core/agent: cap tool results in the request-prep pass

A tool result now stays whole in its message (up to a storage ceiling) and
is trimmed on the request copy by the request-prep pass, where soft compact
already runs. The trimmed copy names the document that holds the rest, so
every surface (chat-completions, Responses, Messages) shares one rule.

New [agent] hard_max_tool_result_chars bounds the stored body; the wire cap
stays [agent] max_tool_result_chars.

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

tests/test_agent/test_budget.py

@@ -1,27 +1,49 @@
 from __future__ import annotations
 
-from plyngent.agent.budget import estimate_message_chars, truncate_tool_result
+from plyngent.agent.budget import (
+    cap_hard_tool_text,
+    cap_tool_message,
+    estimate_message_chars,
+    truncate_for_request,
+)
 from plyngent.lmproto.openai_compatible.model import ToolChatMessage, UserChatMessage
 
 
-def test_truncate_tool_result_short() -> None:
-    assert truncate_tool_result("hello", 100) == "hello"
+def test_cap_hard_tool_text_short_untouched() -> None:
+    assert cap_hard_tool_text("hello", 100) == "hello"
 
 
-def test_truncate_tool_result_long() -> None:
-    text = "a" * 50
-    out = truncate_tool_result(text, 20)
-    assert "Truncated" in out
-    assert "20" in out
-    assert "30" in out
-    # Generic tool results now embed a memory token too (resumable via get_truncated).
-    assert "truncate_token=" in out
-    assert out.startswith(("a" * 10, "a" * 20))  # marker is budgeted
+def test_cap_hard_tool_text_cuts_with_ceiling_marker() -> None:
+    out = cap_hard_tool_text("a" * 50, 20)
+    assert out.startswith("a" * 20)
+    assert "[Stored at the 20-char ceiling: 30 chars beyond it]" in out
 
 
-def test_truncate_tool_result_fits_no_marker() -> None:
-    assert truncate_tool_result("tiny", 100) == "tiny"
-    assert "Truncated" not in truncate_tool_result("tiny", 100)
+def test_cap_tool_message_names_the_document() -> None:
+    message = ToolChatMessage(content="a" * 50, tool_call_id="call-7")
+    capped = cap_tool_message(message, 20)
+    assert capped is not message
+    assert capped.tool_call_id == "call-7"
+    assert "document_id=call-7" in capped.content
+    assert capped.content.startswith("a")
+    # The stored message keeps its body whole.
+    assert message.content == "a" * 50
+
+
+def test_cap_tool_message_short_untouched() -> None:
+    message = ToolChatMessage(content="tiny", tool_call_id="call-1")
+    assert cap_tool_message(message, 100) is message
+
+
+def test_truncate_for_request_caps_only_tool_messages() -> None:
+    user = UserChatMessage(content="u" * 1000)
+    tool = ToolChatMessage(content="t" * 1000, tool_call_id="call-1")
+    out = truncate_for_request([user, tool], max_tool_result_chars=200)
+    assert out[0] is user
+    capped = out[1]
+    assert isinstance(capped, ToolChatMessage)
+    assert "document_id=call-1" in capped.content
+    assert len(capped.content) <= 200
 
 
 def test_estimate_message_chars() -> None: