Removing old patches

When the API doesn't provide a call_id for tool calls, the fallback
generated a random uuid4 hex. This made every API call's input unique
when replayed, preventing OpenAI's prompt cache from matching the
prefix across turns.

Replaced all four uuid4 fallback sites with a deterministic hash of
(function_name, arguments, position_index). The same tool call now
always produces the same fallback call_id, preserving cache-friendly
input stability.

Affected code paths:
- _chat_messages_to_responses_input() — Codex input reconstruction
- _normalize_codex_response() — function_call and custom_tool_call
- _build_assistant_message() — assistant message construction

environments/__init__.py

@@ -13,6 +13,7 @@ Core layers:
 Concrete environments:
     - terminal_test_env/: Simple file-creation tasks for testing the stack
     - hermes_swe_env/: SWE-bench style tasks with Modal sandboxes
+    - endless_terminals/: Terminal tasks from HuggingFace dataset with Apptainer containers
 
 Benchmarks (eval-only):
     - benchmarks/terminalbench_2/: Terminal-Bench 2.0 evaluation

environments/endless_terminals/__init__.py

@@ -0,0 +1,5 @@
+"""Endless Terminals Environment - Terminal task training from HuggingFace dataset."""
+
+from .endless_terminals_env import EndlessTerminalsEnv, EndlessTerminalsEnvConfig
+
+__all__ = ["EndlessTerminalsEnv", "EndlessTerminalsEnvConfig"]

environments/endless_terminals/tinker_qwen.yaml

@@ -0,0 +1,91 @@
+# Endless Terminals - Qwen3-4B-Instruct-2507
+# Single config for both trainer (launch_training.py) and env (endless_terminals_env.py serve)
+#
+# Usage:
+#   Terminal 1: run-api
+#   Terminal 2: cd tinker-atropos && python launch_training.py --config ../environments/endless_terminals/tinker_qwen.yaml
+#   Terminal 3: python environments/endless_terminals/endless_terminals_env.py serve --config environments/endless_terminals/tinker_qwen.yaml
+
+env:
+  # Toolsets
+  enabled_toolsets: ["terminal", "file"]
+
+  # Model / tokenizer
+  tokenizer_name: "Qwen/Qwen3-4B-Instruct-2507"
+
+  # Agent configuration
+  max_agent_turns: 16
+  max_token_length: 2048
+  agent_temperature: 0.6
+  extra_body:
+    chat_template_kwargs:
+      enable_thinking: false
+  tool_call_parser: "hermes"
+
+  # Terminal backend
+  terminal_backend: "docker"
+
+  # Dataset settings
+  use_dataset: true
+  dataset_name: "obiwan96/endless-terminals"
+  dataset_split: "train"
+  dataset_cache_dir: "~/.cache/huggingface/datasets"
+  tasks_base_dir: "/Users/samherring/Desktop/Projects/Hermes-Agent/endless-terminals"
+
+  # Test execution
+  test_timeout_s: 180
+  default_docker_image: "ubuntu:22.04"
+  max_concurrent_containers: 16
+
+  # Training configuration
+  group_size: 16
+  batch_size: 64          # 4 groups × 16 rollouts per step
+  total_steps: 500
+  steps_per_eval: 5
+  min_items_sent_before_logging: 1
+  ensure_scores_are_not_same: true
+  max_num_workers: 2048
+  worker_timeout: 3600
+  inference_weight: 1.0
+  eval_limit_ratio: 0.1
+  rollout_server_url: "http://localhost:8000"
+
+  # Evaluation configuration
+  num_eval_tasks: 20
+  eval_split_ratio: 0.1
+
+  # Logging
+  use_wandb: true
+  wandb_name: "endless-terminals-qwen3-4b"
+
+  # System prompt
+  system_prompt: >
+    You are a skilled Linux system administrator and programmer.
+    You have access to a terminal and file tools to complete system administration
+    and programming tasks. Use the tools effectively to solve the given task,
+    and verify your solution works correctly before finishing.
+    Keep each command short and focused — break complex tasks into multiple steps
+    rather than writing long one-liners.
+
+tinker:
+  lora_rank: 32
+  learning_rate: 0.0000005
+  max_token_trainer_length: 32768
+  checkpoint_dir: "./temp/"
+  save_checkpoint_interval: 50
+  wandb_project: "endless-terminals"
+  wandb_group: null
+  wandb_run_name: "qwen3-4b"
+  tool_call_parser: "hermes"
+
+openai:
+  - model_name: "Qwen/Qwen3-4B-Instruct-2507"
+    base_url: "http://localhost:8001/v1"
+    api_key: "x"
+    weight: 1.0
+    num_requests_for_eval: 64
+    timeout: 600
+    server_type: "sglang"
+
+slurm: false
+testing: false

environments/hermes_base_env.py

@@ -298,7 +298,6 @@ class HermesAgentBaseEnv(BaseEnv):
             return False
 
         server = self.server.servers[0]
-        # If the server is an OpenAI server (not VLLM/SGLang), use direct mode
         from atroposlib.envs.server_handling.openai_server import OpenAIServer
         return not isinstance(server, OpenAIServer)
 

environments/tool_call_parsers/hermes_parser.py

@@ -48,7 +48,13 @@ class HermesToolCallParser(ToolCallParser):
                 if not raw_json.strip():
                     continue
 
-                tc_data = json.loads(raw_json)
+                try:
+                    tc_data = json.loads(raw_json)
+                except json.JSONDecodeError:
+                    # Fix invalid backslash escapes from shell commands in JSON strings
+                    # e.g. \s \w \d \n (unescaped) → \\s \\w \\d \\n
+                    fixed = re.sub(r'\\([^"\\/bfnrtu0-9\n])', r'\\\\\1', raw_json)
+                    tc_data = json.loads(fixed)
                 tool_calls.append(
                     ChatCompletionMessageToolCall(
                         id=f"call_{uuid.uuid4().hex[:8]}",

run_agent.py

@@ -2907,6 +2907,19 @@ class AIAgent:
             })
         return converted or None
 
+    @staticmethod
+    def _deterministic_call_id(fn_name: str, arguments: str, index: int = 0) -> str:
+        """Generate a deterministic call_id from tool call content.
+
+        Used as a fallback when the API doesn't provide a call_id.
+        Deterministic IDs prevent cache invalidation — random UUIDs would
+        make every API call's prefix unique, breaking OpenAI's prompt cache.
+        """
+        import hashlib
+        seed = f"{fn_name}:{arguments}:{index}"
+        digest = hashlib.sha256(seed.encode("utf-8", errors="replace")).hexdigest()[:12]
+        return f"call_{digest}"
+
     @staticmethod
     def _split_responses_tool_id(raw_id: Any) -> tuple[Optional[str], Optional[str]]:
         """Split a stored tool id into (call_id, response_item_id)."""
@@ -3013,7 +3026,8 @@ class AIAgent:
                                 ):
                                     call_id = f"call_{embedded_response_item_id[len('fc_'):]}"
                                 else:
-                                    call_id = f"call_{uuid.uuid4().hex[:12]}"
+                                    _raw_args = str(fn.get("arguments", "{}"))
+                                    call_id = self._deterministic_call_id(fn_name, _raw_args, len(items))
                             call_id = call_id.strip()
 
                             arguments = fn.get("arguments", "{}")
@@ -3377,7 +3391,7 @@ class AIAgent:
                 embedded_call_id, _ = self._split_responses_tool_id(raw_item_id)
                 call_id = raw_call_id if isinstance(raw_call_id, str) and raw_call_id.strip() else embedded_call_id
                 if not isinstance(call_id, str) or not call_id.strip():
-                    call_id = f"call_{uuid.uuid4().hex[:12]}"
+                    call_id = self._deterministic_call_id(fn_name, arguments, len(tool_calls))
                 call_id = call_id.strip()
                 response_item_id = raw_item_id if isinstance(raw_item_id, str) else None
                 response_item_id = self._derive_responses_function_call_id(call_id, response_item_id)
@@ -3398,7 +3412,7 @@ class AIAgent:
                 embedded_call_id, _ = self._split_responses_tool_id(raw_item_id)
                 call_id = raw_call_id if isinstance(raw_call_id, str) and raw_call_id.strip() else embedded_call_id
                 if not isinstance(call_id, str) or not call_id.strip():
-                    call_id = f"call_{uuid.uuid4().hex[:12]}"
+                    call_id = self._deterministic_call_id(fn_name, arguments, len(tool_calls))
                 call_id = call_id.strip()
                 response_item_id = raw_item_id if isinstance(raw_item_id, str) else None
                 response_item_id = self._derive_responses_function_call_id(call_id, response_item_id)
@@ -4933,7 +4947,10 @@ class AIAgent:
                     if isinstance(raw_id, str) and raw_id.strip():
                         call_id = raw_id.strip()
                     else:
-                        call_id = f"call_{uuid.uuid4().hex[:12]}"
+                        _fn = getattr(tool_call, "function", None)
+                        _fn_name = getattr(_fn, "name", "") if _fn else ""
+                        _fn_args = getattr(_fn, "arguments", "{}") if _fn else "{}"
+                        call_id = self._deterministic_call_id(_fn_name, _fn_args, len(tool_calls))
                 call_id = call_id.strip()
 
                 response_item_id = getattr(tool_call, "response_item_id", None)