64646dda56
* feat(agent): read_preview — the desktop-gated tool that reads the in-app browser The agent could open the preview pane (open_preview) and read the embedded terminal (read_terminal), but the browser it had just opened was a black box — 'what does this page say?' had no answer. read_preview mirrors read_terminal end to end: HERMES_DESKTOP-gated via check_fn (zero schema footprint outside the GUI), dispatched through the same agent callback pattern, windowed with start/count so a long page pages instead of flooding context. * feat(gateway): preview.read blocking bridge Same lifecycle as terminal.read: the tool blocks on preview.read.request, the renderer answers preview.read.respond (allow_expired — a slow page extraction losing the 45s race must not surface a raw 4009), and a timeout emits preview.read.expire so late answers resolve quietly. * feat(desktop): the renderer serializes the active preview tab for the agent preview-reader.ts is the preview analog of the terminal's buffer registry: the URL pane registers a page reader (webview executeJavaScript → title + visible innerText) keyed by tab id; readActivePreview resolves the ACTIVE tab, windows the text (24k cap per read), and answers file/artifact tabs with identity plus a note pointing at the tool that reads that content directly. The gateway event handler answers preview.read.request beside terminal.read.request.
99 lines
3.5 KiB
Python
99 lines
3.5 KiB
Python
#!/usr/bin/env python3
|
|
"""Read the in-app browser / preview pane in the Hermes desktop GUI.
|
|
|
|
The preview's content lives in the desktop renderer (a sandboxed ``<webview>``
|
|
for URL tabs), so this tool round-trips through the gateway's blocking-prompt
|
|
bridge — the same one ``read_terminal`` uses: tui_gateway emits
|
|
``preview.read.request``, the renderer serializes the active preview tab and
|
|
answers with ``preview.read.respond``. This module is just schema + a thin
|
|
dispatcher over the platform-injected callback.
|
|
"""
|
|
|
|
import json
|
|
from typing import Callable, Optional
|
|
|
|
from tools.registry import registry, tool_error
|
|
from utils import env_var_enabled
|
|
|
|
|
|
def read_preview_tool(
|
|
start: Optional[int] = None,
|
|
count: Optional[int] = None,
|
|
callback: Optional[Callable] = None,
|
|
) -> str:
|
|
"""Return the active preview tab's contents (+ metadata) as a JSON string."""
|
|
if callback is None:
|
|
return tool_error("read_preview is only available in the Hermes desktop app.")
|
|
|
|
try:
|
|
window = {
|
|
key: max(floor, int(val))
|
|
for key, val, floor in (("start", start, 0), ("count", count, 1))
|
|
if val is not None
|
|
}
|
|
except (TypeError, ValueError):
|
|
return tool_error("start and count must be integers.")
|
|
|
|
try:
|
|
raw = callback(**window)
|
|
except Exception as exc:
|
|
return tool_error(f"Failed to read the preview pane: {exc}")
|
|
|
|
if not raw:
|
|
return tool_error("No preview tab is open, or the read timed out.")
|
|
|
|
# Desktop answers with a JSON object; pass it through, else wrap the raw text.
|
|
try:
|
|
return json.dumps(json.loads(raw), ensure_ascii=False)
|
|
except (TypeError, ValueError):
|
|
return json.dumps({"text": str(raw)}, ensure_ascii=False)
|
|
|
|
|
|
def check_read_preview_requirements() -> bool:
|
|
"""Desktop GUI only — HERMES_DESKTOP is set on the gateway the app spawns."""
|
|
return env_var_enabled("HERMES_DESKTOP")
|
|
|
|
|
|
READ_PREVIEW_SCHEMA = {
|
|
"name": "read_preview",
|
|
"description": (
|
|
"Read what's currently shown in the in-app browser / preview pane of the "
|
|
"Hermes desktop GUI (the pane open_preview opens beside this chat). Call "
|
|
"with no arguments for the first window of the active tab's content. "
|
|
"Returns JSON {kind, url, title, text, start, end, total_chars, note?}: "
|
|
"a URL (Browser) tab's text is the rendered page's visible text — page "
|
|
"through longer pages with `start`/`count` (character offsets, capped "
|
|
"per read); a file tab answers identity only (read the file with "
|
|
"read_file); an artifact tab points back at the conversation. Use after "
|
|
"open_preview, or whenever the user refers to what's on screen in the "
|
|
"browser ('what does this page say?')."
|
|
),
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"start": {
|
|
"type": "integer",
|
|
"description": "0-indexed character offset into the page text. Omit for the start.",
|
|
},
|
|
"count": {
|
|
"type": "integer",
|
|
"description": "Characters to return from start. Defaults to (and is capped at) the per-read maximum.",
|
|
},
|
|
},
|
|
},
|
|
}
|
|
|
|
|
|
registry.register(
|
|
name="read_preview",
|
|
toolset="terminal",
|
|
schema=READ_PREVIEW_SCHEMA,
|
|
handler=lambda args, **kw: read_preview_tool(
|
|
start=args.get("start"),
|
|
count=args.get("count"),
|
|
callback=kw.get("callback"),
|
|
),
|
|
check_fn=check_read_preview_requirements,
|
|
emoji="🔍",
|
|
)
|