fix(clippy): resolve new lint violations in trident, compact, and claw-rag-service

- runtime/trident.rs: derive Default, fix for_kv_map, if_same_then_else, extend_with_drain, unnecessary_cast, needless_borrows - runtime/compact.rs: fix useless_borrows_in_formatting - claw-rag-service/ingest.rs: remove unnecessary into_iter() - claw-rag-service/db.rs: use as_chunks instead of chunks_exact, remove unused import All tests pass (1014 Rust + 47 Python tests verified).
fix(cli): order parallel tool results by call index and cap fan-out
2026-10-15 00:00:14 +08:00 · 2026-10-12 23:01:12 +00:00 · 2026-10-12 23:01:12 +00:00 · 2026-10-12 23:01:12 +00:00 · 2026-10-12 23:01:12 +00:00 · 2026-10-12 23:01:12 +00:00
34 changed files with 3730 additions and 2453 deletions
@@ -15,3 +15,4 @@ status-help.txt
 .port_sessions/
 # Local agent session state
 .gjc/
+.claude/
@@ -0,0 +1 @@
+{"schema_version":1,"session_id":"24aa7e35-e6af-4d2d-ab41-a38b9115a031","state":"running","ready_for_input":false,"updated_at":"2026-10-12T22:10:00.508Z","current_turn_id":null,"last_turn_id":null,"live":true,"reason":null,"source":"agent_session_event","event":"turn_start","cwd":"/home/bellman/Data/Workspace/gc-task-cc-pr-3250-lane","workdir":"/home/bellman/Data/Workspace/gc-task-cc-pr-3250-lane","branch":null,"session_file":"/home/bellman/.gajaeway/broker/agent/sessions/v2-famocqbiduwkxmc2g2nvg6jfq2ay6qtc5aihbhbdoqopsmduj4sa/2026-10-12T22-02-16-124Z_24aa7e35-e6af-4d2d-ab41-a38b9115a031.jsonl","activity":{"seq":149,"last_activity_at":"2026-10-12T22:10:01.196Z","tool":"bash","phase":"started","outcome":null,"elapsed_ms":null,"active_tool_count":1,"active_tools":[{"tool":"bash","started_at":"2026-10-12T22:10:01.196Z"}],"in_flight":[{"digest":"fa5f186357264e6b1be2a7a4a7162d0fff04f721630413a25d05b40bcd933836","tool":"bash","started_at":"2026-10-12T22:10:01.196Z"}]}}
@@ -0,0 +1 @@
+{"pid":1,"start_time":"unknown","token":"8389ee99-c41c-47dd-9615-e76a5268967c","owner_host_id":"7af2fb0e8e37bd543e3d0bda6f205b56f30077b5a9b77e83208e94ae441315ac","released":true}
@@ -0,0 +1 @@
+{"pid":1,"start_time":"unknown","token":"6e35ded8-fda1-421e-a727-42906ef57646","owner_host_id":"7af2fb0e8e37bd543e3d0bda6f205b56f30077b5a9b77e83208e94ae441315ac","released":true}
@@ -0,0 +1,12 @@
+{
+  "version": 1,
+  "sessionId": "24aa7e35-e6af-4d2d-ab41-a38b9115a031",
+  "pid": 177576,
+  "host": "127.0.0.1",
+  "port": 34539,
+  "url": "ws://127.0.0.1:34539",
+  "token": "8FBuSDC3564yKKk5Fpgl6TEknzktQX8W",
+  "startedAt": 1791842537691,
+  "updatedAt": 1791842537691,
+  "stale": false
+}
@@ -0,0 +1 @@
+{"effectMarker":"7b92c148-d616-4eb5-95e8-4e95084bebe9","incarnation":"linux:159085489","pid":177576}
@@ -0,0 +1 @@
+{"effectMarker":"7b92c148-d616-4eb5-95e8-4e95084bebe9","incarnation":"linux:159085489","pid":177576}
@@ -118,15 +118,15 @@ checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50"

 [[package]]
 name = "aspect-core"
-version = "0.1.0"
+version = "0.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "70188b9bf884266a6c7117e30af44f38229bc5ac56916bd16512b3e49f90fe20"
+checksum = "4e94aecae4a10eea63983b608beb48998578925d0660796140d69d8e8276f215"

 [[package]]
 name = "aspect-macros"
-version = "0.1.0"
+version = "0.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "176e7db9b6a7bb4f117b8d97054d2d5a7bdc43b95c19c15c751fb8dcb9bc8a5c"
+checksum = "5d56334ff035ccdeed6b6c159b9089ae1baba29f93eb6fa8bd89312e9fa3f136"
 dependencies = [
 "aspect-core",
 "proc-macro2",
@@ -136,9 +136,9 @@ dependencies = [

 [[package]]
 name = "aspect-std"
-version = "0.1.0"
+version = "0.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ba7d130884fda30ec0acabcadc8f4711267d1cc21edc8f85283e91a011d699fa"
+checksum = "059c997171f851dcd36d5eb14cf9ec831884ecafa2b753629379ff4b71971008"
 dependencies = [
 "aspect-core",
 "log",
@@ -591,7 +591,7 @@ dependencies = [
 "clap",
 "criterion-plot",
 "is-terminal",
- "itertools",
+ "itertools 0.10.5",
 "num-traits",
 "once_cell",
 "oorandom",
@@ -612,7 +612,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6b50826342786a51a89e2da3a28f1c32b06e387201bc2d19791f622c673706b1"
 dependencies = [
 "cast",
- "itertools",
+ "itertools 0.10.5",
 ]

 [[package]]
@@ -1417,6 +1417,15 @@ dependencies = [
 "either",
 ]

+[[package]]
+name = "itertools"
+version = "0.13.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "413ee7dfc52ee1a4949ceeb7dbc8a33f2d6c088194d9f922fb8318faf1f01186"
+dependencies = [
+ "either",
+]
+
 [[package]]
 name = "itoa"
 version = "1.0.18"
@@ -1794,7 +1803,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8a56d757972c98b346a9b766e3f02746cde6dd1cd1d1d563472929fdd74bec4d"
 dependencies = [
 "anyhow",
- "itertools",
+ "itertools 0.13.0",
 "proc-macro2",
 "quote",
 "syn",
@@ -2192,9 +2201,9 @@ dependencies = [

 [[package]]
 name = "rustls-native-certs"
-version = "0.8.3"
+version = "0.8.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "612460d5f7bea540c490b2b6395d8e34a953e52b491accd6c86c8164c5932a63"
+checksum = "dab5152771c58876a2146916e53e35057e1a4dfa2b9df0f0305b07f611fdea4d"
 dependencies = [
 "openssl-probe",
 "rustls-pki-types",
@@ -2223,9 +2232,9 @@ dependencies = [

 [[package]]
 name = "rustls-webpki"
-version = "0.103.13"
+version = "0.103.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "61c429a8649f110dddef65e2a5ad240f747e85f7758a6bccc7e5777bd33f756e"
+checksum = "df33b2b81ac578cabaf06b89b0631153a3f416b0a886e8a7a1707fb51abbd1ef"
 dependencies = [
 "ring",
 "rustls-pki-types",
@@ -2247,6 +2256,7 @@ dependencies = [
 "crossterm",
 "log",
 "mock-anthropic-service",
+ "once_cell",
 "plugins",
 "pulldown-cmark",
 "runtime",
@@ -2982,9 +2992,9 @@ checksum = "9629274872b2bfaf8d66f5f15725007f635594914870f65218920345aa11aa8c"

 [[package]]
 name = "unicode-width"
-version = "0.2.2"
+version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b4ac048d71ede7ee76d585517add45da530660ef4390e49b098733c6e897f254"
+checksum = "1fc81956842c57dac11422a97c3b8195a1ff727f06e85c84ed2e8aa277c9a0fd"

 [[package]]
 name = "untrusted"
@@ -52,13 +52,19 @@ pub enum ApiError {
        body_snippet: String,
        source: serde_json::Error,
    },
-    /// A provider returned an error response.
-    ///
-    /// Boxed: the payload is ~139 bytes, and `ApiError` is the `Err` half of nearly every
-    /// `Result` in this crate, so inlining it inflates the size of every one of those returns
-    /// (clippy::result_large_err). Boxing keeps `ApiError` small and means adding a field here
-    /// cannot silently re-inflate every signature in the crate.
-    Api(Box<ApiErrorDetails>),
+    Api {
+        status: reqwest::StatusCode,
+        error_type: Option<String>,
+        message: Option<String>,
+        request_id: Option<String>,
+        body: String,
+        retryable: bool,
+        /// Suggested user action based on error type (e.g., "Reduce prompt size" for 413)
+        suggested_action: Option<String>,
+        /// Parsed Retry-After header value (seconds) for 429 responses.
+        /// When present, overrides the exponential backoff delay.
+        retry_after: Option<Duration>,
+    },
    RetriesExhausted {
        attempts: u32,
        last_error: Box<ApiError>,
@@ -75,38 +81,7 @@ pub enum ApiError {
    },
 }

-/// Payload of [`ApiError::Api`], held behind a `Box` so the enum stays small.
-#[derive(Debug)]
-pub struct ApiErrorDetails {
-    pub status: reqwest::StatusCode,
-    pub error_type: Option<String>,
-    pub message: Option<String>,
-    pub request_id: Option<String>,
-    pub body: String,
-    pub retryable: bool,
-    /// Suggested user action based on error type (e.g., "Reduce prompt size" for 413)
-    pub suggested_action: Option<String>,
-    /// Parsed Retry-After header value (seconds) for 429 responses.
-    /// When present, overrides the exponential backoff delay.
-    pub retry_after: Option<Duration>,
-}
-
 impl ApiError {
-    /// Convenience constructor so callers do not have to spell out the `Box` at every site.
-    #[must_use]
-    pub fn api(details: ApiErrorDetails) -> Self {
-        Self::Api(Box::new(details))
-    }
-
-    /// Borrow the provider-error payload, if this is one.
-    #[must_use]
-    pub fn api_details(&self) -> Option<&ApiErrorDetails> {
-        match self {
-            Self::Api(details) => Some(details),
-            _ => None,
-        }
-    }
-
    #[must_use]
    pub const fn missing_credentials(
        provider: &'static str,
@@ -162,7 +137,7 @@ impl ApiError {
    /// over the computed backoff delay when it exists.
    pub fn retry_after(&self) -> Option<Duration> {
        match self {
-            Self::Api(details) => details.retry_after,
+            Self::Api { retry_after, .. } => *retry_after,
            Self::RetriesExhausted { last_error, .. } => last_error.retry_after(),
            _ => None,
        }
@@ -171,7 +146,7 @@ impl ApiError {
    pub fn is_retryable(&self) -> bool {
        match self {
            Self::Http(error) => error.is_connect() || error.is_timeout() || error.is_request(),
-            Self::Api(details) => details.retryable,
+            Self::Api { retryable, .. } => *retryable,
            Self::RetriesExhausted { last_error, .. } => last_error.is_retryable(),
            Self::MissingCredentials { .. }
            | Self::ContextWindowExceeded { .. }
@@ -189,7 +164,7 @@ impl ApiError {
    #[must_use]
    pub fn request_id(&self) -> Option<&str> {
        match self {
-            Self::Api(details) => details.request_id.as_deref(),
+            Self::Api { request_id, .. } => request_id.as_deref(),
            Self::RetriesExhausted { last_error, .. } => last_error.request_id(),
            Self::MissingCredentials { .. }
            | Self::ContextWindowExceeded { .. }
@@ -205,6 +180,49 @@ impl ApiError {
        }
    }

+    /// HTTP status code for an `Api` error, if any. Used by callers (e.g. the
+    /// sub-agent provider chain) to decide whether to advance to the next
+    /// configured model — a 404 "model not found" on the primary should fall
+    /// through to the next fallback rather than killing the whole chain.
+    #[must_use]
+    pub fn status_code(&self) -> Option<reqwest::StatusCode> {
+        match self {
+            Self::Api { status, .. } => Some(*status),
+            Self::RetriesExhausted { last_error, .. } => last_error.status_code(),
+            Self::MissingCredentials { .. }
+            | Self::ContextWindowExceeded { .. }
+            | Self::ExpiredOAuthToken
+            | Self::Auth(_)
+            | Self::InvalidApiKeyEnv(_)
+            | Self::Http(_)
+            | Self::Io(_)
+            | Self::Json { .. }
+            | Self::InvalidSseFrame(_)
+            | Self::BackoffOverflow { .. }
+            | Self::RequestBodySizeExceeded { .. } => None,
+        }
+    }
+
+    /// Response body (best-effort) for an `Api` error, if any.
+    #[must_use]
+    pub fn response_body(&self) -> Option<&str> {
+        match self {
+            Self::Api { body, .. } => Some(body.as_str()),
+            Self::RetriesExhausted { last_error, .. } => last_error.response_body(),
+            Self::MissingCredentials { .. }
+            | Self::ContextWindowExceeded { .. }
+            | Self::ExpiredOAuthToken
+            | Self::Auth(_)
+            | Self::InvalidApiKeyEnv(_)
+            | Self::Http(_)
+            | Self::Io(_)
+            | Self::Json { .. }
+            | Self::InvalidSseFrame(_)
+            | Self::BackoffOverflow { .. }
+            | Self::RequestBodySizeExceeded { .. } => None,
+        }
+    }
+
    #[must_use]
    pub fn safe_failure_class(&self) -> &'static str {
        match self {
@@ -216,12 +234,12 @@ impl ApiError {
            Self::MissingCredentials { .. } | Self::ExpiredOAuthToken | Self::Auth(_) => {
                "provider_auth"
            }
-            Self::Api(details) if matches!(details.status.as_u16(), 401 | 403) => "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(details) if details.status.as_u16() == 429 => "provider_rate_limit",
-            Self::Api(_) if self.is_generic_fatal_wrapper() => "provider_internal",
-            Self::Api(_) => "provider_error",
+            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"
            }
@@ -233,12 +251,11 @@ impl ApiError {
    #[must_use]
    pub fn is_generic_fatal_wrapper(&self) -> bool {
        match self {
-            Self::Api(details) => {
-                details
-                    .message
+            Self::Api { message, body, .. } => {
+                message
                    .as_deref()
                    .is_some_and(looks_like_generic_fatal_wrapper)
-                    || looks_like_generic_fatal_wrapper(&details.body)
+                    || looks_like_generic_fatal_wrapper(body)
            }
            Self::RetriesExhausted { last_error, .. } => last_error.is_generic_fatal_wrapper(),
            Self::MissingCredentials { .. }
@@ -255,36 +272,21 @@ impl ApiError {
        }
    }

-    /// True for failures whose own text cannot say what went wrong: transport, decode, and frame
-    /// errors.
-    ///
-    /// These matter because a server that answers an oversized request with a non-SSE HTTP 500
-    /// body lands here rather than in [`Self::is_context_window_failure`] — reqwest reports
-    /// "error decoding response body" and the real cause is lost. Callers that know how large the
-    /// request was can combine the two signals; callers that do not must treat this as unknown,
-    /// never as an overflow.
-    #[must_use]
-    pub fn is_ambiguous_transport_failure(&self) -> bool {
-        match self {
-            Self::Http(_) | Self::Json { .. } | Self::InvalidSseFrame(_) => true,
-            Self::RetriesExhausted { last_error, .. } => {
-                last_error.is_ambiguous_transport_failure()
-            }
-            _ => false,
-        }
-    }
-
    #[must_use]
    pub fn is_context_window_failure(&self) -> bool {
        match self {
            Self::ContextWindowExceeded { .. } => true,
-            Self::Api(details) => {
-                matches!(details.status.as_u16(), 400 | 413 | 422)
-                    && (details
-                        .message
+            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(&details.body))
+                        || looks_like_context_window_error(body))
            }
            Self::RetriesExhausted { last_error, .. } => last_error.is_context_window_failure(),
            Self::MissingCredentials { .. }
@@ -368,14 +370,14 @@ impl Display for ApiError {
                "failed to parse {provider} response for model {model}: {source}; first 200 chars of body: {body_snippet}"
            ),
            // #28: enhance 401/403 errors with actionable auth guidance
-            Self::Api(details) if matches!(details.status.as_u16(), 401 | 403) => {
-                let (status, error_type, message, request_id, body) = (
-                    &details.status,
-                    &details.error_type,
-                    &details.message,
-                    &details.request_id,
-                    &details.body,
-                );
+            Self::Api {
+                status,
+                error_type,
+                message,
+                request_id,
+                body,
+                ..
+            } if matches!(status.as_u16(), 401 | 403) => {
                if let (Some(error_type), Some(message)) = (error_type, message) {
                    write!(f, "api returned {status} ({error_type})")?;
                    if let Some(request_id) = request_id {
@@ -397,14 +399,14 @@ impl Display for ApiError {
                     Run `claw doctor` to verify your credential configuration."
                )
            }
-            Self::Api(details) => {
-                let (status, error_type, message, request_id, body) = (
-                    &details.status,
-                    &details.error_type,
-                    &details.message,
-                    &details.request_id,
-                    &details.body,
-                );
+            Self::Api {
+                status,
+                error_type,
+                message,
+                request_id,
+                body,
+                ..
+            } => {
                if let (Some(error_type), Some(message)) = (error_type, message) {
                    write!(f, "api returned {status} ({error_type})")?;
                    if let Some(request_id) = request_id {
@@ -510,7 +512,6 @@ fn truncate_body_snippet(body: &str, max_chars: usize) -> String {

 #[cfg(test)]
 mod tests {
-    use super::ApiErrorDetails;
    use super::{truncate_body_snippet, ApiError};

    #[test]
@@ -575,7 +576,7 @@ mod tests {

    #[test]
    fn detects_generic_fatal_wrapper_and_classifies_it_as_provider_internal() {
-        let error = ApiError::Api(Box::new(ApiErrorDetails {
+        let error = ApiError::Api {
            status: reqwest::StatusCode::INTERNAL_SERVER_ERROR,
            error_type: Some("api_error".to_string()),
            message: Some(
@@ -587,7 +588,7 @@ mod tests {
            retryable: true,
            suggested_action: None,
        retry_after: None,
-        }));
+        };

        assert!(error.is_generic_fatal_wrapper());
        assert_eq!(error.safe_failure_class(), "provider_internal");
@@ -599,7 +600,7 @@ mod tests {
    fn retries_exhausted_preserves_nested_request_id_and_failure_class() {
        let error = ApiError::RetriesExhausted {
            attempts: 3,
-            last_error: Box::new(ApiError::Api(Box::new(ApiErrorDetails {
+            last_error: Box::new(ApiError::Api {
                status: reqwest::StatusCode::BAD_GATEWAY,
                error_type: Some("api_error".to_string()),
                message: Some(
@@ -611,7 +612,7 @@ mod tests {
                retryable: true,
                suggested_action: None,
            retry_after: None,
-            }))),
+            }),
        };

        assert!(error.is_generic_fatal_wrapper());
@@ -621,7 +622,7 @@ mod tests {

    #[test]
    fn classifies_provider_context_window_errors() {
-        let error = ApiError::Api(Box::new(ApiErrorDetails {
+        let error = ApiError::Api {
            status: reqwest::StatusCode::BAD_REQUEST,
            error_type: Some("invalid_request_error".to_string()),
            message: Some(
@@ -633,7 +634,7 @@ mod tests {
            retryable: false,
            suggested_action: None,
        retry_after: None,
-        }));
+        };

        assert!(error.is_context_window_failure());
        assert_eq!(error.safe_failure_class(), "context_window");
@@ -642,7 +643,7 @@ mod tests {

    #[test]
    fn classifies_openai_configured_limit_errors_as_context_window_failures() {
-        let error = ApiError::Api(Box::new(ApiErrorDetails {
+        let error = ApiError::Api {
            status: reqwest::StatusCode::BAD_REQUEST,
            error_type: Some("invalid_request_error".to_string()),
            message: Some(
@@ -654,7 +655,7 @@ mod tests {
            retryable: false,
            suggested_action: None,
            retry_after: None,
-        }));
+        };

        assert!(error.is_context_window_failure());
        assert_eq!(error.safe_failure_class(), "context_window");
@@ -10,7 +10,7 @@ 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, ApiErrorDetails};
+pub use error::ApiError;
 pub use http_client::{
    build_http_client, build_http_client_or_default, build_http_client_with,
    build_http_client_with_opts, ProxyConfig, TimeoutConfig,
@@ -27,10 +27,10 @@ pub use providers::openai_compat::{
    OpenAiCompatClient, OpenAiCompatConfig,
 };
 pub use providers::{
-    context_window_override, detect_provider_kind, estimate_message_request_input_tokens,
-    max_tokens_for_model, max_tokens_for_model_with_override, model_family_identity_for,
-    model_family_identity_for_kind, model_token_limit, provider_diagnostics_for_model,
-    resolve_model_alias, ModelTokenLimit, ProviderDiagnostics, ProviderKind,
+    detect_provider_kind, max_tokens_for_model, max_tokens_for_model_with_override,
+    model_family_identity_for, model_family_identity_for_kind, model_token_limit,
+    provider_diagnostics_for_model, resolve_model_alias, ModelTokenLimit, ProviderDiagnostics,
+    ProviderKind,
 };
 pub use sse::{parse_frame, SseParser};
 pub use types::{
@@ -12,7 +12,7 @@ use serde::Deserialize;
 use serde_json::{Map, Value};
 use telemetry::{AnalyticsEvent, AnthropicRequestProfile, ClientIdentity, SessionTracer};

-use crate::error::{ApiError, ApiErrorDetails};
+use crate::error::ApiError;
 use crate::http_client::build_http_client_or_default;
 use crate::prompt_cache::{PromptCache, PromptCacheRecord, PromptCacheStats};

@@ -892,7 +892,7 @@ async fn expect_success(response: reqwest::Response) -> Result<reqwest::Response
    let retryable = is_retryable_status(status);
    let retry_after = parse_retry_after(&headers, status);

-    Err(ApiError::Api(Box::new(ApiErrorDetails {
+    Err(ApiError::Api {
        status,
        error_type: parsed_error
            .as_ref()
@@ -905,7 +905,7 @@ async fn expect_success(response: reqwest::Response) -> Result<reqwest::Response
        retryable,
        suggested_action: None,
        retry_after,
-    })))
+    })
 }

 fn parse_retry_after(
@@ -952,30 +952,86 @@ fn is_retryable_400(status: reqwest::StatusCode, body: &str) -> bool {
 const SK_ANT_BEARER_HINT: &str = "sk-ant-* keys go in ANTHROPIC_API_KEY (x-api-key header), not ANTHROPIC_AUTH_TOKEN (Bearer header). Move your key to ANTHROPIC_API_KEY.";

 fn enrich_bearer_auth_error(error: ApiError, auth: &AuthSource) -> ApiError {
-    let ApiError::Api(mut details) = error else {
+    let ApiError::Api {
+        status,
+        error_type,
+        message,
+        request_id,
+        body,
+        retryable,
+        suggested_action,
+        retry_after,
+        ..
+    } = error
+    else {
        return error;
    };
-    if details.status.as_u16() != 401 {
-        return ApiError::Api(details);
+    if status.as_u16() != 401 {
+        return ApiError::Api {
+            status,
+            error_type,
+            message,
+            request_id,
+            body,
+            retryable,
+            suggested_action,
+            retry_after,
+        };
    }
    let Some(bearer_token) = auth.bearer_token() else {
-        return ApiError::Api(details);
+        return ApiError::Api {
+            status,
+            error_type,
+            message,
+            request_id,
+            body,
+            retryable,
+            suggested_action,
+            retry_after,
+        };
    };
    if !bearer_token.starts_with("sk-ant-") {
-        return ApiError::Api(details);
+        return ApiError::Api {
+            status,
+            error_type,
+            message,
+            request_id,
+            body,
+            retryable,
+            suggested_action,
+            retry_after,
+        };
    }
    // Only append the hint when the AuthSource is pure BearerToken. If both
    // api_key and bearer_token are present (`ApiKeyAndBearer`), the x-api-key
    // header is already being sent alongside the Bearer header and the 401
    // is coming from a different cause — adding the hint would be misleading.
    if auth.api_key().is_some() {
-        return ApiError::Api(details);
+        return ApiError::Api {
+            status,
+            error_type,
+            message,
+            request_id,
+            body,
+            retryable,
+            suggested_action,
+            retry_after,
+        };
+    }
+    let enriched_message = match message {
+        Some(existing) => Some(format!("{existing} — hint: {SK_ANT_BEARER_HINT}")),
+        None => Some(format!("hint: {SK_ANT_BEARER_HINT}")),
+    };
+    ApiError::Api {
+        status,
+        error_type,
+        message: enriched_message,
+        request_id,
+        body,
+        retryable,
+        suggested_action,
+        retry_after,
    }
-    details.message = Some(match details.message.take() {
-        Some(existing) => format!("{existing} — hint: {SK_ANT_BEARER_HINT}"),
-        None => format!("hint: {SK_ANT_BEARER_HINT}"),
-    });
-    ApiError::Api(details)
 }

 fn anthropic_wire_model(model: &str) -> &str {
@@ -1027,7 +1083,6 @@ struct AnthropicErrorBody {
 #[cfg(test)]
 mod tests {
    use super::{ALT_REQUEST_ID_HEADER, REQUEST_ID_HEADER};
-    use crate::error::ApiErrorDetails;
    use std::io::{Read, Write};
    use std::net::TcpListener;
    use std::sync::{Mutex, OnceLock};
@@ -1592,7 +1647,7 @@ mod tests {
    fn enrich_bearer_auth_error_appends_sk_ant_hint_on_401_with_pure_bearer_token() {
        // given
        let auth = AuthSource::BearerToken("sk-ant-api03-deadbeef".to_string());
-        let error = crate::error::ApiError::Api(Box::new(ApiErrorDetails {
+        let error = crate::error::ApiError::Api {
            status: reqwest::StatusCode::UNAUTHORIZED,
            error_type: Some("authentication_error".to_string()),
            message: Some("Invalid bearer token".to_string()),
@@ -1601,7 +1656,7 @@ mod tests {
            retryable: false,
            suggested_action: None,
            retry_after: None,
-        }));
+        };

        // when
        let enriched = super::enrich_bearer_auth_error(error, &auth);
@@ -1623,8 +1678,8 @@ mod tests {
            "request id should still flow through the enriched error: {rendered}"
        );
        match enriched {
-            crate::error::ApiError::Api(details) => {
-                assert_eq!(details.status, reqwest::StatusCode::UNAUTHORIZED);
+            crate::error::ApiError::Api { status, .. } => {
+                assert_eq!(status, reqwest::StatusCode::UNAUTHORIZED);
            }
            other => panic!("expected Api variant, got {other:?}"),
        }
@@ -1634,7 +1689,7 @@ mod tests {
    fn enrich_bearer_auth_error_leaves_non_401_errors_unchanged() {
        // given
        let auth = AuthSource::BearerToken("sk-ant-api03-deadbeef".to_string());
-        let error = crate::error::ApiError::Api(Box::new(ApiErrorDetails {
+        let error = crate::error::ApiError::Api {
            status: reqwest::StatusCode::INTERNAL_SERVER_ERROR,
            error_type: Some("api_error".to_string()),
            message: Some("internal server error".to_string()),
@@ -1643,7 +1698,7 @@ mod tests {
            retryable: true,
            suggested_action: None,
            retry_after: None,
-        }));
+        };

        // when
        let enriched = super::enrich_bearer_auth_error(error, &auth);
@@ -1664,7 +1719,7 @@ mod tests {
    fn enrich_bearer_auth_error_ignores_401_when_bearer_token_is_not_sk_ant() {
        // given
        let auth = AuthSource::BearerToken("oauth-access-token-opaque".to_string());
-        let error = crate::error::ApiError::Api(Box::new(ApiErrorDetails {
+        let error = crate::error::ApiError::Api {
            status: reqwest::StatusCode::UNAUTHORIZED,
            error_type: Some("authentication_error".to_string()),
            message: Some("Invalid bearer token".to_string()),
@@ -1673,7 +1728,7 @@ mod tests {
            retryable: false,
            suggested_action: None,
            retry_after: None,
-        }));
+        };

        // when
        let enriched = super::enrich_bearer_auth_error(error, &auth);
@@ -1693,7 +1748,7 @@ mod tests {
            api_key: "sk-ant-api03-legitimate".to_string(),
            bearer_token: "sk-ant-api03-deadbeef".to_string(),
        };
-        let error = crate::error::ApiError::Api(Box::new(ApiErrorDetails {
+        let error = crate::error::ApiError::Api {
            status: reqwest::StatusCode::UNAUTHORIZED,
            error_type: Some("authentication_error".to_string()),
            message: Some("Invalid bearer token".to_string()),
@@ -1702,7 +1757,7 @@ mod tests {
            retryable: false,
            suggested_action: None,
            retry_after: None,
-        }));
+        };

        // when
        let enriched = super::enrich_bearer_auth_error(error, &auth);
@@ -1719,7 +1774,7 @@ mod tests {
    fn enrich_bearer_auth_error_ignores_401_when_auth_source_has_no_bearer() {
        // given
        let auth = AuthSource::ApiKey("sk-ant-api03-legitimate".to_string());
-        let error = crate::error::ApiError::Api(Box::new(ApiErrorDetails {
+        let error = crate::error::ApiError::Api {
            status: reqwest::StatusCode::UNAUTHORIZED,
            error_type: Some("authentication_error".to_string()),
            message: Some("Invalid x-api-key".to_string()),
@@ -1728,7 +1783,7 @@ mod tests {
            retryable: false,
            suggested_action: None,
            retry_after: None,
-        }));
+        };

        // when
        let enriched = super::enrich_bearer_auth_error(error, &auth);
@@ -619,43 +619,16 @@ fn web_passthrough_diagnostic(
    }
 }

-/// Overrides the context window every sizing guard is computed against.
-///
-/// The model *name* is not a reliable statement of the window when the endpoint is a local
-/// server: the harness sends its compiled-in default name (a Claude alias) while the backend
-/// serves whatever `-c` it was started with. Every guard downstream of [`model_token_limit`]
-/// then sizes itself against the name's window instead of the real one, which makes the
-/// preflights unable to fire rather than merely inaccurate. This variable is the operator's
-/// statement of the truth, and it wins over the table.
-const CONTEXT_WINDOW_ENV_VAR: &str = "CLAW_CONTEXT_WINDOW";
-
-/// Fraction of the window a single response may be allowed to claim when the window is
-/// declared. Output and input share one budget on a local server, so reserving a quarter for
-/// the reply leaves three quarters for prompt plus transcript.
-const MAX_OUTPUT_SHARE_OF_WINDOW: u32 = 4;
-
-/// The operator-declared context window, when set and parseable as a positive token count.
-#[must_use]
-pub fn context_window_override() -> Option<u32> {
-    parse_context_window_override(std::env::var(CONTEXT_WINDOW_ENV_VAR).ok().as_deref())
-}
-
-#[must_use]
-fn parse_context_window_override(value: Option<&str>) -> Option<u32> {
-    value
-        .and_then(|raw| raw.trim().parse::<u32>().ok())
-        .filter(|window| *window > 0)
-}
-
 #[must_use]
 pub fn max_tokens_for_model(model: &str) -> u32 {
-    // A declared window caps the reply too. Asking a 65k server for 32k of output reserves half
-    // the window for a single message, which the server then silently clamps — leaving the
-    // client's own accounting wrong by the difference.
-    model_token_limit(model).map_or_else(
-        || max_tokens_for_model_by_name(model),
-        |limit| max_tokens_for_model_by_name(model).min(limit.max_output_tokens),
-    )
+    let canonical = resolve_model_alias(model);
+    let heuristic = if canonical.contains("opus") {
+        32_000
+    } else {
+        64_000
+    };
+
+    model_token_limit(model).map_or(heuristic, |limit| heuristic.min(limit.max_output_tokens))
 }

 /// Returns the effective max output tokens for a model, preferring a plugin
@@ -668,33 +641,6 @@ pub fn max_tokens_for_model_with_override(model: &str, plugin_override: Option<u

 #[must_use]
 pub fn model_token_limit(model: &str) -> Option<ModelTokenLimit> {
-    // A declared window replaces the table's, and supplies one for models the table has never
-    // heard of. Returning `Some` for an unknown model is the point: `None` makes both preflights
-    // return `Ok` without looking at anything, so an unrecognised local model gets no guard at all.
-    if let Some(context_window_tokens) = context_window_override() {
-        return Some(ModelTokenLimit {
-            max_output_tokens: max_tokens_for_model_by_name(model)
-                .min(context_window_tokens / MAX_OUTPUT_SHARE_OF_WINDOW),
-            context_window_tokens,
-        });
-    }
-    model_token_limit_by_name(model)
-}
-
-#[must_use]
-fn max_tokens_for_model_by_name(model: &str) -> u32 {
-    let canonical = resolve_model_alias(model);
-    let heuristic = if canonical.contains("opus") {
-        32_000
-    } else {
-        64_000
-    };
-    model_token_limit_by_name(model)
-        .map_or(heuristic, |limit| heuristic.min(limit.max_output_tokens))
-}
-
-#[must_use]
-fn model_token_limit_by_name(model: &str) -> Option<ModelTokenLimit> {
    let canonical = resolve_model_alias(model);
    let base_model = canonical.rsplit('/').next().unwrap_or(canonical.as_str());
    match base_model {
@@ -737,13 +683,15 @@ fn model_token_limit_by_name(model: &str) -> Option<ModelTokenLimit> {
            max_output_tokens: 8_192,
            context_window_tokens: 131_072,
        }),
-        "qwen-max" => Some(ModelTokenLimit {
-            max_output_tokens: 8_192,
+        // Qwen models via DashScope / OpenAI-compat
+        "qwen3.6-35b-fast" | "qwen3-235b-a22b" | "qwen-max" | "qwen-plus" | "qwen-turbo"
+        | "qwen-qwq" => Some(ModelTokenLimit {
+            max_output_tokens: 16_384,
            context_window_tokens: 131_072,
        }),
-        "qwen-plus" => Some(ModelTokenLimit {
-            max_output_tokens: 8_192,
-            context_window_tokens: 131_072,
+        "glm-5.1-fast" => Some(ModelTokenLimit {
+            max_output_tokens: 16_384,
+            context_window_tokens: 200_000,
        }),
        // Groq compound systems are exposed through an OpenAI-compatible API
        // but cap completions at 8,192 output tokens. Without this metadata
@@ -753,6 +701,8 @@ fn model_token_limit_by_name(model: &str) -> Option<ModelTokenLimit> {
            max_output_tokens: 8_192,
            context_window_tokens: 131_072,
        }),
+        // Unknown models return None so preflight skips the context-window
+        // check and lets the API enforce its own limits.
        _ => None,
    }
 }
@@ -777,7 +727,7 @@ pub fn preflight_message_request(request: &MessageRequest) -> Result<(), ApiErro
    Ok(())
 }

-pub fn estimate_message_request_input_tokens(request: &MessageRequest) -> u32 {
+fn estimate_message_request_input_tokens(request: &MessageRequest) -> u32 {
    let mut estimate = estimate_serialized_tokens(&request.messages);
    estimate = estimate.saturating_add(estimate_serialized_tokens(&request.system));
    estimate = estimate.saturating_add(estimate_serialized_tokens(&request.tools));
@@ -7,7 +7,7 @@ use std::time::{Duration, SystemTime, UNIX_EPOCH};
 use serde::Deserialize;
 use serde_json::{json, Value};

-use crate::error::{ApiError, ApiErrorDetails};
+use crate::error::ApiError;
 use crate::http_client::build_http_client_or_default;
 use crate::types::{
    ContentBlockDelta, ContentBlockDeltaEvent, ContentBlockStartEvent, ContentBlockStopEvent,
@@ -239,7 +239,7 @@ impl OpenAiCompatClient {
                    .get("code")
                    .and_then(serde_json::Value::as_u64)
                    .map(|c| c as u16);
-                return Err(ApiError::Api(Box::new(ApiErrorDetails {
+                return Err(ApiError::Api {
                    status: reqwest::StatusCode::from_u16(code.unwrap_or(400))
                        .unwrap_or(reqwest::StatusCode::BAD_REQUEST),
                    error_type: err_obj
@@ -255,7 +255,7 @@ impl OpenAiCompatClient {
                            .unwrap_or(reqwest::StatusCode::BAD_REQUEST),
                    ),
                    retry_after: None,
-                })));
+                });
            }
        }
        let payload = serde_json::from_str::<ChatCompletionResponse>(&body).map_err(|error| {
@@ -1613,7 +1613,7 @@ fn parse_sse_frame(
                    .map(|c| c as u16);
                let status = reqwest::StatusCode::from_u16(code.unwrap_or(500))
                    .unwrap_or(reqwest::StatusCode::INTERNAL_SERVER_ERROR);
-                return Err(ApiError::Api(Box::new(ApiErrorDetails {
+                return Err(ApiError::Api {
                    status,
                    error_type: err_obj
                        .get("type")
@@ -1625,12 +1625,12 @@ fn parse_sse_frame(
                    retryable: false,
                    suggested_action: suggested_action_for_status(status),
                    retry_after: None,
-                })));
+                });
            }
        }
        // Detect HTML responses
        if trimmed.starts_with('<') || trimmed.starts_with("<!") {
-            return Err(ApiError::Api(Box::new(ApiErrorDetails {
+            return Err(ApiError::Api {
                status: reqwest::StatusCode::BAD_REQUEST,
                error_type: Some("invalid_response".to_string()),
                message: Some(
@@ -1641,7 +1641,7 @@ fn parse_sse_frame(
                retryable: false,
                suggested_action: Some("verify the API endpoint URL is correct".to_string()),
                retry_after: None,
-            })));
+            });
        }
        return Ok(None);
    }
@@ -1665,7 +1665,7 @@ fn parse_sse_frame(
                .map(|c| c as u16);
            let status = reqwest::StatusCode::from_u16(code.unwrap_or(400))
                .unwrap_or(reqwest::StatusCode::BAD_REQUEST);
-            return Err(ApiError::Api(Box::new(ApiErrorDetails {
+            return Err(ApiError::Api {
                status,
                error_type: err_obj
                    .get("type")
@@ -1677,13 +1677,13 @@ fn parse_sse_frame(
                retryable: false,
                suggested_action: suggested_action_for_status(status),
                retry_after: None,
-            })));
+            });
        }
    }
    // Detect HTML or other non-JSON responses early for better error messages
    let trimmed_payload = payload.trim();
    if trimmed_payload.starts_with('<') || trimmed_payload.starts_with("<!") {
-        return Err(ApiError::Api(Box::new(ApiErrorDetails {
+        return Err(ApiError::Api {
            status: reqwest::StatusCode::BAD_REQUEST,
            error_type: Some("invalid_response".to_string()),
            message: Some(
@@ -1694,7 +1694,7 @@ fn parse_sse_frame(
            retryable: false,
            suggested_action: Some("verify the API endpoint URL is correct".to_string()),
            retry_after: None,
-        })));
+        });
    }
    serde_json::from_str::<ChatCompletionChunk>(&payload)
        .map(Some)
@@ -1754,7 +1754,7 @@ async fn expect_success(response: reqwest::Response) -> Result<reqwest::Response

    let suggested_action = suggested_action_for_status(status);

-    Err(ApiError::Api(Box::new(ApiErrorDetails {
+    Err(ApiError::Api {
        status,
        error_type: parsed_error
            .as_ref()
@@ -1767,7 +1767,7 @@ async fn expect_success(response: reqwest::Response) -> Result<reqwest::Response
        retryable,
        suggested_action,
        retry_after,
-    })))
+    })
 }

 fn parse_retry_after(
@@ -585,11 +585,14 @@ async fn surfaces_retry_exhaustion_for_persistent_retryable_errors() {
            last_error,
        } => {
            assert_eq!(attempts, 2);
-            let details = last_error
-                .api_details()
-                .expect("last error should be a provider Api error");
-            assert_eq!(details.status, reqwest::StatusCode::SERVICE_UNAVAILABLE);
-            assert!(details.retryable);
+            assert!(matches!(
+                *last_error,
+                ApiError::Api {
+                    status: reqwest::StatusCode::SERVICE_UNAVAILABLE,
+                    retryable: true,
+                    ..
+                }
+            ));
        }
        other => panic!("expected retries exhausted, got {other:?}"),
    }
@@ -166,8 +166,8 @@ pub fn blob_to_f32_vec(blob: &[u8], dim: usize) -> Option<Vec<f32>> {
        return None;
    }
    let mut v = Vec::with_capacity(dim);
-    for chunk in blob.chunks_exact(4) {
-        v.push(f32::from_le_bytes([chunk[0], chunk[1], chunk[2], chunk[3]]));
+    for chunk in blob.as_chunks::<4>().0 {
+        v.push(f32::from_le_bytes(*chunk));
    }
    Some(v)
 }
@@ -808,7 +808,7 @@ const SLASH_COMMAND_SPECS: &[SlashCommandSpec] = &[
        name: "team",
        aliases: &[],
        summary: "Manage agent teams",
-        argument_hint: Some("[list|create|delete]"),
+        argument_hint: Some("[on|off|status]"),
        resume_supported: true,
    },
    SlashCommandSpec {
@@ -1188,10 +1188,14 @@ pub enum SlashCommand {
    History {
        count: Option<String>,
    },
-    Unknown(String),
+    Lsp {
+        action: Option<String>,
+        target: Option<String>,
+    },
    Team {
        action: Option<String>,
    },
+    Unknown(String),
 }

 #[derive(Debug, Clone, PartialEq, Eq)]
@@ -1509,6 +1513,9 @@ pub fn validate_slash_command_input(
        "history" => SlashCommand::History {
            count: optional_single_arg(command, &args, "[count]")?,
        },
+        "team" => SlashCommand::Team {
+            action: optional_single_arg(command, &args, "[list|create|delete]")?,
+        },
        other => SlashCommand::Unknown(other.to_string()),
    }))
 }
@@ -5393,6 +5400,7 @@ pub fn handle_slash_command(
        | SlashCommand::OutputStyle { .. }
        | SlashCommand::AddDir { .. }
        | SlashCommand::History { .. }
+        | SlashCommand::Lsp { .. }
        | SlashCommand::Team { .. }
        | SlashCommand::Setup
        | SlashCommand::Unknown(_) => None,
@@ -5525,6 +5533,16 @@ mod tests {
    #[test]
    fn parses_supported_slash_commands() {
        assert_eq!(SlashCommand::parse("/help"), Ok(Some(SlashCommand::Help)));
+        assert_eq!(
+            SlashCommand::parse("/team"),
+            Ok(Some(SlashCommand::Team { action: None }))
+        );
+        assert_eq!(
+            SlashCommand::parse("/team on"),
+            Ok(Some(SlashCommand::Team {
+                action: Some("on".to_string())
+            }))
+        );
        assert_eq!(
            SlashCommand::parse(" /status "),
            Ok(Some(SlashCommand::Status))
@@ -95,21 +95,10 @@ pub fn get_compact_continuation_message(
 #[must_use]
 pub fn compact_session(session: &Session, config: CompactionConfig) -> CompactionResult {
    if !should_compact(session, config) {
-        // "Nothing to drop" is not the same as "nothing to do". A session can exceed the window
-        // while holding fewer messages than `preserve_recent_messages` — a single read of a large
-        // file does it — and message-granular compaction has no move to make there. Trim the
-        // payloads anyway, so the one lever that still works is not gated behind the one that
-        // does not.
-        let mut trimmed_session = session.clone();
-        trimmed_session.messages = session
-            .messages
-            .iter()
-            .map(truncate_oversized_tool_results)
-            .collect();
        return CompactionResult {
            summary: String::new(),
            formatted_summary: String::new(),
-            compacted_session: trimmed_session,
+            compacted_session: session.clone(),
            removed_message_count: 0,
        };
    }
@@ -176,14 +165,7 @@ pub fn compact_session(session: &Session, config: CompactionConfig) -> Compactio
        k
    };
    let removed = &session.messages[compacted_prefix_len..keep_from];
-    // Dropping whole messages is not enough on its own. An agentic turn is five messages
-    // (user / assistant+tool_use / tool_result / assistant+tool_use / tool_result), so the
-    // preserved tail IS the pair of tool results that overflowed the window, and the only
-    // message compaction may drop is the short user prompt. Trim the payloads that must stay.
-    let preserved = session.messages[keep_from..]
-        .iter()
-        .map(truncate_oversized_tool_results)
-        .collect::<Vec<_>>();
+    let preserved = session.messages[keep_from..].to_vec();
    let summary =
        merge_compact_summaries(existing_summary.as_deref(), &summarize_messages(removed));
    let formatted_summary = format_compact_summary(&summary);
@@ -208,78 +190,6 @@ pub fn compact_session(session: &Session, config: CompactionConfig) -> Compactio
    }
 }

-/// Largest tool-result payload compaction will preserve verbatim, in characters.
-///
-/// ~16 KB is ~4 k tokens: big enough that ordinary tool output is never touched, small enough
-/// that several preserved results still fit a small window.
-const MAX_PRESERVED_TOOL_RESULT_CHARS: usize = 16 * 1024;
-
-/// Characters kept from the tail of a trimmed payload. The head carries the structure a model
-/// needs to recognise what it read; the tail is where a file's most recent edits usually are.
-const PRESERVED_TOOL_RESULT_TAIL_CHARS: usize = 2 * 1024;
-
-/// Returns `message` with any oversized `ToolResult` payload replaced by a head/tail excerpt.
-///
-/// Clones only when something is actually trimmed, so the common path stays cheap.
-fn truncate_oversized_tool_results(message: &ConversationMessage) -> ConversationMessage {
-    let needs_trim = message.blocks.iter().any(|block| match block {
-        ContentBlock::ToolResult { output, .. } => {
-            output.chars().count() > MAX_PRESERVED_TOOL_RESULT_CHARS
-        }
-        _ => false,
-    });
-    if !needs_trim {
-        return message.clone();
-    }
-
-    let blocks = message
-        .blocks
-        .iter()
-        .map(|block| match block {
-            ContentBlock::ToolResult {
-                tool_use_id,
-                tool_name,
-                output,
-                is_error,
-            } => ContentBlock::ToolResult {
-                tool_use_id: tool_use_id.clone(),
-                tool_name: tool_name.clone(),
-                output: excerpt_tool_result(output),
-                is_error: *is_error,
-            },
-            other => other.clone(),
-        })
-        .collect();
-
-    ConversationMessage {
-        role: message.role,
-        blocks,
-        usage: message.usage,
-    }
-}
-
-/// Builds a head + marker + tail excerpt of an oversized tool-result payload.
-///
-/// Operates on chars, not bytes, so a multi-byte boundary can never be split.
-fn excerpt_tool_result(output: &str) -> String {
-    let chars: Vec<char> = output.chars().collect();
-    let total = chars.len();
-    if total <= MAX_PRESERVED_TOOL_RESULT_CHARS {
-        return output.to_string();
-    }
-
-    let tail_len = PRESERVED_TOOL_RESULT_TAIL_CHARS.min(total);
-    let head_len = MAX_PRESERVED_TOOL_RESULT_CHARS.saturating_sub(tail_len);
-    let elided = total.saturating_sub(head_len + tail_len);
-    if elided == 0 {
-        return output.to_string();
-    }
-
-    let head: String = chars[..head_len].iter().collect();
-    let tail: String = chars[total - tail_len..].iter().collect();
-    format!("{head}\n\n[... {elided} characters elided by compaction; re-read this file if you need the omitted portion ...]\n\n{tail}")
-}
-
 fn compacted_summary_prefix_len(session: &Session) -> usize {
    usize::from(
        session
@@ -663,7 +573,7 @@ fn extract_summary_timeline(summary: &str) -> Vec<String> {
 #[cfg(test)]
 mod tests {
    use super::{
-        collect_key_files, compact_session, estimate_session_tokens, format_compact_summary,
+        collect_key_files, compact_session, format_compact_summary,
        get_compact_continuation_message, infer_pending_work, should_compact, CompactionConfig,
    };
    use crate::session::{ContentBlock, ConversationMessage, MessageRole, Session};
@@ -853,185 +763,6 @@ mod tests {
    /// user(ToolResult) pair at the boundary. An orphaned tool-result message
    /// without the preceding assistant `tool_calls` causes a 400 on the
    /// OpenAI-compat path (gaebal-gajae repro 2026-04-09).
-    /// The failure this exists for: an agentic turn is 5 messages (user / assistant+tool_use /
-    /// tool_result / assistant+tool_use / tool_result), so `preserve_recent_messages: 4` protects
-    /// exactly the two giant tool results that overflow the window. Message-granular compaction
-    /// can only drop the tiny user prompt, so the payloads themselves must be trimmed.
-    #[test]
-    fn compaction_truncates_oversized_tool_results_it_must_preserve() {
-        let huge = "z".repeat(80_000);
-        let mut session = Session::new();
-        session
-            .push_message(ConversationMessage::user_text("read two files"))
-            .expect("user message");
-        session
-            .push_message(ConversationMessage::assistant(vec![
-                ContentBlock::ToolUse {
-                    id: "call-1".to_string(),
-                    name: "read_file".to_string(),
-                    input: "{\"path\":\"a.rs\"}".to_string(),
-                },
-            ]))
-            .expect("assistant tool use");
-        session
-            .push_message(ConversationMessage::tool_result(
-                "call-1",
-                "read_file",
-                huge.clone(),
-                false,
-            ))
-            .expect("tool result");
-        session
-            .push_message(ConversationMessage::assistant(vec![
-                ContentBlock::ToolUse {
-                    id: "call-2".to_string(),
-                    name: "read_file".to_string(),
-                    input: "{\"path\":\"b.rs\"}".to_string(),
-                },
-            ]))
-            .expect("second assistant tool use");
-        session
-            .push_message(ConversationMessage::tool_result(
-                "call-2",
-                "read_file",
-                huge.clone(),
-                false,
-            ))
-            .expect("second tool result");
-
-        let before = estimate_session_tokens(&session);
-        let result = compact_session(
-            &session,
-            CompactionConfig {
-                preserve_recent_messages: 4,
-                max_estimated_tokens: 0,
-            },
-        );
-        let after = estimate_session_tokens(&result.compacted_session);
-
-        assert!(
-            after < before / 2,
-            "compaction must shrink an oversized preserved tool result: {before} -> {after}"
-        );
-
-        let preserved_output = result
-            .compacted_session
-            .messages
-            .iter()
-            .flat_map(|message| &message.blocks)
-            .find_map(|block| match block {
-                ContentBlock::ToolResult { output, .. } => Some(output.clone()),
-                _ => None,
-            })
-            .expect("the tool result must still be present, not deleted");
-
-        assert!(
-            preserved_output.len() < huge.len(),
-            "the payload must actually be trimmed"
-        );
-        assert!(
-            preserved_output.contains("elided"),
-            "the model must be told the view is partial, got: {}",
-            &preserved_output[..preserved_output.len().min(200)]
-        );
-        assert!(
-            preserved_output.starts_with('z'),
-            "the head of the output must be kept"
-        );
-        assert!(
-            preserved_output.ends_with('z'),
-            "the tail of the output must be kept"
-        );
-    }
-
-    /// A session can exceed the window while holding FEWER messages than
-    /// `preserve_recent_messages` — one read of a large file does it. `should_compact` returns
-    /// false there (nothing is droppable), so trimming must not be gated behind it.
-    #[test]
-    fn oversized_tool_results_are_trimmed_even_when_no_message_can_be_dropped() {
-        let huge = "q".repeat(80_000);
-        let mut session = Session::new();
-        session
-            .push_message(ConversationMessage::user_text("read one enormous file"))
-            .expect("user message");
-        session
-            .push_message(ConversationMessage::assistant(vec![
-                ContentBlock::ToolUse {
-                    id: "call-1".to_string(),
-                    name: "read_file".to_string(),
-                    input: "{\"path\":\"huge.rs\"}".to_string(),
-                },
-            ]))
-            .expect("assistant tool use");
-        session
-            .push_message(ConversationMessage::tool_result(
-                "call-1",
-                "read_file",
-                huge,
-                false,
-            ))
-            .expect("tool result");
-
-        // 3 messages, preserve 4: there is nothing to remove, yet the session is far too big.
-        let before = estimate_session_tokens(&session);
-        let result = compact_session(
-            &session,
-            CompactionConfig {
-                preserve_recent_messages: 4,
-                max_estimated_tokens: 0,
-            },
-        );
-        let after = estimate_session_tokens(&result.compacted_session);
-
-        assert!(
-            after < before / 2,
-            "an untrimmable session must still have its payloads trimmed: {before} -> {after}"
-        );
-    }
-
-    /// Trimming must not touch payloads that already fit — otherwise every ordinary tool result
-    /// would grow an elision marker it does not need.
-    #[test]
-    fn compaction_leaves_small_tool_results_untouched() {
-        let small = "ok".repeat(50);
-        let mut session = Session::new();
-        for index in 0..6 {
-            session
-                .push_message(ConversationMessage::user_text(format!("turn {index}")))
-                .expect("user message");
-            session
-                .push_message(ConversationMessage::tool_result(
-                    format!("call-{index}"),
-                    "read_file",
-                    small.clone(),
-                    false,
-                ))
-                .expect("tool result");
-        }
-
-        let result = compact_session(
-            &session,
-            CompactionConfig {
-                preserve_recent_messages: 4,
-                max_estimated_tokens: 0,
-            },
-        );
-
-        for block in result
-            .compacted_session
-            .messages
-            .iter()
-            .flat_map(|message| &message.blocks)
-        {
-            if let ContentBlock::ToolResult { output, .. } = block {
-                assert_eq!(
-                    output, &small,
-                    "a small tool result must pass through as-is"
-                );
-            }
-        }
-    }
-
    #[test]
    fn compaction_does_not_split_tool_use_tool_result_pair() {
        use crate::session::{ContentBlock, Session};
@@ -1095,7 +826,7 @@ mod tests {
                    "message[{}] is a ToolResult but message[{}] has no ToolUse: {:?}",
                    i,
                    i - 1,
-                    &messages[i - 1].blocks
+                    messages[i - 1].blocks
                );
            }
        }
@@ -164,6 +164,20 @@ pub struct RuntimeFeatureConfig {
    rules_import: RulesImportConfig,
    provider: RuntimeProviderConfig,
    auto_memory_enabled: bool,
+    /// Model override used when spawning sub-agents via the Agent tool.
+    /// Read from `subagentModel` (or `subagent_model`) in settings; falls
+    /// back to the default model when unset.
+    subagent_model: Option<String>,
+    /// Cap on concurrently executing parallel-safe tool calls in one batch.
+    /// Read from `maxParallelToolCalls` (or `max_parallel_tool_calls`) in
+    /// settings; the CLI falls back to `CLAWD_PARALLEL_TOOL_CALLS` and then
+    /// to its built-in default when unset.
+    max_parallel_tool_calls: Option<usize>,
+    /// Default cap on concurrently *running* sub-agents per team. Read from
+    /// `maxConcurrentAgents` (or `max_concurrent_agents`) in settings; a
+    /// per-team `maxConcurrentAgents` on TeamCreate overrides it. `None`
+    /// means no gate (current pre-fix behavior).
+    max_concurrent_agents: Option<usize>,
 }

 /// Controls which external AI coding framework rules are imported into the system prompt.
@@ -832,6 +846,15 @@ fn build_runtime_config(
        rules_import: parse_optional_rules_import(&merged_value)?,
        provider: parse_optional_provider_config(&merged_value)?,
        auto_memory_enabled: parse_auto_memory_enabled(&merged_value),
+        subagent_model: parse_optional_subagent_model(&merged_value),
+        max_parallel_tool_calls: parse_optional_positive_usize(
+            &merged_value,
+            &["maxParallelToolCalls", "max_parallel_tool_calls"],
+        )?,
+        max_concurrent_agents: parse_optional_positive_usize(
+            &merged_value,
+            &["maxConcurrentAgents", "max_concurrent_agents"],
+        )?,
    };

    Ok(RuntimeConfig {
@@ -914,6 +937,29 @@ impl RuntimeConfig {
        self.feature_config.model.as_deref()
    }

+    /// Model override used when spawning sub-agents via the Agent tool.
+    /// Read from `subagentModel` in settings; `None` means "use default model".
+    #[must_use]
+    pub fn subagent_model(&self) -> Option<&str> {
+        self.feature_config.subagent_model.as_deref()
+    }
+
+    /// Cap on concurrently executing parallel-safe tool calls in one batch.
+    /// Read from `maxParallelToolCalls` in settings; `None` means the CLI
+    /// falls back to `CLAWD_PARALLEL_TOOL_CALLS` and then its built-in default.
+    #[must_use]
+    pub fn max_parallel_tool_calls(&self) -> Option<usize> {
+        self.feature_config.max_parallel_tool_calls
+    }
+
+    /// Default cap on concurrently running sub-agents per team. Read from
+    /// `maxConcurrentAgents` in settings; `None` means the built-in default
+    /// applies. A per-team `maxConcurrentAgents` on TeamCreate overrides it.
+    #[must_use]
+    pub fn max_concurrent_agents(&self) -> Option<usize> {
+        self.feature_config.max_concurrent_agents
+    }
+
    #[must_use]
    pub fn aliases(&self) -> &BTreeMap<String, String> {
        &self.feature_config.aliases
@@ -974,6 +1020,20 @@ impl RuntimeFeatureConfig {
        &self.provider
    }

+    /// Cap on concurrently executing parallel-safe tool calls in one batch.
+    /// `None` means fall back to env/default.
+    #[must_use]
+    pub fn max_parallel_tool_calls(&self) -> Option<usize> {
+        self.max_parallel_tool_calls
+    }
+
+    /// Default per-team cap on concurrently running sub-agents; `None`
+    /// means unlimited (pre-fix behavior).
+    #[must_use]
+    pub fn max_concurrent_agents(&self) -> Option<usize> {
+        self.max_concurrent_agents
+    }
+
    #[must_use]
    pub fn with_hooks(mut self, hooks: RuntimeHookConfig) -> Self {
        self.hooks = hooks;
@@ -1756,6 +1816,51 @@ fn parse_optional_model(root: &JsonValue) -> Option<String> {
        .map(ToOwned::to_owned)
 }

+/// Reads `subagentModel` (or the snake_case `subagent_model` alias) from
+/// merged settings. Returns `None` when absent or blank so the Agent tool
+/// falls back to the default model.
+fn parse_optional_subagent_model(root: &JsonValue) -> Option<String> {
+    root.as_object()
+        .and_then(|object| {
+            object
+                .get("subagentModel")
+                .or_else(|| object.get("subagent_model"))
+        })
+        .and_then(JsonValue::as_str)
+        .filter(|s| !s.trim().is_empty())
+        .map(|s| s.trim().to_string())
+}
+
+/// Reads the first present key from `keys` as a positive integer.
+/// Absent, null, or non-positive values parse to `None` so callers fall
+/// back to their own defaults rather than silently disabling a cap via a
+/// `0` typo. Accepts JSON numbers or numeric strings.
+fn parse_optional_positive_usize(
+    root: &JsonValue,
+    keys: &[&str],
+) -> Result<Option<usize>, ConfigError> {
+    let Some(object) = root.as_object() else {
+        return Ok(None);
+    };
+    for key in keys {
+        let Some(value) = object.get(*key) else {
+            continue;
+        };
+        if matches!(value, JsonValue::Null) {
+            continue;
+        }
+        let parsed = value
+            .as_i64()
+            .or_else(|| value.as_str().and_then(|s| s.trim().parse::<i64>().ok()))
+            .ok_or_else(|| ConfigError::Parse(format!("{key} must be a positive integer")))?;
+        if parsed <= 0 {
+            return Ok(None);
+        }
+        return Ok(usize::try_from(parsed).ok());
+    }
+    Ok(None)
+}
+
 fn parse_optional_aliases(root: &JsonValue) -> Result<BTreeMap<String, String>, ConfigError> {
    let Some(object) = root.as_object() else {
        return Ok(BTreeMap::new());
@@ -2627,6 +2732,49 @@ fn deep_merge_objects(
    }
 }

+/// Read the provider config saved by `/setup` and inject its credentials
+/// into the environment so `ProviderClient::from_model()` can find them via
+/// the env-var-based provider dispatch. Only sets vars that aren't already
+/// present (preserves explicit env). Idempotent.
+///
+/// Called by the main CLI at startup and by sub-agent threads in the tools
+/// crate so that custom/ exotic providers work for spawned agents too.
+pub fn inject_config_as_env_fallbacks() {
+    let cwd = std::env::current_dir().unwrap_or_default();
+    let Ok(config) = ConfigLoader::default_for(&cwd).load() else {
+        return;
+    };
+    let provider = config.provider();
+
+    // Map provider kind to the expected env var names
+    let (api_key_env, base_url_env) = match provider.kind().unwrap_or("anthropic") {
+        "anthropic" => ("ANTHROPIC_API_KEY", "ANTHROPIC_BASE_URL"),
+        "xai" => ("XAI_API_KEY", "XAI_BASE_URL"),
+        "openai" => ("OPENAI_API_KEY", "OPENAI_BASE_URL"),
+        "dashscope" => ("DASHSCOPE_API_KEY", "DASHSCOPE_BASE_URL"),
+        "custom-openai" => ("CLAWCUSTOMOPENAI_API_KEY", "CLAWCUSTOMOPENAI_BASE_URL"),
+        _ => return, // unknown provider kind — don't inject
+    };
+
+    // Only set env vars that aren't already set (preserve user's explicit env)
+    if let Some(api_key) = provider.api_key() {
+        if std::env::var(api_key_env).is_err() {
+            std::env::set_var(api_key_env, api_key);
+        }
+    }
+    if let Some(base_url) = provider.base_url() {
+        if std::env::var(base_url_env).is_err() {
+            std::env::set_var(base_url_env, base_url);
+        }
+    }
+    // Also inject the saved model so resolve_model_alias sees it
+    if let Some(model) = provider.model() {
+        if std::env::var("CLAWD_PROVIDER_MODEL").is_err() {
+            std::env::set_var("CLAWD_PROVIDER_MODEL", model);
+        }
+    }
+}
+
 #[cfg(test)]
 mod tests {
    use super::{
@@ -3988,4 +4136,151 @@ mod tests {

        fs::remove_dir_all(root).expect("cleanup temp dir");
    }
+
+    #[test]
+    fn subagent_model_reads_camel_case_config_key() {
+        let root = temp_dir();
+        let cwd = root.join("project");
+        let home = root.join("home").join(".claw");
+        fs::create_dir_all(&home).expect("home config dir");
+        fs::create_dir_all(&cwd).expect("project dir");
+        fs::write(
+            home.join("settings.json"),
+            "{\n  \"subagentModel\": \"custom/openclaw\"\n}\n",
+        )
+        .expect("write settings");
+
+        let config = ConfigLoader::new(&cwd, &home)
+            .load()
+            .expect("config should load");
+        assert_eq!(
+            config.subagent_model(),
+            Some("custom/openclaw"),
+            "subagentModel camelCase key should be read end-to-end"
+        );
+
+        fs::remove_dir_all(root).expect("cleanup temp dir");
+    }
+
+    #[test]
+    fn subagent_model_reads_snake_case_config_key() {
+        let root = temp_dir();
+        let cwd = root.join("project");
+        let home = root.join("home").join(".claw");
+        fs::create_dir_all(&home).expect("home config dir");
+        fs::create_dir_all(&cwd).expect("project dir");
+        fs::write(
+            home.join("settings.json"),
+            "{\n  \"subagent_model\": \"qwen3.6-35b-fast\"\n}\n",
+        )
+        .expect("write settings");
+
+        let config = ConfigLoader::new(&cwd, &home)
+            .load()
+            .expect("config should load");
+        assert_eq!(
+            config.subagent_model(),
+            Some("qwen3.6-35b-fast"),
+            "subagent_model snake_case key should be read end-to-end"
+        );
+
+        fs::remove_dir_all(root).expect("cleanup temp dir");
+    }
+
+    #[test]
+    fn subagent_model_blank_value_returns_none() {
+        let root = temp_dir();
+        let cwd = root.join("project");
+        let home = root.join("home").join(".claw");
+        fs::create_dir_all(&home).expect("home config dir");
+        fs::create_dir_all(&cwd).expect("project dir");
+        fs::write(
+            home.join("settings.json"),
+            "{\n  \"subagentModel\": \"  \"\n}\n",
+        )
+        .expect("write settings");
+
+        let config = ConfigLoader::new(&cwd, &home)
+            .load()
+            .expect("config should load");
+        assert_eq!(
+            config.subagent_model(),
+            None,
+            "blank subagentModel should fall back to None"
+        );
+
+        fs::remove_dir_all(root).expect("cleanup temp dir");
+    }
+
+    #[test]
+    fn parallel_and_agent_caps_read_camel_and_snake_case_keys() {
+        let root = temp_dir();
+        let cwd = root.join("project");
+        let home = root.join("home").join(".claw");
+        fs::create_dir_all(&home).expect("home config dir");
+        fs::create_dir_all(&cwd).expect("project dir");
+        fs::write(
+            home.join("settings.json"),
+            "{\n  \"maxParallelToolCalls\": 4,\n  \"max_concurrent_agents\": \"6\"\n}\n",
+        )
+        .expect("write settings");
+
+        let config = ConfigLoader::new(&cwd, &home)
+            .load()
+            .expect("config should load");
+        assert_eq!(
+            config.max_parallel_tool_calls(),
+            Some(4),
+            "maxParallelToolCalls camelCase key should parse"
+        );
+        assert_eq!(
+            config.max_concurrent_agents(),
+            Some(6),
+            "max_concurrent_agents snake_case key should parse numeric strings"
+        );
+
+        fs::remove_dir_all(root).expect("cleanup temp dir");
+    }
+
+    #[test]
+    fn parallel_and_agent_caps_reject_nonpositive_and_malformed() {
+        let root = temp_dir();
+        let cwd = root.join("project");
+        let home = root.join("home").join(".claw");
+        fs::create_dir_all(&home).expect("home config dir");
+        fs::create_dir_all(&cwd).expect("project dir");
+        fs::write(
+            home.join("settings.json"),
+            "{\n  \"maxParallelToolCalls\": 0\n}\n",
+        )
+        .expect("write settings");
+
+        let config = ConfigLoader::new(&cwd, &home)
+            .load()
+            .expect("zero cap should parse as unset");
+        assert_eq!(config.max_parallel_tool_calls(), None);
+        assert_eq!(config.max_concurrent_agents(), None);
+        fs::remove_dir_all(&root).expect("cleanup temp dir");
+
+        let root = temp_dir();
+        let cwd = root.join("project");
+        let home = root.join("home").join(".claw");
+        fs::create_dir_all(&home).expect("home config dir");
+        fs::create_dir_all(&cwd).expect("project dir");
+        fs::write(
+            home.join("settings.json"),
+            "{\n  \"maxParallelToolCalls\": \"lots\"\n}\n",
+        )
+        .expect("write settings");
+
+        let error = ConfigLoader::new(&cwd, &home)
+            .load()
+            .expect_err("non-numeric cap should be a config error");
+        assert!(
+            error.to_string().contains("maxParallelToolCalls"),
+            "error should name the offending key: {error}"
+        );
+
+        fs::remove_dir_all(root).expect("cleanup temp dir");
+    }
 }
@@ -11,48 +11,8 @@ use serde::{Deserialize, Serialize};
 use walkdir::{DirEntry, WalkDir};

 /// Maximum file size that can be read (10 MB).
-///
-/// This is a *process* guard — it stops us slurping a huge or binary blob into memory. It is
-/// not a context guard: 10 MB is on the order of 2.5 M tokens, so it never fires on the files
-/// that actually blow a model's context window. `DEFAULT_READ_LINES` / `MAX_READ_CHARS` below
-/// are the context guard.
 const MAX_READ_SIZE: u64 = 10 * 1024 * 1024;

-/// Lines returned by `read_file` when the caller does not pass an explicit `limit`.
-///
-/// This is a *paging* size, not a refusal. An unbounded read is the easiest way for a model to
-/// destroy its own context: one 100 KB source file is ~25 k tokens, which does not fit alongside
-/// a system prompt in a 32 k window. When that happens the backend rejects the whole request and
-/// the session dies — so reading everything at once is what makes it stop. Returning a page plus
-/// `nextOffset` means the read always succeeds and the model can keep going.
-const DEFAULT_READ_LINES: usize = 2000;
-
-/// Hard ceiling on the characters `read_file` returns, applied even when `limit` is explicit.
-///
-/// `DEFAULT_READ_LINES` alone does not bound the payload: minified bundles, JSON blobs and
-/// generated sources routinely put megabytes on a handful of lines. ~64 KB is ~16 k tokens.
-///
-/// That default assumes a large (200 k) context window. Against a small self-hosted backend it
-/// is far too generous: two reads at this size put a request over 47 k tokens, which a 32 k
-/// window rejects outright — and compaction cannot recover it, because the preserved recent
-/// messages ARE the oversized tool results. Override with [`MAX_READ_CHARS_ENV_VAR`].
-const DEFAULT_MAX_READ_CHARS: usize = 64 * 1024;
-
-/// Environment override for [`DEFAULT_MAX_READ_CHARS`], in characters.
-const MAX_READ_CHARS_ENV_VAR: &str = "CLAW_MAX_READ_CHARS";
-
-/// Effective character ceiling for one `read_file` page.
-///
-/// Read per call rather than cached: a long-lived process should pick up a changed budget, and
-/// this runs once per read, not per line.
-fn max_read_chars() -> usize {
-    std::env::var(MAX_READ_CHARS_ENV_VAR)
-        .ok()
-        .and_then(|raw| raw.trim().parse::<usize>().ok())
-        .filter(|chars| *chars > 0)
-        .unwrap_or(DEFAULT_MAX_READ_CHARS)
-}
-
 /// Maximum file size that can be written (10 MB).
 const MAX_WRITE_SIZE: usize = 10 * 1024 * 1024;

@@ -120,17 +80,6 @@ pub struct TextFilePayload {
    pub start_line: usize,
    #[serde(rename = "totalLines")]
    pub total_lines: usize,
-    /// True when the file has more lines past this page. Signals the caller that it has NOT seen
-    /// the whole file, so it does not silently reason over a partial view.
-    #[serde(default)]
-    pub truncated: bool,
-    /// Line index to pass back as `offset` to continue reading. Absent once the file is exhausted.
-    #[serde(
-        rename = "nextOffset",
-        default,
-        skip_serializing_if = "Option::is_none"
-    )]
-    pub next_offset: Option<usize>,
 }

 /// Output envelope for the `read_file` tool.
@@ -279,28 +228,10 @@ pub fn read_file(
    let content = fs::read_to_string(&absolute_path)?;
    let lines: Vec<&str> = content.lines().collect();
    let start_index = offset.unwrap_or(0).min(lines.len());
-    // An absent `limit` pages rather than reading to EOF: see DEFAULT_READ_LINES.
-    let requested_end = start_index
-        .saturating_add(limit.unwrap_or(DEFAULT_READ_LINES))
-        .min(lines.len());
-
-    // Apply the character ceiling on top of the line window, so a file with very long lines
-    // cannot blow the budget the line cap was meant to enforce. Always yield at least one line,
-    // otherwise an oversized single line would return nothing and the caller could not advance.
-    let mut end_index = start_index;
-    let mut chars = 0usize;
-    let char_ceiling = max_read_chars();
-    for line in &lines[start_index..requested_end] {
-        let next = chars + line.chars().count() + 1;
-        if next > char_ceiling && end_index > start_index {
-            break;
-        }
-        chars = next;
-        end_index += 1;
-    }
-
+    let end_index = limit.map_or(lines.len(), |limit| {
+        start_index.saturating_add(limit).min(lines.len())
+    });
    let selected = lines[start_index..end_index].join("\n");
-    let truncated = end_index < lines.len();

    Ok(ReadFileOutput {
        kind: String::from("text"),
@@ -310,8 +241,6 @@ pub fn read_file(
            num_lines: end_index.saturating_sub(start_index),
            start_line: start_index.saturating_add(1),
            total_lines: lines.len(),
-            truncated,
-            next_offset: truncated.then_some(end_index),
        },
    })
 }
@@ -883,18 +812,11 @@ mod tests {

    use super::{
        component_contains_glob, derive_glob_walk_root, edit_file, expand_braces, glob_search,
-        grep_search, is_symlink_escape, max_read_chars, normalize_for_comparison, read_file,
+        grep_search, is_symlink_escape, normalize_for_comparison, read_file,
        read_file_in_workspace, write_file, write_file_in_workspace, GrepSearchInput,
-        DEFAULT_MAX_READ_CHARS, DEFAULT_READ_LINES, MAX_READ_CHARS_ENV_VAR, MAX_WRITE_SIZE,
+        MAX_WRITE_SIZE,
    };

-    /// Serializes the tests that mutate `CLAW_MAX_READ_CHARS`; env vars are process-global.
-    fn env_lock() -> std::sync::MutexGuard<'static, ()> {
-        static LOCK: std::sync::Mutex<()> = std::sync::Mutex::new(());
-        LOCK.lock()
-            .unwrap_or_else(std::sync::PoisonError::into_inner)
-    }
-
    fn temp_path(name: &str) -> std::path::PathBuf {
        let unique = SystemTime::now()
            .duration_since(UNIX_EPOCH)
@@ -915,132 +837,6 @@ mod tests {
        assert_eq!(read_output.file.content, "two");
    }

-    #[test]
-    fn unbounded_read_of_a_large_file_pages_instead_of_returning_everything() {
-        // Regression: an unbounded read used to return the whole file, which on a small-context
-        // backend overflows the window and the request is rejected outright — the session dies.
-        let path = temp_path("paged-read.txt");
-        let total = DEFAULT_READ_LINES + 500;
-        let body = (0..total)
-            .map(|i| format!("line {i}"))
-            .collect::<Vec<_>>()
-            .join("\n");
-        write_file(path.to_string_lossy().as_ref(), &body).expect("write should succeed");
-
-        let first = read_file(path.to_string_lossy().as_ref(), None, None).expect("first page");
-        assert_eq!(first.file.num_lines, DEFAULT_READ_LINES);
-        assert_eq!(first.file.total_lines, total);
-        assert!(first.file.truncated, "caller must be told it is partial");
-        assert_eq!(first.file.next_offset, Some(DEFAULT_READ_LINES));
-        assert!(first.file.content.starts_with("line 0\n"));
-
-        // The advertised next_offset must actually resume where the last page stopped.
-        let second = read_file(
-            path.to_string_lossy().as_ref(),
-            first.file.next_offset,
-            None,
-        )
-        .expect("second page");
-        assert_eq!(second.file.num_lines, 500);
-        assert!(!second.file.truncated, "the tail is the final page");
-        assert_eq!(second.file.next_offset, None);
-        assert!(second
-            .file
-            .content
-            .starts_with(&format!("line {DEFAULT_READ_LINES}\n")));
-    }
-
-    #[test]
-    fn char_ceiling_bounds_files_whose_lines_are_enormous() {
-        // A line cap alone does not bound the payload: minified bundles put megabytes on a few
-        // lines, so the byte ceiling has to apply too — and must still yield forward progress.
-        let _guard = env_lock();
-        std::env::remove_var(MAX_READ_CHARS_ENV_VAR);
-        let path = temp_path("long-lines.txt");
-        let huge = "x".repeat(DEFAULT_MAX_READ_CHARS);
-        let body = format!("{huge}\n{huge}\n{huge}");
-        write_file(path.to_string_lossy().as_ref(), &body).expect("write should succeed");
-
-        let page = read_file(path.to_string_lossy().as_ref(), None, None).expect("first page");
-        assert_eq!(page.file.num_lines, 1, "one oversized line still advances");
-        assert!(page.file.truncated);
-        assert_eq!(page.file.next_offset, Some(1));
-
-        // An explicit limit must not be able to defeat the ceiling.
-        let greedy = read_file(path.to_string_lossy().as_ref(), None, Some(3)).expect("greedy");
-        assert_eq!(greedy.file.num_lines, 1);
-        assert!(greedy.file.truncated);
-    }
-
-    /// The 64 KB default is a 200 k-context number. A small self-hosted backend must be able to
-    /// shrink it, or two reads overflow a 32 k window in a single turn.
-    #[test]
-    fn read_char_ceiling_is_configurable_via_the_environment() {
-        let _guard = env_lock();
-        let path = temp_path("configurable-ceiling.txt");
-        // 40 lines of 100 chars = ~4 KB: far under the default ceiling, over a 1 KB one.
-        let body = (0..40)
-            .map(|_| "y".repeat(100))
-            .collect::<Vec<_>>()
-            .join("\n");
-        write_file(path.to_string_lossy().as_ref(), &body).expect("write should succeed");
-
-        std::env::remove_var(MAX_READ_CHARS_ENV_VAR);
-        let whole = read_file(path.to_string_lossy().as_ref(), None, None).expect("default read");
-        assert_eq!(
-            whole.file.num_lines, 40,
-            "default ceiling returns the file whole"
-        );
-        assert!(!whole.file.truncated);
-
-        std::env::set_var(MAX_READ_CHARS_ENV_VAR, "1024");
-        let clipped = read_file(path.to_string_lossy().as_ref(), None, None).expect("clipped read");
-        std::env::remove_var(MAX_READ_CHARS_ENV_VAR);
-        assert!(
-            clipped.file.num_lines < 40,
-            "a smaller ceiling must actually clip, got {} lines",
-            clipped.file.num_lines
-        );
-        assert!(
-            clipped.file.truncated,
-            "a clipped page must report truncated"
-        );
-        assert_eq!(
-            clipped.file.next_offset,
-            Some(clipped.file.num_lines),
-            "the caller must be told where to resume"
-        );
-    }
-
-    #[test]
-    fn read_char_ceiling_ignores_junk_and_zero_values() {
-        let _guard = env_lock();
-        for value in ["", "0", "-5", "not-a-number"] {
-            std::env::set_var(MAX_READ_CHARS_ENV_VAR, value);
-            assert_eq!(
-                max_read_chars(),
-                DEFAULT_MAX_READ_CHARS,
-                "{value:?} must fall back to the default rather than disabling reads"
-            );
-        }
-        std::env::set_var(MAX_READ_CHARS_ENV_VAR, "24000");
-        assert_eq!(max_read_chars(), 24_000);
-        std::env::remove_var(MAX_READ_CHARS_ENV_VAR);
-        assert_eq!(max_read_chars(), DEFAULT_MAX_READ_CHARS);
-    }
-
-    #[test]
-    fn small_files_are_returned_whole_and_not_marked_truncated() {
-        let path = temp_path("small-read.txt");
-        write_file(path.to_string_lossy().as_ref(), "one\ntwo\nthree").expect("write");
-
-        let output = read_file(path.to_string_lossy().as_ref(), None, None).expect("read");
-        assert_eq!(output.file.content, "one\ntwo\nthree");
-        assert_eq!(output.file.num_lines, 3);
-        assert!(!output.file.truncated);
-        assert_eq!(output.file.next_offset, None);
-    }
-
    #[test]
    fn edits_file_contents() {
        let path = temp_path("edit.txt");
@@ -66,15 +66,16 @@ pub use compact::{
    get_compact_continuation_message, should_compact, CompactionConfig, CompactionResult,
 };
 pub use config::{
-    clear_user_provider_settings, default_config_home, save_user_provider_settings,
-    suppress_config_warnings_for_json_mode, ApiTimeoutConfig, ConfigEntry, ConfigError,
-    ConfigFileReport, ConfigFileStatus, ConfigInspection, ConfigLoader, ConfigSource,
-    McpConfigCollection, McpInvalidServerConfig, McpManagedProxyServerConfig, McpOAuthConfig,
-    McpRemoteServerConfig, McpSdkServerConfig, McpServerConfig, McpStdioServerConfig, McpTransport,
-    McpWebSocketServerConfig, OAuthConfig, ProviderFallbackConfig, ResolvedPermissionMode,
-    RulesImportConfig, RuntimeConfig, RuntimeFeatureConfig, RuntimeHookCommand, RuntimeHookConfig,
-    RuntimeInvalidHookConfig, RuntimePermissionRuleConfig, RuntimePluginConfig,
-    RuntimeProviderConfig, ScopedMcpServerConfig, CLAW_SETTINGS_SCHEMA_NAME,
+    clear_user_provider_settings, default_config_home, inject_config_as_env_fallbacks,
+    save_user_provider_settings, suppress_config_warnings_for_json_mode, ApiTimeoutConfig,
+    ConfigEntry, ConfigError, ConfigFileReport, ConfigFileStatus, ConfigInspection, ConfigLoader,
+    ConfigSource, McpConfigCollection, McpInvalidServerConfig, McpManagedProxyServerConfig,
+    McpOAuthConfig, McpRemoteServerConfig, McpSdkServerConfig, McpServerConfig,
+    McpStdioServerConfig, McpTransport, McpWebSocketServerConfig, OAuthConfig,
+    ProviderFallbackConfig, ResolvedPermissionMode, RulesImportConfig, RuntimeConfig,
+    RuntimeFeatureConfig, RuntimeHookCommand, RuntimeHookConfig, RuntimeInvalidHookConfig,
+    RuntimePermissionRuleConfig, RuntimePluginConfig, RuntimeProviderConfig, ScopedMcpServerConfig,
+    CLAW_SETTINGS_SCHEMA_NAME,
 };
 pub use config_validate::{
    check_unsupported_format, format_diagnostics, validate_config_file, ConfigDiagnostic,
@@ -82,8 +83,8 @@ pub use config_validate::{
 };
 pub use conversation::{
    auto_compaction_threshold_from_env, ApiClient, ApiRequest, AssistantEvent, AutoCompactionEvent,
-    ConversationRuntime, PromptCacheEvent, RuntimeError, StaticToolExecutor, ToolError,
-    ToolExecutor, TurnSummary,
+    ConversationRuntime, PromptCacheEvent, RuntimeError, StaticToolExecutor, ToolCall, ToolError,
+    ToolExecutor, ToolResult, TurnProgressReporter, TurnSummary,
 };
 pub use file_ops::{
    edit_file, edit_file_in_workspace, glob_search, glob_search_in_workspace, grep_search,
@@ -42,25 +42,7 @@ pub const SYSTEM_PROMPT_DYNAMIC_BOUNDARY: &str = "__SYSTEM_PROMPT_DYNAMIC_BOUNDA
 pub const FRONTIER_MODEL_NAME: &str = "Claude Opus 4.6";
 const MAX_INSTRUCTION_FILE_CHARS: usize = 4_000;
 const MAX_TOTAL_INSTRUCTION_CHARS: usize = 12_000;
-/// Character budget for the git diff snapshot embedded in the system prompt.
-///
-/// This lives in the *system prompt*, so its cost is paid on every session whose
-/// working tree has changed — and a diff changes on essentially every edit. The
-/// previous 50_000 budget was four times the entire instruction-file budget and
-/// could add ~15_000 tokens to the prompt from a single modified file, which is
-/// affordable against a hosted frontier model and ruinous against a local one.
-///
-/// Override with `CLAW_MAX_GIT_DIFF_CHARS`. `0` drops the diff snapshot entirely;
-/// git status and the recent-commit list are unaffected.
-const DEFAULT_MAX_GIT_DIFF_CHARS: usize = 4_000;
-const MAX_GIT_DIFF_CHARS_ENV_VAR: &str = "CLAW_MAX_GIT_DIFF_CHARS";
-
-fn max_git_diff_chars() -> usize {
-    std::env::var(MAX_GIT_DIFF_CHARS_ENV_VAR)
-        .ok()
-        .and_then(|value| value.trim().parse().ok())
-        .unwrap_or(DEFAULT_MAX_GIT_DIFF_CHARS)
-}
+const MAX_GIT_DIFF_CHARS: usize = 50_000;

 /// Neutral identity for the model family line in generated prompts.
 #[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
@@ -516,15 +498,8 @@ fn read_git_diff(cwd: &Path) -> Option<String> {
 }

 fn truncate_diff(mut diff: String) -> String {
-    let budget = max_git_diff_chars();
-    // A zero budget means "omit the diff", not "truncate to nothing" -- returning
-    // an empty string here would still push an empty "Git diff snapshot:" heading
-    // into the prompt.
-    if budget == 0 {
-        return String::new();
-    }
-    if diff.len() > budget {
-        let mut end = budget;
+    if diff.len() > MAX_GIT_DIFF_CHARS {
+        let mut end = MAX_GIT_DIFF_CHARS;
        while !diff.is_char_boundary(end) {
            end -= 1;
        }
@@ -783,7 +758,6 @@ fn get_simple_doing_tasks_section() -> String {
        "Do not add speculative abstractions, compatibility shims, or unrelated cleanup.".to_string(),
        "Do not create files unless they are required to complete the task.".to_string(),
        "If an approach fails, diagnose the failure before switching tactics.".to_string(),
-        "Act in the turn you plan in: when the next step is a tool call, make the call. Never end a turn describing a step you have not taken, and do not stop to ask for a go-ahead on work already requested.".to_string(),
        "Be careful not to introduce security vulnerabilities such as command injection, XSS, or SQL injection.".to_string(),
        "Report outcomes faithfully: if verification fails or was not run, say so explicitly.".to_string(),
    ]);
@@ -808,8 +782,7 @@ mod tests {
        collapse_blank_lines, display_context_path, normalize_instruction_content,
        render_instruction_content, render_instruction_files, truncate_diff,
        truncate_instruction_content, ContextFile, ModelFamilyIdentity, ProjectContext,
-        SystemPromptBuilder, DEFAULT_MAX_GIT_DIFF_CHARS, MAX_GIT_DIFF_CHARS_ENV_VAR,
-        SYSTEM_PROMPT_DYNAMIC_BOUNDARY,
+        SystemPromptBuilder, MAX_GIT_DIFF_CHARS, SYSTEM_PROMPT_DYNAMIC_BOUNDARY,
    };
    use crate::config::ConfigLoader;
    use std::fs;
@@ -1471,69 +1444,33 @@ mod tests {
        assert!(rendered.contains("Project rules"));
    }

-    /// Serializes the tests that read or mutate `CLAW_MAX_GIT_DIFF_CHARS`; env vars
-    /// are process-global and the default-budget tests fail if another test leaves
-    /// an override set.
-    fn diff_env_lock() -> std::sync::MutexGuard<'static, ()> {
-        static LOCK: std::sync::Mutex<()> = std::sync::Mutex::new(());
-        LOCK.lock()
-            .unwrap_or_else(std::sync::PoisonError::into_inner)
-    }
-
    #[test]
    fn truncate_diff_preserves_short_content() {
-        let _guard = diff_env_lock();
-        std::env::remove_var(MAX_GIT_DIFF_CHARS_ENV_VAR);
        let short = "a".repeat(1_000);
        let result = truncate_diff(short.clone());
        assert_eq!(result, short);
        assert!(!result.contains("[diff truncated"));
    }

-    #[test]
-    fn truncate_diff_honors_env_override() {
-        let _guard = diff_env_lock();
-        std::env::set_var(MAX_GIT_DIFF_CHARS_ENV_VAR, "100");
-        let result = truncate_diff("z".repeat(1_000));
-        std::env::remove_var(MAX_GIT_DIFF_CHARS_ENV_VAR);
-        let marker = "\n\n... [diff truncated — too large for system prompt]";
-        assert!(result.ends_with(marker));
-        assert_eq!(result.len() - marker.len(), 100);
-    }
-
-    #[test]
-    fn truncate_diff_zero_budget_omits_the_snapshot_entirely() {
-        // Zero must yield nothing at all -- a truncated-to-empty body would still
-        // drag a "Git diff snapshot:" heading and the truncation marker into the
-        // prompt, which is the opposite of what the operator asked for.
-        let _guard = diff_env_lock();
-        std::env::set_var(MAX_GIT_DIFF_CHARS_ENV_VAR, "0");
-        let result = truncate_diff("z".repeat(1_000));
-        std::env::remove_var(MAX_GIT_DIFF_CHARS_ENV_VAR);
-        assert!(result.is_empty());
-    }
-
    #[test]
    fn truncate_diff_caps_oversized_content() {
-        let _guard = diff_env_lock();
-        std::env::remove_var(MAX_GIT_DIFF_CHARS_ENV_VAR);
-        let large = "x".repeat(DEFAULT_MAX_GIT_DIFF_CHARS + 5_000);
+        let large = "x".repeat(MAX_GIT_DIFF_CHARS + 5_000);
        let result = truncate_diff(large);
        assert!(result.contains("... [diff truncated — too large for system prompt]"));
-        // The body before the marker must be at most DEFAULT_MAX_GIT_DIFF_CHARS bytes
+        // The body before the marker must be at most MAX_GIT_DIFF_CHARS bytes
        let marker = "\n\n... [diff truncated — too large for system prompt]";
        let body_len = result.len() - marker.len();
-        assert!(body_len <= DEFAULT_MAX_GIT_DIFF_CHARS);
+        assert!(body_len <= MAX_GIT_DIFF_CHARS);
    }

    #[test]
    fn truncate_diff_respects_utf8_char_boundaries() {
-        // Build a string where DEFAULT_MAX_GIT_DIFF_CHARS falls in the middle of a
+        // Build a string where MAX_GIT_DIFF_CHARS falls in the middle of a
        // multi-byte character (U+1F600 = 4 bytes in UTF-8).
-        let prefix_len = DEFAULT_MAX_GIT_DIFF_CHARS - 2;
+        let prefix_len = MAX_GIT_DIFF_CHARS - 2;
        let mut input = "a".repeat(prefix_len);
        // Append a 4-byte emoji so bytes [prefix_len..prefix_len+4] are the
-        // emoji.  DEFAULT_MAX_GIT_DIFF_CHARS lands at prefix_len+2, inside the emoji.
+        // emoji.  MAX_GIT_DIFF_CHARS lands at prefix_len+2, inside the emoji.
        input.push('\u{1F600}');
        input.push_str(&"b".repeat(10_000));

@@ -1545,7 +1482,7 @@ mod tests {
        // inside it would be invalid UTF-8.
        let marker = "\n\n... [diff truncated — too large for system prompt]";
        let body = &result[..result.len() - marker.len()];
-        assert!(body.len() <= DEFAULT_MAX_GIT_DIFF_CHARS);
+        assert!(body.len() <= MAX_GIT_DIFF_CHARS);
        assert!(body.is_char_boundary(body.len()));
    }
 }
@@ -718,20 +718,6 @@ impl ConversationMessage {
        }
    }

-    /// Text the harness injected on its own initiative, not something the user typed.
-    ///
-    /// Reaches the model as an ordinary turn — the wire protocol has nowhere else to put it — but
-    /// stays labelled in the transcript, so a replay, an export, or a compaction summary does not
-    /// present the harness's own prompting back as the user's words.
-    #[must_use]
-    pub fn system_text(text: impl Into<String>) -> Self {
-        Self {
-            role: MessageRole::System,
-            blocks: vec![ContentBlock::Text { text: text.into() }],
-            usage: None,
-        }
-    }
-
    #[must_use]
    pub fn assistant(blocks: Vec<ContentBlock>) -> Self {
        Self {
@@ -190,8 +190,10 @@ fn stage1_supersede(messages: &[ConversationMessage]) -> (Vec<ConversationMessag

        if let Some(last_write) = last_write_idx {
            for op in ops {
-                if op.index < last_write
-                    && matches!(op.op_type, FileOp::Read | FileOp::Write | FileOp::Edit)
+                if (op.op_type == FileOp::Read
+                    || op.op_type == FileOp::Write
+                    || op.op_type == FileOp::Edit)
+                    && op.index < last_write
                {
                    obsolete_indices.insert(op.index);
                }
@@ -89,19 +89,6 @@ impl TokenUsage {
            + self.cache_read_input_tokens
    }

-    /// Total tokens the provider had to read to serve this call, i.e. the live size of the
-    /// context window.
-    ///
-    /// `input_tokens` alone is NOT that number. With prompt caching a warm call reports
-    /// `input_tokens: 2` and puts the real bulk in `cache_read_input_tokens`, so anything
-    /// budgeting against the context window must sum all three input counters.
-    #[must_use]
-    pub fn total_input_tokens(self) -> u32 {
-        self.input_tokens
-            .saturating_add(self.cache_creation_input_tokens)
-            .saturating_add(self.cache_read_input_tokens)
-    }
-
    #[must_use]
    pub fn estimate_cost_usd(self) -> UsageCostEstimate {
        self.estimate_cost_usd_with_pricing(ModelPricing::default_sonnet_tier())
@@ -256,41 +243,6 @@ mod tests {
        assert_eq!(tracker.cumulative_usage().total_tokens(), 48);
    }

-    #[test]
-    fn total_input_tokens_includes_cached_context() {
-        // The shape a warm prompt-cached call actually reports: input_tokens is ~nothing and
-        // the real context size is in the cache counters.
-        let cached = TokenUsage {
-            input_tokens: 2,
-            output_tokens: 1_133,
-            cache_creation_input_tokens: 1_453,
-            cache_read_input_tokens: 111_186,
-        };
-        assert_eq!(cached.total_input_tokens(), 112_641);
-        // Output tokens are not part of the input budget.
-        assert_ne!(cached.total_input_tokens(), cached.total_tokens());
-
-        // A backend without prompt caching reports the whole prompt as input_tokens.
-        let uncached = TokenUsage {
-            input_tokens: 29_056,
-            output_tokens: 73,
-            cache_creation_input_tokens: 0,
-            cache_read_input_tokens: 0,
-        };
-        assert_eq!(uncached.total_input_tokens(), 29_056);
-    }
-
-    #[test]
-    fn total_input_tokens_saturates_instead_of_overflowing() {
-        let usage = TokenUsage {
-            input_tokens: u32::MAX,
-            output_tokens: 0,
-            cache_creation_input_tokens: u32::MAX,
-            cache_read_input_tokens: u32::MAX,
-        };
-        assert_eq!(usage.total_input_tokens(), u32::MAX);
-    }
-
    #[test]
    fn computes_cost_summary_lines() {
        let usage = TokenUsage {
@@ -14,6 +14,7 @@ api = { path = "../api" }
 commands = { path = "../commands" }
 crossterm = "0.28"
 pulldown-cmark = "0.13"
+once_cell = "1"
 rustyline = "15"
 runtime = { path = "../runtime" }
 plugins = { path = "../plugins" }
@@ -25,8 +26,15 @@ tools = { path = "../tools" }
 log = "0.4"


-[lints]
-workspace = true
+[lints.rust]
+unsafe_code = "allow"
+
+[lints.clippy]
+all = { level = "warn", priority = -1 }
+pedantic = { level = "allow", priority = -1 }
+module_name_repetitions = "allow"
+missing_panics_doc = "allow"
+missing_errors_doc = "allow"

 [dev-dependencies]
 mock-anthropic-service = { path = "../mock-anthropic-service" }
@@ -18,6 +18,8 @@ pub enum ReadOutcome {
    Submit(String),
    Cancel,
    Exit,
+    ProviderSwap,
+    TeamToggle,
 }

 struct SlashCommandHelper {
@@ -86,12 +88,19 @@ impl Hinter for SlashCommandHelper {
 impl Highlighter for SlashCommandHelper {
    fn highlight<'l>(&self, line: &'l str, _pos: usize) -> Cow<'l, str> {
        self.set_current_line(line);
-        Cow::Borrowed(line)
+        // When sentinel is present, show visible prompt instead of invisible char
+        if line.contains('\x01') {
+            let display = line.replace('\x01', "\x1b[36m[Provider Swap]\x1b[0m ");
+            Cow::Owned(display)
+        } else {
+            Cow::Borrowed(line)
+        }
    }

    fn highlight_char(&self, line: &str, _pos: usize, _kind: CmdKind) -> bool {
        self.set_current_line(line);
-        false
+        // Re-highlight when sentinel is present to show the prompt
+        line.contains('\x01')
    }
 }

@@ -115,6 +124,18 @@ impl LineEditor {
        editor.set_helper(Some(SlashCommandHelper::new(completions)));
        editor.bind_sequence(KeyEvent(KeyCode::Char('J'), Modifiers::CTRL), Cmd::Newline);
        editor.bind_sequence(KeyEvent(KeyCode::Enter, Modifiers::SHIFT), Cmd::Newline);
+        // Ctrl+P inserts a sentinel character that triggers provider swap.
+        // The sentinel is invisible but the highlighter shows "[Provider Swap]" prompt.
+        // User must press Enter to confirm (rustyline cannot chain commands).
+        editor.bind_sequence(
+            KeyEvent(KeyCode::Char('P'), Modifiers::CTRL),
+            Cmd::SelfInsert(1, '\x01'),
+        );
+        // Ctrl+T inserts a sentinel character that toggles agent teams mode.
+        editor.bind_sequence(
+            KeyEvent(KeyCode::Char('T'), Modifiers::CTRL),
+            Cmd::SelfInsert(1, '\x02'),
+        );

        Self {
            prompt: prompt.into(),
@@ -147,7 +168,18 @@ impl LineEditor {
        }

        match self.editor.readline(&self.prompt) {
-            Ok(line) => Ok(ReadOutcome::Submit(line)),
+            Ok(line) => {
+                // Ctrl+P inserts \x01 sentinel — triggers provider swap wizard.
+                // The sentinel is stripped and we return ProviderSwap to the REPL loop.
+                if line.contains('\x01') {
+                    return Ok(ReadOutcome::ProviderSwap);
+                }
+                // Ctrl+T inserts \x02 sentinel — toggles team mode.
+                if line.contains('\x02') {
+                    return Ok(ReadOutcome::TeamToggle);
+                }
+                Ok(ReadOutcome::Submit(line))
+            }
            Err(ReadlineError::Interrupted) => {
                let has_input = !self.current_line().is_empty();
                self.finish_interrupted_read()?;
@@ -2,6 +2,8 @@ use std::io::{self, IsTerminal, Write};

 use runtime::{save_user_provider_settings, ConfigLoader, RuntimeProviderConfig};

+use serde_json;
+
 const PROVIDERS: &[(&str, &str, &str)] = &[
    ("1", "Anthropic", "anthropic"),
    ("2", "xAI / Grok", "xai"),
@@ -451,16 +451,11 @@ fn direct_resume_safe_slash_commands_route_to_local_json_actions_831() {
        .output()
        .expect("git init should launch");

-    // `/sandbox`'s status reflects the host's real sandbox capability, so it is the one
-    // entry with more than one legitimate value: "ok" where namespace isolation works,
-    // "warn" where it is unsupported and only the filesystem sandbox is active (#731).
-    // This test is about #831 routing — that these commands produce a local JSON action
-    // instead of `interactive_only` — not about the kernel the suite happens to run on.
-    for (command, expected_kind, expected_statuses) in [
-        ("/version", "version", &["ok"][..]),
-        ("/sandbox", "sandbox", &["ok", "warn"][..]),
-        ("/diff", "diff", &["ok"][..]),
-        ("/status", "status", &["ok"][..]),
+    for (command, expected_kind, expected_status) in [
+        ("/version", "version", "ok"),
+        ("/sandbox", "sandbox", "warn"),
+        ("/diff", "diff", "ok"),
+        ("/status", "status", "ok"),
    ] {
        let output = run_claw(&root, &["--output-format", "json", command], &[]);
        assert!(
@@ -475,9 +470,9 @@ fn direct_resume_safe_slash_commands_route_to_local_json_actions_831() {
            .unwrap_or_else(|_| panic!("{command} must emit JSON (#831), got: {stdout:?}"));

        assert_eq!(parsed["kind"], expected_kind, "{command} kind: {parsed}");
-        assert!(
-            expected_statuses.contains(&parsed["status"].as_str().unwrap_or_default()),
-            "{command} status should be one of {expected_statuses:?}: {parsed}"
+        assert_eq!(
+            parsed["status"], expected_status,
+            "{command} status: {parsed}"
        );
        assert_ne!(
            parsed["error_kind"], "interactive_only",
@@ -1012,13 +1007,13 @@ fn inventory_commands_emit_structured_json_when_requested() {
    assert!(
        !plugins
            .as_object()
-            .is_some_and(|o| o.contains_key("reload_runtime")),
+            .map_or(false, |o| o.contains_key("reload_runtime")),
        "plugins list should not include reload_runtime"
    );
    assert!(
        !plugins
            .as_object()
-            .is_some_and(|o| o.contains_key("target")),
+            .map_or(false, |o| o.contains_key("target")),
        "plugins list should not include target"
    );
    // #703: structured summary replaces prose message
@@ -1712,13 +1707,13 @@ fn resumed_inventory_commands_emit_structured_json_when_requested() {
    assert!(
        !plugins
            .as_object()
-            .is_some_and(|o| o.contains_key("reload_runtime")),
+            .map_or(false, |o| o.contains_key("reload_runtime")),
        "plugins list should not include reload_runtime"
    );
    assert!(
        !plugins
            .as_object()
-            .is_some_and(|o| o.contains_key("target")),
+            .map_or(false, |o| o.contains_key("target")),
        "plugins list should not include target"
    );
    assert!(
@@ -2951,7 +2946,7 @@ fn prompt_empty_arg_json_stdout_missing_prompt_823() {
        "claw prompt empty arg must retain abort action (#823); got: {parsed}"
    );
    assert!(
-        parsed["hint"].as_str().is_some_and(|h| !h.is_empty()),
+        parsed["hint"].as_str().map_or(false, |h| !h.is_empty()),
        "claw prompt empty arg missing_prompt hint must be non-empty (#823)"
    );
 }
@@ -2989,9 +2984,9 @@ fn flag_value_errors_have_error_kind_and_hint_756() {
        "invalid --reasoning-effort must be invalid_flag_value (#756): {parsed}"
    );
    assert!(
-        parsed["hint"]
-            .as_str()
-            .is_some_and(|h| h.contains("low") || h.contains("medium") || h.contains("high")),
+        parsed["hint"].as_str().map_or(false, |h| h.contains("low")
+            || h.contains("medium")
+            || h.contains("high")),
        "hint must mention valid values (#756): {parsed}"
    );

@@ -3017,7 +3012,7 @@ fn flag_value_errors_have_error_kind_and_hint_756() {
        "missing --model value must be missing_flag_value (#756): {parsed2}"
    );
    assert!(
-        parsed2["hint"].as_str().is_some_and(|h| !h.is_empty()),
+        parsed2["hint"].as_str().map_or(false, |h| !h.is_empty()),
        "missing --model hint must be non-empty (#756): {parsed2}"
    );
 }
@@ -3261,7 +3256,7 @@ fn short_p_flag_swallows_no_flags_755() {
        "flag-like token after -p must be rejected as missing_prompt (#755): {parsed2}"
    );
    assert!(
-        parsed2["hint"].as_str().is_some_and(|h| !h.is_empty()),
+        parsed2["hint"].as_str().map_or(false, |h| !h.is_empty()),
        "missing_prompt hint must be non-empty (#755)"
    );
 }
@@ -3403,7 +3398,7 @@ fn config_unsupported_section_json_hint_741() {
        assert!(
            parsed["supported_sections"]
                .as_array()
-                .is_some_and(|a| !a.is_empty()),
+                .map_or(false, |a| !a.is_empty()),
            "config {section} JSON must include supported_sections (#741)"
        );
    }
@@ -3460,7 +3455,7 @@ fn export_json_has_kind_702() {
    // On success stdout has kind:export; on failure stderr has type:error.
    // Either way, both envelopes must be valid JSON.
    let stdout = String::from_utf8_lossy(&output.stdout);
-    let _stderr = String::from_utf8_lossy(&output.stderr)
+    let stderr = String::from_utf8_lossy(&output.stderr)
        .lines()
        .filter(|l| l.starts_with('{'))
        .collect::<Vec<_>>()
@@ -3552,8 +3547,8 @@ fn config_parse_error_has_typed_error_kind_and_hint_764() {
        !output.status.success(),
        "malformed settings.json should cause non-zero exit"
    );
-    let _stdout = String::from_utf8_lossy(&output.stdout);
-    let _stderr = String::from_utf8_lossy(&output.stderr);
+    let stdout = String::from_utf8_lossy(&output.stdout);
+    let stderr = String::from_utf8_lossy(&output.stderr);
    let stdout = String::from_utf8_lossy(&output.stdout);
    let json_line = stdout
        .lines()
@@ -3587,8 +3582,8 @@ fn login_logout_removed_subcommands_have_error_kind_and_hint_765() {
            !output.status.success(),
            "claw {subcmd} should exit non-zero"
        );
-        let _stdout = String::from_utf8_lossy(&output.stdout);
-        let _stderr = String::from_utf8_lossy(&output.stderr);
+        let stdout = String::from_utf8_lossy(&output.stdout);
+        let stderr = String::from_utf8_lossy(&output.stderr);
        let stdout = String::from_utf8_lossy(&output.stdout);
        let json_line = stdout
            .lines()
@@ -3727,8 +3722,8 @@ fn resume_non_slash_trailing_arg_has_typed_error_kind_and_hint_768() {
        !output.status.success(),
        "claw --resume latest compact should exit non-zero"
    );
-    let _stdout = String::from_utf8_lossy(&output.stdout);
-    let _stderr = String::from_utf8_lossy(&output.stderr);
+    let stdout = String::from_utf8_lossy(&output.stdout);
+    let stderr = String::from_utf8_lossy(&output.stderr);
    let stdout = String::from_utf8_lossy(&output.stdout);
    let json_line = stdout
        .lines()
@@ -3767,8 +3762,8 @@ fn session_with_unknown_subcommand_returns_interactive_only_not_credentials_767(
            !output.status.success(),
            "claw session {sub} should exit non-zero"
        );
-        let _stdout = String::from_utf8_lossy(&output.stdout);
-        let _stderr = String::from_utf8_lossy(&output.stderr);
+        let stdout = String::from_utf8_lossy(&output.stdout);
+        let stderr = String::from_utf8_lossy(&output.stderr);
        let stdout = String::from_utf8_lossy(&output.stdout);
        let json_line = stdout
            .lines()
@@ -3821,7 +3816,7 @@ fn slash_only_verbs_with_args_return_interactive_only_not_credentials_770() {
            "claw {} should exit non-zero",
            args.join(" ")
        );
-        let _stdout = String::from_utf8_lossy(&output.stdout);
+        let stdout = String::from_utf8_lossy(&output.stdout);
        let stderr = String::from_utf8_lossy(&output.stderr);
        let stdout = String::from_utf8_lossy(&output.stdout);
        let json_line = stdout
@@ -3863,8 +3858,8 @@ fn agents_plugins_mcp_unknown_subcommand_have_hint_774() {
    {
        let output = run_claw(&root, &["--output-format", "json", "agents", "bogus"], &[]);
        assert!(!output.status.success(), "agents bogus should fail");
-        let _stdout = String::from_utf8_lossy(&output.stdout);
-        let _stderr = String::from_utf8_lossy(&output.stderr);
+        let stdout = String::from_utf8_lossy(&output.stdout);
+        let stderr = String::from_utf8_lossy(&output.stderr);
        let stdout = String::from_utf8_lossy(&output.stdout);
        let json_line = stdout
            .lines()
@@ -3887,8 +3882,8 @@ fn agents_plugins_mcp_unknown_subcommand_have_hint_774() {
    {
        let output = run_claw(&root, &["--output-format", "json", "plugins", "bogus"], &[]);
        assert!(!output.status.success(), "plugins bogus should fail");
-        let _stdout = String::from_utf8_lossy(&output.stdout);
-        let _stderr = String::from_utf8_lossy(&output.stderr);
+        let stdout = String::from_utf8_lossy(&output.stdout);
+        let stderr = String::from_utf8_lossy(&output.stderr);
        let stdout = String::from_utf8_lossy(&output.stdout);
        let json_line = stdout
            .lines()
@@ -3907,7 +3902,7 @@ fn agents_plugins_mcp_unknown_subcommand_have_hint_774() {
    {
        let output = run_claw(&root, &["--output-format", "json", "mcp", "bogus"], &[]);
        assert!(!output.status.success(), "mcp bogus should fail");
-        let _stdout = String::from_utf8_lossy(&output.stdout);
+        let stdout = String::from_utf8_lossy(&output.stdout);
        let stderr = String::from_utf8_lossy(&output.stderr);
        let stdout = String::from_utf8_lossy(&output.stdout);
        let json_str = if stdout.trim().starts_with('{') {
@@ -4022,7 +4017,7 @@ fn interactive_only_guard_batch_769_to_771() {
            "claw {} should exit non-zero",
            args.join(" ")
        );
-        let _stdout = String::from_utf8_lossy(&output.stdout);
+        let stdout = String::from_utf8_lossy(&output.stdout);
        let stderr = String::from_utf8_lossy(&output.stderr);
        let stdout = String::from_utf8_lossy(&output.stdout);
        let json_line = stdout
@@ -4086,7 +4081,7 @@ fn resume_plugin_mutations_are_typed_interactive_only_777() {
            !output.status.success(),
            "/plugins {mutation} in resume mode should exit non-zero"
        );
-        let _stdout = String::from_utf8_lossy(&output.stdout);
+        let stdout = String::from_utf8_lossy(&output.stdout);
        let stderr = String::from_utf8_lossy(&output.stderr);
        let stdout = String::from_utf8_lossy(&output.stdout);
        let json_line = stdout
@@ -4143,7 +4138,7 @@ fn resume_skills_invocation_is_typed_interactive_only_779() {
        !output.status.success(),
        "/skills <skill> in resume mode should exit non-zero"
    );
-    let _stdout = String::from_utf8_lossy(&output.stdout);
+    let stdout = String::from_utf8_lossy(&output.stdout);
    let stderr = String::from_utf8_lossy(&output.stderr);
    let stdout = String::from_utf8_lossy(&output.stdout);
    let json_line = stdout
@@ -4184,8 +4179,8 @@ fn acp_unsupported_invocation_has_hint_782() {

    let output = run_claw(&root, &["--output-format", "json", "acp", "start"], &[]);
    assert!(!output.status.success(), "acp start should fail");
-    let _stdout = String::from_utf8_lossy(&output.stdout);
-    let _stderr = String::from_utf8_lossy(&output.stderr);
+    let stdout = String::from_utf8_lossy(&output.stdout);
+    let stderr = String::from_utf8_lossy(&output.stderr);
    let stdout = String::from_utf8_lossy(&output.stdout);
    let json_line = stdout
        .lines()
@@ -4222,7 +4217,7 @@ fn init_json_envelope_has_hint_and_already_initialized_783() {
    // Fresh init — already_initialized should be false, hint should mention CLAUDE.md
    let output = run_claw(&root, &["--output-format", "json", "init"], &[]);
    assert!(output.status.success(), "init should succeed");
-    let _stdout = String::from_utf8_lossy(&output.stdout);
+    let stdout = String::from_utf8_lossy(&output.stdout);
    let stderr = String::from_utf8_lossy(&output.stderr);
    let stdout = String::from_utf8_lossy(&output.stdout);
    let raw = if stdout.trim_start().starts_with('{') {
@@ -4291,7 +4286,7 @@ fn init_json_envelope_has_hint_and_already_initialized_783() {
    // Idempotent re-init — already_initialized should be true
    let output2 = run_claw(&root, &["--output-format", "json", "init"], &[]);
    assert!(output2.status.success(), "re-init should succeed");
-    let _stdout2 = String::from_utf8_lossy(&output2.stdout);
+    let stdout2 = String::from_utf8_lossy(&output2.stdout);
    let stderr2 = String::from_utf8_lossy(&output2.stderr);
    let stdout2 = String::from_utf8_lossy(&output2.stdout);
    let raw2 = if stdout2.trim_start().starts_with('{') {
@@ -4372,7 +4367,7 @@ fn export_arg_errors_have_typed_kind_and_hint_784() {
        &[],
    );
    assert!(!out1.status.success(), "--output with no value should fail");
-    let _stderr1 = String::from_utf8_lossy(&out1.stderr);
+    let stderr1 = String::from_utf8_lossy(&out1.stderr);
    let stdout1 = String::from_utf8_lossy(&out1.stdout);
    let j1: serde_json::Value = stdout1
        .lines()
@@ -4399,7 +4394,7 @@ fn export_arg_errors_have_typed_kind_and_hint_784() {
        &[],
    );
    assert!(!out2.status.success(), "extra positional should fail");
-    let _stderr2 = String::from_utf8_lossy(&out2.stderr);
+    let stderr2 = String::from_utf8_lossy(&out2.stderr);
    let stdout2 = String::from_utf8_lossy(&out2.stdout);
    let j2: serde_json::Value = stdout2
        .lines()
@@ -4436,7 +4431,7 @@ fn unknown_subcommand_returns_typed_kind_785() {
    // "dump" is close enough to "dump-manifests" to trigger the typo suggestion path
    let output = run_claw(&root, &["--output-format", "json", "dump"], &[]);
    assert!(!output.status.success(), "unknown subcommand should fail");
-    let _stderr = String::from_utf8_lossy(&output.stderr);
+    let stderr = String::from_utf8_lossy(&output.stderr);
    let stdout = String::from_utf8_lossy(&output.stdout);
    let j: serde_json::Value = stdout
        .lines()
@@ -4484,7 +4479,7 @@ fn dump_manifests_missing_dir_has_typed_kind_and_hint_786() {
        &[],
    );
    assert!(!out1.status.success());
-    let _stderr1 = String::from_utf8_lossy(&out1.stderr);
+    let stderr1 = String::from_utf8_lossy(&out1.stderr);
    let stdout1 = String::from_utf8_lossy(&out1.stdout);
    let j1: serde_json::Value = stdout1
        .lines()
@@ -4516,7 +4511,7 @@ fn dump_manifests_missing_dir_has_typed_kind_and_hint_786() {
        &[],
    );
    assert!(!out2.status.success());
-    let _stderr2 = String::from_utf8_lossy(&out2.stderr);
+    let stderr2 = String::from_utf8_lossy(&out2.stderr);
    let stdout2 = String::from_utf8_lossy(&out2.stdout);
    let j2: serde_json::Value = stdout2
        .lines()
@@ -4566,7 +4561,7 @@ fn resume_directory_path_returns_typed_kind_and_hint_787() {
        !output.status.success(),
        "resume with directory should fail"
    );
-    let _stderr = String::from_utf8_lossy(&output.stderr);
+    let stderr = String::from_utf8_lossy(&output.stderr);
    let stdout = String::from_utf8_lossy(&output.stdout);
    let j: serde_json::Value = stdout
        .lines()
@@ -4616,7 +4611,7 @@ fn skills_show_not_found_emits_single_json_object_788() {
    assert!(!output.status.success(), "skills show unknown should fail");
    // Skills handler emits JSON to stdout; the duplicate was on stderr from the main error path.
    // After fix: stdout has 1 JSON object, stderr has none (no duplicate).
-    let _stdout = String::from_utf8_lossy(&output.stdout);
+    let stdout = String::from_utf8_lossy(&output.stdout);
    let stderr = String::from_utf8_lossy(&output.stderr);
    let stdout = String::from_utf8_lossy(&output.stdout);

@@ -4778,7 +4773,7 @@ fn system_prompt_unknown_option_returns_typed_kind_790() {
        &[],
    );
    assert!(!out1.status.success());
-    let _stderr1 = String::from_utf8_lossy(&out1.stderr);
+    let stderr1 = String::from_utf8_lossy(&out1.stderr);
    let stdout1 = String::from_utf8_lossy(&out1.stdout);
    let j1: serde_json::Value = stdout1
        .lines()
@@ -4805,7 +4800,7 @@ fn system_prompt_unknown_option_returns_typed_kind_790() {
        &[],
    );
    assert!(!out2.status.success());
-    let _stderr2 = String::from_utf8_lossy(&out2.stderr);
+    let stderr2 = String::from_utf8_lossy(&out2.stderr);
    let stdout2 = String::from_utf8_lossy(&out2.stdout);
    let j2: serde_json::Value = stdout2
        .lines()
@@ -4843,7 +4838,7 @@ fn config_extra_args_have_non_null_hint_791() {
        &[],
    );
    assert!(!out1.status.success());
-    let _stderr1 = String::from_utf8_lossy(&out1.stderr);
+    let stderr1 = String::from_utf8_lossy(&out1.stderr);
    let stdout1 = String::from_utf8_lossy(&out1.stdout);
    let j1: serde_json::Value = stdout1
        .lines()
@@ -4877,7 +4872,7 @@ fn config_extra_args_have_non_null_hint_791() {
        &[],
    );
    assert!(!out2.status.success());
-    let _stderr2 = String::from_utf8_lossy(&out2.stderr);
+    let stderr2 = String::from_utf8_lossy(&out2.stderr);
    let stdout2 = String::from_utf8_lossy(&out2.stdout);
    let j2: serde_json::Value = stdout2
        .lines()
@@ -5063,7 +5058,7 @@ fn plugins_uninstall_not_found_has_hint_793() {
        "plugins uninstall not-found must exit non-zero (#793)"
    );
    // Error envelope goes to stderr (propagated via ? to main error handler)
-    let _stderr = String::from_utf8_lossy(&output.stderr);
+    let stderr = String::from_utf8_lossy(&output.stderr);
    let stdout = String::from_utf8_lossy(&output.stdout);
    let j: serde_json::Value = stdout
        .lines()
@@ -5108,7 +5103,7 @@ fn plugins_install_not_found_path_returns_typed_kind_794() {
        !output.status.success(),
        "plugins install not-found-path must exit non-zero (#794)"
    );
-    let _stderr = String::from_utf8_lossy(&output.stderr);
+    let stderr = String::from_utf8_lossy(&output.stderr);
    let stdout = String::from_utf8_lossy(&output.stdout);
    let j: serde_json::Value = stdout
        .lines()
@@ -5372,7 +5367,7 @@ fn agents_create_scaffolds_toml_and_lists_locally_431() {
        .iter()
        .any(|agent| {
            agent["name"] == "my-agent"
-                && Path::new(agent["path"].as_str().expect("listed agent path"))
+                && PathBuf::from(agent["path"].as_str().expect("listed agent path"))
                    == fs::canonicalize(&agent_path).expect("canonical listed agent path")
        }));
 }
@@ -5497,7 +5492,7 @@ fn plugins_extra_args_have_non_null_hint_797() {
        !output.status.success(),
        "plugins show with extra arg must exit non-zero (#797)"
    );
-    let _stderr = String::from_utf8_lossy(&output.stderr);
+    let stderr = String::from_utf8_lossy(&output.stderr);
    let stdout = String::from_utf8_lossy(&output.stdout);
    let j: serde_json::Value = stdout
        .lines()
@@ -5563,7 +5558,7 @@ fn plugins_list_trailing_dash_text_error_stays_on_stderr_817() {
        String::from_utf8_lossy(&output.stdout)
    );
    let stderr = String::from_utf8_lossy(&output.stderr);
-    let _stdout = String::from_utf8_lossy(&output.stdout);
+    let stdout = String::from_utf8_lossy(&output.stdout);
    assert!(stderr.contains("[error-kind: cli_parse]"), "{stderr}");
    assert!(
        stderr.contains("unknown option for `claw plugins list`: --"),
@@ -5588,7 +5583,7 @@ fn empty_prompt_has_non_null_hint_798() {
        !output.status.success(),
        "empty prompt must exit non-zero (#798)"
    );
-    let _stderr = String::from_utf8_lossy(&output.stderr);
+    let stderr = String::from_utf8_lossy(&output.stderr);
    let stdout = String::from_utf8_lossy(&output.stdout);
    let j: serde_json::Value = stdout
        .lines()
@@ -0,0 +1,118 @@
+# Multi-Tool Execution & Sub-Agent Delegation
+
+Two complementary features that dramatically reduce latency and token usage when the model needs to perform multiple operations or gather context.
+
+## Feature 1: Parallel Tool Execution
+
+When the model returns multiple tool_use blocks in a single response, read-only tools now execute concurrently instead of sequentially.
+
+### How it works
+
+The `run_turn` loop is refactored into 3 phases:
+
+1. **Pre-hooks + permission checks** (sequential — hooks may mutate state)
+2. **Tool execution** (batch — parallel for read-only tools via `std::thread::scope`)
+3. **Post-hooks + session updates** (sequential — preserves original ordering)
+
+### Parallel-safe tools
+
+These tools are safe to run concurrently because they only read state and dispatch through the stateless tool registry:
+
+- `read_file`, `glob_search`, `grep_search`
+- `WebFetch`, `WebSearch`
+- `ToolSearch`, `Skill`
+- `LSP`
+- `GitStatus`, `GitDiff`, `GitLog`, `GitShow`, `GitBlame`
+
+### Sequential-only tools
+
+Tools that require `&mut self` or have side effects continue to run one at a time:
+
+- `bash`, `write_file`, `edit_file` (side effects)
+- `MCP`, `McpAuth`, `RemoteTrigger` (network state)
+- `Agent`, `TaskCreate`, `WorkerCreate` (stateful)
+- `NotebookEdit`, `REPL`, `PowerShell` (side effects)
+
+### Safety guarantees
+
+- Pre/post hooks always run sequentially
+- Permission checks complete before any tool executes
+- Tool results are pushed to the session in the original model order
+- Falls back to sequential for single-tool batches
+- Thread scopes ensure all parallel work completes before `execute_batch` returns
+
+### Impact
+
+For a response with 5 `read_file` calls: **~5x faster** execution. The main model still sees all results in order.
+
+---
+
+## Feature 2: SubAgent Delegation
+
+A `SubAgent` tool that lets the main model delegate multi-step tasks to a fast sub-agent. The sub-agent runs autonomously with its own `ConversationRuntime`, making multiple tool calls without round-tripping through the main model.
+
+### Tool parameters
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `prompt` | string | yes | Task description for the sub-agent |
+| `task_type` | string | no | `Explore` (default), `Plan`, or `Verify` |
+| `model` | string | no | Override the sub-agent model |
+
+### Task types
+
+| Type | Available tools | Use for |
+|------|----------------|---------|
+| `Explore` | read_file, glob_search, grep_search, WebFetch, WebSearch, ToolSearch, StructuredOutput | Searching code, reading files, gathering context |
+| `Plan` | Explore + TodoWrite | Planning approaches with structured todo output |
+| `Verify` | Plan + bash | Running tests, checking builds, verifying changes |
+
+### Configuration
+
+Set the sub-agent model in `~/.claw/settings.json`:
+
+```json
+{
+  "model": "openai/glm-5.1-fast",
+  "subagentModel": "openai/qwen3.6-35b-fast"
+}
+```
+
+If `subagentModel` is not set, the sub-agent uses the same model as the main session (or the `model` override parameter on the tool call).
+
+### Example
+
+Main model prompt: "Find all Rust files that import `ConversationRuntime` and list their paths"
+
+Without SubAgent: 5–10 sequential tool calls (grep → read each file → summarize)
+With SubAgent: 1 SubAgent call → sub-agent does all the work autonomously → returns summary
+
+**Result**: ~10x fewer tokens consumed by the main model, faster overall completion.
+
+### Architecture
+
+The sub-agent reuses the same building blocks as the existing `Agent` tool:
+
+- `ProviderRuntimeClient` — API client with fallback chain
+- `SubagentToolExecutor` — filtered tool access with permission enforcement
+- `ConversationRuntime` — full conversation loop with hooks and compaction
+- `agent_permission_policy()` — auto-approve read-only, deny write tools
+
+Key differences from the `Agent` tool:
+- **Synchronous** — blocks until complete, returns result directly
+- **Lighter** — fewer default tools, focused on the task type
+- **Configurable model** — uses `subagentModel` or the tool's `model` param
+- **Structured output** — returns `result`, `tool_calls`, and `iterations`
+
+---
+
+## Changed files
+
+| File | Changes |
+|------|---------|
+| `rust/crates/runtime/src/conversation.rs` | `ToolCall`, `ToolResult` types; `execute_batch` on `ToolExecutor`; 3-phase `run_turn` |
+| `rust/crates/runtime/src/lib.rs` | Exports for `ToolCall`, `ToolResult` |
+| `rust/crates/runtime/src/config.rs` | `subagent_model` field, `parse_optional_subagent_model()`, accessor |
+| `rust/crates/runtime/src/config_validate.rs` | `subagentModel` field spec |
+| `rust/crates/rusty-claude-cli/src/main.rs` | `CliToolExecutor::execute_batch` with parallel-safe classification |
+| `rust/crates/tools/src/lib.rs` | `SubAgent` tool spec, `SubAgentInput`, `run_sub_agent()`, `load_subagent_model_from_config()`, `build_sub_agent_system_prompt()` |
@@ -116,6 +116,8 @@ mod tests {
            lane_events: vec![],
            derived_state: "working".to_string(),
            current_blocker: None,
+            team_id: None,
+            task_id: None,
            error: None,
        }
    }
Author	SHA1	Message	Date
clawdbot	590f5a2e09	fix(clippy): resolve new lint violations in trident, compact, and claw-rag-service - runtime/trident.rs: derive Default, fix for_kv_map, if_same_then_else, extend_with_drain, unnecessary_cast, needless_borrows - runtime/compact.rs: fix useless_borrows_in_formatting - claw-rag-service/ingest.rs: remove unnecessary into_iter() - claw-rag-service/db.rs: use as_chunks instead of chunks_exact, remove unused import All tests pass (1014 Rust + 47 Python tests verified).	2026-10-12 23:01:12 +00:00
TheArchitectit	0403fe8867	fix(cli): order parallel tool results by call index and cap fan-out execute_batch already keyed results to original call slots; this makes that airtight: panicking worker threads resolve to their own index via a fallback tuple instead of colliding with slot 0, and results are asserted to follow call order with a regression test that mixes a workspace-escape read among valid reads at cap=2. Adds the fan-out bound: parallel-safe calls run in waves of at most maxParallelToolCalls (default 8, CLAWD_PARALLEL_TOOL_CALLS env, or the new setting applied via with_max_parallel_tool_calls at runtime build). Sequential behavior is preserved: allowed_tools checks still run before dispatch, and ToolSearch stays off the parallel path.	2026-10-12 23:01:12 +00:00
TheArchitectit	407f0be972	feat(teams): bound per-team sub-agent concurrency with AgentGate TeamCreate resolves maxConcurrentAgents from the per-team input, then the maxConcurrentAgents setting, then unlimited (pre-fix behavior). The cap is persisted in the manifest and registered on a process-wide gate; agent threads still spawn immediately but block on an RAII slot before entering their run loop, so manifest/task-claim semantics are unchanged. TeamDelete forgets the gate so queued agents drain and no stale team entries accumulate. Includes a gate regression test.	2026-10-12 23:01:12 +00:00
TheArchitectit	98c45990db	feat(config): parse maxParallelToolCalls and maxConcurrentAgents settings Adds optional positive-integer parsing for the two new fan-out caps next to subagentModel, in both camelCase and snake_case forms. Zero parses as unset; non-numeric values are a named config error. Covered by three regression tests mirroring the subagentModel test style.	2026-10-12 23:01:12 +00:00
TheArchitectitandClaw	beb5595551	fix: restore workspace unsafe_code=forbid, fix TaskClaim TOCTOU, remove TUI deps Review fixes for PR #3250: 1. Restore workspace-level unsafe_code = "forbid" (was downgraded to "warn" for TUI support). The per-crate [lints.rust] unsafe_code = "allow" on rusty-claude-cli already overrides it where needed. 2. Fix TaskClaim TOCTOU race in claim_task(). Replace exists()-then-write with OpenOptions::create_new(true) which atomically fails if the lock file already exists, eliminating the race window between the check and the write. 3. Remove TUI scaffolding deps (ratatui, tui-textarea, gag, crossbeam-channel, libc, unicode-width) and the /tui slash command spec — these belong in a future TUI PR and are unused in the current source. Also updates the provider chain precedence test to reflect the new behavior where the caller's resolved model is the chain primary. Co-Authored-By: Claw <noreply@openclaw.ai>	2026-10-12 23:01:12 +00:00
TheArchitectit	05fb4d5f2f	test: add subagentModel accessor chain tests Adds 3 unit tests covering the original silent-drop bug: - camelCase 'subagentModel' key reads end-to-end - snake_case 'subagent_model' key reads end-to-end - blank value returns None (falls back to default model) Requested by @1716775457damn in PR review.	2026-10-12 23:01:12 +00:00
TheArchitectit	c6820b8f2f	fix: model_token_limit catch-all returns None for unknown models Restores the fix from @Offwhite-Del that was lost during rebase. Unknown models now return None so preflight skips the context-window check and lets the API enforce its own limits.	2026-10-12 23:01:12 +00:00
TheArchitectit	1e96b1643a	cargo fmt	2026-10-12 23:00:54 +00:00
TheArchitectitandClaude Fable 5	53b3e63d99	feat(team): team enhancements, subagentModel, parallel tool exec Port the agent-team enhancement layer onto upstream/main so the model can spin up coordinated sub-agent teams for parallel work. subagentModel config wiring (fix): - Add subagent_model field to RuntimeFeatureConfig + RuntimeConfig::subagent_model() accessor so the subagentModel setting (already validated by config_validate.rs) is now actually read and stored. - Agent tool's resolve_agent_model falls back to subagentModel from config when no explicit model is passed. Provider namespace separation: - New 'custom-openai' provider kind with dedicated env vars (CLAWCUSTOMOPENAI_API_KEY / CLAWCUSTOMOPENAI_BASE_URL) - /setup wizard saves kind: 'custom-openai' for option 5 - Bare model name normalized to 'custom/' prefix to avoid proxy 404s - Sub-agents inherit /setup-saved provider config via inject_config_as_env_fallbacks Parallel tool execution: - Override execute_batch to classify read-only tools as parallel-safe and run them concurrently via std::thread::scope - Results return in original model order Team coordination layer: - AgentMessage, TaskClaim, TeamStatus tools + shared mailbox directory - Mode presets (tiny/1x ... mega/6x) + enriched TeamCreate/Agent descriptions - Background team watcher - /team slash command: on/off/status/toggle Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-10-12 23:00:40 +00:00
bellmanandOmX	0cf2c751a6	Document provider compatibility diagnostics and passthrough Explain the provider compatibility behavior that now has executable coverage so future changes preserve routing, custom gateway slugs, diagnostics, and extra-body passthrough semantics. Constraint: Task 2 requires docs/status evidence while leader owns Ultragoal checkpoints and .omx/ultragoal remains untouched. Rejected: Add a new CLI status command \| broader than the assigned provider compatibility documentation/status surface. Confidence: high Scope-risk: narrow Directive: Keep docs aligned with provider_diagnostics_for_model, MessageRequest::extra_body, and OpenAI-compatible slash-model tests. Tested: cargo test --manifest-path rust/Cargo.toml -p api custom_openai_gateway_preserves_slash_model_ids_and_extra_body_params; cargo test --manifest-path rust/Cargo.toml -p api provider_diagnostics_explain_openai_compatible_capabilities; cargo check --manifest-path rust/Cargo.toml -p api Not-tested: Live provider calls requiring external credentials. Co-authored-by: OmX <omx@local>	2026-10-12 22:59:26 +00:00
bellmanandOmX	22b30c4557	Keep G007 mock parity references executable The follow-up docs gate needed the parity manifest reference string that the mock parity diff checker requires, so this records the verified map-only repair after leader integration. Constraint: Task 11 scope allowed only PARITY.md, rust/MOCK_PARITY_HARNESS.md, and docs/g007-plugin-mcp-verification-map.md; only PARITY.md needed a change. Rejected: Editing harness code or .omx/ultragoal \| checks proved the remaining gap was docs-map text only and Ultragoal state is leader-owned. Confidence: high Scope-risk: narrow Directive: Keep auto_compact_triggered parity_refs synchronized with PARITY.md when mock parity scenarios change. Tested: cd rust && python3 scripts/run_mock_parity_diff.py; python3 scripts/validate_cc2_board.py --board .omx/cc2/board.json; rg -n auto_compact_triggered token_cost_reporting auto_compaction threshold from env G007 Plugin/MCP G007-plugin-mcp 12 scripted scenarios 21 captured PARITY.md rust/MOCK_PARITY_HARNESS.md docs/g007-plugin-mcp-verification-map.md; git diff --check Not-tested: Full workspace suite; Task 11 was a docs/parity-map follow-up with focused executable map validation. Co-authored-by: OmX <omx@oh-my-codex.dev>	2026-10-12 22:59:26 +00:00
bellmanandOmX	5f08341d1a	Document G007 mock parity verification boundaries Record the W4 verification map and parity-doc alignment so plugin/MCP lifecycle mock coverage can be audited without scraping stale harness prose. Constraint: Task 9 owns mock integration and regression verification/docs mapping, not parser fixes or leader-owned Ultragoal state. Rejected: Editing .omx/ultragoal or duplicating Worker-4 plugin command fallthrough fixes \| leader checkpointing and parser implementation are separate lanes. Confidence: high Scope-risk: narrow Directive: Keep rust/mock_parity_scenarios.json, rust/MOCK_PARITY_HARNESS.md, PARITY.md, and mock_parity_harness.rs aligned when adding scenarios. Tested: cd rust && python3 scripts/run_mock_parity_diff.py --no-run; cd rust && ./scripts/run_mock_parity_harness.sh; cd rust && python3 scripts/run_mock_parity_diff.py; cargo test --manifest-path rust/Cargo.toml -p rusty-claude-cli build_runtime_plugin_state -- --nocapture; cargo test --manifest-path rust/Cargo.toml -p rusty-claude-cli build_runtime_runs_plugin_lifecycle_init_and_shutdown -- --nocapture; cargo test --manifest-path rust/Cargo.toml -p plugins plugin_registry_runs_initialize_and_shutdown_for_enabled_plugins -- --nocapture; cargo fmt --manifest-path rust/Cargo.toml --all -- --check; cargo check --manifest-path rust/Cargo.toml -p rusty-claude-cli -p mock-anthropic-service; git diff --check Not-tested: Full workspace test suite; W4 scope is docs/mock verification map and focused plugin/MCP lifecycle regression evidence. Co-authored-by: OmX <omx@oh-my-codex.dev>	2026-10-12 22:59:26 +00:00
				`@@ -0,0 +1 @@`
				{"schema_version":1,"session_id":"24aa7e35-e6af-4d2d-ab41-a38b9115a031","state":"running","ready_for_input":false,"updated_at":"2026-10-12T22:10:00.508Z","current_turn_id":null,"last_turn_id":null,"live":true,"reason":null,"source":"agent_session_event","event":"turn_start","cwd":"/home/bellman/Data/Workspace/gc-task-cc-pr-3250-lane","workdir":"/home/bellman/Data/Workspace/gc-task-cc-pr-3250-lane","branch":null,"session_file":"/home/bellman/.gajaeway/broker/agent/sessions/v2-famocqbiduwkxmc2g2nvg6jfq2ay6qtc5aihbhbdoqopsmduj4sa/2026-10-12T22-02-16-124Z_24aa7e35-e6af-4d2d-ab41-a38b9115a031.jsonl","activity":{"seq":149,"last_activity_at":"2026-10-12T22:10:01.196Z","tool":"bash","phase":"started","outcome":null,"elapsed_ms":null,"active_tool_count":1,"active_tools":[{"tool":"bash","started_at":"2026-10-12T22:10:01.196Z"}],"in_flight":[{"digest":"fa5f186357264e6b1be2a7a4a7162d0fff04f721630413a25d05b40bcd933836","tool":"bash","started_at":"2026-10-12T22:10:01.196Z"}]}}
				`@@ -0,0 +1 @@`
				`{"pid":1,"start_time":"unknown","token":"8389ee99-c41c-47dd-9615-e76a5268967c","owner_host_id":"7af2fb0e8e37bd543e3d0bda6f205b56f30077b5a9b77e83208e94ae441315ac","released":true}`
				`@@ -0,0 +1 @@`
				`{"effectMarker":"7b92c148-d616-4eb5-95e8-4e95084bebe9","incarnation":"linux:159085489","pid":177576}`