mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-06-09 08:21:50 +00:00
feat: native AWS Bedrock provider via Converse API
Salvaged from PR #7920 by JiaDe-Wu — cherry-picked Bedrock-specific additions onto current main, skipping stale-branch reverts (293 commits behind). Dual-path architecture: - Claude models → AnthropicBedrock SDK (prompt caching, thinking budgets) - Non-Claude models → Converse API via boto3 (Nova, DeepSeek, Llama, Mistral) Includes: - Core adapter (agent/bedrock_adapter.py, 1098 lines) - Full provider registration (auth, models, providers, config, runtime, main) - IAM credential chain + Bedrock API Key auth modes - Dynamic model discovery via ListFoundationModels + ListInferenceProfiles - Streaming with delta callbacks, error classification, guardrails - hermes doctor + hermes auth integration - /usage pricing for 7 Bedrock models - 130 automated tests (79 unit + 28 integration + follow-up fixes) - Documentation (website/docs/guides/aws-bedrock.md) - boto3 optional dependency (pip install hermes-agent[bedrock]) Co-authored-by: JiaDe WU <40445668+JiaDe-Wu@users.noreply.github.com>
This commit is contained in:
parent
21afc9502a
commit
0cb8c51fa5
18 changed files with 3543 additions and 20 deletions
|
|
@ -298,6 +298,33 @@ def build_anthropic_client(api_key: str, base_url: str = None):
|
|||
return _anthropic_sdk.Anthropic(**kwargs)
|
||||
|
||||
|
||||
def build_anthropic_bedrock_client(region: str):
|
||||
"""Create an AnthropicBedrock client for Bedrock Claude models.
|
||||
|
||||
Uses the Anthropic SDK's native Bedrock adapter, which provides full
|
||||
Claude feature parity: prompt caching, thinking budgets, adaptive
|
||||
thinking, fast mode — features not available via the Converse API.
|
||||
|
||||
Auth uses the boto3 default credential chain (IAM roles, SSO, env vars).
|
||||
"""
|
||||
if _anthropic_sdk is None:
|
||||
raise ImportError(
|
||||
"The 'anthropic' package is required for the Bedrock provider. "
|
||||
"Install it with: pip install 'anthropic>=0.39.0'"
|
||||
)
|
||||
if not hasattr(_anthropic_sdk, "AnthropicBedrock"):
|
||||
raise ImportError(
|
||||
"anthropic.AnthropicBedrock not available. "
|
||||
"Upgrade with: pip install 'anthropic>=0.39.0'"
|
||||
)
|
||||
from httpx import Timeout
|
||||
|
||||
return _anthropic_sdk.AnthropicBedrock(
|
||||
aws_region=region,
|
||||
timeout=Timeout(timeout=900.0, connect=10.0),
|
||||
)
|
||||
|
||||
|
||||
def read_claude_code_credentials() -> Optional[Dict[str, Any]]:
|
||||
"""Read refreshable Claude Code OAuth credentials from ~/.claude/.credentials.json.
|
||||
|
||||
|
|
|
|||
1098
agent/bedrock_adapter.py
Normal file
1098
agent/bedrock_adapter.py
Normal file
File diff suppressed because it is too large
Load diff
|
|
@ -112,6 +112,10 @@ _RATE_LIMIT_PATTERNS = [
|
|||
"please retry after",
|
||||
"resource_exhausted",
|
||||
"rate increased too quickly", # Alibaba/DashScope throttling
|
||||
# AWS Bedrock throttling
|
||||
"throttlingexception",
|
||||
"too many concurrent requests",
|
||||
"servicequotaexceededexception",
|
||||
]
|
||||
|
||||
# Usage-limit patterns that need disambiguation (could be billing OR rate_limit)
|
||||
|
|
@ -171,6 +175,11 @@ _CONTEXT_OVERFLOW_PATTERNS = [
|
|||
# Chinese error messages (some providers return these)
|
||||
"超过最大长度",
|
||||
"上下文长度",
|
||||
# AWS Bedrock Converse API error patterns
|
||||
"input is too long",
|
||||
"max input token",
|
||||
"input token",
|
||||
"exceeds the maximum number of input tokens",
|
||||
]
|
||||
|
||||
# Model not found patterns
|
||||
|
|
|
|||
|
|
@ -1012,6 +1012,16 @@ def get_model_context_length(
|
|||
if ctx:
|
||||
return ctx
|
||||
|
||||
# 4b. AWS Bedrock — use static context length table.
|
||||
# Bedrock's ListFoundationModels doesn't expose context window sizes,
|
||||
# so we maintain a curated table in bedrock_adapter.py.
|
||||
if provider == "bedrock" or (base_url and "bedrock-runtime" in base_url):
|
||||
try:
|
||||
from agent.bedrock_adapter import get_bedrock_context_length
|
||||
return get_bedrock_context_length(model)
|
||||
except ImportError:
|
||||
pass # boto3 not installed — fall through to generic resolution
|
||||
|
||||
# 5. Provider-aware lookups (before generic OpenRouter cache)
|
||||
# These are provider-specific and take priority over the generic OR cache,
|
||||
# since the same model can have different context limits per provider
|
||||
|
|
|
|||
|
|
@ -284,6 +284,80 @@ _OFFICIAL_DOCS_PRICING: Dict[tuple[str, str], PricingEntry] = {
|
|||
source_url="https://ai.google.dev/pricing",
|
||||
pricing_version="google-pricing-2026-03-16",
|
||||
),
|
||||
# AWS Bedrock — pricing per the Bedrock pricing page.
|
||||
# Bedrock charges the same per-token rates as the model provider but
|
||||
# through AWS billing. These are the on-demand prices (no commitment).
|
||||
# Source: https://aws.amazon.com/bedrock/pricing/
|
||||
(
|
||||
"bedrock",
|
||||
"anthropic.claude-opus-4-6",
|
||||
): PricingEntry(
|
||||
input_cost_per_million=Decimal("15.00"),
|
||||
output_cost_per_million=Decimal("75.00"),
|
||||
source="official_docs_snapshot",
|
||||
source_url="https://aws.amazon.com/bedrock/pricing/",
|
||||
pricing_version="bedrock-pricing-2026-04",
|
||||
),
|
||||
(
|
||||
"bedrock",
|
||||
"anthropic.claude-sonnet-4-6",
|
||||
): PricingEntry(
|
||||
input_cost_per_million=Decimal("3.00"),
|
||||
output_cost_per_million=Decimal("15.00"),
|
||||
source="official_docs_snapshot",
|
||||
source_url="https://aws.amazon.com/bedrock/pricing/",
|
||||
pricing_version="bedrock-pricing-2026-04",
|
||||
),
|
||||
(
|
||||
"bedrock",
|
||||
"anthropic.claude-sonnet-4-5",
|
||||
): PricingEntry(
|
||||
input_cost_per_million=Decimal("3.00"),
|
||||
output_cost_per_million=Decimal("15.00"),
|
||||
source="official_docs_snapshot",
|
||||
source_url="https://aws.amazon.com/bedrock/pricing/",
|
||||
pricing_version="bedrock-pricing-2026-04",
|
||||
),
|
||||
(
|
||||
"bedrock",
|
||||
"anthropic.claude-haiku-4-5",
|
||||
): PricingEntry(
|
||||
input_cost_per_million=Decimal("0.80"),
|
||||
output_cost_per_million=Decimal("4.00"),
|
||||
source="official_docs_snapshot",
|
||||
source_url="https://aws.amazon.com/bedrock/pricing/",
|
||||
pricing_version="bedrock-pricing-2026-04",
|
||||
),
|
||||
(
|
||||
"bedrock",
|
||||
"amazon.nova-pro",
|
||||
): PricingEntry(
|
||||
input_cost_per_million=Decimal("0.80"),
|
||||
output_cost_per_million=Decimal("3.20"),
|
||||
source="official_docs_snapshot",
|
||||
source_url="https://aws.amazon.com/bedrock/pricing/",
|
||||
pricing_version="bedrock-pricing-2026-04",
|
||||
),
|
||||
(
|
||||
"bedrock",
|
||||
"amazon.nova-lite",
|
||||
): PricingEntry(
|
||||
input_cost_per_million=Decimal("0.06"),
|
||||
output_cost_per_million=Decimal("0.24"),
|
||||
source="official_docs_snapshot",
|
||||
source_url="https://aws.amazon.com/bedrock/pricing/",
|
||||
pricing_version="bedrock-pricing-2026-04",
|
||||
),
|
||||
(
|
||||
"bedrock",
|
||||
"amazon.nova-micro",
|
||||
): PricingEntry(
|
||||
input_cost_per_million=Decimal("0.035"),
|
||||
output_cost_per_million=Decimal("0.14"),
|
||||
source="official_docs_snapshot",
|
||||
source_url="https://aws.amazon.com/bedrock/pricing/",
|
||||
pricing_version="bedrock-pricing-2026-04",
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue