
+        "\"model\":\"grok-3\",",
+        "\"choices\":[{",
+        "\"message\":{\"role\":\"assistant\",\"content\":\"Hello from Grok\",\"tool_calls\":[]},",
+        "\"finish_reason\":\"stop\"",
+        "}],",
+        "\"usage\":{\"prompt_tokens\":11,\"completion_tokens\":5}",
+        "}"
+    );
+    let server = spawn_server(
+        state.clone(),
+        vec![http_response("200 OK", "application/json", body)],
+    )
+    .await;
+
+    let client = OpenAiCompatClient::new("xai-test-key", OpenAiCompatConfig::xai())
+        .with_base_url(server.base_url());
+    let response = client
+        .send_message(&sample_request(false))
+        .await
+        .expect("request should succeed");
+
+    assert_eq!(response.model, "grok-3");
+    assert_eq!(response.total_tokens(), 16);
+    assert_eq!(
+        response.content,
+        vec![OutputContentBlock::Text {
+            text: "Hello from Grok".to_string(),
+        }]
+    );
+
+    let captured = state.lock().await;
+    let request = captured.first().expect("server should capture request");
+    assert_eq!(request.path, "/chat/completions");
+    assert_eq!(
+        request.headers.get("authorization").map(String::as_str),
+        Some("Bearer xai-test-key")
+    );
+    let body: serde_json::Value = serde_json::from_str(&request.body).expect("json body");
+    assert_eq!(body["model"], json!("grok-3"));
+    assert_eq!(body["messages"][0]["role"], json!("system"));
+    assert_eq!(body["tools"][0]["type"], json!("function"));
+}
+
+#[tokio::test]
+async fn send_message_accepts_full_chat_completions_endpoint_override() {
+    let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
+    let body = concat!(
+        "{",
+        "\"id\":\"chatcmpl_full_endpoint\",",
+        "\"model\":\"grok-3\",",
+        "\"choices\":[{",
+        "\"message\":{\"role\":\"assistant\",\"content\":\"Endpoint override works\",\"tool_calls\":[]},",
+        "\"finish_reason\":\"stop\"",
+        "}],",
+        "\"usage\":{\"prompt_tokens\":7,\"completion_tokens\":3}",
+        "}"
+    );
+    let server = spawn_server(
+        state.clone(),
+        vec![http_response("200 OK", "application/json", body)],
+    )
+    .await;
+
+    let endpoint_url = format!("{}/chat/completions", server.base_url());
+    let client = OpenAiCompatClient::new("xai-test-key", OpenAiCompatConfig::xai())
+        .with_base_url(endpoint_url);
+    let response = client
+        .send_message(&sample_request(false))
+        .await
+        .expect("request should succeed");
+
+    assert_eq!(response.total_tokens(), 10);
+
+    let captured = state.lock().await;
+    let request = captured.first().expect("server should capture request");
+    assert_eq!(request.path, "/chat/completions");
+}
+
+#[tokio::test]
+async fn stream_message_normalizes_text_and_multiple_tool_calls() {
+    let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
+    let sse = concat!(
+        "data: {\"id\":\"chatcmpl_stream\",\"model\":\"grok-3\",\"choices\":[{\"delta\":{\"content\":\"Hello\"}}]}\n\n",
+        "data: {\"id\":\"chatcmpl_stream\",\"choices\":[{\"delta\":{\"tool_calls\":[{\"index\":0,\"id\":\"call_1\",\"function\":{\"name\":\"weather\",\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\"}},{\"index\":1,\"id\":\"call_2\",\"function\":{\"name\":\"clock\",\"arguments\":\"{\\\"zone\\\":\\\"UTC\\\"}\"}}]}}]}\n\n",
+        "data: {\"id\":\"chatcmpl_stream\",\"choices\":[{\"delta\":{},\"finish_reason\":\"tool_calls\"}]}\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_grok_stream")],
+        )],
+    )
+    .await;
+
+    let client = OpenAiCompatClient::new("xai-test-key", OpenAiCompatConfig::xai())
+        .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_grok_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::ContentBlockStart(ContentBlockStartEvent {
+            index: 1,
+            content_block: OutputContentBlock::ToolUse { .. },
+        })
+    ));
+    assert!(matches!(
+        events[4],
+        StreamEvent::ContentBlockDelta(ContentBlockDeltaEvent {
+            index: 1,
+            delta: ContentBlockDelta::InputJsonDelta { .. },
+        })
+    ));
+    assert!(matches!(
+        events[5],
+        StreamEvent::ContentBlockStart(ContentBlockStartEvent {
+            index: 2,
+            content_block: OutputContentBlock::ToolUse { .. },
+        })
+    ));
+    assert!(matches!(
+        events[6],
+        StreamEvent::ContentBlockDelta(ContentBlockDeltaEvent {
+            index: 2,
+            delta: ContentBlockDelta::InputJsonDelta { .. },
+        })
+    ));
+    assert!(matches!(
+        events[7],
+        StreamEvent::ContentBlockStop(ContentBlockStopEvent { index: 1 })
+    ));
+    assert!(matches!(
+        events[8],
+        StreamEvent::ContentBlockStop(ContentBlockStopEvent { index: 2 })
+    ));
+    assert!(matches!(
+        events[9],
+        StreamEvent::ContentBlockStop(ContentBlockStopEvent { index: 0 })
+    ));
+    assert!(matches!(events[10], StreamEvent::MessageDelta(_)));
+    assert!(matches!(events[11], StreamEvent::MessageStop(_)));
+
+    let captured = state.lock().await;
+    let request = captured.first().expect("captured request");
+    assert_eq!(request.path, "/chat/completions");
+    assert!(request.body.contains("\"stream\":true"));
+}
+
+#[tokio::test]
+async fn provider_client_dispatches_xai_requests_from_env() {
+    let _lock = env_lock();
+    let _api_key = ScopedEnvVar::set("XAI_API_KEY", "xai-test-key");
+
+    let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
+    let server = spawn_server(
+        state.clone(),
+        vec![http_response(
+            "200 OK",
+            "application/json",
+            "{\"id\":\"chatcmpl_provider\",\"model\":\"grok-3\",\"choices\":[{\"message\":{\"role\":\"assistant\",\"content\":\"Through provider client\",\"tool_calls\":[]},\"finish_reason\":\"stop\"}],\"usage\":{\"prompt_tokens\":9,\"completion_tokens\":4}}",
+        )],
+    )
+    .await;
+    let _base_url = ScopedEnvVar::set("XAI_BASE_URL", server.base_url());
+
+    let client =
+        ProviderClient::from_model("grok").expect("xAI provider client should be constructed");
+    assert!(matches!(client, ProviderClient::Xai(_)));
+
+    let response = client
+        .send_message(&sample_request(false))
+        .await
+        .expect("provider-dispatched request should succeed");
+
+    assert_eq!(response.total_tokens(), 13);
+
+    let captured = state.lock().await;
+    let request = captured.first().expect("captured request");
+    assert_eq!(request.path, "/chat/completions");
+    assert_eq!(
+        request.headers.get("authorization").map(String::as_str),
+        Some("Bearer xai-test-key")
+    );
+}
+
+#[derive(Debug, Clone, PartialEq, Eq)]
+struct CapturedRequest {
+    path: String,
+    headers: HashMap<String, String>,
+    body: String,
+}
+
+struct TestServer {
+    base_url: String,
+    join_handle: tokio::task::JoinHandle<()>,
+}
+
+impl TestServer {
+    fn base_url(&self) -> String {
+        self.base_url.clone()
+    }
+}
+
+impl Drop for TestServer {
+    fn drop(&mut self) {
+        self.join_handle.abort();
+    }
+}
+
+async fn spawn_server(
+    state: Arc<Mutex<Vec<CapturedRequest>>>,
+    responses: Vec<String>,
+) -> TestServer {
+    let listener = TcpListener::bind("127.0.0.1:0")
+        .await
+        .expect("listener should bind");
+    let address = listener.local_addr().expect("listener addr");
+    let join_handle = tokio::spawn(async move {
+        for response in responses {
+            let (mut socket, _) = listener.accept().await.expect("accept");
+            let mut buffer = Vec::new();
+            let mut header_end = None;
+            loop {
+                let mut chunk = [0_u8; 1024];
+                let read = socket.read(&mut chunk).await.expect("read request");
+                if read == 0 {
+                    break;
+                }
+                buffer.extend_from_slice(&chunk[..read]);
+                if let Some(position) = find_header_end(&buffer) {
+                    header_end = Some(position);
+                    break;
+                }
+            }
+
+            let header_end = header_end.expect("headers should exist");
+            let (header_bytes, remaining) = buffer.split_at(header_end);
+            let header_text = String::from_utf8(header_bytes.to_vec()).expect("utf8 headers");
+            let mut lines = header_text.split("\r\n");
+            let request_line = lines.next().expect("request line");
+            let path = request_line
+                .split_whitespace()
+                .nth(1)
+                .expect("path")
+                .to_string();
+            let mut headers = HashMap::new();
+            let mut content_length = 0_usize;
+            for line in lines {
+                if line.is_empty() {
+                    continue;
+                }
+                let (name, value) = line.split_once(':').expect("header");
+                let value = value.trim().to_string();
+                if name.eq_ignore_ascii_case("content-length") {
+                    content_length = value.parse().expect("content length");
+                }
+                headers.insert(name.to_ascii_lowercase(), value);
+            }
+
+            let mut body = remaining[4..].to_vec();
+            while body.len() < content_length {
+                let mut chunk = vec![0_u8; content_length - body.len()];
+                let read = socket.read(&mut chunk).await.expect("read body");
+                if read == 0 {
+                    break;
+                }
+                body.extend_from_slice(&chunk[..read]);
+            }
+
+            state.lock().await.push(CapturedRequest {
+                path,
+                headers,
+                body: String::from_utf8(body).expect("utf8 body"),
+            });
+
+            socket
+                .write_all(response.as_bytes())
+                .await
+                .expect("write response");
+        }
+    });
+
+    TestServer {
+        base_url: format!("http://{address}"),
+        join_handle,
+    }
+}
+
+fn find_header_end(bytes: &[u8]) -> Option<usize> {
+    bytes.windows(4).position(|window| window == b"\r\n\r\n")
+}
+
+fn http_response(status: &str, content_type: &str, body: &str) -> String {
+    http_response_with_headers(status, content_type, body, &[])
+}
+
+fn http_response_with_headers(
+    status: &str,
+    content_type: &str,
+    body: &str,
+    headers: &[(&str, &str)],
+) -> String {
+    let mut extra_headers = String::new();
+    for (name, value) in headers {
+        use std::fmt::Write as _;
+        write!(&mut extra_headers, "{name}: {value}\r\n").expect("header write");
+    }
+    format!(
+        "HTTP/1.1 {status}\r\ncontent-type: {content_type}\r\n{extra_headers}content-length: {}\r\nconnection: close\r\n\r\n{body}",
+        body.len()
+    )
+}
+
+fn sample_request(stream: bool) -> MessageRequest {
+    MessageRequest {
+        model: "grok-3".to_string(),
+        max_tokens: 64,
+        messages: vec![InputMessage {
+            role: "user".to_string(),
+            content: vec![InputContentBlock::Text {
+                text: "Say hello".to_string(),
+            }],
+        }],
+        system: Some("Use tools when needed".to_string()),
+        tools: Some(vec![ToolDefinition {
+            name: "weather".to_string(),
+            description: Some("Fetches weather".to_string()),
+            input_schema: json!({
+                "type": "object",
+                "properties": {"city": {"type": "string"}},
+                "required": ["city"]
+            }),
+        }]),
+        tool_choice: Some(ToolChoice::Auto),
+        stream,
+    }
+}
+
+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())
+}
+
+struct ScopedEnvVar {
+    key: &'static str,
+    previous: Option<OsString>,
+}
+
+impl ScopedEnvVar {
+    fn set(key: &'static str, value: impl AsRef<std::ffi::OsStr>) -> Self {
+        let previous = std::env::var_os(key);
+        std::env::set_var(key, value);
+        Self { key, previous }
+    }
+}
+
+impl Drop for ScopedEnvVar {
+    fn drop(&mut self) {
+        match &self.previous {
+            Some(value) => std::env::set_var(self.key, value),
+            None => std::env::remove_var(self.key),
+        }
+    }
+}

rust/crates/api/tests/provider_client_integration.rs

@@ -0,0 +1,86 @@
+use std::ffi::OsString;
+use std::sync::{Mutex, OnceLock};
+
+use api::{read_xai_base_url, ApiError, AuthSource, ProviderClient, ProviderKind};
+
+#[test]
+fn provider_client_routes_grok_aliases_through_xai() {
+    let _lock = env_lock();
+    let _xai_api_key = EnvVarGuard::set("XAI_API_KEY", Some("xai-test-key"));
+
+    let client = ProviderClient::from_model("grok-mini").expect("grok alias should resolve");
+
+    assert_eq!(client.provider_kind(), ProviderKind::Xai);
+}
+
+#[test]
+fn provider_client_reports_missing_xai_credentials_for_grok_models() {
+    let _lock = env_lock();
+    let _xai_api_key = EnvVarGuard::set("XAI_API_KEY", None);
+
+    let error = ProviderClient::from_model("grok-3")
+        .expect_err("grok requests without XAI_API_KEY should fail fast");
+
+    match error {
+        ApiError::MissingCredentials { provider, env_vars } => {
+            assert_eq!(provider, "xAI");
+            assert_eq!(env_vars, &["XAI_API_KEY"]);
+        }
+        other => panic!("expected missing xAI credentials, got {other:?}"),
+    }
+}
+
+#[test]
+fn provider_client_uses_explicit_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 client = ProviderClient::from_model_with_default_auth(
+        "claude-sonnet-4-6",
+        Some(AuthSource::ApiKey("claw-test-key".to_string())),
+    )
+    .expect("explicit auth should avoid env lookup");
+
+    assert_eq!(client.provider_kind(), ProviderKind::ClawApi);
+}
+
+#[test]
+fn read_xai_base_url_prefers_env_override() {
+    let _lock = env_lock();
+    let _xai_base_url = EnvVarGuard::set("XAI_BASE_URL", Some("https://example.xai.test/v1"));
+
+    assert_eq!(read_xai_base_url(), "https://example.xai.test/v1");
+}
+
+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())
+}
+
+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),
+        }
+    }
+}