Claude Code v2.1.257 adds Fable 5.1, containment-escape gating, and outside-folder read prompts, while Hermes Agent and Codex reports show orchestration and deploy credentials still failing in production workflows.

In this episode

1. v2.1.257 — Anthropic

   What's changed Added Claude Fable 5.1 ( claude-fable-5-1 ), now the default Fable model — 1M context, $10/$50 per Mtok with $0.25/Mtok cache reads Added "Time format" ( timeFormat ) and timeZone settings: 12-hour, 24-hour, 24-hour UTC, or a strftime pattern for the turn-end clock and transcript-view timestamps Added a Containment Escape rule to auto mode so cloud metadata-credential fetches,…

2. async_delegation wake self-post: 600s client timeout + no per-session lock ⇒ duplicate concurrent turns, delayed and dropped results · Issue #100689 · NousResearch/hermes-agent · GitHub — GitHub

   # async_delegation wake self-post: 600s client timeout + no per-session lock ⇒ duplicate concurrent turns, delayed and dropped results

- State: open

- Author: zbabiarz

- Created: 2026-09-01T20:48:11Z

- Updated: 2026-09-02T03:09:29Z

- Repository: NousResearch/hermes-agent

- Number: #100689

## Labels

- type/bug

- comp/gateway

- tool/delegate

- P2

- sweeper:risk-session-state

-…

Subagents (Agent tool, custom types) die silently at startup: no transcript, no error, no log; parent never notified · Issue #91298 · anthropics/claude-code · GitHub — Anthropic

# Subagents (Agent tool, custom types) die silently at startup: no transcript, no error, no log; parent never notified

- State: open

- Author: cciordas

- Created: 2026-09-01T19:18:18Z

- Updated: 2026-09-01T19:19:36Z

- Repository: anthropics/claude-code

- Number: #91298

## Labels

- bug

- has repro

- platform:linux

- area:agents

---

## Summary

Subagents spawned via the Agent tool (custom…

Sites source repository write credential is already expired when issued · Issue #42119 · openai/codex · GitHub — GitHub

# Sites source repository write credential is already expired when issued

- State: open

- Author: v19880112-lab

- Created: 2026-09-01T19:14:14Z

- Updated: 2026-09-01T19:14:54Z

- Repository: openai/codex

- Number: #42119

## Labels

- bug

- auth

- app

---

### What issue are you seeing?

A Sites project cannot be published because create_source_repository_write_credential returns a source write…

[BUG] Cowork: sessions-api/sessions-bridge emit zero log output — device bridge never initializes (Windows, 1.40609.0.0) · Issue #91252 · anthropics/claude-code · GitHub — Anthropic

# [BUG] Cowork: sessions-api/sessions-bridge emit zero log output — device bridge never initializes (Windows, 1.40609.0.0)

- State: open

- Author: jonathanlavignenrcan

- Created: 2026-09-01T15:29:13Z

- Updated: 2026-09-01T15:30:47Z

- Repository: anthropics/claude-code

- Number: #91252

## Labels

- bug

- has repro

- platform:windows

- area:cowork

---

### Preflight Checklist

- [x] I have…

Daily TopFive for AI Coding Daily. Links above go to the original articles. Follow and rate AI Coding Daily wherever you listen. Feedback? Email [email protected].

Claude Code v2.1.252 fixes Mac Bash task failures, Remote Control stalls, and oversized failure notifications, while Anthropic usage-limit math and PostHog’s AGENTS.md advice point to a quieter theme: agent reliability now depends on less context, not louder prompts.

In this episode

1. v2.1.252 — Anthropic

   What's changed Fixed Bash commands failing with "task output swap refused (tasks dir moved or linked)" on some Macs Fixed "always allow" not saving in a project that has no .claude/settings.local.json yet Fixed Remote Control sessions hosted by Claude Desktop or VS Code stalling for minutes after a tool finished when the connection to claude.ai was degraded Fixed background task notifications…

2. Step Back — Anthropic has reportedly reduced Claude Code’s context window by 17%—what changes in practice for developers, and how can we tell whether that’s a manageable workflow constraint or a meaningful loss of coding reliability?Background sources
   • Anthropic is cutting Claude Code's current weekly limits by 17% — Mayank Parmar
   • Context Window and Token Budget — Claude Code · Engineering Playbook — Vercel
   • Claude Code users to get 17% less weekly usage from September 14 as Anthropic ends 50% boost - The Economic Times — Indiatimes
   • An update on recent Claude Code quality reports — Anthropic
3. Your AGENTS.md is holding you back - by Jina Yoon — PostHog

   Read this before deleting your AGENTS.md - by Jina Yoon

SubscribeSign in

# Read this before deleting your AGENTS.md

### The three best ways to unhobble your AI agents

Aug 31, 2026

26

4

Share

Context engineering used to focus on adding information that base models lacked:

But then the models kept getting better. Now, the same context your agents couldn’t function without can make them…

Daily TopFive for AI Coding Daily. Links above go to the original articles. Follow and rate AI Coding Daily wherever you listen. Feedback? Email [email protected].

Claude Code v2.1.251 adds model-switch hooks, prompt-cache visibility, and path-traversal fixes, while Caveman chases token cuts and Gemini users report large-file corruption. The through-line: agent control surfaces are becoming production infrastructure, not UI garnish.

In this episode

1. v2.1.251 — Anthropic

   What's changed Added PreModelSwitch and PostModelSwitch hook events (block, confirm, or annotate a model switch); SessionStart resume hooks now receive session staleness and the estimated re-cache cost Added live streaming of a foreground subagent's tool calls and results to Remote Control clients (background subagents, the default, still show status only) Added a Spend limit bar to /usage and a…

2. JuliusBrussee/caveman — GitHub

   # JuliusBrussee/caveman

Published: 2026-08-30T17:10:03+00:00

Source: github.com (github.com)

Language: en

## Story

# JuliusBrussee/caveman

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

- Stars: 101860

- Forks: 5928

- Watchers: 101860

- Open issues: 108

- License: Other

- Homepage: https://docs.caveman.so/docs/quickstart

-…

• “Author here. A few people are arguing against a stronger claim than the repo is meant to make. As well, this was very much intended to be a joke and not research level commentary. This skill is not intended to reduce hidden reasoning / thinking tokens. Anthropic’s own docs…” — Hacker News (904 pts thread)

  Our take: We buy the author’s distinction: cutting visible filler is not the same as cutting hidden reasoning. That matters, because the production question is not “can we make Claude grunt,” it is “can we reduce cheap-but-annoying output without damaging task state.”

• “Idk I try talk like cavemen to claude. Claude seems answer less good. We have more misunderstandings. Feel like sometimes need more words in total to explain previous instructions. Also less context is more damage if typo. Who agrees? Could be just feeling I have. I often ad…” — Hacker News (904 pts thread)

  Our take: This is the real counterweight: compression is lossy, and with agents the loss often shows up as one extra clarification turn that eats the savings. Fewer tokens only wins if the ambiguity budget does not quietly move from the model to the human.

• “This is neat but my employer rates my performance based on token consumption; is there one that makes Claude needlessly verbose?” — Hacker News (904 pts thread)

  Our take: Unfortunately, yes: if your org rewards token burn, the optimal agent is just a junior consultant with a context window. We’re joking, mostly, but cost dashboards do create exactly this kind of perverse theater.

Gemini models corrupts large UTF-8 source files during surgical edits - Google AI Studio - Google AI Developers Forum — Google

Gemini models corrupts large UTF-8 source files during surgical edits - Google AI Studio - Google AI Developers Forum

Skip to where you left off (post 3) Skip to last reply Skip to top

# Build with Google AI Forum

Read the community guidelines arrow_forward Browse topics by tag arrow_forward

Hi Everyone,

Starting June 19, 2026, the Gemini API will stop accepting requests from unrestricted…

[Bug]: Desktop feature toggles (e.g. Kanban) enable the UI panel but never the agent-side toolset — and nothing tells the user there are two switches · Issue #96969 · NousResearch/hermes-agent · GitHub — GitHub

# [Bug]: Desktop feature toggles (e.g. Kanban) enable the UI panel but never the agent-side toolset — and nothing tells the user there are two switches

- State: open

- Author: zengzheqing

- Created: 2026-08-28T07:56:11Z

- Updated: 2026-08-28T07:58:34Z

- Repository: NousResearch/hermes-agent

- Number: #96969

## Labels

- type/bug

- comp/tools

- comp/cron

- tool/skills

- area/config

- P3

-…

I built CI for prompts, and the first bug was in the tests - DEV Community — DEV Community

I built CI for prompts, and the first bug was in the tests - DEV Community

Parth Gupta

Posted on Aug 30

# I built CI for prompts, and the first bug was in the tests

Sentinel is a prompt regression gate. It runs an eval suite against both versions of a changed prompt, accounts for run-to-run noise, and stops before merge. Built in a week for the Agent Harness Hackathon (WeMakeDevs ×…

Daily TopFive for AI Coding Daily. Links above go to the original articles. Follow and rate AI Coding Daily wherever you listen. Feedback? Email [email protected].

Claude Code v2.1.248 adds restricted mode while VS Code Copilot hooks overfire and Codex on Windows hits a no-window launch bug. The through-line: agent tooling is moving from impressive demos to stubborn production controls.

In this episode

1. v2.1.248 — Anthropic

   What's changed Added --restricted (or CLAUDE_CODE_RESTRICTED=1 ): removes the built-in tools that run commands or code and WebFetch (unless named in --tools ), keeps file tools inside the working directory, refuses bypassPermissions , and ignores user, project and local settings files Added experimental.cacheTtl ( "5m" or "1h" ) to agent frontmatter: a per-agent prompt cache TTL used when no…

2. Hooks with matcher field do not filter by tool · Issue #332988 · microsoft/vscode · GitHub — GitHub

   # Hooks with matcher field do not filter by tool

- State: open

- Author: lonitra

- Created: 2026-08-27T17:21:27Z

- Updated: 2026-08-27T17:30:49Z

- Repository: microsoft/vscode

- Number: #332988

- Assignees: pwang347

## Labels

- new release

---

- VS Code Version: 1.135.0

- Feature (e.g. agent/edit/ask mode): Hooks (PreToolUse / PostToolUse)

- Selected model (e.g. GPT 4.1, Claude 3.7 Sonnet):…

Windows Desktop launches ChatGPT.exe background processes but no UI/window appears · Issue #41075 · openai/codex · GitHub — OpenAI

# Windows Desktop launches ChatGPT.exe background processes but no UI/window appears

- State: closed

- Author: muliang1007x-png

- Created: 2026-08-27T07:12:37Z

- Updated: 2026-08-27T07:19:03Z

- Repository: openai/codex

- Number: #41075

## Labels

- bug

- windows-os

- app

---

### What version of the Codex App are you…

AG-UI tool-return rehydration parses twice, using `validate_python` where `validate_json` stays in Rust · Issue #7826 · pydantic/pydantic-ai · GitHub — GitHub

# AG-UI tool-return rehydration parses twice, using `validate_python` where `validate_json` stays in Rust

- State: open

- Author: dsfaccini

- Created: 2026-08-27T17:01:47Z

- Updated: 2026-08-27T17:02:12Z

- Repository: pydantic/pydantic-ai

- Number: #7826

- Assignees: dsfaccini

## Labels

- performance

- AG-UI

---

> This issue was posted by Claude Code using claude-opus-5 on behalf of…

The Bug Class AI Coding Agents Keep Introducing (and How We Started Catching It in CI) - DEV Community — DEV Community

The Bug Class AI Coding Agents Keep Introducing (and How We Started Catching It in CI) - DEV Community

## The pattern

AI coding agents are good at producing a diff that works in the narrowest sense — the function still returns what the test expects. What they're not reliably good at is preserving properties nobody wrote a test for in the first place.

The two we kept running into: an…

Daily TopFive for AI Coding Daily. Links above go to the original articles. Follow and rate AI Coding Daily wherever you listen. Feedback? Email [email protected].

Claude Code v2.1.247 fixes sub-agent fallback and prompt-overflow wedges while adding feedback drafts and API cost profiling; meanwhile, GPT-5.6 users document week-long long-running execution failures. The center of gravity is agent infrastructure breaking at workload boundaries.

In this episode

1. v2.1.247 — Anthropic

   What's changed Added the SendFeedback tool: when something goes wrong in a session, Claude can draft a feedback report for you to review and send from /feedback (turn off with the feedbackDrafts setting) Added {id, text, cooldownSessions, priority} entries, tipsFile , and label to spinnerTipsOverride , so organizations can rotate their own tips alongside the built-in ones Added a tip on Bash…

2. Seven days of GPT-5.6 Sol regressions: Extra High now ... — OpenAI

   : August 26 Update — Seven days of GPT-5.6 Sol regressions: Extra High now stalls at “Thinking,” Activity sidebar is inaccessible, and long-context/file/execution failures continue after the routing fix** - ChatGPT / Bugs - OpenAI Developer Community

# : August 26 Update — Seven days of GPT-5.6 Sol regressions: Extra High now stalls at “Thinking,” Activity sidebar is inaccessible, and…

GPT-5.6 High execution regression: ordinary Chat went 102m26s -> repeated ~25–26m stops on same Plus account; Work still gets long-run handoff - ChatGPT / Bugs - OpenAI Developer Community — OpenAI Developer Community

GPT-5.6 High execution regression: ordinary Chat went 102m26s -> repeated ~25–26m stops on same Plus account; Work still gets long-run handoff - ChatGPT / Bugs - OpenAI Developer Community

Skip to where you left off (post 6) Skip to last reply Skip to top

You have selected 0 posts.

441 views 1 link

read 13 min

Summarize

6 / 8

Aug 25

# Reproducible ChatGPT Plus execution-class regression:…

Debugging a Flaky LLM Pipeline: Timeouts, Truncation, and a 40-Line Probe - DEV Community — DEV Community

Debugging a Flaky LLM Pipeline: Timeouts, Truncation, and a 40-Line Probe - DEV Community

Posted on Aug 25

# Debugging a Flaky LLM Pipeline: Timeouts, Truncation, and a 40-Line Probe

The failure had nothing to do with the free server, and everything to do with two assumptions I had baked into my harness. I moved a small LLM batch pipeline to MonkeyCode's free server to cut costs, and within…

Context Drift on a Free Server: A Reproducible Memory Stress Test - DEV Community — DEV Community

# Context Drift on a Free Server: A Reproducible Memory Stress Test - DEV Community

Published: 2026-08-25T04:40:05+00:00

Source: dev.to (dev.to)

Language: en

## Story

Context Drift on a Free Server: A Reproducible Memory Stress Test - DEV Community

A developer asks a free coding model to refactor a service in twelve steps. Steps one through three pass cleanly. By step five, the model renames…

Daily TopFive for AI Coding Daily. Links above go to the original articles. Follow and rate AI Coding Daily wherever you listen. Feedback? Email [email protected].

Claude Code v2.1.246 adds sharper MCP interruption reporting and permission warnings as a glibc 2.44 crash gets bisected; meanwhile Codex Desktop and practitioner benchmarks show agent workflows still losing goals, preserving stale context, and looping expensively.

In this episode

1. v2.1.246 — Anthropic

   What's changed Added a startup warning for Bash allow rules with a wildcard before the subcommand (e.g. Bash(git * main) ), since they also match options inserted before the subcommand Added an Auto mode tab to /permissions for viewing and editing auto mode classifier rules Added the turn's completion time to the end-of-turn duration line, e.g. ✻ Sautéed for 23s · done 6:05 PM Fixed fullscreen…

2. 2.1.242+ segfault is glibc-2.44-only: bisected 2.35→2.44, glibc 2.44's __newlocale refactor added an unconditional free(NULL); simulating a NULL guard boots 2.1.243 cleanly · Issue #89420 · anthropics/claude-code · GitHub — Anthropic

   # 2.1.242+ segfault is glibc-2.44-only: bisected 2.35→2.44, glibc 2.44's __newlocale refactor added an unconditional free(NULL); simulating a NULL guard boots 2.1.243 cleanly

- State: open

- Author: mhpsy

- Created: 2026-08-25T03:23:11Z

- Updated: 2026-08-25T03:24:27Z

- Repository: anthropics/claude-code

- Number: #89420

## Labels

- duplicate

- has repro

- platform:linux

- area:packaging

-…

Codex Desktop repeatedly loses the original acceptance goal after compaction and enters endless subagent/test loops - Codex - OpenAI Developer Community — OpenAI

Codex Desktop repeatedly loses the original acceptance goal after compaction and enters endless subagent/test loops - Codex - OpenAI Developer Community

Skip to where you left off (post 12) Skip to last reply Skip to top

You have selected 0 posts.

169 views 6 likes 1 link

read 11 min

Summarize

12 / 13

Aug 25

I would like to know whether other developers have experienced the following…

I Deleted the Wrong Turn. Three LLM Endpoints Still Repeated Its Answer. - DEV Community — DEV Community

I Deleted the Wrong Turn. Three LLM Endpoints Still Repeated Its Answer. - DEV Community

Posted on Aug 24 • Originally published at chenxiachan.github.io

# I Deleted the Wrong Turn. Three LLM Endpoints Still Repeated Its Answer.

I assumed that removing a wrong turn would repair an LLM conversation.

Then I tested it.

In one deliberately simple case, a conversation began with a verified…

The loop your agent can't see - DEV Community — DEV Community

The loop your agent can't see - DEV Community

Dibyanshu kumar

Posted on Aug 24

# The loop your agent can't see

## The $136 design document

One ticket. Eleven design turns. $136 in model spend. Zero lines of code.

Our AI development orchestrator had been running tickets end to end for weeks — read the ticket, sketch, design, code, review, open the PR — and on this one it never left…

Daily TopFive for AI Coding Daily. Links above go to the original articles. Follow and rate AI Coding Daily wherever you listen. Feedback? Email [email protected].

Claude Code v2.1.243 adds loop-level usage, managed pricing, keyless Console login, and MCP reconnect fixes, while GitHub Agentic Workflows tightens safe-output PR steering and agent bugs expose brittle provider-error, Remote SSH, and LiteLLM/Anthropic tool-chain edges.

In this episode

1. v2.1.243 — Anthropic

   What's changed Added a Loops breakdown to /usage : per-loop run count, total tokens, tokens per run, and last run, so runaway or chatty /loop tasks are easy to spot Added modelPicker setting: curate the /model picker with an ordered, labeled list of models (any id spelling, including Vertex/Bedrock ids), appended to or replacing the built-in lineup Added promptCacheTtl and subagentPromptCacheTtl…

2. Weekly Update – August 24, 2026 | GitHub Agentic Workflows — GitHub

   Weekly Update – August 24, 2026 | GitHub Agentic Workflows

# Weekly Update – August 24, 2026

Aug 24, 2026

Another busy week for github/gh-aw! We shipped three pre-releases (`v0.87.1`,`v0.87.2`, and`v0.87.4`) and merged dozens of pull requests focused on safe-output reliability, compiler robustness, and internal reporting accuracy. Here’s what stood out.

## Release Highlights

The v0.87.4 line…

web: backend error text is returned to the model verbatim — provider error envelopes are never normalized · Issue #93697 · NousResearch/hermes-agent · GitHub — GitHub

# web: backend error text is returned to the model verbatim — provider error envelopes are never normalized

- State: open

- Author: caretor

- Created: 2026-08-24T08:08:04Z

- Updated: 2026-08-24T08:14:31Z

- Repository: NousResearch/hermes-agent

- Number: #93697

## Labels

- type/security

- comp/plugins

- tool/web

- P3

---

## Version

Hermes Agent v0.20.3 (tag `v2026.8.16.2`). Found by code…

Remote SSH (Mac → Mac): Agent tools hang indefinitely (often on git); integrated terminal git is fine - Bug Reports - Cursor - Community Forum — Cursor

Remote SSH (Mac → Mac): Agent tools hang indefinitely (often on git); integrated terminal git is fine - Bug Reports - Cursor - Community Forum

# Remote SSH (Mac → Mac): Agent tools hang indefinitely (often on git); integrated terminal git is fine

koliyo (Nils Hjelte) August 24, 2026, 10:24am 1

### Where does the bug appear (feature/product)?

Cursor IDE

### Describe the Bug

###…

openai-responses: trailing empty assistant text block causes "assistant message prefill" 400 on Anthropic models via LiteLLM · Issue #8553 · earendil-works/pi · GitHub — GitHub

# openai-responses: trailing empty assistant text block causes "assistant message prefill" 400 on Anthropic models via LiteLLM

- State: closed

- Author: AppleQQWW

- Created: 2026-08-24T08:30:11Z

- Updated: 2026-08-24T08:30:21Z

- Repository: earendil-works/pi

- Number: #8553

## Labels

- bug

- untriaged

---

### What happened?

Environment

- @earendil-works/pi-ai version: 0.82.1

- Route:…

Daily TopFive for AI Coding Daily. Links above go to the original articles. Follow and rate AI Coding Daily wherever you listen. Feedback? Email [email protected].

Claude Code 2.1.239 tightens cost reporting, API migration, and proxy fixes while fresh GitHub reports flag stranded subagent replies, broken Desktop plugin env substitution, Areev credential-broker gaps, and opencode’s v2 provider auth regression.

In this episode

1. v2.1.239 — Anthropic

   What's changed Cost estimates ( /cost , status line, --max-budget-usd ) now include the 1.1× US-only-inference premium for data-residency workspaces Added the one-time fullscreen renderer offer on Bedrock, Vertex, Foundry and other previously excluded setups; new installs there now start in fullscreen Added /claude-api upgrade to migrate Python projects from anthropic 0.x to 1.x, and updated the…

2. Code-carrying tools bypass the credential broker; --allow-executor is CLI-only; two doc corrections · Issue #87 · AreevAI/areev · GitHub — GitHub

   # Code-carrying tools bypass the credential broker; --allow-executor is CLI-only; two doc corrections

- State: closed

- Author: sathish-mg

- Created: 2026-08-21T18:52:00Z

- Updated: 2026-08-22T04:32:34Z

- Repository: AreevAI/areev

- Number: #87

## Labels

- bug

---

## 1. A code-carrying tool cannot reach the credential broker

`CodeExecutor::execute_code` (`crates/areev-run/src/executor.rs`)…

SendMessage racing an agent's task stop strands the reply with no notification · Issue #88741 · anthropics/claude-code · GitHub — Anthropic

# SendMessage racing an agent's task stop strands the reply with no notification

- State: open

- Author: kerneltoast

- Created: 2026-08-22T02:27:52Z

- Updated: 2026-08-23T23:16:44Z

- Repository: anthropics/claude-code

- Number: #88741

## Labels

- bug

- has repro

- platform:linux

- area:agents

---

## Environment

- Claude Code 2.1.238, Linux, interactive terminal session (tmux)

- Background…

V2 runner sends a non-credential env var as the bearer API key for env-configured providers · Issue #44065 · anomalyco/opencode · GitHub — anomalyco

# V2 runner sends a non-credential env var as the bearer API key for env-configured providers

- State: open

- Author: chandlerm923

- Created: 2026-08-22T06:01:33Z

- Updated: 2026-08-22T06:03:46Z

- Repository: anomalyco/opencode

- Number: #44065

- Assignees: neriousy

---

### Description

models.dev lists a provider's env vars in setup order, e.g.

`cloudflare-workers-ai:…

Marketplace plugin ${user_config.x} substitution fails via CCD --plugin-dir invocation · Issue #88529 · anthropics/claude-code · GitHub — Anthropic

# Marketplace plugin ${user_config.x} substitution fails via CCD --plugin-dir invocation

- State: open

- Author: sashof

- Created: 2026-08-21T12:51:03Z

- Updated: 2026-08-23T00:16:04Z

- Repository: anthropics/claude-code

- Number: #88529

## Labels

- bug

- has repro

- platform:macos

- area:mcp

- area:plugins

- area:desktop

---

## Bug: Marketplace plugin `${user_config.x}` substitution fails…

Daily TopFive for AI Coding Daily. Links above go to the original articles. Follow and rate AI Coding Daily wherever you listen. Feedback? Email [email protected].

Claude Code v2.1.238 adds marketplace header helpers, runner controls, and long-session fixes, while Microsoft’s ThinkingBox benchmark and MCP migration notes push agent tooling toward stateful, observable production behavior.

In this episode

1. v2.1.238 — Anthropic

   What's changed Added a keybindingFlavor setting: set it to "readline" to make Ctrl+W in the prompt delete back to the previous whitespace, as in Bash; the default ( "classic" ) is unchanged Plugin marketplaces: headersHelper on a url marketplace or a catalog entry runs a command that mints HTTP headers (e.g. a short-lived token) for catalog and same-origin archive fetches A catalog entry's…

2. ThinkingBox: Measuring whether agents finish the job — Microsoft

   ThinkingBox: Measuring whether agents finish the job

# How we built ThinkingBox to measure whether agents finish the job

ThinkingBox separates the execution framework from the benchmark package. This split lets builders update the harness and benchmark independently.

By Liang-Chun Tsai Principal Machine Learning Engineer, Microsoft

2026.08.19

You ask a travel support agent to add a…

When your MCP tool fails: errors, hangs, and empty results — what Claude Code actually does with each - DEV Community — DEV Community

When your MCP tool fails: errors, hangs, and empty results — what Claude Code actually does with each - DEV Community

Yesterday I posted a one-liner on Bluesky: an MCP tool that errors teaches the model something, one that hangs teaches it nothing. A reply pointed out a third case that is worse than both — the tool that returns a successful, empty result. It doesn't burn the turn. It burns the…

MCP 2.0 Breaking Changes Every QA Engineer Must Know — Scrolltest

MCP 2.0 Breaking Changes Every QA Engineer Must Know

# MCP 2.0 Breaking Changes Every QA Engineer Must Know

By Promode August 19, 2026 August 19, 2026

On July 28, 2026, the MCP Python SDK shipped version 2.0.0 as a stable release, and `pip install mcp` now installs 2.x by default. If your team built test tooling, AI agents, or browser automation on top of the Model Context Protocol in the…

36% Cheaper, 38% Faster: What Structured AI Context Is Worth — Blog — Unabyss — Unabyss

36% Cheaper, 38% Faster: What Structured AI Context Is Worth — Blog — Unabyss

← Back to the blog

Marcin Uchacz

Marcin Uchacz on LinkedIn

Marcin Uchacz on X

CEO & Co-founder, Unabyss

20 August 2026 · 4 min read

We ran the same 20 tasks 60 times in Claude Code, changing one thing: whether the assistant had our context structured and waiting, or had to go assemble it. With context ready, the…

Daily TopFive for AI Coding Daily. Links above go to the original articles. Follow and rate AI Coding Daily wherever you listen. Feedback? Email [email protected].

Claude Code v2.1.237 fixes prompt caching for gateway sessions as Cursor pushes cloud agents toward event-driven work, while Scale AI’s SWE-Bench Pro raises the bar on coding-agent evals and forces a harder production-readiness question.

In this episode

1. Releases · anthropics/claude-code — Anthropics

   Releases · anthropics/claude-code · GitHub

## Release list

Jump to release

- v2.1.237

- v2.1.236

- v2.1.235

- v2.1.234

- v2.1.233

- v2.1.232

- v2.1.231

- v2.1.229

- v2.1.228

- v2.1.227

Compare

# Choose a tag to compare

ashwin-ant released this 20 Aug 00:54

## What's changed

- Fixed prompt caching for sessions using an LLM gateway or custom base URL

- Added a built-in "Concise" output…

Cloud Agents and Cursor Harness Improvements — Cursor

We're continuing to improve cloud agents and the Cursor harness so always-on agents can operate as a system, building and shipping software on their own without the need for intervention at each loop. With this release, cloud agents can automatically pick up work in response to events, hold a goal until it's met, and stay on course through long-running sessions. Subscriptions Cursor can now…

SWE-Bench Pro (Public Dataset) - Scale Labs — Scale AI

[](https://labs.scale.com/)[[PAPERS]](https://labs.scale.com/papers)[[BLOG]](https://labs.scale.com/blog)[LEADERBOARDS][[SHOWDOWN]](https://labs.scale.com/showdown)⌘K

⌘K

Agentic

[DrugDiscoveryBench](https://labs.scale.com/leaderboard/drugdiscoverybench)

[SWE Atlas -…

Step Back — SWE-Bench Pro and newer coding agents suggest better performance on software tasks, but what would convince us that these systems are genuinely improving at production engineering rather than simply getting better at the benchmark’s particular setup?Background sources

• SWE-Bench Pro: Raising the Bar for Agentic Coding | Scale AI — Scale AI
• SWE Atlas is Complete: Measuring Coding Agents Across the Engineering Loop | Scale AI — Scale AI
• Many SWE-bench-Passing PRs Would Not Be Merged into Main - METR — Parker Whitfill
• RDEL #144: How well do public benchmarks predict AI coding agent performance in production? — Lizzie Matusov

smolmachines / smolvm as a sandbox for untrusted Python & JavaScript — Simon Willison's Weblog

Research: smolmachines / smolvm as a sandbox for untrusted Python & JavaScript I tasked Claude Fable 5 running in Claude Code for web with the following research task: Put https://smolmachines.com through its paces as a fast secure sandbox. Explore what it would take to use this to run untrusted Python and JavaScript code in a way that is limited in what RAM and CPU time it can take up…

Daily TopFive for AI Coding Daily. Links above go to the original articles. Follow and rate AI Coding Daily wherever you listen. Feedback? Email [email protected].