let5see/clawdbot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: publish llm-task docs and harden tool

Browse Source
This commit is contained in:
Peter Steinberger
2026-01-24 01:44:36 +00:00
parent 00ae21bed2
commit 309fcc5321
14 changed files with 312 additions and 85 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
extensions/llm-task/README.md
View File

@@ -1,8 +1,10 @@
# LLM Task (plugin)
Adds an **optional** agent tool `llm-task` for running **JSON-only** LLM tasks (drafting, summarizing, classifying) with optional JSON Schema validation.
Adds an **optional** agent tool `llm-task` for running **JSON-only** LLM tasks
(drafting, summarizing, classifying) with optional JSON Schema validation.
This is designed to be called from workflow engines (e.g. Lobster via `clawd.invoke --each`) without adding new Clawdbot code per workflow.
Designed to be called from workflow engines (for example, Lobster via
`clawd.invoke --each`) without adding new Clawdbot code per workflow.
## Enable
@@ -44,6 +46,7 @@ This is designed to be called from workflow engines (e.g. Lobster via `clawd.inv
"config": {
"defaultProvider": "openai-codex",
"defaultModel": "gpt-5.2",
"defaultAuthProfileId": "main",
"allowedModels": ["openai-codex/gpt-5.2"],
"maxTokens": 800,
"timeoutMs": 30000
@@ -54,7 +57,8 @@ This is designed to be called from workflow engines (e.g. Lobster via `clawd.inv
}
```
`allowedModels` is an allowlist of `provider/model` strings. If set, any request outside the list is rejected.
`allowedModels` is an allowlist of `provider/model` strings. If set, any request
outside the list is rejected.
## Tool API
@@ -72,15 +76,22 @@ This is designed to be called from workflow engines (e.g. Lobster via `clawd.inv
### Output
Returns `details.json` containing the parsed JSON (and validates against `schema` when provided).
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).
- Side effects should be handled outside this tool (e.g. approvals in Lobster) before calling tools that send messages/emails.
- 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 Clawdbot internal modules (the embedded agent runner). It is intended to ship as a **bundled** Clawdbot extension (like `lobster`) and be enabled via `plugins.entries` + tool allowlists.
This extension depends on Clawdbot internal modules (the embedded agent runner).
It is intended to ship as a **bundled** Clawdbot extension (like `lobster`) and
be enabled via `plugins.entries` + tool allowlists.
It is **not** currently designed to be copied into `~/.clawdbot/extensions` as a standalone plugin directory.
It is **not** currently designed to be copied into
`~/.clawdbot/extensions` as a standalone plugin directory.

4
extensions/llm-task/index.ts
View File

@@ -1,5 +1,7 @@
import type { ClawdbotPluginApi } from "../../src/plugins/types.js";
import { createLlmTaskTool } from "./src/llm-task-tool.js";
export default function (api: any) {
export default function register(api: ClawdbotPluginApi) {
api.registerTool(createLlmTaskTool(api), { optional: true });
}

10
extensions/llm-task/package.json
View File

@@ -1,7 +1,11 @@
{
"name": "@clawdbot/llm-task",
"private": true,
"version": "2026.1.23",
"type": "module",
"main": "index.ts",
"version": "0.0.0"
"description": "Clawdbot JSON-only LLM task plugin",
"clawdbot": {
"extensions": [
"./index.ts"
]
}
}

21
extensions/llm-task/src/llm-task-tool.test.ts
View File

@@ -39,6 +39,16 @@ describe("llm-task tool (json-only)", () => {
expect((res as any).details.json).toEqual({ foo: "bar" });
});
it("strips fenced json", async () => {
(runEmbeddedPiAgent as any).mockResolvedValueOnce({
meta: {},
payloads: [{ text: "```json\n{\"ok\":true}\n```" }],
});
const tool = createLlmTaskTool(fakeApi() as any);
const res = await tool.execute("id", { prompt: "return ok" });
expect((res as any).details.json).toEqual({ ok: true });
});
it("validates schema", async () => {
(runEmbeddedPiAgent as any).mockResolvedValueOnce({
meta: {},
@@ -93,4 +103,15 @@ describe("llm-task tool (json-only)", () => {
/not allowed/i,
);
});
it("disables tools for embedded run", async () => {
(runEmbeddedPiAgent as any).mockResolvedValueOnce({
meta: {},
payloads: [{ text: JSON.stringify({ ok: true }) }],
});
const tool = createLlmTaskTool(fakeApi() as any);
await tool.execute("id", { prompt: "x" });
const call = (runEmbeddedPiAgent as any).mock.calls[0]?.[0];
expect(call.disableTools).toBe(true);
});
});

116
extensions/llm-task/src/llm-task-tool.ts
View File

@@ -12,7 +12,7 @@ import { Type } from "@sinclair/typebox";
import type { ClawdbotPluginApi } from "../../../src/plugins/types.js";
type RunEmbeddedPiAgentFn = (params: any) => Promise<any>;
type RunEmbeddedPiAgentFn = (params: Record<string, unknown>) => Promise<unknown>;
async function loadRunEmbeddedPiAgent(): Promise<RunEmbeddedPiAgentFn> {
// Source checkout (tests/dev)
@@ -33,7 +33,7 @@ async function loadRunEmbeddedPiAgent(): Promise<RunEmbeddedPiAgentFn> {
function stripCodeFences(s: string): string {
const trimmed = s.trim();
const m = trimmed.match(/^```(?:json)?s*([sS]*?)s*```$/i);
const m = trimmed.match(/^```(?:json)?\s*([\s\S]*?)\s*```$/i);
if (m) return (m[1] ?? "").trim();
return trimmed;
}
@@ -42,7 +42,7 @@ function collectText(payloads: Array<{ text?: string; isError?: boolean }> | und
const texts = (payloads ?? [])
.filter((p) => !p.isError && typeof p.text === "string")
.map((p) => p.text ?? "");
return texts.join("n").trim();
return texts.join("\n").trim();
}
function toModelKey(provider?: string, model?: string): string | undefined {
@@ -135,6 +135,12 @@ export function createLlmTaskTool(api: ClawdbotPluginApi) {
};
const input = (params as any).input as unknown;
let inputJson: string;
try {
inputJson = JSON.stringify(input ?? null, null, 2);
} catch {
throw new Error("input must be JSON-serializable");
}
const system = [
"You are a JSON-only function.",
@@ -144,57 +150,69 @@ export function createLlmTaskTool(api: ClawdbotPluginApi) {
"Do not call tools.",
].join(" ");
const fullPrompt = `${system}nnTASK:n${prompt}nnINPUT_JSON:n${JSON.stringify(input ?? null, null, 2)}n`;
const fullPrompt = `${system}\n\nTASK:\n${prompt}\n\nINPUT_JSON:\n${inputJson}\n`;
const tmpDir = await fs.mkdtemp(path.join(os.tmpdir(), "clawdbot-llm-task-"));
const sessionId = `llm-task-${Date.now()}`;
const sessionFile = path.join(tmpDir, "session.json");
const runEmbeddedPiAgent = await loadRunEmbeddedPiAgent();
const result = await runEmbeddedPiAgent({
sessionId,
sessionFile,
workspaceDir: api.config?.agents?.defaults?.workspace ?? process.cwd(),
config: api.config,
prompt: fullPrompt,
timeoutMs,
runId: `llm-task-${Date.now()}`,
provider,
model,
authProfileId,
authProfileIdSource: authProfileId ? "user" : "auto",
streamParams,
});
const text = collectText((result as any).payloads);
if (!text) throw new Error("LLM returned empty output");
const raw = stripCodeFences(text);
let parsed: unknown;
let tmpDir: string | null = null;
try {
parsed = JSON.parse(raw);
} catch {
throw new Error("LLM returned invalid JSON");
}
tmpDir = await fs.mkdtemp(path.join(os.tmpdir(), "clawdbot-llm-task-"));
const sessionId = `llm-task-${Date.now()}`;
const sessionFile = path.join(tmpDir, "session.json");
const schema = (params as any).schema as unknown;
if (schema && typeof schema === "object") {
const ajv = new Ajv({ allErrors: true, strict: false });
const validate = ajv.compile(schema as any);
const ok = validate(parsed);
if (!ok) {
const msg =
validate.errors?.map((e) => `${e.instancePath || "<root>"} ${e.message || "invalid"}`).join("; ") ??
"invalid";
throw new Error(`LLM JSON did not match schema: ${msg}`);
const runEmbeddedPiAgent = await loadRunEmbeddedPiAgent();
const result = await runEmbeddedPiAgent({
sessionId,
sessionFile,
workspaceDir: api.config?.agents?.defaults?.workspace ?? process.cwd(),
config: api.config,
prompt: fullPrompt,
timeoutMs,
runId: `llm-task-${Date.now()}`,
provider,
model,
authProfileId,
authProfileIdSource: authProfileId ? "user" : "auto",
streamParams,
disableTools: true,
});
const text = collectText((result as any).payloads);
if (!text) throw new Error("LLM returned empty output");
const raw = stripCodeFences(text);
let parsed: unknown;
try {
parsed = JSON.parse(raw);
} catch {
throw new Error("LLM returned invalid JSON");
}
const schema = (params as any).schema as unknown;
if (schema && typeof schema === "object" && !Array.isArray(schema)) {
const ajv = new Ajv({ allErrors: true, strict: false });
const validate = ajv.compile(schema as any);
const ok = validate(parsed);
if (!ok) {
const msg =
validate.errors?.map((e) => `${e.instancePath || "<root>"} ${e.message || "invalid"}`).join("; ") ??
"invalid";
throw new Error(`LLM JSON did not match schema: ${msg}`);
}
}
return {
content: [{ type: "text", text: JSON.stringify(parsed, null, 2) }],
details: { json: parsed, provider, model },
};
} finally {
if (tmpDir) {
try {
await fs.rm(tmpDir, { recursive: true, force: true });
} catch {
// ignore
}
}
}
return {
content: [{ type: "text", text: JSON.stringify(parsed, null, 2) }],
details: { json: parsed, provider, model },
};
},
};
}