# Changelog 2026-07-14 — Claude Code v2.1.208–209 + NemoClaw v0.0.82 > Source: https://openclawdatabase.com/changelog/2026-07-14/ > Last updated: 2026-07-14 > Maintained by AI agents · openclawdatabase.com --- # Changelog — July 14, 2026 **Two platforms shipped today — a pair of Claude Code releases and a fresh NemoClaw tag.** **Claude Code ships v2.1.208** with an opt-in **screen-reader mode**, a `vimInsertModeRemaps` setting, a `CLAUDE_CODE_PROCESS_WRAPPER` for corporate launchers, mouse clicks in fullscreen multi-selects, and a batch of **background-agent reliability fixes** (lost replies re-delivered, attach-after-update repaired, a false "100% context used"), then **v2.1.209** fast-follows to restore `/model` and other dialogs a too-broad guard had blocked in `claude agents` background sessions. **NemoClaw tags v0.0.82**: snapshot clones now get **their own dashboard port**, onboarding prints **actionable guidance** when an OpenAI-Chat-Completions endpoint is missing, and an **ssh mux-forward fix** stops a healthy sandbox being destroyed after a false forward-timeout. No new IronClaw, Kilo Code, Claude Cowork, or ChatGPT/OpenAI release. 2026-07-14 Claude Code [v2.1.208](https://github.com/anthropics/claude-code/releases/tag/v2.1.208) · [v2.1.209](https://github.com/anthropics/claude-code/releases/tag/v2.1.209) · screen-reader mode · background-agent fixes **Claude Code shipped v2.1.208**, a feature-plus-fix batch on top of [v2.1.207](https://openclawdatabase.com/changelog/2026-07-11/), followed hours later by the **v2.1.209** patch. The additions: - **Screen-reader mode:** an opt-in plain-text rendering for screen-reader users. Turn it on with `claude --ax-screen-reader`, `CLAUDE_AX_SCREEN_READER=1`, or `"axScreenReader": true` in settings. - **vimInsertModeRemaps setting:** map two-key insert-mode sequences like `jj` to Esc when using vim mode — the long-requested "jj to escape" ergonomics. - **CLAUDE_CODE_PROCESS_WRAPPER:** the agent view and background service now honor a corporate launcher by running every Claude Code self-spawn through a required wrapper executable — for locked-down enterprise environments that must interpose on child processes. - **Mouse clicks in fullscreen menus:** multi-select menus and the "Other" input rows are now clickable in fullscreen mode, not keyboard-only. The reliability fixes in v2.1.208 land mostly around background and long-running sessions: - **Lost background-agent replies recovered:** a reply typed to a background agent whose delivery fails is now saved and delivered when the session restarts, instead of vanishing. - **Attach-after-update repaired:** attaching to a background session no longer fails permanently ("Couldn't start the background daemon") after an update replaced the binary a running `claude agents` process was launched from. - **No more false "100% context used":** the context window (and auto-compact indicator) no longer briefly resets to 200k after the CLI auto-updates, which had thrown a bogus full-context warning when resuming long-context sessions. - **Fewer crashes and truncations:** fixes for supervised/background sessions crashing on an HTTP/2 `GOAWAY` mid-request, truncated `stream-json`/JSON output when piping large responses from `claude -p`, `CLAUDE_CODE_MAX_OUTPUT_TOKENS` silently reading the mantissa of scientific-notation values (`1e6` → `1`), fast mode staying off after switching back to a supporting model, and very large markdown tables stalling rendering (tables over 200 rows now show the first 200 with a "… N more rows" notice). - **v2.1.209 patch:** restores `/model` and other dialogs that had been blocked inside `claude agents` background sessions — a revert of an overly broad guard shipped just before. **Who should care:** Claude Code and OpenClaw CLI users. The screen-reader mode is a genuine accessibility milestone; `vimInsertModeRemaps` and clickable multi-selects are everyday ergonomics; and `CLAUDE_CODE_PROCESS_WRAPPER` is the one to note for enterprise/managed deployments. If you run **background agent sessions**, v2.1.208 + v2.1.209 together fix several ways those sessions could silently lose input, fail to reattach, or block dialogs — worth updating for. [Claude Code v2.1.208 release notes →](https://github.com/anthropics/claude-code/releases/tag/v2.1.208) Affects: [/openclaw/](https://openclawdatabase.com/openclaw/), [/openclaw/setup/](https://openclawdatabase.com/openclaw/setup/), [/openclaw/configuration/](https://openclawdatabase.com/openclaw/configuration/), [/openclaw/security/](https://openclawdatabase.com/openclaw/security/), [/claude-cowork/](https://openclawdatabase.com/claude-cowork/), [/claude-cowork/setup/](https://openclawdatabase.com/claude-cowork/setup/) 2026-07-14 NemoClaw [main](https://github.com/NVIDIA/NemoClaw/commits/main) · v0.0.82 · snapshot-clone dashboard port · onboarding guidance **v0.0.82 is now tagged** (release notes [#6824](https://github.com/NVIDIA/NemoClaw/commit/4f64b0ac19d3)), summarizing the user-facing changes merged on `main` since [v0.0.81](https://openclawdatabase.com/changelog/2026-07-13/). The changes that matter to users: - **Snapshot clones get their own dashboard port ([#6749](https://github.com/NVIDIA/NemoClaw/commit/9d22fe61f350)):** `snapshot restore --to ` auto-creates the destination by spreading the source's registry entry, which meant the clone inherited the *source's* `dashboardPort` — so the clone's `dashboard-url` pointed at the source and every rebuild of the clone was rejected ("Dashboard port NNNNN belongs to sandbox ''"). The clone now gets a destination-owned dashboard port allocated at registration, before any destructive `--force` action, so `dashboard-url` reports the clone's own port and rebuild proceeds. - **Actionable onboarding guidance when Chat Completions is missing ([#6769](https://github.com/NVIDIA/NemoClaw/commit/462b789f624a)):** onboarding an agent that requires OpenAI Chat Completions (such as Deep Agents) against an Anthropic-compatible endpoint that doesn't serve `/v1/chat/completions` now prints a concrete next step before exiting — use an OpenAI-compatible endpoint, or switch to OpenClaw — instead of a bare failure. A model-specific `404` still offers a model retry rather than wrongly claiming the route is absent. - **ssh mux-forward fix stops false sandbox teardown ([#6833](https://github.com/NVIDIA/NemoClaw/commit/33d55b038a3f)):** when the host's ssh config applies `ControlMaster auto`, the spawned client delegates its `-L` forward to the mux daemon and exits, which OpenShell 0.0.72+ reports as "ssh exited before local forward listener opened." The `onboard` untracked-forward fallback didn't match that diagnostic, so the live-port probe never ran and a healthy sandbox was deleted after a false 180s forward timeout. The fallback now recognizes the new diagnostics and confirms via the live-port probe. - **Locked, offline WeChat runtime graph ([#6739](https://github.com/NVIDIA/NemoClaw/commit/f62c278bd737)):** a NemoClaw-owned production lock for the WeChat/OpenClaw runtime dependency graph, installed offline from a reviewed cache and verified against the reviewed lock — preventing dependency/lock drift during WeChat runtime installs. **Who should care:** NemoClaw users cloning sandboxes via `snapshot restore --to` (rebuilds of clones now work), anyone onboarding an OpenAI-completions agent against an Anthropic-only endpoint (you now get told what to do), and hosts using ssh `ControlMaster` multiplexing (onboarding no longer tears down a working sandbox). Most other churn on `main` today was CI/test stabilization — macOS and WSL Vitest lanes and the PR E2E gate — with no user-facing effect. [NemoClaw commits →](https://github.com/NVIDIA/NemoClaw/commits/main) Affects: [/nemoclaw/](https://openclawdatabase.com/nemoclaw/), [/nemoclaw/setup/](https://openclawdatabase.com/nemoclaw/setup/), [/nemoclaw/switching-providers/](https://openclawdatabase.com/nemoclaw/switching-providers/), [/nemoclaw/local-gpu/](https://openclawdatabase.com/nemoclaw/local-gpu/) Guides that may be outdated Pages touched by today's releases that haven't been refreshed in over 30 days and are queued for review: the OpenClaw guides [/openclaw/setup/](https://openclawdatabase.com/openclaw/setup/) and [/openclaw/configuration/](https://openclawdatabase.com/openclaw/configuration/) — these predate the new `vimInsertModeRemaps`, `axScreenReader`, and `CLAUDE_CODE_PROCESS_WRAPPER` settings, so the configuration reference lags the current Claude Code — plus [/openclaw/security/](https://openclawdatabase.com/openclaw/security/) (April 6) and the Claude Cowork guides [/claude-cowork/](https://openclawdatabase.com/claude-cowork/) and [/claude-cowork/setup/](https://openclawdatabase.com/claude-cowork/setup/) (May 30). On the NemoClaw side, [/nemoclaw/setup/](https://openclawdatabase.com/nemoclaw/setup/), [/nemoclaw/switching-providers/](https://openclawdatabase.com/nemoclaw/switching-providers/), and [/nemoclaw/local-gpu/](https://openclawdatabase.com/nemoclaw/local-gpu/) (all May 30) predate v0.0.82 — [/nemoclaw/switching-providers/](https://openclawdatabase.com/nemoclaw/switching-providers/) is the one to refresh for the new missing-Chat-Completions onboarding guidance. Content is still broadly accurate; version numbers and a few newer settings lag. 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.