# tinker_cookbook.tool_use.build_agent_tool_env

### [**tinker_cookbook.tool_use.build_agent_tool_env**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/tool_use/agent_tool_message_env.py#L361)(*renderer*, *tools*, *initial_messages*, *reward_fn*, *rollout_config*, *model_name*, *max_turns*, *failed_parse_reward*, *terminate_on_parse_error*, *max_tool_calls*, *max_trajectory_tokens*, *max_generation_tokens*, *context_overflow_reward*, *terminate_on_length*, *parse_error_policy*)

Convenience method to build an EnvFromMessageEnv for tool-using agents.

The primary configuration surface is `rollout_config`: one composite `~tinker_cookbook.rl.rollout_presets.RolloutConfig` (e.g. from `~tinker_cookbook.rl.rollout_presets.simple` or `~tinker_cookbook.rl.rollout_presets.agentic`) that drives the env-side knobs here, the runner-side budgets when the same config is passed to `run_rollout`, and the reward semantics when its `termination` is passed to `do_group_rollout`. The individual keyword arguments below remain supported; where both are given, the explicit keyword wins.

**Parameters:**

- [**renderer**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/tool_use/agent_tool_message_env.py#L362) (*[Renderer](https://tinker-docs.thinkingmachines.ai/cookbook/api-reference/renderers/renderer/index.md)*) – The renderer for tokenizing messages.
- [**tools**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/tool_use/agent_tool_message_env.py#L363) (*list\[[Tool](https://tinker-docs.thinkingmachines.ai/cookbook/api-reference/tool_use/types_tool/index.md)\]*) – List of tools the agent can call (must implement Tool protocol).
- [**initial_messages**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/tool_use/agent_tool_message_env.py#L364) (*list\[[Message](https://tinker-docs.thinkingmachines.ai/cookbook/api-reference/renderers/message/index.md)\]*) – Initial conversation history (system prompt, user message, etc.).
- [**reward_fn**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/tool_use/agent_tool_message_env.py#L365) (*RewardFn*) – Function that grades a completed episode. Takes the message history and returns (reward, metrics). Called once at episode end. Receives the full history by default; with a rollout_config whose termination policy is set, it receives only the completion suffix (messages generated during the rollout) unless `pass_all_messages_to_grader` is True, and is bounded by `grader_timeout_seconds` when set.
- [**rollout_config**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/tool_use/agent_tool_message_env.py#L367) (*RolloutConfig | None*) – Composite rollout configuration. Applies the env-side
- [**model_name**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/tool_use/agent_tool_message_env.py#L368) (*str | None*) – The model this env will run against. When set and `rollout_config` is not, the model's default configuration applies (`~tinker_cookbook.rl.rollout_presets.default_rollout_config_for_model`: `thinkingmachines/Inkling` models default to `~tinker_cookbook.rl.rollout_presets.agentic`). Pass `rollout_config=simple()` to opt out of a model default.
- [**max_turns**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/tool_use/agent_tool_message_env.py#L369) (*int | None*) – Maximum turns before episode ends. Default `None` means `rollout_config.limits.max_turns` when set, else 5.
- [**failed_parse_reward**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/tool_use/agent_tool_message_env.py#L370) (*float*) – Reward when model output fails to parse. Applied both when the renderer cannot parse the response and when a turn's tool calls are all malformed (`unparsed_tool_calls`).
- [**terminate_on_parse_error**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/tool_use/agent_tool_message_env.py#L371) (*bool*) – Whether a parse failure ends the episode. Defaults to True.
- [**max_tool_calls**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/tool_use/agent_tool_message_env.py#L372) (*int | None*) – Maximum tool calls per episode (checked pre-dispatch and mid-batch; the episode ends with StopReason.MAX_TOOL_CALLS). Default None = no cap. A rollout runner configured with `RolloutLimits.max_tool_calls` also sets this (the tighter cap wins).
- [**max_trajectory_tokens**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/tool_use/agent_tool_message_env.py#L373) (*int | None*) – Maximum tokens in trajectory before terminating episode.
- [**max_generation_tokens**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/tool_use/agent_tool_message_env.py#L374) (*int | None*) – Maximum tokens per generation. When set, the episode terminates if the trajectory + generation budget would exceed *max_trajectory_tokens*, preventing context overflow errors.
- [**context_overflow_reward**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/tool_use/agent_tool_message_env.py#L375) (*float*) – Reward assigned when the episode is terminated due to context overflow. Defaults to -0.1.
- [**terminate_on_length**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/tool_use/agent_tool_message_env.py#L376) (*bool | None*) – Whether a per-turn sampler "length" stop ends the episode. Set False (LENGTH-continue) to keep the truncated turn and continue — intended for use with a rollout runner enforcing cumulative token budgets via `RolloutLimits`, which is then what bounds the episode. Default `None` resolves to False when `rollout_config` configures a cumulative token budget (the runner owns LENGTH handling), else True (the default).
- [**parse_error_policy**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/tool_use/agent_tool_message_env.py#L377) (*ParseErrorPolicy | None*) – Optional `ParseErrorPolicy` governing parse failures. When set, it supersedes the one-shot `failed_parse_reward` / `terminate_on_parse_error` semantics for parse-error turns: structural failures (broken framing) stop immediately with `StopReason.PARSE_ERROR`; content failures (unparsable tool calls) are retried with an injected corrective message up to `max_consecutive` times. Default `None` keeps those one-shot semantics. A rollout runner configured with a policy also sets this via `set_parse_error_policy`.

**Returns:** An EnvFromMessageEnv ready for RL training.