Files
optimclaw/src/config/mod.rs
T
5c2ba44f12 feat(llm): declarative provider registry (#618)
* feat(llm): declarative provider registry, replace hardcoded provider configs

Replace the hardcoded LlmBackend enum and per-provider config structs with
a declarative JSON registry. Adding a new OpenAI-compatible provider now
requires zero Rust code changes -- just add an entry to providers.json.

- Add providers.json with 14 providers (openai, anthropic, ollama,
  openai_compatible, tinfoil, openrouter, groq, nvidia, venice, together,
  fireworks, deepseek, cerebras, sambanova)
- Add src/llm/registry.rs with ProviderProtocol, SetupHint,
  ProviderDefinition, and ProviderRegistry types
- Rewrite src/config/llm.rs: remove LlmBackend enum and 5 per-provider
  config structs, replace with generic RegistryProviderConfig
- Simplify src/llm/mod.rs: remove 5 create_*_provider functions, dispatch
  on ProviderProtocol (3 code paths for all providers)
- Dynamic setup wizard: menu built from registry.selectable(), generic
  credential collection dispatched by SetupHint kind
- Dynamic secret injection: inject_llm_keys_from_secrets() discovers
  secret-to-env mappings from registry instead of hardcoded list
- Users can extend with ~/.ironclaw/providers.json (no recompile)
- Subsumes open provider PRs: Groq #570, NVIDIA NIM #576, Venice.ai #451
  (Gemini #476 excluded -- not OpenAI-compatible)

[skip-regression-check]

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

* feat(llm): self-sufficient provider auth, onboard --provider-only, extract SessionConfig

- NearAiChatProvider handles its own session auth lazily in
  resolve_bearer_token() instead of requiring main.rs to pre-check.
  Triggers OAuth/API-key login on first request when no token exists.

- Add `ironclaw onboard --provider-only` to reconfigure just the LLM
  provider and model selection without re-running the full wizard.

- Extract auth_base_url and session_path from NearAiConfig into
  LlmConfig::session (SessionConfig). Callers now use
  config.llm.session directly instead of reaching into nearai fields.

[skip-regression-check]

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

* fix(llm): address PR review comments on provider registry

- Use registry.selectable() instead of registry.all() for secret
  injection to avoid duplicates from user provider overrides.

- Fix selectable() dedup bug: check setup hint on the final (overridden)
  definition, not the first occurrence. User overrides that add a setup
  hint are now included correctly.

- Only store openai_compatible_base_url for providers that actually use
  LLM_BASE_URL, preventing base URL pollution for groq/nvidia/etc.

- Normalize provider_id to canonical registry def.id instead of using
  the raw user-supplied alias string.

- Add comment explaining why .completions_api() is used over the
  default Responses API path.

[skip-regression-check]

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

* fix(docker): copy providers.json into build context

The declarative provider registry uses `include_str!("../../providers.json")`
at compile time, so the file must be present in the Docker builder stage.

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

* fix(llm): address second-round PR review comments (#618)

- Make --channels-only and --provider-only mutually exclusive via clap
  conflicts_with (Copilot: cli/mod.rs)
- Add 5s timeout to fetch_openai_compatible_models(), matching the other
  three model-fetch helpers (Copilot: wizard.rs)
- Apply models_filter from setup hints when listing models, so Groq's
  "chat" filter actually excludes non-chat models (Copilot: wizard.rs)
- Normalize LlmConfig.backend to the canonical provider ID instead of
  the raw user-supplied alias string (Copilot: llm.rs)
- Add models_filter() accessor to SetupHint with regression test

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

* fix(test): relax flaky parallel speedup timing threshold

The test_parallel_speedup test asserted <500ms but CI runners can be
slow enough to exceed that while still proving parallelism. Bumped to
800ms which still validates parallel execution (sequential would be
~600ms minimum) while tolerating CI jitter.

[skip-regression-check]

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

* fix(llm): handle api_key_login path in resolve_bearer_token, warn on missing keys

- resolve_bearer_token() now checks NEARAI_API_KEY env var after
  ensure_authenticated(), handling the case where the user entered an
  API key via the interactive login flow (which sets the env var but
  not a session token)
- Add tracing::warn when creating an OpenAI-compatible provider without
  an API key, making 401 errors easier to diagnose
- Add regression test for resolve_bearer_token auth paths

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

* style: fix formatting in nearai_chat test

[skip-regression-check]

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

* fix(llm): correct bearer token priority, handle setup-less providers (#618)

- resolve_bearer_token(): session token now takes priority over
  NEARAI_API_KEY env var, preventing unexpected auth mode switches.
  The env var fallback only triggers after ensure_authenticated() when
  no session token was stored (api_key_login path).
- run_provider_setup(): providers with setup: None no longer error,
  allowing env-var-only providers to be kept during re-onboarding.
- Split bearer token test into 3 focused tests: config api_key path,
  session token path, and session-beats-env-var precedence test.
- Add test for wizard handling of providers without setup hints.

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

* test(llm): comprehensive tests for provider registry, config, and auth

Add 13 new tests covering the critical paths in the provider system:

Bearer token auth priority (nearai_chat.rs):
- config api_key wins over session token and env var
- session token wins over env var (prevents mid-run auth mode switches)
- config api_key path works in isolation
- session token path works in isolation

Config resolution (config/llm.rs):
- backend alias normalization (open_ai → openai)
- unknown backend falls back to openai_compatible
- nearai aliases (nearai, near_ai, near) all resolve correctly
- base URL resolution priority (env > settings > registry default)

Registry dedup (registry.rs):
- user override adds setup hint → appears in selectable()
- user override removes setup hint → excluded from selectable()
- selectable() preserves insertion order during dedup
- all built-in ApiKey providers have api_key_env set

Wizard (wizard.rs):
- setup: None providers don't error during re-onboarding

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

---------

Co-authored-by: Claude Opus 4.6 <[email protected]>
2026-03-07 02:18:57 +00:00

331 lines
12 KiB
Rust

//! Configuration for IronClaw.
//!
//! Settings are loaded with priority: env var > database > default.
//! `DATABASE_URL` lives in `~/.ironclaw/.env` (loaded via dotenvy early
//! in startup). Everything else comes from env vars, the DB settings
//! table, or auto-detection.
mod agent;
mod builder;
mod channels;
mod database;
mod embeddings;
mod heartbeat;
pub(crate) mod helpers;
mod hygiene;
mod llm;
mod routines;
mod safety;
mod sandbox;
mod secrets;
mod skills;
mod tunnel;
mod wasm;
use std::collections::HashMap;
use std::sync::OnceLock;
use crate::error::ConfigError;
use crate::settings::Settings;
// Re-export all public types so `crate::config::FooConfig` continues to work.
pub use self::agent::AgentConfig;
pub use self::builder::BuilderModeConfig;
pub use self::channels::{ChannelsConfig, CliConfig, GatewayConfig, HttpConfig, SignalConfig};
pub use self::database::{DatabaseBackend, DatabaseConfig, SslMode, default_libsql_path};
pub use self::embeddings::EmbeddingsConfig;
pub use self::heartbeat::HeartbeatConfig;
pub use self::hygiene::HygieneConfig;
pub use self::llm::{LlmConfig, NearAiConfig, RegistryProviderConfig};
pub use self::routines::RoutineConfig;
pub use self::safety::SafetyConfig;
pub use self::sandbox::{ClaudeCodeConfig, SandboxModeConfig};
pub use self::secrets::SecretsConfig;
pub use self::skills::SkillsConfig;
pub use self::tunnel::TunnelConfig;
pub use self::wasm::WasmConfig;
pub use crate::llm::session::SessionConfig;
/// Thread-safe overlay for injected env vars (secrets loaded from DB).
///
/// Used by `inject_llm_keys_from_secrets()` to make API keys available to
/// `optional_env()` without unsafe `set_var` calls. `optional_env()` checks
/// real env vars first, then falls back to this overlay.
static INJECTED_VARS: OnceLock<HashMap<String, String>> = OnceLock::new();
/// Main configuration for the agent.
#[derive(Debug, Clone)]
pub struct Config {
pub database: DatabaseConfig,
pub llm: LlmConfig,
pub embeddings: EmbeddingsConfig,
pub tunnel: TunnelConfig,
pub channels: ChannelsConfig,
pub agent: AgentConfig,
pub safety: SafetyConfig,
pub wasm: WasmConfig,
pub secrets: SecretsConfig,
pub builder: BuilderModeConfig,
pub heartbeat: HeartbeatConfig,
pub hygiene: HygieneConfig,
pub routines: RoutineConfig,
pub sandbox: SandboxModeConfig,
pub claude_code: ClaudeCodeConfig,
pub skills: SkillsConfig,
pub observability: crate::observability::ObservabilityConfig,
}
impl Config {
/// Create a full Config for integration tests without reading env vars.
///
/// Requires the `libsql` feature. Sets up:
/// - libSQL database at the given path
/// - WASM and embeddings disabled
/// - Skills enabled with the given directories
/// - Heartbeat, routines, sandbox, builder all disabled
/// - Safety with injection check off, 100k output limit
#[cfg(feature = "libsql")]
pub fn for_testing(
libsql_path: std::path::PathBuf,
skills_dir: std::path::PathBuf,
installed_skills_dir: std::path::PathBuf,
) -> Self {
Self {
database: DatabaseConfig {
backend: DatabaseBackend::LibSql,
url: secrecy::SecretString::from("unused://test".to_string()),
pool_size: 1,
ssl_mode: SslMode::Disable,
libsql_path: Some(libsql_path),
libsql_url: None,
libsql_auth_token: None,
},
llm: LlmConfig::for_testing(),
embeddings: EmbeddingsConfig::default(),
tunnel: TunnelConfig::default(),
channels: ChannelsConfig {
cli: CliConfig { enabled: false },
http: None,
gateway: None,
signal: None,
wasm_channels_dir: std::path::PathBuf::from("/tmp/ironclaw-test-channels"),
wasm_channels_enabled: false,
wasm_channel_owner_ids: HashMap::new(),
},
agent: AgentConfig::for_testing(),
safety: SafetyConfig {
max_output_length: 100_000,
injection_check_enabled: false,
},
wasm: WasmConfig {
enabled: false,
..WasmConfig::default()
},
secrets: SecretsConfig::default(),
builder: BuilderModeConfig {
enabled: false,
..BuilderModeConfig::default()
},
heartbeat: HeartbeatConfig::default(),
hygiene: HygieneConfig::default(),
routines: RoutineConfig {
enabled: false,
..RoutineConfig::default()
},
sandbox: SandboxModeConfig {
enabled: false,
..SandboxModeConfig::default()
},
claude_code: ClaudeCodeConfig::default(),
skills: SkillsConfig {
enabled: true,
local_dir: skills_dir,
installed_dir: installed_skills_dir,
..SkillsConfig::default()
},
observability: crate::observability::ObservabilityConfig::default(),
}
}
/// Load configuration from environment variables and the database.
///
/// Priority: env var > TOML config file > DB settings > default.
/// This is the primary way to load config after DB is connected.
pub async fn from_db(
store: &(dyn crate::db::SettingsStore + Sync),
user_id: &str,
) -> Result<Self, ConfigError> {
Self::from_db_with_toml(store, user_id, None).await
}
/// Load from DB with an optional TOML config file overlay.
pub async fn from_db_with_toml(
store: &(dyn crate::db::SettingsStore + Sync),
user_id: &str,
toml_path: Option<&std::path::Path>,
) -> Result<Self, ConfigError> {
let _ = dotenvy::dotenv();
crate::bootstrap::load_ironclaw_env();
// Load all settings from DB into a Settings struct
let mut db_settings = match store.get_all_settings(user_id).await {
Ok(map) => Settings::from_db_map(&map),
Err(e) => {
tracing::warn!("Failed to load settings from DB, using defaults: {}", e);
Settings::default()
}
};
// Overlay TOML config file (values win over DB settings)
Self::apply_toml_overlay(&mut db_settings, toml_path)?;
Self::build(&db_settings).await
}
/// Load configuration from environment variables only (no database).
///
/// Used during early startup before the database is connected,
/// and by CLI commands that don't have DB access.
/// Falls back to legacy `settings.json` on disk if present.
///
/// Loads both `./.env` (standard, higher priority) and `~/.ironclaw/.env`
/// (lower priority) via dotenvy, which never overwrites existing vars.
pub async fn from_env() -> Result<Self, ConfigError> {
Self::from_env_with_toml(None).await
}
/// Load from env with an optional TOML config file overlay.
pub async fn from_env_with_toml(
toml_path: Option<&std::path::Path>,
) -> Result<Self, ConfigError> {
let _ = dotenvy::dotenv();
crate::bootstrap::load_ironclaw_env();
let mut settings = Settings::load();
// Overlay TOML config file (values win over JSON settings)
Self::apply_toml_overlay(&mut settings, toml_path)?;
Self::build(&settings).await
}
/// Load and merge a TOML config file into settings.
///
/// If `explicit_path` is `Some`, loads from that path (errors are fatal).
/// If `None`, tries the default path `~/.ironclaw/config.toml` (missing
/// file is silently ignored).
fn apply_toml_overlay(
settings: &mut Settings,
explicit_path: Option<&std::path::Path>,
) -> Result<(), ConfigError> {
let path = explicit_path
.map(std::path::PathBuf::from)
.unwrap_or_else(Settings::default_toml_path);
match Settings::load_toml(&path) {
Ok(Some(toml_settings)) => {
settings.merge_from(&toml_settings);
tracing::debug!("Loaded TOML config from {}", path.display());
}
Ok(None) => {
if explicit_path.is_some() {
return Err(ConfigError::ParseError(format!(
"Config file not found: {}",
path.display()
)));
}
}
Err(e) => {
if explicit_path.is_some() {
return Err(ConfigError::ParseError(format!(
"Failed to load config file {}: {}",
path.display(),
e
)));
}
tracing::warn!("Failed to load default config file: {}", e);
}
}
Ok(())
}
/// Build config from settings (shared by from_env and from_db).
async fn build(settings: &Settings) -> Result<Self, ConfigError> {
Ok(Self {
database: DatabaseConfig::resolve()?,
llm: LlmConfig::resolve(settings)?,
embeddings: EmbeddingsConfig::resolve(settings)?,
tunnel: TunnelConfig::resolve(settings)?,
channels: ChannelsConfig::resolve(settings)?,
agent: AgentConfig::resolve(settings)?,
safety: SafetyConfig::resolve()?,
wasm: WasmConfig::resolve()?,
secrets: SecretsConfig::resolve().await?,
builder: BuilderModeConfig::resolve()?,
heartbeat: HeartbeatConfig::resolve(settings)?,
hygiene: HygieneConfig::resolve()?,
routines: RoutineConfig::resolve()?,
sandbox: SandboxModeConfig::resolve()?,
claude_code: ClaudeCodeConfig::resolve()?,
skills: SkillsConfig::resolve()?,
observability: crate::observability::ObservabilityConfig {
backend: std::env::var("OBSERVABILITY_BACKEND").unwrap_or_else(|_| "none".into()),
},
})
}
}
/// Load API keys from the encrypted secrets store into a thread-safe overlay.
///
/// This bridges the gap between secrets stored during onboarding and the
/// env-var-first resolution in `LlmConfig::resolve()`. Keys in the overlay
/// are read by `optional_env()` before falling back to `std::env::var()`,
/// so explicit env vars always win.
pub async fn inject_llm_keys_from_secrets(
secrets: &dyn crate::secrets::SecretsStore,
user_id: &str,
) {
// Static mappings for well-known providers.
// The registry's setup hints define secret_name -> env_var mappings,
// so new providers added to providers.json get injection automatically.
let mut mappings: Vec<(&str, &str)> = vec![("llm_nearai_api_key", "NEARAI_API_KEY")];
// Dynamically discover secret->env mappings from the provider registry.
// Uses selectable() which deduplicates user overrides correctly.
let registry = crate::llm::ProviderRegistry::load();
let dynamic_mappings: Vec<(String, String)> = registry
.selectable()
.iter()
.filter_map(|def| {
def.api_key_env.as_ref().and_then(|env_var| {
def.setup
.as_ref()
.and_then(|s| s.secret_name())
.map(|secret_name| (secret_name.to_string(), env_var.clone()))
})
})
.collect();
for (secret, env_var) in &dynamic_mappings {
mappings.push((secret, env_var));
}
let mut injected = HashMap::new();
for (secret_name, env_var) in mappings {
match std::env::var(env_var) {
Ok(val) if !val.is_empty() => continue,
_ => {}
}
match secrets.get_decrypted(user_id, secret_name).await {
Ok(decrypted) => {
injected.insert(env_var.to_string(), decrypted.expose().to_string());
tracing::debug!("Loaded secret '{}' for env var '{}'", secret_name, env_var);
}
Err(_) => {
// Secret doesn't exist, that's fine
}
}
}
let _ = INJECTED_VARS.set(injected);
}