fix: worker context token

core/framework/server/queen_orchestrator.py

@@ -359,6 +359,7 @@ async def create_queen(
         queen_goal,
         queen_loop_config as _base_loop_config,
     )
+    from framework.config import get_max_tokens as _get_max_tokens
     from framework.agents.queen.nodes import (
         _QUEEN_INCUBATING_TOOLS,
         _QUEEN_INDEPENDENT_TOOLS,
@@ -982,7 +983,12 @@ async def create_queen(
                 llm=session.llm,
                 available_tools=queen_tools,
                 goal_context=queen_goal.to_prompt_context(),
-                max_tokens=lc.get("max_tokens", 8192),
+                # Honor configuration.json (llm.max_tokens) instead of
+                # hard-defaulting to 8192. The legacy fallback ignored both
+                # the user's saved ceiling AND the model's actual output
+                # capacity (e.g. glm-5.1 / kimi-k2.5 both support 32k out),
+                # which silently truncated long tool-emitting turns.
+                max_tokens=lc.get("max_tokens", _get_max_tokens()),
                 stream_id="queen",
                 execution_id=session.id,
                 dynamic_tools_provider=phase_state.get_current_tools,

core/framework/server/session_manager.py

@@ -19,7 +19,7 @@ from datetime import datetime
 from pathlib import Path
 from typing import Any, Literal
 
-from framework.config import QUEENS_DIR
+from framework.config import QUEENS_DIR, get_max_tokens
 from framework.host.triggers import TriggerDefinition
 
 logger = logging.getLogger(__name__)
@@ -700,7 +700,10 @@ class SessionManager:
             available_tools=all_tools,
             goal_context=goal.to_prompt_context(),
             goal=goal,
-            max_tokens=8192,
+            # Worker output cap — pull from configuration.json instead of
+            # hard-coding 8192. glm-5.1/kimi-k2.5 both support 32k out, and
+            # capping at 8k silently truncates long worker turns mid-tool.
+            max_tokens=get_max_tokens(),
             stream_id=worker_name,
             execution_id=worker_name,
             identity_prompt=worker_data.get("identity_prompt", ""),