mirror of
https://github.com/outbackdingo/optimclaw.git
synced 2026-08-31 16:49:34 +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
@@ -358,10 +358,6 @@ impl Agent {
|
||||
}
|
||||
});
|
||||
|
||||
tracing::info!(
|
||||
"Heartbeat enabled with {}s interval",
|
||||
hb_config.interval_secs
|
||||
);
|
||||
let hygiene = self
|
||||
.hygiene_config
|
||||
.as_ref()
|
||||
@@ -373,6 +369,7 @@ impl Agent {
|
||||
hygiene,
|
||||
workspace.clone(),
|
||||
self.cheap_llm().clone(),
|
||||
self.safety().clone(),
|
||||
Some(notify_tx),
|
||||
))
|
||||
} else {
|
||||
|
||||
+10
-7
@@ -13,7 +13,7 @@ use crate::agent::submission::SubmissionResult;
|
||||
use crate::agent::{Agent, MessageIntent};
|
||||
use crate::channels::{IncomingMessage, StatusUpdate};
|
||||
use crate::error::Error;
|
||||
use crate::llm::ChatMessage;
|
||||
use crate::llm::{ChatMessage, Reasoning};
|
||||
|
||||
impl Agent {
|
||||
/// Handle job-related intents without turn tracking.
|
||||
@@ -235,6 +235,7 @@ impl Agent {
|
||||
crate::workspace::hygiene::HygieneConfig::default(),
|
||||
workspace.clone(),
|
||||
self.llm().clone(),
|
||||
self.safety().clone(),
|
||||
);
|
||||
|
||||
match runner.check_heartbeat().await {
|
||||
@@ -295,10 +296,11 @@ impl Agent {
|
||||
.with_max_tokens(512)
|
||||
.with_temperature(0.3);
|
||||
|
||||
match self.llm().complete(request).await {
|
||||
Ok(response) => Ok(SubmissionResult::response(format!(
|
||||
let reasoning = Reasoning::new(self.llm().clone(), self.safety().clone());
|
||||
match reasoning.complete(request).await {
|
||||
Ok((text, _usage)) => Ok(SubmissionResult::response(format!(
|
||||
"Thread Summary:\n\n{}",
|
||||
response.content.trim()
|
||||
text.trim()
|
||||
))),
|
||||
Err(e) => Ok(SubmissionResult::error(format!("Summarize failed: {}", e))),
|
||||
}
|
||||
@@ -342,10 +344,11 @@ impl Agent {
|
||||
.with_max_tokens(512)
|
||||
.with_temperature(0.5);
|
||||
|
||||
match self.llm().complete(request).await {
|
||||
Ok(response) => Ok(SubmissionResult::response(format!(
|
||||
let reasoning = Reasoning::new(self.llm().clone(), self.safety().clone());
|
||||
match reasoning.complete(request).await {
|
||||
Ok((text, _usage)) => Ok(SubmissionResult::response(format!(
|
||||
"Suggested Next Steps:\n\n{}",
|
||||
response.content.trim()
|
||||
text.trim()
|
||||
))),
|
||||
Err(e) => Ok(SubmissionResult::error(format!("Suggest failed: {}", e))),
|
||||
}
|
||||
|
||||
@@ -12,7 +12,8 @@ use chrono::Utc;
|
||||
use crate::agent::context_monitor::{CompactionStrategy, ContextBreakdown};
|
||||
use crate::agent::session::Thread;
|
||||
use crate::error::Error;
|
||||
use crate::llm::{ChatMessage, CompletionRequest, LlmProvider};
|
||||
use crate::llm::{ChatMessage, CompletionRequest, LlmProvider, Reasoning};
|
||||
use crate::safety::SafetyLayer;
|
||||
use crate::workspace::Workspace;
|
||||
|
||||
/// Result of a compaction operation.
|
||||
@@ -33,12 +34,13 @@ pub struct CompactionResult {
|
||||
/// Compacts conversation context to stay within limits.
|
||||
pub struct ContextCompactor {
|
||||
llm: Arc<dyn LlmProvider>,
|
||||
safety: Arc<SafetyLayer>,
|
||||
}
|
||||
|
||||
impl ContextCompactor {
|
||||
/// Create a new context compactor.
|
||||
pub fn new(llm: Arc<dyn LlmProvider>) -> Self {
|
||||
Self { llm }
|
||||
pub fn new(llm: Arc<dyn LlmProvider>, safety: Arc<SafetyLayer>) -> Self {
|
||||
Self { llm, safety }
|
||||
}
|
||||
|
||||
/// Compact a thread's context using the given strategy.
|
||||
@@ -231,8 +233,9 @@ Be brief but capture all important details. Use bullet points."#,
|
||||
.with_max_tokens(1024)
|
||||
.with_temperature(0.3);
|
||||
|
||||
let response = self.llm.complete(request).await?;
|
||||
Ok(response.content)
|
||||
let reasoning = Reasoning::new(self.llm.clone(), self.safety.clone());
|
||||
let (text, _) = reasoning.complete(request).await?;
|
||||
Ok(text)
|
||||
}
|
||||
|
||||
/// Write a summary to the workspace daily log.
|
||||
|
||||
+32
-5
@@ -109,10 +109,17 @@ impl Agent {
|
||||
let job_ctx = JobContext::with_user(&message.user_id, "chat", "Interactive chat session");
|
||||
|
||||
const MAX_TOOL_ITERATIONS: usize = 10;
|
||||
// Force a text-only response on the last iteration to guarantee termination
|
||||
// instead of hard-erroring. The penultimate iteration also gets a nudge
|
||||
// message so the LLM knows it should wrap up.
|
||||
const FORCE_TEXT_AT: usize = MAX_TOOL_ITERATIONS;
|
||||
const NUDGE_AT: usize = MAX_TOOL_ITERATIONS - 1;
|
||||
let mut iteration = 0;
|
||||
loop {
|
||||
iteration += 1;
|
||||
if iteration > MAX_TOOL_ITERATIONS {
|
||||
// Hard ceiling one past the forced-text iteration (should never be reached
|
||||
// since FORCE_TEXT_AT guarantees a text response, but kept as a safety net).
|
||||
if iteration > MAX_TOOL_ITERATIONS + 1 {
|
||||
return Err(crate::error::LlmError::InvalidResponse {
|
||||
provider: "agent".to_string(),
|
||||
reason: format!("Exceeded maximum tool iterations ({})", MAX_TOOL_ITERATIONS),
|
||||
@@ -143,6 +150,19 @@ impl Agent {
|
||||
.into());
|
||||
}
|
||||
|
||||
// Inject a nudge message when approaching the iteration limit so the
|
||||
// LLM is aware it should produce a final answer on the next turn.
|
||||
if iteration == NUDGE_AT {
|
||||
context_messages.push(ChatMessage::system(
|
||||
"You are approaching the tool call limit. \
|
||||
Provide your best final answer on the next response \
|
||||
using the information you have gathered so far. \
|
||||
Do not call any more tools.",
|
||||
));
|
||||
}
|
||||
|
||||
let force_text = iteration >= FORCE_TEXT_AT;
|
||||
|
||||
// Refresh tool definitions each iteration so newly built tools become visible
|
||||
let tool_defs = self.tools().tool_definitions().await;
|
||||
|
||||
@@ -162,8 +182,9 @@ impl Agent {
|
||||
tool_defs
|
||||
};
|
||||
|
||||
// Call LLM with current context
|
||||
let context = ReasoningContext::new()
|
||||
// Call LLM with current context; force_text drops tools to guarantee a
|
||||
// text response on the final iteration.
|
||||
let mut context = ReasoningContext::new()
|
||||
.with_messages(context_messages.clone())
|
||||
.with_tools(tool_defs)
|
||||
.with_metadata({
|
||||
@@ -171,6 +192,14 @@ impl Agent {
|
||||
m.insert("thread_id".to_string(), thread_id.to_string());
|
||||
m
|
||||
});
|
||||
context.force_text = force_text;
|
||||
|
||||
if force_text {
|
||||
tracing::info!(
|
||||
iteration,
|
||||
"Forcing text-only response (iteration limit reached)"
|
||||
);
|
||||
}
|
||||
|
||||
let output = reasoning.respond_with_tools(&context).await?;
|
||||
|
||||
@@ -799,7 +828,6 @@ mod tests {
|
||||
input_tokens: 0,
|
||||
output_tokens: 0,
|
||||
finish_reason: FinishReason::Stop,
|
||||
response_id: None,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -813,7 +841,6 @@ mod tests {
|
||||
input_tokens: 0,
|
||||
output_tokens: 0,
|
||||
finish_reason: FinishReason::Stop,
|
||||
response_id: None,
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
+11
-13
@@ -29,7 +29,8 @@ use std::time::Duration;
|
||||
use tokio::sync::mpsc;
|
||||
|
||||
use crate::channels::OutgoingResponse;
|
||||
use crate::llm::{ChatMessage, CompletionRequest, FinishReason, LlmProvider};
|
||||
use crate::llm::{ChatMessage, CompletionRequest, LlmProvider, Reasoning};
|
||||
use crate::safety::SafetyLayer;
|
||||
use crate::workspace::Workspace;
|
||||
use crate::workspace::hygiene::HygieneConfig;
|
||||
|
||||
@@ -100,6 +101,7 @@ pub struct HeartbeatRunner {
|
||||
hygiene_config: HygieneConfig,
|
||||
workspace: Arc<Workspace>,
|
||||
llm: Arc<dyn LlmProvider>,
|
||||
safety: Arc<SafetyLayer>,
|
||||
response_tx: Option<mpsc::Sender<OutgoingResponse>>,
|
||||
consecutive_failures: u32,
|
||||
}
|
||||
@@ -111,12 +113,14 @@ impl HeartbeatRunner {
|
||||
hygiene_config: HygieneConfig,
|
||||
workspace: Arc<Workspace>,
|
||||
llm: Arc<dyn LlmProvider>,
|
||||
safety: Arc<SafetyLayer>,
|
||||
) -> Self {
|
||||
Self {
|
||||
config,
|
||||
hygiene_config,
|
||||
workspace,
|
||||
llm,
|
||||
safety,
|
||||
response_tx: None,
|
||||
consecutive_failures: 0,
|
||||
}
|
||||
@@ -258,25 +262,18 @@ impl HeartbeatRunner {
|
||||
.with_max_tokens(max_tokens)
|
||||
.with_temperature(0.3);
|
||||
|
||||
let response = match self.llm.complete(request).await {
|
||||
let reasoning = Reasoning::new(self.llm.clone(), self.safety.clone());
|
||||
let (content, _usage) = match reasoning.complete(request).await {
|
||||
Ok(r) => r,
|
||||
Err(e) => return HeartbeatResult::Failed(format!("LLM call failed: {}", e)),
|
||||
};
|
||||
|
||||
let content = response.content.trim();
|
||||
let content = content.trim();
|
||||
|
||||
// Guard against empty content. Reasoning models (e.g. GLM-4.7) may
|
||||
// burn all output tokens on chain-of-thought and return content: null.
|
||||
if content.is_empty() {
|
||||
return if response.finish_reason == FinishReason::Length {
|
||||
HeartbeatResult::Failed(
|
||||
"LLM response was truncated (finish_reason=length) with no content. \
|
||||
The model may have exhausted its token budget on reasoning."
|
||||
.to_string(),
|
||||
)
|
||||
} else {
|
||||
HeartbeatResult::Failed("LLM returned empty content.".to_string())
|
||||
};
|
||||
return HeartbeatResult::Failed("LLM returned empty content.".to_string());
|
||||
}
|
||||
|
||||
// Check if nothing needs attention
|
||||
@@ -355,9 +352,10 @@ pub fn spawn_heartbeat(
|
||||
hygiene_config: HygieneConfig,
|
||||
workspace: Arc<Workspace>,
|
||||
llm: Arc<dyn LlmProvider>,
|
||||
safety: Arc<SafetyLayer>,
|
||||
response_tx: Option<mpsc::Sender<OutgoingResponse>>,
|
||||
) -> tokio::task::JoinHandle<()> {
|
||||
let mut runner = HeartbeatRunner::new(config, hygiene_config, workspace, llm);
|
||||
let mut runner = HeartbeatRunner::new(config, hygiene_config, workspace, llm, safety);
|
||||
if let Some(tx) = response_tx {
|
||||
runner = runner.with_response_channel(tx);
|
||||
}
|
||||
|
||||
@@ -185,10 +185,6 @@ pub struct Thread {
|
||||
/// Pending auth token request (thread is in auth mode).
|
||||
#[serde(default)]
|
||||
pub pending_auth: Option<PendingAuth>,
|
||||
/// Last NEAR AI response ID for response chaining. Persisted to DB
|
||||
/// metadata so we can resume chaining across restarts.
|
||||
#[serde(default)]
|
||||
pub last_response_id: Option<String>,
|
||||
}
|
||||
|
||||
impl Thread {
|
||||
@@ -205,7 +201,6 @@ impl Thread {
|
||||
metadata: serde_json::Value::Null,
|
||||
pending_approval: None,
|
||||
pending_auth: None,
|
||||
last_response_id: None,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -222,7 +217,6 @@ impl Thread {
|
||||
metadata: serde_json::Value::Null,
|
||||
pending_approval: None,
|
||||
pending_auth: None,
|
||||
last_response_id: None,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -863,7 +857,6 @@ mod tests {
|
||||
|
||||
thread.start_turn("hello");
|
||||
thread.complete_turn("world");
|
||||
thread.last_response_id = Some("resp_abc123".to_string());
|
||||
|
||||
let json = serde_json::to_string(&thread).unwrap();
|
||||
let restored: Thread = serde_json::from_str(&json).unwrap();
|
||||
@@ -873,7 +866,6 @@ mod tests {
|
||||
assert_eq!(restored.turns.len(), 1);
|
||||
assert_eq!(restored.turns[0].user_input, "hello");
|
||||
assert_eq!(restored.turns[0].response, Some("world".to_string()));
|
||||
assert_eq!(restored.last_response_id, Some("resp_abc123".to_string()));
|
||||
}
|
||||
|
||||
#[test]
|
||||
|
||||
+39
-90
@@ -87,20 +87,6 @@ impl Agent {
|
||||
thread.restore_from_messages(chat_messages);
|
||||
}
|
||||
|
||||
// Restore response chain from conversation metadata
|
||||
if let Some(store) = self.store()
|
||||
&& let Ok(Some(metadata)) = store.get_conversation_metadata(thread_uuid).await
|
||||
&& let Some(rid) = metadata
|
||||
.get("last_response_id")
|
||||
.and_then(|v| v.as_str())
|
||||
.map(String::from)
|
||||
{
|
||||
thread.last_response_id = Some(rid.clone());
|
||||
self.llm()
|
||||
.seed_response_chain(&thread_uuid.to_string(), rid);
|
||||
tracing::debug!("Restored response chain for thread {}", thread_uuid);
|
||||
}
|
||||
|
||||
// Insert into session and register with session manager
|
||||
{
|
||||
let mut sess = session.lock().await;
|
||||
@@ -228,7 +214,7 @@ impl Agent {
|
||||
)
|
||||
.await;
|
||||
|
||||
let compactor = ContextCompactor::new(self.llm().clone());
|
||||
let compactor = ContextCompactor::new(self.llm().clone(), self.safety().clone());
|
||||
if let Err(e) = compactor
|
||||
.compact(thread, strategy, self.workspace().map(|w| w.as_ref()))
|
||||
.await
|
||||
@@ -325,7 +311,6 @@ impl Agent {
|
||||
};
|
||||
|
||||
thread.complete_turn(&response);
|
||||
self.persist_response_chain(thread);
|
||||
let _ = self
|
||||
.channels
|
||||
.send_status(
|
||||
@@ -335,8 +320,10 @@ impl Agent {
|
||||
)
|
||||
.await;
|
||||
|
||||
// Fire-and-forget: persist turn to DB
|
||||
self.persist_turn(thread_id, &message.user_id, content, Some(&response));
|
||||
// Persist turn to DB before returning so the write
|
||||
// completes even if the process shuts down right after.
|
||||
self.persist_turn(thread_id, &message.user_id, content, Some(&response))
|
||||
.await;
|
||||
|
||||
Ok(SubmissionResult::response(response))
|
||||
}
|
||||
@@ -366,15 +353,16 @@ impl Agent {
|
||||
thread.fail_turn(e.to_string());
|
||||
|
||||
// Persist the user message even on failure
|
||||
self.persist_turn(thread_id, &message.user_id, content, None);
|
||||
self.persist_turn(thread_id, &message.user_id, content, None)
|
||||
.await;
|
||||
|
||||
Ok(SubmissionResult::error(e.to_string()))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Fire-and-forget: persist a turn (user message + optional assistant response) to the DB.
|
||||
pub(super) fn persist_turn(
|
||||
/// Persist a turn (user message + optional assistant response) to the DB.
|
||||
pub(super) async fn persist_turn(
|
||||
&self,
|
||||
thread_id: Uuid,
|
||||
user_id: &str,
|
||||
@@ -386,70 +374,29 @@ impl Agent {
|
||||
None => return,
|
||||
};
|
||||
|
||||
let user_id = user_id.to_string();
|
||||
let user_input = user_input.to_string();
|
||||
let response = response.map(String::from);
|
||||
if let Err(e) = store
|
||||
.ensure_conversation(thread_id, "gateway", user_id, None)
|
||||
.await
|
||||
{
|
||||
tracing::warn!("Failed to ensure conversation {}: {}", thread_id, e);
|
||||
return;
|
||||
}
|
||||
|
||||
tokio::spawn(async move {
|
||||
if let Err(e) = store
|
||||
.ensure_conversation(thread_id, "gateway", &user_id, None)
|
||||
if let Err(e) = store
|
||||
.add_conversation_message(thread_id, "user", user_input)
|
||||
.await
|
||||
{
|
||||
tracing::warn!("Failed to persist user message: {}", e);
|
||||
return;
|
||||
}
|
||||
|
||||
if let Some(resp) = response
|
||||
&& let Err(e) = store
|
||||
.add_conversation_message(thread_id, "assistant", resp)
|
||||
.await
|
||||
{
|
||||
tracing::warn!("Failed to ensure conversation {}: {}", thread_id, e);
|
||||
return;
|
||||
}
|
||||
|
||||
if let Err(e) = store
|
||||
.add_conversation_message(thread_id, "user", &user_input)
|
||||
.await
|
||||
{
|
||||
tracing::warn!("Failed to persist user message: {}", e);
|
||||
return;
|
||||
}
|
||||
|
||||
if let Some(ref resp) = response
|
||||
&& let Err(e) = store
|
||||
.add_conversation_message(thread_id, "assistant", resp)
|
||||
.await
|
||||
{
|
||||
tracing::warn!("Failed to persist assistant message: {}", e);
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
/// Sync the provider's response chain ID to the thread and DB metadata.
|
||||
///
|
||||
/// Call after a successful agentic loop to persist the latest
|
||||
/// `previous_response_id` so chaining survives restarts.
|
||||
pub(super) fn persist_response_chain(&self, thread: &mut crate::agent::session::Thread) {
|
||||
let tid = thread.id.to_string();
|
||||
let response_id = match self.llm().get_response_chain_id(&tid) {
|
||||
Some(rid) => rid,
|
||||
None => return,
|
||||
};
|
||||
|
||||
// Update in-memory thread
|
||||
thread.last_response_id = Some(response_id.clone());
|
||||
|
||||
// Fire-and-forget DB write
|
||||
let store = match self.store() {
|
||||
Some(s) => Arc::clone(s),
|
||||
None => return,
|
||||
};
|
||||
let thread_id = thread.id;
|
||||
tokio::spawn(async move {
|
||||
let val = serde_json::json!(response_id);
|
||||
if let Err(e) = store
|
||||
.update_conversation_metadata_field(thread_id, "last_response_id", &val)
|
||||
.await
|
||||
{
|
||||
tracing::warn!(
|
||||
"Failed to persist response chain for thread {}: {}",
|
||||
thread_id,
|
||||
e
|
||||
);
|
||||
}
|
||||
});
|
||||
{
|
||||
tracing::warn!("Failed to persist assistant message: {}", e);
|
||||
}
|
||||
}
|
||||
|
||||
pub(super) async fn process_undo(
|
||||
@@ -562,7 +509,7 @@ impl Agent {
|
||||
crate::agent::context_monitor::CompactionStrategy::Summarize { keep_recent: 5 },
|
||||
);
|
||||
|
||||
let compactor = ContextCompactor::new(self.llm().clone());
|
||||
let compactor = ContextCompactor::new(self.llm().clone(), self.safety().clone());
|
||||
match compactor
|
||||
.compact(thread, strategy, self.workspace().map(|w| w.as_ref()))
|
||||
.await
|
||||
@@ -1072,9 +1019,9 @@ impl Agent {
|
||||
let user_input = thread.last_turn().map(|t| t.user_input.clone());
|
||||
thread.complete_turn(&response);
|
||||
if let Some(input) = user_input {
|
||||
self.persist_turn(thread_id, &message.user_id, &input, Some(&response));
|
||||
self.persist_turn(thread_id, &message.user_id, &input, Some(&response))
|
||||
.await;
|
||||
}
|
||||
self.persist_response_chain(thread);
|
||||
let _ = self
|
||||
.channels
|
||||
.send_status(
|
||||
@@ -1112,7 +1059,8 @@ impl Agent {
|
||||
let user_input = thread.last_turn().map(|t| t.user_input.clone());
|
||||
thread.fail_turn(e.to_string());
|
||||
if let Some(input) = user_input {
|
||||
self.persist_turn(thread_id, &message.user_id, &input, None);
|
||||
self.persist_turn(thread_id, &message.user_id, &input, None)
|
||||
.await;
|
||||
}
|
||||
Ok(SubmissionResult::error(e.to_string()))
|
||||
}
|
||||
@@ -1131,7 +1079,8 @@ impl Agent {
|
||||
thread.clear_pending_approval();
|
||||
thread.complete_turn(&rejection);
|
||||
if let Some(input) = user_input {
|
||||
self.persist_turn(thread_id, &message.user_id, &input, Some(&rejection));
|
||||
self.persist_turn(thread_id, &message.user_id, &input, Some(&rejection))
|
||||
.await;
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1171,9 +1120,9 @@ impl Agent {
|
||||
thread.enter_auth_mode(ext_name.clone());
|
||||
thread.complete_turn(&instructions);
|
||||
if let Some(input) = user_input {
|
||||
self.persist_turn(thread_id, &message.user_id, &input, Some(&instructions));
|
||||
self.persist_turn(thread_id, &message.user_id, &input, Some(&instructions))
|
||||
.await;
|
||||
}
|
||||
self.persist_response_chain(thread);
|
||||
}
|
||||
}
|
||||
let _ = self
|
||||
|
||||
Reference in New Issue
Block a user