core/agent: token-ify generic tool-result cap and compact shrinks

src/plyngent/agent/budget.py

@@ -31,27 +31,23 @@ DEFAULT_CONTEXT_MAX_CHARS = DEFAULT_CONTEXT_MAX_TOKENS * 4
 def truncate_tool_result(
     text: str,
     max_chars: int = DEFAULT_TOOL_RESULT_MAX_CHARS,
-    *,
-    hint: bool = True,
 ) -> str:
     """Cap tool output so huge dumps do not flood model context.
 
-    This is the generic agent-loop cap for arbitrary tool results — there is no
-    resumable source, so no ``TRUNCATE_TOKEN`` is emitted here. Token-capable
-    sources (``read_file`` / ``fetch`` / ``get_truncated``) embed their own
-    ``[TRUNCATE_TOKEN: ...]`` marker via :func:`truncate_with_token`, and only
-    there does the result point the model at ``get_truncated`` (hint and token
-    always appear together). ``hint=False`` keeps the terse marker for internal
-    shrinks whose cap is not a user-facing knob (e.g. request-time compacting).
+    This is the generic agent-loop cap for arbitrary tool results. It embeds a
+    memory truncate token via :func:`truncate_generic` so the model can always
+    resume the remainder with ``get_truncated`` — resumable or not (remainders
+    live in the in-memory store for the process lifetime). The compact marker
+    ``[Truncated (N chars max.; M omitted). truncate_token=...]`` is emitted
+    only when output is actually cut.
     """
     if max_chars < 1:
         return text
     if len(text) <= max_chars:
         return text
-    omitted = len(text) - max_chars
-    if hint:
-        return f"{text[:max_chars]}\n...[Truncated ({max_chars} chars max.; {omitted} chars omitted)]"
-    return f"{text[:max_chars]}\n...[truncated {omitted} characters]"
+    from plyngent.tools.truncate_token import truncate_generic
+
+    return truncate_generic(text, max_chars)
 
 
 def estimate_message_chars(message: AnyChatMessage) -> int:
@@ -119,7 +115,7 @@ def _shrink_tool(message: ToolChatMessage, max_chars: int) -> ToolChatMessage:
         return message
     return msgspec.structs.replace(
         message,
-        content=truncate_tool_result(message.content, max_chars, hint=False),
+        content=truncate_tool_result(message.content, max_chars),
     )
 
 

tests/test_agent/test_budget.py

@@ -11,21 +11,17 @@ def test_truncate_tool_result_short() -> None:
 def test_truncate_tool_result_long() -> None:
     text = "a" * 50
     out = truncate_tool_result(text, 20)
-    assert out.startswith("a" * 20)
     assert "Truncated" in out
     assert "20" in out
     assert "30" in out
-    # Generic tool results carry no resumable source → no token, no get_truncated.
-    assert "get_truncated" not in out
-    assert "TRUNCATE_TOKEN" not 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_truncate_tool_result_no_hint() -> None:
-    text = "a" * 50
-    out = truncate_tool_result(text, 20, hint=False)
-    assert out.startswith("a" * 20)
-    assert "truncated" in out
-    assert "get_truncated" not 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_estimate_message_chars() -> None:

tests/test_agent/test_compact.py

@@ -40,21 +40,18 @@ def test_truncate_tool_result_short() -> None:
 def test_truncate_tool_result_long() -> None:
     text = "a" * 50
     out = truncate_tool_result(text, 20)
-    assert out.startswith("a" * 20)
     assert "Truncated" in out
     assert "20" in out
     assert "30" in out
-    # Generic tool results carry no resumable source → no token, no get_truncated.
-    assert "get_truncated" not in out
-    assert "TRUNCATE_TOKEN" not in out
+    # Generic tool results now embed a memory token too (resumable via get_truncated).
+    assert "truncate_token=" in out
 
 
 def test_truncate_tool_result_no_hint() -> None:
     text = "a" * 50
-    out = truncate_tool_result(text, 20, hint=False)
-    assert out.startswith("a" * 20)
-    assert "truncated" in out
-    assert "get_truncated" not in out
+    out = truncate_tool_result(text, 20)
+    assert "Truncated" in out
+    assert "truncate_token=" in out
 
 
 def test_compact_shrinks_old_tool_results() -> None:
@@ -94,7 +91,9 @@ def test_compact_shrinks_old_tool_results() -> None:
     )
     assert isinstance(compacted[2], ToolChatMessage)
     assert len(compacted[2].content) < original_len
-    assert "truncated" in compacted[2].content
+    assert "Truncated" in compacted[2].content
+    # Compact shrinks carry a token too (resumable via get_truncated).
+    assert "truncate_token=" in compacted[2].content
     # Full history unchanged
     assert isinstance(messages[2], ToolChatMessage)
     assert len(messages[2].content) == original_len
@@ -134,7 +133,7 @@ def test_compact_uses_api_calibration() -> None:
     # Raw est under budget → no compact
     no_api = compact_messages_for_request(messages, max_tokens=est + 100)
     assert isinstance(no_api[1], ToolChatMessage)
-    assert "truncated" not in no_api[1].content
+    assert "Truncated" not in no_api[1].content
     # Calibrate so measured size is 5x → over a mid budget → shrink old tool
     compacted = compact_messages_for_request(
         messages,
@@ -147,7 +146,7 @@ def test_compact_uses_api_calibration() -> None:
     assert isinstance(compacted[1], ToolChatMessage)
     old = messages[1]
     assert isinstance(old, ToolChatMessage)
-    assert "truncated" in compacted[1].content or len(compacted[1].content) < len(old.content)
+    assert "Truncated" in compacted[1].content or len(compacted[1].content) < len(old.content)
 
 
 def _response(message: AssistantChatMessage) -> ChatCompletionResponse: