Bedrock providers ignore AWS_ENDPOINT_URL_BEDROCK_RUNTIME env var

Summary

ChatBedrockAnthropic/ChatAWSBedrock (chatlas/_provider_bedrock.py) and the Converse-based provider (chatlas/_provider_bedrock_converse.py) both compute base_url from the AWS region whenever no explicit base_url is passed:

# _provider_bedrock.py / _provider_bedrock_converse.py
resolved_base_url = base_url or bedrock_base_url("converse", aws_region)  # or "messages"/"responses"

This bypasses botocore's native support for AWS_ENDPOINT_URL_BEDROCK_RUNTIME (and the generic AWS_ENDPOINT_URL), which is the standard way to point AWS SDKs at a custom Bedrock runtime endpoint (e.g. VPC endpoints, proxies, local testing, FIPS endpoints, or region-specific overrides not covered by the built-in formula).

ellmer just added this: chat_aws_bedrock() now defaults base_url from AWS_ENDPOINT_URL_BEDROCK_RUNTIME (tidyverse/ellmer#1104). The corresponding Anthropic-direct case, ANTHROPIC_BASE_URL, is already handled for free in chatlas since the anthropic Python SDK reads that env var internally -- no action needed there.

Expected fix

In _provider_bedrock.py and _provider_bedrock_converse.py, when base_url is not explicitly passed, check os.environ.get("AWS_ENDPOINT_URL_BEDROCK_RUNTIME") before falling back to the computed bedrock_base_url(...) formula.

References

• ellmer PR: tidyverse/ellmer#1104
• chatlas: chatlas/_provider_bedrock.py, chatlas/_provider_bedrock_converse.py (resolved_base_url = base_url or bedrock_base_url(...))

Start in chatlas/_provider_bedrock.py and chatlas/_provider_bedrock_converse.py at the documented resolved_base_url fallback. Check how the AWS_ENDPOINT_URL_BEDROCK_RUNTIME environment variable should take precedence when base_url is omitted, while preserving the computed Bedrock URL fallback. Done means both provider paths honor the environment variable and existing behavior remains intact.