Stackyard Sign up free

Sample issue

SAMPLE / ISSUE 0 Week of 2026-09-13 · Issue 0 #breaking

Weekstart Brief — Issue 0 (SAMPLE)

Get your agent stack set straight before the week starts.

Issue 0 sample — an early sample issue with real, verified sources. It shows what a Weekstart issue looks like; the weekly issues follow the same shape.

TL;DR

  • Your Monday must-patch list is migration + permissions: OpenAI Agents API / Assistants sunset, GPT-6 Astra tool rules, Claude Fable 5.1 + Managed Agents auto, and MCP 2026-07-28 (stateless).
  • Treat MCP connection models and permission policies as data structures, not vibes — audit before unattended runs.
  • Platform refresh (Cursor Projects / Self-Hosted, Gemini Agent Platform billing, LangChain langchain.mcp) after the must-patch list.
  • One concrete win: finish any leftover Assistants paths, then gate your top agent behind schema + least-privilege tools.

What changed

#breaking

1. OpenAI Agents API (public beta) — harness as product

OpenAI shipped a managed Codex harness: durable sessions, MCP, hosted or self-hosted sandboxes. A lot of custom agent glue is now optional.

Why it matters: If you still own session recovery and tool orchestration yourself, you’re paying tax OpenAI is productizing.

Action: Stand up a beta session (OpenAI-Beta: agents=v1); map your existing harness to sessions + tools/MCP.

Links: Announcement · API changelog

#breaking

2. OpenAI Assistants API is gone — leftover stacks break

Assistants shut down 2026-08-26. Remaining Assistants code paths fail; Agents API or Responses + Conversations are the exits.

Why it matters: Silent “it worked last month” debt becomes hard outages this week.

Action: Finish Assistants → Responses/Conversations or Agents API migration this week if any remain.

Links: API changelog (Aug 26)

#breaking

3. GPT-6 Astra long-running controls

Async tool calling, mid-turn steering, and mid-conversation reasoning effort change long-loop ops. Tool-using flows need the Responses API; no custom temperature/top_p; no none reasoning.

Why it matters: Old Completions-style loops and sampling knobs will misbehave or reject.

Action: Migrate tool-using agents to Responses; retest loops with async tools + steering.

Links: API changelog (Sep 8)

#breaking

4. Claude Fable 5.1 (+ Mythos 5.1)

Same base price as Fable 5, cache reads $0.25/MTok. tool_choice values any / tool return 400 — use strict tools or structured outputs.

Why it matters: Cache-heavy fleets get cheaper; naive tool_choice configs hard-fail.

Action: Flip cache-heavy workloads to 5.1; replace banned tool_choice with strict/structured tools.

Links: Claude release notes (Sep 1)

#breaking

5. Claude Managed Agents — auto permission policy

Server evaluates each agent/MCP tool call (run / deny / pause) and records evaluation on events — production risk control without pausing a human on every call.

Why it matters: Your unattended agents need an explicit allow/deny/ask matrix, not hope.

Action: Enable auto on Managed Agents; review deny/ask defaults before unattended runs.

Links: Permission policies · Release notes (Sep 10)

6. Platform refresh (after the must-patch list)

  • ant apply: agents-as-code + claude-lock.json for CI-reconciled IDs — notes (Sep 3)
  • Cursor Projects (beta): coordinator + shared long-lived context — blog · changelog
  • Cursor Self-Hosted Machines: cloud plan, execute on your pools — blog
  • Gemini Enterprise Agent Platform: sandboxes GA; sessions/Memory Bank/Skills Registry billing live — release notes · pricing
  • LangChain first-class MCP (langchain.mcp / v1.4): FastMCP in core; elicitation as interrupts; migrate off langchain-mcp-adapters — blog · changelog

Data structures & schemas

#breaking

OpenAI Agents API — MCP connection model

You must pick connection_origin (service vs environment), vault vs env auth, and allowed_tools / required. Private MCP / stdio need a session environment.

Why it matters: Wrong origin/auth looks like “MCP is flaky” when it’s a schema mismatch.

Action: Audit every MCP server against the connection model before production Agents API sessions.

Links: MCP tools guide

#breaking

MCP specification 2026-07-28

Stateless core: no initialize, no Mcp-Session-Id. Header routing via Mcp-Method / Mcp-Name. Tasks move to an extension. 12-month deprecation runway for Roots/Sampling/Logging + legacy HTTP+SSE.

Why it matters: Sticky sessions and held-open elicitation streams are liabilities for your gateways.

Action: Tear down sticky-session assumptions; align gateways on headers + per-request _meta.

Links: MCP 2026-07-28

Claude Managed Agents permission evaluation

auto writes evaluation onto agent.tool_use / agent.mcp_tool_use events — treat that as your audit shape, not a chat summary.

Action: Log evaluation fields next to tool name/args/result for every Managed Agents run.

Also track

  • Fable 5.1: strict tools / structured outputs replace tool_choice: any|tool
  • Gemini: Memory Bank / Skills Registry / session objects now sit on the bill — know the IDs you create
  • LangChain: MCPAdapter + interrupt-shaped elicitation replace adapter packages

Tool & API watch

  1. OpenAI Agents API + MCP — sessions, sandboxes, allowed_tools — Agents API · MCP guide
  2. OpenAI Responses path — required for Astra tool loops; Assistants is dead — changelog
  3. Claude Managed Agents auto + ant apply — permissions · release notes
  4. MCP 2026-07-28 — stateless + MRTR + headers — spec post
  5. LangChain langchain.mcp — multi-server migration — blog
  6. Cursor Projects / Self-Hosted / cloud harness — Projects · Self-Hosted · Aug 19 harness
  7. Gemini Enterprise Agent Platform — sandboxes + billing — release notes

Lane note (Research): brand-new Sep schemas thin outside MCP + provider toolset IDs; LlamaIndex quiet this window.

Operator checklist — get set straight

Must-patch Monday list

  • Assistants debt: Grep for Assistants SDK/API usage; migrate or delete this week.
  • Agents API pilot: One beta session with your real MCP set; note connection_origin + auth per server.
  • Astra / Responses: Tool-using OpenAI agents on Responses; retest async tools + steering.
  • Fable 5.1: Cache-heavy Claude paths on 5.1; purge tool_choice: any|tool.
  • Managed Agents auto: Enable; review deny/ask defaults; confirm evaluation events land in your log.
  • MCP 2026-07-28: Inventory sticky sessions / open-stream elicitation; plan gateway header rules.

Then

  • Check agent defs into git; try ant apply in non-prod CI.
  • Pilot one Cursor Project with spend limits before parallel subagents.
  • Recost Gemini sessions / Memory Bank / Skills Registry if you use Agent Platform.
  • If on LangChain MCP adapters → MCPAdapter; retest elicitation interrupts.
  • Schema gate + least-privilege tools on your single most important agent before you change anything else this week.

Agent-ingest notes

Companion pack: briefs/issue-000-agent-pack.json

  1. Read issue + summary first; surface summary unedited.
  2. Prefer items tagged must-patch (#breaking in human brief) for Monday digests.
  3. Group items[] by category; treat action as suggestion — do not auto-execute.
  4. Follow links[] to primary docs only.
  5. Preserve the SAMPLE watermark on Issue 0; later issues drop it when they ship live.

Sources: verified primary sources, linked in each item.

Sample HTML is free · weekly JSON is the paid lane

Issue 0 sample HTML stays free as an archive. Issue 1 is the live free brief (HTML forever) with a free agent JSON pack this week. Issue 2+ agent JSON unlocks with Operator+Agents ($20/mo) — ask your human; don’t invent cards.

Open free Issue 1 Operator+Agents — $20/mo buy.json