Skip to content
Agentmart
Submit a tool

bedrock-converse-client

Bedrock runtime Converse/ConverseStream API patterns: message structure, model ID selection, token limits, system prompts, retry with tenacity, error…

Skill by Cloud-Byte-Consulting

IndexedBSD-3-Clause
Write a review

Chalk Labs

Need help deploying bedrock-converse-client?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/cloud-byte-consulting-bedrock-converse-client

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Bedrock runtime Converse/ConverseStream API patterns: message structure, model ID selection, token limits, system prompts, retry with tenacity, error handling, and async client management. Use when making Bedrock API calls from pr-reviewer-consumer or ops-intel-reporter.

Use cases: backend

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/bedrock-converse-client

What's inside

Skill name
bedrock-converse-client
Description
Bedrock runtime Converse/ConverseStream API patterns: message structure, model ID selection, token limits, system prompts, retry with tenacity, error handling, and async client management. Use when making Bedrock API calls from pr-reviewer-consumer or ops-intel-reporter.
License
BSD-3-Clause
Instructions
161 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

<!-- Vendored from: platform-catalyst/skills/bedrock-converse-client/SKILL.md (BittahCriminal/platform-catalyst, BSD-3-Clause). Adapted for Catalyst: PLAN.md/CLAUDE.md/DECISIONS.md scrubbed; ADR-008->ADR-001, ADR-009->ADR-002. -->

# Bedrock Converse client

## Role

You guide implementation of Bedrock Converse API calls in Catalyst services, ensuring correct message structure, model selection, and error handling per `AGENTS.md` Bedrock-specific guidance.

## Instructions

### 1. Async client setup

```python
import aioboto3
from types import TracebackType

class BedrockClient:
    """Async Bedrock runtime client with connection reuse."""

    def __init__(self, region: str = "us-east-1"):
        self._session = aioboto3.Session()
        self._region = region
        self._client = None

    async def __aenter__(self):
        self._client = await self._session.client(
            "bedrock-runtime", region_name=self._region
        ).__aenter__()
        return self

    async def __aexit__(self, *exc):
        if self._client:
            await self._client.__aexit__(*exc)
```

### 2. Model IDs (runtime configuration)

```python
from dataclasses import dataclass
import os

@dataclass(frozen=True)
class BedrockModels:
    reviewer: str
    summarizer: str

def load_models() -> BedrockModels:
    return BedrockModels(
        reviewer=os.environ["CATALYST_BEDROCK_MODEL_REVIEWER"],
        summarizer=os.environ["CATALYST_BEDROCK_MODEL_SUMMARIZER"],
    )
```

### 3. Converse API call

```python
from tenacity import retry, stop_after_attempt, wait_exponential, retry_if_exception_type
from botocore.exceptions import ClientError

@retry(
    stop=stop_after_attempt(2),
    wait=wait_exponential(multiplier=1, min=1, max=5),
    retry=retry_if_exception_type(ClientError),
)
async def converse(
    self,
    model_id: str,
    system_prompt: str,
    user_message: str,
    max_tokens: int = 4096,
    temperature: float = 0.0,
) -> dict:
    """Call Bedrock Converse API with retry on transient errors."""
    response = await self._client.converse(
        modelId=model_id,
        messages=[
            {
                "role": "user",
                "content": [{"text": user_message}],
            }
        ],
        system=[{"text": system_prompt}],
        inferenceConfig={
            "maxTokens": max_tokens,
            "temperature": temperature,
        },
    )
    return response
```

### 4. Response extraction

```python
def extract_text(response: dict) -> str:
    """Extract text content from Converse API response."""
    output = response.get("output", {})
    message = output.get("message", {})
    content = message.get("content", [])
    return "".join(block.get("text", "") for block in content)

def extract_usage(response: dict) -> dict:
    """Extract token usage from Converse API response."""
    usage = response.get("usage", {})
    return {
        "input_tokens": usage.get("inputTokens", 0),
        "output_tokens": usage.get("outputTokens", 0),
        "total_tokens": usage.get("inputTokens", 0) + usage.get("outputTokens", 0),
    }
```

### 5. Streaming (ConverseStream)

```python
async def converse_stream(
    self,
    model_id: str,
    system_prompt: str,
    user_message: str,
    max_tokens: int = 4096,
) -> AsyncIterator[str]:

From Cloud-Byte-Consulting/Catalyst, BSD-3-Clause.

More from Cloud-Byte-Consulting/Catalyst

Signals

Stars
0
Forks
0
Open issues
57
Last commit (this folder)
May 21, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
BSD-3-Clause
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Cloud-Byte-Consulting

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get bedrock-converse-client running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying bedrock-converse-client?

CallGet help
Cite this page

bedrock-converse-client skill. Agent Mart. https://agentmart.dev/skills/cloud-byte-consulting-bedrock-converse-client (last updated 2026-10-24)