mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-11-06 13:26:40 +00:00
Teknium
95505c60e9
The deferred tool_search catalog shows each tool's first sentence clipped to 60 chars, so lines like 'image_generate: Generate high-quality images from text prompts, or edit /…' hid that it edits with reference images on the user's configured model. An agent skipped it and called FAL directly with a hardcoded model. - catalog line cap 60 -> 80 (CATALOG_SUMMARY_MAX_CHARS); every built-in tool's first sentence now fits and leads with what it does - image_generate/video_generate say they use the configured model; image_generate says to use it rather than direct API calls/scripts - web_search/web_extract/browser_exec name when to use each other - drop a duplicated cronjob sentence and filler in skill_view/video_generate - regenerate tests/fixtures/prompt_surface
105 lines
4.1 KiB
Python
105 lines
4.1 KiB
Python
"""Agent-facing tool: respond to a native JS dialog captured by the CDP supervisor.
|
|
|
|
Response-only: the agent calls ``browser_dialog(action=...)`` for a dialog the
|
|
supervisor holds; with several queued, the error names the candidate ids. Gated on ``_browser_cdp_check`` so it
|
|
appears together with ``browser_cdp``. Design: ``website/docs/developer-guide/browser-supervisor.md``.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from typing import Any, Dict, Optional
|
|
|
|
from tools.browser_supervisor import SUPERVISOR_REGISTRY
|
|
from tools.registry import registry
|
|
|
|
BROWSER_DIALOG_SCHEMA: dict[str, Any] = {
|
|
"name": "browser_dialog",
|
|
"description": (
|
|
"Accept or dismiss a native JS dialog (alert/confirm/prompt) blocking the page.\n\n"
|
|
"**Workflow:** when a page is blocked by a native dialog the CDP "
|
|
"supervisor captured, call this tool with ``action='accept'`` or "
|
|
"``action='dismiss'``.\n\n"
|
|
"**Prompt dialogs:** pass ``prompt_text`` to supply the response "
|
|
"string. Ignored for alert/confirm/beforeunload.\n\n"
|
|
"**Multiple dialogs:** if more than one dialog is queued (rare — "
|
|
"happens when a second dialog fires while the first is still open), "
|
|
"pass ``dialog_id`` (the error lists the candidates) to disambiguate.\n\n"
|
|
"**Availability:** only present when a CDP endpoint is attached — "
|
|
"a local Chromium-family browser via ``/browser connect``, or "
|
|
"``browser.cdp_url`` in config.yaml."
|
|
),
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"action": {
|
|
"type": "string",
|
|
"enum": ["accept", "dismiss"],
|
|
"description": (
|
|
"'accept' clicks OK / returns the prompt text. "
|
|
"'dismiss' clicks Cancel / returns null from prompt(). "
|
|
"For ``beforeunload`` dialogs: 'accept' allows the "
|
|
"navigation, 'dismiss' keeps the page."
|
|
),
|
|
},
|
|
"prompt_text": {
|
|
"type": "string",
|
|
"description": (
|
|
"Response string for a ``prompt()`` dialog. Ignored for "
|
|
"other dialog types. Defaults to empty string."
|
|
),
|
|
},
|
|
"dialog_id": {
|
|
"type": "string",
|
|
"description": (
|
|
"Specific dialog to respond to, from "
|
|
"the candidate ids a previous call listed. Required "
|
|
"only when multiple dialogs are queued."
|
|
),
|
|
},
|
|
},
|
|
"required": ["action"],
|
|
},
|
|
}
|
|
|
|
|
|
def browser_dialog(
|
|
action: str,
|
|
prompt_text: Optional[str] = None,
|
|
dialog_id: Optional[str] = None,
|
|
task_id: Optional[str] = None,
|
|
) -> str:
|
|
"""Respond to a pending dialog on the active task's CDP supervisor."""
|
|
supervisor = SUPERVISOR_REGISTRY.get(task_id or "default")
|
|
if supervisor is None:
|
|
return json.dumps({
|
|
"success": False,
|
|
"error": (
|
|
"No CDP supervisor is attached to this task: no browser "
|
|
"session has been started yet. Call browser_exec or "
|
|
"/browser connect first."
|
|
),
|
|
})
|
|
result = supervisor.respond_to_dialog(action=action, prompt_text=prompt_text, dialog_id=dialog_id)
|
|
if result.get("ok"):
|
|
return json.dumps({"success": True, "action": action, "dialog": result.get("dialog", {})})
|
|
return json.dumps({"success": False, "error": result.get("error", "unknown error")})
|
|
|
|
|
|
def _browser_dialog_check() -> bool:
|
|
"""Gate: same as ``browser_cdp`` so the two tools appear/disappear together."""
|
|
from tools.browser_cdp_tool import _browser_cdp_check
|
|
|
|
return _browser_cdp_check()
|
|
|
|
|
|
registry.register(
|
|
name="browser_dialog",
|
|
toolset="browser-cdp",
|
|
schema=BROWSER_DIALOG_SCHEMA,
|
|
handler=lambda args, **kw: browser_dialog(action=args.get("action", ""), prompt_text=args.get("prompt_text"),
|
|
dialog_id=args.get("dialog_id"), task_id=kw.get("task_id")),
|
|
check_fn=_browser_dialog_check,
|
|
emoji="💬",
|
|
)
|