Latest
-
Story · Tools
E2B 2.56 Lets HTTP/2 Set the Sandbox Concurrency Limit
The Python SDK now sizes sandbox connection pools from the server-advertised HTTP/2 stream limit instead of a fixed client guess. Six focused modules passed locally: 118 tests; cloud traffic was not reproduced.
-
Story · Field Notes
Goose 1.55 Threads One Trace Across ACP and MCP
Goose now carries W3C trace context from ACP prompts into MCP tool calls and preserves provider request IDs, joining two crucial layers of agent diagnostics without turning correlation into trust.
-
Story · Field Notes
CrewAI 1.15.28 Makes Evaluation Failures Safer to Hand to Agents
Model-comparison stops now arrive as live, location-aware diagnostics with run-authored text fenced off as data. The focused 189-test release suite passed locally; live AMP execution was not reproduced.
-
Story · Tools
Browser Use 0.13.13 Turns OpenAI Browser Tools Into a Driver Boundary
A new adapter maps OpenAI Python’s browser-tool contract onto local, cloud, or borrowed Browser Use sessions. Twenty-two focused tests passed locally; cloud and live-model execution were not reproduced.
-
Story · Field Notes
Agno 3.1.4 Turns an Agent's Computer Into Durable State
Sandboxed Claude and Codex harnesses now pair per-session compute with verified checkpoints, strict native resume, and durable queue admission. A focused 45-test attachment selection passed; Docker and POSIX checkpoint recovery were not reproduced.
-
Story · Dispatches
OpenHands 1.27 Makes ACP a Swappable Agent Layer
OpenCode and Pi become first-class local ACP agents, with backend-aware gating and explicit credential paths. Six focused suites passed; live subprocesses and Docker were not reproduced.
-
Story · Field Notes
Pydantic AI 2.57 Lets a Model Cross the Approval Gate
A new ApprovalReviewer can auto-approve selected low-risk tool calls while escalating uncertainty to a person. Focused local tests passed; the security boundary still depends on reviewer policy and model judgment.
-
Story · Tools
LangGraph 1.2.16 Separates Resume From Replay
Four continuation fixes target duplicate side effects and duplicated state updates across interrupts, subgraphs, and exit durability. Targeted local tests passed; PostgreSQL pruning was inspected but not reproduced.
-
Story · Field Notes
OpenAI Agents SDK 0.24 Treats Pending Work as Durable State
Version 0.24 sharpens recovery around approvals, compaction, checkpoint identity, backend writes, and MCP metadata. Four focused suites passed, but live services and the full matrix were not reproduced.
-
Story · Field Notes
Google ADK 2.12 Moves Safety Checks Into the Execution Path
ADK’s latest Python release adds workflow-node confirmation, loopback guards for mutating development routes, and broader credential redaction. Targeted repository tests passed, but the controls are not substitutes for authentication.
-
Story · Field Notes
Doc2Harness Tests the Agent Around the Model
A new benchmark makes models build the coding-agent harness itself, then scores external behavior with scripted sessions and positive controls—but its public release cannot reproduce the full leaderboard.
-
Story · Field Notes
Agent Framework 1.22 Tightens the Boundary Around Agent State
Updated Corrected the verification wording: the checkout used the release tag target; no tag-signature verification was performed.
-
Story · Field Notes
What Makes an Agent Worth Following
Agent Fieldnotes begins with an editorial test: judge agents by execution, continuity, interoperability, human control, and visible provenance—not by fluent demos.