Metadata-Version: 2.4
Name: audacity-sdk
Version: 0.1.1
Summary: Audacity Investments AI SDK — Bedrock-parity client for the Audacity LLM gateway
Author-email: Audacity Investments <eng@audacityinvestments.com>
License: Audacity Investments SDK License
        
        Copyright (c) 2026 Audacity Investments. All rights reserved.
        
        This software is proprietary to Audacity Investments. Permission is granted
        to download, install, and use this software solely to access services
        provided by Audacity Investments, subject to your agreement with Audacity
        Investments.
        
        You may not modify, distribute, sublicense, or create derivative works of
        this software, in whole or in part, except as expressly permitted in
        writing by Audacity Investments.
        
        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
        AUDACITY INVESTMENTS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY
        ARISING FROM THE USE OF THE SOFTWARE.
        
Project-URL: Homepage, https://portal.audacityinvestments.com
Project-URL: Repository, https://github.com/Audacity-Investments/audacity-sdk
Keywords: audacity,llm,ai,bedrock
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Operating System :: OS Independent
Classifier: Typing :: Typed
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Dynamic: license-file

# audacity-sdk

Python client for the Audacity Investments LLM gateway.  Exposes the same
**Amazon Bedrock Converse** surface so teams migrating off Bedrock can swap
the client constructor and keep the rest of their call-sites unchanged.

---

## Installation

```bash
pip install audacity-sdk
```

Zero runtime dependencies — stdlib only. Requires Python 3.9+.

---

## Quick start

### Non-streaming (Converse)

```python
from audacity import Audacity

client = Audacity(api_key="audacity_api_…")   # or set AUDACITY_API_KEY

response = client.converse(
    modelId="gpt-5.4-mini",
    messages=[{"role": "user", "content": [{"text": "What is 2+2?"}]}],
    inferenceConfig={"maxTokens": 256, "temperature": 0.0},
)

print(response["output"]["message"]["content"][0]["text"])
print(response["stopReason"])   # "end_turn"
print(response["usage"])        # {"inputTokens": …, "outputTokens": …, "totalTokens": …}
print(response["metrics"])      # {"latencyMs": …}
```

### Streaming (ConverseStream)

```python
from audacity import Audacity

client = Audacity()

stream_response = client.converse_stream(
    modelId="gpt-5.4-mini",
    messages=[{"role": "user", "content": [{"text": "Write me a haiku."}]}],
)

for event in stream_response["stream"]:         # boto3 parity: response["stream"]
    if "contentBlockDelta" in event:
        delta = event["contentBlockDelta"]["delta"]
        print(delta.get("text", ""), end="", flush=True)

print()  # newline at end
```

---

## Migrating from boto3 bedrock-runtime

```python
# BEFORE — boto3
import boto3
client = boto3.client("bedrock-runtime", region_name="us-east-1")

response = client.converse(
    modelId="anthropic.claude-3-sonnet-20240229-v1:0",
    messages=[{"role": "user", "content": [{"text": "Hi"}]}],
)

# AFTER — Audacity SDK
from audacity import Audacity
client = Audacity(api_key="audacity_api_…")   # only line that changes

response = client.converse(
    modelId="gpt-5.4-mini",                   # use Audacity model ID
    messages=[{"role": "user", "content": [{"text": "Hi"}]}],
)
```

Streaming diff:

```python
# BEFORE — boto3
stream_resp = client.converse_stream(modelId=…, messages=…)
for event in stream_resp["stream"]:
    …

# AFTER — Audacity SDK (identical call-site)
stream_resp = client.converse_stream(modelId=…, messages=…)
for event in stream_resp["stream"]:
    …
```

---

## Tool use

```python
response = client.converse(
    modelId="gpt-5.4-mini",
    messages=[{"role": "user", "content": [{"text": "What's the weather in NYC?"}]}],
    toolConfig={
        "tools": [{
            "toolSpec": {
                "name": "get_weather",
                "description": "Get current weather for a city",
                "inputSchema": {
                    "json": {
                        "type": "object",
                        "properties": {"city": {"type": "string"}},
                        "required": ["city"],
                    }
                },
            }
        }],
        "toolChoice": {"auto": {}},
    },
)

# Assistant responds with a tool call
tool_use = response["output"]["message"]["content"][0]["toolUse"]
print(tool_use["name"])   # "get_weather"
print(tool_use["input"])  # {"city": "NYC"}

# Send tool result back
response2 = client.converse(
    modelId="gpt-5.4-mini",
    messages=[
        {"role": "user",  "content": [{"text": "What's the weather in NYC?"}]},
        {"role": "assistant", "content": response["output"]["message"]["content"]},
        {"role": "user",  "content": [
            {"toolResult": {
                "toolUseId": tool_use["toolUseId"],
                "content": [{"text": "Sunny, 72°F"}],
            }}
        ]},
    ],
)
```

---

## Images (vision models)

Bedrock-style `image` content blocks are supported in user messages. Pass raw
bytes (encoded for you) or a URL (Audacity extension):

```python
with open("chart.png", "rb") as f:
    image_bytes = f.read()

response = client.converse(
    modelId="gpt-5.5",
    messages=[{
        "role": "user",
        "content": [
            {"text": "What does this chart show?"},
            {"image": {"format": "png", "source": {"bytes": image_bytes}}},
        ],
    }],
)

# Or reference a hosted image directly (not available in Bedrock):
# {"image": {"format": "jpeg", "source": {"url": "https://example.com/photo.jpg"}}}
```

`format` is one of `png`, `jpeg`, `gif`, `webp`. Use a vision-capable model.

---

## Error handling

```python
from audacity import Audacity
from audacity.exceptions import (
    MissingApiKeyError,
    AccessDeniedException,
    ThrottlingException,
    ServiceQuotaExceededException,
    ModelStreamErrorException,
    SdkError,
)

client = Audacity()

try:
    response = client.converse(modelId="gpt-5.4-mini", messages=[…])
except client.exceptions.ThrottlingException as e:
    print(f"Rate limited: {e.message}, retry after {e.retry_after_seconds}s")
except client.exceptions.AccessDeniedException as e:
    print(f"Auth error [{e.status_code}]: {e.message}")
except client.exceptions.ServiceQuotaExceededException as e:
    print(f"Budget exhausted: {e.message}")
except SdkError as e:
    print(f"Network/decode error: {e.message}")
```

Streaming errors surface when you iterate the stream:

```python
try:
    for event in stream_response["stream"]:
        …
except client.exceptions.ModelStreamErrorException as e:
    print(f"Stream broken: {e.message}")
```

---

## Configuration & environment variables

| Constructor parameter | Environment variable | Default |
|---|---|---|
| `api_key` | `AUDACITY_API_KEY` | — (required) |
| `base_url` | `AUDACITY_BASE_URL` | `https://portal.audacityinvestments.com` |
| `timeout` | — | `120.0` seconds |
| `max_retries` | — | `2` (3 total attempts) |

```python
client = Audacity(
    api_key="audacity_api_…",
    base_url="https://portal.audacityinvestments.com",
    timeout=60.0,
    max_retries=3,
)
```

---

## Retry behaviour

The SDK automatically retries transient failures with jittered exponential
backoff (capped at 20 s):

- Retried: `ThrottlingException` (429), `ModelTimeoutException` (408),
  `ServiceUnavailableException` (502/503/504), `InternalServerException` (500),
  network errors.
- Never retried: `AccessDeniedException`, `ValidationException`,
  `ResourceNotFoundException`, `ServiceQuotaExceededException`
  (including `BUDGET_EXCEEDED` at 429/402), or any 4xx except 408/429.
- Streaming: retries apply only before the first SSE byte; after that,
  connection drops raise `ModelStreamErrorException`.
