fix(run_agent): preserve dotted Bedrock inference-profile model IDs (#11976)

Bedrock rejects ``global-anthropic-claude-opus-4-7`` with ``HTTP 400:
The provided model identifier is invalid`` because its inference
profile IDs embed structural dots
(``global.anthropic.claude-opus-4-7``) that ``normalize_model_name``
was converting to hyphens.  ``AIAgent._anthropic_preserve_dots`` did
not include ``bedrock`` in its provider allowlist, so every Claude-on-
Bedrock request through the AnthropicBedrock SDK path shipped with
the mangled model ID and failed.

Root cause
----------
``run_agent.py:_anthropic_preserve_dots`` (previously line 6589)
controls whether ``agent.anthropic_adapter.normalize_model_name``
converts dots to hyphens.  The function listed Alibaba, MiniMax,
OpenCode Go/Zen and ZAI but not Bedrock, so when a user set
``provider: bedrock`` with a dotted inference-profile model the flag
returned False and ``normalize_model_name`` mangled every dot in the
ID.  All four call sites in run_agent.py
(``build_anthropic_kwargs`` + three fallback / review / summary paths
at lines 6707, 7343, 8408, 8440) read from this same helper.

The bug shape matches #5211 for opencode-go, which was fixed in commit
f77be22c by extending this same allowlist.

Fix
---
* Add ``"bedrock"`` to the provider allowlist.
* Add ``"bedrock-runtime."`` to the base-URL heuristic as
  defense-in-depth, so a custom-provider-shaped config with
  ``base_url: https://bedrock-runtime.<region>.amazonaws.com`` also
  takes the preserve-dots path even if ``provider`` isn't explicitly
  set to ``"bedrock"``.  This mirrors how the code downstream at
  run_agent.py:759 already treats either signal as "this is Bedrock".

Bedrock model ID shapes covered
-------------------------------
| Shape | Preserved |
| --- | --- |
| ``global.anthropic.claude-opus-4-7`` (reporter's exact ID) | ✓ |
| ``us.anthropic.claude-sonnet-4-5-20250929-v1:0`` | ✓ |
| ``apac.anthropic.claude-haiku-4-5`` | ✓ |
| ``anthropic.claude-3-5-sonnet-20241022-v2:0`` (foundation) | ✓ |
| ``eu.anthropic.claude-3-5-sonnet`` (regional inference profile) | ✓ |

Non-Claude Bedrock models (Nova, Llama, DeepSeek) take the
``bedrock_converse`` / boto3 path which does not call
``normalize_model_name``, so they were never affected by this bug
and remain unaffected by the fix.

Narrow scope — explicitly not changed
-------------------------------------
* ``bedrock_converse`` path (non-Claude Bedrock models) — already
  correct; no ``normalize_model_name`` in that pipeline.
* Provider aliases (``aws``, ``aws-bedrock``, ``amazon``,
  ``amazon-bedrock``) — if a user bypasses the alias-normalization
  pipeline and passes ``provider="aws"`` directly, the base-URL
  heuristic still catches it because Bedrock always uses a
  ``bedrock-runtime.`` endpoint.  Adding the aliases themselves to the
  provider set is cheap but would be scope creep for this fix.
* No other places in ``agent/anthropic_adapter.py`` mangle dots, so
  the fix is confined to ``_anthropic_preserve_dots``.

Regression coverage
-------------------
``tests/agent/test_bedrock_integration.py`` gains three new classes:

* ``TestBedrockPreserveDotsFlag`` (5 tests): flag returns True for
  ``provider="bedrock"`` and for Bedrock runtime URLs (us-east-1 and
  ap-northeast-2 — the reporter's region); returns False for non-
  Bedrock AWS URLs like ``s3.us-east-1.amazonaws.com``; canary that
  Anthropic-native still returns False.
* ``TestBedrockModelNameNormalization`` (5 tests): every documented
  Bedrock model-ID shape survives ``normalize_model_name`` with the
  flag on; inverse canary pins that ``preserve_dots=False`` still
  mangles (so a future refactor can't decouple the flag from its
  effect).
* ``TestBedrockBuildAnthropicKwargsEndToEnd`` (2 tests): integration
  through ``build_anthropic_kwargs`` shows the reporter's exact model
  ID ends up unmangled in the outgoing kwargs.

Three of the new flag tests fail on unpatched ``origin/main`` with
``assert False is True`` (preserve-dots returning False for Bedrock),
confirming the regression is caught.

Validation
----------
``source venv/bin/activate && python -m pytest
tests/agent/test_bedrock_integration.py tests/agent/test_minimax_provider.py
-q`` -> 84 passed (40 new bedrock tests + 44 pre-existing, including
the minimax canaries that pin the pattern this fix mirrors).

CI-aligned broad suite: 12827 passed, 39 skipped, 19 pre-existing
baseline failures (all reproduce on clean ``origin/main``; none in
the touched code path).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Brian D. Evans 2026-04-18 07:04:38 +01:00 committed by Teknium
parent 323e827f4a
commit 1cf1016e72
2 changed files with 194 additions and 3 deletions

View file

@ -267,3 +267,174 @@ class TestPackaging:
from pathlib import Path
content = (Path(__file__).parent.parent.parent / "pyproject.toml").read_text()
assert '"hermes-agent[bedrock]"' in content
# ---------------------------------------------------------------------------
# Model ID dot preservation — regression for #11976
# ---------------------------------------------------------------------------
# AWS Bedrock inference-profile model IDs embed structural dots:
#
# global.anthropic.claude-opus-4-7
# us.anthropic.claude-sonnet-4-5-20250929-v1:0
# apac.anthropic.claude-haiku-4-5
#
# ``agent.anthropic_adapter.normalize_model_name`` converts dots to hyphens
# unless the caller opts in via ``preserve_dots=True``. Before this fix,
# ``AIAgent._anthropic_preserve_dots`` returned False for the ``bedrock``
# provider, so Claude-on-Bedrock requests went out with
# ``global-anthropic-claude-opus-4-7`` (all dots mangled to hyphens) and
# Bedrock rejected them with:
#
# HTTP 400: The provided model identifier is invalid.
#
# The fix adds ``bedrock`` to the preserve-dots provider allowlist and
# ``bedrock-runtime.`` to the base-URL heuristic, mirroring the shape of
# the opencode-go fix for #5211 (commit f77be22c), which extended this
# same allowlist.
class TestBedrockPreserveDotsFlag:
"""``AIAgent._anthropic_preserve_dots`` must return True on Bedrock so
inference-profile IDs survive the normalize step intact."""
def test_bedrock_provider_preserves_dots(self):
from types import SimpleNamespace
agent = SimpleNamespace(provider="bedrock", base_url="")
from run_agent import AIAgent
assert AIAgent._anthropic_preserve_dots(agent) is True
def test_bedrock_runtime_us_east_1_url_preserves_dots(self):
"""Defense-in-depth: even without an explicit ``provider="bedrock"``,
a ``bedrock-runtime.us-east-1.amazonaws.com`` base URL must not
mangle dots."""
from types import SimpleNamespace
agent = SimpleNamespace(
provider="custom",
base_url="https://bedrock-runtime.us-east-1.amazonaws.com",
)
from run_agent import AIAgent
assert AIAgent._anthropic_preserve_dots(agent) is True
def test_bedrock_runtime_ap_northeast_2_url_preserves_dots(self):
"""Reporter-reported region (ap-northeast-2) exercises the same
base-URL heuristic."""
from types import SimpleNamespace
agent = SimpleNamespace(
provider="custom",
base_url="https://bedrock-runtime.ap-northeast-2.amazonaws.com",
)
from run_agent import AIAgent
assert AIAgent._anthropic_preserve_dots(agent) is True
def test_non_bedrock_aws_url_does_not_preserve_dots(self):
"""Unrelated AWS endpoints (e.g. ``s3.us-east-1.amazonaws.com``)
must not accidentally activate the dot-preservation heuristic
the heuristic is scoped to the ``bedrock-runtime.`` substring
specifically."""
from types import SimpleNamespace
agent = SimpleNamespace(
provider="custom",
base_url="https://s3.us-east-1.amazonaws.com",
)
from run_agent import AIAgent
assert AIAgent._anthropic_preserve_dots(agent) is False
def test_anthropic_native_still_does_not_preserve_dots(self):
"""Canary: adding Bedrock to the allowlist must not weaken the
existing Anthropic native behaviour ``claude-sonnet-4.6`` still
becomes ``claude-sonnet-4-6`` for the Anthropic API."""
from types import SimpleNamespace
agent = SimpleNamespace(provider="anthropic", base_url="https://api.anthropic.com")
from run_agent import AIAgent
assert AIAgent._anthropic_preserve_dots(agent) is False
class TestBedrockModelNameNormalization:
"""End-to-end: ``normalize_model_name`` + the preserve-dots flag
reproduce the exact production request shape for each Bedrock model
family, confirming the fix resolves the reporter's HTTP 400."""
def test_global_anthropic_inference_profile_preserved(self):
"""The reporter's exact model ID."""
from agent.anthropic_adapter import normalize_model_name
assert normalize_model_name(
"global.anthropic.claude-opus-4-7", preserve_dots=True
) == "global.anthropic.claude-opus-4-7"
def test_us_anthropic_dated_inference_profile_preserved(self):
"""Regional + dated Sonnet inference profile."""
from agent.anthropic_adapter import normalize_model_name
assert normalize_model_name(
"us.anthropic.claude-sonnet-4-5-20250929-v1:0",
preserve_dots=True,
) == "us.anthropic.claude-sonnet-4-5-20250929-v1:0"
def test_apac_anthropic_haiku_inference_profile_preserved(self):
"""APAC inference profile — same structural-dot shape."""
from agent.anthropic_adapter import normalize_model_name
assert normalize_model_name(
"apac.anthropic.claude-haiku-4-5", preserve_dots=True
) == "apac.anthropic.claude-haiku-4-5"
def test_preserve_false_mangles_as_documented(self):
"""Canary: with ``preserve_dots=False`` the function still
produces the broken all-hyphen form this is the shape that
Bedrock rejected and that the fix avoids. Keeping this test
locks in the existing behaviour of ``normalize_model_name`` so a
future refactor doesn't accidentally decouple the knob from its
effect."""
from agent.anthropic_adapter import normalize_model_name
assert normalize_model_name(
"global.anthropic.claude-opus-4-7", preserve_dots=False
) == "global-anthropic-claude-opus-4-7"
def test_bare_foundation_model_id_preserved(self):
"""Non-inference-profile Bedrock IDs
(e.g. ``anthropic.claude-3-5-sonnet-20241022-v2:0``) use dots as
vendor separators and must also survive intact under
``preserve_dots=True``."""
from agent.anthropic_adapter import normalize_model_name
assert normalize_model_name(
"anthropic.claude-3-5-sonnet-20241022-v2:0",
preserve_dots=True,
) == "anthropic.claude-3-5-sonnet-20241022-v2:0"
class TestBedrockBuildAnthropicKwargsEndToEnd:
"""Integration: calling ``build_anthropic_kwargs`` with a Bedrock-
shaped model ID and ``preserve_dots=True`` produces the unmangled
model string in the outgoing kwargs the exact body sent to the
``bedrock-runtime.`` endpoint. This is the integration-level
regression for the reporter's HTTP 400."""
def test_bedrock_inference_profile_survives_build_kwargs(self):
from agent.anthropic_adapter import build_anthropic_kwargs
kwargs = build_anthropic_kwargs(
model="global.anthropic.claude-opus-4-7",
messages=[{"role": "user", "content": "hi"}],
tools=None,
max_tokens=1024,
reasoning_config=None,
preserve_dots=True,
)
assert kwargs["model"] == "global.anthropic.claude-opus-4-7", (
"Bedrock inference-profile ID was mangled in build_anthropic_kwargs: "
f"{kwargs['model']!r}"
)
def test_bedrock_model_mangled_without_preserve_dots(self):
"""Inverse canary: without the flag, ``build_anthropic_kwargs``
still produces the broken form so the fix in
``_anthropic_preserve_dots`` is the load-bearing piece that
wires ``preserve_dots=True`` through to this builder for the
Bedrock case."""
from agent.anthropic_adapter import build_anthropic_kwargs
kwargs = build_anthropic_kwargs(
model="global.anthropic.claude-opus-4-7",
messages=[{"role": "user", "content": "hi"}],
tools=None,
max_tokens=1024,
reasoning_config=None,
preserve_dots=False,
)
assert kwargs["model"] == "global-anthropic-claude-opus-4-7"