Files
optimclaw/src/agent/commands.rs
T
448383cfb0 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]>
2026-02-20 20:43:32 +00:00

508 lines
19 KiB
Rust

//! System commands and job handlers for the agent.
//!
//! Extracted from `agent_loop.rs` to isolate the /help, /model, /status,
//! and other command processing from the core agent loop.
use std::sync::Arc;
use tokio::sync::Mutex;
use uuid::Uuid;
use crate::agent::session::Session;
use crate::agent::submission::SubmissionResult;
use crate::agent::{Agent, MessageIntent};
use crate::channels::{IncomingMessage, StatusUpdate};
use crate::error::Error;
use crate::llm::{ChatMessage, Reasoning};
impl Agent {
/// Handle job-related intents without turn tracking.
pub(super) async fn handle_job_or_command(
&self,
intent: MessageIntent,
message: &IncomingMessage,
) -> Result<SubmissionResult, Error> {
// Send thinking status for non-trivial operations
if let MessageIntent::CreateJob { .. } = &intent {
let _ = self
.channels
.send_status(
&message.channel,
StatusUpdate::Thinking("Processing...".into()),
&message.metadata,
)
.await;
}
let response = match intent {
MessageIntent::CreateJob {
title,
description,
category,
} => {
self.handle_create_job(&message.user_id, title, description, category)
.await?
}
MessageIntent::CheckJobStatus { job_id } => {
self.handle_check_status(&message.user_id, job_id).await?
}
MessageIntent::CancelJob { job_id } => {
self.handle_cancel_job(&message.user_id, &job_id).await?
}
MessageIntent::ListJobs { filter } => {
self.handle_list_jobs(&message.user_id, filter).await?
}
MessageIntent::HelpJob { job_id } => {
self.handle_help_job(&message.user_id, &job_id).await?
}
MessageIntent::Command { command, args } => {
match self.handle_command(&command, &args).await? {
Some(s) => s,
None => return Ok(SubmissionResult::Ok { message: None }), // Shutdown signal
}
}
_ => "Unknown intent".to_string(),
};
Ok(SubmissionResult::response(response))
}
async fn handle_create_job(
&self,
user_id: &str,
title: String,
description: String,
category: Option<String>,
) -> Result<String, Error> {
// Create job context
let job_id = self
.context_manager
.create_job_for_user(user_id, &title, &description)
.await?;
// Update category if provided
if let Some(cat) = category {
self.context_manager
.update_context(job_id, |ctx| {
ctx.category = Some(cat);
})
.await?;
}
// Persist new job to database (fire-and-forget)
if let Some(store) = self.store()
&& let Ok(ctx) = self.context_manager.get_context(job_id).await
{
let store = store.clone();
tokio::spawn(async move {
if let Err(e) = store.save_job(&ctx).await {
tracing::warn!("Failed to persist new job {}: {}", job_id, e);
}
});
}
// Schedule for execution
self.scheduler.schedule(job_id).await?;
Ok(format!(
"Created job: {}\nID: {}\n\nThe job has been scheduled and is now running.",
title, job_id
))
}
async fn handle_check_status(
&self,
user_id: &str,
job_id: Option<String>,
) -> Result<String, Error> {
match job_id {
Some(id) => {
let uuid = Uuid::parse_str(&id)
.map_err(|_| crate::error::JobError::NotFound { id: Uuid::nil() })?;
let ctx = self.context_manager.get_context(uuid).await?;
if ctx.user_id != user_id {
return Err(crate::error::JobError::NotFound { id: uuid }.into());
}
Ok(format!(
"Job: {}\nStatus: {:?}\nCreated: {}\nStarted: {}\nActual cost: {}",
ctx.title,
ctx.state,
ctx.created_at.format("%Y-%m-%d %H:%M:%S"),
ctx.started_at
.map(|t| t.format("%Y-%m-%d %H:%M:%S").to_string())
.unwrap_or_else(|| "Not started".to_string()),
ctx.actual_cost
))
}
None => {
// Show summary of all jobs
let summary = self.context_manager.summary_for(user_id).await;
Ok(format!(
"Jobs summary:\n Total: {}\n In Progress: {}\n Completed: {}\n Failed: {}\n Stuck: {}",
summary.total,
summary.in_progress,
summary.completed,
summary.failed,
summary.stuck
))
}
}
}
async fn handle_cancel_job(&self, user_id: &str, job_id: &str) -> Result<String, Error> {
let uuid = Uuid::parse_str(job_id)
.map_err(|_| crate::error::JobError::NotFound { id: Uuid::nil() })?;
let ctx = self.context_manager.get_context(uuid).await?;
if ctx.user_id != user_id {
return Err(crate::error::JobError::NotFound { id: uuid }.into());
}
self.scheduler.stop(uuid).await?;
Ok(format!("Job {} has been cancelled.", job_id))
}
async fn handle_list_jobs(
&self,
user_id: &str,
_filter: Option<String>,
) -> Result<String, Error> {
let jobs = self.context_manager.all_jobs_for(user_id).await;
if jobs.is_empty() {
return Ok("No jobs found.".to_string());
}
let mut output = String::from("Jobs:\n");
for job_id in jobs {
if let Ok(ctx) = self.context_manager.get_context(job_id).await
&& ctx.user_id == user_id
{
output.push_str(&format!(" {} - {} ({:?})\n", job_id, ctx.title, ctx.state));
}
}
Ok(output)
}
async fn handle_help_job(&self, user_id: &str, job_id: &str) -> Result<String, Error> {
let uuid = Uuid::parse_str(job_id)
.map_err(|_| crate::error::JobError::NotFound { id: Uuid::nil() })?;
let ctx = self.context_manager.get_context(uuid).await?;
if ctx.user_id != user_id {
return Err(crate::error::JobError::NotFound { id: uuid }.into());
}
if ctx.state == crate::context::JobState::Stuck {
// Attempt recovery
self.context_manager
.update_context(uuid, |ctx| ctx.attempt_recovery())
.await?
.map_err(|s| crate::error::JobError::ContextError {
id: uuid,
reason: s,
})?;
// Reschedule
self.scheduler.schedule(uuid).await?;
Ok(format!(
"Job {} was stuck. Attempting recovery (attempt #{}).",
job_id,
ctx.repair_attempts + 1
))
} else {
Ok(format!(
"Job {} is not stuck (current state: {:?}). No help needed.",
job_id, ctx.state
))
}
}
/// Trigger a manual heartbeat check.
pub(super) async fn process_heartbeat(&self) -> Result<SubmissionResult, Error> {
let Some(workspace) = self.workspace() else {
return Ok(SubmissionResult::error(
"Heartbeat requires a workspace (database must be connected).",
));
};
let runner = crate::agent::HeartbeatRunner::new(
crate::agent::HeartbeatConfig::default(),
crate::workspace::hygiene::HygieneConfig::default(),
workspace.clone(),
self.llm().clone(),
self.safety().clone(),
);
match runner.check_heartbeat().await {
crate::agent::HeartbeatResult::Ok => Ok(SubmissionResult::ok_with_message(
"Heartbeat: all clear, nothing needs attention.",
)),
crate::agent::HeartbeatResult::NeedsAttention(msg) => Ok(SubmissionResult::response(
format!("Heartbeat findings:\n\n{}", msg),
)),
crate::agent::HeartbeatResult::Skipped => Ok(SubmissionResult::ok_with_message(
"Heartbeat skipped: no HEARTBEAT.md checklist found in workspace.",
)),
crate::agent::HeartbeatResult::Failed(err) => Ok(SubmissionResult::error(format!(
"Heartbeat failed: {}",
err
))),
}
}
/// Summarize the current thread's conversation.
pub(super) async fn process_summarize(
&self,
session: Arc<Mutex<Session>>,
thread_id: Uuid,
) -> Result<SubmissionResult, Error> {
let messages = {
let sess = session.lock().await;
let thread = sess
.threads
.get(&thread_id)
.ok_or_else(|| Error::from(crate::error::JobError::NotFound { id: thread_id }))?;
thread.messages()
};
if messages.is_empty() {
return Ok(SubmissionResult::ok_with_message(
"Nothing to summarize (empty thread).",
));
}
// Build a summary prompt with the conversation
let mut context = Vec::new();
context.push(ChatMessage::system(
"Summarize the conversation so far in 3-5 concise bullet points. \
Focus on decisions made, actions taken, and key outcomes. \
Be brief and factual.",
));
// Include the conversation messages (truncate to last 20 to avoid context overflow)
let start = if messages.len() > 20 {
messages.len() - 20
} else {
0
};
context.extend_from_slice(&messages[start..]);
context.push(ChatMessage::user("Summarize this conversation."));
let request = crate::llm::CompletionRequest::new(context)
.with_max_tokens(512)
.with_temperature(0.3);
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{}",
text.trim()
))),
Err(e) => Ok(SubmissionResult::error(format!("Summarize failed: {}", e))),
}
}
/// Suggest next steps based on the current thread.
pub(super) async fn process_suggest(
&self,
session: Arc<Mutex<Session>>,
thread_id: Uuid,
) -> Result<SubmissionResult, Error> {
let messages = {
let sess = session.lock().await;
let thread = sess
.threads
.get(&thread_id)
.ok_or_else(|| Error::from(crate::error::JobError::NotFound { id: thread_id }))?;
thread.messages()
};
if messages.is_empty() {
return Ok(SubmissionResult::ok_with_message(
"Nothing to suggest from (empty thread).",
));
}
let mut context = Vec::new();
context.push(ChatMessage::system(
"Based on the conversation so far, suggest 2-4 concrete next steps the user could take. \
Be actionable and specific. Format as a numbered list.",
));
let start = if messages.len() > 20 {
messages.len() - 20
} else {
0
};
context.extend_from_slice(&messages[start..]);
context.push(ChatMessage::user("What should I do next?"));
let request = crate::llm::CompletionRequest::new(context)
.with_max_tokens(512)
.with_temperature(0.5);
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{}",
text.trim()
))),
Err(e) => Ok(SubmissionResult::error(format!("Suggest failed: {}", e))),
}
}
/// Handle system commands that bypass thread-state checks entirely.
pub(super) async fn handle_system_command(
&self,
command: &str,
args: &[String],
) -> Result<SubmissionResult, Error> {
match command {
"help" => Ok(SubmissionResult::response(concat!(
"System:\n",
" /help Show this help\n",
" /model [name] Show or switch the active model\n",
" /version Show version info\n",
" /tools List available tools\n",
" /debug Toggle debug mode\n",
" /ping Connectivity check\n",
"\n",
"Jobs:\n",
" /job <desc> Create a new job\n",
" /status [id] Check job status\n",
" /cancel <id> Cancel a job\n",
" /list List all jobs\n",
"\n",
"Session:\n",
" /undo Undo last turn\n",
" /redo Redo undone turn\n",
" /compact Compress context window\n",
" /clear Clear current thread\n",
" /interrupt Stop current operation\n",
" /new New conversation thread\n",
" /thread <id> Switch to thread\n",
" /resume <id> Resume from checkpoint\n",
"\n",
"Agent:\n",
" /heartbeat Run heartbeat check\n",
" /summarize Summarize current thread\n",
" /suggest Suggest next steps\n",
"\n",
" /quit Exit",
))),
"ping" => Ok(SubmissionResult::response("pong!")),
"version" => Ok(SubmissionResult::response(format!(
"{} v{}",
env!("CARGO_PKG_NAME"),
env!("CARGO_PKG_VERSION")
))),
"tools" => {
let tools = self.tools().list().await;
Ok(SubmissionResult::response(format!(
"Available tools: {}",
tools.join(", ")
)))
}
"debug" => {
// Debug toggle is handled client-side in the REPL.
// For non-REPL channels, just acknowledge.
Ok(SubmissionResult::ok_with_message(
"Debug toggle is handled by your client.",
))
}
"model" => {
let current = self.llm().active_model_name();
if args.is_empty() {
// Show current model and list available models
let mut out = format!("Active model: {}\n", current);
match self.llm().list_models().await {
Ok(models) if !models.is_empty() => {
out.push_str("\nAvailable models:\n");
for m in &models {
let marker = if *m == current { " (active)" } else { "" };
out.push_str(&format!(" {}{}\n", m, marker));
}
out.push_str("\nUse /model <name> to switch.");
}
Ok(_) => {
out.push_str(
"\nCould not fetch model list. Use /model <name> to switch.",
);
}
Err(e) => {
out.push_str(&format!(
"\nCould not fetch models: {}. Use /model <name> to switch.",
e
));
}
}
Ok(SubmissionResult::response(out))
} else {
let requested = &args[0];
// Validate the model exists
match self.llm().list_models().await {
Ok(models) if !models.is_empty() => {
if !models.iter().any(|m| m == requested) {
return Ok(SubmissionResult::error(format!(
"Unknown model: {}. Available models:\n {}",
requested,
models.join("\n ")
)));
}
}
Ok(_) => {
// Empty model list, can't validate but try anyway
}
Err(e) => {
tracing::warn!("Could not fetch model list for validation: {}", e);
}
}
match self.llm().set_model(requested) {
Ok(()) => Ok(SubmissionResult::response(format!(
"Switched model to: {}",
requested
))),
Err(e) => Ok(SubmissionResult::error(format!(
"Failed to switch model: {}",
e
))),
}
}
}
_ => Ok(SubmissionResult::error(format!(
"Unknown command: {}. Try /help",
command
))),
}
}
/// Handle legacy command routing from the Router (job commands that go through
/// process_user_input -> router -> handle_job_or_command -> here).
pub(super) async fn handle_command(
&self,
command: &str,
args: &[String],
) -> Result<Option<String>, Error> {
// System commands are now handled directly via Submission::SystemCommand,
// but the router may still send us unknown /commands.
match self.handle_system_command(command, args).await? {
SubmissionResult::Response { content } => Ok(Some(content)),
SubmissionResult::Ok { message } => Ok(message),
SubmissionResult::Error { message } => Ok(Some(format!("Error: {}", message))),
_ => Ok(None),
}
}
}