The AI Toolchain — issue -328, September 22, 2025

Agno v2.0.8 adds CometAPI as a model provider, allow_partial_failure for MultiMCPTools, and dependencies access inside custom tools.

$ git clone --branch v2.0.8 https://github.com/agno-agi/agno.git
# already have the repo? check out this version:
$ git checkout v2.0.8

from agno.tools.mcp import MultiMCPTools

tools = MultiMCPTools(
    servers=["npx -y @modelcontextprotocol/server-github", "npx -y @modelcontextprotocol/server-slack"],
    allow_partial_failure=True
)

• ›Adds allow_partial_failure flag to MultiMCPTools toolkit, letting multi-server MCP setups continue when individual servers fail.
• ›Exposes dependencies as a built-in argument on custom tools, making injected dependencies directly accessible inside tool function bodies.
• ›Adds CometAPI as a new model provider.
• ›Supports multiple text_contents entries in add_contents() on Knowledge, enabling bulk text ingestion in a single call.

Haystack v2.18.0 adds pipeline error snapshots with resume support, PipelineTool, structured outputs for OpenAI generators, and runtime Agent system prompts.

$ git clone --branch v2.18.0 https://github.com/deepset-ai/haystack.git
# already have the repo? check out this version:
$ git checkout v2.18.0

try:
    pipeline.run(data=input_data)
except PipelineRuntimeError as exc_info:
    snapshot = exc_info.value.pipeline_snapshot
    intermediate_outputs = snapshot.pipeline_state.pipeline_outputs
    # inspect outputs, fix the issue, then resume
    pipeline.run(data={}, snapshot=snapshot)

from haystack import Pipeline
from haystack.tools import PipelineTool

retrieval_pipeline = Pipeline()
# ... add components ...

retrieval_tool = PipelineTool(
    pipeline=retrieval_pipeline,
    input_mapping={"query": ["bm25_retriever.query"]},
    output_mapping={"ranker.documents": "documents"},
    name="retrieval_tool",
    description="Use to retrieve documents",
)

from pydantic import BaseModel
from haystack.components.generators.chat import OpenAIChatGenerator
from haystack.dataclasses import ChatMessage

class CalendarEvent(BaseModel):
    event_name: str
    event_date: str
    event_location: str

generator = OpenAIChatGenerator(
    model="gpt-4o-2024-08-06",
    generation_kwargs={"response_format": CalendarEvent}
)
result = generator.run([ChatMessage.from_user("The Open NLP Meetup is in Berlin on September 19.")])
print(result["replies"][0].text)

• ›Adds snapshot argument to pipeline.run() to resume a failed pipeline from its last successful checkpoint, and exposes pipeline_snapshot.pipeline_state.pipeline_outputs on the PipelineRuntimeError exception for mid-run inspection.
• ›Adds PipelineTool class in haystack.tools to expose full Haystack Pipelines as LLM-compatible tools, with input_mapping and output_mapping arguments for fine-grained control over which pipeline inputs and outputs are visible to the LLM.
• ›Adds response_format support (Pydantic model or JSON schema) in generation_kwargs for OpenAIChatGenerator and AzureOpenAIChatGenerator; Pydantic models are supported for non-streaming, JSON schema for streaming responses.
• ›Adds request_headers parameter to LinkContentFetcher for custom per-request HTTP headers, with precedence order: httpx client defaults → component defaults → request_headers → rotating User-Agent.
• ›Adds exclude_subdomains parameter to SerperDevWebSearch; when True, restricts results to exact domains in allowed_domains, filtering out subdomains (defaults to False for backward compatibility).

Continue 1.18.0 adds --id flag for cn serve, AWS Bedrock tool streaming, and improved search-and-replace fallbacks.

$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]

$ cn serve --id my-workspace-server

• ›Adds --id flag to the cn serve command for identifying server instances.
• ›Enables tool call streaming for the AWS Bedrock provider.
• ›Introduces search-and-replace fallback logic with unified handling across edit operations.
• ›Adds PostHog telemetry tracking for CLI tool errors.

Arize Phoenix Helm chart gains IPv6 support and configurable image registry.

$ git clone --branch arize-phoenix-v11.35.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.35.0

• ›Adds IPv6 support to the Helm chart deployment.
• ›Allows image registry configuration in the Helm chart.

LanceDB v0.22.1-beta.3 adds shallow clone support for tables.

$ git clone --branch v0.22.1-beta.3 https://github.com/lancedb/lancedb.git
# already have the repo? check out this version:
$ git checkout v0.22.1-beta.3

• ›Adds shallow clone capability for tables, enabling fast duplication without copying all underlying data.

$ git clone --branch python-v0.25.1-beta.3 https://github.com/lancedb/lancedb.git
# already have the repo? check out this version:
$ git checkout python-v0.25.1-beta.3

Milvus 2.5.18 adds configurable delete snapshot size, expression result caching, and a configurable interim index build ratio.

$ git clone --branch v2.5.18 https://github.com/milvus-io/milvus.git
# already have the repo? check out this version:
$ git checkout v2.5.18

• ›Adds a param to modify delete snapshot size, giving operators control over memory trade-offs during delete-heavy workloads.
• ›Adds a param item forcing all indices ready for a segment before it is served, improving query consistency guarantees.
• ›Supports expression result cache, reducing redundant evaluation overhead for repeated filter expressions.
• ›Makes the build ratio of the interim index configurable, letting operators tune indexing resource usage.
• ›Removes the timeout for compaction tasks, preventing premature cancellation of long-running compaction jobs.