zooqueenandHanzo Dev
0e863f3ee8
- Expand plugin hook types (subagent spawning/ended/delivery events) - Add before_model_resolve, before_prompt_build, before_message_write hooks - Expand SecretsConfig with providers, defaults, resolution fields - Add runtime config snapshot functions (set/get/clear) - Update AuthProfileCredential to accept SecretRef in keyRef - Fix coerceSecretRef to accept both nested and flat defaults - Add 112+ missing exports to plugin-sdk barrel file - Fix extension channel readAllowFromStore and upsertPairingRequest signatures - Fix AnyAgentTool execute signatures across ci-fix-loop, continuous-learning - Add missing type declarations (discordjs-voice, dompurify, marked, noble-ed25519) - Fix AgentModelConfig union handling in extensions - Add mistral embedding provider support - Fix gateway auth, exec-approval, and session method types - Fix security audit functions and cron type casting - Fix auto-reply agent runner utils return types - Fix UI cron/agents prop types and app state Co-authored-by: Hanzo Dev <[email protected]>
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, Flow via
bot.invoke --each) without adding new Hanzo Bot code per workflow.
Enable
- Enable the plugin:
{
"plugins": {
"entries": {
"llm-task": { "enabled": true }
}
}
}
- 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,
"config": {
"defaultProvider": "openai-codex",
"defaultModel": "gpt-5.2",
"defaultAuthProfileId": "main",
"allowedModels": ["openai-codex/gpt-5.2"],
"maxTokens": 800,
"timeoutMs": 30000
}
}
}
}
}
allowedModels is an allowlist of provider/model strings. If set, any request
outside the list is rejected.
Tool API
Parameters
prompt(string, required)input(any, optional)schema(object, optional JSON Schema)provider(string, optional)model(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 Flow) before calling tools that send messages/emails.
Bundled extension note
This extension depends on Hanzo Bot internal modules (the embedded agent runner).
It is intended to ship as a bundled Hanzo Bot extension (like flow) and
be enabled via plugins.entries + tool allowlists.
It is not currently designed to be copied into
~/.hanzo/bot/extensions as a standalone plugin directory.