agentbyte 0.53.0__tar.gz → 0.54.0__tar.gz

{agentbyte-0.53.0 → agentbyte-0.54.0}/CHANGELOG.md

@@ -6,6 +6,31 @@ The format follows Keep a Changelog principles and semantic versioning.
 
 ## [Unreleased]
 
+## [0.54.0] - 2026-10-12
+
+### Added
+
+- Anthropic/Bedrock prompt caching: `AnthropicConversionMixin` now tags the `system` block
+  with a `cache_control: {"type": "ephemeral"}` breakpoint whenever a `SystemMessage` is
+  present, so both `AnthropicChatCompletionClient` and `AnthropicBedrockChatCompletionClient`
+  get cache-read discounting through the same shared request-building code — no config flag,
+  no-op below the per-model minimum cacheable size. Added a matching
+  `examples/llm/anthropic_bedrock_prompt_caching_cost_smoke_test.py` alongside the existing
+  OpenAI/Azure smoke test.
+- `examples/agents/anthropic_agent_example.py`: Bedrock Claude injected via
+  `AnthropicBedrockChatCompletionClient.from_region()` driven through `Agent.run()`/
+  `Agent.run_stream()`. `examples/agents/cohere_bedrock_embedding_example.py`: raw
+  `CohereBedrockEmbeddingClient` calls, then the same client wrapped in `EmbeddingBatcher`,
+  then with `LoggingMiddleware` added — both live-verified end to end against real Bedrock.
+
+### Fixed
+
+- `PricingRegistry.ANTHROPIC_CHAT_PRICING` had no exact entry for `claude-sonnet-4-5` or
+  `claude-sonnet-4-6`; both resolved only through the generic `claude-sonnet-4` prefix
+  fallback, which happened to match current pricing ($3/$15 per MTok) but offered no
+  protection against a future divergent repricing (the same reasoning that already justified
+  separate `claude-opus-4-5`..`claude-opus-4-8` entries). Added explicit entries for both.
+
 ## [0.53.0] - 2026-10-10
 
 ### Added

{agentbyte-0.53.0 → agentbyte-0.54.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: agentbyte
-Version: 0.53.0
+Version: 0.54.0
 Summary: A toolkit for designing multiagent systems
 Author-email: MrDataPsycho <mr.data.psycho@gmail.com>
 License-Expression: LicenseRef-Proprietary
@@ -90,7 +90,7 @@ Description-Content-Type: text/markdown
 
 Agentbyte is an observability-first agentic AI framework for building and studying multiagent systems with a learning-first, implementation-oriented workflow.
 
-Current release: **0.53.0**
+Current release: **0.54.0**
 
 ## Building an Agent
 

{agentbyte-0.53.0 → agentbyte-0.54.0}/README.md

@@ -2,7 +2,7 @@
 
 Agentbyte is an observability-first agentic AI framework for building and studying multiagent systems with a learning-first, implementation-oriented workflow.
 
-Current release: **0.53.0**
+Current release: **0.54.0**
 
 ## Building an Agent
 

agentbyte-0.54.0/src/agentbyte/__about__.py

@@ -0,0 +1,2 @@
+__version__ = "0.54.0"
+VERSION = __version__

{agentbyte-0.53.0 → agentbyte-0.54.0}/src/agentbyte/llm/anthropic/_conversion.py

@@ -94,7 +94,15 @@ class AnthropicConversionMixin:
 
         system = self._extract_system(messages)
         if system is not None:
-            api_kwargs["system"] = system
+            # A single `cache_control` breakpoint on the system block marks it
+            # as a cache candidate for Anthropic's Messages API (no beta header
+            # needed as of anthropic==1.13.0's non-beta `TextBlockParam`). This
+            # is a no-op below the per-model minimum cacheable size and strictly
+            # beneficial above it, so there's no config flag for it -- shared
+            # here means both direct Anthropic and Bedrock transports get it.
+            api_kwargs["system"] = [
+                {"type": "text", "text": system, "cache_control": {"type": "ephemeral"}}
+            ]
 
         api_messages = self._convert_messages_to_api_format(messages)
         api_tools = self._convert_tools(tools)
@@ -182,7 +190,15 @@ class AnthropicConversionMixin:
 
         system = self._extract_system(messages)
         if system is not None:
-            api_kwargs["system"] = system
+            # A single `cache_control` breakpoint on the system block marks it
+            # as a cache candidate for Anthropic's Messages API (no beta header
+            # needed as of anthropic==1.13.0's non-beta `TextBlockParam`). This
+            # is a no-op below the per-model minimum cacheable size and strictly
+            # beneficial above it, so there's no config flag for it -- shared
+            # here means both direct Anthropic and Bedrock transports get it.
+            api_kwargs["system"] = [
+                {"type": "text", "text": system, "cache_control": {"type": "ephemeral"}}
+            ]
 
         api_messages = self._convert_messages_to_api_format(messages)
         api_tools = self._convert_tools(tools)

{agentbyte-0.53.0 → agentbyte-0.54.0}/src/agentbyte/llm/pricing.py

@@ -456,6 +456,13 @@ class PricingRegistry:
         "claude-opus-4-5": ModelPricing(input_per_1m=5.0, output_per_1m=25.0),
         "claude-opus-4": ModelPricing(input_per_1m=15.0, output_per_1m=75.0),
         "claude-sonnet-5": ModelPricing(input_per_1m=2.0, output_per_1m=10.0),
+        # claude-sonnet-4-6/-4-5 currently price identically to claude-sonnet-4 ($3/$15,
+        # verified against platform.claude.com/docs/en/about-claude/pricing), so the
+        # prefix fallback already resolved them correctly -- listed explicitly anyway so a
+        # future divergent repricing (as happened for claude-opus-4-5 vs. claude-opus-4)
+        # doesn't silently fall through to the wrong rate.
+        "claude-sonnet-4-6": ModelPricing(input_per_1m=3.0, output_per_1m=15.0),
+        "claude-sonnet-4-5": ModelPricing(input_per_1m=3.0, output_per_1m=15.0),
         "claude-sonnet-4": ModelPricing(input_per_1m=3.0, output_per_1m=15.0),
         "claude-haiku-5-5": ModelPricing(
             input_per_1m=0.10,

{agentbyte-0.53.0 → agentbyte-0.54.0}/tests/llm/test_anthropic_bedrock_client.py

@@ -13,7 +13,7 @@ import pytest
 
 from agentbyte.llm import AnthropicBedrockChatCompletionClient
 from agentbyte.llm.types import ModelPricing
-from agentbyte.messages import UserMessage
+from agentbyte.messages import SystemMessage, UserMessage
 
 
 def _block(block_type, **fields):
@@ -73,6 +73,37 @@ async def test_bedrock_create_parses_tool_calls_and_usage():
     assert result.usage.cost_estimate is not None
 
 
+@pytest.mark.asyncio
+async def test_bedrock_create_marks_system_block_as_cache_breakpoint():
+    """The `cache_control` breakpoint is set in the shared AnthropicConversionMixin,
+    so the Bedrock transport gets prompt caching for free -- same as the direct
+    client's test_anthropic_create_splits_system_message_to_top_level_param."""
+    fake_response = _FakeResponse(
+        model="anthropic.claude-haiku-4-5-20251001-v1:0",
+        content=[_block("text", text="ok")],
+        usage=_usage(input_tokens=1, output_tokens=1),
+    )
+    fake_client = _FakeBedrockClient(response=fake_response)
+    client = AnthropicBedrockChatCompletionClient(
+        model="anthropic.claude-haiku-4-5-20251001-v1:0", client=fake_client
+    )
+
+    await client.create(
+        messages=[
+            SystemMessage(content="You are helpful.", source="system"),
+            UserMessage(content="hi", source="user"),
+        ]
+    )
+
+    assert fake_client.last_kwargs["system"] == [
+        {
+            "type": "text",
+            "text": "You are helpful.",
+            "cache_control": {"type": "ephemeral"},
+        }
+    ]
+
+
 def test_bedrock_estimate_cost_normalizes_anthropic_prefix_and_version_suffix():
     """The Bedrock-specific ID normalizer is the whole reason this client needs
     its own _estimate_cost: strip "anthropic." and "-vN:0" before resolving

{agentbyte-0.53.0 → agentbyte-0.54.0}/tests/llm/test_anthropic_client.py

@@ -108,12 +108,98 @@ async def test_anthropic_create_splits_system_message_to_top_level_param():
         ]
     )
 
-    assert fake_client.last_kwargs["system"] == "You are helpful."
+    assert fake_client.last_kwargs["system"] == [
+        {
+            "type": "text",
+            "text": "You are helpful.",
+            "cache_control": {"type": "ephemeral"},
+        }
+    ]
     sent_messages = fake_client.last_kwargs["messages"]
     assert all(m["role"] != "system" for m in sent_messages)
     assert len(sent_messages) == 1
 
 
+@pytest.mark.asyncio
+async def test_anthropic_create_omits_system_kwarg_when_no_system_message():
+    fake_response = _FakeResponse(
+        model="claude-sonnet-4-5",
+        content=[_block("text", text="ok")],
+        usage=_usage(input_tokens=1, output_tokens=1),
+    )
+    fake_client = _FakeAnthropicClient(response=fake_response)
+    client = AnthropicChatCompletionClient(model="claude-sonnet-4-5", client=fake_client)
+
+    await client.create(messages=[UserMessage(content="hi", source="user")])
+
+    assert "system" not in fake_client.last_kwargs
+
+
+@pytest.mark.asyncio
+async def test_anthropic_create_stream_marks_system_block_as_cache_breakpoint():
+    events = [
+        types.SimpleNamespace(
+            type="message_start",
+            message=types.SimpleNamespace(model="claude-sonnet-4-5"),
+        ),
+        types.SimpleNamespace(
+            type="content_block_delta",
+            index=0,
+            delta=_block("text_delta", text="Hello"),
+        ),
+        types.SimpleNamespace(
+            type="message_delta",
+            delta=types.SimpleNamespace(stop_reason="end_turn"),
+            usage=_usage(input_tokens=4, output_tokens=2),
+        ),
+    ]
+    fake_client = _FakeAnthropicClient(stream=_FakeStream(events))
+    client = AnthropicChatCompletionClient(model="claude-sonnet-4-5", client=fake_client)
+
+    async for _ in client.create_stream(
+        messages=[
+            SystemMessage(content="You are helpful.", source="system"),
+            UserMessage(content="hi", source="user"),
+        ]
+    ):
+        pass
+
+    assert fake_client.last_kwargs["system"] == [
+        {
+            "type": "text",
+            "text": "You are helpful.",
+            "cache_control": {"type": "ephemeral"},
+        }
+    ]
+
+
+@pytest.mark.asyncio
+async def test_anthropic_create_stream_omits_system_kwarg_when_no_system_message():
+    events = [
+        types.SimpleNamespace(
+            type="message_start",
+            message=types.SimpleNamespace(model="claude-sonnet-4-5"),
+        ),
+        types.SimpleNamespace(
+            type="content_block_delta",
+            index=0,
+            delta=_block("text_delta", text="Hello"),
+        ),
+        types.SimpleNamespace(
+            type="message_delta",
+            delta=types.SimpleNamespace(stop_reason="end_turn"),
+            usage=_usage(input_tokens=4, output_tokens=2),
+        ),
+    ]
+    fake_client = _FakeAnthropicClient(stream=_FakeStream(events))
+    client = AnthropicChatCompletionClient(model="claude-sonnet-4-5", client=fake_client)
+
+    async for _ in client.create_stream(messages=[UserMessage(content="hi", source="user")]):
+        pass
+
+    assert "system" not in fake_client.last_kwargs
+
+
 @pytest.mark.asyncio
 async def test_anthropic_create_converts_openai_shaped_tools_to_anthropic_shape():
     fake_response = _FakeResponse(

agentbyte-0.53.0/src/agentbyte/__about__.py

@@ -1,2 +0,0 @@
-__version__ = "0.53.0"
-VERSION = __version__