diff --git a/.env.example b/.env.example index 8fd44c5a..b52412c5 100644 --- a/.env.example +++ b/.env.example @@ -4,7 +4,7 @@ DATABASE_POOL_SIZE=10 # LLM Provider # LLM_BACKEND=nearai # default -# Possible values: nearai, ollama, openai_compatible, openai, anthropic, tinfoil +# Possible values: nearai, ollama, openai_compatible, openai, anthropic, tinfoil, openai_codex # LLM_REQUEST_TIMEOUT_SECS=120 # Increase for local LLMs (Ollama, vLLM, LM Studio) # === Anthropic Direct === @@ -31,7 +31,7 @@ DATABASE_POOL_SIZE=10 # Base URL defaults to https://private.near.ai # 2. API key: Set NEARAI_API_KEY to use API key auth from cloud.near.ai. # Base URL defaults to https://cloud-api.near.ai -NEARAI_MODEL=zai-org/GLM-5-FP8 +NEARAI_MODEL=Qwen/Qwen3.5-122B-A10B NEARAI_BASE_URL=https://private.near.ai NEARAI_AUTH_URL=https://private.near.ai # NEARAI_SESSION_TOKEN=sess_... # hosting providers: set this @@ -92,6 +92,13 @@ NEARAI_AUTH_URL=https://private.near.ai # long = 1-hour TTL, 2.0× (200%) write surcharge # ANTHROPIC_CACHE_RETENTION=short +# === OpenAI Codex (ChatGPT subscription, OAuth) === +# LLM_BACKEND=openai_codex +# OPENAI_CODEX_MODEL=gpt-5.3-codex # default +# OPENAI_CODEX_CLIENT_ID=app_EMoamEEZ73f0CkXaXp7hrann # override (rare) +# OPENAI_CODEX_AUTH_URL=https://auth.openai.com # override (rare) +# OPENAI_CODEX_API_URL=https://chatgpt.com/backend-api/codex # override (rare) + # For full provider setup guide see docs/LLM_PROVIDERS.md # Channel Configuration diff --git a/CLAUDE.md b/CLAUDE.md index d47292e1..e2d84c1e 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -158,6 +158,8 @@ src/ │ ├── secrets/ # Secrets management (AES-256-GCM, OS keychain for master key) │ +├── profile.rs # Psychographic profile types, 9-dimension analysis framework +│ ├── setup/ # 7-step onboarding wizard — see src/setup/README.md │ ├── skills/ # SKILL.md prompt extension system — see .claude/rules/skills.md diff --git a/skills/delegation/SKILL.md b/skills/delegation/SKILL.md new file mode 100644 index 00000000..0163dd32 --- /dev/null +++ b/skills/delegation/SKILL.md @@ -0,0 +1,75 @@ +--- +name: delegation +version: 0.1.0 +description: Helps users delegate tasks, break them into steps, set deadlines, and track progress via routines and memory. +activation: + keywords: + - delegate + - hand off + - assign task + - help me with + - take care of + - remind me to + - schedule + - plan my + - manage my + - track this + patterns: + - "can you.*handle" + - "I need (help|someone) to" + - "take over" + - "set up a reminder" + - "follow up on" + tags: + - personal-assistant + - task-management + - delegation + max_context_tokens: 1500 +--- + +# Task Delegation Assistant + +When the user wants to delegate a task or get help managing something, follow this process: + +## 1. Clarify the Task + +Ask what needs to be done, by when, and any constraints. Get enough detail to act independently but don't over-interrogate. If the request is clear, skip straight to planning. + +## 2. Break It Down + +Decompose the task into concrete, actionable steps. Use `memory_write` to persist the task plan to a path like `tasks/{task-name}.md` with: +- Clear description +- Steps with checkboxes +- Due date (if any) +- Status: pending/in-progress/done + +## 3. Set Up Tracking + +If the task is recurring or has a deadline: +- Create a routine using `routine_create` for scheduled check-ins +- Add a heartbeat item if it needs daily monitoring +- Set up an event-triggered routine if it depends on external input + +## 4. Use Profile Context + +Check `USER.md` for the user's preferences: +- **Proactivity level**: High = check in frequently. Low = only report on completion. +- **Communication style**: Match their preferred tone and detail level. +- **Focus areas**: Prioritize tasks that align with their stated goals. + +## 5. Execute or Queue + +- If you can do it now (search, draft, organize, calculate), do it immediately. +- If it requires waiting, external action, or follow-up, create a reminder routine. +- If it requires tools you don't have, explain what's needed and suggest alternatives. + +## 6. Report Back + +Always confirm the plan with the user before starting execution. After completing, update the task file in memory and notify the user with a concise summary. + +## Communication Guidelines + +- Be direct and action-oriented +- Confirm understanding before acting on ambiguous requests +- When in doubt about autonomy level, ask once then remember the answer +- Use `memory_write` to track delegation preferences for future reference diff --git a/skills/routine-advisor/SKILL.md b/skills/routine-advisor/SKILL.md new file mode 100644 index 00000000..3bb10c72 --- /dev/null +++ b/skills/routine-advisor/SKILL.md @@ -0,0 +1,118 @@ +--- +name: routine-advisor +version: 0.1.0 +description: Suggests relevant cron routines based on user context, goals, and observed patterns +activation: + keywords: + - every day + - every morning + - every week + - routine + - automate + - remind me + - check daily + - monitor + - recurring + - schedule + - habit + - workflow + - keep forgetting + - always have to + - repetitive + - notifications + - digest + - summary + - review daily + - weekly review + patterns: + - "I (always|usually|often|regularly) (check|do|look at|review)" + - "every (morning|evening|week|day|monday|friday)" + - "I (wish|want) (I|it) (could|would) (automatically|auto)" + - "is there a way to (auto|schedule|set up)" + - "can you (check|monitor|watch|track).*for me" + - "I keep (forgetting|missing|having to)" + tags: + - automation + - scheduling + - personal-assistant + - productivity + max_context_tokens: 1500 +--- + +# Routine Advisor + +When the conversation suggests the user has a repeatable task or could benefit from automation, consider suggesting a routine. + +## When to Suggest + +Suggest a routine when you notice: +- The user describes doing something repeatedly ("I check my PRs every morning") +- The user mentions forgetting recurring tasks ("I keep forgetting to...") +- The user asks you to do something that sounds periodic +- You've learned enough about the user to propose a relevant automation +- The user has installed extensions that enable new monitoring capabilities + +## How to Suggest + +Be specific and concrete. Not "Want me to set up a routine?" but rather: "I noticed you review PRs every morning. Want me to create a daily 9am routine that checks your open PRs and sends you a summary?" + +Always include: +1. What the routine would do (specific action) +2. When it would run (specific schedule in plain language) +3. How it would notify them (which channel they're on) + +Wait for the user to confirm before creating. + +## Pacing + +- First 1-3 conversations: Do NOT suggest routines. Focus on helping and learning. +- After learning 2-3 user patterns: Suggest your first routine. Keep it simple. +- After 5+ conversations: Suggest more routines as patterns emerge. +- Never suggest more than 1 routine per conversation unless the user is clearly interested. +- If the user declines, wait at least 3 conversations before suggesting again. + +## Creating Routines + +Use the `routine_create` tool. Before creating, check `routine_list` to avoid duplicates. + +Parameters: +- `trigger_type`: Usually "cron" for scheduled tasks +- `schedule`: Standard cron format. Common schedules: + - Daily 9am: `0 9 * * *` + - Weekday mornings: `0 9 * * MON-FRI` + - Weekly Monday: `0 9 * * MON` + - Every 2 hours during work: `0 9-17/2 * * MON-FRI` + - Sunday evening: `0 18 * * SUN` +- `action_type`: "lightweight" for simple checks, "full_job" for multi-step tasks +- `prompt`: Clear, specific instruction for what the routine should do +- `context_paths`: Workspace files to load as context (e.g., `["context/profile.json", "MEMORY.md"]`) + +## Routine Ideas by User Type + +**Developer:** +- Daily PR review digest (check open PRs, summarize what needs attention) +- CI/CD failure alerts (monitor build status) +- Weekly dependency update check +- Daily standup prep (summarize yesterday's work from daily logs) + +**Professional:** +- Morning briefing (today's priorities from memory + any pending tasks) +- End-of-day summary (what was accomplished, what's pending) +- Weekly goal review (check progress against stated goals) +- Meeting prep reminders + +**Health/Personal:** +- Daily exercise or habit check-in +- Weekly meal planning prompt +- Monthly budget review reminder + +**General:** +- Daily news digest on topics of interest +- Weekly reflection prompt (what went well, what to improve) +- Periodic task/reminder check-in +- Regular cleanup of stale tasks or notes +- Weekly profile evolution (if the user has a profile in `context/profile.json`, suggest a Monday routine that reads the profile via `memory_read`, searches recent conversations for new patterns with `memory_search`, and updates the profile via `memory_write` if any fields should change with confidence > 0.6 — be conservative, only update with clear evidence) + +## Awareness + +Before suggesting, consider what tools and extensions are currently available. Only suggest routines the agent can actually execute. If a routine would need a tool that isn't installed, mention that too: "If you connect your calendar, I could also send you a morning briefing with today's meetings." diff --git a/src/agent/CLAUDE.md b/src/agent/CLAUDE.md index e55c9591..686753de 100644 --- a/src/agent/CLAUDE.md +++ b/src/agent/CLAUDE.md @@ -113,7 +113,7 @@ Check-insert is done under a single write lock to prevent TOCTOU races. A cleanu 4. Detects broken tools via `store.get_broken_tools(5)` (threshold: 5 failures). Requires `with_store()` to be called; returns empty without a store. 5. Attempts to rebuild broken tools via `SoftwareBuilder`. Requires `with_builder()` to be called; returns `ManualRequired` without a builder. -Note: the `stuck_threshold` duration is stored but currently unused (marked `#[allow(dead_code)]`). Stuck detection relies on `JobState::Stuck` being set by the state machine, not wall-clock time comparison. +The `stuck_threshold` duration is used for time-based detection of `InProgress` jobs that have been running longer than the threshold. When `detect_stuck_jobs()` finds such jobs, it transitions them to `Stuck` before returning them, enabling the normal `attempt_recovery()` path. Repair results: `Success`, `Retry`, `Failed`, `ManualRequired`. `Retry` does NOT notify the user (to avoid spam). diff --git a/src/agent/agent_loop.rs b/src/agent/agent_loop.rs index 4282daa5..dbc9d38b 100644 --- a/src/agent/agent_loop.rs +++ b/src/agent/agent_loop.rs @@ -31,6 +31,13 @@ use crate::skills::SkillRegistry; use crate::tools::ToolRegistry; use crate::workspace::Workspace; +/// Static greeting persisted to DB and broadcast on first launch. +/// +/// Sent before the LLM is involved so the user sees something immediately. +/// The conversational onboarding (profile building, channel setup) happens +/// organically in the subsequent turns driven by BOOTSTRAP.md. +const BOOTSTRAP_GREETING: &str = include_str!("../workspace/seeds/GREETING.md"); + /// Collapse a tool output string into a single-line preview for display. pub(crate) fn truncate_for_preview(output: &str, max_chars: usize) -> String { let collapsed: String = output @@ -113,6 +120,17 @@ async fn resolve_routine_notification_target( .await } +pub(crate) fn chat_tool_execution_metadata(message: &IncomingMessage) -> serde_json::Value { + serde_json::json!({ + "notify_channel": message.channel, + "notify_user": message + .routing_target() + .unwrap_or_else(|| message.user_id.clone()), + "notify_thread_id": message.thread_id, + "notify_metadata": message.metadata, + }) +} + fn should_fallback_routine_notification(error: &ChannelError) -> bool { !matches!(error, ChannelError::MissingRoutingTarget { .. }) } @@ -340,6 +358,32 @@ impl Agent { /// Run the agent main loop. pub async fn run(self) -> Result<(), Error> { + // Proactive bootstrap: persist the static greeting to DB *before* + // starting channels so the first web client sees it via history. + let bootstrap_thread_id = if self + .workspace() + .is_some_and(|ws| ws.take_bootstrap_pending()) + { + tracing::debug!( + "Fresh workspace detected — persisting static bootstrap greeting to DB" + ); + if let Some(store) = self.store() { + let thread_id = store + .get_or_create_assistant_conversation("default", "gateway") + .await + .ok(); + if let Some(id) = thread_id { + self.persist_assistant_response(id, "gateway", "default", BOOTSTRAP_GREETING) + .await; + } + thread_id + } else { + None + } + } else { + None + }; + // Start channels let mut message_stream = self.channels.start_all().await?; @@ -671,6 +715,30 @@ impl Agent { None }; + // Bootstrap phase 2: register the thread in session manager and + // broadcast the greeting via SSE for any clients already connected. + // The greeting was already persisted to DB before start_all(), so + // clients that connect after this point will see it via history. + if let Some(id) = bootstrap_thread_id { + // Use get_or_create_session (not resolve_thread) to avoid creating + // an orphan thread. Then insert the DB-sourced thread directly. + let session = self.session_manager.get_or_create_session("default").await; + { + use crate::agent::session::Thread; + let mut sess = session.lock().await; + let thread = Thread::with_id(id, sess.id); + sess.active_thread = Some(id); + sess.threads.entry(id).or_insert(thread); + } + self.session_manager + .register_thread("default", "gateway", id, session) + .await; + + let mut out = OutgoingResponse::text(BOOTSTRAP_GREETING.to_string()); + out.thread_id = Some(id.to_string()); + let _ = self.channels.broadcast("gateway", "default", out).await; + } + // Main message loop tracing::debug!("Agent {} ready and listening", self.config.name); @@ -864,9 +932,6 @@ impl Agent { } async fn handle_message(&self, message: &IncomingMessage) -> Result, Error> { - // Log at info level only for tracking without exposing PII (user_id can be a phone number) - tracing::info!(message_id = %message.id, "Processing message"); - // Log sensitive details at debug level for troubleshooting tracing::debug!( message_id = %message.id, @@ -946,10 +1011,6 @@ impl Agent { } // Resolve session and thread - tracing::debug!( - message_id = %message.id, - "Resolving session and thread" - ); let (session, thread_id) = self .session_manager .resolve_thread( @@ -1127,9 +1188,10 @@ impl Agent { #[cfg(test)] mod tests { use super::{ - resolve_routine_notification_user, should_fallback_routine_notification, - truncate_for_preview, + chat_tool_execution_metadata, resolve_routine_notification_user, + should_fallback_routine_notification, truncate_for_preview, }; + use crate::channels::IncomingMessage; use crate::error::ChannelError; #[test] @@ -1225,6 +1287,50 @@ mod tests { assert_eq!(resolve_routine_notification_user(&metadata), None); // safety: test-only assertion } + #[test] + fn chat_tool_execution_metadata_prefers_message_routing_target() { + let message = IncomingMessage::new("telegram", "owner-scope", "hello") + .with_sender_id("telegram-user") + .with_thread("thread-7") + .with_metadata(serde_json::json!({ + "chat_id": 424242, + "chat_type": "private", + })); + + let metadata = chat_tool_execution_metadata(&message); + assert_eq!( + metadata.get("notify_channel").and_then(|v| v.as_str()), + Some("telegram") + ); // safety: test-only assertion + assert_eq!( + metadata.get("notify_user").and_then(|v| v.as_str()), + Some("424242") + ); // safety: test-only assertion + assert_eq!( + metadata.get("notify_thread_id").and_then(|v| v.as_str()), + Some("thread-7") + ); // safety: test-only assertion + } + + #[test] + fn chat_tool_execution_metadata_falls_back_to_user_scope_without_route() { + let message = IncomingMessage::new("gateway", "owner-scope", "hello").with_sender_id(""); + + let metadata = chat_tool_execution_metadata(&message); + assert_eq!( + metadata.get("notify_channel").and_then(|v| v.as_str()), + Some("gateway") + ); // safety: test-only assertion + assert_eq!( + metadata.get("notify_user").and_then(|v| v.as_str()), + Some("owner-scope") + ); // safety: test-only assertion + assert_eq!( + metadata.get("notify_thread_id"), + Some(&serde_json::Value::Null) + ); // safety: test-only assertion + } + #[test] fn targeted_routine_notifications_do_not_fallback_without_owner_route() { let error = ChannelError::MissingRoutingTarget { diff --git a/src/agent/dispatcher.rs b/src/agent/dispatcher.rs index 0b47c928..fc3da61b 100644 --- a/src/agent/dispatcher.rs +++ b/src/agent/dispatcher.rs @@ -144,12 +144,7 @@ impl Agent { .with_requester_id(&message.sender_id); job_ctx.http_interceptor = self.deps.http_interceptor.clone(); job_ctx.user_timezone = user_tz.name().to_string(); - job_ctx.metadata = serde_json::json!({ - "notify_channel": message.channel, - "notify_user": message.user_id, - "notify_thread_id": message.thread_id, - "notify_metadata": message.metadata, - }); + job_ctx.metadata = crate::agent::agent_loop::chat_tool_execution_metadata(message); // Build system prompts once for this turn. Two variants: with tools // (normal iterations) and without (force_text final iteration). diff --git a/src/agent/job_monitor.rs b/src/agent/job_monitor.rs index 6497861a..675d0426 100644 --- a/src/agent/job_monitor.rs +++ b/src/agent/job_monitor.rs @@ -14,12 +14,15 @@ //! Agent Loop //! ``` +use std::sync::Arc; + use tokio::sync::{broadcast, mpsc}; use tokio::task::JoinHandle; use uuid::Uuid; use crate::channels::IncomingMessage; use crate::channels::web::types::SseEvent; +use crate::context::{ContextManager, JobState}; /// Route context for forwarding job monitor events back to the user's channel. #[derive(Debug, Clone)] @@ -40,10 +43,23 @@ pub struct JobMonitorRoute { /// Tool use/result and status events are intentionally skipped (too noisy for /// the main agent's context window). pub fn spawn_job_monitor( + job_id: Uuid, + event_rx: broadcast::Receiver<(Uuid, SseEvent)>, + inject_tx: mpsc::Sender, + route: JobMonitorRoute, +) -> JoinHandle<()> { + spawn_job_monitor_with_context(job_id, event_rx, inject_tx, route, None) +} + +/// Like `spawn_job_monitor`, but also transitions the job's in-memory state +/// when it receives a `JobResult` event. This ensures fire-and-forget sandbox +/// jobs don't stay `InProgress` forever in the `ContextManager`. +pub fn spawn_job_monitor_with_context( job_id: Uuid, mut event_rx: broadcast::Receiver<(Uuid, SseEvent)>, inject_tx: mpsc::Sender, route: JobMonitorRoute, + context_manager: Option>, ) -> JoinHandle<()> { let short_id = job_id.to_string()[..8].to_string(); @@ -77,6 +93,26 @@ pub fn spawn_job_monitor( } } SseEvent::JobResult { status, .. } => { + // Transition in-memory state so the job frees its + // max_jobs slot and query tools show the final state. + if let Some(ref cm) = context_manager { + let target = if status == "completed" { + JobState::Completed + } else { + JobState::Failed + }; + let reason = if status != "completed" { + Some(format!("Container finished: {}", status)) + } else { + None + }; + let _ = cm + .update_context(job_id, |ctx| { + let _ = ctx.transition_to(target, reason); + }) + .await; + } + let mut msg = IncomingMessage::new( route.channel.clone(), route.user_id.clone(), @@ -121,6 +157,62 @@ pub fn spawn_job_monitor( }) } +/// Lightweight watcher that only transitions ContextManager state on job +/// completion. Used when monitor routing metadata is absent (no channel to +/// inject messages into) but we still need to free the `max_jobs` slot. +pub fn spawn_completion_watcher( + job_id: Uuid, + mut event_rx: broadcast::Receiver<(Uuid, SseEvent)>, + context_manager: Arc, +) -> JoinHandle<()> { + let short_id = job_id.to_string()[..8].to_string(); + + tokio::spawn(async move { + loop { + match event_rx.recv().await { + Ok((ev_job_id, SseEvent::JobResult { status, .. })) if ev_job_id == job_id => { + let target = if status == "completed" { + JobState::Completed + } else { + JobState::Failed + }; + let reason = if status != "completed" { + Some(format!("Container finished: {}", status)) + } else { + None + }; + let _ = context_manager + .update_context(job_id, |ctx| { + let _ = ctx.transition_to(target, reason); + }) + .await; + tracing::debug!( + job_id = %short_id, + status = %status, + "Completion watcher exiting (job finished)" + ); + break; + } + Ok(_) => {} + Err(broadcast::error::RecvError::Lagged(n)) => { + tracing::warn!( + job_id = %short_id, + skipped = n, + "Completion watcher lagged" + ); + } + Err(broadcast::error::RecvError::Closed) => { + tracing::debug!( + job_id = %short_id, + "Broadcast channel closed, stopping completion watcher" + ); + break; + } + } + } + }) +} + #[cfg(test)] mod tests { use super::*; @@ -294,4 +386,139 @@ mod tests { let msg = IncomingMessage::new("monitor", "system", "test").into_internal(); assert!(msg.is_internal); } + + // === Regression: fire-and-forget sandbox jobs must transition out of InProgress === + // Before this fix, spawn_job_monitor only forwarded SSE messages but never + // updated ContextManager. Background sandbox jobs stayed InProgress forever, + // permanently consuming a max_jobs slot. + + #[tokio::test] + async fn test_monitor_transitions_context_on_completion() { + use crate::context::{ContextManager, JobState}; + + let cm = Arc::new(ContextManager::new(5)); + let job_id = Uuid::new_v4(); + cm.register_sandbox_job(job_id, "user-1", "Build app", "desc") + .await + .unwrap(); + + let (event_tx, _) = broadcast::channel::<(Uuid, SseEvent)>(16); + let (inject_tx, mut inject_rx) = mpsc::channel::(16); + + let handle = spawn_job_monitor_with_context( + job_id, + event_tx.subscribe(), + inject_tx, + test_route(), + Some(Arc::clone(&cm)), + ); + + // Send completion event + event_tx + .send(( + job_id, + SseEvent::JobResult { + job_id: job_id.to_string(), + status: "completed".to_string(), + session_id: None, + fallback_deliverable: None, + }, + )) + .unwrap(); + + // Drain the injected message + let _ = tokio::time::timeout(std::time::Duration::from_secs(1), inject_rx.recv()).await; + + // Wait for monitor to exit + tokio::time::timeout(std::time::Duration::from_secs(1), handle) + .await + .expect("monitor should exit") + .expect("monitor should not panic"); + + // Job should now be Completed, not InProgress + let ctx = cm.get_context(job_id).await.unwrap(); + assert_eq!(ctx.state, JobState::Completed); + } + + #[tokio::test] + async fn test_monitor_transitions_context_on_failure() { + use crate::context::{ContextManager, JobState}; + + let cm = Arc::new(ContextManager::new(5)); + let job_id = Uuid::new_v4(); + cm.register_sandbox_job(job_id, "user-1", "Build app", "desc") + .await + .unwrap(); + + let (event_tx, _) = broadcast::channel::<(Uuid, SseEvent)>(16); + let (inject_tx, mut inject_rx) = mpsc::channel::(16); + + let handle = spawn_job_monitor_with_context( + job_id, + event_tx.subscribe(), + inject_tx, + test_route(), + Some(Arc::clone(&cm)), + ); + + // Send failure event + event_tx + .send(( + job_id, + SseEvent::JobResult { + job_id: job_id.to_string(), + status: "failed".to_string(), + session_id: None, + fallback_deliverable: None, + }, + )) + .unwrap(); + + let _ = tokio::time::timeout(std::time::Duration::from_secs(1), inject_rx.recv()).await; + tokio::time::timeout(std::time::Duration::from_secs(1), handle) + .await + .expect("monitor should exit") + .expect("monitor should not panic"); + + let ctx = cm.get_context(job_id).await.unwrap(); + assert_eq!(ctx.state, JobState::Failed); + } + + // === Regression: completion watcher (no route metadata) === + // When monitor_route_from_ctx() returns None, spawn_completion_watcher + // must still transition the job so the max_jobs slot is freed. + + #[tokio::test] + async fn test_completion_watcher_transitions_on_result() { + use crate::context::{ContextManager, JobState}; + + let cm = Arc::new(ContextManager::new(5)); + let job_id = Uuid::new_v4(); + cm.register_sandbox_job(job_id, "user-1", "Build app", "desc") + .await + .unwrap(); + + let (event_tx, _) = broadcast::channel::<(Uuid, SseEvent)>(16); + let handle = spawn_completion_watcher(job_id, event_tx.subscribe(), Arc::clone(&cm)); + + event_tx + .send(( + job_id, + SseEvent::JobResult { + job_id: job_id.to_string(), + status: "completed".to_string(), + session_id: None, + fallback_deliverable: None, + }, + )) + .unwrap(); + + tokio::time::timeout(std::time::Duration::from_secs(1), handle) + .await + .expect("watcher should exit") + .expect("watcher should not panic"); + + let ctx = cm.get_context(job_id).await.unwrap(); + assert_eq!(ctx.state, JobState::Completed); + } } diff --git a/src/agent/routine.rs b/src/agent/routine.rs index 7d87bd9a..2178db0c 100644 --- a/src/agent/routine.rs +++ b/src/agent/routine.rs @@ -688,16 +688,36 @@ pub fn content_hash(content: &str) -> u64 { hasher.finish() } +/// Normalize a cron expression to the 7-field format expected by the `cron` crate. +/// +/// The `cron` crate requires: `sec min hour day-of-month month day-of-week year`. +/// Standard cron uses 5 fields: `min hour day-of-month month day-of-week`. +/// This function auto-expands: +/// - 5-field → prepend `0` (seconds) and append `*` (year) +/// - 6-field → append `*` (year) +/// - 7-field → pass through unchanged +pub fn normalize_cron_expression(schedule: &str) -> String { + let trimmed = schedule.trim(); + let fields: Vec<&str> = trimmed.split_whitespace().collect(); + match fields.len() { + 5 => format!("0 {} *", trimmed), + 6 => format!("{} *", trimmed), + _ => trimmed.to_string(), + } +} + /// Parse a cron expression and compute the next fire time from now. /// +/// Accepts standard 5-field, 6-field, or 7-field cron expressions (auto-normalized). /// When `timezone` is provided and valid, the schedule is evaluated in that /// timezone and the result is converted back to UTC. Otherwise UTC is used. pub fn next_cron_fire( schedule: &str, timezone: Option<&str>, ) -> Result>, RoutineError> { + let normalized = normalize_cron_expression(schedule); let cron_schedule = - cron::Schedule::from_str(schedule).map_err(|e| RoutineError::InvalidCron { + cron::Schedule::from_str(&normalized).map_err(|e| RoutineError::InvalidCron { reason: e.to_string(), })?; if let Some(tz) = timezone.and_then(crate::timezone::parse_timezone) { @@ -878,6 +898,7 @@ mod tests { use crate::agent::routine::{ FullJobPermissionMode, MAX_TOOL_ROUNDS_LIMIT, RoutineAction, RoutineGuardrails, RunStatus, Trigger, content_hash, describe_cron, effective_full_job_tool_permissions, next_cron_fire, + normalize_cron_expression, }; #[test] @@ -1157,6 +1178,55 @@ mod tests { assert_eq!(Trigger::Manual.type_tag(), "manual"); } + #[test] + fn test_normalize_cron_5_field() { + // Standard cron: min hour dom month dow + assert_eq!(normalize_cron_expression("0 9 * * 1"), "0 0 9 * * 1 *"); + assert_eq!( + normalize_cron_expression("0 9 * * MON-FRI"), + "0 0 9 * * MON-FRI *" + ); + } + + #[test] + fn test_normalize_cron_6_field() { + // 6-field: sec min hour dom month dow + assert_eq!( + normalize_cron_expression("0 0 9 * * MON-FRI"), + "0 0 9 * * MON-FRI *" + ); + } + + #[test] + fn test_normalize_cron_7_field_passthrough() { + // Already 7-field: no change + assert_eq!( + normalize_cron_expression("0 0 9 * * MON-FRI *"), + "0 0 9 * * MON-FRI *" + ); + } + + #[test] + fn test_next_cron_fire_5_field_accepted() { + // Standard 5-field cron should now work through normalization + let result = next_cron_fire("0 9 * * 1", None); + assert!( + result.is_ok(), + "5-field cron should be accepted: {result:?}" + ); + assert!(result.unwrap().is_some()); + } + + #[test] + fn test_next_cron_fire_5_field_with_timezone() { + let result = next_cron_fire("0 9 * * MON-FRI", Some("America/New_York")); + assert!( + result.is_ok(), + "5-field cron with timezone should be accepted: {result:?}" + ); + assert!(result.unwrap().is_some()); + } + #[test] fn test_action_lightweight_backward_compat_no_use_tools() { // Simulate old DB record without use_tools field diff --git a/src/agent/self_repair.rs b/src/agent/self_repair.rs index db491194..4e58cb15 100644 --- a/src/agent/self_repair.rs +++ b/src/agent/self_repair.rs @@ -66,6 +66,7 @@ pub trait SelfRepair: Send + Sync { /// Default self-repair implementation. pub struct DefaultSelfRepair { context_manager: Arc, + /// Jobs in `InProgress` longer than this are treated as stuck. stuck_threshold: Duration, max_repair_attempts: u32, store: Option>, @@ -111,15 +112,58 @@ impl DefaultSelfRepair { #[async_trait] impl SelfRepair for DefaultSelfRepair { async fn detect_stuck_jobs(&self) -> Vec { - let stuck_ids = self.context_manager.find_stuck_jobs().await; + let stuck_ids = self + .context_manager + .find_stuck_jobs_with_threshold(Some(self.stuck_threshold)) + .await; let mut stuck_jobs = Vec::new(); for job_id in stuck_ids { if let Ok(ctx) = self.context_manager.get_context(job_id).await - && ctx.state == JobState::Stuck + && matches!(ctx.state, JobState::Stuck | JobState::InProgress) { - // Measure stuck_duration from the most recent Stuck transition, - // not from started_at (which reflects when the job first ran). + // InProgress jobs detected by threshold need to be transitioned + // to Stuck before they can be repaired (attempt_recovery requires + // Stuck state). These jobs already passed the threshold check in + // find_stuck_jobs_with_threshold, so skip the duration filter below. + let just_transitioned = ctx.state == JobState::InProgress; + if just_transitioned { + let reason = "exceeded stuck_threshold"; + let transition = self + .context_manager + .update_context(job_id, |ctx| ctx.mark_stuck(reason)) + .await; + match transition { + Ok(Ok(())) => {} + Ok(Err(e)) => { + tracing::warn!( + job = %job_id, + "Failed to mark InProgress job as Stuck: {}", + e + ); + continue; + } + Err(e) => { + tracing::warn!( + job = %job_id, + "Failed to transition InProgress job to Stuck: {}", + e + ); + continue; + } + } + } + + // Re-fetch context after potential InProgress->Stuck transition + // so that stuck_since picks up the new transition timestamp. + let ctx = match self.context_manager.get_context(job_id).await { + Ok(c) => c, + Err(_) => continue, + }; + + // Use the timestamp of the most recent Stuck transition, not started_at. + // A job that ran for hours before becoming stuck should not immediately + // exceed the threshold — we measure from when it actually became stuck. let stuck_since = ctx .transitions .iter() @@ -134,8 +178,10 @@ impl SelfRepair for DefaultSelfRepair { }) .unwrap_or_default(); - // Only report jobs that have been stuck long enough - if stuck_duration < self.stuck_threshold { + // Only report already-Stuck jobs that have been stuck long enough. + // Jobs just transitioned from InProgress skip this check — they + // were already vetted by find_stuck_jobs_with_threshold. + if !just_transitioned && stuck_duration < self.stuck_threshold { continue; } @@ -163,10 +209,17 @@ impl SelfRepair for DefaultSelfRepair { }); } - // Try to recover the job + // Try to recover the job. + // If the job is still InProgress (detected via stuck_threshold), transition + // it to Stuck first so that attempt_recovery() can move it back to InProgress. let result = self .context_manager - .update_context(job.job_id, |ctx| ctx.attempt_recovery()) + .update_context(job.job_id, |ctx| { + if ctx.state == JobState::InProgress { + ctx.transition_to(JobState::Stuck, Some("exceeded stuck_threshold".into()))?; + } + ctx.attempt_recovery() + }) .await; match result { @@ -489,6 +542,82 @@ mod tests { ); } + #[tokio::test] + async fn detect_and_repair_in_progress_job_via_threshold() { + let cm = Arc::new(ContextManager::new(10)); + let job_id = cm.create_job("Long running", "desc").await.unwrap(); + + // Transition to InProgress. + cm.update_context(job_id, |ctx| ctx.transition_to(JobState::InProgress, None)) + .await + .unwrap() + .unwrap(); + + // Backdate started_at to simulate a job running for 10 minutes. + cm.update_context(job_id, |ctx| { + ctx.started_at = Some(Utc::now() - chrono::Duration::seconds(600)); + }) + .await + .unwrap(); + + // Use a 5-minute threshold so the 10-minute job is detected. + let repair = DefaultSelfRepair::new(Arc::clone(&cm), Duration::from_secs(300), 3); + + // detect_stuck_jobs should find it and transition InProgress -> Stuck. + let stuck = repair.detect_stuck_jobs().await; + assert_eq!(stuck.len(), 1); + assert_eq!(stuck[0].job_id, job_id); + + // After detection the job should now be in Stuck state. + let ctx = cm.get_context(job_id).await.unwrap(); + assert_eq!(ctx.state, JobState::Stuck); + + // Repair should recover it: Stuck -> InProgress. + let result = repair.repair_stuck_job(&stuck[0]).await.unwrap(); + assert!( + matches!(result, RepairResult::Success { .. }), + "Expected Success, got: {:?}", + result + ); + + // Job should be back to InProgress after recovery. + let ctx = cm.get_context(job_id).await.unwrap(); + assert_eq!(ctx.state, JobState::InProgress); + } + + #[tokio::test] + async fn detect_broken_tools_returns_empty_without_store() { + let cm = Arc::new(ContextManager::new(10)); + let repair = DefaultSelfRepair::new(cm, Duration::from_secs(60), 3); + + // No store configured, should return empty. + let broken = repair.detect_broken_tools().await; + assert!(broken.is_empty()); + } + + #[tokio::test] + async fn repair_broken_tool_returns_manual_without_builder() { + let cm = Arc::new(ContextManager::new(10)); + let repair = DefaultSelfRepair::new(cm, Duration::from_secs(60), 3); + + let broken = BrokenTool { + name: "test-tool".to_string(), + failure_count: 10, + last_error: Some("crash".to_string()), + first_failure: Utc::now(), + last_failure: Utc::now(), + last_build_result: None, + repair_attempts: 0, + }; + + let result = repair.repair_broken_tool(&broken).await.unwrap(); + assert!( + matches!(result, RepairResult::ManualRequired { .. }), + "Expected ManualRequired without builder, got: {:?}", + result + ); + } + #[tokio::test] async fn detect_stuck_jobs_filters_by_threshold() { let cm = Arc::new(ContextManager::new(10)); @@ -581,39 +710,6 @@ mod tests { ); } - #[tokio::test] - async fn detect_broken_tools_returns_empty_without_store() { - let cm = Arc::new(ContextManager::new(10)); - let repair = DefaultSelfRepair::new(cm, Duration::from_secs(60), 3); - - // No store configured, should return empty. - let broken = repair.detect_broken_tools().await; - assert!(broken.is_empty()); - } - - #[tokio::test] - async fn repair_broken_tool_returns_manual_without_builder() { - let cm = Arc::new(ContextManager::new(10)); - let repair = DefaultSelfRepair::new(cm, Duration::from_secs(60), 3); - - let broken = BrokenTool { - name: "test-tool".to_string(), - failure_count: 10, - last_error: Some("crash".to_string()), - first_failure: Utc::now(), - last_failure: Utc::now(), - last_build_result: None, - repair_attempts: 0, - }; - - let result = repair.repair_broken_tool(&broken).await.unwrap(); - assert!( - matches!(result, RepairResult::ManualRequired { .. }), - "Expected ManualRequired without builder, got: {:?}", - result - ); - } - /// Mock SoftwareBuilder that returns a successful build result. struct MockBuilder { build_count: std::sync::atomic::AtomicU32, diff --git a/src/agent/thread_ops.rs b/src/agent/thread_ops.rs index e8b8d09a..0fb968f1 100644 --- a/src/agent/thread_ops.rs +++ b/src/agent/thread_ops.rs @@ -939,6 +939,7 @@ impl Agent { JobContext::with_user(&message.user_id, "chat", "Interactive chat session") .with_requester_id(&message.sender_id); job_ctx.http_interceptor = self.deps.http_interceptor.clone(); + job_ctx.metadata = crate::agent::agent_loop::chat_tool_execution_metadata(message); // Prefer a valid timezone from the approval message, fall back to the // resolved timezone stored when the approval was originally requested. let tz_candidate = message diff --git a/src/app.rs b/src/app.rs index c6892477..df246458 100644 --- a/src/app.rs +++ b/src/app.rs @@ -694,7 +694,11 @@ impl AppBuilder { // Post-init validation: if a non-nearai backend was selected but // credentials were never resolved (deferred resolution found no keys), // fail early with a clear error instead of a confusing runtime failure. - if self.config.llm.backend != "nearai" && self.config.llm.provider.is_none() { + if self.config.llm.backend != "nearai" + && self.config.llm.backend != "bedrock" + && self.config.llm.backend != "openai_codex" + && self.config.llm.provider.is_none() + { let backend = &self.config.llm.backend; anyhow::bail!( "LLM_BACKEND={backend} is configured but no credentials were found. \ @@ -723,6 +727,17 @@ impl AppBuilder { dev_loaded_tool_names, ) = self.init_extensions(&tools, &hooks).await?; + // Load bootstrap-completed flag from settings so that existing users + // who already completed onboarding don't re-get bootstrap injection. + if let Some(ref ws) = workspace { + let toml_path = crate::settings::Settings::default_toml_path(); + if let Ok(Some(settings)) = crate::settings::Settings::load_toml(&toml_path) + && settings.profile_onboarding_completed + { + ws.mark_bootstrap_completed(); + } + } + // Seed workspace and backfill embeddings if let Some(ref ws) = workspace { // Import workspace files from disk FIRST if WORKSPACE_IMPORT_DIR is set. diff --git a/src/channels/wasm/wrapper.rs b/src/channels/wasm/wrapper.rs index 8f0c9db4..be7768d0 100644 --- a/src/channels/wasm/wrapper.rs +++ b/src/channels/wasm/wrapper.rs @@ -3314,6 +3314,7 @@ mod tests { use std::sync::Arc; use crate::channels::Channel; + use crate::channels::OutgoingResponse; use crate::channels::wasm::capabilities::ChannelCapabilities; use crate::channels::wasm::runtime::{ PreparedChannelModule, WasmChannelRuntime, WasmChannelRuntimeConfig, @@ -3401,6 +3402,16 @@ mod tests { assert!(channel.health_check().await.is_err()); } + #[tokio::test] + async fn test_broadcast_delegates_to_call_on_broadcast() { + let channel = create_test_channel(); + // With `component: None`, call_on_broadcast short-circuits to Ok(()). + let result = channel + .broadcast("146032821", OutgoingResponse::text("hello")) + .await; + assert!(result.is_ok()); + } + #[tokio::test] async fn test_execute_poll_no_wasm_returns_empty() { // When there's no WASM module (None component), execute_poll diff --git a/src/channels/web/server.rs b/src/channels/web/server.rs index 501852d4..169bb0bf 100644 --- a/src/channels/web/server.rs +++ b/src/channels/web/server.rs @@ -344,6 +344,7 @@ pub async fn start_server( .route("/", get(index_handler)) .route("/style.css", get(css_handler)) .route("/app.js", get(js_handler)) + .route("/theme-init.js", get(theme_init_handler)) .route("/favicon.ico", get(favicon_handler)) .route("/i18n/index.js", get(i18n_index_handler)) .route("/i18n/en.js", get(i18n_en_handler)) @@ -465,6 +466,16 @@ async fn js_handler() -> impl IntoResponse { ) } +async fn theme_init_handler() -> impl IntoResponse { + ( + [ + (header::CONTENT_TYPE, "application/javascript"), + (header::CACHE_CONTROL, "no-cache"), + ], + include_str!("static/theme-init.js"), + ) +} + async fn favicon_handler() -> impl IntoResponse { ( [ diff --git a/src/channels/web/static/app.js b/src/channels/web/static/app.js index 8b029068..e8e84132 100644 --- a/src/channels/web/static/app.js +++ b/src/channels/web/static/app.js @@ -1,5 +1,69 @@ // IronClaw Web Gateway - Client +// --- Theme Management (dark / light / system) --- +// Icon switching is handled by pure CSS via data-theme-mode on . + +function getSystemTheme() { + return window.matchMedia('(prefers-color-scheme: light)').matches ? 'light' : 'dark'; +} + +const VALID_THEME_MODES = { dark: true, light: true, system: true }; + +function getThemeMode() { + const stored = localStorage.getItem('ironclaw-theme'); + return (stored && VALID_THEME_MODES[stored]) ? stored : 'system'; +} + +function resolveTheme(mode) { + return mode === 'system' ? getSystemTheme() : mode; +} + +function applyTheme(mode) { + const resolved = resolveTheme(mode); + document.documentElement.setAttribute('data-theme', resolved); + document.documentElement.setAttribute('data-theme-mode', mode); + const titleKeys = { dark: 'theme.tooltipDark', light: 'theme.tooltipLight', system: 'theme.tooltipSystem' }; + const btn = document.getElementById('theme-toggle'); + if (btn) btn.title = (typeof I18n !== 'undefined' && titleKeys[mode]) ? I18n.t(titleKeys[mode]) : ('Theme: ' + mode); + const announce = document.getElementById('theme-announce'); + if (announce) announce.textContent = (typeof I18n !== 'undefined') ? I18n.t('theme.announce', { mode: mode }) : ('Theme: ' + mode); +} + +function toggleTheme() { + const cycle = { dark: 'light', light: 'system', system: 'dark' }; + const current = getThemeMode(); + const next = cycle[current] || 'dark'; + localStorage.setItem('ironclaw-theme', next); + applyTheme(next); +} + +// Apply theme immediately (FOUC prevention is done via inline script in , +// but we call again here to ensure tooltip is set after DOM is ready). +applyTheme(getThemeMode()); + +// Delay enabling theme transition to avoid flash on initial load. +requestAnimationFrame(function() { + requestAnimationFrame(function() { + document.body.classList.add('theme-transition'); + }); +}); + +// Listen for OS theme changes — only re-apply when in 'system' mode. +const mql = window.matchMedia('(prefers-color-scheme: light)'); +const onSchemeChange = function() { + if (getThemeMode() === 'system') { + applyTheme('system'); + } +}; +if (mql.addEventListener) { + mql.addEventListener('change', onSchemeChange); +} else if (mql.addListener) { + mql.addListener(onSchemeChange); +} + +// Bind theme toggle button (CSP-compliant — no inline onclick). +document.getElementById('theme-toggle').addEventListener('click', toggleTheme); + let token = ''; let eventSource = null; let logEventSource = null; @@ -100,6 +164,30 @@ document.getElementById('token-input').addEventListener('keydown', (e) => { if (e.key === 'Enter') authenticate(); }); +// --- Static element event bindings (CSP-compliant, no inline handlers) --- +document.getElementById('auth-connect-btn').addEventListener('click', () => authenticate()); +document.getElementById('restart-overlay').addEventListener('click', () => cancelRestart()); +document.getElementById('restart-close-btn').addEventListener('click', () => cancelRestart()); +document.getElementById('restart-cancel-btn').addEventListener('click', () => cancelRestart()); +document.getElementById('restart-confirm-btn').addEventListener('click', () => confirmRestart()); +document.getElementById('language-btn').addEventListener('click', () => toggleLanguageMenu()); +// Language option clicks handled by delegated data-action="switch-language" handler. +document.getElementById('restart-btn').addEventListener('click', () => triggerRestart()); +document.getElementById('thread-new-btn').addEventListener('click', () => createNewThread()); +document.getElementById('thread-toggle-btn').addEventListener('click', () => toggleThreadSidebar()); +document.getElementById('assistant-thread').addEventListener('click', () => switchToAssistant()); +document.getElementById('send-btn').addEventListener('click', () => sendMessage()); +document.getElementById('memory-edit-btn').addEventListener('click', () => startMemoryEdit()); +document.getElementById('memory-save-btn').addEventListener('click', () => saveMemoryEdit()); +document.getElementById('memory-cancel-btn').addEventListener('click', () => cancelMemoryEdit()); +document.getElementById('logs-server-level').addEventListener('change', function() { setServerLogLevel(this.value); }); +document.getElementById('logs-pause-btn').addEventListener('click', () => toggleLogsPause()); +document.getElementById('logs-clear-btn').addEventListener('click', () => clearLogs()); +document.getElementById('wasm-install-btn').addEventListener('click', () => installWasmExtension()); +document.getElementById('mcp-add-btn').addEventListener('click', () => addMcpServer()); +document.getElementById('skill-search-btn').addEventListener('click', () => searchClawHub()); +document.getElementById('skill-install-btn').addEventListener('click', () => installSkillFromForm()); + // Auto-authenticate from URL param or saved session (function autoAuth() { const params = new URLSearchParams(window.location.search); diff --git a/src/channels/web/static/i18n/en.js b/src/channels/web/static/i18n/en.js index cd57a400..de08c7db 100644 --- a/src/channels/web/static/i18n/en.js +++ b/src/channels/web/static/i18n/en.js @@ -24,6 +24,12 @@ I18n.register('en', { 'restart.progressSubtitle': 'Please wait for the process to restart...', 'restart.checkLogs': 'Check the Logs tab for details after restart completes.', + // Theme + 'theme.tooltipDark': 'Theme: Dark (click for Light)', + 'theme.tooltipLight': 'Theme: Light (click for System)', + 'theme.tooltipSystem': 'Theme: System (click for Dark)', + 'theme.announce': 'Theme: {mode}', + // Tabs 'tab.chat': 'Chat', 'tab.memory': 'Memory', diff --git a/src/channels/web/static/i18n/zh-CN.js b/src/channels/web/static/i18n/zh-CN.js index 028ff5fc..8bc6edd4 100644 --- a/src/channels/web/static/i18n/zh-CN.js +++ b/src/channels/web/static/i18n/zh-CN.js @@ -24,6 +24,12 @@ I18n.register('zh-CN', { 'restart.progressSubtitle': '请等待进程重启...', 'restart.checkLogs': '重启完成后，请查看日志标签页了解详情。', + // 主题 + 'theme.tooltipDark': '主题：深色（点击切换浅色）', + 'theme.tooltipLight': '主题：浅色（点击切换跟随系统）', + 'theme.tooltipSystem': '主题：跟随系统（点击切换深色）', + 'theme.announce': '主题：{mode}', + // 标签页 'tab.chat': '聊天', 'tab.memory': '记忆', diff --git a/src/channels/web/static/index.html b/src/channels/web/static/index.html index b342cb53..113d144e 100644 --- a/src/channels/web/static/index.html +++ b/src/channels/web/static/index.html @@ -25,6 +25,7 @@ integrity="sha384-pN9zSKOnTZwXRtYZAu0PBPEgR2B7DOC1aeLxQ33oJ0oy5iN1we6gm57xldM2irDG" crossorigin="anonymous" > + @@ -109,6 +110,18 @@ + +