mirror of
https://github.com/outbackdingo/optimclaw.git
synced 2026-09-01 17:19:24 +00:00
refactor: remove Responses API, consolidate to Chat Completions (#272)
* fix: strip reasoning from LLM responses and persist assistant messages reliably - Filter out `type: "reasoning"` output items from NEAR AI Responses API parsing so chain-of-thought never reaches the UI (nearai.rs) - Rewrite clean_response with regex-based tag stripping that is code-aware (preserves tags inside fenced blocks and inline backticks), supports 9+ tag names (think, thought, reasoning, reflection, etc.), handles <final> extraction, pipe-delimited tags, and case/whitespace tolerance (reasoning.rs) - Add Reasoning::complete() helper so all non-agentic LLM call sites (summarize, suggest, heartbeat, compaction) get automatic response cleaning; thread SafetyLayer through to those callers - Change persist_turn from fire-and-forget tokio::spawn to awaited async so both user and assistant messages are written before returning, preventing data loss on shutdown/restart - Pass input_count through seed_response_chain so response chaining delta calculation is accurate after thread hydration on restart - Make NearAiResponse.usage optional and preserve response_id in alt response path for chaining continuity - Persist session token to DB during onboarding wizard so runtime loads it without legacy-key fallback; suppress spurious warning on fresh installs - Fix dev tool double-registration when builder already registers them - Load dotenv/ironclaw env for doctor and status subcommands - Reduce startup log noise (demote info→debug for skills, remove redundant info lines) Co-Authored-By: Claude Opus 4.6 <[email protected]> * Nudge to not loop over tools continuesly * refactor: remove Responses API, consolidate NEAR AI to Chat Completions only The Responses API provider (nearai.rs, 1278 lines) added significant complexity (response chaining state machine, delta message calculation, previous_response_id persistence) for marginal benefit. This consolidates to the Chat Completions API only, upgrading NearAiChatProvider with dual auth (session token + API key) and 401 retry for session token renewal. - Delete src/llm/nearai.rs (Responses API provider) - Upgrade nearai_chat.rs with SessionManager, dual auth, flexible list_models - Remove response_id from CompletionResponse and ToolCompletionResponse - Remove seed_response_chain/get_response_chain_id from LlmProvider trait - Remove response chain persistence from agent (thread_ops, session) - Remove NearAiApiMode enum and NEARAI_API_MODE config - Clean up all wrapper providers (retry, circuit_breaker, failover, cache) - Update documentation (CLAUDE.md, .env.example) Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: runtime log level control via gateway UI and URL parameter Add server-side log level switching using tracing_subscriber::reload::Layer so the EnvFilter can be swapped at runtime without restarting. Expose via GET/PUT /api/logs/level endpoints, a "Server: LEVEL" dropdown in the logs toolbar, and a ?log_level=debug URL parameter for one-click activation. Also applies cargo fmt to pre-existing files (llm/, tests/). Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]>
This commit is contained in:
Illia Polosukhin
co-authored by
Claude Opus 4.6
Claude Opus 4.6
parent
7df356c109
commit
448383cfb0
+4
-49
@@ -121,37 +121,7 @@ pub struct LlmConfig {
|
||||
pub tinfoil: Option<TinfoilConfig>,
|
||||
}
|
||||
|
||||
/// API mode for NEAR AI.
|
||||
///
|
||||
/// - `Responses` = **NEAR AI Chat** (`private.near.ai`, session token auth)
|
||||
/// - `ChatCompletions` = **NEAR AI Cloud** (`cloud-api.near.ai`, API key auth)
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Default)]
|
||||
pub enum NearAiApiMode {
|
||||
/// NEAR AI Chat: Responses API with session token auth
|
||||
#[default]
|
||||
Responses,
|
||||
/// NEAR AI Cloud: Chat Completions API with API key auth
|
||||
ChatCompletions,
|
||||
}
|
||||
|
||||
impl std::str::FromStr for NearAiApiMode {
|
||||
type Err = String;
|
||||
|
||||
fn from_str(s: &str) -> Result<Self, Self::Err> {
|
||||
match s.to_lowercase().as_str() {
|
||||
"responses" | "response" => Ok(Self::Responses),
|
||||
"chat_completions" | "chatcompletions" | "chat" | "completions" => {
|
||||
Ok(Self::ChatCompletions)
|
||||
}
|
||||
_ => Err(format!(
|
||||
"invalid API mode '{}', expected 'responses' or 'chat_completions'",
|
||||
s
|
||||
)),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// NEAR AI configuration (shared by Chat and Cloud modes).
|
||||
/// NEAR AI configuration.
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct NearAiConfig {
|
||||
/// Model to use (e.g., "claude-3-5-sonnet-20241022", "gpt-4o")
|
||||
@@ -160,16 +130,13 @@ pub struct NearAiConfig {
|
||||
/// Falls back to the main model if not set.
|
||||
pub cheap_model: Option<String>,
|
||||
/// Base URL for the NEAR AI API.
|
||||
/// Chat mode default: `https://private.near.ai`
|
||||
/// Cloud mode default: `https://cloud-api.near.ai`
|
||||
/// Default: `https://private.near.ai` (session token) or `https://cloud-api.near.ai` (API key)
|
||||
pub base_url: String,
|
||||
/// Base URL for auth/refresh endpoints (default: https://private.near.ai)
|
||||
pub auth_base_url: String,
|
||||
/// Path to session file (default: ~/.ironclaw/session.json)
|
||||
pub session_path: PathBuf,
|
||||
/// API mode: NEAR AI Chat (Responses) or NEAR AI Cloud (ChatCompletions)
|
||||
pub api_mode: NearAiApiMode,
|
||||
/// API key for NEAR AI Cloud (required for ChatCompletions mode)
|
||||
/// API key for NEAR AI Cloud. When set, uses API key auth; otherwise uses session token auth.
|
||||
pub api_key: Option<SecretString>,
|
||||
/// Optional fallback model for failover (default: None).
|
||||
/// When set, a secondary provider is created with this model and wrapped
|
||||
@@ -229,17 +196,6 @@ impl LlmConfig {
|
||||
// Resolve NEAR AI config only when backend is NearAi (or when explicitly configured)
|
||||
let nearai_api_key = optional_env("NEARAI_API_KEY")?.map(SecretString::from);
|
||||
|
||||
let api_mode = if let Some(mode_str) = optional_env("NEARAI_API_MODE")? {
|
||||
mode_str.parse().map_err(|e| ConfigError::InvalidValue {
|
||||
key: "NEARAI_API_MODE".to_string(),
|
||||
message: e,
|
||||
})?
|
||||
} else if nearai_api_key.is_some() {
|
||||
NearAiApiMode::ChatCompletions
|
||||
} else {
|
||||
NearAiApiMode::Responses
|
||||
};
|
||||
|
||||
let nearai = NearAiConfig {
|
||||
model: optional_env("NEARAI_MODEL")?
|
||||
.or_else(|| settings.selected_model.clone())
|
||||
@@ -249,7 +205,7 @@ impl LlmConfig {
|
||||
}),
|
||||
cheap_model: optional_env("NEARAI_CHEAP_MODEL")?,
|
||||
base_url: optional_env("NEARAI_BASE_URL")?.unwrap_or_else(|| {
|
||||
if api_mode == NearAiApiMode::ChatCompletions {
|
||||
if nearai_api_key.is_some() {
|
||||
"https://cloud-api.near.ai".to_string()
|
||||
} else {
|
||||
"https://private.near.ai".to_string()
|
||||
@@ -260,7 +216,6 @@ impl LlmConfig {
|
||||
session_path: optional_env("NEARAI_SESSION_PATH")?
|
||||
.map(PathBuf::from)
|
||||
.unwrap_or_else(default_session_path),
|
||||
api_mode,
|
||||
api_key: nearai_api_key,
|
||||
fallback_model: optional_env("NEARAI_FALLBACK_MODEL")?,
|
||||
max_retries: parse_optional_env("NEARAI_MAX_RETRIES", 3)?,
|
||||
|
||||
+1
-1
@@ -37,7 +37,7 @@ pub use self::embeddings::EmbeddingsConfig;
|
||||
pub use self::heartbeat::HeartbeatConfig;
|
||||
pub use self::hygiene::HygieneConfig;
|
||||
pub use self::llm::{
|
||||
AnthropicDirectConfig, LlmBackend, LlmConfig, NearAiApiMode, NearAiConfig, OllamaConfig,
|
||||
AnthropicDirectConfig, LlmBackend, LlmConfig, NearAiConfig, OllamaConfig,
|
||||
OpenAiCompatibleConfig, OpenAiDirectConfig, TinfoilConfig,
|
||||
};
|
||||
pub use self::routines::RoutineConfig;
|
||||
|
||||
Reference in New Issue
Block a user