chore: resolve conflicts

This commit is contained in:
italic-jinxin
2026-03-20 13:29:17 +08:00
110 changed files with 8713 additions and 2350 deletions
+43 -6
View File
@@ -8,6 +8,9 @@ use crate::llm::SessionManager;
use crate::settings::Settings;
use crate::workspace::EmbeddingProvider;
/// Default maximum number of cached embeddings.
pub const DEFAULT_EMBEDDING_CACHE_SIZE: usize = 10_000;
/// Embeddings provider configuration.
#[derive(Debug, Clone)]
pub struct EmbeddingsConfig {
@@ -26,6 +29,12 @@ pub struct EmbeddingsConfig {
/// Custom base URL for OpenAI-compatible embedding providers.
/// When set, overrides the default `https://api.openai.com`.
pub openai_base_url: Option<String>,
/// Maximum entries in the embedding LRU cache (default 10,000).
///
/// Approximate raw embedding payload: `cache_size × dimension × 4 bytes`.
/// 10,000 × 1536 floats ≈ 58 MB (payload only; actual memory is higher
/// due to HashMap buckets, per-entry Vec/timestamp overhead).
pub cache_size: usize,
}
impl Default for EmbeddingsConfig {
@@ -40,6 +49,7 @@ impl Default for EmbeddingsConfig {
ollama_base_url: "http://localhost:11434".to_string(),
dimension,
openai_base_url: None,
cache_size: DEFAULT_EMBEDDING_CACHE_SIZE,
}
}
}
@@ -47,7 +57,7 @@ impl Default for EmbeddingsConfig {
/// Infer the embedding dimension from a well-known model name.
///
/// Falls back to 1536 (OpenAI text-embedding-3-small default) for unknown models.
fn default_dimension_for_model(model: &str) -> usize {
pub(crate) fn default_dimension_for_model(model: &str) -> usize {
match model {
"text-embedding-3-small" => 1536,
"text-embedding-3-large" => 3072,
@@ -80,6 +90,15 @@ impl EmbeddingsConfig {
let openai_base_url = optional_env("EMBEDDING_BASE_URL")?;
let cache_size = parse_optional_env("EMBEDDING_CACHE_SIZE", DEFAULT_EMBEDDING_CACHE_SIZE)?;
if cache_size == 0 {
return Err(ConfigError::InvalidValue {
key: "EMBEDDING_CACHE_SIZE".to_string(),
message: "must be at least 1".to_string(),
});
}
Ok(Self {
enabled,
provider,
@@ -88,6 +107,7 @@ impl EmbeddingsConfig {
ollama_base_url,
dimension,
openai_base_url,
cache_size,
})
}
@@ -183,13 +203,13 @@ mod tests {
std::env::remove_var("EMBEDDING_MODEL");
std::env::remove_var("OPENAI_API_KEY");
std::env::remove_var("EMBEDDING_BASE_URL");
std::env::remove_var("EMBEDDING_CACHE_SIZE");
}
}
#[test]
fn embeddings_disabled_not_overridden_by_openai_key() {
let _guard = ENV_MUTEX.lock().expect("env mutex poisoned");
clear_embedding_env();
// SAFETY: Under ENV_MUTEX, no concurrent env access.
unsafe {
@@ -240,7 +260,6 @@ mod tests {
#[test]
fn embeddings_env_override_takes_precedence() {
let _guard = ENV_MUTEX.lock().expect("env mutex poisoned");
clear_embedding_env();
// SAFETY: Under ENV_MUTEX.
unsafe {
@@ -281,10 +300,8 @@ mod tests {
let config = EmbeddingsConfig::resolve(&settings).expect("resolve should succeed");
assert_eq!(
config.openai_base_url.as_deref(),
Some("https://custom.example.com"),
"EMBEDDING_BASE_URL env var should be parsed into openai_base_url"
Some("https://custom.example.com")
);
// SAFETY: Under ENV_MUTEX.
unsafe {
std::env::remove_var("EMBEDDING_BASE_URL");
@@ -303,4 +320,24 @@ mod tests {
"openai_base_url should be None when EMBEDDING_BASE_URL is not set"
);
}
#[test]
fn cache_size_zero_rejected() {
let _guard = ENV_MUTEX.lock().expect("env mutex poisoned");
clear_embedding_env();
// SAFETY: Under ENV_MUTEX.
unsafe {
std::env::set_var("EMBEDDING_CACHE_SIZE", "0");
}
let settings = Settings::default();
let result = EmbeddingsConfig::resolve(&settings);
assert!(result.is_err(), "cache_size=0 should be rejected");
let err = result.unwrap_err().to_string();
assert!(err.contains("at least 1"), "should mention minimum: {err}");
// SAFETY: Under ENV_MUTEX.
unsafe {
std::env::remove_var("EMBEDDING_CACHE_SIZE");
}
}
}
+1 -1
View File
@@ -109,7 +109,7 @@ impl LlmConfig {
// Always resolve NEAR AI config (used for embeddings even when not the primary backend)
let nearai_api_key = optional_env("NEARAI_API_KEY")?.map(SecretString::from);
let nearai = NearAiConfig {
model: Self::resolve_model("NEARAI_MODEL", settings, "zai-org/GLM-latest")?,
model: Self::resolve_model("NEARAI_MODEL", settings, crate::llm::DEFAULT_MODEL)?,
cheap_model: optional_env("NEARAI_CHEAP_MODEL")?,
base_url: optional_env("NEARAI_BASE_URL")?.unwrap_or_else(|| {
if nearai_api_key.is_some() {
+2 -2
View File
@@ -9,7 +9,7 @@ mod agent;
mod builder;
mod channels;
mod database;
mod embeddings;
pub(crate) mod embeddings;
mod heartbeat;
pub(crate) mod helpers;
mod hygiene;
@@ -38,7 +38,7 @@ pub use self::channels::{
ChannelsConfig, CliConfig, DEFAULT_GATEWAY_PORT, GatewayConfig, HttpConfig, SignalConfig,
};
pub use self::database::{DatabaseBackend, DatabaseConfig, SslMode, default_libsql_path};
pub use self::embeddings::EmbeddingsConfig;
pub use self::embeddings::{DEFAULT_EMBEDDING_CACHE_SIZE, EmbeddingsConfig};
pub use self::heartbeat::HeartbeatConfig;
pub use self::hygiene::HygieneConfig;
pub use self::llm::default_session_path;
+29 -35
View File
@@ -7,7 +7,7 @@ use secrecy::SecretString;
pub struct RelayConfig {
/// Base URL of the channel-relay service (e.g., `http://localhost:3001`).
pub url: String,
/// API key for authenticated channel-relay endpoints.
/// Bearer token for authenticated channel-relay endpoints (`sk-agent-*`).
pub api_key: SecretString,
/// Override for the OAuth callback URL (e.g., a tunnel URL).
pub callback_url: Option<String>,
@@ -15,12 +15,8 @@ pub struct RelayConfig {
pub instance_id: Option<String>,
/// HTTP request timeout in seconds (default: 30).
pub request_timeout_secs: u64,
/// SSE stream long-poll timeout in seconds (default: 86400 = 24 h).
pub stream_timeout_secs: u64,
/// Initial exponential backoff in milliseconds (default: 1000).
pub backoff_initial_ms: u64,
/// Maximum exponential backoff in milliseconds (default: 60000).
pub backoff_max_ms: u64,
/// Path for the webhook callback endpoint (default: `/relay/events`).
pub webhook_path: String,
}
impl std::fmt::Debug for RelayConfig {
@@ -31,9 +27,7 @@ impl std::fmt::Debug for RelayConfig {
.field("callback_url", &self.callback_url)
.field("instance_id", &self.instance_id)
.field("request_timeout_secs", &self.request_timeout_secs)
.field("stream_timeout_secs", &self.stream_timeout_secs)
.field("backoff_initial_ms", &self.backoff_initial_ms)
.field("backoff_max_ms", &self.backoff_max_ms)
.field("webhook_path", &self.webhook_path)
.finish()
}
}
@@ -41,8 +35,10 @@ impl std::fmt::Debug for RelayConfig {
impl RelayConfig {
/// Load relay config from environment variables.
///
/// Returns `None` if either `CHANNEL_RELAY_URL` or `CHANNEL_RELAY_API_KEY`
/// is not set, making the relay integration opt-in.
/// Returns `None` if either of the required env vars (`CHANNEL_RELAY_URL`,
/// `CHANNEL_RELAY_API_KEY`) is not set, making the relay integration opt-in.
/// The signing secret is fetched from channel-relay at activation time via
/// the authenticated `/relay/signing-secret` endpoint — no env var required.
pub fn from_env() -> Option<Self> {
Self::from_env_reader(|key| std::env::var(key).ok())
}
@@ -55,9 +51,7 @@ impl RelayConfig {
callback_url: None,
instance_id: None,
request_timeout_secs: 30,
stream_timeout_secs: 86400,
backoff_initial_ms: 1000,
backoff_max_ms: 60000,
webhook_path: "/relay/events".into(),
}
}
@@ -73,15 +67,7 @@ impl RelayConfig {
request_timeout_secs: env("RELAY_REQUEST_TIMEOUT_SECS")
.and_then(|v| v.parse().ok())
.unwrap_or(30),
stream_timeout_secs: env("RELAY_STREAM_TIMEOUT_SECS")
.and_then(|v| v.parse().ok())
.unwrap_or(86400),
backoff_initial_ms: env("RELAY_BACKOFF_INITIAL_MS")
.and_then(|v| v.parse().ok())
.unwrap_or(1000),
backoff_max_ms: env("RELAY_BACKOFF_MAX_MS")
.and_then(|v| v.parse().ok())
.unwrap_or(60000),
webhook_path: env("RELAY_WEBHOOK_PATH").unwrap_or_else(|| "/relay/events".into()),
})
}
}
@@ -97,7 +83,21 @@ mod tests {
}
#[test]
fn from_env_reader_loads_defaults() {
fn from_env_reader_requires_only_url_and_api_key() {
// Signing secret is fetched at activation time — only URL + API key needed.
let config = RelayConfig::from_env_reader(|key| match key {
"CHANNEL_RELAY_URL" => Some("http://localhost:3001".into()),
"CHANNEL_RELAY_API_KEY" => Some("test-key".into()),
_ => None,
});
assert!(
config.is_some(),
"relay config should load with just URL + API key"
);
}
#[test]
fn from_env_reader_loads_all_required() {
let config = RelayConfig::from_env_reader(|key| match key {
"CHANNEL_RELAY_URL" => Some("http://localhost:3001".into()),
"CHANNEL_RELAY_API_KEY" => Some("test-key".into()),
@@ -107,9 +107,7 @@ mod tests {
assert_eq!(config.url, "http://localhost:3001");
assert_eq!(config.request_timeout_secs, 30);
assert_eq!(config.stream_timeout_secs, 86400);
assert_eq!(config.backoff_initial_ms, 1000);
assert_eq!(config.backoff_max_ms, 60000);
assert_eq!(config.webhook_path, "/relay/events");
assert!(config.callback_url.is_none());
assert!(config.instance_id.is_none());
}
@@ -122,9 +120,7 @@ mod tests {
"IRONCLAW_OAUTH_CALLBACK_URL" => Some("https://tunnel.example.com".into()),
"IRONCLAW_INSTANCE_ID" => Some("my-instance".into()),
"RELAY_REQUEST_TIMEOUT_SECS" => Some("60".into()),
"RELAY_STREAM_TIMEOUT_SECS" => Some("43200".into()),
"RELAY_BACKOFF_INITIAL_MS" => Some("2000".into()),
"RELAY_BACKOFF_MAX_MS" => Some("120000".into()),
"RELAY_WEBHOOK_PATH" => Some("/custom/events".into()),
_ => None,
})
.expect("config should be Some");
@@ -135,9 +131,7 @@ mod tests {
);
assert_eq!(config.instance_id.as_deref(), Some("my-instance"));
assert_eq!(config.request_timeout_secs, 60);
assert_eq!(config.stream_timeout_secs, 43200);
assert_eq!(config.backoff_initial_ms, 2000);
assert_eq!(config.backoff_max_ms, 120000);
assert_eq!(config.webhook_path, "/custom/events");
}
#[test]
@@ -148,7 +142,7 @@ mod tests {
}
#[test]
fn debug_redacts_api_key() {
fn debug_redacts_secrets() {
let config = RelayConfig::from_values("http://localhost:3001", "super-secret");
let debug = format!("{:?}", config);
assert!(debug.contains("[REDACTED]"));