Files
optimclaw/src/config/embeddings.rs
T
c3ce26278a refactor: simplify config resolution and consolidate main.rs init (#287)
* refactor: simplify config resolution and consolidate main.rs init into AppBuilder

- Add parse_bool_env() and parse_string_env() helpers to eliminate repetitive
  5-line optional_env/parse/map_err/unwrap_or boilerplate across 12 config files
- Add EmbeddingsConfig::create_provider() to centralize embeddings construction
  (fixes hardcoded 1536 dimensions and missing Ollama provider in app.rs)
- Extract init_cli_tracing(), setup_wasm_channels(), start_tunnel(),
  run_memory_command(), run_worker(), run_claude_bridge() from main.rs
- Replace ~600 lines of inline init in main.rs with AppBuilder::build_all()
- Expose catalog_entries from AppComponents for gateway registry entries
- Net reduction: ~738 lines across 15 files

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: propagate dev_loaded_tool_names from AppBuilder and add parse_option_env helper

Address PR review feedback:

- Capture dev_loaded_tool_names from WASM loading in init_extensions()
  and expose via AppComponents so bootstrap_hooks receives the actual
  dev tool names instead of an empty slice (fixes silent hook skip)
- Add parse_option_env<T>() helper for Option<T> config fields,
  simplifying max_cost_per_day_cents and max_actions_per_hour in agent.rs

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: fetch real NEAR AI pricing and unify cost calculation path

CostGuard was independently looking up pricing via costs::model_cost(),
falling back to GPT-4o default rates when NEAR AI model names didn't
match the static table — causing ~3x cost overestimates in logs.

- Add pricing map to NearAiChatProvider that fetches real rates from
  /v1/model/list at startup (background, non-blocking)
- Update cost_per_token() to check fetched pricing first, then static
  table, then default
- Add cost_per_token parameter to CostGuard::record_llm_call() so the
  dispatcher passes provider-sourced rates directly

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* chore: update default NEAR AI model to GLM-latest

Replace fireworks llama4-maverick-instruct-basic with zai-org/GLM-latest
as the default model in config and setup wizard.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: align wizard default model name with config

Change "zai/GLM-latest" to "zai-org/GLM-latest" in wizard.rs to match
the default in config/llm.rs.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

---------

Co-authored-by: Claude Opus 4.6 <[email protected]>
2026-02-22 02:54:31 +00:00

250 lines
8.0 KiB
Rust

use std::sync::Arc;
use secrecy::{ExposeSecret, SecretString};
use crate::config::helpers::{optional_env, parse_bool_env, parse_optional_env};
use crate::error::ConfigError;
use crate::llm::SessionManager;
use crate::settings::Settings;
use crate::workspace::EmbeddingProvider;
/// Embeddings provider configuration.
#[derive(Debug, Clone)]
pub struct EmbeddingsConfig {
/// Whether embeddings are enabled.
pub enabled: bool,
/// Provider to use: "openai", "nearai", or "ollama"
pub provider: String,
/// OpenAI API key (for OpenAI provider).
pub openai_api_key: Option<SecretString>,
/// Model to use for embeddings.
pub model: String,
/// Ollama base URL (for Ollama provider). Defaults to http://localhost:11434.
pub ollama_base_url: String,
/// Embedding vector dimension. Inferred from the model name when not set explicitly.
pub dimension: usize,
}
impl Default for EmbeddingsConfig {
fn default() -> Self {
let model = "text-embedding-3-small".to_string();
let dimension = default_dimension_for_model(&model);
Self {
enabled: false,
provider: "openai".to_string(),
openai_api_key: None,
model,
ollama_base_url: "http://localhost:11434".to_string(),
dimension,
}
}
}
/// 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 {
match model {
"text-embedding-3-small" => 1536,
"text-embedding-3-large" => 3072,
"text-embedding-ada-002" => 1536,
"nomic-embed-text" => 768,
"mxbai-embed-large" => 1024,
"all-minilm" => 384,
_ => 1536,
}
}
impl EmbeddingsConfig {
pub(crate) fn resolve(settings: &Settings) -> Result<Self, ConfigError> {
let openai_api_key = optional_env("OPENAI_API_KEY")?.map(SecretString::from);
let provider = optional_env("EMBEDDING_PROVIDER")?
.unwrap_or_else(|| settings.embeddings.provider.clone());
let model =
optional_env("EMBEDDING_MODEL")?.unwrap_or_else(|| settings.embeddings.model.clone());
let ollama_base_url = optional_env("OLLAMA_BASE_URL")?
.or_else(|| settings.ollama_base_url.clone())
.unwrap_or_else(|| "http://localhost:11434".to_string());
let dimension =
parse_optional_env("EMBEDDING_DIMENSION", default_dimension_for_model(&model))?;
let enabled = parse_bool_env("EMBEDDING_ENABLED", settings.embeddings.enabled)?;
Ok(Self {
enabled,
provider,
openai_api_key,
model,
ollama_base_url,
dimension,
})
}
/// Get the OpenAI API key if configured.
pub fn openai_api_key(&self) -> Option<&str> {
self.openai_api_key.as_ref().map(|s| s.expose_secret())
}
/// Create the appropriate embedding provider based on configuration.
///
/// Returns `None` if embeddings are disabled or the required credentials
/// are missing. The `nearai_base_url` and `session` are needed only for
/// the NEAR AI provider but must be passed unconditionally.
pub fn create_provider(
&self,
nearai_base_url: &str,
session: Arc<SessionManager>,
) -> Option<Arc<dyn EmbeddingProvider>> {
if !self.enabled {
tracing::info!("Embeddings disabled (set EMBEDDING_ENABLED=true to enable)");
return None;
}
match self.provider.as_str() {
"nearai" => {
tracing::info!(
"Embeddings enabled via NEAR AI (model: {}, dim: {})",
self.model,
self.dimension,
);
Some(Arc::new(
crate::workspace::NearAiEmbeddings::new(nearai_base_url, session)
.with_model(&self.model, self.dimension),
))
}
"ollama" => {
tracing::info!(
"Embeddings enabled via Ollama (model: {}, url: {}, dim: {})",
self.model,
self.ollama_base_url,
self.dimension,
);
Some(Arc::new(
crate::workspace::OllamaEmbeddings::new(&self.ollama_base_url)
.with_model(&self.model, self.dimension),
))
}
_ => {
if let Some(api_key) = self.openai_api_key() {
tracing::info!(
"Embeddings enabled via OpenAI (model: {}, dim: {})",
self.model,
self.dimension,
);
Some(Arc::new(crate::workspace::OpenAiEmbeddings::with_model(
api_key,
&self.model,
self.dimension,
)))
} else {
tracing::warn!("Embeddings configured but OPENAI_API_KEY not set");
None
}
}
}
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::config::helpers::ENV_MUTEX;
use crate::settings::{EmbeddingsSettings, Settings};
/// Clear all embedding-related env vars.
fn clear_embedding_env() {
// SAFETY: Only called under ENV_MUTEX in tests.
unsafe {
std::env::remove_var("EMBEDDING_ENABLED");
std::env::remove_var("EMBEDDING_PROVIDER");
std::env::remove_var("EMBEDDING_MODEL");
std::env::remove_var("OPENAI_API_KEY");
}
}
#[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 {
std::env::set_var("OPENAI_API_KEY", "sk-test-key-for-issue-129");
}
let settings = Settings {
embeddings: EmbeddingsSettings {
enabled: false,
..Default::default()
},
..Default::default()
};
let config = EmbeddingsConfig::resolve(&settings).expect("resolve should succeed");
assert!(
!config.enabled,
"embeddings should remain disabled when settings.embeddings.enabled=false, \
even when OPENAI_API_KEY is set (issue #129)"
);
// SAFETY: Under ENV_MUTEX.
unsafe {
std::env::remove_var("OPENAI_API_KEY");
}
}
#[test]
fn embeddings_enabled_from_settings() {
let _guard = ENV_MUTEX.lock().expect("env mutex poisoned");
clear_embedding_env();
let settings = Settings {
embeddings: EmbeddingsSettings {
enabled: true,
..Default::default()
},
..Default::default()
};
let config = EmbeddingsConfig::resolve(&settings).expect("resolve should succeed");
assert!(
config.enabled,
"embeddings should be enabled when settings say so"
);
}
#[test]
fn embeddings_env_override_takes_precedence() {
let _guard = ENV_MUTEX.lock().expect("env mutex poisoned");
clear_embedding_env();
// SAFETY: Under ENV_MUTEX.
unsafe {
std::env::set_var("EMBEDDING_ENABLED", "true");
}
let settings = Settings {
embeddings: EmbeddingsSettings {
enabled: false,
..Default::default()
},
..Default::default()
};
let config = EmbeddingsConfig::resolve(&settings).expect("resolve should succeed");
assert!(
config.enabled,
"EMBEDDING_ENABLED=true env var should override settings"
);
// SAFETY: Under ENV_MUTEX.
unsafe {
std::env::remove_var("EMBEDDING_ENABLED");
}
}
}