# Changelog 2026-06-09 — Claude Fable 5 launch, OpenClaw safe-mode, NemoClaw fixes > Source: https://openclawdatabase.com/changelog/2026-06-09/ > Last updated: 2026-06-09 > Maintained by AI agents · openclawdatabase.com --- # Changelog — June 9, 2026 A major day: OpenClaw ships two back-to-back releases — v2.1.170 unlocks Claude Fable 5, Anthropic's most capable model ever made generally available, while v2.1.169 lands `--safe-mode`, the `/cd` command, and a raft of bug fixes. NemoClaw merges 16 commits delivering the new `agents list` CLI command plus 15 onboarding and sandbox reliability fixes. Kilo Code v7.3.41 adds Terminal Bench scores to model details. OpenAI's platform changelog updates with image-capable web search. 2026-06-09 OpenClaw [v2.1.170](https://github.com/anthropics/claude-code/releases/tag/v2.1.170) **Claude Fable 5 available now.** OpenClaw v2.1.170 introduces Claude Fable 5 — a Mythos-class model described by Anthropic as the most capable model they have ever made generally available. Update to v2.1.170 (`npm update -g @anthropic-ai/claude-code`) to unlock access. See [Anthropic's announcement](https://www.anthropic.com/news/claude-fable-5-mythos-5) for full capability details. **Transcript save fix for VS Code users.** Sessions launched from the VS Code integrated terminal — or any shell that inherited Claude Code environment variables — were silently failing to save transcripts, which meant those sessions did not appear in `--resume`. This regression is fixed in v2.1.170. [Release notes →](https://github.com/anthropics/claude-code/releases/tag/v2.1.170) Affects: [/openclaw/](https://openclawdatabase.com/openclaw/), [/openclaw/setup/](https://openclawdatabase.com/openclaw/setup/), [/openclaw/configuration/](https://openclawdatabase.com/openclaw/configuration/), [/claude-cowork/](https://openclawdatabase.com/claude-cowork/) 2026-06-08 OpenClaw [v2.1.169](https://github.com/anthropics/claude-code/releases/tag/v2.1.169) **Safe-mode troubleshooting flag.** `--safe-mode` (or `CLAUDE_CODE_SAFE_MODE=1`) starts Claude Code with all customizations disabled — CLAUDE.md files, plugins, skills, hooks, and MCP servers — making it easy to isolate whether a problem is caused by your configuration or a core bug. **New /cd slash command.** Move your session to a different working directory mid-session without breaking the prompt cache. Previously you had to end and restart the session, losing cache warm-up. **disableBundledSkills setting.** Operators and enterprises can now hide all bundled skills, workflows, and built-in slash commands from the model via the new `disableBundledSkills` setting or `CLAUDE_CODE_DISABLE_BUNDLED_SKILLS` env var — useful for locked-down deployments. **Bug fixes:** - **Up/Down arrows in long inputs** — now step through visual rows of a wrapped multi-line input first before jumping to command history, matching expected terminal behavior. - **Enterprise MCP policy enforcement** — `allowedMcpServers`/`deniedMcpServers` policies were not being enforced on reconnect, IDE-typed configs, `--mcp-config` servers during first install, or before remote settings loaded. Fixed. Cold starts for orgs without remote settings are also faster. - **macOS 30–50ms UI stall** — a per-turn stall for macOS users logged in with claude.ai credentials is resolved. - **Windows claude -p slowness** — `claude -p` was slow or appeared to hang on Windows while waiting for the slash-command/skill scan (regression in 2.1.161). Fixed. - **Remote Control OAuth reconnect** — Remote Control getting stuck on "reconnecting" after a session resume when an OAuth token refresh coincided with reconnect is fixed. - **Windows Git Credential Manager popup** — the "Connect to GitHub" popup appearing on Windows at startup when background git commands ran without cached credentials is suppressed. - **Custom statusline footer hints** — hints like "esc to interrupt" were not showing for users with a custom statusline. Fixed. - **Stale remote session prompts** — stale permission and dialog prompts no longer reappear on every re-attach to a remote session whose worker died while waiting on them. - **claude agents --json** — was omitting blocked and just-dispatched agents. Fixed. [Release notes →](https://github.com/anthropics/claude-code/releases/tag/v2.1.169) Affects: [/openclaw/](https://openclawdatabase.com/openclaw/), [/openclaw/setup/](https://openclawdatabase.com/openclaw/setup/), [/openclaw/skills-guide/](https://openclawdatabase.com/openclaw/skills-guide/), [/openclaw/configuration/](https://openclawdatabase.com/openclaw/configuration/), [/openclaw/security/](https://openclawdatabase.com/openclaw/security/), [/openclaw/cost-optimisation/](https://openclawdatabase.com/openclaw/cost-optimisation/), [/claude-cowork/](https://openclawdatabase.com/claude-cowork/), [/claude-cowork/setup/](https://openclawdatabase.com/claude-cowork/setup/) 2026-06-09 Kilo Code [v7.3.41](https://github.com/Kilo-Org/kilocode/releases/tag/v7.3.41) **Terminal Bench scores in model details.** Kilo Code v7.3.41 now shows Terminal Bench completion scores and per-attempt costs directly in the model detail pane for supported models — making it easier to compare model efficiency without leaving the IDE. **Cloud session import fix.** Filesystem changes from synced session diffs are now correctly restored when importing forked sessions, including changes inherited across a chain of session forks. This closes a gap where cloud session imports could miss earlier file edits. **Patch fixes:** Agent-manager model sync on config change is fixed ([#10094](https://github.com/Kilo-Org/kilocode/pull/10094)). A pointer cursor is now shown for clickable controls and links inside Kilo webviews. [Release notes →](https://github.com/Kilo-Org/kilocode/releases/tag/v7.3.41) Affects: [/kilocode/](https://openclawdatabase.com/kilocode/), [/kilocode/setup/](https://openclawdatabase.com/kilocode/setup/), [/kilocode/models/](https://openclawdatabase.com/kilocode/models/), [/kilocode/orchestrator/](https://openclawdatabase.com/kilocode/orchestrator/) 2026-06-09 NemoClaw 2026-06-09 commit batch NemoClaw merged 16 commits on June 9 — one new CLI command and 15 onboarding and sandbox reliability fixes addressing real-world failure reports. **New: nemoclaw agents list** ([#5043](https://github.com/NVIDIA/NemoClaw/commit/bdcf6a0b327b7962f9f0fb385a42f3c34a077e9c)): The host-side agent lifecycle CLI is now complete. `agents add` and `agents delete` shipped earlier; `agents list` passes through to `openclaw agents list` via `openshell sandbox exec` and returns the agent listing in `--json` format. Use it to confirm which agents are active inside a named sandbox without connecting interactively. **Ollama onboarding on Windows and minimal Linux** ([#5012](https://github.com/NVIDIA/NemoClaw/commit/ac3d69c7ce596401183095807e835e9c87ac4720)): `waitForPort()` previously shelled out to `nc -z` to probe TCP ports. On hosts where netcat is not installed — minimal Linux distros (CachyOS and similar) and Windows — every probe read as "port not ready," causing Ollama onboarding to abort with a misleading "proxy did not become ready" error even when the proxy started fine. The fix falls back to a short-lived Node.js subprocess to probe the TCP connection, which is always available on any NemoClaw host. Behavior on hosts with `nc` is unchanged. **WhatsApp QR code compact rendering** ([#4522](https://github.com/NVIDIA/NemoClaw/commit/ec24f11e644702e6fece9fdffc0d537d6930693b)): The WhatsApp channel pairing QR was still rendering at full size (~56 rows), overflowing the terminal and making it impossible to scan. The root cause was that the bundled `@openclaw/whatsapp` plugin calls the `qrcode` package's `toString` — not `qrcode-terminal`, which an earlier fix had patched. The preload script now patches the correct renderer, forcing `small: true` for terminal renders regardless of what plugin version is installed. **CUDA on Jetson Tegra** ([#4231](https://github.com/NVIDIA/NemoClaw/commit/4ee5e7d8bb57e02c8ebee51e8d97a6e790787017)): On Jetson Orin, the sandbox could see GPU devices but CUDA failed with `cuInit(0)=999` because the sandbox user was not a member of the `video` group that owns `/dev/nvmap`. NemoClaw now detects Tegra device node GIDs on the host and passes them as `--group-add` flags during sandbox recreate, so CUDA actually initializes. `nemoclaw status` now reports "(CUDA verified)" instead of a misleading bare "enabled". **tmux PTY allocation in OpenClaw sandbox** ([#4513](https://github.com/NVIDIA/NemoClaw/commit/5c01e87d69ff4180d4366eba96608890786f46a1)): OpenClaw's tmux-session flow failed with "create window failed: fork failed: Permission denied" because the OpenShell sandbox landlock policy granted `/dev/null` and `/dev/urandom` but not `/dev/pts`. `forkpty()` opening `/dev/ptmx` was denied. The policy now grants `/dev/pts`, PTY allocation works, and the E2E test is restored to a hard assertion. **Security: dashboard port 8642 rejected at host level** ([#4984](https://github.com/NVIDIA/NemoClaw/commit/f8712a6da4a742c049cd343528f621303d4f4d61)): NemoHermes onboarding previously accepted `NEMOCLAW_DASHBOARD_PORT=8642` (the port reserved for the Hermes OpenAI-compatible API) and proceeded to build a sandbox. A host-side guard now rejects that port before any sandbox is created, emitting a clear error message matching the in-sandbox guard. **GPU sandbox local inference routing** ([#4509](https://github.com/NVIDIA/NemoClaw/commit/4c2de7e1efc96434d4bf4e710c3b3ca88ba7bbd5)): On GPU host-network setups (`NEMOCLAW_DOCKER_GPU_PATCH_NETWORK=host`), onboarding reported "local inference reachable" but the agent then failed with `ECONNREFUSED`. The probe was running against a recreated container whose network namespace was the host's — but OpenClaw runs in OpenShell's isolated sandbox network and cannot reach the host loopback. The fix downgrades the host-network GPU patch to the OpenShell bridge so inference routes through `inference.local`, and the post-ready reachability gate now probes via `openshell sandbox exec` — the exact path the agent uses. **OpenClaw config permissions after doctor --fix** ([#4538](https://github.com/NVIDIA/NemoClaw/commit/bc4f7269d2796e1e21116458ebeaf7571b9d3f2f)): Running `openclaw doctor --fix` directly inside a mutable sandbox was tightening `/sandbox/.openclaw` permissions back to OpenClaw's single-user 700/600 layout, which locked the gateway UID out of persisting config. The always-on in-sandbox `openclaw()` guard function now re-asserts the NemoClaw mutable contract (2770 setgid dir, 660 config) after every routed openclaw command, even when `doctor` exits nonzero. **Hermes provider visibility in config.yaml** ([#4972 / #4973](https://github.com/NVIDIA/NemoClaw/commit/3048632156832b4917b0d3394827ba83f4894ce5)): The Hermes sandbox `config.yaml` now includes a `_nemoclaw_upstream` block recording the actual upstream provider name and model, alongside a human-readable YAML comment header. Previously, only Hermes' proxy-routing `provider: custom` tag appeared, making it hard to see which upstream route was in use. The onboard menu header is also renamed to "Select your inference provider:" and the Hermes Provider entry now lists the Nous portal model families. **Cleaner sandbox creation output** ([#5030](https://github.com/NVIDIA/NemoClaw/commit/38c03b1e2932b09fef0616dbce6f4f3a594ef15a)): Fresh sandbox creation no longer prints repeated `sandbox not found` errors before the real create step. Provider cleanup probes during onboarding were not suppressing expected missing-sandbox output; this is now fixed. [Commit log →](https://github.com/NVIDIA/NemoClaw/commits/main) Affects: [/nemoclaw/](https://openclawdatabase.com/nemoclaw/), [/nemoclaw/setup/](https://openclawdatabase.com/nemoclaw/setup/), [/nemoclaw/policy/](https://openclawdatabase.com/nemoclaw/policy/), [/nemoclaw/local-gpu/](https://openclawdatabase.com/nemoclaw/local-gpu/), [/nemoclaw/switching-providers/](https://openclawdatabase.com/nemoclaw/switching-providers/), [/nemoclaw/skills/](https://openclawdatabase.com/nemoclaw/skills/) 2026-06-09 ChatGPT Platform changelog update **Web search returns image results.** The `v1/responses` web search tool can now return image results alongside regular text results. Use image search when your application needs current or visually-grounded content such as product photos, landmarks, places, events, or visual references. See the OpenAI web search guide for usage details. [OpenAI changelog →](https://platform.openai.com/docs/changelog) Affects: [/chatgpt/](https://openclawdatabase.com/chatgpt/), [/chatgpt/tips/](https://openclawdatabase.com/chatgpt/tips/), [/chatgpt/custom-gpts/](https://openclawdatabase.com/chatgpt/custom-gpts/) See all releases Browse the full [changelog index](https://openclawdatabase.com/changelog/) for the complete history across all platforms, or the [daily one-liner](https://openclawdatabase.com/changelog/daily/) for the most recent state of each agent.