LightWorker
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LIGHTWORKER_HOME | No | The directory where LightWorker stores its SQLite database, worktrees, and state. Defaults to the platform-specific state directory (e.g., %LOCALAPPDATA%\LightWorker on Windows or ${XDG_STATE_HOME:-$HOME/.local/state}/lightworker on macOS/Linux). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| orchestrateC | Queue a bounded Lead Codex planning run. It creates a dependency-aware task graph and automatically dispatches allowed child tasks. |
| delegate_taskB | Queue one bounded worker task. Explore/review are read-only; execute uses an isolated git worktree and may require approval. |
| delegate_batchB | Queue up to the configured limit of already-decomposed worker tasks. |
| get_taskB | Get one task, its dependencies, and structured result when available. |
| claim_native_dispatchesB | Claim queued Codex-native tickets for this current host. For every ticket, call spawn_agent, then native_subagent_started. This is the real native bridge; it never runs codex exec as a fallback. |
| native_subagent_startedC | Acknowledge that the current Codex host spawned a native subagent for a claimed LightWorker ticket. |
| native_subagent_eventB | Write a bounded native-thread progress event and refresh its dispatch lease while waiting with wait_threads. |
| native_subagent_completedC | Persist the terminal result returned by a native Codex subagent after wait_threads completes. |
| get_task_treeB | List every task belonging to an orchestration root. |
| list_tasksA | List recent tasks, optionally filtered by status. |
| wait_tasksA | Wait up to 55 seconds for tasks to reach a terminal or approval state. |
| get_eventsA | Read append-only task events after an event cursor. |
| get_cache_metricsA | Return materialized cold/warm cache telemetry and target status without scanning event JSON. |
| approve_taskB | Release one task that is awaiting approval into the execution queue. |
| cancel_taskA | Cancel a queued or active task and terminate its worker process tree. |
| retry_fallbackA | Clone a failed read-only task onto its configured fallback gateway. Never falls back automatically. |
| escalate_taskA | Create one budgeted read-only retry using a deeper worker profile. The original task remains unchanged. |
| doctorA | Check local Codex, proxy ports, state paths, model allowlist, and concurrency. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 18 tools
Most tools have a distinct resource/action: delegation (delegate_task, delegate_batch, orchestrate), task lifecycle (approve/cancel/retry/escalate), and native subagent lifecycle are separated. Boundaries are mostly clear, though retry_fallback vs escalate_task and the multi-step native_* flow require careful reading.
Names are overwhelmingly snake_case and follow verb_noun for most operations (get_task, list_tasks, cancel_task, delegate_batch). Exceptions like doctor, orchestrate, and the native_subagent_* resource_event pattern are minor deviations rather than chaotic.
18 tools is slightly above the typical 3-15 range, but the orchestration domain is broad and each tool maps to a distinct lifecycle step or diagnostic. It is heavy but not obviously bloated.
The surface covers delegation, orchestration, task inspection/waiting/events, approval, cancellation, fallback/escalation, diagnostics, cache metrics, and native subagent lifecycle. Minor gaps like explicit approval rejection or lease release are workaroundable, and some workflow references external host tools (spawn_agent, wait_threads).