mirror of
https://github.com/NCBM/plyngent.git
synced 2026-11-07 07:17:54 +08:00
core/tools: show images instead of describing them
New `view_image` reads a local picture (JPEG, PNG, GIF, WebP, sniffed from its bytes) and hands it to the model as an image part, with an optional `detail` level — `low` measured 3.4x cheaper on a 1200x900 picture. `read_file` now points at it instead of returning decode noise. `fetch_local` returns an image response as the picture itself, and MCP image content blocks become image parts instead of `[image: ...]` placeholders, so a screenshot server finally reaches the model.
This commit is contained in:
@@ -0,0 +1,68 @@
|
||||
"""``view_image``: a local picture reaches the model as a picture."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import base64
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from plyngent.agent import ToolOutput
|
||||
from plyngent.tools.file.read import read_file
|
||||
from plyngent.tools.file.view_image import view_image
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from pathlib import Path
|
||||
|
||||
# A real 1x1 PNG: the format is sniffed from these bytes.
|
||||
PNG = base64.b64decode(
|
||||
"iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mP8z8BQDwAEhQGAhKmMIQAAAABJRU5ErkJggg=="
|
||||
)
|
||||
|
||||
|
||||
async def test_view_image_attaches_the_picture(workspace: Path) -> None:
|
||||
(workspace / "shot.png").write_bytes(PNG)
|
||||
|
||||
output = await view_image.handler("shot.png")
|
||||
|
||||
assert isinstance(output, ToolOutput)
|
||||
assert output.text == "image: shot.png (attached below)"
|
||||
url = output.images[0].image_url.url
|
||||
assert url.startswith("data:image/png;base64,")
|
||||
assert base64.b64decode(url.partition(",")[2]) == PNG
|
||||
|
||||
|
||||
async def test_the_detail_level_reaches_the_part(workspace: Path) -> None:
|
||||
(workspace / "shot.png").write_bytes(PNG)
|
||||
|
||||
output = await view_image.handler("shot.png", detail="low")
|
||||
|
||||
assert isinstance(output, ToolOutput)
|
||||
assert output.images[0].image_url.detail == "low"
|
||||
|
||||
|
||||
async def test_an_unknown_detail_level_is_an_error(workspace: Path) -> None:
|
||||
(workspace / "shot.png").write_bytes(PNG)
|
||||
|
||||
assert "detail must be one of" in await view_image.handler("shot.png", detail="huge")
|
||||
|
||||
|
||||
async def test_a_non_image_file_is_an_error(workspace: Path) -> None:
|
||||
(workspace / "notes.txt").write_text("hello")
|
||||
|
||||
result = await view_image.handler("notes.txt")
|
||||
|
||||
assert isinstance(result, str)
|
||||
assert "not a JPEG, PNG, GIF, or WebP image" in result
|
||||
|
||||
|
||||
async def test_a_missing_file_is_an_error(workspace: Path) -> None:
|
||||
del workspace
|
||||
|
||||
assert await view_image.handler("nope.png") == "error: file not found: nope.png"
|
||||
|
||||
|
||||
async def test_read_file_points_at_view_image_for_a_picture(workspace: Path) -> None:
|
||||
(workspace / "shot.png").write_bytes(PNG)
|
||||
|
||||
result = await read_file.handler("shot.png")
|
||||
|
||||
assert result == "error: shot.png is an image (image/png); use view_image to look at it"
|
||||
Reference in New Issue
Block a user