core/agent+cli: keep a round cut off at the output limit

src/plyngent/agent/__init__.py

@@ -17,6 +17,7 @@ from .events import ReasoningDeltaEvent as ReasoningDeltaEvent
 from .events import TextDeltaEvent as TextDeltaEvent
 from .events import ToolCallEvent as ToolCallEvent
 from .events import ToolResultEvent as ToolResultEvent
+from .events import TruncatedEvent as TruncatedEvent
 from .events import UsageEvent as UsageEvent
 from .loop import DEFAULT_MAX_ROUNDS as DEFAULT_MAX_ROUNDS
 from .loop import run_chat_loop as run_chat_loop
@@ -26,6 +27,7 @@ from .notices import format_moment as format_moment
 from .notices import has_notice as has_notice
 from .notices import resume_notice as resume_notice
 from .notices import skill_tools_notice as skill_tools_notice
+from .notices import truncated_turn_notice as truncated_turn_notice
 from .tools import DangerClassifier as DangerClassifier
 from .tools import ToolConfirmHook as ToolConfirmHook
 from .tools import ToolDefinition as ToolDefinition

src/plyngent/agent/chat.py

@@ -27,7 +27,8 @@ from .directive_checkpoint import (
     parse_checkpoint_bands,
 )
 from .events import UsageEvent
-from .loop import DEFAULT_MAX_ROUNDS, run_chat_loop
+from .loop import DEFAULT_MAX_ROUNDS, DEFAULT_MAX_TRUNCATION_CONTINUES, run_chat_loop
+from .notices import TRUNCATED_NOTICE_KIND, notice_of_kind
 from .todo_nag import (
     DEFAULT_TODO_NAG_STRATEGY,
     parse_todo_nag_strategy,
@@ -140,8 +141,10 @@ def incomplete_turn_user_text(messages: Sequence[AnyChatMessage]) -> str | None:
     """User text for an incomplete turn, if history can be retried.
 
     Incomplete when the last non-system message is a user message (failed before
-    any commit), or tool results after a complete tool batch (failed on a later
-    model round — keep tools so retry does not re-execute side effects).
+    any commit), tool results after a complete tool batch (failed on a later
+    model round — keep tools so retry does not re-execute side effects), or a
+    partial answer under a truncation notice (the round hit the output limit; its
+    answer was kept, so retry continues it instead of regenerating).
     Trailing developer messages (host notices, directive checkpoints) belong to
     the turn but never end it, so they are skipped when reading the tail.
     """
@@ -150,14 +153,17 @@ def incomplete_turn_user_text(messages: Sequence[AnyChatMessage]) -> str | None:
     if messages and isinstance(messages[0], SystemChatMessage):
         start = 1
     body = list(messages[start:])
+    truncated = False
     while body and isinstance(body[-1], DeveloperChatMessage):
+        if notice_of_kind(body[-1], TRUNCATED_NOTICE_KIND):
+            truncated = True
         _ = body.pop()
     if not body:
         return None
     last = body[-1]
     if isinstance(last, UserChatMessage):
         return last.content
-    if isinstance(last, ToolChatMessage):
+    if isinstance(last, ToolChatMessage) or (truncated and isinstance(last, AssistantChatMessage)):
         # Walk back to the user that opened this turn.
         for msg in reversed(body):
             if isinstance(msg, UserChatMessage):
@@ -289,6 +295,8 @@ class ChatAgent:
     memory: MemoryStore | None
     session_id: int | None
     max_rounds: int
+    # Rounds a turn may carry on after hitting the output limit (0 = none).
+    max_truncation_continues: int
     temperature: float | None
     # Resolved thinking strength ("" = provider default); see config.reasoning.
     reasoning_effort: str
@@ -322,6 +330,7 @@ class ChatAgent:
         memory: MemoryStore | None = None,
         session_id: int | None = None,
         max_rounds: int = DEFAULT_MAX_ROUNDS,
+        max_truncation_continues: int = DEFAULT_MAX_TRUNCATION_CONTINUES,
         temperature: float | None = None,
         reasoning_effort: str = "",
         messages: Sequence[AnyChatMessage] | None = None,
@@ -345,6 +354,7 @@ class ChatAgent:
         self.memory = memory
         self.session_id = session_id
         self.max_rounds = max_rounds
+        self.max_truncation_continues = max(0, int(max_truncation_continues))
         self.temperature = temperature
         self.reasoning_effort = reasoning_effort
         self.on_limit = on_limit
@@ -603,6 +613,7 @@ class ChatAgent:
                 model=self.model,
                 tools=self.tools,
                 max_rounds=self.max_rounds,
+                max_truncation_continues=self.max_truncation_continues,
                 temperature=self.temperature,
                 reasoning_effort=self.reasoning_effort,
                 on_limit=self.on_limit,
@@ -747,6 +758,7 @@ class ChatAgent:
             memory=None,
             session_id=None,
             max_rounds=rounds,
+            max_truncation_continues=self.max_truncation_continues,
             temperature=self.temperature,
             reasoning_effort=self.reasoning_effort,
             on_limit=self.on_limit,

src/plyngent/agent/events.py

@@ -34,6 +34,19 @@ class MaxRoundsEvent(Struct, tag_field="type", tag="max_rounds"):
     continued: bool = False
 
 
+class TruncatedEvent(Struct, tag_field="type", tag="truncated"):
+    """A round the provider cut off at the output limit (``finish_reason=length``).
+
+    The partial answer stays in history rather than being discarded, and the
+    model is told where it stopped (see ``notices.truncated_turn_notice``);
+    ``continued`` says whether the turn went on with another round or is waiting
+    for ``/retry``.
+    """
+
+    kept_chars: int = 0
+    continued: bool = False
+
+
 class ErrorEvent(Struct, tag_field="type", tag="error"):
     message: str
     retryable: bool = True
@@ -60,6 +73,7 @@ type AgentEvent = (
     | ToolCallEvent
     | ToolResultEvent
     | MaxRoundsEvent
+    | TruncatedEvent
     | ErrorEvent
     | CancelledEvent
     | UsageEvent

src/plyngent/agent/loop.py

@@ -43,8 +43,11 @@ from .events import (
     TextDeltaEvent,
     ToolCallEvent,
     ToolResultEvent,
+    TruncatedEvent,
     UsageEvent,
 )
+from .finish_reason import chat_finish_reason
+from .notices import truncated_turn_notice
 from .todo_nag import (
     DEFAULT_TODO_NAG_STRATEGY,
     inject_todo_nag_for_stack_with_events,
@@ -68,6 +71,10 @@ if TYPE_CHECKING:
 
 
 DEFAULT_MAX_ROUNDS = 32
+# Rounds cut off at the output limit are kept and the model carries on in another
+# round, this many times per turn; 0 stops after the truncated round (`/retry`
+# continues it from the kept partial answer).
+DEFAULT_MAX_TRUNCATION_CONTINUES = 2
 
 
 async def _call_on_limit(on_limit: LimitContinueHook, reason: str) -> bool:
@@ -150,6 +157,11 @@ def _assistant_has_payload(assistant: AssistantChatMessage) -> bool:
     return bool(isinstance(reasoning, str) and reasoning.strip())
 
 
+def _kept_chars(assistant: AssistantChatMessage) -> int:
+    """How much answer a cut-off round had written (0 if only reasoning/blocks)."""
+    return len(assistant.content) if isinstance(assistant.content, str) else 0
+
+
 def _finish_reason_value(finish: object) -> str | None:
     if finish is UNSET or finish is None:
         return None
@@ -163,20 +175,26 @@ def _validate_assistant_terminal(
     *,
     finish_reason: str | None,
     stream_terminal: bool,
-) -> None:
-    """Raise when the round is not a usable agent stop.
+) -> bool:
+    """Raise when the round is not a usable agent stop; True if it hit the output limit.
 
-    Distinguishes empty generation, truncated/filtered stops, and missing
-    stream terminals (network/client glitch) from a normal stop/tool_calls end.
+    Distinguishes empty generation, filtered stops, and missing stream terminals
+    (network/client glitch) from a normal stop/tool_calls end. A round cut off at
+    the output limit is not an error of its own: what it wrote is usable, so the
+    caller keeps it and tells the model where it stopped. A truncated round that
+    wrote nothing stays a failure — there is nothing to continue from.
     """
     reason = (finish_reason or "").lower() or None
+    canonical = chat_finish_reason(reason, has_tool_calls=False)
 
-    if reason in {"length", "content_filter"}:
-        label = "truncated (max tokens)" if reason == "length" else "content filter"
-        detail = ""
-        if isinstance(assistant.content, str) and assistant.content.strip():
-            detail = f"; partial text kept ({len(assistant.content)} chars)"
-        msg = f"model stopped early: {label}{detail}"
+    if canonical == "length":
+        if _assistant_has_payload(assistant):
+            return True
+        msg = "model stopped early: output limit reached with nothing written"
+        raise RuntimeError(msg)
+
+    if canonical == "content_filter":
+        msg = "model stopped early: content filter"
         raise RuntimeError(msg)
 
     if reason in {"failed", "incomplete", "cancelled"}:
@@ -184,7 +202,7 @@ def _validate_assistant_terminal(
         raise RuntimeError(msg)
 
     if _assistant_has_payload(assistant):
-        return
+        return False
 
     if not stream_terminal and reason is None:
         msg = (
@@ -249,7 +267,7 @@ async def _non_stream_round(
     choice = response.choices[0]
     assistant = choice.message
     finish = _finish_reason_value(choice.finish_reason)
-    _validate_assistant_terminal(
+    truncated = _validate_assistant_terminal(
         assistant,
         finish_reason=finish,
         stream_terminal=True,
@@ -260,6 +278,8 @@ async def _non_stream_round(
     if isinstance(assistant.content, str) and assistant.content:
         yield TextDeltaEvent(content=assistant.content)
     yield AssistantMessageEvent(message=assistant)
+    if truncated:
+        yield TruncatedEvent(kept_chars=_kept_chars(assistant))
     yield UsageEvent(
         usage=resolve_round_usage(response.usage, param.messages, assistant),
     )
@@ -376,12 +396,14 @@ async def _stream_round(
     # If we got payload but no finish_reason, treat as terminal (some providers
     # omit it); if empty and no finish_reason, flag as missing terminal.
     stream_terminal = saw_terminal or _assistant_has_payload(assistant)
-    _validate_assistant_terminal(
+    truncated = _validate_assistant_terminal(
         assistant,
         finish_reason=finish_reason,
         stream_terminal=stream_terminal,
     )
     yield AssistantMessageEvent(message=assistant)
+    if truncated:
+        yield TruncatedEvent(kept_chars=_kept_chars(assistant))
     yield UsageEvent(
         usage=resolve_round_usage(last_api_usage, param.messages, assistant),
     )
@@ -408,6 +430,27 @@ async def _assistant_round(
         yield event
 
 
+def _keep_truncated_round(
+    messages: list[AnyChatMessage],
+    truncated: TruncatedEvent,
+    *,
+    continued: bool,
+) -> TruncatedEvent:
+    """Keep a round cut off at the output limit and tell the model where it stopped.
+
+    The answer and its thinking blocks stay in ``messages`` (the provider verifies
+    those blocks, so dropping them would make the round uncontinuable), but the
+    round's tool calls go: a half-written call must not run, its arguments may not
+    even parse, and the model re-issues it after reading the notice. Returns the
+    event to yield, with the continuation outcome filled in.
+    """
+    last = messages[-1]
+    if isinstance(last, AssistantChatMessage) and last.tool_calls is not UNSET and last.tool_calls:
+        messages[-1] = msgspec.structs.replace(last, tool_calls=UNSET)
+    messages.append(truncated_turn_notice().to_message())
+    return msgspec.structs.replace(truncated, continued=continued)
+
+
 def _last_assistant(messages: list[AnyChatMessage], pre_len: int) -> AssistantChatMessage:
     if len(messages) <= pre_len:
         msg = "model round produced no assistant message"
@@ -448,13 +491,14 @@ async def _maybe_inject_directive_checkpoints(
     return new_band
 
 
-async def run_chat_loop(  # noqa: C901 — multi-phase tool loop
+async def run_chat_loop(  # noqa: C901, PLR0915 — multi-phase tool loop
     client: AnyLLMClient,
     messages: list[AnyChatMessage],
     *,
     model: str,
     tools: ToolRegistry | None = None,
     max_rounds: int = DEFAULT_MAX_ROUNDS,
+    max_truncation_continues: int = DEFAULT_MAX_TRUNCATION_CONTINUES,
     temperature: float | None = None,
     reasoning_effort: str = "",
     on_limit: LimitContinueHook | None = None,
@@ -481,6 +525,12 @@ async def run_chat_loop(  # noqa: C901 — multi-phase tool loop
     the provider's own default); each API surface maps it onto its own wire field
     (see ``config.reasoning``).
 
+    A round the provider cuts off at the output limit (``finish_reason=length``)
+    is kept instead of failing the turn: its answer and thinking blocks stay in
+    ``messages``, its tool calls are dropped, and a truncation notice tells the
+    model where it stopped. Up to *max_truncation_continues* rounds per turn then
+    carry on from there (0 = stop, leaving the turn for ``/retry``).
+
     *provider_tools* are hosted/provider-side tools (OpenAI Responses only, e.g.
     ``web_search``) merged into the request as opaque dicts; never executed by the
     :class:`ToolRegistry`. Ignored by non-Responses clients.
@@ -500,6 +550,7 @@ async def run_chat_loop(  # noqa: C901 — multi-phase tool loop
 
     rounds_used = 0
     allowance = max_rounds
+    truncation_continues = 0
     # Calibrate soft-compact from last model call's prompt_tokens (API preferred).
     prompt_tokens_hint: int | None = None
     sent_estimate_tokens: int | None = None
@@ -532,6 +583,7 @@ async def run_chat_loop(  # noqa: C901 — multi-phase tool loop
 
             pre_len = len(messages)
             last_usage_event: UsageEvent | None = None
+            truncated: TruncatedEvent | None = None
             async for event in _assistant_round(
                 client,
                 param,
@@ -544,9 +596,24 @@ async def run_chat_loop(  # noqa: C901 — multi-phase tool loop
                     prompt_tokens_hint = event.usage.prompt_tokens
                     sent_estimate_tokens = sent_est
                     last_usage_event = event
+                if isinstance(event, TruncatedEvent):
+                    # Yielded below, once the continuation decision is known.
+                    truncated = event
+                    continue
                 yield event
 
             assistant = _last_assistant(messages, pre_len)
+            if truncated is not None:
+                # The provider cut the round off at the output limit: keep what it
+                # wrote and tell the model where it stopped (see the helper).
+                continued = truncation_continues < max_truncation_continues
+                if continued:
+                    truncation_continues += 1
+                yield _keep_truncated_round(messages, truncated, continued=continued)
+                if continued:
+                    continue
+                return
+
             tool_calls = assistant.tool_calls
             has_tools = tool_calls is not UNSET and bool(tool_calls) and tools is not None
             if has_tools:

src/plyngent/agent/notices.py

@@ -27,6 +27,11 @@ if TYPE_CHECKING:
 # developer messages (durable directive checkpoints share the role).
 NOTICE_MARKER = "[plyngent notice"
 
+# Notice kind for a turn the provider cut off at the output limit. The turn's
+# partial answer is kept, so the agent reads such a turn as unfinished and
+# ``/retry`` continues it (see ``ChatAgent.pending_retry_text``).
+TRUNCATED_NOTICE_KIND = "truncated"
+
 
 @dataclass(frozen=True, slots=True)
 class Notice:
@@ -41,14 +46,18 @@ class Notice:
         return DeveloperChatMessage(content=f"{NOTICE_MARKER}: {self.kind}]\n{self.body.strip()}")
 
 
+def notice_of_kind(message: AnyChatMessage, kind: str) -> bool:
+    """Whether *message* is a notice of *kind*."""
+    return isinstance(message, DeveloperChatMessage) and message.content.startswith(f"{NOTICE_MARKER}: {kind}]")
+
+
 def has_notice(messages: Sequence[AnyChatMessage], kind: str) -> bool:
     """Whether *messages* already carries a notice of *kind*.
 
     Notices are persisted with the transcript, so a host asks this before
     pushing one that belongs to the session rather than to an event.
     """
-    marker = f"{NOTICE_MARKER}: {kind}]"
-    return any(isinstance(message, DeveloperChatMessage) and message.content.startswith(marker) for message in messages)
+    return any(notice_of_kind(message, kind) for message in messages)
 
 
 def format_moment(moment: datetime | None) -> str:
@@ -82,6 +91,27 @@ def resume_notice(*, last_active: datetime | None) -> Notice:
     return Notice(kind="resume", body=body, summary=summary)
 
 
+def truncated_turn_notice() -> Notice:
+    """Notice for a round the provider cut off at the output limit.
+
+    The partial answer is kept in the transcript (thinking blocks included, so
+    the provider still verifies them), which is why the model has to be told the
+    round was not finished: it continues from what it already wrote, re-issues
+    the tool call that was dropped, and keeps the remainder short enough to fit.
+    """
+    body = (
+        "Your previous round was cut off at the output limit (max_tokens). The partial answer it wrote "
+        "was kept in the transcript, and any tool call in that round was discarded — re-issue it if you "
+        "still need it. Continue from where the answer stopped instead of writing it again from the "
+        "start, and keep the rest short enough to finish: split the work, or hand off what is left."
+    )
+    return Notice(
+        kind=TRUNCATED_NOTICE_KIND,
+        body=body,
+        summary="output truncated (max_tokens); partial answer kept",
+    )
+
+
 _ASIDE_BODIES: dict[str, str] = {
     "read": (
         "Side question: this exchange is not saved to the session transcript and does not "

src/plyngent/cli/display.py

@@ -21,6 +21,7 @@ from plyngent.agent import (
     TextDeltaEvent,
     ToolCallEvent,
     ToolResultEvent,
+    TruncatedEvent,
     UsageEvent,
 )
 from plyngent.lmproto.openai_compatible.model import AssistantFunctionToolCall
@@ -1289,6 +1290,14 @@ async def render_events(  # noqa: C901, PLR0915 — one branch per event type
                 )
             else:
                 click.secho(f"\n[max rounds reached: {event.rounds}]", fg="red")
+        elif isinstance(event, TruncatedEvent):
+            flush_assistant()
+            tool_lines.close_line()
+            tail = "continuing" if event.continued else "/retry continues from here"
+            click.secho(
+                f"\n[limit] output truncated ({event.kept_chars} chars kept); {tail}",
+                fg="yellow",
+            )
         elif isinstance(event, UsageEvent):
             _ = event
         else:

tests/test_agent/test_loop.py

@@ -14,10 +14,12 @@ from plyngent.agent import (
     ToolCallEvent,
     ToolRegistry,
     ToolResultEvent,
+    TruncatedEvent,
     UsageEvent,
     run_chat_loop,
     tool,
 )
+from plyngent.agent.notices import TRUNCATED_NOTICE_KIND, notice_of_kind
 from plyngent.config.models import DatabaseConfig
 from plyngent.lmproto.openai_compatible.model import (
     AnyChatMessage,
@@ -987,20 +989,115 @@ async def test_empty_completion_raises() -> None:
         _ = [e async for e in run_chat_loop(client, messages, model="m", stream=False)]
 
 
-async def test_length_finish_raises() -> None:
+async def test_length_finish_keeps_the_partial_answer_and_continues() -> None:
     client = ScriptedClient(
         [
-            _response(
-                AssistantChatMessage(content="partial"),
-                finish_reason="length",
-            )
+            _response(AssistantChatMessage(content="partial"), finish_reason="length"),
+            _response(AssistantChatMessage(content="rest")),
         ]
     )
     messages: list[AnyChatMessage] = [UserChatMessage(content="hi")]
-    with pytest.raises(RuntimeError, match="truncated"):
+    events = [e async for e in run_chat_loop(client, messages, model="m", stream=False)]
+
+    truncated = [e for e in events if isinstance(e, TruncatedEvent)]
+    assert len(truncated) == 1
+    assert truncated[0].kept_chars == len("partial")
+    assert truncated[0].continued
+    # The partial answer stays in history under a truncation notice, and the
+    # continuation round is sent that history — the model continues its answer
+    # rather than writing it again from the start.
+    assert isinstance(messages[1], AssistantChatMessage)
+    assert messages[1].content == "partial"
+    assert notice_of_kind(messages[2], TRUNCATED_NOTICE_KIND)
+    assert isinstance(messages[3], AssistantChatMessage)
+    assert messages[3].content == "rest"
+    assert any(notice_of_kind(m, TRUNCATED_NOTICE_KIND) for m in client.calls[1].messages)
+
+
+async def test_length_finish_stops_once_the_continuation_budget_is_spent() -> None:
+    client = ScriptedClient([_response(AssistantChatMessage(content="partial"), finish_reason="length")] * 2)
+    messages: list[AnyChatMessage] = [UserChatMessage(content="hi")]
+    events = [
+        e
+        async for e in run_chat_loop(
+            client,
+            messages,
+            model="m",
+            stream=False,
+            max_truncation_continues=1,
+        )
+    ]
+
+    assert [e.continued for e in events if isinstance(e, TruncatedEvent)] == [True, False]
+    assert len(client.calls) == 2
+    # Nothing raised: the turn ends with the partial answer kept, so `/retry`
+    # continues it instead of regenerating.
+    assert isinstance(messages[-2], AssistantChatMessage)
+    assert messages[-2].content == "partial"
+    assert notice_of_kind(messages[-1], TRUNCATED_NOTICE_KIND)
+
+
+async def test_length_finish_drops_the_rounds_tool_calls() -> None:
+    ran: list[str] = []
+
+    @tool(name="boom", register=False)
+    async def _boom(argument: str) -> str:
+        ran.append(argument)
+        return "ran"
+
+    call = AssistantFunctionToolCall(
+        id="c1",
+        function=AssistantFunctionTool(name="boom", arguments='{"argument": "x"'),
+    )
+    client = ScriptedClient(
+        [
+            _response(
+                AssistantChatMessage(content="partial", tool_calls=[call]),
+                finish_reason="length",
+            ),
+            _response(AssistantChatMessage(content="done")),
+        ]
+    )
+    messages: list[AnyChatMessage] = [UserChatMessage(content="hi")]
+    events = [e async for e in run_chat_loop(client, messages, model="m", tools=ToolRegistry([_boom]), stream=False)]
+
+    # A call cut off mid-write is not replayed: the model re-issues it after
+    # reading the notice.
+    assert ran == []
+    assert not [e for e in events if isinstance(e, (ToolCallEvent, ToolResultEvent))]
+    kept = messages[1]
+    assert isinstance(kept, AssistantChatMessage)
+    assert kept.content == "partial"
+    assert kept.tool_calls is UNSET
+
+
+async def test_length_finish_without_content_still_raises() -> None:
+    client = ScriptedClient([_response(AssistantChatMessage(content=None), finish_reason="length")])
+    messages: list[AnyChatMessage] = [UserChatMessage(content="hi")]
+    with pytest.raises(RuntimeError, match="output limit reached with nothing written"):
         _ = [e async for e in run_chat_loop(client, messages, model="m", stream=False)]
 
 
+async def test_truncated_turn_is_retryable() -> None:
+    store = await MemoryStore.open(DatabaseConfig())
+    session = await store.create_session(name="t")
+    client = ScriptedClient(
+        [
+            _response(AssistantChatMessage(content="partial"), finish_reason="length"),
+            _response(AssistantChatMessage(content="rest")),
+        ]
+    )
+    agent = ChatAgent(client, model="m", memory=store, session_id=session.sid, max_truncation_continues=0, stream=False)
+    _ = [e async for e in agent.run("hi")]
+
+    # Kept, not rolled back: the turn is unfinished, so retry continues it.
+    assert agent.pending_retry_text == "hi"
+    _ = [e async for e in agent.retry()]
+    assert any(notice_of_kind(m, TRUNCATED_NOTICE_KIND) for m in client.calls[1].messages)
+    assert agent.pending_retry_text is None
+    await store.close()
+
+
 async def test_content_filter_finish_raises() -> None:
     client = ScriptedClient(
         [

tests/test_agent/test_notices.py

@@ -2,7 +2,16 @@ from __future__ import annotations
 
 from datetime import UTC, datetime, timedelta, timezone
 
-from plyngent.agent import ChatAgent, Notice, aside_notice, format_moment, has_notice, resume_notice, skill_tools_notice
+from plyngent.agent import (
+    ChatAgent,
+    Notice,
+    aside_notice,
+    format_moment,
+    has_notice,
+    resume_notice,
+    skill_tools_notice,
+    truncated_turn_notice,
+)
 from plyngent.agent.chat import incomplete_turn_user_text
 from plyngent.config.models import DatabaseConfig
 from plyngent.lmproto.openai_compatible.model import (
@@ -124,3 +133,26 @@ def test_trailing_developer_message_keeps_incomplete_turn_detectable() -> None:
     # A finished turn (trailing assistant) stays non-retryable past a notice.
     done = [UserChatMessage(content="do it"), AssistantChatMessage(content="ok"), notice]
     assert incomplete_turn_user_text(done) is None
+
+
+def test_truncated_turn_notice_keeps_the_partial_answer_retryable() -> None:
+    """A kept partial answer is unfinished work, so retry continues it."""
+    tail = [
+        UserChatMessage(content="do it"),
+        AssistantChatMessage(content="partial answer"),
+        truncated_turn_notice().to_message(),
+    ]
+    assert incomplete_turn_user_text(tail) == "do it"
+    # The same tail without the truncation notice is a finished turn.
+    assert incomplete_turn_user_text(tail[:2]) is None
+
+
+def test_truncated_turn_notice_tells_the_model_where_it_stopped() -> None:
+    notice = truncated_turn_notice()
+    assert notice.kind == "truncated"
+    assert notice.to_message().content.startswith("[plyngent notice: truncated]")
+    assert "max_tokens" in notice.body
+    # The dropped call and the kept answer are both spelled out.
+    assert "discarded" in notice.body
+    assert "kept in the transcript" in notice.body
+    assert "max_tokens" in notice.summary

tests/test_cli/test_display.py

@@ -2,7 +2,14 @@ from __future__ import annotations
 
 from typing import TYPE_CHECKING
 
-from plyngent.agent import ErrorEvent, ReasoningDeltaEvent, TextDeltaEvent, ToolCallEvent, ToolResultEvent
+from plyngent.agent import (
+    ErrorEvent,
+    ReasoningDeltaEvent,
+    TextDeltaEvent,
+    ToolCallEvent,
+    ToolResultEvent,
+    TruncatedEvent,
+)
 from plyngent.cli.display import (
     _RUN_BATCH_CMD_LIMIT,
     _clear_streamed_lines,
@@ -1257,3 +1264,12 @@ async def test_pretty_prefix_closed_before_error_line(
     assert "* Read 'a.txt' \n" in out
     assert "[error] source=tool boom\n" in out
     assert "* Read 'a.txt' (error)\n" in out
+
+
+async def test_render_truncated_round(capsys: pytest.CaptureFixture[str]) -> None:
+    """A round cut off at the output limit says so, and how the turn goes on."""
+    await render_events(_aiter([TruncatedEvent(kept_chars=42, continued=True)]))
+    assert "[limit] output truncated (42 chars kept); continuing\n" in capsys.readouterr().out
+
+    await render_events(_aiter([TruncatedEvent(kept_chars=42, continued=False)]))
+    assert "[limit] output truncated (42 chars kept); /retry continues from here\n" in capsys.readouterr().out