feat(sambanova): update model YAMLs [bot]

[models-bot]

Auto-generated by poc-agent for provider sambanova.

---

Note

Low Risk
Single metadata field on a preview model catalog entry; no runtime or API logic changes.

Overview
Marks SambaNova gemma-4-31B-it as supporting extended thinking/reasoning by adding thinking: true to its provider model YAML, consistent with other reasoning-capable SambaNova entries.

^{Reviewed by Cursor Bugbot for commit 0cac8a3. Bugbot is set up for automated code reviews on this repo. Configure here.}

[github-actions]

/test-models

[harshiv-26]

Gateway test results

• Total: 4
• Passed: 2
• Failed: 0
• Validation failed: 2
• Errored: 0
• Skipped: 0
• Success rate: 50.0%

Provider	Model	Scenarios
sambanova	gemma-4-31B-it	success: params:stream, params validation_failure: reasoning:stream, reasoning

Failures (2)

sambanova/gemma-4-31B-it — reasoning:stream (validation_failure)

Error

Traceback (most recent call last):
  File "/tmp/tmp_hgk6380/snippet.py", line 31, in <module>
    raise Exception("VALIDATION FAILED: reasoning stream - no reasoning information in stream")
Exception: VALIDATION FAILED: reasoning stream - no reasoning information in stream

Code snippet

from openai import OpenAI

client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")

response = client.chat.completions.create(
    model="test-v2-sambanova/gemma-4-31B-it",
    messages=[
        {"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
    ],
    reasoning_effort="medium",
    stream=True,
)
_reasoning_detected = False
for chunk in response:
    if chunk.choices and len(chunk.choices) > 0:
        delta = chunk.choices[0].delta
        if delta.content is not None:
            print(delta.content, end="", flush=True)
        if getattr(delta, "reasoning_content", None) is not None:
            _reasoning_detected = True
        if getattr(delta, "reasoning", None) is not None:
            _reasoning_detected = True

    _usage = getattr(chunk, "usage", None)
    if _usage is not None:
        _details = getattr(_usage, "completion_tokens_details", None)
        if _details and getattr(_details, "reasoning_tokens", 0) > 0:
            _reasoning_detected = True

if not _reasoning_detected:
    raise Exception("VALIDATION FAILED: reasoning stream - no reasoning information in stream")
print("\nVALIDATION: reasoning stream SUCCESS")

Output

To calculate $3^{3^{3^3}}$, we must follow the mathematical convention for **tetration** (repeated exponentiation). When exponents are stacked without parentheses, they are evaluated from the **top down** (right-associative).

The expression is evaluated in these steps:
1. $3^3$ (The top layer)
2. $3^{(Result\ of\ Step\ 1)}$
3. $3^{(Result\ of\ Step\ 2)}$

---

### Step 1: The first exponent
First, we calculate the highest exponent in the stack:
$$3^3 = 3 \times 3 \times 3 = 27$$

Now the expression simplifies to:
$$3^{3^{27}}$$

### Step 2: The second exponent
Next, we must calculate $3^{27}$. This is a very large number.
Using a calculator or logarithms:
$$3^{27} = 7,625,597,484,987$$

Now the expression simplifies to:
$$3^{7,625,597,484,987}$$

### Step 3: The final calculation
The final step is to raise $3$ to the power of $7.6$ trillion. 

To understand how large this number is, we can estimate its size using base-10 logarithms ($\log_{10}$):
$$\text{Number of digits} \approx \log_{10}(3^{7,625,597,484,987})$$
$$\text{Number of digits} \approx 7,625,597,484,987 \times \log_{10}(3)$$
$$\text{Number of digits} \approx 7,625,597,484,987 \times 0.4771$$
$$\text{Number of digits} \approx 3,638,334,640,024$$

### Final Conclusion
The number $3^{3^{3^3}}$ is far too large to be written out in standard decimal notation. 

*   **Exact form:** $3^{7,625,597,484,987}$
*   **Approximate size:** A number with approximately **3.6 trillion digits**.

To put this in perspective, if you printed this number in standard font on paper, the strip of paper would stretch from the Earth to the Sun and back several times.

sambanova/gemma-4-31B-it — reasoning (validation_failure)

Error

Traceback (most recent call last):
  File "/tmp/tmpb7t477nx/snippet.py", line 39, in <module>
    raise Exception("VALIDATION FAILED: reasoning - no reasoning information in response")
Exception: VALIDATION FAILED: reasoning - no reasoning information in response

Code snippet

from openai import OpenAI

client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")

response = client.chat.completions.create(
    model="test-v2-sambanova/gemma-4-31B-it",
    messages=[
        {"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
    ],
    reasoning_effort="medium",
    stream=False,
)
_usage = getattr(response, "usage", None)
_reasoning_detected = False

_choices = getattr(response, "choices", None)
if _choices and len(_choices) > 0:
    _message = getattr(_choices[0], "message", None)
else:
    _message = None

if _message and getattr(_message, "content", None) is not None:
    print(_message.content)

if _usage is not None:
    _output_token_details = getattr(_usage, "completion_tokens_details", None)
    if _output_token_details and getattr(_output_token_details, "reasoning_tokens", 0) > 0:
        _reasoning_detected = True
    elif getattr(_usage, "reasoning", None) is not None:
        _reasoning_detected = True

if getattr(_message, "reasoning_content", None) is not None:
    _reasoning_detected = True
elif getattr(_message, "reasoning", None) is not None:
    _reasoning_detected = True

if not _reasoning_detected:
    print("Response: ", response)
    raise Exception("VALIDATION FAILED: reasoning - no reasoning information in response")
print("VALIDATION: reasoning SUCCESS")

Output

To calculate $3^{3^{3^3}}$, we must follow the mathematical convention for **tetration** (repeated exponentiation). When exponents are stacked without parentheses, they are evaluated from the **top down** (right-associative).

The expression is evaluated in these steps:
1. $3^3$ (The top layer)
2. $3^{(Result\ of\ Step\ 1)}$
3. $3^{(Result\ of\ Step\ 2)}$

---

### Step 1: The first exponent
First, we calculate the highest exponent in the stack:
$$3^3 = 3 \times 3 \times 3 = 27$$

Now the expression simplifies to:
$$3^{3^{27}}$$

### Step 2: The second exponent
Next, we must calculate $3^{27}$. This is a very large number.
Using a calculator or logarithms:
$$3^{27} = 7,625,597,484,987$$

Now the expression simplifies to:
$$3^{7,625,597,484,987}$$

### Step 3: The final calculation
The final step is to raise $3$ to the power of $7.6$ trillion. 

To understand how large this number is, we can estimate its size using base-10 logarithms ($\log_{10}$):
$$\text{Number of digits} \approx \log_{10}(3^{7,625,597,484,987})$$
$$\text{Number of digits} \approx 7,625,597,484,987 \times \log_{10}(3)$$
$$\text{Number of digits} \approx 7,625,597,484,987 \times 0.4771$$
$$\text{Number of digits} \approx 3,638,334,640,024$$

### Final Conclusion
The number $3^{3^{3^3}}$ is far too large to be written out in standard decimal notation. 

*   **Exact form:** $3^{7,625,597,484,987}$
*   **Approximate size:** A number with approximately **3.6 trillion digits**.

To put this in perspective, if you printed this number in standard font on paper, the strip of paper would stretch from the Earth to the Sun and back several times.
Response:  ChatCompletion(id='721ddab3-ff07-42db-bc7f-b58fcb58ff8c', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content='To calculate $3^{3^{3^3}}$, we must follow the mathematical convention for **tetration** (repeated exponentiation). When exponents are stacked without parentheses, they are evaluated from the **top down** (right-associative).\n\nThe expression is evaluated in these steps:\n1. $3^3$ (The top layer)\n2. $3^{(Result\\ of\\ Step\\ 1)}$\n3. $3^{(Result\\ of\\ Step\\ 2)}$\n\n---\n\n### Step 1: The first exponent\nFirst, we calculate the highest exponent in the stack:\n$$3^3 = 3 \\times 3 \\times 3 = 27$$\n\nNow the expression simplifies to:\n$$3^{3^{27}}$$\n\n### Step 2: The second exponent\nNext, we must calculate $3^{27}$. This is a very large number.\nUsing a calculator or logarithms:\n$$3^{27} = 7,625,597,484,987$$\n\nNow the expression simplifies to:\n$$3^{7,625,597,484,987}$$\n\n### Step 3: The final calculation\nThe final step is to raise $3$ to the power of $7.6$ trillion. \n\nTo understand how large this number is, we can estimate its size using base-10 logarithms ($\\log_{10}$):\n$$\\text{Number of digits} \\approx \\log_{10}(3^{7,625,597,484,987})$$\n$$\\text{Number of digits} \\approx 7,625,597,484,987 \\times \\log_{10}(3)$$\n$$\\text{Number of digits} \\approx 7,625,597,484,987 \\times 0.4771$$\n$$\\text{Number of digits} \\approx 3,638,334,640,024$$\n\n### Final Conclusion\nThe number $3^{3^{3^3}}$ is far too large to be written out in standard decimal notation. \n\n*   **Exact form:** $3^{7,625,597,484,987}$\n*   **Approximate size:** A number with approximately **3.6 trillion digits**.\n\nTo put this in perspective, if you printed this number in standard font on paper, the strip of paper would stretch from the Earth to the Sun and back several times.', refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=None))], created=1783909136, model='gemma-4-31B-it', object='chat.completion', service_tier=None, system_fingerprint='fastcoe', usage=CompletionUsage(completion_tokens=564, prompt_tokens=34, total_tokens=598, completion_tokens_details=None, prompt_tokens_details=None), provider='sambanova')

Successes (2)

sambanova/gemma-4-31B-it — params:stream (success)

Output

The capital of France is Paris.

sambanova/gemma-4-31B-it — params (success)

Output

The capital of France is Paris.