Skip to content
LiveLeaLife logoLiveLeaLife
Skip to content
Training State
Whether the continuous training coordinator loop is currently running. Enabled=true means training is allowed; Running=true means the loop is actively ticking and launching training runs.
Stopped
enabled false
Success (Last 100)
Completion rate for the most recent 100 training outcomes. This will lag after changes; it improves as new runs complete successfully.
0%
0/0
Queue Pending
Pending training sources waiting to be executed. Queue sources are operator-enqueued prompts; curriculum sources are auto-seeded hosts/tasks.
0
curriculum 0 | hosts 0
Running Runs (Total)
Total active runs across the whole runtime. Training Max Active Runs applies only to training cycles. Control-plane runs (eval/canary/manual) are counted separately as non-training.
0
training 0/- | non-training 0
System
Derived system health from diag snapshot. Same canonical derivation used on Dashboard. Worker + scheduler + ollama signals.
...
worker down | queue depth 0

Live Training SourceExact source currently executing in the training loop. When curriculum fallback is On and queue is empty, this will show curriculum_fallback.

Confirms what is being trained right now and what will be picked next.

Selection Modequeue_pending means operator queue source. curriculum_fallback means queue is empty and fallback selected curriculum source.

none

Fallback Enabled (Live)Runtime toggle currently applied in the trainer process.

Off

Queue PendingPending operator-queued training sources.

0

Curriculum PendingPending curriculum sources eligible only when fallback is enabled and queue is empty.

0

Training Outcomes StorageTraining outcomes are appended as new rows and not rewritten by source selection.

Unknown

No active training cycle and no eligible next source preview.

Queue Training PromptsAdds new training sources to the operator queue. These will be executed by the training coordinator and used for learning/self-improvement signals (memory recall + memory upsert + outcome trace).

Create and enqueue custom training prompts while training is active.

Recent Training CyclesEach cycle corresponds to one training source being turned into a task + run, then finalized into an outcome. Use Error + Status to diagnose why training success is low.

showing 0

No cycles yet

Start training or queue prompts to create cycles.

Pending Training SourcesBacklog rows waiting in the training source queue. This makes Queue Pending fully inspectable instead of only showing a summary count.

queue 0/0 | curriculum 0/0

Queue Sources (Pending)

No pending queue sources.

Curriculum Sources (Pending)

No pending curriculum sources.

Runtime SettingsThese settings apply immediately (no restart) and control training behavior while runs are active.

Live applied values and editable selectors.

Applied Now (Live)Current runtime values already active on the running backend process.

Selectors match live values

Training-Only Runtime SettingsThese controls affect training loop behavior only and apply without restart.

Training Max Active RunsTraining-only cap: limits active training cycles, not total runtime runs.

-

Loop Interval (s)Delay between scheduler ticks when capacity is available.

-

Recent Host WindowHost dedupe window used to diversify training source selection.

-

Retry Budget / SourceMax failed attempts allowed per training source before disablement.

-

Default Pages TargetDefault page-count target only when prompt does not explicitly set one.

-

Curriculum FallbackWhether curriculum sources are allowed when operator queue is empty.

Off

Campaign Lock ModeWhen enabled, campaign queue selection is locked to keep training intake stable.

Off

All-Task Runtime Settings (Read-only)Global values shared by training and manually-created runs.

Global Max Concurrent RunsHard upper limit for all simultaneously running runs in the system.

-

Reserved Control SlotsSlots reserved for non-training control-plane work (self-improve/model-promotion/canary).

0

Effective Training CeilingDerived cap for training-only slots: Global Max Concurrent Runs minus Reserved Control Slots.

-

Running Split (Now)Real-time active run breakdown used to explain why total running can exceed the training-only cap.

training 0 | non-training 0

Controller Max Calls / RunHow many controller-model URL-pick calls are allowed per run.

-

Browser Headful (Global)Whether browser sessions render with visible UI windows.

Off

Browser Autostart (Global)Whether browser sessions are auto-launched for run execution.

Off

Change SelectorsDraft values you can edit before applying live runtime updates.

Training-only settings. Edit values below, then click Apply Settings. Global runtime caps remain read-only here.

Selector: Off
Toggle to change selector value
Selector: Off
Toggle to change selector value

Pending ChangesDifference between currently applied runtime values and your draft selectors.

No pending runtime setting changes.

Live SnapshotLive training + diagnostics values (auto-refreshing). Use this to confirm settings take effect and that training is making progress.

Auto-refreshing diagnostics state.

Model Update Progress

state none
window unavailableno success delta configured
Window collecting outcomesnext action: Continue successful runs to hit the next eval window.
Successes0
Watermark0
Next Target-
Live Applies0
Active -Active Controller Tag -Active Standard Task Model -Candidate -Last apply Last eval attempt Threshold reached

Last UpdatedWhen this panel last refreshed from live API diagnostics.

Last HeartbeatMost recent training coordinator heartbeat. If stale, the trainer loop may be stuck.

Latest CycleMost recent training cycle ID executed by the coordinator.

-

Latest Cycle StatusTerminal status of the latest cycle (running/completed/failed/cancelled).

-

Next Eval Due (success count)When total successful outcomes reach this number, promotion evaluation is due.

0

Last Eval AttemptMost recent promotion evaluation attempt timestamp.

Last Eval ResultLatest eval attempt outcome (triggered/blocked/completed/failed).

-

Eval Retry AtIf evaluation is blocked, this is the next scheduled retry.

Last ErrorLatest coordinator-level error code. This is not always a run failure; it can be a gate signal.

-

Oldest Pending SourceOldest queued training source waiting to run. Older timestamps indicate queue backlog.

Trace Coverage (diag)Share of recent outcomes with usable training trace payloads (used by self-improve/export).

0%

Diag Outcome WindowCanonical diag-snapshot outcome counters. Same values shown on Dashboard's Training Success Rate card.

0/0 (last 0)

Training viewfingerprint no-snapshotcache 0s / 0s ttl