Deepcoder

uv pip install -e ".[tinker]"                          # rllm + tinker backend
uv pip install --no-deps -e cookbooks/deepcoder        # this cookbook
rllm agent list                                        # should show "deepcoder"

python cookbooks/deepcoder/prepare_data.py
# Smoke-size:
python cookbooks/deepcoder/prepare_data.py --train-size 200 --test-size 50

rllm eval deepcoder \
    --agent deepcoder \
    --evaluator deepcoder \
    --model agentica-org/DeepCoder-14B-Preview \
    --base-url http://localhost:8000/v1 \
    --split test \
    --max-examples 20

# Tinker (single-machine LoRA)
bash cookbooks/deepcoder/train_tinker.sh

# Verl (distributed GPU)
bash cookbooks/deepcoder/train_verl.sh

@rllm.rollout(name="deepcoder")
async def deepcoder_flow(task: Task, config: AgentConfig) -> Episode:
    question = str(task.metadata.get("question") or task.instruction or "")
    client = AsyncOpenAI(base_url=config.base_url, api_key="EMPTY")
    messages = [
        {"role": "system", "content": SYSTEM_PROMPT},
        {"role": "user", "content": question},
    ]

    resp = await client.chat.completions.create(
        model=config.model, messages=messages,
        temperature=0.6, max_tokens=16384, timeout=600,
    )
    content = resp.choices[0].message.content or ""
    messages.append({"role": "assistant", "content": content})
    step = Step(chat_completions=list(messages), model_response=content, action=content, thought=content)

    return Episode(
        trajectories=[Trajectory(name="deepcoder", steps=[step])],
        artifacts={"answer": content},
    )