# paperclip v2026.831.0

- Product: paperclip (https://whatsnew.fyi/product/paperclip)
- Vendor: paperclip
- Date: 2026-09-02
- Version: v2026.831.0
- Original notes: https://github.com/paperclipai/paperclip/releases/tag/v2026.831.0
- Permalink: https://whatsnew.fyi/product/paperclip/releases/v2026.831.0

What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.

Reuse: the summaries, labels and curation here are © What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'.

---

- **changed** — Node.js 24.11.0 or newer is required
- **changed** — Invalid agent credentials are rejected instead of downgraded, returning a 401 with the cause instead of falling through to anonymous local-user actor
- **removed** — Company brand color and per-company attachment size limit fields are removed from the company General page, create/update APIs, and portability manifest
- **changed** — Silent-run detection no longer creates evaluation issues, recovery actions, comments, or wake requests automatically
- **changed** — Stranded-task recovery stops automatic takeovers and routes exhausted and unsafe recovery to a board-owned action instead of reassigning work
- **changed** — Agent thought text is excluded from automatic issue comments in ACPX run summaries
- **changed** — Grok adapter no longer defaults --permission-mode to dontAsk
- **added** — Skill library now reaches agents with a deterministic manifest in run instructions
- **added** — Agents can list skills over MCP
- **added** — Newly hired agents receive the five core Paperclip skills by default
- **added** — Installing a skill offers an Enable for agents step that pre-selects every skills-capable agent
- **changed** — Skill failures now surface in run output with their cause instead of silently vanishing
- **added** — Kimi Code is a first-class adapter running Moonshot's Kimi Code CLI on the shared ACP engine with live streaming transcripts and tool-call lifecycle
- **added** — PAPERCLIP_HIDDEN_SETTINGS environment variable hides settings surfaces by key for operators hosting Paperclip for others
- **added** — PAPERCLIP_SETTING_DEFAULTS environment variable overrides schema defaults of selected instance settings without persisting
- **added** — Managed-sandbox-only mode hides host-path and execution-engine surfaces entirely

#### Paperclip v2026.831.0

> Released: 2026-08-31

Paperclip v2026.831.0 soaked as `2026.828.0-beta.0` and carries 175 commits. The company skill library now actually reaches your agents at run time, Kimi Code joins the adapter lineup, operators hosting Paperclip for others get real control over which settings surfaces their users see, the sandbox callback bridge is rebuilt on a bounded HTTP/2 transport, and onboarding sheds its mission step for a shorter arc with the agent front and center. It also raises the Node.js floor to 24 — read the Upgrade Guide before updating a source install.

##### Breaking Changes

- **Node.js 24.11.0 or newer is required.** Every package manifest declares the new floor and the Docker images ship Node 24. Only managed installs (`paperclipai install`) refuse outright on an older Node; npm installs and a directly started server on Node 22/23 print an unsupported-version warning and continue. A warning is not support — upgrade Node before taking this release. ([#11792](https://github.com/paperclipai/paperclip/pull/11792), [#11890](https://github.com/paperclipai/paperclip/pull/11890))
- **Invalid agent credentials are rejected instead of downgraded.** A bearer token that fails verification now returns a 401 naming the cause (expired, unverifiable, terminated agent, wrong company, …) instead of silently falling through to the anonymous local-user actor. Any integration that depended on that fall-through will start seeing 401s — that fall-through was the bug. ([#11589](https://github.com/paperclipai/paperclip/pull/11589))
- **The company brand color and per-company attachment size limit are gone.** The fields are removed from the company General page, the create/update APIs, and the portability manifest; migration `0229` drops the columns. Export bundles that carry the old fields still import — the values are ignored. ([#12291](https://github.com/paperclipai/paperclip/pull/12291))
- **Silent-run detection no longer takes action on its own.** Output silence still surfaces as a suspicious/critical level on active-run summaries in the UI, but it no longer creates evaluation issues, recovery actions, comments, or wake requests. Stranded-task recovery similarly stops automatic takeovers: exhausted and unsafe recovery now routes to a board-owned action instead of reassigning work by itself. ([#12242](https://github.com/paperclipai/paperclip/pull/12242), [#11961](https://github.com/paperclipai/paperclip/pull/11961))
- **Agent thought text stays out of automatic issue comments.** ACPX run summaries are limited to the final output segment, and the legacy full-summary setting is deliberately ignored so configuration cannot bypass the containment. ([#11801](https://github.com/paperclipai/paperclip/pull/11801), @nearfolk)
- **Grok no longer defaults `--permission-mode` to `dontAsk`.** The adapter passes no permission-mode flag unless one is explicitly configured; `--always-approve` remains the unattended policy. ([#11898](https://github.com/paperclipai/paperclip/pull/11898))

##### Highlights

- **Your skill library now reaches your agents** — Skills used to be something you installed and hoped for. Now every agent run carries a deterministic manifest of the company's skill library in its instructions, agents can list skills over MCP, newly hired CEOs get the five core Paperclip skills by default, and installing a skill offers an "Enable for agents" step that pre-selects every skills-capable agent. When a skill fails to materialize, the failure is surfaced in the run output with its cause instead of the skill silently vanishing — and legacy runners are pinned back to the canonical operational skill. ([#12147](https://github.com/paperclipai/paperclip/pull/12147), [#12138](https://github.com/paperclipai/paperclip/pull/12138), [#12136](https://github.com/paperclipai/paperclip/pull/12136), [#12146](https://github.com/paperclipai/paperclip/pull/12146), [#12225](https://github.com/paperclipai/paperclip/pull/12225))
- *

_[Truncated at 4000 characters — full notes: https://github.com/paperclipai/paperclip/releases/tag/v2026.831.0]_