core/tools: embed truncate tokens in fetch (offset param)

This commit is contained in:
2026-08-11 14:55:55 +08:00
parent 8cd456171c
commit c96f669bcb
2 changed files with 48 additions and 7 deletions
+17 -7
View File
@@ -16,6 +16,7 @@ from plyngent.tools.net.policy import (
parse_fetch_url,
soft_confirm_reason,
)
from plyngent.tools.truncate_token import truncate_with_token
def format_fetch_result(
@@ -32,13 +33,20 @@ def format_fetch_result(
warnings: list[str],
body_kind: str,
max_chars: int,
offset: int = 0,
) -> str:
text = body_text
char_truncated = False
if max_chars >= 1 and len(text) > max_chars:
omitted = len(text) - max_chars
text = text[:max_chars] + f"\n...[truncated {omitted} characters]"
char_truncated = True
start = max(0, offset)
body = body_text[start:]
body, token = truncate_with_token(
body,
max_chars,
kind="http",
location=final_url,
offset=start,
limit=max_chars,
total_len=len(body_text),
)
char_truncated = token is not None
warn_line = "; ".join(warnings) if warnings else ""
parts = [
f"status={status}",
@@ -54,7 +62,7 @@ def format_fetch_result(
if warn_line:
parts.append(f"warnings={warn_line}")
parts.append("--- body ---")
parts.append(text)
parts.append(body)
return "\n".join(parts)
@@ -72,6 +80,7 @@ async def fetch(
max_redirects: int = DEFAULT_MAX_REDIRECTS,
follow_redirects: bool = True,
allow_http_downgrade: bool = False,
offset: int = 0,
) -> str:
"""HTTP request (GET/POST/PUT/DELETE); return status, metadata, and truncated body.
@@ -122,6 +131,7 @@ async def fetch(
warnings=result.warnings,
body_kind=result.body_kind,
max_chars=max_chars,
offset=offset,
)
+31
View File
@@ -20,6 +20,7 @@ from plyngent.tools.net.policy import (
parse_fetch_url,
soft_confirm_reason,
)
from plyngent.tools.truncate_token import decode_truncate_token
from tests.test_tools.helpers import call_async
if TYPE_CHECKING:
@@ -237,6 +238,36 @@ async def test_fetch_truncation_and_binary(workspace: Path, http_server: str) ->
assert "binary body omitted" in out_bin
async def test_fetch_char_truncation_embeds_token(workspace: Path, http_server: str) -> None:
del workspace
port = int(http_server.rsplit(":", 1)[1])
grant_private_host("127.0.0.1", port)
out = await call_async(fetch, f"{http_server}/big", max_chars=1000)
assert "truncated=true" in out
body = out.split("--- body ---", 1)[-1]
assert "TRUNCATE_TOKEN:" in body
token_line = next(ln for ln in body.splitlines() if "TRUNCATE_TOKEN:" in ln)
token_str = token_line.split("[TRUNCATE_TOKEN: ", 1)[1].rstrip("]")
token = decode_truncate_token(token_str)
assert token is not None
assert token.kind == "http"
assert token.offset == 1000 # next chunk starts at max_chars
assert token.limit == 1000
async def test_fetch_offset_skips_body(workspace: Path, http_server: str) -> None:
del workspace
port = int(http_server.rsplit(":", 1)[1])
grant_private_host("127.0.0.1", port)
# /big body is 5000 chars; offset 4900 leaves 100 chars, no token needed.
out = await call_async(fetch, f"{http_server}/big", max_chars=200, offset=4900)
body = out.split("--- body ---", 1)[-1]
assert body.strip() == "x" * 100
assert "TRUNCATE_TOKEN:" not in out
async def test_fetch_private_denied_without_grant(workspace: Path, http_server: str) -> None:
del workspace
# No grant, no policy hook → hard deny (even though server is up).