fix(bedrock): route ARNs via converse, named AWS profiles, and au. re…

[mhaitana]

Description

Fix three related gaps in Bedrock support that prevented headroom from working with Claude Code when CLAUDE_CODE_USE_BEDROCK=0 and ANTHROPIC_BASE_URL is pointed at the proxy:

1. ARN passthrough used the wrong LiteLLM route — application inference profile ARNs (e.g. arn:aws:bedrock:ap-southeast-2:<account>:application-inference-profile/<id>) were forwarded as bedrock/<arn>, which LiteLLM rejects with HTTP 400 "Try calling via converse route". Fixed to bedrock/converse/<arn>.

2. Named AWS profile not forwarded to completion calls — --bedrock-profile was wired through the CLI → config → LiteLLMBackend.__init__ and used to fetch the model map at startup,
   but never stored on self. All four acompletion() call sites (send_message, stream_message, send_openai_message, stream_openai_message) passed only aws_region_name — the
   actual Bedrock calls used ambient credentials regardless of the flag. Fixed by storing self.profile_name and passing aws_profile_name= to every acompletion() call.

3. ap-southeast-2 used the wrong region prefix — Australia should use au. for cross-region inference profile IDs, not apac.. Added ap-southeast-2 → "au" to _BEDROCK_REGION_PREFIXES and "au." to the strip list in _normalize_bedrock_profile_id.

Closes #

Type of Change

• Bug fix (non-breaking change that fixes an issue)

Changes Made

• backends/litellm.py: route arn:aws: model IDs via bedrock/converse/<arn> in map_model_id
• backends/litellm.py: store profile_name as self.profile_name in LiteLLMBackend.__init__; pass aws_profile_name= to acompletion() in all four call sites; use
  boto3.Session(profile_name=...) for startup discovery; cache key is region:profile_name to prevent cross-profile collisions
• backends/litellm.py: add ap-southeast-2 → "au" to _BEDROCK_REGION_PREFIXES; add "au." to prefix strip list in _normalize_bedrock_profile_id
• providers/registry.py: pass profile_name=bedrock_profile to LiteLLMBackend
• proxy/server.py: pass config.bedrock_profile to create_proxy_backend
• docs/claude-code-bedrock-headroom.md: remove false claim that ARNs in ANTHROPIC_DEFAULT_*_MODEL bypass the proxy; fix troubleshooting table
• tests/test_bedrock_region.py: update test_arn_passthrough to expect bedrock/converse/<arn>; update cache key format; add test_profile_cache_isolation,
  test_ap_southeast_2_uses_au_prefix, and TestBedrockProfileForwardedToCompletion (3 async tests asserting aws_profile_name appears in acompletion() kwargs for named profiles and is
  absent for the no-profile case)
• tests/test_provider_registry*.py, test_vertex_claude_compression.py: update litellm_backend_cls stubs to accept profile_name=None

Testing

• Unit tests pass (pytest)
• New tests added for new functionality
• Manual testing performed

Test Output

$ pytest tests/test_bedrock_region.py tests/test_provider_registry.py tests/test_provider_registry_extended.py \
    -k "not test_fallback_when_boto3_import_fails and not test_fallback_when_api_call_fails and not test_successful_fetch" -q
collected 51 items / 3 deselected / 48 selected

tests/test_bedrock_region.py ...........................
tests/test_provider_registry.py ...........
tests/test_provider_registry_extended.py .......

48 passed, 3 deselected in 2.00s

Note: 3 deselected tests use patch("builtins.import") which hangs under Python 3.13 — pre-existing issue unrelated to these changes.

Real Behavior Proof

• Environment: macOS, Python 3.13, Claude Code with CLAUDE_CODE_USE_BEDROCK=0, ANTHROPIC_BASE_URL=http://127.0.0.1:8787, AWS ap-southeast-2, application inference profile ARNs in ANTHROPIC_DEFAULT_*_MODEL
• Exact command / steps: headroom proxy --port 8787 --backend bedrock --region ap-southeast-2 --bedrock-profile "my-sso-profile"
• Observed result: Requests routed correctly to bedrock/converse/arn:aws:bedrock:ap-southeast-2:...:application-inference-profile/<id> as confirmed in LiteLLM logs
• Not tested: EU/APAC region ARN passthrough (logic is identical); non-SSO credential flows

15:29:44 - LiteLLM:INFO: utils.py:4090 - 
LiteLLM completion() model= converse/arn:aws:bedrock:ap-southeast-2:<account>:application-inference-profile/<id>; provider = bedrock
2026-06-26 15:29:44,322 - LiteLLM - INFO - 
LiteLLM completion() model= converse/arn:aws:bedrock:ap-southeast-2:<account>:application-inference-profile/<id>; provider = bedrock
15:31:09 - LiteLLM:INFO: utils.py:4090 - 
LiteLLM completion() model= converse/arn:aws:bedrock:ap-southeast-2:<account>:application-inference-profile/<id>; provider = bedrock
2026-06-26 15:31:09,928 - LiteLLM - INFO - 
LiteLLM completion() model= converse/arn:aws:bedrock:ap-southeast-2:<account>:application-inference-profile/<id>; provider = bedrock
15:34:26 - LiteLLM:INFO: utils.py:4090 - 
LiteLLM completion() model= converse/arn:aws:bedrock:ap-southeast-2:<account>:application-inference-profile/<id>; provider = bedrock
2026-06-26 15:34:26,811 - LiteLLM - INFO - 
LiteLLM completion() model= converse/arn:aws:bedrock:ap-southeast-2:<account>:application-inference-profile/<id>; provider = bedrock

Review Readiness

• I have performed a self-review
• This PR is ready for human review

Checklist

• My code follows the project's style guidelines
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes

Additional Notes

The 3 skipped tests (test_fallback_when_boto3_import_fails, test_fallback_when_api_call_fails, test_successful_fetch) pre-exist in the repo and use patch("builtins.__import__") which hangs under Python 3.13. Not affected by these changes.

[github-actions]

PR governance

This PR follows the template and is marked ready for human review.

[JerrettDavis]

The ARN-to-converse mapping and �u. prefix pieces look useful, but I found two blockers to fix before merge.\n\nFirst, --bedrock-profile is only applied to fetch_bedrock_inference_profiles(). The actual LiteLLM request paths still only pass �ws_region_name into �completion; they do not pass a profile/client/credentials value and this PR does not set AWS_PROFILE for the process. That means startup discovery can use the named SSO profile, while the real Bedrock completion still uses ambient/default credentials. Please wire the profile through the actual Bedrock LiteLLM calls (or explicitly set/document the environment mechanism and test it), and add a regression that captures the completion kwargs for a named profile.\n\nSecond, the new Claude Code Bedrock guide contradicts itself. The TL;DR says ANTHROPIC_DEFAULTMODEL must use standard Claude names and not ARNs because ARNs make Claude Code bypass ANTHROPIC_BASE_URL; later the application-inference-profile section says to pass ARN values directly in ANTHROPIC_DEFAULT_MODEL. Those cannot both be safe. Please make the guide consistent with the verified path so users do not accidentally bypass Headroom while thinking they are compressed.

[JerrettDavis]

The follow-up resolves the blockers I raised. profile_name now persists on the backend and is passed as aws_profile_name through the Anthropic, streaming Anthropic, OpenAI, and streaming OpenAI LiteLLM paths, with regression coverage around the completion kwargs. The guide is also internally consistent now about running Claude Code in normal Anthropic mode and letting Headroom handle Bedrock. I do not see a remaining blocker.

[JerrettDavis]

Reviewed the Bedrock ARN/profile changes. ARNs route through �edrock/converse, the named AWS profile is used both for discovery and LiteLLM calls, and the cache key includes profile so credentials do not cross-contaminate model maps. This will need a careful rebase with the newer botocore preflight work in #1553, but I do not see a code blocker in this PR itself.

[JerrettDavis]

Applied a style-only formatter commit to the Bedrock profile tests ( ests/test_bedrock_region.py, ests/test_vertex_claude_compression.py) to address the current
uff format --check failure. The other red test shard was canceled by a runner shutdown signal before any assertion failure; I do not see a code-level blocker in the Bedrock ARN/profile changes.

[JerrettDavis]

Reviewed the latest Bedrock head after the formatter, boto3 Session test fix, and merge-from-main commits. The implementation still routes Bedrock ARNs through bedrock/converse, forwards aws_profile_name on the real LiteLLM call paths, keeps profile-specific model-map caching isolated, and the updated tests now mock the same boto3.Session(...).client(...) shape used by the code.

The current CI/security/docs checks are green; no additional code changes requested.