tools: keep tool output whole and let the request-prep pass cap it

run_argv, run_argv_batch, fetch, fetch_local, and the vcs tools now return
their output whole, so the request-prep cap trims it on the wire and names
its document. A fetched page or a long log reads on from the tool message,
with no re-fetch and no re-run.

The run_argv_batch run budget stays as an execution guard: it stops a
runaway batch from spawning further huge-output steps.

Co-authored-by: CommandCodeBot <noreply@commandcode.ai>

src/plyngent/tools/net/fetch_local.py

@@ -9,7 +9,6 @@ from plyngent.tools.net.client import FetchResult, http_fetch
 from plyngent.tools.net.policy import (
     DEFAULT_MAX_BODY_CHARS_IN,
     DEFAULT_MAX_BYTES,
-    DEFAULT_MAX_CHARS,
     DEFAULT_MAX_REDIRECTS,
     DEFAULT_TIMEOUT_SECONDS,
     FetchPolicyError,
@@ -18,7 +17,6 @@ from plyngent.tools.net.policy import (
     parse_fetch_url,
     soft_confirm_reason,
 )
-from plyngent.tools.truncate_token import truncate_to_memory
 from plyngent.tools.workspace import image_input_refusal
 
 
@@ -35,15 +33,13 @@ def format_fetch_result(
     security: str,
     warnings: list[str],
     body_kind: str,
-    max_chars: int,
     offset: int = 0,
 ) -> str:
     start = max(0, offset)
-    # The body is already in hand, so the remainder is kept in memory rather than
-    # re-requested: resuming a fetch must not cost another round trip (latency)
-    # nor re-hit the remote (rate limits / risk control).
-    body, token = truncate_to_memory(body_text[start:], max_chars)
-    char_truncated = token is not None
+    # The body is kept whole in the tool message (the request-prep pass trims it
+    # on the wire and names its document), so resuming reads the message rather
+    # than re-hitting the remote.
+    body = body_text[start:]
     warn_line = "; ".join(warnings) if warnings else ""
     parts = [
         f"status={status}",
@@ -52,7 +48,7 @@ def format_fetch_result(
         f"content_type={content_type}",
         f"body_kind={body_kind}",
         f"bytes={body_bytes}",
-        f"truncated={'true' if truncated or char_truncated else 'false'}",
+        f"truncated={'true' if truncated else 'false'}",
         f"redirects={redirects}",
         f"security={security}",
     ]
@@ -73,19 +69,18 @@ async def fetch_local(
     user_agent: str | None = None,
     timeout_seconds: float = DEFAULT_TIMEOUT_SECONDS,
     max_bytes: int = DEFAULT_MAX_BYTES,
-    max_chars: int = DEFAULT_MAX_CHARS,
     max_redirects: int = DEFAULT_MAX_REDIRECTS,
     follow_redirects: bool = True,
     allow_http_downgrade: bool = False,
     offset: int = 0,
 ) -> str | ToolOutput:
-    """HTTP request (GET/POST/PUT/DELETE); return status, metadata, and truncated body.
+    """HTTP request (GET/POST/PUT/DELETE); return status, metadata, and the body.
 
     Use for public docs/APIs or (after human policy allow) local/LAN servers.
     ``offset`` skips that many leading characters of the body (0-based), for
-    paging through a body larger than ``max_chars``; a body truncated by
-    ``max_chars`` keeps its remainder in memory instead, resumable via its
-    ``truncate_token`` without another request.
+    paging through a body the wire cap trimmed; a trimmed body keeps its
+    remainder in the tool message, so its ``document_id`` reads the rest with no
+    new request.
     ``user_agent`` sets User-Agent when provided and takes precedence over a
     User-Agent entry in ``headers``. A headers-only User-Agent is kept as-is.
     When both omit UA, a small default is used.
@@ -138,7 +133,6 @@ async def fetch_local(
         security=result.security,
         warnings=result.warnings,
         body_kind=result.body_kind,
-        max_chars=max_chars,
         offset=offset,
     )
     return _attach_image(text, result)

src/plyngent/tools/net/fetch_remote.py

@@ -13,8 +13,6 @@ import inspect
 from typing import TYPE_CHECKING
 
 from plyngent.agent.tools import ToolDefinition, ToolTag, schema_from_callable
-from plyngent.tools.net.policy import DEFAULT_MAX_CHARS
-from plyngent.tools.truncate_token import truncate_to_memory
 
 if TYPE_CHECKING:
     from plyngent.lmproto.deepseek.webtools import DeepseekWebToolsClient
@@ -27,31 +25,28 @@ def format_page_result(
     title: str,
     url: str,
     content: str,
-    max_chars: int,
     offset: int = 0,
 ) -> str:
     """Render a fetched page the way the other structured tool results read."""
     start = max(0, offset)
-    body, token = truncate_to_memory(content[start:], max_chars)
+    # The page is kept whole in the tool message (the request-prep pass trims it
+    # on the wire and names its document), so neither a re-fetch nor a charge
+    # follows a read of the rest.
+    body = content[start:]
     parts = [
         f"title={' '.join(title.split()) or '(untitled)'}",
         f"url={url}",
         f"chars={len(content)}",
-        f"truncated={'true' if token is not None else 'false'}",
         "--- content ---",
         body,
     ]
     return "\n".join(parts)
 
 
-def build_fetch_tool(
-    client: DeepseekWebToolsClient,
-    *,
-    default_max_chars: int = DEFAULT_MAX_CHARS,
-) -> ToolDefinition:
+def build_fetch_tool(client: DeepseekWebToolsClient) -> ToolDefinition:
     """A ``fetch`` definition backed by DeepSeek's Fetch API."""
 
-    async def fetch(url: str, offset: int = 0, max_chars: int = default_max_chars) -> str:
+    async def fetch(url: str, offset: int = 0) -> str:
         """Read a public web page as Markdown through DeepSeek's Fetch API.
 
         Use for public articles and docs when clean Markdown is enough. The page
@@ -60,9 +55,9 @@ def build_fetch_tool(
         when you need the raw HTTP status/headers. A successful fetch is billed
         per request (failures are not).
 
-        ``offset`` (0-based) skips leading characters of the content. A body cut
-        by ``max_chars`` keeps its remainder in memory, resumable via its
-        ``truncate_token`` without another request (and without another charge).
+        ``offset`` (0-based) skips leading characters of the content. The page is
+        kept whole in the tool message, so a trimmed ``document_id`` reads the
+        rest with no new request (and no new charge).
         """
         try:
             page = await client.fetch(url)
@@ -72,7 +67,6 @@ def build_fetch_tool(
             title=page.title,
             url=url,
             content=page.content,
-            max_chars=max_chars,
             offset=offset,
         )
 

src/plyngent/tools/net/policy.py

@@ -36,7 +36,6 @@ DEFAULT_USER_AGENT = "plyngent-fetch/0.2"
 DEFAULT_MAX_REDIRECTS = 5
 DEFAULT_TIMEOUT_SECONDS = 30.0
 DEFAULT_MAX_BYTES = 1_000_000
-DEFAULT_MAX_CHARS = 32_000
 DEFAULT_MAX_BODY_CHARS_IN = 256_000  # request body size limit (tool arg)
 
 # Cloud / link-local style targets never granted via policy UI.

src/plyngent/tools/process/command_exec.py

@@ -18,26 +18,9 @@ from plyngent.tools.workspace import (
 )
 
 DEFAULT_TIMEOUT_SECONDS = 30
-DEFAULT_MAX_OUTPUT_CHARS = 32_000
 DEFAULT_MAX_BATCH_STEPS = 20
 
 
-def truncate_output(text: str, label: str, max_chars: int = DEFAULT_MAX_OUTPUT_CHARS) -> str:
-    """Cap a per-stream output block; embed a truncate token when cut.
-
-    ``label`` (stdout/stderr/batch) is kept for call-site clarity but the
-    marker itself is the uniform ``[Truncated (N chars max.; M omitted).
-    truncate_token=...]`` (no label), matching every other truncation site.
-    Returns ``text`` unchanged when it fits.
-    """
-    del label
-    if max_chars < 1 or len(text) <= max_chars:
-        return text
-    from plyngent.tools.truncate_token import truncate_generic
-
-    return truncate_generic(text, max_chars)
-
-
 def format_command_result(
     *,
     returncode: int | None,
@@ -53,9 +36,9 @@ def format_command_result(
         f"cwd={workdir_display}",
         f"cmd={shlex.join(command)}",
         "--- stdout ---",
-        truncate_output(stdout, "stdout"),
+        stdout,
         "--- stderr ---",
-        truncate_output(stderr, "stderr"),
+        stderr,
     ]
     return "\n".join(parts)
 

src/plyngent/tools/process/run_argv_batch.py

@@ -9,13 +9,14 @@ from plyngent.tools.workspace import WorkspaceError
 
 from .command_exec import (
     DEFAULT_MAX_BATCH_STEPS,
-    DEFAULT_MAX_OUTPUT_CHARS,
     DEFAULT_TIMEOUT_SECONDS,
     CommandStepResult,
     execute_argv,
-    truncate_output,
 )
 
+# Execution budget: stop the batch once accumulated output crosses this factor
+# of the base budget, so a runaway batch cannot keep spawning huge-output steps.
+BATCH_OUTPUT_BUDGET_CHARS = 32_000
 BATCH_OUTPUT_SOFT_CAP_FACTOR = 4
 
 
@@ -102,9 +103,9 @@ def _format_step(index: int, result: CommandStepResult, *, pipe_out: bool) -> st
             f"pipe_out={'true' if pipe_out else 'false'}",
             f"mix_stderr={'true' if result.mix_stderr else 'false'}",
             "--- stdout ---",
-            truncate_output(result.stdout, "stdout"),
+            result.stdout,
             "--- stderr ---",
-            truncate_output(result.stderr, "stderr"),
+            result.stderr,
         ]
     )
 
@@ -147,7 +148,7 @@ async def _run_batch_steps(
         effective_stop = stop_on_error if step["stop_on_error"] is None else bool(step["stop_on_error"])
         if failed and effective_stop:
             return results, True
-        if total_chars > DEFAULT_MAX_OUTPUT_CHARS * BATCH_OUTPUT_SOFT_CAP_FACTOR:
+        if total_chars > BATCH_OUTPUT_BUDGET_CHARS * BATCH_OUTPUT_SOFT_CAP_FACTOR:
             return results, True
         del index  # used for clarity in loop only
 
@@ -178,7 +179,9 @@ async def run_argv_batch(
         }
 
     ``pipe_out`` is set on the **provider** step. Last-step ``pipe_out`` is an error.
-    Default ``stop_on_error`` is true. Max 20 steps; total output budget 32k chars.
+    Default ``stop_on_error`` is true. Max 20 steps; the batch stops early once
+    accumulated output passes the run budget (128k chars). Each step's output is
+    kept whole for the model; a long result carries a ``document_id`` to read on.
     """
     try:
         raw_steps = _normalize_steps(steps)
@@ -195,8 +198,6 @@ async def run_argv_batch(
         body = "\n".join(
             _format_step(i, result, pipe_out=bool(step["pipe_out"])) for i, (step, result) in enumerate(results)
         )
-        if len(body) > DEFAULT_MAX_OUTPUT_CHARS:
-            body = truncate_output(body, "batch")
         last_exit = results[-1][1].exit_code if results else ""
         return "\n".join(
             [

src/plyngent/tools/vcs/git_backend.py

@@ -8,7 +8,6 @@ if TYPE_CHECKING:
     from pathlib import Path
 
 DEFAULT_TIMEOUT_SECONDS = 30.0
-DEFAULT_MAX_OUTPUT_CHARS = 64_000
 
 
 def is_git_repo(root: Path) -> bool:
@@ -32,13 +31,6 @@ class _GitResult:
         self.returncode = returncode
 
 
-def _truncate(text: str) -> str:
-    if len(text) <= DEFAULT_MAX_OUTPUT_CHARS:
-        return text
-    omitted = len(text) - DEFAULT_MAX_OUTPUT_CHARS
-    return f"{text[:DEFAULT_MAX_OUTPUT_CHARS]}\n...[truncated {omitted} characters]"
-
-
 def _run_git(root: Path, args: list[str], *, timeout: float = DEFAULT_TIMEOUT_SECONDS) -> _GitResult:
     argv = ["git", "-c", "color.ui=false", *args]
     try:
@@ -57,12 +49,12 @@ def _run_git(root: Path, args: list[str], *, timeout: float = DEFAULT_TIMEOUT_SE
     except OSError as exc:
         return _GitResult(ok=False, stdout="", stderr=str(exc), returncode=1)
 
-    stdout = _truncate(completed.stdout or "")
-    stderr = _truncate(completed.stderr or "")
+    # Output is kept whole; the request-prep pass trims it on the wire and names
+    # its document, so a long log/diff reads on rather than re-running git.
     return _GitResult(
         ok=completed.returncode == 0,
-        stdout=stdout,
-        stderr=stderr,
+        stdout=completed.stdout or "",
+        stderr=completed.stderr or "",
         returncode=completed.returncode,
     )
 

tests/test_tools/test_fetch_local.py

@@ -23,7 +23,6 @@ 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:
@@ -299,37 +298,30 @@ 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_local, 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
-    # The body is kept in memory, so resuming never repeats the request.
-    assert token.kind == "memory"
-    assert token.limit == 1000
-    assert 0 < token.offset < 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_local, f"{http_server}/big", max_chars=200, offset=4900)
+    # /big body is 5000 chars; offset 4900 leaves the last 100 chars.
+    out = await call_async(fetch_local, f"{http_server}/big", offset=4900)
     body = out.split("--- body ---", 1)[-1]
     assert body.strip() == "x" * 100
     assert "truncate_token=" not in out
 
 
+async def test_fetch_keeps_the_body_whole(workspace: Path, http_server: str) -> None:
+    """The body is stored whole (the request-prep pass caps it on the wire)."""
+    del workspace
+    port = int(http_server.rsplit(":", 1)[1])
+    grant_private_host("127.0.0.1", port)
+
+    out = await call_async(fetch_local, f"{http_server}/big")
+    body = out.split("--- body ---", 1)[-1].strip()
+    assert body == "x" * 5000
+    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).

tests/test_tools/test_fetch_remote.py

@@ -24,8 +24,8 @@ class _Client:
         return self.page
 
 
-def _tool(client: _Client, *, max_chars: int = 32_000):
-    return build_fetch_tool(client, default_max_chars=max_chars)
+def _tool(client: _Client):
+    return build_fetch_tool(client)
 
 
 def test_definition_shape() -> None:
@@ -33,7 +33,7 @@ def test_definition_shape() -> None:
     assert definition.name == FETCH_TOOL_NAME == "fetch"
     assert definition.tags == ToolTag.LOCAL | ToolTag.READ_ONLY
     properties = definition.parameters["properties"]
-    assert set(properties) == {"url", "offset", "max_chars"}
+    assert set(properties) == {"url", "offset"}
     assert definition.parameters["required"] == ["url"]
     assert "fetch_local" in definition.description
 
@@ -48,7 +48,6 @@ async def test_handler_renders_title_url_and_content() -> None:
         "title=Example article",
         "url=https://example.com/article",
         "chars=16",
-        "truncated=false",
         "--- content ---",
         "# Heading",
         "",
@@ -57,14 +56,13 @@ async def test_handler_renders_title_url_and_content() -> None:
 
 
 @pytest.mark.asyncio
-async def test_offset_and_truncation_keep_the_remainder_resumable() -> None:
+async def test_offset_skips_leading_content() -> None:
     client = _Client(page=FetchResponse(title="", content="0123456789"))
-    result = await _tool(client, max_chars=3).handler(url="https://example.com/", offset=5)
+    result = await _tool(client).handler(url="https://example.com/", offset=5)
 
     assert "title=(untitled)" in result
-    assert "--- content ---\n567" in result
-    assert "truncated=true" in result
-    assert "truncate_token=" in result
+    assert "--- content ---\n56789" in result
+    assert "truncate_token=" not in result
 
 
 @pytest.mark.asyncio

tests/test_tools/test_get_truncated.py

@@ -84,42 +84,6 @@ async def test_get_truncated_file_missing(workspace: Path) -> None:
     assert out.startswith("error:")
 
 
-async def test_get_truncated_serves_a_fetch_body_without_refetching(monkeypatch) -> None:
-    """A fetch body's token reads the stored remainder; the request is not repeated."""
-    from plyngent.tools.net.fetch_local import format_fetch_result
-
-    fetch_module = importlib.import_module("plyngent.tools.net.fetch_local")
-
-    async def _must_not_refetch(*_args: object, **_kwargs: object) -> str:
-        msg = "resuming a fetch body must not re-run the request"
-        raise AssertionError(msg)
-
-    monkeypatch.setattr(fetch_module, "http_fetch", _must_not_refetch)
-    first = format_fetch_result(
-        status=200,
-        final_url="https://example.com/x",
-        content_type="text/plain",
-        body_text="x" * 600,
-        body_bytes=600,
-        truncated=False,
-        redirects=0,
-        method="GET",
-        security="public",
-        warnings=[],
-        body_kind="text",
-        max_chars=200,
-    )
-    token = _extract_token(first)
-    assert token is not None
-    parsed = decode_truncate_token(token)
-    assert parsed is not None
-    assert parsed.kind == "memory"
-    out = await call_async(get_truncated, token, max_chars=200)
-    content, _, _ = out.partition("\n[Truncated")
-    assert content == "x" * len(content)
-    assert 0 < len(content) <= 200
-
-
 async def test_get_truncated_memory_chains() -> None:
     from plyngent.tools.truncate_token import truncate_generic
 

tests/test_tools/test_process.py

@@ -192,14 +192,14 @@ async def test_run_argv_timeout_keeps_partial_output(workspace: object) -> None:
     assert "partial-out" in out
 
 
-async def test_run_argv_stdout_cap_embeds_token(workspace: object) -> None:
+async def test_run_argv_returns_the_full_stdout(workspace: object) -> None:
     del workspace
-    # Per-stream cap default is 32000 chars: a bigger stdout embeds a token.
+    # The result is stored whole; the request-prep pass caps it on the wire and
+    # names its document, so nothing is cut at the tool.
     out = await call_async(run_argv, _py("print('x' * 40000)"))
-    assert "truncate_token=" in out
-    token_line = next(ln for ln in out.splitlines() if "truncate_token=" in ln)
-    assert "[Truncated (32000 chars max.;" in token_line
-    assert "[Truncated" in out
+    body = out.split("--- stdout ---", 1)[1].split("--- stderr ---", 1)[0].strip()
+    assert body == "x" * 40000
+    assert "truncate_token=" not in out
 
 
 async def test_run_argv_small_stdout_no_marker(workspace: object) -> None: