mirror of
https://github.com/instructkr/claw-code.git
synced 2026-04-06 08:04:50 +08:00
Compare commits
8 Commits
fix/p2-19-
...
fix/p013-o
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
00b557c8b7 | ||
|
|
31163be347 | ||
|
|
eb4d3b11ee | ||
|
|
9bd7a78ca8 | ||
|
|
24d8f916c8 | ||
|
|
30883bddbd | ||
|
|
1a2fa1581e | ||
|
|
fa72cd665e |
BIN
assets/sigrid-photo.png
Normal file
BIN
assets/sigrid-photo.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 73 KiB |
2
rust/.claw/sessions/session-1775386832313-0.jsonl
Normal file
2
rust/.claw/sessions/session-1775386832313-0.jsonl
Normal file
@@ -0,0 +1,2 @@
|
||||
{"created_at_ms":1775386832313,"session_id":"session-1775386832313-0","type":"session_meta","updated_at_ms":1775386832313,"version":1}
|
||||
{"message":{"blocks":[{"text":"status --help","type":"text"}],"role":"user"},"type":"message"}
|
||||
2
rust/.claw/sessions/session-1775386842352-0.jsonl
Normal file
2
rust/.claw/sessions/session-1775386842352-0.jsonl
Normal file
@@ -0,0 +1,2 @@
|
||||
{"created_at_ms":1775386842352,"session_id":"session-1775386842352-0","type":"session_meta","updated_at_ms":1775386842352,"version":1}
|
||||
{"message":{"blocks":[{"text":"doctor --help","type":"text"}],"role":"user"},"type":"message"}
|
||||
2
rust/.claw/sessions/session-1775386852257-0.jsonl
Normal file
2
rust/.claw/sessions/session-1775386852257-0.jsonl
Normal file
@@ -0,0 +1,2 @@
|
||||
{"created_at_ms":1775386852257,"session_id":"session-1775386852257-0","type":"session_meta","updated_at_ms":1775386852257,"version":1}
|
||||
{"message":{"blocks":[{"text":"doctor --help","type":"text"}],"role":"user"},"type":"message"}
|
||||
2
rust/.claw/sessions/session-1775386853666-0.jsonl
Normal file
2
rust/.claw/sessions/session-1775386853666-0.jsonl
Normal file
@@ -0,0 +1,2 @@
|
||||
{"created_at_ms":1775386853666,"session_id":"session-1775386853666-0","type":"session_meta","updated_at_ms":1775386853666,"version":1}
|
||||
{"message":{"blocks":[{"text":"status --help","type":"text"}],"role":"user"},"type":"message"}
|
||||
@@ -8,6 +8,13 @@ pub enum ApiError {
|
||||
provider: &'static str,
|
||||
env_vars: &'static [&'static str],
|
||||
},
|
||||
ContextWindowExceeded {
|
||||
model: String,
|
||||
estimated_input_tokens: u32,
|
||||
requested_output_tokens: u32,
|
||||
estimated_total_tokens: u32,
|
||||
context_window_tokens: u32,
|
||||
},
|
||||
ExpiredOAuthToken,
|
||||
Auth(String),
|
||||
InvalidApiKeyEnv(VarError),
|
||||
@@ -48,6 +55,7 @@ impl ApiError {
|
||||
Self::Api { retryable, .. } => *retryable,
|
||||
Self::RetriesExhausted { last_error, .. } => last_error.is_retryable(),
|
||||
Self::MissingCredentials { .. }
|
||||
| Self::ContextWindowExceeded { .. }
|
||||
| Self::ExpiredOAuthToken
|
||||
| Self::Auth(_)
|
||||
| Self::InvalidApiKeyEnv(_)
|
||||
@@ -67,6 +75,16 @@ impl Display for ApiError {
|
||||
"missing {provider} credentials; export {} before calling the {provider} API",
|
||||
env_vars.join(" or ")
|
||||
),
|
||||
Self::ContextWindowExceeded {
|
||||
model,
|
||||
estimated_input_tokens,
|
||||
requested_output_tokens,
|
||||
estimated_total_tokens,
|
||||
context_window_tokens,
|
||||
} => write!(
|
||||
f,
|
||||
"context_window_blocked for {model}: estimated input {estimated_input_tokens} + requested output {requested_output_tokens} = {estimated_total_tokens} tokens exceeds the {context_window_tokens}-token context window; compact the session or reduce request size before retrying"
|
||||
),
|
||||
Self::ExpiredOAuthToken => {
|
||||
write!(
|
||||
f,
|
||||
|
||||
@@ -14,7 +14,7 @@ use telemetry::{AnalyticsEvent, AnthropicRequestProfile, ClientIdentity, Session
|
||||
use crate::error::ApiError;
|
||||
use crate::prompt_cache::{PromptCache, PromptCacheRecord, PromptCacheStats};
|
||||
|
||||
use super::{Provider, ProviderFuture};
|
||||
use super::{preflight_message_request, Provider, ProviderFuture};
|
||||
use crate::sse::SseParser;
|
||||
use crate::types::{MessageDeltaEvent, MessageRequest, MessageResponse, StreamEvent, Usage};
|
||||
|
||||
@@ -294,6 +294,8 @@ impl AnthropicClient {
|
||||
}
|
||||
}
|
||||
|
||||
preflight_message_request(&request)?;
|
||||
|
||||
let response = self.send_with_retry(&request).await?;
|
||||
let request_id = request_id_from_headers(response.headers());
|
||||
let mut response = response
|
||||
@@ -337,6 +339,7 @@ impl AnthropicClient {
|
||||
&self,
|
||||
request: &MessageRequest,
|
||||
) -> Result<MessageStream, ApiError> {
|
||||
preflight_message_request(request)?;
|
||||
let response = self
|
||||
.send_with_retry(&request.clone().with_streaming())
|
||||
.await?;
|
||||
|
||||
@@ -1,6 +1,8 @@
|
||||
use std::future::Future;
|
||||
use std::pin::Pin;
|
||||
|
||||
use serde::Serialize;
|
||||
|
||||
use crate::error::ApiError;
|
||||
use crate::types::{MessageRequest, MessageResponse};
|
||||
|
||||
@@ -40,6 +42,12 @@ pub struct ProviderMetadata {
|
||||
pub default_base_url: &'static str,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||
pub struct ModelTokenLimit {
|
||||
pub max_output_tokens: u32,
|
||||
pub context_window_tokens: u32,
|
||||
}
|
||||
|
||||
const MODEL_REGISTRY: &[(&str, ProviderMetadata)] = &[
|
||||
(
|
||||
"opus",
|
||||
@@ -182,17 +190,86 @@ pub fn detect_provider_kind(model: &str) -> ProviderKind {
|
||||
|
||||
#[must_use]
|
||||
pub fn max_tokens_for_model(model: &str) -> u32 {
|
||||
model_token_limit(model).map_or_else(
|
||||
|| {
|
||||
let canonical = resolve_model_alias(model);
|
||||
if canonical.contains("opus") {
|
||||
32_000
|
||||
} else {
|
||||
64_000
|
||||
}
|
||||
},
|
||||
|limit| limit.max_output_tokens,
|
||||
)
|
||||
}
|
||||
|
||||
#[must_use]
|
||||
pub fn model_token_limit(model: &str) -> Option<ModelTokenLimit> {
|
||||
let canonical = resolve_model_alias(model);
|
||||
if canonical.contains("opus") {
|
||||
32_000
|
||||
} else {
|
||||
64_000
|
||||
match canonical.as_str() {
|
||||
"claude-opus-4-6" => Some(ModelTokenLimit {
|
||||
max_output_tokens: 32_000,
|
||||
context_window_tokens: 200_000,
|
||||
}),
|
||||
"claude-sonnet-4-6" | "claude-haiku-4-5-20251213" => Some(ModelTokenLimit {
|
||||
max_output_tokens: 64_000,
|
||||
context_window_tokens: 200_000,
|
||||
}),
|
||||
"grok-3" | "grok-3-mini" => Some(ModelTokenLimit {
|
||||
max_output_tokens: 64_000,
|
||||
context_window_tokens: 131_072,
|
||||
}),
|
||||
_ => None,
|
||||
}
|
||||
}
|
||||
|
||||
pub fn preflight_message_request(request: &MessageRequest) -> Result<(), ApiError> {
|
||||
let Some(limit) = model_token_limit(&request.model) else {
|
||||
return Ok(());
|
||||
};
|
||||
|
||||
let estimated_input_tokens = estimate_message_request_input_tokens(request);
|
||||
let estimated_total_tokens = estimated_input_tokens.saturating_add(request.max_tokens);
|
||||
if estimated_total_tokens > limit.context_window_tokens {
|
||||
return Err(ApiError::ContextWindowExceeded {
|
||||
model: resolve_model_alias(&request.model),
|
||||
estimated_input_tokens,
|
||||
requested_output_tokens: request.max_tokens,
|
||||
estimated_total_tokens,
|
||||
context_window_tokens: limit.context_window_tokens,
|
||||
});
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
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));
|
||||
estimate = estimate.saturating_add(estimate_serialized_tokens(&request.tool_choice));
|
||||
estimate
|
||||
}
|
||||
|
||||
fn estimate_serialized_tokens<T: Serialize>(value: &T) -> u32 {
|
||||
serde_json::to_vec(value)
|
||||
.ok()
|
||||
.map_or(0, |bytes| (bytes.len() / 4 + 1) as u32)
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::{detect_provider_kind, max_tokens_for_model, resolve_model_alias, ProviderKind};
|
||||
use serde_json::json;
|
||||
|
||||
use crate::error::ApiError;
|
||||
use crate::types::{
|
||||
InputContentBlock, InputMessage, MessageRequest, ToolChoice, ToolDefinition,
|
||||
};
|
||||
|
||||
use super::{
|
||||
detect_provider_kind, max_tokens_for_model, model_token_limit, preflight_message_request,
|
||||
resolve_model_alias, ProviderKind,
|
||||
};
|
||||
|
||||
#[test]
|
||||
fn resolves_grok_aliases() {
|
||||
@@ -215,4 +292,86 @@ mod tests {
|
||||
assert_eq!(max_tokens_for_model("opus"), 32_000);
|
||||
assert_eq!(max_tokens_for_model("grok-3"), 64_000);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn returns_context_window_metadata_for_supported_models() {
|
||||
assert_eq!(
|
||||
model_token_limit("claude-sonnet-4-6")
|
||||
.expect("claude-sonnet-4-6 should be registered")
|
||||
.context_window_tokens,
|
||||
200_000
|
||||
);
|
||||
assert_eq!(
|
||||
model_token_limit("grok-mini")
|
||||
.expect("grok-mini should resolve to a registered model")
|
||||
.context_window_tokens,
|
||||
131_072
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn preflight_blocks_requests_that_exceed_the_model_context_window() {
|
||||
let request = MessageRequest {
|
||||
model: "claude-sonnet-4-6".to_string(),
|
||||
max_tokens: 64_000,
|
||||
messages: vec![InputMessage {
|
||||
role: "user".to_string(),
|
||||
content: vec![InputContentBlock::Text {
|
||||
text: "x".repeat(600_000),
|
||||
}],
|
||||
}],
|
||||
system: Some("Keep the answer short.".to_string()),
|
||||
tools: Some(vec![ToolDefinition {
|
||||
name: "weather".to_string(),
|
||||
description: Some("Fetches weather".to_string()),
|
||||
input_schema: json!({
|
||||
"type": "object",
|
||||
"properties": { "city": { "type": "string" } },
|
||||
}),
|
||||
}]),
|
||||
tool_choice: Some(ToolChoice::Auto),
|
||||
stream: true,
|
||||
};
|
||||
|
||||
let error = preflight_message_request(&request)
|
||||
.expect_err("oversized request should be rejected before the provider call");
|
||||
|
||||
match error {
|
||||
ApiError::ContextWindowExceeded {
|
||||
model,
|
||||
estimated_input_tokens,
|
||||
requested_output_tokens,
|
||||
estimated_total_tokens,
|
||||
context_window_tokens,
|
||||
} => {
|
||||
assert_eq!(model, "claude-sonnet-4-6");
|
||||
assert!(estimated_input_tokens > 136_000);
|
||||
assert_eq!(requested_output_tokens, 64_000);
|
||||
assert!(estimated_total_tokens > context_window_tokens);
|
||||
assert_eq!(context_window_tokens, 200_000);
|
||||
}
|
||||
other => panic!("expected context-window preflight failure, got {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn preflight_skips_unknown_models() {
|
||||
let request = MessageRequest {
|
||||
model: "unknown-model".to_string(),
|
||||
max_tokens: 64_000,
|
||||
messages: vec![InputMessage {
|
||||
role: "user".to_string(),
|
||||
content: vec![InputContentBlock::Text {
|
||||
text: "x".repeat(600_000),
|
||||
}],
|
||||
}],
|
||||
system: None,
|
||||
tools: None,
|
||||
tool_choice: None,
|
||||
stream: false,
|
||||
};
|
||||
|
||||
preflight_message_request(&request)
|
||||
.expect("models without context metadata should skip the guarded preflight");
|
||||
}
|
||||
}
|
||||
|
||||
@@ -12,7 +12,7 @@ use crate::types::{
|
||||
ToolChoice, ToolDefinition, ToolResultContentBlock, Usage,
|
||||
};
|
||||
|
||||
use super::{Provider, ProviderFuture};
|
||||
use super::{preflight_message_request, Provider, ProviderFuture};
|
||||
|
||||
pub const DEFAULT_XAI_BASE_URL: &str = "https://api.x.ai/v1";
|
||||
pub const DEFAULT_OPENAI_BASE_URL: &str = "https://api.openai.com/v1";
|
||||
@@ -128,6 +128,7 @@ impl OpenAiCompatClient {
|
||||
stream: false,
|
||||
..request.clone()
|
||||
};
|
||||
preflight_message_request(&request)?;
|
||||
let response = self.send_with_retry(&request).await?;
|
||||
let request_id = request_id_from_headers(response.headers());
|
||||
let payload = response.json::<ChatCompletionResponse>().await?;
|
||||
@@ -142,6 +143,7 @@ impl OpenAiCompatClient {
|
||||
&self,
|
||||
request: &MessageRequest,
|
||||
) -> Result<MessageStream, ApiError> {
|
||||
preflight_message_request(request)?;
|
||||
let response = self
|
||||
.send_with_retry(&request.clone().with_streaming())
|
||||
.await?;
|
||||
|
||||
@@ -103,6 +103,41 @@ async fn send_message_posts_json_and_parses_response() {
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn send_message_blocks_oversized_requests_before_the_http_call() {
|
||||
let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
|
||||
let server = spawn_server(
|
||||
state.clone(),
|
||||
vec![http_response("200 OK", "application/json", "{}")],
|
||||
)
|
||||
.await;
|
||||
|
||||
let client = AnthropicClient::new("test-key").with_base_url(server.base_url());
|
||||
let error = client
|
||||
.send_message(&MessageRequest {
|
||||
model: "claude-sonnet-4-6".to_string(),
|
||||
max_tokens: 64_000,
|
||||
messages: vec![InputMessage {
|
||||
role: "user".to_string(),
|
||||
content: vec![InputContentBlock::Text {
|
||||
text: "x".repeat(600_000),
|
||||
}],
|
||||
}],
|
||||
system: Some("Keep the answer short.".to_string()),
|
||||
tools: None,
|
||||
tool_choice: None,
|
||||
stream: false,
|
||||
})
|
||||
.await
|
||||
.expect_err("oversized request should fail local context-window preflight");
|
||||
|
||||
assert!(matches!(error, ApiError::ContextWindowExceeded { .. }));
|
||||
assert!(
|
||||
state.lock().await.is_empty(),
|
||||
"preflight failure should avoid any upstream HTTP request"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn send_message_applies_request_profile_and_records_telemetry() {
|
||||
let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
|
||||
|
||||
@@ -4,10 +4,10 @@ use std::sync::Arc;
|
||||
use std::sync::{Mutex as StdMutex, OnceLock};
|
||||
|
||||
use api::{
|
||||
ContentBlockDelta, ContentBlockDeltaEvent, ContentBlockStartEvent, ContentBlockStopEvent,
|
||||
InputContentBlock, InputMessage, MessageDeltaEvent, MessageRequest, OpenAiCompatClient,
|
||||
OpenAiCompatConfig, OutputContentBlock, ProviderClient, StreamEvent, ToolChoice,
|
||||
ToolDefinition,
|
||||
ApiError, ContentBlockDelta, ContentBlockDeltaEvent, ContentBlockStartEvent,
|
||||
ContentBlockStopEvent, InputContentBlock, InputMessage, MessageDeltaEvent, MessageRequest,
|
||||
OpenAiCompatClient, OpenAiCompatConfig, OutputContentBlock, ProviderClient, StreamEvent,
|
||||
ToolChoice, ToolDefinition,
|
||||
};
|
||||
use serde_json::json;
|
||||
use tokio::io::{AsyncReadExt, AsyncWriteExt};
|
||||
@@ -63,6 +63,42 @@ async fn send_message_uses_openai_compatible_endpoint_and_auth() {
|
||||
assert_eq!(body["tools"][0]["type"], json!("function"));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn send_message_blocks_oversized_xai_requests_before_the_http_call() {
|
||||
let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
|
||||
let server = spawn_server(
|
||||
state.clone(),
|
||||
vec![http_response("200 OK", "application/json", "{}")],
|
||||
)
|
||||
.await;
|
||||
|
||||
let client = OpenAiCompatClient::new("xai-test-key", OpenAiCompatConfig::xai())
|
||||
.with_base_url(server.base_url());
|
||||
let error = client
|
||||
.send_message(&MessageRequest {
|
||||
model: "grok-3".to_string(),
|
||||
max_tokens: 64_000,
|
||||
messages: vec![InputMessage {
|
||||
role: "user".to_string(),
|
||||
content: vec![InputContentBlock::Text {
|
||||
text: "x".repeat(300_000),
|
||||
}],
|
||||
}],
|
||||
system: Some("Keep the answer short.".to_string()),
|
||||
tools: None,
|
||||
tool_choice: None,
|
||||
stream: false,
|
||||
})
|
||||
.await
|
||||
.expect_err("oversized request should fail local context-window preflight");
|
||||
|
||||
assert!(matches!(error, ApiError::ContextWindowExceeded { .. }));
|
||||
assert!(
|
||||
state.lock().await.is_empty(),
|
||||
"preflight failure should avoid any upstream HTTP request"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn send_message_accepts_full_chat_completions_endpoint_override() {
|
||||
let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
|
||||
|
||||
@@ -114,8 +114,12 @@ impl LaneEvent {
|
||||
|
||||
#[must_use]
|
||||
pub fn finished(emitted_at: impl Into<String>, detail: Option<String>) -> Self {
|
||||
Self::new(LaneEventName::Finished, LaneEventStatus::Completed, emitted_at)
|
||||
.with_optional_detail(detail)
|
||||
Self::new(
|
||||
LaneEventName::Finished,
|
||||
LaneEventStatus::Completed,
|
||||
emitted_at,
|
||||
)
|
||||
.with_optional_detail(detail)
|
||||
}
|
||||
|
||||
#[must_use]
|
||||
@@ -161,19 +165,14 @@ impl LaneEvent {
|
||||
mod tests {
|
||||
use serde_json::json;
|
||||
|
||||
use super::{
|
||||
LaneEvent, LaneEventBlocker, LaneEventName, LaneEventStatus, LaneFailureClass,
|
||||
};
|
||||
use super::{LaneEvent, LaneEventBlocker, LaneEventName, LaneEventStatus, LaneFailureClass};
|
||||
|
||||
#[test]
|
||||
fn canonical_lane_event_names_serialize_to_expected_wire_values() {
|
||||
let cases = [
|
||||
(LaneEventName::Started, "lane.started"),
|
||||
(LaneEventName::Ready, "lane.ready"),
|
||||
(
|
||||
LaneEventName::PromptMisdelivery,
|
||||
"lane.prompt_misdelivery",
|
||||
),
|
||||
(LaneEventName::PromptMisdelivery, "lane.prompt_misdelivery"),
|
||||
(LaneEventName::Blocked, "lane.blocked"),
|
||||
(LaneEventName::Red, "lane.red"),
|
||||
(LaneEventName::Green, "lane.green"),
|
||||
@@ -193,7 +192,10 @@ mod tests {
|
||||
];
|
||||
|
||||
for (event, expected) in cases {
|
||||
assert_eq!(serde_json::to_value(event).expect("serialize event"), json!(expected));
|
||||
assert_eq!(
|
||||
serde_json::to_value(event).expect("serialize event"),
|
||||
json!(expected)
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -599,7 +599,10 @@ mod tests {
|
||||
));
|
||||
|
||||
match result {
|
||||
McpPhaseResult::Failure { phase: failed_phase, error } => {
|
||||
McpPhaseResult::Failure {
|
||||
phase: failed_phase,
|
||||
error,
|
||||
} => {
|
||||
assert_eq!(failed_phase, phase);
|
||||
assert_eq!(error.phase, phase);
|
||||
assert_eq!(
|
||||
|
||||
@@ -360,8 +360,10 @@ impl McpServerManagerError {
|
||||
}
|
||||
|
||||
fn recoverable(&self) -> bool {
|
||||
!matches!(self.lifecycle_phase(), McpLifecyclePhase::InitializeHandshake)
|
||||
&& matches!(self, Self::Transport { .. } | Self::Timeout { .. })
|
||||
!matches!(
|
||||
self.lifecycle_phase(),
|
||||
McpLifecyclePhase::InitializeHandshake
|
||||
) && matches!(self, Self::Transport { .. } | Self::Timeout { .. })
|
||||
}
|
||||
|
||||
fn discovery_failure(&self, server_name: &str) -> McpDiscoveryFailure {
|
||||
@@ -417,10 +419,9 @@ impl McpServerManagerError {
|
||||
("method".to_string(), (*method).to_string()),
|
||||
("timeout_ms".to_string(), timeout_ms.to_string()),
|
||||
]),
|
||||
Self::UnknownTool { qualified_name } => BTreeMap::from([(
|
||||
"qualified_tool".to_string(),
|
||||
qualified_name.clone(),
|
||||
)]),
|
||||
Self::UnknownTool { qualified_name } => {
|
||||
BTreeMap::from([("qualified_tool".to_string(), qualified_name.clone())])
|
||||
}
|
||||
Self::UnknownServer { server_name } => {
|
||||
BTreeMap::from([("server".to_string(), server_name.clone())])
|
||||
}
|
||||
@@ -1425,11 +1426,10 @@ mod tests {
|
||||
use crate::mcp_client::McpClientBootstrap;
|
||||
|
||||
use super::{
|
||||
spawn_mcp_stdio_process, JsonRpcId, JsonRpcRequest, JsonRpcResponse,
|
||||
McpInitializeClientInfo, McpInitializeParams, McpInitializeResult, McpInitializeServerInfo,
|
||||
McpListToolsResult, McpReadResourceParams, McpReadResourceResult, McpServerManager,
|
||||
McpServerManagerError, McpStdioProcess, McpTool, McpToolCallParams,
|
||||
unsupported_server_failed_server,
|
||||
spawn_mcp_stdio_process, unsupported_server_failed_server, JsonRpcId, JsonRpcRequest,
|
||||
JsonRpcResponse, McpInitializeClientInfo, McpInitializeParams, McpInitializeResult,
|
||||
McpInitializeServerInfo, McpListToolsResult, McpReadResourceParams, McpReadResourceResult,
|
||||
McpServerManager, McpServerManagerError, McpStdioProcess, McpTool, McpToolCallParams,
|
||||
};
|
||||
use crate::McpLifecyclePhase;
|
||||
|
||||
@@ -2698,7 +2698,10 @@ mod tests {
|
||||
);
|
||||
assert!(!report.failed_servers[0].recoverable);
|
||||
assert_eq!(
|
||||
report.failed_servers[0].context.get("method").map(String::as_str),
|
||||
report.failed_servers[0]
|
||||
.context
|
||||
.get("method")
|
||||
.map(String::as_str),
|
||||
Some("initialize")
|
||||
);
|
||||
assert!(report.failed_servers[0].error.contains("initialize"));
|
||||
|
||||
@@ -4,7 +4,6 @@ use std::fs;
|
||||
use std::path::{Path, PathBuf};
|
||||
use std::time::UNIX_EPOCH;
|
||||
|
||||
|
||||
use crate::session::{Session, SessionError};
|
||||
|
||||
pub const PRIMARY_SESSION_EXTENSION: &str = "jsonl";
|
||||
|
||||
@@ -66,11 +66,7 @@ pub fn validate_packet(packet: TaskPacket) -> Result<ValidatedPacket, TaskPacket
|
||||
&packet.reporting_contract,
|
||||
&mut errors,
|
||||
);
|
||||
validate_required(
|
||||
"escalation_policy",
|
||||
&packet.escalation_policy,
|
||||
&mut errors,
|
||||
);
|
||||
validate_required("escalation_policy", &packet.escalation_policy, &mut errors);
|
||||
|
||||
for (index, test) in packet.acceptance_tests.iter().enumerate() {
|
||||
if test.trim().is_empty() {
|
||||
@@ -146,9 +142,9 @@ mod tests {
|
||||
assert!(error
|
||||
.errors()
|
||||
.contains(&"repo must not be empty".to_string()));
|
||||
assert!(error.errors().contains(
|
||||
&"acceptance_tests contains an empty value at index 1".to_string()
|
||||
));
|
||||
assert!(error
|
||||
.errors()
|
||||
.contains(&"acceptance_tests contains an empty value at index 1".to_string()));
|
||||
}
|
||||
|
||||
#[test]
|
||||
|
||||
@@ -76,11 +76,7 @@ impl TaskRegistry {
|
||||
}
|
||||
|
||||
pub fn create(&self, prompt: &str, description: Option<&str>) -> Task {
|
||||
self.create_task(
|
||||
prompt.to_owned(),
|
||||
description.map(str::to_owned),
|
||||
None,
|
||||
)
|
||||
self.create_task(prompt.to_owned(), description.map(str::to_owned), None)
|
||||
}
|
||||
|
||||
pub fn create_from_packet(
|
||||
|
||||
@@ -257,7 +257,9 @@ impl WorkerRegistry {
|
||||
let prompt_preview = prompt_preview(worker.last_prompt.as_deref().unwrap_or_default());
|
||||
let message = match observation.target {
|
||||
WorkerPromptTarget::Shell => {
|
||||
format!("worker prompt landed in shell instead of coding agent: {prompt_preview}")
|
||||
format!(
|
||||
"worker prompt landed in shell instead of coding agent: {prompt_preview}"
|
||||
)
|
||||
}
|
||||
WorkerPromptTarget::WrongTarget => format!(
|
||||
"worker prompt landed in the wrong target instead of {}: {}",
|
||||
@@ -312,7 +314,9 @@ impl WorkerRegistry {
|
||||
worker.last_error = None;
|
||||
}
|
||||
|
||||
if detect_ready_for_prompt(screen_text, &lowered) && worker.status != WorkerStatus::ReadyForPrompt {
|
||||
if detect_ready_for_prompt(screen_text, &lowered)
|
||||
&& worker.status != WorkerStatus::ReadyForPrompt
|
||||
{
|
||||
worker.status = WorkerStatus::ReadyForPrompt;
|
||||
worker.prompt_in_flight = false;
|
||||
if matches!(
|
||||
@@ -412,7 +416,10 @@ impl WorkerRegistry {
|
||||
worker_id: worker.worker_id.clone(),
|
||||
status: worker.status,
|
||||
ready: worker.status == WorkerStatus::ReadyForPrompt,
|
||||
blocked: matches!(worker.status, WorkerStatus::TrustRequired | WorkerStatus::Failed),
|
||||
blocked: matches!(
|
||||
worker.status,
|
||||
WorkerStatus::TrustRequired | WorkerStatus::Failed
|
||||
),
|
||||
replay_prompt_ready: worker.replay_prompt.is_some(),
|
||||
last_error: worker.last_error.clone(),
|
||||
})
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
449
rust/crates/rusty-claude-cli/tests/output_format_contract.rs
Normal file
449
rust/crates/rusty-claude-cli/tests/output_format_contract.rs
Normal file
@@ -0,0 +1,449 @@
|
||||
use std::fs;
|
||||
use std::io::{Read, Write};
|
||||
use std::net::TcpListener;
|
||||
use std::path::{Path, PathBuf};
|
||||
use std::process::{Command, Output};
|
||||
use std::sync::atomic::{AtomicU64, Ordering};
|
||||
use std::thread;
|
||||
use std::time::{SystemTime, UNIX_EPOCH};
|
||||
|
||||
use mock_anthropic_service::{MockAnthropicService, SCENARIO_PREFIX};
|
||||
use serde_json::{json, Value};
|
||||
|
||||
static TEMP_COUNTER: AtomicU64 = AtomicU64::new(0);
|
||||
|
||||
#[test]
|
||||
fn help_emits_json_when_requested() {
|
||||
let root = unique_temp_dir("help-json");
|
||||
fs::create_dir_all(&root).expect("temp dir should exist");
|
||||
let envs = isolated_env(&root);
|
||||
|
||||
let parsed = assert_json_command(&root, &["--output-format", "json", "help"], &envs);
|
||||
|
||||
assert_eq!(parsed["kind"], "help");
|
||||
assert!(parsed["message"]
|
||||
.as_str()
|
||||
.expect("help message")
|
||||
.contains("Usage:"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn version_emits_json_when_requested() {
|
||||
let root = unique_temp_dir("version-json");
|
||||
fs::create_dir_all(&root).expect("temp dir should exist");
|
||||
let envs = isolated_env(&root);
|
||||
|
||||
let parsed = assert_json_command(&root, &["--output-format", "json", "version"], &envs);
|
||||
|
||||
assert_eq!(parsed["kind"], "version");
|
||||
assert_eq!(parsed["version"], env!("CARGO_PKG_VERSION"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn status_emits_json_when_requested() {
|
||||
let root = unique_temp_dir("status-json");
|
||||
fs::create_dir_all(&root).expect("temp dir should exist");
|
||||
let envs = isolated_env(&root);
|
||||
|
||||
let parsed = assert_json_command(&root, &["--output-format", "json", "status"], &envs);
|
||||
|
||||
assert_eq!(parsed["kind"], "status");
|
||||
assert!(parsed["workspace"]["cwd"].as_str().is_some());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sandbox_emits_json_when_requested() {
|
||||
let root = unique_temp_dir("sandbox-json");
|
||||
fs::create_dir_all(&root).expect("temp dir should exist");
|
||||
let envs = isolated_env(&root);
|
||||
|
||||
let parsed = assert_json_command(&root, &["--output-format", "json", "sandbox"], &envs);
|
||||
|
||||
assert_eq!(parsed["kind"], "sandbox");
|
||||
assert!(parsed["sandbox"].is_object());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn dump_manifests_emits_json_when_requested() {
|
||||
let root = unique_temp_dir("dump-manifests-json");
|
||||
fs::create_dir_all(&root).expect("temp dir should exist");
|
||||
let upstream = write_upstream_fixture(&root);
|
||||
let mut envs = isolated_env(&root);
|
||||
envs.push((
|
||||
"CLAUDE_CODE_UPSTREAM".to_string(),
|
||||
upstream.display().to_string(),
|
||||
));
|
||||
|
||||
let parsed = assert_json_command(&root, &["--output-format", "json", "dump-manifests"], &envs);
|
||||
|
||||
assert_eq!(parsed["kind"], "dump-manifests");
|
||||
assert_eq!(parsed["commands"], 1);
|
||||
assert_eq!(parsed["tools"], 1);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn bootstrap_plan_emits_json_when_requested() {
|
||||
let root = unique_temp_dir("bootstrap-plan-json");
|
||||
fs::create_dir_all(&root).expect("temp dir should exist");
|
||||
let envs = isolated_env(&root);
|
||||
|
||||
let parsed = assert_json_command(&root, &["--output-format", "json", "bootstrap-plan"], &envs);
|
||||
|
||||
assert_eq!(parsed["kind"], "bootstrap-plan");
|
||||
assert!(parsed["phases"].as_array().expect("phases array").len() > 1);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn agents_emits_json_when_requested() {
|
||||
let root = unique_temp_dir("agents-json");
|
||||
fs::create_dir_all(&root).expect("temp dir should exist");
|
||||
let envs = isolated_env(&root);
|
||||
|
||||
let parsed = assert_json_command(&root, &["--output-format", "json", "agents"], &envs);
|
||||
|
||||
assert_eq!(parsed["kind"], "agents");
|
||||
assert!(!parsed["message"].as_str().expect("agents text").is_empty());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn mcp_emits_json_when_requested() {
|
||||
let root = unique_temp_dir("mcp-json");
|
||||
fs::create_dir_all(&root).expect("temp dir should exist");
|
||||
let envs = isolated_env(&root);
|
||||
|
||||
let parsed = assert_json_command(&root, &["--output-format", "json", "mcp"], &envs);
|
||||
|
||||
assert_eq!(parsed["kind"], "mcp");
|
||||
assert!(parsed["message"]
|
||||
.as_str()
|
||||
.expect("mcp text")
|
||||
.contains("MCP"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn skills_emits_json_when_requested() {
|
||||
let root = unique_temp_dir("skills-json");
|
||||
fs::create_dir_all(&root).expect("temp dir should exist");
|
||||
let envs = isolated_env(&root);
|
||||
|
||||
let parsed = assert_json_command(&root, &["--output-format", "json", "skills"], &envs);
|
||||
|
||||
assert_eq!(parsed["kind"], "skills");
|
||||
assert!(!parsed["message"].as_str().expect("skills text").is_empty());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn system_prompt_emits_json_when_requested() {
|
||||
let root = unique_temp_dir("system-prompt-json");
|
||||
fs::create_dir_all(&root).expect("temp dir should exist");
|
||||
let envs = isolated_env(&root);
|
||||
|
||||
let parsed = assert_json_command(&root, &["--output-format", "json", "system-prompt"], &envs);
|
||||
|
||||
assert_eq!(parsed["kind"], "system-prompt");
|
||||
assert!(parsed["message"]
|
||||
.as_str()
|
||||
.expect("system prompt text")
|
||||
.contains("You are an interactive agent"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn login_emits_json_when_requested() {
|
||||
let root = unique_temp_dir("login-json");
|
||||
let workspace = root.join("workspace");
|
||||
fs::create_dir_all(&workspace).expect("workspace should exist");
|
||||
let mut envs = isolated_env(&root);
|
||||
let callback_port = reserve_port();
|
||||
let token_port = reserve_port();
|
||||
|
||||
fs::create_dir_all(workspace.join(".claw")).expect("config dir should exist");
|
||||
fs::write(
|
||||
workspace.join(".claw").join("settings.json"),
|
||||
json!({
|
||||
"oauth": {
|
||||
"clientId": "test-client",
|
||||
"authorizeUrl": format!("http://127.0.0.1:{token_port}/authorize"),
|
||||
"tokenUrl": format!("http://127.0.0.1:{token_port}/token"),
|
||||
"callbackPort": callback_port,
|
||||
"scopes": ["user:test"]
|
||||
}
|
||||
})
|
||||
.to_string(),
|
||||
)
|
||||
.expect("oauth config should write");
|
||||
|
||||
let token_server = thread::spawn(move || {
|
||||
let listener = TcpListener::bind(("127.0.0.1", token_port)).expect("token server bind");
|
||||
let (mut stream, _) = listener.accept().expect("token request");
|
||||
let mut request = [0_u8; 4096];
|
||||
let _ = stream
|
||||
.read(&mut request)
|
||||
.expect("token request should read");
|
||||
let body = json!({
|
||||
"access_token": "test-access-token",
|
||||
"refresh_token": "test-refresh-token",
|
||||
"expires_at": 9_999_999_999_u64,
|
||||
"scopes": ["user:test"]
|
||||
})
|
||||
.to_string();
|
||||
let response = format!(
|
||||
"HTTP/1.1 200 OK\r\ncontent-type: application/json\r\ncontent-length: {}\r\nconnection: close\r\n\r\n{}",
|
||||
body.len(),
|
||||
body
|
||||
);
|
||||
stream
|
||||
.write_all(response.as_bytes())
|
||||
.expect("token response should write");
|
||||
});
|
||||
|
||||
let bin_dir = root.join("bin");
|
||||
fs::create_dir_all(&bin_dir).expect("bin dir should exist");
|
||||
let opener_path = bin_dir.join("xdg-open");
|
||||
fs::write(
|
||||
&opener_path,
|
||||
format!(
|
||||
"#!/usr/bin/env python3\nimport http.client\nimport sys\nimport urllib.parse\nurl = sys.argv[1]\nquery = urllib.parse.parse_qs(urllib.parse.urlparse(url).query)\nstate = query['state'][0]\nconn = http.client.HTTPConnection('127.0.0.1', {callback_port}, timeout=5)\nconn.request('GET', f\"/callback?code=test-code&state={{urllib.parse.quote(state)}}\")\nresp = conn.getresponse()\nresp.read()\nconn.close()\n"
|
||||
),
|
||||
)
|
||||
.expect("xdg-open wrapper should write");
|
||||
#[cfg(unix)]
|
||||
{
|
||||
use std::os::unix::fs::PermissionsExt;
|
||||
let mut permissions = fs::metadata(&opener_path)
|
||||
.expect("wrapper metadata")
|
||||
.permissions();
|
||||
permissions.set_mode(0o755);
|
||||
fs::set_permissions(&opener_path, permissions).expect("wrapper permissions");
|
||||
}
|
||||
let original_path = envs
|
||||
.iter()
|
||||
.find(|(key, _)| key == "PATH")
|
||||
.map(|(_, value)| value.clone())
|
||||
.unwrap_or_default();
|
||||
for (key, value) in &mut envs {
|
||||
if key == "PATH" {
|
||||
*value = format!("{}:{original_path}", bin_dir.display());
|
||||
}
|
||||
}
|
||||
|
||||
let parsed = assert_json_command(&workspace, &["--output-format", "json", "login"], &envs);
|
||||
|
||||
token_server.join().expect("token server should finish");
|
||||
assert_eq!(parsed["kind"], "login");
|
||||
assert_eq!(parsed["callback_port"], callback_port);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn logout_emits_json_when_requested() {
|
||||
let root = unique_temp_dir("logout-json");
|
||||
fs::create_dir_all(&root).expect("temp dir should exist");
|
||||
let envs = isolated_env(&root);
|
||||
|
||||
let parsed = assert_json_command(&root, &["--output-format", "json", "logout"], &envs);
|
||||
|
||||
assert_eq!(parsed["kind"], "logout");
|
||||
assert!(parsed["message"]
|
||||
.as_str()
|
||||
.expect("logout text")
|
||||
.contains("cleared"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn init_emits_json_when_requested() {
|
||||
let root = unique_temp_dir("init-json");
|
||||
let workspace = root.join("workspace");
|
||||
fs::create_dir_all(&workspace).expect("workspace should exist");
|
||||
let envs = isolated_env(&root);
|
||||
|
||||
let parsed = assert_json_command(&workspace, &["--output-format", "json", "init"], &envs);
|
||||
|
||||
assert_eq!(parsed["kind"], "init");
|
||||
assert!(workspace.join("CLAUDE.md").exists());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn prompt_subcommand_emits_json_when_requested() {
|
||||
let root = unique_temp_dir("prompt-subcommand-json");
|
||||
fs::create_dir_all(&root).expect("temp dir should exist");
|
||||
let mut envs = isolated_env(&root);
|
||||
let runtime = tokio::runtime::Runtime::new().expect("tokio runtime should build");
|
||||
let server = runtime
|
||||
.block_on(MockAnthropicService::spawn())
|
||||
.expect("mock service should start");
|
||||
envs.push(("ANTHROPIC_API_KEY".to_string(), "test-key".to_string()));
|
||||
envs.push(("ANTHROPIC_BASE_URL".to_string(), server.base_url()));
|
||||
|
||||
let prompt = format!("{SCENARIO_PREFIX}streaming_text");
|
||||
let args = vec![
|
||||
"--model".to_string(),
|
||||
"sonnet".to_string(),
|
||||
"--permission-mode".to_string(),
|
||||
"read-only".to_string(),
|
||||
"--output-format".to_string(),
|
||||
"json".to_string(),
|
||||
"prompt".to_string(),
|
||||
prompt,
|
||||
];
|
||||
let output = run_claw_with_env_owned(&root, &args, &envs);
|
||||
let parsed = parse_json_stdout(&output);
|
||||
|
||||
assert_eq!(parsed["model"], "claude-sonnet-4-6");
|
||||
assert!(parsed["message"]
|
||||
.as_str()
|
||||
.expect("assistant text")
|
||||
.contains("streaming"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn bare_prompt_mode_emits_json_when_requested() {
|
||||
let root = unique_temp_dir("bare-prompt-json");
|
||||
fs::create_dir_all(&root).expect("temp dir should exist");
|
||||
let mut envs = isolated_env(&root);
|
||||
let runtime = tokio::runtime::Runtime::new().expect("tokio runtime should build");
|
||||
let server = runtime
|
||||
.block_on(MockAnthropicService::spawn())
|
||||
.expect("mock service should start");
|
||||
envs.push(("ANTHROPIC_API_KEY".to_string(), "test-key".to_string()));
|
||||
envs.push(("ANTHROPIC_BASE_URL".to_string(), server.base_url()));
|
||||
|
||||
let prompt = format!("{SCENARIO_PREFIX}streaming_text");
|
||||
let args = vec![
|
||||
"--model".to_string(),
|
||||
"sonnet".to_string(),
|
||||
"--permission-mode".to_string(),
|
||||
"read-only".to_string(),
|
||||
"--output-format".to_string(),
|
||||
"json".to_string(),
|
||||
prompt,
|
||||
];
|
||||
let output = run_claw_with_env_owned(&root, &args, &envs);
|
||||
let parsed = parse_json_stdout(&output);
|
||||
|
||||
assert_eq!(parsed["model"], "claude-sonnet-4-6");
|
||||
assert!(parsed["message"]
|
||||
.as_str()
|
||||
.expect("assistant text")
|
||||
.contains("streaming"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn resume_restore_emits_json_when_requested() {
|
||||
let root = unique_temp_dir("resume-json");
|
||||
fs::create_dir_all(&root).expect("temp dir should exist");
|
||||
let envs = isolated_env(&root);
|
||||
let session_path = root.join("session.jsonl");
|
||||
fs::write(
|
||||
&session_path,
|
||||
"{\"type\":\"session_meta\",\"version\":3,\"session_id\":\"resume-json\",\"created_at_ms\":0,\"updated_at_ms\":0}\n{\"type\":\"message\",\"message\":{\"role\":\"user\",\"blocks\":[{\"type\":\"text\",\"text\":\"hello\"}]}}\n",
|
||||
)
|
||||
.expect("session should write");
|
||||
|
||||
let args = vec![
|
||||
"--output-format".to_string(),
|
||||
"json".to_string(),
|
||||
"--resume".to_string(),
|
||||
session_path.display().to_string(),
|
||||
];
|
||||
let output = run_claw_with_env_owned(&root, &args, &envs);
|
||||
let parsed = parse_json_stdout(&output);
|
||||
|
||||
assert_eq!(parsed["kind"], "resume");
|
||||
assert_eq!(parsed["messages"], 1);
|
||||
}
|
||||
|
||||
fn assert_json_command(current_dir: &Path, args: &[&str], envs: &[(String, String)]) -> Value {
|
||||
let output = run_claw_with_env(current_dir, args, envs);
|
||||
parse_json_stdout(&output)
|
||||
}
|
||||
|
||||
fn parse_json_stdout(output: &Output) -> Value {
|
||||
assert!(
|
||||
output.status.success(),
|
||||
"stdout:\n{}\n\nstderr:\n{}",
|
||||
String::from_utf8_lossy(&output.stdout),
|
||||
String::from_utf8_lossy(&output.stderr)
|
||||
);
|
||||
serde_json::from_slice(&output.stdout).expect("stdout should be json")
|
||||
}
|
||||
|
||||
fn run_claw_with_env(current_dir: &Path, args: &[&str], envs: &[(String, String)]) -> Output {
|
||||
let owned_args = args
|
||||
.iter()
|
||||
.map(|value| (*value).to_string())
|
||||
.collect::<Vec<_>>();
|
||||
run_claw_with_env_owned(current_dir, &owned_args, envs)
|
||||
}
|
||||
|
||||
fn run_claw_with_env_owned(
|
||||
current_dir: &Path,
|
||||
args: &[String],
|
||||
envs: &[(String, String)],
|
||||
) -> Output {
|
||||
let mut command = Command::new(env!("CARGO_BIN_EXE_claw"));
|
||||
command.current_dir(current_dir).args(args).env_clear();
|
||||
for (key, value) in envs {
|
||||
command.env(key, value);
|
||||
}
|
||||
command.output().expect("claw should launch")
|
||||
}
|
||||
|
||||
fn isolated_env(root: &Path) -> Vec<(String, String)> {
|
||||
let config_home = root.join("config-home");
|
||||
let home = root.join("home");
|
||||
fs::create_dir_all(&config_home).expect("config home should exist");
|
||||
fs::create_dir_all(&home).expect("home should exist");
|
||||
vec![
|
||||
(
|
||||
"CLAW_CONFIG_HOME".to_string(),
|
||||
config_home.display().to_string(),
|
||||
),
|
||||
("HOME".to_string(), home.display().to_string()),
|
||||
(
|
||||
"PATH".to_string(),
|
||||
std::env::var("PATH").unwrap_or_else(|_| "/usr/bin:/bin".to_string()),
|
||||
),
|
||||
("NO_COLOR".to_string(), "1".to_string()),
|
||||
]
|
||||
}
|
||||
|
||||
fn write_upstream_fixture(root: &Path) -> PathBuf {
|
||||
let upstream = root.join("claw-code");
|
||||
let src = upstream.join("src");
|
||||
let entrypoints = src.join("entrypoints");
|
||||
fs::create_dir_all(&entrypoints).expect("upstream entrypoints dir should exist");
|
||||
fs::write(
|
||||
src.join("commands.ts"),
|
||||
"import FooCommand from './commands/foo'\n",
|
||||
)
|
||||
.expect("commands fixture should write");
|
||||
fs::write(
|
||||
src.join("tools.ts"),
|
||||
"import ReadTool from './tools/read'\n",
|
||||
)
|
||||
.expect("tools fixture should write");
|
||||
fs::write(
|
||||
entrypoints.join("cli.tsx"),
|
||||
"if (args[0] === '--version') {}\nstartupProfiler()\n",
|
||||
)
|
||||
.expect("cli fixture should write");
|
||||
upstream
|
||||
}
|
||||
|
||||
fn reserve_port() -> u16 {
|
||||
let listener = TcpListener::bind(("127.0.0.1", 0)).expect("ephemeral port should bind");
|
||||
let port = listener.local_addr().expect("local addr").port();
|
||||
drop(listener);
|
||||
port
|
||||
}
|
||||
|
||||
fn unique_temp_dir(label: &str) -> PathBuf {
|
||||
let millis = SystemTime::now()
|
||||
.duration_since(UNIX_EPOCH)
|
||||
.expect("clock should be after epoch")
|
||||
.as_millis();
|
||||
let counter = TEMP_COUNTER.fetch_add(1, Ordering::Relaxed);
|
||||
std::env::temp_dir().join(format!(
|
||||
"claw-output-format-{label}-{}-{millis}-{counter}",
|
||||
std::process::id()
|
||||
))
|
||||
}
|
||||
@@ -7,6 +7,7 @@ use std::time::{SystemTime, UNIX_EPOCH};
|
||||
|
||||
use runtime::ContentBlock;
|
||||
use runtime::Session;
|
||||
use serde_json::Value;
|
||||
|
||||
static TEMP_COUNTER: AtomicU64 = AtomicU64::new(0);
|
||||
|
||||
@@ -221,6 +222,52 @@ fn resume_latest_restores_the_most_recent_managed_session() {
|
||||
assert!(stdout.contains(newer_path.to_str().expect("utf8 path")));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn resumed_status_command_emits_structured_json_when_requested() {
|
||||
// given
|
||||
let temp_dir = unique_temp_dir("resume-status-json");
|
||||
fs::create_dir_all(&temp_dir).expect("temp dir should exist");
|
||||
let session_path = temp_dir.join("session.jsonl");
|
||||
|
||||
let mut session = Session::new();
|
||||
session
|
||||
.push_user_text("resume status json fixture")
|
||||
.expect("session write should succeed");
|
||||
session
|
||||
.save_to_path(&session_path)
|
||||
.expect("session should persist");
|
||||
|
||||
// when
|
||||
let output = run_claw(
|
||||
&temp_dir,
|
||||
&[
|
||||
"--output-format",
|
||||
"json",
|
||||
"--resume",
|
||||
session_path.to_str().expect("utf8 path"),
|
||||
"/status",
|
||||
],
|
||||
);
|
||||
|
||||
// then
|
||||
assert!(
|
||||
output.status.success(),
|
||||
"stdout:\n{}\n\nstderr:\n{}",
|
||||
String::from_utf8_lossy(&output.stdout),
|
||||
String::from_utf8_lossy(&output.stderr)
|
||||
);
|
||||
|
||||
let stdout = String::from_utf8(output.stdout).expect("stdout should be utf8");
|
||||
let parsed: Value =
|
||||
serde_json::from_str(stdout.trim()).expect("resume status output should be json");
|
||||
assert_eq!(parsed["kind"], "status");
|
||||
assert_eq!(parsed["messages"], 1);
|
||||
assert_eq!(
|
||||
parsed["workspace"]["session"],
|
||||
session_path.to_str().expect("utf8 path")
|
||||
);
|
||||
}
|
||||
|
||||
fn run_claw(current_dir: &Path, args: &[&str]) -> Output {
|
||||
run_claw_with_env(current_dir, args, &[])
|
||||
}
|
||||
|
||||
@@ -16,7 +16,7 @@ use runtime::{
|
||||
use crate::AgentOutput;
|
||||
|
||||
/// Detects if a lane should be automatically marked as completed.
|
||||
///
|
||||
///
|
||||
/// Returns `Some(LaneContext)` with `completed = true` if all conditions met,
|
||||
/// `None` if lane should remain active.
|
||||
#[allow(dead_code)]
|
||||
@@ -29,29 +29,29 @@ pub(crate) fn detect_lane_completion(
|
||||
if output.error.is_some() {
|
||||
return None;
|
||||
}
|
||||
|
||||
|
||||
// Must have finished status
|
||||
if !output.status.eq_ignore_ascii_case("completed")
|
||||
&& !output.status.eq_ignore_ascii_case("finished")
|
||||
{
|
||||
return None;
|
||||
}
|
||||
|
||||
|
||||
// Must have no current blocker
|
||||
if output.current_blocker.is_some() {
|
||||
return None;
|
||||
}
|
||||
|
||||
|
||||
// Must have green tests
|
||||
if !test_green {
|
||||
return None;
|
||||
}
|
||||
|
||||
|
||||
// Must have pushed code
|
||||
if !has_pushed {
|
||||
return None;
|
||||
}
|
||||
|
||||
|
||||
// All conditions met — create completed context
|
||||
Some(LaneContext {
|
||||
lane_id: output.agent_id.clone(),
|
||||
@@ -67,9 +67,7 @@ pub(crate) fn detect_lane_completion(
|
||||
|
||||
/// Evaluates policy actions for a completed lane.
|
||||
#[allow(dead_code)]
|
||||
pub(crate) fn evaluate_completed_lane(
|
||||
context: &LaneContext,
|
||||
) -> Vec<PolicyAction> {
|
||||
pub(crate) fn evaluate_completed_lane(context: &LaneContext) -> Vec<PolicyAction> {
|
||||
let engine = PolicyEngine::new(vec![
|
||||
PolicyRule::new(
|
||||
"closeout-completed-lane",
|
||||
@@ -87,7 +85,7 @@ pub(crate) fn evaluate_completed_lane(
|
||||
5,
|
||||
),
|
||||
]);
|
||||
|
||||
|
||||
evaluate(&engine, context)
|
||||
}
|
||||
|
||||
@@ -114,53 +112,53 @@ mod tests {
|
||||
error: None,
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
#[test]
|
||||
fn detects_completion_when_all_conditions_met() {
|
||||
let output = test_output();
|
||||
let result = detect_lane_completion(&output, true, true);
|
||||
|
||||
|
||||
assert!(result.is_some());
|
||||
let context = result.unwrap();
|
||||
assert!(context.completed);
|
||||
assert_eq!(context.green_level, 3);
|
||||
assert_eq!(context.blocker, LaneBlocker::None);
|
||||
}
|
||||
|
||||
|
||||
#[test]
|
||||
fn no_completion_when_error_present() {
|
||||
let mut output = test_output();
|
||||
output.error = Some("Build failed".to_string());
|
||||
|
||||
|
||||
let result = detect_lane_completion(&output, true, true);
|
||||
assert!(result.is_none());
|
||||
}
|
||||
|
||||
|
||||
#[test]
|
||||
fn no_completion_when_not_finished() {
|
||||
let mut output = test_output();
|
||||
output.status = "Running".to_string();
|
||||
|
||||
|
||||
let result = detect_lane_completion(&output, true, true);
|
||||
assert!(result.is_none());
|
||||
}
|
||||
|
||||
|
||||
#[test]
|
||||
fn no_completion_when_tests_not_green() {
|
||||
let output = test_output();
|
||||
|
||||
|
||||
let result = detect_lane_completion(&output, false, true);
|
||||
assert!(result.is_none());
|
||||
}
|
||||
|
||||
|
||||
#[test]
|
||||
fn no_completion_when_not_pushed() {
|
||||
let output = test_output();
|
||||
|
||||
|
||||
let result = detect_lane_completion(&output, true, false);
|
||||
assert!(result.is_none());
|
||||
}
|
||||
|
||||
|
||||
#[test]
|
||||
fn evaluate_triggers_closeout_for_completed_lane() {
|
||||
let context = LaneContext {
|
||||
@@ -173,9 +171,9 @@ mod tests {
|
||||
completed: true,
|
||||
reconciled: false,
|
||||
};
|
||||
|
||||
|
||||
let actions = evaluate_completed_lane(&context);
|
||||
|
||||
|
||||
assert!(actions.contains(&PolicyAction::CloseoutLane));
|
||||
assert!(actions.contains(&PolicyAction::CleanupSession));
|
||||
}
|
||||
|
||||
@@ -17,7 +17,6 @@ use runtime::{
|
||||
permission_enforcer::{EnforcementResult, PermissionEnforcer},
|
||||
read_file,
|
||||
summary_compression::compress_summary_text,
|
||||
TaskPacket,
|
||||
task_registry::TaskRegistry,
|
||||
team_cron_registry::{CronRegistry, TeamRegistry},
|
||||
worker_boot::{WorkerReadySnapshot, WorkerRegistry},
|
||||
@@ -25,7 +24,7 @@ use runtime::{
|
||||
BranchFreshness, ContentBlock, ConversationMessage, ConversationRuntime, GrepSearchInput,
|
||||
LaneEvent, LaneEventBlocker, LaneEventName, LaneEventStatus, LaneFailureClass,
|
||||
McpDegradedReport, MessageRole, PermissionMode, PermissionPolicy, PromptCacheEvent,
|
||||
RuntimeError, Session, ToolError, ToolExecutor,
|
||||
RuntimeError, Session, TaskPacket, ToolError, ToolExecutor,
|
||||
};
|
||||
use serde::{Deserialize, Serialize};
|
||||
use serde_json::{json, Value};
|
||||
@@ -1878,27 +1877,25 @@ fn branch_divergence_output(
|
||||
dangerously_disable_sandbox: None,
|
||||
return_code_interpretation: Some("preflight_blocked:branch_divergence".to_string()),
|
||||
no_output_expected: Some(false),
|
||||
structured_content: Some(vec![
|
||||
serde_json::to_value(
|
||||
LaneEvent::new(
|
||||
LaneEventName::BranchStaleAgainstMain,
|
||||
LaneEventStatus::Blocked,
|
||||
iso8601_now(),
|
||||
)
|
||||
.with_failure_class(LaneFailureClass::BranchDivergence)
|
||||
.with_detail(stderr.clone())
|
||||
.with_data(json!({
|
||||
"branch": branch,
|
||||
"mainRef": main_ref,
|
||||
"commitsBehind": commits_behind,
|
||||
"commitsAhead": commits_ahead,
|
||||
"missingCommits": missing_fixes,
|
||||
"blockedCommand": command,
|
||||
"recommendedAction": format!("merge or rebase {main_ref} before workspace tests")
|
||||
})),
|
||||
structured_content: Some(vec![serde_json::to_value(
|
||||
LaneEvent::new(
|
||||
LaneEventName::BranchStaleAgainstMain,
|
||||
LaneEventStatus::Blocked,
|
||||
iso8601_now(),
|
||||
)
|
||||
.expect("lane event should serialize"),
|
||||
]),
|
||||
.with_failure_class(LaneFailureClass::BranchDivergence)
|
||||
.with_detail(stderr.clone())
|
||||
.with_data(json!({
|
||||
"branch": branch,
|
||||
"mainRef": main_ref,
|
||||
"commitsBehind": commits_behind,
|
||||
"commitsAhead": commits_ahead,
|
||||
"missingCommits": missing_fixes,
|
||||
"blockedCommand": command,
|
||||
"recommendedAction": format!("merge or rebase {main_ref} before workspace tests")
|
||||
})),
|
||||
)
|
||||
.expect("lane event should serialize")]),
|
||||
persisted_output_path: None,
|
||||
persisted_output_size: None,
|
||||
sandbox_status: None,
|
||||
@@ -3297,12 +3294,12 @@ fn persist_agent_terminal_state(
|
||||
next_manifest.current_blocker = blocker.clone();
|
||||
next_manifest.error = error;
|
||||
if let Some(blocker) = blocker {
|
||||
next_manifest.lane_events.push(
|
||||
LaneEvent::blocked(iso8601_now(), &blocker),
|
||||
);
|
||||
next_manifest.lane_events.push(
|
||||
LaneEvent::failed(iso8601_now(), &blocker),
|
||||
);
|
||||
next_manifest
|
||||
.lane_events
|
||||
.push(LaneEvent::blocked(iso8601_now(), &blocker));
|
||||
next_manifest
|
||||
.lane_events
|
||||
.push(LaneEvent::failed(iso8601_now(), &blocker));
|
||||
} else {
|
||||
next_manifest.current_blocker = None;
|
||||
let compressed_detail = result
|
||||
@@ -4952,8 +4949,8 @@ mod tests {
|
||||
agent_permission_policy, allowed_tools_for_subagent, classify_lane_failure,
|
||||
execute_agent_with_spawn, execute_tool, final_assistant_text, mvp_tool_specs,
|
||||
permission_mode_from_plugin, persist_agent_terminal_state, push_output_block,
|
||||
run_task_packet, AgentInput, AgentJob, GlobalToolRegistry, LaneEventName,
|
||||
LaneFailureClass, SubagentToolExecutor,
|
||||
run_task_packet, AgentInput, AgentJob, GlobalToolRegistry, LaneEventName, LaneFailureClass,
|
||||
SubagentToolExecutor,
|
||||
};
|
||||
use api::OutputContentBlock;
|
||||
use runtime::{
|
||||
@@ -5977,7 +5974,10 @@ mod tests {
|
||||
"gateway routing rejected the request",
|
||||
LaneFailureClass::GatewayRouting,
|
||||
),
|
||||
("tool failed: denied tool execution from hook", LaneFailureClass::ToolRuntime),
|
||||
(
|
||||
"tool failed: denied tool execution from hook",
|
||||
LaneFailureClass::ToolRuntime,
|
||||
),
|
||||
("thread creation failed", LaneFailureClass::Infra),
|
||||
];
|
||||
|
||||
@@ -6000,11 +6000,17 @@ mod tests {
|
||||
(LaneEventName::MergeReady, "lane.merge.ready"),
|
||||
(LaneEventName::Finished, "lane.finished"),
|
||||
(LaneEventName::Failed, "lane.failed"),
|
||||
(LaneEventName::BranchStaleAgainstMain, "branch.stale_against_main"),
|
||||
(
|
||||
LaneEventName::BranchStaleAgainstMain,
|
||||
"branch.stale_against_main",
|
||||
),
|
||||
];
|
||||
|
||||
for (event, expected) in cases {
|
||||
assert_eq!(serde_json::to_value(event).expect("serialize lane event"), json!(expected));
|
||||
assert_eq!(
|
||||
serde_json::to_value(event).expect("serialize lane event"),
|
||||
json!(expected)
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user