Gemini 4 Carbon のデベロッパー向けガイド

from google import genai
from google.genai import types

client = genai.Client(enterprise=True, project="PROJECT_ID", location="global")

response = client.models.generate_content(
    model="gemini-4-carbon",
    contents="Design a lock-free ring buffer in Rust for multi-producer, single-consumer telemetry ingestion.",
    config=types.GenerateContentConfig(
        thinking_config=types.ThinkingConfig(
            thinking_level="MEDIUM",  # Default: "MEDIUM" (Valid: "LOW", "MEDIUM", "HIGH")
        ),
    ),
)
print(response.text)

from google import genai

client = genai.Client(enterprise=True, project="PROJECT_ID", location="global")

# Turn 1: Initial request (stored server-side by default)
turn1 = client.interactions.create(
    model="gemini-4-carbon",
    input="Design a lock-free ring buffer in Rust for multi-producer, single-consumer telemetry ingestion.",
    store=True,
)
print(turn1.output_text)

# Turn 2: Continue the conversation using previous_interaction_id
turn2 = client.interactions.create(
    model="gemini-4-carbon",
    input="Add a bounded backpressure policy and unit tests for concurrent writers.",
    previous_interaction_id=turn1.id,
)
print(turn2.output_text)

curl -X POST \
-H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
-H "Content-Type: application/json" \
"https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/publishers/google/models/gemini-4-carbon:generateContent" \
-d '{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Provide an architectural review of this Go interface."
        }
      ]
    }
  ],
  "generationConfig": {
    "thinkingConfig": {
      "thinkingLevel": "MEDIUM"
    }
  }
}'

from google import genai

client = genai.Client(
    enterprise=True,
    project="PROJECT_ID",
    location="global",
)

# Automatic continuation is enabled by default in google-genai >= 2.34.0.
# Unary calls merge all segments into one Interaction with summed usage.
interaction = client.interactions.create(
    model="gemini-4-carbon",
    input="Write a complete formal proof of the prime number theorem.",
    generation_config={
        "max_output_tokens": 256000,
        "thinking_level": "high",
    },
)
print(interaction.output_text)
print(f"Merged segment IDs: {interaction.continuation_ids}")
print(f"Initial input tokens: {interaction.usage.initial_input_tokens}")

# Optional: Delete each stored server segment (last segment first) before its 7-day TTL expires.
for segment_id in reversed(interaction.continuation_ids or [interaction.id]):
    client.interactions.delete(id=segment_id)

# Streaming yields events across all segments in order. Intermediate segments
# emit interaction.completed with status="requires_continuation".
stream = client.interactions.create(
    model="gemini-4-carbon",
    input="Write a complete formal proof of the prime number theorem.",
    stream=True,
    generation_config={
        "max_output_tokens": 256000,
        "thinking_level": "high",
    },
)
for event in stream:
    if event.event_type == "step.delta" and getattr(event.delta, "text", None):
        print(event.delta.text, end="", flush=True)
    elif (
        event.event_type == "interaction.completed"
        and event.interaction.status != "requires_continuation"
    ):
        print(f"\nFinal status: {event.interaction.status}")

# Set automatic_continuation=False to return after a single segment.
single_segment = client.interactions.create(
    model="gemini-4-carbon",
    input="Write a complete formal proof of the prime number theorem.",
    generation_config={"max_output_tokens": 256000, "thinking_level": "high"},
    automatic_continuation=False,
)

from google import genai

client = genai.Client(
    enterprise=True,
    project="PROJECT_ID",
    location="global",
)

prompt = "Write a complete formal proof of the prime number theorem."

# Stored loop (store=True, default): chain previous_interaction_id + continuation_token
# without resending input.
segment = client.interactions.create(
    model="gemini-4-carbon",
    input=prompt,
    store=True,
    generation_config={"max_output_tokens": 131072, "thinking_level": "high"},
    automatic_continuation=False,
)
full_text = segment.output_text or ""

while segment.status == "requires_continuation" and segment.continuation_token:
    segment = client.interactions.create(
        model="gemini-4-carbon",
        previous_interaction_id=segment.id,
        continuation_token=segment.continuation_token,
        generation_config={"max_output_tokens": 131072, "thinking_level": "high"},
        automatic_continuation=False,
    )
    full_text += segment.output_text or ""

# If status == "incomplete", max_output_tokens was exhausted; raise max_output_tokens
# to continue (leaving default automatic_continuation=True lets the SDK finish remaining segments).
if segment.status == "incomplete" and segment.continuation_token:
    segment = client.interactions.create(
        model="gemini-4-carbon",
        previous_interaction_id=segment.id,
        continuation_token=segment.continuation_token,
        generation_config={"max_output_tokens": 256000, "thinking_level": "high"},
    )
    full_text += segment.output_text or ""

# Stateless loop (store=False): resend original input + continuation_token
# with no previous_interaction_id.
stateless_seg = client.interactions.create(
    model="gemini-4-carbon",
    input=prompt,
    store=False,
    generation_config={"max_output_tokens": 131072, "thinking_level": "high"},
    automatic_continuation=False,
)
stateless_text = stateless_seg.output_text or ""
while stateless_seg.status == "requires_continuation" and stateless_seg.continuation_token:
    stateless_seg = client.interactions.create(
        model="gemini-4-carbon",
        input=prompt,
        store=False,
        continuation_token=stateless_seg.continuation_token,
        generation_config={"max_output_tokens": 131072, "thinking_level": "high"},
        automatic_continuation=False,
    )
    stateless_text += stateless_seg.output_text or ""

# Segment 1: Start a stored interaction (store=true by default)
curl -s -X POST \
  -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  -H "Content-Type: application/json" \
  "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions" \
  -d '{
    "model": "gemini-4-carbon",
    "store": true,
    "input": "Write a complete formal proof of the prime number theorem.",
    "generation_config": {
      "max_output_tokens": 131072,
      "thinking_level": "high"
    }
  }'

# Segment 2: When status is "requires_continuation", pass previous_interaction_id
# and continuation_token without resending input
curl -s -X POST \
  -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  -H "Content-Type: application/json" \
  "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions" \
  -d '{
    "model": "gemini-4-carbon",
    "store": true,
    "previous_interaction_id": "SEGMENT_1_ID",
    "continuation_token": "CONTINUATION_TOKEN",
    "generation_config": {
      "max_output_tokens": 131072,
      "thinking_level": "high"
    }
  }'

# Segment 1: Stateless interaction (store=false)
curl -s -X POST \
  -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  -H "Content-Type: application/json" \
  "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions" \
  -d '{
    "model": "gemini-4-carbon",
    "store": false,
    "input": "Write a complete formal proof of the prime number theorem.",
    "generation_config": {
      "max_output_tokens": 131072,
      "thinking_level": "high"
    }
  }'

# Segment 2: Resend the original input and continuation_token (no previous_interaction_id)
curl -s -X POST \
  -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  -H "Content-Type: application/json" \
  "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions" \
  -d '{
    "model": "gemini-4-carbon",
    "store": false,
    "input": "Write a complete formal proof of the prime number theorem.",
    "continuation_token": "CONTINUATION_TOKEN",
    "generation_config": {
      "max_output_tokens": 131072,
      "thinking_level": "high"
    }
  }'

import time
from google import genai

client = genai.Client(
    enterprise=True,
    project="PROJECT_ID",
    location="global",
)

# Start a server-managed background long decode (requires store=True)
interaction = client.interactions.create(
    model="gemini-4-carbon",
    input="Write a complete formal proof of the prime number theorem.",
    background=True,
    store=True,
    generation_config={"max_output_tokens": 256000, "thinking_level": "high"},
)

while interaction.status in ("queued", "in_progress"):
    time.sleep(10)
    interaction = client.interactions.get(id=interaction.id)

print(f"Status: {interaction.status}")
print(interaction.output_text)

# Optional: Cancel an in-progress background interaction and resume later
# from its persisted checkpoint continuation_token (if >= 32,768 tokens decoded).
# cancelled = client.interactions.cancel(id=interaction.id)
# if cancelled.continuation_token:
#     resumed = client.interactions.create(
#         model="gemini-4-carbon",
#         previous_interaction_id=cancelled.id,
#         continuation_token=cancelled.continuation_token,
#         background=True,
#         generation_config={"max_output_tokens": 256000, "thinking_level": "high"},
#     )

# Start a server-managed background long decode (requires store=true)
curl -s -X POST \
  -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  -H "Content-Type: application/json" \
  "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions" \
  -d '{
    "model": "gemini-4-carbon",
    "background": true,
    "store": true,
    "input": "Write a complete formal proof of the prime number theorem.",
    "generation_config": {
      "max_output_tokens": 256000,
      "thinking_level": "high"
    }
  }'

# Poll the interaction until status reaches completed, incomplete, failed, or cancelled
curl -s -X GET \
  -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions/INTERACTION_ID"

# Optional: Cancel an in-progress background decode
curl -s -X POST \
  -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions/INTERACTION_ID/cancel"

# Optional: Resume a cancelled background decode from its checkpoint continuation_token
curl -s -X POST \
  -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  -H "Content-Type: application/json" \
  "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions" \
  -d '{
    "model": "gemini-4-carbon",
    "background": true,
    "store": true,
    "previous_interaction_id": "INTERACTION_ID",
    "continuation_token": "CONTINUATION_TOKEN",
    "generation_config": {
      "max_output_tokens": 256000,
      "thinking_level": "high"
    }
  }'

from google import genai
from google.genai import errors

client = genai.Client(
    enterprise=True,
    project="PROJECT_ID",
    location="global",
)

# With default automatic_continuation=True, stream=True automatically
# reconnects from the latest interaction.status_update checkpoint (32,768
# output tokens, then every 5,000 tokens) if no output was yielded after the
# checkpoint. If a disconnect occurs after output was yielded since the last
# checkpoint, the SDK raises ContinuationInterruptedError so you can resume
# from err.continuation_token.
stream = client.interactions.create(
    model="gemini-4-carbon",
    input="Write a complete formal proof of the prime number theorem.",
    stream=True,
    store=True,
    generation_config={"max_output_tokens": 256000, "thinking_level": "high"},
)

try:
    for event in stream:
        if event.event_type == "step.delta" and getattr(event.delta, "text", None):
            print(event.delta.text, end="", flush=True)
except errors.ContinuationInterruptedError as err:
    # Resuming from a mid-segment checkpoint regenerates any output yielded
    # after that checkpoint.
    if err.interaction_id and err.continuation_token:
        resumed_stream = client.interactions.create(
            model="gemini-4-carbon",
            previous_interaction_id=err.interaction_id,
            continuation_token=err.continuation_token,
            stream=True,
            store=True,
            generation_config={"max_output_tokens": 256000, "thinking_level": "high"},
        )
        for event in resumed_stream:
            if event.event_type == "step.delta" and getattr(event.delta, "text", None):
                print(event.delta.text, end="", flush=True)

# Start a streaming interaction; save interaction.id from interaction.created
# and the latest continuation_token from interaction.status_update SSE events
curl -N -X POST \
  -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  -H "Content-Type: application/json" \
  "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions" \
  -d '{
    "model": "gemini-4-carbon",
    "stream": true,
    "store": true,
    "input": "Write a complete formal proof of the prime number theorem.",
    "generation_config": {
      "max_output_tokens": 256000,
      "thinking_level": "high"
    }
  }'

# Resume a dropped stream from the last saved checkpoint continuation_token
# (for store=false, resend the original input instead of previous_interaction_id)
curl -N -X POST \
  -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  -H "Content-Type: application/json" \
  "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions" \
  -d '{
    "model": "gemini-4-carbon",
    "stream": true,
    "store": true,
    "previous_interaction_id": "SEGMENT_ID",
    "continuation_token": "CHECKPOINT_CONTINUATION_TOKEN",
    "generation_config": {
      "max_output_tokens": 256000,
      "thinking_level": "high"
    }
  }'

from google import genai
from google.genai import types

client = genai.Client(enterprise=True, project="PROJECT_ID", location="global")

# Automatic continuation is enabled by default in google-genai >= 2.30.1.
# Chunks across all continuation requests are yielded as a single stream.
for chunk in client.models.generate_content_stream(
    model="gemini-4-carbon",
    contents="Write a complete formal proof of the prime number theorem.",
    config=types.GenerateContentConfig(
        max_output_tokens=256000,
        thinking_config=types.ThinkingConfig(thinking_level="HIGH"),
    ),
):
    print(chunk.text, end="")

# Set automatic_continuation=False to disable automatic continuation.
for chunk in client.models.generate_content_stream(
    model="gemini-4-carbon",
    contents="Write a complete formal proof of the prime number theorem.",
    config=types.GenerateContentConfig(
        thinking_config=types.ThinkingConfig(thinking_level="HIGH"),
        automatic_continuation=False,
    ),
):
    print(chunk.text, end="")

# Request 1: Initial request with maxOutputTokens > 32,768
curl -s -X POST \
  -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  -H "Content-Type: application/json" \
  "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/publishers/google/models/gemini-4-carbon:generateContent" \
  -d '{
    "contents": [{
      "role": "user",
      "parts": [{"text": "Write a complete formal proof of the prime number theorem."}]
    }],
    "generationConfig": {
      "maxOutputTokens": 131072,
      "thinkingConfig": {"thinkingLevel": "HIGH"}
    }
  }'

# Request 2: Resend the original request with top-level continuationToken
# from Request 1 (candidates[0].continuationToken)
curl -s -X POST \
  -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  -H "Content-Type: application/json" \
  "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/publishers/google/models/gemini-4-carbon:generateContent" \
  -d '{
    "contents": [{
      "role": "user",
      "parts": [{"text": "Write a complete formal proof of the prime number theorem."}]
    }],
    "continuationToken": "CONTINUATION_TOKEN",
    "generationConfig": {
      "maxOutputTokens": 131072,
      "thinkingConfig": {"thinkingLevel": "HIGH"}
    }
  }'