cli/config: --auto-continue flag and [agent] auto_continue_limits

src/plyngent/cli/app.py

@@ -124,9 +124,14 @@ def _read_prompt_text(prompt: str | None, *, stdin_isatty: bool) -> str | None:
     return text or None
 
 
-def _setup_hooks(*, interactive: bool) -> None:
-    """Install interactive limit hooks (workspace policy is set on ReplState)."""
-    if interactive:
+def _setup_hooks(*, interactive: bool, auto_continue: bool) -> None:
+    """Install limit hooks (workspace policy is set on ReplState).
+
+    ``auto_continue`` keeps the PTY/limit hook installed for one-shot runs so
+    ``--auto-continue`` / ``[agent] auto_continue_limits`` can raise limits
+    without a prompt; otherwise non-interactive runs keep today's deny.
+    """
+    if interactive or auto_continue:
         install_cli_limit_hooks()
     else:
         from plyngent.tools.process.pty_session import PtyManager
@@ -221,6 +226,7 @@ async def _run_chat(  # noqa: C901, PLR0912, PLR0915 — chat orchestration
     prompt_text: str | None,
     stream: bool,
     yes: bool,
+    auto_continue: bool,
     quiet: bool,
 ) -> int:
     oneshot = prompt_text is not None
@@ -236,7 +242,8 @@ async def _run_chat(  # noqa: C901, PLR0912, PLR0915 — chat orchestration
         if store.recoverable_providers:
             _warn_recoverable_providers(store.recoverable_providers)
 
-    _setup_hooks(interactive=interactive)
+    auto_effective = auto_continue or store.agent_config.auto_continue_limits
+    _setup_hooks(interactive=interactive, auto_continue=auto_effective)
     # --yes forces sticky YOLO; else derive from config.confirm_destructive.
     from plyngent.cli.state import YoloMode
 
@@ -315,6 +322,7 @@ async def _run_chat(  # noqa: C901, PLR0912, PLR0915 — chat orchestration
             max_rounds=max_rounds,
             stream_enabled=stream,
             interactive_limits=interactive,
+            auto_continue_limits=auto_effective,
             yolo=yolo,
             mcp_manager=mcp_manager,
         )
@@ -480,6 +488,12 @@ def main(ctx: click.Context, log_level: str) -> None:
     default=False,
     help="Enable YOLO: skip destructive-tool confirms (sticky for this process).",
 )
+@click.option(
+    "--auto-continue",
+    is_flag=True,
+    default=False,
+    help="Auto-raise tool/PTY limits without prompting (like answering yyy).",
+)
 @click.option(
     "--quiet",
     is_flag=True,
@@ -498,6 +512,7 @@ def chat_cmd(
     prompt: str | None,
     stream: bool,  # noqa: FBT001
     yes: bool,  # noqa: FBT001
+    auto_continue: bool,  # noqa: FBT001
     quiet: bool,  # noqa: FBT001
 ) -> None:
     """Interactive chat REPL, or one-shot with ``-p`` / stdin.
@@ -538,6 +553,7 @@ def chat_cmd(
             prompt_text=prompt_text,
             stream=stream,
             yes=yes,
+            auto_continue=auto_continue,
             quiet=quiet,
         )
     )

src/plyngent/cli/repl.py

@@ -36,14 +36,17 @@ def _echo_interrupted() -> None:
 async def run_repl(state: ReplState) -> None:
     """Interactive chat loop with readline editing, history, and Tab completion."""
     setup_readline(state)
+    from plyngent.cli.limits import auto_continue_enabled
+
     yolo = state.effective_yolo()
     yolo_part = f"  yolo={yolo}" if yolo != "off" else ""
+    auto_part = "  limit_auto=on" if auto_continue_enabled() else ""
     click.echo(
         f"plyngent chat  provider={state.provider_name}  model={state.model}  "
         f"session={state.session_id}  tools={'on' if state.tools_enabled else 'off'}  "
         f"rounds={state.max_rounds}  messages={len(state.agent.messages)}  "
         f"stream={'on' if state.agent.stream else 'off'}  "
-        f"verbose={'on' if state.verbose else 'off'}{yolo_part}"
+        f"verbose={'on' if state.verbose else 'off'}{yolo_part}{auto_part}"
     )
     click.echo('Type /help for commands. Multiline: """ … """. Empty line is ignored.')
 

src/plyngent/cli/state.py

@@ -69,6 +69,8 @@ class ReplState:
     markdown_enabled: bool = True
     # One-shot / scripts: never prompt to raise tool-loop limits.
     interactive_limits: bool = True
+    # Auto-raise tool/PTY limits without prompting (--auto-continue / config).
+    auto_continue_limits: bool = False
     # Soft destructive-tool confirms: None → derive from config.confirm_destructive.
     # off = confirm; on = skip (sticky); once = skip next user turn then off.
     yolo: YoloMode | None = None
@@ -97,6 +99,9 @@ class ReplState:
         self.instance_state.workspace_root = self.workspace
         self.instance_state.workspace.root = self.workspace
         self._install_config_access()
+        from plyngent.cli.limits import set_auto_continue_default
+
+        set_auto_continue_default(enabled=self.auto_continue_limits)
         self.session_state = self._session_data_for_todo()
         self.agent = self._make_agent()
         self.sync_display_flags()
@@ -340,7 +345,7 @@ class ReplState:
         return "\n\n".join(parts)
 
     def _make_agent(self) -> ChatAgent:
-        from plyngent.cli.limits import prompt_continue_limit_async
+        from plyngent.cli.limits import auto_continue_enabled, prompt_continue_limit_async
         from plyngent.config import compose_agent_system_content
 
         agent_cfg = self.config.agent_config
@@ -350,7 +355,7 @@ class ReplState:
             agent_cfg.tool_directives,
             mcp_text,
         )
-        on_limit = prompt_continue_limit_async if self.interactive_limits else None
+        on_limit = prompt_continue_limit_async if (self.interactive_limits or auto_continue_enabled()) else None
         peak = 0
         band = 0
         last_req = None

src/plyngent/config/models.py

@@ -117,6 +117,9 @@ class AgentConfig(Struct, omit_defaults=True):
     # Static directory pre-allow (resolved path → mode); never prompts.
     # Denylist still applies, and the path must exist when chat starts.
     allow_paths: dict[str, AllowPathMode] = field(default_factory=dict)
+    # Auto-raise tool/PTY limits without prompting (same as answering ``yyy``);
+    # process-wide, so every turn skips the limit confirm.
+    auto_continue_limits: bool = False
     max_context_tokens: int = 200_000
 
     # How to inject todo stack nags into model context (see agent/todo_nag.py).