feat(budget): make tool result persistence thresholds configurable

Add BudgetConfig dataclass to centralize and make overridable the
hardcoded constants (50K per-result, 200K per-turn, 2K preview) that
control when tool outputs get persisted to sandbox. Configurable at
the RL environment level via HermesAgentEnvConfig fields, threaded
through HermesAgentLoop to the storage layer.

Resolution: pinned (read_file=inf) > env config overrides > registry
per-tool > default. CLI override: --env.turn_budget_chars 80000

environments/agent_loop.py

@@ -140,6 +140,7 @@ class HermesAgentLoop:
         temperature: float = 1.0,
         max_tokens: Optional[int] = None,
         extra_body: Optional[Dict[str, Any]] = None,
+        budget_config: Optional["BudgetConfig"] = None,
     ):
         """
         Initialize the agent loop.
@@ -156,7 +157,11 @@ class HermesAgentLoop:
             extra_body: Extra parameters passed to the OpenAI client's create() call.
                         Used for OpenRouter provider preferences, transforms, etc.
                         e.g. {"provider": {"ignore": ["DeepInfra"]}}
+            budget_config: Tool result persistence budget. Controls per-tool
+                        thresholds, per-turn aggregate budget, and preview size.
+                        If None, uses DEFAULT_BUDGET (current hardcoded values).
         """
+        from tools.budget_config import DEFAULT_BUDGET
         self.server = server
         self.tool_schemas = tool_schemas
         self.valid_tool_names = valid_tool_names
@@ -165,6 +170,7 @@ class HermesAgentLoop:
         self.temperature = temperature
         self.max_tokens = max_tokens
         self.extra_body = extra_body
+        self.budget_config = budget_config or DEFAULT_BUDGET
 
     async def run(self, messages: List[Dict[str, Any]]) -> AgentResult:
         """
@@ -455,6 +461,8 @@ class HermesAgentLoop:
                             tool_name=tool_name,
                             tool_use_id=tc_id,
                             env=get_active_env(self.task_id),
+                            threshold=self.budget_config.resolve_threshold(tool_name),
+                            preview_size=self.budget_config.preview_size,
                         )
                     except Exception:
                         pass  # Persistence is best-effort in eval path
@@ -470,7 +478,12 @@ class HermesAgentLoop:
                 try:
                     num_tcs = len(assistant_msg.tool_calls)
                     if num_tcs > 0:
-                        enforce_turn_budget(messages[-num_tcs:], env=get_active_env(self.task_id))
+                        enforce_turn_budget(
+                            messages[-num_tcs:],
+                            env=get_active_env(self.task_id),
+                            budget=self.budget_config.turn_budget,
+                            preview_size=self.budget_config.preview_size,
+                        )
                 except Exception:
                     pass
 

environments/agentic_opd_env.py

@@ -1048,6 +1048,7 @@ class AgenticOPDEnv(HermesAgentBaseEnv):
                     temperature=0.0,
                     max_tokens=self.config.max_token_length,
                     extra_body=self.config.extra_body,
+                    budget_config=self.config.build_budget_config(),
                 )
                 result = await agent.run(messages)
 

environments/benchmarks/terminalbench_2/terminalbench2_env.py

@@ -541,6 +541,7 @@ class TerminalBench2EvalEnv(HermesAgentBaseEnv):
                         temperature=self.config.agent_temperature,
                         max_tokens=self.config.max_token_length,
                         extra_body=self.config.extra_body,
+                        budget_config=self.config.build_budget_config(),
                     )
                     result = await agent.run(messages)
             else:
@@ -553,6 +554,7 @@ class TerminalBench2EvalEnv(HermesAgentBaseEnv):
                     temperature=self.config.agent_temperature,
                     max_tokens=self.config.max_token_length,
                     extra_body=self.config.extra_body,
+                    budget_config=self.config.build_budget_config(),
                 )
                 result = await agent.run(messages)
 

environments/benchmarks/yc_bench/yc_bench_env.py

@@ -549,6 +549,7 @@ class YCBenchEvalEnv(HermesAgentBaseEnv):
                 temperature=self.config.agent_temperature,
                 max_tokens=self.config.max_token_length,
                 extra_body=self.config.extra_body,
+                budget_config=self.config.build_budget_config(),
             )
             result = await agent.run(messages)
 

environments/hermes_base_env.py

@@ -62,6 +62,11 @@ from atroposlib.type_definitions import Item
 
 from environments.agent_loop import AgentResult, HermesAgentLoop
 from environments.tool_context import ToolContext
+from tools.budget_config import (
+    DEFAULT_RESULT_SIZE_CHARS,
+    DEFAULT_TURN_BUDGET_CHARS,
+    DEFAULT_PREVIEW_SIZE_CHARS,
+)
 
 # Import hermes-agent toolset infrastructure
 from model_tools import get_tool_definitions
@@ -160,6 +165,32 @@ class HermesAgentEnvConfig(BaseEnvConfig):
         "Options: hermes, mistral, llama3_json, qwen, deepseek_v3, etc.",
     )
 
+    # --- Tool result budget ---
+    # Defaults imported from tools.budget_config (single source of truth).
+    default_result_size_chars: int = Field(
+        default=DEFAULT_RESULT_SIZE_CHARS,
+        description="Default per-tool threshold (chars) for persisting large results "
+        "to sandbox. Results exceeding this are written to /tmp/hermes-results/ "
+        "and replaced with a preview. Per-tool registry values take precedence "
+        "unless overridden via tool_result_overrides.",
+    )
+    turn_budget_chars: int = Field(
+        default=DEFAULT_TURN_BUDGET_CHARS,
+        description="Aggregate char budget per assistant turn. If all tool results "
+        "in a single turn exceed this, the largest are persisted to disk first.",
+    )
+    preview_size_chars: int = Field(
+        default=DEFAULT_PREVIEW_SIZE_CHARS,
+        description="Size of the inline preview shown after a tool result is persisted.",
+    )
+    tool_result_overrides: Optional[Dict[str, int]] = Field(
+        default=None,
+        description="Per-tool threshold overrides (chars). Keys are tool names, "
+        "values are char thresholds. Overrides both the default and registry "
+        "per-tool values. Example: {'terminal': 10000, 'search_files': 5000}. "
+        "Note: read_file is pinned to infinity and cannot be overridden.",
+    )
+
     # --- Provider-specific parameters ---
     # Passed as extra_body to the OpenAI client's chat.completions.create() call.
     # Useful for OpenRouter provider preferences, transforms, route settings, etc.
@@ -176,6 +207,16 @@ class HermesAgentEnvConfig(BaseEnvConfig):
         "transforms, and other provider-specific settings.",
     )
 
+    def build_budget_config(self):
+        """Build a BudgetConfig from env config fields."""
+        from tools.budget_config import BudgetConfig
+        return BudgetConfig(
+            default_result_size=self.default_result_size_chars,
+            turn_budget=self.turn_budget_chars,
+            preview_size=self.preview_size_chars,
+            tool_overrides=dict(self.tool_result_overrides) if self.tool_result_overrides else {},
+        )
+
 
 class HermesAgentBaseEnv(BaseEnv):
     """
@@ -490,6 +531,7 @@ class HermesAgentBaseEnv(BaseEnv):
                         temperature=self.config.agent_temperature,
                         max_tokens=self.config.max_token_length,
                         extra_body=self.config.extra_body,
+                        budget_config=self.config.build_budget_config(),
                     )
                     result = await agent.run(messages)
             except NotImplementedError:
@@ -507,6 +549,7 @@ class HermesAgentBaseEnv(BaseEnv):
                     temperature=self.config.agent_temperature,
                     max_tokens=self.config.max_token_length,
                     extra_body=self.config.extra_body,
+                    budget_config=self.config.build_budget_config(),
                 )
                 result = await agent.run(messages)
         else:
@@ -520,6 +563,7 @@ class HermesAgentBaseEnv(BaseEnv):
                 temperature=self.config.agent_temperature,
                 max_tokens=self.config.max_token_length,
                 extra_body=self.config.extra_body,
+                budget_config=self.config.build_budget_config(),
             )
             result = await agent.run(messages)
 

environments/web_research_env.py

@@ -472,6 +472,7 @@ class WebResearchEnv(HermesAgentBaseEnv):
                     temperature=0.0,  # Deterministic for eval
                     max_tokens=self.config.max_token_length,
                     extra_body=self.config.extra_body,
+                    budget_config=self.config.build_budget_config(),
                 )
                 result = await agent.run(messages)