Files
openclaw/extensions/llm-task
Peter Steinberger 6192673da4 perf(doctor): delete the heavy doctor barrel and finish slimming enumeration (#120882)
* refactor(plugin-sdk): delete the heavy runtime-doctor barrel

Nothing may pull the state-db/kysely graph through a doctor barrel anymore.
The barrel's remaining heavy exports move to two narrow private-local
subpaths, each with a single purpose:

- doctor-repair-runtime: install-path diagnosis, plugin config removal, and
  state-database schema detect/repair (matrix doctor, voice-call lazy import)
- plugin-state-store-runtime: the sync keyed-store factory. It stays out of
  plugin-state-runtime because hot channel entrypoints import that at module
  load and opening a store pulls the state-database graph.

Doctor closures also stop pulling ssrf-runtime (fetch-guard + gateway net)
for two legacy private-network helpers that live in the lighter ssrf-policy
subpath: mattermost, nextcloud-talk, tlon, matrix.

The closure guard now forbids the two new heavy subpaths instead of the
deleted barrel, so the invariant keeps being enforced where it still applies.

* perf(doctor): keep heavy graphs out of every doctor closure

Doctor enumeration cold-loads each declaring plugin's contract closure, so
one heavy import in a closure is paid by the whole sweep. Four barrels were
still dragging unrelated graphs in for trivial helpers; each is repaired at
the leaf rather than by caching downstream:

- Legacy private-network config migration moves to a config leaf. It only
  reshapes records, but lived beside the SSRF runtime (DNS, proxy, logging),
  costing mattermost ~2.7s. ssrf-policy re-exports it, surface unchanged.
- Streaming config readers move to a leaf. They read two config keys, but
  streaming.ts also formats tool aggregates, pulling tool-display/logging/
  acp-core; that cost slack ~2.3s.
- signal took the channel-secret barrel for isRecord; the canonical plugin
  record guard is string-coerce-runtime (root AGENTS.md).
- llm-task took the provider-model barrel for parseModelRef, now a narrow
  model-ref-parse subpath.

Full doctor enumeration of all 42 declaring plugins, built mode:
legacy config rules 6668ms -> 1265ms, state migrations 184ms -> 127ms.
No plugin remains an outlier; the slowest is now ~380ms against a ~200ms floor.

Public export surfaces of every touched SDK subpath are byte-identical
(verified by diffing built module exports before/after); the API baseline
hashes move only because re-exported declarations emit differently.

The closure guard gains rules for each repaired barrel so the invariant
holds for future closures.

* fix(release): exclude new private-local declarations from the published package

Same pack-path rule as c41da3759f: private-local subpaths ship without d.ts.

* fix(doctor): repair the closure guard violations that break main

The landed guard fails on main: three closures import heavy barrels for one
symbol each. Two more surfaced once the guard learned about the provider-model
barrel. Each gets a narrow subpath at the leaf:

- telegram sent-message-cache + state-migrations took the session-store barrel
  (session accessor + state-db) for resolveStorePath -> session-store-paths
- discord thread-bindings.state took the channel-outbound barrel (reply
  pipeline + channel registry) for one identity write -> outbound-echo-runtime
- discord model-picker took the provider-model barrel for normalizeProviderId,
  which model-ref-parse now exposes beside parseModelRef

The guard also stops walking artifacts of plugins whose manifest declares no
doctor surface. Such a declaration gates the artifact off every enumeration
path exactly as resolvePluginDoctorContracts does, so its closure cost is never
paid; anthropic ("doctorContract": {}) was being held to a cost it cannot
incur. Absent declarations still load eagerly and stay enforced.

Side effect worth naming: discord's built doctor contract now loads again.
On main both discord and telegram fail to require in packaged builds (an
ESM-only transitive dep) and silently lose their repairs; this restores
discord and takes enumerated legacy config rules from 87 to 99. Telegram's
built artifact still pulls execa through dist chunking - a build-level defect
with a different owner, filed as follow-up.
2026-08-08 22:01:44 -07:00
..

LLM Task (plugin)

Adds an optional agent tool llm-task for running JSON-only LLM tasks (drafting, summarizing, classifying) with optional JSON Schema validation.

Designed to be called from workflow engines (for example, Lobster via openclaw.invoke --each) without adding new OpenClaw code per workflow.

Enable

  1. Enable the plugin:
{
  "plugins": {
    "entries": {
      "llm-task": { "enabled": true }
    }
  }
}
  1. Allowlist the tool (it is registered with optional: true):
{
  "agents": {
    "list": [
      {
        "id": "main",
        "tools": { "allow": ["llm-task"] }
      }
    ]
  }
}

Config (optional)

{
  "plugins": {
    "entries": {
      "llm-task": {
        "enabled": true,
        "llm": {
          "allowModelOverride": true,
          "allowedCompletionModels": ["openai/gpt-5.6-sol"],
          "allowAuthProfileOverride": true
        },
        "config": {
          "defaultProvider": "openai",
          "defaultModel": "gpt-5.6-sol",
          "defaultAuthProfileId": "main",
          "maxTokens": 800,
          "timeoutMs": 30000
        }
      }
    }
  }
}

The host-owned llm policy authorizes model/profile overrides. Its allowedCompletionModels restricts every completion, including the resolved agent default. Run openclaw doctor --fix once for entries created by older releases; Doctor grants the shipped selection permissions and moves legacy config.allowedModels values into llm.allowedCompletionModels without widening them.

Tool API

Parameters

  • prompt (string, required)
  • input (any, optional)
  • schema (object, optional JSON Schema)
  • provider (string, optional)
  • model (string, optional)
  • thinking (string, optional)
  • authProfileId (string, optional)
  • temperature (number, optional)
  • maxTokens (number, optional)
  • timeoutMs (number, optional)

Output

Returns details.json containing the parsed JSON (and validates against schema when provided).

Notes

  • The tool is JSON-only and instructs the model to output only JSON (no code fences, no commentary).
  • No tools are exposed to the model for this run.
  • Side effects should be handled outside this tool (for example, approvals in Lobster) before calling tools that send messages/emails.

Bundled extension note

This extension depends on OpenClaw internal modules (the embedded agent runner). It is intended to ship as a bundled OpenClaw extension (like lobster) and be enabled via plugins.entries + tool allowlists.

It is not currently designed to be copied into ~/.openclaw/extensions as a standalone plugin directory.